summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--.mailmap6
-rw-r--r--CREDITS1
-rw-r--r--Documentation/ABI/stable/sysfs-class-ubi9
-rw-r--r--Documentation/ABI/testing/configfs-usb-gadget-uvc58
-rw-r--r--Documentation/ABI/testing/sysfs-bus-iio-proximity-as39352
-rw-r--r--Documentation/DocBook/device-drivers.tmpl36
-rw-r--r--Documentation/DocBook/gpu.tmpl6
-rw-r--r--Documentation/arm64/silicon-errata.txt1
-rw-r--r--Documentation/devicetree/bindings/display/imx/ldb.txt1
-rw-r--r--Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt2
-rw-r--r--Documentation/devicetree/bindings/hwmon/ina2xx.txt1
-rw-r--r--Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt4
-rw-r--r--Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt3
-rw-r--r--Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt6
-rw-r--r--Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt4
-rw-r--r--Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt6
-rw-r--r--Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt (renamed from Documentation/devicetree/bindings/bus/ti-gpmc.txt)17
-rw-r--r--Documentation/devicetree/bindings/mips/cpu_irq.txt2
-rw-r--r--Documentation/devicetree/bindings/mmc/microchip,sdhci-pic32.txt2
-rw-r--r--Documentation/devicetree/bindings/mtd/atmel-nand.txt2
-rw-r--r--Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt1
-rw-r--r--Documentation/devicetree/bindings/mtd/gpmc-nand.txt19
-rw-r--r--Documentation/devicetree/bindings/mtd/nand.txt46
-rw-r--r--Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt8
-rw-r--r--Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt2
-rw-r--r--Documentation/devicetree/bindings/serial/microchip,pic32-uart.txt2
-rw-r--r--Documentation/devicetree/bindings/sound/max98371.txt17
-rw-r--r--Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt5
-rw-r--r--Documentation/devicetree/bindings/sound/mt8173-rt5650.txt10
-rw-r--r--Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt48
-rw-r--r--Documentation/devicetree/bindings/sound/tas571x.txt10
-rw-r--r--Documentation/devicetree/bindings/sound/tas5720.txt25
-rw-r--r--Documentation/devicetree/bindings/spi/microchip,spi-pic32.txt34
-rw-r--r--Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt3
-rw-r--r--Documentation/devicetree/bindings/spi/sqi-pic32.txt18
-rw-r--r--Documentation/devicetree/bindings/thermal/nvidia,tegra124-soctherm.txt12
-rw-r--r--Documentation/devicetree/bindings/thermal/rcar-thermal.txt1
-rw-r--r--Documentation/devicetree/bindings/thermal/tango-thermal.txt17
-rw-r--r--Documentation/devicetree/bindings/thermal/thermal-generic-adc.txt89
-rw-r--r--Documentation/devicetree/bindings/vendor-prefixes.txt2
-rw-r--r--Documentation/devicetree/bindings/watchdog/fsl-imx-wdt.txt4
-rw-r--r--Documentation/devicetree/bindings/watchdog/microchip,pic32-dmt.txt4
-rw-r--r--Documentation/devicetree/bindings/watchdog/microchip,pic32-wdt.txt4
-rw-r--r--Documentation/devicetree/bindings/watchdog/renesas-wdt.txt25
-rw-r--r--Documentation/filesystems/dax.txt32
-rw-r--r--Documentation/filesystems/devpts.txt145
-rw-r--r--Documentation/filesystems/directory-locking32
-rw-r--r--Documentation/filesystems/overlayfs.txt9
-rw-r--r--Documentation/filesystems/porting7
-rw-r--r--Documentation/hwmon/max344406
-rw-r--r--Documentation/infiniband/sysfs.txt12
-rw-r--r--Documentation/kbuild/kconfig-language.txt22
-rw-r--r--Documentation/kdump/gdbmacros.txt93
-rw-r--r--Documentation/leds/leds-class.txt4
-rw-r--r--Documentation/networking/dsa/dsa.txt17
-rw-r--r--Documentation/networking/ip-sysctl.txt8
-rw-r--r--Documentation/pwm.txt30
-rw-r--r--Documentation/scsi/scsi_eh.txt8
-rw-r--r--Documentation/scsi/tcm_qla2xxx.txt22
-rw-r--r--Documentation/security/keys.txt5
-rw-r--r--Documentation/sysctl/kernel.txt14
-rwxr-xr-xDocumentation/target/tcm_mod_builder.py16
-rw-r--r--Documentation/thermal/sysfs-api.txt44
-rw-r--r--Documentation/watchdog/hpwdt.txt57
-rw-r--r--Documentation/watchdog/watchdog-parameters.txt4
-rw-r--r--MAINTAINERS120
-rw-r--r--Makefile74
-rw-r--r--arch/Kconfig15
-rw-r--r--arch/alpha/include/asm/pgalloc.h4
-rw-r--r--arch/arc/Kconfig31
-rw-r--r--arch/arc/Makefile4
-rw-r--r--arch/arc/boot/dts/abilis_tb100.dtsi2
-rw-r--r--arch/arc/boot/dts/abilis_tb101.dtsi2
-rw-r--r--arch/arc/boot/dts/axc001.dtsi1
-rw-r--r--arch/arc/boot/dts/axc003.dtsi1
-rw-r--r--arch/arc/boot/dts/axc003_idu.dtsi1
-rw-r--r--arch/arc/boot/dts/eznps.dts1
-rw-r--r--arch/arc/boot/dts/nsim_700.dts1
-rw-r--r--arch/arc/boot/dts/nsimosci.dts1
-rw-r--r--arch/arc/boot/dts/nsimosci_hs.dts1
-rw-r--r--arch/arc/boot/dts/nsimosci_hs_idu.dts1
-rw-r--r--arch/arc/boot/dts/skeleton.dtsi1
-rw-r--r--arch/arc/boot/dts/skeleton_hs.dtsi1
-rw-r--r--arch/arc/boot/dts/skeleton_hs_idu.dtsi1
-rw-r--r--arch/arc/boot/dts/vdk_axc003.dtsi1
-rw-r--r--arch/arc/boot/dts/vdk_axc003_idu.dtsi1
-rw-r--r--arch/arc/include/asm/atomic.h45
-rw-r--r--arch/arc/include/asm/entry-compact.h4
-rw-r--r--arch/arc/include/asm/mmu_context.h2
-rw-r--r--arch/arc/include/asm/pgalloc.h4
-rw-r--r--arch/arc/include/asm/pgtable.h2
-rw-r--r--arch/arc/include/asm/processor.h2
-rw-r--r--arch/arc/include/asm/smp.h2
-rw-r--r--arch/arc/include/asm/spinlock.h292
-rw-r--r--arch/arc/include/asm/thread_info.h2
-rw-r--r--arch/arc/include/asm/uaccess.h2
-rw-r--r--arch/arc/include/uapi/asm/swab.h2
-rw-r--r--arch/arc/include/uapi/asm/unistd.h1
-rw-r--r--arch/arc/kernel/entry-compact.S18
-rw-r--r--arch/arc/kernel/intc-compact.c6
-rw-r--r--arch/arc/kernel/perf_event.c8
-rw-r--r--arch/arc/kernel/setup.c2
-rw-r--r--arch/arc/kernel/signal.c2
-rw-r--r--arch/arc/kernel/stacktrace.c2
-rw-r--r--arch/arc/kernel/troubleshoot.c2
-rw-r--r--arch/arc/mm/cache.c6
-rw-r--r--arch/arc/mm/dma.c2
-rw-r--r--arch/arm/boot/Makefile1
-rw-r--r--arch/arm/boot/bootp/Makefile3
-rw-r--r--arch/arm/boot/dts/Makefile2
-rw-r--r--arch/arm/boot/dts/am437x-sk-evm.dts2
-rw-r--r--arch/arm/boot/dts/am57xx-idk-common.dtsi32
-rw-r--r--arch/arm/boot/dts/dm8148-evm.dts8
-rw-r--r--arch/arm/boot/dts/dm8148-t410.dts9
-rw-r--r--arch/arm/boot/dts/dra7.dtsi2
-rw-r--r--arch/arm/boot/dts/dra74x.dtsi4
-rw-r--r--arch/arm/boot/dts/exynos3250-monk.dts47
-rw-r--r--arch/arm/boot/dts/exynos3250-rinato.dts88
-rw-r--r--arch/arm/boot/dts/exynos3250.dtsi181
-rw-r--r--arch/arm/boot/dts/exynos4210.dtsi159
-rw-r--r--arch/arm/boot/dts/exynos4412-odroid-common.dtsi56
-rw-r--r--arch/arm/boot/dts/exynos4412-ppmu-common.dtsi50
-rw-r--r--arch/arm/boot/dts/exynos4412-trats2.dts88
-rw-r--r--arch/arm/boot/dts/exynos4x12.dtsi174
-rw-r--r--arch/arm/boot/dts/exynos5250-snow-common.dtsi13
-rw-r--r--arch/arm/boot/dts/exynos5420-peach-pit.dts13
-rw-r--r--arch/arm/boot/dts/exynos5420.dtsi407
-rw-r--r--arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi99
-rw-r--r--arch/arm/boot/dts/imx7d-nitrogen7.dts745
-rw-r--r--arch/arm/boot/dts/imx7d.dtsi31
-rw-r--r--arch/arm/boot/dts/omap3-evm-37xx.dts2
-rw-r--r--arch/arm/boot/dts/omap3-igep.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-igep0020-common.dtsi11
-rw-r--r--arch/arm/boot/dts/omap3-n900.dts4
-rw-r--r--arch/arm/boot/dts/omap3-n950-n9.dtsi6
-rw-r--r--arch/arm/boot/dts/omap3-zoom3.dts6
-rw-r--r--arch/arm/boot/dts/omap5-board-common.dtsi48
-rw-r--r--arch/arm/boot/dts/omap5-igep0050.dts26
-rw-r--r--arch/arm/boot/dts/omap5-uevm.dts10
-rw-r--r--arch/arm/boot/dts/r8a7779.dtsi54
-rw-r--r--arch/arm/boot/dts/r8a7790.dtsi155
-rw-r--r--arch/arm/boot/dts/r8a7791.dtsi156
-rw-r--r--arch/arm/boot/dts/r8a7793.dtsi111
-rw-r--r--arch/arm/boot/dts/r8a7794.dtsi116
-rw-r--r--arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts1
-rw-r--r--arch/arm/boot/dts/stih407-family.dtsi3
-rw-r--r--arch/arm/boot/dts/sun6i-a31s-primo81.dts2
-rw-r--r--arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts2
-rw-r--r--arch/arm/boot/dts/tegra124-jetson-tk1.dts116
-rw-r--r--arch/arm/boot/dts/tegra124-nyan.dtsi122
-rw-r--r--arch/arm/boot/dts/tegra124-venice2.dts101
-rw-r--r--arch/arm/boot/dts/tegra124.dtsi167
-rw-r--r--arch/arm/boot/dts/vf-colibri-eval-v3.dtsi16
-rw-r--r--arch/arm/boot/dts/vf-colibri.dtsi33
-rw-r--r--arch/arm/boot/dts/vfxxx.dtsi19
-rw-r--r--arch/arm/configs/exynos_defconfig1
-rw-r--r--arch/arm/configs/multi_v7_defconfig1
-rw-r--r--arch/arm/include/asm/kvm_host.h6
-rw-r--r--arch/arm/include/asm/kvm_mmio.h3
-rw-r--r--arch/arm/include/asm/pgalloc.h2
-rw-r--r--arch/arm/include/asm/pgtable-2level.h1
-rw-r--r--arch/arm/include/asm/pgtable-3level.h5
-rw-r--r--arch/arm/include/asm/pgtable.h1
-rw-r--r--arch/arm/kernel/perf_callchain.c10
-rw-r--r--arch/arm/kernel/ptrace.c2
-rw-r--r--arch/arm/kernel/smp.c2
-rw-r--r--arch/arm/kvm/Kconfig7
-rw-r--r--arch/arm/kvm/Makefile11
-rw-r--r--arch/arm/kvm/arm.c38
-rw-r--r--arch/arm/kvm/mmio.c24
-rw-r--r--arch/arm/mach-exynos/Kconfig1
-rw-r--r--arch/arm/mach-imx/mach-imx6ul.c2
-rw-r--r--arch/arm/mach-lpc32xx/Makefile2
-rw-r--r--arch/arm/mach-lpc32xx/include/mach/irqs.h2
-rw-r--r--arch/arm/mach-lpc32xx/irq.c477
-rw-r--r--arch/arm/mach-omap1/ams-delta-fiq-handler.S6
-rw-r--r--arch/arm/mach-omap1/ams-delta-fiq.c5
-rw-r--r--arch/arm/mach-omap1/include/mach/ams-delta-fiq.h2
-rw-r--r--arch/arm/mach-omap2/Kconfig12
-rw-r--r--arch/arm/mach-omap2/gpmc-nand.c7
-rw-r--r--arch/arm/mach-omap2/omap-secure.h1
-rw-r--r--arch/arm/mach-omap2/omap-smp.c48
-rw-r--r--arch/arm/mach-omap2/powerdomain.c9
-rw-r--r--arch/arm/mach-omap2/powerdomains7xx_data.c76
-rw-r--r--arch/arm/mach-omap2/timer.c7
-rw-r--r--arch/arm/mach-pxa/Kconfig2
-rw-r--r--arch/arm/mach-pxa/eseries.c2
-rw-r--r--arch/arm/mach-pxa/spitz.c55
-rw-r--r--arch/arm/mach-s3c24xx/mach-rx1950.c6
-rw-r--r--arch/arm/mach-vexpress/spc.c2
-rw-r--r--arch/arm/plat-samsung/devs.c2
-rw-r--r--arch/arm/vdso/Makefile2
-rw-r--r--arch/arm64/Kconfig21
-rw-r--r--arch/arm64/Kconfig.debug25
-rw-r--r--arch/arm64/Makefile6
-rw-r--r--arch/arm64/boot/dts/lg/lg1312.dtsi2
-rw-r--r--arch/arm64/boot/dts/renesas/r8a7795.dtsi123
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399.dtsi2
-rw-r--r--arch/arm64/configs/defconfig2
-rw-r--r--arch/arm64/include/asm/elf.h4
-rw-r--r--arch/arm64/include/asm/kgdb.h45
-rw-r--r--arch/arm64/include/asm/kvm_host.h6
-rw-r--r--arch/arm64/include/asm/kvm_mmio.h3
-rw-r--r--arch/arm64/include/asm/memory.h3
-rw-r--r--arch/arm64/include/asm/page.h12
-rw-r--r--arch/arm64/include/asm/pgalloc.h2
-rw-r--r--arch/arm64/include/asm/smp.h12
-rw-r--r--arch/arm64/include/asm/spinlock.h42
-rw-r--r--arch/arm64/include/asm/uaccess.h13
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h8
-rw-r--r--arch/arm64/include/uapi/asm/unistd.h3
-rw-r--r--arch/arm64/kernel/cpuinfo.c8
-rw-r--r--arch/arm64/kernel/hibernate.c6
-rw-r--r--arch/arm64/kernel/kgdb.c14
-rw-r--r--arch/arm64/kernel/perf_callchain.c14
-rw-r--r--arch/arm64/kernel/smp.c18
-rw-r--r--arch/arm64/kernel/traps.c31
-rw-r--r--arch/arm64/kvm/Kconfig7
-rw-r--r--arch/arm64/kvm/Makefile12
-rw-r--r--arch/arm64/kvm/hyp/vgic-v3-sr.c36
-rw-r--r--arch/arm64/kvm/inject_fault.c2
-rw-r--r--arch/arm64/kvm/sys_regs.c13
-rw-r--r--arch/arm64/mm/context.c9
-rw-r--r--arch/arm64/mm/dump.c8
-rw-r--r--arch/arm64/mm/fault.c4
-rw-r--r--arch/arm64/mm/flush.c4
-rw-r--r--arch/arm64/mm/hugetlbpage.c14
-rw-r--r--arch/avr32/include/asm/pgalloc.h6
-rw-r--r--arch/c6x/include/uapi/asm/unistd.h1
-rw-r--r--arch/cris/arch-v32/drivers/mach-a3/nandflash.c1
-rw-r--r--arch/cris/arch-v32/drivers/mach-fs/nandflash.c1
-rw-r--r--arch/cris/include/asm/pgalloc.h4
-rw-r--r--arch/frv/mm/pgalloc.c6
-rw-r--r--arch/h8300/Kconfig1
-rw-r--r--arch/h8300/boot/compressed/Makefile1
-rw-r--r--arch/h8300/include/asm/hash.h53
-rw-r--r--arch/h8300/include/uapi/asm/unistd.h2
-rw-r--r--arch/hexagon/include/asm/pgalloc.h4
-rw-r--r--arch/hexagon/include/uapi/asm/unistd.h1
-rw-r--r--arch/ia64/Kconfig2
-rw-r--r--arch/ia64/Makefile6
-rw-r--r--arch/ia64/include/asm/thread_info.h8
-rw-r--r--arch/ia64/kernel/init_task.c1
-rw-r--r--arch/m32r/boot/compressed/Makefile1
-rw-r--r--arch/m68k/Kconfig.cpu1
-rw-r--r--arch/m68k/include/asm/hash.h59
-rw-r--r--arch/m68k/include/asm/mcf_pgalloc.h4
-rw-r--r--arch/m68k/include/asm/motorola_pgalloc.h4
-rw-r--r--arch/m68k/include/asm/sun3_pgalloc.h4
-rw-r--r--arch/metag/include/asm/pgalloc.h5
-rw-r--r--arch/metag/include/uapi/asm/unistd.h2
-rw-r--r--arch/metag/kernel/perf_callchain.c10
-rw-r--r--arch/microblaze/Kconfig1
-rw-r--r--arch/microblaze/include/asm/hash.h81
-rw-r--r--arch/microblaze/include/asm/pgalloc.h4
-rw-r--r--arch/microblaze/include/asm/unistd.h2
-rw-r--r--arch/microblaze/include/uapi/asm/unistd.h3
-rw-r--r--arch/microblaze/kernel/syscall_table.S3
-rw-r--r--arch/microblaze/mm/pgtable.c3
-rw-r--r--arch/microblaze/pci/pci-common.c2
-rw-r--r--arch/mips/Kconfig1
-rw-r--r--arch/mips/boot/dts/ingenic/jz4740.dtsi2
-rw-r--r--arch/mips/boot/dts/ralink/mt7620a.dtsi2
-rw-r--r--arch/mips/boot/dts/ralink/rt2880.dtsi2
-rw-r--r--arch/mips/boot/dts/ralink/rt3050.dtsi2
-rw-r--r--arch/mips/boot/dts/ralink/rt3883.dtsi2
-rw-r--r--arch/mips/boot/dts/xilfpga/nexys4ddr.dts2
-rw-r--r--arch/mips/cavium-octeon/smp.c2
-rw-r--r--arch/mips/include/asm/asmmacro.h99
-rw-r--r--arch/mips/include/asm/hazards.h8
-rw-r--r--arch/mips/include/asm/kvm_host.h3
-rw-r--r--arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h2
-rw-r--r--arch/mips/include/asm/mach-au1x00/gpio-au1300.h2
-rw-r--r--arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h2
-rw-r--r--arch/mips/include/asm/mach-ip27/dma-coherence.h2
-rw-r--r--arch/mips/include/asm/mach-ip32/dma-coherence.h2
-rw-r--r--arch/mips/include/asm/mach-jz4740/jz4740_nand.h2
-rw-r--r--arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h2
-rw-r--r--arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h2
-rw-r--r--arch/mips/include/asm/mach-loongson64/loongson_hwmon.h2
-rw-r--r--arch/mips/include/asm/mach-malta/kernel-entry-init.h6
-rw-r--r--arch/mips/include/asm/mips_mt.h2
-rw-r--r--arch/mips/include/asm/mipsregs.h188
-rw-r--r--arch/mips/include/asm/msa.h21
-rw-r--r--arch/mips/include/asm/octeon/cvmx-cmd-queue.h2
-rw-r--r--arch/mips/include/asm/octeon/cvmx-helper-board.h2
-rw-r--r--arch/mips/include/asm/octeon/cvmx-ipd.h2
-rw-r--r--arch/mips/include/asm/octeon/cvmx-pow.h2
-rw-r--r--arch/mips/include/asm/pgalloc.h6
-rw-r--r--arch/mips/include/asm/pgtable.h10
-rw-r--r--arch/mips/include/asm/sgi/hpc3.h2
-rw-r--r--arch/mips/jz4740/board-qi_lb60.c87
-rw-r--r--arch/mips/kernel/branch.c4
-rw-r--r--arch/mips/kernel/cps-vec.S15
-rw-r--r--arch/mips/kernel/cpu-probe.c4
-rw-r--r--arch/mips/kernel/elf.c2
-rw-r--r--arch/mips/kernel/irq.c3
-rw-r--r--arch/mips/kernel/mips-r2-to-r6-emul.c2
-rw-r--r--arch/mips/kernel/perf_event.c12
-rw-r--r--arch/mips/kernel/process.c2
-rw-r--r--arch/mips/kernel/signal.c8
-rw-r--r--arch/mips/kernel/smp-cps.c8
-rw-r--r--arch/mips/kvm/emulate.c19
-rw-r--r--arch/mips/kvm/interrupt.h1
-rw-r--r--arch/mips/kvm/locore.S1
-rw-r--r--arch/mips/kvm/mips.c11
-rw-r--r--arch/mips/lasat/picvue_proc.c4
-rw-r--r--arch/mips/lib/ashldi3.c2
-rw-r--r--arch/mips/lib/ashrdi3.c2
-rw-r--r--arch/mips/lib/bswapdi.c2
-rw-r--r--arch/mips/lib/bswapsi.c2
-rw-r--r--arch/mips/lib/cmpdi2.c2
-rw-r--r--arch/mips/lib/lshrdi3.c2
-rw-r--r--arch/mips/lib/memcpy.S2
-rw-r--r--arch/mips/lib/ucmpdi2.c2
-rw-r--r--arch/mips/loongson64/loongson-3/hpet.c2
-rw-r--r--arch/mips/math-emu/dsemul.c4
-rw-r--r--arch/mips/mm/tlbex.c22
-rw-r--r--arch/mips/oprofile/op_impl.h2
-rw-r--r--arch/mips/pci/ops-bridge.c4
-rw-r--r--arch/mips/pistachio/init.c8
-rw-r--r--arch/mips/ralink/mt7620.c112
-rw-r--r--arch/mips/sgi-ip27/ip27-hubio.c2
-rw-r--r--arch/mips/sgi-ip27/ip27-nmi.c2
-rw-r--r--arch/mips/sgi-ip27/ip27-xtalk.c2
-rw-r--r--arch/mips/sni/rm200.c2
-rw-r--r--arch/mips/vdso/Makefile4
-rw-r--r--arch/mips/vr41xx/common/cmu.c2
-rw-r--r--arch/mn10300/boot/compressed/Makefile1
-rw-r--r--arch/mn10300/include/asm/thread_info.h2
-rw-r--r--arch/mn10300/kernel/kgdb.c3
-rw-r--r--arch/mn10300/mm/pgtable.c6
-rw-r--r--arch/nios2/Makefile4
-rw-r--r--arch/nios2/boot/compressed/Makefile1
-rw-r--r--arch/nios2/include/asm/pgalloc.h5
-rw-r--r--arch/nios2/include/uapi/asm/unistd.h2
-rw-r--r--arch/openrisc/include/asm/pgalloc.h2
-rw-r--r--arch/openrisc/include/uapi/asm/unistd.h1
-rw-r--r--arch/openrisc/mm/ioremap.c2
-rw-r--r--arch/parisc/Kconfig3
-rw-r--r--arch/parisc/include/asm/cmpxchg.h9
-rw-r--r--arch/parisc/include/asm/eisa_eeprom.h4
-rw-r--r--arch/parisc/include/asm/ftrace.h2
-rw-r--r--arch/parisc/include/asm/futex.h70
-rw-r--r--arch/parisc/include/asm/ldcw.h2
-rw-r--r--arch/parisc/include/asm/pgalloc.h7
-rw-r--r--arch/parisc/include/asm/syscall.h9
-rw-r--r--arch/parisc/include/asm/thread_info.h4
-rw-r--r--arch/parisc/include/asm/traps.h2
-rw-r--r--arch/parisc/include/asm/uaccess.h91
-rw-r--r--arch/parisc/include/uapi/asm/pdc.h2
-rw-r--r--arch/parisc/include/uapi/asm/ptrace.h48
-rw-r--r--arch/parisc/include/uapi/asm/unistd.h34
-rw-r--r--arch/parisc/kernel/entry.S13
-rw-r--r--arch/parisc/kernel/ftrace.c7
-rw-r--r--arch/parisc/kernel/processor.c5
-rw-r--r--arch/parisc/kernel/ptrace.c368
-rw-r--r--arch/parisc/kernel/syscall.S1
-rw-r--r--arch/parisc/kernel/time.c58
-rw-r--r--arch/parisc/kernel/unaligned.c13
-rw-r--r--arch/parisc/kernel/unwind.c22
-rw-r--r--arch/parisc/lib/bitops.c6
-rw-r--r--arch/parisc/math-emu/fpudispatch.c2
-rw-r--r--arch/powerpc/Kconfig2
-rw-r--r--arch/powerpc/include/asm/book3s/32/pgalloc.h1
-rw-r--r--arch/powerpc/include/asm/book3s/64/mmu-hash.h1
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgalloc.h28
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h1
-rw-r--r--arch/powerpc/include/asm/book3s/64/radix.h15
-rw-r--r--arch/powerpc/include/asm/book3s/64/tlbflush-radix.h3
-rw-r--r--arch/powerpc/include/asm/book3s/64/tlbflush.h14
-rw-r--r--arch/powerpc/include/asm/book3s/pgalloc.h5
-rw-r--r--arch/powerpc/include/asm/nohash/64/pgalloc.h10
-rw-r--r--arch/powerpc/include/asm/reg.h6
-rw-r--r--arch/powerpc/kernel/eeh_driver.c9
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S7
-rw-r--r--arch/powerpc/kernel/pci_64.c1
-rw-r--r--arch/powerpc/kernel/process.c10
-rw-r--r--arch/powerpc/kernel/prom_init.c3
-rw-r--r--arch/powerpc/kernel/ptrace.c4
-rw-r--r--arch/powerpc/kernel/tm.S61
-rw-r--r--arch/powerpc/mm/hash_native_64.c14
-rw-r--r--arch/powerpc/mm/hash_utils_64.c36
-rw-r--r--arch/powerpc/mm/hugetlbpage.c2
-rw-r--r--arch/powerpc/mm/mmu_context_book3s64.c2
-rw-r--r--arch/powerpc/mm/pgtable-book3s64.c5
-rw-r--r--arch/powerpc/mm/pgtable-radix.c37
-rw-r--r--arch/powerpc/mm/pgtable_32.c4
-rw-r--r--arch/powerpc/mm/pgtable_64.c3
-rw-r--r--arch/powerpc/mm/tlb-radix.c92
-rw-r--r--arch/powerpc/perf/callchain.c20
-rw-r--r--arch/powerpc/platforms/512x/clock-commonclk.c2
-rw-r--r--arch/powerpc/platforms/cell/spufs/coredump.c2
-rw-r--r--arch/powerpc/platforms/pseries/eeh_pseries.c49
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c4
-rw-r--r--arch/powerpc/sysdev/axonram.c2
-rw-r--r--arch/s390/boot/compressed/Makefile1
-rw-r--r--arch/s390/configs/default_defconfig44
-rw-r--r--arch/s390/configs/gcov_defconfig34
-rw-r--r--arch/s390/configs/performance_defconfig36
-rw-r--r--arch/s390/configs/zfcpdump_defconfig4
-rw-r--r--arch/s390/defconfig44
-rw-r--r--arch/s390/include/asm/fpu/api.h2
-rw-r--r--arch/s390/include/asm/kvm_host.h1
-rw-r--r--arch/s390/kernel/ipl.c7
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c8
-rw-r--r--arch/s390/kernel/perf_event.c4
-rw-r--r--arch/s390/kvm/intercept.c2
-rw-r--r--arch/s390/kvm/kvm-s390.c3
-rw-r--r--arch/s390/mm/fault.c1
-rw-r--r--arch/s390/mm/pgalloc.c2
-rw-r--r--arch/s390/mm/pgtable.c2
-rw-r--r--arch/s390/net/bpf_jit.h4
-rw-r--r--arch/s390/net/bpf_jit_comp.c4
-rw-r--r--arch/score/include/asm/pgalloc.h5
-rw-r--r--arch/score/include/uapi/asm/unistd.h1
-rw-r--r--arch/sh/boot/compressed/Makefile1
-rw-r--r--arch/sh/boot/romimage/Makefile1
-rw-r--r--arch/sh/include/asm/pgalloc.h4
-rw-r--r--arch/sh/kernel/perf_callchain.c4
-rw-r--r--arch/sh/mm/pgtable.c2
-rw-r--r--arch/sparc/include/asm/head_64.h4
-rw-r--r--arch/sparc/include/asm/pgalloc_64.h6
-rw-r--r--arch/sparc/include/asm/ttable.h8
-rw-r--r--arch/sparc/kernel/Makefile1
-rw-r--r--arch/sparc/kernel/perf_event.c14
-rw-r--r--arch/sparc/kernel/rtrap_64.S57
-rw-r--r--arch/sparc/kernel/signal32.c46
-rw-r--r--arch/sparc/kernel/signal_32.c41
-rw-r--r--arch/sparc/kernel/signal_64.c31
-rw-r--r--arch/sparc/kernel/sigutil_32.c9
-rw-r--r--arch/sparc/kernel/sigutil_64.c10
-rw-r--r--arch/sparc/kernel/urtt_fill.S98
-rw-r--r--arch/sparc/mm/init_64.c16
-rw-r--r--arch/tile/include/asm/thread_info.h2
-rw-r--r--arch/tile/include/uapi/asm/unistd.h1
-rw-r--r--arch/tile/kernel/perf_event.c6
-rw-r--r--arch/tile/kernel/process.c3
-rw-r--r--arch/tile/mm/pgtable.c2
-rw-r--r--arch/um/include/shared/registers.h2
-rw-r--r--arch/um/kernel/mem.c4
-rw-r--r--arch/um/kernel/process.c2
-rw-r--r--arch/um/os-Linux/signal.c28
-rw-r--r--arch/unicore32/boot/Makefile2
-rw-r--r--arch/unicore32/boot/compressed/Makefile1
-rw-r--r--arch/unicore32/include/asm/pgalloc.h2
-rw-r--r--arch/unicore32/include/uapi/asm/unistd.h2
-rw-r--r--arch/x86/Kconfig9
-rw-r--r--arch/x86/boot/Makefile3
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/entry/thunk_64.S11
-rw-r--r--arch/x86/entry/vdso/Makefile4
-rw-r--r--arch/x86/events/core.c14
-rw-r--r--arch/x86/events/intel/p4.c2
-rw-r--r--arch/x86/events/intel/rapl.c2
-rw-r--r--arch/x86/events/intel/uncore.c2
-rw-r--r--arch/x86/events/intel/uncore_snbep.c21
-rw-r--r--arch/x86/ia32/ia32_aout.c17
-rw-r--r--arch/x86/include/asm/bugs.h8
-rw-r--r--arch/x86/include/asm/cpufeature.h12
-rw-r--r--arch/x86/include/asm/disabled-features.h6
-rw-r--r--arch/x86/include/asm/intel-family.h68
-rw-r--r--arch/x86/include/asm/intel_telemetry.h2
-rw-r--r--arch/x86/include/asm/kprobes.h11
-rw-r--r--arch/x86/include/asm/kvm_host.h11
-rw-r--r--arch/x86/include/asm/msr.h4
-rw-r--r--arch/x86/include/asm/pgalloc.h4
-rw-r--r--arch/x86/include/asm/pmc_core.h27
-rw-r--r--arch/x86/include/asm/pvclock.h25
-rw-r--r--arch/x86/include/asm/stacktrace.h6
-rw-r--r--arch/x86/include/uapi/asm/svm.h44
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c4
-rw-r--r--arch/x86/kernel/cpu/common.c7
-rw-r--r--arch/x86/kernel/cpu/intel.c37
-rw-r--r--arch/x86/kernel/dumpstack.c22
-rw-r--r--arch/x86/kernel/dumpstack_32.c4
-rw-r--r--arch/x86/kernel/dumpstack_64.c8
-rw-r--r--arch/x86/kernel/espfix_64.c2
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c12
-rw-r--r--arch/x86/kernel/process_64.c4
-rw-r--r--arch/x86/kernel/ptrace.c4
-rw-r--r--arch/x86/kernel/pvclock.c11
-rw-r--r--arch/x86/kernel/traps.c20
-rw-r--r--arch/x86/kernel/tsc_msr.c3
-rw-r--r--arch/x86/kvm/cpuid.c22
-rw-r--r--arch/x86/kvm/lapic.c3
-rw-r--r--arch/x86/kvm/mmu.c8
-rw-r--r--arch/x86/kvm/svm.c25
-rw-r--r--arch/x86/kvm/vmx.c86
-rw-r--r--arch/x86/kvm/x86.c18
-rw-r--r--arch/x86/kvm/x86.h7
-rw-r--r--arch/x86/mm/fault.c11
-rw-r--r--arch/x86/mm/pgtable.c2
-rw-r--r--arch/x86/pci/xen.c7
-rw-r--r--arch/x86/platform/efi/efi_64.c2
-rw-r--r--arch/x86/platform/efi/efi_stub_64.S9
-rw-r--r--arch/x86/purgatory/Makefile2
-rw-r--r--arch/x86/realmode/rm/Makefile1
-rw-r--r--arch/x86/um/os-Linux/registers.c49
-rw-r--r--arch/x86/um/ptrace_32.c5
-rw-r--r--arch/x86/um/ptrace_64.c16
-rw-r--r--arch/x86/um/shared/sysdep/ptrace_64.h4
-rw-r--r--arch/x86/um/signal.c37
-rw-r--r--arch/x86/um/user-offsets.c2
-rw-r--r--arch/x86/xen/mmu.c74
-rw-r--r--arch/x86/xen/p2m.c2
-rw-r--r--arch/x86/xen/setup.c65
-rw-r--r--arch/x86/xen/time.c6
-rw-r--r--arch/xtensa/include/asm/pgalloc.h2
-rw-r--r--arch/xtensa/kernel/perf_event.c10
-rw-r--r--block/blk-lib.c12
-rw-r--r--block/blk-mq.c21
-rw-r--r--block/ioctl.c1
-rw-r--r--crypto/asymmetric_keys/Kconfig1
-rw-r--r--crypto/crypto_user.c1
-rw-r--r--drivers/acpi/acpi_dbg.c22
-rw-r--r--drivers/acpi/acpi_processor.c9
-rw-r--r--drivers/acpi/acpi_video.c9
-rw-r--r--drivers/acpi/acpica/exconfig.c2
-rw-r--r--drivers/acpi/acpica/hwregs.c169
-rw-r--r--drivers/acpi/acpica/nsparse.c9
-rw-r--r--drivers/acpi/battery.c2
-rw-r--r--drivers/acpi/bus.c2
-rw-r--r--drivers/acpi/device_pm.c1
-rw-r--r--drivers/acpi/ec.c29
-rw-r--r--drivers/acpi/internal.h2
-rw-r--r--drivers/acpi/nfit.c12
-rw-r--r--drivers/acpi/nfit.h10
-rw-r--r--drivers/acpi/pci_link.c2
-rw-r--r--drivers/acpi/processor_throttling.c9
-rw-r--r--drivers/acpi/utils.c6
-rw-r--r--drivers/ata/ahci_seattle.c2
-rw-r--r--drivers/ata/libata-eh.c2
-rw-r--r--drivers/ata/sata_highbank.c2
-rw-r--r--drivers/ata/sata_mv.c2
-rw-r--r--drivers/atm/firestream.c6
-rw-r--r--drivers/atm/iphase.c2
-rw-r--r--drivers/base/Makefile2
-rw-r--r--drivers/base/isa.c2
-rw-r--r--drivers/base/module.c8
-rw-r--r--drivers/base/power/main.c5
-rw-r--r--drivers/base/power/opp/cpu.c12
-rw-r--r--drivers/base/power/opp/of.c10
-rw-r--r--drivers/base/power/opp/opp.h8
-rw-r--r--drivers/bcma/driver_chipcommon_sflash.c1
-rw-r--r--drivers/block/aoe/aoecmd.c2
-rw-r--r--drivers/block/brd.c2
-rw-r--r--drivers/block/nbd.c2
-rw-r--r--drivers/block/rbd.c305
-rw-r--r--drivers/block/xen-blkfront.c35
-rw-r--r--drivers/char/ipmi/ipmi_msghandler.c8
-rw-r--r--drivers/clk/Kconfig1
-rw-r--r--drivers/clk/clk-oxnas.c4
-rw-r--r--drivers/clk/clk-pwm.c17
-rw-r--r--drivers/clk/microchip/clk-pic32mzda.c10
-rw-r--r--drivers/clk/rockchip/clk-cpu.c4
-rw-r--r--drivers/clk/rockchip/clk-mmc-phase.c12
-rw-r--r--drivers/clk/rockchip/clk-rk3399.c8
-rw-r--r--drivers/clk/tegra/clk-tegra210.c2
-rw-r--r--drivers/connector/cn_proc.c43
-rw-r--r--drivers/cpufreq/cpufreq-dt-platdev.c7
-rw-r--r--drivers/cpufreq/cpufreq.c90
-rw-r--r--drivers/cpufreq/intel_pstate.c50
-rw-r--r--drivers/cpufreq/mt8173-cpufreq.c11
-rw-r--r--drivers/cpufreq/omap-cpufreq.c2
-rw-r--r--drivers/cpufreq/pcc-cpufreq.c2
-rw-r--r--drivers/cpuidle/cpuidle.c2
-rw-r--r--drivers/crypto/caam/ctrl.c2
-rw-r--r--drivers/crypto/ccp/ccp-crypto-aes-xts.c17
-rw-r--r--drivers/crypto/omap-sham.c2
-rw-r--r--drivers/crypto/ux500/hash/hash_core.c4
-rw-r--r--drivers/crypto/vmx/aes_cbc.c2
-rw-r--r--drivers/crypto/vmx/aes_ctr.c2
-rw-r--r--drivers/crypto/vmx/ppc-xlate.pl2
-rw-r--r--drivers/devfreq/devfreq.c27
-rw-r--r--drivers/devfreq/event/exynos-nocp.c3
-rw-r--r--drivers/dma-buf/dma-buf.c7
-rw-r--r--drivers/dma-buf/reservation.c72
-rw-r--r--drivers/dma/at_xdmac.c82
-rw-r--r--drivers/dma/mv_xor.c10
-rw-r--r--drivers/dma/sun4i-dma.c16
-rw-r--r--drivers/edac/edac_mc.c3
-rw-r--r--drivers/edac/sb_edac.c35
-rw-r--r--drivers/extcon/extcon-palmas.c2
-rw-r--r--drivers/firmware/efi/arm-init.c14
-rw-r--r--drivers/gpio/Kconfig9
-rw-r--r--drivers/gpio/gpio-104-dio-48e.c4
-rw-r--r--drivers/gpio/gpio-104-idi-48.c1
-rw-r--r--drivers/gpio/gpio-bcm-kona.c4
-rw-r--r--drivers/gpio/gpio-lpc32xx.c48
-rw-r--r--drivers/gpio/gpio-tegra.c9
-rw-r--r--drivers/gpio/gpio-xlp.c2
-rw-r--r--drivers/gpio/gpio-zynq.c7
-rw-r--r--drivers/gpio/gpiolib-of.c1
-rw-r--r--drivers/gpio/gpiolib.c78
-rw-r--r--drivers/gpu/drm/Makefile2
-rw-r--r--drivers/gpu/drm/amd/acp/Kconfig1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu.h9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c14
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c25
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c25
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c27
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c28
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c24
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c23
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c111
-rw-r--r--drivers/gpu/drm/amd/amdgpu/ci_dpm.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cik.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cik_ih.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cik_sdma.c22
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cz_dpm.c13
-rw-r--r--drivers/gpu/drm/amd/amdgpu/cz_ih.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/dce_v11_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/fiji_dpm.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c19
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c39
-rw-r--r--drivers/gpu/drm/amd/amdgpu/iceland_dpm.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/iceland_ih.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/kv_dpm.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c20
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c29
-rw-r--r--drivers/gpu/drm/amd/amdgpu/tonga_dpm.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/tonga_ih.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vi.c15
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process.c70
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_topology.c2
-rw-r--r--drivers/gpu/drm/amd/include/amd_shared.h1
-rw-r--r--drivers/gpu/drm/amd/include/atombios.h72
-rw-r--r--drivers/gpu/drm/amd/include/cgs_common.h6
-rw-r--r--drivers/gpu/drm/amd/powerplay/amd_powerplay.c8
-rw-r--r--drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c3
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c49
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c6
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c47
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h1
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c467
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h4
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c2
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c6
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c18
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c47
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h34
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c40
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h16
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c147
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/hwmgr.h4
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h3
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h1
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/smu74.h75
-rw-r--r--drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h43
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c2
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c6
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c51
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c1
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c7
-rw-r--r--drivers/gpu/drm/arm/hdlcd_crtc.c86
-rw-r--r--drivers/gpu/drm/arm/hdlcd_drv.c68
-rw-r--r--drivers/gpu/drm/arm/hdlcd_drv.h5
-rw-r--r--drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c10
-rw-r--r--drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c10
-rw-r--r--drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c2
-rw-r--r--drivers/gpu/drm/drm_atomic.c30
-rw-r--r--drivers/gpu/drm/drm_crtc.c5
-rw-r--r--drivers/gpu/drm/drm_crtc_helper.c54
-rw-r--r--drivers/gpu/drm/drm_dp_dual_mode_helper.c366
-rw-r--r--drivers/gpu/drm/drm_dp_mst_topology.c8
-rw-r--r--drivers/gpu/drm/drm_fb_cma_helper.c2
-rw-r--r--drivers/gpu/drm/drm_gem_cma_helper.c12
-rw-r--r--drivers/gpu/drm/drm_modes.c2
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_iommu.c1
-rw-r--r--drivers/gpu/drm/exynos/exynos7_drm_decon.c1
-rw-r--r--drivers/gpu/drm/exynos/exynos_dp.c5
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_core.c1
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_fimd.c5
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_g2d.c12
-rw-r--r--drivers/gpu/drm/exynos/exynos_drm_plane.c2
-rw-r--r--drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c3
-rw-r--r--drivers/gpu/drm/i915/i915_debugfs.c4
-rw-r--r--drivers/gpu/drm/i915/i915_dma.c6
-rw-r--r--drivers/gpu/drm/i915/i915_drv.c5
-rw-r--r--drivers/gpu/drm/i915/i915_drv.h2
-rw-r--r--drivers/gpu/drm/i915/i915_gem.c11
-rw-r--r--drivers/gpu/drm/i915/i915_gem_gtt.c8
-rw-r--r--drivers/gpu/drm/i915/i915_gem_gtt.h1
-rw-r--r--drivers/gpu/drm/i915/intel_bios.c82
-rw-r--r--drivers/gpu/drm/i915/intel_ddi.c16
-rw-r--r--drivers/gpu/drm/i915/intel_display.c110
-rw-r--r--drivers/gpu/drm/i915/intel_dp.c31
-rw-r--r--drivers/gpu/drm/i915/intel_dp_link_training.c26
-rw-r--r--drivers/gpu/drm/i915/intel_dpll_mgr.c13
-rw-r--r--drivers/gpu/drm/i915/intel_drv.h10
-rw-r--r--drivers/gpu/drm/i915/intel_dsi.c144
-rw-r--r--drivers/gpu/drm/i915/intel_fbc.c3
-rw-r--r--drivers/gpu/drm/i915/intel_hdmi.c107
-rw-r--r--drivers/gpu/drm/i915/intel_lrc.c146
-rw-r--r--drivers/gpu/drm/i915/intel_lrc.h1
-rw-r--r--drivers/gpu/drm/i915/intel_lvds.c2
-rw-r--r--drivers/gpu/drm/i915/intel_mocs.c12
-rw-r--r--drivers/gpu/drm/i915/intel_panel.c6
-rw-r--r--drivers/gpu/drm/i915/intel_pm.c2
-rw-r--r--drivers/gpu/drm/i915/intel_psr.c55
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.c207
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.h6
-rw-r--r--drivers/gpu/drm/i915/intel_vbt_defs.h19
-rw-r--r--drivers/gpu/drm/imx/imx-drm-core.c21
-rw-r--r--drivers/gpu/drm/imx/imx-drm.h7
-rw-r--r--drivers/gpu/drm/imx/imx-ldb.c78
-rw-r--r--drivers/gpu/drm/imx/imx-tve.c6
-rw-r--r--drivers/gpu/drm/imx/ipuv3-crtc.c12
-rw-r--r--drivers/gpu/drm/imx/ipuv3-plane.c5
-rw-r--r--drivers/gpu/drm/imx/parallel-display.c40
-rw-r--r--drivers/gpu/drm/mediatek/mtk_dpi.c5
-rw-r--r--drivers/gpu/drm/mediatek/mtk_dsi.c4
-rw-r--r--drivers/gpu/drm/mgag200/mgag200_mode.c10
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_gpu.c2
-rw-r--r--drivers/gpu/drm/msm/msm_fbdev.c4
-rw-r--r--drivers/gpu/drm/msm/msm_gem.c2
-rw-r--r--drivers/gpu/drm/msm/msm_gem_submit.c7
-rw-r--r--drivers/gpu/drm/msm/msm_rd.c3
-rw-r--r--drivers/gpu/drm/msm/msm_ringbuffer.c4
-rw-r--r--drivers/gpu/drm/omapdrm/Kconfig1
-rw-r--r--drivers/gpu/drm/omapdrm/displays/connector-hdmi.c1
-rw-r--r--drivers/gpu/drm/omapdrm/displays/encoder-opa362.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-dpi.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c1
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c2
-rw-r--r--drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c2
-rw-r--r--drivers/gpu/drm/omapdrm/dss/dsi.c10
-rw-r--r--drivers/gpu/drm/omapdrm/dss/dss.c1
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4.c11
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi4_core.c2
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi5.c11
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi5_core.c6
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi_phy.c1
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi_pll.c1
-rw-r--r--drivers/gpu/drm/omapdrm/dss/hdmi_wp.c1
-rw-r--r--drivers/gpu/drm/omapdrm/omap_debugfs.c2
-rw-r--r--drivers/gpu/drm/omapdrm/omap_dmm_tiler.c1
-rw-r--r--drivers/gpu/drm/omapdrm/omap_fb.c2
-rw-r--r--drivers/gpu/drm/omapdrm/omap_gem.c1
-rw-r--r--drivers/gpu/drm/radeon/atombios_crtc.c5
-rw-r--r--drivers/gpu/drm/radeon/kv_dpm.c2
-rw-r--r--drivers/gpu/drm/radeon/radeon_device.c23
-rw-r--r--drivers/gpu/drm/sti/sti_crtc.c10
-rw-r--r--drivers/gpu/drm/sti/sti_vtg.c4
-rw-r--r--drivers/gpu/drm/sun4i/Kconfig2
-rw-r--r--drivers/gpu/drm/sun4i/sun4i_backend.c4
-rw-r--r--drivers/gpu/drm/sun4i/sun4i_dotclock.c39
-rw-r--r--drivers/gpu/drm/sun4i/sun4i_drv.c50
-rw-r--r--drivers/gpu/drm/sun4i/sun4i_rgb.c16
-rw-r--r--drivers/gpu/drm/sun4i/sun4i_tcon.c23
-rw-r--r--drivers/gpu/drm/tilcdc/tilcdc_tfp410.c2
-rw-r--r--drivers/gpu/drm/vc4/vc4_crtc.c32
-rw-r--r--drivers/gpu/drm/vc4/vc4_drv.c14
-rw-r--r--drivers/gpu/drm/vc4/vc4_kms.c16
-rw-r--r--drivers/gpu/drm/vc4/vc4_regs.h4
-rw-r--r--drivers/gpu/drm/vmwgfx/vmwgfx_msg.c4
-rw-r--r--drivers/gpu/host1x/hw/intr_hw.c2
-rw-r--r--drivers/gpu/ipu-v3/ipu-common.c5
-rw-r--r--drivers/hid/hid-elo.c2
-rw-r--r--drivers/hid/hid-multitouch.c26
-rw-r--r--drivers/hid/usbhid/hiddev.c10
-rw-r--r--drivers/hwmon/dell-smm-hwmon.c85
-rw-r--r--drivers/hwmon/emc2103.c2
-rw-r--r--drivers/hwmon/fam15h_power.c8
-rw-r--r--drivers/hwmon/lm75.c10
-rw-r--r--drivers/hwmon/lm90.c2
-rw-r--r--drivers/hwmon/ntc_thermistor.c12
-rw-r--r--drivers/hwmon/pwm-fan.c26
-rw-r--r--drivers/hwmon/scpi-hwmon.c48
-rw-r--r--drivers/hwmon/tmp102.c8
-rw-r--r--drivers/hwtracing/coresight/coresight-tmc-etr.c11
-rw-r--r--drivers/hwtracing/coresight/coresight.c15
-rw-r--r--drivers/i2c/busses/Kconfig3
-rw-r--r--drivers/i2c/busses/i2c-at91.c2
-rw-r--r--drivers/i2c/busses/i2c-i801.c99
-rw-r--r--drivers/i2c/busses/i2c-octeon.c17
-rw-r--r--drivers/i2c/busses/i2c-rcar.c2
-rw-r--r--drivers/i2c/i2c-dev.c25
-rw-r--r--drivers/i2c/muxes/i2c-mux-reg.c1
-rw-r--r--drivers/iio/accel/kxsd9.c4
-rw-r--r--drivers/iio/accel/st_accel_buffer.c2
-rw-r--r--drivers/iio/accel/st_accel_core.c1
-rw-r--r--drivers/iio/adc/ad7266.c7
-rw-r--r--drivers/iio/common/st_sensors/st_sensors_buffer.c25
-rw-r--r--drivers/iio/common/st_sensors/st_sensors_core.c8
-rw-r--r--drivers/iio/common/st_sensors/st_sensors_trigger.c96
-rw-r--r--drivers/iio/dac/Kconfig2
-rw-r--r--drivers/iio/dac/ad5592r-base.c2
-rw-r--r--drivers/iio/gyro/st_gyro_buffer.c2
-rw-r--r--drivers/iio/gyro/st_gyro_core.c1
-rw-r--r--drivers/iio/humidity/am2315.c4
-rw-r--r--drivers/iio/humidity/hdc100x.c20
-rw-r--r--drivers/iio/imu/bmi160/bmi160_core.c16
-rw-r--r--drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c5
-rw-r--r--drivers/iio/industrialio-trigger.c23
-rw-r--r--drivers/iio/light/apds9960.c1
-rw-r--r--drivers/iio/light/bh1780.c10
-rw-r--r--drivers/iio/light/max44000.c1
-rw-r--r--drivers/iio/magnetometer/st_magn_buffer.c2
-rw-r--r--drivers/iio/magnetometer/st_magn_core.c1
-rw-r--r--drivers/iio/pressure/bmp280.c4
-rw-r--r--drivers/iio/pressure/st_pressure_buffer.c2
-rw-r--r--drivers/iio/pressure/st_pressure_core.c81
-rw-r--r--drivers/iio/proximity/as3935.c17
-rw-r--r--drivers/infiniband/Kconfig2
-rw-r--r--drivers/infiniband/core/Makefile12
-rw-r--r--drivers/infiniband/core/addr.c226
-rw-r--r--drivers/infiniband/core/cache.c14
-rw-r--r--drivers/infiniband/core/cm.c4
-rw-r--r--drivers/infiniband/core/cma.c62
-rw-r--r--drivers/infiniband/core/core_priv.h16
-rw-r--r--drivers/infiniband/core/device.c62
-rw-r--r--drivers/infiniband/core/iwpm_msg.c2
-rw-r--r--drivers/infiniband/core/mad.c19
-rw-r--r--drivers/infiniband/core/multicast.c23
-rw-r--r--drivers/infiniband/core/sa_query.c211
-rw-r--r--drivers/infiniband/core/sysfs.c374
-rw-r--r--drivers/infiniband/core/uverbs_cmd.c2
-rw-r--r--drivers/infiniband/core/verbs.c16
-rw-r--r--drivers/infiniband/hw/Makefile1
-rw-r--r--drivers/infiniband/hw/cxgb3/cxio_hal.c2
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_provider.c147
-rw-r--r--drivers/infiniband/hw/cxgb4/provider.c58
-rw-r--r--drivers/infiniband/hw/hfi1/Kconfig (renamed from drivers/staging/rdma/hfi1/Kconfig)0
-rw-r--r--drivers/infiniband/hw/hfi1/Makefile (renamed from drivers/staging/rdma/hfi1/Makefile)2
-rw-r--r--drivers/infiniband/hw/hfi1/affinity.c (renamed from drivers/staging/rdma/hfi1/affinity.c)31
-rw-r--r--drivers/infiniband/hw/hfi1/affinity.h (renamed from drivers/staging/rdma/hfi1/affinity.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/aspm.h (renamed from drivers/staging/rdma/hfi1/aspm.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/chip.c (renamed from drivers/staging/rdma/hfi1/chip.c)63
-rw-r--r--drivers/infiniband/hw/hfi1/chip.h (renamed from drivers/staging/rdma/hfi1/chip.h)6
-rw-r--r--drivers/infiniband/hw/hfi1/chip_registers.h (renamed from drivers/staging/rdma/hfi1/chip_registers.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/common.h (renamed from drivers/staging/rdma/hfi1/common.h)5
-rw-r--r--drivers/infiniband/hw/hfi1/debugfs.c (renamed from drivers/staging/rdma/hfi1/debugfs.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/debugfs.h (renamed from drivers/staging/rdma/hfi1/debugfs.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/device.c (renamed from drivers/staging/rdma/hfi1/device.c)18
-rw-r--r--drivers/infiniband/hw/hfi1/device.h (renamed from drivers/staging/rdma/hfi1/device.h)3
-rw-r--r--drivers/infiniband/hw/hfi1/dma.c (renamed from drivers/staging/rdma/hfi1/dma.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/driver.c (renamed from drivers/staging/rdma/hfi1/driver.c)2
-rw-r--r--drivers/infiniband/hw/hfi1/efivar.c (renamed from drivers/staging/rdma/hfi1/efivar.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/efivar.h (renamed from drivers/staging/rdma/hfi1/efivar.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/eprom.c102
-rw-r--r--drivers/infiniband/hw/hfi1/eprom.h (renamed from drivers/staging/rdma/hfi1/eprom.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/file_ops.c (renamed from drivers/staging/rdma/hfi1/file_ops.c)550
-rw-r--r--drivers/infiniband/hw/hfi1/firmware.c (renamed from drivers/staging/rdma/hfi1/firmware.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/hfi.h (renamed from drivers/staging/rdma/hfi1/hfi.h)7
-rw-r--r--drivers/infiniband/hw/hfi1/init.c (renamed from drivers/staging/rdma/hfi1/init.c)26
-rw-r--r--drivers/infiniband/hw/hfi1/intr.c (renamed from drivers/staging/rdma/hfi1/intr.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/iowait.h (renamed from drivers/staging/rdma/hfi1/iowait.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/mad.c (renamed from drivers/staging/rdma/hfi1/mad.c)118
-rw-r--r--drivers/infiniband/hw/hfi1/mad.h (renamed from drivers/staging/rdma/hfi1/mad.h)2
-rw-r--r--drivers/infiniband/hw/hfi1/mmu_rb.c (renamed from drivers/staging/rdma/hfi1/mmu_rb.c)22
-rw-r--r--drivers/infiniband/hw/hfi1/mmu_rb.h (renamed from drivers/staging/rdma/hfi1/mmu_rb.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/opa_compat.h (renamed from drivers/staging/rdma/hfi1/opa_compat.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/pcie.c (renamed from drivers/staging/rdma/hfi1/pcie.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/pio.c (renamed from drivers/staging/rdma/hfi1/pio.c)29
-rw-r--r--drivers/infiniband/hw/hfi1/pio.h (renamed from drivers/staging/rdma/hfi1/pio.h)8
-rw-r--r--drivers/infiniband/hw/hfi1/pio_copy.c (renamed from drivers/staging/rdma/hfi1/pio_copy.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/platform.c (renamed from drivers/staging/rdma/hfi1/platform.c)27
-rw-r--r--drivers/infiniband/hw/hfi1/platform.h (renamed from drivers/staging/rdma/hfi1/platform.h)1
-rw-r--r--drivers/infiniband/hw/hfi1/qp.c (renamed from drivers/staging/rdma/hfi1/qp.c)9
-rw-r--r--drivers/infiniband/hw/hfi1/qp.h (renamed from drivers/staging/rdma/hfi1/qp.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/qsfp.c (renamed from drivers/staging/rdma/hfi1/qsfp.c)3
-rw-r--r--drivers/infiniband/hw/hfi1/qsfp.h (renamed from drivers/staging/rdma/hfi1/qsfp.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/rc.c (renamed from drivers/staging/rdma/hfi1/rc.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/ruc.c (renamed from drivers/staging/rdma/hfi1/ruc.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/sdma.c (renamed from drivers/staging/rdma/hfi1/sdma.c)4
-rw-r--r--drivers/infiniband/hw/hfi1/sdma.h (renamed from drivers/staging/rdma/hfi1/sdma.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/sdma_txreq.h (renamed from drivers/staging/rdma/hfi1/sdma_txreq.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/sysfs.c (renamed from drivers/staging/rdma/hfi1/sysfs.c)4
-rw-r--r--drivers/infiniband/hw/hfi1/trace.c (renamed from drivers/staging/rdma/hfi1/trace.c)21
-rw-r--r--drivers/infiniband/hw/hfi1/trace.h (renamed from drivers/staging/rdma/hfi1/trace.h)5
-rw-r--r--drivers/infiniband/hw/hfi1/twsi.c (renamed from drivers/staging/rdma/hfi1/twsi.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/twsi.h (renamed from drivers/staging/rdma/hfi1/twsi.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/uc.c (renamed from drivers/staging/rdma/hfi1/uc.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/ud.c (renamed from drivers/staging/rdma/hfi1/ud.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/user_exp_rcv.c (renamed from drivers/staging/rdma/hfi1/user_exp_rcv.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/user_exp_rcv.h (renamed from drivers/staging/rdma/hfi1/user_exp_rcv.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/user_pages.c (renamed from drivers/staging/rdma/hfi1/user_pages.c)0
-rw-r--r--drivers/infiniband/hw/hfi1/user_sdma.c (renamed from drivers/staging/rdma/hfi1/user_sdma.c)24
-rw-r--r--drivers/infiniband/hw/hfi1/user_sdma.h (renamed from drivers/staging/rdma/hfi1/user_sdma.h)0
-rw-r--r--drivers/infiniband/hw/hfi1/verbs.c (renamed from drivers/staging/rdma/hfi1/verbs.c)4
-rw-r--r--drivers/infiniband/hw/hfi1/verbs.h (renamed from drivers/staging/rdma/hfi1/verbs.h)1
-rw-r--r--drivers/infiniband/hw/hfi1/verbs_txreq.c (renamed from drivers/staging/rdma/hfi1/verbs_txreq.c)4
-rw-r--r--drivers/infiniband/hw/hfi1/verbs_txreq.h (renamed from drivers/staging/rdma/hfi1/verbs_txreq.h)1
-rw-r--r--drivers/infiniband/hw/i40iw/i40iw.h2
-rw-r--r--drivers/infiniband/hw/i40iw/i40iw_verbs.c162
-rw-r--r--drivers/infiniband/hw/mlx4/ah.c2
-rw-r--r--drivers/infiniband/hw/mlx4/mad.c24
-rw-r--r--drivers/infiniband/hw/mlx4/main.c7
-rw-r--r--drivers/infiniband/hw/mlx4/mlx4_ib.h2
-rw-r--r--drivers/infiniband/hw/mlx4/mr.c34
-rw-r--r--drivers/infiniband/hw/mlx4/qp.c6
-rw-r--r--drivers/infiniband/hw/mlx5/cq.c12
-rw-r--r--drivers/infiniband/hw/mlx5/mad.c2
-rw-r--r--drivers/infiniband/hw/mlx5/main.c22
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c48
-rw-r--r--drivers/infiniband/hw/qib/qib_file_ops.c5
-rw-r--r--drivers/infiniband/hw/qib/qib_iba7322.c15
-rw-r--r--drivers/infiniband/hw/qib/qib_mad.c6
-rw-r--r--drivers/infiniband/hw/qib/qib_verbs.h1
-rw-r--r--drivers/infiniband/hw/usnic/usnic_uiom.c5
-rw-r--r--drivers/infiniband/sw/rdmavt/cq.c1
-rw-r--r--drivers/infiniband/sw/rdmavt/mr.c4
-rw-r--r--drivers/infiniband/sw/rdmavt/qp.c38
-rw-r--r--drivers/infiniband/sw/rdmavt/vt.c4
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h5
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_cm.c4
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c109
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c147
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c48
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_verbs.c3
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_vlan.c8
-rw-r--r--drivers/infiniband/ulp/isert/ib_isert.c11
-rw-r--r--drivers/infiniband/ulp/srp/ib_srp.c7
-rw-r--r--drivers/infiniband/ulp/srpt/ib_srpt.c14
-rw-r--r--drivers/infiniband/ulp/srpt/ib_srpt.h1
-rw-r--r--drivers/input/joystick/xpad.c57
-rw-r--r--drivers/input/misc/max77693-haptic.c17
-rw-r--r--drivers/input/misc/max8997_haptic.c6
-rw-r--r--drivers/input/misc/pwm-beeper.c75
-rw-r--r--drivers/input/misc/uinput.c6
-rw-r--r--drivers/input/mouse/elantech.c8
-rw-r--r--drivers/input/mouse/vmmouse.c22
-rw-r--r--drivers/input/touchscreen/sun4i-ts.c9
-rw-r--r--drivers/input/touchscreen/wacom_w8001.c11
-rw-r--r--drivers/iommu/amd_iommu_init.c2
-rw-r--r--drivers/iommu/arm-smmu-v3.c19
-rw-r--r--drivers/iommu/arm-smmu.c8
-rw-r--r--drivers/iommu/intel-iommu.c335
-rw-r--r--drivers/iommu/iova.c421
-rw-r--r--drivers/iommu/rockchip-iommu.c2
-rw-r--r--drivers/irqchip/irq-clps711x.c2
-rw-r--r--drivers/irqchip/irq-gic-v3-its.c49
-rw-r--r--drivers/irqchip/irq-gic-v3.c2
-rw-r--r--drivers/irqchip/irq-gic.c2
-rw-r--r--drivers/irqchip/irq-hip04.c2
-rw-r--r--drivers/irqchip/irq-mips-gic.c22
-rw-r--r--drivers/irqchip/irq-pic32-evic.c2
-rw-r--r--drivers/irqchip/spear-shirq.c2
-rw-r--r--drivers/leds/led-core.c9
-rw-r--r--drivers/leds/leds-pwm.c11
-rw-r--r--drivers/leds/trigger/ledtrig-heartbeat.c31
-rw-r--r--drivers/mcb/mcb-core.c17
-rw-r--r--drivers/md/bcache/alloc.c2
-rw-r--r--drivers/md/bcache/btree.c2
-rw-r--r--drivers/md/bcache/writeback.c3
-rw-r--r--drivers/media/i2c/adp1653.c10
-rw-r--r--drivers/media/platform/s5p-tv/mixer_drv.c2
-rw-r--r--drivers/media/usb/dvb-usb-v2/af9015.c2
-rw-r--r--drivers/media/usb/uvc/uvc_v4l2.c97
-rw-r--r--drivers/media/v4l2-core/v4l2-mc.c2
-rw-r--r--drivers/memory/Kconfig1
-rw-r--r--drivers/memory/fsl_ifc.c36
-rw-r--r--drivers/memory/omap-gpmc.c659
-rw-r--r--drivers/mfd/max77620.c2
-rw-r--r--drivers/mfd/twl4030-irq.c2
-rw-r--r--drivers/misc/mei/client.c2
-rw-r--r--drivers/mmc/card/block.c24
-rw-r--r--drivers/mmc/core/core.c4
-rw-r--r--drivers/mmc/core/host.c24
-rw-r--r--drivers/mmc/core/mmc.c4
-rw-r--r--drivers/mmc/host/dw_mmc-rockchip.c72
-rw-r--r--drivers/mmc/host/dw_mmc.c12
-rw-r--r--drivers/mmc/host/sdhci-acpi.c13
-rw-r--r--drivers/mmc/host/sdhci-esdhc-imx.c2
-rw-r--r--drivers/mmc/host/sdhci-of-at91.c2
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c5
-rw-r--r--drivers/mmc/host/sdhci.c4
-rw-r--r--drivers/mmc/host/sunxi-mmc.c9
-rw-r--r--drivers/mtd/chips/Kconfig1
-rw-r--r--drivers/mtd/devices/bcm47xxsflash.c29
-rw-r--r--drivers/mtd/devices/bcm47xxsflash.h3
-rw-r--r--drivers/mtd/devices/docg3.c46
-rw-r--r--drivers/mtd/devices/m25p80.c22
-rw-r--r--drivers/mtd/devices/pmc551.c2
-rw-r--r--drivers/mtd/maps/ck804xrom.c4
-rw-r--r--drivers/mtd/maps/esb2rom.c4
-rw-r--r--drivers/mtd/maps/ichxrom.c4
-rw-r--r--drivers/mtd/maps/uclinux.c27
-rw-r--r--drivers/mtd/mtdchar.c123
-rw-r--r--drivers/mtd/mtdconcat.c2
-rw-r--r--drivers/mtd/mtdcore.c360
-rw-r--r--drivers/mtd/mtdpart.c23
-rw-r--r--drivers/mtd/nand/ams-delta.c1
-rw-r--r--drivers/mtd/nand/atmel_nand.c350
-rw-r--r--drivers/mtd/nand/atmel_nand_nfc.h3
-rw-r--r--drivers/mtd/nand/au1550nd.c1
-rw-r--r--drivers/mtd/nand/bf5xx_nand.c52
-rw-r--r--drivers/mtd/nand/brcmnand/brcmnand.c290
-rw-r--r--drivers/mtd/nand/cafe_nand.c44
-rw-r--r--drivers/mtd/nand/cmx270_nand.c1
-rw-r--r--drivers/mtd/nand/davinci_nand.c210
-rw-r--r--drivers/mtd/nand/denali.c50
-rw-r--r--drivers/mtd/nand/diskonchip.c60
-rw-r--r--drivers/mtd/nand/docg4.c33
-rw-r--r--drivers/mtd/nand/fsl_elbc_nand.c84
-rw-r--r--drivers/mtd/nand/fsl_ifc_nand.c317
-rw-r--r--drivers/mtd/nand/fsl_upm.c1
-rw-r--r--drivers/mtd/nand/fsmc_nand.c332
-rw-r--r--drivers/mtd/nand/gpio.c1
-rw-r--r--drivers/mtd/nand/gpmi-nand/gpmi-nand.c161
-rw-r--r--drivers/mtd/nand/hisi504_nand.c40
-rw-r--r--drivers/mtd/nand/jz4740_nand.c3
-rw-r--r--drivers/mtd/nand/jz4780_bch.c1
-rw-r--r--drivers/mtd/nand/jz4780_nand.c21
-rw-r--r--drivers/mtd/nand/lpc32xx_mlc.c51
-rw-r--r--drivers/mtd/nand/lpc32xx_slc.c83
-rw-r--r--drivers/mtd/nand/mpc5121_nfc.c1
-rw-r--r--drivers/mtd/nand/mxc_nand.c257
-rw-r--r--drivers/mtd/nand/nand_base.c637
-rw-r--r--drivers/mtd/nand/nand_bch.c48
-rw-r--r--drivers/mtd/nand/nandsim.c10
-rw-r--r--drivers/mtd/nand/nuc900_nand.c1
-rw-r--r--drivers/mtd/nand/omap2.c448
-rw-r--r--drivers/mtd/nand/orion_nand.c1
-rw-r--r--drivers/mtd/nand/pasemi_nand.c16
-rw-r--r--drivers/mtd/nand/plat_nand.c1
-rw-r--r--drivers/mtd/nand/pxa3xx_nand.c132
-rw-r--r--drivers/mtd/nand/qcom_nandc.c88
-rw-r--r--drivers/mtd/nand/s3c2410.c36
-rw-r--r--drivers/mtd/nand/sh_flctl.c115
-rw-r--r--drivers/mtd/nand/sharpsl.c2
-rw-r--r--drivers/mtd/nand/sm_common.c93
-rw-r--r--drivers/mtd/nand/socrates_nand.c1
-rw-r--r--drivers/mtd/nand/sunxi_nand.c600
-rw-r--r--drivers/mtd/nand/vf610_nfc.c35
-rw-r--r--drivers/mtd/onenand/onenand_base.c235
-rw-r--r--drivers/mtd/spi-nor/spi-nor.c1
-rw-r--r--drivers/mtd/ubi/build.c16
-rw-r--r--drivers/mtd/ubi/debug.c3
-rw-r--r--drivers/mtd/ubi/eba.c69
-rw-r--r--drivers/mtd/ubi/fastmap.c1
-rw-r--r--drivers/mtd/ubi/kapi.c10
-rw-r--r--drivers/mtd/ubi/ubi.h2
-rw-r--r--drivers/mtd/ubi/vmt.c2
-rw-r--r--drivers/mtd/ubi/wl.c2
-rw-r--r--drivers/net/bonding/bond_3ad.c64
-rw-r--r--drivers/net/can/at91_can.c5
-rw-r--r--drivers/net/can/c_can/c_can.c38
-rw-r--r--drivers/net/can/dev.c9
-rw-r--r--drivers/net/can/usb/Kconfig5
-rw-r--r--drivers/net/can/usb/gs_usb.c14
-rw-r--r--drivers/net/can/usb/kvaser_usb.c8
-rw-r--r--drivers/net/ethernet/amd/au1000_eth.c4
-rw-r--r--drivers/net/ethernet/arc/emac_mdio.c2
-rw-r--r--drivers/net/ethernet/atheros/alx/main.c15
-rw-r--r--drivers/net/ethernet/broadcom/bgmac.c8
-rw-r--r--drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c168
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c46
-rw-r--r--drivers/net/ethernet/cavium/thunder/nic_main.c16
-rw-r--r--drivers/net/ethernet/cavium/thunder/thunder_bgx.c91
-rw-r--r--drivers/net/ethernet/cavium/thunder/thunder_bgx.h2
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h1
-rw-r--r--drivers/net/ethernet/ethoc.c7
-rw-r--r--drivers/net/ethernet/ezchip/nps_enet.c4
-rw-r--r--drivers/net/ethernet/freescale/fec_main.c16
-rw-r--r--drivers/net/ethernet/freescale/fman/fman.c2
-rw-r--r--drivers/net/ethernet/freescale/fman/fman_muram.c4
-rw-r--r--drivers/net/ethernet/freescale/fman/fman_muram.h4
-rw-r--r--drivers/net/ethernet/freescale/gianfar.c3
-rw-r--r--drivers/net/ethernet/hisilicon/hns/hns_ethtool.c11
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c14
-rw-r--r--drivers/net/ethernet/intel/e1000e/netdev.c15
-rw-r--r--drivers/net/ethernet/marvell/mvneta_bm.c1
-rw-r--r--drivers/net/ethernet/mediatek/mtk_eth_soc.c101
-rw-r--r--drivers/net/ethernet/mediatek/mtk_eth_soc.h3
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/cmd.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_ethtool.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_netdev.c63
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_port.c18
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_tx.c8
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/main.c6
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/mlx4_en.h3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/cmd.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c34
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_main.c40
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_rx.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_stats.h228
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tx.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.c69
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fs_core.c40
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/main.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/qp.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/vport.c38
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/vxlan.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/wq.c15
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum.c209
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum.h5
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/switchx2.c5
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_net_common.c6
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_dcbx.c5
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_dev.c52
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_hsi.h1
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_l2.c8
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_main.c64
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_spq.c31
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_sriov.h4
-rw-r--r--drivers/net/ethernet/qlogic/qede/qede_ethtool.c5
-rw-r--r--drivers/net/ethernet/qlogic/qede/qede_main.c35
-rw-r--r--drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c2
-rw-r--r--drivers/net/ethernet/qlogic/qlge/qlge_main.c3
-rw-r--r--drivers/net/ethernet/sfc/ef10.c16
-rw-r--r--drivers/net/ethernet/sfc/efx.c32
-rw-r--r--drivers/net/ethernet/sfc/farch.c3
-rw-r--r--drivers/net/ethernet/sfc/mcdi_port.c7
-rw-r--r--drivers/net/ethernet/sfc/net_driver.h12
-rw-r--r--drivers/net/ethernet/sfc/rx.c102
-rw-r--r--drivers/net/ethernet/smsc/smsc911x.c2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c6
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c2
-rw-r--r--drivers/net/ethernet/ti/cpsw.c6
-rw-r--r--drivers/net/ethernet/tile/tilegx.c6
-rw-r--r--drivers/net/fddi/skfp/Makefile2
-rw-r--r--drivers/net/geneve.c22
-rw-r--r--drivers/net/macsec.c49
-rw-r--r--drivers/net/phy/fixed_phy.c22
-rw-r--r--drivers/net/phy/marvell.c82
-rw-r--r--drivers/net/phy/smsc.c17
-rw-r--r--drivers/net/team/team.c11
-rw-r--r--drivers/net/usb/pegasus.c2
-rw-r--r--drivers/net/usb/r8152.c37
-rw-r--r--drivers/net/usb/smsc95xx.c51
-rw-r--r--drivers/net/virtio_net.c18
-rw-r--r--drivers/net/vmxnet3/vmxnet3_drv.c2
-rw-r--r--drivers/net/vmxnet3/vmxnet3_int.h4
-rw-r--r--drivers/net/vrf.c4
-rw-r--r--drivers/net/vxlan.c61
-rw-r--r--drivers/net/wireless/ath/ath10k/core.c2
-rw-r--r--drivers/net/wireless/ath/ath10k/htt_rx.c1
-rw-r--r--drivers/net/wireless/ath/ath10k/mac.c2
-rw-r--r--drivers/net/wireless/ath/ath9k/reg.h8
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c16
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c8
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c4
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/scan.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/sta.c16
-rw-r--r--drivers/net/wireless/mac80211_hwsim.c1
-rw-r--r--drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c2
-rw-r--r--drivers/net/wireless/realtek/rtlwifi/core.c6
-rw-r--r--drivers/net/wireless/ti/wlcore/spi.c4
-rw-r--r--drivers/nvdimm/pfn_devs.c51
-rw-r--r--drivers/nvdimm/pmem.c10
-rw-r--r--drivers/nvme/host/core.c37
-rw-r--r--drivers/nvme/host/nvme.h1
-rw-r--r--drivers/nvme/host/pci.c32
-rw-r--r--drivers/nvmem/core.c22
-rw-r--r--drivers/of/Makefile1
-rw-r--r--drivers/of/fdt.c15
-rw-r--r--drivers/of/irq.c19
-rw-r--r--drivers/of/of_mtd.c119
-rw-r--r--drivers/of/of_reserved_mem.c11
-rw-r--r--drivers/pci/vc.c4
-rw-r--r--drivers/perf/arm_pmu.c14
-rw-r--r--drivers/phy/phy-bcm-ns-usb2.c4
-rw-r--r--drivers/phy/phy-exynos-mipi-video.c6
-rw-r--r--drivers/phy/phy-miphy28lp.c3
-rw-r--r--drivers/phy/phy-rcar-gen3-usb2.c14
-rw-r--r--drivers/phy/phy-rockchip-dp.c2
-rw-r--r--drivers/phy/phy-stih407-usb.c4
-rw-r--r--drivers/phy/phy-sun4i-usb.c14
-rw-r--r--drivers/phy/phy-ti-pipe3.c15
-rw-r--r--drivers/phy/phy-twl4030-usb.c14
-rw-r--r--drivers/pinctrl/Makefile2
-rw-r--r--drivers/pinctrl/freescale/pinctrl-imx.c4
-rw-r--r--drivers/pinctrl/intel/pinctrl-baytrail.c16
-rw-r--r--drivers/pinctrl/mediatek/pinctrl-mtk-common.c5
-rw-r--r--drivers/pinctrl/nomadik/pinctrl-nomadik.c2
-rw-r--r--drivers/pinctrl/pinctrl-single.c3
-rw-r--r--drivers/pinctrl/tegra/Makefile2
-rw-r--r--drivers/platform/chrome/Kconfig10
-rw-r--r--drivers/platform/chrome/Makefile15
-rw-r--r--drivers/platform/chrome/chromeos_laptop.c22
-rw-r--r--drivers/platform/chrome/chromeos_pstore.c55
-rw-r--r--drivers/platform/chrome/cros_ec_dev.c7
-rw-r--r--drivers/platform/chrome/cros_ec_lightbar.c10
-rw-r--r--drivers/platform/chrome/cros_ec_proto.c4
-rw-r--r--drivers/platform/chrome/cros_kbd_led_backlight.c122
-rw-r--r--drivers/platform/x86/Kconfig20
-rw-r--r--drivers/platform/x86/Makefile1
-rw-r--r--drivers/platform/x86/asus-laptop.c15
-rw-r--r--drivers/platform/x86/asus-wmi.c5
-rw-r--r--drivers/platform/x86/dell-rbtn.c56
-rw-r--r--drivers/platform/x86/fujitsu-laptop.c63
-rw-r--r--drivers/platform/x86/ideapad-laptop.c21
-rw-r--r--drivers/platform/x86/intel_menlow.c49
-rw-r--r--drivers/platform/x86/intel_pmc_core.c200
-rw-r--r--drivers/platform/x86/intel_pmc_core.h51
-rw-r--r--drivers/platform/x86/intel_telemetry_core.c6
-rw-r--r--drivers/platform/x86/intel_telemetry_pltdrv.c2
-rw-r--r--drivers/platform/x86/sony-laptop.c3
-rw-r--r--drivers/platform/x86/surfacepro3_button.c9
-rw-r--r--drivers/platform/x86/thinkpad_acpi.c130
-rw-r--r--drivers/power/power_supply_core.c27
-rw-r--r--drivers/power/tps65217_charger.c6
-rw-r--r--drivers/ptp/ptp_chardev.c12
-rw-r--r--drivers/pwm/core.c225
-rw-r--r--drivers/pwm/pwm-atmel-hlcdc.c2
-rw-r--r--drivers/pwm/pwm-crc.c2
-rw-r--r--drivers/pwm/pwm-lpc18xx-sct.c2
-rw-r--r--drivers/pwm/pwm-omap-dmtimer.c2
-rw-r--r--drivers/pwm/pwm-rcar.c2
-rw-r--r--drivers/pwm/pwm-sun4i.c3
-rw-r--r--drivers/pwm/sysfs.c70
-rw-r--r--drivers/regulator/anatop-regulator.c2
-rw-r--r--drivers/regulator/max77620-regulator.c7
-rw-r--r--drivers/regulator/qcom_smd-regulator.c15
-rw-r--r--drivers/regulator/tps51632-regulator.c9
-rw-r--r--drivers/s390/block/dcssblk.c4
-rw-r--r--drivers/scsi/53c700.c4
-rw-r--r--drivers/scsi/aacraid/aacraid.h5
-rw-r--r--drivers/scsi/aacraid/linit.c11
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_scsih.c3
-rw-r--r--drivers/scsi/qla2xxx/Kconfig9
-rw-r--r--drivers/scsi/qla2xxx/qla_target.c56
-rw-r--r--drivers/scsi/qla2xxx/qla_target.h4
-rw-r--r--drivers/scsi/qla2xxx/tcm_qla2xxx.c59
-rw-r--r--drivers/scsi/qla2xxx/tcm_qla2xxx.h1
-rw-r--r--drivers/scsi/scsi_devinfo.c1
-rw-r--r--drivers/scsi/scsi_error.c4
-rw-r--r--drivers/scsi/scsi_lib.c7
-rw-r--r--drivers/scsi/sd.c17
-rw-r--r--drivers/scsi/sd.h5
-rw-r--r--drivers/soc/mediatek/mtk-pmic-wrap.c6
-rw-r--r--drivers/spi/Kconfig21
-rw-r--r--drivers/spi/Makefile2
-rw-r--r--drivers/spi/spi-axi-spi-engine.c1
-rw-r--r--drivers/spi/spi-bcm53xx.c78
-rw-r--r--drivers/spi/spi-cadence.c244
-rw-r--r--drivers/spi/spi-davinci.c76
-rw-r--r--drivers/spi/spi-dln2.c2
-rw-r--r--drivers/spi/spi-dw-pci.c2
-rw-r--r--drivers/spi/spi-ep93xx.c2
-rw-r--r--drivers/spi/spi-fsl-dspi.c7
-rw-r--r--drivers/spi/spi-fsl-espi.c30
-rw-r--r--drivers/spi/spi-octeon.c17
-rw-r--r--drivers/spi/spi-omap2-mcspi.c83
-rw-r--r--drivers/spi/spi-pic32-sqi.c727
-rw-r--r--drivers/spi/spi-pic32.c878
-rw-r--r--drivers/spi/spi-pxa2xx-dma.c28
-rw-r--r--drivers/spi/spi-pxa2xx-pci.c4
-rw-r--r--drivers/spi/spi-pxa2xx.c15
-rw-r--r--drivers/spi/spi-pxa2xx.h3
-rw-r--r--drivers/spi/spi-qup.c15
-rw-r--r--drivers/spi/spi-rockchip.c13
-rw-r--r--drivers/spi/spi-st-ssc4.c8
-rw-r--r--drivers/spi/spi-sun4i.c23
-rw-r--r--drivers/spi/spi-sun6i.c10
-rw-r--r--drivers/spi/spi-ti-qspi.c7
-rw-r--r--drivers/spi/spi-zynqmp-gqspi.c3
-rw-r--r--drivers/spi/spi.c7
-rw-r--r--drivers/staging/Kconfig2
-rw-r--r--drivers/staging/Makefile1
-rw-r--r--drivers/staging/iio/accel/sca3000_core.c2
-rw-r--r--drivers/staging/iio/adc/ad7606_spi.c2
-rw-r--r--drivers/staging/iio/impedance-analyzer/ad5933.c6
-rw-r--r--drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c7
-rw-r--r--drivers/staging/lustre/lustre/llite/llite_internal.h4
-rw-r--r--drivers/staging/lustre/lustre/llite/xattr.c6
-rw-r--r--drivers/staging/mt29f_spinand/mt29f_spinand.c49
-rw-r--r--drivers/staging/rdma/Kconfig27
-rw-r--r--drivers/staging/rdma/Makefile2
-rw-r--r--drivers/staging/rdma/hfi1/TODO6
-rw-r--r--drivers/staging/rdma/hfi1/diag.c1925
-rw-r--r--drivers/staging/rdma/hfi1/eprom.c471
-rw-r--r--drivers/staging/rtl8188eu/core/rtw_efuse.c2
-rw-r--r--drivers/staging/rtl8188eu/hal/usb_halinit.c3
-rw-r--r--drivers/target/iscsi/Kconfig2
-rw-r--r--drivers/target/iscsi/Makefile1
-rw-r--r--drivers/target/iscsi/cxgbit/Kconfig7
-rw-r--r--drivers/target/iscsi/cxgbit/Makefile6
-rw-r--r--drivers/target/iscsi/cxgbit/cxgbit.h353
-rw-r--r--drivers/target/iscsi/cxgbit/cxgbit_cm.c2086
-rw-r--r--drivers/target/iscsi/cxgbit/cxgbit_ddp.c325
-rw-r--r--drivers/target/iscsi/cxgbit/cxgbit_lro.h72
-rw-r--r--drivers/target/iscsi/cxgbit/cxgbit_main.c702
-rw-r--r--drivers/target/iscsi/cxgbit/cxgbit_target.c1561
-rw-r--r--drivers/target/iscsi/iscsi_target.c701
-rw-r--r--drivers/target/iscsi/iscsi_target_configfs.c158
-rw-r--r--drivers/target/iscsi/iscsi_target_datain_values.c1
-rw-r--r--drivers/target/iscsi/iscsi_target_erl0.c2
-rw-r--r--drivers/target/iscsi/iscsi_target_login.c17
-rw-r--r--drivers/target/iscsi/iscsi_target_nego.c19
-rw-r--r--drivers/target/iscsi/iscsi_target_parameters.c1
-rw-r--r--drivers/target/iscsi/iscsi_target_util.c5
-rw-r--r--drivers/target/loopback/tcm_loop.c12
-rw-r--r--drivers/target/sbp/sbp_target.c12
-rw-r--r--drivers/target/target_core_alua.c6
-rw-r--r--drivers/target/target_core_configfs.c70
-rw-r--r--drivers/target/target_core_internal.h6
-rw-r--r--drivers/target/target_core_pr.c2
-rw-r--r--drivers/target/target_core_rd.c4
-rw-r--r--drivers/target/target_core_tpg.c83
-rw-r--r--drivers/target/target_core_transport.c26
-rw-r--r--drivers/target/tcm_fc/tcm_fc.h1
-rw-r--r--drivers/target/tcm_fc/tfc_conf.c1
-rw-r--r--drivers/target/tcm_fc/tfc_sess.c12
-rw-r--r--drivers/thermal/Kconfig31
-rw-r--r--drivers/thermal/Makefile4
-rw-r--r--drivers/thermal/cpu_cooling.c16
-rw-r--r--drivers/thermal/gov_bang_bang.c8
-rw-r--r--drivers/thermal/hisi_thermal.c45
-rw-r--r--drivers/thermal/int340x_thermal/int3406_thermal.c2
-rw-r--r--drivers/thermal/int340x_thermal/processor_thermal_device.c108
-rw-r--r--drivers/thermal/intel_powerclamp.c47
-rw-r--r--drivers/thermal/mtk_thermal.c12
-rw-r--r--drivers/thermal/of-thermal.c10
-rw-r--r--drivers/thermal/qcom-spmi-temp-alarm.c3
-rw-r--r--drivers/thermal/rcar_thermal.c2
-rw-r--r--drivers/thermal/rockchip_thermal.c280
-rw-r--r--drivers/thermal/tango_thermal.c109
-rw-r--r--drivers/thermal/tegra/Kconfig13
-rw-r--r--drivers/thermal/tegra/Makefile6
-rw-r--r--drivers/thermal/tegra/soctherm-fuse.c169
-rw-r--r--drivers/thermal/tegra/soctherm.c685
-rw-r--r--drivers/thermal/tegra/soctherm.h127
-rw-r--r--drivers/thermal/tegra/tegra124-soctherm.c196
-rw-r--r--drivers/thermal/tegra/tegra132-soctherm.c196
-rw-r--r--drivers/thermal/tegra/tegra210-soctherm.c197
-rw-r--r--drivers/thermal/tegra_soctherm.c476
-rw-r--r--drivers/thermal/thermal-generic-adc.c182
-rw-r--r--drivers/thermal/ti-soc-thermal/ti-thermal-common.c5
-rw-r--r--drivers/thermal/x86_pkg_temp_thermal.c2
-rw-r--r--drivers/tty/Kconfig11
-rw-r--r--drivers/tty/pty.c20
-rw-r--r--drivers/tty/serial/amba-pl011.c2
-rw-r--r--drivers/tty/serial/sprd_serial.c2
-rw-r--r--drivers/tty/vt/vt.c1
-rw-r--r--drivers/usb/common/usb-otg-fsm.c2
-rw-r--r--drivers/usb/core/hcd.c17
-rw-r--r--drivers/usb/core/quirks.c23
-rw-r--r--drivers/usb/dwc2/core.h27
-rw-r--r--drivers/usb/dwc2/gadget.c24
-rw-r--r--drivers/usb/dwc3/core.h1
-rw-r--r--drivers/usb/dwc3/dwc3-exynos.c19
-rw-r--r--drivers/usb/dwc3/dwc3-st.c16
-rw-r--r--drivers/usb/dwc3/gadget.c30
-rw-r--r--drivers/usb/gadget/composite.c21
-rw-r--r--drivers/usb/gadget/configfs.c1
-rw-r--r--drivers/usb/gadget/function/f_fs.c30
-rw-r--r--drivers/usb/gadget/function/f_printer.c8
-rw-r--r--drivers/usb/gadget/function/f_tcm.c31
-rw-r--r--drivers/usb/gadget/function/f_uac2.c13
-rw-r--r--drivers/usb/gadget/function/storage_common.c4
-rw-r--r--drivers/usb/gadget/legacy/inode.c17
-rw-r--r--drivers/usb/gadget/udc/udc-core.c12
-rw-r--r--drivers/usb/host/ehci-hcd.c9
-rw-r--r--drivers/usb/host/ehci-hub.c14
-rw-r--r--drivers/usb/host/ehci-msm.c14
-rw-r--r--drivers/usb/host/ehci-st.c6
-rw-r--r--drivers/usb/host/ehci-tegra.c16
-rw-r--r--drivers/usb/host/ohci-q.c3
-rw-r--r--drivers/usb/host/ohci-st.c6
-rw-r--r--drivers/usb/host/xhci-pci.c5
-rw-r--r--drivers/usb/host/xhci-plat.c3
-rw-r--r--drivers/usb/host/xhci-ring.c30
-rw-r--r--drivers/usb/host/xhci.c29
-rw-r--r--drivers/usb/musb/musb_core.c85
-rw-r--r--drivers/usb/musb/musb_core.h3
-rw-r--r--drivers/usb/musb/musb_gadget.c34
-rw-r--r--drivers/usb/musb/musb_host.c68
-rw-r--r--drivers/usb/musb/omap2430.c257
-rw-r--r--drivers/usb/musb/sunxi.c54
-rw-r--r--drivers/usb/phy/phy-twl6030-usb.c29
-rw-r--r--drivers/usb/serial/mos7720.c1
-rw-r--r--drivers/usb/storage/uas.c2
-rw-r--r--drivers/usb/usbip/vhci_hcd.c2
-rw-r--r--drivers/vfio/pci/vfio_pci.c55
-rw-r--r--drivers/vfio/pci/vfio_pci_config.c49
-rw-r--r--drivers/vfio/pci/vfio_pci_intrs.c6
-rw-r--r--drivers/vfio/pci/vfio_pci_private.h1
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c2
-rw-r--r--drivers/vfio/vfio_iommu_type1.c2
-rw-r--r--drivers/vhost/scsi.c12
-rw-r--r--drivers/video/backlight/lm3630a_bl.c9
-rw-r--r--drivers/video/backlight/lp855x_bl.c6
-rw-r--r--drivers/video/backlight/lp8788_bl.c6
-rw-r--r--drivers/video/backlight/pwm_bl.c14
-rw-r--r--drivers/video/fbdev/da8xx-fb.c4
-rw-r--r--drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c6
-rw-r--r--drivers/video/fbdev/ssd1307fb.c11
-rw-r--r--drivers/virtio/virtio_balloon.c20
-rw-r--r--drivers/watchdog/Kconfig10
-rw-r--r--drivers/watchdog/Makefile1
-rw-r--r--drivers/watchdog/cpwd.c4
-rw-r--r--drivers/watchdog/f71808e_wdt.c30
-rw-r--r--drivers/watchdog/imx2_wdt.c19
-rw-r--r--drivers/watchdog/jz4740_wdt.c4
-rw-r--r--drivers/watchdog/octeon-wdt-main.c2
-rw-r--r--drivers/watchdog/qcom-wdt.c7
-rw-r--r--drivers/watchdog/renesas_wdt.c213
-rw-r--r--drivers/watchdog/shwdt.c4
-rw-r--r--drivers/watchdog/sp5100_tco.c15
-rw-r--r--drivers/watchdog/watchdog_core.c2
-rw-r--r--drivers/watchdog/watchdog_dev.c1
-rw-r--r--drivers/xen/Makefile1
-rw-r--r--drivers/xen/balloon.c28
-rw-r--r--drivers/xen/events/events_base.c6
-rw-r--r--drivers/xen/gntdev.c2
-rw-r--r--drivers/xen/xen-pciback/conf_space.c6
-rw-r--r--drivers/xen/xen-pciback/conf_space_header.c18
-rw-r--r--drivers/xen/xen-scsiback.c11
-rw-r--r--fs/9p/acl.c6
-rw-r--r--fs/9p/vfs_file.c6
-rw-r--r--fs/9p/xattr.c5
-rw-r--r--fs/Kconfig1
-rw-r--r--fs/affs/super.c5
-rw-r--r--fs/afs/write.c4
-rw-r--r--fs/autofs4/autofs_i.h8
-rw-r--r--fs/autofs4/expire.c27
-rw-r--r--fs/autofs4/root.c2
-rw-r--r--fs/autofs4/waitq.c7
-rw-r--r--fs/bad_inode.c4
-rw-r--r--fs/binfmt_aout.c19
-rw-r--r--fs/binfmt_elf.c13
-rw-r--r--fs/binfmt_elf_fdpic.c2
-rw-r--r--fs/binfmt_flat.c6
-rw-r--r--fs/block_dev.c114
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/btrfs_inode.h2
-rw-r--r--fs/btrfs/check-integrity.c4
-rw-r--r--fs/btrfs/ctree.c33
-rw-r--r--fs/btrfs/ctree.h8
-rw-r--r--fs/btrfs/delayed-inode.c27
-rw-r--r--fs/btrfs/delayed-inode.h10
-rw-r--r--fs/btrfs/delayed-ref.h2
-rw-r--r--fs/btrfs/dev-replace.c2
-rw-r--r--fs/btrfs/disk-io.c68
-rw-r--r--fs/btrfs/disk-io.h2
-rw-r--r--fs/btrfs/extent-tree.c81
-rw-r--r--fs/btrfs/extent_io.c136
-rw-r--r--fs/btrfs/extent_io.h38
-rw-r--r--fs/btrfs/extent_map.c2
-rw-r--r--fs/btrfs/file-item.c2
-rw-r--r--fs/btrfs/file.c75
-rw-r--r--fs/btrfs/free-space-cache.c20
-rw-r--r--fs/btrfs/free-space-cache.h2
-rw-r--r--fs/btrfs/hash.c5
-rw-r--r--fs/btrfs/hash.h1
-rw-r--r--fs/btrfs/inode.c62
-rw-r--r--fs/btrfs/ioctl.c30
-rw-r--r--fs/btrfs/ordered-data.c9
-rw-r--r--fs/btrfs/ordered-data.h4
-rw-r--r--fs/btrfs/qgroup.c24
-rw-r--r--fs/btrfs/raid56.c6
-rw-r--r--fs/btrfs/reada.c2
-rw-r--r--fs/btrfs/relocation.c19
-rw-r--r--fs/btrfs/root-tree.c4
-rw-r--r--fs/btrfs/scrub.c61
-rw-r--r--fs/btrfs/send.c6
-rw-r--r--fs/btrfs/struct-funcs.c2
-rw-r--r--fs/btrfs/super.c69
-rw-r--r--fs/btrfs/tests/btrfs-tests.c8
-rw-r--r--fs/btrfs/tests/btrfs-tests.h27
-rw-r--r--fs/btrfs/tests/extent-buffer-tests.c13
-rw-r--r--fs/btrfs/tests/extent-io-tests.c92
-rw-r--r--fs/btrfs/tests/free-space-tests.c83
-rw-r--r--fs/btrfs/tests/free-space-tree-tests.c30
-rw-r--r--fs/btrfs/tests/inode-tests.c346
-rw-r--r--fs/btrfs/tests/qgroup-tests.c113
-rw-r--r--fs/btrfs/transaction.c12
-rw-r--r--fs/btrfs/transaction.h4
-rw-r--r--fs/btrfs/tree-log.c14
-rw-r--r--fs/btrfs/ulist.c2
-rw-r--r--fs/btrfs/volumes.c161
-rw-r--r--fs/btrfs/xattr.c12
-rw-r--r--fs/cachefiles/interface.c2
-rw-r--r--fs/ceph/addr.c220
-rw-r--r--fs/ceph/cache.c143
-rw-r--r--fs/ceph/cache.h44
-rw-r--r--fs/ceph/caps.c74
-rw-r--r--fs/ceph/debugfs.c2
-rw-r--r--fs/ceph/dir.c376
-rw-r--r--fs/ceph/export.c10
-rw-r--r--fs/ceph/file.c116
-rw-r--r--fs/ceph/inode.c159
-rw-r--r--fs/ceph/ioctl.c14
-rw-r--r--fs/ceph/mds_client.c140
-rw-r--r--fs/ceph/mds_client.h17
-rw-r--r--fs/ceph/mdsmap.c43
-rw-r--r--fs/ceph/super.c47
-rw-r--r--fs/ceph/super.h16
-rw-r--r--fs/ceph/xattr.c32
-rw-r--r--fs/cifs/cifs_unicode.c33
-rw-r--r--fs/cifs/cifs_unicode.h2
-rw-r--r--fs/cifs/cifsfs.c3
-rw-r--r--fs/cifs/cifsglob.h1
-rw-r--r--fs/cifs/connect.c4
-rw-r--r--fs/cifs/file.c14
-rw-r--r--fs/cifs/ntlmssp.h2
-rw-r--r--fs/cifs/sess.c80
-rw-r--r--fs/cifs/smb2pdu.c37
-rw-r--r--fs/cifs/xattr.c9
-rw-r--r--fs/compat.c4
-rw-r--r--fs/coredump.c4
-rw-r--r--fs/dax.c852
-rw-r--r--fs/dcache.c82
-rw-r--r--fs/debugfs/file.c7
-rw-r--r--fs/devpts/inode.c191
-rw-r--r--fs/direct-io.c14
-rw-r--r--fs/ecryptfs/crypto.c9
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h4
-rw-r--r--fs/ecryptfs/inode.c7
-rw-r--r--fs/ecryptfs/kthread.c13
-rw-r--r--fs/ecryptfs/mmap.c3
-rw-r--r--fs/ext2/file.c4
-rw-r--r--fs/ext2/inode.c12
-rw-r--r--fs/ext2/super.c11
-rw-r--r--fs/ext2/xattr_security.c7
-rw-r--r--fs/ext2/xattr_trusted.c7
-rw-r--r--fs/ext2/xattr_user.c9
-rw-r--r--fs/ext4/balloc.c3
-rw-r--r--fs/ext4/dir.c5
-rw-r--r--fs/ext4/ext4.h20
-rw-r--r--fs/ext4/ext4_jbd2.h15
-rw-r--r--fs/ext4/extents.c20
-rw-r--r--fs/ext4/extents_status.c2
-rw-r--r--fs/ext4/file.c6
-rw-r--r--fs/ext4/ialloc.c59
-rw-r--r--fs/ext4/indirect.c127
-rw-r--r--fs/ext4/inline.c2
-rw-r--r--fs/ext4/inode.c323
-rw-r--r--fs/ext4/ioctl.c2
-rw-r--r--fs/ext4/mballoc.c12
-rw-r--r--fs/ext4/mmp.c4
-rw-r--r--fs/ext4/move_extent.c2
-rw-r--r--fs/ext4/namei.c9
-rw-r--r--fs/ext4/page-io.c2
-rw-r--r--fs/ext4/resize.c2
-rw-r--r--fs/ext4/super.c15
-rw-r--r--fs/ext4/xattr_security.c7
-rw-r--r--fs/ext4/xattr_trusted.c7
-rw-r--r--fs/ext4/xattr_user.c9
-rw-r--r--fs/f2fs/xattr.c12
-rw-r--r--fs/fscache/page.c2
-rw-r--r--fs/fuse/dir.c10
-rw-r--r--fs/fuse/fuse_i.h9
-rw-r--r--fs/fuse/inode.c19
-rw-r--r--fs/gfs2/dir.c15
-rw-r--r--fs/gfs2/xattr.c6
-rw-r--r--fs/hfs/attr.c6
-rw-r--r--fs/hfs/hfs_fs.h2
-rw-r--r--fs/hfsplus/xattr.c12
-rw-r--r--fs/hfsplus/xattr.h2
-rw-r--r--fs/hfsplus/xattr_security.c7
-rw-r--r--fs/hfsplus/xattr_trusted.c7
-rw-r--r--fs/hfsplus/xattr_user.c7
-rw-r--r--fs/hpfs/super.c42
-rw-r--r--fs/internal.h1
-rw-r--r--fs/jbd2/commit.c4
-rw-r--r--fs/jbd2/journal.c35
-rw-r--r--fs/jbd2/transaction.c22
-rw-r--r--fs/jffs2/security.c7
-rw-r--r--fs/jffs2/xattr_trusted.c7
-rw-r--r--fs/jffs2/xattr_user.c7
-rw-r--r--fs/jfs/xattr.c14
-rw-r--r--fs/kernfs/inode.c11
-rw-r--r--fs/kernfs/kernfs-internal.h3
-rw-r--r--fs/libfs.c118
-rw-r--r--fs/lockd/svc.c13
-rw-r--r--fs/locks.c2
-rw-r--r--fs/namei.c273
-rw-r--r--fs/namespace.c11
-rw-r--r--fs/nfs/callback_proc.c9
-rw-r--r--fs/nfs/callback_xdr.c17
-rw-r--r--fs/nfs/delegation.c9
-rw-r--r--fs/nfs/delegation.h2
-rw-r--r--fs/nfs/dir.c11
-rw-r--r--fs/nfs/direct.c27
-rw-r--r--fs/nfs/filelayout/filelayout.c6
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c200
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.h17
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c119
-rw-r--r--fs/nfs/inode.c1
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/nfs42.h1
-rw-r--r--fs/nfs/nfs42proc.c107
-rw-r--r--fs/nfs/nfs42xdr.c146
-rw-r--r--fs/nfs/nfs4_fs.h12
-rw-r--r--fs/nfs/nfs4file.c23
-rw-r--r--fs/nfs/nfs4proc.c216
-rw-r--r--fs/nfs/nfs4state.c20
-rw-r--r--fs/nfs/nfs4trace.h10
-rw-r--r--fs/nfs/nfs4xdr.c43
-rw-r--r--fs/nfs/pagelist.c6
-rw-r--r--fs/nfs/pnfs.c355
-rw-r--r--fs/nfs/pnfs.h17
-rw-r--r--fs/nfs/pnfs_nfs.c68
-rw-r--r--fs/nfs/read.c4
-rw-r--r--fs/nfs/super.c9
-rw-r--r--fs/nfs/write.c64
-rw-r--r--fs/nfsd/blocklayout.c2
-rw-r--r--fs/nfsd/nfs2acl.c20
-rw-r--r--fs/nfsd/nfs3acl.c16
-rw-r--r--fs/nfsd/nfs3xdr.c2
-rw-r--r--fs/nfsd/nfs4acl.c16
-rw-r--r--fs/nfsd/nfs4callback.c18
-rw-r--r--fs/nfsd/nfs4layouts.c2
-rw-r--r--fs/nfsd/nfs4state.c75
-rw-r--r--fs/nfsd/state.h7
-rw-r--r--fs/nilfs2/the_nilfs.c2
-rw-r--r--fs/ocfs2/Makefile2
-rw-r--r--fs/ocfs2/buffer_head_io.c5
-rw-r--r--fs/ocfs2/cluster/heartbeat.c180
-rw-r--r--fs/ocfs2/cluster/tcp_internal.h5
-rw-r--r--fs/ocfs2/inode.c7
-rw-r--r--fs/ocfs2/journal.h2
-rw-r--r--fs/ocfs2/xattr.c23
-rw-r--r--fs/orangefs/xattr.c10
-rw-r--r--fs/overlayfs/copy_up.c26
-rw-r--r--fs/overlayfs/dir.c78
-rw-r--r--fs/overlayfs/inode.c60
-rw-r--r--fs/overlayfs/overlayfs.h6
-rw-r--r--fs/overlayfs/readdir.c18
-rw-r--r--fs/overlayfs/super.c39
-rw-r--r--fs/posix_acl.c42
-rw-r--r--fs/proc/root.c7
-rw-r--r--fs/readdir.c16
-rw-r--r--fs/reiserfs/super.c9
-rw-r--r--fs/reiserfs/xattr_security.c9
-rw-r--r--fs/reiserfs/xattr_trusted.c9
-rw-r--r--fs/reiserfs/xattr_user.c9
-rw-r--r--fs/ubifs/debug.c2
-rw-r--r--fs/ubifs/file.c24
-rw-r--r--fs/ubifs/xattr.c7
-rw-r--r--fs/udf/partition.c13
-rw-r--r--fs/udf/super.c22
-rw-r--r--fs/udf/udf_sb.h5
-rw-r--r--fs/xattr.c13
-rw-r--r--fs/xfs/kmem.c26
-rw-r--r--fs/xfs/kmem.h2
-rw-r--r--fs/xfs/libxfs/xfs_attr.c58
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c22
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c9
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c99
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h1
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h5
-rw-r--r--fs/xfs/libxfs/xfs_sb.c8
-rw-r--r--fs/xfs/libxfs/xfs_shared.h102
-rw-r--r--fs/xfs/xfs_aops.c353
-rw-r--r--fs/xfs/xfs_aops.h15
-rw-r--r--fs/xfs/xfs_attr.h4
-rw-r--r--fs/xfs/xfs_attr_inactive.c16
-rw-r--r--fs/xfs/xfs_attr_list.c85
-rw-r--r--fs/xfs/xfs_bmap_util.c60
-rw-r--r--fs/xfs/xfs_buf.c12
-rw-r--r--fs/xfs/xfs_buf.h20
-rw-r--r--fs/xfs/xfs_buf_item.c121
-rw-r--r--fs/xfs/xfs_dquot.c9
-rw-r--r--fs/xfs/xfs_file.c15
-rw-r--r--fs/xfs/xfs_fsops.c14
-rw-r--r--fs/xfs/xfs_icache.c290
-rw-r--r--fs/xfs/xfs_inode.c167
-rw-r--r--fs/xfs/xfs_inode.h5
-rw-r--r--fs/xfs/xfs_inode_item.c6
-rw-r--r--fs/xfs/xfs_ioctl.c31
-rw-r--r--fs/xfs/xfs_iomap.c53
-rw-r--r--fs/xfs/xfs_iops.c117
-rw-r--r--fs/xfs/xfs_log.c62
-rw-r--r--fs/xfs/xfs_log.h3
-rw-r--r--fs/xfs/xfs_log_cil.c1
-rw-r--r--fs/xfs/xfs_log_priv.h1
-rw-r--r--fs/xfs/xfs_log_recover.c12
-rw-r--r--fs/xfs/xfs_mount.c23
-rw-r--r--fs/xfs/xfs_mount.h34
-rw-r--r--fs/xfs/xfs_pnfs.c7
-rw-r--r--fs/xfs/xfs_qm.c9
-rw-r--r--fs/xfs/xfs_qm_syscalls.c26
-rw-r--r--fs/xfs/xfs_rtalloc.c21
-rw-r--r--fs/xfs/xfs_super.c77
-rw-r--r--fs/xfs/xfs_symlink.c37
-rw-r--r--fs/xfs/xfs_sysfs.c291
-rw-r--r--fs/xfs/xfs_sysfs.h3
-rw-r--r--fs/xfs/xfs_trace.h16
-rw-r--r--fs/xfs/xfs_trans.c88
-rw-r--r--fs/xfs/xfs_trans.h8
-rw-r--r--fs/xfs/xfs_xattr.c26
-rw-r--r--include/acpi/video.h6
-rw-r--r--include/asm-generic/preempt.h4
-rw-r--r--include/asm-generic/qspinlock.h53
-rw-r--r--include/drm/drm_dp_dual_mode_helper.h92
-rw-r--r--include/drm/i915_pciids.h10
-rw-r--r--include/dt-bindings/thermal/tegra124-soctherm.h1
-rw-r--r--include/kvm/arm_arch_timer.h11
-rw-r--r--include/kvm/arm_pmu.h4
-rw-r--r--include/kvm/arm_vgic.h20
-rw-r--r--include/kvm/vgic/vgic.h246
-rw-r--r--include/linux/audit.h24
-rw-r--r--include/linux/bcma/bcma_driver_chipcommon.h1
-rw-r--r--include/linux/binfmts.h1
-rw-r--r--include/linux/blkdev.h15
-rw-r--r--include/linux/bpf.h32
-rw-r--r--include/linux/ceph/ceph_frag.h4
-rw-r--r--include/linux/ceph/ceph_fs.h20
-rw-r--r--include/linux/ceph/decode.h2
-rw-r--r--include/linux/ceph/libceph.h57
-rw-r--r--include/linux/ceph/mon_client.h23
-rw-r--r--include/linux/ceph/osd_client.h236
-rw-r--r--include/linux/ceph/osdmap.h163
-rw-r--r--include/linux/ceph/rados.h34
-rw-r--r--include/linux/clk-provider.h2
-rw-r--r--include/linux/cpuidle.h3
-rw-r--r--include/linux/dax.h41
-rw-r--r--include/linux/dcache.h40
-rw-r--r--include/linux/devpts_fs.h9
-rw-r--r--include/linux/dma-buf.h13
-rw-r--r--include/linux/efi.h2
-rw-r--r--include/linux/err.h2
-rw-r--r--include/linux/errno.h1
-rw-r--r--include/linux/export.h33
-rw-r--r--include/linux/fence.h2
-rw-r--r--include/linux/fs.h4
-rw-r--r--include/linux/fscache-cache.h2
-rw-r--r--include/linux/fsl_ifc.h45
-rw-r--r--include/linux/hash.h108
-rw-r--r--include/linux/iio/common/st_sensors.h9
-rw-r--r--include/linux/inet_diag.h6
-rw-r--r--include/linux/init_task.h2
-rw-r--r--include/linux/iova.h23
-rw-r--r--include/linux/irqchip/arm-gic-v3.h12
-rw-r--r--include/linux/irqchip/arm-gic.h2
-rw-r--r--include/linux/isa.h5
-rw-r--r--include/linux/jbd2.h16
-rw-r--r--include/linux/jump_label.h16
-rw-r--r--include/linux/kasan.h11
-rw-r--r--include/linux/kvm_host.h7
-rw-r--r--include/linux/leds.h23
-rw-r--r--include/linux/memory_hotplug.h2
-rw-r--r--include/linux/mfd/cros_ec.h6
-rw-r--r--include/linux/mfd/da9052/da9052.h2
-rw-r--r--include/linux/mfd/twl6040.h1
-rw-r--r--include/linux/mlx4/device.h1
-rw-r--r--include/linux/mlx5/device.h8
-rw-r--r--include/linux/mlx5/mlx5_ifc.h12
-rw-r--r--include/linux/mlx5/qp.h7
-rw-r--r--include/linux/mlx5/vport.h2
-rw-r--r--include/linux/mm.h11
-rw-r--r--include/linux/mm_types.h2
-rw-r--r--include/linux/mmc/host.h4
-rw-r--r--include/linux/mtd/fsmc.h18
-rw-r--r--include/linux/mtd/map.h19
-rw-r--r--include/linux/mtd/mtd.h63
-rw-r--r--include/linux/mtd/nand.h28
-rw-r--r--include/linux/mtd/onenand.h2
-rw-r--r--include/linux/mtd/sharpsl.h2
-rw-r--r--include/linux/mtd/spi-nor.h1
-rw-r--r--include/linux/namei.h2
-rw-r--r--include/linux/net.h3
-rw-r--r--include/linux/nfs4.h28
-rw-r--r--include/linux/nfs_fs_sb.h1
-rw-r--r--include/linux/nfs_xdr.h30
-rw-r--r--include/linux/of.h2
-rw-r--r--include/linux/of_mtd.h50
-rw-r--r--include/linux/of_pci.h2
-rw-r--r--include/linux/of_reserved_mem.h7
-rw-r--r--include/linux/omap-gpmc.h172
-rw-r--r--include/linux/page_idle.h43
-rw-r--r--include/linux/perf_event.h34
-rw-r--r--include/linux/platform_data/at24.h2
-rw-r--r--include/linux/platform_data/gpmc-omap.h172
-rw-r--r--include/linux/platform_data/mtd-nand-omap2.h12
-rw-r--r--include/linux/pwm.h326
-rw-r--r--include/linux/qed/qed_eth_if.h1
-rw-r--r--include/linux/reservation.h53
-rw-r--r--include/linux/reset.h211
-rw-r--r--include/linux/rwsem.h2
-rw-r--r--include/linux/sched.h7
-rw-r--r--include/linux/sctp.h2
-rw-r--r--include/linux/seqlock.h7
-rw-r--r--include/linux/slub_def.h16
-rw-r--r--include/linux/sock_diag.h6
-rw-r--r--include/linux/spi/spi.h6
-rw-r--r--include/linux/stringhash.h76
-rw-r--r--include/linux/sunrpc/auth.h26
-rw-r--r--include/linux/sunrpc/clnt.h3
-rw-r--r--include/linux/sunrpc/msg_prot.h4
-rw-r--r--include/linux/sunrpc/svc_rdma.h2
-rw-r--r--include/linux/sunrpc/svc_xprt.h1
-rw-r--r--include/linux/sunrpc/svcauth.h40
-rw-r--r--include/linux/sunrpc/xprt.h2
-rw-r--r--include/linux/sunrpc/xprtrdma.h4
-rw-r--r--include/linux/thermal.h3
-rw-r--r--include/linux/timekeeping.h3
-rw-r--r--include/linux/usb/ehci_def.h4
-rw-r--r--include/linux/usb/gadget.h3
-rw-r--r--include/linux/usb/musb.h5
-rw-r--r--include/linux/xattr.h7
-rw-r--r--include/media/v4l2-mc.h2
-rw-r--r--include/net/compat.h1
-rw-r--r--include/net/gre.h2
-rw-r--r--include/net/ip6_tunnel.h3
-rw-r--r--include/net/ip_vs.h2
-rw-r--r--include/net/netfilter/nf_queue.h4
-rw-r--r--include/net/netfilter/nf_tables.h1
-rw-r--r--include/net/netns/netfilter.h2
-rw-r--r--include/net/pkt_cls.h10
-rw-r--r--include/net/pkt_sched.h1
-rw-r--r--include/net/sch_generic.h6
-rw-r--r--include/net/tc_act/tc_ife.h6
-rw-r--r--include/rdma/ib_mad.h60
-rw-r--r--include/rdma/ib_pack.h5
-rw-r--r--include/rdma/ib_sa.h12
-rw-r--r--include/rdma/ib_verbs.h132
-rw-r--r--include/rdma/rdma_vt.h17
-rw-r--r--include/rdma/rdmavt_qp.h5
-rw-r--r--include/target/iscsi/iscsi_target_core.h27
-rw-r--r--include/target/iscsi/iscsi_transport.h41
-rw-r--r--include/target/target_core_base.h2
-rw-r--r--include/target/target_core_fabric.h6
-rw-r--r--include/trace/events/kvm.h6
-rw-r--r--include/uapi/asm-generic/unistd.h3
-rw-r--r--include/uapi/linux/btrfs.h2
-rw-r--r--include/uapi/linux/ethtool.h11
-rw-r--r--include/uapi/linux/fuse.h7
-rw-r--r--include/uapi/linux/gtp.h2
-rw-r--r--include/uapi/linux/input-event-codes.h31
-rw-r--r--include/uapi/linux/input.h1
-rw-r--r--include/uapi/linux/netfilter/Kbuild1
-rw-r--r--include/uapi/linux/netfilter/xt_SYNPROXY.h2
-rw-r--r--include/uapi/linux/nvme_ioctl.h1
-rw-r--r--include/uapi/linux/perf_event.h1
-rw-r--r--include/uapi/linux/pkt_cls.h4
-rw-r--r--include/uapi/mtd/mtd-abi.h2
-rw-r--r--include/uapi/rdma/hfi/hfi1_user.h80
-rw-r--r--include/uapi/rdma/rdma_netlink.h10
-rw-r--r--include/uapi/sound/Kbuild3
-rw-r--r--include/uapi/sound/asoc.h44
-rw-r--r--include/video/imx-ipu-v3.h2
-rw-r--r--init/Kconfig29
-rw-r--r--init/main.c11
-rw-r--r--kernel/audit.c17
-rw-r--r--kernel/audit.h4
-rw-r--r--kernel/auditsc.c8
-rw-r--r--kernel/bpf/inode.c1
-rw-r--r--kernel/bpf/stackmap.c3
-rw-r--r--kernel/bpf/verifier.c41
-rw-r--r--kernel/cgroup.c148
-rw-r--r--kernel/events/callchain.c36
-rw-r--r--kernel/events/core.c8
-rw-r--r--kernel/fork.c52
-rw-r--r--kernel/futex.c14
-rw-r--r--kernel/gcov/Kconfig1
-rw-r--r--kernel/irq/ipi.c2
-rw-r--r--kernel/jump_label.c36
-rw-r--r--kernel/kcov.c7
-rw-r--r--kernel/locking/mutex-debug.c12
-rw-r--r--kernel/locking/mutex-debug.h4
-rw-r--r--kernel/locking/mutex.c15
-rw-r--r--kernel/locking/mutex.h2
-rw-r--r--kernel/locking/percpu-rwsem.c1
-rw-r--r--kernel/locking/qspinlock.c60
-rw-r--r--kernel/locking/rwsem.c16
-rw-r--r--kernel/pid.c2
-rw-r--r--kernel/power/process.c12
-rw-r--r--kernel/relay.c1
-rw-r--r--kernel/sched/core.c60
-rw-r--r--kernel/sched/cpufreq_schedutil.c4
-rw-r--r--kernel/sched/debug.c15
-rw-r--r--kernel/sched/fair.c72
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/sched/stats.h3
-rw-r--r--kernel/sysctl.c11
-rw-r--r--kernel/time/hrtimer.c1
-rw-r--r--kernel/trace/bpf_trace.c14
-rw-r--r--kernel/trace/trace_printk.c7
-rw-r--r--lib/Kconfig.debug14
-rw-r--r--lib/Makefile2
-rw-r--r--lib/dma-debug.c2
-rw-r--r--lib/iov_iter.c2
-rw-r--r--lib/test_hash.c250
-rw-r--r--lib/test_uuid.c133
-rw-r--r--lib/uuid.c4
-rw-r--r--mm/Kconfig3
-rw-r--r--mm/cma.c7
-rw-r--r--mm/compaction.c39
-rw-r--r--mm/fadvise.c11
-rw-r--r--mm/filemap.c32
-rw-r--r--mm/hugetlb.c46
-rw-r--r--mm/internal.h3
-rw-r--r--mm/kasan/kasan.c10
-rw-r--r--mm/kasan/kasan.h1
-rw-r--r--mm/kmemleak.c2
-rw-r--r--mm/memcontrol.c53
-rw-r--r--mm/memory.c71
-rw-r--r--mm/memory_hotplug.c4
-rw-r--r--mm/mempool.c12
-rw-r--r--mm/migrate.c2
-rw-r--r--mm/mmap.c16
-rw-r--r--mm/nommu.c2
-rw-r--r--mm/oom_kill.c44
-rw-r--r--mm/page-writeback.c21
-rw-r--r--mm/page_alloc.c39
-rw-r--r--mm/page_ext.c4
-rw-r--r--mm/page_owner.c32
-rw-r--r--mm/page_poison.c8
-rw-r--r--mm/percpu.c73
-rw-r--r--mm/rmap.c2
-rw-r--r--mm/shmem.c9
-rw-r--r--mm/swap.c31
-rw-r--r--mm/swap_state.c5
-rw-r--r--mm/truncate.c62
-rw-r--r--mm/vmalloc.c9
-rw-r--r--mm/vmstat.c2
-rw-r--r--mm/z3fold.c24
-rw-r--r--mm/zsmalloc.c35
-rw-r--r--net/8021q/vlan.c5
-rw-r--r--net/8021q/vlan.h2
-rw-r--r--net/8021q/vlan_dev.c20
-rw-r--r--net/9p/client.c8
-rw-r--r--net/atm/signaling.c2
-rw-r--r--net/atm/svc.c4
-rw-r--r--net/ax25/af_ax25.c3
-rw-r--r--net/ax25/ax25_ds_timer.c5
-rw-r--r--net/ax25/ax25_std_timer.c5
-rw-r--r--net/ax25/ax25_subr.c3
-rw-r--r--net/batman-adv/routing.c1
-rw-r--r--net/batman-adv/soft-interface.c9
-rw-r--r--net/batman-adv/translation-table.c50
-rw-r--r--net/batman-adv/types.h2
-rw-r--r--net/bridge/br_fdb.c2
-rw-r--r--net/bridge/br_input.c15
-rw-r--r--net/bridge/br_multicast.c4
-rw-r--r--net/bridge/br_netlink.c2
-rw-r--r--net/bridge/br_private.h23
-rw-r--r--net/ceph/ceph_common.c2
-rw-r--r--net/ceph/ceph_strings.c16
-rw-r--r--net/ceph/debugfs.c147
-rw-r--r--net/ceph/mon_client.c393
-rw-r--r--net/ceph/osd_client.c4031
-rw-r--r--net/ceph/osdmap.c651
-rw-r--r--net/compat.c20
-rw-r--r--net/core/filter.c16
-rw-r--r--net/core/gen_stats.c2
-rw-r--r--net/core/hwbm.c3
-rw-r--r--net/core/neighbour.c6
-rw-r--r--net/core/net-sysfs.c1
-rw-r--r--net/core/pktgen.c8
-rw-r--r--net/ieee802154/nl802154.c4
-rw-r--r--net/ipv4/af_inet.c8
-rw-r--r--net/ipv4/esp4.c52
-rw-r--r--net/ipv4/gre_demux.c10
-rw-r--r--net/ipv4/ip_gre.c26
-rw-r--r--net/ipv4/ipconfig.c4
-rw-r--r--net/ipv4/ipmr.c4
-rw-r--r--net/ipv4/sysctl_net_ipv4.c4
-rw-r--r--net/ipv4/tcp_output.c7
-rw-r--r--net/ipv4/udp.c90
-rw-r--r--net/ipv6/Kconfig9
-rw-r--r--net/ipv6/Makefile2
-rw-r--r--net/ipv6/fou6.c2
-rw-r--r--net/ipv6/icmp.c2
-rw-r--r--net/ipv6/ip6_checksum.c7
-rw-r--r--net/ipv6/ip6_gre.c8
-rw-r--r--net/ipv6/ip6_output.c11
-rw-r--r--net/ipv6/ip6mr.c1
-rw-r--r--net/ipv6/netfilter/nf_dup_ipv6.c1
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/sit.c4
-rw-r--r--net/ipv6/tcp_ipv6.c8
-rw-r--r--net/ipv6/udp.c83
-rw-r--r--net/kcm/kcmproc.c1
-rw-r--r--net/l2tp/l2tp_core.c2
-rw-r--r--net/l2tp/l2tp_ip6.c12
-rw-r--r--net/lapb/lapb_in.c5
-rw-r--r--net/lapb/lapb_out.c4
-rw-r--r--net/lapb/lapb_subr.c14
-rw-r--r--net/mac80211/mesh.c11
-rw-r--r--net/mac80211/sta_info.h2
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c5
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c5
-rw-r--r--net/netfilter/nf_conntrack_core.c2
-rw-r--r--net/netfilter/nf_conntrack_ftp.c1
-rw-r--r--net/netfilter/nf_conntrack_helper.c9
-rw-r--r--net/netfilter/nf_conntrack_irc.c1
-rw-r--r--net/netfilter/nf_conntrack_sane.c1
-rw-r--r--net/netfilter/nf_conntrack_sip.c1
-rw-r--r--net/netfilter/nf_conntrack_standalone.c2
-rw-r--r--net/netfilter/nf_conntrack_tftp.c1
-rw-r--r--net/netfilter/nf_queue.c17
-rw-r--r--net/netfilter/nf_tables_api.c26
-rw-r--r--net/netfilter/nf_tables_core.c2
-rw-r--r--net/netfilter/nfnetlink_queue.c20
-rw-r--r--net/netfilter/nft_hash.c3
-rw-r--r--net/netfilter/nft_rbtree.c3
-rw-r--r--net/netfilter/x_tables.c4
-rw-r--r--net/openvswitch/actions.c20
-rw-r--r--net/openvswitch/conntrack.c14
-rw-r--r--net/packet/af_packet.c25
-rw-r--r--net/rds/ib_cm.c2
-rw-r--r--net/rds/loop.c5
-rw-r--r--net/rds/rds.h2
-rw-r--r--net/rds/recv.c2
-rw-r--r--net/rds/send.c1
-rw-r--r--net/rds/sysctl.c3
-rw-r--r--net/rds/tcp.c78
-rw-r--r--net/rds/tcp.h3
-rw-r--r--net/rds/tcp_connect.c26
-rw-r--r--net/rds/tcp_listen.c20
-rw-r--r--net/rds/tcp_recv.c2
-rw-r--r--net/rds/tcp_send.c14
-rw-r--r--net/rds/threads.c10
-rw-r--r--net/rds/transport.c3
-rw-r--r--net/rxrpc/rxkad.c4
-rw-r--r--net/sched/act_api.c2
-rw-r--r--net/sched/act_ife.c53
-rw-r--r--net/sched/act_ipt.c7
-rw-r--r--net/sched/act_police.c40
-rw-r--r--net/sched/cls_flower.c6
-rw-r--r--net/sched/cls_u32.c72
-rw-r--r--net/sched/sch_api.c4
-rw-r--r--net/sched/sch_drr.c4
-rw-r--r--net/sched/sch_fifo.c4
-rw-r--r--net/sched/sch_fq_codel.c26
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_hfsc.c12
-rw-r--r--net/sched/sch_htb.c15
-rw-r--r--net/sched/sch_ingress.c12
-rw-r--r--net/sched/sch_netem.c12
-rw-r--r--net/sched/sch_prio.c71
-rw-r--r--net/sched/sch_qfq.c6
-rw-r--r--net/sched/sch_red.c4
-rw-r--r--net/sched/sch_tbf.c4
-rw-r--r--net/sctp/sctp_diag.c9
-rw-r--r--net/sctp/socket.c1
-rw-r--r--net/sunrpc/auth.c9
-rw-r--r--net/sunrpc/auth_generic.c13
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c6
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c9
-rw-r--r--net/sunrpc/auth_unix.c6
-rw-r--r--net/sunrpc/clnt.c48
-rw-r--r--net/sunrpc/svc_xprt.c25
-rw-r--r--net/sunrpc/xdr.c2
-rw-r--r--net/sunrpc/xprtrdma/backchannel.c16
-rw-r--r--net/sunrpc/xprtrdma/fmr_ops.c134
-rw-r--r--net/sunrpc/xprtrdma/frwr_ops.c214
-rw-r--r--net/sunrpc/xprtrdma/physical_ops.c39
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c517
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_marshal.c32
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_recvfrom.c34
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c28
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c17
-rw-r--r--net/sunrpc/xprtrdma/transport.c16
-rw-r--r--net/sunrpc/xprtrdma/verbs.c78
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h47
-rw-r--r--net/sunrpc/xprtsock.c7
-rw-r--r--net/tipc/bearer.c2
-rw-r--r--net/tipc/link.c3
-rw-r--r--net/tipc/msg.c6
-rw-r--r--net/tipc/msg.h11
-rw-r--r--net/tipc/netlink_compat.c114
-rw-r--r--net/tipc/socket.c54
-rw-r--r--net/unix/af_unix.c6
-rw-r--r--net/vmw_vsock/af_vsock.c12
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/wireless/util.c2
-rw-r--r--net/wireless/wext-core.c25
-rw-r--r--scripts/Kbuild.include45
-rw-r--r--scripts/Makefile.build44
-rw-r--r--scripts/Makefile.extrawarn1
-rw-r--r--scripts/Makefile.lib8
-rwxr-xr-xscripts/adjust_autoksyms.sh101
-rw-r--r--scripts/basic/fixdep.c61
-rwxr-xr-xscripts/checkpatch.pl1
-rwxr-xr-xscripts/coccicheck2
-rw-r--r--scripts/coccinelle/api/setup_timer.cocci4
-rw-r--r--scripts/coccinelle/misc/compare_const_fl.cocci171
-rw-r--r--scripts/genksyms/genksyms.c3
-rw-r--r--scripts/kconfig/confdata.c4
-rw-r--r--scripts/kconfig/symbol.c14
-rw-r--r--scripts/mod/file2alias.c2
-rw-r--r--scripts/package/Makefile4
-rwxr-xr-xscripts/package/builddeb5
-rwxr-xr-xscripts/package/mkspec5
-rw-r--r--security/keys/compat.c2
-rw-r--r--security/keys/dh.c8
-rw-r--r--security/keys/internal.h5
-rw-r--r--security/keys/key.c2
-rw-r--r--security/keys/keyctl.c4
-rw-r--r--security/smack/smack_lsm.c2
-rw-r--r--security/yama/yama_lsm.c69
-rw-r--r--sound/drivers/dummy.c1
-rw-r--r--sound/hda/hdac_regmap.c4
-rw-r--r--sound/pci/hda/hda_intel.c11
-rw-r--r--sound/pci/hda/hda_tegra.c20
-rw-r--r--sound/pci/hda/patch_realtek.c95
-rw-r--r--sound/soc/codecs/Kconfig38
-rw-r--r--sound/soc/codecs/Makefile11
-rw-r--r--sound/soc/codecs/ak4642.c3
-rw-r--r--sound/soc/codecs/max98371.c441
-rw-r--r--sound/soc/codecs/max98371.h67
-rw-r--r--sound/soc/codecs/rt298.c51
-rw-r--r--sound/soc/codecs/rt298.h2
-rw-r--r--sound/soc/codecs/rt5677.c24
-rw-r--r--sound/soc/codecs/tas571x.c141
-rw-r--r--sound/soc/codecs/tas571x.h22
-rw-r--r--sound/soc/codecs/tas5720.c620
-rw-r--r--sound/soc/codecs/tas5720.h90
-rw-r--r--sound/soc/codecs/tlv320aic31xx.c10
-rw-r--r--sound/soc/codecs/tlv320aic32x4-i2c.c74
-rw-r--r--sound/soc/codecs/tlv320aic32x4-spi.c76
-rw-r--r--sound/soc/codecs/tlv320aic32x4.c279
-rw-r--r--sound/soc/codecs/tlv320aic32x4.h7
-rw-r--r--sound/soc/codecs/twl6040.c16
-rw-r--r--sound/soc/codecs/wm8962.c9
-rw-r--r--sound/soc/codecs/wm8962.h6
-rw-r--r--sound/soc/generic/simple-card.c1
-rw-r--r--sound/soc/kirkwood/Kconfig1
-rw-r--r--sound/soc/mediatek/Kconfig1
-rw-r--r--sound/soc/mediatek/mt8173-rt5650-rt5676.c27
-rw-r--r--sound/soc/mediatek/mt8173-rt5650.c50
-rw-r--r--sound/soc/mediatek/mtk-afe-pcm.c2
-rw-r--r--sound/soc/omap/mcbsp.c8
-rw-r--r--sound/soc/omap/omap-pcm.c2
-rw-r--r--sound/soc/pxa/brownstone.c1
-rw-r--r--sound/soc/pxa/mioa701_wm9713.c1
-rw-r--r--sound/soc/pxa/mmp-pcm.c1
-rw-r--r--sound/soc/pxa/mmp-sspa.c1
-rw-r--r--sound/soc/pxa/palm27x.c1
-rw-r--r--sound/soc/pxa/pxa-ssp.c1
-rw-r--r--sound/soc/pxa/pxa2xx-ac97.c1
-rw-r--r--sound/soc/pxa/pxa2xx-pcm.c1
-rw-r--r--sound/soc/qcom/lpass-platform.c8
-rw-r--r--sound/soc/sh/rcar/adg.c8
-rw-r--r--sound/soc/sh/rcar/dma.c12
-rw-r--r--sound/soc/sh/rcar/rsnd.h13
-rw-r--r--sound/soc/sh/rcar/src.c4
-rw-r--r--sound/soc/soc-topology.c48
-rw-r--r--sound/soc/sti/sti_uniperif.c144
-rw-r--r--sound/soc/sti/uniperif.h220
-rw-r--r--sound/soc/sti/uniperif_player.c182
-rw-r--r--sound/soc/sti/uniperif_reader.c229
-rw-r--r--tools/Makefile6
-rw-r--r--tools/build/Makefile.build8
-rw-r--r--tools/kvm/kvm_stat/Makefile41
-rwxr-xr-xtools/kvm/kvm_stat/kvm_stat1127
-rw-r--r--tools/kvm/kvm_stat/kvm_stat.txt63
-rw-r--r--tools/objtool/Makefile4
-rw-r--r--tools/objtool/elf.h5
-rw-r--r--tools/perf/Documentation/perf-report.txt5
-rw-r--r--tools/perf/Documentation/perf-script.txt2
-rw-r--r--tools/perf/Documentation/perf-trace.txt3
-rw-r--r--tools/perf/builtin-annotate.c5
-rw-r--r--tools/perf/builtin-buildid-cache.c8
-rw-r--r--tools/perf/builtin-diff.c5
-rw-r--r--tools/perf/builtin-record.c81
-rw-r--r--tools/perf/builtin-report.c7
-rw-r--r--tools/perf/builtin-script.c7
-rw-r--r--tools/perf/builtin-stat.c22
-rw-r--r--tools/perf/builtin-timechart.c5
-rw-r--r--tools/perf/builtin-top.c6
-rw-r--r--tools/perf/builtin-trace.c274
-rw-r--r--tools/perf/perf.c3
-rw-r--r--tools/perf/util/annotate.c32
-rw-r--r--tools/perf/util/build-id.c2
-rw-r--r--tools/perf/util/data-convert-bt.c41
-rw-r--r--tools/perf/util/db-export.c3
-rw-r--r--tools/perf/util/dso.c7
-rw-r--r--tools/perf/util/event.c2
-rw-r--r--tools/perf/util/evlist.c34
-rw-r--r--tools/perf/util/evlist.h4
-rw-r--r--tools/perf/util/evsel.c13
-rw-r--r--tools/perf/util/evsel.h1
-rw-r--r--tools/perf/util/hist.c9
-rw-r--r--tools/perf/util/hist.h2
-rw-r--r--tools/perf/util/machine.c35
-rw-r--r--tools/perf/util/machine.h1
-rw-r--r--tools/perf/util/scripting-engines/trace-event-perl.c3
-rw-r--r--tools/perf/util/sort.c84
-rw-r--r--tools/perf/util/sort.h2
-rw-r--r--tools/perf/util/stat-shadow.c8
-rw-r--r--tools/perf/util/symbol.c49
-rw-r--r--tools/perf/util/symbol.h7
-rw-r--r--tools/perf/util/top.h1
-rw-r--r--tools/perf/util/util.c3
-rw-r--r--tools/perf/util/util.h3
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc9
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc9
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc9
-rw-r--r--tools/testing/selftests/net/reuseport_bpf.c10
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c8
-rw-r--r--tools/testing/selftests/vm/compaction_test.c2
-rw-r--r--tools/testing/selftests/vm/thuge-gen.c2
-rw-r--r--tools/virtio/ringtest/Makefile7
-rw-r--r--tools/virtio/ringtest/README4
-rw-r--r--tools/virtio/ringtest/main.c2
-rw-r--r--tools/virtio/ringtest/noring.c69
-rwxr-xr-xtools/virtio/ringtest/run-on-all.sh4
-rw-r--r--tools/virtio/ringtest/virtio_ring_0_9.c49
-rw-r--r--tools/virtio/ringtest/virtio_ring_inorder.c2
-rw-r--r--tools/vm/slabinfo.c2
-rw-r--r--virt/kvm/arm/arch_timer.c68
-rw-r--r--virt/kvm/arm/hyp/timer-sr.c5
-rw-r--r--virt/kvm/arm/hyp/vgic-v2-sr.c24
-rw-r--r--virt/kvm/arm/pmu.c25
-rw-r--r--virt/kvm/arm/vgic-v2.c4
-rw-r--r--virt/kvm/arm/vgic-v3.c8
-rw-r--r--virt/kvm/arm/vgic.c86
-rw-r--r--virt/kvm/arm/vgic/vgic-init.c452
-rw-r--r--virt/kvm/arm/vgic/vgic-irqfd.c52
-rw-r--r--virt/kvm/arm/vgic/vgic-kvm-device.c431
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio-v2.c446
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio-v3.c455
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio.c524
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio.h150
-rw-r--r--virt/kvm/arm/vgic/vgic-v2.c356
-rw-r--r--virt/kvm/arm/vgic/vgic-v3.c334
-rw-r--r--virt/kvm/arm/vgic/vgic.c619
-rw-r--r--virt/kvm/arm/vgic/vgic.h131
-rw-r--r--virt/kvm/irqchip.c2
-rw-r--r--virt/kvm/kvm_main.c211
2225 files changed, 56886 insertions, 25560 deletions
diff --git a/.mailmap b/.mailmap
index 08b80428f583..52489f564069 100644
--- a/.mailmap
+++ b/.mailmap
@@ -21,6 +21,7 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
Andrew Morton <akpm@linux-foundation.org>
Andrew Vasquez <andrew.vasquez@qlogic.com>
Andy Adamson <andros@citi.umich.edu>
+Antoine Tenart <antoine.tenart@free-electrons.com>
Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
Archit Taneja <archit@ti.com>
Arnaud Patard <arnaud.patard@rtp-net.org>
@@ -30,6 +31,9 @@ Axel Lin <axel.lin@gmail.com>
Ben Gardner <bgardner@wabtec.com>
Ben M Cahill <ben.m.cahill@intel.com>
Björn Steinbrink <B.Steinbrink@gmx.de>
+Boris Brezillon <boris.brezillon@free-electrons.com>
+Boris Brezillon <boris.brezillon@free-electrons.com> <b.brezillon.dev@gmail.com>
+Boris Brezillon <boris.brezillon@free-electrons.com> <b.brezillon@overkiz.com>
Brian Avery <b.avery@hp.com>
Brian King <brking@us.ibm.com>
Christoph Hellwig <hch@lst.de>
@@ -89,6 +93,7 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
Linas Vepstas <linas@austin.ibm.com>
Mark Brown <broonie@sirena.org.uk>
Matthieu CASTET <castet.matthieu@free.fr>
+Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com> <mchehab@infradead.org> <mchehab@redhat.com> <m.chehab@samsung.com> <mchehab@osg.samsung.com> <mchehab@s-opensource.com>
Mayuresh Janorkar <mayur@ti.com>
Michael Buesch <m@bues.ch>
Michel Dänzer <michel@tungstengraphics.com>
@@ -122,6 +127,7 @@ Santosh Shilimkar <santosh.shilimkar@oracle.org>
Sascha Hauer <s.hauer@pengutronix.de>
S.Çağlar Onur <caglar@pardus.org.tr>
Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
+Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> <shuah.khan@hp.com> <shuahkh@osg.samsung.com> <shuah.kh@samsung.com>
Simon Kelley <simon@thekelleys.org.uk>
Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
Stephen Hemminger <shemminger@osdl.org>
diff --git a/CREDITS b/CREDITS
index 0f0bf22afe0c..2a3fbcd229e6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -649,6 +649,7 @@ D: Configure, Menuconfig, xconfig
N: Mauro Carvalho Chehab
E: m.chehab@samsung.org
+E: mchehab@osg.samsung.com
E: mchehab@infradead.org
D: Media subsystem (V4L/DVB) drivers and core
D: EDAC drivers and EDAC 3.0 core rework
diff --git a/Documentation/ABI/stable/sysfs-class-ubi b/Documentation/ABI/stable/sysfs-class-ubi
index 18d471d9faea..a6b324014692 100644
--- a/Documentation/ABI/stable/sysfs-class-ubi
+++ b/Documentation/ABI/stable/sysfs-class-ubi
@@ -107,6 +107,15 @@ Contact: Artem Bityutskiy <dedekind@infradead.org>
Description:
Number of physical eraseblocks reserved for bad block handling.
+What: /sys/class/ubi/ubiX/ro_mode
+Date: April 2016
+KernelVersion: 4.7
+Contact: linux-mtd@lists.infradead.org
+Description:
+ Contains ASCII "1\n" if the read-only flag is set on this
+ device, and "0\n" if it is cleared. UBI devices mark themselves
+ as read-only when they detect an unrecoverable error.
+
What: /sys/class/ubi/ubiX/total_eraseblocks
Date: July 2006
KernelVersion: 2.6.22
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc
index 2f4a0051b32d..1ba0d0fda9c0 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-uvc
+++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc
@@ -1,6 +1,6 @@
What: /config/usb-gadget/gadget/functions/uvc.name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: UVC function directory
streaming_maxburst - 0..15 (ss only)
@@ -9,37 +9,37 @@ Description: UVC function directory
What: /config/usb-gadget/gadget/functions/uvc.name/control
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Control descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/class
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/class/ss
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Super speed control class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/class/fs
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Full speed control class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Terminal descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/output
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Output terminal descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/output/default
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Default output terminal descriptors
All attributes read only:
@@ -53,12 +53,12 @@ Description: Default output terminal descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Camera terminal descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera/default
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Default camera terminal descriptors
All attributes read only:
@@ -75,12 +75,12 @@ Description: Default camera terminal descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/processing
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Processing unit descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/processing/default
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Default processing unit descriptors
All attributes read only:
@@ -94,49 +94,49 @@ Description: Default processing unit descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/header
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Control header descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/control/header/name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Specific control header descriptors
dwClockFrequency
bcdUVC
What: /config/usb-gadget/gadget/functions/uvc.name/streaming
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Streaming descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Streaming class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/ss
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Super speed streaming class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/hs
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: High speed streaming class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/fs
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Full speed streaming class descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Color matching descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching/default
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Default color matching descriptors
All attributes read only:
@@ -150,12 +150,12 @@ Description: Default color matching descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: MJPEG format descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Specific MJPEG format descriptors
All attributes read only,
@@ -174,7 +174,7 @@ Description: Specific MJPEG format descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name/name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Specific MJPEG frame descriptors
dwFrameInterval - indicates how frame interval can be
@@ -196,12 +196,12 @@ Description: Specific MJPEG frame descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Uncompressed format descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Specific uncompressed format descriptors
bmaControls - this format's data for bmaControls in
@@ -221,7 +221,7 @@ Description: Specific uncompressed format descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name/name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Specific uncompressed frame descriptors
dwFrameInterval - indicates how frame interval can be
@@ -243,12 +243,12 @@ Description: Specific uncompressed frame descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Streaming header descriptors
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header/name
Date: Dec 2014
-KernelVersion: 3.20
+KernelVersion: 4.0
Description: Specific streaming header descriptors
All attributes read only:
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
index 6708c5e264aa..33e96f740639 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
+++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
@@ -1,4 +1,4 @@
-What /sys/bus/iio/devices/iio:deviceX/in_proximity_raw
+What /sys/bus/iio/devices/iio:deviceX/in_proximity_input
Date: March 2014
KernelVersion: 3.15
Contact: Matt Ranostay <mranostay@gmail.com>
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index de79efdad46c..8c68768ebee5 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -128,16 +128,44 @@ X!Edrivers/base/interface.c
!Edrivers/base/platform.c
!Edrivers/base/bus.c
</sect1>
- <sect1><title>Device Drivers DMA Management</title>
+ <sect1>
+ <title>Buffer Sharing and Synchronization</title>
+ <para>
+ The dma-buf subsystem provides the framework for sharing buffers
+ for hardware (DMA) access across multiple device drivers and
+ subsystems, and for synchronizing asynchronous hardware access.
+ </para>
+ <para>
+ This is used, for example, by drm "prime" multi-GPU support, but
+ is of course not limited to GPU use cases.
+ </para>
+ <para>
+ The three main components of this are: (1) dma-buf, representing
+ a sg_table and exposed to userspace as a file descriptor to allow
+ passing between devices, (2) fence, which provides a mechanism
+ to signal when one device as finished access, and (3) reservation,
+ which manages the shared or exclusive fence(s) associated with
+ the buffer.
+ </para>
+ <sect2><title>dma-buf</title>
!Edrivers/dma-buf/dma-buf.c
+!Iinclude/linux/dma-buf.h
+ </sect2>
+ <sect2><title>reservation</title>
+!Pdrivers/dma-buf/reservation.c Reservation Object Overview
+!Edrivers/dma-buf/reservation.c
+!Iinclude/linux/reservation.h
+ </sect2>
+ <sect2><title>fence</title>
!Edrivers/dma-buf/fence.c
-!Edrivers/dma-buf/seqno-fence.c
!Iinclude/linux/fence.h
+!Edrivers/dma-buf/seqno-fence.c
!Iinclude/linux/seqno-fence.h
-!Edrivers/dma-buf/reservation.c
-!Iinclude/linux/reservation.h
!Edrivers/dma-buf/sync_file.c
!Iinclude/linux/sync_file.h
+ </sect2>
+ </sect1>
+ <sect1><title>Device Drivers DMA Management</title>
!Edrivers/base/dma-coherent.c
!Edrivers/base/dma-mapping.c
</sect1>
diff --git a/Documentation/DocBook/gpu.tmpl b/Documentation/DocBook/gpu.tmpl
index 4a0c599b6a6d..7586bf75f62e 100644
--- a/Documentation/DocBook/gpu.tmpl
+++ b/Documentation/DocBook/gpu.tmpl
@@ -1628,6 +1628,12 @@ void intel_crt_init(struct drm_device *dev)
!Edrivers/gpu/drm/drm_dp_helper.c
</sect2>
<sect2>
+ <title>Display Port Dual Mode Adaptor Helper Functions Reference</title>
+!Pdrivers/gpu/drm/drm_dp_dual_mode_helper.c dp dual mode helpers
+!Iinclude/drm/drm_dp_dual_mode_helper.h
+!Edrivers/gpu/drm/drm_dp_dual_mode_helper.c
+ </sect2>
+ <sect2>
<title>Display Port MST Helper Functions Reference</title>
!Pdrivers/gpu/drm/drm_dp_mst_topology.c dp mst helper
!Iinclude/drm/drm_dp_mst_helper.h
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index c6938e50e71f..4da60b463995 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -56,6 +56,7 @@ stable kernels.
| ARM | MMU-500 | #841119,#826419 | N/A |
| | | | |
| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 |
+| Cavium | ThunderX ITS | #23144 | CAVIUM_ERRATUM_23144 |
| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 |
| Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 |
| Cavium | ThunderX SMMUv2 | #27704 | N/A |
diff --git a/Documentation/devicetree/bindings/display/imx/ldb.txt b/Documentation/devicetree/bindings/display/imx/ldb.txt
index 0a175d991b52..a407462c885e 100644
--- a/Documentation/devicetree/bindings/display/imx/ldb.txt
+++ b/Documentation/devicetree/bindings/display/imx/ldb.txt
@@ -62,6 +62,7 @@ Required properties:
display-timings are used instead.
Optional properties (required if display-timings are used):
+ - ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing
- display-timings : A node that describes the display timings as defined in
Documentation/devicetree/bindings/display/display-timing.txt.
- fsl,data-mapping : should be "spwg" or "jeida"
diff --git a/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt b/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt
index ef3752889496..dd031fc93b55 100644
--- a/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt
@@ -33,7 +33,7 @@ gpio0: gpio0@1f860000 {
gpio-controller;
interrupt-controller;
#interrupt-cells = <2>;
- clocks = <&PBCLK4>;
+ clocks = <&rootclk PB4CLK>;
microchip,gpio-bank = <0>;
gpio-ranges = <&pic32_pinctrl 0 0 16>;
};
diff --git a/Documentation/devicetree/bindings/hwmon/ina2xx.txt b/Documentation/devicetree/bindings/hwmon/ina2xx.txt
index 9bcd5e87830d..02af0d94e921 100644
--- a/Documentation/devicetree/bindings/hwmon/ina2xx.txt
+++ b/Documentation/devicetree/bindings/hwmon/ina2xx.txt
@@ -7,6 +7,7 @@ Required properties:
- "ti,ina220" for ina220
- "ti,ina226" for ina226
- "ti,ina230" for ina230
+ - "ti,ina231" for ina231
- reg: I2C address
Optional properties:
diff --git a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
index bfeabb843941..71191ff0e781 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
@@ -44,8 +44,8 @@ Required properties:
- our-claim-gpio: The GPIO that we use to claim the bus.
- their-claim-gpios: The GPIOs that the other sides use to claim the bus.
Note that some implementations may only support a single other master.
-- Standard I2C mux properties. See mux.txt in this directory.
-- Single I2C child bus node at reg 0. See mux.txt in this directory.
+- Standard I2C mux properties. See i2c-mux.txt in this directory.
+- Single I2C child bus node at reg 0. See i2c-mux.txt in this directory.
Optional properties:
- slew-delay-us: microseconds to wait for a GPIO to go high. Default is 10 us.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt
index 6078aefe7ed4..7ce23ac61308 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt
@@ -27,7 +27,8 @@ Required properties:
- i2c-bus-name: The name of this bus. Also needed as pinctrl-name for the I2C
parents.
-Furthermore, I2C mux properties and child nodes. See mux.txt in this directory.
+Furthermore, I2C mux properties and child nodes. See i2c-mux.txt in this
+directory.
Example:
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt
index 66709a825541..21da3ecbb370 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt
@@ -22,8 +22,8 @@ Required properties:
- i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
port is connected to.
- mux-gpios: list of gpios used to control the muxer
-* Standard I2C mux properties. See mux.txt in this directory.
-* I2C child bus nodes. See mux.txt in this directory.
+* Standard I2C mux properties. See i2c-mux.txt in this directory.
+* I2C child bus nodes. See i2c-mux.txt in this directory.
Optional properties:
- idle-state: value to set the muxer to when idle. When no value is
@@ -33,7 +33,7 @@ For each i2c child node, an I2C child bus will be created. They will
be numbered based on their order in the device tree.
Whenever an access is made to a device on a child bus, the value set
-in the revelant node's reg property will be output using the list of
+in the relevant node's reg property will be output using the list of
GPIOs, the first in the list holding the least-significant value.
If an idle state is defined, using the idle-state (optional) property,
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
index ae8af1694e95..33119a98e144 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
@@ -28,9 +28,9 @@ Also required are:
* Standard pinctrl properties that specify the pin mux state for each child
bus. See ../pinctrl/pinctrl-bindings.txt.
-* Standard I2C mux properties. See mux.txt in this directory.
+* Standard I2C mux properties. See i2c-mux.txt in this directory.
-* I2C child bus nodes. See mux.txt in this directory.
+* I2C child bus nodes. See i2c-mux.txt in this directory.
For each named state defined in the pinctrl-names property, an I2C child bus
will be created. I2C child bus numbers are assigned based on the index into
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt
index 688783fbe696..de00d7fc450b 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt
@@ -7,8 +7,8 @@ Required properties:
- compatible: i2c-mux-reg
- i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
port is connected to.
-* Standard I2C mux properties. See mux.txt in this directory.
-* I2C child bus nodes. See mux.txt in this directory.
+* Standard I2C mux properties. See i2c-mux.txt in this directory.
+* I2C child bus nodes. See i2c-mux.txt in this directory.
Optional properties:
- reg: this pair of <offset size> specifies the register to control the mux.
@@ -24,7 +24,7 @@ Optional properties:
given, it defaults to the last value used.
Whenever an access is made to a device on a child bus, the value set
-in the revelant node's reg property will be output to the register.
+in the relevant node's reg property will be output to the register.
If an idle state is defined, using the idle-state (optional) property,
whenever an access is not being made to a device on a child bus, the
diff --git a/Documentation/devicetree/bindings/bus/ti-gpmc.txt b/Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt
index 01683707060b..21055e210234 100644
--- a/Documentation/devicetree/bindings/bus/ti-gpmc.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt
@@ -32,6 +32,19 @@ Required properties:
bootloader) are used for the physical address decoding.
As this will change in the future, filling correct
values here is a requirement.
+ - interrupt-controller: The GPMC driver implements and interrupt controller for
+ the NAND events "fifoevent" and "termcount" plus the
+ rising/falling edges on the GPMC_WAIT pins.
+ The interrupt number mapping is as follows
+ 0 - NAND_fifoevent
+ 1 - NAND_termcount
+ 2 - GPMC_WAIT0 pin edge
+ 3 - GPMC_WAIT1 pin edge, and so on.
+ - interrupt-cells: Must be set to 2
+ - gpio-controller: The GPMC driver implements a GPIO controller for the
+ GPMC WAIT pins that can be used as general purpose inputs.
+ 0 maps to GPMC_WAIT0 pin.
+ - gpio-cells: Must be set to 2
Timing properties for child nodes. All are optional and default to 0.
@@ -130,6 +143,10 @@ Example for an AM33xx board:
#address-cells = <2>;
#size-cells = <1>;
ranges = <0 0 0x08000000 0x10000000>; /* CS0 @addr 0x8000000, size 0x10000000 */
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ #gpio-cells = <2>;
/* child nodes go here */
};
diff --git a/Documentation/devicetree/bindings/mips/cpu_irq.txt b/Documentation/devicetree/bindings/mips/cpu_irq.txt
index fc149f326dae..f080f06da6d8 100644
--- a/Documentation/devicetree/bindings/mips/cpu_irq.txt
+++ b/Documentation/devicetree/bindings/mips/cpu_irq.txt
@@ -13,7 +13,7 @@ Required properties:
- compatible : Should be "mti,cpu-interrupt-controller"
Example devicetree:
- cpu-irq: cpu-irq@0 {
+ cpu-irq: cpu-irq {
#address-cells = <0>;
interrupt-controller;
diff --git a/Documentation/devicetree/bindings/mmc/microchip,sdhci-pic32.txt b/Documentation/devicetree/bindings/mmc/microchip,sdhci-pic32.txt
index 71ad57e050b1..3149297b3933 100644
--- a/Documentation/devicetree/bindings/mmc/microchip,sdhci-pic32.txt
+++ b/Documentation/devicetree/bindings/mmc/microchip,sdhci-pic32.txt
@@ -20,7 +20,7 @@ Example:
compatible = "microchip,pic32mzda-sdhci";
reg = <0x1f8ec000 0x100>;
interrupts = <191 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&REFCLKO4>, <&PBCLK5>;
+ clocks = <&rootclk REF4CLK>, <&rootclk PB5CLK>;
clock-names = "base_clk", "sys_clk";
bus-width = <4>;
cap-sd-highspeed;
diff --git a/Documentation/devicetree/bindings/mtd/atmel-nand.txt b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
index d53aba98fbc9..3e7ee99d3949 100644
--- a/Documentation/devicetree/bindings/mtd/atmel-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
@@ -39,7 +39,7 @@ Optional properties:
Nand Flash Controller(NFC) is an optional sub-node
Required properties:
-- compatible : "atmel,sama5d3-nfc" or "atmel,sama5d4-nfc".
+- compatible : "atmel,sama5d3-nfc".
- reg : should specify the address and size used for NFC command registers,
NFC registers and NFC SRAM. NFC SRAM address and size can be absent
if don't want to use it.
diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
index 0f6985b5de49..7066597c9a81 100644
--- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
+++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
@@ -24,6 +24,7 @@ Required properties:
brcm,brcmnand-v5.0
brcm,brcmnand-v6.0
brcm,brcmnand-v6.1
+ brcm,brcmnand-v6.2
brcm,brcmnand-v7.0
brcm,brcmnand-v7.1
brcm,brcmnand
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index fb733c4e1c11..3ee7e202657c 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -13,7 +13,11 @@ Documentation/devicetree/bindings/mtd/nand.txt
Required properties:
- - reg: The CS line the peripheral is connected to
+ - compatible: "ti,omap2-nand"
+ - reg: range id (CS number), base offset and length of the
+ NAND I/O space
+ - interrupt-parent: must point to gpmc node
+ - interrupts: Two interrupt specifiers, one for fifoevent, one for termcount.
Optional properties:
@@ -44,6 +48,7 @@ Optional properties:
locating ECC errors for BCHx algorithms. SoC devices which have
ELM hardware engines should specify this device node in .dtsi
Using ELM for ECC error correction frees some CPU cycles.
+ - rb-gpios: GPIO specifier for the ready/busy# pin.
For inline partition table parsing (optional):
@@ -55,20 +60,26 @@ Example for an AM33xx board:
gpmc: gpmc@50000000 {
compatible = "ti,am3352-gpmc";
ti,hwmods = "gpmc";
- reg = <0x50000000 0x1000000>;
+ reg = <0x50000000 0x36c>;
interrupts = <100>;
gpmc,num-cs = <8>;
gpmc,num-waitpins = <2>;
#address-cells = <2>;
#size-cells = <1>;
- ranges = <0 0 0x08000000 0x2000>; /* CS0: NAND */
+ ranges = <0 0 0x08000000 0x1000000>; /* CS0 space, 16MB */
elm_id = <&elm>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
nand@0,0 {
- reg = <0 0 0>; /* CS0, offset 0 */
+ compatible = "ti,omap2-nand";
+ reg = <0 0 4>; /* CS0, offset 0, NAND I/O window 4 */
+ interrupt-parent = <&gpmc>;
+ interrupts = <0 IRQ_TYPE_NONE>, <1 IRQ_TYPE NONE>;
nand-bus-width = <16>;
ti,nand-ecc-opt = "bch8";
ti,nand-xfer-type = "polled";
+ rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
index b53f92e252d4..3733300de8dd 100644
--- a/Documentation/devicetree/bindings/mtd/nand.txt
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -1,8 +1,31 @@
-* MTD generic binding
+* NAND chip and NAND controller generic binding
+
+NAND controller/NAND chip representation:
+
+The NAND controller should be represented with its own DT node, and all
+NAND chips attached to this controller should be defined as children nodes
+of the NAND controller. This representation should be enforced even for
+simple controllers supporting only one chip.
+
+Mandatory NAND controller properties:
+- #address-cells: depends on your controller. Should at least be 1 to
+ encode the CS line id.
+- #size-cells: depends on your controller. Put zero unless you need a
+ mapping between CS lines and dedicated memory regions
+
+Optional NAND controller properties
+- ranges: only needed if you need to define a mapping between CS lines and
+ memory regions
+
+Optional NAND chip properties:
- nand-ecc-mode : String, operation mode of the NAND ecc mode.
- Supported values are: "none", "soft", "hw", "hw_syndrome", "hw_oob_first",
- "soft_bch".
+ Supported values are: "none", "soft", "hw", "hw_syndrome",
+ "hw_oob_first".
+ Deprecated values:
+ "soft_bch": use "soft" and nand-ecc-algo instead
+- nand-ecc-algo: string, algorithm of NAND ECC.
+ Supported values are: "hamming", "bch".
- nand-bus-width : 8 or 16 bus width if not present 8
- nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
@@ -19,3 +42,20 @@ errors per {size} bytes".
The interpretation of these parameters is implementation-defined, so not all
implementations must support all possible combinations. However, implementations
are encouraged to further specify the value(s) they support.
+
+Example:
+
+ nand-controller {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* controller specific properties */
+
+ nand@0 {
+ reg = <0>;
+ nand-ecc-mode = "soft";
+ nand-ecc-algo = "bch";
+
+ /* controller specific properties */
+ };
+ };
diff --git a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
index 14aa6cf58201..6a9a63cb0543 100644
--- a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
+++ b/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
@@ -13,10 +13,10 @@ Optional properties:
initialization. This is an array of 28 values(u8).
- marvell,wakeup-pin: It represents wakeup pin number of the bluetooth chip.
- firmware will use the pin to wakeup host system.
+ firmware will use the pin to wakeup host system (u16).
- marvell,wakeup-gap-ms: wakeup gap represents wakeup latency of the host
platform. The value will be configured to firmware. This
- is needed to work chip's sleep feature as expected.
+ is needed to work chip's sleep feature as expected (u16).
- interrupt-parent: phandle of the parent interrupt controller
- interrupts : interrupt pin number to the cpu. Driver will request an irq based
on this interrupt number. During system suspend, the irq will be
@@ -50,7 +50,7 @@ calibration data is also available in below example.
0x37 0x01 0x1c 0x00 0xff 0xff 0xff 0xff 0x01 0x7f 0x04 0x02
0x00 0x00 0xba 0xce 0xc0 0xc6 0x2d 0x00 0x00 0x00 0x00 0x00
0x00 0x00 0xf0 0x00>;
- marvell,wakeup-pin = <0x0d>;
- marvell,wakeup-gap-ms = <0x64>;
+ marvell,wakeup-pin = /bits/ 16 <0x0d>;
+ marvell,wakeup-gap-ms = /bits/ 16 <0x64>;
};
};
diff --git a/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt
index 4b5efa51bec7..29b72e303ebf 100644
--- a/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt
@@ -34,7 +34,7 @@ pic32_pinctrl: pinctrl@1f801400{
#size-cells = <1>;
compatible = "microchip,pic32mzda-pinctrl";
reg = <0x1f801400 0x400>;
- clocks = <&PBCLK1>;
+ clocks = <&rootclk PB1CLK>;
pinctrl_uart2: pinctrl_uart2 {
uart2-tx {
diff --git a/Documentation/devicetree/bindings/serial/microchip,pic32-uart.txt b/Documentation/devicetree/bindings/serial/microchip,pic32-uart.txt
index 65b38bf60ae0..7a34345d0ca3 100644
--- a/Documentation/devicetree/bindings/serial/microchip,pic32-uart.txt
+++ b/Documentation/devicetree/bindings/serial/microchip,pic32-uart.txt
@@ -20,7 +20,7 @@ Example:
interrupts = <112 IRQ_TYPE_LEVEL_HIGH>,
<113 IRQ_TYPE_LEVEL_HIGH>,
<114 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&PBCLK2>;
+ clocks = <&rootclk PB2CLK>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_uart1
&pinctrl_uart1_cts
diff --git a/Documentation/devicetree/bindings/sound/max98371.txt b/Documentation/devicetree/bindings/sound/max98371.txt
new file mode 100644
index 000000000000..6c285235e64b
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/max98371.txt
@@ -0,0 +1,17 @@
+max98371 codec
+
+This device supports I2C mode only.
+
+Required properties:
+
+- compatible : "maxim,max98371"
+- reg : The chip select number on the I2C bus
+
+Example:
+
+&i2c {
+ max98371: max98371@0x31 {
+ compatible = "maxim,max98371";
+ reg = <0x31>;
+ };
+};
diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
index f205ce9e31dd..ac28cdb4910e 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
@@ -1,15 +1,16 @@
-MT8173 with RT5650 RT5676 CODECS
+MT8173 with RT5650 RT5676 CODECS and HDMI via I2S
Required properties:
- compatible : "mediatek,mt8173-rt5650-rt5676"
- mediatek,audio-codec: the phandles of rt5650 and rt5676 codecs
+ and of the hdmi encoder node
- mediatek,platform: the phandle of MT8173 ASoC platform
Example:
sound {
compatible = "mediatek,mt8173-rt5650-rt5676";
- mediatek,audio-codec = <&rt5650 &rt5676>;
+ mediatek,audio-codec = <&rt5650 &rt5676 &hdmi0>;
mediatek,platform = <&afe>;
};
diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt
index fe5a5ef1714d..5bfa6b60530b 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt
@@ -5,11 +5,21 @@ Required properties:
- mediatek,audio-codec: the phandles of rt5650 codecs
- mediatek,platform: the phandle of MT8173 ASoC platform
+Optional subnodes:
+- codec-capture : the subnode of rt5650 codec capture
+Required codec-capture subnode properties:
+- sound-dai: audio codec dai name on capture path
+ <&rt5650 0> : Default setting. Connect rt5650 I2S1 for capture. (dai_name = rt5645-aif1)
+ <&rt5650 1> : Connect rt5650 I2S2 for capture. (dai_name = rt5645-aif2)
+
Example:
sound {
compatible = "mediatek,mt8173-rt5650";
mediatek,audio-codec = <&rt5650>;
mediatek,platform = <&afe>;
+ codec-capture {
+ sound-dai = <&rt5650 1>;
+ };
};
diff --git a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
index 028fa1c82f50..4d9a83d9a017 100644
--- a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
@@ -37,17 +37,18 @@ Required properties:
- dai-name: DAI name that describes the IP.
+ - IP mode: IP working mode depending on associated codec.
+ "HDMI" connected to HDMI codec and support IEC HDMI formats (player only).
+ "SPDIF" connected to SPDIF codec and support SPDIF formats (player only).
+ "PCM" PCM standard mode for I2S or TDM bus.
+ "TDM" TDM mode for TDM bus.
+
Required properties ("st,sti-uni-player" compatibility only):
- clocks: CPU_DAI IP clock source, listed in the same order than the
CPU_DAI properties.
- uniperiph-id: internal SOC IP instance ID.
- - IP mode: IP working mode depending on associated codec.
- "HDMI" connected to HDMI codec IP and IEC HDMI formats.
- "SPDIF"connected to SPDIF codec and support SPDIF formats.
- "PCM" PCM standard mode for I2S or TDM bus.
-
Optional properties:
- pinctrl-0: defined for CPU_DAI@1 and CPU_DAI@4 to describe I2S PIOs for
external codecs connection.
@@ -56,6 +57,22 @@ Optional properties:
Example:
+ sti_uni_player1: sti-uni-player@1 {
+ compatible = "st,sti-uni-player";
+ status = "okay";
+ #sound-dai-cells = <0>;
+ st,syscfg = <&syscfg_core>;
+ clocks = <&clk_s_d0_flexgen CLK_PCM_1>;
+ reg = <0x8D81000 0x158>;
+ interrupts = <GIC_SPI 85 IRQ_TYPE_NONE>;
+ dmas = <&fdma0 3 0 1>;
+ st,dai-name = "Uni Player #1 (I2S)";
+ dma-names = "tx";
+ st,uniperiph-id = <1>;
+ st,version = <5>;
+ st,mode = "TDM";
+ };
+
sti_uni_player2: sti-uni-player@2 {
compatible = "st,sti-uni-player";
status = "okay";
@@ -65,7 +82,7 @@ Example:
reg = <0x8D82000 0x158>;
interrupts = <GIC_SPI 86 IRQ_TYPE_NONE>;
dmas = <&fdma0 4 0 1>;
- dai-name = "Uni Player #1 (DAC)";
+ dai-name = "Uni Player #2 (DAC)";
dma-names = "tx";
uniperiph-id = <2>;
version = <5>;
@@ -82,7 +99,7 @@ Example:
interrupts = <GIC_SPI 89 IRQ_TYPE_NONE>;
dmas = <&fdma0 7 0 1>;
dma-names = "tx";
- dai-name = "Uni Player #1 (PIO)";
+ dai-name = "Uni Player #3 (SPDIF)";
uniperiph-id = <3>;
version = <5>;
mode = "SPDIF";
@@ -99,6 +116,7 @@ Example:
dma-names = "rx";
dai-name = "Uni Reader #1 (HDMI RX)";
version = <3>;
+ st,mode = "PCM";
};
2) sti-sas-codec: internal audio codec IPs driver
@@ -152,4 +170,20 @@ Example of audio card declaration:
sound-dai = <&sti_sasg_codec 0>;
};
};
+ simple-audio-card,dai-link@2 {
+ /* TDM playback */
+ format = "left_j";
+ frame-inversion = <1>;
+ cpu {
+ sound-dai = <&sti_uni_player1>;
+ dai-tdm-slot-num = <16>;
+ dai-tdm-slot-width = <16>;
+ dai-tdm-slot-tx-mask =
+ <1 1 1 1 0 0 0 0 0 0 1 1 0 0 1 1>;
+ };
+
+ codec {
+ sound-dai = <&sti_sasg_codec 3>;
+ };
+ };
};
diff --git a/Documentation/devicetree/bindings/sound/tas571x.txt b/Documentation/devicetree/bindings/sound/tas571x.txt
index 0ac31d8d5ac4..b4959f10b74b 100644
--- a/Documentation/devicetree/bindings/sound/tas571x.txt
+++ b/Documentation/devicetree/bindings/sound/tas571x.txt
@@ -1,4 +1,4 @@
-Texas Instruments TAS5711/TAS5717/TAS5719 stereo power amplifiers
+Texas Instruments TAS5711/TAS5717/TAS5719/TAS5721 stereo power amplifiers
The codec is controlled through an I2C interface. It also has two other
signals that can be wired up to GPIOs: reset (strongly recommended), and
@@ -6,7 +6,11 @@ powerdown (optional).
Required properties:
-- compatible: "ti,tas5711", "ti,tas5717", or "ti,tas5719"
+- compatible: should be one of the following:
+ - "ti,tas5711",
+ - "ti,tas5717",
+ - "ti,tas5719",
+ - "ti,tas5721"
- reg: The I2C address of the device
- #sound-dai-cells: must be equal to 0
@@ -25,6 +29,8 @@ Optional properties:
- PVDD_B-supply: regulator phandle for the PVDD_B supply (5711)
- PVDD_C-supply: regulator phandle for the PVDD_C supply (5711)
- PVDD_D-supply: regulator phandle for the PVDD_D supply (5711)
+- DRVDD-supply: regulator phandle for the DRVDD supply (5721)
+- PVDD-supply: regulator phandle for the PVDD supply (5721)
Example:
diff --git a/Documentation/devicetree/bindings/sound/tas5720.txt b/Documentation/devicetree/bindings/sound/tas5720.txt
new file mode 100644
index 000000000000..806ea7381483
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/tas5720.txt
@@ -0,0 +1,25 @@
+Texas Instruments TAS5720 Mono Audio amplifier
+
+The TAS5720 serial control bus communicates through the I2C protocol only. The
+serial bus is also used for periodic codec fault checking/reporting during
+audio playback. For more product information please see the links below:
+
+http://www.ti.com/product/TAS5720L
+http://www.ti.com/product/TAS5720M
+
+Required properties:
+
+- compatible : "ti,tas5720"
+- reg : I2C slave address
+- dvdd-supply : phandle to a 3.3-V supply for the digital circuitry
+- pvdd-supply : phandle to a supply used for the Class-D amp and the analog
+
+Example:
+
+tas5720: tas5720@6c {
+ status = "okay";
+ compatible = "ti,tas5720";
+ reg = <0x6c>;
+ dvdd-supply = <&vdd_3v3_reg>;
+ pvdd-supply = <&amp_supply_reg>;
+};
diff --git a/Documentation/devicetree/bindings/spi/microchip,spi-pic32.txt b/Documentation/devicetree/bindings/spi/microchip,spi-pic32.txt
new file mode 100644
index 000000000000..79de379f4dc0
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/microchip,spi-pic32.txt
@@ -0,0 +1,34 @@
+Microchip PIC32 SPI Master controller
+
+Required properties:
+- compatible: Should be "microchip,pic32mzda-spi".
+- reg: Address and length of register space for the device.
+- interrupts: Should contain all three spi interrupts in sequence
+ of <fault-irq>, <receive-irq>, <transmit-irq>.
+- interrupt-names: Should be "fault", "rx", "tx" in order.
+- clocks: Phandle of the clock generating SPI clock on the bus.
+- clock-names: Should be "mck0".
+- cs-gpios: Specifies the gpio pins to be used for chipselects.
+ See: Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Optional properties:
+- dmas: Two or more DMA channel specifiers following the convention outlined
+ in Documentation/devicetree/bindings/dma/dma.txt
+- dma-names: Names for the dma channels. There must be at least one channel
+ named "spi-tx" for transmit and named "spi-rx" for receive.
+
+Example:
+
+spi1: spi@1f821000 {
+ compatible = "microchip,pic32mzda-spi";
+ reg = <0x1f821000 0x200>;
+ interrupts = <109 IRQ_TYPE_LEVEL_HIGH>,
+ <110 IRQ_TYPE_LEVEL_HIGH>,
+ <111 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "fault", "rx", "tx";
+ clocks = <&PBCLK2>;
+ clock-names = "mck0";
+ cs-gpios = <&gpio3 4 GPIO_ACTIVE_LOW>;
+ dmas = <&dma 134>, <&dma 135>;
+ dma-names = "spi-rx", "spi-tx";
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt b/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
index 1ad0fe310ff9..ff5893d275a2 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
@@ -16,8 +16,7 @@ Required properties:
Optional property:
- big-endian: If present the dspi device's registers are implemented
- in big endian mode, otherwise in native mode(same with CPU), for more
- detail please see: Documentation/devicetree/bindings/regmap/regmap.txt.
+ in big endian mode.
Optional SPI slave node properties:
- fsl,spi-cs-sck-delay: a delay in nanoseconds between activating chip
diff --git a/Documentation/devicetree/bindings/spi/sqi-pic32.txt b/Documentation/devicetree/bindings/spi/sqi-pic32.txt
new file mode 100644
index 000000000000..c82d021bce50
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/sqi-pic32.txt
@@ -0,0 +1,18 @@
+Microchip PIC32 Quad SPI controller
+-----------------------------------
+Required properties:
+- compatible: Should be "microchip,pic32mzda-sqi".
+- reg: Address and length of SQI controller register space.
+- interrupts: Should contain SQI interrupt.
+- clocks: Should contain phandle of two clocks in sequence, one that drives
+ clock on SPI bus and other that drives SQI controller.
+- clock-names: Should be "spi_ck" and "reg_ck" in order.
+
+Example:
+ sqi1: spi@1f8e2000 {
+ compatible = "microchip,pic32mzda-sqi";
+ reg = <0x1f8e2000 0x200>;
+ clocks = <&rootclk REF2CLK>, <&rootclk PB5CLK>;
+ clock-names = "spi_ck", "reg_ck";
+ interrupts = <169 IRQ_TYPE_LEVEL_HIGH>;
+ };
diff --git a/Documentation/devicetree/bindings/thermal/nvidia,tegra124-soctherm.txt b/Documentation/devicetree/bindings/thermal/nvidia,tegra124-soctherm.txt
index 6908d3aca598..edebfa0a985e 100644
--- a/Documentation/devicetree/bindings/thermal/nvidia,tegra124-soctherm.txt
+++ b/Documentation/devicetree/bindings/thermal/nvidia,tegra124-soctherm.txt
@@ -26,6 +26,10 @@ Required properties :
of this property. See <dt-bindings/thermal/tegra124-soctherm.h> for a
list of valid values when referring to thermal sensors.
+Note:
+- the "critical" type trip points will be set to SOC_THERM hardware as the
+shut down temperature. Once the temperature of this thermal zone is higher
+than it, the system will be shutdown or reset by hardware.
Example :
@@ -51,5 +55,13 @@ Example: referring to thermal sensors :
thermal-sensors =
<&soctherm TEGRA124_SOCTHERM_SENSOR_CPU>;
+
+ trips {
+ cpu_shutdown_trip: shutdown-trip {
+ temperature = <102500>;
+ hysteresis = <1000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
index e5ee3f159893..a8e52c8ccfcc 100644
--- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
@@ -11,7 +11,6 @@ Required properties:
- "renesas,thermal-r8a7791" (R-Car M2-W)
- "renesas,thermal-r8a7792" (R-Car V2H)
- "renesas,thermal-r8a7793" (R-Car M2-N)
- - "renesas,thermal-r8a7794" (R-Car E2)
- reg : Address range of the thermal registers.
The 1st reg will be recognized as common register
if it has "interrupts".
diff --git a/Documentation/devicetree/bindings/thermal/tango-thermal.txt b/Documentation/devicetree/bindings/thermal/tango-thermal.txt
new file mode 100644
index 000000000000..212198d4b937
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/tango-thermal.txt
@@ -0,0 +1,17 @@
+* Tango Thermal
+
+The SMP8758 SoC includes 3 instances of this temperature sensor
+(in the CPU, video decoder, and PCIe controller).
+
+Required properties:
+- #thermal-sensor-cells: Should be 0 (see thermal.txt)
+- compatible: "sigma,smp8758-thermal"
+- reg: Address range of the thermal registers
+
+Example:
+
+ cpu_temp: thermal@920100 {
+ #thermal-sensor-cells = <0>;
+ compatible = "sigma,smp8758-thermal";
+ reg = <0x920100 12>;
+ };
diff --git a/Documentation/devicetree/bindings/thermal/thermal-generic-adc.txt b/Documentation/devicetree/bindings/thermal/thermal-generic-adc.txt
new file mode 100644
index 000000000000..d72355502b78
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/thermal-generic-adc.txt
@@ -0,0 +1,89 @@
+General Purpose Analog To Digital Converter (ADC) based thermal sensor.
+
+On some of platforms, thermal sensor like thermistors are connected to
+one of ADC channel and sensor resistance is read via voltage across the
+sensor resistor. The voltage read across the sensor is mapped to
+temperature using voltage-temperature lookup table.
+
+Required properties:
+===================
+- compatible: Must be "generic-adc-thermal".
+- temperature-lookup-table: Two dimensional array of Integer; lookup table
+ to map the relation between ADC value and
+ temperature. When ADC is read, the value is
+ looked up on the table to get the equivalent
+ temperature.
+ The first value of the each row of array is the
+ temperature in milliCelsius and second value of
+ the each row of array is the ADC read value.
+- #thermal-sensor-cells: Should be 1. See ./thermal.txt for a description
+ of this property.
+
+Example :
+#include <dt-bindings/thermal/thermal.h>
+
+i2c@7000c400 {
+ ads1015: ads1015@4a {
+ reg = <0x4a>;
+ compatible = "ads1015";
+ sampling-frequency = <3300>;
+ #io-channel-cells = <1>;
+ };
+};
+
+tboard_thermistor: thermal-sensor {
+ compatible = "generic-adc-thermal";
+ #thermal-sensor-cells = <0>;
+ io-channels = <&ads1015 1>;
+ io-channel-names = "sensor-channel";
+ temperature-lookup-table = < (-40000) 2578
+ (-39000) 2577
+ (-38000) 2576
+ (-37000) 2575
+ (-36000) 2574
+ (-35000) 2573
+ (-34000) 2572
+ (-33000) 2571
+ (-32000) 2569
+ (-31000) 2568
+ (-30000) 2567
+ ::::::::::
+ 118000 254
+ 119000 247
+ 120000 240
+ 121000 233
+ 122000 226
+ 123000 220
+ 124000 214
+ 125000 208>;
+};
+
+dummy_cool_dev: dummy-cool-dev {
+ compatible = "dummy-cooling-dev";
+ #cooling-cells = <2>; /* min followed by max */
+};
+
+thermal-zones {
+ Tboard {
+ polling-delay = <15000>; /* milliseconds */
+ polling-delay-passive = <0>; /* milliseconds */
+ thermal-sensors = <&tboard_thermistor>;
+
+ trips {
+ therm_est_trip: therm_est_trip {
+ temperature = <40000>;
+ type = "active";
+ hysteresis = <1000>;
+ };
+ };
+
+ cooling-maps {
+ map0 {
+ trip = <&therm_est_trip>;
+ cooling-device = <&dummy_cool_dev THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ contribution = <100>;
+ };
+
+ };
+ };
+};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index a7440bcd67ff..2c2500df0dce 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -255,6 +255,7 @@ synology Synology, Inc.
SUNW Sun Microsystems, Inc
tbs TBS Technologies
tcl Toby Churchill Ltd.
+technexion TechNexion
technologic Technologic Systems
thine THine Electronics, Inc.
ti Texas Instruments
@@ -269,6 +270,7 @@ tronsmart Tronsmart
truly Truly Semiconductors Limited
tyan Tyan Computer Corporation
upisemi uPI Semiconductor Corp.
+uniwest United Western Technologies Corp (UniWest)
urt United Radiant Technology Corporation
usi Universal Scientific Industrial Co., Ltd.
v3 V3 Semiconductor
diff --git a/Documentation/devicetree/bindings/watchdog/fsl-imx-wdt.txt b/Documentation/devicetree/bindings/watchdog/fsl-imx-wdt.txt
index 8dab6fd024aa..107280ef0025 100644
--- a/Documentation/devicetree/bindings/watchdog/fsl-imx-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/fsl-imx-wdt.txt
@@ -5,10 +5,12 @@ Required properties:
- reg : Should contain WDT registers location and length
- interrupts : Should contain WDT interrupt
-Optional property:
+Optional properties:
- big-endian: If present the watchdog device's registers are implemented
in big endian mode, otherwise in native mode(same with CPU), for more
detail please see: Documentation/devicetree/bindings/regmap/regmap.txt.
+- fsl,ext-reset-output: If present the watchdog device is configured to
+ assert its external reset (WDOG_B) instead of issuing a software reset.
Examples:
diff --git a/Documentation/devicetree/bindings/watchdog/microchip,pic32-dmt.txt b/Documentation/devicetree/bindings/watchdog/microchip,pic32-dmt.txt
index 852f694f3177..49485f831373 100644
--- a/Documentation/devicetree/bindings/watchdog/microchip,pic32-dmt.txt
+++ b/Documentation/devicetree/bindings/watchdog/microchip,pic32-dmt.txt
@@ -8,12 +8,12 @@ Required properties:
- compatible: must be "microchip,pic32mzda-dmt".
- reg: physical base address of the controller and length of memory mapped
region.
-- clocks: phandle of parent clock (should be &PBCLK7).
+- clocks: phandle of source clk. Should be <&rootclk PB7CLK>.
Example:
watchdog@1f800a00 {
compatible = "microchip,pic32mzda-dmt";
reg = <0x1f800a00 0x80>;
- clocks = <&PBCLK7>;
+ clocks = <&rootclk PB7CLK>;
};
diff --git a/Documentation/devicetree/bindings/watchdog/microchip,pic32-wdt.txt b/Documentation/devicetree/bindings/watchdog/microchip,pic32-wdt.txt
index d1401030e75c..f03a29a1b323 100644
--- a/Documentation/devicetree/bindings/watchdog/microchip,pic32-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/microchip,pic32-wdt.txt
@@ -7,12 +7,12 @@ Required properties:
- compatible: must be "microchip,pic32mzda-wdt".
- reg: physical base address of the controller and length of memory mapped
region.
-- clocks: phandle of source clk. should be <&LPRC> clk.
+- clocks: phandle of source clk. Should be <&rootclk LPRCCLK>.
Example:
watchdog@1f800800 {
compatible = "microchip,pic32mzda-wdt";
reg = <0x1f800800 0x200>;
- clocks = <&LPRC>;
+ clocks = <&rootclk LPRCCLK>;
};
diff --git a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt
new file mode 100644
index 000000000000..b9512f1eb80a
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt
@@ -0,0 +1,25 @@
+Renesas Watchdog Timer (WDT) Controller
+
+Required properties:
+- compatible : Should be "renesas,r8a7795-wdt", or "renesas,rcar-gen3-wdt"
+
+ When compatible with the generic version, nodes must list the SoC-specific
+ version corresponding to the platform first, followed by the generic
+ version.
+
+- reg : Should contain WDT registers location and length
+- clocks : the clock feeding the watchdog timer.
+
+Optional properties:
+- timeout-sec : Contains the watchdog timeout in seconds
+- power-domains : the power domain the WDT belongs to
+
+Examples:
+
+ wdt0: watchdog@e6020000 {
+ compatible = "renesas,r8a7795-wdt", "renesas,rcar-gen3-wdt";
+ reg = <0 0xe6020000 0 0x0c>;
+ clocks = <&cpg CPG_MOD 402>;
+ power-domains = <&cpg>;
+ timeout-sec = <60>;
+ };
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 7bde64014a89..ce4587d257d2 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -79,6 +79,38 @@ These filesystems may be used for inspiration:
- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
+Handling Media Errors
+---------------------
+
+The libnvdimm subsystem stores a record of known media error locations for
+each pmem block device (in gendisk->badblocks). If we fault at such location,
+or one with a latent error not yet discovered, the application can expect
+to receive a SIGBUS. Libnvdimm also allows clearing of these errors by simply
+writing the affected sectors (through the pmem driver, and if the underlying
+NVDIMM supports the clear_poison DSM defined by ACPI).
+
+Since DAX IO normally doesn't go through the driver/bio path, applications or
+sysadmins have an option to restore the lost data from a prior backup/inbuilt
+redundancy in the following ways:
+
+1. Delete the affected file, and restore from a backup (sysadmin route):
+ This will free the file system blocks that were being used by the file,
+ and the next time they're allocated, they will be zeroed first, which
+ happens through the driver, and will clear bad sectors.
+
+2. Truncate or hole-punch the part of the file that has a bad-block (at least
+ an entire aligned sector has to be hole-punched, but not necessarily an
+ entire filesystem block).
+
+These are the two basic paths that allow DAX filesystems to continue operating
+in the presence of media errors. More robust error recovery mechanisms can be
+built on top of this in the future, for example, involving redundancy/mirroring
+provided at the block layer through DM, or additionally, at the filesystem
+level. These would have to rely on the above two tenets, that error clearing
+can happen either by sending an IO through the driver, or zeroing (also through
+the driver).
+
+
Shortcomings
------------
diff --git a/Documentation/filesystems/devpts.txt b/Documentation/filesystems/devpts.txt
index 30d2fcb32f72..9f94fe276dea 100644
--- a/Documentation/filesystems/devpts.txt
+++ b/Documentation/filesystems/devpts.txt
@@ -1,141 +1,26 @@
+Each mount of the devpts filesystem is now distinct such that ptys
+and their indicies allocated in one mount are independent from ptys
+and their indicies in all other mounts.
-To support containers, we now allow multiple instances of devpts filesystem,
-such that indices of ptys allocated in one instance are independent of indices
-allocated in other instances of devpts.
+All mounts of the devpts filesystem now create a /dev/pts/ptmx node
+with permissions 0000.
-To preserve backward compatibility, this support for multiple instances is
-enabled only if:
+To retain backwards compatibility the a ptmx device node (aka any node
+created with "mknod name c 5 2") when opened will look for an instance
+of devpts under the name "pts" in the same directory as the ptmx device
+node.
- - CONFIG_DEVPTS_MULTIPLE_INSTANCES=y, and
- - '-o newinstance' mount option is specified while mounting devpts
-
-IOW, devpts now supports both single-instance and multi-instance semantics.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=n, there is no change in behavior and
-this referred to as the "legacy" mode. In this mode, the new mount options
-(-o newinstance and -o ptmxmode) will be ignored with a 'bogus option' message
-on console.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and devpts is mounted without the
-'newinstance' option (as in current start-up scripts) the new mount binds
-to the initial kernel mount of devpts. This mode is referred to as the
-'single-instance' mode and the current, single-instance semantics are
-preserved, i.e PTYs are common across the system.
-
-The only difference between this single-instance mode and the legacy mode
-is the presence of new, '/dev/pts/ptmx' node with permissions 0000, which
-can safely be ignored.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and 'newinstance' option is specified,
-the mount is considered to be in the multi-instance mode and a new instance
-of the devpts fs is created. Any ptys created in this instance are independent
-of ptys in other instances of devpts. Like in the single-instance mode, the
-/dev/pts/ptmx node is present. To effectively use the multi-instance mode,
-open of /dev/ptmx must be a redirected to '/dev/pts/ptmx' using a symlink or
-bind-mount.
-
-Eg: A container startup script could do the following:
-
- $ chmod 0666 /dev/pts/ptmx
- $ rm /dev/ptmx
- $ ln -s pts/ptmx /dev/ptmx
- $ ns_exec -cm /bin/bash
-
- # We are now in new container
-
- $ umount /dev/pts
- $ mount -t devpts -o newinstance lxcpts /dev/pts
- $ sshd -p 1234
-
-where 'ns_exec -cm /bin/bash' calls clone() with CLONE_NEWNS flag and execs
-/bin/bash in the child process. A pty created by the sshd is not visible in
-the original mount of /dev/pts.
+As an option instead of placing a /dev/ptmx device node at /dev/ptmx
+it is possible to place a symlink to /dev/pts/ptmx at /dev/ptmx or
+to bind mount /dev/ptx/ptmx to /dev/ptmx. If you opt for using
+the devpts filesystem in this manner devpts should be mounted with
+the ptmxmode=0666, or chmod 0666 /dev/pts/ptmx should be called.
Total count of pty pairs in all instances is limited by sysctls:
kernel.pty.max = 4096 - global limit
-kernel.pty.reserve = 1024 - reserve for initial instance
+kernel.pty.reserve = 1024 - reserved for filesystems mounted from the initial mount namespace
kernel.pty.nr - current count of ptys
Per-instance limit could be set by adding mount option "max=<count>".
This feature was added in kernel 3.4 together with sysctl kernel.pty.reserve.
In kernels older than 3.4 sysctl kernel.pty.max works as per-instance limit.
-
-User-space changes
-------------------
-
-In multi-instance mode (i.e '-o newinstance' mount option is specified at least
-once), following user-space issues should be noted.
-
-1. If -o newinstance mount option is never used, /dev/pts/ptmx can be ignored
- and no change is needed to system-startup scripts.
-
-2. To effectively use multi-instance mode (i.e -o newinstance is specified)
- administrators or startup scripts should "redirect" open of /dev/ptmx to
- /dev/pts/ptmx using either a bind mount or symlink.
-
- $ mount -t devpts -o newinstance devpts /dev/pts
-
- followed by either
-
- $ rm /dev/ptmx
- $ ln -s pts/ptmx /dev/ptmx
- $ chmod 666 /dev/pts/ptmx
- or
- $ mount -o bind /dev/pts/ptmx /dev/ptmx
-
-3. The '/dev/ptmx -> pts/ptmx' symlink is the preferred method since it
- enables better error-reporting and treats both single-instance and
- multi-instance mounts similarly.
-
- But this method requires that system-startup scripts set the mode of
- /dev/pts/ptmx correctly (default mode is 0000). The scripts can set the
- mode by, either
-
- - adding ptmxmode mount option to devpts entry in /etc/fstab, or
- - using 'chmod 0666 /dev/pts/ptmx'
-
-4. If multi-instance mode mount is needed for containers, but the system
- startup scripts have not yet been updated, container-startup scripts
- should bind mount /dev/ptmx to /dev/pts/ptmx to avoid breaking single-
- instance mounts.
-
- Or, in general, container-startup scripts should use:
-
- mount -t devpts -o newinstance -o ptmxmode=0666 devpts /dev/pts
- if [ ! -L /dev/ptmx ]; then
- mount -o bind /dev/pts/ptmx /dev/ptmx
- fi
-
- When all devpts mounts are multi-instance, /dev/ptmx can permanently be
- a symlink to pts/ptmx and the bind mount can be ignored.
-
-5. A multi-instance mount that is not accompanied by the /dev/ptmx to
- /dev/pts/ptmx redirection would result in an unusable/unreachable pty.
-
- mount -t devpts -o newinstance lxcpts /dev/pts
-
- immediately followed by:
-
- open("/dev/ptmx")
-
- would create a pty, say /dev/pts/7, in the initial kernel mount.
- But /dev/pts/7 would be invisible in the new mount.
-
-6. The permissions for /dev/pts/ptmx node should be specified when mounting
- /dev/pts, using the '-o ptmxmode=%o' mount option (default is 0000).
-
- mount -t devpts -o newinstance -o ptmxmode=0644 devpts /dev/pts
-
- The permissions can be later be changed as usual with 'chmod'.
-
- chmod 666 /dev/pts/ptmx
-
-7. A mount of devpts without the 'newinstance' option results in binding to
- initial kernel mount. This behavior while preserving legacy semantics,
- does not provide strict isolation in a container environment. i.e by
- mounting devpts without the 'newinstance' option, a container could
- get visibility into the 'host' or root container's devpts.
-
- To workaround this and have strict isolation, all mounts of devpts,
- including the mount in the root container, should use the newinstance
- option.
diff --git a/Documentation/filesystems/directory-locking b/Documentation/filesystems/directory-locking
index 09bbf9a54f80..c314badbcfc6 100644
--- a/Documentation/filesystems/directory-locking
+++ b/Documentation/filesystems/directory-locking
@@ -1,30 +1,37 @@
Locking scheme used for directory operations is based on two
-kinds of locks - per-inode (->i_mutex) and per-filesystem
+kinds of locks - per-inode (->i_rwsem) and per-filesystem
(->s_vfs_rename_mutex).
- When taking the i_mutex on multiple non-directory objects, we
+ When taking the i_rwsem on multiple non-directory objects, we
always acquire the locks in order by increasing address. We'll call
that "inode pointer" order in the following.
For our purposes all operations fall in 5 classes:
1) read access. Locking rules: caller locks directory we are accessing.
+The lock is taken shared.
-2) object creation. Locking rules: same as above.
+2) object creation. Locking rules: same as above, but the lock is taken
+exclusive.
3) object removal. Locking rules: caller locks parent, finds victim,
-locks victim and calls the method.
+locks victim and calls the method. Locks are exclusive.
4) rename() that is _not_ cross-directory. Locking rules: caller locks
-the parent and finds source and target. If target already exists, lock
-it. If source is a non-directory, lock it. If that means we need to
-lock both, lock them in inode pointer order.
+the parent and finds source and target. In case of exchange (with
+RENAME_EXCHANGE in rename2() flags argument) lock both. In any case,
+if the target already exists, lock it. If the source is a non-directory,
+lock it. If we need to lock both, lock them in inode pointer order.
+Then call the method. All locks are exclusive.
+NB: we might get away with locking the the source (and target in exchange
+case) shared.
5) link creation. Locking rules:
* lock parent
* check that source is not a directory
* lock source
* call the method.
+All locks are exclusive.
6) cross-directory rename. The trickiest in the whole bunch. Locking
rules:
@@ -35,11 +42,12 @@ rules:
fail with -ENOTEMPTY
* if new parent is equal to or is a descendent of source
fail with -ELOOP
- * If target exists, lock it. If source is a non-directory, lock
- it. In case that means we need to lock both source and target,
- do so in inode pointer order.
+ * If it's an exchange, lock both the source and the target.
+ * If the target exists, lock it. If the source is a non-directory,
+ lock it. If we need to lock both, do so in inode pointer order.
* call the method.
-
+All ->i_rwsem are taken exclusive. Again, we might get away with locking
+the the source (and target in exchange case) shared.
The rules above obviously guarantee that all directories that are going to be
read, modified or removed by method will be locked by caller.
@@ -73,7 +81,7 @@ objects - A < B iff A is an ancestor of B.
attempt to acquire some lock and already holds at least one lock. Let's
consider the set of contended locks. First of all, filesystem lock is
not contended, since any process blocked on it is not holding any locks.
-Thus all processes are blocked on ->i_mutex.
+Thus all processes are blocked on ->i_rwsem.
By (3), any process holding a non-directory lock can only be
waiting on another non-directory lock with a larger address. Therefore
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index 28091457b71a..d6259c786316 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -194,15 +194,6 @@ If a file with multiple hard links is copied up, then this will
"break" the link. Changes will not be propagated to other names
referring to the same inode.
-Symlinks in /proc/PID/ and /proc/PID/fd which point to a non-directory
-object in overlayfs will not contain valid absolute paths, only
-relative paths leading up to the filesystem's root. This will be
-fixed in the future.
-
-Some operations are not atomic, for example a crash during copy_up or
-rename will leave the filesystem in an inconsistent state. This will
-be addressed in the future.
-
Changes to underlying filesystems
---------------------------------
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 46f3bb7a02f5..a5fb89cac615 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -578,3 +578,10 @@ in your dentry operations instead.
--
[mandatory]
->atomic_open() calls without O_CREAT may happen in parallel.
+--
+[mandatory]
+ ->setxattr() and xattr_handler.set() get dentry and inode passed separately.
+ dentry might be yet to be attached to inode, so do _not_ use its ->d_inode
+ in the instances. Rationale: !@#!@# security_d_instantiate() needs to be
+ called before we attach dentry to inode and !@#!@##!@$!$#!@#$!@$!@$ smack
+ ->d_instantiate() uses not just ->getxattr() but ->setxattr() as well.
diff --git a/Documentation/hwmon/max34440 b/Documentation/hwmon/max34440
index f5b1fcaa9e4e..9ba6587b7657 100644
--- a/Documentation/hwmon/max34440
+++ b/Documentation/hwmon/max34440
@@ -5,17 +5,17 @@ Supported chips:
* Maxim MAX34440
Prefixes: 'max34440'
Addresses scanned: -
- Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX34440.pdf
+ Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34440.pdf
* Maxim MAX34441
PMBus 5-Channel Power-Supply Manager and Intelligent Fan Controller
Prefixes: 'max34441'
Addresses scanned: -
- Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX34441.pdf
+ Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34441.pdf
* Maxim MAX34446
PMBus Power-Supply Data Logger
Prefixes: 'max34446'
Addresses scanned: -
- Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX34446.pdf
+ Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34446.pdf
* Maxim MAX34460
PMBus 12-Channel Voltage Monitor & Sequencer
Prefix: 'max34460'
diff --git a/Documentation/infiniband/sysfs.txt b/Documentation/infiniband/sysfs.txt
index 3ecf0c3a133f..45bcafe6ff8a 100644
--- a/Documentation/infiniband/sysfs.txt
+++ b/Documentation/infiniband/sysfs.txt
@@ -56,6 +56,18 @@ SYSFS FILES
ports/1/pkeys/10 contains the value at index 10 in port 1's P_Key
table.
+ There is an optional "hw_counters" subdirectory that may be under either
+ the parent device or the port subdirectories or both. If present,
+ there are a list of counters provided by the hardware. They may match
+ some of the counters in the counters directory, but they often include
+ many other counters. In addition to the various counters, there will
+ be a file named "lifespan" that configures how frequently the core
+ should update the counters when they are being accessed (counters are
+ not updated if they are not being accessed). The lifespan is in milli-
+ seconds and defaults to 10 unless set to something else by the driver.
+ Users may echo a value between 0 - 10000 to the lifespan file to set
+ the length of time between updates in milliseconds.
+
MTHCA
The Mellanox HCA driver also creates the files:
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index c52856da0cad..db101857b2c9 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -241,9 +241,8 @@ comment "module support disabled"
depends on !MODULES
MODVERSIONS directly depends on MODULES, this means it's only visible if
-MODULES is different from 'n'. The comment on the other hand is always
-visible when MODULES is visible (the (empty) dependency of MODULES is
-also part of the comment dependencies).
+MODULES is different from 'n'. The comment on the other hand is only
+visible when MODULES is set to 'n'.
Kconfig syntax
@@ -285,12 +284,17 @@ choices:
"endchoice"
This defines a choice group and accepts any of the above attributes as
-options. A choice can only be of type bool or tristate, while a boolean
-choice only allows a single config entry to be selected, a tristate
-choice also allows any number of config entries to be set to 'm'. This
-can be used if multiple drivers for a single hardware exists and only a
-single driver can be compiled/loaded into the kernel, but all drivers
-can be compiled as modules.
+options. A choice can only be of type bool or tristate. If no type is
+specified for a choice, it's type will be determined by the type of
+the first choice element in the group or remain unknown if none of the
+choice elements have a type specified, as well.
+
+While a boolean choice only allows a single config entry to be
+selected, a tristate choice also allows any number of config entries
+to be set to 'm'. This can be used if multiple drivers for a single
+hardware exists and only a single driver can be compiled/loaded into
+the kernel, but all drivers can be compiled as modules.
+
A choice accepts another option "optional", which allows to set the
choice to 'n' and no entry needs to be selected.
If no [symbol] is associated with a choice, then you can not have multiple
diff --git a/Documentation/kdump/gdbmacros.txt b/Documentation/kdump/gdbmacros.txt
index 35f6a982a0d5..220d0a80ca2c 100644
--- a/Documentation/kdump/gdbmacros.txt
+++ b/Documentation/kdump/gdbmacros.txt
@@ -170,21 +170,92 @@ document trapinfo
address the kernel panicked.
end
+define dump_log_idx
+ set $idx = $arg0
+ if ($argc > 1)
+ set $prev_flags = $arg1
+ else
+ set $prev_flags = 0
+ end
+ set $msg = ((struct printk_log *) (log_buf + $idx))
+ set $prefix = 1
+ set $newline = 1
+ set $log = log_buf + $idx + sizeof(*$msg)
-define dmesg
- set $i = 0
- set $end_idx = (log_end - 1) & (log_buf_len - 1)
+ # prev & LOG_CONT && !(msg->flags & LOG_PREIX)
+ if (($prev_flags & 8) && !($msg->flags & 4))
+ set $prefix = 0
+ end
+
+ # msg->flags & LOG_CONT
+ if ($msg->flags & 8)
+ # (prev & LOG_CONT && !(prev & LOG_NEWLINE))
+ if (($prev_flags & 8) && !($prev_flags & 2))
+ set $prefix = 0
+ end
+ # (!(msg->flags & LOG_NEWLINE))
+ if (!($msg->flags & 2))
+ set $newline = 0
+ end
+ end
+
+ if ($prefix)
+ printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000
+ end
+ if ($msg->text_len != 0)
+ eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len
+ end
+ if ($newline)
+ printf "\n"
+ end
+ if ($msg->dict_len > 0)
+ set $dict = $log + $msg->text_len
+ set $idx = 0
+ set $line = 1
+ while ($idx < $msg->dict_len)
+ if ($line)
+ printf " "
+ set $line = 0
+ end
+ set $c = $dict[$idx]
+ if ($c == '\0')
+ printf "\n"
+ set $line = 1
+ else
+ if ($c < ' ' || $c >= 127 || $c == '\\')
+ printf "\\x%02x", $c
+ else
+ printf "%c", $c
+ end
+ end
+ set $idx = $idx + 1
+ end
+ printf "\n"
+ end
+end
+document dump_log_idx
+ Dump a single log given its index in the log buffer. The first
+ parameter is the index into log_buf, the second is optional and
+ specified the previous log buffer's flags, used for properly
+ formatting continued lines.
+end
- while ($i < logged_chars)
- set $idx = (log_end - 1 - logged_chars + $i) & (log_buf_len - 1)
+define dmesg
+ set $i = log_first_idx
+ set $end_idx = log_first_idx
+ set $prev_flags = 0
- if ($idx + 100 <= $end_idx) || \
- ($end_idx <= $idx && $idx + 100 < log_buf_len)
- printf "%.100s", &log_buf[$idx]
- set $i = $i + 100
+ while (1)
+ set $msg = ((struct printk_log *) (log_buf + $i))
+ if ($msg->len == 0)
+ set $i = 0
else
- printf "%c", log_buf[$idx]
- set $i = $i + 1
+ dump_log_idx $i $prev_flags
+ set $i = $i + $msg->len
+ set $prev_flags = $msg->flags
+ end
+ if ($i == $end_idx)
+ loop_break
end
end
end
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index d406d98339b2..44f5e6bccd97 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -74,8 +74,8 @@ blink_set() function (see <linux/leds.h>). To set an LED to blinking,
however, it is better to use the API function led_blink_set(), as it
will check and implement software fallback if necessary.
-To turn off blinking again, use the API function led_brightness_set()
-as that will not just set the LED brightness but also stop any software
+To turn off blinking, use the API function led_brightness_set()
+with brightness value LED_OFF, which should stop any software
timers that may have been required for blinking.
The blink_set() function should choose a user friendly blinking value
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
index 631b0f7ae16f..9d05ed7f7da5 100644
--- a/Documentation/networking/dsa/dsa.txt
+++ b/Documentation/networking/dsa/dsa.txt
@@ -369,8 +369,6 @@ does not allocate any driver private context space.
Switch configuration
--------------------
-- priv_size: additional size needed by the switch driver for its private context
-
- tag_protocol: this is to indicate what kind of tagging protocol is supported,
should be a valid value from the dsa_tag_protocol enum
@@ -416,11 +414,6 @@ PHY devices and link management
to the switch port MDIO registers. If unavailable return a negative error
code.
-- poll_link: Function invoked by DSA to query the link state of the switch
- builtin Ethernet PHYs, per port. This function is responsible for calling
- netif_carrier_{on,off} when appropriate, and can be used to poll all ports in a
- single call. Executes from workqueue context.
-
- adjust_link: Function invoked by the PHY library when a slave network device
is attached to a PHY device. This function is responsible for appropriately
configuring the switch port link parameters: speed, duplex, pause based on
@@ -542,6 +535,16 @@ Bridge layer
Bridge VLAN filtering
---------------------
+- port_vlan_filtering: bridge layer function invoked when the bridge gets
+ configured for turning on or off VLAN filtering. If nothing specific needs to
+ be done at the hardware level, this callback does not need to be implemented.
+ When VLAN filtering is turned on, the hardware must be programmed with
+ rejecting 802.1Q frames which have VLAN IDs outside of the programmed allowed
+ VLAN ID map/rules. If there is no PVID programmed into the switch port,
+ untagged frames must be rejected as well. When turned off the switch must
+ accept any 802.1Q frames irrespective of their VLAN ID, and untagged frames are
+ allowed.
+
- port_vlan_prepare: bridge layer function invoked when the bridge prepares the
configuration of a VLAN on the given port. If the operation is not supported
by the hardware, this function should return -EOPNOTSUPP to inform the bridge
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6c7f365b1515..9ae929395b24 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1036,15 +1036,17 @@ proxy_arp_pvlan - BOOLEAN
shared_media - BOOLEAN
Send(router) or accept(host) RFC1620 shared media redirects.
- Overrides ip_secure_redirects.
+ Overrides secure_redirects.
shared_media for the interface will be enabled if at least one of
conf/{all,interface}/shared_media is set to TRUE,
it will be disabled otherwise
default TRUE
secure_redirects - BOOLEAN
- Accept ICMP redirect messages only for gateways,
- listed in default gateway list.
+ Accept ICMP redirect messages only to gateways listed in the
+ interface's current gateway list. Even if disabled, RFC1122 redirect
+ rules still apply.
+ Overridden by shared_media.
secure_redirects for the interface will be enabled if at least one of
conf/{all,interface}/secure_redirects is set to TRUE,
it will be disabled otherwise
diff --git a/Documentation/pwm.txt b/Documentation/pwm.txt
index ca895fd211e4..789b27c6ec99 100644
--- a/Documentation/pwm.txt
+++ b/Documentation/pwm.txt
@@ -42,9 +42,26 @@ variants of these functions, devm_pwm_get() and devm_pwm_put(), also exist.
After being requested, a PWM has to be configured using:
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns);
+int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state);
-To start/stop toggling the PWM output use pwm_enable()/pwm_disable().
+This API controls both the PWM period/duty_cycle config and the
+enable/disable state.
+
+The pwm_config(), pwm_enable() and pwm_disable() functions are just wrappers
+around pwm_apply_state() and should not be used if the user wants to change
+several parameter at once. For example, if you see pwm_config() and
+pwm_{enable,disable}() calls in the same function, this probably means you
+should switch to pwm_apply_state().
+
+The PWM user API also allows one to query the PWM state with pwm_get_state().
+
+In addition to the PWM state, the PWM API also exposes PWM arguments, which
+are the reference PWM config one should use on this PWM.
+PWM arguments are usually platform-specific and allows the PWM user to only
+care about dutycycle relatively to the full period (like, duty = 50% of the
+period). struct pwm_args contains 2 fields (period and polarity) and should
+be used to set the initial PWM config (usually done in the probe function
+of the PWM user). PWM arguments are retrieved with pwm_get_args().
Using PWMs with the sysfs interface
-----------------------------------
@@ -105,6 +122,15 @@ goes low for the remainder of the period. Conversely, a signal with inversed
polarity starts low for the duration of the duty cycle and goes high for the
remainder of the period.
+Drivers are encouraged to implement ->apply() instead of the legacy
+->enable(), ->disable() and ->config() methods. Doing that should provide
+atomicity in the PWM config workflow, which is required when the PWM controls
+a critical device (like a regulator).
+
+The implementation of ->get_state() (a method used to retrieve initial PWM
+state) is also encouraged for the same reason: letting the PWM user know
+about the current PWM state would allow him to avoid glitches.
+
Locking
-------
diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 8638f61c8c9d..37eca00796ee 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -263,19 +263,23 @@ scmd->allowed.
3. scmd recovered
ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
- - shost->host_failed--
- clear scmd->eh_eflags
- scsi_setup_cmd_retry()
- move from local eh_work_q to local eh_done_q
LOCKING: none
+ CONCURRENCY: at most one thread per separate eh_work_q to
+ keep queue manipulation lockless
4. EH completes
ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
- layer of failure.
+ layer of failure. May be called concurrently but must have
+ a no more than one thread per separate eh_work_q to
+ manipulate the queue locklessly
- scmd is removed from eh_done_q and scmd->eh_entry is cleared
- if retry is necessary, scmd is requeued using
scsi_queue_insert()
- otherwise, scsi_finish_command() is invoked for scmd
+ - zero shost->host_failed
LOCKING: queue or finish function performs appropriate locking
diff --git a/Documentation/scsi/tcm_qla2xxx.txt b/Documentation/scsi/tcm_qla2xxx.txt
new file mode 100644
index 000000000000..c3a670a25e2b
--- /dev/null
+++ b/Documentation/scsi/tcm_qla2xxx.txt
@@ -0,0 +1,22 @@
+tcm_qla2xxx jam_host attribute
+------------------------------
+There is now a new module endpoint atribute called jam_host
+attribute: jam_host: boolean=0/1
+This attribute and accompanying code is only included if the
+Kconfig parameter TCM_QLA2XXX_DEBUG is set to Y
+By default this jammer code and functionality is disabled
+
+Use this attribute to control the discarding of SCSI commands to a
+selected host.
+This may be useful for testing error handling and simulating slow drain
+and other fabric issues.
+
+Setting a boolean of 1 for the jam_host attribute for a particular host
+ will discard the commands for that host.
+Reset back to 0 to stop the jamming.
+
+Enable host 4 to be jammed
+echo 1 > /sys/kernel/config/target/qla2xxx/21:00:00:24:ff:27:8f:ae/tpgt_1/attrib/jam_host
+
+Disable jamming on host 4
+echo 0 > /sys/kernel/config/target/qla2xxx/21:00:00:24:ff:27:8f:ae/tpgt_1/attrib/jam_host
diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 20d05719bceb..3849814bfe6d 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -826,7 +826,8 @@ The keyctl syscall functions are:
(*) Compute a Diffie-Hellman shared secret or public key
long keyctl(KEYCTL_DH_COMPUTE, struct keyctl_dh_params *params,
- char *buffer, size_t buflen);
+ char *buffer, size_t buflen,
+ void *reserved);
The params struct contains serial numbers for three keys:
@@ -843,6 +844,8 @@ The keyctl syscall functions are:
public key. If the base is the remote public key, the result is
the shared secret.
+ The reserved argument must be set to NULL.
+
The buffer length must be at least the length of the prime, or zero.
If the buffer length is nonzero, the length of the result is
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index daabdd7ee543..a3683ce2a2f3 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -61,6 +61,7 @@ show up in /proc/sys/kernel:
- perf_cpu_time_max_percent
- perf_event_paranoid
- perf_event_max_stack
+- perf_event_max_contexts_per_stack
- pid_max
- powersave-nap [ PPC only ]
- printk
@@ -668,6 +669,19 @@ The default value is 127.
==============================================================
+perf_event_max_contexts_per_stack:
+
+Controls maximum number of stack frame context entries for
+(attr.sample_type & PERF_SAMPLE_CALLCHAIN) configured events, for
+instance, when using 'perf record -g' or 'perf trace --call-graph fp'.
+
+This can only be done when no events are in use that have callchains
+enabled, otherwise writing to this file will return -EBUSY.
+
+The default value is 8.
+
+==============================================================
+
pid_max:
PID allocation wrap value. When the kernel's next PID value
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 7d370c9b1450..94bf6944bb1e 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -294,8 +294,6 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
buf += " .tpg_check_prod_mode_write_protect = " + fabric_mod_name + "_check_false,\n"
buf += " .tpg_get_inst_index = " + fabric_mod_name + "_tpg_get_inst_index,\n"
buf += " .release_cmd = " + fabric_mod_name + "_release_cmd,\n"
- buf += " .shutdown_session = " + fabric_mod_name + "_shutdown_session,\n"
- buf += " .close_session = " + fabric_mod_name + "_close_session,\n"
buf += " .sess_get_index = " + fabric_mod_name + "_sess_get_index,\n"
buf += " .sess_get_initiator_sid = NULL,\n"
buf += " .write_pending = " + fabric_mod_name + "_write_pending,\n"
@@ -467,20 +465,6 @@ def tcm_mod_dump_fabric_ops(proto_ident, fabric_mod_dir_var, fabric_mod_name):
buf += "}\n\n"
bufi += "void " + fabric_mod_name + "_release_cmd(struct se_cmd *);\n"
- if re.search('shutdown_session\)\(', fo):
- buf += "int " + fabric_mod_name + "_shutdown_session(struct se_session *se_sess)\n"
- buf += "{\n"
- buf += " return 0;\n"
- buf += "}\n\n"
- bufi += "int " + fabric_mod_name + "_shutdown_session(struct se_session *);\n"
-
- if re.search('close_session\)\(', fo):
- buf += "void " + fabric_mod_name + "_close_session(struct se_session *se_sess)\n"
- buf += "{\n"
- buf += " return;\n"
- buf += "}\n\n"
- bufi += "void " + fabric_mod_name + "_close_session(struct se_session *);\n"
-
if re.search('sess_get_index\)\(', fo):
buf += "u32 " + fabric_mod_name + "_sess_get_index(struct se_session *se_sess)\n"
buf += "{\n"
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index ed419d6c8dec..efc3f3d293c4 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -69,8 +69,8 @@ temperature) and throttle appropriate devices.
1.1.2 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
This interface function removes the thermal zone device.
- It deletes the corresponding entry form /sys/class/thermal folder and
- unbind all the thermal cooling devices it uses.
+ It deletes the corresponding entry from /sys/class/thermal folder and
+ unbinds all the thermal cooling devices it uses.
1.1.3 struct thermal_zone_device *thermal_zone_of_sensor_register(
struct device *dev, int sensor_id, void *data,
@@ -146,32 +146,32 @@ temperature) and throttle appropriate devices.
This interface function adds a new thermal cooling device (fan/processor/...)
to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
- to all the thermal zone devices register at the same time.
+ to all the thermal zone devices registered at the same time.
name: the cooling device name.
devdata: device private data.
ops: thermal cooling devices call-backs.
.get_max_state: get the Maximum throttle state of the cooling device.
- .get_cur_state: get the Current throttle state of the cooling device.
+ .get_cur_state: get the Currently requested throttle state of the cooling device.
.set_cur_state: set the Current throttle state of the cooling device.
1.2.2 void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
- This interface function remove the thermal cooling device.
- It deletes the corresponding entry form /sys/class/thermal folder and
- unbind itself from all the thermal zone devices using it.
+ This interface function removes the thermal cooling device.
+ It deletes the corresponding entry from /sys/class/thermal folder and
+ unbinds itself from all the thermal zone devices using it.
1.3 interface for binding a thermal zone device with a thermal cooling device
1.3.1 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
int trip, struct thermal_cooling_device *cdev,
unsigned long upper, unsigned long lower, unsigned int weight);
- This interface function bind a thermal cooling device to the certain trip
+ This interface function binds a thermal cooling device to a particular trip
point of a thermal zone device.
This function is usually called in the thermal zone device .bind callback.
tz: the thermal zone device
cdev: thermal cooling device
- trip: indicates which trip point the cooling devices is associated with
- in this thermal zone.
+ trip: indicates which trip point in this thermal zone the cooling device
+ is associated with.
upper:the Maximum cooling state for this trip point.
THERMAL_NO_LIMIT means no upper limit,
and the cooling device can be in max_state.
@@ -184,13 +184,13 @@ temperature) and throttle appropriate devices.
1.3.2 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
int trip, struct thermal_cooling_device *cdev);
- This interface function unbind a thermal cooling device from the certain
+ This interface function unbinds a thermal cooling device from a particular
trip point of a thermal zone device. This function is usually called in
the thermal zone device .unbind callback.
tz: the thermal zone device
cdev: thermal cooling device
- trip: indicates which trip point the cooling devices is associated with
- in this thermal zone.
+ trip: indicates which trip point in this thermal zone the cooling device
+ is associated with.
1.4 Thermal Zone Parameters
1.4.1 struct thermal_bind_params
@@ -210,13 +210,13 @@ temperature) and throttle appropriate devices.
this thermal zone and cdev, for a particular trip point.
If nth bit is set, then the cdev and thermal zone are bound
for trip point n.
- .limits: This is an array of cooling state limits. Must have exactly
- 2 * thermal_zone.number_of_trip_points. It is an array consisting
- of tuples <lower-state upper-state> of state limits. Each trip
- will be associated with one state limit tuple when binding.
- A NULL pointer means <THERMAL_NO_LIMITS THERMAL_NO_LIMITS>
- on all trips. These limits are used when binding a cdev to a
- trip point.
+ .binding_limits: This is an array of cooling state limits. Must have
+ exactly 2 * thermal_zone.number_of_trip_points. It is an
+ array consisting of tuples <lower-state upper-state> of
+ state limits. Each trip will be associated with one state
+ limit tuple when binding. A NULL pointer means
+ <THERMAL_NO_LIMITS THERMAL_NO_LIMITS> on all trips.
+ These limits are used when binding a cdev to a trip point.
.match: This call back returns success(0) if the 'tz and cdev' need to
be bound, as per platform data.
1.4.2 struct thermal_zone_params
@@ -351,8 +351,8 @@ cdev[0-*]
RO, Optional
cdev[0-*]_trip_point
- The trip point with which cdev[0-*] is associated in this thermal
- zone; -1 means the cooling device is not associated with any trip
+ The trip point in this thermal zone which cdev[0-*] is associated
+ with; -1 means the cooling device is not associated with any trip
point.
RO, Optional
diff --git a/Documentation/watchdog/hpwdt.txt b/Documentation/watchdog/hpwdt.txt
index 9488078900e0..a40398cce9d1 100644
--- a/Documentation/watchdog/hpwdt.txt
+++ b/Documentation/watchdog/hpwdt.txt
@@ -1,64 +1,67 @@
-Last reviewed: 06/02/2009
+Last reviewed: 04/04/2016
- HP iLO2 NMI Watchdog Driver
- NMI sourcing for iLO2 based ProLiant Servers
+ HPE iLO NMI Watchdog Driver
+ NMI sourcing for iLO based ProLiant Servers
Documentation and Driver by
- Thomas Mingarelli <thomas.mingarelli@hp.com>
+ Thomas Mingarelli <thomas.mingarelli@hpe.com>
- The HP iLO2 NMI Watchdog driver is a kernel module that provides basic
+ The HPE iLO NMI Watchdog driver is a kernel module that provides basic
watchdog functionality and the added benefit of NMI sourcing. Both the
watchdog functionality and the NMI sourcing capability need to be enabled
by the user. Remember that the two modes are not dependent on one another.
A user can have the NMI sourcing without the watchdog timer and vice-versa.
+ All references to iLO in this document imply it also works on iLO2 and all
+ subsequent generations.
Watchdog functionality is enabled like any other common watchdog driver. That
is, an application needs to be started that kicks off the watchdog timer. A
basic application exists in the Documentation/watchdog/src directory called
watchdog-test.c. Simply compile the C file and kick it off. If the system
- gets into a bad state and hangs, the HP ProLiant iLO 2 timer register will
+ gets into a bad state and hangs, the HPE ProLiant iLO timer register will
not be updated in a timely fashion and a hardware system reset (also known as
an Automatic Server Recovery (ASR)) event will occur.
- The hpwdt driver also has four (4) module parameters. They are the following:
+ The hpwdt driver also has three (3) module parameters. They are the following:
- soft_margin - allows the user to set the watchdog timer value
- allow_kdump - allows the user to save off a kernel dump image after an NMI
+ soft_margin - allows the user to set the watchdog timer value.
+ Default value is 30 seconds.
+ allow_kdump - allows the user to save off a kernel dump image after an NMI.
+ Default value is 1/ON
nowayout - basic watchdog parameter that does not allow the timer to
be restarted or an impending ASR to be escaped.
- priority - determines whether or not the hpwdt driver is first on the
- die_notify list to handle NMIs or last. The default value
- for this module parameter is 0 or LAST. If the user wants to
- enable NMI sourcing then reload the hpwdt driver with
- priority=1 (and boot with nmi_watchdog=0).
+ Default value is set when compiling the kernel. If it is set
+ to "Y", then there is no way of disabling the watchdog once
+ it has been started.
NOTE: More information about watchdog drivers in general, including the ioctl
interface to /dev/watchdog can be found in
Documentation/watchdog/watchdog-api.txt and Documentation/IPMI.txt.
- The priority parameter was introduced due to other kernel software that relied
- on handling NMIs (like oprofile). Keeping hpwdt's priority at 0 (or LAST)
- enables the users of NMIs for non critical events to be work as expected.
-
The NMI sourcing capability is disabled by default due to the inability to
distinguish between "NMI Watchdog Ticks" and "HW generated NMI events" in the
Linux kernel. What this means is that the hpwdt nmi handler code is called
each time the NMI signal fires off. This could amount to several thousands of
NMIs in a matter of seconds. If a user sees the Linux kernel's "dazed and
confused" message in the logs or if the system gets into a hung state, then
- the hpwdt driver can be reloaded with the "priority" module parameter set
- (priority=1).
+ the hpwdt driver can be reloaded.
1. If the kernel has not been booted with nmi_watchdog turned off then
- edit /boot/grub/menu.lst and place the nmi_watchdog=0 at the end of the
- currently booting kernel line.
+ edit and place the nmi_watchdog=0 at the end of the currently booting
+ kernel line. Depending on your Linux distribution and platform setup:
+ For non-UEFI systems
+ /boot/grub/grub.conf or
+ /boot/grub/menu.lst
+ For UEFI systems
+ /boot/efi/EFI/distroname/grub.conf or
+ /boot/efi/efi/distroname/elilo.conf
2. reboot the sever
- 3. Once the system comes up perform a rmmod hpwdt
- 4. insmod /lib/modules/`uname -r`/kernel/drivers/char/watchdog/hpwdt.ko priority=1
+ 3. Once the system comes up perform a modprobe -r hpwdt
+ 4. modprobe /lib/modules/`uname -r`/kernel/drivers/watchdog/hpwdt.ko
Now, the hpwdt can successfully receive and source the NMI and provide a log
- message that details the reason for the NMI (as determined by the HP BIOS).
+ message that details the reason for the NMI (as determined by the HPE BIOS).
- Below is a list of NMIs the HP BIOS understands along with the associated
+ Below is a list of NMIs the HPE BIOS understands along with the associated
code (reason):
No source found 00h
@@ -92,4 +95,4 @@ Last reviewed: 06/02/2009
-- Tom Mingarelli
- (thomas.mingarelli@hp.com)
+ (thomas.mingarelli@hpe.com)
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
index c161399a6b5c..a8d364227a77 100644
--- a/Documentation/watchdog/watchdog-parameters.txt
+++ b/Documentation/watchdog/watchdog-parameters.txt
@@ -86,6 +86,10 @@ nowayout: Watchdog cannot be stopped once started
davinci_wdt:
heartbeat: Watchdog heartbeat period in seconds from 1 to 600, default 60
-------------------------------------------------
+ebc-c384_wdt:
+timeout: Watchdog timeout in seconds. (1<=timeout<=15300, default=60)
+nowayout: Watchdog cannot be stopped once started
+-------------------------------------------------
ep93xx_wdt:
nowayout: Watchdog cannot be stopped once started
timeout: Watchdog timeout in seconds. (1<=timeout<=3600, default=TBD)
diff --git a/MAINTAINERS b/MAINTAINERS
index 330200688228..1209323b7e43 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -595,6 +595,10 @@ S: Odd Fixes
L: linux-alpha@vger.kernel.org
F: arch/alpha/
+ALPS PS/2 TOUCHPAD DRIVER
+R: Pali Rohár <pali.rohar@gmail.com>
+F: drivers/input/mouse/alps.*
+
ALTERA MAILBOX DRIVER
M: Ley Foon Tan <lftan@altera.com>
L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
@@ -1159,6 +1163,7 @@ F: arch/arm/mach-footbridge/
ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
M: Sascha Hauer <kernel@pengutronix.de>
+R: Fabio Estevam <fabio.estevam@nxp.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
@@ -2242,7 +2247,8 @@ F: include/net/ax25.h
F: net/ax25/
AZ6007 DVB DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -2304,7 +2310,7 @@ BCACHE (BLOCK LAYER CACHE)
M: Kent Overstreet <kent.overstreet@gmail.com>
L: linux-bcache@vger.kernel.org
W: http://bcache.evilpiepirate.org
-S: Maintained
+S: Orphan
F: drivers/md/bcache/
BDISP ST MEDIA DRIVER
@@ -2505,6 +2511,7 @@ M: Hauke Mehrtens <hauke@hauke-m.de>
M: Rafał Miłecki <zajec5@gmail.com>
L: linux-mips@linux-mips.org
S: Maintained
+F: Documentation/devicetree/bindings/mips/brcm/
F: arch/mips/bcm47xx/*
F: arch/mips/include/asm/mach-bcm47xx/*
@@ -2708,7 +2715,8 @@ F: Documentation/filesystems/btrfs.txt
F: fs/btrfs/
BTTV VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -2772,9 +2780,9 @@ F: include/net/caif/
F: net/caif/
CALGARY x86-64 IOMMU
-M: Muli Ben-Yehuda <muli@il.ibm.com>
-M: "Jon D. Mason" <jdmason@kudzu.us>
-L: discuss@x86-64.org
+M: Muli Ben-Yehuda <mulix@mulix.org>
+M: Jon Mason <jdmason@kudzu.us>
+L: iommu@lists.linux-foundation.org
S: Maintained
F: arch/x86/kernel/pci-calgary_64.c
F: arch/x86/kernel/tce_64.c
@@ -3085,6 +3093,7 @@ M: Stephen Boyd <sboyd@codeaurora.org>
L: linux-clk@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git
S: Maintained
+F: Documentation/devicetree/bindings/clock/
F: drivers/clk/
X: drivers/clk/clkdev.c
F: include/linux/clk-pr*
@@ -3342,7 +3351,8 @@ S: Maintained
F: drivers/media/dvb-frontends/cx24120*
CX88 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -3772,6 +3782,7 @@ Q: https://patchwork.kernel.org/project/linux-dmaengine/list/
S: Maintained
F: drivers/dma/
F: include/linux/dmaengine.h
+F: Documentation/devicetree/bindings/dma/
F: Documentation/dmaengine/
T: git git://git.infradead.org/users/vkoul/slave-dma.git
@@ -4289,7 +4300,8 @@ F: fs/ecryptfs/
EDAC-CORE
M: Doug Thompson <dougthompson@xmission.com>
M: Borislav Petkov <bp@alien8.de>
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac.git linux_next
@@ -4334,7 +4346,8 @@ S: Maintained
F: drivers/edac/e7xxx_edac.c
EDAC-GHES
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/ghes_edac.c
@@ -4358,19 +4371,22 @@ S: Maintained
F: drivers/edac/i5000_edac.c
EDAC-I5400
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i5400_edac.c
EDAC-I7300
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i7300_edac.c
EDAC-I7CORE
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i7core_edac.c
@@ -4407,7 +4423,8 @@ S: Maintained
F: drivers/edac/r82600_edac.c
EDAC-SBRIDGE
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/sb_edac.c
@@ -4466,7 +4483,8 @@ S: Maintained
F: drivers/net/ethernet/ibm/ehea/
EM28XX VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -5308,6 +5326,13 @@ F: drivers/block/cciss*
F: include/linux/cciss_ioctl.h
F: include/uapi/linux/cciss_ioctl.h
+HFI1 DRIVER
+M: Mike Marciniszyn <mike.marciniszyn@intel.com>
+M: Dennis Dalessandro <dennis.dalessandro@intel.com>
+L: linux-rdma@vger.kernel.org
+S: Supported
+F: drivers/infiniband/hw/hfi1
+
HFS FILESYSTEM
L: linux-fsdevel@vger.kernel.org
S: Orphan
@@ -5837,7 +5862,6 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma.git
S: Supported
F: Documentation/infiniband/
F: drivers/infiniband/
-F: drivers/staging/rdma/
F: include/uapi/linux/if_infiniband.h
F: include/uapi/rdma/
F: include/rdma/
@@ -6096,6 +6120,14 @@ S: Maintained
F: arch/x86/include/asm/intel_telemetry.h
F: drivers/platform/x86/intel_telemetry*
+INTEL PMC CORE DRIVER
+M: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com>
+M: Vishwanath Somayaji <vishwanath.somayaji@intel.com>
+L: platform-driver-x86@vger.kernel.org
+S: Maintained
+F: arch/x86/include/asm/pmc_core.h
+F: drivers/platform/x86/intel_pmc_core*
+
IOC3 ETHERNET DRIVER
M: Ralf Baechle <ralf@linux-mips.org>
L: linux-mips@linux-mips.org
@@ -6413,8 +6445,9 @@ F: Documentation/kbuild/kconfig-language.txt
F: scripts/kconfig/
KDUMP
-M: Vivek Goyal <vgoyal@redhat.com>
-M: Haren Myneni <hbabu@us.ibm.com>
+M: Dave Young <dyoung@redhat.com>
+M: Baoquan He <bhe@redhat.com>
+R: Vivek Goyal <vgoyal@redhat.com>
L: kexec@lists.infradead.org
W: http://lse.sourceforge.net/kdump/
S: Maintained
@@ -6470,6 +6503,7 @@ F: include/uapi/linux/sunrpc/
KERNEL SELFTEST FRAMEWORK
M: Shuah Khan <shuahkh@osg.samsung.com>
+M: Shuah Khan <shuah@kernel.org>
L: linux-kselftest@vger.kernel.org
T: git git://git.kernel.org/pub/scm/shuah/linux-kselftest
S: Maintained
@@ -6491,6 +6525,7 @@ F: arch/*/include/asm/kvm*
F: include/linux/kvm*
F: include/uapi/linux/kvm*
F: virt/kvm/
+F: tools/kvm/
KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V
M: Joerg Roedel <joro@8bytes.org>
@@ -6559,7 +6594,7 @@ L: kexec@lists.infradead.org
S: Maintained
F: include/linux/kexec.h
F: include/uapi/linux/kexec.h
-F: kernel/kexec.c
+F: kernel/kexec*
KEYS/KEYRINGS:
M: David Howells <dhowells@redhat.com>
@@ -7340,7 +7375,8 @@ S: Supported
F: drivers/media/pci/netup_unidvb/*
MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
P: LinuxTV.org Project
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -7388,7 +7424,7 @@ F: drivers/scsi/megaraid.*
F: drivers/scsi/megaraid/
MELLANOX ETHERNET DRIVER (mlx4_en)
-M: Eugenia Emantayev <eugenia@mellanox.com>
+M: Tariq Toukan <tariqt@mellanox.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
@@ -7505,6 +7541,7 @@ W: http://www.linux-mips.org/
T: git git://git.linux-mips.org/pub/scm/ralf/linux.git
Q: http://patchwork.linux-mips.org/project/linux-mips/list/
S: Supported
+F: Documentation/devicetree/bindings/mips/
F: Documentation/mips/
F: arch/mips/
@@ -7971,6 +8008,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
S: Odd Fixes
+F: Documentation/devicetree/bindings/net/
F: drivers/net/
F: include/linux/if_*
F: include/linux/netdevice.h
@@ -7989,6 +8027,7 @@ Q: http://patchwork.kernel.org/project/linux-wireless/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next.git
S: Maintained
+F: Documentation/devicetree/bindings/net/wireless/
F: drivers/net/wireless/
NETXEN (1/10) GbE SUPPORT
@@ -8386,10 +8425,9 @@ F: drivers/i2c/busses/i2c-ocores.c
OPEN FIRMWARE AND FLATTENED DEVICE TREE
M: Rob Herring <robh+dt@kernel.org>
M: Frank Rowand <frowand.list@gmail.com>
-M: Grant Likely <grant.likely@linaro.org>
L: devicetree@vger.kernel.org
W: http://www.devicetree.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/glikely/linux.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
S: Maintained
F: drivers/of/
F: include/linux/of*.h
@@ -8397,12 +8435,10 @@ F: scripts/dtc/
OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS
M: Rob Herring <robh+dt@kernel.org>
-M: Pawel Moll <pawel.moll@arm.com>
M: Mark Rutland <mark.rutland@arm.com>
-M: Ian Campbell <ijc+devicetree@hellion.org.uk>
-M: Kumar Gala <galak@codeaurora.org>
L: devicetree@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
+Q: http://patchwork.ozlabs.org/project/devicetree-bindings/list/
S: Maintained
F: Documentation/devicetree/
F: arch/*/boot/dts/
@@ -8881,6 +8917,7 @@ F: arch/*/kernel/*/perf_event*.c
F: arch/*/kernel/*/*/perf_event*.c
F: arch/*/include/asm/perf_event.h
F: arch/*/kernel/perf_callchain.c
+F: arch/*/events/*
F: tools/perf/
PERSONALITY HANDLING
@@ -8925,6 +8962,8 @@ M: Linus Walleij <linus.walleij@linaro.org>
L: linux-gpio@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git
S: Maintained
+F: Documentation/devicetree/bindings/pinctrl/
+F: Documentation/pinctrl.txt
F: drivers/pinctrl/
F: include/linux/pinctrl/
@@ -9832,7 +9871,8 @@ S: Odd Fixes
F: drivers/media/i2c/saa6588*
SAA7134 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -10351,7 +10391,8 @@ S: Maintained
F: drivers/media/radio/si4713/radio-usb-si4713.c
SIANO DVB DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -10909,12 +10950,6 @@ M: Arnaud Patard <arnaud.patard@rtp-net.org>
S: Odd Fixes
F: drivers/staging/xgifb/
-HFI1 DRIVER
-M: Mike Marciniszyn <infinipath@intel.com>
-L: linux-rdma@vger.kernel.org
-S: Supported
-F: drivers/staging/rdma/hfi1
-
STARFIRE/DURALAN NETWORK DRIVER
M: Ion Badulescu <ionut@badula.org>
S: Odd Fixes
@@ -11123,7 +11158,8 @@ S: Maintained
F: drivers/media/i2c/tda9840*
TEA5761 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -11131,7 +11167,8 @@ S: Odd fixes
F: drivers/media/tuners/tea5761.*
TEA5767 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -11295,6 +11332,7 @@ F: drivers/platform/x86/thinkpad_acpi.c
TI BANDGAP AND THERMAL DRIVER
M: Eduardo Valentin <edubezval@gmail.com>
+M: Keerthy <j-keerthy@ti.com>
L: linux-pm@vger.kernel.org
L: linux-omap@vger.kernel.org
S: Maintained
@@ -11517,7 +11555,8 @@ F: include/linux/shmem_fs.h
F: mm/shmem.c
TM6000 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
@@ -11871,7 +11910,8 @@ F: drivers/usb/common/usb-otg-fsm.c
USB OVER IP DRIVER
M: Valentina Manea <valentina.manea.m@gmail.com>
-M: Shuah Khan <shuah.kh@samsung.com>
+M: Shuah Khan <shuahkh@osg.samsung.com>
+M: Shuah Khan <shuah@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
F: Documentation/usb/usbip_protocol.txt
@@ -11942,6 +11982,7 @@ L: linux-usb@vger.kernel.org
W: http://www.linux-usb.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git
S: Supported
+F: Documentation/devicetree/bindings/usb/
F: Documentation/usb/
F: drivers/usb/
F: include/linux/usb.h
@@ -12115,6 +12156,7 @@ VIRTIO CORE, NET AND BLOCK DRIVERS
M: "Michael S. Tsirkin" <mst@redhat.com>
L: virtualization@lists.linux-foundation.org
S: Maintained
+F: Documentation/devicetree/bindings/virtio/
F: drivers/virtio/
F: tools/virtio/
F: drivers/net/virtio_net.c
@@ -12345,6 +12387,7 @@ L: linux-watchdog@vger.kernel.org
W: http://www.linux-watchdog.org/
T: git git://www.linux-watchdog.org/linux-watchdog.git
S: Maintained
+F: Documentation/devicetree/bindings/watchdog/
F: Documentation/watchdog/
F: drivers/watchdog/
F: include/linux/watchdog.h
@@ -12502,7 +12545,8 @@ S: Maintained
F: arch/x86/entry/vdso/
XC2028/3028 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
diff --git a/Makefile b/Makefile
index 0f9cb36d45c2..0d504893df6e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
VERSION = 4
-PATCHLEVEL = 6
+PATCHLEVEL = 7
SUBLEVEL = 0
-EXTRAVERSION =
-NAME = Charred Weasel
+EXTRAVERSION = -rc6
+NAME = Psychotic Stoned Sheep
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
@@ -128,6 +128,10 @@ _all:
# Cancel implicit rules on top Makefile
$(CURDIR)/Makefile Makefile: ;
+ifneq ($(words $(subst :, ,$(CURDIR))), 1)
+ $(error main directory cannot contain spaces nor colons)
+endif
+
ifneq ($(KBUILD_OUTPUT),)
# Invoke a second make in the output directory, passing relevant variables
# check that the output directory actually exists
@@ -142,7 +146,7 @@ PHONY += $(MAKECMDGOALS) sub-make
$(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make
@:
-sub-make: FORCE
+sub-make:
$(Q)$(MAKE) -C $(KBUILD_OUTPUT) KBUILD_SRC=$(CURDIR) \
-f $(CURDIR)/Makefile $(filter-out _all sub-make,$(MAKECMDGOALS))
@@ -359,12 +363,14 @@ CHECK = sparse
CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
-Wbitwise -Wno-return-void $(CF)
+NOSTDINC_FLAGS =
CFLAGS_MODULE =
AFLAGS_MODULE =
LDFLAGS_MODULE =
CFLAGS_KERNEL =
AFLAGS_KERNEL =
-CFLAGS_GCOV = -fprofile-arcs -ftest-coverage
+LDFLAGS_vmlinux =
+CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
CFLAGS_KCOV = -fsanitize-coverage=trace-pc
@@ -617,7 +623,11 @@ KBUILD_CFLAGS += $(call cc-option,-fno-delete-null-pointer-checks,)
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,)
else
-KBUILD_CFLAGS += -O2
+ifdef CONFIG_PROFILE_ALL_BRANCHES
+KBUILD_CFLAGS += -O2 $(call cc-disable-warning,maybe-uninitialized,)
+else
+KBUILD_CFLAGS += -O2
+endif
endif
# Tell gcc to never replace conditional load with a non-conditional one
@@ -697,9 +707,10 @@ KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
else
-# This warning generated too much noise in a regular build.
-# Use make W=1 to enable this warning (see scripts/Makefile.build)
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.build)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
endif
ifdef CONFIG_FRAME_POINTER
@@ -926,27 +937,41 @@ export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) arch Doc
vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_INIT) $(KBUILD_VMLINUX_MAIN)
-# Final link of vmlinux
- cmd_link-vmlinux = $(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux)
-quiet_cmd_link-vmlinux = LINK $@
-
-# Include targets which we want to
-# execute if the rest of the kernel build went well.
-vmlinux: scripts/link-vmlinux.sh $(vmlinux-deps) FORCE
+# Include targets which we want to execute sequentially if the rest of the
+# kernel build went well. If CONFIG_TRIM_UNUSED_KSYMS is set, this might be
+# evaluated more than once.
+PHONY += vmlinux_prereq
+vmlinux_prereq: $(vmlinux-deps) FORCE
ifdef CONFIG_HEADERS_CHECK
$(Q)$(MAKE) -f $(srctree)/Makefile headers_check
endif
-ifdef CONFIG_SAMPLES
- $(Q)$(MAKE) $(build)=samples
-endif
ifdef CONFIG_BUILD_DOCSRC
$(Q)$(MAKE) $(build)=Documentation
endif
ifdef CONFIG_GDB_SCRIPTS
$(Q)ln -fsn `cd $(srctree) && /bin/pwd`/scripts/gdb/vmlinux-gdb.py
endif
+ifdef CONFIG_TRIM_UNUSED_KSYMS
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh \
+ "$(MAKE) KBUILD_MODULES=1 -f $(srctree)/Makefile vmlinux_prereq"
+endif
+
+# standalone target for easier testing
+include/generated/autoksyms.h: FORCE
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh true
+
+# Final link of vmlinux
+ cmd_link-vmlinux = $(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux)
+quiet_cmd_link-vmlinux = LINK $@
+
+vmlinux: scripts/link-vmlinux.sh vmlinux_prereq $(vmlinux-deps) FORCE
+$(call if_changed,link-vmlinux)
+# Build samples along the rest of the kernel
+ifdef CONFIG_SAMPLES
+vmlinux-dirs += samples
+endif
+
# The actual objects are generated when descending,
# make sure no implicit rule kicks in
$(sort $(vmlinux-deps)): $(vmlinux-dirs) ;
@@ -998,10 +1023,12 @@ prepare2: prepare3 outputmakefile asm-generic
prepare1: prepare2 $(version_h) include/generated/utsrelease.h \
include/config/auto.conf
$(cmd_crmodverdir)
+ $(Q)test -e include/generated/autoksyms.h || \
+ touch include/generated/autoksyms.h
archprepare: archheaders archscripts prepare1 scripts_basic
-prepare0: archprepare FORCE
+prepare0: archprepare
$(Q)$(MAKE) $(build)=.
# All the preparing..
@@ -1061,7 +1088,7 @@ INSTALL_FW_PATH=$(INSTALL_MOD_PATH)/lib/firmware
export INSTALL_FW_PATH
PHONY += firmware_install
-firmware_install: FORCE
+firmware_install:
@mkdir -p $(objtree)/firmware
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.fwinst obj=firmware __fw_install
@@ -1081,7 +1108,7 @@ PHONY += archscripts
archscripts:
PHONY += __headers
-__headers: $(version_h) scripts_basic asm-generic archheaders archscripts FORCE
+__headers: $(version_h) scripts_basic asm-generic archheaders archscripts
$(Q)$(MAKE) $(build)=scripts build_unifdef
PHONY += headers_install_all
@@ -1192,7 +1219,8 @@ else # CONFIG_MODULES
# Modules not configured
# ---------------------------------------------------------------------------
-modules modules_install: FORCE
+PHONY += modules modules_install
+modules modules_install:
@echo >&2
@echo >&2 "The present kernel configuration has modules disabled."
@echo >&2 "Type 'make config' and enable loadable module support."
@@ -1283,6 +1311,7 @@ boards := $(sort $(notdir $(boards)))
board-dirs := $(dir $(wildcard $(srctree)/arch/$(SRCARCH)/configs/*/*_defconfig))
board-dirs := $(sort $(notdir $(board-dirs:/=)))
+PHONY += help
help:
@echo 'Cleaning targets:'
@echo ' clean - Remove most generated files but keep the config and'
@@ -1453,6 +1482,7 @@ $(clean-dirs):
clean: rm-dirs := $(MODVERDIR)
clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers
+PHONY += help
help:
@echo ' Building external modules.'
@echo ' Syntax: make -C path/to/kernel/src M=$$PWD target'
diff --git a/arch/Kconfig b/arch/Kconfig
index b16e74e4b5af..15996290fed4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -226,8 +226,8 @@ config ARCH_INIT_TASK
config ARCH_TASK_STRUCT_ALLOCATOR
bool
-# Select if arch has its private alloc_thread_info() function
-config ARCH_THREAD_INFO_ALLOCATOR
+# Select if arch has its private alloc_thread_stack() function
+config ARCH_THREAD_STACK_ALLOCATOR
bool
# Select if arch wants to size task_struct dynamically via arch_task_struct_size:
@@ -598,6 +598,17 @@ config HAVE_STACK_VALIDATION
Architecture supports the 'objtool check' host tool command, which
performs compile-time stack metadata validation.
+config HAVE_ARCH_HASH
+ bool
+ default n
+ help
+ If this is set, the architecture provides an <asm/hash.h>
+ file which provides platform-specific implementations of some
+ functions in <linux/hash.h> or fs/namei.c.
+
+config ISA_BUS_API
+ def_bool ISA
+
#
# ABI hall of shame
#
diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h
index aab14a019c20..c2ebb6f36c9d 100644
--- a/arch/alpha/include/asm/pgalloc.h
+++ b/arch/alpha/include/asm/pgalloc.h
@@ -40,7 +40,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pmd_t *
pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
- pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
return ret;
}
@@ -53,7 +53,7 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd)
static inline pte_t *
pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
return pte;
}
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 0dcbacfdea4b..0d3e59f56974 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -61,7 +61,7 @@ config RWSEM_GENERIC_SPINLOCK
def_bool y
config ARCH_DISCONTIGMEM_ENABLE
- def_bool y
+ def_bool n
config ARCH_FLATMEM_ENABLE
def_bool y
@@ -186,9 +186,6 @@ if SMP
config ARC_HAS_COH_CACHES
def_bool n
-config ARC_HAS_REENTRANT_IRQ_LV2
- def_bool n
-
config ARC_MCIP
bool "ARConnect Multicore IP (MCIP) Support "
depends on ISA_ARCV2
@@ -366,25 +363,10 @@ config NODES_SHIFT
if ISA_ARCOMPACT
config ARC_COMPACT_IRQ_LEVELS
- bool "ARCompact IRQ Priorities: High(2)/Low(1)"
+ bool "Setup Timer IRQ as high Priority"
default n
- # Timer HAS to be high priority, for any other high priority config
- select ARC_IRQ3_LV2
# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
- depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2
-
-if ARC_COMPACT_IRQ_LEVELS
-
-config ARC_IRQ3_LV2
- bool
-
-config ARC_IRQ5_LV2
- bool
-
-config ARC_IRQ6_LV2
- bool
-
-endif #ARC_COMPACT_IRQ_LEVELS
+ depends on !SMP
config ARC_FPU_SAVE_RESTORE
bool "Enable FPU state persistence across context switch"
@@ -407,11 +389,6 @@ config ARC_HAS_LLSC
default y
depends on !ARC_CANT_LLSC
-config ARC_STAR_9000923308
- bool "Workaround for llock/scond livelock"
- default n
- depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
-
config ARC_HAS_SWAPE
bool "Insn: SWAPE (endian-swap)"
default y
@@ -471,7 +448,7 @@ config LINUX_LINK_BASE
config HIGHMEM
bool "High Memory Support"
- select DISCONTIGMEM
+ select ARCH_DISCONTIGMEM_ENABLE
help
With ARC 2G:2G address split, only upper 2G is directly addressable by
kernel. Enable this to potentially allow access to rest of 2G and PAE
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 02fabef2891c..85814e74677d 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -66,8 +66,6 @@ endif
endif
-cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables
-
# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
ifeq ($(atleast_gcc48),y)
cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2
@@ -127,7 +125,7 @@ libs-y += arch/arc/lib/ $(LIBGCC)
boot := arch/arc/boot
-#default target for make without any arguements.
+#default target for make without any arguments.
KBUILD_IMAGE := bootpImage
all: $(KBUILD_IMAGE)
diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi
index 3942634f805a..02410b211433 100644
--- a/arch/arc/boot/dts/abilis_tb100.dtsi
+++ b/arch/arc/boot/dts/abilis_tb100.dtsi
@@ -23,8 +23,6 @@
/ {
- clock-frequency = <500000000>; /* 500 MHZ */
-
soc100 {
bus-frequency = <166666666>;
diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi
index b0467229a5c4..f9e7686044eb 100644
--- a/arch/arc/boot/dts/abilis_tb101.dtsi
+++ b/arch/arc/boot/dts/abilis_tb101.dtsi
@@ -23,8 +23,6 @@
/ {
- clock-frequency = <500000000>; /* 500 MHZ */
-
soc100 {
bus-frequency = <166666666>;
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index 3e02f152edcb..6ae2c476ad82 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -15,7 +15,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <750000000>; /* 750 MHZ */
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 378e455a94c4..14df46f141bf 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -14,7 +14,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <90000000>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 64c94b2860ab..3d6cfa32bf51 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -14,7 +14,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <90000000>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/eznps.dts b/arch/arc/boot/dts/eznps.dts
index b89f6c3eb352..1e0d225791c1 100644
--- a/arch/arc/boot/dts/eznps.dts
+++ b/arch/arc/boot/dts/eznps.dts
@@ -18,7 +18,6 @@
/ {
compatible = "ezchip,arc-nps";
- clock-frequency = <83333333>; /* 83.333333 MHZ */
#address-cells = <1>;
#size-cells = <1>;
interrupt-parent = <&intc>;
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 5d5e373e0ebc..63970513e4ae 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -11,7 +11,6 @@
/ {
compatible = "snps,nsim";
- clock-frequency = <80000000>; /* 80 MHZ */
#address-cells = <1>;
#size-cells = <1>;
interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index b5b060adce8a..763d66c883da 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,7 +11,6 @@
/ {
compatible = "snps,nsimosci";
- clock-frequency = <20000000>; /* 20 MHZ */
#address-cells = <1>;
#size-cells = <1>;
interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 325e73090a18..4eb97c584b18 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -11,7 +11,6 @@
/ {
compatible = "snps,nsimosci_hs";
- clock-frequency = <20000000>; /* 20 MHZ */
#address-cells = <1>;
#size-cells = <1>;
interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index ee03d7126581..853f897eb2a3 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -11,7 +11,6 @@
/ {
compatible = "snps,nsimosci_hs";
- clock-frequency = <5000000>; /* 5 MHZ */
#address-cells = <1>;
#size-cells = <1>;
interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
index 3a10cc633e2b..65808fe0a290 100644
--- a/arch/arc/boot/dts/skeleton.dtsi
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -13,7 +13,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <80000000>; /* 80 MHZ */
#address-cells = <1>;
#size-cells = <1>;
chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
index 71fd308a9298..2dfe8037dfbb 100644
--- a/arch/arc/boot/dts/skeleton_hs.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -8,7 +8,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <80000000>; /* 80 MHZ */
#address-cells = <1>;
#size-cells = <1>;
chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
index d1cb25a66989..4c11079f3565 100644
--- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -8,7 +8,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <80000000>; /* 80 MHZ */
#address-cells = <1>;
#size-cells = <1>;
chosen { };
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
index ad4ee43bd2ac..0fd6ba985b16 100644
--- a/arch/arc/boot/dts/vdk_axc003.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -14,7 +14,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <50000000>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
index a3cb6263c581..82214cd7ba0c 100644
--- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -15,7 +15,6 @@
/ {
compatible = "snps,arc";
- clock-frequency = <50000000>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 5f3dcbbc0cc9..dd683995bc9d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -25,50 +25,17 @@
#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
-#ifdef CONFIG_ARC_STAR_9000923308
-
-#define SCOND_FAIL_RETRY_VAR_DEF \
- unsigned int delay = 1, tmp; \
-
-#define SCOND_FAIL_RETRY_ASM \
- " bz 4f \n" \
- " ; --- scond fail delay --- \n" \
- " mov %[tmp], %[delay] \n" /* tmp = delay */ \
- "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \
- " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \
- " rol %[delay], %[delay] \n" /* delay *= 2 */ \
- " b 1b \n" /* start over */ \
- "4: ; --- success --- \n" \
-
-#define SCOND_FAIL_RETRY_VARS \
- ,[delay] "+&r" (delay),[tmp] "=&r" (tmp) \
-
-#else /* !CONFIG_ARC_STAR_9000923308 */
-
-#define SCOND_FAIL_RETRY_VAR_DEF
-
-#define SCOND_FAIL_RETRY_ASM \
- " bnz 1b \n" \
-
-#define SCOND_FAIL_RETRY_VARS
-
-#endif
-
#define ATOMIC_OP(op, c_op, asm_op) \
static inline void atomic_##op(int i, atomic_t *v) \
{ \
- unsigned int val; \
- SCOND_FAIL_RETRY_VAR_DEF \
+ unsigned int val; \
\
__asm__ __volatile__( \
"1: llock %[val], [%[ctr]] \n" \
" " #asm_op " %[val], %[val], %[i] \n" \
" scond %[val], [%[ctr]] \n" \
- " \n" \
- SCOND_FAIL_RETRY_ASM \
- \
+ " bnz 1b \n" \
: [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \
- SCOND_FAIL_RETRY_VARS \
: [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \
[i] "ir" (i) \
: "cc"); \
@@ -77,8 +44,7 @@ static inline void atomic_##op(int i, atomic_t *v) \
#define ATOMIC_OP_RETURN(op, c_op, asm_op) \
static inline int atomic_##op##_return(int i, atomic_t *v) \
{ \
- unsigned int val; \
- SCOND_FAIL_RETRY_VAR_DEF \
+ unsigned int val; \
\
/* \
* Explicit full memory barrier needed before/after as \
@@ -90,11 +56,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \
"1: llock %[val], [%[ctr]] \n" \
" " #asm_op " %[val], %[val], %[i] \n" \
" scond %[val], [%[ctr]] \n" \
- " \n" \
- SCOND_FAIL_RETRY_ASM \
- \
+ " bnz 1b \n" \
: [val] "=&r" (val) \
- SCOND_FAIL_RETRY_VARS \
: [ctr] "r" (&v->counter), \
[i] "ir" (i) \
: "cc"); \
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index e0e1faf03c50..14c310f2e0b1 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -76,8 +76,8 @@
* We need to be a bit more cautious here. What if a kernel bug in
* L1 ISR, caused SP to go whaco (some small value which looks like
* USER stk) and then we take L2 ISR.
- * Above brlo alone would treat it as a valid L1-L2 sceanrio
- * instead of shouting alound
+ * Above brlo alone would treat it as a valid L1-L2 scenario
+ * instead of shouting around
* The only feasible way is to make sure this L2 happened in
* L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
* L1 ISR before it switches stack
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 1fd467ef658f..b0b87f2447f5 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -83,7 +83,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm)
local_flush_tlb_all();
/*
- * Above checke for rollover of 8 bit ASID in 32 bit container.
+ * Above check for rollover of 8 bit ASID in 32 bit container.
* If the container itself wrapped around, set it to a non zero
* "generation" to distinguish from no context
*/
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 86ed671286df..3749234b7419 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -95,7 +95,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
{
pte_t *pte;
- pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO,
+ pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
__get_order_pte());
return pte;
@@ -107,7 +107,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
pgtable_t pte_pg;
struct page *page;
- pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+ pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte());
if (!pte_pg)
return 0;
memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t));
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 034bbdc0ff61..858f98ef7f1b 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -47,7 +47,7 @@
* Page Tables are purely for Linux VM's consumption and the bits below are
* suited to that (uniqueness). Hence some are not implemented in the TLB and
* some have different value in TLB.
- * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in
+ * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in
* seperate PD0 and PD1, which combined forms a translation entry)
* while for PTE perspective, they are 8 and 9 respectively
* with MMU v3: Most bits (except SHARED) represent the exact hardware pos
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index f9048994b22f..16b630fbeb6a 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -78,7 +78,7 @@ struct task_struct;
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp)
/*
- * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
+ * Where about of Task's sp, fp, blink when it was last seen in kernel mode.
* Look in process.c for details of kernel stack layout
*/
#define TSK_K_ESP(tsk) (tsk->thread.ksp)
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 991380438d6b..89fdd1b0a76e 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void)
* (1) These insn were introduced only in 4.10 release. So for older released
* support needed.
*
- * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be
+ * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be
* gaurantted by the platform (not something which core handles).
* Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
* disabling for atomicity.
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index 800e7c430ca5..cded4a9b5438 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -20,11 +20,6 @@
#ifdef CONFIG_ARC_HAS_LLSC
-/*
- * A normal LLOCK/SCOND based system, w/o need for livelock workaround
- */
-#ifndef CONFIG_ARC_STAR_9000923308
-
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
unsigned int val;
@@ -238,293 +233,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
smp_mb();
}
-#else /* CONFIG_ARC_STAR_9000923308 */
-
-/*
- * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
- * coherency transactions in the SCU. The exclusive line state keeps rotating
- * among contenting cores leading to a never ending cycle. So break the cycle
- * by deferring the retry of failed exclusive access (SCOND). The actual delay
- * needed is function of number of contending cores as well as the unrelated
- * coherency traffic from other cores. To keep the code simple, start off with
- * small delay of 1 which would suffice most cases and in case of contention
- * double the delay. Eventually the delay is sufficient such that the coherency
- * pipeline is drained, thus a subsequent exclusive access would succeed.
- */
-
-#define SCOND_FAIL_RETRY_VAR_DEF \
- unsigned int delay, tmp; \
-
-#define SCOND_FAIL_RETRY_ASM \
- " ; --- scond fail delay --- \n" \
- " mov %[tmp], %[delay] \n" /* tmp = delay */ \
- "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \
- " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \
- " rol %[delay], %[delay] \n" /* delay *= 2 */ \
- " b 1b \n" /* start over */ \
- " \n" \
- "4: ; --- done --- \n" \
-
-#define SCOND_FAIL_RETRY_VARS \
- ,[delay] "=&r" (delay), [tmp] "=&r" (tmp) \
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
- unsigned int val;
- SCOND_FAIL_RETRY_VAR_DEF;
-
- smp_mb();
-
- __asm__ __volatile__(
- "0: mov %[delay], 1 \n"
- "1: llock %[val], [%[slock]] \n"
- " breq %[val], %[LOCKED], 0b \n" /* spin while LOCKED */
- " scond %[LOCKED], [%[slock]] \n" /* acquire */
- " bz 4f \n" /* done */
- " \n"
- SCOND_FAIL_RETRY_ASM
-
- : [val] "=&r" (val)
- SCOND_FAIL_RETRY_VARS
- : [slock] "r" (&(lock->slock)),
- [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__)
- : "memory", "cc");
-
- smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
- unsigned int val, got_it = 0;
- SCOND_FAIL_RETRY_VAR_DEF;
-
- smp_mb();
-
- __asm__ __volatile__(
- "0: mov %[delay], 1 \n"
- "1: llock %[val], [%[slock]] \n"
- " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */
- " scond %[LOCKED], [%[slock]] \n" /* acquire */
- " bz.d 4f \n"
- " mov.z %[got_it], 1 \n" /* got it */
- " \n"
- SCOND_FAIL_RETRY_ASM
-
- : [val] "=&r" (val),
- [got_it] "+&r" (got_it)
- SCOND_FAIL_RETRY_VARS
- : [slock] "r" (&(lock->slock)),
- [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__)
- : "memory", "cc");
-
- smp_mb();
-
- return got_it;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
- smp_mb();
-
- lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
-
- smp_mb();
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers but only one writer.
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
- */
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
- unsigned int val;
- SCOND_FAIL_RETRY_VAR_DEF;
-
- smp_mb();
-
- /*
- * zero means writer holds the lock exclusively, deny Reader.
- * Otherwise grant lock to first/subseq reader
- *
- * if (rw->counter > 0) {
- * rw->counter--;
- * ret = 1;
- * }
- */
-
- __asm__ __volatile__(
- "0: mov %[delay], 1 \n"
- "1: llock %[val], [%[rwlock]] \n"
- " brls %[val], %[WR_LOCKED], 0b\n" /* <= 0: spin while write locked */
- " sub %[val], %[val], 1 \n" /* reader lock */
- " scond %[val], [%[rwlock]] \n"
- " bz 4f \n" /* done */
- " \n"
- SCOND_FAIL_RETRY_ASM
-
- : [val] "=&r" (val)
- SCOND_FAIL_RETRY_VARS
- : [rwlock] "r" (&(rw->counter)),
- [WR_LOCKED] "ir" (0)
- : "memory", "cc");
-
- smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
- unsigned int val, got_it = 0;
- SCOND_FAIL_RETRY_VAR_DEF;
-
- smp_mb();
-
- __asm__ __volatile__(
- "0: mov %[delay], 1 \n"
- "1: llock %[val], [%[rwlock]] \n"
- " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */
- " sub %[val], %[val], 1 \n" /* counter-- */
- " scond %[val], [%[rwlock]] \n"
- " bz.d 4f \n"
- " mov.z %[got_it], 1 \n" /* got it */
- " \n"
- SCOND_FAIL_RETRY_ASM
-
- : [val] "=&r" (val),
- [got_it] "+&r" (got_it)
- SCOND_FAIL_RETRY_VARS
- : [rwlock] "r" (&(rw->counter)),
- [WR_LOCKED] "ir" (0)
- : "memory", "cc");
-
- smp_mb();
-
- return got_it;
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
- unsigned int val;
- SCOND_FAIL_RETRY_VAR_DEF;
-
- smp_mb();
-
- /*
- * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
- * deny writer. Otherwise if unlocked grant to writer
- * Hence the claim that Linux rwlocks are unfair to writers.
- * (can be starved for an indefinite time by readers).
- *
- * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
- * rw->counter = 0;
- * ret = 1;
- * }
- */
-
- __asm__ __volatile__(
- "0: mov %[delay], 1 \n"
- "1: llock %[val], [%[rwlock]] \n"
- " brne %[val], %[UNLOCKED], 0b \n" /* while !UNLOCKED spin */
- " mov %[val], %[WR_LOCKED] \n"
- " scond %[val], [%[rwlock]] \n"
- " bz 4f \n"
- " \n"
- SCOND_FAIL_RETRY_ASM
-
- : [val] "=&r" (val)
- SCOND_FAIL_RETRY_VARS
- : [rwlock] "r" (&(rw->counter)),
- [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__),
- [WR_LOCKED] "ir" (0)
- : "memory", "cc");
-
- smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_write_trylock(arch_rwlock_t *rw)
-{
- unsigned int val, got_it = 0;
- SCOND_FAIL_RETRY_VAR_DEF;
-
- smp_mb();
-
- __asm__ __volatile__(
- "0: mov %[delay], 1 \n"
- "1: llock %[val], [%[rwlock]] \n"
- " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */
- " mov %[val], %[WR_LOCKED] \n"
- " scond %[val], [%[rwlock]] \n"
- " bz.d 4f \n"
- " mov.z %[got_it], 1 \n" /* got it */
- " \n"
- SCOND_FAIL_RETRY_ASM
-
- : [val] "=&r" (val),
- [got_it] "+&r" (got_it)
- SCOND_FAIL_RETRY_VARS
- : [rwlock] "r" (&(rw->counter)),
- [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__),
- [WR_LOCKED] "ir" (0)
- : "memory", "cc");
-
- smp_mb();
-
- return got_it;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
- unsigned int val;
-
- smp_mb();
-
- /*
- * rw->counter++;
- */
- __asm__ __volatile__(
- "1: llock %[val], [%[rwlock]] \n"
- " add %[val], %[val], 1 \n"
- " scond %[val], [%[rwlock]] \n"
- " bnz 1b \n"
- " \n"
- : [val] "=&r" (val)
- : [rwlock] "r" (&(rw->counter))
- : "memory", "cc");
-
- smp_mb();
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
- unsigned int val;
-
- smp_mb();
-
- /*
- * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
- */
- __asm__ __volatile__(
- "1: llock %[val], [%[rwlock]] \n"
- " scond %[UNLOCKED], [%[rwlock]]\n"
- " bnz 1b \n"
- " \n"
- : [val] "=&r" (val)
- : [rwlock] "r" (&(rw->counter)),
- [UNLOCKED] "r" (__ARCH_RW_LOCK_UNLOCKED__)
- : "memory", "cc");
-
- smp_mb();
-}
-
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
-
-#endif /* CONFIG_ARC_STAR_9000923308 */
-
#else /* !CONFIG_ARC_HAS_LLSC */
static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 3af67455659a..2d79e527fa50 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -103,7 +103,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
/*
* _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
- * SYSCALL_TRACE is anways seperately/unconditionally tested right after a
+ * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a
* syscall, so all that reamins to be tested is _TIF_WORK_MASK
*/
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index d1da6032b715..a78d5670884f 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -32,7 +32,7 @@
#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
/*
- * Algorthmically, for __user_ok() we want do:
+ * Algorithmically, for __user_ok() we want do:
* (start < TASK_SIZE) && (start+len < TASK_SIZE)
* where TASK_SIZE could either be retrieved from thread_info->addr_limit or
* emitted directly in code.
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
index 095599a73195..71f3918b0fc3 100644
--- a/arch/arc/include/uapi/asm/swab.h
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -74,7 +74,7 @@
__tmp ^ __in; \
})
-#elif (ARC_BSWAP_TYPE == 2) /* Custom single cycle bwap instruction */
+#elif (ARC_BSWAP_TYPE == 2) /* Custom single cycle bswap instruction */
#define __arch_swab32(x) \
({ \
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 39e58d1cdf90..41fa2ec9e02c 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -15,6 +15,7 @@
#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
#define _UAPI_ASM_ARC_UNISTD_H
+#define __ARCH_WANT_RENAMEAT
#define __ARCH_WANT_SYS_EXECVE
#define __ARCH_WANT_SYS_CLONE
#define __ARCH_WANT_SYS_VFORK
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
index 0cb0abaa0479..98812c1248df 100644
--- a/arch/arc/kernel/entry-compact.S
+++ b/arch/arc/kernel/entry-compact.S
@@ -91,27 +91,13 @@ VECTOR mem_service ; 0x8, Mem exception (0x1)
VECTOR instr_service ; 0x10, Instrn Error (0x2)
; ******************** Device ISRs **********************
-#ifdef CONFIG_ARC_IRQ3_LV2
-VECTOR handle_interrupt_level2
-#else
-VECTOR handle_interrupt_level1
-#endif
-
-VECTOR handle_interrupt_level1
-
-#ifdef CONFIG_ARC_IRQ5_LV2
-VECTOR handle_interrupt_level2
-#else
-VECTOR handle_interrupt_level1
-#endif
-
-#ifdef CONFIG_ARC_IRQ6_LV2
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
VECTOR handle_interrupt_level2
#else
VECTOR handle_interrupt_level1
#endif
-.rept 25
+.rept 28
VECTOR handle_interrupt_level1 ; Other devices
.endr
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index c5cceca36118..ce9deb953ca9 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -28,10 +28,8 @@ void arc_init_IRQ(void)
{
int level_mask = 0;
- /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
- level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3;
- level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
- level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
+ /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */
+ level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ;
/*
* Write to register, even if no LV2 IRQs configured to reset it
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 8b134cfe5e1f..08f03d9b5b3e 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -48,7 +48,7 @@ struct arc_callchain_trace {
static int callchain_trace(unsigned int addr, void *data)
{
struct arc_callchain_trace *ctrl = data;
- struct perf_callchain_entry *entry = ctrl->perf_stuff;
+ struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
perf_callchain_store(entry, addr);
if (ctrl->depth++ < 3)
@@ -58,7 +58,7 @@ static int callchain_trace(unsigned int addr, void *data)
}
void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct arc_callchain_trace ctrl = {
.depth = 0,
@@ -69,7 +69,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
}
void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
/*
* User stack can't be unwound trivially with kernel dwarf unwinder
@@ -108,7 +108,7 @@ static void arc_perf_event_update(struct perf_event *event,
int64_t delta = new_raw_count - prev_raw_count;
/*
- * We don't afaraid of hwc->prev_count changing beneath our feet
+ * We aren't afraid of hwc->prev_count changing beneath our feet
* because there's no way for us to re-enter this function anytime.
*/
local64_set(&hwc->prev_count, new_raw_count);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index f63b8bfefb0c..2ee7a4d758a8 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -392,7 +392,7 @@ void __init setup_arch(char **cmdline_p)
/*
* If we are here, it is established that @uboot_arg didn't
* point to DT blob. Instead if u-boot says it is cmdline,
- * Appent to embedded DT cmdline.
+ * append to embedded DT cmdline.
* setup_machine_fdt() would have populated @boot_command_line
*/
if (uboot_tag == 1) {
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 004b7f0bc76c..6cb3736b6b83 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -34,7 +34,7 @@
* -ViXS were still seeing crashes when using insmod to load drivers.
* It turned out that the code to change Execute permssions for TLB entries
* of user was not guarded for interrupts (mod_tlb_permission)
- * This was cauing TLB entries to be overwritten on unrelated indexes
+ * This was causing TLB entries to be overwritten on unrelated indexes
*
* Vineetg: July 15th 2008: Bug #94183
* -Exception happens in Delay slot of a JMP, and before user space resumes,
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index e0efff15a5ae..b9192a653b7e 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
* prelogue is setup (callee regs saved and then fp set and not other
* way around
*/
- pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
+ pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
return 0;
#endif
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index a6f91e88ce36..934150e7ac48 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -276,7 +276,7 @@ static int tlb_stats_open(struct inode *inode, struct file *file)
return 0;
}
-/* called on user read(): display the couters */
+/* called on user read(): display the counters */
static ssize_t tlb_stats_output(struct file *file, /* file descriptor */
char __user *user_buf, /* user buffer */
size_t len, /* length of buffer */
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9e5eddbb856f..5a294b2c3cb3 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -215,7 +215,7 @@ slc_chk:
* ------------------
* This ver of MMU supports variable page sizes (1k-16k): although Linux will
* only support 8k (default), 16k and 4k.
- * However from hardware perspective, smaller page sizes aggrevate aliasing
+ * However from hardware perspective, smaller page sizes aggravate aliasing
* meaning more vaddr bits needed to disambiguate the cache-line-op ;
* the existing scheme of piggybacking won't work for certain configurations.
* Two new registers IC_PTAG and DC_PTAG inttoduced.
@@ -302,7 +302,7 @@ void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr,
/*
* This is technically for MMU v4, using the MMU v3 programming model
- * Special work for HS38 aliasing I-cache configuratino with PAE40
+ * Special work for HS38 aliasing I-cache configuration with PAE40
* - upper 8 bits of paddr need to be written into PTAG_HI
* - (and needs to be written before the lower 32 bits)
* Note that PTAG_HI is hoisted outside the line loop
@@ -936,7 +936,7 @@ void arc_cache_init(void)
ic->ver, CONFIG_ARC_MMU_VER);
/*
- * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG
+ * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG
* pair to provide vaddr/paddr respectively, just as in MMU v3
*/
if (is_isa_arcv2() && ic->alias)
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c8e36fa5659..73d7e4c75b7d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -10,7 +10,7 @@
* DMA Coherent API Notes
*
* I/O is inherently non-coherent on ARC. So a coherent DMA buffer is
- * implemented by accessintg it using a kernel virtual address, with
+ * implemented by accessing it using a kernel virtual address, with
* Cache bit off in the TLB entry.
*
* The default DMA address == Phy address which is 0x8000_0000 based.
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 446705a4325a..5be33a2d59a9 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -82,7 +82,6 @@ $(obj)/uImage: $(obj)/zImage FORCE
$(obj)/bootp/bootp: $(obj)/zImage initrd FORCE
$(Q)$(MAKE) $(build)=$(obj)/bootp $@
- @:
$(obj)/bootpImage: $(obj)/bootp/bootp FORCE
$(call if_changed,objcopy)
diff --git a/arch/arm/boot/bootp/Makefile b/arch/arm/boot/bootp/Makefile
index 5761f0039133..5e4acd253b30 100644
--- a/arch/arm/boot/bootp/Makefile
+++ b/arch/arm/boot/bootp/Makefile
@@ -17,7 +17,6 @@ targets := bootp init.o kernel.o initrd.o
# Note that bootp.lds picks up kernel.o and initrd.o
$(obj)/bootp: $(src)/bootp.lds $(addprefix $(obj)/,init.o kernel.o initrd.o) FORCE
$(call if_changed,ld)
- @:
# kernel.o and initrd.o includes a binary image using
# .incbin, a dependency which is not tracked automatically
@@ -26,4 +25,4 @@ $(obj)/kernel.o: arch/arm/boot/zImage FORCE
$(obj)/initrd.o: $(INITRD) FORCE
-PHONY += $(INITRD) FORCE
+PHONY += $(INITRD)
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 0f89d87cb2a0..414b42710a36 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -399,6 +399,7 @@ dtb-$(CONFIG_SOC_IMX6UL) += \
imx6ul-tx6ul-mainboard.dtb
dtb-$(CONFIG_SOC_IMX7D) += \
imx7d-cl-som-imx7.dtb \
+ imx7d-nitrogen7.dtb \
imx7d-sbc-imx7.dtb \
imx7d-sdb.dtb
dtb-$(CONFIG_SOC_LS1021A) += \
@@ -740,6 +741,7 @@ dtb-$(CONFIG_MACH_SUN7I) += \
sun7i-a20-olimex-som-evb.dtb \
sun7i-a20-olinuxino-lime.dtb \
sun7i-a20-olinuxino-lime2.dtb \
+ sun7i-a20-olinuxino-lime2-emmc.dtb \
sun7i-a20-olinuxino-micro.dtb \
sun7i-a20-orangepi.dtb \
sun7i-a20-orangepi-mini.dtb \
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index d82dd6e3f9b1..5687d6b4da60 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -418,7 +418,7 @@
status = "okay";
pinctrl-names = "default";
pinctrl-0 = <&i2c0_pins>;
- clock-frequency = <400000>;
+ clock-frequency = <100000>;
tps@24 {
compatible = "ti,tps65218";
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index b01a5948cdd0..0e63b9dff6e7 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -60,10 +60,26 @@
tps659038_pmic {
compatible = "ti,tps659038-pmic";
+
+ smps12-in-supply = <&vmain>;
+ smps3-in-supply = <&vmain>;
+ smps45-in-supply = <&vmain>;
+ smps6-in-supply = <&vmain>;
+ smps7-in-supply = <&vmain>;
+ smps8-in-supply = <&vmain>;
+ smps9-in-supply = <&vmain>;
+ ldo1-in-supply = <&vmain>;
+ ldo2-in-supply = <&vmain>;
+ ldo3-in-supply = <&vmain>;
+ ldo4-in-supply = <&vmain>;
+ ldo9-in-supply = <&vmain>;
+ ldoln-in-supply = <&vmain>;
+ ldousb-in-supply = <&vmain>;
+ ldortc-in-supply = <&vmain>;
+
regulators {
smps12_reg: smps12 {
/* VDD_MPU */
- vin-supply = <&vmain>;
regulator-name = "smps12";
regulator-min-microvolt = <850000>;
regulator-max-microvolt = <1250000>;
@@ -73,7 +89,6 @@
smps3_reg: smps3 {
/* VDD_DDR EMIF1 EMIF2 */
- vin-supply = <&vmain>;
regulator-name = "smps3";
regulator-min-microvolt = <1350000>;
regulator-max-microvolt = <1350000>;
@@ -84,7 +99,6 @@
smps45_reg: smps45 {
/* VDD_DSPEVE on AM572 */
/* VDD_IVA + VDD_DSP on AM571 */
- vin-supply = <&vmain>;
regulator-name = "smps45";
regulator-min-microvolt = <850000>;
regulator-max-microvolt = <1250000>;
@@ -94,7 +108,6 @@
smps6_reg: smps6 {
/* VDD_GPU */
- vin-supply = <&vmain>;
regulator-name = "smps6";
regulator-min-microvolt = <850000>;
regulator-max-microvolt = <1250000>;
@@ -104,7 +117,6 @@
smps7_reg: smps7 {
/* VDD_CORE */
- vin-supply = <&vmain>;
regulator-name = "smps7";
regulator-min-microvolt = <850000>;
regulator-max-microvolt = <1150000>;
@@ -115,13 +127,11 @@
smps8_reg: smps8 {
/* 5728 - VDD_IVAHD */
/* 5718 - N.C. test point */
- vin-supply = <&vmain>;
regulator-name = "smps8";
};
smps9_reg: smps9 {
/* VDD_3_3D */
- vin-supply = <&vmain>;
regulator-name = "smps9";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
@@ -132,7 +142,6 @@
ldo1_reg: ldo1 {
/* VDDSHV8 - VSDMMC */
/* NOTE: on rev 1.3a, data supply */
- vin-supply = <&vmain>;
regulator-name = "ldo1";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
@@ -142,7 +151,6 @@
ldo2_reg: ldo2 {
/* VDDSH18V */
- vin-supply = <&vmain>;
regulator-name = "ldo2";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
@@ -152,7 +160,6 @@
ldo3_reg: ldo3 {
/* R1.3a 572x V1_8PHY_LDO3: USB, SATA */
- vin-supply = <&vmain>;
regulator-name = "ldo3";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
@@ -162,7 +169,6 @@
ldo4_reg: ldo4 {
/* R1.3a 572x V1_8PHY_LDO4: PCIE, HDMI*/
- vin-supply = <&vmain>;
regulator-name = "ldo4";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
@@ -174,7 +180,6 @@
ldo9_reg: ldo9 {
/* VDD_RTC */
- vin-supply = <&vmain>;
regulator-name = "ldo9";
regulator-min-microvolt = <840000>;
regulator-max-microvolt = <1160000>;
@@ -184,7 +189,6 @@
ldoln_reg: ldoln {
/* VDDA_1V8_PLL */
- vin-supply = <&vmain>;
regulator-name = "ldoln";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
@@ -194,7 +198,6 @@
ldousb_reg: ldousb {
/* VDDA_3V_USB: VDDA_USBHS33 */
- vin-supply = <&vmain>;
regulator-name = "ldousb";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
@@ -204,7 +207,6 @@
ldortc_reg: ldortc {
/* VDDA_RTC */
- vin-supply = <&vmain>;
regulator-name = "ldortc";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index cbc17b0794b1..4128fa91823c 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -93,6 +93,10 @@
};
};
+&mmc1 {
+ status = "disabled";
+};
+
&mmc2 {
pinctrl-names = "default";
pinctrl-0 = <&sd1_pins>;
@@ -101,6 +105,10 @@
cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
};
+&mmc3 {
+ status = "disabled";
+};
+
&pincntl {
sd1_pins: pinmux_sd1_pins {
pinctrl-single,pins = <
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 5d4313fd5a46..3f184863e0c5 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -45,6 +45,14 @@
phy-mode = "rgmii";
};
+&mmc1 {
+ status = "disabled";
+};
+
+&mmc2 {
+ status = "disabled";
+};
+
&mmc3 {
pinctrl-names = "default";
pinctrl-0 = <&sd2_pins>;
@@ -53,6 +61,7 @@
dmas = <&edma_xbar 8 0 1 /* use SDTXEVT1 instead of MCASP0TX */
&edma_xbar 9 0 2>; /* use SDRXEVT1 instead of MCASP0RX */
dma-names = "tx", "rx";
+ non-removable;
};
&pincntl {
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index e0074014385a..3a8f3976f6f9 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1451,6 +1451,8 @@
ti,hwmods = "gpmc";
reg = <0x50000000 0x37c>; /* device IO registers */
interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
+ dmas = <&edma_xbar 4 0>;
+ dma-names = "rxtx";
gpmc,num-cs = <8>;
gpmc,num-waitpins = <2>;
#address-cells = <2>;
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index 4220eeffc65a..5e06020f450b 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -107,8 +107,8 @@
reg = <0x58000000 0x80>,
<0x58004054 0x4>,
<0x58004300 0x20>,
- <0x58005054 0x4>,
- <0x58005300 0x20>;
+ <0x58009054 0x4>,
+ <0x58009300 0x20>;
reg-names = "dss", "pll1_clkctrl", "pll1",
"pll2_clkctrl", "pll2";
diff --git a/arch/arm/boot/dts/exynos3250-monk.dts b/arch/arm/boot/dts/exynos3250-monk.dts
index 267f81adb42f..8c8906266310 100644
--- a/arch/arm/boot/dts/exynos3250-monk.dts
+++ b/arch/arm/boot/dts/exynos3250-monk.dts
@@ -14,6 +14,7 @@
/dts-v1/;
#include "exynos3250.dtsi"
+#include "exynos4412-ppmu-common.dtsi"
#include <dt-bindings/input/input.h>
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/clock/samsung,s2mps11.h>
@@ -156,6 +157,12 @@
};
};
+&bus_dmc {
+ devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>;
+ vdd-supply = <&buck1_reg>;
+ status = "okay";
+};
+
&cpu0 {
cpu0-supply = <&buck2_reg>;
};
@@ -458,46 +465,6 @@
status = "okay";
};
-&ppmu_dmc0 {
- status = "okay";
-
- events {
- ppmu_dmc0_3: ppmu-event3-dmc0 {
- event-name = "ppmu-event3-dmc0";
- };
- };
-};
-
-&ppmu_dmc1 {
- status = "okay";
-
- events {
- ppmu_dmc1_3: ppmu-event3-dmc1 {
- event-name = "ppmu-event3-dmc1";
- };
- };
-};
-
-&ppmu_leftbus {
- status = "okay";
-
- events {
- ppmu_leftbus_3: ppmu-event3-leftbus {
- event-name = "ppmu-event3-leftbus";
- };
- };
-};
-
-&ppmu_rightbus {
- status = "okay";
-
- events {
- ppmu_rightbus_3: ppmu-event3-rightbus {
- event-name = "ppmu-event3-rightbus";
- };
- };
-};
-
&xusbxti {
clock-frequency = <24000000>;
};
diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts
index 31eb09bae0a2..e422819591dc 100644
--- a/arch/arm/boot/dts/exynos3250-rinato.dts
+++ b/arch/arm/boot/dts/exynos3250-rinato.dts
@@ -14,6 +14,7 @@
/dts-v1/;
#include "exynos3250.dtsi"
+#include "exynos4412-ppmu-common.dtsi"
#include <dt-bindings/input/input.h>
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/clock/samsung,s2mps11.h>
@@ -147,6 +148,53 @@
};
};
+&bus_dmc {
+ devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>;
+ vdd-supply = <&buck1_reg>;
+ status = "okay";
+};
+
+&bus_leftbus {
+ devfreq-events = <&ppmu_leftbus_3>, <&ppmu_rightbus_3>;
+ vdd-supply = <&buck3_reg>;
+ status = "okay";
+};
+
+&bus_rightbus {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_lcd0 {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_fsys {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_mcuisp {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_isp {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_peril {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_mfc {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
&cpu0 {
cpu0-supply = <&buck2_reg>;
};
@@ -635,46 +683,6 @@
status = "okay";
};
-&ppmu_dmc0 {
- status = "okay";
-
- events {
- ppmu_dmc0_3: ppmu-event3-dmc0 {
- event-name = "ppmu-event3-dmc0";
- };
- };
-};
-
-&ppmu_dmc1 {
- status = "okay";
-
- events {
- ppmu_dmc1_3: ppmu-event3-dmc1 {
- event-name = "ppmu-event3-dmc1";
- };
- };
-};
-
-&ppmu_leftbus {
- status = "okay";
-
- events {
- ppmu_leftbus_3: ppmu-event3-leftbus {
- event-name = "ppmu-event3-leftbus";
- };
- };
-};
-
-&ppmu_rightbus {
- status = "okay";
-
- events {
- ppmu_rightbus_3: ppmu-event3-rightbus {
- event-name = "ppmu-event3-rightbus";
- };
- };
-};
-
&xusbxti {
clock-frequency = <24000000>;
};
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 094782b207ee..62f3dcd9e046 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -713,6 +713,187 @@
clock-names = "ppmu";
status = "disabled";
};
+
+ bus_dmc: bus_dmc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu_dmc CLK_DIV_DMC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_dmc_opp_table>;
+ status = "disabled";
+ };
+
+ bus_dmc_opp_table: opp_table1 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@50000000 {
+ opp-hz = /bits/ 64 <50000000>;
+ opp-microvolt = <800000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ opp-microvolt = <800000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ opp-microvolt = <800000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ opp-microvolt = <825000>;
+ };
+ opp@400000000 {
+ opp-hz = /bits/ 64 <400000000>;
+ opp-microvolt = <875000>;
+ };
+ };
+
+ bus_leftbus: bus_leftbus {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_GDL>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_rightbus: bus_rightbus {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_GDR>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_lcd0: bus_lcd0 {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_ACLK_160>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_fsys: bus_fsys {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_ACLK_200>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_mcuisp: bus_mcuisp {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_ACLK_400_MCUISP>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_mcuisp_opp_table>;
+ status = "disabled";
+ };
+
+ bus_isp: bus_isp {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_ACLK_266>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_isp_opp_table>;
+ status = "disabled";
+ };
+
+ bus_peril: bus_peril {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_DIV_ACLK_100>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_peril_opp_table>;
+ status = "disabled";
+ };
+
+ bus_mfc: bus_mfc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&cmu CLK_SCLK_MFC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_leftbus_opp_table: opp_table2 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@50000000 {
+ opp-hz = /bits/ 64 <50000000>;
+ opp-microvolt = <900000>;
+ };
+ opp@80000000 {
+ opp-hz = /bits/ 64 <80000000>;
+ opp-microvolt = <900000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ opp-microvolt = <1000000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ opp-microvolt = <1000000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ opp-microvolt = <1000000>;
+ };
+ };
+
+ bus_mcuisp_opp_table: opp_table3 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@50000000 {
+ opp-hz = /bits/ 64 <50000000>;
+ };
+ opp@80000000 {
+ opp-hz = /bits/ 64 <80000000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ opp@400000000 {
+ opp-hz = /bits/ 64 <400000000>;
+ };
+ };
+
+ bus_isp_opp_table: opp_table4 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@50000000 {
+ opp-hz = /bits/ 64 <50000000>;
+ };
+ opp@80000000 {
+ opp-hz = /bits/ 64 <80000000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ opp@300000000 {
+ opp-hz = /bits/ 64 <300000000>;
+ };
+ };
+
+ bus_peril_opp_table: opp_table5 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@50000000 {
+ opp-hz = /bits/ 64 <50000000>;
+ };
+ opp@80000000 {
+ opp-hz = /bits/ 64 <80000000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index c1cb8df6da07..2d9b02967105 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -257,6 +257,165 @@
power-domains = <&pd_lcd1>;
#iommu-cells = <0>;
};
+
+ bus_dmc: bus_dmc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_DMC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_dmc_opp_table>;
+ status = "disabled";
+ };
+
+ bus_acp: bus_acp {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_ACP>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_acp_opp_table>;
+ status = "disabled";
+ };
+
+ bus_peri: bus_peri {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK100>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_peri_opp_table>;
+ status = "disabled";
+ };
+
+ bus_fsys: bus_fsys {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK133>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_fsys_opp_table>;
+ status = "disabled";
+ };
+
+ bus_display: bus_display {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK160>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_display_opp_table>;
+ status = "disabled";
+ };
+
+ bus_lcd0: bus_lcd0 {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK200>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_leftbus: bus_leftbus {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_GDL>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_rightbus: bus_rightbus {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_GDR>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_mfc: bus_mfc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_SCLK_MFC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_dmc_opp_table: opp_table1 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ opp-microvolt = <1025000>;
+ };
+ opp@267000000 {
+ opp-hz = /bits/ 64 <267000000>;
+ opp-microvolt = <1050000>;
+ };
+ opp@400000000 {
+ opp-hz = /bits/ 64 <400000000>;
+ opp-microvolt = <1150000>;
+ };
+ };
+
+ bus_acp_opp_table: opp_table2 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ };
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ };
+
+ bus_peri_opp_table: opp_table3 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@5000000 {
+ opp-hz = /bits/ 64 <5000000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ };
+
+ bus_fsys_opp_table: opp_table4 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@10000000 {
+ opp-hz = /bits/ 64 <10000000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ };
+ };
+
+ bus_display_opp_table: opp_table5 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ };
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ };
+ };
+
+ bus_leftbus_opp_table: opp_table6 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ };
};
&gic {
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index cab0f07d7d28..ec7619a384a2 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -11,6 +11,7 @@
#include <dt-bindings/input/input.h>
#include <dt-bindings/clock/maxim,max77686.h>
#include "exynos4412.dtsi"
+#include "exynos4412-ppmu-common.dtsi"
#include <dt-bindings/gpio/gpio.h>
/ {
@@ -108,6 +109,53 @@
};
};
+&bus_dmc {
+ devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>;
+ vdd-supply = <&buck1_reg>;
+ status = "okay";
+};
+
+&bus_acp {
+ devfreq = <&bus_dmc>;
+ status = "okay";
+};
+
+&bus_c2c {
+ devfreq = <&bus_dmc>;
+ status = "okay";
+};
+
+&bus_leftbus {
+ devfreq-events = <&ppmu_leftbus_3>, <&ppmu_rightbus_3>;
+ vdd-supply = <&buck3_reg>;
+ status = "okay";
+};
+
+&bus_rightbus {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_display {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_fsys {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_peri {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_mfc {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
&cpu0 {
cpu0-supply = <&buck2_reg>;
};
@@ -359,8 +407,8 @@
buck1_reg: BUCK1 {
regulator-name = "vdd_mif";
- regulator-min-microvolt = <1000000>;
- regulator-max-microvolt = <1000000>;
+ regulator-min-microvolt = <900000>;
+ regulator-max-microvolt = <1100000>;
regulator-always-on;
regulator-boot-on;
};
@@ -375,8 +423,8 @@
buck3_reg: BUCK3 {
regulator-name = "vdd_int";
- regulator-min-microvolt = <1000000>;
- regulator-max-microvolt = <1000000>;
+ regulator-min-microvolt = <900000>;
+ regulator-max-microvolt = <1050000>;
regulator-always-on;
regulator-boot-on;
};
diff --git a/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi b/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi
new file mode 100644
index 000000000000..16e4b77d8cb1
--- /dev/null
+++ b/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi
@@ -0,0 +1,50 @@
+/*
+ * Device tree sources for Exynos4412 PPMU common device tree
+ *
+ * Copyright (C) 2015 Samsung Electronics
+ * Author: Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+&ppmu_dmc0 {
+ status = "okay";
+
+ events {
+ ppmu_dmc0_3: ppmu-event3-dmc0 {
+ event-name = "ppmu-event3-dmc0";
+ };
+ };
+};
+
+&ppmu_dmc1 {
+ status = "okay";
+
+ events {
+ ppmu_dmc1_3: ppmu-event3-dmc1 {
+ event-name = "ppmu-event3-dmc1";
+ };
+ };
+};
+
+&ppmu_leftbus {
+ status = "okay";
+
+ events {
+ ppmu_leftbus_3: ppmu-event3-leftbus {
+ event-name = "ppmu-event3-leftbus";
+ };
+ };
+};
+
+&ppmu_rightbus {
+ status = "okay";
+
+ events {
+ ppmu_rightbus_3: ppmu-event3-rightbus {
+ event-name = "ppmu-event3-rightbus";
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 5d1eaea3f778..9336fd4824d9 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -14,6 +14,7 @@
/dts-v1/;
#include "exynos4412.dtsi"
+#include "exynos4412-ppmu-common.dtsi"
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/clock/maxim,max77686.h>
@@ -288,6 +289,53 @@
status = "okay";
};
+&bus_dmc {
+ devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>;
+ vdd-supply = <&buck1_reg>;
+ status = "okay";
+};
+
+&bus_acp {
+ devfreq = <&bus_dmc>;
+ status = "okay";
+};
+
+&bus_c2c {
+ devfreq = <&bus_dmc>;
+ status = "okay";
+};
+
+&bus_leftbus {
+ devfreq-events = <&ppmu_leftbus_3>, <&ppmu_rightbus_3>;
+ vdd-supply = <&buck3_reg>;
+ status = "okay";
+};
+
+&bus_rightbus {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_display {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_fsys {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_peri {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
+&bus_mfc {
+ devfreq = <&bus_leftbus>;
+ status = "okay";
+};
+
&cpu0 {
cpu0-supply = <&buck2_reg>;
};
@@ -871,46 +919,6 @@
assigned-clock-parents = <&clock CLK_XUSBXTI>;
};
-&ppmu_dmc0 {
- status = "okay";
-
- events {
- ppmu_dmc0_3: ppmu-event3-dmc0 {
- event-name = "ppmu-event3-dmc0";
- };
- };
-};
-
-&ppmu_dmc1 {
- status = "okay";
-
- events {
- ppmu_dmc1_3: ppmu-event3-dmc1 {
- event-name = "ppmu-event3-dmc1";
- };
- };
-};
-
-&ppmu_leftbus {
- status = "okay";
-
- events {
- ppmu_leftbus_3: ppmu-event3-leftbus {
- event-name = "ppmu-event3-leftbus";
- };
- };
-};
-
-&ppmu_rightbus {
- status = "okay";
-
- events {
- ppmu_rightbus_3: ppmu-event3-rightbus {
- event-name = "ppmu-event3-rightbus";
- };
- };
-};
-
&pinctrl_0 {
pinctrl-names = "default";
pinctrl-0 = <&sleep0>;
diff --git a/arch/arm/boot/dts/exynos4x12.dtsi b/arch/arm/boot/dts/exynos4x12.dtsi
index b7490ea0c75c..c452499ae8c9 100644
--- a/arch/arm/boot/dts/exynos4x12.dtsi
+++ b/arch/arm/boot/dts/exynos4x12.dtsi
@@ -281,6 +281,180 @@
clocks = <&clock CLK_SMMU_LITE1>, <&clock CLK_FIMC_LITE1>;
#iommu-cells = <0>;
};
+
+ bus_dmc: bus_dmc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_DMC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_dmc_opp_table>;
+ status = "disabled";
+ };
+
+ bus_acp: bus_acp {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_ACP>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_acp_opp_table>;
+ status = "disabled";
+ };
+
+ bus_c2c: bus_c2c {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_C2C>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_dmc_opp_table>;
+ status = "disabled";
+ };
+
+ bus_dmc_opp_table: opp_table1 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ opp-microvolt = <900000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ opp-microvolt = <900000>;
+ };
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ opp-microvolt = <900000>;
+ };
+ opp@267000000 {
+ opp-hz = /bits/ 64 <267000000>;
+ opp-microvolt = <950000>;
+ };
+ opp@400000000 {
+ opp-hz = /bits/ 64 <400000000>;
+ opp-microvolt = <1050000>;
+ };
+ };
+
+ bus_acp_opp_table: opp_table2 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ };
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ };
+ opp@267000000 {
+ opp-hz = /bits/ 64 <267000000>;
+ };
+ };
+
+ bus_leftbus: bus_leftbus {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_GDL>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_rightbus: bus_rightbus {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DIV_GDR>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_display: bus_display {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK160>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_display_opp_table>;
+ status = "disabled";
+ };
+
+ bus_fsys: bus_fsys {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK133>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_fsys_opp_table>;
+ status = "disabled";
+ };
+
+ bus_peri: bus_peri {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_ACLK100>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_peri_opp_table>;
+ status = "disabled";
+ };
+
+ bus_mfc: bus_mfc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_SCLK_MFC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_leftbus_opp_table>;
+ status = "disabled";
+ };
+
+ bus_leftbus_opp_table: opp_table3 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ opp-microvolt = <900000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ opp-microvolt = <925000>;
+ };
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ opp-microvolt = <950000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ opp-microvolt = <1000000>;
+ };
+ };
+
+ bus_display_opp_table: opp_table4 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@160000000 {
+ opp-hz = /bits/ 64 <160000000>;
+ };
+ opp@200000000 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ };
+
+ bus_fsys_opp_table: opp_table5 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp@134000000 {
+ opp-hz = /bits/ 64 <134000000>;
+ };
+ };
+
+ bus_peri_opp_table: opp_table6 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp@50000000 {
+ opp-hz = /bits/ 64 <50000000>;
+ };
+ opp@100000000 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ };
};
&combiner {
diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
index ddfe1f558c10..fa14f77df563 100644
--- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi
+++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
@@ -242,7 +242,7 @@
hpd-gpios = <&gpx0 7 GPIO_ACTIVE_HIGH>;
ports {
- port0 {
+ port {
dp_out: endpoint {
remote-endpoint = <&bridge_in>;
};
@@ -485,13 +485,20 @@
edid-emulation = <5>;
ports {
- port0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+
bridge_out: endpoint {
remote-endpoint = <&panel_in>;
};
};
- port1 {
+ port@1 {
+ reg = <1>;
+
bridge_in: endpoint {
remote-endpoint = <&dp_out>;
};
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index f9d2e4f1a0e0..1de972d46a87 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -163,7 +163,7 @@
hpd-gpios = <&gpx2 6 GPIO_ACTIVE_HIGH>;
ports {
- port0 {
+ port {
dp_out: endpoint {
remote-endpoint = <&bridge_in>;
};
@@ -631,13 +631,20 @@
use-external-pwm;
ports {
- port0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+
bridge_out: endpoint {
remote-endpoint = <&panel_in>;
};
};
- port1 {
+ port@1 {
+ reg = <1>;
+
bridge_in: endpoint {
remote-endpoint = <&dp_out>;
};
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 4c8523471c65..c6e05eb88937 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -294,6 +294,42 @@
};
};
+ nocp_mem0_0: nocp@10CA1000 {
+ compatible = "samsung,exynos5420-nocp";
+ reg = <0x10CA1000 0x200>;
+ status = "disabled";
+ };
+
+ nocp_mem0_1: nocp@10CA1400 {
+ compatible = "samsung,exynos5420-nocp";
+ reg = <0x10CA1400 0x200>;
+ status = "disabled";
+ };
+
+ nocp_mem1_0: nocp@10CA1800 {
+ compatible = "samsung,exynos5420-nocp";
+ reg = <0x10CA1800 0x200>;
+ status = "disabled";
+ };
+
+ nocp_mem1_1: nocp@10CA1C00 {
+ compatible = "samsung,exynos5420-nocp";
+ reg = <0x10CA1C00 0x200>;
+ status = "disabled";
+ };
+
+ nocp_g3d_0: nocp@11A51000 {
+ compatible = "samsung,exynos5420-nocp";
+ reg = <0x11A51000 0x200>;
+ status = "disabled";
+ };
+
+ nocp_g3d_1: nocp@11A51400 {
+ compatible = "samsung,exynos5420-nocp";
+ reg = <0x11A51400 0x200>;
+ status = "disabled";
+ };
+
gsc_pd: power-domain@10044000 {
compatible = "samsung,exynos4210-pd";
reg = <0x10044000 0x20>;
@@ -1188,6 +1224,377 @@
power-domains = <&disp_pd>;
#iommu-cells = <0>;
};
+
+ bus_wcore: bus_wcore {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK400_WCORE>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_wcore_opp_table>;
+ status = "disabled";
+ };
+
+ bus_noc: bus_noc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK100_NOC>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_noc_opp_table>;
+ status = "disabled";
+ };
+
+ bus_fsys_apb: bus_fsys_apb {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_PCLK200_FSYS>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_fsys_apb_opp_table>;
+ status = "disabled";
+ };
+
+ bus_fsys: bus_fsys {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK200_FSYS>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_fsys_apb_opp_table>;
+ status = "disabled";
+ };
+
+ bus_fsys2: bus_fsys2 {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK200_FSYS2>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_fsys2_opp_table>;
+ status = "disabled";
+ };
+
+ bus_mfc: bus_mfc {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK333>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_mfc_opp_table>;
+ status = "disabled";
+ };
+
+ bus_gen: bus_gen {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK266>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_gen_opp_table>;
+ status = "disabled";
+ };
+
+ bus_peri: bus_peri {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK66>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_peri_opp_table>;
+ status = "disabled";
+ };
+
+ bus_g2d: bus_g2d {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK333_G2D>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_g2d_opp_table>;
+ status = "disabled";
+ };
+
+ bus_g2d_acp: bus_g2d_acp {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK266_G2D>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_g2d_acp_opp_table>;
+ status = "disabled";
+ };
+
+ bus_jpeg: bus_jpeg {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK300_JPEG>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_jpeg_opp_table>;
+ status = "disabled";
+ };
+
+ bus_jpeg_apb: bus_jpeg_apb {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK166>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_jpeg_apb_opp_table>;
+ status = "disabled";
+ };
+
+ bus_disp1_fimd: bus_disp1_fimd {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK300_DISP1>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_disp1_fimd_opp_table>;
+ status = "disabled";
+ };
+
+ bus_disp1: bus_disp1 {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK400_DISP1>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_disp1_opp_table>;
+ status = "disabled";
+ };
+
+ bus_gscl_scaler: bus_gscl_scaler {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK300_GSCL>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_gscl_opp_table>;
+ status = "disabled";
+ };
+
+ bus_mscl: bus_mscl {
+ compatible = "samsung,exynos-bus";
+ clocks = <&clock CLK_DOUT_ACLK400_MSCL>;
+ clock-names = "bus";
+ operating-points-v2 = <&bus_mscl_opp_table>;
+ status = "disabled";
+ };
+
+ bus_wcore_opp_table: opp_table2 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <84000000>;
+ opp-microvolt = <925000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <111000000>;
+ opp-microvolt = <950000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <222000000>;
+ opp-microvolt = <950000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <333000000>;
+ opp-microvolt = <950000>;
+ };
+ opp04 {
+ opp-hz = /bits/ 64 <400000000>;
+ opp-microvolt = <987500>;
+ };
+ };
+
+ bus_noc_opp_table: opp_table3 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <67000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <75000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <86000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ };
+
+ bus_fsys_apb_opp_table: opp_table4 {
+ compatible = "operating-points-v2";
+ opp-shared;
+
+ opp00 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ };
+
+ bus_fsys2_opp_table: opp_table5 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <75000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <100000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <150000000>;
+ };
+ };
+
+ bus_mfc_opp_table: opp_table6 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <96000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <111000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <167000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <222000000>;
+ };
+ opp04 {
+ opp-hz = /bits/ 64 <333000000>;
+ };
+ };
+
+ bus_gen_opp_table: opp_table7 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <89000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <133000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <178000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <267000000>;
+ };
+ };
+
+ bus_peri_opp_table: opp_table8 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <67000000>;
+ };
+ };
+
+ bus_g2d_opp_table: opp_table9 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <84000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <167000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <222000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <300000000>;
+ };
+ opp04 {
+ opp-hz = /bits/ 64 <333000000>;
+ };
+ };
+
+ bus_g2d_acp_opp_table: opp_table10 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <67000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <133000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <178000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <267000000>;
+ };
+ };
+
+ bus_jpeg_opp_table: opp_table11 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <75000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <150000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <300000000>;
+ };
+ };
+
+ bus_jpeg_apb_opp_table: opp_table12 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <84000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <111000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <134000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <167000000>;
+ };
+ };
+
+ bus_disp1_fimd_opp_table: opp_table13 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <120000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ };
+
+ bus_disp1_opp_table: opp_table14 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <120000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <300000000>;
+ };
+ };
+
+ bus_gscl_opp_table: opp_table15 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <150000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <200000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <300000000>;
+ };
+ };
+
+ bus_mscl_opp_table: opp_table16 {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <84000000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <167000000>;
+ };
+ opp02 {
+ opp-hz = /bits/ 64 <222000000>;
+ };
+ opp03 {
+ opp-hz = /bits/ 64 <333000000>;
+ };
+ opp04 {
+ opp-hz = /bits/ 64 <400000000>;
+ };
+ };
};
&dp {
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
index 20fa7612080d..2a4e10bc8801 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
@@ -56,6 +56,89 @@
};
};
+&bus_wcore {
+ devfreq-events = <&nocp_mem0_0>, <&nocp_mem0_1>,
+ <&nocp_mem1_0>, <&nocp_mem1_1>;
+ vdd-supply = <&buck3_reg>;
+ exynos,saturation-ratio = <100>;
+ status = "okay";
+};
+
+&bus_noc {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_fsys_apb {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_fsys {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_fsys2 {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_mfc {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_gen {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_peri {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_g2d {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_g2d_acp {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_jpeg {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_jpeg_apb {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_disp1_fimd {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_disp1 {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_gscl_scaler {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
+&bus_mscl {
+ devfreq = <&bus_wcore>;
+ status = "okay";
+};
+
&clock_audss {
assigned-clocks = <&clock_audss EXYNOS_MOUT_AUDSS>,
<&clock_audss EXYNOS_MOUT_I2S>,
@@ -361,6 +444,22 @@
vqmmc-supply = <&ldo13_reg>;
};
+&nocp_mem0_0 {
+ status = "okay";
+};
+
+&nocp_mem0_1 {
+ status = "okay";
+};
+
+&nocp_mem1_0 {
+ status = "okay";
+};
+
+&nocp_mem1_1 {
+ status = "okay";
+};
+
&pinctrl_0 {
hdmi_hpd_irq: hdmi-hpd-irq {
samsung,pins = "gpx3-7";
diff --git a/arch/arm/boot/dts/imx7d-nitrogen7.dts b/arch/arm/boot/dts/imx7d-nitrogen7.dts
new file mode 100644
index 000000000000..1ce97800f0c5
--- /dev/null
+++ b/arch/arm/boot/dts/imx7d-nitrogen7.dts
@@ -0,0 +1,745 @@
+/*
+ * Copyright 2016 Boundary Devices, Inc.
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ * a) This file is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ * b) Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include "imx7d.dtsi"
+
+/ {
+ model = "Boundary Devices i.MX7 Nitrogen7 Board";
+ compatible = "boundary,imx7d-nitrogen7", "fsl,imx7d";
+
+ aliases {
+ fb_lcd = &lcdif;
+ t_lcd = &t_lcd;
+ };
+
+ memory {
+ reg = <0x80000000 0x40000000>;
+ };
+
+ backlight-j9 {
+ compatible = "gpio-backlight";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_backlight_j9>;
+ gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+ default-on;
+ };
+
+ backlight-j20 {
+ compatible = "pwm-backlight";
+ pwms = <&pwm1 0 5000000>;
+ brightness-levels = <0 4 8 16 32 64 128 255>;
+ default-brightness-level = <6>;
+ status = "okay";
+ };
+
+ reg_usb_otg1_vbus: regulator-usb-otg1-vbus {
+ compatible = "regulator-fixed";
+ regulator-name = "usb_otg1_vbus";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ gpio = <&gpio1 5 GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ };
+
+ reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
+ compatible = "regulator-fixed";
+ regulator-name = "usb_otg2_vbus";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ gpio = <&gpio4 7 GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ };
+
+ reg_can2_3v3: regulator-can2-3v3 {
+ compatible = "regulator-fixed";
+ regulator-name = "can2-3v3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ gpio = <&gpio2 14 GPIO_ACTIVE_LOW>;
+ };
+
+ reg_vref_1v8: regulator-vref-1v8 {
+ compatible = "regulator-fixed";
+ regulator-name = "vref-1v8";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ };
+
+ reg_vref_3v3: regulator-vref-3v3 {
+ compatible = "regulator-fixed";
+ regulator-name = "vref-3v3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
+ reg_wlan: regulator-wlan {
+ compatible = "regulator-fixed";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ clocks = <&clks IMX7D_CLKO2_ROOT_DIV>;
+ clock-names = "slow";
+ regulator-name = "reg_wlan";
+ startup-delay-us = <70000>;
+ gpio = <&gpio4 21 GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ };
+};
+
+&adc1 {
+ vref-supply = <&reg_vref_1v8>;
+ status = "okay";
+};
+
+&adc2 {
+ vref-supply = <&reg_vref_1v8>;
+ status = "okay";
+};
+
+&clks {
+ assigned-clocks = <&clks IMX7D_CLKO2_ROOT_SRC>,
+ <&clks IMX7D_CLKO2_ROOT_DIV>;
+ assigned-clock-parents = <&clks IMX7D_CKIL>;
+ assigned-clock-rates = <0>, <32768>;
+};
+
+&cpu0 {
+ arm-supply = <&sw1a_reg>;
+};
+
+&fec1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_enet1>;
+ assigned-clocks = <&clks IMX7D_ENET1_TIME_ROOT_SRC>,
+ <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
+ assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
+ assigned-clock-rates = <0>, <100000000>;
+ phy-mode = "rgmii";
+ phy-handle = <&ethphy0>;
+ fsl,magic-packet;
+ status = "okay";
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ ethphy0: ethernet-phy@4 {
+ reg = <4>;
+ };
+ };
+};
+
+&flexcan2 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_flexcan2>;
+ xceiver-supply = <&reg_can2_3v3>;
+ status = "okay";
+};
+
+&i2c1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c1>;
+ status = "okay";
+
+ pmic: pfuze3000@08 {
+ compatible = "fsl,pfuze3000";
+ reg = <0x08>;
+
+ regulators {
+ sw1a_reg: sw1a {
+ regulator-min-microvolt = <700000>;
+ regulator-max-microvolt = <1475000>;
+ regulator-boot-on;
+ regulator-always-on;
+ regulator-ramp-delay = <6250>;
+ };
+
+ /* use sw1c_reg to align with pfuze100/pfuze200 */
+ sw1c_reg: sw1b {
+ regulator-min-microvolt = <700000>;
+ regulator-max-microvolt = <1475000>;
+ regulator-boot-on;
+ regulator-always-on;
+ regulator-ramp-delay = <6250>;
+ };
+
+ sw2_reg: sw2 {
+ regulator-min-microvolt = <1500000>;
+ regulator-max-microvolt = <1850000>;
+ regulator-boot-on;
+ regulator-always-on;
+ };
+
+ sw3a_reg: sw3 {
+ regulator-min-microvolt = <900000>;
+ regulator-max-microvolt = <1650000>;
+ regulator-boot-on;
+ regulator-always-on;
+ };
+
+ swbst_reg: swbst {
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5150000>;
+ };
+
+ snvs_reg: vsnvs {
+ regulator-min-microvolt = <1000000>;
+ regulator-max-microvolt = <3000000>;
+ regulator-boot-on;
+ regulator-always-on;
+ };
+
+ vref_reg: vrefddr {
+ regulator-boot-on;
+ regulator-always-on;
+ };
+
+ vgen1_reg: vldo1 {
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ vgen2_reg: vldo2 {
+ regulator-min-microvolt = <800000>;
+ regulator-max-microvolt = <1550000>;
+ regulator-always-on;
+ };
+
+ vgen3_reg: vccsd {
+ regulator-min-microvolt = <2850000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ vgen4_reg: v33 {
+ regulator-min-microvolt = <2850000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ vgen5_reg: vldo3 {
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ vgen6_reg: vldo4 {
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+ };
+ };
+};
+
+&i2c2 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c2>;
+ status = "okay";
+
+ rtc@68 {
+ compatible = "rv4162";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c2_rv4162>;
+ reg = <0x68>;
+ interrupts-extended = <&gpio2 15 IRQ_TYPE_LEVEL_LOW>;
+ };
+};
+
+&i2c3 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c3>;
+ status = "okay";
+
+ touch@48 {
+ compatible = "ti,tsc2004";
+ reg = <0x48>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c3_tsc2004>;
+ interrupts-extended = <&gpio3 4 IRQ_TYPE_EDGE_FALLING>;
+ wakeup-gpios = <&gpio3 4 GPIO_ACTIVE_LOW>;
+ };
+};
+
+&i2c4 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c4>;
+ status = "okay";
+
+ codec: wm8960@1a {
+ compatible = "wlf,wm8960";
+ reg = <0x1a>;
+ clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+ clock-names = "mclk";
+ wlf,shared-lrclk;
+ };
+};
+
+&lcdif {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_lcdif_dat
+ &pinctrl_lcdif_ctrl>;
+ lcd-supply = <&reg_vref_3v3>;
+ display = <&display0>;
+ status = "okay";
+
+ display0: lcd-display {
+ bits-per-pixel = <16>;
+ bus-width = <18>;
+
+ display-timings {
+ native-mode = <&t_lcd>;
+ t_lcd: t_lcd_default {
+ /* default to Okaya display */
+ clock-frequency = <30000000>;
+ hactive = <800>;
+ vactive = <480>;
+ hfront-porch = <40>;
+ hback-porch = <40>;
+ hsync-len = <48>;
+ vback-porch = <29>;
+ vfront-porch = <13>;
+ vsync-len = <3>;
+ hsync-active = <0>;
+ vsync-active = <0>;
+ de-active = <1>;
+ pixelclk-active = <0>;
+ };
+ };
+ };
+};
+
+&pwm1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_pwm1>;
+ status = "okay";
+};
+
+&pwm2 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_pwm2>;
+ status = "okay";
+};
+
+&uart1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_uart1>;
+ assigned-clocks = <&clks IMX7D_UART1_ROOT_SRC>;
+ assigned-clock-parents = <&clks IMX7D_OSC_24M_CLK>;
+ status = "okay";
+};
+
+&uart2 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_uart2>;
+ assigned-clocks = <&clks IMX7D_UART2_ROOT_SRC>;
+ assigned-clock-parents = <&clks IMX7D_OSC_24M_CLK>;
+ status = "okay";
+};
+
+&uart3 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_uart3>;
+ assigned-clocks = <&clks IMX7D_UART3_ROOT_SRC>;
+ assigned-clock-parents = <&clks IMX7D_OSC_24M_CLK>;
+ status = "okay";
+};
+
+&uart6 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_uart6>;
+ assigned-clocks = <&clks IMX7D_UART6_ROOT_SRC>;
+ assigned-clock-parents = <&clks IMX7D_PLL_SYS_MAIN_240M_CLK>;
+ fsl,uart-has-rtscts;
+ status = "okay";
+};
+
+&usbotg1 {
+ vbus-supply = <&reg_usb_otg1_vbus>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usbotg1>;
+ status = "okay";
+};
+
+&usbotg2 {
+ vbus-supply = <&reg_usb_otg2_vbus>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usbotg2>;
+ dr_mode = "host";
+ status = "okay";
+};
+
+&usdhc1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usdhc1>;
+ cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+ vmmc-supply = <&vgen3_reg>;
+ bus-width = <4>;
+ fsl,tuning-step = <2>;
+ wakeup-source;
+ keep-power-in-suspend;
+ status = "okay";
+};
+
+&usdhc2 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usdhc2>;
+ bus-width = <4>;
+ non-removable;
+ vmmc-supply = <&reg_wlan>;
+ cap-power-off-card;
+ keep-power-in-suspend;
+ status = "okay";
+
+ wlcore: wlcore@2 {
+ compatible = "ti,wl1271";
+ reg = <2>;
+ interrupt-parent = <&gpio4>;
+ interrupts = <20 IRQ_TYPE_LEVEL_HIGH>;
+ ref-clock-frequency = <38400000>;
+ };
+};
+
+&usdhc3 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usdhc3>;
+ assigned-clocks = <&clks IMX7D_USDHC3_ROOT_CLK>;
+ assigned-clock-rates = <400000000>;
+ bus-width = <8>;
+ fsl,tuning-step = <2>;
+ non-removable;
+ status = "okay";
+};
+
+&wdog1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_wdog1>;
+ status = "okay";
+};
+
+&iomuxc {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_hog_1 &pinctrl_j2>;
+
+ pinctrl_hog_1: hoggrp-1 {
+ fsl,pins = <
+ MX7D_PAD_SD3_RESET_B__GPIO6_IO11 0x5d
+ MX7D_PAD_GPIO1_IO13__GPIO1_IO13 0x7d
+ MX7D_PAD_ECSPI2_MISO__GPIO4_IO22 0x7d
+ >;
+ };
+
+ pinctrl_enet1: enet1grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO10__ENET1_MDIO 0x3
+ MX7D_PAD_GPIO1_IO11__ENET1_MDC 0x3
+ MX7D_PAD_GPIO1_IO12__CCM_ENET_REF_CLK1 0x3
+ MX7D_PAD_ENET1_RGMII_TXC__ENET1_RGMII_TXC 0x71
+ MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0 0x71
+ MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1 0x71
+ MX7D_PAD_ENET1_RGMII_TD2__ENET1_RGMII_TD2 0x71
+ MX7D_PAD_ENET1_RGMII_TD3__ENET1_RGMII_TD3 0x71
+ MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL 0x71
+ MX7D_PAD_ENET1_RGMII_RXC__ENET1_RGMII_RXC 0x71
+ MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0 0x11
+ MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1 0x11
+ MX7D_PAD_ENET1_RGMII_RD2__ENET1_RGMII_RD2 0x11
+ MX7D_PAD_ENET1_RGMII_RD3__ENET1_RGMII_RD3 0x71
+ MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL 0x11
+ MX7D_PAD_SD3_STROBE__GPIO6_IO10 0x75
+ >;
+ };
+
+ pinctrl_flexcan2: flexcan2grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO14__FLEXCAN2_RX 0x7d
+ MX7D_PAD_GPIO1_IO15__FLEXCAN2_TX 0x7d
+ MX7D_PAD_EPDC_DATA14__GPIO2_IO14 0x7d
+ >;
+ };
+
+ pinctrl_i2c1: i2c1grp {
+ fsl,pins = <
+ MX7D_PAD_I2C1_SDA__I2C1_SDA 0x4000007f
+ MX7D_PAD_I2C1_SCL__I2C1_SCL 0x4000007f
+ >;
+ };
+
+ pinctrl_i2c2: i2c2grp {
+ fsl,pins = <
+ MX7D_PAD_I2C2_SDA__I2C2_SDA 0x4000007f
+ MX7D_PAD_I2C2_SCL__I2C2_SCL 0x4000007f
+ >;
+ };
+
+ pinctrl_i2c2_rv4162: i2c2-rv4162grp {
+ fsl,pins = <
+ MX7D_PAD_EPDC_DATA15__GPIO2_IO15 0x7d
+ >;
+ };
+
+ pinctrl_i2c3: i2c3grp {
+ fsl,pins = <
+ MX7D_PAD_I2C3_SDA__I2C3_SDA 0x4000007f
+ MX7D_PAD_I2C3_SCL__I2C3_SCL 0x4000007f
+ >;
+ };
+
+ pinctrl_i2c3_tsc2004: i2c3tsc2004grp {
+ fsl,pins = <
+ MX7D_PAD_LCD_RESET__GPIO3_IO4 0x79
+ MX7D_PAD_SD2_WP__GPIO5_IO10 0x7d
+ >;
+ };
+
+ pinctrl_i2c4: i2c4grp {
+ fsl,pins = <
+ MX7D_PAD_I2C4_SDA__I2C4_SDA 0x4000007f
+ MX7D_PAD_I2C4_SCL__I2C4_SCL 0x4000007f
+ >;
+ };
+
+ pinctrl_j2: j2grp {
+ fsl,pins = <
+ MX7D_PAD_SAI1_TX_DATA__GPIO6_IO15 0x7d
+ MX7D_PAD_EPDC_BDR0__GPIO2_IO28 0x7d
+ MX7D_PAD_SAI1_RX_DATA__GPIO6_IO12 0x7d
+ MX7D_PAD_EPDC_BDR1__GPIO2_IO29 0x7d
+ MX7D_PAD_SD1_WP__GPIO5_IO1 0x7d
+ MX7D_PAD_EPDC_SDSHR__GPIO2_IO19 0x7d
+ MX7D_PAD_SD1_RESET_B__GPIO5_IO2 0x7d
+ MX7D_PAD_SD2_RESET_B__GPIO5_IO11 0x7d
+ MX7D_PAD_EPDC_DATA07__GPIO2_IO7 0x7d
+ MX7D_PAD_EPDC_DATA08__GPIO2_IO8 0x7d
+ MX7D_PAD_EPDC_DATA09__GPIO2_IO9 0x7d
+ MX7D_PAD_EPDC_DATA10__GPIO2_IO10 0x7d
+ MX7D_PAD_EPDC_DATA11__GPIO2_IO11 0x7d
+ MX7D_PAD_EPDC_DATA12__GPIO2_IO12 0x7d
+ MX7D_PAD_SAI1_TX_SYNC__GPIO6_IO14 0x7d
+ MX7D_PAD_EPDC_DATA13__GPIO2_IO13 0x7d
+ MX7D_PAD_SAI1_TX_BCLK__GPIO6_IO13 0x7d
+ MX7D_PAD_SD2_CD_B__GPIO5_IO9 0x7d
+ MX7D_PAD_EPDC_GDCLK__GPIO2_IO24 0x7d
+ MX7D_PAD_SAI2_RX_DATA__GPIO6_IO21 0x7d
+ MX7D_PAD_EPDC_GDOE__GPIO2_IO25 0x7d
+ MX7D_PAD_EPDC_GDRL__GPIO2_IO26 0x7d
+ MX7D_PAD_SAI2_TX_DATA__GPIO6_IO22 0x7d
+ MX7D_PAD_EPDC_SDCE0__GPIO2_IO20 0x7d
+ MX7D_PAD_SAI2_TX_BCLK__GPIO6_IO20 0x7d
+ MX7D_PAD_EPDC_SDCE1__GPIO2_IO21 0x7d
+ MX7D_PAD_SAI2_TX_SYNC__GPIO6_IO19 0x7d
+ MX7D_PAD_EPDC_SDCE2__GPIO2_IO22 0x7d
+ MX7D_PAD_EPDC_SDCE3__GPIO2_IO23 0x7d
+ MX7D_PAD_EPDC_GDSP__GPIO2_IO27 0x7d
+ MX7D_PAD_EPDC_SDCLK__GPIO2_IO16 0x7d
+ MX7D_PAD_EPDC_SDLE__GPIO2_IO17 0x7d
+ MX7D_PAD_EPDC_SDOE__GPIO2_IO18 0x7d
+ MX7D_PAD_EPDC_PWR_COM__GPIO2_IO30 0x7d
+ MX7D_PAD_EPDC_PWR_STAT__GPIO2_IO31 0x7d
+ >;
+ };
+
+ pinctrl_lcdif_dat: lcdifdatgrp {
+ fsl,pins = <
+ MX7D_PAD_LCD_DATA00__LCD_DATA0 0x79
+ MX7D_PAD_LCD_DATA01__LCD_DATA1 0x79
+ MX7D_PAD_LCD_DATA02__LCD_DATA2 0x79
+ MX7D_PAD_LCD_DATA03__LCD_DATA3 0x79
+ MX7D_PAD_LCD_DATA04__LCD_DATA4 0x79
+ MX7D_PAD_LCD_DATA05__LCD_DATA5 0x79
+ MX7D_PAD_LCD_DATA06__LCD_DATA6 0x79
+ MX7D_PAD_LCD_DATA07__LCD_DATA7 0x79
+ MX7D_PAD_LCD_DATA08__LCD_DATA8 0x79
+ MX7D_PAD_LCD_DATA09__LCD_DATA9 0x79
+ MX7D_PAD_LCD_DATA10__LCD_DATA10 0x79
+ MX7D_PAD_LCD_DATA11__LCD_DATA11 0x79
+ MX7D_PAD_LCD_DATA12__LCD_DATA12 0x79
+ MX7D_PAD_LCD_DATA13__LCD_DATA13 0x79
+ MX7D_PAD_LCD_DATA14__LCD_DATA14 0x79
+ MX7D_PAD_LCD_DATA15__LCD_DATA15 0x79
+ MX7D_PAD_LCD_DATA16__LCD_DATA16 0x79
+ MX7D_PAD_LCD_DATA17__LCD_DATA17 0x79
+ MX7D_PAD_LCD_DATA18__LCD_DATA18 0x79
+ MX7D_PAD_LCD_DATA19__LCD_DATA19 0x79
+ MX7D_PAD_LCD_DATA20__LCD_DATA20 0x79
+ MX7D_PAD_LCD_DATA21__LCD_DATA21 0x79
+ MX7D_PAD_LCD_DATA22__LCD_DATA22 0x79
+ MX7D_PAD_LCD_DATA23__LCD_DATA23 0x79
+ >;
+ };
+
+ pinctrl_lcdif_ctrl: lcdifctrlgrp {
+ fsl,pins = <
+ MX7D_PAD_LCD_CLK__LCD_CLK 0x79
+ MX7D_PAD_LCD_ENABLE__LCD_ENABLE 0x79
+ MX7D_PAD_LCD_VSYNC__LCD_VSYNC 0x79
+ MX7D_PAD_LCD_HSYNC__LCD_HSYNC 0x79
+ >;
+ };
+
+ pinctrl_pwm2: pwm2grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO09__PWM2_OUT 0x7d
+ >;
+ };
+
+ pinctrl_uart1: uart1grp {
+ fsl,pins = <
+ MX7D_PAD_UART1_TX_DATA__UART1_DCE_TX 0x79
+ MX7D_PAD_UART1_RX_DATA__UART1_DCE_RX 0x79
+ >;
+ };
+
+ pinctrl_uart2: uart2grp {
+ fsl,pins = <
+ MX7D_PAD_UART2_TX_DATA__UART2_DCE_TX 0x79
+ MX7D_PAD_UART2_RX_DATA__UART2_DCE_RX 0x79
+ >;
+ };
+
+ pinctrl_uart3: uart3grp {
+ fsl,pins = <
+ MX7D_PAD_UART3_TX_DATA__UART3_DCE_TX 0x79
+ MX7D_PAD_UART3_RX_DATA__UART3_DCE_RX 0x79
+ MX7D_PAD_EPDC_DATA04__GPIO2_IO4 0x7d
+ >;
+ };
+
+ pinctrl_uart6: uart6grp {
+ fsl,pins = <
+ MX7D_PAD_ECSPI1_MOSI__UART6_DCE_TX 0x79
+ MX7D_PAD_ECSPI1_SCLK__UART6_DCE_RX 0x79
+ MX7D_PAD_ECSPI1_SS0__UART6_DCE_CTS 0x79
+ MX7D_PAD_ECSPI1_MISO__UART6_DCE_RTS 0x79
+ >;
+ };
+
+ pinctrl_usbotg2: usbotg2grp {
+ fsl,pins = <
+ MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x7d
+ MX7D_PAD_UART3_CTS_B__GPIO4_IO7 0x14
+ >;
+ };
+
+ pinctrl_usdhc1: usdhc1grp {
+ fsl,pins = <
+ MX7D_PAD_SD1_CMD__SD1_CMD 0x59
+ MX7D_PAD_SD1_CLK__SD1_CLK 0x19
+ MX7D_PAD_SD1_DATA0__SD1_DATA0 0x59
+ MX7D_PAD_SD1_DATA1__SD1_DATA1 0x59
+ MX7D_PAD_SD1_DATA2__SD1_DATA2 0x59
+ MX7D_PAD_SD1_DATA3__SD1_DATA3 0x59
+ MX7D_PAD_GPIO1_IO08__SD1_VSELECT 0x75
+ MX7D_PAD_SD1_CD_B__GPIO5_IO0 0x75
+ >;
+ };
+
+ pinctrl_usdhc2: usdhc2grp {
+ fsl,pins = <
+ MX7D_PAD_SD2_CMD__SD2_CMD 0x59
+ MX7D_PAD_SD2_CLK__SD2_CLK 0x19
+ MX7D_PAD_SD2_DATA0__SD2_DATA0 0x59
+ MX7D_PAD_SD2_DATA1__SD2_DATA1 0x59
+ MX7D_PAD_SD2_DATA2__SD2_DATA2 0x59
+ MX7D_PAD_SD2_DATA3__SD2_DATA3 0x59
+ MX7D_PAD_ECSPI2_SCLK__GPIO4_IO20 0x59
+ MX7D_PAD_ECSPI2_MOSI__GPIO4_IO21 0x59
+ >;
+ };
+
+ pinctrl_usdhc3: usdhc3grp {
+ fsl,pins = <
+ MX7D_PAD_SD3_CMD__SD3_CMD 0x59
+ MX7D_PAD_SD3_CLK__SD3_CLK 0x19
+ MX7D_PAD_SD3_DATA0__SD3_DATA0 0x59
+ MX7D_PAD_SD3_DATA1__SD3_DATA1 0x59
+ MX7D_PAD_SD3_DATA2__SD3_DATA2 0x59
+ MX7D_PAD_SD3_DATA3__SD3_DATA3 0x59
+ MX7D_PAD_SD3_DATA4__SD3_DATA4 0x59
+ MX7D_PAD_SD3_DATA5__SD3_DATA5 0x59
+ MX7D_PAD_SD3_DATA6__SD3_DATA6 0x59
+ MX7D_PAD_SD3_DATA7__SD3_DATA7 0x59
+ >;
+ };
+};
+
+&iomuxc_lpsr {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_hog_2>;
+
+ pinctrl_hog_2: hoggrp-2 {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO02__GPIO1_IO2 0x7d
+ MX7D_PAD_GPIO1_IO03__CCM_CLKO2 0x7d
+ >;
+ };
+
+ pinctrl_backlight_j9: backlightj9grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO07__GPIO1_IO7 0x7d
+ >;
+ };
+
+ pinctrl_pwm1: pwm1grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO01__PWM1_OUT 0x7d
+ >;
+ };
+
+ pinctrl_usbotg1: usbotg1grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO04__USB_OTG1_OC 0x7d
+ MX7D_PAD_GPIO1_IO05__GPIO1_IO5 0x14
+ >;
+ };
+
+ pinctrl_wdog1: wdog1grp {
+ fsl,pins = <
+ MX7D_PAD_GPIO1_IO00__WDOD1_WDOG_B 0x75
+ >;
+ };
+};
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index b5a50e0e7ff1..6b3faa298417 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -651,6 +651,17 @@
#pwm-cells = <2>;
status = "disabled";
};
+
+ lcdif: lcdif@30730000 {
+ compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif";
+ reg = <0x30730000 0x10000>;
+ interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>,
+ <&clks IMX7D_CLK_DUMMY>,
+ <&clks IMX7D_CLK_DUMMY>;
+ clock-names = "pix", "axi", "disp_axi";
+ status = "disabled";
+ };
};
aips3: aips-bus@30800000 {
@@ -693,6 +704,26 @@
status = "disabled";
};
+ flexcan1: can@30a00000 {
+ compatible = "fsl,imx7d-flexcan", "fsl,imx6q-flexcan";
+ reg = <0x30a00000 0x10000>;
+ interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clks IMX7D_CLK_DUMMY>,
+ <&clks IMX7D_CAN1_ROOT_CLK>;
+ clock-names = "ipg", "per";
+ status = "disabled";
+ };
+
+ flexcan2: can@30a10000 {
+ compatible = "fsl,imx7d-flexcan", "fsl,imx6q-flexcan";
+ reg = <0x30a10000 0x10000>;
+ interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clks IMX7D_CLK_DUMMY>,
+ <&clks IMX7D_CAN2_ROOT_CLK>;
+ clock-names = "ipg", "per";
+ status = "disabled";
+ };
+
i2c1: i2c@30a20000 {
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts
index 76056ba92ced..ed449827c3d3 100644
--- a/arch/arm/boot/dts/omap3-evm-37xx.dts
+++ b/arch/arm/boot/dts/omap3-evm-37xx.dts
@@ -85,7 +85,7 @@
OMAP3_CORE1_IOPAD(0x2158, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_clk.sdmmc2_clk */
OMAP3_CORE1_IOPAD(0x215a, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_cmd.sdmmc2_cmd */
OMAP3_CORE1_IOPAD(0x215c, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat0.sdmmc2_dat0 */
- OMAP3_CORE1_IOPAD(0x215e, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */
+ OMAP3_CORE1_IOPAD(0x215e, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */
OMAP3_CORE1_IOPAD(0x2160, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat2.sdmmc2_dat2 */
OMAP3_CORE1_IOPAD(0x2162, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat3.sdmmc2_dat3 */
>;
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index 41f5d386f21f..f4f2ce46d681 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -188,6 +188,7 @@
vmmc-supply = <&vmmc1>;
vmmc_aux-supply = <&vsim>;
bus-width = <4>;
+ cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>;
};
&mmc3 {
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index d6f839cab649..b6971060648a 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -194,6 +194,12 @@
OMAP3630_CORE2_IOPAD(0x25f8, PIN_OUTPUT | MUX_MODE4) /* etk_d14.gpio_28 */
>;
};
+
+ mmc1_wp_pins: pinmux_mmc1_cd_pins {
+ pinctrl-single,pins = <
+ OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT | MUX_MODE4) /* etk_d15.gpio_29 */
+ >;
+ };
};
&i2c3 {
@@ -250,3 +256,8 @@
};
};
};
+
+&mmc1 {
+ pinctrl-0 = <&mmc1_pins &mmc1_wp_pins>;
+ wp-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>; /* gpio_29 */
+};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index d9e2d9c6e999..2b74a81d1de2 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -288,7 +288,7 @@
pinctrl-single,pins = <
OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */
OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1) /* ssi1_flag_tx */
- OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+ OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */
OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1) /* ssi1_dat_tx */
OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1) /* ssi1_dat_rx */
OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1) /* ssi1_flag_rx */
@@ -300,7 +300,7 @@
modem_pins: pinmux_modem {
pinctrl-single,pins = <
OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE4) /* gpio 70 => cmt_apeslpx */
- OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio 72 => ape_rst_rq */
+ OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | MUX_MODE4) /* gpio 72 => ape_rst_rq */
OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE4) /* gpio 73 => cmt_rst_rq */
OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE4) /* gpio 74 => cmt_en */
OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE4) /* gpio 75 => cmt_rst */
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index a00ca761675d..927b17fc4ed8 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -97,7 +97,7 @@
OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1) /* ssi1_dat_tx */
OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1) /* ssi1_flag_tx */
OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */
- OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+ OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */
OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1) /* ssi1_dat_rx */
OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1) /* ssi1_flag_rx */
OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE1) /* ssi1_rdy_rx */
@@ -110,7 +110,7 @@
OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE7) /* ssi1_dat_tx */
OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE7) /* ssi1_flag_tx */
OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLDOWN | MUX_MODE7) /* ssi1_rdy_tx */
- OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+ OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */
OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE7) /* ssi1_dat_rx */
OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE7) /* ssi1_flag_rx */
OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE4) /* ssi1_rdy_rx */
@@ -120,7 +120,7 @@
modem_pins1: pinmux_modem_core1_pins {
pinctrl-single,pins = <
- OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio_34 (ape_rst_rq) */
+ OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | MUX_MODE4) /* gpio_34 (ape_rst_rq) */
OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE4) /* gpio_88 (cmt_rst_rq) */
OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE4) /* gpio_93 (cmt_apeslpx) */
>;
diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts
index f19170bdcc1f..c29b41dc7b95 100644
--- a/arch/arm/boot/dts/omap3-zoom3.dts
+++ b/arch/arm/boot/dts/omap3-zoom3.dts
@@ -98,7 +98,7 @@
pinctrl-single,pins = <
OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */
OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */
- OMAP3_CORE1_IOPAD(0x217a, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */
+ OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */
OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */
>;
};
@@ -107,7 +107,7 @@
pinctrl-single,pins = <
OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */
OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */
- OMAP3_CORE1_IOPAD(0x219e, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */
+ OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */
OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */
>;
};
@@ -125,7 +125,7 @@
pinctrl-single,pins = <
OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_clk.sdmmc3_clk */
OMAP3630_CORE2_IOPAD(0x25e4, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d4.sdmmc3_dat0 */
- OMAP3630_CORE2_IOPAD(0x25e6, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */
+ OMAP3630_CORE2_IOPAD(0x25e6, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */
OMAP3630_CORE2_IOPAD(0x25e8, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d6.sdmmc3_dat2 */
OMAP3630_CORE2_IOPAD(0x25e2, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d3.sdmmc3_dat3 */
>;
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index dc759a3028b7..5d5b620b7d9b 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -14,6 +14,29 @@
display0 = &hdmi0;
};
+ vmain: fixedregulator-vmain {
+ compatible = "regulator-fixed";
+ regulator-name = "vmain";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ };
+
+ vsys_cobra: fixedregulator-vsys_cobra {
+ compatible = "regulator-fixed";
+ regulator-name = "vsys_cobra";
+ vin-supply = <&vmain>;
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ };
+
+ vdds_1v8_main: fixedregulator-vdds_1v8_main {
+ compatible = "regulator-fixed";
+ regulator-name = "vdds_1v8_main";
+ vin-supply = <&smps7_reg>;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ };
+
vmmcsd_fixed: fixedregulator-mmcsd {
compatible = "regulator-fixed";
regulator-name = "vmmcsd_fixed";
@@ -309,7 +332,7 @@
wlcore_irq_pin: pinmux_wlcore_irq_pin {
pinctrl-single,pins = <
- OMAP5_IOPAD(0x40, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */
+ OMAP5_IOPAD(0x40, PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */
>;
};
};
@@ -409,6 +432,26 @@
ti,ldo6-vibrator;
+ smps123-in-supply = <&vsys_cobra>;
+ smps45-in-supply = <&vsys_cobra>;
+ smps6-in-supply = <&vsys_cobra>;
+ smps7-in-supply = <&vsys_cobra>;
+ smps8-in-supply = <&vsys_cobra>;
+ smps9-in-supply = <&vsys_cobra>;
+ smps10_out2-in-supply = <&vsys_cobra>;
+ smps10_out1-in-supply = <&vsys_cobra>;
+ ldo1-in-supply = <&vsys_cobra>;
+ ldo2-in-supply = <&vsys_cobra>;
+ ldo3-in-supply = <&vdds_1v8_main>;
+ ldo4-in-supply = <&vdds_1v8_main>;
+ ldo5-in-supply = <&vsys_cobra>;
+ ldo6-in-supply = <&vdds_1v8_main>;
+ ldo7-in-supply = <&vsys_cobra>;
+ ldo8-in-supply = <&vsys_cobra>;
+ ldo9-in-supply = <&vmmcsd_fixed>;
+ ldoln-in-supply = <&vsys_cobra>;
+ ldousb-in-supply = <&vsys_cobra>;
+
regulators {
smps123_reg: smps123 {
/* VDD_OPP_MPU */
@@ -600,7 +643,8 @@
pinctrl-0 = <&twl6040_pins>;
interrupts = <GIC_SPI 119 IRQ_TYPE_NONE>; /* IRQ_SYS_2N cascaded to gic */
- ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>; /* gpio line 141 */
+
+ /* audpwron gpio defined in the board specific dts */
vio-supply = <&smps7_reg>;
v2v1-supply = <&smps9_reg>;
diff --git a/arch/arm/boot/dts/omap5-igep0050.dts b/arch/arm/boot/dts/omap5-igep0050.dts
index 46ecb1dd3b5c..f75ce02fb398 100644
--- a/arch/arm/boot/dts/omap5-igep0050.dts
+++ b/arch/arm/boot/dts/omap5-igep0050.dts
@@ -35,6 +35,22 @@
};
};
+/* LDO4 is VPP1 - ball AD9 */
+&ldo4_reg {
+ regulator-min-microvolt = <2000000>;
+ regulator-max-microvolt = <2000000>;
+};
+
+/*
+ * LDO7 is used for HDMI: VDDA_DSIPORTA - ball AA33, VDDA_DSIPORTC - ball AE33,
+ * VDDA_HDMI - ball AN25
+ */
+&ldo7_reg {
+ status = "okay";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+};
+
&omap5_pmx_core {
i2c4_pins: pinmux_i2c4_pins {
pinctrl-single,pins = <
@@ -52,3 +68,13 @@
<&gpio7 3 0>; /* 195, SDA */
};
+&twl6040 {
+ ti,audpwron-gpio = <&gpio5 16 GPIO_ACTIVE_HIGH>; /* gpio line 144 */
+};
+
+&twl6040_pins {
+ pinctrl-single,pins = <
+ OMAP5_IOPAD(0x1c4, PIN_OUTPUT | MUX_MODE6) /* mcspi1_somi.gpio5_144 */
+ OMAP5_IOPAD(0x1ca, PIN_OUTPUT | MUX_MODE6) /* perslimbus2_clock.gpio5_145 */
+ >;
+};
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 60b3fbb3bf07..a51e60518eb6 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -51,3 +51,13 @@
<&gpio9 1 GPIO_ACTIVE_HIGH>, /* TCA6424A P00, LS OE */
<&gpio7 1 GPIO_ACTIVE_HIGH>; /* GPIO 193, HPD */
};
+
+&twl6040 {
+ ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>; /* gpio line 141 */
+};
+
+&twl6040_pins {
+ pinctrl-single,pins = <
+ OMAP5_IOPAD(0x1be, PIN_OUTPUT | MUX_MODE6) /* mcspi1_somi.gpio5_141 */
+ >;
+};
diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi
index 0c82097daffc..b9bbcce69dfb 100644
--- a/arch/arm/boot/dts/r8a7779.dtsi
+++ b/arch/arm/boot/dts/r8a7779.dtsi
@@ -14,6 +14,7 @@
#include <dt-bindings/clock/r8a7779-clock.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/power/r8a7779-sysc.h>
/ {
compatible = "renesas,r8a7779";
@@ -34,18 +35,21 @@
compatible = "arm,cortex-a9";
reg = <1>;
clock-frequency = <1000000000>;
+ power-domains = <&sysc R8A7779_PD_ARM1>;
};
cpu@2 {
device_type = "cpu";
compatible = "arm,cortex-a9";
reg = <2>;
clock-frequency = <1000000000>;
+ power-domains = <&sysc R8A7779_PD_ARM2>;
};
cpu@3 {
device_type = "cpu";
compatible = "arm,cortex-a9";
reg = <3>;
clock-frequency = <1000000000>;
+ power-domains = <&sysc R8A7779_PD_ARM3>;
};
};
@@ -173,7 +177,7 @@
reg = <0xffc70000 0x1000>;
interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_I2C0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -184,7 +188,7 @@
reg = <0xffc71000 0x1000>;
interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_I2C1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -195,7 +199,7 @@
reg = <0xffc72000 0x1000>;
interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_I2C2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -206,7 +210,7 @@
reg = <0xffc73000 0x1000>;
interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_I2C3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -218,7 +222,7 @@
clocks = <&mstp0_clks R8A7779_CLK_SCIF0>,
<&cpg_clocks R8A7779_CLK_S1>, <&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -230,7 +234,7 @@
clocks = <&mstp0_clks R8A7779_CLK_SCIF1>,
<&cpg_clocks R8A7779_CLK_S1>, <&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -242,7 +246,7 @@
clocks = <&mstp0_clks R8A7779_CLK_SCIF2>,
<&cpg_clocks R8A7779_CLK_S1>, <&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -254,7 +258,7 @@
clocks = <&mstp0_clks R8A7779_CLK_SCIF3>,
<&cpg_clocks R8A7779_CLK_S1>, <&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -266,7 +270,7 @@
clocks = <&mstp0_clks R8A7779_CLK_SCIF4>,
<&cpg_clocks R8A7779_CLK_S1>, <&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -278,7 +282,7 @@
clocks = <&mstp0_clks R8A7779_CLK_SCIF5>,
<&cpg_clocks R8A7779_CLK_S1>, <&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -300,7 +304,7 @@
<GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_TMU0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
#renesas,channels = <3>;
@@ -315,7 +319,7 @@
<GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_TMU1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
#renesas,channels = <3>;
@@ -330,7 +334,7 @@
<GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7779_CLK_TMU2>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
#renesas,channels = <3>;
@@ -342,7 +346,7 @@
reg = <0xfc600000 0x2000>;
interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7779_CLK_SATA>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
};
sdhi0: sd@ffe4c000 {
@@ -350,7 +354,7 @@
reg = <0xffe4c000 0x100>;
interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7779_CLK_SDHI0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -359,7 +363,7 @@
reg = <0xffe4d000 0x100>;
interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7779_CLK_SDHI1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -368,7 +372,7 @@
reg = <0xffe4e000 0x100>;
interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7779_CLK_SDHI2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -377,7 +381,7 @@
reg = <0xffe4f000 0x100>;
interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7779_CLK_SDHI3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -388,7 +392,7 @@
#address-cells = <1>;
#size-cells = <0>;
clocks = <&mstp0_clks R8A7779_CLK_HSPI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -399,7 +403,7 @@
#address-cells = <1>;
#size-cells = <0>;
clocks = <&mstp0_clks R8A7779_CLK_HSPI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -410,7 +414,7 @@
#address-cells = <1>;
#size-cells = <0>;
clocks = <&mstp0_clks R8A7779_CLK_HSPI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -419,7 +423,7 @@
reg = <0 0xfff80000 0 0x40000>;
interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7779_CLK_DU>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
status = "disabled";
ports {
@@ -585,4 +589,10 @@
"mmc1", "mmc0";
};
};
+
+ sysc: system-controller@ffd85000 {
+ compatible = "renesas,r8a7779-sysc";
+ reg = <0xffd85000 0x0200>;
+ #power-domain-cells = <1>;
+ };
};
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 935064fe7b13..83cf23cd26bb 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -13,6 +13,7 @@
#include <dt-bindings/clock/r8a7790-clock.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/power/r8a7790-sysc.h>
/ {
compatible = "renesas,r8a7790";
@@ -52,6 +53,7 @@
voltage-tolerance = <1>; /* 1% */
clocks = <&cpg_clocks R8A7790_CLK_Z>;
clock-latency = <300000>; /* 300 us */
+ power-domains = <&sysc R8A7790_PD_CA15_CPU0>;
next-level-cache = <&L2_CA15>;
/* kHz - uV - OPPs unknown yet */
@@ -68,6 +70,7 @@
compatible = "arm,cortex-a15";
reg = <1>;
clock-frequency = <1300000000>;
+ power-domains = <&sysc R8A7790_PD_CA15_CPU1>;
next-level-cache = <&L2_CA15>;
};
@@ -76,6 +79,7 @@
compatible = "arm,cortex-a15";
reg = <2>;
clock-frequency = <1300000000>;
+ power-domains = <&sysc R8A7790_PD_CA15_CPU2>;
next-level-cache = <&L2_CA15>;
};
@@ -84,6 +88,7 @@
compatible = "arm,cortex-a15";
reg = <3>;
clock-frequency = <1300000000>;
+ power-domains = <&sysc R8A7790_PD_CA15_CPU3>;
next-level-cache = <&L2_CA15>;
};
@@ -92,6 +97,7 @@
compatible = "arm,cortex-a7";
reg = <0x100>;
clock-frequency = <780000000>;
+ power-domains = <&sysc R8A7790_PD_CA7_CPU0>;
next-level-cache = <&L2_CA7>;
};
@@ -100,6 +106,7 @@
compatible = "arm,cortex-a7";
reg = <0x101>;
clock-frequency = <780000000>;
+ power-domains = <&sysc R8A7790_PD_CA7_CPU1>;
next-level-cache = <&L2_CA7>;
};
@@ -108,6 +115,7 @@
compatible = "arm,cortex-a7";
reg = <0x102>;
clock-frequency = <780000000>;
+ power-domains = <&sysc R8A7790_PD_CA7_CPU2>;
next-level-cache = <&L2_CA7>;
};
@@ -116,6 +124,7 @@
compatible = "arm,cortex-a7";
reg = <0x103>;
clock-frequency = <780000000>;
+ power-domains = <&sysc R8A7790_PD_CA7_CPU3>;
next-level-cache = <&L2_CA7>;
};
};
@@ -141,12 +150,14 @@
L2_CA15: cache-controller@0 {
compatible = "cache";
+ power-domains = <&sysc R8A7790_PD_CA15_SCU>;
cache-unified;
cache-level = <2>;
};
L2_CA7: cache-controller@1 {
compatible = "cache";
+ power-domains = <&sysc R8A7790_PD_CA7_SCU>;
cache-unified;
cache-level = <2>;
};
@@ -173,7 +184,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7790_CLK_GPIO0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
gpio1: gpio@e6051000 {
@@ -186,7 +197,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7790_CLK_GPIO1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
gpio2: gpio@e6052000 {
@@ -199,7 +210,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7790_CLK_GPIO2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
gpio3: gpio@e6053000 {
@@ -212,7 +223,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7790_CLK_GPIO3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
gpio4: gpio@e6054000 {
@@ -225,7 +236,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7790_CLK_GPIO4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
gpio5: gpio@e6055000 {
@@ -238,7 +249,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7790_CLK_GPIO5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
thermal: thermal@e61f0000 {
@@ -248,7 +259,7 @@
reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#thermal-sensor-cells = <0>;
};
@@ -267,7 +278,7 @@
<GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7790_CLK_CMT0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,channels-mask = <0x60>;
@@ -287,7 +298,7 @@
<GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7790_CLK_CMT1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,channels-mask = <0xff>;
@@ -304,7 +315,7 @@
<GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp4_clks R8A7790_CLK_IRQC>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
dmac0: dma-controller@e6700000 {
@@ -333,7 +344,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7790_CLK_SYS_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -364,7 +375,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7790_CLK_SYS_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -393,7 +404,7 @@
"ch12";
clocks = <&mstp5_clks R8A7790_CLK_AUDIO_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <13>;
};
@@ -422,7 +433,7 @@
"ch12";
clocks = <&mstp5_clks R8A7790_CLK_AUDIO_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <13>;
};
@@ -434,7 +445,7 @@
GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "ch0", "ch1";
clocks = <&mstp3_clks R8A7790_CLK_USBDMAC0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <2>;
};
@@ -446,7 +457,7 @@
GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "ch0", "ch1";
clocks = <&mstp3_clks R8A7790_CLK_USBDMAC1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <2>;
};
@@ -458,7 +469,7 @@
reg = <0 0xe6508000 0 0x40>;
interrupts = <GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7790_CLK_I2C0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -470,7 +481,7 @@
reg = <0 0xe6518000 0 0x40>;
interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7790_CLK_I2C1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -482,7 +493,7 @@
reg = <0 0xe6530000 0 0x40>;
interrupts = <GIC_SPI 286 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7790_CLK_I2C2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -494,7 +505,7 @@
reg = <0 0xe6540000 0 0x40>;
interrupts = <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7790_CLK_I2C3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -508,7 +519,7 @@
clocks = <&mstp3_clks R8A7790_CLK_IIC0>;
dmas = <&dmac0 0x61>, <&dmac0 0x62>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -521,7 +532,7 @@
clocks = <&mstp3_clks R8A7790_CLK_IIC1>;
dmas = <&dmac0 0x65>, <&dmac0 0x66>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -534,7 +545,7 @@
clocks = <&mstp3_clks R8A7790_CLK_IIC2>;
dmas = <&dmac0 0x69>, <&dmac0 0x6a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -547,7 +558,7 @@
clocks = <&mstp9_clks R8A7790_CLK_IICDVFS>;
dmas = <&dmac0 0x77>, <&dmac0 0x78>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -558,7 +569,7 @@
clocks = <&mstp3_clks R8A7790_CLK_MMCIF0>;
dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
reg-io-width = <4>;
status = "disabled";
max-frequency = <97500000>;
@@ -571,7 +582,7 @@
clocks = <&mstp3_clks R8A7790_CLK_MMCIF1>;
dmas = <&dmac0 0xe1>, <&dmac0 0xe2>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
reg-io-width = <4>;
status = "disabled";
max-frequency = <97500000>;
@@ -590,7 +601,7 @@
dmas = <&dmac1 0xcd>, <&dmac1 0xce>;
dma-names = "tx", "rx";
max-frequency = <195000000>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -602,7 +613,7 @@
dmas = <&dmac1 0xc9>, <&dmac1 0xca>;
dma-names = "tx", "rx";
max-frequency = <195000000>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -614,7 +625,7 @@
dmas = <&dmac1 0xc1>, <&dmac1 0xc2>;
dma-names = "tx", "rx";
max-frequency = <97500000>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -626,7 +637,7 @@
dmas = <&dmac1 0xd3>, <&dmac1 0xd4>;
dma-names = "tx", "rx";
max-frequency = <97500000>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -639,7 +650,7 @@
clock-names = "fck";
dmas = <&dmac0 0x21>, <&dmac0 0x22>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -652,7 +663,7 @@
clock-names = "fck";
dmas = <&dmac0 0x25>, <&dmac0 0x26>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -665,7 +676,7 @@
clock-names = "fck";
dmas = <&dmac0 0x27>, <&dmac0 0x28>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -678,7 +689,7 @@
clock-names = "fck";
dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -691,7 +702,7 @@
clock-names = "fck";
dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -704,7 +715,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -718,7 +729,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -732,7 +743,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -746,7 +757,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -760,7 +771,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -774,7 +785,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -783,7 +794,7 @@
reg = <0 0xee700000 0 0x400>;
interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_ETHER>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
phy-mode = "rmii";
#address-cells = <1>;
#size-cells = <0>;
@@ -796,7 +807,7 @@
reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>;
interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_ETHERAVB>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -807,7 +818,7 @@
reg = <0 0xee300000 0 0x2000>;
interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_SATA0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -816,7 +827,7 @@
reg = <0 0xee500000 0 0x2000>;
interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_SATA1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -828,7 +839,7 @@
dmas = <&usb_dmac0 0>, <&usb_dmac0 1>,
<&usb_dmac1 0>, <&usb_dmac1 1>;
dma-names = "ch0", "ch1", "ch2", "ch3";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,buswait = <4>;
phys = <&usb0 1>;
phy-names = "usb";
@@ -842,7 +853,7 @@
#size-cells = <0>;
clocks = <&mstp7_clks R8A7790_CLK_HSUSB>;
clock-names = "usbhs";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
usb0: usb-channel@0 {
@@ -860,7 +871,7 @@
reg = <0 0xe6ef0000 0 0x1000>;
interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_VIN0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -869,7 +880,7 @@
reg = <0 0xe6ef1000 0 0x1000>;
interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_VIN1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -878,7 +889,7 @@
reg = <0 0xe6ef2000 0 0x1000>;
interrupts = <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_VIN2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -887,7 +898,7 @@
reg = <0 0xe6ef3000 0 0x1000>;
interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7790_CLK_VIN3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -896,7 +907,7 @@
reg = <0 0xfe920000 0 0x8000>;
interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7790_CLK_VSP1_R>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,has-sru;
renesas,#rpf = <5>;
@@ -909,7 +920,7 @@
reg = <0 0xfe928000 0 0x8000>;
interrupts = <GIC_SPI 267 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7790_CLK_VSP1_S>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,has-lut;
renesas,has-sru;
@@ -923,7 +934,7 @@
reg = <0 0xfe930000 0 0x8000>;
interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7790_CLK_VSP1_DU0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,has-lif;
renesas,has-lut;
@@ -937,7 +948,7 @@
reg = <0 0xfe938000 0 0x8000>;
interrupts = <GIC_SPI 247 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7790_CLK_VSP1_DU1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
renesas,has-lif;
renesas,has-lut;
@@ -992,7 +1003,7 @@
clocks = <&mstp9_clks R8A7790_CLK_RCAN0>,
<&cpg_clocks R8A7790_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1003,7 +1014,7 @@
clocks = <&mstp9_clks R8A7790_CLK_RCAN1>,
<&cpg_clocks R8A7790_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1012,7 +1023,7 @@
reg = <0 0xfe980000 0 0x10300>;
interrupts = <GIC_SPI 272 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7790_CLK_JPU>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
};
clocks {
@@ -1447,6 +1458,12 @@
};
};
+ sysc: system-controller@e6180000 {
+ compatible = "renesas,r8a7790-sysc";
+ reg = <0 0xe6180000 0 0x0200>;
+ #power-domain-cells = <1>;
+ };
+
qspi: spi@e6b10000 {
compatible = "renesas,qspi-r8a7790", "renesas,qspi";
reg = <0 0xe6b10000 0 0x2c>;
@@ -1454,7 +1471,7 @@
clocks = <&mstp9_clks R8A7790_CLK_QSPI_MOD>;
dmas = <&dmac0 0x17>, <&dmac0 0x18>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
num-cs = <1>;
#address-cells = <1>;
#size-cells = <0>;
@@ -1468,7 +1485,7 @@
clocks = <&mstp0_clks R8A7790_CLK_MSIOF0>;
dmas = <&dmac0 0x51>, <&dmac0 0x52>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1481,7 +1498,7 @@
clocks = <&mstp2_clks R8A7790_CLK_MSIOF1>;
dmas = <&dmac0 0x55>, <&dmac0 0x56>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1494,7 +1511,7 @@
clocks = <&mstp2_clks R8A7790_CLK_MSIOF2>;
dmas = <&dmac0 0x41>, <&dmac0 0x42>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1507,7 +1524,7 @@
clocks = <&mstp2_clks R8A7790_CLK_MSIOF3>;
dmas = <&dmac0 0x45>, <&dmac0 0x46>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1518,7 +1535,7 @@
reg = <0 0xee000000 0 0xc00>;
interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7790_CLK_SSUSB>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
phys = <&usb2 1>;
phy-names = "usb";
status = "disabled";
@@ -1531,7 +1548,7 @@
<0 0xee080000 0 0x1100>;
interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
bus-range = <0 0>;
@@ -1566,7 +1583,7 @@
<0 0xee0a0000 0 0x1100>;
interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
bus-range = <1 1>;
@@ -1584,7 +1601,7 @@
compatible = "renesas,pci-r8a7790", "renesas,pci-rcar-gen2";
device_type = "pci";
clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
reg = <0 0xee0d0000 0 0xc00>,
<0 0xee0c0000 0 0x1100>;
interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
@@ -1637,7 +1654,7 @@
interrupt-map = <0 0 0 0 &gic GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7790_CLK_PCIEC>, <&pcie_bus_clk>;
clock-names = "pcie", "pcie_bus";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1680,7 +1697,7 @@
"mix.0", "mix.1",
"dvc.0", "dvc.1",
"clk_a", "clk_b", "clk_c", "clk_i";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
status = "disabled";
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 565c270e549d..db67e342c585 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -13,6 +13,7 @@
#include <dt-bindings/clock/r8a7791-clock.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/power/r8a7791-sysc.h>
/ {
compatible = "renesas,r8a7791";
@@ -51,6 +52,7 @@
voltage-tolerance = <1>; /* 1% */
clocks = <&cpg_clocks R8A7791_CLK_Z>;
clock-latency = <300000>; /* 300 us */
+ power-domains = <&sysc R8A7791_PD_CA15_CPU0>;
next-level-cache = <&L2_CA15>;
/* kHz - uV - OPPs unknown yet */
@@ -67,6 +69,7 @@
compatible = "arm,cortex-a15";
reg = <1>;
clock-frequency = <1500000000>;
+ power-domains = <&sysc R8A7791_PD_CA15_CPU1>;
next-level-cache = <&L2_CA15>;
};
};
@@ -92,6 +95,7 @@
L2_CA15: cache-controller@0 {
compatible = "cache";
+ power-domains = <&sysc R8A7791_PD_CA15_SCU>;
cache-unified;
cache-level = <2>;
};
@@ -118,7 +122,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio1: gpio@e6051000 {
@@ -131,7 +135,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio2: gpio@e6052000 {
@@ -144,7 +148,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio3: gpio@e6053000 {
@@ -157,7 +161,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio4: gpio@e6054000 {
@@ -170,7 +174,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio5: gpio@e6055000 {
@@ -183,7 +187,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio6: gpio@e6055400 {
@@ -196,7 +200,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO6>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
gpio7: gpio@e6055800 {
@@ -209,7 +213,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7791_CLK_GPIO7>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
thermal: thermal@e61f0000 {
@@ -219,7 +223,7 @@
reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp5_clks R8A7791_CLK_THERMAL>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#thermal-sensor-cells = <0>;
};
@@ -238,7 +242,7 @@
<GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7791_CLK_CMT0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
renesas,channels-mask = <0x60>;
@@ -258,7 +262,7 @@
<GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7791_CLK_CMT1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
renesas,channels-mask = <0xff>;
@@ -281,7 +285,7 @@
<GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp4_clks R8A7791_CLK_IRQC>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
dmac0: dma-controller@e6700000 {
@@ -310,7 +314,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7791_CLK_SYS_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -341,7 +345,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7791_CLK_SYS_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -370,7 +374,7 @@
"ch12";
clocks = <&mstp5_clks R8A7791_CLK_AUDIO_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <13>;
};
@@ -399,7 +403,7 @@
"ch12";
clocks = <&mstp5_clks R8A7791_CLK_AUDIO_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <13>;
};
@@ -411,7 +415,7 @@
GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "ch0", "ch1";
clocks = <&mstp3_clks R8A7791_CLK_USBDMAC0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <2>;
};
@@ -423,7 +427,7 @@
GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "ch0", "ch1";
clocks = <&mstp3_clks R8A7791_CLK_USBDMAC1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <2>;
};
@@ -436,7 +440,7 @@
reg = <0 0xe6508000 0 0x40>;
interrupts = <GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7791_CLK_I2C0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -448,7 +452,7 @@
reg = <0 0xe6518000 0 0x40>;
interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7791_CLK_I2C1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -460,7 +464,7 @@
reg = <0 0xe6530000 0 0x40>;
interrupts = <GIC_SPI 286 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7791_CLK_I2C2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -472,7 +476,7 @@
reg = <0 0xe6540000 0 0x40>;
interrupts = <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7791_CLK_I2C3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -484,7 +488,7 @@
reg = <0 0xe6520000 0 0x40>;
interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7791_CLK_I2C4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -497,7 +501,7 @@
reg = <0 0xe6528000 0 0x40>;
interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7791_CLK_I2C5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -512,7 +516,7 @@
clocks = <&mstp9_clks R8A7791_CLK_IICDVFS>;
dmas = <&dmac0 0x77>, <&dmac0 0x78>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -525,7 +529,7 @@
clocks = <&mstp3_clks R8A7791_CLK_IIC0>;
dmas = <&dmac0 0x61>, <&dmac0 0x62>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -538,7 +542,7 @@
clocks = <&mstp3_clks R8A7791_CLK_IIC1>;
dmas = <&dmac0 0x65>, <&dmac0 0x66>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -554,7 +558,7 @@
clocks = <&mstp3_clks R8A7791_CLK_MMCIF0>;
dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
reg-io-width = <4>;
status = "disabled";
max-frequency = <97500000>;
@@ -567,7 +571,7 @@
clocks = <&mstp3_clks R8A7791_CLK_SDHI0>;
dmas = <&dmac1 0xcd>, <&dmac1 0xce>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -578,7 +582,7 @@
clocks = <&mstp3_clks R8A7791_CLK_SDHI1>;
dmas = <&dmac1 0xc1>, <&dmac1 0xc2>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -589,7 +593,7 @@
clocks = <&mstp3_clks R8A7791_CLK_SDHI2>;
dmas = <&dmac1 0xd3>, <&dmac1 0xd4>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -602,7 +606,7 @@
clock-names = "fck";
dmas = <&dmac0 0x21>, <&dmac0 0x22>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -615,7 +619,7 @@
clock-names = "fck";
dmas = <&dmac0 0x25>, <&dmac0 0x26>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -628,7 +632,7 @@
clock-names = "fck";
dmas = <&dmac0 0x27>, <&dmac0 0x28>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -641,7 +645,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -654,7 +658,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -667,7 +671,7 @@
clock-names = "fck";
dmas = <&dmac0 0x23>, <&dmac0 0x24>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -680,7 +684,7 @@
clock-names = "fck";
dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -693,7 +697,7 @@
clock-names = "fck";
dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -706,7 +710,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -720,7 +724,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -734,7 +738,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -748,7 +752,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -762,7 +766,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -776,7 +780,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -790,7 +794,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -804,7 +808,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -818,7 +822,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -832,7 +836,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -841,7 +845,7 @@
reg = <0 0xee700000 0 0x400>;
interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_ETHER>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
phy-mode = "rmii";
#address-cells = <1>;
#size-cells = <0>;
@@ -854,7 +858,7 @@
reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>;
interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_ETHERAVB>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -865,7 +869,7 @@
reg = <0 0xee300000 0 0x2000>;
interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_SATA0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -874,7 +878,7 @@
reg = <0 0xee500000 0 0x2000>;
interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_SATA1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -886,7 +890,7 @@
dmas = <&usb_dmac0 0>, <&usb_dmac0 1>,
<&usb_dmac1 0>, <&usb_dmac1 1>;
dma-names = "ch0", "ch1", "ch2", "ch3";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
renesas,buswait = <4>;
phys = <&usb0 1>;
phy-names = "usb";
@@ -900,7 +904,7 @@
#size-cells = <0>;
clocks = <&mstp7_clks R8A7791_CLK_HSUSB>;
clock-names = "usbhs";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
usb0: usb-channel@0 {
@@ -918,7 +922,7 @@
reg = <0 0xe6ef0000 0 0x1000>;
interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_VIN0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -927,7 +931,7 @@
reg = <0 0xe6ef1000 0 0x1000>;
interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_VIN1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -936,7 +940,7 @@
reg = <0 0xe6ef2000 0 0x1000>;
interrupts = <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7791_CLK_VIN2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -945,7 +949,7 @@
reg = <0 0xfe928000 0 0x8000>;
interrupts = <GIC_SPI 267 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7791_CLK_VSP1_S>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
renesas,has-lut;
renesas,has-sru;
@@ -959,7 +963,7 @@
reg = <0 0xfe930000 0 0x8000>;
interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7791_CLK_VSP1_DU0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
renesas,has-lif;
renesas,has-lut;
@@ -973,7 +977,7 @@
reg = <0 0xfe938000 0 0x8000>;
interrupts = <GIC_SPI 247 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7791_CLK_VSP1_DU1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
renesas,has-lif;
renesas,has-lut;
@@ -1019,7 +1023,7 @@
clocks = <&mstp9_clks R8A7791_CLK_RCAN0>,
<&cpg_clocks R8A7791_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1030,7 +1034,7 @@
clocks = <&mstp9_clks R8A7791_CLK_RCAN1>,
<&cpg_clocks R8A7791_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1039,7 +1043,7 @@
reg = <0 0xfe980000 0 0x10300>;
interrupts = <GIC_SPI 272 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7791_CLK_JPU>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
};
clocks {
@@ -1463,6 +1467,12 @@
};
};
+ sysc: system-controller@e6180000 {
+ compatible = "renesas,r8a7791-sysc";
+ reg = <0 0xe6180000 0 0x0200>;
+ #power-domain-cells = <1>;
+ };
+
qspi: spi@e6b10000 {
compatible = "renesas,qspi-r8a7791", "renesas,qspi";
reg = <0 0xe6b10000 0 0x2c>;
@@ -1470,7 +1480,7 @@
clocks = <&mstp9_clks R8A7791_CLK_QSPI_MOD>;
dmas = <&dmac0 0x17>, <&dmac0 0x18>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
num-cs = <1>;
#address-cells = <1>;
#size-cells = <0>;
@@ -1484,7 +1494,7 @@
clocks = <&mstp0_clks R8A7791_CLK_MSIOF0>;
dmas = <&dmac0 0x51>, <&dmac0 0x52>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1497,7 +1507,7 @@
clocks = <&mstp2_clks R8A7791_CLK_MSIOF1>;
dmas = <&dmac0 0x55>, <&dmac0 0x56>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1510,7 +1520,7 @@
clocks = <&mstp2_clks R8A7791_CLK_MSIOF2>;
dmas = <&dmac0 0x41>, <&dmac0 0x42>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -1521,7 +1531,7 @@
reg = <0 0xee000000 0 0xc00>;
interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7791_CLK_SSUSB>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
phys = <&usb2 1>;
phy-names = "usb";
status = "disabled";
@@ -1534,7 +1544,7 @@
<0 0xee080000 0 0x1100>;
interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7791_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
bus-range = <0 0>;
@@ -1569,7 +1579,7 @@
<0 0xee0c0000 0 0x1100>;
interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7791_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
bus-range = <1 1>;
@@ -1619,7 +1629,7 @@
interrupt-map = <0 0 0 0 &gic GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7791_CLK_PCIEC>, <&pcie_bus_clk>;
clock-names = "pcie", "pcie_bus";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1722,7 +1732,7 @@
"mix.0", "mix.1",
"dvc.0", "dvc.1",
"clk_a", "clk_b", "clk_c", "clk_i";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
status = "disabled";
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index cf6dc2aeef20..1dd6d202cd4c 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -11,6 +11,7 @@
#include <dt-bindings/clock/r8a7793-clock.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/power/r8a7793-sysc.h>
/ {
compatible = "renesas,r8a7793";
@@ -43,6 +44,7 @@
voltage-tolerance = <1>; /* 1% */
clocks = <&cpg_clocks R8A7793_CLK_Z>;
clock-latency = <300000>; /* 300 us */
+ power-domains = <&sysc R8A7793_PD_CA15_CPU0>;
/* kHz - uV - OPPs unknown yet */
operating-points = <1500000 1000000>,
@@ -76,6 +78,7 @@
L2_CA15: cache-controller@0 {
compatible = "cache";
+ power-domains = <&sysc R8A7793_PD_CA15_SCU>;
cache-unified;
cache-level = <2>;
};
@@ -102,7 +105,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio1: gpio@e6051000 {
@@ -115,7 +118,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio2: gpio@e6052000 {
@@ -128,7 +131,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio3: gpio@e6053000 {
@@ -141,7 +144,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio4: gpio@e6054000 {
@@ -154,7 +157,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio5: gpio@e6055000 {
@@ -167,7 +170,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio6: gpio@e6055400 {
@@ -180,7 +183,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO6>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
gpio7: gpio@e6055800 {
@@ -193,7 +196,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7793_CLK_GPIO7>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
thermal: thermal@e61f0000 {
@@ -203,7 +206,7 @@
reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp5_clks R8A7793_CLK_THERMAL>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
#thermal-sensor-cells = <0>;
};
@@ -222,7 +225,7 @@
<GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7793_CLK_CMT0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
renesas,channels-mask = <0x60>;
@@ -242,7 +245,7 @@
<GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7793_CLK_CMT1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
renesas,channels-mask = <0xff>;
@@ -265,7 +268,7 @@
<GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp4_clks R8A7793_CLK_IRQC>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
};
dmac0: dma-controller@e6700000 {
@@ -294,7 +297,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7793_CLK_SYS_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -325,7 +328,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7793_CLK_SYS_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -354,7 +357,7 @@
"ch12";
clocks = <&mstp5_clks R8A7793_CLK_AUDIO_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <13>;
};
@@ -383,7 +386,7 @@
"ch12";
clocks = <&mstp5_clks R8A7793_CLK_AUDIO_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <13>;
};
@@ -396,7 +399,7 @@
reg = <0 0xe6508000 0 0x40>;
interrupts = <GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7793_CLK_I2C0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -408,7 +411,7 @@
reg = <0 0xe6518000 0 0x40>;
interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7793_CLK_I2C1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -420,7 +423,7 @@
reg = <0 0xe6530000 0 0x40>;
interrupts = <GIC_SPI 286 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7793_CLK_I2C2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -432,7 +435,7 @@
reg = <0 0xe6540000 0 0x40>;
interrupts = <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7793_CLK_I2C3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -444,7 +447,7 @@
reg = <0 0xe6520000 0 0x40>;
interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7793_CLK_I2C4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -457,7 +460,7 @@
reg = <0 0xe6528000 0 0x40>;
interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7793_CLK_I2C5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -472,7 +475,7 @@
clocks = <&mstp9_clks R8A7793_CLK_IICDVFS>;
dmas = <&dmac0 0x77>, <&dmac0 0x78>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -485,7 +488,7 @@
clocks = <&mstp3_clks R8A7793_CLK_IIC0>;
dmas = <&dmac0 0x61>, <&dmac0 0x62>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -498,7 +501,7 @@
clocks = <&mstp3_clks R8A7793_CLK_IIC1>;
dmas = <&dmac0 0x65>, <&dmac0 0x66>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -514,7 +517,7 @@
clocks = <&mstp3_clks R8A7793_CLK_SDHI0>;
dmas = <&dmac0 0xcd>, <&dmac0 0xce>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -525,7 +528,7 @@
clocks = <&mstp3_clks R8A7793_CLK_SDHI1>;
dmas = <&dmac0 0xc1>, <&dmac0 0xc2>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -536,7 +539,7 @@
clocks = <&mstp3_clks R8A7793_CLK_SDHI2>;
dmas = <&dmac0 0xd3>, <&dmac0 0xd4>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -549,7 +552,7 @@
clock-names = "fck";
dmas = <&dmac0 0x21>, <&dmac0 0x22>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -562,7 +565,7 @@
clock-names = "fck";
dmas = <&dmac0 0x25>, <&dmac0 0x26>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -575,7 +578,7 @@
clock-names = "fck";
dmas = <&dmac0 0x27>, <&dmac0 0x28>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -588,7 +591,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -601,7 +604,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -614,7 +617,7 @@
clock-names = "fck";
dmas = <&dmac0 0x23>, <&dmac0 0x24>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -627,7 +630,7 @@
clock-names = "fck";
dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -640,7 +643,7 @@
clock-names = "fck";
dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -653,7 +656,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -667,7 +670,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -681,7 +684,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -695,7 +698,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -709,7 +712,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -723,7 +726,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -737,7 +740,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -751,7 +754,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -765,7 +768,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -779,7 +782,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -788,7 +791,7 @@
reg = <0 0xee700000 0 0x400>;
interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7793_CLK_ETHER>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
phy-mode = "rmii";
#address-cells = <1>;
#size-cells = <0>;
@@ -802,7 +805,7 @@
clocks = <&mstp9_clks R8A7793_CLK_QSPI_MOD>;
dmas = <&dmac0 0x17>, <&dmac0 0x18>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
num-cs = <1>;
#address-cells = <1>;
#size-cells = <0>;
@@ -846,7 +849,7 @@
clocks = <&mstp9_clks R8A7793_CLK_RCAN0>,
<&cpg_clocks R8A7793_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -857,7 +860,7 @@
clocks = <&mstp9_clks R8A7793_CLK_RCAN1>,
<&cpg_clocks R8A7793_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1221,6 +1224,12 @@
};
};
+ sysc: system-controller@e6180000 {
+ compatible = "renesas,r8a7793-sysc";
+ reg = <0 0xe6180000 0 0x0200>;
+ #power-domain-cells = <1>;
+ };
+
ipmmu_sy0: mmu@e6280000 {
compatible = "renesas,ipmmu-r8a7793", "renesas,ipmmu-vmsa";
reg = <0 0xe6280000 0 0x1000>;
@@ -1316,7 +1325,7 @@
"src.4", "src.3", "src.2", "src.1", "src.0",
"dvc.0", "dvc.1",
"clk_a", "clk_b", "clk_c", "clk_i";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
status = "disabled";
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index e45b23f31149..f334a3a715f2 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -12,6 +12,7 @@
#include <dt-bindings/clock/r8a7794-clock.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/power/r8a7794-sysc.h>
/ {
compatible = "renesas,r8a7794";
@@ -42,6 +43,7 @@
compatible = "arm,cortex-a7";
reg = <0>;
clock-frequency = <1000000000>;
+ power-domains = <&sysc R8A7794_PD_CA7_CPU0>;
next-level-cache = <&L2_CA7>;
};
@@ -50,12 +52,14 @@
compatible = "arm,cortex-a7";
reg = <1>;
clock-frequency = <1000000000>;
+ power-domains = <&sysc R8A7794_PD_CA7_CPU1>;
next-level-cache = <&L2_CA7>;
};
};
L2_CA7: cache-controller@1 {
compatible = "cache";
+ power-domains = <&sysc R8A7794_PD_CA7_SCU>;
cache-unified;
cache-level = <2>;
};
@@ -82,7 +86,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
gpio1: gpio@e6051000 {
@@ -95,7 +99,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
gpio2: gpio@e6052000 {
@@ -108,7 +112,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
gpio3: gpio@e6053000 {
@@ -121,7 +125,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
gpio4: gpio@e6054000 {
@@ -134,7 +138,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
gpio5: gpio@e6055000 {
@@ -147,7 +151,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
gpio6: gpio@e6055400 {
@@ -160,7 +164,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&mstp9_clks R8A7794_CLK_GPIO6>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
cmt0: timer@ffca0000 {
@@ -170,7 +174,7 @@
<GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp1_clks R8A7794_CLK_CMT0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
renesas,channels-mask = <0x60>;
@@ -190,7 +194,7 @@
<GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7794_CLK_CMT1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
renesas,channels-mask = <0xff>;
@@ -221,7 +225,7 @@
<GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp4_clks R8A7794_CLK_IRQC>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
};
pfc: pin-controller@e6060000 {
@@ -255,7 +259,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7794_CLK_SYS_DMAC0>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -286,7 +290,7 @@
"ch12", "ch13", "ch14";
clocks = <&mstp2_clks R8A7794_CLK_SYS_DMAC1>;
clock-names = "fck";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <15>;
};
@@ -300,7 +304,7 @@
clock-names = "fck";
dmas = <&dmac0 0x21>, <&dmac0 0x22>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -313,7 +317,7 @@
clock-names = "fck";
dmas = <&dmac0 0x25>, <&dmac0 0x26>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -326,7 +330,7 @@
clock-names = "fck";
dmas = <&dmac0 0x27>, <&dmac0 0x28>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -339,7 +343,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -352,7 +356,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -365,7 +369,7 @@
clock-names = "fck";
dmas = <&dmac0 0x23>, <&dmac0 0x24>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -378,7 +382,7 @@
clock-names = "fck";
dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -391,7 +395,7 @@
clock-names = "fck";
dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -404,7 +408,7 @@
clock-names = "fck";
dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -418,7 +422,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -432,7 +436,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -446,7 +450,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -460,7 +464,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -474,7 +478,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -488,7 +492,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -502,7 +506,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -516,7 +520,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -530,7 +534,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -539,7 +543,7 @@
reg = <0 0xee700000 0 0x400>;
interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7794_CLK_ETHER>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
phy-mode = "rmii";
#address-cells = <1>;
#size-cells = <0>;
@@ -552,7 +556,7 @@
reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>;
interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7794_CLK_ETHERAVB>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -564,7 +568,7 @@
reg = <0 0xe6508000 0 0x40>;
interrupts = <GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7794_CLK_I2C0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
i2c-scl-internal-delay-ns = <6>;
@@ -576,7 +580,7 @@
reg = <0 0xe6518000 0 0x40>;
interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7794_CLK_I2C1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
i2c-scl-internal-delay-ns = <6>;
@@ -588,7 +592,7 @@
reg = <0 0xe6530000 0 0x40>;
interrupts = <GIC_SPI 286 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7794_CLK_I2C2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
i2c-scl-internal-delay-ns = <6>;
@@ -600,7 +604,7 @@
reg = <0 0xe6540000 0 0x40>;
interrupts = <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7794_CLK_I2C3>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
i2c-scl-internal-delay-ns = <6>;
@@ -612,7 +616,7 @@
reg = <0 0xe6520000 0 0x40>;
interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7794_CLK_I2C4>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
i2c-scl-internal-delay-ns = <6>;
@@ -624,7 +628,7 @@
reg = <0 0xe6528000 0 0x40>;
interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp9_clks R8A7794_CLK_I2C5>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
i2c-scl-internal-delay-ns = <6>;
@@ -638,7 +642,7 @@
clocks = <&mstp3_clks R8A7794_CLK_IIC0>;
dmas = <&dmac0 0x61>, <&dmac0 0x62>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -651,7 +655,7 @@
clocks = <&mstp3_clks R8A7794_CLK_IIC1>;
dmas = <&dmac0 0x65>, <&dmac0 0x66>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -664,7 +668,7 @@
clocks = <&mstp3_clks R8A7794_CLK_MMCIF0>;
dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
reg-io-width = <4>;
status = "disabled";
};
@@ -674,7 +678,7 @@
reg = <0 0xee100000 0 0x200>;
interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7794_CLK_SDHI0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -683,7 +687,7 @@
reg = <0 0xee140000 0 0x100>;
interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7794_CLK_SDHI1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -692,7 +696,7 @@
reg = <0 0xee160000 0 0x100>;
interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp3_clks R8A7794_CLK_SDHI2>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -703,7 +707,7 @@
clocks = <&mstp9_clks R8A7794_CLK_QSPI_MOD>;
dmas = <&dmac0 0x17>, <&dmac0 0x18>;
dma-names = "tx", "rx";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
num-cs = <1>;
#address-cells = <1>;
#size-cells = <0>;
@@ -715,7 +719,7 @@
reg = <0 0xe6ef0000 0 0x1000>;
interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7794_CLK_VIN0>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -724,7 +728,7 @@
reg = <0 0xe6ef1000 0 0x1000>;
interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp8_clks R8A7794_CLK_VIN1>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -735,7 +739,7 @@
<0 0xee080000 0 0x1100>;
interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7794_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
bus-range = <0 0>;
@@ -770,7 +774,7 @@
<0 0xee0c0000 0 0x1100>;
interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7794_CLK_EHCI>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
bus-range = <1 1>;
@@ -803,7 +807,7 @@
reg = <0 0xe6590000 0 0x100>;
interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp7_clks R8A7794_CLK_HSUSB>;
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
renesas,buswait = <4>;
phys = <&usb0 1>;
phy-names = "usb";
@@ -817,7 +821,7 @@
#size-cells = <0>;
clocks = <&mstp7_clks R8A7794_CLK_HSUSB>;
clock-names = "usbhs";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
usb0: usb-channel@0 {
@@ -865,7 +869,7 @@
clocks = <&mstp9_clks R8A7794_CLK_RCAN0>,
<&cpg_clocks R8A7794_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -876,7 +880,7 @@
clocks = <&mstp9_clks R8A7794_CLK_RCAN1>,
<&cpg_clocks R8A7794_CLK_RCAN>, <&can_clk>;
clock-names = "clkp1", "clkp2", "can_clk";
- power-domains = <&cpg_clocks>;
+ power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1213,6 +1217,12 @@
};
};
+ sysc: system-controller@e6180000 {
+ compatible = "renesas,r8a7794-sysc";
+ reg = <0 0xe6180000 0 0x0200>;
+ #power-domain-cells = <1>;
+ };
+
ipmmu_sy0: mmu@e6280000 {
compatible = "renesas,ipmmu-r8a7794", "renesas,ipmmu-vmsa";
reg = <0 0xe6280000 0 0x1000>;
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
index a3601e4c0a2e..b844473601d2 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
@@ -136,6 +136,7 @@
&gmac1 {
status = "okay";
phy-mode = "rgmii";
+ phy-handle = <&phy1>;
snps,reset-gpio = <&porta 0 GPIO_ACTIVE_LOW>;
snps,reset-active-low;
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index ad8ba10764a3..d294e82447a2 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -24,18 +24,21 @@
compatible = "shared-dma-pool";
reg = <0x40000000 0x01000000>;
no-map;
+ status = "disabled";
};
gp1_reserved: rproc@41000000 {
compatible = "shared-dma-pool";
reg = <0x41000000 0x01000000>;
no-map;
+ status = "disabled";
};
audio_reserved: rproc@42000000 {
compatible = "shared-dma-pool";
reg = <0x42000000 0x01000000>;
no-map;
+ status = "disabled";
};
dmu_reserved: rproc@43000000 {
diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
index 68b479b8772c..73c133f5e79c 100644
--- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
@@ -176,8 +176,6 @@
};
&reg_dc1sw {
- regulator-min-microvolt = <3000000>;
- regulator-max-microvolt = <3000000>;
regulator-name = "vcc-lcd";
};
diff --git a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
index 360adfb1e9ca..d6ad6196a768 100644
--- a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
@@ -135,8 +135,6 @@
&reg_dc1sw {
regulator-name = "vcc-lcd-usb2";
- regulator-min-microvolt = <3000000>;
- regulator-max-microvolt = <3000000>;
};
&reg_dc5ldo {
diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
index a99f07ad6312..941f36263c8f 100644
--- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts
+++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
@@ -38,11 +38,17 @@
vddio-pex-ctl-supply = <&vdd_3v3_lp0>;
avdd-pll-erefe-supply = <&avdd_1v05_run>;
+ /* Mini PCIe */
pci@1,0 {
+ phys = <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-4}>;
+ phy-names = "pcie-0";
status = "okay";
};
+ /* Gigabit Ethernet */
pci@2,0 {
+ phys = <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-2}>;
+ phy-names = "pcie-0";
status = "okay";
};
};
@@ -1677,6 +1683,9 @@
sata@0,70020000 {
status = "okay";
+ phys = <&{/padctl@0,7009f000/pads/sata/lanes/sata-0}>;
+ phy-names = "sata-0";
+
hvdd-supply = <&vdd_3v3_lp0>;
vddio-supply = <&vdd_1v05_run>;
avdd-supply = <&vdd_1v05_run>;
@@ -1689,28 +1698,107 @@
status = "okay";
};
+ usb@0,70090000 {
+ phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-0}>, /* Micro A/B */
+ <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* Mini PCIe */
+ <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* USB3 */
+ <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>; /* USB3 */
+ phy-names = "usb2-0", "usb2-1", "usb2-2", "usb3-0";
+
+ avddio-pex-supply = <&vdd_1v05_run>;
+ dvddio-pex-supply = <&vdd_1v05_run>;
+ avdd-usb-supply = <&vdd_3v3_lp0>;
+ avdd-pll-utmip-supply = <&vddio_1v8>;
+ avdd-pll-erefe-supply = <&avdd_1v05_run>;
+ avdd-usb-ss-pll-supply = <&vdd_1v05_run>;
+ hvdd-usb-ss-supply = <&vdd_3v3_lp0>;
+ hvdd-usb-ss-pll-e-supply = <&vdd_3v3_lp0>;
+
+ status = "okay";
+ };
+
padctl@0,7009f000 {
- pinctrl-0 = <&padctl_default>;
- pinctrl-names = "default";
+ status = "okay";
- padctl_default: pinmux {
- usb3 {
- nvidia,lanes = "pcie-0", "pcie-1";
- nvidia,function = "usb3";
- nvidia,iddq = <0>;
+ pads {
+ usb2 {
+ status = "okay";
+
+ lanes {
+ usb2-0 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+
+ usb2-1 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+
+ usb2-2 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+ };
};
pcie {
- nvidia,lanes = "pcie-2", "pcie-3",
- "pcie-4";
- nvidia,function = "pcie";
- nvidia,iddq = <0>;
+ status = "okay";
+
+ lanes {
+ pcie-0 {
+ nvidia,function = "usb3-ss";
+ status = "okay";
+ };
+
+ pcie-2 {
+ nvidia,function = "pcie";
+ status = "okay";
+ };
+
+ pcie-4 {
+ nvidia,function = "pcie";
+ status = "okay";
+ };
+ };
};
sata {
- nvidia,lanes = "sata-0";
- nvidia,function = "sata";
- nvidia,iddq = <0>;
+ status = "okay";
+
+ lanes {
+ sata-0 {
+ nvidia,function = "sata";
+ status = "okay";
+ };
+ };
+ };
+ };
+
+ ports {
+ /* Micro A/B */
+ usb2-0 {
+ status = "okay";
+ mode = "otg";
+ };
+
+ /* Mini PCIe */
+ usb2-1 {
+ status = "okay";
+ mode = "host";
+ };
+
+ /* USB3 */
+ usb2-2 {
+ status = "okay";
+ mode = "host";
+
+ vbus-supply = <&vdd_usb3_vbus>;
+ };
+
+ usb3-0 {
+ nvidia,usb2-companion = <2>;
+ status = "okay";
};
};
};
diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi
index 5f1fc1410bd0..0710a600cc69 100644
--- a/arch/arm/boot/dts/tegra124-nyan.dtsi
+++ b/arch/arm/boot/dts/tegra124-nyan.dtsi
@@ -224,7 +224,7 @@
regulator-always-on;
};
- ldo0 {
+ avdd_1v05_run: ldo0 {
regulator-name = "+1.05V_RUN_AVDD";
regulator-min-microvolt = <1050000>;
regulator-max-microvolt = <1050000>;
@@ -368,6 +368,99 @@
status = "okay";
};
+ usb@0,70090000 {
+ phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-0}>, /* 1st USB A */
+ <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* Internal USB */
+ <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* 2nd USB A */
+ <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>, /* 1st USB A */
+ <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-1}>; /* 2nd USB A */
+ phy-names = "usb2-0", "usb2-1", "usb2-2", "usb3-0", "usb3-1";
+
+ avddio-pex-supply = <&vdd_1v05_run>;
+ dvddio-pex-supply = <&vdd_1v05_run>;
+ avdd-usb-supply = <&vdd_3v3_lp0>;
+ avdd-pll-utmip-supply = <&vddio_1v8>;
+ avdd-pll-erefe-supply = <&avdd_1v05_run>;
+ avdd-usb-ss-pll-supply = <&vdd_1v05_run>;
+ hvdd-usb-ss-supply = <&vdd_3v3_lp0>;
+ hvdd-usb-ss-pll-e-supply = <&vdd_3v3_lp0>;
+
+ status = "okay";
+ };
+
+ padctl@0,7009f000 {
+ status = "okay";
+
+ pads {
+ usb2 {
+ status = "okay";
+
+ lanes {
+ usb2-0 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+
+ usb2-1 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+
+ usb2-2 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+ };
+ };
+
+ pcie {
+ status = "okay";
+
+ lanes {
+ pcie-0 {
+ nvidia,function = "usb3-ss";
+ status = "okay";
+ };
+
+ pcie-1 {
+ nvidia,function = "usb3-ss";
+ status = "okay";
+ };
+ };
+ };
+ };
+
+ ports {
+ usb2-0 {
+ vbus-supply = <&vdd_usb1_vbus>;
+ status = "okay";
+ mode = "otg";
+ };
+
+ usb2-1 {
+ vbus-supply = <&vdd_run_cam>;
+ status = "okay";
+ mode = "host";
+ };
+
+ usb2-2 {
+ vbus-supply = <&vdd_usb3_vbus>;
+ status = "okay";
+ mode = "host";
+ };
+
+ usb3-0 {
+ nvidia,usb2-companion = <0>;
+ status = "okay";
+ };
+
+ usb3-1 {
+ nvidia,usb2-companion = <1>;
+ status = "okay";
+ };
+ };
+ };
+
sdhci0_pwrseq: sdhci0_pwrseq {
compatible = "mmc-pwrseq-simple";
@@ -414,33 +507,6 @@
};
};
- usb@0,7d000000 { /* Rear external USB port. */
- status = "okay";
- };
-
- usb-phy@0,7d000000 {
- status = "okay";
- vbus-supply = <&vdd_usb1_vbus>;
- };
-
- usb@0,7d004000 { /* Internal webcam. */
- status = "okay";
- };
-
- usb-phy@0,7d004000 {
- status = "okay";
- vbus-supply = <&vdd_run_cam>;
- };
-
- usb@0,7d008000 { /* Left external USB port. */
- status = "okay";
- };
-
- usb-phy@0,7d008000 {
- status = "okay";
- vbus-supply = <&vdd_usb3_vbus>;
- };
-
backlight: backlight {
compatible = "pwm-backlight";
diff --git a/arch/arm/boot/dts/tegra124-venice2.dts b/arch/arm/boot/dts/tegra124-venice2.dts
index 0318258dde3e..973446d07182 100644
--- a/arch/arm/boot/dts/tegra124-venice2.dts
+++ b/arch/arm/boot/dts/tegra124-venice2.dts
@@ -757,7 +757,7 @@
regulator-always-on;
};
- ldo0 {
+ avdd_1v05_run: ldo0 {
regulator-name = "+1.05V_RUN_AVDD";
regulator-min-microvolt = <1050000>;
regulator-max-microvolt = <1050000>;
@@ -899,6 +899,105 @@
status = "okay";
};
+ usb@0,70090000 {
+ phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-0}>, /* 1st USB A */
+ <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* Internal USB */
+ <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* 2nd USB A */
+ <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>, /* 1st USB A */
+ <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-1}>; /* 2nd USB A */
+ phy-names = "usb2-0", "usb2-1", "usb2-2", "usb3-0", "usb3-1";
+
+ avddio-pex-supply = <&vdd_1v05_run>;
+ dvddio-pex-supply = <&vdd_1v05_run>;
+ avdd-usb-supply = <&vdd_3v3_lp0>;
+ avdd-pll-utmip-supply = <&vddio_1v8>;
+ avdd-pll-erefe-supply = <&avdd_1v05_run>;
+ avdd-usb-ss-pll-supply = <&vdd_1v05_run>;
+ hvdd-usb-ss-supply = <&vdd_3v3_lp0>;
+ hvdd-usb-ss-pll-e-supply = <&vdd_3v3_lp0>;
+
+ status = "okay";
+ };
+
+ padctl@0,7009f000 {
+ pads {
+ usb2 {
+ status = "okay";
+
+ lanes {
+ usb2-0 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+
+ usb2-1 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+
+ usb2-2 {
+ nvidia,function = "xusb";
+ status = "okay";
+ };
+ };
+ };
+
+ pcie {
+ status = "okay";
+
+ lanes {
+ pcie-0 {
+ nvidia,function = "usb3-ss";
+ status = "okay";
+ };
+
+ pcie-1 {
+ nvidia,function = "usb3-ss";
+ status = "okay";
+ };
+
+ pcie-1 {
+ nvidia,function = "usb3-ss";
+ status = "okay";
+ };
+ };
+ };
+ };
+
+ ports {
+ usb2-0 {
+ status = "okay";
+ mode = "otg";
+
+ vbus-supply = <&vdd_usb1_vbus>;
+ };
+
+ usb2-1 {
+ status = "okay";
+ mode = "host";
+
+ vbus-supply = <&vdd_run_cam>;
+ };
+
+ usb2-2 {
+ status = "okay";
+ mode = "host";
+
+ vbus-supply = <&vdd_usb3_vbus>;
+ };
+
+ usb3-0 {
+ nvidia,usb2-companion = <0>;
+ status = "okay";
+ };
+
+ usb3-1 {
+ nvidia,usb2-companion = <2>;
+ status = "okay";
+ };
+ };
+ };
+
sdhci@0,700b0400 {
cd-gpios = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_HIGH>;
power-gpios = <&gpio TEGRA_GPIO(R, 0) GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi
index e4eac1f01e64..ea4811870de2 100644
--- a/arch/arm/boot/dts/tegra124.dtsi
+++ b/arch/arm/boot/dts/tegra124.dtsi
@@ -2,7 +2,6 @@
#include <dt-bindings/gpio/tegra-gpio.h>
#include <dt-bindings/memory/tegra124-mc.h>
#include <dt-bindings/pinctrl/pinctrl-tegra.h>
-#include <dt-bindings/pinctrl/pinctrl-tegra-xusb.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/reset/tegra124-car.h>
#include <dt-bindings/thermal/tegra124-soctherm.h>
@@ -51,9 +50,6 @@
reset-names = "pex", "afi", "pcie_x";
status = "disabled";
- phys = <&padctl TEGRA_XUSB_PADCTL_PCIE>;
- phy-names = "pcie";
-
pci@1,0 {
device_type = "pci";
assigned-addresses = <0x82000800 0 0x01000000 0 0x1000>;
@@ -622,8 +618,6 @@
<&tegra_car 123>,
<&tegra_car 129>;
reset-names = "sata", "sata-oob", "sata-cold";
- phys = <&padctl TEGRA_XUSB_PADCTL_SATA>;
- phy-names = "sata-phy";
status = "disabled";
};
@@ -642,13 +636,172 @@
status = "disabled";
};
+ usb@0,70090000 {
+ compatible = "nvidia,tegra124-xusb";
+ reg = <0x0 0x70090000 0x0 0x8000>,
+ <0x0 0x70098000 0x0 0x1000>,
+ <0x0 0x70099000 0x0 0x1000>;
+ reg-names = "hcd", "fpci", "ipfs";
+
+ interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+
+ clocks = <&tegra_car TEGRA124_CLK_XUSB_HOST>,
+ <&tegra_car TEGRA124_CLK_XUSB_HOST_SRC>,
+ <&tegra_car TEGRA124_CLK_XUSB_FALCON_SRC>,
+ <&tegra_car TEGRA124_CLK_XUSB_SS>,
+ <&tegra_car TEGRA124_CLK_XUSB_SS_DIV2>,
+ <&tegra_car TEGRA124_CLK_XUSB_SS_SRC>,
+ <&tegra_car TEGRA124_CLK_XUSB_HS_SRC>,
+ <&tegra_car TEGRA124_CLK_XUSB_FS_SRC>,
+ <&tegra_car TEGRA124_CLK_PLL_U_480M>,
+ <&tegra_car TEGRA124_CLK_CLK_M>,
+ <&tegra_car TEGRA124_CLK_PLL_E>;
+ clock-names = "xusb_host", "xusb_host_src",
+ "xusb_falcon_src", "xusb_ss",
+ "xusb_ss_div2", "xusb_ss_src",
+ "xusb_hs_src", "xusb_fs_src",
+ "pll_u_480m", "clk_m", "pll_e";
+ resets = <&tegra_car 89>, <&tegra_car 156>,
+ <&tegra_car 143>;
+ reset-names = "xusb_host", "xusb_ss", "xusb_src";
+
+ nvidia,xusb-padctl = <&padctl>;
+
+ status = "disabled";
+ };
+
padctl: padctl@0,7009f000 {
compatible = "nvidia,tegra124-xusb-padctl";
reg = <0x0 0x7009f000 0x0 0x1000>;
resets = <&tegra_car 142>;
reset-names = "padctl";
- #phy-cells = <1>;
+ pads {
+ usb2 {
+ status = "disabled";
+
+ lanes {
+ usb2-0 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb2-1 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb2-2 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+
+ ulpi {
+ status = "disabled";
+
+ lanes {
+ ulpi-0 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+
+ hsic {
+ status = "disabled";
+
+ lanes {
+ hsic-0 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ hsic-1 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+
+ pcie {
+ status = "disabled";
+
+ lanes {
+ pcie-0 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ pcie-1 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ pcie-2 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ pcie-3 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ pcie-4 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+
+ sata {
+ status = "disabled";
+
+ lanes {
+ sata-0 {
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+ };
+
+ ports {
+ usb2-0 {
+ status = "disabled";
+ };
+
+ usb2-1 {
+ status = "disabled";
+ };
+
+ usb2-2 {
+ status = "disabled";
+ };
+
+ ulpi-0 {
+ status = "disabled";
+ };
+
+ hsic-0 {
+ status = "disabled";
+ };
+
+ hsic-1 {
+ status = "disabled";
+ };
+
+ usb3-0 {
+ status = "disabled";
+ };
+
+ usb3-1 {
+ status = "disabled";
+ };
+ };
};
sdhci@0,700b0000 {
diff --git a/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi b/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
index 4d8b7f693535..a8a8e434fb27 100644
--- a/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
+++ b/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
@@ -50,6 +50,11 @@
clock-frequency = <16000000>;
};
+ panel: panel {
+ compatible = "edt,et057090dhu";
+ backlight = <&bl>;
+ };
+
reg_3v3: regulator-3v3 {
compatible = "regulator-fixed";
regulator-name = "3.3V";
@@ -83,6 +88,13 @@
status = "okay";
};
+&dcu0 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_dcu0_1>;
+ fsl,panel = <&panel>;
+ status = "okay";
+};
+
&dspi1 {
status = "okay";
@@ -134,6 +146,10 @@
vin-supply = <&reg_3v3>;
};
+&tcon0 {
+ status = "okay";
+};
+
&uart0 {
status = "okay";
};
diff --git a/arch/arm/boot/dts/vf-colibri.dtsi b/arch/arm/boot/dts/vf-colibri.dtsi
index 226a86ffd3c9..b7417094dc11 100644
--- a/arch/arm/boot/dts/vf-colibri.dtsi
+++ b/arch/arm/boot/dts/vf-colibri.dtsi
@@ -222,6 +222,39 @@
>;
};
+ pinctrl_dcu0_1: dcu0grp_1 {
+ fsl,pins = <
+ VF610_PAD_PTE0__DCU0_HSYNC 0x1902
+ VF610_PAD_PTE1__DCU0_VSYNC 0x1902
+ VF610_PAD_PTE2__DCU0_PCLK 0x1902
+ VF610_PAD_PTE4__DCU0_DE 0x1902
+ VF610_PAD_PTE5__DCU0_R0 0x1902
+ VF610_PAD_PTE6__DCU0_R1 0x1902
+ VF610_PAD_PTE7__DCU0_R2 0x1902
+ VF610_PAD_PTE8__DCU0_R3 0x1902
+ VF610_PAD_PTE9__DCU0_R4 0x1902
+ VF610_PAD_PTE10__DCU0_R5 0x1902
+ VF610_PAD_PTE11__DCU0_R6 0x1902
+ VF610_PAD_PTE12__DCU0_R7 0x1902
+ VF610_PAD_PTE13__DCU0_G0 0x1902
+ VF610_PAD_PTE14__DCU0_G1 0x1902
+ VF610_PAD_PTE15__DCU0_G2 0x1902
+ VF610_PAD_PTE16__DCU0_G3 0x1902
+ VF610_PAD_PTE17__DCU0_G4 0x1902
+ VF610_PAD_PTE18__DCU0_G5 0x1902
+ VF610_PAD_PTE19__DCU0_G6 0x1902
+ VF610_PAD_PTE20__DCU0_G7 0x1902
+ VF610_PAD_PTE21__DCU0_B0 0x1902
+ VF610_PAD_PTE22__DCU0_B1 0x1902
+ VF610_PAD_PTE23__DCU0_B2 0x1902
+ VF610_PAD_PTE24__DCU0_B3 0x1902
+ VF610_PAD_PTE25__DCU0_B4 0x1902
+ VF610_PAD_PTE26__DCU0_B5 0x1902
+ VF610_PAD_PTE27__DCU0_B6 0x1902
+ VF610_PAD_PTE28__DCU0_B7 0x1902
+ >;
+ };
+
pinctrl_dspi1: dspi1grp {
fsl,pins = <
VF610_PAD_PTD5__DSPI1_CS0 0x33e2
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 04ef54d45a91..2c13ec696ac5 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -311,6 +311,14 @@
<20000000>;
};
+ tcon0: timing-controller@4003d000 {
+ compatible = "fsl,vf610-tcon";
+ reg = <0x4003d000 0x1000>;
+ clocks = <&clks VF610_CLK_TCON0>;
+ clock-names = "ipg";
+ status = "disabled";
+ };
+
wdoga5: wdog@4003e000 {
compatible = "fsl,vf610-wdt", "fsl,imx21-wdt";
reg = <0x4003e000 0x1000>;
@@ -416,6 +424,17 @@
status = "disabled";
};
+ dcu0: dcu@40058000 {
+ compatible = "fsl,vf610-dcu";
+ reg = <0x40058000 0x1200>;
+ interrupts = <30 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clks VF610_CLK_DCU0>,
+ <&clks VF610_CLK_DCU0_DIV>;
+ clock-names = "dcu", "pix";
+ fsl,tcon = <&tcon0>;
+ status = "disabled";
+ };
+
i2c0: i2c@40066000 {
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 10f49ab5328e..47195e8690b4 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -82,6 +82,7 @@ CONFIG_TOUCHSCREEN_MMS114=y
CONFIG_INPUT_MISC=y
CONFIG_INPUT_MAX77693_HAPTIC=y
CONFIG_INPUT_MAX8997_HAPTIC=y
+CONFIG_KEYBOARD_SAMSUNG=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_SAMSUNG=y
CONFIG_SERIAL_SAMSUNG_CONSOLE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 8f857564657f..8a5fff1b7f6f 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -264,6 +264,7 @@ CONFIG_KEYBOARD_TEGRA=y
CONFIG_KEYBOARD_SPEAR=y
CONFIG_KEYBOARD_ST_KEYSCAN=y
CONFIG_KEYBOARD_CROS_EC=m
+CONFIG_KEYBOARD_SAMSUNG=m
CONFIG_MOUSE_PS2_ELANTECH=y
CONFIG_MOUSE_CYAPA=m
CONFIG_MOUSE_ELAN_I2C=y
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 0df6b1fc9655..96387d477e91 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -41,6 +41,8 @@
#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
+#define KVM_REQ_VCPU_EXIT 8
+
u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -226,6 +228,10 @@ static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+void kvm_arm_halt_guest(struct kvm *kvm);
+void kvm_arm_resume_guest(struct kvm *kvm);
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu);
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu);
int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);
diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h
index d8e90c8cb5fa..f3a7de71f515 100644
--- a/arch/arm/include/asm/kvm_mmio.h
+++ b/arch/arm/include/asm/kvm_mmio.h
@@ -28,6 +28,9 @@ struct kvm_decode {
bool sign_extend;
};
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
phys_addr_t fault_ipa);
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 19cfab526d13..20febb368844 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -29,7 +29,7 @@
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+ return (pmd_t *)get_zeroed_page(GFP_KERNEL);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index aeddd28b3595..92fd2c8a9af0 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#define pmd_large(pmd) (pmd_val(pmd) & 2)
#define pmd_bad(pmd) (pmd_val(pmd) & 2)
+#define pmd_present(pmd) (pmd_val(pmd))
#define copy_pmd(pmdpd,pmdps) \
do { \
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index fa70db7c714b..2a029bceaf2f 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -211,6 +211,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
: !!(pmd_val(pmd) & (val)))
#define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val)))
+#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID))
#define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF))
#define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL))
static inline pte_t pte_mkspecial(pte_t pte)
@@ -249,10 +250,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
-/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
static inline pmd_t pmd_mknotpresent(pmd_t pmd)
{
- return __pmd(0);
+ return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID);
}
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 348caabb7625..d62204060cbe 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
#define pmd_none(pmd) (!pmd_val(pmd))
-#define pmd_present(pmd) (pmd_val(pmd))
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 27563befa8a2..22bf1f64d99a 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -31,7 +31,7 @@ struct frame_tail {
*/
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
- struct perf_callchain_entry *entry)
+ struct perf_callchain_entry_ctx *entry)
{
struct frame_tail buftail;
unsigned long err;
@@ -59,7 +59,7 @@ user_backtrace(struct frame_tail __user *tail,
}
void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct frame_tail __user *tail;
@@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
tail = (struct frame_tail __user *)regs->ARM_fp - 1;
- while ((entry->nr < sysctl_perf_event_max_stack) &&
+ while ((entry->nr < entry->max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = user_backtrace(tail, entry);
}
@@ -89,13 +89,13 @@ static int
callchain_trace(struct stackframe *fr,
void *data)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, fr->pc);
return 0;
}
void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stackframe fr;
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ef9119f7462e..4d9375814b53 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
if (ret)
return ret;
- vfp_flush_hwstate(thread);
thread->vfpstate.hard = new_vfp;
+ vfp_flush_hwstate(thread);
return 0;
}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index df90bc59bfce..861521606c6d 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -486,7 +486,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
{
- trace_ipi_raise(target, ipi_types[ipinr]);
+ trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
__smp_cross_call(target, ipinr);
}
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 95a000515e43..02abfff68ee5 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -46,6 +46,13 @@ config KVM_ARM_HOST
---help---
Provides host support for ARM processors.
+config KVM_NEW_VGIC
+ bool "New VGIC implementation"
+ depends on KVM
+ default y
+ ---help---
+ uses the new VGIC implementation
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index eb1bf4309c13..a596b58f6d37 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -21,7 +21,18 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/
obj-y += kvm-arm.o init.o interrupts.o
obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
+
+ifeq ($(CONFIG_KVM_NEW_VGIC),y)
+obj-y += $(KVM)/arm/vgic/vgic.o
+obj-y += $(KVM)/arm/vgic/vgic-init.o
+obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
+obj-y += $(KVM)/arm/vgic/vgic-v2.o
+obj-y += $(KVM)/arm/vgic/vgic-mmio.o
+obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
+obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
+else
obj-y += $(KVM)/arm/vgic.o
obj-y += $(KVM)/arm/vgic-v2.o
obj-y += $(KVM)/arm/vgic-v2-emul.o
+endif
obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 237d5d82f0af..f1bde7c4e736 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -263,6 +263,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
kvm_timer_vcpu_terminate(vcpu);
kvm_vgic_vcpu_destroy(vcpu);
kvm_pmu_vcpu_destroy(vcpu);
+ kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
@@ -455,7 +456,7 @@ static void update_vttbr(struct kvm *kvm)
static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- int ret;
+ int ret = 0;
if (likely(vcpu->arch.has_run_once))
return 0;
@@ -478,9 +479,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
* interrupts from the virtual timer with a userspace gic.
*/
if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
- kvm_timer_enable(kvm);
+ ret = kvm_timer_enable(vcpu);
- return 0;
+ return ret;
}
bool kvm_arch_intc_initialized(struct kvm *kvm)
@@ -488,30 +489,37 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
return vgic_initialized(kvm);
}
-static void kvm_arm_halt_guest(struct kvm *kvm) __maybe_unused;
-static void kvm_arm_resume_guest(struct kvm *kvm) __maybe_unused;
-
-static void kvm_arm_halt_guest(struct kvm *kvm)
+void kvm_arm_halt_guest(struct kvm *kvm)
{
int i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
vcpu->arch.pause = true;
- force_vm_exit(cpu_all_mask);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_VCPU_EXIT);
+}
+
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pause = true;
+ kvm_vcpu_kick(vcpu);
}
-static void kvm_arm_resume_guest(struct kvm *kvm)
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu)
+{
+ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+
+ vcpu->arch.pause = false;
+ swake_up(wq);
+}
+
+void kvm_arm_resume_guest(struct kvm *kvm)
{
int i;
struct kvm_vcpu *vcpu;
- kvm_for_each_vcpu(i, vcpu, kvm) {
- struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
-
- vcpu->arch.pause = false;
- swake_up(wq);
- }
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_arm_resume_vcpu(vcpu);
}
static void vcpu_sleep(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 0f6600f05137..10f80a6c797a 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -23,7 +23,7 @@
#include "trace.h"
-static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data)
{
void *datap = NULL;
union {
@@ -55,7 +55,7 @@ static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
memcpy(buf, datap, len);
}
-static unsigned long mmio_read_buf(char *buf, unsigned int len)
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len)
{
unsigned long data = 0;
union {
@@ -66,7 +66,7 @@ static unsigned long mmio_read_buf(char *buf, unsigned int len)
switch (len) {
case 1:
- data = buf[0];
+ data = *(u8 *)buf;
break;
case 2:
memcpy(&tmp.hword, buf, len);
@@ -87,11 +87,10 @@ static unsigned long mmio_read_buf(char *buf, unsigned int len)
/**
* kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
+ * or in-kernel IO emulation
+ *
* @vcpu: The VCPU pointer
* @run: The VCPU run struct containing the mmio data
- *
- * This should only be called after returning from userspace for MMIO load
- * emulation.
*/
int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
@@ -104,7 +103,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (len > sizeof(unsigned long))
return -EINVAL;
- data = mmio_read_buf(run->mmio.data, len);
+ data = kvm_mmio_read_buf(run->mmio.data, len);
if (vcpu->arch.mmio_decode.sign_extend &&
len < sizeof(unsigned long)) {
@@ -190,7 +189,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
len);
trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
- mmio_write_buf(data_buf, len, data);
+ kvm_mmio_write_buf(data_buf, len, data);
ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len,
data_buf);
@@ -206,18 +205,19 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
run->mmio.is_write = is_write;
run->mmio.phys_addr = fault_ipa;
run->mmio.len = len;
- if (is_write)
- memcpy(run->mmio.data, data_buf, len);
if (!ret) {
/* We handled the access successfully in the kernel. */
+ if (!is_write)
+ memcpy(run->mmio.data, data_buf, len);
vcpu->stat.mmio_exit_kernel++;
kvm_handle_mmio_return(vcpu, run);
return 1;
- } else {
- vcpu->stat.mmio_exit_user++;
}
+ if (is_write)
+ memcpy(run->mmio.data, data_buf, len);
+ vcpu->stat.mmio_exit_user++;
run->exit_reason = KVM_EXIT_MMIO;
return 0;
}
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index e65aa7d11b20..20dcf6e904b2 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -61,7 +61,6 @@ config ARCH_EXYNOS4
select CLKSRC_SAMSUNG_PWM if CPU_EXYNOS4210
select CPU_EXYNOS4210
select GIC_NON_BANKED
- select KEYBOARD_SAMSUNG if INPUT_KEYBOARD
select MIGHT_HAVE_CACHE_L2X0
help
Samsung EXYNOS4 (Cortex-A9) SoC based systems
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index a38b16b69923..b56de4b8cdf2 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev)
static void __init imx6ul_enet_phy_init(void)
{
if (IS_BUILTIN(CONFIG_PHYLIB))
- phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff,
+ phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK,
ksz8081_phy_fixup);
}
diff --git a/arch/arm/mach-lpc32xx/Makefile b/arch/arm/mach-lpc32xx/Makefile
index c70709ada692..79b6b07e115d 100644
--- a/arch/arm/mach-lpc32xx/Makefile
+++ b/arch/arm/mach-lpc32xx/Makefile
@@ -2,6 +2,6 @@
# Makefile for the linux kernel.
#
-obj-y := irq.o common.o serial.o
+obj-y := common.o serial.o
obj-y += pm.o suspend.o
obj-y += phy3250.o
diff --git a/arch/arm/mach-lpc32xx/include/mach/irqs.h b/arch/arm/mach-lpc32xx/include/mach/irqs.h
index 9e3b90df32e1..00190535df90 100644
--- a/arch/arm/mach-lpc32xx/include/mach/irqs.h
+++ b/arch/arm/mach-lpc32xx/include/mach/irqs.h
@@ -112,6 +112,6 @@
#define IRQ_LPC32XX_GPI_06 LPC32XX_SIC2_IRQ(28)
#define IRQ_LPC32XX_SYSCLK LPC32XX_SIC2_IRQ(31)
-#define NR_IRQS 96
+#define LPC32XX_NR_IRQS 96
#endif
diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c
deleted file mode 100644
index 2ae431e8bc1b..000000000000
--- a/arch/arm/mach-lpc32xx/irq.c
+++ /dev/null
@@ -1,477 +0,0 @@
-/*
- * arch/arm/mach-lpc32xx/irq.c
- *
- * Author: Kevin Wells <kevin.wells@nxp.com>
- *
- * Copyright (C) 2010 NXP Semiconductors
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/irqdomain.h>
-#include <linux/module.h>
-
-#include <mach/irqs.h>
-#include <mach/hardware.h>
-#include <mach/platform.h>
-#include "common.h"
-
-/*
- * Default value representing the Activation polarity of all internal
- * interrupt sources
- */
-#define MIC_APR_DEFAULT 0x3FF0EFE0
-#define SIC1_APR_DEFAULT 0xFBD27186
-#define SIC2_APR_DEFAULT 0x801810C0
-
-/*
- * Default value representing the Activation Type of all internal
- * interrupt sources. All are level sensitive.
- */
-#define MIC_ATR_DEFAULT 0x00000000
-#define SIC1_ATR_DEFAULT 0x00026000
-#define SIC2_ATR_DEFAULT 0x00000000
-
-static struct irq_domain *lpc32xx_mic_domain;
-static struct device_node *lpc32xx_mic_np;
-
-struct lpc32xx_event_group_regs {
- void __iomem *enab_reg;
- void __iomem *edge_reg;
- void __iomem *maskstat_reg;
- void __iomem *rawstat_reg;
-};
-
-static const struct lpc32xx_event_group_regs lpc32xx_event_int_regs = {
- .enab_reg = LPC32XX_CLKPWR_INT_ER,
- .edge_reg = LPC32XX_CLKPWR_INT_AP,
- .maskstat_reg = LPC32XX_CLKPWR_INT_SR,
- .rawstat_reg = LPC32XX_CLKPWR_INT_RS,
-};
-
-static const struct lpc32xx_event_group_regs lpc32xx_event_pin_regs = {
- .enab_reg = LPC32XX_CLKPWR_PIN_ER,
- .edge_reg = LPC32XX_CLKPWR_PIN_AP,
- .maskstat_reg = LPC32XX_CLKPWR_PIN_SR,
- .rawstat_reg = LPC32XX_CLKPWR_PIN_RS,
-};
-
-struct lpc32xx_event_info {
- const struct lpc32xx_event_group_regs *event_group;
- u32 mask;
-};
-
-/*
- * Maps an IRQ number to and event mask and register
- */
-static const struct lpc32xx_event_info lpc32xx_events[NR_IRQS] = {
- [IRQ_LPC32XX_GPI_08] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_08_BIT,
- },
- [IRQ_LPC32XX_GPI_09] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_09_BIT,
- },
- [IRQ_LPC32XX_GPI_19] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_19_BIT,
- },
- [IRQ_LPC32XX_GPI_07] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_07_BIT,
- },
- [IRQ_LPC32XX_GPI_00] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_00_BIT,
- },
- [IRQ_LPC32XX_GPI_01] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_01_BIT,
- },
- [IRQ_LPC32XX_GPI_02] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_02_BIT,
- },
- [IRQ_LPC32XX_GPI_03] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_03_BIT,
- },
- [IRQ_LPC32XX_GPI_04] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_04_BIT,
- },
- [IRQ_LPC32XX_GPI_05] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_05_BIT,
- },
- [IRQ_LPC32XX_GPI_06] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_06_BIT,
- },
- [IRQ_LPC32XX_GPI_28] = {
- .event_group = &lpc32xx_event_pin_regs,
- .mask = LPC32XX_CLKPWR_EXTSRC_GPI_28_BIT,
- },
- [IRQ_LPC32XX_GPIO_00] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_GPIO_00_BIT,
- },
- [IRQ_LPC32XX_GPIO_01] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_GPIO_01_BIT,
- },
- [IRQ_LPC32XX_GPIO_02] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_GPIO_02_BIT,
- },
- [IRQ_LPC32XX_GPIO_03] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_GPIO_03_BIT,
- },
- [IRQ_LPC32XX_GPIO_04] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_GPIO_04_BIT,
- },
- [IRQ_LPC32XX_GPIO_05] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_GPIO_05_BIT,
- },
- [IRQ_LPC32XX_KEY] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_KEY_BIT,
- },
- [IRQ_LPC32XX_ETHERNET] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_MAC_BIT,
- },
- [IRQ_LPC32XX_USB_OTG_ATX] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_USBATXINT_BIT,
- },
- [IRQ_LPC32XX_USB_HOST] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_USB_BIT,
- },
- [IRQ_LPC32XX_RTC] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_RTC_BIT,
- },
- [IRQ_LPC32XX_MSTIMER] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_MSTIMER_BIT,
- },
- [IRQ_LPC32XX_TS_AUX] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_TS_AUX_BIT,
- },
- [IRQ_LPC32XX_TS_P] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_TS_P_BIT,
- },
- [IRQ_LPC32XX_TS_IRQ] = {
- .event_group = &lpc32xx_event_int_regs,
- .mask = LPC32XX_CLKPWR_INTSRC_ADC_BIT,
- },
-};
-
-static void get_controller(unsigned int irq, unsigned int *base,
- unsigned int *irqbit)
-{
- if (irq < 32) {
- *base = LPC32XX_MIC_BASE;
- *irqbit = 1 << irq;
- } else if (irq < 64) {
- *base = LPC32XX_SIC1_BASE;
- *irqbit = 1 << (irq - 32);
- } else {
- *base = LPC32XX_SIC2_BASE;
- *irqbit = 1 << (irq - 64);
- }
-}
-
-static void lpc32xx_mask_irq(struct irq_data *d)
-{
- unsigned int reg, ctrl, mask;
-
- get_controller(d->hwirq, &ctrl, &mask);
-
- reg = __raw_readl(LPC32XX_INTC_MASK(ctrl)) & ~mask;
- __raw_writel(reg, LPC32XX_INTC_MASK(ctrl));
-}
-
-static void lpc32xx_unmask_irq(struct irq_data *d)
-{
- unsigned int reg, ctrl, mask;
-
- get_controller(d->hwirq, &ctrl, &mask);
-
- reg = __raw_readl(LPC32XX_INTC_MASK(ctrl)) | mask;
- __raw_writel(reg, LPC32XX_INTC_MASK(ctrl));
-}
-
-static void lpc32xx_ack_irq(struct irq_data *d)
-{
- unsigned int ctrl, mask;
-
- get_controller(d->hwirq, &ctrl, &mask);
-
- __raw_writel(mask, LPC32XX_INTC_RAW_STAT(ctrl));
-
- /* Also need to clear pending wake event */
- if (lpc32xx_events[d->hwirq].mask != 0)
- __raw_writel(lpc32xx_events[d->hwirq].mask,
- lpc32xx_events[d->hwirq].event_group->rawstat_reg);
-}
-
-static void __lpc32xx_set_irq_type(unsigned int irq, int use_high_level,
- int use_edge)
-{
- unsigned int reg, ctrl, mask;
-
- get_controller(irq, &ctrl, &mask);
-
- /* Activation level, high or low */
- reg = __raw_readl(LPC32XX_INTC_POLAR(ctrl));
- if (use_high_level)
- reg |= mask;
- else
- reg &= ~mask;
- __raw_writel(reg, LPC32XX_INTC_POLAR(ctrl));
-
- /* Activation type, edge or level */
- reg = __raw_readl(LPC32XX_INTC_ACT_TYPE(ctrl));
- if (use_edge)
- reg |= mask;
- else
- reg &= ~mask;
- __raw_writel(reg, LPC32XX_INTC_ACT_TYPE(ctrl));
-
- /* Use same polarity for the wake events */
- if (lpc32xx_events[irq].mask != 0) {
- reg = __raw_readl(lpc32xx_events[irq].event_group->edge_reg);
-
- if (use_high_level)
- reg |= lpc32xx_events[irq].mask;
- else
- reg &= ~lpc32xx_events[irq].mask;
-
- __raw_writel(reg, lpc32xx_events[irq].event_group->edge_reg);
- }
-}
-
-static int lpc32xx_set_irq_type(struct irq_data *d, unsigned int type)
-{
- switch (type) {
- case IRQ_TYPE_EDGE_RISING:
- /* Rising edge sensitive */
- __lpc32xx_set_irq_type(d->hwirq, 1, 1);
- irq_set_handler_locked(d, handle_edge_irq);
- break;
-
- case IRQ_TYPE_EDGE_FALLING:
- /* Falling edge sensitive */
- __lpc32xx_set_irq_type(d->hwirq, 0, 1);
- irq_set_handler_locked(d, handle_edge_irq);
- break;
-
- case IRQ_TYPE_LEVEL_LOW:
- /* Low level sensitive */
- __lpc32xx_set_irq_type(d->hwirq, 0, 0);
- irq_set_handler_locked(d, handle_level_irq);
- break;
-
- case IRQ_TYPE_LEVEL_HIGH:
- /* High level sensitive */
- __lpc32xx_set_irq_type(d->hwirq, 1, 0);
- irq_set_handler_locked(d, handle_level_irq);
- break;
-
- /* Other modes are not supported */
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int lpc32xx_irq_wake(struct irq_data *d, unsigned int state)
-{
- unsigned long eventreg;
-
- if (lpc32xx_events[d->hwirq].mask != 0) {
- eventreg = __raw_readl(lpc32xx_events[d->hwirq].
- event_group->enab_reg);
-
- if (state)
- eventreg |= lpc32xx_events[d->hwirq].mask;
- else {
- eventreg &= ~lpc32xx_events[d->hwirq].mask;
-
- /*
- * When disabling the wakeup, clear the latched
- * event
- */
- __raw_writel(lpc32xx_events[d->hwirq].mask,
- lpc32xx_events[d->hwirq].
- event_group->rawstat_reg);
- }
-
- __raw_writel(eventreg,
- lpc32xx_events[d->hwirq].event_group->enab_reg);
-
- return 0;
- }
-
- /* Clear event */
- __raw_writel(lpc32xx_events[d->hwirq].mask,
- lpc32xx_events[d->hwirq].event_group->rawstat_reg);
-
- return -ENODEV;
-}
-
-static void __init lpc32xx_set_default_mappings(unsigned int apr,
- unsigned int atr, unsigned int offset)
-{
- unsigned int i;
-
- /* Set activation levels for each interrupt */
- i = 0;
- while (i < 32) {
- __lpc32xx_set_irq_type(offset + i, ((apr >> i) & 0x1),
- ((atr >> i) & 0x1));
- i++;
- }
-}
-
-static struct irq_chip lpc32xx_irq_chip = {
- .name = "MIC",
- .irq_ack = lpc32xx_ack_irq,
- .irq_mask = lpc32xx_mask_irq,
- .irq_unmask = lpc32xx_unmask_irq,
- .irq_set_type = lpc32xx_set_irq_type,
- .irq_set_wake = lpc32xx_irq_wake
-};
-
-static void lpc32xx_sic1_handler(struct irq_desc *desc)
-{
- unsigned long ints = __raw_readl(LPC32XX_INTC_STAT(LPC32XX_SIC1_BASE));
-
- while (ints != 0) {
- int irqno = fls(ints) - 1;
-
- ints &= ~(1 << irqno);
-
- generic_handle_irq(LPC32XX_SIC1_IRQ(irqno));
- }
-}
-
-static void lpc32xx_sic2_handler(struct irq_desc *desc)
-{
- unsigned long ints = __raw_readl(LPC32XX_INTC_STAT(LPC32XX_SIC2_BASE));
-
- while (ints != 0) {
- int irqno = fls(ints) - 1;
-
- ints &= ~(1 << irqno);
-
- generic_handle_irq(LPC32XX_SIC2_IRQ(irqno));
- }
-}
-
-static int __init __lpc32xx_mic_of_init(struct device_node *node,
- struct device_node *parent)
-{
- lpc32xx_mic_np = node;
-
- return 0;
-}
-
-static const struct of_device_id mic_of_match[] __initconst = {
- { .compatible = "nxp,lpc3220-mic", .data = __lpc32xx_mic_of_init },
- { }
-};
-
-void __init lpc32xx_init_irq(void)
-{
- unsigned int i;
-
- /* Setup MIC */
- __raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_MIC_BASE));
- __raw_writel(MIC_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_MIC_BASE));
- __raw_writel(MIC_ATR_DEFAULT, LPC32XX_INTC_ACT_TYPE(LPC32XX_MIC_BASE));
-
- /* Setup SIC1 */
- __raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_SIC1_BASE));
- __raw_writel(SIC1_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC1_BASE));
- __raw_writel(SIC1_ATR_DEFAULT,
- LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC1_BASE));
-
- /* Setup SIC2 */
- __raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_SIC2_BASE));
- __raw_writel(SIC2_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC2_BASE));
- __raw_writel(SIC2_ATR_DEFAULT,
- LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC2_BASE));
-
- /* Configure supported IRQ's */
- for (i = 0; i < NR_IRQS; i++) {
- irq_set_chip_and_handler(i, &lpc32xx_irq_chip,
- handle_level_irq);
- irq_clear_status_flags(i, IRQ_NOREQUEST);
- }
-
- /* Set default mappings */
- lpc32xx_set_default_mappings(MIC_APR_DEFAULT, MIC_ATR_DEFAULT, 0);
- lpc32xx_set_default_mappings(SIC1_APR_DEFAULT, SIC1_ATR_DEFAULT, 32);
- lpc32xx_set_default_mappings(SIC2_APR_DEFAULT, SIC2_ATR_DEFAULT, 64);
-
- /* Initially disable all wake events */
- __raw_writel(0, LPC32XX_CLKPWR_P01_ER);
- __raw_writel(0, LPC32XX_CLKPWR_INT_ER);
- __raw_writel(0, LPC32XX_CLKPWR_PIN_ER);
-
- /*
- * Default wake activation polarities, all pin sources are low edge
- * triggered
- */
- __raw_writel(LPC32XX_CLKPWR_INTSRC_TS_P_BIT |
- LPC32XX_CLKPWR_INTSRC_MSTIMER_BIT |
- LPC32XX_CLKPWR_INTSRC_RTC_BIT,
- LPC32XX_CLKPWR_INT_AP);
- __raw_writel(0, LPC32XX_CLKPWR_PIN_AP);
-
- /* Clear latched wake event states */
- __raw_writel(__raw_readl(LPC32XX_CLKPWR_PIN_RS),
- LPC32XX_CLKPWR_PIN_RS);
- __raw_writel(__raw_readl(LPC32XX_CLKPWR_INT_RS),
- LPC32XX_CLKPWR_INT_RS);
-
- of_irq_init(mic_of_match);
-
- lpc32xx_mic_domain = irq_domain_add_legacy(lpc32xx_mic_np, NR_IRQS,
- 0, 0, &irq_domain_simple_ops,
- NULL);
- if (!lpc32xx_mic_domain)
- panic("Unable to add MIC irq domain\n");
-
- /* MIC SUBIRQx interrupts will route handling to the chain handlers */
- irq_set_chained_handler(IRQ_LPC32XX_SUB1IRQ, lpc32xx_sic1_handler);
- irq_set_chained_handler(IRQ_LPC32XX_SUB2IRQ, lpc32xx_sic2_handler);
-}
diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 5d7fb596bf4a..bf608441b357 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -43,8 +43,8 @@
#define OTHERS_MASK (MODEM_IRQ_MASK | HOOK_SWITCH_MASK)
/* IRQ handler register bitmasks */
-#define DEFERRED_FIQ_MASK (0x1 << (INT_DEFERRED_FIQ % IH2_BASE))
-#define GPIO_BANK1_MASK (0x1 << INT_GPIO_BANK1)
+#define DEFERRED_FIQ_MASK OMAP_IRQ_BIT(INT_DEFERRED_FIQ)
+#define GPIO_BANK1_MASK OMAP_IRQ_BIT(INT_GPIO_BANK1)
/* Driver buffer byte offsets */
#define BUF_MASK (FIQ_MASK * 4)
@@ -110,7 +110,7 @@ ENTRY(qwerty_fiqin_start)
mov r8, #2 @ reset FIQ agreement
str r8, [r12, #IRQ_CONTROL_REG_OFFSET]
- cmp r10, #INT_GPIO_BANK1 @ is it GPIO bank interrupt?
+ cmp r10, #(INT_GPIO_BANK1 - NR_IRQS_LEGACY) @ is it GPIO interrupt?
beq gpio @ yes - process it
mov r8, #1
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index d1f12095f315..ec760ae2f917 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -109,7 +109,8 @@ void __init ams_delta_init_fiq(void)
* Since no set_type() method is provided by OMAP irq chip,
* switch to edge triggered interrupt type manually.
*/
- offset = IRQ_ILR0_REG_OFFSET + INT_DEFERRED_FIQ * 0x4;
+ offset = IRQ_ILR0_REG_OFFSET +
+ ((INT_DEFERRED_FIQ - NR_IRQS_LEGACY) & 0x1f) * 0x4;
val = omap_readl(DEFERRED_FIQ_IH_BASE + offset) & ~(1 << 1);
omap_writel(val, DEFERRED_FIQ_IH_BASE + offset);
@@ -149,7 +150,7 @@ void __init ams_delta_init_fiq(void)
/*
* Redirect GPIO interrupts to FIQ
*/
- offset = IRQ_ILR0_REG_OFFSET + INT_GPIO_BANK1 * 0x4;
+ offset = IRQ_ILR0_REG_OFFSET + (INT_GPIO_BANK1 - NR_IRQS_LEGACY) * 0x4;
val = omap_readl(OMAP_IH1_BASE + offset) | 1;
omap_writel(val, OMAP_IH1_BASE + offset);
}
diff --git a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
index adb5e7649659..6dfc3e1210a3 100644
--- a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
+++ b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
@@ -14,6 +14,8 @@
#ifndef __AMS_DELTA_FIQ_H
#define __AMS_DELTA_FIQ_H
+#include <mach/irqs.h>
+
/*
* Interrupt number used for passing control from FIQ to IRQ.
* IRQ12, described as reserved, has been selected.
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 0517f0c1581a..1a648e9dfaa0 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -17,6 +17,7 @@ config ARCH_OMAP3
select PM_OPP if PM
select PM if CPU_IDLE
select SOC_HAS_OMAP2_SDRC
+ select ARM_ERRATA_430973
config ARCH_OMAP4
bool "TI OMAP4"
@@ -36,6 +37,7 @@ config ARCH_OMAP4
select PM if CPU_IDLE
select ARM_ERRATA_754322
select ARM_ERRATA_775420
+ select OMAP_INTERCONNECT
config SOC_OMAP5
bool "TI OMAP5"
@@ -67,6 +69,8 @@ config SOC_AM43XX
select HAVE_ARM_SCU
select GENERIC_CLOCKEVENTS_BROADCAST
select HAVE_ARM_TWD
+ select ARM_ERRATA_754322
+ select ARM_ERRATA_775420
config SOC_DRA7XX
bool "TI DRA7XX"
@@ -240,4 +244,12 @@ endmenu
endif
+config OMAP5_ERRATA_801819
+ bool "Errata 801819: An eviction from L1 data cache might stall indefinitely"
+ depends on SOC_OMAP5 || SOC_DRA7XX
+ help
+ A livelock can occur in the L2 cache arbitration that might prevent
+ a snoop from completing. Under certain conditions this can cause the
+ system to deadlock.
+
endmenu
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
index 72918c4973ea..f6ac027f3c3b 100644
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ b/arch/arm/mach-omap2/gpmc-nand.c
@@ -97,10 +97,7 @@ int gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data,
gpmc_nand_res[2].start = gpmc_get_client_irq(GPMC_IRQ_COUNT_EVENT);
memset(&s, 0, sizeof(struct gpmc_settings));
- if (gpmc_nand_data->of_node)
- gpmc_read_settings_dt(gpmc_nand_data->of_node, &s);
- else
- gpmc_set_legacy(gpmc_nand_data, &s);
+ gpmc_set_legacy(gpmc_nand_data, &s);
s.device_nand = true;
@@ -121,8 +118,6 @@ int gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data,
if (err < 0)
goto out_free_cs;
- gpmc_update_nand_reg(&gpmc_nand_data->reg, gpmc_nand_data->cs);
-
if (!gpmc_hwecc_bch_capable(gpmc_nand_data->ecc_opt)) {
pr_err("omap2-nand: Unsupported NAND ECC scheme selected\n");
err = -EINVAL;
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index af2851fbcdf0..bae263fba640 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -46,6 +46,7 @@
#define OMAP5_DRA7_MON_SET_CNTFRQ_INDEX 0x109
#define OMAP5_MON_AMBA_IF_INDEX 0x108
+#define OMAP5_DRA7_MON_SET_ACR_INDEX 0x107
/* Secure PPA(Primary Protected Application) APIs */
#define OMAP4_PPA_L2_POR_INDEX 0x23
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index c625cc10d9f9..8cd1de914ee4 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -50,6 +50,39 @@ void __iomem *omap4_get_scu_base(void)
return scu_base;
}
+#ifdef CONFIG_OMAP5_ERRATA_801819
+void omap5_erratum_workaround_801819(void)
+{
+ u32 acr, revidr;
+ u32 acr_mask;
+
+ /* REVIDR[3] indicates erratum fix available on silicon */
+ asm volatile ("mrc p15, 0, %0, c0, c0, 6" : "=r" (revidr));
+ if (revidr & (0x1 << 3))
+ return;
+
+ asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr));
+ /*
+ * BIT(27) - Disables streaming. All write-allocate lines allocate in
+ * the L1 or L2 cache.
+ * BIT(25) - Disables streaming. All write-allocate lines allocate in
+ * the L1 cache.
+ */
+ acr_mask = (0x3 << 25) | (0x3 << 27);
+ /* do we already have it done.. if yes, skip expensive smc */
+ if ((acr & acr_mask) == acr_mask)
+ return;
+
+ acr |= acr_mask;
+ omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr);
+
+ pr_debug("%s: ARM erratum workaround 801819 applied on CPU%d\n",
+ __func__, smp_processor_id());
+}
+#else
+static inline void omap5_erratum_workaround_801819(void) { }
+#endif
+
static void omap4_secondary_init(unsigned int cpu)
{
/*
@@ -64,12 +97,15 @@ static void omap4_secondary_init(unsigned int cpu)
omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX,
4, 0, 0, 0, 0, 0);
- /*
- * Configure the CNTFRQ register for the secondary cpu's which
- * indicates the frequency of the cpu local timers.
- */
- if (soc_is_omap54xx() || soc_is_dra7xx())
+ if (soc_is_omap54xx() || soc_is_dra7xx()) {
+ /*
+ * Configure the CNTFRQ register for the secondary cpu's which
+ * indicates the frequency of the cpu local timers.
+ */
set_cntfreq();
+ /* Configure ACR to disable streaming WA for 801819 */
+ omap5_erratum_workaround_801819();
+ }
/*
* Synchronise with the boot thread.
@@ -218,6 +254,8 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
if (cpu_is_omap446x())
startup_addr = omap4460_secondary_startup;
+ if (soc_is_dra74x() || soc_is_omap54xx())
+ omap5_erratum_workaround_801819();
/*
* Write the address of secondary startup routine into the
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 78af6d8cf2e2..daf2753de7aa 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -186,8 +186,9 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag)
trace_state = (PWRDM_TRACE_STATES_FLAG |
((next & OMAP_POWERSTATE_MASK) << 8) |
((prev & OMAP_POWERSTATE_MASK) << 0));
- trace_power_domain_target(pwrdm->name, trace_state,
- smp_processor_id());
+ trace_power_domain_target_rcuidle(pwrdm->name,
+ trace_state,
+ smp_processor_id());
}
break;
default:
@@ -523,8 +524,8 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
/* Trace the pwrdm desired target state */
- trace_power_domain_target(pwrdm->name, pwrst,
- smp_processor_id());
+ trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
+ smp_processor_id());
/* Program the pwrdm desired target state */
ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);
}
diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c
index 0ec2d00f4237..eb350a673133 100644
--- a/arch/arm/mach-omap2/powerdomains7xx_data.c
+++ b/arch/arm/mach-omap2/powerdomains7xx_data.c
@@ -36,14 +36,7 @@ static struct powerdomain iva_7xx_pwrdm = {
.prcm_offs = DRA7XX_PRM_IVA_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
- .pwrsts_logic_ret = PWRSTS_OFF,
.banks = 4,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* hwa_mem */
- [1] = PWRSTS_OFF_RET, /* sl2_mem */
- [2] = PWRSTS_OFF_RET, /* tcm1_mem */
- [3] = PWRSTS_OFF_RET, /* tcm2_mem */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* hwa_mem */
[1] = PWRSTS_ON, /* sl2_mem */
@@ -76,12 +69,7 @@ static struct powerdomain ipu_7xx_pwrdm = {
.prcm_offs = DRA7XX_PRM_IPU_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
- .pwrsts_logic_ret = PWRSTS_OFF,
.banks = 2,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* aessmem */
- [1] = PWRSTS_OFF_RET, /* periphmem */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* aessmem */
[1] = PWRSTS_ON, /* periphmem */
@@ -95,11 +83,7 @@ static struct powerdomain dss_7xx_pwrdm = {
.prcm_offs = DRA7XX_PRM_DSS_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
- .pwrsts_logic_ret = PWRSTS_OFF,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* dss_mem */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* dss_mem */
},
@@ -111,13 +95,8 @@ static struct powerdomain l4per_7xx_pwrdm = {
.name = "l4per_pwrdm",
.prcm_offs = DRA7XX_PRM_L4PER_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
- .pwrsts = PWRSTS_RET_ON,
- .pwrsts_logic_ret = PWRSTS_RET,
+ .pwrsts = PWRSTS_ON,
.banks = 2,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* nonretained_bank */
- [1] = PWRSTS_OFF_RET, /* retained_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* nonretained_bank */
[1] = PWRSTS_ON, /* retained_bank */
@@ -132,9 +111,6 @@ static struct powerdomain gpu_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* gpu_mem */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* gpu_mem */
},
@@ -148,8 +124,6 @@ static struct powerdomain wkupaon_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* wkup_bank */
},
@@ -161,15 +135,7 @@ static struct powerdomain core_7xx_pwrdm = {
.prcm_offs = DRA7XX_PRM_CORE_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_ON,
- .pwrsts_logic_ret = PWRSTS_RET,
.banks = 5,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* core_nret_bank */
- [1] = PWRSTS_OFF_RET, /* core_ocmram */
- [2] = PWRSTS_OFF_RET, /* core_other_bank */
- [3] = PWRSTS_OFF_RET, /* ipu_l2ram */
- [4] = PWRSTS_OFF_RET, /* ipu_unicache */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* core_nret_bank */
[1] = PWRSTS_ON, /* core_ocmram */
@@ -226,11 +192,7 @@ static struct powerdomain vpe_7xx_pwrdm = {
.prcm_offs = DRA7XX_PRM_VPE_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
- .pwrsts_logic_ret = PWRSTS_OFF,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* vpe_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* vpe_bank */
},
@@ -260,14 +222,8 @@ static struct powerdomain l3init_7xx_pwrdm = {
.name = "l3init_pwrdm",
.prcm_offs = DRA7XX_PRM_L3INIT_INST,
.prcm_partition = DRA7XX_PRM_PARTITION,
- .pwrsts = PWRSTS_RET_ON,
- .pwrsts_logic_ret = PWRSTS_RET,
+ .pwrsts = PWRSTS_ON,
.banks = 3,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* gmac_bank */
- [1] = PWRSTS_OFF_RET, /* l3init_bank1 */
- [2] = PWRSTS_OFF_RET, /* l3init_bank2 */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* gmac_bank */
[1] = PWRSTS_ON, /* l3init_bank1 */
@@ -283,9 +239,6 @@ static struct powerdomain eve3_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* eve3_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* eve3_bank */
},
@@ -299,9 +252,6 @@ static struct powerdomain emu_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* emu_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* emu_bank */
},
@@ -314,11 +264,6 @@ static struct powerdomain dsp2_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 3,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* dsp2_edma */
- [1] = PWRSTS_OFF_RET, /* dsp2_l1 */
- [2] = PWRSTS_OFF_RET, /* dsp2_l2 */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* dsp2_edma */
[1] = PWRSTS_ON, /* dsp2_l1 */
@@ -334,11 +279,6 @@ static struct powerdomain dsp1_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 3,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* dsp1_edma */
- [1] = PWRSTS_OFF_RET, /* dsp1_l1 */
- [2] = PWRSTS_OFF_RET, /* dsp1_l2 */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* dsp1_edma */
[1] = PWRSTS_ON, /* dsp1_l1 */
@@ -354,9 +294,6 @@ static struct powerdomain cam_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* vip_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* vip_bank */
},
@@ -370,9 +307,6 @@ static struct powerdomain eve4_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* eve4_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* eve4_bank */
},
@@ -386,9 +320,6 @@ static struct powerdomain eve2_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* eve2_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* eve2_bank */
},
@@ -402,9 +333,6 @@ static struct powerdomain eve1_7xx_pwrdm = {
.prcm_partition = DRA7XX_PRM_PARTITION,
.pwrsts = PWRSTS_OFF_ON,
.banks = 1,
- .pwrsts_mem_ret = {
- [0] = PWRSTS_OFF_RET, /* eve1_bank */
- },
.pwrsts_mem_on = {
[0] = PWRSTS_ON, /* eve1_bank */
},
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 5b385bb8aff9..cb9497a20fb3 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -496,8 +496,7 @@ void __init omap_init_time(void)
__omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon",
2, "timer_sys_ck", NULL, false);
- if (of_have_populated_dt())
- clocksource_probe();
+ clocksource_probe();
}
#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX)
@@ -505,6 +504,8 @@ void __init omap3_secure_sync32k_timer_init(void)
{
__omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure",
2, "timer_sys_ck", NULL, false);
+
+ clocksource_probe();
}
#endif /* CONFIG_ARCH_OMAP3 */
@@ -513,6 +514,8 @@ void __init omap3_gptimer_timer_init(void)
{
__omap_sync32k_timer_init(2, "timer_sys_ck", NULL,
1, "timer_sys_ck", "ti,timer-alwon", true);
+
+ clocksource_probe();
}
#endif
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 7ee4652b4c61..cd894d69e766 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -6,6 +6,7 @@ comment "Intel/Marvell Dev Platforms (sorted by hardware release time)"
config MACH_PXA27X_DT
bool "Support PXA27x platforms from device tree"
+ select PINCTRL
select POWER_SUPPLY
select PXA27x
select USE_OF
@@ -17,6 +18,7 @@ config MACH_PXA27X_DT
config MACH_PXA3XX_DT
bool "Support PXA3xx platforms from device tree"
select CPU_PXA300
+ select PINCTRL
select POWER_SUPPLY
select PXA3xx
select USE_OF
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index e838b11fb8c7..fa9d71d194f0 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -128,7 +128,7 @@ struct resource eseries_tmio_resources[] = {
/* Some e-series hardware cannot control the 32K clock */
static void __init __maybe_unused eseries_register_clks(void)
{
- clk_register_fixed_rate(NULL, "CLK_CK32K", NULL, CLK_IS_ROOT, 32768);
+ clk_register_fixed_rate(NULL, "CLK_CK32K", NULL, 0, 32768);
}
#ifdef CONFIG_MACH_E330
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index d9578bc49fdc..bd7cd8b6a286 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -763,14 +763,49 @@ static struct nand_bbt_descr spitz_nand_bbt = {
.pattern = scan_ff_pattern
};
-static struct nand_ecclayout akita_oobinfo = {
- .oobfree = { {0x08, 0x09} },
- .eccbytes = 24,
- .eccpos = {
- 0x05, 0x01, 0x02, 0x03, 0x06, 0x07, 0x15, 0x11,
- 0x12, 0x13, 0x16, 0x17, 0x25, 0x21, 0x22, 0x23,
- 0x26, 0x27, 0x35, 0x31, 0x32, 0x33, 0x36, 0x37,
- },
+static int akita_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 12)
+ return -ERANGE;
+
+ switch (section % 3) {
+ case 0:
+ oobregion->offset = 5;
+ oobregion->length = 1;
+ break;
+
+ case 1:
+ oobregion->offset = 1;
+ oobregion->length = 3;
+ break;
+
+ case 2:
+ oobregion->offset = 6;
+ oobregion->length = 2;
+ break;
+ }
+
+ oobregion->offset += (section / 3) * 0x10;
+
+ return 0;
+}
+
+static int akita_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 8;
+ oobregion->length = 9;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops akita_ooblayout_ops = {
+ .ecc = akita_ooblayout_ecc,
+ .free = akita_ooblayout_free,
};
static struct sharpsl_nand_platform_data spitz_nand_pdata = {
@@ -804,11 +839,11 @@ static void __init spitz_nand_init(void)
} else if (machine_is_akita()) {
spitz_nand_partitions[1].size = 58 * 1024 * 1024;
spitz_nand_bbt.len = 1;
- spitz_nand_pdata.ecc_layout = &akita_oobinfo;
+ spitz_nand_pdata.ecc_layout = &akita_ooblayout_ops;
} else if (machine_is_borzoi()) {
spitz_nand_partitions[1].size = 32 * 1024 * 1024;
spitz_nand_bbt.len = 1;
- spitz_nand_pdata.ecc_layout = &akita_oobinfo;
+ spitz_nand_pdata.ecc_layout = &akita_ooblayout_ops;
}
platform_device_register(&spitz_nand_device);
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index 774c982a7b7e..25a139bb9826 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -496,6 +496,12 @@ static int rx1950_backlight_init(struct device *dev)
return PTR_ERR(lcd_pwm);
}
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(lcd_pwm);
+
rx1950_lcd_power(1);
rx1950_bl_power(1);
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index 5766ce2be32b..8409cab3f760 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -547,7 +547,7 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev)
init.name = dev_name(cpu_dev);
init.ops = &clk_spc_ops;
- init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE;
+ init.flags = CLK_GET_RATE_NOCACHE;
init.num_parents = 0;
return devm_clk_register(cpu_dev, &spc->hw);
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 84baa16f4c0b..e93aa6734147 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -68,7 +68,7 @@
#include <linux/platform_data/asoc-s3c.h>
#include <linux/platform_data/spi-s3c64xx.h>
-static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
+#define samsung_device_dma_mask (*((u64[]) { DMA_BIT_MASK(32) }))
/* AC97 */
#ifdef CONFIG_CPU_S3C2440
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 1160434eece0..59a8fa7b8a3b 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -74,5 +74,5 @@ $(MODLIB)/vdso: FORCE
@mkdir -p $(MODLIB)/vdso
PHONY += vdso_install
-vdso_install: $(obj)/vdso.so.dbg $(MODLIB)/vdso FORCE
+vdso_install: $(obj)/vdso.so.dbg $(MODLIB)/vdso
$(call cmd,vdso_install)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 76747d92bc72..5a0a691d4220 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -113,6 +113,18 @@ config ARCH_PHYS_ADDR_T_64BIT
config MMU
def_bool y
+config ARM64_PAGE_SHIFT
+ int
+ default 16 if ARM64_64K_PAGES
+ default 14 if ARM64_16K_PAGES
+ default 12
+
+config ARM64_CONT_SHIFT
+ int
+ default 5 if ARM64_64K_PAGES
+ default 7 if ARM64_16K_PAGES
+ default 4
+
config ARCH_MMAP_RND_BITS_MIN
default 14 if ARM64_64K_PAGES
default 16 if ARM64_16K_PAGES
@@ -426,6 +438,15 @@ config CAVIUM_ERRATUM_22375
If unsure, say Y.
+config CAVIUM_ERRATUM_23144
+ bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+ depends on NUMA
+ default y
+ help
+ ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_23154
bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
default y
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 710fde4ad0f0..0cc758cdd0dc 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -12,7 +12,8 @@ config ARM64_PTDUMP
who are working in architecture specific areas of the kernel.
It is probably not a good idea to enable this feature in a production
kernel.
- If in doubt, say "N"
+
+ If in doubt, say N.
config PID_IN_CONTEXTIDR
bool "Write the current PID to the CONTEXTIDR register"
@@ -38,15 +39,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
value.
config DEBUG_SET_MODULE_RONX
- bool "Set loadable kernel module data as NX and text as RO"
- depends on MODULES
- help
- This option helps catch unintended modifications to loadable
- kernel module's text and read-only data. It also prevents execution
- of module data. Such protection may interfere with run-time code
- patching and dynamic kernel tracing - and they might also protect
- against certain classes of kernel exploits.
- If in doubt, say "N".
+ bool "Set loadable kernel module data as NX and text as RO"
+ depends on MODULES
+ default y
+ help
+ Is this is set, kernel module text and rodata will be made read-only.
+ This is to help catch accidental or malicious attempts to change the
+ kernel's executable code.
+
+ If in doubt, say Y.
config DEBUG_RODATA
bool "Make kernel text and rodata read-only"
@@ -56,7 +57,7 @@ config DEBUG_RODATA
is to help catch accidental or malicious attempts to change the
kernel's executable code.
- If in doubt, say Y
+ If in doubt, say Y.
config DEBUG_ALIGN_RODATA
depends on DEBUG_RODATA
@@ -69,7 +70,7 @@ config DEBUG_ALIGN_RODATA
alignment and potentially wasted space. Turn on this option if
performance is more important than memory pressure.
- If in doubt, say N
+ If in doubt, say N.
source "drivers/hwtracing/coresight/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 354d75402ace..648a32c89541 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -60,7 +60,9 @@ head-y := arch/arm64/kernel/head.o
# The byte offset of the kernel image in RAM from the start of RAM.
ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
-TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}')
+TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
+ int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
+ rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
else
TEXT_OFFSET := 0x00080000
endif
@@ -93,7 +95,7 @@ boot := arch/arm64/boot
Image: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-Image.%: vmlinux
+Image.%: Image
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
zinstall install:
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 3a4e9a2ab313..fbafa24cd533 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -125,7 +125,7 @@
#size-cells = <1>;
#interrupts-cells = <3>;
- compatible = "arm,amba-bus";
+ compatible = "simple-bus";
interrupt-parent = <&gic>;
ranges;
diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
index 7cb2d72e7378..3285a9286786 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
@@ -10,6 +10,7 @@
#include <dt-bindings/clock/r8a7795-cpg-mssr.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/r8a7795-sysc.h>
/ {
compatible = "renesas,r8a7795";
@@ -39,6 +40,7 @@
compatible = "arm,cortex-a57", "arm,armv8";
reg = <0x0>;
device_type = "cpu";
+ power-domains = <&sysc R8A7795_PD_CA57_CPU0>;
next-level-cache = <&L2_CA57>;
enable-method = "psci";
};
@@ -47,6 +49,7 @@
compatible = "arm,cortex-a57","arm,armv8";
reg = <0x1>;
device_type = "cpu";
+ power-domains = <&sysc R8A7795_PD_CA57_CPU1>;
next-level-cache = <&L2_CA57>;
enable-method = "psci";
};
@@ -54,6 +57,7 @@
compatible = "arm,cortex-a57","arm,armv8";
reg = <0x2>;
device_type = "cpu";
+ power-domains = <&sysc R8A7795_PD_CA57_CPU2>;
next-level-cache = <&L2_CA57>;
enable-method = "psci";
};
@@ -61,6 +65,7 @@
compatible = "arm,cortex-a57","arm,armv8";
reg = <0x3>;
device_type = "cpu";
+ power-domains = <&sysc R8A7795_PD_CA57_CPU3>;
next-level-cache = <&L2_CA57>;
enable-method = "psci";
};
@@ -68,12 +73,14 @@
L2_CA57: cache-controller@0 {
compatible = "cache";
+ power-domains = <&sysc R8A7795_PD_CA57_SCU>;
cache-unified;
cache-level = <2>;
};
L2_CA53: cache-controller@1 {
compatible = "cache";
+ power-domains = <&sysc R8A7795_PD_CA53_SCU>;
cache-unified;
cache-level = <2>;
};
@@ -168,7 +175,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 912>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio1: gpio@e6051000 {
@@ -182,7 +189,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 911>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio2: gpio@e6052000 {
@@ -196,7 +203,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 910>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio3: gpio@e6053000 {
@@ -210,7 +217,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 909>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio4: gpio@e6054000 {
@@ -224,7 +231,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 908>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio5: gpio@e6055000 {
@@ -238,7 +245,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 907>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio6: gpio@e6055400 {
@@ -252,7 +259,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 906>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
gpio7: gpio@e6055800 {
@@ -266,7 +273,7 @@
#interrupt-cells = <2>;
interrupt-controller;
clocks = <&cpg CPG_MOD 905>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
pmu_a57 {
@@ -302,6 +309,12 @@
#power-domain-cells = <0>;
};
+ sysc: system-controller@e6180000 {
+ compatible = "renesas,r8a7795-sysc";
+ reg = <0 0xe6180000 0 0x0400>;
+ #power-domain-cells = <1>;
+ };
+
audma0: dma-controller@ec700000 {
compatible = "renesas,rcar-dmac";
reg = <0 0xec700000 0 0x10000>;
@@ -329,7 +342,7 @@
"ch12", "ch13", "ch14", "ch15";
clocks = <&cpg CPG_MOD 502>;
clock-names = "fck";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <16>;
};
@@ -361,7 +374,7 @@
"ch12", "ch13", "ch14", "ch15";
clocks = <&cpg CPG_MOD 501>;
clock-names = "fck";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <16>;
};
@@ -383,7 +396,7 @@
GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH
GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 407>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
};
dmac0: dma-controller@e6700000 {
@@ -414,7 +427,7 @@
"ch12", "ch13", "ch14", "ch15";
clocks = <&cpg CPG_MOD 219>;
clock-names = "fck";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <16>;
};
@@ -447,7 +460,7 @@
"ch12", "ch13", "ch14", "ch15";
clocks = <&cpg CPG_MOD 218>;
clock-names = "fck";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <16>;
};
@@ -480,7 +493,7 @@
"ch12", "ch13", "ch14", "ch15";
clocks = <&cpg CPG_MOD 217>;
clock-names = "fck";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <16>;
};
@@ -522,7 +535,7 @@
"ch20", "ch21", "ch22", "ch23",
"ch24";
clocks = <&cpg CPG_MOD 812>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
phy-mode = "rgmii-id";
#address-cells = <1>;
#size-cells = <0>;
@@ -539,7 +552,7 @@
clock-names = "clkp1", "clkp2", "can_clk";
assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
assigned-clock-rates = <40000000>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -554,7 +567,7 @@
clock-names = "clkp1", "clkp2", "can_clk";
assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
assigned-clock-rates = <40000000>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -570,7 +583,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x31>, <&dmac1 0x30>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -586,7 +599,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x33>, <&dmac1 0x32>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -602,7 +615,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x35>, <&dmac1 0x34>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -618,7 +631,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x37>, <&dmac0 0x36>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -634,7 +647,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x39>, <&dmac0 0x38>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -649,7 +662,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x51>, <&dmac1 0x50>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -664,7 +677,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x53>, <&dmac1 0x52>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -679,7 +692,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x13>, <&dmac1 0x12>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -694,7 +707,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x57>, <&dmac0 0x56>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -709,7 +722,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac0 0x59>, <&dmac0 0x58>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -724,7 +737,7 @@
clock-names = "fck", "brg_int", "scif_clk";
dmas = <&dmac1 0x5b>, <&dmac1 0x5a>;
dma-names = "tx", "rx";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -735,7 +748,7 @@
reg = <0 0xe6500000 0 0x40>;
interrupts = <GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 931>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -747,7 +760,7 @@
reg = <0 0xe6508000 0 0x40>;
interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 930>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -759,7 +772,7 @@
reg = <0 0xe6510000 0 0x40>;
interrupts = <GIC_SPI 286 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 929>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -771,7 +784,7 @@
reg = <0 0xe66d0000 0 0x40>;
interrupts = <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 928>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -783,7 +796,7 @@
reg = <0 0xe66d8000 0 0x40>;
interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 927>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -795,7 +808,7 @@
reg = <0 0xe66e0000 0 0x40>;
interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 919>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <110>;
status = "disabled";
};
@@ -807,7 +820,7 @@
reg = <0 0xe66e8000 0 0x40>;
interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 918>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
i2c-scl-internal-delay-ns = <6>;
status = "disabled";
};
@@ -857,7 +870,7 @@
"src.1", "src.0",
"dvc.0", "dvc.1",
"clk_a", "clk_b", "clk_c", "clk_i";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
rcar_sound,dvc {
@@ -991,7 +1004,7 @@
reg = <0 0xee000000 0 0xc00>;
interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 328>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1000,7 +1013,7 @@
reg = <0 0xee040000 0 0xc00>;
interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 327>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1012,7 +1025,7 @@
GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "ch0", "ch1";
clocks = <&cpg CPG_MOD 330>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <2>;
};
@@ -1025,7 +1038,7 @@
GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "ch0", "ch1";
clocks = <&cpg CPG_MOD 331>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#dma-cells = <1>;
dma-channels = <2>;
};
@@ -1035,7 +1048,7 @@
reg = <0 0xee100000 0 0x2000>;
interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 314>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1044,7 +1057,7 @@
reg = <0 0xee120000 0 0x2000>;
interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 313>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1053,7 +1066,7 @@
reg = <0 0xee140000 0 0x2000>;
interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 312>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
cap-mmc-highspeed;
status = "disabled";
};
@@ -1063,7 +1076,7 @@
reg = <0 0xee160000 0 0x2000>;
interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 311>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
cap-mmc-highspeed;
status = "disabled";
};
@@ -1073,7 +1086,7 @@
reg = <0 0xee080200 0 0x700>;
interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 703>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#phy-cells = <0>;
status = "disabled";
};
@@ -1082,7 +1095,7 @@
compatible = "renesas,usb2-phy-r8a7795";
reg = <0 0xee0a0200 0 0x700>;
clocks = <&cpg CPG_MOD 702>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#phy-cells = <0>;
status = "disabled";
};
@@ -1091,7 +1104,7 @@
compatible = "renesas,usb2-phy-r8a7795";
reg = <0 0xee0c0200 0 0x700>;
clocks = <&cpg CPG_MOD 701>;
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
#phy-cells = <0>;
status = "disabled";
};
@@ -1103,7 +1116,7 @@
clocks = <&cpg CPG_MOD 703>;
phys = <&usb2_phy0>;
phy-names = "usb";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1114,7 +1127,7 @@
clocks = <&cpg CPG_MOD 702>;
phys = <&usb2_phy1>;
phy-names = "usb";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1125,7 +1138,7 @@
clocks = <&cpg CPG_MOD 701>;
phys = <&usb2_phy2>;
phy-names = "usb";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1136,7 +1149,7 @@
clocks = <&cpg CPG_MOD 703>;
phys = <&usb2_phy0>;
phy-names = "usb";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1147,7 +1160,7 @@
clocks = <&cpg CPG_MOD 702>;
phys = <&usb2_phy1>;
phy-names = "usb";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1158,7 +1171,7 @@
clocks = <&cpg CPG_MOD 701>;
phys = <&usb2_phy2>;
phy-names = "usb";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
pciec0: pcie@fe000000 {
@@ -1182,7 +1195,7 @@
interrupt-map = <0 0 0 0 &gic GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 319>, <&pcie_bus_clk>;
clock-names = "pcie", "pcie_bus";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
@@ -1207,7 +1220,7 @@
interrupt-map = <0 0 0 0 &gic GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 318>, <&pcie_bus_clk>;
clock-names = "pcie", "pcie_bus";
- power-domains = <&cpg>;
+ power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
status = "disabled";
};
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 46f325a143b0..d7f8e06910bc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -163,7 +163,7 @@
};
amba {
- compatible = "arm,amba-bus";
+ compatible = "simple-bus";
#address-cells = <2>;
#size-cells = <2>;
ranges;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 89171505e750..fd2d74d0491e 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -200,6 +200,8 @@ CONFIG_SENSORS_INA2XX=m
CONFIG_THERMAL=y
CONFIG_THERMAL_EMULATION=y
CONFIG_EXYNOS_THERMAL=y
+CONFIG_WATCHDOG=y
+CONFIG_RENESAS_WDT=y
CONFIG_MFD_SPMI_PMIC=y
CONFIG_MFD_SEC_CORE=y
CONFIG_MFD_HI655X_PMIC=y
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 7a09c48c0475..579b6e654f2d 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
#define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12))
#endif
-#ifdef CONFIG_COMPAT
-
#ifdef __AARCH64EB__
#define COMPAT_ELF_PLATFORM ("v8b")
#else
#define COMPAT_ELF_PLATFORM ("v8l")
#endif
+#ifdef CONFIG_COMPAT
+
#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3)
/* AArch32 registers. */
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c8120c..da84645525b9 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
#endif /* !__ASSEMBLY__ */
/*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
*
* General purpose regs:
* r0-r30: 64 bit
* sp,pc : 64 bit
- * pstate : 64 bit
- * Total: 34
+ * pstate : 32 bit
+ * Total: 33 + 1
* FPU regs:
* f0-f31: 128 bit
- * Total: 32
- * Extra regs
* fpsr & fpcr: 32 bit
- * Total: 2
+ * Total: 32 + 2
*
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
*/
-#define _GP_REGS 34
+#define _GP_REGS 33
#define _FP_REGS 32
-#define _EXTRA_REGS 2
+#define _EXTRA_REGS 3
/*
* general purpose registers size in bytes.
* pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e63d23bad36e..49095fc4b482 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -43,6 +43,8 @@
#define KVM_VCPU_MAX_FEATURES 4
+#define KVM_REQ_VCPU_EXIT 8
+
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
int kvm_arch_dev_ioctl_check_extension(long ext);
@@ -327,6 +329,10 @@ static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
+void kvm_arm_halt_guest(struct kvm *kvm);
+void kvm_arm_resume_guest(struct kvm *kvm);
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu);
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu);
u64 __kvm_call_hyp(void *hypfn, ...);
#define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__)
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
index fe612a962576..75ea42079757 100644
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -30,6 +30,9 @@ struct kvm_decode {
bool sign_extend;
};
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
phys_addr_t fault_ipa);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 72a3025bb583..31b73227b41f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -55,8 +55,9 @@
#define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
/*
- * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * PAGE_OFFSET - the virtual address of the start of the linear map (top
* (VA_BITS - 1))
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image
* VA_BITS - the maximum number of bits for virtual addresses.
* VA_START - the first kernel virtual address.
* TASK_SIZE - the maximum size of a user space task.
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 17b45f7d96d3..8472c6def5ef 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -23,16 +23,8 @@
/* PAGE_SHIFT determines the page size */
/* CONT_SHIFT determines the number of pages which can be tracked together */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define PAGE_SHIFT 16
-#define CONT_SHIFT 5
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define PAGE_SHIFT 14
-#define CONT_SHIFT 7
-#else
-#define PAGE_SHIFT 12
-#define CONT_SHIFT 4
-#endif
+#define PAGE_SHIFT CONFIG_ARM64_PAGE_SHIFT
+#define CONT_SHIFT CONFIG_ARM64_CONT_SHIFT
#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585d085a..d25f4f137c2a 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
#define check_pgt_cache() do { } while (0)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
#if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e50405274..022644704a93 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
cpu_park_loop();
}
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
#endif /* ifndef __ASSEMBLY__ */
#endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682bfe002..e875a5a551d7 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
unsigned int tmp;
arch_spinlock_t lockval;
+ u32 owner;
+
+ /*
+ * Ensure prior spin_lock operations to other locks have completed
+ * on this CPU before we test whether "lock" is locked.
+ */
+ smp_mb();
+ owner = READ_ONCE(lock->owner) << 16;
asm volatile(
" sevl\n"
"1: wfe\n"
"2: ldaxr %w0, %2\n"
+ /* Is the lock free? */
" eor %w1, %w0, %w0, ror #16\n"
-" cbnz %w1, 1b\n"
+" cbz %w1, 3f\n"
+ /* Lock taken -- has there been a subsequent unlock->lock transition? */
+" eor %w1, %w3, %w0, lsl #16\n"
+" cbz %w1, 1b\n"
+ /*
+ * The owner has been updated, so there was an unlock->lock
+ * transition that we missed. That means we can rely on the
+ * store-release of the unlock operation paired with the
+ * load-acquire of the lock operation to publish any of our
+ * previous stores to the new lock owner and therefore don't
+ * need to bother with the writeback below.
+ */
+" b 4f\n"
+"3:\n"
+ /*
+ * Serialise against any concurrent lockers by writing back the
+ * unlocked lock value
+ */
ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
" stxr %w1, %w0, %2\n"
-" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */
- /* LSE atomics */
" nop\n"
-" nop\n")
+" nop\n",
+ /* LSE atomics */
+" mov %w1, %w0\n"
+" cas %w0, %w0, %2\n"
+" eor %w1, %w1, %w0\n")
+ /* Somebody else wrote to the lock, GOTO 10 and reload the value */
+" cbnz %w1, 2b\n"
+"4:"
: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
- :
+ : "r" (owner)
: "memory");
}
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
+ smp_mb(); /* See arch_spin_unlock_wait */
return !arch_spin_value_unlocked(READ_ONCE(*lock));
}
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 0685d74572af..9e397a542756 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -81,19 +81,6 @@ static inline void set_fs(mm_segment_t fs)
#define segment_eq(a, b) ((a) == (b))
/*
- * Return 1 if addr < current->addr_limit, 0 otherwise.
- */
-#define __addr_ok(addr) \
-({ \
- unsigned long flag; \
- asm("cmp %1, %0; cset %0, lo" \
- : "=&r" (flag) \
- : "r" (addr), "0" (current_thread_info()->addr_limit) \
- : "cc"); \
- flag; \
-})
-
-/*
* Test whether a block of memory is a valid user space address.
* Returns 1 if the range is valid, 0 otherwise.
*
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 41e58fe3c041..e78ac26324bd 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
#define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2)
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5)
-#define __NR_compat_syscalls 390
+#define __NR_compat_syscalls 394
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5b925b761a2a..b7e8ef16ff0d 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -801,6 +801,14 @@ __SYSCALL(__NR_execveat, compat_sys_execveat)
__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
#define __NR_membarrier 389
__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 390
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 391
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 392
+__SYSCALL(__NR_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 393
+__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h
index 1caadc24e3fe..043d17a21342 100644
--- a/arch/arm64/include/uapi/asm/unistd.h
+++ b/arch/arm64/include/uapi/asm/unistd.h
@@ -13,4 +13,7 @@
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+
+#define __ARCH_WANT_RENAMEAT
+
#include <asm-generic/unistd.h>
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 3808470486f3..c173d329397f 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
#include <linux/bitops.h>
#include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/personality.h>
@@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = {
static int c_show(struct seq_file *m, void *v)
{
int i, j;
+ bool compat = personality(current->personality) == PER_LINUX32;
for_each_online_cpu(i) {
struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v)
* "processor". Give glibc what it expects.
*/
seq_printf(m, "processor\t: %d\n", i);
+ if (compat)
+ seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+ MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
loops_per_jiffy / (500000UL/HZ),
@@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v)
* software which does already (at least for 32-bit).
*/
seq_puts(m, "Features\t:");
- if (personality(current->personality) == PER_LINUX32) {
+ if (compat) {
#ifdef CONFIG_COMPAT
for (j = 0; compat_hwcap_str[j]; j++)
if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d740f4..21ab5df9fa76 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
#include <asm/pgtable.h>
#include <asm/pgtable-hwdef.h>
#include <asm/sections.h>
+#include <asm/smp.h>
#include <asm/suspend.h>
#include <asm/virt.h>
@@ -236,6 +237,11 @@ int swsusp_arch_suspend(void)
unsigned long flags;
struct sleep_stack_data state;
+ if (cpus_are_stuck_in_kernel()) {
+ pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+ return -EBUSY;
+ }
+
local_dbg_save(flags);
if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b67531a13136..b5f063e5eff7 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
{ "x30", 8, offsetof(struct pt_regs, regs[30])},
{ "sp", 8, offsetof(struct pt_regs, sp)},
{ "pc", 8, offsetof(struct pt_regs, pc)},
- { "pstate", 8, offsetof(struct pt_regs, pstate)},
+ /*
+ * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote
+ * protocol disagrees. Therefore we must extract only the lower
+ * 32-bits. Look for the big comment in asm/kgdb.h for more
+ * detail.
+ */
+ { "pstate", 4, offsetof(struct pt_regs, pstate)
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ + 4
+#endif
+ },
{ "v0", 16, -1 },
{ "v1", 16, -1 },
{ "v2", 16, -1 },
@@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
memset((char *)gdb_regs, 0, NUMREGBYTES);
thread_regs = task_pt_regs(task);
memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+ /* Special case for PSTATE (check comments in asm/kgdb.h for details) */
+ dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs);
}
void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 32c3c6e70119..713ca824f266 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -31,7 +31,7 @@ struct frame_tail {
*/
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
- struct perf_callchain_entry *entry)
+ struct perf_callchain_entry_ctx *entry)
{
struct frame_tail buftail;
unsigned long err;
@@ -76,7 +76,7 @@ struct compat_frame_tail {
static struct compat_frame_tail __user *
compat_user_backtrace(struct compat_frame_tail __user *tail,
- struct perf_callchain_entry *entry)
+ struct perf_callchain_entry_ctx *entry)
{
struct compat_frame_tail buftail;
unsigned long err;
@@ -106,7 +106,7 @@ compat_user_backtrace(struct compat_frame_tail __user *tail,
}
#endif /* CONFIG_COMPAT */
-void perf_callchain_user(struct perf_callchain_entry *entry,
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
@@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
tail = (struct frame_tail __user *)regs->regs[29];
- while (entry->nr < sysctl_perf_event_max_stack &&
+ while (entry->nr < entry->max_stack &&
tail && !((unsigned long)tail & 0xf))
tail = user_backtrace(tail, entry);
} else {
@@ -132,7 +132,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
- while ((entry->nr < sysctl_perf_event_max_stack) &&
+ while ((entry->nr < entry->max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = compat_user_backtrace(tail, entry);
#endif
@@ -146,12 +146,12 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
*/
static int callchain_trace(struct stackframe *frame, void *data)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, frame->pc);
return 0;
}
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
struct stackframe frame;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e0842cb3b..62ff3c0622e2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ int any_cpu = raw_smp_processor_id();
+
+ if (cpu_ops[any_cpu]->cpu_die)
+ return true;
+#endif
+ return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+ bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+ return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c5392081b49b..2a43012616b7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
/*
* We need to switch to kernel mode so that we can use __get_user
- * to safely read from kernel space. Note that we now dump the
- * code first, just in case the backtrace kills us.
+ * to safely read from kernel space.
*/
fs = get_fs();
set_fs(KERNEL_DS);
@@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where)
print_ip_sym(where);
}
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
{
unsigned long addr = instruction_pointer(regs);
- mm_segment_t fs;
char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
int i;
- /*
- * We need to switch to kernel mode so that we can use __get_user
- * to safely read from kernel space. Note that we now dump the
- * code first, just in case the backtrace kills us.
- */
- fs = get_fs();
- set_fs(KERNEL_DS);
-
for (i = -4; i < 1; i++) {
unsigned int val, bad;
@@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
}
}
printk("%sCode: %s\n", lvl, str);
+}
- set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+ if (!user_mode(regs)) {
+ mm_segment_t fs = get_fs();
+ set_fs(KERNEL_DS);
+ __dump_instr(lvl, regs);
+ set_fs(fs);
+ } else {
+ __dump_instr(lvl, regs);
+ }
}
static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
@@ -477,8 +477,9 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
void __user *pc = (void __user *)instruction_pointer(regs);
console_verbose();
- pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
- handler[reason], esr, esr_get_class_string(esr));
+ pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
+ handler[reason], smp_processor_id(), esr,
+ esr_get_class_string(esr));
__show_regs(regs);
info.si_signo = SIGILL;
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index aa2e34e99582..c4f26ef91e77 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -54,6 +54,13 @@ config KVM_ARM_PMU
Adds support for a virtual Performance Monitoring Unit (PMU) in
virtual machines.
+config KVM_NEW_VGIC
+ bool "New VGIC implementation"
+ depends on KVM
+ default y
+ ---help---
+ uses the new VGIC implementation
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 122cff482ac4..a7a958ca29d5 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -20,10 +20,22 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o
kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
+ifeq ($(CONFIG_KVM_NEW_VGIC),y)
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o
+else
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
+endif
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index fff7cd42b3a3..5f8f80b4a224 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -169,7 +169,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
* Make sure stores to the GIC via the memory mapped interface
* are now visible to the system register interface.
*/
- dsb(st);
+ if (!cpu_if->vgic_sre)
+ dsb(st);
cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2);
@@ -190,12 +191,11 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
continue;
- if (cpu_if->vgic_elrsr & (1 << i)) {
+ if (cpu_if->vgic_elrsr & (1 << i))
cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
- continue;
- }
+ else
+ cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
- cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
__gic_v3_set_lr(0, i);
}
@@ -236,8 +236,12 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
val = read_gicreg(ICC_SRE_EL2);
write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
- isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
- write_gicreg(1, ICC_SRE_EL1);
+
+ if (!cpu_if->vgic_sre) {
+ /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
+ isb();
+ write_gicreg(1, ICC_SRE_EL1);
+ }
}
void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
@@ -256,8 +260,10 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
* been actually programmed with the value we want before
* starting to mess with the rest of the GIC.
*/
- write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
- isb();
+ if (!cpu_if->vgic_sre) {
+ write_gicreg(0, ICC_SRE_EL1);
+ isb();
+ }
val = read_gicreg(ICH_VTR_EL2);
max_lr_idx = vtr_to_max_lr_idx(val);
@@ -306,18 +312,18 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
* (re)distributors. This ensure the guest will read the
* correct values from the memory-mapped interface.
*/
- isb();
- dsb(sy);
+ if (!cpu_if->vgic_sre) {
+ isb();
+ dsb(sy);
+ }
vcpu->arch.vgic_cpu.live_lrs = live_lrs;
/*
* Prevent the guest from touching the GIC system registers if
* SRE isn't enabled for GICv3 emulation.
*/
- if (!cpu_if->vgic_sre) {
- write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
- ICC_SRE_EL2);
- }
+ write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
+ ICC_SRE_EL2);
}
void __hyp_text __vgic_v3_init_lrs(void)
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 4d1ac81870d2..e9e0e6db73f6 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -162,7 +162,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
if (!is_iabt)
- esr |= ESR_ELx_EC_DABT_LOW;
+ esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7bbe3ff02602..a57d650f552c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -134,6 +134,17 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
return true;
}
+static bool access_gic_sre(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write)
+ return ignore_write(vcpu, p);
+
+ p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+ return true;
+}
+
static bool trap_raz_wi(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
@@ -958,7 +969,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
access_gic_sgi },
/* ICC_SRE_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
- trap_raz_wi },
+ access_gic_sre },
/* CONTEXTIDR_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b397802088..efcf1f7ef1e4 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
&asid_generation);
flush_context(cpu);
- /* We have at least 1 ASID per CPU, so this will always succeed */
+ /* We have more ASIDs than CPUs, so this will always succeed */
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
set_asid:
@@ -227,8 +227,11 @@ switch_mm_fastpath:
static int asids_init(void)
{
asid_bits = get_cpu_asid_bits();
- /* If we end up with more CPUs than ASIDs, expect things to crash */
- WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+ /*
+ * Expect allocation after rollover to fail if we don't have at least
+ * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+ */
+ WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
atomic64_set(&asid_generation, ASID_FIRST_VERSION);
asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
GFP_KERNEL);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 8404190fe2bd..ccfde237d6e6 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -150,6 +150,7 @@ static const struct prot_bits pte_bits[] = {
struct pg_level {
const struct prot_bits *bits;
+ const char *name;
size_t num;
u64 mask;
};
@@ -157,15 +158,19 @@ struct pg_level {
static struct pg_level pg_level[] = {
{
}, { /* pgd */
+ .name = "PGD",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
}, { /* pud */
+ .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
}, { /* pmd */
+ .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
}, { /* pte */
+ .name = "PTE",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
},
@@ -214,7 +219,8 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
delta >>= 10;
unit++;
}
- seq_printf(st->seq, "%9lu%c", delta, *unit);
+ seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+ pg_level[st->level].name);
if (pg_level[st->level].bits)
dump_prot(st, pg_level[st->level].bits,
pg_level[st->level].num);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5954881a35ac..013e2cbe7924 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
* PTE_RDONLY is cleared by default in the asm below, so set it in
* back if necessary (read-only or clean PTE).
*/
- if (!pte_write(entry) || !dirty)
+ if (!pte_write(entry) || !pte_sw_dirty(entry))
pte_val(entry) |= PTE_RDONLY;
/*
@@ -441,7 +441,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
return 1;
}
-static struct fault_info {
+static const struct fault_info {
int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
int sig;
int code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea8ce68..43a76b07eb32 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
{
struct page *page = pte_page(pte);
- /* no flushing needed for anonymous pages */
- if (!page_mapping(page))
- return;
-
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
sync_icache_aliases(page_address(page),
PAGE_SIZE << compound_order(page));
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index aa8aee7d6929..2e49bd252fe7 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,6 +306,10 @@ static __init int setup_hugepagesz(char *opt)
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+ } else if (ps == (PAGE_SIZE * CONT_PTES)) {
+ hugetlb_add_hstate(CONT_PTE_SHIFT);
+ } else if (ps == (PMD_SIZE * CONT_PMDS)) {
+ hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -314,3 +318,13 @@ static __init int setup_hugepagesz(char *opt)
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+ if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+ hugetlb_add_hstate(CONT_PMD_SHIFT);
+ return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h
index 1aba19d68c5e..db039cb368be 100644
--- a/arch/avr32/include/asm/pgalloc.h
+++ b/arch/avr32/include/asm/pgalloc.h
@@ -43,7 +43,7 @@ static inline void pgd_ctor(void *x)
*/
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
- return quicklist_alloc(QUICK_PGD, GFP_KERNEL | __GFP_REPEAT, pgd_ctor);
+ return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor);
}
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -54,7 +54,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+ return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -63,7 +63,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
struct page *page;
void *pg;
- pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+ pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
if (!pg)
return NULL;
diff --git a/arch/c6x/include/uapi/asm/unistd.h b/arch/c6x/include/uapi/asm/unistd.h
index e7d09a614d10..12d73d9d81f5 100644
--- a/arch/c6x/include/uapi/asm/unistd.h
+++ b/arch/c6x/include/uapi/asm/unistd.h
@@ -14,6 +14,7 @@
* more details.
*/
+#define __ARCH_WANT_RENAMEAT
#define __ARCH_WANT_SYS_CLONE
/* Use the standard ABI for syscalls. */
diff --git a/arch/cris/arch-v32/drivers/mach-a3/nandflash.c b/arch/cris/arch-v32/drivers/mach-a3/nandflash.c
index 5aa3f5162310..3f646c787e58 100644
--- a/arch/cris/arch-v32/drivers/mach-a3/nandflash.c
+++ b/arch/cris/arch-v32/drivers/mach-a3/nandflash.c
@@ -157,6 +157,7 @@ struct mtd_info *__init crisv32_nand_flash_probe(void)
/* 20 us command delay time */
this->chip_delay = 20;
this->ecc.mode = NAND_ECC_SOFT;
+ this->ecc.algo = NAND_ECC_HAMMING;
/* Enable the following for a flash based bad block table */
/* this->bbt_options = NAND_BBT_USE_FLASH; */
diff --git a/arch/cris/arch-v32/drivers/mach-fs/nandflash.c b/arch/cris/arch-v32/drivers/mach-fs/nandflash.c
index a7c17b0f172a..a74540514bdb 100644
--- a/arch/cris/arch-v32/drivers/mach-fs/nandflash.c
+++ b/arch/cris/arch-v32/drivers/mach-fs/nandflash.c
@@ -148,6 +148,7 @@ struct mtd_info *__init crisv32_nand_flash_probe(void)
/* 20 us command delay time */
this->chip_delay = 20;
this->ecc.mode = NAND_ECC_SOFT;
+ this->ecc.algo = NAND_ECC_HAMMING;
/* Enable the following for a flash based bad block table */
/* this->bbt_options = NAND_BBT_USE_FLASH; */
diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h
index 235ece437ddd..42f1affb9c2d 100644
--- a/arch/cris/include/asm/pgalloc.h
+++ b/arch/cris/include/asm/pgalloc.h
@@ -24,14 +24,14 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
return pte;
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *pte;
- pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+ pte = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
if (!pte)
return NULL;
if (!pgtable_page_ctor(pte)) {
diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 41907d25ed38..c9ed14f6c67d 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -22,7 +22,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE)));
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+ pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
if (pte)
clear_page(pte);
return pte;
@@ -33,9 +33,9 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
struct page *page;
#ifdef CONFIG_HIGHPTE
- page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+ page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
#else
- page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+ page = alloc_pages(GFP_KERNEL, 0);
#endif
if (!page)
return NULL;
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index aa232de2d4bc..3ae852507e57 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -20,6 +20,7 @@ config H8300
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZO
select HAVE_ARCH_KGDB
+ select HAVE_ARCH_HASH
select CPU_NO_EFFICIENT_FFS
config RWSEM_GENERIC_SPINLOCK
diff --git a/arch/h8300/boot/compressed/Makefile b/arch/h8300/boot/compressed/Makefile
index 7643633f1330..613bfe6f5272 100644
--- a/arch/h8300/boot/compressed/Makefile
+++ b/arch/h8300/boot/compressed/Makefile
@@ -23,7 +23,6 @@ LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -estartup -T $(obj)/vmlinux.lds \
$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE
$(call if_changed,ld)
- @:
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
diff --git a/arch/h8300/include/asm/hash.h b/arch/h8300/include/asm/hash.h
new file mode 100644
index 000000000000..04cfbd2bd850
--- /dev/null
+++ b/arch/h8300/include/asm/hash.h
@@ -0,0 +1,53 @@
+#ifndef _ASM_HASH_H
+#define _ASM_HASH_H
+
+/*
+ * The later H8SX models have a 32x32-bit multiply, but the H8/300H
+ * and H8S have only 16x16->32. Since it's tolerably compact, this is
+ * basically an inlined version of the __mulsi3 code. Since the inputs
+ * are not expected to be small, it's also simplfied by skipping the
+ * early-out checks.
+ *
+ * (Since neither CPU has any multi-bit shift instructions, a
+ * shift-and-add version is a non-starter.)
+ *
+ * TODO: come up with an arch-specific version of the hashing in fs/namei.c,
+ * since that is heavily dependent on rotates. Which, as mentioned, suck
+ * horribly on H8.
+ */
+
+#if defined(CONFIG_CPU_H300H) || defined(CONFIG_CPU_H8S)
+
+#define HAVE_ARCH__HASH_32 1
+
+/*
+ * Multiply by k = 0x61C88647. Fitting this into three registers requires
+ * one extra instruction, but reducing register pressure will probably
+ * make that back and then some.
+ *
+ * GCC asm note: %e1 is the high half of operand %1, while %f1 is the
+ * low half. So if %1 is er4, then %e1 is e4 and %f1 is r4.
+ *
+ * This has been designed to modify x in place, since that's the most
+ * common usage, but preserve k, since hash_64() makes two calls in
+ * quick succession.
+ */
+static inline u32 __attribute_const__ __hash_32(u32 x)
+{
+ u32 temp;
+
+ asm( "mov.w %e1,%f0"
+ "\n mulxu.w %f2,%0" /* klow * xhigh */
+ "\n mov.w %f0,%e1" /* The extra instruction */
+ "\n mov.w %f1,%f0"
+ "\n mulxu.w %e2,%0" /* khigh * xlow */
+ "\n add.w %e1,%f0"
+ "\n mulxu.w %f2,%1" /* klow * xlow */
+ "\n add.w %f0,%e1"
+ : "=&r" (temp), "=r" (x)
+ : "%r" (GOLDEN_RATIO_32), "1" (x));
+ return x;
+}
+
+#endif
+#endif /* _ASM_HASH_H */
diff --git a/arch/h8300/include/uapi/asm/unistd.h b/arch/h8300/include/uapi/asm/unistd.h
index 7a2eb698def3..7dd20ef7625a 100644
--- a/arch/h8300/include/uapi/asm/unistd.h
+++ b/arch/h8300/include/uapi/asm/unistd.h
@@ -1,3 +1,5 @@
#define __ARCH_NOMMU
+#define __ARCH_WANT_RENAMEAT
+
#include <asm-generic/unistd.h>
diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h
index 77da3b0ae3c2..eeebf862c46c 100644
--- a/arch/hexagon/include/asm/pgalloc.h
+++ b/arch/hexagon/include/asm/pgalloc.h
@@ -64,7 +64,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
{
struct page *pte;
- pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ pte = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!pte)
return NULL;
if (!pgtable_page_ctor(pte)) {
@@ -78,7 +78,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+ gfp_t flags = GFP_KERNEL | __GFP_ZERO;
return (pte_t *) __get_free_page(flags);
}
diff --git a/arch/hexagon/include/uapi/asm/unistd.h b/arch/hexagon/include/uapi/asm/unistd.h
index ffee405d6803..21517600432b 100644
--- a/arch/hexagon/include/uapi/asm/unistd.h
+++ b/arch/hexagon/include/uapi/asm/unistd.h
@@ -27,6 +27,7 @@
*/
#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
#define __ARCH_WANT_SYS_EXECVE
#define __ARCH_WANT_SYS_CLONE
#define __ARCH_WANT_SYS_VFORK
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index f80758cb7157..e109ee95e919 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -45,7 +45,7 @@ config IA64
select GENERIC_SMP_IDLE_THREAD
select ARCH_INIT_TASK
select ARCH_TASK_STRUCT_ALLOCATOR
- select ARCH_THREAD_INFO_ALLOCATOR
+ select ARCH_THREAD_STACK_ALLOCATOR
select ARCH_CLOCKSOURCE_DATA
select GENERIC_TIME_VSYSCALL_OLD
select SYSCTL_ARCH_UNALIGN_NO_WARN
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index 970d0bd99621..c100d780f1eb 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -95,8 +95,8 @@ define archhelp
echo '* unwcheck - Check vmlinux for invalid unwind info'
endef
-archprepare: make_nr_irqs_h FORCE
-PHONY += make_nr_irqs_h FORCE
+archprepare: make_nr_irqs_h
+PHONY += make_nr_irqs_h
-make_nr_irqs_h: FORCE
+make_nr_irqs_h:
$(Q)$(MAKE) $(build)=arch/ia64/kernel include/generated/nr-irqs.h
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index aa995b67c3f5..d1212b84fb83 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -48,15 +48,15 @@ struct thread_info {
#ifndef ASM_OFFSETS_C
/* how to get the thread information struct from C */
#define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE))
-#define alloc_thread_info_node(tsk, node) \
- ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
+#define alloc_thread_stack_node(tsk, node) \
+ ((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE))
#define task_thread_info(tsk) ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
#else
#define current_thread_info() ((struct thread_info *) 0)
-#define alloc_thread_info_node(tsk, node) ((struct thread_info *) 0)
+#define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0)
#define task_thread_info(tsk) ((struct thread_info *) 0)
#endif
-#define free_thread_info(ti) /* nothing */
+#define free_thread_stack(ti) /* nothing */
#define task_stack_page(tsk) ((void *)(tsk))
#define __HAVE_THREAD_FUNCTIONS
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index f9efe9739d3f..0eaa89f3defd 100644
--- a/arch/ia64/kernel/init_task.c
+++ b/arch/ia64/kernel/init_task.c
@@ -26,6 +26,7 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
* handled. This is done by having a special ".data..init_task" section...
*/
#define init_thread_info init_task_mem.s.thread_info
+#define init_stack init_task_mem.stack
union {
struct {
diff --git a/arch/m32r/boot/compressed/Makefile b/arch/m32r/boot/compressed/Makefile
index 01729c2979ba..0606a727aab2 100644
--- a/arch/m32r/boot/compressed/Makefile
+++ b/arch/m32r/boot/compressed/Makefile
@@ -19,7 +19,6 @@ LDFLAGS_vmlinux := -T
$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS) $(obj)/piggy.o FORCE
$(call if_changed,ld)
- @:
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 8ace920ca24a..967260f2eb1c 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -41,6 +41,7 @@ config M68000
select CPU_HAS_NO_UNALIGNED
select GENERIC_CSUM
select CPU_NO_EFFICIENT_FFS
+ select HAVE_ARCH_HASH
help
The Freescale (was Motorola) 68000 CPU is the first generation of
the well known M68K family of processors. The CPU core as well as
diff --git a/arch/m68k/include/asm/hash.h b/arch/m68k/include/asm/hash.h
new file mode 100644
index 000000000000..6407af84a994
--- /dev/null
+++ b/arch/m68k/include/asm/hash.h
@@ -0,0 +1,59 @@
+#ifndef _ASM_HASH_H
+#define _ASM_HASH_H
+
+/*
+ * If CONFIG_M68000=y (original mc68000/010), this file is #included
+ * to work around the lack of a MULU.L instruction.
+ */
+
+#define HAVE_ARCH__HASH_32 1
+/*
+ * While it would be legal to substitute a different hash operation
+ * entirely, let's keep it simple and just use an optimized multiply
+ * by GOLDEN_RATIO_32 = 0x61C88647.
+ *
+ * The best way to do that appears to be to multiply by 0x8647 with
+ * shifts and adds, and use mulu.w to multiply the high half by 0x61C8.
+ *
+ * Because the 68000 has multi-cycle shifts, this addition chain is
+ * chosen to minimise the shift distances.
+ *
+ * Despite every attempt to spoon-feed it simple operations, GCC
+ * 6.1.1 doggedly insists on doing annoying things like converting
+ * "lsl.l #2,<reg>" (12 cycles) to two adds (8+8 cycles).
+ *
+ * It also likes to notice two shifts in a row, like "a = x << 2" and
+ * "a <<= 7", and convert that to "a = x << 9". But shifts longer
+ * than 8 bits are extra-slow on m68k, so that's a lose.
+ *
+ * Since the 68000 is a very simple in-order processor with no
+ * instruction scheduling effects on execution time, we can safely
+ * take it out of GCC's hands and write one big asm() block.
+ *
+ * Without calling overhead, this operation is 30 bytes (14 instructions
+ * plus one immediate constant) and 166 cycles.
+ *
+ * (Because %2 is fetched twice, it can't be postincrement, and thus it
+ * can't be a fully general "g" or "m". Register is preferred, but
+ * offsettable memory or immediate will work.)
+ */
+static inline u32 __attribute_const__ __hash_32(u32 x)
+{
+ u32 a, b;
+
+ asm( "move.l %2,%0" /* a = x * 0x0001 */
+ "\n lsl.l #2,%0" /* a = x * 0x0004 */
+ "\n move.l %0,%1"
+ "\n lsl.l #7,%0" /* a = x * 0x0200 */
+ "\n add.l %2,%0" /* a = x * 0x0201 */
+ "\n add.l %0,%1" /* b = x * 0x0205 */
+ "\n add.l %0,%0" /* a = x * 0x0402 */
+ "\n add.l %0,%1" /* b = x * 0x0607 */
+ "\n lsl.l #5,%0" /* a = x * 0x8040 */
+ : "=&d,d" (a), "=&r,r" (b)
+ : "r,roi?" (x)); /* a+b = x*0x8647 */
+
+ return ((u16)(x*0x61c8) << 16) + a + b;
+}
+
+#endif /* _ASM_HASH_H */
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index f9924fbcfe42..fb95aed5f428 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -14,7 +14,7 @@ extern const char bad_pmd_string[];
extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- unsigned long page = __get_free_page(GFP_DMA|__GFP_REPEAT);
+ unsigned long page = __get_free_page(GFP_DMA);
if (!page)
return NULL;
@@ -51,7 +51,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
static inline struct page *pte_alloc_one(struct mm_struct *mm,
unsigned long address)
{
- struct page *page = alloc_pages(GFP_DMA|__GFP_REPEAT, 0);
+ struct page *page = alloc_pages(GFP_DMA, 0);
pte_t *pte;
if (!page)
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 24bcba496c75..c895b987202c 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -11,7 +11,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad
{
pte_t *pte;
- pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
if (pte) {
__flush_page_to_ram(pte);
flush_tlb_kernel_page(pte);
@@ -32,7 +32,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres
struct page *page;
pte_t *pte;
- page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+ page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
if(!page)
return NULL;
if (!pgtable_page_ctor(page)) {
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index 0931388de47f..1901f61f926f 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -37,7 +37,7 @@ do { \
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- unsigned long page = __get_free_page(GFP_KERNEL|__GFP_REPEAT);
+ unsigned long page = __get_free_page(GFP_KERNEL);
if (!page)
return NULL;
@@ -49,7 +49,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
unsigned long address)
{
- struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+ struct page *page = alloc_pages(GFP_KERNEL, 0);
if (page == NULL)
return NULL;
diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h
index 3104df0a4822..c2caa1ee4360 100644
--- a/arch/metag/include/asm/pgalloc.h
+++ b/arch/metag/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT |
- __GFP_ZERO);
+ pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
return pte;
}
@@ -51,7 +50,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
unsigned long address)
{
struct page *pte;
- pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+ pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
if (!pte)
return NULL;
if (!pgtable_page_ctor(pte)) {
diff --git a/arch/metag/include/uapi/asm/unistd.h b/arch/metag/include/uapi/asm/unistd.h
index b80b8e899d22..459b6ec15848 100644
--- a/arch/metag/include/uapi/asm/unistd.h
+++ b/arch/metag/include/uapi/asm/unistd.h
@@ -7,6 +7,8 @@
* (at your option) any later version.
*/
+#define __ARCH_WANT_RENAMEAT
+
/* Use the standard ABI for syscalls. */
#include <asm-generic/unistd.h>
diff --git a/arch/metag/kernel/perf_callchain.c b/arch/metag/kernel/perf_callchain.c
index 252abc12a5a3..3e8e048040df 100644
--- a/arch/metag/kernel/perf_callchain.c
+++ b/arch/metag/kernel/perf_callchain.c
@@ -29,7 +29,7 @@ static bool is_valid_call(unsigned long calladdr)
static struct metag_frame __user *
user_backtrace(struct metag_frame __user *user_frame,
- struct perf_callchain_entry *entry)
+ struct perf_callchain_entry_ctx *entry)
{
struct metag_frame frame;
unsigned long calladdr;
@@ -56,7 +56,7 @@ user_backtrace(struct metag_frame __user *user_frame,
}
void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
unsigned long sp = regs->ctx.AX[0].U0;
struct metag_frame __user *frame;
@@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
--frame;
- while ((entry->nr < sysctl_perf_event_max_stack) && frame)
+ while ((entry->nr < entry->max_stack) && frame)
frame = user_backtrace(frame, entry);
}
@@ -78,13 +78,13 @@ static int
callchain_trace(struct stackframe *fr,
void *data)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, fr->pc);
return 0;
}
void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stackframe fr;
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index f17c3a4fb697..636e0720fb20 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -16,6 +16,7 @@ config MICROBLAZE
select GENERIC_IRQ_SHOW
select GENERIC_PCI_IOMAP
select GENERIC_SCHED_CLOCK
+ select HAVE_ARCH_HASH
select HAVE_ARCH_KGDB
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
diff --git a/arch/microblaze/include/asm/hash.h b/arch/microblaze/include/asm/hash.h
new file mode 100644
index 000000000000..753513ae8cb0
--- /dev/null
+++ b/arch/microblaze/include/asm/hash.h
@@ -0,0 +1,81 @@
+#ifndef _ASM_HASH_H
+#define _ASM_HASH_H
+
+/*
+ * Fortunately, most people who want to run Linux on Microblaze enable
+ * both multiplier and barrel shifter, but omitting them is technically
+ * a supported configuration.
+ *
+ * With just a barrel shifter, we can implement an efficient constant
+ * multiply using shifts and adds. GCC can find a 9-step solution, but
+ * this 6-step solution was found by Yevgen Voronenko's implementation
+ * of the Hcub algorithm at http://spiral.ece.cmu.edu/mcm/gen.html.
+ *
+ * That software is really not designed for a single multiplier this large,
+ * but if you run it enough times with different seeds, it'll find several
+ * 6-shift, 6-add sequences for computing x * 0x61C88647. They are all
+ * c = (x << 19) + x;
+ * a = (x << 9) + c;
+ * b = (x << 23) + a;
+ * return (a<<11) + (b<<6) + (c<<3) - b;
+ * with variations on the order of the final add.
+ *
+ * Without even a shifter, it's hopless; any hash function will suck.
+ */
+
+#if CONFIG_XILINX_MICROBLAZE0_USE_HW_MUL == 0
+
+#define HAVE_ARCH__HASH_32 1
+
+/* Multiply by GOLDEN_RATIO_32 = 0x61C88647 */
+static inline u32 __attribute_const__ __hash_32(u32 a)
+{
+#if CONFIG_XILINX_MICROBLAZE0_USE_BARREL
+ unsigned int b, c;
+
+ /* Phase 1: Compute three intermediate values */
+ b = a << 23;
+ c = (a << 19) + a;
+ a = (a << 9) + c;
+ b += a;
+
+ /* Phase 2: Compute (a << 11) + (b << 6) + (c << 3) - b */
+ a <<= 5;
+ a += b; /* (a << 5) + b */
+ a <<= 3;
+ a += c; /* (a << 8) + (b << 3) + c */
+ a <<= 3;
+ return a - b; /* (a << 11) + (b << 6) + (c << 3) - b */
+#else
+ /*
+ * "This is really going to hurt."
+ *
+ * Without a barrel shifter, left shifts are implemented as
+ * repeated additions, and the best we can do is an optimal
+ * addition-subtraction chain. This one is not known to be
+ * optimal, but at 37 steps, it's decent for a 31-bit multiplier.
+ *
+ * Question: given its size (37*4 = 148 bytes per instance),
+ * and slowness, is this worth having inline?
+ */
+ unsigned int b, c, d;
+
+ b = a << 4; /* 4 */
+ c = b << 1; /* 1 5 */
+ b += a; /* 1 6 */
+ c += b; /* 1 7 */
+ c <<= 3; /* 3 10 */
+ c -= a; /* 1 11 */
+ d = c << 7; /* 7 18 */
+ d += b; /* 1 19 */
+ d <<= 8; /* 8 27 */
+ d += a; /* 1 28 */
+ d <<= 1; /* 1 29 */
+ d += b; /* 1 30 */
+ d <<= 6; /* 6 36 */
+ return d + c; /* 1 37 total instructions*/
+#endif
+}
+
+#endif /* !CONFIG_XILINX_MICROBLAZE0_USE_HW_MUL */
+#endif /* _ASM_HASH_H */
diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index 61436d69775c..7c89390c0c13 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -116,9 +116,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
struct page *ptepage;
#ifdef CONFIG_HIGHPTE
- int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT;
+ int flags = GFP_KERNEL | __GFP_HIGHMEM;
#else
- int flags = GFP_KERNEL | __GFP_REPEAT;
+ int flags = GFP_KERNEL;
#endif
ptepage = alloc_pages(flags, 0);
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index 76ed17b56fea..805ae5d712e8 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -38,6 +38,6 @@
#endif /* __ASSEMBLY__ */
-#define __NR_syscalls 389
+#define __NR_syscalls 392
#endif /* _ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h
index 32850c73be09..a8bd3fa28bc7 100644
--- a/arch/microblaze/include/uapi/asm/unistd.h
+++ b/arch/microblaze/include/uapi/asm/unistd.h
@@ -404,5 +404,8 @@
#define __NR_memfd_create 386
#define __NR_bpf 387
#define __NR_execveat 388
+#define __NR_userfaultfd 389
+#define __NR_membarrier 390
+#define __NR_mlock2 391
#endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index 29c8568ec55c..6b3dd99126d7 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -389,3 +389,6 @@ ENTRY(sys_call_table)
.long sys_memfd_create
.long sys_bpf
.long sys_execveat
+ .long sys_userfaultfd
+ .long sys_membarrier /* 390 */
+ .long sys_mlock2
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4f4520e779a5..eb99fcc76088 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -239,8 +239,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
{
pte_t *pte;
if (mem_init_done) {
- pte = (pte_t *)__get_free_page(GFP_KERNEL |
- __GFP_REPEAT | __GFP_ZERO);
+ pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
} else {
pte = (pte_t *)early_get_page();
if (pte)
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 35654be3f1c0..14cba600da7a 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -48,6 +48,8 @@ static int global_phb_number; /* Global phb counter */
resource_size_t isa_mem_base;
unsigned long isa_io_base;
+EXPORT_SYMBOL(isa_io_base);
+
static int pci_bus_count;
struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 46938847e794..ac91939b9b75 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -398,6 +398,7 @@ config MACH_PISTACHIO
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_SUPPORTS_MIPS_CPS
select SYS_SUPPORTS_MULTITHREADING
+ select SYS_SUPPORTS_RELOCATABLE
select SYS_SUPPORTS_ZBOOT
select SYS_HAS_EARLY_PRINTK
select USE_GENERIC_EARLY_PRINTK_8250
diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi
index 4a9c8f2a72d6..f6ae6ed9c4b1 100644
--- a/arch/mips/boot/dts/ingenic/jz4740.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi
@@ -5,7 +5,7 @@
#size-cells = <1>;
compatible = "ingenic,jz4740";
- cpuintc: interrupt-controller@0 {
+ cpuintc: interrupt-controller {
#address-cells = <0>;
#interrupt-cells = <1>;
interrupt-controller;
diff --git a/arch/mips/boot/dts/ralink/mt7620a.dtsi b/arch/mips/boot/dts/ralink/mt7620a.dtsi
index 08bf24fefe9f..793c0c7ca921 100644
--- a/arch/mips/boot/dts/ralink/mt7620a.dtsi
+++ b/arch/mips/boot/dts/ralink/mt7620a.dtsi
@@ -9,7 +9,7 @@
};
};
- cpuintc: cpuintc@0 {
+ cpuintc: cpuintc {
#address-cells = <0>;
#interrupt-cells = <1>;
interrupt-controller;
diff --git a/arch/mips/boot/dts/ralink/rt2880.dtsi b/arch/mips/boot/dts/ralink/rt2880.dtsi
index 182afde2f2e1..fb2faef0ab79 100644
--- a/arch/mips/boot/dts/ralink/rt2880.dtsi
+++ b/arch/mips/boot/dts/ralink/rt2880.dtsi
@@ -9,7 +9,7 @@
};
};
- cpuintc: cpuintc@0 {
+ cpuintc: cpuintc {
#address-cells = <0>;
#interrupt-cells = <1>;
interrupt-controller;
diff --git a/arch/mips/boot/dts/ralink/rt3050.dtsi b/arch/mips/boot/dts/ralink/rt3050.dtsi
index e3203d414fee..d3cb57f985da 100644
--- a/arch/mips/boot/dts/ralink/rt3050.dtsi
+++ b/arch/mips/boot/dts/ralink/rt3050.dtsi
@@ -9,7 +9,7 @@
};
};
- cpuintc: cpuintc@0 {
+ cpuintc: cpuintc {
#address-cells = <0>;
#interrupt-cells = <1>;
interrupt-controller;
diff --git a/arch/mips/boot/dts/ralink/rt3883.dtsi b/arch/mips/boot/dts/ralink/rt3883.dtsi
index 3b131dd0d5ac..3d6fc9afdaf6 100644
--- a/arch/mips/boot/dts/ralink/rt3883.dtsi
+++ b/arch/mips/boot/dts/ralink/rt3883.dtsi
@@ -9,7 +9,7 @@
};
};
- cpuintc: cpuintc@0 {
+ cpuintc: cpuintc {
#address-cells = <0>;
#interrupt-cells = <1>;
interrupt-controller;
diff --git a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts
index 686ebd11386d..48d21127c3f3 100644
--- a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts
+++ b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts
@@ -10,7 +10,7 @@
reg = <0x0 0x08000000>;
};
- cpuintc: interrupt-controller@0 {
+ cpuintc: interrupt-controller {
#address-cells = <0>;
#interrupt-cells = <1>;
interrupt-controller;
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index dff88aa7e377..33aab89259f3 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -384,7 +384,7 @@ static int octeon_cpu_callback(struct notifier_block *nfb,
{
unsigned int cpu = (unsigned long)hcpu;
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
octeon_update_boot_vector(cpu);
break;
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 6741673c92ca..56584a659183 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -19,6 +19,28 @@
#include <asm/asmmacro-64.h>
#endif
+/*
+ * Helper macros for generating raw instruction encodings.
+ */
+#ifdef CONFIG_CPU_MICROMIPS
+ .macro insn32_if_mm enc
+ .insn
+ .hword ((\enc) >> 16)
+ .hword ((\enc) & 0xffff)
+ .endm
+
+ .macro insn_if_mips enc
+ .endm
+#else
+ .macro insn32_if_mm enc
+ .endm
+
+ .macro insn_if_mips enc
+ .insn
+ .word (\enc)
+ .endm
+#endif
+
#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
.macro local_irq_enable reg=t0
ei
@@ -341,38 +363,6 @@
.endm
#else
-#ifdef CONFIG_CPU_MICROMIPS
-#define CFC_MSA_INSN 0x587e0056
-#define CTC_MSA_INSN 0x583e0816
-#define LDB_MSA_INSN 0x58000807
-#define LDH_MSA_INSN 0x58000817
-#define LDW_MSA_INSN 0x58000827
-#define LDD_MSA_INSN 0x58000837
-#define STB_MSA_INSN 0x5800080f
-#define STH_MSA_INSN 0x5800081f
-#define STW_MSA_INSN 0x5800082f
-#define STD_MSA_INSN 0x5800083f
-#define COPY_SW_MSA_INSN 0x58b00056
-#define COPY_SD_MSA_INSN 0x58b80056
-#define INSERT_W_MSA_INSN 0x59300816
-#define INSERT_D_MSA_INSN 0x59380816
-#else
-#define CFC_MSA_INSN 0x787e0059
-#define CTC_MSA_INSN 0x783e0819
-#define LDB_MSA_INSN 0x78000820
-#define LDH_MSA_INSN 0x78000821
-#define LDW_MSA_INSN 0x78000822
-#define LDD_MSA_INSN 0x78000823
-#define STB_MSA_INSN 0x78000824
-#define STH_MSA_INSN 0x78000825
-#define STW_MSA_INSN 0x78000826
-#define STD_MSA_INSN 0x78000827
-#define COPY_SW_MSA_INSN 0x78b00059
-#define COPY_SD_MSA_INSN 0x78b80059
-#define INSERT_W_MSA_INSN 0x79300819
-#define INSERT_D_MSA_INSN 0x79380819
-#endif
-
/*
* Temporary until all toolchains in use include MSA support.
*/
@@ -380,8 +370,8 @@
.set push
.set noat
SET_HARDFLOAT
- .insn
- .word CFC_MSA_INSN | (\cs << 11)
+ insn_if_mips 0x787e0059 | (\cs << 11)
+ insn32_if_mm 0x587e0056 | (\cs << 11)
move \rd, $1
.set pop
.endm
@@ -391,7 +381,8 @@
.set noat
SET_HARDFLOAT
move $1, \rs
- .word CTC_MSA_INSN | (\cd << 6)
+ insn_if_mips 0x783e0819 | (\cd << 6)
+ insn32_if_mm 0x583e0816 | (\cd << 6)
.set pop
.endm
@@ -400,7 +391,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word LDB_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000820 | (\wd << 6)
+ insn32_if_mm 0x58000807 | (\wd << 6)
.set pop
.endm
@@ -409,7 +401,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word LDH_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000821 | (\wd << 6)
+ insn32_if_mm 0x58000817 | (\wd << 6)
.set pop
.endm
@@ -418,7 +411,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word LDW_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000822 | (\wd << 6)
+ insn32_if_mm 0x58000827 | (\wd << 6)
.set pop
.endm
@@ -427,7 +421,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word LDD_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000823 | (\wd << 6)
+ insn32_if_mm 0x58000837 | (\wd << 6)
.set pop
.endm
@@ -436,7 +431,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word STB_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000824 | (\wd << 6)
+ insn32_if_mm 0x5800080f | (\wd << 6)
.set pop
.endm
@@ -445,7 +441,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word STH_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000825 | (\wd << 6)
+ insn32_if_mm 0x5800081f | (\wd << 6)
.set pop
.endm
@@ -454,7 +451,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word STW_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000826 | (\wd << 6)
+ insn32_if_mm 0x5800082f | (\wd << 6)
.set pop
.endm
@@ -463,7 +461,8 @@
.set noat
SET_HARDFLOAT
PTR_ADDU $1, \base, \off
- .word STD_MSA_INSN | (\wd << 6)
+ insn_if_mips 0x78000827 | (\wd << 6)
+ insn32_if_mm 0x5800083f | (\wd << 6)
.set pop
.endm
@@ -471,8 +470,8 @@
.set push
.set noat
SET_HARDFLOAT
- .insn
- .word COPY_SW_MSA_INSN | (\n << 16) | (\ws << 11)
+ insn_if_mips 0x78b00059 | (\n << 16) | (\ws << 11)
+ insn32_if_mm 0x58b00056 | (\n << 16) | (\ws << 11)
.set pop
.endm
@@ -480,8 +479,8 @@
.set push
.set noat
SET_HARDFLOAT
- .insn
- .word COPY_SD_MSA_INSN | (\n << 16) | (\ws << 11)
+ insn_if_mips 0x78b80059 | (\n << 16) | (\ws << 11)
+ insn32_if_mm 0x58b80056 | (\n << 16) | (\ws << 11)
.set pop
.endm
@@ -489,7 +488,8 @@
.set push
.set noat
SET_HARDFLOAT
- .word INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6)
+ insn_if_mips 0x79300819 | (\n << 16) | (\wd << 6)
+ insn32_if_mm 0x59300816 | (\n << 16) | (\wd << 6)
.set pop
.endm
@@ -497,7 +497,8 @@
.set push
.set noat
SET_HARDFLOAT
- .word INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6)
+ insn_if_mips 0x79380819 | (\n << 16) | (\wd << 6)
+ insn32_if_mm 0x59380816 | (\n << 16) | (\wd << 6)
.set pop
.endm
#endif
diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h
index dbb1eb6e284f..e0fecf206f2c 100644
--- a/arch/mips/include/asm/hazards.h
+++ b/arch/mips/include/asm/hazards.h
@@ -58,8 +58,8 @@
* address of a label as argument to inline assembler. Gas otoh has the
* annoying difference between la and dla which are only usable for 32-bit
* rsp. 64-bit code, so can't be used without conditional compilation.
- * The alterantive is switching the assembler to 64-bit code which happens
- * to work right even for 32-bit code ...
+ * The alternative is switching the assembler to 64-bit code which happens
+ * to work right even for 32-bit code...
*/
#define instruction_hazard() \
do { \
@@ -133,8 +133,8 @@ do { \
* address of a label as argument to inline assembler. Gas otoh has the
* annoying difference between la and dla which are only usable for 32-bit
* rsp. 64-bit code, so can't be used without conditional compilation.
- * The alterantive is switching the assembler to 64-bit code which happens
- * to work right even for 32-bit code ...
+ * The alternative is switching the assembler to 64-bit code which happens
+ * to work right even for 32-bit code...
*/
#define __instruction_hazard() \
do { \
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 6733ac575da4..36a391d289aa 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -74,7 +74,7 @@
#define KVM_GUEST_KUSEG 0x00000000UL
#define KVM_GUEST_KSEG0 0x40000000UL
#define KVM_GUEST_KSEG23 0x60000000UL
-#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0x60000000)
+#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0xe0000000)
#define KVM_GUEST_CPHYSADDR(a) ((_ACAST32_(a)) & 0x1fffffff)
#define KVM_GUEST_CKSEG0ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0)
@@ -338,6 +338,7 @@ struct kvm_mips_tlb {
#define KVM_MIPS_GUEST_TLB_SIZE 64
struct kvm_vcpu_arch {
void *host_ebase, *guest_ebase;
+ int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
unsigned long host_stack;
unsigned long host_gp;
diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
index ca8077afac4a..456ddba152c4 100644
--- a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
@@ -100,7 +100,7 @@ typedef volatile struct au1xxx_ddma_desc {
u32 dscr_nxtptr; /* Next descriptor pointer (mostly) */
/*
* First 32 bytes are HW specific!!!
- * Lets have some SW data following -- make sure it's 32 bytes.
+ * Let's have some SW data following -- make sure it's 32 bytes.
*/
u32 sw_status;
u32 sw_context;
diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1300.h b/arch/mips/include/asm/mach-au1x00/gpio-au1300.h
index ce02894271c6..d607d643b973 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio-au1300.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio-au1300.h
@@ -140,7 +140,7 @@ static inline int au1300_gpio_getinitlvl(unsigned int gpio)
* Cases 1 and 3 are intended for boards which want to provide their own
* GPIO namespace and -operations (i.e. for example you have 8 GPIOs
* which are in part provided by spare Au1300 GPIO pins and in part by
-* an external FPGA but you still want them to be accssible in linux
+* an external FPGA but you still want them to be accessible in linux
* as gpio0-7. The board can of course use the alchemy_gpioX_* functions
* as required).
*/
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
index 466fc85899f4..c4e856f27040 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
@@ -22,7 +22,7 @@ struct bcm63xx_enet_platform_data {
int has_phy_interrupt;
int phy_interrupt;
- /* if has_phy, use autonegociated pause parameters or force
+ /* if has_phy, use autonegotiated pause parameters or force
* them */
int pause_auto;
int pause_rx;
diff --git a/arch/mips/include/asm/mach-ip27/dma-coherence.h b/arch/mips/include/asm/mach-ip27/dma-coherence.h
index 1daa64412569..04d862020ac9 100644
--- a/arch/mips/include/asm/mach-ip27/dma-coherence.h
+++ b/arch/mips/include/asm/mach-ip27/dma-coherence.h
@@ -64,7 +64,7 @@ static inline void plat_post_dma_flush(struct device *dev)
static inline int plat_device_is_coherent(struct device *dev)
{
- return 1; /* IP27 non-cohernet mode is unsupported */
+ return 1; /* IP27 non-coherent mode is unsupported */
}
#endif /* __ASM_MACH_IP27_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-ip32/dma-coherence.h b/arch/mips/include/asm/mach-ip32/dma-coherence.h
index 0a0b0e2ced60..7bdf212587a0 100644
--- a/arch/mips/include/asm/mach-ip32/dma-coherence.h
+++ b/arch/mips/include/asm/mach-ip32/dma-coherence.h
@@ -86,7 +86,7 @@ static inline void plat_post_dma_flush(struct device *dev)
static inline int plat_device_is_coherent(struct device *dev)
{
- return 0; /* IP32 is non-cohernet */
+ return 0; /* IP32 is non-coherent */
}
#endif /* __ASM_MACH_IP32_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
index 398733e3e2cf..7f7b0fc554da 100644
--- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
+++ b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
@@ -27,7 +27,7 @@ struct jz_nand_platform_data {
unsigned char banks[JZ_NAND_NUM_BANKS];
- void (*ident_callback)(struct platform_device *, struct nand_chip *,
+ void (*ident_callback)(struct platform_device *, struct mtd_info *,
struct mtd_partition **, int *num_partitions);
};
diff --git a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
index 7023883ca50f..8e9b022c3594 100644
--- a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
+++ b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
@@ -22,7 +22,7 @@
/*
* during early_printk no ioremap possible at this early stage
- * lets use KSEG1 instead
+ * let's use KSEG1 instead
*/
#define LTQ_ASC0_BASE_ADDR 0x1E100C00
#define LTQ_EARLY_ASC KSEG1ADDR(LTQ_ASC0_BASE_ADDR)
diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h
index f87310755319..17b41bb5991f 100644
--- a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h
+++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h
@@ -75,7 +75,7 @@ extern __iomem void *ltq_cgu_membase;
/*
* during early_printk no ioremap is possible
- * lets use KSEG1 instead
+ * let's use KSEG1 instead
*/
#define LTQ_ASC1_BASE_ADDR 0x1E100C00
#define LTQ_EARLY_ASC KSEG1ADDR(LTQ_ASC1_BASE_ADDR)
diff --git a/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h b/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
index 4431fc54a36c..74230d0ca98b 100644
--- a/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
+++ b/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
@@ -24,7 +24,7 @@ struct temp_range {
u8 level;
};
-#define CONSTANT_SPEED_POLICY 0 /* at constent speed */
+#define CONSTANT_SPEED_POLICY 0 /* at constant speed */
#define STEP_SPEED_POLICY 1 /* use up/down arrays to describe policy */
#define KERNEL_HELPER_POLICY 2 /* kernel as a helper to fan control */
diff --git a/arch/mips/include/asm/mach-malta/kernel-entry-init.h b/arch/mips/include/asm/mach-malta/kernel-entry-init.h
index 0cf8622db27f..ab03eb3fadac 100644
--- a/arch/mips/include/asm/mach-malta/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-malta/kernel-entry-init.h
@@ -56,7 +56,7 @@
(0 << MIPS_SEGCFG_PA_SHIFT) | \
(1 << MIPS_SEGCFG_EU_SHIFT)) << 16)
or t0, t2
- mtc0 t0, $5, 2
+ mtc0 t0, CP0_SEGCTL0
/* SegCtl1 */
li t0, ((MIPS_SEGCFG_MUSUK << MIPS_SEGCFG_AM_SHIFT) | \
@@ -67,7 +67,7 @@
(0 << MIPS_SEGCFG_PA_SHIFT) | \
(1 << MIPS_SEGCFG_EU_SHIFT)) << 16)
ins t0, t1, 16, 3
- mtc0 t0, $5, 3
+ mtc0 t0, CP0_SEGCTL1
/* SegCtl2 */
li t0, ((MIPS_SEGCFG_MUSUK << MIPS_SEGCFG_AM_SHIFT) | \
@@ -77,7 +77,7 @@
(4 << MIPS_SEGCFG_PA_SHIFT) | \
(1 << MIPS_SEGCFG_EU_SHIFT)) << 16)
or t0, t2
- mtc0 t0, $5, 4
+ mtc0 t0, CP0_SEGCTL2
jal mips_ihb
mfc0 t0, $16, 5
diff --git a/arch/mips/include/asm/mips_mt.h b/arch/mips/include/asm/mips_mt.h
index f6ba004a7711..aa4cca060e0a 100644
--- a/arch/mips/include/asm/mips_mt.h
+++ b/arch/mips/include/asm/mips_mt.h
@@ -1,5 +1,5 @@
/*
- * Definitions and decalrations for MIPS MT support that are common between
+ * Definitions and declarations for MIPS MT support that are common between
* the VSMP, and AP/SP kernel models.
*/
#ifndef __ASM_MIPS_MT_H
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 25d01577d0b5..e1ca65c62f6a 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -48,6 +48,9 @@
#define CP0_CONF $3
#define CP0_CONTEXT $4
#define CP0_PAGEMASK $5
+#define CP0_SEGCTL0 $5, 2
+#define CP0_SEGCTL1 $5, 3
+#define CP0_SEGCTL2 $5, 4
#define CP0_WIRED $6
#define CP0_INFO $7
#define CP0_HWRENA $7, 0
@@ -726,6 +729,8 @@
#define MIPS_PWFIELD_PTEI_SHIFT 0
#define MIPS_PWFIELD_PTEI_MASK 0x0000003f
+#define MIPS_PWSIZE_PS_SHIFT 30
+#define MIPS_PWSIZE_PS_MASK 0x40000000
#define MIPS_PWSIZE_GDW_SHIFT 24
#define MIPS_PWSIZE_GDW_MASK 0x3f000000
#define MIPS_PWSIZE_UDW_SHIFT 18
@@ -739,6 +744,12 @@
#define MIPS_PWCTL_PWEN_SHIFT 31
#define MIPS_PWCTL_PWEN_MASK 0x80000000
+#define MIPS_PWCTL_XK_SHIFT 28
+#define MIPS_PWCTL_XK_MASK 0x10000000
+#define MIPS_PWCTL_XS_SHIFT 27
+#define MIPS_PWCTL_XS_MASK 0x08000000
+#define MIPS_PWCTL_XU_SHIFT 26
+#define MIPS_PWCTL_XU_MASK 0x04000000
#define MIPS_PWCTL_DPH_SHIFT 7
#define MIPS_PWCTL_DPH_MASK 0x00000080
#define MIPS_PWCTL_HUGEPG_SHIFT 6
@@ -1046,6 +1057,33 @@ static inline int mm_insn_16bit(u16 insn)
}
/*
+ * Helper macros for generating raw instruction encodings in inline asm.
+ */
+#ifdef CONFIG_CPU_MICROMIPS
+#define _ASM_INSN16_IF_MM(_enc) \
+ ".insn\n\t" \
+ ".hword (" #_enc ")\n\t"
+#define _ASM_INSN32_IF_MM(_enc) \
+ ".insn\n\t" \
+ ".hword ((" #_enc ") >> 16)\n\t" \
+ ".hword ((" #_enc ") & 0xffff)\n\t"
+#else
+#define _ASM_INSN_IF_MIPS(_enc) \
+ ".insn\n\t" \
+ ".word (" #_enc ")\n\t"
+#endif
+
+#ifndef _ASM_INSN16_IF_MM
+#define _ASM_INSN16_IF_MM(_enc)
+#endif
+#ifndef _ASM_INSN32_IF_MM
+#define _ASM_INSN32_IF_MM(_enc)
+#endif
+#ifndef _ASM_INSN_IF_MIPS
+#define _ASM_INSN_IF_MIPS(_enc)
+#endif
+
+/*
* TLB Invalidate Flush
*/
static inline void tlbinvf(void)
@@ -1053,7 +1091,9 @@ static inline void tlbinvf(void)
__asm__ __volatile__(
".set push\n\t"
".set noreorder\n\t"
- ".word 0x42000004\n\t" /* tlbinvf */
+ "# tlbinvf\n\t"
+ _ASM_INSN_IF_MIPS(0x42000004)
+ _ASM_INSN32_IF_MM(0x0000537c)
".set pop");
}
@@ -1274,9 +1314,9 @@ do { \
" .set push \n" \
" .set noat \n" \
" .set mips32r2 \n" \
- " .insn \n" \
" # mfhc0 $1, %1 \n" \
- " .word (0x40410000 | ((%1 & 0x1f) << 11)) \n" \
+ _ASM_INSN_IF_MIPS(0x40410000 | ((%1 & 0x1f) << 11)) \
+ _ASM_INSN32_IF_MM(0x002000f4 | ((%1 & 0x1f) << 16)) \
" move %0, $1 \n" \
" .set pop \n" \
: "=r" (__res) \
@@ -1292,8 +1332,8 @@ do { \
" .set mips32r2 \n" \
" move $1, %0 \n" \
" # mthc0 $1, %1 \n" \
- " .insn \n" \
- " .word (0x40c10000 | ((%1 & 0x1f) << 11)) \n" \
+ _ASM_INSN_IF_MIPS(0x40c10000 | ((%1 & 0x1f) << 11)) \
+ _ASM_INSN32_IF_MM(0x002002f4 | ((%1 & 0x1f) << 16)) \
" .set pop \n" \
: \
: "r" (value), "i" (register)); \
@@ -1743,7 +1783,8 @@ do { \
".set\tpush\n\t" \
".set\tnoat\n\t" \
"# mfgc0\t$1, $%1, %2\n\t" \
- ".word\t(0x40610000 | %1 << 11 | %2)\n\t" \
+ _ASM_INSN_IF_MIPS(0x40610000 | %1 << 11 | %2) \
+ _ASM_INSN32_IF_MM(0x002004fc | %1 << 16 | %2 << 11) \
"move\t%0, $1\n\t" \
".set\tpop" \
: "=r" (__res) \
@@ -1757,7 +1798,8 @@ do { \
".set\tpush\n\t" \
".set\tnoat\n\t" \
"# dmfgc0\t$1, $%1, %2\n\t" \
- ".word\t(0x40610100 | %1 << 11 | %2)\n\t" \
+ _ASM_INSN_IF_MIPS(0x40610100 | %1 << 11 | %2) \
+ _ASM_INSN32_IF_MM(0x582004fc | %1 << 16 | %2 << 11) \
"move\t%0, $1\n\t" \
".set\tpop" \
: "=r" (__res) \
@@ -1770,9 +1812,10 @@ do { \
__asm__ __volatile__( \
".set\tpush\n\t" \
".set\tnoat\n\t" \
- "move\t$1, %0\n\t" \
+ "move\t$1, %z0\n\t" \
"# mtgc0\t$1, $%1, %2\n\t" \
- ".word\t(0x40610200 | %1 << 11 | %2)\n\t" \
+ _ASM_INSN_IF_MIPS(0x40610200 | %1 << 11 | %2) \
+ _ASM_INSN32_IF_MM(0x002006fc | %1 << 16 | %2 << 11) \
".set\tpop" \
: : "Jr" ((unsigned int)(value)), \
"i" (register), "i" (sel)); \
@@ -1783,9 +1826,10 @@ do { \
__asm__ __volatile__( \
".set\tpush\n\t" \
".set\tnoat\n\t" \
- "move\t$1, %0\n\t" \
+ "move\t$1, %z0\n\t" \
"# dmtgc0\t$1, $%1, %2\n\t" \
- ".word\t(0x40610300 | %1 << 11 | %2)\n\t" \
+ _ASM_INSN_IF_MIPS(0x40610300 | %1 << 11 | %2) \
+ _ASM_INSN32_IF_MM(0x582006fc | %1 << 16 | %2 << 11) \
".set\tpop" \
: : "Jr" (value), \
"i" (register), "i" (sel)); \
@@ -2246,7 +2290,6 @@ do { \
#else
-#ifdef CONFIG_CPU_MICROMIPS
#define rddsp(mask) \
({ \
unsigned int __res; \
@@ -2255,8 +2298,8 @@ do { \
" .set push \n" \
" .set noat \n" \
" # rddsp $1, %x1 \n" \
- " .hword ((0x0020067c | (%x1 << 14)) >> 16) \n" \
- " .hword ((0x0020067c | (%x1 << 14)) & 0xffff) \n" \
+ _ASM_INSN_IF_MIPS(0x7c000cb8 | (%x1 << 16)) \
+ _ASM_INSN32_IF_MM(0x0020067c | (%x1 << 14)) \
" move %0, $1 \n" \
" .set pop \n" \
: "=r" (__res) \
@@ -2271,22 +2314,22 @@ do { \
" .set noat \n" \
" move $1, %0 \n" \
" # wrdsp $1, %x1 \n" \
- " .hword ((0x0020167c | (%x1 << 14)) >> 16) \n" \
- " .hword ((0x0020167c | (%x1 << 14)) & 0xffff) \n" \
+ _ASM_INSN_IF_MIPS(0x7c2004f8 | (%x1 << 11)) \
+ _ASM_INSN32_IF_MM(0x0020167c | (%x1 << 14)) \
" .set pop \n" \
: \
: "r" (val), "i" (mask)); \
} while (0)
-#define _umips_dsp_mfxxx(ins) \
+#define _dsp_mfxxx(ins) \
({ \
unsigned long __treg; \
\
__asm__ __volatile__( \
" .set push \n" \
" .set noat \n" \
- " .hword 0x0001 \n" \
- " .hword %x1 \n" \
+ _ASM_INSN_IF_MIPS(0x00000810 | %X1) \
+ _ASM_INSN32_IF_MM(0x0001007c | %x1) \
" move %0, $1 \n" \
" .set pop \n" \
: "=r" (__treg) \
@@ -2294,101 +2337,28 @@ do { \
__treg; \
})
-#define _umips_dsp_mtxxx(val, ins) \
+#define _dsp_mtxxx(val, ins) \
do { \
__asm__ __volatile__( \
" .set push \n" \
" .set noat \n" \
" move $1, %0 \n" \
- " .hword 0x0001 \n" \
- " .hword %x1 \n" \
+ _ASM_INSN_IF_MIPS(0x00200011 | %X1) \
+ _ASM_INSN32_IF_MM(0x0001207c | %x1) \
" .set pop \n" \
: \
: "r" (val), "i" (ins)); \
} while (0)
-#define _umips_dsp_mflo(reg) _umips_dsp_mfxxx((reg << 14) | 0x107c)
-#define _umips_dsp_mfhi(reg) _umips_dsp_mfxxx((reg << 14) | 0x007c)
-
-#define _umips_dsp_mtlo(val, reg) _umips_dsp_mtxxx(val, ((reg << 14) | 0x307c))
-#define _umips_dsp_mthi(val, reg) _umips_dsp_mtxxx(val, ((reg << 14) | 0x207c))
-
-#define mflo0() _umips_dsp_mflo(0)
-#define mflo1() _umips_dsp_mflo(1)
-#define mflo2() _umips_dsp_mflo(2)
-#define mflo3() _umips_dsp_mflo(3)
-
-#define mfhi0() _umips_dsp_mfhi(0)
-#define mfhi1() _umips_dsp_mfhi(1)
-#define mfhi2() _umips_dsp_mfhi(2)
-#define mfhi3() _umips_dsp_mfhi(3)
+#ifdef CONFIG_CPU_MICROMIPS
-#define mtlo0(x) _umips_dsp_mtlo(x, 0)
-#define mtlo1(x) _umips_dsp_mtlo(x, 1)
-#define mtlo2(x) _umips_dsp_mtlo(x, 2)
-#define mtlo3(x) _umips_dsp_mtlo(x, 3)
+#define _dsp_mflo(reg) _dsp_mfxxx((reg << 14) | 0x1000)
+#define _dsp_mfhi(reg) _dsp_mfxxx((reg << 14) | 0x0000)
-#define mthi0(x) _umips_dsp_mthi(x, 0)
-#define mthi1(x) _umips_dsp_mthi(x, 1)
-#define mthi2(x) _umips_dsp_mthi(x, 2)
-#define mthi3(x) _umips_dsp_mthi(x, 3)
+#define _dsp_mtlo(val, reg) _dsp_mtxxx(val, ((reg << 14) | 0x1000))
+#define _dsp_mthi(val, reg) _dsp_mtxxx(val, ((reg << 14) | 0x0000))
#else /* !CONFIG_CPU_MICROMIPS */
-#define rddsp(mask) \
-({ \
- unsigned int __res; \
- \
- __asm__ __volatile__( \
- " .set push \n" \
- " .set noat \n" \
- " # rddsp $1, %x1 \n" \
- " .word 0x7c000cb8 | (%x1 << 16) \n" \
- " move %0, $1 \n" \
- " .set pop \n" \
- : "=r" (__res) \
- : "i" (mask)); \
- __res; \
-})
-
-#define wrdsp(val, mask) \
-do { \
- __asm__ __volatile__( \
- " .set push \n" \
- " .set noat \n" \
- " move $1, %0 \n" \
- " # wrdsp $1, %x1 \n" \
- " .word 0x7c2004f8 | (%x1 << 11) \n" \
- " .set pop \n" \
- : \
- : "r" (val), "i" (mask)); \
-} while (0)
-
-#define _dsp_mfxxx(ins) \
-({ \
- unsigned long __treg; \
- \
- __asm__ __volatile__( \
- " .set push \n" \
- " .set noat \n" \
- " .word (0x00000810 | %1) \n" \
- " move %0, $1 \n" \
- " .set pop \n" \
- : "=r" (__treg) \
- : "i" (ins)); \
- __treg; \
-})
-
-#define _dsp_mtxxx(val, ins) \
-do { \
- __asm__ __volatile__( \
- " .set push \n" \
- " .set noat \n" \
- " move $1, %0 \n" \
- " .word (0x00200011 | %1) \n" \
- " .set pop \n" \
- : \
- : "r" (val), "i" (ins)); \
-} while (0)
#define _dsp_mflo(reg) _dsp_mfxxx((reg << 21) | 0x0002)
#define _dsp_mfhi(reg) _dsp_mfxxx((reg << 21) | 0x0000)
@@ -2396,6 +2366,8 @@ do { \
#define _dsp_mtlo(val, reg) _dsp_mtxxx(val, ((reg << 11) | 0x0002))
#define _dsp_mthi(val, reg) _dsp_mtxxx(val, ((reg << 11) | 0x0000))
+#endif /* CONFIG_CPU_MICROMIPS */
+
#define mflo0() _dsp_mflo(0)
#define mflo1() _dsp_mflo(1)
#define mflo2() _dsp_mflo(2)
@@ -2416,7 +2388,6 @@ do { \
#define mthi2(x) _dsp_mthi(x, 2)
#define mthi3(x) _dsp_mthi(x, 3)
-#endif /* CONFIG_CPU_MICROMIPS */
#endif
/*
@@ -2556,28 +2527,32 @@ static inline void guest_tlb_probe(void)
{
__asm__ __volatile__(
"# tlbgp\n\t"
- ".word 0x42000010");
+ _ASM_INSN_IF_MIPS(0x42000010)
+ _ASM_INSN32_IF_MM(0x0000017c));
}
static inline void guest_tlb_read(void)
{
__asm__ __volatile__(
"# tlbgr\n\t"
- ".word 0x42000009");
+ _ASM_INSN_IF_MIPS(0x42000009)
+ _ASM_INSN32_IF_MM(0x0000117c));
}
static inline void guest_tlb_write_indexed(void)
{
__asm__ __volatile__(
"# tlbgwi\n\t"
- ".word 0x4200000a");
+ _ASM_INSN_IF_MIPS(0x4200000a)
+ _ASM_INSN32_IF_MM(0x0000217c));
}
static inline void guest_tlb_write_random(void)
{
__asm__ __volatile__(
"# tlbgwr\n\t"
- ".word 0x4200000e");
+ _ASM_INSN_IF_MIPS(0x4200000e)
+ _ASM_INSN32_IF_MM(0x0000317c));
}
/*
@@ -2587,7 +2562,8 @@ static inline void guest_tlbinvf(void)
{
__asm__ __volatile__(
"# tlbginvf\n\t"
- ".word 0x4200000c");
+ _ASM_INSN_IF_MIPS(0x4200000c)
+ _ASM_INSN32_IF_MM(0x0000517c));
}
#endif /* !TOOLCHAIN_SUPPORTS_VIRT */
diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h
index 6e4effa6f626..ddf496cb2a2a 100644
--- a/arch/mips/include/asm/msa.h
+++ b/arch/mips/include/asm/msa.h
@@ -192,13 +192,6 @@ static inline void write_msa_##name(unsigned int val) \
* allow compilation with toolchains that do not support MSA. Once all
* toolchains in use support MSA these can be removed.
*/
-#ifdef CONFIG_CPU_MICROMIPS
-#define CFC_MSA_INSN 0x587e0056
-#define CTC_MSA_INSN 0x583e0816
-#else
-#define CFC_MSA_INSN 0x787e0059
-#define CTC_MSA_INSN 0x783e0819
-#endif
#define __BUILD_MSA_CTL_REG(name, cs) \
static inline unsigned int read_msa_##name(void) \
@@ -207,11 +200,12 @@ static inline unsigned int read_msa_##name(void) \
__asm__ __volatile__( \
" .set push\n" \
" .set noat\n" \
- " .insn\n" \
- " .word %1 | (" #cs " << 11)\n" \
+ " # cfcmsa $1, $%1\n" \
+ _ASM_INSN_IF_MIPS(0x787e0059 | %1 << 11) \
+ _ASM_INSN32_IF_MM(0x587e0056 | %1 << 11) \
" move %0, $1\n" \
" .set pop\n" \
- : "=r"(reg) : "i"(CFC_MSA_INSN)); \
+ : "=r"(reg) : "i"(cs)); \
return reg; \
} \
\
@@ -221,10 +215,11 @@ static inline void write_msa_##name(unsigned int val) \
" .set push\n" \
" .set noat\n" \
" move $1, %0\n" \
- " .insn\n" \
- " .word %1 | (" #cs " << 6)\n" \
+ " # ctcmsa $%1, $1\n" \
+ _ASM_INSN_IF_MIPS(0x783e0819 | %1 << 6) \
+ _ASM_INSN32_IF_MM(0x583e0816 | %1 << 6) \
" .set pop\n" \
- : : "r"(val), "i"(CTC_MSA_INSN)); \
+ : : "r"(val), "i"(cs)); \
}
#endif /* !TOOLCHAIN_SUPPORTS_MSA */
diff --git a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
index 8d05d9069823..a07a36f7d814 100644
--- a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
+++ b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
@@ -146,7 +146,7 @@ typedef struct {
* This structure contains the global state of all command queues.
* It is stored in a bootmem named block and shared by all
* applications running on Octeon. Tickets are stored in a differnet
- * cahce line that queue information to reduce the contention on the
+ * cache line that queue information to reduce the contention on the
* ll/sc used to get a ticket. If this is not the case, the update
* of queue state causes the ll/sc to fail quite often.
*/
diff --git a/arch/mips/include/asm/octeon/cvmx-helper-board.h b/arch/mips/include/asm/octeon/cvmx-helper-board.h
index 893320375aef..cda93aee712c 100644
--- a/arch/mips/include/asm/octeon/cvmx-helper-board.h
+++ b/arch/mips/include/asm/octeon/cvmx-helper-board.h
@@ -94,7 +94,7 @@ extern int cvmx_helper_board_get_mii_address(int ipd_port);
* @phy_addr: The address of the PHY to program
* @link_flags:
* Flags to control autonegotiation. Bit 0 is autonegotiation
- * enable/disable to maintain backware compatibility.
+ * enable/disable to maintain backward compatibility.
* @link_info: Link speed to program. If the speed is zero and autonegotiation
* is enabled, all possible negotiation speeds are advertised.
*
diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h
index e13490ebbb27..cbdc14b77435 100644
--- a/arch/mips/include/asm/octeon/cvmx-ipd.h
+++ b/arch/mips/include/asm/octeon/cvmx-ipd.h
@@ -39,7 +39,7 @@
enum cvmx_ipd_mode {
CVMX_IPD_OPC_MODE_STT = 0LL, /* All blocks DRAM, not cached in L2 */
- CVMX_IPD_OPC_MODE_STF = 1LL, /* All bloccks into L2 */
+ CVMX_IPD_OPC_MODE_STF = 1LL, /* All blocks into L2 */
CVMX_IPD_OPC_MODE_STF1_STT = 2LL, /* 1st block L2, rest DRAM */
CVMX_IPD_OPC_MODE_STF2_STT = 3LL /* 1st, 2nd blocks L2, rest DRAM */
};
diff --git a/arch/mips/include/asm/octeon/cvmx-pow.h b/arch/mips/include/asm/octeon/cvmx-pow.h
index 51531563f8dc..410bb70e5aac 100644
--- a/arch/mips/include/asm/octeon/cvmx-pow.h
+++ b/arch/mips/include/asm/octeon/cvmx-pow.h
@@ -2051,7 +2051,7 @@ static inline void cvmx_pow_tag_sw_desched(uint32_t tag,
}
/**
- * Descchedules the current work queue entry.
+ * Deschedules the current work queue entry.
*
* @no_sched: no schedule flag value to be set on the work queue
* entry. If this is set the entry will not be
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index b336037e8768..93c079a1cfc8 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -69,7 +69,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
{
pte_t *pte;
- pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, PTE_ORDER);
+ pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
return pte;
}
@@ -79,7 +79,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
{
struct page *pte;
- pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+ pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
if (!pte)
return NULL;
clear_highpage(pte);
@@ -113,7 +113,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
pmd_t *pmd;
- pmd = (pmd_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PMD_ORDER);
+ pmd = (pmd_t *) __get_free_pages(GFP_KERNEL, PMD_ORDER);
if (pmd)
pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table);
return pmd;
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index a6b611f1da43..f53816744d60 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -24,7 +24,7 @@ struct mm_struct;
struct vm_area_struct;
#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \
- _CACHE_CACHABLE_NONCOHERENT)
+ _page_cachable_default)
#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_WRITE | \
_page_cachable_default)
#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \
@@ -476,7 +476,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
pte.pte_low &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK);
pte.pte_high &= (_PFN_MASK | _CACHE_MASK);
pte.pte_low |= pgprot_val(newprot) & ~_PFNX_MASK;
- pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK;
+ pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK);
return pte;
}
#elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
@@ -491,7 +491,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
#else
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
- return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+ return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
+ (pgprot_val(newprot) & ~_PAGE_CHG_MASK));
}
#endif
@@ -632,7 +633,8 @@ static inline struct page *pmd_page(pmd_t pmd)
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
- pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot);
+ pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) |
+ (pgprot_val(newprot) & ~_PAGE_CHG_MASK);
return pmd;
}
diff --git a/arch/mips/include/asm/sgi/hpc3.h b/arch/mips/include/asm/sgi/hpc3.h
index 4a9c99050c13..c0e3dc0293a7 100644
--- a/arch/mips/include/asm/sgi/hpc3.h
+++ b/arch/mips/include/asm/sgi/hpc3.h
@@ -39,7 +39,7 @@ struct hpc3_pbus_dmacregs {
volatile u32 pbdma_dptr; /* pbus dma channel desc ptr */
u32 _unused0[0x1000/4 - 2]; /* padding */
volatile u32 pbdma_ctrl; /* pbus dma channel control register has
- * copletely different meaning for read
+ * completely different meaning for read
* compared with write */
/* read */
#define HPC3_PDMACTRL_INT 0x00000001 /* interrupt (cleared after read) */
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 4e3f9b7a02e4..258fd03c9ef5 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -48,20 +48,6 @@
#define QI_LB60_GPIO_KEYIN8 JZ_GPIO_PORTD(26)
/* NAND */
-static struct nand_ecclayout qi_lb60_ecclayout_1gb = {
- .eccbytes = 36,
- .eccpos = {
- 6, 7, 8, 9, 10, 11, 12, 13,
- 14, 15, 16, 17, 18, 19, 20, 21,
- 22, 23, 24, 25, 26, 27, 28, 29,
- 30, 31, 32, 33, 34, 35, 36, 37,
- 38, 39, 40, 41
- },
- .oobfree = {
- { .offset = 2, .length = 4 },
- { .offset = 42, .length = 22 }
- },
-};
/* Early prototypes of the QI LB60 had only 1GB of NAND.
* In order to support these devices as well the partition and ecc layout is
@@ -84,25 +70,6 @@ static struct mtd_partition qi_lb60_partitions_1gb[] = {
},
};
-static struct nand_ecclayout qi_lb60_ecclayout_2gb = {
- .eccbytes = 72,
- .eccpos = {
- 12, 13, 14, 15, 16, 17, 18, 19,
- 20, 21, 22, 23, 24, 25, 26, 27,
- 28, 29, 30, 31, 32, 33, 34, 35,
- 36, 37, 38, 39, 40, 41, 42, 43,
- 44, 45, 46, 47, 48, 49, 50, 51,
- 52, 53, 54, 55, 56, 57, 58, 59,
- 60, 61, 62, 63, 64, 65, 66, 67,
- 68, 69, 70, 71, 72, 73, 74, 75,
- 76, 77, 78, 79, 80, 81, 82, 83
- },
- .oobfree = {
- { .offset = 2, .length = 10 },
- { .offset = 84, .length = 44 },
- },
-};
-
static struct mtd_partition qi_lb60_partitions_2gb[] = {
{
.name = "NAND BOOT partition",
@@ -121,19 +88,67 @@ static struct mtd_partition qi_lb60_partitions_2gb[] = {
},
};
+static int qi_lb60_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = 36;
+ oobregion->offset = 6;
+
+ if (mtd->oobsize == 128) {
+ oobregion->length *= 2;
+ oobregion->offset *= 2;
+ }
+
+ return 0;
+}
+
+static int qi_lb60_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ int eccbytes = 36, eccoff = 6;
+
+ if (section > 1)
+ return -ERANGE;
+
+ if (mtd->oobsize == 128) {
+ eccbytes *= 2;
+ eccoff *= 2;
+ }
+
+ if (!section) {
+ oobregion->offset = 2;
+ oobregion->length = eccoff - 2;
+ } else {
+ oobregion->offset = eccoff + eccbytes;
+ oobregion->length = mtd->oobsize - oobregion->offset;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops qi_lb60_ooblayout_ops = {
+ .ecc = qi_lb60_ooblayout_ecc,
+ .free = qi_lb60_ooblayout_free,
+};
+
static void qi_lb60_nand_ident(struct platform_device *pdev,
- struct nand_chip *chip, struct mtd_partition **partitions,
+ struct mtd_info *mtd, struct mtd_partition **partitions,
int *num_partitions)
{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
if (chip->page_shift == 12) {
- chip->ecc.layout = &qi_lb60_ecclayout_2gb;
*partitions = qi_lb60_partitions_2gb;
*num_partitions = ARRAY_SIZE(qi_lb60_partitions_2gb);
} else {
- chip->ecc.layout = &qi_lb60_ecclayout_1gb;
*partitions = qi_lb60_partitions_1gb;
*num_partitions = ARRAY_SIZE(qi_lb60_partitions_1gb);
}
+
+ mtd_set_ooblayout(mtd, &qi_lb60_ooblayout_ops);
}
static struct jz_nand_platform_data qi_lb60_nand_pdata = {
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index ceca6cc41b2b..6dc3f1fdaccc 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -481,7 +481,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
/*
* OK we are here either because we hit a NAL
* instruction or because we are emulating an
- * old bltzal{,l} one. Lets figure out what the
+ * old bltzal{,l} one. Let's figure out what the
* case really is.
*/
if (!insn.i_format.rs) {
@@ -515,7 +515,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
/*
* OK we are here either because we hit a BAL
* instruction or because we are emulating an
- * old bgezal{,l} one. Lets figure out what the
+ * old bgezal{,l} one. Let's figure out what the
* case really is.
*/
if (!insn.i_format.rs) {
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 51b98dc371b3..59476a607add 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -441,6 +441,21 @@ LEAF(mips_cps_boot_vpes)
mfc0 t0, CP0_CONFIG
mttc0 t0, CP0_CONFIG
+ /*
+ * Copy the EVA config from this VPE if the CPU supports it.
+ * CONFIG3 must exist to be running MT startup - just read it.
+ */
+ mfc0 t0, CP0_CONFIG, 3
+ and t0, t0, MIPS_CONF3_SC
+ beqz t0, 3f
+ nop
+ mfc0 t0, CP0_SEGCTL0
+ mttc0 t0, CP0_SEGCTL0
+ mfc0 t0, CP0_SEGCTL1
+ mttc0 t0, CP0_SEGCTL1
+ mfc0 t0, CP0_SEGCTL2
+ mttc0 t0, CP0_SEGCTL2
+3:
/* Ensure no software interrupts are pending */
mttc0 zero, CP0_CAUSE
mttc0 zero, CP0_STATUS
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 5ac5c3e23460..a88d44247cc8 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -833,10 +833,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c)
c->options |= MIPS_CPU_MAAR;
if (config5 & MIPS_CONF5_LLB)
c->options |= MIPS_CPU_RW_LLB;
-#ifdef CONFIG_XPA
if (config5 & MIPS_CONF5_MVH)
- c->options |= MIPS_CPU_XPA;
-#endif
+ c->options |= MIPS_CPU_MVH;
if (cpu_has_mips_r6 && (config5 & MIPS_CONF5_VP))
c->options |= MIPS_CPU_VP;
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index c3c234dc0c07..891f5ee63983 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -88,7 +88,7 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
elf32 = ehdr->e32.e_ident[EI_CLASS] == ELFCLASS32;
flags = elf32 ? ehdr->e32.e_flags : ehdr->e64.e_flags;
- /* Lets see if this is an O32 ELF */
+ /* Let's see if this is an O32 ELF */
if (elf32) {
if (flags & EF_MIPS_FP64) {
/*
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 8eb5af805964..f25f7eab7307 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -54,6 +54,9 @@ void __init init_IRQ(void)
for (i = 0; i < NR_IRQS; i++)
irq_set_noprobe(i);
+ if (cpu_has_veic)
+ clear_c0_status(ST0_IM);
+
arch_init_irq();
}
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index 625ee770b1aa..7ff2a557f4aa 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -2202,7 +2202,7 @@ fpu_emul:
}
/*
- * Lets not return to userland just yet. It's constly and
+ * Let's not return to userland just yet. It's costly and
* it's likely we have more R2 instructions to emulate
*/
if (!err && (pass++ < MIPS_R2_EMUL_TOTAL_PASS)) {
diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index 5021c546ad07..d64056e0bb56 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/arch/mips/kernel/perf_event.c
@@ -25,8 +25,8 @@
* the user stack callchains, we will add it here.
*/
-static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
- unsigned long reg29)
+static void save_raw_perf_callchain(struct perf_callchain_entry_ctx *entry,
+ unsigned long reg29)
{
unsigned long *sp = (unsigned long *)reg29;
unsigned long addr;
@@ -35,14 +35,14 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
addr = *sp++;
if (__kernel_text_address(addr)) {
perf_callchain_store(entry, addr);
- if (entry->nr >= sysctl_perf_event_max_stack)
+ if (entry->nr >= entry->max_stack)
break;
}
}
}
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+ struct pt_regs *regs)
{
unsigned long sp = regs->regs[29];
#ifdef CONFIG_KALLSYMS
@@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
}
do {
perf_callchain_store(entry, pc);
- if (entry->nr >= sysctl_perf_event_max_stack)
+ if (entry->nr >= entry->max_stack)
break;
pc = unwind_stack(current, &sp, pc, &ra);
} while (pc);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 411c971e3417..813ed7829c61 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -345,7 +345,7 @@ static int get_frame_info(struct mips_frame_info *info)
return 0;
if (info->pc_offset < 0) /* leaf */
return 1;
- /* prologue seems boggus... */
+ /* prologue seems bogus... */
err:
return -1;
}
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index ab042291fbfd..ae4231452115 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -770,15 +770,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
sigset_t *oldset = sigmask_to_save();
int ret;
struct mips_abi *abi = current->thread.abi;
-#ifdef CONFIG_CPU_MICROMIPS
- void *vdso;
- unsigned long tmp = (unsigned long)current->mm->context.vdso;
-
- set_isa16_mode(tmp);
- vdso = (void *)tmp;
-#else
void *vdso = current->mm->context.vdso;
-#endif
if (regs->regs[0]) {
switch(regs->regs[2]) {
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 1061bd2e7e9c..4ed36f288d64 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -359,8 +359,12 @@ static void cps_init_secondary(void)
BUG_ON(ident != mips_cm_vp_id(smp_processor_id()));
}
- change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 |
- STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7);
+ if (cpu_has_veic)
+ clear_c0_status(ST0_IM);
+ else
+ change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 |
+ STATUSF_IP4 | STATUSF_IP5 |
+ STATUSF_IP6 | STATUSF_IP7);
}
static void cps_smp_finish(void)
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 396df6eb0a12..645c8a1982a7 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1636,6 +1636,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
if (index < 0) {
vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK);
vcpu->arch.host_cp0_badvaddr = va;
+ vcpu->arch.pc = curr_pc;
er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run,
vcpu);
preempt_enable();
@@ -1647,6 +1648,8 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
* invalid exception to the guest
*/
if (!TLB_IS_VALID(*tlb, va)) {
+ vcpu->arch.host_cp0_badvaddr = va;
+ vcpu->arch.pc = curr_pc;
er = kvm_mips_emulate_tlbinv_ld(cause, NULL,
run, vcpu);
preempt_enable();
@@ -1666,7 +1669,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
cache, op, base, arch->gprs[base], offset);
er = EMULATE_FAIL;
preempt_enable();
- goto dont_update_pc;
+ goto done;
}
@@ -1694,16 +1697,20 @@ skip_fault:
kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
cache, op, base, arch->gprs[base], offset);
er = EMULATE_FAIL;
- preempt_enable();
- goto dont_update_pc;
}
preempt_enable();
+done:
+ /* Rollback PC only if emulation was unsuccessful */
+ if (er == EMULATE_FAIL)
+ vcpu->arch.pc = curr_pc;
dont_update_pc:
- /* Rollback PC */
- vcpu->arch.pc = curr_pc;
-done:
+ /*
+ * This is for exceptions whose emulation updates the PC, so do not
+ * overwrite the PC under any circumstances
+ */
+
return er;
}
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdfad703..2143884709e4 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
#define MIPS_EXC_MAX 12
/* XXXSL More to follow */
+extern char __kvm_mips_vcpu_run_end[];
extern char mips32_exception[], mips32_exceptionEnd[];
extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 3ef03009de5f..828fcfc1cd7f 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1)
/* Jump to guest */
eret
+EXPORT(__kvm_mips_vcpu_run_end)
VECTOR(MIPSX(exception), unknown)
/* Find out what mode we came from and jump to the proper handler. */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index dc052fb5c7a2..44da5259f390 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
memcpy(gebase + offset, mips32_GuestException,
mips32_GuestExceptionEnd - mips32_GuestException);
+#ifdef MODULE
+ offset += mips32_GuestExceptionEnd - mips32_GuestException;
+ memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+ __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+ vcpu->arch.vcpu_run = gebase + offset;
+#else
+ vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
/* Invalidate the icache for these ranges */
local_flush_icache_range((unsigned long)gebase,
(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
@@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
/* Disable hardware page table walking while in guest */
htw_stop();
- r = __kvm_mips_vcpu_run(run, vcpu);
+ r = vcpu->arch.vcpu_run(run, vcpu);
/* Re-enable HTW before enabling interrupts */
htw_start();
diff --git a/arch/mips/lasat/picvue_proc.c b/arch/mips/lasat/picvue_proc.c
index b42095880667..27533c109f92 100644
--- a/arch/mips/lasat/picvue_proc.c
+++ b/arch/mips/lasat/picvue_proc.c
@@ -43,7 +43,7 @@ static int pvc_line_proc_show(struct seq_file *m, void *v)
{
int lineno = *(int *)m->private;
- if (lineno < 0 || lineno > PVC_NLINES) {
+ if (lineno < 0 || lineno >= PVC_NLINES) {
printk(KERN_WARNING "proc_read_line: invalid lineno %d\n", lineno);
return 0;
}
@@ -67,7 +67,7 @@ static ssize_t pvc_line_proc_write(struct file *file, const char __user *buf,
char kbuf[PVC_LINELEN];
size_t len;
- BUG_ON(lineno < 0 || lineno > PVC_NLINES);
+ BUG_ON(lineno < 0 || lineno >= PVC_NLINES);
len = min(count, sizeof(kbuf) - 1);
if (copy_from_user(kbuf, buf, len))
diff --git a/arch/mips/lib/ashldi3.c b/arch/mips/lib/ashldi3.c
index beb80f316095..927dc94a030f 100644
--- a/arch/mips/lib/ashldi3.c
+++ b/arch/mips/lib/ashldi3.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-long long __ashldi3(long long u, word_type b)
+long long notrace __ashldi3(long long u, word_type b)
{
DWunion uu, w;
word_type bm;
diff --git a/arch/mips/lib/ashrdi3.c b/arch/mips/lib/ashrdi3.c
index c884a912b660..9fdf1a598428 100644
--- a/arch/mips/lib/ashrdi3.c
+++ b/arch/mips/lib/ashrdi3.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-long long __ashrdi3(long long u, word_type b)
+long long notrace __ashrdi3(long long u, word_type b)
{
DWunion uu, w;
word_type bm;
diff --git a/arch/mips/lib/bswapdi.c b/arch/mips/lib/bswapdi.c
index 77e5f9c1f005..e3e77aa52c95 100644
--- a/arch/mips/lib/bswapdi.c
+++ b/arch/mips/lib/bswapdi.c
@@ -1,6 +1,6 @@
#include <linux/module.h>
-unsigned long long __bswapdi2(unsigned long long u)
+unsigned long long notrace __bswapdi2(unsigned long long u)
{
return (((u) & 0xff00000000000000ull) >> 56) |
(((u) & 0x00ff000000000000ull) >> 40) |
diff --git a/arch/mips/lib/bswapsi.c b/arch/mips/lib/bswapsi.c
index 2b302ff121d2..530a8afe6fda 100644
--- a/arch/mips/lib/bswapsi.c
+++ b/arch/mips/lib/bswapsi.c
@@ -1,6 +1,6 @@
#include <linux/module.h>
-unsigned int __bswapsi2(unsigned int u)
+unsigned int notrace __bswapsi2(unsigned int u)
{
return (((u) & 0xff000000) >> 24) |
(((u) & 0x00ff0000) >> 8) |
diff --git a/arch/mips/lib/cmpdi2.c b/arch/mips/lib/cmpdi2.c
index 8c1306437ed1..06857da96993 100644
--- a/arch/mips/lib/cmpdi2.c
+++ b/arch/mips/lib/cmpdi2.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-word_type __cmpdi2(long long a, long long b)
+word_type notrace __cmpdi2(long long a, long long b)
{
const DWunion au = {
.ll = a
diff --git a/arch/mips/lib/lshrdi3.c b/arch/mips/lib/lshrdi3.c
index dcf8d6810b7c..364547449c65 100644
--- a/arch/mips/lib/lshrdi3.c
+++ b/arch/mips/lib/lshrdi3.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-long long __lshrdi3(long long u, word_type b)
+long long notrace __lshrdi3(long long u, word_type b)
{
DWunion uu, w;
word_type bm;
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index 9245e1705e69..6c303a94a196 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -256,7 +256,7 @@
/*
* Macro to build the __copy_user common code
- * Arguements:
+ * Arguments:
* mode : LEGACY_MODE or EVA_MODE
* from : Source operand. USEROP or KERNELOP
* to : Destination operand. USEROP or KERNELOP
diff --git a/arch/mips/lib/ucmpdi2.c b/arch/mips/lib/ucmpdi2.c
index bb4cb2f828ea..bd599f58234c 100644
--- a/arch/mips/lib/ucmpdi2.c
+++ b/arch/mips/lib/ucmpdi2.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-word_type __ucmpdi2(unsigned long long a, unsigned long long b)
+word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b)
{
const DWunion au = {.ll = a};
const DWunion bu = {.ll = b};
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index a2631a52ca99..249039af66c4 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -212,7 +212,7 @@ static void hpet_setup(void)
/* set hpet base address */
smbus_write(SMBUS_PCI_REGB4, HPET_ADDR);
- /* enable decodeing of access to HPET MMIO*/
+ /* enable decoding of access to HPET MMIO*/
smbus_enable(SMBUS_PCI_REG40, (1 << 28));
/* HPET irq enable */
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index d4ceacd4fa12..47074887e64c 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -8,7 +8,7 @@
#include "ieee754.h"
/*
- * Emulate the arbritrary instruction ir at xcp->cp0_epc. Required when
+ * Emulate the arbitrary instruction ir at xcp->cp0_epc. Required when
* we have to emulate the instruction in a COP1 branch delay slot. Do
* not change cp0_epc due to the instruction
*
@@ -88,7 +88,7 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc)
fr = (struct emuframe __user *)
((regs->regs[29] - sizeof(struct emuframe)) & ~0x7);
- /* Verify that the stack pointer is not competely insane */
+ /* Verify that the stack pointer is not completely insane */
if (unlikely(!access_ok(VERIFY_WRITE, fr, sizeof(struct emuframe))))
return SIGBUS;
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 274da90adf0d..4004b659ce50 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -2361,8 +2361,9 @@ static void print_htw_config(void)
(config & MIPS_PWFIELD_PTEI_MASK) >> MIPS_PWFIELD_PTEI_SHIFT);
config = read_c0_pwsize();
- pr_debug("PWSize (0x%0*lx): GDW: 0x%02lx UDW: 0x%02lx MDW: 0x%02lx PTW: 0x%02lx PTEW: 0x%02lx\n",
+ pr_debug("PWSize (0x%0*lx): PS: 0x%lx GDW: 0x%02lx UDW: 0x%02lx MDW: 0x%02lx PTW: 0x%02lx PTEW: 0x%02lx\n",
field, config,
+ (config & MIPS_PWSIZE_PS_MASK) >> MIPS_PWSIZE_PS_SHIFT,
(config & MIPS_PWSIZE_GDW_MASK) >> MIPS_PWSIZE_GDW_SHIFT,
(config & MIPS_PWSIZE_UDW_MASK) >> MIPS_PWSIZE_UDW_SHIFT,
(config & MIPS_PWSIZE_MDW_MASK) >> MIPS_PWSIZE_MDW_SHIFT,
@@ -2370,9 +2371,12 @@ static void print_htw_config(void)
(config & MIPS_PWSIZE_PTEW_MASK) >> MIPS_PWSIZE_PTEW_SHIFT);
pwctl = read_c0_pwctl();
- pr_debug("PWCtl (0x%x): PWEn: 0x%x DPH: 0x%x HugePg: 0x%x Psn: 0x%x\n",
+ pr_debug("PWCtl (0x%x): PWEn: 0x%x XK: 0x%x XS: 0x%x XU: 0x%x DPH: 0x%x HugePg: 0x%x Psn: 0x%x\n",
pwctl,
(pwctl & MIPS_PWCTL_PWEN_MASK) >> MIPS_PWCTL_PWEN_SHIFT,
+ (pwctl & MIPS_PWCTL_XK_MASK) >> MIPS_PWCTL_XK_SHIFT,
+ (pwctl & MIPS_PWCTL_XS_MASK) >> MIPS_PWCTL_XS_SHIFT,
+ (pwctl & MIPS_PWCTL_XU_MASK) >> MIPS_PWCTL_XU_SHIFT,
(pwctl & MIPS_PWCTL_DPH_MASK) >> MIPS_PWCTL_DPH_SHIFT,
(pwctl & MIPS_PWCTL_HUGEPG_MASK) >> MIPS_PWCTL_HUGEPG_SHIFT,
(pwctl & MIPS_PWCTL_PSN_MASK) >> MIPS_PWCTL_PSN_SHIFT);
@@ -2427,15 +2431,25 @@ static void config_htw_params(void)
if (CONFIG_PGTABLE_LEVELS >= 3)
pwsize |= ilog2(PTRS_PER_PMD) << MIPS_PWSIZE_MDW_SHIFT;
- pwsize |= ilog2(sizeof(pte_t)/4) << MIPS_PWSIZE_PTEW_SHIFT;
+ /* Set pointer size to size of directory pointers */
+ if (config_enabled(CONFIG_64BIT))
+ pwsize |= MIPS_PWSIZE_PS_MASK;
+ /* PTEs may be multiple pointers long (e.g. with XPA) */
+ pwsize |= ((PTE_T_LOG2 - PGD_T_LOG2) << MIPS_PWSIZE_PTEW_SHIFT)
+ & MIPS_PWSIZE_PTEW_MASK;
write_c0_pwsize(pwsize);
/* Make sure everything is set before we enable the HTW */
back_to_back_c0_hazard();
- /* Enable HTW and disable the rest of the pwctl fields */
+ /*
+ * Enable HTW (and only for XUSeg on 64-bit), and disable the rest of
+ * the pwctl fields.
+ */
config = 1 << MIPS_PWCTL_PWEN_SHIFT;
+ if (config_enabled(CONFIG_64BIT))
+ config |= MIPS_PWCTL_XU_MASK;
write_c0_pwctl(config);
pr_info("Hardware Page Table Walker enabled\n");
diff --git a/arch/mips/oprofile/op_impl.h b/arch/mips/oprofile/op_impl.h
index 7c2da27ece04..a4e758a39af4 100644
--- a/arch/mips/oprofile/op_impl.h
+++ b/arch/mips/oprofile/op_impl.h
@@ -24,7 +24,7 @@ struct op_counter_config {
unsigned long unit_mask;
};
-/* Per-architecture configury and hooks. */
+/* Per-architecture configure and hooks. */
struct op_mips_model {
void (*reg_setup) (struct op_counter_config *);
void (*cpu_setup) (void *dummy);
diff --git a/arch/mips/pci/ops-bridge.c b/arch/mips/pci/ops-bridge.c
index 438319465cb4..57e1463fcd02 100644
--- a/arch/mips/pci/ops-bridge.c
+++ b/arch/mips/pci/ops-bridge.c
@@ -33,9 +33,9 @@ static u32 emulate_ioc3_cfg(int where, int size)
* The Bridge ASIC supports both type 0 and type 1 access. Type 1 is
* not really documented, so right now I can't write code which uses it.
* Therefore we use type 0 accesses for now even though they won't work
- * correcly for PCI-to-PCI bridges.
+ * correctly for PCI-to-PCI bridges.
*
- * The function is complicated by the ultimate brokeness of the IOC3 chip
+ * The function is complicated by the ultimate brokenness of the IOC3 chip
* which is used in SGI systems. The IOC3 can only handle 32-bit PCI
* accesses and does only decode parts of it's address space.
*/
diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c
index 956c92eabfab..ab79828230ab 100644
--- a/arch/mips/pistachio/init.c
+++ b/arch/mips/pistachio/init.c
@@ -83,12 +83,16 @@ static void __init plat_setup_iocoherency(void)
}
}
-void __init plat_mem_setup(void)
+void __init *plat_get_fdt(void)
{
if (fw_arg0 != -2)
panic("Device-tree not present");
+ return (void *)fw_arg1;
+}
- __dt_setup_arch((void *)fw_arg1);
+void __init plat_mem_setup(void)
+{
+ __dt_setup_arch(plat_get_fdt());
plat_setup_iocoherency();
}
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 88b82fe21ae6..d40edda0ca3b 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -188,6 +188,41 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = {
FUNC("gpio", 0, 11, 1),
};
+static struct rt2880_pmx_func p4led_kn_grp_mt7628[] = {
+ FUNC("jtag", 3, 30, 1),
+ FUNC("util", 2, 30, 1),
+ FUNC("gpio", 1, 30, 1),
+ FUNC("p4led_kn", 0, 30, 1),
+};
+
+static struct rt2880_pmx_func p3led_kn_grp_mt7628[] = {
+ FUNC("jtag", 3, 31, 1),
+ FUNC("util", 2, 31, 1),
+ FUNC("gpio", 1, 31, 1),
+ FUNC("p3led_kn", 0, 31, 1),
+};
+
+static struct rt2880_pmx_func p2led_kn_grp_mt7628[] = {
+ FUNC("jtag", 3, 32, 1),
+ FUNC("util", 2, 32, 1),
+ FUNC("gpio", 1, 32, 1),
+ FUNC("p2led_kn", 0, 32, 1),
+};
+
+static struct rt2880_pmx_func p1led_kn_grp_mt7628[] = {
+ FUNC("jtag", 3, 33, 1),
+ FUNC("util", 2, 33, 1),
+ FUNC("gpio", 1, 33, 1),
+ FUNC("p1led_kn", 0, 33, 1),
+};
+
+static struct rt2880_pmx_func p0led_kn_grp_mt7628[] = {
+ FUNC("jtag", 3, 34, 1),
+ FUNC("rsvd", 2, 34, 1),
+ FUNC("gpio", 1, 34, 1),
+ FUNC("p0led_kn", 0, 34, 1),
+};
+
static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
FUNC("rsvd", 3, 35, 1),
FUNC("rsvd", 2, 35, 1),
@@ -195,16 +230,61 @@ static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
FUNC("wled_kn", 0, 35, 1),
};
+static struct rt2880_pmx_func p4led_an_grp_mt7628[] = {
+ FUNC("jtag", 3, 39, 1),
+ FUNC("util", 2, 39, 1),
+ FUNC("gpio", 1, 39, 1),
+ FUNC("p4led_an", 0, 39, 1),
+};
+
+static struct rt2880_pmx_func p3led_an_grp_mt7628[] = {
+ FUNC("jtag", 3, 40, 1),
+ FUNC("util", 2, 40, 1),
+ FUNC("gpio", 1, 40, 1),
+ FUNC("p3led_an", 0, 40, 1),
+};
+
+static struct rt2880_pmx_func p2led_an_grp_mt7628[] = {
+ FUNC("jtag", 3, 41, 1),
+ FUNC("util", 2, 41, 1),
+ FUNC("gpio", 1, 41, 1),
+ FUNC("p2led_an", 0, 41, 1),
+};
+
+static struct rt2880_pmx_func p1led_an_grp_mt7628[] = {
+ FUNC("jtag", 3, 42, 1),
+ FUNC("util", 2, 42, 1),
+ FUNC("gpio", 1, 42, 1),
+ FUNC("p1led_an", 0, 42, 1),
+};
+
+static struct rt2880_pmx_func p0led_an_grp_mt7628[] = {
+ FUNC("jtag", 3, 43, 1),
+ FUNC("rsvd", 2, 43, 1),
+ FUNC("gpio", 1, 43, 1),
+ FUNC("p0led_an", 0, 43, 1),
+};
+
static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
- FUNC("rsvd", 3, 35, 1),
- FUNC("rsvd", 2, 35, 1),
- FUNC("gpio", 1, 35, 1),
- FUNC("wled_an", 0, 35, 1),
+ FUNC("rsvd", 3, 44, 1),
+ FUNC("rsvd", 2, 44, 1),
+ FUNC("gpio", 1, 44, 1),
+ FUNC("wled_an", 0, 44, 1),
};
#define MT7628_GPIO_MODE_MASK 0x3
+#define MT7628_GPIO_MODE_P4LED_KN 58
+#define MT7628_GPIO_MODE_P3LED_KN 56
+#define MT7628_GPIO_MODE_P2LED_KN 54
+#define MT7628_GPIO_MODE_P1LED_KN 52
+#define MT7628_GPIO_MODE_P0LED_KN 50
#define MT7628_GPIO_MODE_WLED_KN 48
+#define MT7628_GPIO_MODE_P4LED_AN 42
+#define MT7628_GPIO_MODE_P3LED_AN 40
+#define MT7628_GPIO_MODE_P2LED_AN 38
+#define MT7628_GPIO_MODE_P1LED_AN 36
+#define MT7628_GPIO_MODE_P0LED_AN 34
#define MT7628_GPIO_MODE_WLED_AN 32
#define MT7628_GPIO_MODE_PWM1 30
#define MT7628_GPIO_MODE_PWM0 28
@@ -223,9 +303,9 @@ static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
#define MT7628_GPIO_MODE_GPIO 0
static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
- GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
1, MT7628_GPIO_MODE_PWM1),
- GRP_G("pmw0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
1, MT7628_GPIO_MODE_PWM0),
GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
1, MT7628_GPIO_MODE_UART2),
@@ -251,8 +331,28 @@ static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
1, MT7628_GPIO_MODE_GPIO),
GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
1, MT7628_GPIO_MODE_WLED_AN),
+ GRP_G("p0led_an", p0led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P0LED_AN),
+ GRP_G("p1led_an", p1led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P1LED_AN),
+ GRP_G("p2led_an", p2led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P2LED_AN),
+ GRP_G("p3led_an", p3led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P3LED_AN),
+ GRP_G("p4led_an", p4led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P4LED_AN),
GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
1, MT7628_GPIO_MODE_WLED_KN),
+ GRP_G("p0led_kn", p0led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P0LED_KN),
+ GRP_G("p1led_kn", p1led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P1LED_KN),
+ GRP_G("p2led_kn", p2led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P2LED_KN),
+ GRP_G("p3led_kn", p3led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P3LED_KN),
+ GRP_G("p4led_kn", p4led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+ 1, MT7628_GPIO_MODE_P4LED_KN),
{ 0 }
};
diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c
index 328ceb3c86ec..2abe016a0ffc 100644
--- a/arch/mips/sgi-ip27/ip27-hubio.c
+++ b/arch/mips/sgi-ip27/ip27-hubio.c
@@ -105,7 +105,7 @@ static void hub_setup_prb(nasid_t nasid, int prbnum, int credits)
prb.iprb_ff = force_fire_and_forget ? 1 : 0;
/*
- * Set the appropriate number of PIO cresits for the widget.
+ * Set the appropriate number of PIO credits for the widget.
*/
prb.iprb_xtalkctr = credits;
diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c
index a2358b44420c..cfceaea92724 100644
--- a/arch/mips/sgi-ip27/ip27-nmi.c
+++ b/arch/mips/sgi-ip27/ip27-nmi.c
@@ -23,7 +23,7 @@ typedef unsigned long machreg_t;
static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED;
/*
- * Lets see what else we need to do here. Set up sp, gp?
+ * Let's see what else we need to do here. Set up sp, gp?
*/
void nmi_dump(void)
{
diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c
index 20f582a2137a..4fe5678ba74d 100644
--- a/arch/mips/sgi-ip27/ip27-xtalk.c
+++ b/arch/mips/sgi-ip27/ip27-xtalk.c
@@ -67,7 +67,7 @@ static int xbow_probe(nasid_t nasid)
return -ENODEV;
/*
- * Okay, here's a xbow. Lets arbitrate and find
+ * Okay, here's a xbow. Let's arbitrate and find
* out if we should initialize it. Set enabled
* hub connected at highest or lowest widget as
* master.
diff --git a/arch/mips/sni/rm200.c b/arch/mips/sni/rm200.c
index a046b302623e..160b88000b4b 100644
--- a/arch/mips/sni/rm200.c
+++ b/arch/mips/sni/rm200.c
@@ -263,7 +263,7 @@ spurious_8259A_irq:
static int spurious_irq_mask;
/*
* At this point we can be sure the IRQ is spurious,
- * lets ACK and report it. [once per IRQ]
+ * let's ACK and report it. [once per IRQ]
*/
if (!(spurious_irq_mask & irqmask)) {
printk(KERN_DEBUG
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index b369509e9753..3b4538ec0102 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -5,10 +5,12 @@ obj-vdso-y := elf.o gettimeofday.o sigreturn.o
ccflags-vdso := \
$(filter -I%,$(KBUILD_CFLAGS)) \
$(filter -E%,$(KBUILD_CFLAGS)) \
+ $(filter -mmicromips,$(KBUILD_CFLAGS)) \
$(filter -march=%,$(KBUILD_CFLAGS))
cflags-vdso := $(ccflags-vdso) \
$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
- -O2 -g -fPIC -fno-common -fno-builtin -G 0 -DDISABLE_BRANCH_PROFILING \
+ -O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+ -DDISABLE_BRANCH_PROFILING \
$(call cc-option, -fno-stack-protector)
aflags-vdso := $(ccflags-vdso) \
$(filter -I%,$(KBUILD_CFLAGS)) \
diff --git a/arch/mips/vr41xx/common/cmu.c b/arch/mips/vr41xx/common/cmu.c
index 05302bfdd114..89bac9885695 100644
--- a/arch/mips/vr41xx/common/cmu.c
+++ b/arch/mips/vr41xx/common/cmu.c
@@ -3,7 +3,7 @@
*
* Copyright (C) 2001-2002 MontaVista Software Inc.
* Author: Yoichi Yuasa <source@mvista.com>
- * Copuright (C) 2003-2005 Yoichi Yuasa <yuasa@linux-mips.org>
+ * Copyright (C) 2003-2005 Yoichi Yuasa <yuasa@linux-mips.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/arch/mn10300/boot/compressed/Makefile b/arch/mn10300/boot/compressed/Makefile
index 08a95e171685..5f56f9de1061 100644
--- a/arch/mn10300/boot/compressed/Makefile
+++ b/arch/mn10300/boot/compressed/Makefile
@@ -8,7 +8,6 @@ LDFLAGS_vmlinux := -Ttext $(CONFIG_KERNEL_ZIMAGE_BASE_ADDRESS) -e startup_32
$(obj)/vmlinux: $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o FORCE
$(call if_changed,ld)
- @:
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index 4861a78c7160..f5f90bbf019d 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -115,7 +115,7 @@ static inline unsigned long current_stack_pointer(void)
}
#ifndef CONFIG_KGDB
-void arch_release_thread_info(struct thread_info *ti);
+void arch_release_thread_stack(unsigned long *stack);
#endif
#define get_thread_info(ti) get_task_struct((ti)->task)
#define put_thread_info(ti) put_task_struct((ti)->task)
diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c
index 99770823451a..2d7986c386fe 100644
--- a/arch/mn10300/kernel/kgdb.c
+++ b/arch/mn10300/kernel/kgdb.c
@@ -397,8 +397,9 @@ static bool kgdb_arch_undo_singlestep(struct pt_regs *regs)
* single-step state is cleared. At this point the breakpoints should have
* been removed by __switch_to().
*/
-void arch_release_thread_info(struct thread_info *ti)
+void arch_release_thread_stack(unsigned long *stack)
{
+ struct thread_info *ti = (void *)stack;
if (kgdb_sstep_thread == ti) {
kgdb_sstep_thread = NULL;
diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c
index e77a7c728081..9577cf768875 100644
--- a/arch/mn10300/mm/pgtable.c
+++ b/arch/mn10300/mm/pgtable.c
@@ -63,7 +63,7 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+ pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
if (pte)
clear_page(pte);
return pte;
@@ -74,9 +74,9 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
struct page *pte;
#ifdef CONFIG_HIGHPTE
- pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+ pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
#else
- pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+ pte = alloc_pages(GFP_KERNEL, 0);
#endif
if (!pte)
return NULL;
diff --git a/arch/nios2/Makefile b/arch/nios2/Makefile
index 2328f82ba2a8..e74afc12d516 100644
--- a/arch/nios2/Makefile
+++ b/arch/nios2/Makefile
@@ -20,7 +20,7 @@ UTS_SYSNAME = Linux
export MMU
-LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
+LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
KBUILD_CFLAGS += -pipe -D__linux__ -D__ELF__
KBUILD_CFLAGS += $(if $(CONFIG_NIOS2_HW_MUL_SUPPORT),-mhw-mul,-mno-hw-mul)
@@ -53,7 +53,7 @@ all: vmImage
archclean:
$(Q)$(MAKE) $(clean)=$(nios2-boot)
-%.dtb:
+%.dtb: | scripts
$(Q)$(MAKE) $(build)=$(nios2-boot) $(nios2-boot)/$@
dtbs:
diff --git a/arch/nios2/boot/compressed/Makefile b/arch/nios2/boot/compressed/Makefile
index 5b0fb346d888..d5921c9a9726 100644
--- a/arch/nios2/boot/compressed/Makefile
+++ b/arch/nios2/boot/compressed/Makefile
@@ -11,7 +11,6 @@ LDFLAGS_vmlinux := -T
$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS) $(obj)/piggy.o FORCE
$(call if_changed,ld)
- @:
LDFLAGS_piggy.o := -r --format binary --oformat elf32-littlenios2 -T
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index 6e2985e0a7b9..bb47d08c8ef7 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
{
pte_t *pte;
- pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
- PTE_ORDER);
+ pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
return pte;
}
@@ -53,7 +52,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
{
struct page *pte;
- pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+ pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
if (pte) {
if (!pgtable_page_ctor(pte)) {
__free_page(pte);
diff --git a/arch/nios2/include/uapi/asm/unistd.h b/arch/nios2/include/uapi/asm/unistd.h
index c4bf79510461..51a32c71ce2b 100644
--- a/arch/nios2/include/uapi/asm/unistd.h
+++ b/arch/nios2/include/uapi/asm/unistd.h
@@ -17,6 +17,8 @@
#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+
/* Use the standard ABI for syscalls */
#include <asm-generic/unistd.h>
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 21484e5b9e9a..87eebd185089 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -77,7 +77,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
unsigned long address)
{
struct page *pte;
- pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+ pte = alloc_pages(GFP_KERNEL, 0);
if (!pte)
return NULL;
clear_page(page_address(pte));
diff --git a/arch/openrisc/include/uapi/asm/unistd.h b/arch/openrisc/include/uapi/asm/unistd.h
index ce40b71df006..471905bd7745 100644
--- a/arch/openrisc/include/uapi/asm/unistd.h
+++ b/arch/openrisc/include/uapi/asm/unistd.h
@@ -20,6 +20,7 @@
#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index 62b08ef392be..5b2a95116e8f 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -122,7 +122,7 @@ pte_t __init_refok *pte_alloc_one_kernel(struct mm_struct *mm,
pte_t *pte;
if (likely(mem_init_done)) {
- pte = (pte_t *) __get_free_page(GFP_KERNEL | __GFP_REPEAT);
+ pte = (pte_t *) __get_free_page(GFP_KERNEL);
} else {
pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
#if 0
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3d498a676551..dc117385ce2e 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -6,6 +6,7 @@ config PARISC
select HAVE_OPROFILE
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
+ select HAVE_SYSCALL_TRACEPOINTS
select ARCH_WANT_FRAME_POINTERS
select RTC_CLASS
select RTC_DRV_GENERIC
@@ -31,6 +32,8 @@ config PARISC
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_TRACEHOOK
+ select HAVE_UNSTABLE_SCHED_CLOCK if (SMP || !64BIT)
select ARCH_NO_COHERENT_DMA_MMAP
select CPU_NO_EFFICIENT_FFS
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index 0a90b965cccb..7ada30900807 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -52,8 +52,7 @@ extern void __cmpxchg_called_with_bad_pointer(void);
/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
unsigned int new_);
-extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr,
- unsigned long old, unsigned long new_);
+extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
/* don't worry...optimizer will get rid of most of this */
static inline unsigned long
@@ -61,7 +60,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
{
switch (size) {
#ifdef CONFIG_64BIT
- case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+ case 8: return __cmpxchg_u64((u64 *)ptr, old, new_);
#endif
case 4: return __cmpxchg_u32((unsigned int *)ptr,
(unsigned int)old, (unsigned int)new_);
@@ -86,7 +85,7 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
{
switch (size) {
#ifdef CONFIG_64BIT
- case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+ case 8: return __cmpxchg_u64((u64 *)ptr, old, new_);
#endif
case 4: return __cmpxchg_u32(ptr, old, new_);
default:
@@ -111,4 +110,6 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
#endif
+#define cmpxchg64(ptr, o, n) __cmpxchg_u64(ptr, o, n)
+
#endif /* _ASM_PARISC_CMPXCHG_H_ */
diff --git a/arch/parisc/include/asm/eisa_eeprom.h b/arch/parisc/include/asm/eisa_eeprom.h
index 8ce8b85ca588..5637ac962f8e 100644
--- a/arch/parisc/include/asm/eisa_eeprom.h
+++ b/arch/parisc/include/asm/eisa_eeprom.h
@@ -99,7 +99,7 @@ struct eeprom_eisa_slot_info
#define HPEE_MEMORY_DECODE_24BITS 0x04
#define HPEE_MEMORY_DECODE_32BITS 0x08
/* byte 2 and 3 are a 16bit LE value
- * containging the memory size in kilobytes */
+ * containing the memory size in kilobytes */
/* byte 4,5,6 are a 24bit LE value
* containing the memory base address */
@@ -135,7 +135,7 @@ struct eeprom_eisa_slot_info
#define HPEE_PORT_SHARED 0x40
#define HPEE_PORT_MORE 0x80
/* byte 1 and 2 is a 16bit LE value
- * conating the start port number */
+ * containing the start port number */
#define HPEE_PORT_INIT_MAX_LEN 60 /* in bytes here */
/* port init entry byte 0 */
diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h
index 24cd81d58d70..d635c6b0269d 100644
--- a/arch/parisc/include/asm/ftrace.h
+++ b/arch/parisc/include/asm/ftrace.h
@@ -6,6 +6,8 @@ extern void mcount(void);
#define MCOUNT_INSN_SIZE 4
+extern unsigned long sys_call_table[];
+
extern unsigned long return_address(unsigned int);
#define ftrace_return_address(n) return_address(n)
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 49df14805a9b..ac8bd586ace8 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -35,70 +35,57 @@ static inline int
futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
unsigned long int flags;
- u32 val;
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
int oparg = (encoded_op << 8) >> 20;
int cmparg = (encoded_op << 20) >> 20;
- int oldval = 0, ret;
+ int oldval, ret;
+ u32 tmp;
+
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)))
return -EFAULT;
+ _futex_spin_lock_irqsave(uaddr, &flags);
pagefault_disable();
- _futex_spin_lock_irqsave(uaddr, &flags);
+ ret = -EFAULT;
+ if (unlikely(get_user(oldval, uaddr) != 0))
+ goto out_pagefault_enable;
+
+ ret = 0;
+ tmp = oldval;
switch (op) {
case FUTEX_OP_SET:
- /* *(int *)UADDR2 = OPARG; */
- ret = get_user(oldval, uaddr);
- if (!ret)
- ret = put_user(oparg, uaddr);
+ tmp = oparg;
break;
case FUTEX_OP_ADD:
- /* *(int *)UADDR2 += OPARG; */
- ret = get_user(oldval, uaddr);
- if (!ret) {
- val = oldval + oparg;
- ret = put_user(val, uaddr);
- }
+ tmp += oparg;
break;
case FUTEX_OP_OR:
- /* *(int *)UADDR2 |= OPARG; */
- ret = get_user(oldval, uaddr);
- if (!ret) {
- val = oldval | oparg;
- ret = put_user(val, uaddr);
- }
+ tmp |= oparg;
break;
case FUTEX_OP_ANDN:
- /* *(int *)UADDR2 &= ~OPARG; */
- ret = get_user(oldval, uaddr);
- if (!ret) {
- val = oldval & ~oparg;
- ret = put_user(val, uaddr);
- }
+ tmp &= ~oparg;
break;
case FUTEX_OP_XOR:
- /* *(int *)UADDR2 ^= OPARG; */
- ret = get_user(oldval, uaddr);
- if (!ret) {
- val = oldval ^ oparg;
- ret = put_user(val, uaddr);
- }
+ tmp ^= oparg;
break;
default:
ret = -ENOSYS;
}
- _futex_spin_unlock_irqrestore(uaddr, &flags);
+ if (ret == 0 && unlikely(put_user(tmp, uaddr) != 0))
+ ret = -EFAULT;
+out_pagefault_enable:
pagefault_enable();
+ _futex_spin_unlock_irqrestore(uaddr, &flags);
- if (!ret) {
+ if (ret == 0) {
switch (cmp) {
case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
@@ -112,12 +99,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
return ret;
}
-/* Non-atomic version */
static inline int
futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
u32 oldval, u32 newval)
{
- int ret;
u32 val;
unsigned long flags;
@@ -137,17 +122,20 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
*/
_futex_spin_lock_irqsave(uaddr, &flags);
+ if (unlikely(get_user(val, uaddr) != 0)) {
+ _futex_spin_unlock_irqrestore(uaddr, &flags);
+ return -EFAULT;
+ }
- ret = get_user(val, uaddr);
-
- if (!ret && val == oldval)
- ret = put_user(newval, uaddr);
+ if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) {
+ _futex_spin_unlock_irqrestore(uaddr, &flags);
+ return -EFAULT;
+ }
*uval = val;
-
_futex_spin_unlock_irqrestore(uaddr, &flags);
- return ret;
+ return 0;
}
#endif /*__KERNEL__*/
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index 8121aa6db2ff..8be707e1b6c7 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -40,7 +40,7 @@
memory to indicate to the compiler that the assembly code reads
or writes to items other than those listed in the input and output
operands. This may pessimize the code somewhat but __ldcw is
- usually used within code blocks surrounded by memory barriors. */
+ usually used within code blocks surrounded by memory barriers. */
#define __ldcw(a) ({ \
unsigned __ret; \
__asm__ __volatile__(__LDCW " 0(%1),%0" \
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f2fd327dce2e..f08dda3f0995 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -63,8 +63,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
- pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
- PMD_ORDER);
+ pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER);
if (pmd)
memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
return pmd;
@@ -124,7 +123,7 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
static inline pgtable_t
pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
- struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
if (!page)
return NULL;
if (!pgtable_page_ctor(page)) {
@@ -137,7 +136,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
static inline pte_t *
pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
return pte;
}
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 637ce8d6f375..5e0b4e6bd99d 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -8,6 +8,8 @@
#include <linux/err.h>
#include <asm/ptrace.h>
+#define NR_syscalls (__NR_Linux_syscalls)
+
static inline long syscall_get_nr(struct task_struct *tsk,
struct pt_regs *regs)
{
@@ -33,12 +35,19 @@ static inline void syscall_get_arguments(struct task_struct *tsk,
args[1] = regs->gr[25];
case 1:
args[0] = regs->gr[26];
+ case 0:
break;
default:
BUG();
}
}
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->gr[28];
+}
+
static inline void syscall_set_return_value(struct task_struct *task,
struct pt_regs *regs,
int error, long val)
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index e96e693fd58c..7581330ea35b 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -55,6 +55,7 @@ struct thread_info {
#define TIF_SINGLESTEP 9 /* single stepping? */
#define TIF_BLOCKSTEP 10 /* branch stepping? */
#define TIF_SECCOMP 11 /* secure computing */
+#define TIF_SYSCALL_TRACEPOINT 12 /* syscall tracepoint instrumentation */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
@@ -66,12 +67,13 @@ struct thread_info {
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
#define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
+#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
#define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \
_TIF_NEED_RESCHED)
#define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \
_TIF_BLOCKSTEP | _TIF_SYSCALL_AUDIT | \
- _TIF_SECCOMP)
+ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
#ifdef CONFIG_64BIT
# ifdef CONFIG_COMPAT
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 4736020ba5ea..5e953ab4530d 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -8,6 +8,8 @@ struct pt_regs;
void parisc_terminate(char *msg, struct pt_regs *regs,
int code, unsigned long offset) __noreturn __cold;
+void die_if_kernel(char *str, struct pt_regs *regs, long err);
+
/* mm/fault.c */
void do_page_fault(struct pt_regs *regs, unsigned long code,
unsigned long address);
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 7955e43f3f3f..0f59fd9ca205 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -40,14 +40,10 @@ static inline long access_ok(int type, const void __user * addr,
#define get_user __get_user
#if !defined(CONFIG_64BIT)
-#define LDD_KERNEL(ptr) BUILD_BUG()
-#define LDD_USER(ptr) BUILD_BUG()
-#define STD_KERNEL(x, ptr) __put_kernel_asm64(x, ptr)
+#define LDD_USER(ptr) __get_user_asm64(ptr)
#define STD_USER(x, ptr) __put_user_asm64(x, ptr)
#else
-#define LDD_KERNEL(ptr) __get_kernel_asm("ldd", ptr)
#define LDD_USER(ptr) __get_user_asm("ldd", ptr)
-#define STD_KERNEL(x, ptr) __put_kernel_asm("std", x, ptr)
#define STD_USER(x, ptr) __put_user_asm("std", x, ptr)
#endif
@@ -80,70 +76,70 @@ struct exception_data {
unsigned long fault_addr;
};
+/*
+ * load_sr2() preloads the space register %%sr2 - based on the value of
+ * get_fs() - with either a value of 0 to access kernel space (KERNEL_DS which
+ * is 0), or with the current value of %%sr3 to access user space (USER_DS)
+ * memory. The following __get_user_asm() and __put_user_asm() functions have
+ * %%sr2 hard-coded to access the requested memory.
+ */
+#define load_sr2() \
+ __asm__(" or,= %0,%%r0,%%r0\n\t" \
+ " mfsp %%sr3,%0\n\t" \
+ " mtsp %0,%%sr2\n\t" \
+ : : "r"(get_fs()) : )
+
#define __get_user(x, ptr) \
({ \
register long __gu_err __asm__ ("r8") = 0; \
register long __gu_val __asm__ ("r9") = 0; \
\
- if (segment_eq(get_fs(), KERNEL_DS)) { \
- switch (sizeof(*(ptr))) { \
- case 1: __get_kernel_asm("ldb", ptr); break; \
- case 2: __get_kernel_asm("ldh", ptr); break; \
- case 4: __get_kernel_asm("ldw", ptr); break; \
- case 8: LDD_KERNEL(ptr); break; \
- default: BUILD_BUG(); break; \
- } \
- } \
- else { \
- switch (sizeof(*(ptr))) { \
+ load_sr2(); \
+ switch (sizeof(*(ptr))) { \
case 1: __get_user_asm("ldb", ptr); break; \
case 2: __get_user_asm("ldh", ptr); break; \
case 4: __get_user_asm("ldw", ptr); break; \
case 8: LDD_USER(ptr); break; \
default: BUILD_BUG(); break; \
- } \
} \
\
(x) = (__force __typeof__(*(ptr))) __gu_val; \
__gu_err; \
})
-#define __get_kernel_asm(ldx, ptr) \
- __asm__("\n1:\t" ldx "\t0(%2),%0\n\t" \
+#define __get_user_asm(ldx, ptr) \
+ __asm__("\n1:\t" ldx "\t0(%%sr2,%2),%0\n\t" \
ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_1)\
: "=r"(__gu_val), "=r"(__gu_err) \
: "r"(ptr), "1"(__gu_err) \
: "r1");
-#define __get_user_asm(ldx, ptr) \
- __asm__("\n1:\t" ldx "\t0(%%sr3,%2),%0\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_1)\
- : "=r"(__gu_val), "=r"(__gu_err) \
+#if !defined(CONFIG_64BIT)
+
+#define __get_user_asm64(ptr) \
+ __asm__("\n1:\tldw 0(%%sr2,%2),%0" \
+ "\n2:\tldw 4(%%sr2,%2),%R0\n\t" \
+ ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_2)\
+ ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_get_user_skip_1)\
+ : "=r"(__gu_val), "=r"(__gu_err) \
: "r"(ptr), "1"(__gu_err) \
: "r1");
+#endif /* !defined(CONFIG_64BIT) */
+
+
#define __put_user(x, ptr) \
({ \
register long __pu_err __asm__ ("r8") = 0; \
__typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x); \
\
- if (segment_eq(get_fs(), KERNEL_DS)) { \
- switch (sizeof(*(ptr))) { \
- case 1: __put_kernel_asm("stb", __x, ptr); break; \
- case 2: __put_kernel_asm("sth", __x, ptr); break; \
- case 4: __put_kernel_asm("stw", __x, ptr); break; \
- case 8: STD_KERNEL(__x, ptr); break; \
- default: BUILD_BUG(); break; \
- } \
- } \
- else { \
- switch (sizeof(*(ptr))) { \
+ load_sr2(); \
+ switch (sizeof(*(ptr))) { \
case 1: __put_user_asm("stb", __x, ptr); break; \
case 2: __put_user_asm("sth", __x, ptr); break; \
case 4: __put_user_asm("stw", __x, ptr); break; \
case 8: STD_USER(__x, ptr); break; \
default: BUILD_BUG(); break; \
- } \
} \
\
__pu_err; \
@@ -159,17 +155,9 @@ struct exception_data {
* r8/r9 are already listed as err/val.
*/
-#define __put_kernel_asm(stx, x, ptr) \
- __asm__ __volatile__ ( \
- "\n1:\t" stx "\t%2,0(%1)\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_1)\
- : "=r"(__pu_err) \
- : "r"(ptr), "r"(x), "0"(__pu_err) \
- : "r1")
-
#define __put_user_asm(stx, x, ptr) \
__asm__ __volatile__ ( \
- "\n1:\t" stx "\t%2,0(%%sr3,%1)\n\t" \
+ "\n1:\t" stx "\t%2,0(%%sr2,%1)\n\t" \
ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_1)\
: "=r"(__pu_err) \
: "r"(ptr), "r"(x), "0"(__pu_err) \
@@ -178,21 +166,10 @@ struct exception_data {
#if !defined(CONFIG_64BIT)
-#define __put_kernel_asm64(__val, ptr) do { \
- __asm__ __volatile__ ( \
- "\n1:\tstw %2,0(%1)" \
- "\n2:\tstw %R2,4(%1)\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_2)\
- ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_put_user_skip_1)\
- : "=r"(__pu_err) \
- : "r"(ptr), "r"(__val), "0"(__pu_err) \
- : "r1"); \
-} while (0)
-
#define __put_user_asm64(__val, ptr) do { \
__asm__ __volatile__ ( \
- "\n1:\tstw %2,0(%%sr3,%1)" \
- "\n2:\tstw %R2,4(%%sr3,%1)\n\t" \
+ "\n1:\tstw %2,0(%%sr2,%1)" \
+ "\n2:\tstw %R2,4(%%sr2,%1)\n\t" \
ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_2)\
ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_put_user_skip_1)\
: "=r"(__pu_err) \
diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h
index 702498f7705b..0609ff117f67 100644
--- a/arch/parisc/include/uapi/asm/pdc.h
+++ b/arch/parisc/include/uapi/asm/pdc.h
@@ -59,7 +59,7 @@
#define PDC_MODEL_GET_BOOT__OP 8 /* returns boot test options */
#define PDC_MODEL_SET_BOOT__OP 9 /* set boot test options */
-#define PA89_INSTRUCTION_SET 0x4 /* capatibilies returned */
+#define PA89_INSTRUCTION_SET 0x4 /* capabilities returned */
#define PA90_INSTRUCTION_SET 0x8
#define PDC_CACHE 5 /* return/set cache (& TLB) info*/
diff --git a/arch/parisc/include/uapi/asm/ptrace.h b/arch/parisc/include/uapi/asm/ptrace.h
index c4fa6c8b9ad9..02ce2eb99a7f 100644
--- a/arch/parisc/include/uapi/asm/ptrace.h
+++ b/arch/parisc/include/uapi/asm/ptrace.h
@@ -13,6 +13,11 @@
* N.B. gdb/strace care about the size and offsets within this
* structure. If you change things, you may break object compatibility
* for those applications.
+ *
+ * Please do NOT use this structure for future programs, but use
+ * user_regs_struct (see below) instead.
+ *
+ * It can be accessed through PTRACE_PEEKUSR/PTRACE_POKEUSR only.
*/
struct pt_regs {
@@ -33,6 +38,45 @@ struct pt_regs {
unsigned long ipsw; /* CR22 */
};
+/**
+ * struct user_regs_struct - User general purpose registers
+ *
+ * This is the user-visible general purpose register state structure
+ * which is used to define the elf_gregset_t.
+ *
+ * It can be accessed through PTRACE_GETREGSET with NT_PRSTATUS
+ * and through PTRACE_GETREGS.
+ */
+struct user_regs_struct {
+ unsigned long gr[32]; /* PSW is in gr[0] */
+ unsigned long sr[8];
+ unsigned long iaoq[2];
+ unsigned long iasq[2];
+ unsigned long sar; /* CR11 */
+ unsigned long iir; /* CR19 */
+ unsigned long isr; /* CR20 */
+ unsigned long ior; /* CR21 */
+ unsigned long ipsw; /* CR22 */
+ unsigned long cr0;
+ unsigned long cr24, cr25, cr26, cr27, cr28, cr29, cr30, cr31;
+ unsigned long cr8, cr9, cr12, cr13, cr10, cr15;
+ unsigned long _pad[80-64]; /* pad to ELF_NGREG (80) */
+};
+
+/**
+ * struct user_fp_struct - User floating point registers
+ *
+ * This is the user-visible floating point register state structure.
+ * It uses the same layout and size as elf_fpregset_t.
+ *
+ * It can be accessed through PTRACE_GETREGSET with NT_PRFPREG
+ * and through PTRACE_GETFPREGS.
+ */
+struct user_fp_struct {
+ __u64 fr[32];
+};
+
+
/*
* The numbers chosen here are somewhat arbitrary but absolutely MUST
* not overlap with any of the number assigned in <linux/ptrace.h>.
@@ -43,5 +87,9 @@ struct pt_regs {
*/
#define PTRACE_SINGLEBLOCK 12 /* resume execution until next branch */
+#define PTRACE_GETREGS 18
+#define PTRACE_SETREGS 19
+#define PTRACE_GETFPREGS 14
+#define PTRACE_SETFPREGS 15
#endif /* _UAPI_PARISC_PTRACE_H */
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index cc0ce92c93c7..a9b9407f38f7 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -102,7 +102,7 @@
#define __NR_uselib (__NR_Linux + 86)
#define __NR_swapon (__NR_Linux + 87)
#define __NR_reboot (__NR_Linux + 88)
-#define __NR_mmap2 (__NR_Linux + 89)
+#define __NR_mmap2 (__NR_Linux + 89)
#define __NR_mmap (__NR_Linux + 90)
#define __NR_munmap (__NR_Linux + 91)
#define __NR_truncate (__NR_Linux + 92)
@@ -114,7 +114,7 @@
#define __NR_recv (__NR_Linux + 98)
#define __NR_statfs (__NR_Linux + 99)
#define __NR_fstatfs (__NR_Linux + 100)
-#define __NR_stat64 (__NR_Linux + 101)
+#define __NR_stat64 (__NR_Linux + 101)
/* #define __NR_socketcall (__NR_Linux + 102) */
#define __NR_syslog (__NR_Linux + 103)
#define __NR_setitimer (__NR_Linux + 104)
@@ -140,17 +140,17 @@
#define __NR_adjtimex (__NR_Linux + 124)
#define __NR_mprotect (__NR_Linux + 125)
#define __NR_sigprocmask (__NR_Linux + 126)
-#define __NR_create_module (__NR_Linux + 127)
+#define __NR_create_module (__NR_Linux + 127) /* not used */
#define __NR_init_module (__NR_Linux + 128)
#define __NR_delete_module (__NR_Linux + 129)
-#define __NR_get_kernel_syms (__NR_Linux + 130)
+#define __NR_get_kernel_syms (__NR_Linux + 130) /* not used */
#define __NR_quotactl (__NR_Linux + 131)
#define __NR_getpgid (__NR_Linux + 132)
#define __NR_fchdir (__NR_Linux + 133)
#define __NR_bdflush (__NR_Linux + 134)
#define __NR_sysfs (__NR_Linux + 135)
#define __NR_personality (__NR_Linux + 136)
-#define __NR_afs_syscall (__NR_Linux + 137) /* Syscall for Andrew File System */
+#define __NR_afs_syscall (__NR_Linux + 137) /* not used */
#define __NR_setfsuid (__NR_Linux + 138)
#define __NR_setfsgid (__NR_Linux + 139)
#define __NR__llseek (__NR_Linux + 140)
@@ -180,9 +180,9 @@
#define __NR_setresuid (__NR_Linux + 164)
#define __NR_getresuid (__NR_Linux + 165)
#define __NR_sigaltstack (__NR_Linux + 166)
-#define __NR_query_module (__NR_Linux + 167)
+#define __NR_query_module (__NR_Linux + 167) /* not used */
#define __NR_poll (__NR_Linux + 168)
-#define __NR_nfsservctl (__NR_Linux + 169)
+#define __NR_nfsservctl (__NR_Linux + 169) /* not used */
#define __NR_setresgid (__NR_Linux + 170)
#define __NR_getresgid (__NR_Linux + 171)
#define __NR_prctl (__NR_Linux + 172)
@@ -209,18 +209,16 @@
#define __NR_shmdt (__NR_Linux + 193)
#define __NR_shmget (__NR_Linux + 194)
#define __NR_shmctl (__NR_Linux + 195)
-
-#define __NR_getpmsg (__NR_Linux + 196) /* Somebody *wants* streams? */
-#define __NR_putpmsg (__NR_Linux + 197)
-
+#define __NR_getpmsg (__NR_Linux + 196) /* not used */
+#define __NR_putpmsg (__NR_Linux + 197) /* not used */
#define __NR_lstat64 (__NR_Linux + 198)
#define __NR_truncate64 (__NR_Linux + 199)
#define __NR_ftruncate64 (__NR_Linux + 200)
#define __NR_getdents64 (__NR_Linux + 201)
#define __NR_fcntl64 (__NR_Linux + 202)
-#define __NR_attrctl (__NR_Linux + 203)
-#define __NR_acl_get (__NR_Linux + 204)
-#define __NR_acl_set (__NR_Linux + 205)
+#define __NR_attrctl (__NR_Linux + 203) /* not used */
+#define __NR_acl_get (__NR_Linux + 204) /* not used */
+#define __NR_acl_set (__NR_Linux + 205) /* not used */
#define __NR_gettid (__NR_Linux + 206)
#define __NR_readahead (__NR_Linux + 207)
#define __NR_tkill (__NR_Linux + 208)
@@ -228,8 +226,8 @@
#define __NR_futex (__NR_Linux + 210)
#define __NR_sched_setaffinity (__NR_Linux + 211)
#define __NR_sched_getaffinity (__NR_Linux + 212)
-#define __NR_set_thread_area (__NR_Linux + 213)
-#define __NR_get_thread_area (__NR_Linux + 214)
+#define __NR_set_thread_area (__NR_Linux + 213) /* not used */
+#define __NR_get_thread_area (__NR_Linux + 214) /* not used */
#define __NR_io_setup (__NR_Linux + 215)
#define __NR_io_destroy (__NR_Linux + 216)
#define __NR_io_getevents (__NR_Linux + 217)
@@ -278,7 +276,7 @@
#define __NR_mbind (__NR_Linux + 260)
#define __NR_get_mempolicy (__NR_Linux + 261)
#define __NR_set_mempolicy (__NR_Linux + 262)
-#define __NR_vserver (__NR_Linux + 263)
+#define __NR_vserver (__NR_Linux + 263) /* not used */
#define __NR_add_key (__NR_Linux + 264)
#define __NR_request_key (__NR_Linux + 265)
#define __NR_keyctl (__NR_Linux + 266)
@@ -318,7 +316,7 @@
#define __NR_kexec_load (__NR_Linux + 300)
#define __NR_utimensat (__NR_Linux + 301)
#define __NR_signalfd (__NR_Linux + 302)
-#define __NR_timerfd (__NR_Linux + 303)
+#define __NR_timerfd (__NR_Linux + 303) /* not used */
#define __NR_eventfd (__NR_Linux + 304)
#define __NR_fallocate (__NR_Linux + 305)
#define __NR_timerfd_create (__NR_Linux + 306)
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 39127d3e70e5..baa3d9d6e971 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -667,7 +667,7 @@
* boundary
*/
- .text
+ .section .text.hot
.align 2048
ENTRY(fault_vector_20)
@@ -2019,6 +2019,7 @@ ftrace_stub:
.procend
ENDPROC(mcount)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.align 8
.globl return_to_handler
.type return_to_handler, @function
@@ -2040,11 +2041,17 @@ parisc_return_to_handler:
#endif
/* call ftrace_return_to_handler(0) */
+ .import ftrace_return_to_handler,code
+ load32 ftrace_return_to_handler,%ret0
+ load32 .Lftrace_ret,%r2
#ifdef CONFIG_64BIT
ldo -16(%sp),%ret1 /* Reference param save area */
+ bve (%ret0)
+#else
+ bv %r0(%ret0)
#endif
- BL ftrace_return_to_handler,%r2
ldi 0,%r26
+.Lftrace_ret:
copy %ret0,%rp
/* restore original return values */
@@ -2062,6 +2069,8 @@ parisc_return_to_handler:
.procend
ENDPROC(return_to_handler)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_IRQSTACKS
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index b13f9ec6f294..a828a0adf52c 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -18,12 +18,15 @@
#include <asm/ftrace.h>
+#define __hot __attribute__ ((__section__ (".text.hot")))
+
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
* Hook the return address and push it in the stack of return addrs
* in current thread info.
*/
-static void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+static void __hot prepare_ftrace_return(unsigned long *parent,
+ unsigned long self_addr)
{
unsigned long old;
struct ftrace_graph_ent trace;
@@ -53,7 +56,7 @@ static void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-void notrace ftrace_function_trampoline(unsigned long parent,
+void notrace __hot ftrace_function_trampoline(unsigned long parent,
unsigned long self_addr,
unsigned long org_sp_gr3)
{
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index e81ccf1716e9..5adc339eb7c8 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -324,8 +324,9 @@ int init_per_cpu(int cpunum)
per_cpu(cpu_data, cpunum).fp_rev = coproc_cfg.revision;
per_cpu(cpu_data, cpunum).fp_model = coproc_cfg.model;
- printk(KERN_INFO "FP[%d] enabled: Rev %ld Model %ld\n",
- cpunum, coproc_cfg.revision, coproc_cfg.model);
+ if (cpunum == 0)
+ printk(KERN_INFO "FP[%d] enabled: Rev %ld Model %ld\n",
+ cpunum, coproc_cfg.revision, coproc_cfg.model);
/*
** store status register to stack (hopefully aligned)
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 8fb81a391599..b5458b37fc5b 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -4,18 +4,20 @@
* Copyright (C) 2000 Hewlett-Packard Co, Linuxcare Inc.
* Copyright (C) 2000 Matthew Wilcox <matthew@wil.cx>
* Copyright (C) 2000 David Huggins-Daines <dhd@debian.org>
- * Copyright (C) 2008 Helge Deller <deller@gmx.de>
+ * Copyright (C) 2008-2016 Helge Deller <deller@gmx.de>
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
+#include <linux/elf.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/user.h>
#include <linux/personality.h>
+#include <linux/regset.h>
#include <linux/security.h>
#include <linux/seccomp.h>
#include <linux/compat.h>
@@ -30,6 +32,17 @@
/* PSW bits we allow the debugger to modify */
#define USER_PSW_BITS (PSW_N | PSW_B | PSW_V | PSW_CB)
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/*
+ * These are our native regset flavors.
+ */
+enum parisc_regset {
+ REGSET_GENERAL,
+ REGSET_FP
+};
+
/*
* Called by kernel/ptrace.c when detaching..
*
@@ -114,6 +127,7 @@ void user_enable_block_step(struct task_struct *task)
long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
+ unsigned long __user *datap = (unsigned long __user *)data;
unsigned long tmp;
long ret = -EIO;
@@ -126,7 +140,7 @@ long arch_ptrace(struct task_struct *child, long request,
addr >= sizeof(struct pt_regs))
break;
tmp = *(unsigned long *) ((char *) task_regs(child) + addr);
- ret = put_user(tmp, (unsigned long __user *) data);
+ ret = put_user(tmp, datap);
break;
/* Write the word at location addr in the USER area. This will need
@@ -165,6 +179,34 @@ long arch_ptrace(struct task_struct *child, long request,
}
break;
+ case PTRACE_GETREGS: /* Get all gp regs from the child. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_fp_struct),
+ datap);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_fp_struct),
+ datap);
+
default:
ret = ptrace_request(child, request, addr, data);
break;
@@ -283,6 +325,10 @@ long do_syscall_trace_enter(struct pt_regs *regs)
regs->gr[20] = -1UL;
goto out;
}
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_enter(regs, regs->gr[20]);
+#endif
#ifdef CONFIG_64BIT
if (!is_compat_task())
@@ -311,6 +357,324 @@ void do_syscall_trace_exit(struct pt_regs *regs)
audit_syscall_exit(regs);
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_exit(regs, regs->gr[20]);
+#endif
+
if (stepping || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, stepping);
}
+
+
+/*
+ * regset functions.
+ */
+
+static int fpr_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs = task_regs(target);
+ __u64 *k = kbuf;
+ __u64 __user *u = ubuf;
+ __u64 reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < ELF_NFPREG; --count)
+ *k++ = regs->fr[pos++];
+ else
+ for (; count > 0 && pos < ELF_NFPREG; --count)
+ if (__put_user(regs->fr[pos++], u++))
+ return -EFAULT;
+
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ ELF_NFPREG * sizeof(reg), -1);
+}
+
+static int fpr_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct pt_regs *regs = task_regs(target);
+ const __u64 *k = kbuf;
+ const __u64 __user *u = ubuf;
+ __u64 reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < ELF_NFPREG; --count)
+ regs->fr[pos++] = *k++;
+ else
+ for (; count > 0 && pos < ELF_NFPREG; --count) {
+ if (__get_user(reg, u++))
+ return -EFAULT;
+ regs->fr[pos++] = reg;
+ }
+
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ ELF_NFPREG * sizeof(reg), -1);
+}
+
+#define RI(reg) (offsetof(struct user_regs_struct,reg) / sizeof(long))
+
+static unsigned long get_reg(struct pt_regs *regs, int num)
+{
+ switch (num) {
+ case RI(gr[0]) ... RI(gr[31]): return regs->gr[num - RI(gr[0])];
+ case RI(sr[0]) ... RI(sr[7]): return regs->sr[num - RI(sr[0])];
+ case RI(iasq[0]): return regs->iasq[0];
+ case RI(iasq[1]): return regs->iasq[1];
+ case RI(iaoq[0]): return regs->iaoq[0];
+ case RI(iaoq[1]): return regs->iaoq[1];
+ case RI(sar): return regs->sar;
+ case RI(iir): return regs->iir;
+ case RI(isr): return regs->isr;
+ case RI(ior): return regs->ior;
+ case RI(ipsw): return regs->ipsw;
+ case RI(cr27): return regs->cr27;
+ case RI(cr0): return mfctl(0);
+ case RI(cr24): return mfctl(24);
+ case RI(cr25): return mfctl(25);
+ case RI(cr26): return mfctl(26);
+ case RI(cr28): return mfctl(28);
+ case RI(cr29): return mfctl(29);
+ case RI(cr30): return mfctl(30);
+ case RI(cr31): return mfctl(31);
+ case RI(cr8): return mfctl(8);
+ case RI(cr9): return mfctl(9);
+ case RI(cr12): return mfctl(12);
+ case RI(cr13): return mfctl(13);
+ case RI(cr10): return mfctl(10);
+ case RI(cr15): return mfctl(15);
+ default: return 0;
+ }
+}
+
+static void set_reg(struct pt_regs *regs, int num, unsigned long val)
+{
+ switch (num) {
+ case RI(gr[0]): /*
+ * PSW is in gr[0].
+ * Allow writing to Nullify, Divide-step-correction,
+ * and carry/borrow bits.
+ * BEWARE, if you set N, and then single step, it won't
+ * stop on the nullified instruction.
+ */
+ val &= USER_PSW_BITS;
+ regs->gr[0] &= ~USER_PSW_BITS;
+ regs->gr[0] |= val;
+ return;
+ case RI(gr[1]) ... RI(gr[31]):
+ regs->gr[num - RI(gr[0])] = val;
+ return;
+ case RI(iaoq[0]):
+ case RI(iaoq[1]):
+ regs->iaoq[num - RI(iaoq[0])] = val;
+ return;
+ case RI(sar): regs->sar = val;
+ return;
+ default: return;
+#if 0
+ /* do not allow to change any of the following registers (yet) */
+ case RI(sr[0]) ... RI(sr[7]): return regs->sr[num - RI(sr[0])];
+ case RI(iasq[0]): return regs->iasq[0];
+ case RI(iasq[1]): return regs->iasq[1];
+ case RI(iir): return regs->iir;
+ case RI(isr): return regs->isr;
+ case RI(ior): return regs->ior;
+ case RI(ipsw): return regs->ipsw;
+ case RI(cr27): return regs->cr27;
+ case cr0, cr24, cr25, cr26, cr27, cr28, cr29, cr30, cr31;
+ case cr8, cr9, cr12, cr13, cr10, cr15;
+#endif
+ }
+}
+
+static int gpr_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs = task_regs(target);
+ unsigned long *k = kbuf;
+ unsigned long __user *u = ubuf;
+ unsigned long reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < ELF_NGREG; --count)
+ *k++ = get_reg(regs, pos++);
+ else
+ for (; count > 0 && pos < ELF_NGREG; --count)
+ if (__put_user(get_reg(regs, pos++), u++))
+ return -EFAULT;
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ ELF_NGREG * sizeof(reg), -1);
+}
+
+static int gpr_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct pt_regs *regs = task_regs(target);
+ const unsigned long *k = kbuf;
+ const unsigned long __user *u = ubuf;
+ unsigned long reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < ELF_NGREG; --count)
+ set_reg(regs, pos++, *k++);
+ else
+ for (; count > 0 && pos < ELF_NGREG; --count) {
+ if (__get_user(reg, u++))
+ return -EFAULT;
+ set_reg(regs, pos++, reg);
+ }
+
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ ELF_NGREG * sizeof(reg), -1);
+}
+
+static const struct user_regset native_regsets[] = {
+ [REGSET_GENERAL] = {
+ .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .get = gpr_get, .set = gpr_set
+ },
+ [REGSET_FP] = {
+ .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ .size = sizeof(__u64), .align = sizeof(__u64),
+ .get = fpr_get, .set = fpr_set
+ }
+};
+
+static const struct user_regset_view user_parisc_native_view = {
+ .name = "parisc", .e_machine = ELF_ARCH, .ei_osabi = ELFOSABI_LINUX,
+ .regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
+};
+
+#ifdef CONFIG_64BIT
+#include <linux/compat.h>
+
+static int gpr32_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs = task_regs(target);
+ compat_ulong_t *k = kbuf;
+ compat_ulong_t __user *u = ubuf;
+ compat_ulong_t reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < ELF_NGREG; --count)
+ *k++ = get_reg(regs, pos++);
+ else
+ for (; count > 0 && pos < ELF_NGREG; --count)
+ if (__put_user((compat_ulong_t) get_reg(regs, pos++), u++))
+ return -EFAULT;
+
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ ELF_NGREG * sizeof(reg), -1);
+}
+
+static int gpr32_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct pt_regs *regs = task_regs(target);
+ const compat_ulong_t *k = kbuf;
+ const compat_ulong_t __user *u = ubuf;
+ compat_ulong_t reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < ELF_NGREG; --count)
+ set_reg(regs, pos++, *k++);
+ else
+ for (; count > 0 && pos < ELF_NGREG; --count) {
+ if (__get_user(reg, u++))
+ return -EFAULT;
+ set_reg(regs, pos++, reg);
+ }
+
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ ELF_NGREG * sizeof(reg), -1);
+}
+
+/*
+ * These are the regset flavors matching the 32bit native set.
+ */
+static const struct user_regset compat_regsets[] = {
+ [REGSET_GENERAL] = {
+ .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ .size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
+ .get = gpr32_get, .set = gpr32_set
+ },
+ [REGSET_FP] = {
+ .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ .size = sizeof(__u64), .align = sizeof(__u64),
+ .get = fpr_get, .set = fpr_set
+ }
+};
+
+static const struct user_regset_view user_parisc_compat_view = {
+ .name = "parisc", .e_machine = EM_PARISC, .ei_osabi = ELFOSABI_LINUX,
+ .regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
+};
+#endif /* CONFIG_64BIT */
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ BUILD_BUG_ON(sizeof(struct user_regs_struct)/sizeof(long) != ELF_NGREG);
+ BUILD_BUG_ON(sizeof(struct user_fp_struct)/sizeof(__u64) != ELF_NFPREG);
+#ifdef CONFIG_64BIT
+ if (is_compat_task())
+ return &user_parisc_compat_view;
+#endif
+ return &user_parisc_native_view;
+}
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 57b4836b7ecd..d03422e5f188 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -912,6 +912,7 @@ END(lws_table)
.align 8
ENTRY(sys_call_table)
+ .export sys_call_table,data
#include "syscall_table.S"
END(sys_call_table)
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 400acac0a304..31ec99a5f119 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -38,6 +38,18 @@
static unsigned long clocktick __read_mostly; /* timer cycles per tick */
+#ifndef CONFIG_64BIT
+/*
+ * The processor-internal cycle counter (Control Register 16) is used as time
+ * source for the sched_clock() function. This register is 64bit wide on a
+ * 64-bit kernel and 32bit on a 32-bit kernel. Since sched_clock() always
+ * requires a 64bit counter we emulate on the 32-bit kernel the higher 32bits
+ * with a per-cpu variable which we increase every time the counter
+ * wraps-around (which happens every ~4 secounds).
+ */
+static DEFINE_PER_CPU(unsigned long, cr16_high_32_bits);
+#endif
+
/*
* We keep time on PA-RISC Linux by using the Interval Timer which is
* a pair of registers; one is read-only and one is write-only; both
@@ -108,6 +120,12 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
*/
mtctl(next_tick, 16);
+#if !defined(CONFIG_64BIT)
+ /* check for overflow on a 32bit kernel (every ~4 seconds). */
+ if (unlikely(next_tick < now))
+ this_cpu_inc(cr16_high_32_bits);
+#endif
+
/* Skip one clocktick on purpose if we missed next_tick.
* The new CR16 must be "later" than current CR16 otherwise
* itimer would not fire until CR16 wrapped - e.g 4 seconds
@@ -219,6 +237,12 @@ void __init start_cpu_itimer(void)
unsigned int cpu = smp_processor_id();
unsigned long next_tick = mfctl(16) + clocktick;
+#if defined(CONFIG_HAVE_UNSTABLE_SCHED_CLOCK) && defined(CONFIG_64BIT)
+ /* With multiple 64bit CPUs online, the cr16's are not syncronized. */
+ if (cpu != 0)
+ clear_sched_clock_stable();
+#endif
+
mtctl(next_tick, 16); /* kick off Interval Timer (CR16) */
per_cpu(cpu_data, cpu).it_value = next_tick;
@@ -246,15 +270,47 @@ void read_persistent_clock(struct timespec *ts)
}
}
+
+/*
+ * sched_clock() framework
+ */
+
+static u32 cyc2ns_mul __read_mostly;
+static u32 cyc2ns_shift __read_mostly;
+
+u64 sched_clock(void)
+{
+ u64 now;
+
+ /* Get current cycle counter (Control Register 16). */
+#ifdef CONFIG_64BIT
+ now = mfctl(16);
+#else
+ now = mfctl(16) + (((u64) this_cpu_read(cr16_high_32_bits)) << 32);
+#endif
+
+ /* return the value in ns (cycles_2_ns) */
+ return mul_u64_u32_shr(now, cyc2ns_mul, cyc2ns_shift);
+}
+
+
+/*
+ * timer interrupt and sched_clock() initialization
+ */
+
void __init time_init(void)
{
unsigned long current_cr16_khz;
+ current_cr16_khz = PAGE0->mem_10msec/10; /* kHz */
clocktick = (100 * PAGE0->mem_10msec) / HZ;
+ /* calculate mult/shift values for cr16 */
+ clocks_calc_mult_shift(&cyc2ns_mul, &cyc2ns_shift, current_cr16_khz,
+ NSEC_PER_MSEC, 0);
+
start_cpu_itimer(); /* get CPU 0 started */
/* register at clocksource framework */
- current_cr16_khz = PAGE0->mem_10msec/10; /* kHz */
clocksource_register_khz(&clocksource_cr16, current_cr16_khz);
}
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index d7c0acb35ec2..2b65c0177778 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -28,6 +28,7 @@
#include <linux/ratelimit.h>
#include <asm/uaccess.h>
#include <asm/hardirq.h>
+#include <asm/traps.h>
/* #define DEBUG_UNALIGNED 1 */
@@ -130,8 +131,6 @@
int unaligned_enabled __read_mostly = 1;
-void die_if_kernel (char *str, struct pt_regs *regs, long err);
-
static int emulate_ldh(struct pt_regs *regs, int toreg)
{
unsigned long saddr = regs->ior;
@@ -666,7 +665,7 @@ void handle_unaligned(struct pt_regs *regs)
break;
}
- if (modify && R1(regs->iir))
+ if (ret == 0 && modify && R1(regs->iir))
regs->gr[R1(regs->iir)] = newbase;
@@ -677,6 +676,14 @@ void handle_unaligned(struct pt_regs *regs)
if (ret)
{
+ /*
+ * The unaligned handler failed.
+ * If we were called by __get_user() or __put_user() jump
+ * to it's exception fixup handler instead of crashing.
+ */
+ if (!user_mode(regs) && fixup_exception(regs))
+ return;
+
printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
die_if_kernel("Unaligned data reference", regs, 28);
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index ddd988b267a9..e278a87f43cc 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -75,7 +75,10 @@ find_unwind_entry(unsigned long addr)
if (addr >= kernel_unwind_table.start &&
addr <= kernel_unwind_table.end)
e = find_unwind_entry_in_table(&kernel_unwind_table, addr);
- else
+ else {
+ unsigned long flags;
+
+ spin_lock_irqsave(&unwind_lock, flags);
list_for_each_entry(table, &unwind_tables, list) {
if (addr >= table->start &&
addr <= table->end)
@@ -86,6 +89,8 @@ find_unwind_entry(unsigned long addr)
break;
}
}
+ spin_unlock_irqrestore(&unwind_lock, flags);
+ }
return e;
}
@@ -303,18 +308,16 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
insn = *(unsigned int *)npc;
- if ((insn & 0xffffc000) == 0x37de0000 ||
- (insn & 0xffe00000) == 0x6fc00000) {
+ if ((insn & 0xffffc001) == 0x37de0000 ||
+ (insn & 0xffe00001) == 0x6fc00000) {
/* ldo X(sp), sp, or stwm X,D(sp) */
- frame_size += (insn & 0x1 ? -1 << 13 : 0) |
- ((insn & 0x3fff) >> 1);
+ frame_size += (insn & 0x3fff) >> 1;
dbg("analyzing func @ %lx, insn=%08x @ "
"%lx, frame_size = %ld\n", info->ip,
insn, npc, frame_size);
- } else if ((insn & 0xffe00008) == 0x73c00008) {
+ } else if ((insn & 0xffe00009) == 0x73c00008) {
/* std,ma X,D(sp) */
- frame_size += (insn & 0x1 ? -1 << 13 : 0) |
- (((insn >> 4) & 0x3ff) << 3);
+ frame_size += ((insn >> 4) & 0x3ff) << 3;
dbg("analyzing func @ %lx, insn=%08x @ "
"%lx, frame_size = %ld\n", info->ip,
insn, npc, frame_size);
@@ -333,6 +336,9 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
}
}
+ if (frame_size > e->Total_frame_size << 3)
+ frame_size = e->Total_frame_size << 3;
+
if (!unwind_special(info, e->region_start, frame_size)) {
info->prev_sp = info->sp - frame_size;
if (e->Millicode)
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 187118841af1..8e45b0a97abf 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -55,11 +55,10 @@ unsigned long __xchg8(char x, char *ptr)
}
-#ifdef CONFIG_64BIT
-unsigned long __cmpxchg_u64(volatile unsigned long *ptr, unsigned long old, unsigned long new)
+u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new)
{
unsigned long flags;
- unsigned long prev;
+ u64 prev;
_atomic_spin_lock_irqsave(ptr, flags);
if ((prev = *ptr) == old)
@@ -67,7 +66,6 @@ unsigned long __cmpxchg_u64(volatile unsigned long *ptr, unsigned long old, unsi
_atomic_spin_unlock_irqrestore(ptr, flags);
return prev;
}
-#endif
unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsigned int new)
{
diff --git a/arch/parisc/math-emu/fpudispatch.c b/arch/parisc/math-emu/fpudispatch.c
index 673b73e8420d..18df1237c93c 100644
--- a/arch/parisc/math-emu/fpudispatch.c
+++ b/arch/parisc/math-emu/fpudispatch.c
@@ -184,7 +184,7 @@ static void parisc_linux_get_fpu_type(u_int fpregs[])
/*
* this routine will decode the excepting floating point instruction and
- * call the approiate emulation routine.
+ * call the appropriate emulation routine.
* It is called by decode_fpu with the following parameters:
* fpudispatch(current_ir, unimplemented_code, 0, &Fpu_register)
* where current_ir is the instruction to be emulated,
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 01f7464d9fea..0a9d439bcda6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -128,7 +128,7 @@ config PPC
select IRQ_FORCED_THREADING
select HAVE_RCU_TABLE_FREE if SMP
select HAVE_SYSCALL_TRACEPOINTS
- select HAVE_CBPF_JIT
+ select HAVE_CBPF_JIT if CPU_BIG_ENDIAN
select HAVE_ARCH_JUMP_LABEL
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index a2350194fc76..8e21bb492dca 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -102,7 +102,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- tlb_flush_pgtable(tlb, address);
pgtable_page_dtor(table);
pgtable_free_tlb(tlb, page_address(table), 0);
}
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 290157e8d5b2..74839f24f412 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -88,6 +88,7 @@
#define HPTE_R_RPN_SHIFT 12
#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000)
#define HPTE_R_PP ASM_CONST(0x0000000000000003)
+#define HPTE_R_PPP ASM_CONST(0x8000000000000003)
#define HPTE_R_N ASM_CONST(0x0000000000000004)
#define HPTE_R_G ASM_CONST(0x0000000000000008)
#define HPTE_R_M ASM_CONST(0x0000000000000010)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 488279edb1f0..cd5e7aa8cc34 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -41,7 +41,7 @@ extern struct kmem_cache *pgtable_cache[];
pgtable_cache[(shift) - 1]; \
})
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int);
extern void pte_fragment_free(unsigned long *, int);
@@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
return (pgd_t *)__get_free_page(PGALLOC_GFP);
#else
struct page *page;
- page = alloc_pages(PGALLOC_GFP, 4);
+ page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4);
if (!page)
return NULL;
return (pgd_t *) page_address(page);
@@ -93,8 +93,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
- GFP_KERNEL|__GFP_REPEAT);
+ return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -110,13 +109,17 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
unsigned long address)
{
+ /*
+ * By now all the pud entries should be none entries. So go
+ * ahead and flush the page walk cache
+ */
+ flush_tlb_pgtable(tlb, address);
pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE);
}
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
- GFP_KERNEL|__GFP_REPEAT);
+ return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -127,6 +130,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long address)
{
+ /*
+ * By now all the pud entries should be none entries. So go
+ * ahead and flush the page walk cache
+ */
+ flush_tlb_pgtable(tlb, address);
return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX);
}
@@ -151,7 +159,7 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd)
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -198,7 +206,11 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- tlb_flush_pgtable(tlb, address);
+ /*
+ * By now all the pud entries should be none entries. So go
+ * ahead and flush the page walk cache
+ */
+ flush_tlb_pgtable(tlb, address);
pgtable_free_tlb(tlb, table, 0);
}
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 88a5ecaa157b..ab84c89c9e98 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -230,6 +230,7 @@ extern unsigned long __kernel_virt_size;
#define KERN_VIRT_SIZE __kernel_virt_size
extern struct page *vmemmap;
extern unsigned long ioremap_bot;
+extern unsigned long pci_io_base;
#endif /* __ASSEMBLY__ */
#include <asm/book3s/64/hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 937d4e247ac3..df294224e280 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -228,5 +228,20 @@ extern void radix__vmemmap_remove_mapping(unsigned long start,
extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
pgprot_t flags, unsigned int psz);
+
+static inline unsigned long radix__get_tree_size(void)
+{
+ unsigned long rts_field;
+ /*
+ * we support 52 bits, hence 52-31 = 21, 0b10101
+ * RTS encoding details
+ * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
+ * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
+ */
+ rts_field = (0x5UL << 5); /* 6 - 8 bits */
+ rts_field |= (0x2UL << 61);
+
+ return rts_field;
+}
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 13ef38828dfe..3fa94fcac628 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
unsigned long ap, int nid);
+extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
extern void radix__tlb_flush(struct mmu_gather *tlb);
#ifdef CONFIG_SMP
extern void radix__flush_tlb_mm(struct mm_struct *mm);
extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
unsigned long ap, int nid);
+extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
#else
#define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm)
#define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr)
#define radix___flush_tlb_page(mm,addr,p,i) radix___local_flush_tlb_page(mm,addr,p,i)
+#define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr)
#endif
#endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index d98424ae356c..96e5769b18b0 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -72,5 +72,19 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
#define flush_tlb_mm(mm) local_flush_tlb_mm(mm)
#define flush_tlb_page(vma, addr) local_flush_tlb_page(vma, addr)
#endif /* CONFIG_SMP */
+/*
+ * flush the page walk cache for the address
+ */
+static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+ /*
+ * Flush the page table walk cache on freeing a page table. We already
+ * have marked the upper/higher level page table entry none by now.
+ * So it is safe to flush PWC here.
+ */
+ if (!radix_enabled())
+ return;
+ radix__flush_tlb_pwc(tlb, address);
+}
#endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */
diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h
index 54f591e9572e..c0a69ae92256 100644
--- a/arch/powerpc/include/asm/book3s/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/pgalloc.h
@@ -4,11 +4,6 @@
#include <linux/mm.h>
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
- unsigned long address)
-{
-
-}
#ifdef CONFIG_PPC64
#include <asm/book3s/64/pgalloc.h>
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 0c12a3bfe2ab..897d2e1c8a9b 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -57,8 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
- GFP_KERNEL|__GFP_REPEAT);
+ return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -88,7 +87,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -172,7 +171,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
- pte_fragment_fre((unsigned long *)pte, 1);
+ pte_fragment_free((unsigned long *)pte, 1);
}
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
@@ -190,8 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
- GFP_KERNEL|__GFP_REPEAT);
+ return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c1e82e968506..a0948f40bc7b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -717,7 +717,7 @@
#define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */
#define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */
#define SPRN_MMCR1 798
-#define SPRN_MMCR2 769
+#define SPRN_MMCR2 785
#define SPRN_MMCRA 0x312
#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */
#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -754,13 +754,13 @@
#define SPRN_PMC6 792
#define SPRN_PMC7 793
#define SPRN_PMC8 794
-#define SPRN_SIAR 780
-#define SPRN_SDAR 781
#define SPRN_SIER 784
#define SIER_SIPR 0x2000000 /* Sampled MSR_PR */
#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */
#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */
#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */
+#define SPRN_SIAR 796
+#define SPRN_SDAR 797
#define SPRN_TACR 888
#define SPRN_TCSCR 889
#define SPRN_CSIGR 890
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2714a3b81d24..d70101e1e25c 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -642,13 +642,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
if (pe->type & EEH_PE_VF) {
eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
} else {
- eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
pci_lock_rescan_remove();
pci_hp_remove_devices(bus);
pci_unlock_rescan_remove();
}
} else if (frozen_bus) {
- eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data);
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
}
/*
@@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
*/
edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
- if (pe->type & EEH_PE_VF)
+ if (pe->type & EEH_PE_VF) {
eeh_add_virt_device(edev, NULL);
- else
+ } else {
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
pci_hp_add_devices(bus);
+ }
} else if (frozen_bus && rmv_data->removed) {
pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
ssleep(5);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4c9440629128..8bcc1b457115 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1399,11 +1399,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX)
lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */
mtlr r10
-BEGIN_MMU_FTR_SECTION
- b 2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
andi. r10,r12,MSR_RI /* check for unrecoverable exception */
+BEGIN_MMU_FTR_SECTION
beq- 2f
+FTR_SECTION_ELSE
+ b 2f
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
.machine push
.machine "power4"
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3759df52bd67..a5ae49a2dcc4 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -47,7 +47,6 @@ static int __init pcibios_init(void)
printk(KERN_INFO "PCI: Probing PCI hardware\n");
- pci_io_base = ISA_IO_BASE;
/* For now, override phys_mem_access_prot. If we need it,g
* later, we may move that initialization to each ppc_md
*/
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e2f12cbcade9..0b93893424f5 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
current->thread.regs = regs - 1;
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * Clear any transactional state, we're exec()ing. The cause is
+ * not important as there will never be a recheckpoint so it's not
+ * user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+#endif
+
memset(regs->gpr, 0, sizeof(regs->gpr));
regs->ctr = 0;
regs->link = 0;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index da5192590c44..6ee4b72cda42 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = {
W(0xffff0000), W(0x003e0000), /* POWER6 */
W(0xffff0000), W(0x003f0000), /* POWER7 */
W(0xffff0000), W(0x004b0000), /* POWER8E */
+ W(0xffff0000), W(0x004c0000), /* POWER8NVL */
W(0xffff0000), W(0x004d0000), /* POWER8 */
W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */
W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */
@@ -718,7 +719,7 @@ unsigned char ibm_architecture_vec[] = {
* must match by the macro below. Update the definition if
* the structure layout changes.
*/
-#define IBM_ARCH_VEC_NRCORES_OFFSET 125
+#define IBM_ARCH_VEC_NRCORES_OFFSET 133
W(NR_CPUS), /* number of cores supported */
0,
0,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 30a03c03fe73..060b140f03c6 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -377,7 +377,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
#else
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
- offsetof(struct thread_fp_state, fpr[32][0]));
+ offsetof(struct thread_fp_state, fpr[32]));
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&target->thread.fp_state, 0, -1);
@@ -405,7 +405,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
return 0;
#else
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
- offsetof(struct thread_fp_state, fpr[32][0]));
+ offsetof(struct thread_fp_state, fpr[32]));
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&target->thread.fp_state, 0, -1);
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index bf8f34a58670..b7019b559ddb 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
std r3, STK_PARAM(R3)(r1)
SAVE_NVGPRS(r1)
- /* We need to setup MSR for VSX register save instructions. Here we
- * also clear the MSR RI since when we do the treclaim, we won't have a
- * valid kernel pointer for a while. We clear RI here as it avoids
- * adding another mtmsr closer to the treclaim. This makes the region
- * maked as non-recoverable wider than it needs to be but it saves on
- * inserting another mtmsrd later.
- */
+ /* We need to setup MSR for VSX register save instructions. */
mfmsr r14
mr r15, r14
ori r15, r15, MSR_FP
- li r16, MSR_RI
+ li r16, 0
ori r16, r16, MSR_EE /* IRQs hard off */
andc r15, r15, r16
oris r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
1: tdeqi r6, 0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
- /* The moment we treclaim, ALL of our GPRs will switch
+ /* Clear MSR RI since we are about to change r1, EE is already off. */
+ li r4, 0
+ mtmsrd r4, 1
+
+ /*
+ * BE CAREFUL HERE:
+ * At this point we can't take an SLB miss since we have MSR_RI
+ * off. Load only to/from the stack/paca which are in SLB bolted regions
+ * until we turn MSR RI back on.
+ *
+ * The moment we treclaim, ALL of our GPRs will switch
* to user register state. (FPRs, CCR etc. also!)
* Use an sprg and a tm_scratch in the PACA to shuffle.
*/
@@ -197,6 +201,11 @@ dont_backup_fp:
/* Store the PPR in r11 and reset to decent value */
std r11, GPR11(r1) /* Temporary stash */
+
+ /* Reset MSR RI so we can take SLB faults again */
+ li r11, MSR_RI
+ mtmsrd r11, 1
+
mfspr r11, SPRN_PPR
HMT_MEDIUM
@@ -397,11 +406,6 @@ restore_gprs:
ld r5, THREAD_TM_DSCR(r3)
ld r6, THREAD_TM_PPR(r3)
- /* Clear the MSR RI since we are about to change R1. EE is already off
- */
- li r4, 0
- mtmsrd r4, 1
-
REST_GPR(0, r7) /* GPR0 */
REST_2GPRS(2, r7) /* GPR2-3 */
REST_GPR(4, r7) /* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
ld r6, _CCR(r7)
mtcr r6
- REST_GPR(1, r7) /* GPR1 */
- REST_GPR(5, r7) /* GPR5-7 */
REST_GPR(6, r7)
- ld r7, GPR7(r7)
+
+ /*
+ * Store r1 and r5 on the stack so that we can access them
+ * after we clear MSR RI.
+ */
+
+ REST_GPR(5, r7)
+ std r5, -8(r1)
+ ld r5, GPR1(r7)
+ std r5, -16(r1)
+
+ REST_GPR(7, r7)
+
+ /* Clear MSR RI since we are about to change r1. EE is already off */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /*
+ * BE CAREFUL HERE:
+ * At this point we can't take an SLB miss since we have MSR_RI
+ * off. Load only to/from the stack/paca which are in SLB bolted regions
+ * until we turn MSR RI back on.
+ */
+
+ ld r5, -8(r1)
+ ld r1, -16(r1)
/* Commit register state as checkpointed state: */
TRECHKPT
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index d873f6507f72..f8a871a72985 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
DBG_LOW(" -> hit\n");
/* Update the HPTE */
hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
- ~(HPTE_R_PP | HPTE_R_N)) |
- (newpp & (HPTE_R_PP | HPTE_R_N |
+ ~(HPTE_R_PPP | HPTE_R_N)) |
+ (newpp & (HPTE_R_PPP | HPTE_R_N |
HPTE_R_C)));
}
native_unlock_hpte(hptep);
@@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
/* Update the HPTE */
hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
- ~(HPTE_R_PP | HPTE_R_N)) |
- (newpp & (HPTE_R_PP | HPTE_R_N)));
+ ~(HPTE_R_PPP | HPTE_R_N)) |
+ (newpp & (HPTE_R_PPP | HPTE_R_N)));
/*
* Ensure it is out of the tlb too. Bolted entries base and
* actual page size will be same.
@@ -550,7 +550,11 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
}
}
/* This works for all page sizes, and for 256M and 1T segments */
- *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ *ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT;
+ else
+ *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
+
shift = mmu_psize_defs[size].shift;
avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 59268969a0bc..2971ea18c768 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
},
};
+/*
+ * 'R' and 'C' update notes:
+ * - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
+ * create writeable HPTEs without C set, because the hcall H_PROTECT
+ * that we use in that case will not update C
+ * - The above is however not a problem, because we also don't do that
+ * fancy "no flush" variant of eviction and we use H_REMOVE which will
+ * do the right thing and thus we don't have the race I described earlier
+ *
+ * - Under bare metal, we do have the race, so we need R and C set
+ * - We make sure R is always set and never lost
+ * - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
+ */
unsigned long htab_convert_pte_flags(unsigned long pteflags)
{
unsigned long rflags = 0;
@@ -186,19 +199,28 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
rflags |= 0x1;
}
/*
- * Always add "C" bit for perf. Memory coherence is always enabled
+ * We can't allow hardware to update hpte bits. Hence always
+ * set 'R' bit and set 'C' if it is a write fault
*/
- rflags |= HPTE_R_C | HPTE_R_M;
+ rflags |= HPTE_R_R;
+
+ if (pteflags & _PAGE_DIRTY)
+ rflags |= HPTE_R_C;
/*
* Add in WIG bits
*/
if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT)
rflags |= HPTE_R_I;
- if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT)
+ else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
rflags |= (HPTE_R_I | HPTE_R_G);
- if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
- rflags |= (HPTE_R_I | HPTE_R_W);
+ else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+ rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
+ else
+ /*
+ * Add memory coherence if cache inhibited is not set
+ */
+ rflags |= HPTE_R_M;
return rflags;
}
@@ -900,6 +922,10 @@ void __init hash__early_init_mmu(void)
vmemmap = (struct page *)H_VMEMMAP_BASE;
ioremap_bot = IOREMAP_BASE;
+#ifdef CONFIG_PCI
+ pci_io_base = ISA_IO_BASE;
+#endif
+
/* Initialize the MMU Hash table and create the linear mapping
* of memory. Has to be done before SLB initialization as this is
* currently where the page size encoding is obtained.
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5aac1a3f86cd..119d18611500 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -73,7 +73,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
cachep = PGT_CACHE(pdshift - pshift);
#endif
- new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
+ new = kmem_cache_zalloc(cachep, GFP_KERNEL);
BUG_ON(pshift > HUGEPD_SHIFT_MASK);
BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 227b2a6c4544..196222227e82 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -65,7 +65,7 @@ static int radix__init_new_context(struct mm_struct *mm, int index)
/*
* set the process table entry,
*/
- rts_field = 3ull << PPC_BITLSHIFT(2);
+ rts_field = radix__get_tree_size();
process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE);
return 0;
}
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index eb4451144746..670318766545 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -33,10 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
changed = !pmd_same(*(pmdp), entry);
if (changed) {
__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
- /*
- * Since we are not supporting SW TLB systems, we don't
- * have any thing similar to flush_tlb_page_nohash()
- */
+ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
return changed;
}
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 18b2c11604fa..7931e1496f0d 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -160,9 +160,8 @@ redo:
process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
/*
* Fill in the process table.
- * we support 52 bits, hence 52-28 = 24, 11000
*/
- rts_field = 3ull << PPC_BITLSHIFT(2);
+ rts_field = radix__get_tree_size();
process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);
/*
* Fill in the partition table. We are suppose to use effective address
@@ -176,10 +175,8 @@ redo:
static void __init radix_init_partition_table(void)
{
unsigned long rts_field;
- /*
- * we support 52 bits, hence 52-28 = 24, 11000
- */
- rts_field = 3ull << PPC_BITLSHIFT(2);
+
+ rts_field = radix__get_tree_size();
BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
@@ -296,11 +293,6 @@ found:
void __init radix__early_init_mmu(void)
{
unsigned long lpcr;
- /*
- * setup LPCR UPRT based on mmu_features
- */
- lpcr = mfspr(SPRN_LPCR);
- mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
#ifdef CONFIG_PPC_64K_PAGES
/* PAGE_SIZE mappings */
@@ -336,6 +328,11 @@ void __init radix__early_init_mmu(void)
__vmalloc_end = RADIX_VMALLOC_END;
vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
ioremap_bot = IOREMAP_BASE;
+
+#ifdef CONFIG_PCI
+ pci_io_base = ISA_IO_BASE;
+#endif
+
/*
* For now radix also use the same frag size
*/
@@ -343,8 +340,11 @@ void __init radix__early_init_mmu(void)
__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
radix_init_page_sizes();
- if (!firmware_has_feature(FW_FEATURE_LPAR))
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ lpcr = mfspr(SPRN_LPCR);
+ mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
radix_init_partition_table();
+ }
radix_init_pgtable();
}
@@ -353,16 +353,15 @@ void radix__early_init_mmu_secondary(void)
{
unsigned long lpcr;
/*
- * setup LPCR UPRT based on mmu_features
- */
- lpcr = mfspr(SPRN_LPCR);
- mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
- /*
- * update partition table control register, 64 K size.
+ * update partition table control register and UPRT
*/
- if (!firmware_has_feature(FW_FEATURE_LPAR))
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ lpcr = mfspr(SPRN_LPCR);
+ mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+
mtspr(SPRN_PTCR,
__pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+ }
}
void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index bf7bf32b54f8..7f922f557936 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -84,7 +84,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
pte_t *pte;
if (slab_is_available()) {
- pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
} else {
pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
if (pte)
@@ -97,7 +97,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *ptepage;
- gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+ gfp_t flags = GFP_KERNEL | __GFP_ZERO;
ptepage = alloc_pages(flags, 0);
if (!ptepage)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index e009e0604a8a..f5e8d4edb808 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -350,8 +350,7 @@ static pte_t *get_from_cache(struct mm_struct *mm)
static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
{
void *ret = NULL;
- struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
- __GFP_REPEAT | __GFP_ZERO);
+ struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
if (!page)
return NULL;
if (!kernel && !pgtable_page_ctor(page)) {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0fdaf93a3e09..ab2f60e812e2 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -18,16 +18,20 @@
static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbiel_pid(unsigned long pid, int set)
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
+static inline void __tlbiel_pid(unsigned long pid, int set,
+ unsigned long ric)
{
- unsigned long rb,rs,ric,prs,r;
+ unsigned long rb,rs,prs,r;
rb = PPC_BIT(53); /* IS = 1 */
rb |= set << PPC_BITLSHIFT(51);
rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
- ric = 2; /* invalidate all the caches */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set)
/*
* We use 128 set in radix mode and 256 set in hpt mode.
*/
-static inline void _tlbiel_pid(unsigned long pid)
+static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
{
int set;
for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
- __tlbiel_pid(pid, set);
+ __tlbiel_pid(pid, set, ric);
}
return;
}
-static inline void _tlbie_pid(unsigned long pid)
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
{
- unsigned long rb,rs,ric,prs,r;
+ unsigned long rb,rs,prs,r;
rb = PPC_BIT(53); /* IS = 1 */
rs = pid << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
- ric = 2; /* invalidate all the caches */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -67,16 +70,15 @@ static inline void _tlbie_pid(unsigned long pid)
}
static inline void _tlbiel_va(unsigned long va, unsigned long pid,
- unsigned long ap)
+ unsigned long ap, unsigned long ric)
{
- unsigned long rb,rs,ric,prs,r;
+ unsigned long rb,rs,prs,r;
rb = va & ~(PPC_BITMASK(52, 63));
rb |= ap << PPC_BITLSHIFT(58);
rs = pid << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
- ric = 0; /* no cluster flush yet */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -86,16 +88,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
}
static inline void _tlbie_va(unsigned long va, unsigned long pid,
- unsigned long ap)
+ unsigned long ap, unsigned long ric)
{
- unsigned long rb,rs,ric,prs,r;
+ unsigned long rb,rs,prs,r;
rb = va & ~(PPC_BITMASK(52, 63));
rb |= ap << PPC_BITLSHIFT(58);
rs = pid << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
- ric = 0; /* no cluster flush yet */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -117,25 +118,40 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
*/
void radix__local_flush_tlb_mm(struct mm_struct *mm)
{
- unsigned int pid;
+ unsigned long pid;
preempt_disable();
pid = mm->context.id;
if (pid != MMU_NO_CONTEXT)
- _tlbiel_pid(pid);
+ _tlbiel_pid(pid, RIC_FLUSH_ALL);
preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_tlb_mm);
+void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+ unsigned long pid;
+ struct mm_struct *mm = tlb->mm;
+
+ preempt_disable();
+
+ pid = mm->context.id;
+ if (pid != MMU_NO_CONTEXT)
+ _tlbiel_pid(pid, RIC_FLUSH_PWC);
+
+ preempt_enable();
+}
+EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
+
void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
unsigned long ap, int nid)
{
- unsigned int pid;
+ unsigned long pid;
preempt_disable();
pid = mm ? mm->context.id : 0;
if (pid != MMU_NO_CONTEXT)
- _tlbiel_va(vmaddr, pid, ap);
+ _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
preempt_enable();
}
@@ -160,7 +176,7 @@ static int mm_is_core_local(struct mm_struct *mm)
void radix__flush_tlb_mm(struct mm_struct *mm)
{
- unsigned int pid;
+ unsigned long pid;
preempt_disable();
pid = mm->context.id;
@@ -172,20 +188,46 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
- _tlbie_pid(pid);
+ _tlbie_pid(pid, RIC_FLUSH_ALL);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
} else
- _tlbiel_pid(pid);
+ _tlbiel_pid(pid, RIC_FLUSH_ALL);
no_context:
preempt_enable();
}
EXPORT_SYMBOL(radix__flush_tlb_mm);
+void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+ unsigned long pid;
+ struct mm_struct *mm = tlb->mm;
+
+ preempt_disable();
+
+ pid = mm->context.id;
+ if (unlikely(pid == MMU_NO_CONTEXT))
+ goto no_context;
+
+ if (!mm_is_core_local(mm)) {
+ int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+ if (lock_tlbie)
+ raw_spin_lock(&native_tlbie_lock);
+ _tlbie_pid(pid, RIC_FLUSH_PWC);
+ if (lock_tlbie)
+ raw_spin_unlock(&native_tlbie_lock);
+ } else
+ _tlbiel_pid(pid, RIC_FLUSH_PWC);
+no_context:
+ preempt_enable();
+}
+EXPORT_SYMBOL(radix__flush_tlb_pwc);
+
void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
unsigned long ap, int nid)
{
- unsigned int pid;
+ unsigned long pid;
preempt_disable();
pid = mm ? mm->context.id : 0;
@@ -196,11 +238,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
- _tlbie_va(vmaddr, pid, ap);
+ _tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
} else
- _tlbiel_va(vmaddr, pid, ap);
+ _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
bail:
preempt_enable();
}
@@ -224,7 +266,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
- _tlbie_pid(0);
+ _tlbie_pid(0, RIC_FLUSH_ALL);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
}
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 26d37e6f924e..0fc26714780a 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -47,7 +47,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
}
void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
unsigned long sp, next_sp;
unsigned long next_ip;
@@ -76,7 +76,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
next_ip = regs->nip;
lr = regs->link;
level = 0;
- perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+ perf_callchain_store_context(entry, PERF_CONTEXT_KERNEL);
} else {
if (level == 0)
@@ -232,7 +232,7 @@ static int sane_signal_64_frame(unsigned long sp)
puc == (unsigned long) &sf->uc;
}
-static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long sp, next_sp;
@@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
- while (entry->nr < sysctl_perf_event_max_stack) {
+ while (entry->nr < entry->max_stack) {
fp = (unsigned long __user *) sp;
if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
return;
@@ -274,7 +274,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
read_user_stack_64(&uregs[PT_R1], &sp))
return;
level = 0;
- perf_callchain_store(entry, PERF_CONTEXT_USER);
+ perf_callchain_store_context(entry, PERF_CONTEXT_USER);
perf_callchain_store(entry, next_ip);
continue;
}
@@ -319,7 +319,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
return rc;
}
-static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
@@ -439,7 +439,7 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
return mctx->mc_gregs;
}
-static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned int sp, next_sp;
@@ -453,7 +453,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
- while (entry->nr < sysctl_perf_event_max_stack) {
+ while (entry->nr < entry->max_stack) {
fp = (unsigned int __user *) (unsigned long) sp;
if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
return;
@@ -473,7 +473,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
read_user_stack_32(&uregs[PT_R1], &sp))
return;
level = 0;
- perf_callchain_store(entry, PERF_CONTEXT_USER);
+ perf_callchain_store_context(entry, PERF_CONTEXT_USER);
perf_callchain_store(entry, next_ip);
continue;
}
@@ -487,7 +487,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
}
void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
if (current_is_64bit())
perf_callchain_user_64(entry, regs);
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index c50ea76ba66c..6081fbd75330 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -221,7 +221,7 @@ static bool soc_has_mclk_mux0_canin(void)
/* convenience wrappers around the common clk API */
static inline struct clk *mpc512x_clk_fixed(const char *name, int rate)
{
- return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate);
+ return clk_register_fixed_rate(NULL, name, NULL, 0, rate);
}
static inline struct clk *mpc512x_clk_factor(
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 84fb984f29c1..85c85eb3e245 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -172,7 +172,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
if (rc < 0)
goto out;
- skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos;
+ skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
if (!dump_skip(cprm, skip))
goto Eio;
out:
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd97e059..3998e0f9a03b 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -53,7 +53,6 @@ static int ibm_read_slot_reset_state2;
static int ibm_slot_error_detail;
static int ibm_get_config_addr_info;
static int ibm_get_config_addr_info2;
-static int ibm_configure_bridge;
static int ibm_configure_pe;
/*
@@ -81,7 +80,14 @@ static int pseries_eeh_init(void)
ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2");
ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info");
ibm_configure_pe = rtas_token("ibm,configure-pe");
- ibm_configure_bridge = rtas_token("ibm,configure-bridge");
+
+ /*
+ * ibm,configure-pe and ibm,configure-bridge have the same semantics,
+ * however ibm,configure-pe can be faster. If we can't find
+ * ibm,configure-pe then fall back to using ibm,configure-bridge.
+ */
+ if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE)
+ ibm_configure_pe = rtas_token("ibm,configure-bridge");
/*
* Necessary sanity check. We needn't check "get-config-addr-info"
@@ -93,8 +99,7 @@ static int pseries_eeh_init(void)
(ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) ||
ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE ||
- (ibm_configure_pe == RTAS_UNKNOWN_SERVICE &&
- ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) {
+ ibm_configure_pe == RTAS_UNKNOWN_SERVICE) {
pr_info("EEH functionality not supported\n");
return -EINVAL;
}
@@ -615,29 +620,41 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
{
int config_addr;
int ret;
+ /* Waiting 0.2s maximum before skipping configuration */
+ int max_wait = 200;
/* Figure out the PE address */
config_addr = pe->config_addr;
if (pe->addr)
config_addr = pe->addr;
- /* Use new configure-pe function, if supported */
- if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+ while (max_wait > 0) {
ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
config_addr, BUID_HI(pe->phb->buid),
BUID_LO(pe->phb->buid));
- } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
- ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
- config_addr, BUID_HI(pe->phb->buid),
- BUID_LO(pe->phb->buid));
- } else {
- return -EFAULT;
- }
- if (ret)
- pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
- __func__, pe->phb->global_number, pe->addr, ret);
+ if (!ret)
+ return ret;
+
+ /*
+ * If RTAS returns a delay value that's above 100ms, cut it
+ * down to 100ms in case firmware made a mistake. For more
+ * on how these delay values work see rtas_busy_delay_time
+ */
+ if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+ ret <= RTAS_EXTENDED_DELAY_MAX)
+ ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+ max_wait -= rtas_busy_delay_time(ret);
+
+ if (max_wait < 0)
+ break;
+
+ rtas_busy_delay(ret);
+ }
+ pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+ __func__, pe->phb->global_number, pe->addr, ret);
return ret;
}
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index b7dfc1359d01..3e8865b187de 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -927,7 +927,7 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
dn = pci_device_to_OF_node(dev);
pdn = PCI_DN(dn);
buid = pdn->phb->buid;
- cfg_addr = (pdn->busno << 8) | pdn->devfn;
+ cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
cfg_addr, BUID_HI(buid), BUID_LO(buid));
@@ -956,7 +956,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
dn = pci_device_to_OF_node(dev);
pdn = PCI_DN(dn);
buid = pdn->phb->buid;
- cfg_addr = (pdn->busno << 8) | pdn->devfn;
+ cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
do {
/* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 0d112b94d91d..ff75d70f7285 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
*/
static long
axon_ram_direct_access(struct block_device *device, sector_t sector,
- void __pmem **kaddr, pfn_t *pfn)
+ void __pmem **kaddr, pfn_t *pfn, long size)
{
struct axon_ram_bank *bank = device->bd_disk->private_data;
loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index fac6ac9790fa..1dd210347e12 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -22,7 +22,6 @@ OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
$(call if_changed,ld)
- @:
sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 0x\1/p'
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 0ac42cc4f880..d5ec71b2ed02 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -1,8 +1,7 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
-CONFIG_FHANDLE=y
CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
+CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
@@ -13,19 +12,19 @@ CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_NUMA_BALANCING=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
-CONFIG_MEMCG_KMEM=y
-CONFIG_CGROUP_HUGETLB=y
-CONFIG_CGROUP_PERF=y
+CONFIG_BLK_CGROUP=y
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
-CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
@@ -55,7 +54,6 @@ CONFIG_UNIXWARE_DISKLABEL=y
CONFIG_CFQ_GROUP_IOSCHED=y
CONFIG_DEFAULT_DEADLINE=y
CONFIG_LIVEPATCH=y
-CONFIG_MARCH_Z196=y
CONFIG_TUNE_ZEC12=y
CONFIG_NR_CPUS=256
CONFIG_NUMA=y
@@ -65,6 +63,15 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CLEANCACHE=y
+CONFIG_FRONTSWAP=y
+CONFIG_CMA=y
+CONFIG_MEM_SOFT_DIRTY=y
+CONFIG_ZPOOL=m
+CONFIG_ZBUD=m
+CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC_STAT=y
+CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_PCI=y
CONFIG_PCI_DEBUG=y
CONFIG_HOTPLUG_PCI=y
@@ -452,6 +459,7 @@ CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
@@ -537,6 +545,8 @@ CONFIG_DLM=m
CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
CONFIG_FRAME_WARN=1024
CONFIG_READABLE_ASM=y
CONFIG_UNUSED_SYMBOLS=y
@@ -555,13 +565,17 @@ CONFIG_SLUB_DEBUG_ON=y
CONFIG_SLUB_STATS=y
CONFIG_DEBUG_STACK_USAGE=y
CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_VM_VMACACHE=y
CONFIG_DEBUG_VM_RB=y
+CONFIG_DEBUG_VM_PGFLAGS=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
CONFIG_DEBUG_PER_CPU_MAPS=y
CONFIG_DEBUG_SHIRQ=y
CONFIG_DETECT_HUNG_TASK=y
+CONFIG_WQ_WATCHDOG=y
CONFIG_PANIC_ON_OOPS=y
+CONFIG_DEBUG_TIMEKEEPING=y
CONFIG_TIMER_STATS=y
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
@@ -596,6 +610,8 @@ CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_UPROBE_EVENT=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
CONFIG_TEST_LIST_SORT=y
CONFIG_KPROBES_SANITY_TEST=y
@@ -607,7 +623,6 @@ CONFIG_TEST_STRING_HELPERS=y
CONFIG_TEST_KSTRTOX=y
CONFIG_DMA_API_DEBUG=y
CONFIG_TEST_BPF=m
-# CONFIG_STRICT_DEVMEM is not set
CONFIG_S390_PTDUMP=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
@@ -651,7 +666,6 @@ CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=y
CONFIG_CRYPTO_LZO=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
@@ -664,7 +678,7 @@ CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_ASYMMETRIC_KEY_TYPE=m
+CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CRC7=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index a31dcd56f7c0..f46a35115d2d 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -1,8 +1,7 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
-CONFIG_FHANDLE=y
CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
+CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
@@ -13,17 +12,17 @@ CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_NUMA_BALANCING=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
-CONFIG_MEMCG_KMEM=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
-CONFIG_BLK_CGROUP=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
@@ -53,7 +52,6 @@ CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
CONFIG_CFQ_GROUP_IOSCHED=y
CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z196=y
CONFIG_TUNE_ZEC12=y
CONFIG_NR_CPUS=256
CONFIG_NUMA=y
@@ -62,6 +60,14 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CLEANCACHE=y
+CONFIG_FRONTSWAP=y
+CONFIG_CMA=y
+CONFIG_ZSWAP=y
+CONFIG_ZBUD=m
+CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC_STAT=y
+CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_PCI=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
@@ -530,6 +536,8 @@ CONFIG_NLS_UTF8=m
CONFIG_DLM=m
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FRAME_WARN=1024
CONFIG_UNUSED_SYMBOLS=y
@@ -547,13 +555,13 @@ CONFIG_LATENCYTOP=y
CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_BLK_DEV_IO_TRACE=y
# CONFIG_KPROBE_EVENT is not set
+CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
CONFIG_RBTREE_TEST=m
CONFIG_INTERVAL_TREE_TEST=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
-# CONFIG_STRICT_DEVMEM is not set
CONFIG_S390_PTDUMP=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
@@ -597,8 +605,6 @@ CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=y
-CONFIG_CRYPTO_LZO=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
CONFIG_CRYPTO_USER_API_HASH=m
@@ -610,7 +616,7 @@ CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_ASYMMETRIC_KEY_TYPE=m
+CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CRC7=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 7b73bf353345..ba0f2a58b8cd 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -1,8 +1,7 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
-CONFIG_FHANDLE=y
CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
+CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
@@ -14,17 +13,17 @@ CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_NUMA_BALANCING=y
# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
-CONFIG_MEMCG_KMEM=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
-CONFIG_BLK_CGROUP=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
@@ -53,7 +52,6 @@ CONFIG_UNIXWARE_DISKLABEL=y
CONFIG_CFQ_GROUP_IOSCHED=y
CONFIG_DEFAULT_DEADLINE=y
CONFIG_LIVEPATCH=y
-CONFIG_MARCH_Z196=y
CONFIG_TUNE_ZEC12=y
CONFIG_NR_CPUS=512
CONFIG_NUMA=y
@@ -62,6 +60,14 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CLEANCACHE=y
+CONFIG_FRONTSWAP=y
+CONFIG_CMA=y
+CONFIG_ZSWAP=y
+CONFIG_ZBUD=m
+CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC_STAT=y
+CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_PCI=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
@@ -447,6 +453,7 @@ CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
@@ -530,6 +537,8 @@ CONFIG_NLS_UTF8=m
CONFIG_DLM=m
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FRAME_WARN=1024
CONFIG_UNUSED_SYMBOLS=y
@@ -546,11 +555,12 @@ CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_UPROBE_EVENT=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
-# CONFIG_STRICT_DEVMEM is not set
CONFIG_S390_PTDUMP=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
@@ -594,8 +604,6 @@ CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=y
-CONFIG_CRYPTO_LZO=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
CONFIG_CRYPTO_USER_API_HASH=m
@@ -607,7 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_ASYMMETRIC_KEY_TYPE=m
+CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CRC7=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 1719843a55a2..4366a3e3e754 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -1,5 +1,5 @@
# CONFIG_SWAP is not set
-CONFIG_NO_HZ=y
+CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
@@ -7,7 +7,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z196=y
CONFIG_TUNE_ZEC12=y
# CONFIG_COMPAT is not set
CONFIG_NR_CPUS=2
@@ -64,7 +63,6 @@ CONFIG_PANIC_ON_OOPS=y
# CONFIG_SCHED_DEBUG is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=60
# CONFIG_FTRACE is not set
-# CONFIG_STRICT_DEVMEM is not set
# CONFIG_PFAULT is not set
# CONFIG_S390_HYPFS_FS is not set
# CONFIG_VIRTUALIZATION is not set
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index e24f2af4c73b..3f571ea89509 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,8 +1,8 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
-CONFIG_FHANDLE=y
+CONFIG_USELIB=y
CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
+CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
@@ -11,19 +11,19 @@ CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_CGROUPS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
-CONFIG_MEMCG_KMEM=y
-CONFIG_CGROUP_HUGETLB=y
-CONFIG_CGROUP_PERF=y
+CONFIG_BLK_CGROUP=y
CONFIG_CGROUP_SCHED=y
CONFIG_RT_GROUP_SCHED=y
-CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_BLK_DEV_INITRD=y
@@ -44,7 +44,6 @@ CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_DEFAULT_DEADLINE=y
CONFIG_LIVEPATCH=y
-CONFIG_MARCH_Z196=y
CONFIG_NR_CPUS=256
CONFIG_NUMA=y
CONFIG_HZ_100=y
@@ -52,6 +51,14 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CLEANCACHE=y
+CONFIG_FRONTSWAP=y
+CONFIG_CMA=y
+CONFIG_ZSWAP=y
+CONFIG_ZBUD=m
+CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC_STAT=y
+CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_CRASH_DUMP=y
CONFIG_BINFMT_MISC=m
CONFIG_HIBERNATION=y
@@ -61,7 +68,6 @@ CONFIG_UNIX=y
CONFIG_NET_KEY=y
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
-# CONFIG_INET_LRO is not set
CONFIG_L2TP=m
CONFIG_L2TP_DEBUGFS=m
CONFIG_VLAN_8021Q=y
@@ -144,6 +150,9 @@ CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_HUGETLBFS=y
# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
CONFIG_UNUSED_SYMBOLS=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
@@ -158,20 +167,21 @@ CONFIG_LOCK_STAT=y
CONFIG_DEBUG_LOCKDEP=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PI_LIST=y
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_RCU_TRACE=y
CONFIG_LATENCYTOP=y
CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
-CONFIG_TRACER_SNAPSHOT=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_UPROBE_EVENT=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_KPROBES_SANITY_TEST=y
-# CONFIG_STRICT_DEVMEM is not set
CONFIG_S390_PTDUMP=y
CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_AUTHENC=m
@@ -212,8 +222,6 @@ CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_DEFLATE=m
-CONFIG_CRYPTO_ZLIB=m
-CONFIG_CRYPTO_LZO=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
CONFIG_CRYPTO_ANSI_CPRNG=m
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index 5e04f3cbd320..8ae236b0f80b 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc)
" la %0,0\n"
"1:\n"
EX_TABLE(0b,1b)
- : "=d" (rc), "=d" (orig_fpc)
+ : "=d" (rc), "=&d" (orig_fpc)
: "d" (fpc), "0" (-EINVAL));
return rc;
}
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 37b9017c6a96..ac82e8eb936d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -245,6 +245,7 @@ struct kvm_vcpu_stat {
u32 exit_stop_request;
u32 exit_validity;
u32 exit_instruction;
+ u32 exit_pei;
u32 halt_successful_poll;
u32 halt_attempted_poll;
u32 halt_poll_invalid;
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f20abdb5630a..d14069d4b88d 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2064,12 +2064,5 @@ void s390_reset_system(void)
S390_lowcore.program_new_psw.addr =
(unsigned long) s390_base_pgm_handler;
- /*
- * Clear subchannel ID and number to signal new kernel that no CCW or
- * SCSI IPL has been done (for kexec and kdump)
- */
- S390_lowcore.subchannel_id = 0;
- S390_lowcore.subchannel_nr = 0;
-
do_reset_calls();
}
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 59215c518f37..7ec63b1d920d 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -649,6 +649,8 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
/* Performance monitoring unit for s390x */
static struct pmu cpumf_pmu = {
+ .task_ctx_nr = perf_sw_context,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
.pmu_enable = cpumf_pmu_enable,
.pmu_disable = cpumf_pmu_disable,
.event_init = cpumf_pmu_event_init,
@@ -708,12 +710,6 @@ static int __init cpumf_pmu_init(void)
goto out;
}
- /* The CPU measurement counter facility does not have overflow
- * interrupts to do sampling. Sampling must be provided by
- * external means, for example, by timers.
- */
- cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
-
cpumf_pmu.attr_groups = cpumf_cf_event_group();
rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
if (rc) {
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index c3e4099b60a5..87035fa58bbe 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,13 +224,13 @@ arch_initcall(service_level_perf_register);
static int __perf_callchain_kernel(void *data, unsigned long address)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, address);
return 0;
}
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (user_mode(regs))
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 2e6b54e4d3f9..252157181302 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -341,6 +341,8 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
static int handle_partial_execution(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.exit_pei++;
+
if (vcpu->arch.sie_block->ipa == 0xb254) /* MVPG */
return handle_mvpg_pei(vcpu);
if (vcpu->arch.sie_block->ipa >> 8 == 0xae) /* SIGP */
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6d8ec3ac9dd8..43f2a2b80490 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -61,6 +61,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "exit_external_request", VCPU_STAT(exit_external_request) },
{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
{ "exit_instruction", VCPU_STAT(exit_instruction) },
+ { "exit_pei", VCPU_STAT(exit_pei) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
@@ -657,7 +658,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
kvm->arch.model.cpuid = proc->cpuid;
lowest_ibc = sclp.ibc >> 16 & 0xfff;
unblocked_ibc = sclp.ibc & 0xfff;
- if (lowest_ibc) {
+ if (lowest_ibc && proc->ibc) {
if (proc->ibc > unblocked_ibc)
kvm->arch.model.ibc = unblocked_ibc;
else if (proc->ibc < lowest_ibc)
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 7a3144017301..19288c1b36d3 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -250,6 +250,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
report_user_fault(regs, SIGSEGV, 1);
si.si_signo = SIGSEGV;
+ si.si_errno = 0;
si.si_code = si_code;
si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
force_sig_info(SIGSEGV, &si, current);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e8b5962ac12a..e2565d2d0c32 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
return table;
}
/* Allocate a fresh page */
- page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+ page = alloc_page(GFP_KERNEL);
if (!page)
return NULL;
if (!pgtable_page_ctor(page)) {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4324b87f9398..9f0ce0e6eeb4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -437,7 +437,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
pgste = pgste_get_lock(ptep);
pgstev = pgste_val(pgste);
pte = *ptep;
- if (pte_swap(pte) &&
+ if (!reset && pte_swap(pte) &&
((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
(pgstev & _PGSTE_GPS_ZERO))) {
ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index f010c93a88b1..fda605dbc1b4 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
* | | |
* +---------------+ |
* | 8 byte skbp | |
- * R15+170 -> +---------------+ |
+ * R15+176 -> +---------------+ |
* | 8 byte hlen | |
* R15+168 -> +---------------+ |
* | 4 byte align | |
@@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
#define STK_OFF (STK_SPACE - STK_160_UNUSED)
#define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */
#define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */
-#define STK_OFF_SKBP 170 /* Offset of SKB pointer on stack */
+#define STK_OFF_SKBP 176 /* Offset of SKB pointer on stack */
#define STK_OFF_R6 (160 - 11 * 8) /* Offset of r6 on stack */
#define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9133b0ec000b..bee281f3163d 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -45,7 +45,7 @@ struct bpf_jit {
int labels[1]; /* Labels for local jumps */
};
-#define BPF_SIZE_MAX 0x7ffff /* Max size for program (20 bit signed displ) */
+#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */
#define SEEN_SKB 1 /* skb access */
#define SEEN_MEM 2 /* use mem[] for temporary storage */
@@ -450,7 +450,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit)
emit_load_skb_data_hlen(jit);
if (jit->seen & SEEN_SKB_CHANGE)
/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
- EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
+ EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
STK_OFF_SKBP);
}
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 2e067657db98..49b012d78c1a 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
{
pte_t *pte;
- pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
- PTE_ORDER);
+ pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
return pte;
}
@@ -53,7 +52,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
{
struct page *pte;
- pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+ pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
if (!pte)
return NULL;
clear_highpage(pte);
diff --git a/arch/score/include/uapi/asm/unistd.h b/arch/score/include/uapi/asm/unistd.h
index 9cb4260a5f3e..d4008c339e89 100644
--- a/arch/score/include/uapi/asm/unistd.h
+++ b/arch/score/include/uapi/asm/unistd.h
@@ -1,5 +1,6 @@
#define __ARCH_HAVE_MMU
+#define __ARCH_WANT_RENAMEAT
#define __ARCH_WANT_SYSCALL_NO_AT
#define __ARCH_WANT_SYSCALL_NO_FLAGS
#define __ARCH_WANT_SYSCALL_OFF_T
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index 6df826ee7316..c4c47ea9fa94 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -55,7 +55,6 @@ $(addprefix $(obj)/,$(lib1funcs-y)): $(obj)/%: $(lib1funcs-dir)/% FORCE
$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(lib1funcs-obj) FORCE
$(call if_changed,ld)
- @:
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
diff --git a/arch/sh/boot/romimage/Makefile b/arch/sh/boot/romimage/Makefile
index 2216ee57f251..43c41191de5d 100644
--- a/arch/sh/boot/romimage/Makefile
+++ b/arch/sh/boot/romimage/Makefile
@@ -17,7 +17,6 @@ LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(load-y) -e romstart \
$(obj)/vmlinux: $(obj)/head.o $(obj-y) $(obj)/piggy.o FORCE
$(call if_changed,ld)
- @:
OBJCOPYFLAGS += -j .empty_zero_page
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index a33673b3687d..f3f42c84c40f 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+ return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -43,7 +43,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
struct page *page;
void *pg;
- pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+ pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
if (!pg)
return NULL;
page = virt_to_page(pg);
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index cc80b614b5fa..fa2c0cd23eaa 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -21,7 +21,7 @@ static int callchain_stack(void *data, char *name)
static void callchain_address(void *data, unsigned long addr, int reliable)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
if (reliable)
perf_callchain_store(entry, addr);
@@ -33,7 +33,7 @@ static const struct stacktrace_ops callchain_ops = {
};
void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
perf_callchain_store(entry, regs->pc);
diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c
index 26e03a1f7ca4..a62bd8696779 100644
--- a/arch/sh/mm/pgtable.c
+++ b/arch/sh/mm/pgtable.c
@@ -1,7 +1,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
-#define PGALLOC_GFP GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO
static struct kmem_cache *pgd_cachep;
#if PAGETABLE_LEVELS > 2
diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h
index 10e9dabc4c41..f0700cfeedd7 100644
--- a/arch/sparc/include/asm/head_64.h
+++ b/arch/sparc/include/asm/head_64.h
@@ -15,6 +15,10 @@
#define PTREGS_OFF (STACK_BIAS + STACKFRAME_SZ)
+#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
#define __CHEETAH_ID 0x003e0014
#define __JALAPENO_ID 0x003e0016
#define __SERRANO_ID 0x003e0022
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5e3187185b4a..3529f1378cd8 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -41,8 +41,7 @@ static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(pgtable_cache,
- GFP_KERNEL|__GFP_REPEAT);
+ return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -52,8 +51,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(pgtable_cache,
- GFP_KERNEL|__GFP_REPEAT);
+ return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 71b5a67522ab..781b9f1dbdc2 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -589,8 +589,8 @@ user_rtt_fill_64bit: \
restored; \
nop; nop; nop; nop; nop; nop; \
nop; nop; nop; nop; nop; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_dax; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_mna; \
ba,a,pt %xcc, user_rtt_fill_fixup;
@@ -652,8 +652,8 @@ user_rtt_fill_32bit: \
restored; \
nop; nop; nop; nop; nop; \
nop; nop; nop; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_dax; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_mna; \
ba,a,pt %xcc, user_rtt_fill_fixup;
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 7cf9c6ea3f1f..fdb13327fded 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg
CFLAGS_REMOVE_pcr.o := -pg
endif
+obj-$(CONFIG_SPARC64) += urtt_fill.o
obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o
obj-$(CONFIG_SPARC32) += etrap_32.o
obj-$(CONFIG_SPARC32) += rtrap_32.o
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index a4b8b5aed21c..710f3278d448 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1711,7 +1711,7 @@ static int __init init_hw_perf_events(void)
}
pure_initcall(init_hw_perf_events);
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long ksp, fp;
@@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
}
}
#endif
- } while (entry->nr < sysctl_perf_event_max_stack);
+ } while (entry->nr < entry->max_stack);
}
static inline int
@@ -1769,7 +1769,7 @@ valid_user_frame(const void __user *fp, unsigned long size)
return (__range_not_ok(fp, size, TASK_SIZE) == 0);
}
-static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long ufp;
@@ -1790,10 +1790,10 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
pc = sf.callers_pc;
ufp = (unsigned long)sf.fp + STACK_BIAS;
perf_callchain_store(entry, pc);
- } while (entry->nr < sysctl_perf_event_max_stack);
+ } while (entry->nr < entry->max_stack);
}
-static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long ufp;
@@ -1822,11 +1822,11 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
ufp = (unsigned long)sf.fp;
}
perf_callchain_store(entry, pc);
- } while (entry->nr < sysctl_perf_event_max_stack);
+ } while (entry->nr < entry->max_stack);
}
void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
u64 saved_fault_address = current_thread_info()->fault_address;
u8 saved_fault_code = get_thread_fault_code();
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index d08bdaffdbfc..216948ca4382 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -14,10 +14,6 @@
#include <asm/visasm.h>
#include <asm/processor.h>
-#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
-#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
-
#ifdef CONFIG_CONTEXT_TRACKING
# define SCHEDULE_USER schedule_user
#else
@@ -242,52 +238,17 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
wrpr %g1, %cwp
ba,a,pt %xcc, user_rtt_fill_64bit
-user_rtt_fill_fixup:
- rdpr %cwp, %g1
- add %g1, 1, %g1
- wrpr %g1, 0x0, %cwp
-
- rdpr %wstate, %g2
- sll %g2, 3, %g2
- wrpr %g2, 0x0, %wstate
-
- /* We know %canrestore and %otherwin are both zero. */
-
- sethi %hi(sparc64_kern_pri_context), %g2
- ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2
- mov PRIMARY_CONTEXT, %g1
-
-661: stxa %g2, [%g1] ASI_DMMU
- .section .sun4v_1insn_patch, "ax"
- .word 661b
- stxa %g2, [%g1] ASI_MMU
- .previous
-
- sethi %hi(KERNBASE), %g1
- flush %g1
+user_rtt_fill_fixup_dax:
+ ba,pt %xcc, user_rtt_fill_fixup_common
+ mov 1, %g3
- or %g4, FAULT_CODE_WINFIXUP, %g4
- stb %g4, [%g6 + TI_FAULT_CODE]
- stx %g5, [%g6 + TI_FAULT_ADDR]
+user_rtt_fill_fixup_mna:
+ ba,pt %xcc, user_rtt_fill_fixup_common
+ mov 2, %g3
- mov %g6, %l1
- wrpr %g0, 0x0, %tl
-
-661: nop
- .section .sun4v_1insn_patch, "ax"
- .word 661b
- SET_GL(0)
- .previous
-
- wrpr %g0, RTRAP_PSTATE, %pstate
-
- mov %l1, %g6
- ldx [%g6 + TI_TASK], %g4
- LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
- call do_sparc64_fault
- add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+user_rtt_fill_fixup:
+ ba,pt %xcc, user_rtt_fill_fixup_common
+ clr %g3
user_rtt_pre_restore:
add %g1, 1, %g1
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 3c25241fa5cb..91cc2f4ae4d9 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
return 0;
}
+/* Checks if the fp is valid. We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+ if ((((unsigned long) fp) & 15) ||
+ ((unsigned long)fp) > 0x100000000ULL - fplen)
+ return true;
+ return false;
+}
+
void do_sigreturn32(struct pt_regs *regs)
{
struct signal_frame32 __user *sf;
compat_uptr_t fpu_save;
compat_uptr_t rwin_save;
- unsigned int psr;
+ unsigned int psr, ufp;
unsigned int pc, npc;
sigset_t set;
compat_sigset_t seta;
@@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs)
sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
- (((unsigned long) sf) & 3))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
+ goto segv;
+
+ if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+ goto segv;
+
+ if (ufp & 0x7)
goto segv;
- if (get_user(pc, &sf->info.si_regs.pc) ||
+ if (__get_user(pc, &sf->info.si_regs.pc) ||
__get_user(npc, &sf->info.si_regs.npc))
goto segv;
@@ -227,7 +244,7 @@ segv:
asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
{
struct rt_signal_frame32 __user *sf;
- unsigned int psr, pc, npc;
+ unsigned int psr, pc, npc, ufp;
compat_uptr_t fpu_save;
compat_uptr_t rwin_save;
sigset_t set;
@@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
- (((unsigned long) sf) & 3))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
goto segv;
- if (get_user(pc, &sf->regs.pc) ||
+ if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+ goto segv;
+
+ if (ufp & 0x7)
+ goto segv;
+
+ if (__get_user(pc, &sf->regs.pc) ||
__get_user(npc, &sf->regs.npc))
goto segv;
@@ -307,14 +329,6 @@ segv:
force_sig(SIGSEGV, current);
}
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
-{
- if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen)
- return 1;
- return 0;
-}
-
static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
{
unsigned long sp;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 52aa5e4ce5e7..c3c12efe0bc0 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -60,10 +60,22 @@ struct rt_signal_frame {
#define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7)))
#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7)))
+/* Checks if the fp is valid. We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static inline bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+ if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+ return true;
+
+ return false;
+}
+
asmlinkage void do_sigreturn(struct pt_regs *regs)
{
+ unsigned long up_psr, pc, npc, ufp;
struct signal_frame __user *sf;
- unsigned long up_psr, pc, npc;
sigset_t set;
__siginfo_fpu_t __user *fpu_save;
__siginfo_rwin_t __user *rwin_save;
@@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+ if (!invalid_frame_pointer(sf, sizeof(*sf)))
+ goto segv_and_exit;
+
+ if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
goto segv_and_exit;
- if (((unsigned long) sf) & 3)
+ if (ufp & 0x7)
goto segv_and_exit;
err = __get_user(pc, &sf->info.si_regs.pc);
@@ -127,7 +142,7 @@ segv_and_exit:
asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
{
struct rt_signal_frame __user *sf;
- unsigned int psr, pc, npc;
+ unsigned int psr, pc, npc, ufp;
__siginfo_fpu_t __user *fpu_save;
__siginfo_rwin_t __user *rwin_save;
sigset_t set;
@@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
synchronize_user_stack();
sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
- (((unsigned long) sf) & 0x03))
+ if (!invalid_frame_pointer(sf, sizeof(*sf)))
+ goto segv;
+
+ if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+ goto segv;
+
+ if (ufp & 0x7)
goto segv;
err = __get_user(pc, &sf->regs.pc);
@@ -178,15 +198,6 @@ segv:
force_sig(SIGSEGV, current);
}
-/* Checks if the fp is valid */
-static inline int invalid_frame_pointer(void __user *fp, int fplen)
-{
- if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen))
- return 1;
-
- return 0;
-}
-
static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
{
unsigned long sp = regs->u_regs[UREG_FP];
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 39aaec173f66..5ee930c48f4c 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -234,6 +234,17 @@ do_sigsegv:
goto out;
}
+/* Checks if the fp is valid. We always build rt signal frames which
+ * are 16-byte aligned, therefore we can always enforce that the
+ * restore frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp)
+{
+ if (((unsigned long) fp) & 15)
+ return true;
+ return false;
+}
+
struct rt_signal_frame {
struct sparc_stackf ss;
siginfo_t info;
@@ -246,8 +257,8 @@ struct rt_signal_frame {
void do_rt_sigreturn(struct pt_regs *regs)
{
+ unsigned long tpc, tnpc, tstate, ufp;
struct rt_signal_frame __user *sf;
- unsigned long tpc, tnpc, tstate;
__siginfo_fpu_t __user *fpu_save;
__siginfo_rwin_t __user *rwin_save;
sigset_t set;
@@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs)
(regs->u_regs [UREG_FP] + STACK_BIAS);
/* 1. Make sure we are not getting garbage from the user */
- if (((unsigned long) sf) & 3)
+ if (invalid_frame_pointer(sf))
+ goto segv;
+
+ if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
goto segv;
- err = get_user(tpc, &sf->regs.tpc);
+ if ((ufp + STACK_BIAS) & 0x7)
+ goto segv;
+
+ err = __get_user(tpc, &sf->regs.tpc);
err |= __get_user(tnpc, &sf->regs.tnpc);
if (test_thread_flag(TIF_32BIT)) {
tpc &= 0xffffffff;
@@ -308,14 +325,6 @@ segv:
force_sig(SIGSEGV, current);
}
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp)
-{
- if (((unsigned long) fp) & 15)
- return 1;
- return 0;
-}
-
static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
{
unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
index 0f6eebe71e6c..e5fe8cef9a69 100644
--- a/arch/sparc/kernel/sigutil_32.c
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
{
int err;
+
+ if (((unsigned long) fpu) & 3)
+ return -EFAULT;
+
#ifdef CONFIG_SMP
if (test_tsk_thread_flag(current, TIF_USEDFPU))
regs->psr &= ~PSR_EF;
@@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
struct thread_info *t = current_thread_info();
int i, wsaved, err;
- __get_user(wsaved, &rp->wsaved);
+ if (((unsigned long) rp) & 3)
+ return -EFAULT;
+
+ get_user(wsaved, &rp->wsaved);
if (wsaved > NSWINS)
return -EFAULT;
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index 387834a9c56a..36aadcbeac69 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
unsigned long fprs;
int err;
- err = __get_user(fprs, &fpu->si_fprs);
+ if (((unsigned long) fpu) & 7)
+ return -EFAULT;
+
+ err = get_user(fprs, &fpu->si_fprs);
fprs_write(0);
regs->tstate &= ~TSTATE_PEF;
if (fprs & FPRS_DL)
@@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
struct thread_info *t = current_thread_info();
int i, wsaved, err;
- __get_user(wsaved, &rp->wsaved);
+ if (((unsigned long) rp) & 7)
+ return -EFAULT;
+
+ get_user(wsaved, &rp->wsaved);
if (wsaved > NSWINS)
return -EFAULT;
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
new file mode 100644
index 000000000000..5604a2b051d4
--- /dev/null
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -0,0 +1,98 @@
+#include <asm/thread_info.h>
+#include <asm/trap_block.h>
+#include <asm/spitfire.h>
+#include <asm/ptrace.h>
+#include <asm/head.h>
+
+ .text
+ .align 8
+ .globl user_rtt_fill_fixup_common
+user_rtt_fill_fixup_common:
+ rdpr %cwp, %g1
+ add %g1, 1, %g1
+ wrpr %g1, 0x0, %cwp
+
+ rdpr %wstate, %g2
+ sll %g2, 3, %g2
+ wrpr %g2, 0x0, %wstate
+
+ /* We know %canrestore and %otherwin are both zero. */
+
+ sethi %hi(sparc64_kern_pri_context), %g2
+ ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2
+ mov PRIMARY_CONTEXT, %g1
+
+661: stxa %g2, [%g1] ASI_DMMU
+ .section .sun4v_1insn_patch, "ax"
+ .word 661b
+ stxa %g2, [%g1] ASI_MMU
+ .previous
+
+ sethi %hi(KERNBASE), %g1
+ flush %g1
+
+ mov %g4, %l4
+ mov %g5, %l5
+ brnz,pn %g3, 1f
+ mov %g3, %l3
+
+ or %g4, FAULT_CODE_WINFIXUP, %g4
+ stb %g4, [%g6 + TI_FAULT_CODE]
+ stx %g5, [%g6 + TI_FAULT_ADDR]
+1:
+ mov %g6, %l1
+ wrpr %g0, 0x0, %tl
+
+661: nop
+ .section .sun4v_1insn_patch, "ax"
+ .word 661b
+ SET_GL(0)
+ .previous
+
+ wrpr %g0, RTRAP_PSTATE, %pstate
+
+ mov %l1, %g6
+ ldx [%g6 + TI_TASK], %g4
+ LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
+
+ brnz,pn %l3, 1f
+ nop
+
+ call do_sparc64_fault
+ add %sp, PTREGS_OFF, %o0
+ ba,pt %xcc, rtrap
+ nop
+
+1: cmp %g3, 2
+ bne,pn %xcc, 2f
+ nop
+
+ sethi %hi(tlb_type), %g1
+ lduw [%g1 + %lo(tlb_type)], %g1
+ cmp %g1, 3
+ bne,pt %icc, 1f
+ add %sp, PTREGS_OFF, %o0
+ mov %l4, %o2
+ call sun4v_do_mna
+ mov %l5, %o1
+ ba,a,pt %xcc, rtrap
+1: mov %l4, %o1
+ mov %l5, %o2
+ call mem_address_unaligned
+ nop
+ ba,a,pt %xcc, rtrap
+
+2: sethi %hi(tlb_type), %g1
+ mov %l4, %o1
+ lduw [%g1 + %lo(tlb_type)], %g1
+ mov %l5, %o2
+ cmp %g1, 3
+ bne,pt %icc, 1f
+ add %sp, PTREGS_OFF, %o0
+ call sun4v_data_access_exception
+ nop
+ ba,a,pt %xcc, rtrap
+
+1: call spitfire_data_access_exception
+ nop
+ ba,a,pt %xcc, rtrap
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 652683cb4b4b..aec508e37490 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2704,8 +2704,7 @@ void __flush_tlb_all(void)
pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
- __GFP_REPEAT | __GFP_ZERO);
+ struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
pte_t *pte = NULL;
if (page)
@@ -2717,8 +2716,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
pgtable_t pte_alloc_one(struct mm_struct *mm,
unsigned long address)
{
- struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
- __GFP_REPEAT | __GFP_ZERO);
+ struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
if (!page)
return NULL;
if (!pgtable_page_ctor(page)) {
@@ -2824,9 +2822,10 @@ void hugetlb_setup(struct pt_regs *regs)
* the Data-TLB for huge pages.
*/
if (tlb_type == cheetah_plus) {
+ bool need_context_reload = false;
unsigned long ctx;
- spin_lock(&ctx_alloc_lock);
+ spin_lock_irq(&ctx_alloc_lock);
ctx = mm->context.sparc64_ctx_val;
ctx &= ~CTX_PGSZ_MASK;
ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@@ -2845,9 +2844,12 @@ void hugetlb_setup(struct pt_regs *regs)
* also executing in this address space.
*/
mm->context.sparc64_ctx_val = ctx;
- on_each_cpu(context_reload, mm, 0);
+ need_context_reload = true;
}
- spin_unlock(&ctx_alloc_lock);
+ spin_unlock_irq(&ctx_alloc_lock);
+
+ if (need_context_reload)
+ on_each_cpu(context_reload, mm, 0);
}
}
#endif
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 4b7cef9e94e0..c1467ac59ce6 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -78,7 +78,7 @@ struct thread_info {
#ifndef __ASSEMBLY__
-void arch_release_thread_info(struct thread_info *info);
+void arch_release_thread_stack(unsigned long *stack);
/* How to get the thread information struct from C. */
register unsigned long stack_pointer __asm__("sp");
diff --git a/arch/tile/include/uapi/asm/unistd.h b/arch/tile/include/uapi/asm/unistd.h
index 3866397aaf5a..24e9187e85a8 100644
--- a/arch/tile/include/uapi/asm/unistd.h
+++ b/arch/tile/include/uapi/asm/unistd.h
@@ -12,6 +12,7 @@
* more details.
*/
+#define __ARCH_WANT_RENAMEAT
#if !defined(__LP64__) || defined(__SYSCALL_COMPAT)
/* Use the flavor of this syscall that matches the 32-bit API better. */
#define __ARCH_WANT_SYNC_FILE_RANGE2
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index 8767060d70fb..6394c1ccb68e 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -941,7 +941,7 @@ arch_initcall(init_hw_perf_events);
/*
* Tile specific backtracing code for perf_events.
*/
-static inline void perf_callchain(struct perf_callchain_entry *entry,
+static inline void perf_callchain(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
struct KBacktraceIterator kbt;
@@ -992,13 +992,13 @@ static inline void perf_callchain(struct perf_callchain_entry *entry,
}
}
-void perf_callchain_user(struct perf_callchain_entry *entry,
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
perf_callchain(entry, regs);
}
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
perf_callchain(entry, regs);
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 6b705ccc9cc1..a465d8372edd 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -73,8 +73,9 @@ void arch_cpu_idle(void)
/*
* Release a thread_info structure
*/
-void arch_release_thread_info(struct thread_info *info)
+void arch_release_thread_stack(unsigned long *stack)
{
+ struct thread_info *info = (void *)stack;
struct single_step_state *step_state = info->step_state;
if (step_state) {
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 7bf2491a9c1f..c4d5bf841a7f 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -231,7 +231,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address,
int order)
{
- gfp_t flags = GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO;
+ gfp_t flags = GFP_KERNEL|__GFP_ZERO;
struct page *p;
int i;
diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h
index f5b76355ad71..a74449b5b0e3 100644
--- a/arch/um/include/shared/registers.h
+++ b/arch/um/include/shared/registers.h
@@ -9,6 +9,8 @@
#include <sysdep/ptrace.h>
#include <sysdep/archsetjmp.h>
+extern int save_i387_registers(int pid, unsigned long *fp_regs);
+extern int restore_i387_registers(int pid, unsigned long *fp_regs);
extern int save_fp_registers(int pid, unsigned long *fp_regs);
extern int restore_fp_registers(int pid, unsigned long *fp_regs);
extern int save_fpx_registers(int pid, unsigned long *fp_regs);
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index b2a2dff50b4e..e7437ec62710 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -204,7 +204,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte;
- pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
return pte;
}
@@ -212,7 +212,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *pte;
- pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
if (!pte)
return NULL;
if (!pgtable_page_ctor(pte)) {
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 0b04711f1f18..034b42c7ab40 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -398,6 +398,6 @@ int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu)
{
int cpu = current_thread_info()->cpu;
- return save_fp_registers(userspace_pid[cpu], (unsigned long *) fpu);
+ return save_i387_registers(userspace_pid[cpu], (unsigned long *) fpu);
}
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 7801666514ed..8acaf4e384c0 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -29,23 +29,29 @@ void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
{
- struct uml_pt_regs r;
+ struct uml_pt_regs *r;
int save_errno = errno;
- r.is_user = 0;
+ r = malloc(sizeof(struct uml_pt_regs));
+ if (!r)
+ panic("out of memory");
+
+ r->is_user = 0;
if (sig == SIGSEGV) {
/* For segfaults, we want the data from the sigcontext. */
- get_regs_from_mc(&r, mc);
- GET_FAULTINFO_FROM_MC(r.faultinfo, mc);
+ get_regs_from_mc(r, mc);
+ GET_FAULTINFO_FROM_MC(r->faultinfo, mc);
}
/* enable signals if sig isn't IRQ signal */
if ((sig != SIGIO) && (sig != SIGWINCH) && (sig != SIGALRM))
unblock_signals();
- (*sig_info[sig])(sig, si, &r);
+ (*sig_info[sig])(sig, si, r);
errno = save_errno;
+
+ free(r);
}
/*
@@ -83,11 +89,17 @@ void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
static void timer_real_alarm_handler(mcontext_t *mc)
{
- struct uml_pt_regs regs;
+ struct uml_pt_regs *regs;
+
+ regs = malloc(sizeof(struct uml_pt_regs));
+ if (!regs)
+ panic("out of memory");
if (mc != NULL)
- get_regs_from_mc(&regs, mc);
- timer_handler(SIGALRM, NULL, &regs);
+ get_regs_from_mc(regs, mc);
+ timer_handler(SIGALRM, NULL, regs);
+
+ free(regs);
}
void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
diff --git a/arch/unicore32/boot/Makefile b/arch/unicore32/boot/Makefile
index ec7fb70b412b..828855007b29 100644
--- a/arch/unicore32/boot/Makefile
+++ b/arch/unicore32/boot/Makefile
@@ -31,7 +31,7 @@ $(obj)/uImage: $(obj)/zImage FORCE
$(call if_changed,uimage)
@echo ' Image $@ is ready'
-PHONY += initrd FORCE
+PHONY += initrd
initrd:
@test "$(INITRD)" != "" || \
(echo You must specify INITRD; exit -1)
diff --git a/arch/unicore32/boot/compressed/Makefile b/arch/unicore32/boot/compressed/Makefile
index 96494fb646f7..9aecdd3ddc48 100644
--- a/arch/unicore32/boot/compressed/Makefile
+++ b/arch/unicore32/boot/compressed/Makefile
@@ -54,7 +54,6 @@ LDFLAGS_vmlinux += -T
$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head.o $(obj)/piggy.o \
$(obj)/misc.o FORCE
$(call if_changed,ld)
- @:
# We now have a PIC decompressor implementation. Decompressors running
# from RAM should not define ZTEXTADDR. Decompressors running directly
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
index 2e02d1356fdf..26775793c204 100644
--- a/arch/unicore32/include/asm/pgalloc.h
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -28,7 +28,7 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
#define pgd_alloc(mm) get_pgd_slow(mm)
#define pgd_free(mm, pgd) free_pgd_slow(mm, pgd)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
/*
* Allocate one PTE table.
diff --git a/arch/unicore32/include/uapi/asm/unistd.h b/arch/unicore32/include/uapi/asm/unistd.h
index d4cc4559d848..1f63c476528e 100644
--- a/arch/unicore32/include/uapi/asm/unistd.h
+++ b/arch/unicore32/include/uapi/asm/unistd.h
@@ -10,6 +10,8 @@
* published by the Free Software Foundation.
*/
+#define __ARCH_WANT_RENAMEAT
+
/* Use the standard ABI for syscalls. */
#include <asm-generic/unistd.h>
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0a7b885964ba..d9a94da0c29f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2439,6 +2439,15 @@ config PCI_CNB20LE_QUIRK
source "drivers/pci/Kconfig"
+config ISA_BUS
+ bool "ISA-style bus support on modern systems" if EXPERT
+ select ISA_BUS_API
+ help
+ Enables ISA-style drivers on modern systems. This is necessary to
+ support PC/104 devices on X86_64 platforms.
+
+ If unsure, say N.
+
# x86_64 have no ISA slots, but can have ISA-style DMA.
config ISA_DMA_API
bool "ISA-style DMA support" if (X86_64 && EXPERT)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 700a9c6e6159..be8e688fa0d4 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage
for i in lib lib64 share end ; do \
if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+ if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \
+ cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \
+ fi ; \
break ; \
fi ; \
if [ $$i = end ] ; then exit 1 ; fi ; \
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index cfdd8c3f8af2..f1356889204e 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -87,7 +87,6 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
$(call if_changed,ld)
- @:
OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
$(obj)/vmlinux.bin: vmlinux FORCE
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 98df1fa8825c..027aec4a74df 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -8,16 +8,15 @@
#include <linux/linkage.h>
#include "calling.h"
#include <asm/asm.h>
-#include <asm/frame.h>
/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
.macro THUNK name, func, put_ret_addr_in_rdi=0
.globl \name
.type \name, @function
\name:
- FRAME_BEGIN
+ pushq %rbp
+ movq %rsp, %rbp
- /* this one pushes 9 elems, the next one would be %rIP */
pushq %rdi
pushq %rsi
pushq %rdx
@@ -29,8 +28,8 @@
pushq %r11
.if \put_ret_addr_in_rdi
- /* 9*8(%rsp) is return addr on stack */
- movq 9*8(%rsp), %rdi
+ /* 8(%rbp) is return addr on stack */
+ movq 8(%rbp), %rdi
.endif
call \func
@@ -65,7 +64,7 @@ restore:
popq %rdx
popq %rsi
popq %rdi
- FRAME_END
+ popq %rbp
ret
_ASM_NOKPROBE(restore)
#endif
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 6874da5f67fc..253b72eaade6 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -193,10 +193,10 @@ vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%)
$(MODLIB)/vdso: FORCE
@mkdir -p $(MODLIB)/vdso
-$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
+$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso
$(call cmd,vdso_install)
PHONY += vdso_install $(vdso_img_insttargets)
-vdso_install: $(vdso_img_insttargets) FORCE
+vdso_install: $(vdso_img_insttargets)
clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so*
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 73a75aa5a66d..33787ee817f0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2202,7 +2202,7 @@ static int backtrace_stack(void *data, char *name)
static int backtrace_address(void *data, unsigned long addr, int reliable)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
return perf_callchain_store(entry, addr);
}
@@ -2214,7 +2214,7 @@ static const struct stacktrace_ops backtrace_ops = {
};
void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* TODO: We don't support guest os callchain now */
@@ -2268,7 +2268,7 @@ static unsigned long get_segment_base(unsigned int segment)
#include <asm/compat.h>
static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
{
/* 32-bit process in 64-bit kernel. */
unsigned long ss_base, cs_base;
@@ -2283,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
fp = compat_ptr(ss_base + regs->bp);
pagefault_disable();
- while (entry->nr < sysctl_perf_event_max_stack) {
+ while (entry->nr < entry->max_stack) {
unsigned long bytes;
frame.next_frame = 0;
frame.return_address = 0;
@@ -2309,14 +2309,14 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
}
#else
static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
{
return 0;
}
#endif
void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stack_frame frame;
const void __user *fp;
@@ -2343,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
return;
pagefault_disable();
- while (entry->nr < sysctl_perf_event_max_stack) {
+ while (entry->nr < entry->max_stack) {
unsigned long bytes;
frame.next_frame = NULL;
frame.return_address = 0;
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index 0a5ede187d9c..eb0533558c2b 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -826,7 +826,7 @@ static int p4_hw_config(struct perf_event *event)
* Clear bits we reserve to be managed by kernel itself
* and never allowed from a user space
*/
- event->attr.config &= P4_CONFIG_MASK;
+ event->attr.config &= P4_CONFIG_MASK;
rc = p4_validate_raw_event(event);
if (rc)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 99c4bab123cd..e30eef4f29a6 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -714,7 +714,7 @@ static void cleanup_rapl_pmus(void)
int i;
for (i = 0; i < rapl_pmus->maxpkg; i++)
- kfree(rapl_pmus->pmus + i);
+ kfree(rapl_pmus->pmus[i]);
kfree(rapl_pmus);
}
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 16c178916412..fce74062d981 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -891,7 +891,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
return -ENODEV;
pkg = topology_phys_to_logical_pkg(phys_id);
- if (WARN_ON_ONCE(pkg < 0))
+ if (pkg < 0)
return -EINVAL;
if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b2625867ebd1..874e8bd64d1d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2868,27 +2868,10 @@ static struct intel_uncore_type bdx_uncore_cbox = {
.format_group = &hswep_uncore_cbox_format_group,
};
-static struct intel_uncore_type bdx_uncore_sbox = {
- .name = "sbox",
- .num_counters = 4,
- .num_boxes = 4,
- .perf_ctr_bits = 48,
- .event_ctl = HSWEP_S0_MSR_PMON_CTL0,
- .perf_ctr = HSWEP_S0_MSR_PMON_CTR0,
- .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
- .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL,
- .msr_offset = HSWEP_SBOX_MSR_OFFSET,
- .ops = &hswep_uncore_sbox_msr_ops,
- .format_group = &hswep_uncore_sbox_format_group,
-};
-
-#define BDX_MSR_UNCORE_SBOX 3
-
static struct intel_uncore_type *bdx_msr_uncores[] = {
&bdx_uncore_ubox,
&bdx_uncore_cbox,
&hswep_uncore_pcu,
- &bdx_uncore_sbox,
NULL,
};
@@ -2897,10 +2880,6 @@ void bdx_uncore_cpu_init(void)
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
uncore_msr_uncores = bdx_msr_uncores;
-
- /* BDX-DE doesn't have SBOX */
- if (boot_cpu_data.x86_model == 86)
- uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
}
static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index f5e737ff0022..cb26f18d43af 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -116,12 +116,12 @@ static struct linux_binfmt aout_format = {
.min_coredump = PAGE_SIZE
};
-static unsigned long set_brk(unsigned long start, unsigned long end)
+static int set_brk(unsigned long start, unsigned long end)
{
start = PAGE_ALIGN(start);
end = PAGE_ALIGN(end);
if (end <= start)
- return start;
+ return 0;
return vm_brk(start, end - start);
}
@@ -321,7 +321,7 @@ static int load_aout_binary(struct linux_binprm *bprm)
error = vm_brk(text_addr & PAGE_MASK, map_size);
- if (error != (text_addr & PAGE_MASK))
+ if (error)
return error;
error = read_code(bprm->file, text_addr, 32,
@@ -350,7 +350,7 @@ static int load_aout_binary(struct linux_binprm *bprm)
if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
- if (IS_ERR_VALUE(error))
+ if (error)
return error;
read_code(bprm->file, N_TXTADDR(ex), fd_offset,
@@ -378,7 +378,7 @@ static int load_aout_binary(struct linux_binprm *bprm)
beyond_if:
error = set_brk(current->mm->start_brk, current->mm->brk);
- if (IS_ERR_VALUE(error))
+ if (error)
return error;
set_binfmt(&aout_format);
@@ -441,7 +441,7 @@ static int load_aout_library(struct file *file)
}
#endif
retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
- if (IS_ERR_VALUE(retval))
+ if (retval)
goto out;
read_code(file, start_addr, N_TXTOFF(ex),
@@ -461,9 +461,8 @@ static int load_aout_library(struct file *file)
len = PAGE_ALIGN(ex.a_text + ex.a_data);
bss = ex.a_text + ex.a_data + ex.a_bss;
if (bss > len) {
- error = vm_brk(start_addr + len, bss - len);
- retval = error;
- if (error != start_addr + len)
+ retval = vm_brk(start_addr + len, bss - len);
+ if (retval)
goto out;
}
retval = 0;
diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h
index 08abf639075f..5490bbaf71d5 100644
--- a/arch/x86/include/asm/bugs.h
+++ b/arch/x86/include/asm/bugs.h
@@ -1,8 +1,16 @@
#ifndef _ASM_X86_BUGS_H
#define _ASM_X86_BUGS_H
+#include <asm/processor.h>
+
extern void check_bugs(void);
+#if defined(CONFIG_CPU_SUP_INTEL)
+void check_mpx_erratum(struct cpuinfo_x86 *c);
+#else
+static inline void check_mpx_erratum(struct cpuinfo_x86 *c) {}
+#endif
+
#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
int ppro_with_ram_bug(void);
#else
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 25ebb54905e0..483fb547e3c0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -64,9 +64,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
(((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) || \
(((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) || \
(((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) || \
- (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK14)) || \
- (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK15)) || \
- (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
+ (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) || \
+ (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) || \
+ (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
#define DISABLED_MASK_BIT_SET(bit) \
( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0 )) || \
@@ -83,9 +83,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
(((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) || \
(((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) || \
(((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) || \
- (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK14)) || \
- (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK15)) || \
- (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+ (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) || \
+ (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) || \
+ (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 39343be7d4f4..911e9358ceb1 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -29,11 +29,11 @@
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU (1<<(X86_FEATURE_PKU))
-# define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE))
-#else
# define DISABLE_PKU 0
# define DISABLE_OSPKE 0
+#else
+# define DISABLE_PKU (1<<(X86_FEATURE_PKU & 31))
+# define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31))
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
/*
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
new file mode 100644
index 000000000000..6999f7d01a0d
--- /dev/null
+++ b/arch/x86/include/asm/intel-family.h
@@ -0,0 +1,68 @@
+#ifndef _ASM_X86_INTEL_FAMILY_H
+#define _ASM_X86_INTEL_FAMILY_H
+
+/*
+ * "Big Core" Processors (Branded as Core, Xeon, etc...)
+ *
+ * The "_X" parts are generally the EP and EX Xeons, or the
+ * "Extreme" ones, like Broadwell-E.
+ *
+ * Things ending in "2" are usually because we have no better
+ * name for them. There's no processor called "WESTMERE2".
+ */
+
+#define INTEL_FAM6_CORE_YONAH 0x0E
+#define INTEL_FAM6_CORE2_MEROM 0x0F
+#define INTEL_FAM6_CORE2_MEROM_L 0x16
+#define INTEL_FAM6_CORE2_PENRYN 0x17
+#define INTEL_FAM6_CORE2_DUNNINGTON 0x1D
+
+#define INTEL_FAM6_NEHALEM 0x1E
+#define INTEL_FAM6_NEHALEM_EP 0x1A
+#define INTEL_FAM6_NEHALEM_EX 0x2E
+#define INTEL_FAM6_WESTMERE 0x25
+#define INTEL_FAM6_WESTMERE2 0x1F
+#define INTEL_FAM6_WESTMERE_EP 0x2C
+#define INTEL_FAM6_WESTMERE_EX 0x2F
+
+#define INTEL_FAM6_SANDYBRIDGE 0x2A
+#define INTEL_FAM6_SANDYBRIDGE_X 0x2D
+#define INTEL_FAM6_IVYBRIDGE 0x3A
+#define INTEL_FAM6_IVYBRIDGE_X 0x3E
+
+#define INTEL_FAM6_HASWELL_CORE 0x3C
+#define INTEL_FAM6_HASWELL_X 0x3F
+#define INTEL_FAM6_HASWELL_ULT 0x45
+#define INTEL_FAM6_HASWELL_GT3E 0x46
+
+#define INTEL_FAM6_BROADWELL_CORE 0x3D
+#define INTEL_FAM6_BROADWELL_XEON_D 0x56
+#define INTEL_FAM6_BROADWELL_GT3E 0x47
+#define INTEL_FAM6_BROADWELL_X 0x4F
+
+#define INTEL_FAM6_SKYLAKE_MOBILE 0x4E
+#define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E
+#define INTEL_FAM6_SKYLAKE_X 0x55
+#define INTEL_FAM6_KABYLAKE_MOBILE 0x8E
+#define INTEL_FAM6_KABYLAKE_DESKTOP 0x9E
+
+/* "Small Core" Processors (Atom) */
+
+#define INTEL_FAM6_ATOM_PINEVIEW 0x1C
+#define INTEL_FAM6_ATOM_LINCROFT 0x26
+#define INTEL_FAM6_ATOM_PENWELL 0x27
+#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35
+#define INTEL_FAM6_ATOM_CEDARVIEW 0x36
+#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */
+#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */
+#define INTEL_FAM6_ATOM_MERRIFIELD1 0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MERRIFIELD2 0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
+#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
+
+/* Xeon Phi */
+
+#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
+
+#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h
index ed65fe701de5..85029b58d0cd 100644
--- a/arch/x86/include/asm/intel_telemetry.h
+++ b/arch/x86/include/asm/intel_telemetry.h
@@ -99,7 +99,7 @@ struct telemetry_core_ops {
int (*reset_events)(void);
};
-int telemetry_set_pltdata(struct telemetry_core_ops *ops,
+int telemetry_set_pltdata(const struct telemetry_core_ops *ops,
struct telemetry_plt_config *pltconfig);
int telemetry_clear_pltdata(void);
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4421b5da409d..d1d1e5094c28 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -38,12 +38,11 @@ typedef u8 kprobe_opcode_t;
#define RELATIVECALL_OPCODE 0xe8
#define RELATIVE_ADDR_SIZE 4
#define MAX_STACK_SIZE 64
-#define MIN_STACK_SIZE(ADDR) \
- (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
- THREAD_SIZE - (unsigned long)(ADDR))) \
- ? (MAX_STACK_SIZE) \
- : (((unsigned long)current_thread_info()) + \
- THREAD_SIZE - (unsigned long)(ADDR)))
+#define CUR_STACK_SIZE(ADDR) \
+ (current_top_of_stack() - (unsigned long)(ADDR))
+#define MIN_STACK_SIZE(ADDR) \
+ (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \
+ MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR))
#define flush_insn_slot(p) do { } while (0)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0fbe7e70dc1..69e62862b622 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
#include <linux/irqbypass.h>
#include <linux/hyperv.h>
+#include <asm/apic.h>
#include <asm/pvclock-abi.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
@@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+static inline int kvm_cpu_get_apicid(int mps_cpu)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+ return __default_cpu_present_to_apicid(mps_cpu);
+#else
+ WARN_ON_ONCE(1);
+ return BAD_APICID;
+#endif
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 7dc1d8fef7fd..b5fee97813cd 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -122,7 +122,7 @@ notrace static inline void native_write_msr(unsigned int msr,
"2:\n"
_ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
: : "c" (msr), "a"(low), "d" (high) : "memory");
- if (msr_tracepoint_active(__tracepoint_read_msr))
+ if (msr_tracepoint_active(__tracepoint_write_msr))
do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
}
@@ -141,7 +141,7 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
: "c" (msr), "0" (low), "d" (high),
[fault] "i" (-EIO)
: "memory");
- if (msr_tracepoint_active(__tracepoint_read_msr))
+ if (msr_tracepoint_active(__tracepoint_write_msr))
do_trace_write_msr(msr, ((u64)high << 32 | low), err);
return err;
}
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index bf7f8b55b0f9..574c23cf761a 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -81,7 +81,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
struct page *page;
- page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+ page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
if (!page)
return NULL;
if (!pgtable_pmd_page_ctor(page)) {
@@ -125,7 +125,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+ return (pud_t *)get_zeroed_page(GFP_KERNEL);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
diff --git a/arch/x86/include/asm/pmc_core.h b/arch/x86/include/asm/pmc_core.h
new file mode 100644
index 000000000000..d4855f11136d
--- /dev/null
+++ b/arch/x86/include/asm/pmc_core.h
@@ -0,0 +1,27 @@
+/*
+ * Intel Core SoC Power Management Controller Header File
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com>
+ * Vishwanath Somayaji <vishwanath.somayaji@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef _ASM_PMC_CORE_H
+#define _ASM_PMC_CORE_H
+
+/* API to read SLP_S0_RESIDENCY counter */
+int intel_pmc_slp_s0_counter_read(u32 *data);
+
+#endif /* _ASM_PMC_CORE_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index fdcc04020636..7c1c89598688 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -69,29 +69,22 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
}
static __always_inline
-u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
-{
- u64 delta = rdtsc_ordered() - src->tsc_timestamp;
- return pvclock_scale_delta(delta, src->tsc_to_system_mul,
- src->tsc_shift);
-}
-
-static __always_inline
unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
cycle_t *cycles, u8 *flags)
{
unsigned version;
- cycle_t ret, offset;
- u8 ret_flags;
+ cycle_t offset;
+ u64 delta;
version = src->version;
+ /* Make the latest version visible */
+ smp_rmb();
- offset = pvclock_get_nsec_offset(src);
- ret = src->system_time + offset;
- ret_flags = src->flags;
-
- *cycles = ret;
- *flags = ret_flags;
+ delta = rdtsc_ordered() - src->tsc_timestamp;
+ offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+ src->tsc_shift);
+ *cycles = src->system_time + offset;
+ *flags = src->flags;
return version;
}
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 7c247e7404be..0944218af9e2 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -14,7 +14,7 @@ extern int kstack_depth_to_print;
struct thread_info;
struct stacktrace_ops;
-typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+typedef unsigned long (*walk_stack_t)(struct task_struct *task,
unsigned long *stack,
unsigned long bp,
const struct stacktrace_ops *ops,
@@ -23,13 +23,13 @@ typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
int *graph);
extern unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph);
extern unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph);
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index b9e9bb2c6089..3725e145aa58 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -2,10 +2,12 @@
#define _UAPI__SVM_H
#define SVM_EXIT_READ_CR0 0x000
+#define SVM_EXIT_READ_CR2 0x002
#define SVM_EXIT_READ_CR3 0x003
#define SVM_EXIT_READ_CR4 0x004
#define SVM_EXIT_READ_CR8 0x008
#define SVM_EXIT_WRITE_CR0 0x010
+#define SVM_EXIT_WRITE_CR2 0x012
#define SVM_EXIT_WRITE_CR3 0x013
#define SVM_EXIT_WRITE_CR4 0x014
#define SVM_EXIT_WRITE_CR8 0x018
@@ -80,10 +82,12 @@
#define SVM_EXIT_REASONS \
{ SVM_EXIT_READ_CR0, "read_cr0" }, \
+ { SVM_EXIT_READ_CR2, "read_cr2" }, \
{ SVM_EXIT_READ_CR3, "read_cr3" }, \
{ SVM_EXIT_READ_CR4, "read_cr4" }, \
{ SVM_EXIT_READ_CR8, "read_cr8" }, \
{ SVM_EXIT_WRITE_CR0, "write_cr0" }, \
+ { SVM_EXIT_WRITE_CR2, "write_cr2" }, \
{ SVM_EXIT_WRITE_CR3, "write_cr3" }, \
{ SVM_EXIT_WRITE_CR4, "write_cr4" }, \
{ SVM_EXIT_WRITE_CR8, "write_cr8" }, \
@@ -91,26 +95,57 @@
{ SVM_EXIT_READ_DR1, "read_dr1" }, \
{ SVM_EXIT_READ_DR2, "read_dr2" }, \
{ SVM_EXIT_READ_DR3, "read_dr3" }, \
+ { SVM_EXIT_READ_DR4, "read_dr4" }, \
+ { SVM_EXIT_READ_DR5, "read_dr5" }, \
+ { SVM_EXIT_READ_DR6, "read_dr6" }, \
+ { SVM_EXIT_READ_DR7, "read_dr7" }, \
{ SVM_EXIT_WRITE_DR0, "write_dr0" }, \
{ SVM_EXIT_WRITE_DR1, "write_dr1" }, \
{ SVM_EXIT_WRITE_DR2, "write_dr2" }, \
{ SVM_EXIT_WRITE_DR3, "write_dr3" }, \
+ { SVM_EXIT_WRITE_DR4, "write_dr4" }, \
{ SVM_EXIT_WRITE_DR5, "write_dr5" }, \
+ { SVM_EXIT_WRITE_DR6, "write_dr6" }, \
{ SVM_EXIT_WRITE_DR7, "write_dr7" }, \
+ { SVM_EXIT_EXCP_BASE + DE_VECTOR, "DE excp" }, \
{ SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \
{ SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \
+ { SVM_EXIT_EXCP_BASE + OF_VECTOR, "OF excp" }, \
+ { SVM_EXIT_EXCP_BASE + BR_VECTOR, "BR excp" }, \
{ SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \
- { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \
{ SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \
+ { SVM_EXIT_EXCP_BASE + DF_VECTOR, "DF excp" }, \
+ { SVM_EXIT_EXCP_BASE + TS_VECTOR, "TS excp" }, \
+ { SVM_EXIT_EXCP_BASE + NP_VECTOR, "NP excp" }, \
+ { SVM_EXIT_EXCP_BASE + SS_VECTOR, "SS excp" }, \
+ { SVM_EXIT_EXCP_BASE + GP_VECTOR, "GP excp" }, \
+ { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \
+ { SVM_EXIT_EXCP_BASE + MF_VECTOR, "MF excp" }, \
{ SVM_EXIT_EXCP_BASE + AC_VECTOR, "AC excp" }, \
{ SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \
+ { SVM_EXIT_EXCP_BASE + XM_VECTOR, "XF excp" }, \
{ SVM_EXIT_INTR, "interrupt" }, \
{ SVM_EXIT_NMI, "nmi" }, \
{ SVM_EXIT_SMI, "smi" }, \
{ SVM_EXIT_INIT, "init" }, \
{ SVM_EXIT_VINTR, "vintr" }, \
{ SVM_EXIT_CR0_SEL_WRITE, "cr0_sel_write" }, \
+ { SVM_EXIT_IDTR_READ, "read_idtr" }, \
+ { SVM_EXIT_GDTR_READ, "read_gdtr" }, \
+ { SVM_EXIT_LDTR_READ, "read_ldtr" }, \
+ { SVM_EXIT_TR_READ, "read_rt" }, \
+ { SVM_EXIT_IDTR_WRITE, "write_idtr" }, \
+ { SVM_EXIT_GDTR_WRITE, "write_gdtr" }, \
+ { SVM_EXIT_LDTR_WRITE, "write_ldtr" }, \
+ { SVM_EXIT_TR_WRITE, "write_rt" }, \
+ { SVM_EXIT_RDTSC, "rdtsc" }, \
+ { SVM_EXIT_RDPMC, "rdpmc" }, \
+ { SVM_EXIT_PUSHF, "pushf" }, \
+ { SVM_EXIT_POPF, "popf" }, \
{ SVM_EXIT_CPUID, "cpuid" }, \
+ { SVM_EXIT_RSM, "rsm" }, \
+ { SVM_EXIT_IRET, "iret" }, \
+ { SVM_EXIT_SWINT, "swint" }, \
{ SVM_EXIT_INVD, "invd" }, \
{ SVM_EXIT_PAUSE, "pause" }, \
{ SVM_EXIT_HLT, "hlt" }, \
@@ -119,6 +154,7 @@
{ SVM_EXIT_IOIO, "io" }, \
{ SVM_EXIT_MSR, "msr" }, \
{ SVM_EXIT_TASK_SWITCH, "task_switch" }, \
+ { SVM_EXIT_FERR_FREEZE, "ferr_freeze" }, \
{ SVM_EXIT_SHUTDOWN, "shutdown" }, \
{ SVM_EXIT_VMRUN, "vmrun" }, \
{ SVM_EXIT_VMMCALL, "hypercall" }, \
@@ -127,14 +163,16 @@
{ SVM_EXIT_STGI, "stgi" }, \
{ SVM_EXIT_CLGI, "clgi" }, \
{ SVM_EXIT_SKINIT, "skinit" }, \
+ { SVM_EXIT_RDTSCP, "rdtscp" }, \
+ { SVM_EXIT_ICEBP, "icebp" }, \
{ SVM_EXIT_WBINVD, "wbinvd" }, \
{ SVM_EXIT_MONITOR, "monitor" }, \
{ SVM_EXIT_MWAIT, "mwait" }, \
{ SVM_EXIT_XSETBV, "xsetbv" }, \
{ SVM_EXIT_NPF, "npf" }, \
- { SVM_EXIT_RSM, "rsm" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
- { SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }
+ { SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \
+ { SVM_EXIT_ERR, "invalid_guest_state" }
#endif /* _UAPI__SVM_H */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 84e33ff5a6d5..446702ed99dc 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2588,8 +2588,8 @@ static struct resource * __init ioapic_setup_resources(void)
res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
mem += IOAPIC_RESOURCE_NAME_SIZE;
+ ioapics[i].iomem_res = &res[num];
num++;
- ioapics[i].iomem_res = res;
}
ioapic_resources = res;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c343a54bed39..f5c69d8974e1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -674,14 +674,14 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
u64 value;
/* re-enable TopologyExtensions if switched off by BIOS */
- if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+ if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
!cpu_has(c, X86_FEATURE_TOPOEXT)) {
if (msr_set_bit(0xc0011005, 54) > 0) {
rdmsrl(0xc0011005, value);
if (value & BIT_64(54)) {
set_cpu_cap(c, X86_FEATURE_TOPOEXT);
- pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+ pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
}
}
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6ef6ed9ccca6..0fe6953f421c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -37,6 +37,7 @@
#include <asm/mtrr.h>
#include <linux/numa.h>
#include <asm/asm.h>
+#include <asm/bugs.h>
#include <asm/cpu.h>
#include <asm/mce.h>
#include <asm/msr.h>
@@ -270,6 +271,8 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
static __init int setup_disable_smep(char *arg)
{
setup_clear_cpu_cap(X86_FEATURE_SMEP);
+ /* Check for things that depend on SMEP being enabled: */
+ check_mpx_erratum(&boot_cpu_data);
return 1;
}
__setup("nosmep", setup_disable_smep);
@@ -310,6 +313,10 @@ static bool pku_disabled;
static __always_inline void setup_pku(struct cpuinfo_x86 *c)
{
+ /* check the boot processor, plus compile options for PKU: */
+ if (!cpu_feature_enabled(X86_FEATURE_PKU))
+ return;
+ /* checks the actual processor's cpuid bits: */
if (!cpu_has(c, X86_FEATURE_PKU))
return;
if (pku_disabled)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8dae51fd3db1..6e2ffbebbcdb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -25,6 +25,41 @@
#include <asm/apic.h>
#endif
+/*
+ * Just in case our CPU detection goes bad, or you have a weird system,
+ * allow a way to override the automatic disabling of MPX.
+ */
+static int forcempx;
+
+static int __init forcempx_setup(char *__unused)
+{
+ forcempx = 1;
+
+ return 1;
+}
+__setup("intel-skd-046-workaround=disable", forcempx_setup);
+
+void check_mpx_erratum(struct cpuinfo_x86 *c)
+{
+ if (forcempx)
+ return;
+ /*
+ * Turn off the MPX feature on CPUs where SMEP is not
+ * available or disabled.
+ *
+ * Works around Intel Erratum SKD046: "Branch Instructions
+ * May Initialize MPX Bound Registers Incorrectly".
+ *
+ * This might falsely disable MPX on systems without
+ * SMEP, like Atom processors without SMEP. But there
+ * is no such hardware known at the moment.
+ */
+ if (cpu_has(c, X86_FEATURE_MPX) && !cpu_has(c, X86_FEATURE_SMEP)) {
+ setup_clear_cpu_cap(X86_FEATURE_MPX);
+ pr_warn("x86/mpx: Disabling MPX since SMEP not present\n");
+ }
+}
+
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
@@ -173,6 +208,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (edx & (1U << 28))
c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
}
+
+ check_mpx_erratum(c);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2bb25c3fe2e8..ef8017ca5ba9 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -42,16 +42,14 @@ void printk_address(unsigned long address)
static void
print_ftrace_graph_addr(unsigned long addr, void *data,
const struct stacktrace_ops *ops,
- struct thread_info *tinfo, int *graph)
+ struct task_struct *task, int *graph)
{
- struct task_struct *task;
unsigned long ret_addr;
int index;
if (addr != (unsigned long)return_to_handler)
return;
- task = tinfo->task;
index = task->curr_ret_stack;
if (!task->ret_stack || index < *graph)
@@ -68,7 +66,7 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
static inline void
print_ftrace_graph_addr(unsigned long addr, void *data,
const struct stacktrace_ops *ops,
- struct thread_info *tinfo, int *graph)
+ struct task_struct *task, int *graph)
{ }
#endif
@@ -79,10 +77,10 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
*/
-static inline int valid_stack_ptr(struct thread_info *tinfo,
+static inline int valid_stack_ptr(struct task_struct *task,
void *p, unsigned int size, void *end)
{
- void *t = tinfo;
+ void *t = task_stack_page(task);
if (end) {
if (p < end && p >= (end-THREAD_SIZE))
return 1;
@@ -93,14 +91,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo,
}
unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
{
struct stack_frame *frame = (struct stack_frame *)bp;
- while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+ while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
unsigned long addr;
addr = *stack;
@@ -112,7 +110,7 @@ print_context_stack(struct thread_info *tinfo,
} else {
ops->address(data, addr, 0);
}
- print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+ print_ftrace_graph_addr(addr, data, ops, task, graph);
}
stack++;
}
@@ -121,7 +119,7 @@ print_context_stack(struct thread_info *tinfo,
EXPORT_SYMBOL_GPL(print_context_stack);
unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
@@ -129,7 +127,7 @@ print_context_stack_bp(struct thread_info *tinfo,
struct stack_frame *frame = (struct stack_frame *)bp;
unsigned long *ret_addr = &frame->return_address;
- while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
+ while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) {
unsigned long addr = *ret_addr;
if (!__kernel_text_address(addr))
@@ -139,7 +137,7 @@ print_context_stack_bp(struct thread_info *tinfo,
break;
frame = frame->next_frame;
ret_addr = &frame->return_address;
- print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+ print_ftrace_graph_addr(addr, data, ops, task, graph);
}
return (unsigned long)frame;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 464ffd69b92e..fef917e79b9d 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -61,15 +61,13 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
bp = stack_frame(task, regs);
for (;;) {
- struct thread_info *context;
void *end_stack;
end_stack = is_hardirq_stack(stack, cpu);
if (!end_stack)
end_stack = is_softirq_stack(stack, cpu);
- context = task_thread_info(task);
- bp = ops->walk_stack(context, stack, bp, ops, data,
+ bp = ops->walk_stack(task, stack, bp, ops, data,
end_stack, &graph);
/* Stop if not on irq stack */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5f1c6266eb30..d558a8a49016 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -153,7 +153,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
- struct thread_info *tinfo;
unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned long dummy;
unsigned used = 0;
@@ -179,7 +178,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
* current stack address. If the stacks consist of nested
* exceptions
*/
- tinfo = task_thread_info(task);
while (!done) {
unsigned long *stack_end;
enum stack_type stype;
@@ -202,7 +200,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
if (ops->stack(data, id) < 0)
break;
- bp = ops->walk_stack(tinfo, stack, bp, ops,
+ bp = ops->walk_stack(task, stack, bp, ops,
data, stack_end, &graph);
ops->stack(data, "<EOE>");
/*
@@ -218,7 +216,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
if (ops->stack(data, "IRQ") < 0)
break;
- bp = ops->walk_stack(tinfo, stack, bp,
+ bp = ops->walk_stack(task, stack, bp,
ops, data, stack_end, &graph);
/*
* We link to the next stack (which would be
@@ -240,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
/*
* This handles the process stack:
*/
- bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+ bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
put_cpu();
}
EXPORT_SYMBOL(dump_trace);
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 4d38416e2a7f..04f89caef9c4 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -57,7 +57,7 @@
# error "Need more than one PGD for the ESPFIX hack"
#endif
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
/* This contains the *bottom* address of the espfix stack */
DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f29a9c8..c627bf8d98ad 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -130,11 +130,9 @@ void irq_ctx_init(int cpu)
void do_softirq_own_stack(void)
{
- struct thread_info *curstk;
struct irq_stack *irqstk;
u32 *isp, *prev_esp;
- curstk = current_stack();
irqstk = __this_cpu_read(softirq_stack);
/* build the stack frame on the softirq stack */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 38cf7a741250..7847e5c0e0b5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
* normal page fault.
*/
regs->ip = (unsigned long)cur->addr;
+ /*
+ * Trap flag (TF) has been set here because this fault
+ * happened where the single stepping will be done.
+ * So clear it by resetting the current kprobe:
+ */
+ regs->flags &= ~X86_EFLAGS_TF;
+
+ /*
+ * If the TF flag was set before the kprobe hit,
+ * don't touch it:
+ */
regs->flags |= kcb->kprobe_old_flags;
+
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6b16c36f0939..6e789ca1f841 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -532,7 +532,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
switch (code) {
case ARCH_SET_GS:
- if (addr >= TASK_SIZE_OF(task))
+ if (addr >= TASK_SIZE_MAX)
return -EPERM;
cpu = get_cpu();
task->thread.gsindex = 0;
@@ -546,7 +546,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
case ARCH_SET_FS:
/* Not strictly needed for fs, but do it for symmetry
with gs */
- if (addr >= TASK_SIZE_OF(task))
+ if (addr >= TASK_SIZE_MAX)
return -EPERM;
cpu = get_cpu();
task->thread.fsindex = 0;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e60ef918f53d..600edd225e81 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -392,7 +392,7 @@ static int putreg(struct task_struct *child,
#ifdef CONFIG_X86_64
case offsetof(struct user_regs_struct,fs_base):
- if (value >= TASK_SIZE_OF(child))
+ if (value >= TASK_SIZE_MAX)
return -EIO;
/*
* When changing the segment base, use do_arch_prctl
@@ -406,7 +406,7 @@ static int putreg(struct task_struct *child,
/*
* Exactly the same here as the %fs handling above.
*/
- if (value >= TASK_SIZE_OF(child))
+ if (value >= TASK_SIZE_MAX)
return -EIO;
if (child->thread.gsbase != value)
return do_arch_prctl(child, ARCH_SET_GS, value);
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 99bfc025111d..06c58ce46762 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -61,11 +61,16 @@ void pvclock_resume(void)
u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
{
unsigned version;
- cycle_t ret;
u8 flags;
do {
- version = __pvclock_read_cycles(src, &ret, &flags);
+ version = src->version;
+ /* Make the latest version visible */
+ smp_rmb();
+
+ flags = src->flags;
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
} while ((src->version & 1) || version != src->version);
return flags & valid_flags;
@@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
do {
version = __pvclock_read_cycles(src, &ret, &flags);
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
} while ((src->version & 1) || version != src->version);
if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d1590486204a..00f03d82e69a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -96,6 +96,12 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
local_irq_disable();
}
+/*
+ * In IST context, we explicitly disable preemption. This serves two
+ * purposes: it makes it much less likely that we would accidentally
+ * schedule in IST context and it will force a warning if we somehow
+ * manage to schedule by accident.
+ */
void ist_enter(struct pt_regs *regs)
{
if (user_mode(regs)) {
@@ -110,13 +116,7 @@ void ist_enter(struct pt_regs *regs)
rcu_nmi_enter();
}
- /*
- * We are atomic because we're on the IST stack; or we're on
- * x86_32, in which case we still shouldn't schedule; or we're
- * on x86_64 and entered from user mode, in which case we're
- * still atomic unless ist_begin_non_atomic is called.
- */
- preempt_count_add(HARDIRQ_OFFSET);
+ preempt_disable();
/* This code is a bit fragile. Test it. */
RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
@@ -124,7 +124,7 @@ void ist_enter(struct pt_regs *regs)
void ist_exit(struct pt_regs *regs)
{
- preempt_count_sub(HARDIRQ_OFFSET);
+ preempt_enable_no_resched();
if (!user_mode(regs))
rcu_nmi_exit();
@@ -155,7 +155,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
BUG_ON((unsigned long)(current_top_of_stack() -
current_stack_pointer()) >= THREAD_SIZE);
- preempt_count_sub(HARDIRQ_OFFSET);
+ preempt_enable_no_resched();
}
/**
@@ -165,7 +165,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
*/
void ist_end_non_atomic(void)
{
- preempt_count_add(HARDIRQ_OFFSET);
+ preempt_disable();
}
static nokprobe_inline int
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 6aa0f4d9eea6..9911a0620f9a 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -23,6 +23,7 @@
#include <asm/param.h>
/* CPU reference clock frequency: in KHz */
+#define FREQ_80 80000
#define FREQ_83 83200
#define FREQ_100 99840
#define FREQ_133 133200
@@ -56,6 +57,8 @@ static struct freq_desc freq_desc_tables[] = {
{ 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
/* ANN */
{ 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } },
+ /* AIRMONT */
+ { 6, 0x4c, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, FREQ_80, 0, 0, 0 } },
};
static int match_cpu(u8 family, u8 model)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 769af907f824..7597b42a8a88 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -181,19 +181,22 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
struct kvm_cpuid_entry __user *entries)
{
int r, i;
- struct kvm_cpuid_entry *cpuid_entries;
+ struct kvm_cpuid_entry *cpuid_entries = NULL;
r = -E2BIG;
if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
goto out;
r = -ENOMEM;
- cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
- if (!cpuid_entries)
- goto out;
- r = -EFAULT;
- if (copy_from_user(cpuid_entries, entries,
- cpuid->nent * sizeof(struct kvm_cpuid_entry)))
- goto out_free;
+ if (cpuid->nent) {
+ cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) *
+ cpuid->nent);
+ if (!cpuid_entries)
+ goto out;
+ r = -EFAULT;
+ if (copy_from_user(cpuid_entries, entries,
+ cpuid->nent * sizeof(struct kvm_cpuid_entry)))
+ goto out;
+ }
for (i = 0; i < cpuid->nent; i++) {
vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -212,9 +215,8 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
kvm_x86_ops->cpuid_update(vcpu);
r = kvm_update_cpuid(vcpu);
-out_free:
- vfree(cpuid_entries);
out:
+ vfree(cpuid_entries);
return r;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bbb5b283ff63..a397200281c1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
/* __delay is delay_tsc whenever the hardware has TSC, thus always. */
if (guest_tsc < tsc_deadline)
- __delay(tsc_deadline - guest_tsc);
+ __delay(min(tsc_deadline - guest_tsc,
+ nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
}
static void start_apic_timer(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 24e800116ab4..def97b3a392b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -336,12 +336,12 @@ static gfn_t pse36_gfn_delta(u32 gpte)
#ifdef CONFIG_X86_64
static void __set_spte(u64 *sptep, u64 spte)
{
- *sptep = spte;
+ WRITE_ONCE(*sptep, spte);
}
static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
- *sptep = spte;
+ WRITE_ONCE(*sptep, spte);
}
static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
@@ -390,7 +390,7 @@ static void __set_spte(u64 *sptep, u64 spte)
*/
smp_wmb();
- ssptep->spte_low = sspte.spte_low;
+ WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
}
static void __update_clear_spte_fast(u64 *sptep, u64 spte)
@@ -400,7 +400,7 @@ static void __update_clear_spte_fast(u64 *sptep, u64 spte)
ssptep = (union split_spte *)sptep;
sspte = (union split_spte)spte;
- ssptep->spte_low = sspte.spte_low;
+ WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
/*
* If we map the spte from present to nonpresent, we should clear
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2214214c786b..16ef31b87452 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -84,7 +84,7 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
#define TSC_RATIO_MIN 0x0000000000000001ULL
#define TSC_RATIO_MAX 0x000000ffffffffffULL
-#define AVIC_HPA_MASK ~((0xFFFULL << 52) || 0xFFF)
+#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
/*
* 0xff is broadcast, so the max index allowed for physical APIC ID
@@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO);
/* enable / disable AVIC */
static int avic;
+#ifdef CONFIG_X86_LOCAL_APIC
module_param(avic, int, S_IRUGO);
+#endif
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void)
} else
kvm_disable_tdp();
- if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)))
- avic = false;
-
- if (avic)
- pr_info("AVIC enabled\n");
+ if (avic) {
+ if (!npt_enabled ||
+ !boot_cpu_has(X86_FEATURE_AVIC) ||
+ !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+ avic = false;
+ else
+ pr_info("AVIC enabled\n");
+ }
return 0;
@@ -1324,7 +1329,7 @@ free_avic:
static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
{
u64 entry;
- int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu);
+ int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
struct vcpu_svm *svm = to_svm(vcpu);
if (!kvm_vcpu_apicv_active(vcpu))
@@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
u64 entry;
/* ID = 0xff (broadcast), ID > 0xff (reserved) */
- int h_physical_id = __default_cpu_present_to_apicid(cpu);
+ int h_physical_id = kvm_cpu_get_apicid(cpu);
struct vcpu_svm *svm = to_svm(vcpu);
if (!kvm_vcpu_apicv_active(vcpu))
@@ -3597,7 +3602,7 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
u32 icrh = svm->vmcb->control.exit_info_1 >> 32;
u32 icrl = svm->vmcb->control.exit_info_1;
u32 id = svm->vmcb->control.exit_info_2 >> 32;
- u32 index = svm->vmcb->control.exit_info_2 && 0xFF;
+ u32 index = svm->vmcb->control.exit_info_2 & 0xFF;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
trace_kvm_avic_incomplete_ipi(svm->vcpu.vcpu_id, icrh, icrl, id, index);
@@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
if (avic_vcpu_is_running(vcpu))
wrmsrl(SVM_AVIC_DOORBELL,
- __default_cpu_present_to_apicid(vcpu->cpu));
+ kvm_cpu_get_apicid(vcpu->cpu));
else
kvm_vcpu_wake_up(vcpu);
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e605d1ed334f..64a79f271276 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
unsigned int dest;
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return;
do {
@@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return;
/* Set SN when the vCPU is preempted */
@@ -2418,7 +2420,9 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
if (is_guest_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_nested;
- else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
+ else if (cpu_has_secondary_exec_ctrls() &&
+ (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
+ SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
if (is_long_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
else
@@ -4787,6 +4791,19 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+ if (cpu_has_secondary_exec_ctrls()) {
+ if (kvm_vcpu_apicv_active(vcpu))
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_APIC_REGISTER_VIRT |
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+ else
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_APIC_REGISTER_VIRT |
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+ }
+
+ if (cpu_has_vmx_msr_bitmap())
+ vmx_set_msr_bitmap(vcpu);
}
static u32 vmx_exec_control(struct vcpu_vmx *vmx)
@@ -6333,23 +6350,20 @@ static __init int hardware_setup(void)
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
- if (enable_apicv) {
- for (msr = 0x800; msr <= 0x8ff; msr++)
- vmx_disable_intercept_msr_read_x2apic(msr);
-
- /* According SDM, in x2apic mode, the whole id reg is used.
- * But in KVM, it only use the highest eight bits. Need to
- * intercept it */
- vmx_enable_intercept_msr_read_x2apic(0x802);
- /* TMCCT */
- vmx_enable_intercept_msr_read_x2apic(0x839);
- /* TPR */
- vmx_disable_intercept_msr_write_x2apic(0x808);
- /* EOI */
- vmx_disable_intercept_msr_write_x2apic(0x80b);
- /* SELF-IPI */
- vmx_disable_intercept_msr_write_x2apic(0x83f);
- }
+ for (msr = 0x800; msr <= 0x8ff; msr++)
+ vmx_disable_intercept_msr_read_x2apic(msr);
+
+ /* According SDM, in x2apic mode, the whole id reg is used. But in
+ * KVM, it only use the highest eight bits. Need to intercept it */
+ vmx_enable_intercept_msr_read_x2apic(0x802);
+ /* TMCCT */
+ vmx_enable_intercept_msr_read_x2apic(0x839);
+ /* TPR */
+ vmx_disable_intercept_msr_write_x2apic(0x808);
+ /* EOI */
+ vmx_disable_intercept_msr_write_x2apic(0x80b);
+ /* SELF-IPI */
+ vmx_disable_intercept_msr_write_x2apic(0x83f);
if (enable_ept) {
kvm_mmu_set_mask_ptes(0ull,
@@ -6657,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
/* Checks for #GP/#SS exceptions. */
exn = false;
- if (is_protmode(vcpu)) {
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is the only check on the memory
+ * destination for long mode!
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
* - segment type check (#GP(0) may be thrown)
@@ -6674,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
* execute-only code segment
*/
exn = ((s.type & 0xa) == 8);
- }
- if (exn) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- if (is_long_mode(vcpu)) {
- /* Long mode: #GP(0)/#SS(0) if the memory address is in a
- * non-canonical form. This is an only check for long mode.
- */
- exn = is_noncanonical_address(*ret);
- } else if (is_protmode(vcpu)) {
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
*/
exn = (s.unusable != 0);
@@ -10702,7 +10715,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return 0;
vcpu->pre_pcpu = vcpu->cpu;
@@ -10768,7 +10782,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
unsigned long flags;
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return;
do {
@@ -10821,7 +10836,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
int idx, ret = -EINVAL;
if (!kvm_arch_has_assigned_device(kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(kvm->vcpus[0]))
return 0;
idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c805cf494154..7da5dd2057a9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
static unsigned long max_tsc_khz;
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
-{
- return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
- vcpu->arch.virtual_tsc_shift);
-}
-
static u32 adjust_tsc_khz(u32 khz, s32 ppm)
{
u64 v = (u64)khz * (1000000 + ppm);
@@ -2314,6 +2308,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_AMD64_NB_CFG:
case MSR_FAM10H_MMIO_CONF_BASE:
case MSR_AMD64_BU_CFG2:
+ case MSR_IA32_PERF_CTL:
msr_info->data = 0;
break;
case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
@@ -2972,6 +2967,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
| KVM_VCPUEVENT_VALID_SMM))
return -EINVAL;
+ if (events->exception.injected &&
+ (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+ return -EINVAL;
+
process_nmi(vcpu);
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
@@ -3036,6 +3035,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
if (dbgregs->flags)
return -EINVAL;
+ if (dbgregs->dr6 & ~0xffffffffull)
+ return -EINVAL;
+ if (dbgregs->dr7 & ~0xffffffffull)
+ return -EINVAL;
+
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
kvm_update_dr0123(vcpu);
vcpu->arch.dr6 = dbgregs->dr6;
@@ -7815,7 +7819,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
slot = id_to_memslot(slots, id);
if (size) {
- if (WARN_ON(slot->npages))
+ if (slot->npages)
return -EEXIST;
/*
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7ce3634ab5fe..a82ca466b62e 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -2,6 +2,7 @@
#define ARCH_X86_KVM_X86_H
#include <linux/kvm_host.h>
+#include <asm/pvclock.h>
#include "kvm_cache_regs.h"
#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL
@@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns;
extern struct static_key kvm_no_apic_vcpu;
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
+{
+ return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
+ vcpu->arch.virtual_tsc_shift);
+}
+
/* Same "calling convention" as do_div:
* - divide (n << 32) by base
* - put result in n
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 5ce1ed02f7e8..7d1fa7cd2374 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -292,7 +292,7 @@ void vmalloc_sync_all(void)
return;
for (address = VMALLOC_START & PMD_MASK;
- address >= TASK_SIZE && address < FIXADDR_TOP;
+ address >= TASK_SIZE_MAX && address < FIXADDR_TOP;
address += PMD_SIZE) {
struct page *page;
@@ -854,8 +854,13 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
return;
}
#endif
- /* Kernel addresses are always protection faults: */
- if (address >= TASK_SIZE)
+
+ /*
+ * To avoid leaking information about the kernel page table
+ * layout, pretend that user-mode accesses to kernel addresses
+ * are always protection faults.
+ */
+ if (address >= TASK_SIZE_MAX)
error_code |= PF_PROT;
if (likely(show_unhandled_signals))
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e25043..aa0ff4b02a96 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
#include <asm/fixmap.h>
#include <asm/mtrr.h>
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
#ifdef CONFIG_HIGHPTE
#define PGALLOC_USER_GFP __GFP_HIGHMEM
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 4bd08b0fc8ea..99ddab79215e 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -491,8 +491,11 @@ int __init pci_xen_initial_domain(void)
#endif
__acpi_register_gsi = acpi_register_gsi_xen;
__acpi_unregister_gsi = NULL;
- /* Pre-allocate legacy irqs */
- for (irq = 0; irq < nr_legacy_irqs(); irq++) {
+ /*
+ * Pre-allocate the legacy IRQs. Use NR_LEGACY_IRQS here
+ * because we don't have a PIC and thus nr_legacy_irqs() is zero.
+ */
+ for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
int trigger, polarity;
if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6e7242be1c87..b226b3f497f1 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -139,7 +139,7 @@ int __init efi_alloc_page_tables(void)
if (efi_enabled(EFI_OLD_MEMMAP))
return 0;
- gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
+ gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
if (!efi_pgd)
return -ENOMEM;
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 92723aeae0f9..cd95075944ab 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -11,7 +11,6 @@
#include <asm/msr.h>
#include <asm/processor-flags.h>
#include <asm/page_types.h>
-#include <asm/frame.h>
#define SAVE_XMM \
mov %rsp, %rax; \
@@ -40,10 +39,10 @@
mov (%rsp), %rsp
ENTRY(efi_call)
- FRAME_BEGIN
+ pushq %rbp
+ movq %rsp, %rbp
SAVE_XMM
- mov (%rsp), %rax
- mov 8(%rax), %rax
+ mov 16(%rbp), %rax
subq $48, %rsp
mov %r9, 32(%rsp)
mov %rax, 40(%rsp)
@@ -53,6 +52,6 @@ ENTRY(efi_call)
call *%rdi
addq $48, %rsp
RESTORE_XMM
- FRAME_END
+ popq %rbp
ret
ENDPROC(efi_call)
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 92e3e1d84c1d..12734a96df47 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -26,7 +26,5 @@ quiet_cmd_bin2c = BIN2C $@
$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
$(call if_changed,bin2c)
- @:
-
obj-$(CONFIG_KEXEC_FILE) += kexec-purgatory.o
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index b95964610ea7..c556c5ae8de5 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -59,7 +59,6 @@ OBJCOPYFLAGS_realmode.bin := -O binary
targets += realmode.bin
$(obj)/realmode.bin: $(obj)/realmode.elf $(obj)/realmode.relocs FORCE
$(call if_changed,objcopy)
- @:
quiet_cmd_relocs = RELOCS $@
cmd_relocs = arch/x86/tools/relocs --realmode $< > $@
diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c
index 41bfe84e11ab..00f54a91bb4b 100644
--- a/arch/x86/um/os-Linux/registers.c
+++ b/arch/x86/um/os-Linux/registers.c
@@ -11,21 +11,56 @@
#endif
#include <longjmp.h>
#include <sysdep/ptrace_user.h>
+#include <sys/uio.h>
+#include <asm/sigcontext.h>
+#include <linux/elf.h>
-int save_fp_registers(int pid, unsigned long *fp_regs)
+int have_xstate_support;
+
+int save_i387_registers(int pid, unsigned long *fp_regs)
{
if (ptrace(PTRACE_GETFPREGS, pid, 0, fp_regs) < 0)
return -errno;
return 0;
}
-int restore_fp_registers(int pid, unsigned long *fp_regs)
+int save_fp_registers(int pid, unsigned long *fp_regs)
+{
+ struct iovec iov;
+
+ if (have_xstate_support) {
+ iov.iov_base = fp_regs;
+ iov.iov_len = sizeof(struct _xstate);
+ if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0)
+ return -errno;
+ return 0;
+ } else {
+ return save_i387_registers(pid, fp_regs);
+ }
+}
+
+int restore_i387_registers(int pid, unsigned long *fp_regs)
{
if (ptrace(PTRACE_SETFPREGS, pid, 0, fp_regs) < 0)
return -errno;
return 0;
}
+int restore_fp_registers(int pid, unsigned long *fp_regs)
+{
+ struct iovec iov;
+
+ if (have_xstate_support) {
+ iov.iov_base = fp_regs;
+ iov.iov_len = sizeof(struct _xstate);
+ if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0)
+ return -errno;
+ return 0;
+ } else {
+ return restore_i387_registers(pid, fp_regs);
+ }
+}
+
#ifdef __i386__
int have_fpx_regs = 1;
int save_fpx_registers(int pid, unsigned long *fp_regs)
@@ -85,6 +120,16 @@ int put_fp_registers(int pid, unsigned long *regs)
return restore_fp_registers(pid, regs);
}
+void arch_init_registers(int pid)
+{
+ struct _xstate fp_regs;
+ struct iovec iov;
+
+ iov.iov_base = &fp_regs;
+ iov.iov_len = sizeof(struct _xstate);
+ if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) == 0)
+ have_xstate_support = 1;
+}
#endif
unsigned long get_thread_reg(int reg, jmp_buf *buf)
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 47c78d5e5c32..ebd4dd6ef73b 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -194,7 +194,8 @@ static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *c
int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
struct user_i387_struct fpregs;
- err = save_fp_registers(userspace_pid[cpu], (unsigned long *) &fpregs);
+ err = save_i387_registers(userspace_pid[cpu],
+ (unsigned long *) &fpregs);
if (err)
return err;
@@ -214,7 +215,7 @@ static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *c
if (n > 0)
return -EFAULT;
- return restore_fp_registers(userspace_pid[cpu],
+ return restore_i387_registers(userspace_pid[cpu],
(unsigned long *) &fpregs);
}
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index a629694ee750..faab418876ce 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -222,14 +222,14 @@ int is_syscall(unsigned long addr)
static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
{
int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
- long fpregs[HOST_FP_SIZE];
+ struct user_i387_struct fpregs;
- BUG_ON(sizeof(*buf) != sizeof(fpregs));
- err = save_fp_registers(userspace_pid[cpu], fpregs);
+ err = save_i387_registers(userspace_pid[cpu],
+ (unsigned long *) &fpregs);
if (err)
return err;
- n = copy_to_user(buf, fpregs, sizeof(fpregs));
+ n = copy_to_user(buf, &fpregs, sizeof(fpregs));
if (n > 0)
return -EFAULT;
@@ -239,14 +239,14 @@ static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *c
static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
{
int n, cpu = ((struct thread_info *) child->stack)->cpu;
- long fpregs[HOST_FP_SIZE];
+ struct user_i387_struct fpregs;
- BUG_ON(sizeof(*buf) != sizeof(fpregs));
- n = copy_from_user(fpregs, buf, sizeof(fpregs));
+ n = copy_from_user(&fpregs, buf, sizeof(fpregs));
if (n > 0)
return -EFAULT;
- return restore_fp_registers(userspace_pid[cpu], fpregs);
+ return restore_i387_registers(userspace_pid[cpu],
+ (unsigned long *) &fpregs);
}
long subarch_ptrace(struct task_struct *child, long request,
diff --git a/arch/x86/um/shared/sysdep/ptrace_64.h b/arch/x86/um/shared/sysdep/ptrace_64.h
index 919789f1071e..0dc223aa1c2d 100644
--- a/arch/x86/um/shared/sysdep/ptrace_64.h
+++ b/arch/x86/um/shared/sysdep/ptrace_64.h
@@ -57,8 +57,6 @@
#define UPT_SYSCALL_ARG5(r) UPT_R8(r)
#define UPT_SYSCALL_ARG6(r) UPT_R9(r)
-static inline void arch_init_registers(int pid)
-{
-}
+extern void arch_init_registers(int pid);
#endif
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 14fcd01ed992..49e503697022 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -225,26 +225,16 @@ static int copy_sc_from_user(struct pt_regs *regs,
} else
#endif
{
- struct user_i387_struct fp;
-
- err = copy_from_user(&fp, (void *)sc.fpstate,
- sizeof(struct user_i387_struct));
+ err = copy_from_user(regs->regs.fp, (void *)sc.fpstate,
+ sizeof(struct _xstate));
if (err)
return 1;
-
- err = restore_fp_registers(pid, (unsigned long *) &fp);
- if (err < 0) {
- printk(KERN_ERR "copy_sc_from_user - "
- "restore_fp_registers failed, errno = %d\n",
- -err);
- return 1;
- }
}
return 0;
}
static int copy_sc_to_user(struct sigcontext __user *to,
- struct _fpstate __user *to_fp, struct pt_regs *regs,
+ struct _xstate __user *to_fp, struct pt_regs *regs,
unsigned long mask)
{
struct sigcontext sc;
@@ -310,25 +300,22 @@ static int copy_sc_to_user(struct sigcontext __user *to,
return 1;
}
- err = convert_fxsr_to_user(to_fp, &fpx);
+ err = convert_fxsr_to_user(&to_fp->fpstate, &fpx);
if (err)
return 1;
- err |= __put_user(fpx.swd, &to_fp->status);
- err |= __put_user(X86_FXSR_MAGIC, &to_fp->magic);
+ err |= __put_user(fpx.swd, &to_fp->fpstate.status);
+ err |= __put_user(X86_FXSR_MAGIC, &to_fp->fpstate.magic);
if (err)
return 1;
- if (copy_to_user(&to_fp->_fxsr_env[0], &fpx,
+ if (copy_to_user(&to_fp->fpstate._fxsr_env[0], &fpx,
sizeof(struct user_fxsr_struct)))
return 1;
} else
#endif
{
- struct user_i387_struct fp;
-
- err = save_fp_registers(pid, (unsigned long *) &fp);
- if (copy_to_user(to_fp, &fp, sizeof(struct user_i387_struct)))
+ if (copy_to_user(to_fp, regs->regs.fp, sizeof(struct _xstate)))
return 1;
}
@@ -337,7 +324,7 @@ static int copy_sc_to_user(struct sigcontext __user *to,
#ifdef CONFIG_X86_32
static int copy_ucontext_to_user(struct ucontext __user *uc,
- struct _fpstate __user *fp, sigset_t *set,
+ struct _xstate __user *fp, sigset_t *set,
unsigned long sp)
{
int err = 0;
@@ -353,7 +340,7 @@ struct sigframe
char __user *pretcode;
int sig;
struct sigcontext sc;
- struct _fpstate fpstate;
+ struct _xstate fpstate;
unsigned long extramask[_NSIG_WORDS-1];
char retcode[8];
};
@@ -366,7 +353,7 @@ struct rt_sigframe
void __user *puc;
struct siginfo info;
struct ucontext uc;
- struct _fpstate fpstate;
+ struct _xstate fpstate;
char retcode[8];
};
@@ -495,7 +482,7 @@ struct rt_sigframe
char __user *pretcode;
struct ucontext uc;
struct siginfo info;
- struct _fpstate fpstate;
+ struct _xstate fpstate;
};
int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index 470564bbd08e..cb3c22370cf5 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -50,7 +50,7 @@ void foo(void)
DEFINE(HOST_GS, GS);
DEFINE(HOST_ORIG_AX, ORIG_EAX);
#else
- DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long));
+ DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long));
DEFINE_LONGS(HOST_BX, RBX);
DEFINE_LONGS(HOST_CX, RCX);
DEFINE_LONGS(HOST_DI, RDI);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 478a2de543a5..67433714b791 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
/* NOTE: The loop is more greedy than the cleanup_highmap variant.
* We include the PMD passed in on _both_ boundaries. */
- for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+ for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
pmd++, vaddr += PMD_SIZE) {
if (pmd_none(*pmd))
continue;
@@ -1551,41 +1551,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
#endif
}
-#ifdef CONFIG_X86_32
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
- /* If there's an existing pte, then don't allow _PAGE_RW to be set */
- if (pte_val_ma(*ptep) & _PAGE_PRESENT)
- pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
- pte_val_ma(pte));
-
- return pte;
-}
-#else /* CONFIG_X86_64 */
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
- unsigned long pfn;
-
- if (xen_feature(XENFEAT_writable_page_tables) ||
- xen_feature(XENFEAT_auto_translated_physmap) ||
- xen_start_info->mfn_list >= __START_KERNEL_map)
- return pte;
-
- /*
- * Pages belonging to the initial p2m list mapped outside the default
- * address range must be mapped read-only. This region contains the
- * page tables for mapping the p2m list, too, and page tables MUST be
- * mapped read-only.
- */
- pfn = pte_pfn(pte);
- if (pfn >= xen_start_info->first_p2m_pfn &&
- pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
- pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
-
- return pte;
-}
-#endif /* CONFIG_X86_64 */
-
/*
* Init-time set_pte while constructing initial pagetables, which
* doesn't allow RO page table pages to be remapped RW.
@@ -1600,13 +1565,37 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
* so always write the PTE directly and rely on Xen trapping and
* emulating any updates as necessary.
*/
-static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+__visible pte_t xen_make_pte_init(pteval_t pte)
{
- if (pte_mfn(pte) != INVALID_P2M_ENTRY)
- pte = mask_rw_pte(ptep, pte);
- else
- pte = __pte_ma(0);
+#ifdef CONFIG_X86_64
+ unsigned long pfn;
+
+ /*
+ * Pages belonging to the initial p2m list mapped outside the default
+ * address range must be mapped read-only. This region contains the
+ * page tables for mapping the p2m list, too, and page tables MUST be
+ * mapped read-only.
+ */
+ pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+ if (xen_start_info->mfn_list < __START_KERNEL_map &&
+ pfn >= xen_start_info->first_p2m_pfn &&
+ pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+ pte &= ~_PAGE_RW;
+#endif
+ pte = pte_pfn_to_mfn(pte);
+ return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+#ifdef CONFIG_X86_32
+ /* If there's an existing pte, then don't allow _PAGE_RW to be set */
+ if (pte_mfn(pte) != INVALID_P2M_ENTRY
+ && pte_val_ma(*ptep) & _PAGE_PRESENT)
+ pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+ pte_val_ma(pte));
+#endif
native_set_pte(ptep, pte);
}
@@ -2407,6 +2396,7 @@ static void __init xen_post_allocator_init(void)
pv_mmu_ops.alloc_pud = xen_alloc_pud;
pv_mmu_ops.release_pud = xen_release_pud;
#endif
+ pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
#ifdef CONFIG_X86_64
pv_mmu_ops.write_cr3 = &xen_write_cr3;
@@ -2455,7 +2445,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
.pte_val = PV_CALLEE_SAVE(xen_pte_val),
.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
- .make_pte = PV_CALLEE_SAVE(xen_make_pte),
+ .make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
#ifdef CONFIG_X86_PAE
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index cab9f766bb06..dd2a49a8aacc 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -182,7 +182,7 @@ static void * __ref alloc_p2m_page(void)
if (unlikely(!slab_is_available()))
return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE);
- return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
+ return (void *)__get_free_page(GFP_KERNEL);
}
static void __ref free_p2m_page(void *p)
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 7ab29518a3b9..e345891450c3 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -393,6 +393,9 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
unsigned long i = 0;
unsigned long n = end_pfn - start_pfn;
+ if (remap_pfn == 0)
+ remap_pfn = nr_pages;
+
while (i < n) {
unsigned long cur_pfn = start_pfn + i;
unsigned long left = n - i;
@@ -438,17 +441,29 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
return remap_pfn;
}
-static void __init xen_set_identity_and_remap(unsigned long nr_pages)
+static unsigned long __init xen_count_remap_pages(
+ unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+ unsigned long remap_pages)
+{
+ if (start_pfn >= nr_pages)
+ return remap_pages;
+
+ return remap_pages + min(end_pfn, nr_pages) - start_pfn;
+}
+
+static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
+ unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long nr_pages, unsigned long last_val))
{
phys_addr_t start = 0;
- unsigned long last_pfn = nr_pages;
+ unsigned long ret_val = 0;
const struct e820entry *entry = xen_e820_map;
int i;
/*
* Combine non-RAM regions and gaps until a RAM region (or the
- * end of the map) is reached, then set the 1:1 map and
- * remap the memory in those non-RAM regions.
+ * end of the map) is reached, then call the provided function
+ * to perform its duty on the non-RAM region.
*
* The combined non-RAM regions are rounded to a whole number
* of pages so any partial pages are accessible via the 1:1
@@ -466,14 +481,13 @@ static void __init xen_set_identity_and_remap(unsigned long nr_pages)
end_pfn = PFN_UP(entry->addr);
if (start_pfn < end_pfn)
- last_pfn = xen_set_identity_and_remap_chunk(
- start_pfn, end_pfn, nr_pages,
- last_pfn);
+ ret_val = func(start_pfn, end_pfn, nr_pages,
+ ret_val);
start = end;
}
}
- pr_info("Released %ld page(s)\n", xen_released_pages);
+ return ret_val;
}
/*
@@ -596,35 +610,6 @@ static void __init xen_ignore_unusable(void)
}
}
-static unsigned long __init xen_count_remap_pages(unsigned long max_pfn)
-{
- unsigned long extra = 0;
- unsigned long start_pfn, end_pfn;
- const struct e820entry *entry = xen_e820_map;
- int i;
-
- end_pfn = 0;
- for (i = 0; i < xen_e820_map_entries; i++, entry++) {
- start_pfn = PFN_DOWN(entry->addr);
- /* Adjacent regions on non-page boundaries handling! */
- end_pfn = min(end_pfn, start_pfn);
-
- if (start_pfn >= max_pfn)
- return extra + max_pfn - end_pfn;
-
- /* Add any holes in map to result. */
- extra += start_pfn - end_pfn;
-
- end_pfn = PFN_UP(entry->addr + entry->size);
- end_pfn = min(end_pfn, max_pfn);
-
- if (entry->type != E820_RAM)
- extra += end_pfn - start_pfn;
- }
-
- return extra;
-}
-
bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
{
struct e820entry *entry;
@@ -804,7 +789,7 @@ char * __init xen_memory_setup(void)
max_pages = xen_get_max_pages();
/* How many extra pages do we need due to remapping? */
- max_pages += xen_count_remap_pages(max_pfn);
+ max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages);
if (max_pages > max_pfn)
extra_pages += max_pages - max_pfn;
@@ -922,7 +907,9 @@ char * __init xen_memory_setup(void)
* Set identity map on non-RAM pages and prepare remapping the
* underlying RAM.
*/
- xen_set_identity_and_remap(max_pfn);
+ xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk);
+
+ pr_info("Released %ld page(s)\n", xen_released_pages);
return "Xen";
}
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index a0a4e554c6f1..6deba5bc7e34 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -290,11 +290,11 @@ static int xen_vcpuop_set_next_event(unsigned long delta,
WARN_ON(!clockevent_state_oneshot(evt));
single.timeout_abs_ns = get_abs_timeout(delta);
- single.flags = VCPU_SSHOTTMR_future;
+ /* Get an event anyway, even if the timeout is already expired */
+ single.flags = 0;
ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, cpu, &single);
-
- BUG_ON(ret != 0 && ret != -ETIME);
+ BUG_ON(ret != 0);
return ret;
}
diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index d38eb9237e64..1065bc8bcae5 100644
--- a/arch/xtensa/include/asm/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
@@ -44,7 +44,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
pte_t *ptep;
int i;
- ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+ ptep = (pte_t *)__get_free_page(GFP_KERNEL);
if (!ptep)
return NULL;
for (i = 0; i < 1024; i++)
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index a6b00b3af429..ef90479e0397 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -323,23 +323,23 @@ static void xtensa_pmu_read(struct perf_event *event)
static int callchain_trace(struct stackframe *frame, void *data)
{
- struct perf_callchain_entry *entry = data;
+ struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, frame->pc);
return 0;
}
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
- xtensa_backtrace_kernel(regs, sysctl_perf_event_max_stack,
+ xtensa_backtrace_kernel(regs, entry->max_stack,
callchain_trace, NULL, entry);
}
-void perf_callchain_user(struct perf_callchain_entry *entry,
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
- xtensa_backtrace_user(regs, sysctl_perf_event_max_stack,
+ xtensa_backtrace_user(regs, entry->max_stack,
callchain_trace, entry);
}
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 23d7f301a196..9e29dc351695 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -113,6 +113,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
ret = submit_bio_wait(type, bio);
if (ret == -EOPNOTSUPP)
ret = 0;
+ bio_put(bio);
}
blk_finish_plug(&plug);
@@ -165,8 +166,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
}
}
- if (bio)
+ if (bio) {
ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+ bio_put(bio);
+ }
return ret != -EOPNOTSUPP ? ret : 0;
}
EXPORT_SYMBOL(blkdev_issue_write_same);
@@ -206,8 +209,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
}
}
- if (bio)
- return submit_bio_wait(WRITE, bio);
+ if (bio) {
+ ret = submit_bio_wait(WRITE, bio);
+ bio_put(bio);
+ return ret;
+ }
return 0;
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7df9c9263b21..f9b9049b1284 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1262,12 +1262,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_split(q, &bio, q->bio_split);
- if (!is_flush_fua && !blk_queue_nomerges(q)) {
- if (blk_attempt_plug_merge(q, bio, &request_count,
- &same_queue_rq))
- return BLK_QC_T_NONE;
- } else
- request_count = blk_plug_queued_count(q);
+ if (!is_flush_fua && !blk_queue_nomerges(q) &&
+ blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+ return BLK_QC_T_NONE;
rq = blk_mq_map_request(q, bio, &data);
if (unlikely(!rq))
@@ -1358,9 +1355,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_split(q, &bio, q->bio_split);
- if (!is_flush_fua && !blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, &request_count, NULL))
- return BLK_QC_T_NONE;
+ if (!is_flush_fua && !blk_queue_nomerges(q)) {
+ if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
+ return BLK_QC_T_NONE;
+ } else
+ request_count = blk_plug_queued_count(q);
rq = blk_mq_map_request(q, bio, &data);
if (unlikely(!rq))
@@ -2020,7 +2019,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
if (!q->queue_ctx)
- return ERR_PTR(-ENOMEM);
+ goto err_exit;
q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)),
GFP_KERNEL, set->numa_node);
@@ -2084,6 +2083,8 @@ err_map:
kfree(q->queue_hw_ctx);
err_percpu:
free_percpu(q->queue_ctx);
+err_exit:
+ q->mq_ops = NULL;
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(blk_mq_init_allocated_queue);
diff --git a/block/ioctl.c b/block/ioctl.c
index 698c7933d582..ed2397f8de9d 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -4,7 +4,6 @@
#include <linux/gfp.h>
#include <linux/blkpg.h>
#include <linux/hdreg.h>
-#include <linux/badblocks.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/blktrace_api.h>
diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig
index e28e912000a7..331f6baf2df8 100644
--- a/crypto/asymmetric_keys/Kconfig
+++ b/crypto/asymmetric_keys/Kconfig
@@ -13,6 +13,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE
tristate "Asymmetric public-key crypto algorithm subtype"
select MPILIB
select CRYPTO_HASH_INFO
+ select CRYPTO_AKCIPHER
help
This option provides support for asymmetric public key type handling.
If signature generation and/or verification are to be used,
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 43fe85f20d57..7097a3395b25 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -455,6 +455,7 @@ static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = {
[CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
[CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
[CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
+ [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
[CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0,
};
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index 15e4604efba7..1f4128487dd4 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -265,7 +265,7 @@ static int acpi_aml_write_kern(const char *buf, int len)
char *p;
ret = acpi_aml_lock_write(crc, ACPI_AML_OUT_KERN);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
return ret;
/* sync tail before inserting logs */
smp_mb();
@@ -286,7 +286,7 @@ static int acpi_aml_readb_kern(void)
char *p;
ret = acpi_aml_lock_read(crc, ACPI_AML_IN_KERN);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
return ret;
/* sync head before removing cmds */
smp_rmb();
@@ -330,7 +330,7 @@ again:
goto again;
break;
}
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
break;
size += ret;
count -= ret;
@@ -373,7 +373,7 @@ again:
if (ret == 0)
goto again;
}
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
break;
*(msg + size) = (char)ret;
size++;
@@ -526,7 +526,7 @@ static int acpi_aml_open(struct inode *inode, struct file *file)
}
acpi_aml_io.users++;
err_lock:
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
if (acpi_aml_active_reader == file)
acpi_aml_active_reader = NULL;
}
@@ -587,7 +587,7 @@ static int acpi_aml_read_user(char __user *buf, int len)
char *p;
ret = acpi_aml_lock_read(crc, ACPI_AML_OUT_USER);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
return ret;
/* sync head before removing logs */
smp_rmb();
@@ -602,7 +602,7 @@ static int acpi_aml_read_user(char __user *buf, int len)
crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1);
ret = n;
out:
- acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !IS_ERR_VALUE(ret));
+ acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret);
return ret;
}
@@ -634,7 +634,7 @@ again:
goto again;
}
}
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
if (!acpi_aml_running())
ret = 0;
break;
@@ -657,7 +657,7 @@ static int acpi_aml_write_user(const char __user *buf, int len)
char *p;
ret = acpi_aml_lock_write(crc, ACPI_AML_IN_USER);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
return ret;
/* sync tail before inserting cmds */
smp_mb();
@@ -672,7 +672,7 @@ static int acpi_aml_write_user(const char __user *buf, int len)
crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1);
ret = n;
out:
- acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !IS_ERR_VALUE(ret));
+ acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret);
return n;
}
@@ -704,7 +704,7 @@ again:
goto again;
}
}
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
if (!acpi_aml_running())
ret = 0;
break;
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 0d92d0f915e9..c7ba948d253c 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -331,15 +331,6 @@ static int acpi_processor_get_info(struct acpi_device *device)
pr->throttling.duty_width = acpi_gbl_FADT.duty_width;
pr->pblk = object.processor.pblk_address;
-
- /*
- * We don't care about error returns - we just try to mark
- * these reserved so that nobody else is confused into thinking
- * that this region might be unused..
- *
- * (In particular, allocating the IO range for Cardbus)
- */
- request_region(pr->throttling.address, 6, "ACPI CPU throttle");
}
/*
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 3d5b8a099351..c1d138e128cb 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -754,7 +754,8 @@ static int acpi_video_bqc_quirk(struct acpi_video_device *device,
}
int acpi_video_get_levels(struct acpi_device *device,
- struct acpi_video_device_brightness **dev_br)
+ struct acpi_video_device_brightness **dev_br,
+ int *pmax_level)
{
union acpi_object *obj = NULL;
int i, max_level = 0, count = 0, level_ac_battery = 0;
@@ -841,6 +842,8 @@ int acpi_video_get_levels(struct acpi_device *device,
br->count = count;
*dev_br = br;
+ if (pmax_level)
+ *pmax_level = max_level;
out:
kfree(obj);
@@ -869,7 +872,7 @@ acpi_video_init_brightness(struct acpi_video_device *device)
struct acpi_video_device_brightness *br = NULL;
int result = -EINVAL;
- result = acpi_video_get_levels(device->dev, &br);
+ result = acpi_video_get_levels(device->dev, &br, &max_level);
if (result)
return result;
device->brightness = br;
@@ -1737,7 +1740,7 @@ static void acpi_video_run_bcl_for_osi(struct acpi_video_bus *video)
mutex_lock(&video->device_list_lock);
list_for_each_entry(dev, &video->video_device_list, entry) {
- if (!acpi_video_device_lcd_query_levels(dev, &levels))
+ if (!acpi_video_device_lcd_query_levels(dev->dev->handle, &levels))
kfree(levels);
}
mutex_unlock(&video->device_list_lock);
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index a1d177d58254..21932d640a41 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -108,7 +108,9 @@ acpi_ex_add_table(u32 table_index,
/* Add the table to the namespace */
+ acpi_ex_exit_interpreter();
status = acpi_ns_load_table(table_index, parent_node);
+ acpi_ex_enter_interpreter();
if (ACPI_FAILURE(status)) {
acpi_ut_remove_reference(obj_desc);
*ddb_handle = NULL;
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 0f18dbc9a37f..3b7fb99362b6 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -83,27 +83,22 @@ acpi_hw_write_multiple(u32 value,
static u8
acpi_hw_get_access_bit_width(struct acpi_generic_address *reg, u8 max_bit_width)
{
- u64 address;
-
if (!reg->access_width) {
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+ max_bit_width = 32;
+ }
+
/*
* Detect old register descriptors where only the bit_width field
- * makes senses. The target address is copied to handle possible
- * alignment issues.
+ * makes senses.
*/
- ACPI_MOVE_64_TO_64(&address, &reg->address);
- if (!reg->bit_offset && reg->bit_width &&
+ if (reg->bit_width < max_bit_width &&
+ !reg->bit_offset && reg->bit_width &&
ACPI_IS_POWER_OF_TWO(reg->bit_width) &&
- ACPI_IS_ALIGNED(reg->bit_width, 8) &&
- ACPI_IS_ALIGNED(address, reg->bit_width)) {
+ ACPI_IS_ALIGNED(reg->bit_width, 8)) {
return (reg->bit_width);
- } else {
- if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
- return (32);
- } else {
- return (max_bit_width);
- }
}
+ return (max_bit_width);
} else {
return (1 << (reg->access_width + 2));
}
@@ -311,12 +306,6 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
{
u64 address;
- u8 access_width;
- u32 bit_width;
- u8 bit_offset;
- u64 value64;
- u32 new_value32, old_value32;
- u8 index;
acpi_status status;
ACPI_FUNCTION_NAME(hw_write);
@@ -328,145 +317,23 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
return (status);
}
- /* Convert access_width into number of bits based */
-
- access_width = acpi_hw_get_access_bit_width(reg, 32);
- bit_width = reg->bit_offset + reg->bit_width;
- bit_offset = reg->bit_offset;
-
/*
* Two address spaces supported: Memory or IO. PCI_Config is
* not supported here because the GAS structure is insufficient
*/
- index = 0;
- while (bit_width) {
- /*
- * Use offset style bit reads because "Index * AccessWidth" is
- * ensured to be less than 32-bits by acpi_hw_validate_register().
- */
- new_value32 = ACPI_GET_BITS(&value, index * access_width,
- ACPI_MASK_BITS_ABOVE_32
- (access_width));
-
- if (bit_offset >= access_width) {
- bit_offset -= access_width;
- } else {
- /*
- * Use offset style bit masks because access_width is ensured
- * to be less than 32-bits by acpi_hw_validate_register() and
- * bit_offset/bit_width is less than access_width here.
- */
- if (bit_offset) {
- new_value32 &= ACPI_MASK_BITS_BELOW(bit_offset);
- }
- if (bit_width < access_width) {
- new_value32 &= ACPI_MASK_BITS_ABOVE(bit_width);
- }
-
- if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
- if (bit_offset || bit_width < access_width) {
- /*
- * Read old values in order not to modify the bits that
- * are beyond the register bit_width/bit_offset setting.
- */
- status =
- acpi_os_read_memory((acpi_physical_address)
- address +
- index *
- ACPI_DIV_8
- (access_width),
- &value64,
- access_width);
- old_value32 = (u32)value64;
-
- /*
- * Use offset style bit masks because access_width is
- * ensured to be less than 32-bits by
- * acpi_hw_validate_register() and bit_offset/bit_width is
- * less than access_width here.
- */
- if (bit_offset) {
- old_value32 &=
- ACPI_MASK_BITS_ABOVE
- (bit_offset);
- bit_offset = 0;
- }
- if (bit_width < access_width) {
- old_value32 &=
- ACPI_MASK_BITS_BELOW
- (bit_width);
- }
-
- new_value32 |= old_value32;
- }
-
- value64 = (u64)new_value32;
- status =
- acpi_os_write_memory((acpi_physical_address)
- address +
- index *
- ACPI_DIV_8
- (access_width),
- value64, access_width);
- } else { /* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
-
- if (bit_offset || bit_width < access_width) {
- /*
- * Read old values in order not to modify the bits that
- * are beyond the register bit_width/bit_offset setting.
- */
- status =
- acpi_hw_read_port((acpi_io_address)
- address +
- index *
- ACPI_DIV_8
- (access_width),
- &old_value32,
- access_width);
-
- /*
- * Use offset style bit masks because access_width is
- * ensured to be less than 32-bits by
- * acpi_hw_validate_register() and bit_offset/bit_width is
- * less than access_width here.
- */
- if (bit_offset) {
- old_value32 &=
- ACPI_MASK_BITS_ABOVE
- (bit_offset);
- bit_offset = 0;
- }
- if (bit_width < access_width) {
- old_value32 &=
- ACPI_MASK_BITS_BELOW
- (bit_width);
- }
-
- new_value32 |= old_value32;
- }
-
- status = acpi_hw_write_port((acpi_io_address)
- address +
- index *
- ACPI_DIV_8
- (access_width),
- new_value32,
- access_width);
- }
- }
-
- /*
- * Index * access_width is ensured to be less than 32-bits by
- * acpi_hw_validate_register().
- */
- bit_width -=
- bit_width > access_width ? access_width : bit_width;
- index++;
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+ status = acpi_os_write_memory((acpi_physical_address)
+ address, (u64)value,
+ reg->bit_width);
+ } else { /* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
+
+ status = acpi_hw_write_port((acpi_io_address)
+ address, value, reg->bit_width);
}
ACPI_DEBUG_PRINT((ACPI_DB_IO,
"Wrote: %8.8X width %2d to %8.8X%8.8X (%s)\n",
- value, access_width, ACPI_FORMAT_UINT64(address),
+ value, reg->bit_width, ACPI_FORMAT_UINT64(address),
acpi_ut_get_region_name(reg->space_id)));
return (status);
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index f631a47724f0..1783cd7e1446 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -47,6 +47,7 @@
#include "acparser.h"
#include "acdispat.h"
#include "actables.h"
+#include "acinterp.h"
#define _COMPONENT ACPI_NAMESPACE
ACPI_MODULE_NAME("nsparse")
@@ -170,6 +171,8 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
ACPI_FUNCTION_TRACE(ns_parse_table);
+ acpi_ex_enter_interpreter();
+
/*
* AML Parse, pass 1
*
@@ -185,7 +188,7 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS1,
table_index, start_node);
if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
+ goto error_exit;
}
/*
@@ -201,8 +204,10 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS2,
table_index, start_node);
if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
+ goto error_exit;
}
+error_exit:
+ acpi_ex_exit_interpreter();
return_ACPI_STATUS(status);
}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b719ab3090bb..ab234791a0ba 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -1316,7 +1316,7 @@ static int __init acpi_battery_init(void)
static void __exit acpi_battery_exit(void)
{
- async_synchronize_cookie(async_cookie);
+ async_synchronize_cookie(async_cookie + 1);
acpi_bus_unregister_driver(&acpi_battery_driver);
#ifdef CONFIG_ACPI_PROCFS_POWER
acpi_unlock_battery_dir(acpi_battery_dir);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 31e8da648fff..262ca31b86d9 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1051,7 +1051,7 @@ static int __init acpi_bus_init(void)
* Maybe EC region is required at bus_scan/acpi_get_devices. So it
* is necessary to enable it as early as possible.
*/
- acpi_boot_ec_enable();
+ acpi_ec_dsdt_probe();
printk(KERN_INFO PREFIX "Interpreter enabled\n");
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index cd2c3d6d40e0..993fd31394c8 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -319,6 +319,7 @@ int acpi_device_fix_up_power(struct acpi_device *device)
return ret;
}
+EXPORT_SYMBOL_GPL(acpi_device_fix_up_power);
int acpi_device_update_power(struct acpi_device *device, int *state_p)
{
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 0e70181f150c..73c76d646064 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1446,10 +1446,30 @@ ec_parse_io_ports(struct acpi_resource *resource, void *context)
return AE_OK;
}
-int __init acpi_boot_ec_enable(void)
+static const struct acpi_device_id ec_device_ids[] = {
+ {"PNP0C09", 0},
+ {"", 0},
+};
+
+int __init acpi_ec_dsdt_probe(void)
{
- if (!boot_ec)
+ acpi_status status;
+
+ if (boot_ec)
return 0;
+
+ /*
+ * Finding EC from DSDT if there is no ECDT EC available. When this
+ * function is invoked, ACPI tables have been fully loaded, we can
+ * walk namespace now.
+ */
+ boot_ec = make_acpi_ec();
+ if (!boot_ec)
+ return -ENOMEM;
+ status = acpi_get_devices(ec_device_ids[0].id,
+ ec_parse_device, boot_ec, NULL);
+ if (ACPI_FAILURE(status) || !boot_ec->handle)
+ return -ENODEV;
if (!ec_install_handlers(boot_ec)) {
first_ec = boot_ec;
return 0;
@@ -1457,11 +1477,6 @@ int __init acpi_boot_ec_enable(void)
return -EFAULT;
}
-static const struct acpi_device_id ec_device_ids[] = {
- {"PNP0C09", 0},
- {"", 0},
-};
-
#if 0
/*
* Some EC firmware variations refuses to respond QR_EC when SCI_EVT is not
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 9bb0773d39bf..27cc7feabfe4 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -181,7 +181,7 @@ typedef int (*acpi_ec_query_func) (void *data);
int acpi_ec_init(void);
int acpi_ec_ecdt_probe(void);
-int acpi_boot_ec_enable(void);
+int acpi_ec_dsdt_probe(void);
void acpi_ec_block_transactions(void);
void acpi_ec_unblock_transactions(void);
void acpi_ec_unblock_transactions_early(void);
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 2215fc847fa9..ac6ddcc080d4 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -928,7 +928,7 @@ static ssize_t format_show(struct device *dev,
{
struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
- return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->code));
+ return sprintf(buf, "0x%04x\n", le16_to_cpu(dcr->code));
}
static DEVICE_ATTR_RO(format);
@@ -961,8 +961,8 @@ static ssize_t format1_show(struct device *dev,
continue;
if (nfit_dcr->dcr->code == dcr->code)
continue;
- rc = sprintf(buf, "%#x\n",
- be16_to_cpu(nfit_dcr->dcr->code));
+ rc = sprintf(buf, "0x%04x\n",
+ le16_to_cpu(nfit_dcr->dcr->code));
break;
}
if (rc != ENXIO)
@@ -1131,11 +1131,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
/*
* Until standardization materializes we need to consider up to 3
- * different command sets. Note, that checking for function0 (bit0)
- * tells us if any commands are reachable through this uuid.
+ * different command sets. Note, that checking for zero functions
+ * tells us if any commands might be reachable through this uuid.
*/
for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_HPE2; i++)
- if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
+ if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 0))
break;
/* limit the supported commands to those that are publicly documented */
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 11cb38348aef..02b9ea1e8d2e 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -53,12 +53,12 @@ enum nfit_uuids {
};
/*
- * Region format interface codes are stored as an array of bytes in the
- * NFIT DIMM Control Region structure
+ * Region format interface codes are stored with the interface as the
+ * LSB and the function as the MSB.
*/
-#define NFIT_FIC_BYTE cpu_to_be16(0x101) /* byte-addressable energy backed */
-#define NFIT_FIC_BLK cpu_to_be16(0x201) /* block-addressable non-energy backed */
-#define NFIT_FIC_BYTEN cpu_to_be16(0x301) /* byte-addressable non-energy backed */
+#define NFIT_FIC_BYTE cpu_to_le16(0x101) /* byte-addressable energy backed */
+#define NFIT_FIC_BLK cpu_to_le16(0x201) /* block-addressable non-energy backed */
+#define NFIT_FIC_BYTEN cpu_to_le16(0x301) /* byte-addressable non-energy backed */
enum {
NFIT_BLK_READ_FLUSH = 1,
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 8fc7323ed3e8..4ed4061813e6 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -839,7 +839,7 @@ void acpi_penalize_isa_irq(int irq, int active)
{
if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty)))
acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) +
- active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING;
+ (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
}
bool acpi_isa_irq_available(int irq)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index f170d746336d..c72e64893d03 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -676,6 +676,15 @@ static int acpi_processor_get_throttling_fadt(struct acpi_processor *pr)
if (!pr->flags.throttling)
return -ENODEV;
+ /*
+ * We don't care about error returns - we just try to mark
+ * these reserved so that nobody else is confused into thinking
+ * that this region might be unused..
+ *
+ * (In particular, allocating the IO range for Cardbus)
+ */
+ request_region(pr->throttling.address, 6, "ACPI CPU throttle");
+
pr->throttling.state = 0;
duty_mask = pr->throttling.state_count - 1;
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 22c09952e177..b4de130f2d57 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -680,9 +680,6 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
u64 mask = 0;
union acpi_object *obj;
- if (funcs == 0)
- return false;
-
obj = acpi_evaluate_dsm(handle, uuid, rev, 0, NULL);
if (!obj)
return false;
@@ -695,6 +692,9 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
mask |= (((u64)obj->buffer.pointer[i]) << (i * 8));
ACPI_FREE(obj);
+ if (funcs == 0)
+ return true;
+
/*
* Bit 0 indicates whether there's support for any functions other than
* function 0 for the specified UUID and revision.
diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c
index 6e702ab57220..1d31c0c0fc20 100644
--- a/drivers/ata/ahci_seattle.c
+++ b/drivers/ata/ahci_seattle.c
@@ -137,7 +137,7 @@ static const struct ata_port_info *ahci_seattle_get_port_info(
u32 val;
plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL);
- if (IS_ERR(plat_data))
+ if (!plat_data)
return &ahci_port_info;
plat_data->sgpio_ctrl = devm_ioremap_resource(dev,
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 61dc7a99e89a..c6f017458958 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host)
ata_scsi_port_error_handler(host, ap);
/* finish or retry handled scmd's and clean up */
- WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+ WARN_ON(!list_empty(&eh_work_q));
DPRINTK("EXIT\n");
}
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index 8638d575b2b9..aafb8cc03523 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -197,7 +197,7 @@ static void highbank_set_em_messages(struct device *dev,
for (i = 0; i < SGPIO_PINS; i++) {
err = of_get_named_gpio(np, "calxeda,sgpio-gpio", i);
- if (IS_ERR_VALUE(err))
+ if (err < 0)
return;
pdata->sgpio_gpio[i] = err;
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index bd74ee555278..745489a1c86a 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -986,7 +986,7 @@ static inline void mv_write_cached_reg(void __iomem *addr, u32 *old, u32 new)
* Looks like a lot of fuss, but it avoids an unnecessary
* +1 usec read-after-write delay for unaffected registers.
*/
- laddr = (long)addr & 0xffff;
+ laddr = (unsigned long)addr & 0xffff;
if (laddr >= 0x300 && laddr <= 0x33c) {
laddr &= 0x000f;
if (laddr == 0x4 || laddr == 0xc) {
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index a969a7e443be..85aaf2222587 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -181,13 +181,17 @@ static char *res_strings[] = {
"reserved 27",
"reserved 28",
"reserved 29",
- "reserved 30",
+ "reserved 30", /* FIXME: The strings between 30-40 might be wrong. */
"reassembly abort: no buffers",
"receive buffer overflow",
"change in GFC",
"receive buffer full",
"low priority discard - no receive descriptor",
"low priority discard - missing end of packet",
+ "reserved 37",
+ "reserved 38",
+ "reserved 39",
+ "reseverd 40",
"reserved 41",
"reserved 42",
"reserved 43",
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 7d00f2994738..809dd1e02091 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -1128,7 +1128,7 @@ static int rx_pkt(struct atm_dev *dev)
/* make the ptr point to the corresponding buffer desc entry */
buf_desc_ptr += desc;
if (!desc || (desc > iadev->num_rx_desc) ||
- ((buf_desc_ptr->vc_index & 0xffff) > iadev->num_vc)) {
+ ((buf_desc_ptr->vc_index & 0xffff) >= iadev->num_vc)) {
free_desc(dev, desc);
IF_ERR(printk("IA: bad descriptor desc = %d \n", desc);)
return -1;
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 6b2a84e7f2be..2609ba20b396 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
obj-y += power/
obj-$(CONFIG_HAS_DMA) += dma-mapping.o
obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
-obj-$(CONFIG_ISA) += isa.o
+obj-$(CONFIG_ISA_BUS_API) += isa.o
obj-$(CONFIG_FW_LOADER) += firmware_class.o
obj-$(CONFIG_NUMA) += node.o
obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index 91dba65d7264..cd6ccdcf9df0 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -180,4 +180,4 @@ static int __init isa_bus_init(void)
return error;
}
-device_initcall(isa_bus_init);
+postcore_initcall(isa_bus_init);
diff --git a/drivers/base/module.c b/drivers/base/module.c
index db930d3ee312..2a215780eda2 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv)
static void module_create_drivers_dir(struct module_kobject *mk)
{
- if (!mk || mk->drivers_dir)
- return;
+ static DEFINE_MUTEX(drivers_dir_mutex);
- mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+ mutex_lock(&drivers_dir_mutex);
+ if (mk && !mk->drivers_dir)
+ mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+ mutex_unlock(&drivers_dir_mutex);
}
void module_add_driver(struct module *mod, struct device_driver *drv)
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index c81667d4bb60..e44944f4be77 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1267,14 +1267,15 @@ int dpm_suspend_late(pm_message_t state)
error = device_suspend_late(dev);
mutex_lock(&dpm_list_mtx);
+ if (!list_empty(&dev->power.entry))
+ list_move(&dev->power.entry, &dpm_late_early_list);
+
if (error) {
pm_dev_err(dev, state, " late", error);
dpm_save_failed_dev(dev_name(dev));
put_device(dev);
break;
}
- if (!list_empty(&dev->power.entry))
- list_move(&dev->power.entry, &dpm_late_early_list);
put_device(dev);
if (async_error)
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index 83d6e7ba1a34..8c3434bdb26d 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -211,7 +211,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
}
/* Mark opp-table as multiple CPUs are sharing it now */
- opp_table->shared_opp = true;
+ opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
}
unlock:
mutex_unlock(&opp_table_lock);
@@ -227,7 +227,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
*
* This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
*
- * Returns -ENODEV if OPP table isn't already present.
+ * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
+ * table's status is access-unknown.
*
* Locking: The internal opp_table and opp structures are RCU protected.
* Hence this function internally uses RCU updater strategy with mutex locks
@@ -249,9 +250,14 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
goto unlock;
}
+ if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
cpumask_clear(cpumask);
- if (opp_table->shared_opp) {
+ if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
list_for_each_entry(opp_dev, &opp_table->dev_list, node)
cpumask_set_cpu(opp_dev->dev->id, cpumask);
} else {
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 94d2010558e3..1dfd3dd92624 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -34,7 +34,10 @@ static struct opp_table *_managed_opp(const struct device_node *np)
* But the OPPs will be considered as shared only if the
* OPP table contains a "opp-shared" property.
*/
- return opp_table->shared_opp ? opp_table : NULL;
+ if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED)
+ return opp_table;
+
+ return NULL;
}
}
@@ -353,7 +356,10 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
}
opp_table->np = opp_np;
- opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+ if (of_property_read_bool(opp_np, "opp-shared"))
+ opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
+ else
+ opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
mutex_unlock(&opp_table_lock);
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 20f3be22e060..fabd5ca1a083 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -119,6 +119,12 @@ struct opp_device {
#endif
};
+enum opp_table_access {
+ OPP_TABLE_ACCESS_UNKNOWN = 0,
+ OPP_TABLE_ACCESS_EXCLUSIVE = 1,
+ OPP_TABLE_ACCESS_SHARED = 2,
+};
+
/**
* struct opp_table - Device opp structure
* @node: table node - contains the devices with OPPs that
@@ -166,7 +172,7 @@ struct opp_table {
/* For backward compatibility with v1 bindings */
unsigned int voltage_tolerance_v1;
- bool shared_opp;
+ enum opp_table_access shared_opp;
struct dev_pm_opp *suspend_opp;
unsigned int *supported_hw;
diff --git a/drivers/bcma/driver_chipcommon_sflash.c b/drivers/bcma/driver_chipcommon_sflash.c
index 04d706ca5f43..35b13a08ca3e 100644
--- a/drivers/bcma/driver_chipcommon_sflash.c
+++ b/drivers/bcma/driver_chipcommon_sflash.c
@@ -146,7 +146,6 @@ int bcma_sflash_init(struct bcma_drv_cc *cc)
return -ENOTSUPP;
}
- sflash->window = BCMA_SOC_FLASH2;
sflash->blocksize = e->blocksize;
sflash->numblocks = e->numblocks;
sflash->size = sflash->blocksize * sflash->numblocks;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index d597e432e195..ab19adb07a12 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1750,7 +1750,7 @@ aoecmd_init(void)
int ret;
/* get_zeroed_page returns page with ref count 1 */
- p = (void *) get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+ p = (void *) get_zeroed_page(GFP_KERNEL);
if (!p)
return -ENOMEM;
empty_page = virt_to_page(p);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 51a071e32221..c04bd9bc39fd 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -381,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
#ifdef CONFIG_BLK_DEV_RAM_DAX
static long brd_direct_access(struct block_device *bdev, sector_t sector,
- void __pmem **kaddr, pfn_t *pfn)
+ void __pmem **kaddr, pfn_t *pfn, long size)
{
struct brd_device *brd = bdev->bd_disk->private_data;
struct page *page;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 31e73a7a40f2..6a48ed41963f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -941,7 +941,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
debugfs_create_u32("timeout", 0444, dir, &nbd->xmit_timeout);
debugfs_create_u32("blocksize", 0444, dir, &nbd->blksize);
- debugfs_create_file("flags", 0444, dir, &nbd, &nbd_dbg_flags_ops);
+ debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
return 0;
}
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 0ede6d7e2568..81666a56415e 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -350,12 +350,12 @@ struct rbd_device {
struct rbd_spec *spec;
struct rbd_options *opts;
- char *header_name;
+ struct ceph_object_id header_oid;
+ struct ceph_object_locator header_oloc;
struct ceph_file_layout layout;
- struct ceph_osd_event *watch_event;
- struct rbd_obj_request *watch_request;
+ struct ceph_osd_linger_request *watch_handle;
struct rbd_spec *parent_spec;
u64 parent_overlap;
@@ -1596,12 +1596,6 @@ static int rbd_obj_request_wait(struct rbd_obj_request *obj_request)
return __rbd_obj_request_wait(obj_request, 0);
}
-static int rbd_obj_request_wait_timeout(struct rbd_obj_request *obj_request,
- unsigned long timeout)
-{
- return __rbd_obj_request_wait(obj_request, timeout);
-}
-
static void rbd_img_request_complete(struct rbd_img_request *img_request)
{
@@ -1751,12 +1745,6 @@ static void rbd_obj_request_complete(struct rbd_obj_request *obj_request)
complete_all(&obj_request->completion);
}
-static void rbd_osd_trivial_callback(struct rbd_obj_request *obj_request)
-{
- dout("%s: obj %p\n", __func__, obj_request);
- obj_request_done_set(obj_request);
-}
-
static void rbd_osd_read_callback(struct rbd_obj_request *obj_request)
{
struct rbd_img_request *img_request = NULL;
@@ -1828,13 +1816,12 @@ static void rbd_osd_call_callback(struct rbd_obj_request *obj_request)
obj_request_done_set(obj_request);
}
-static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
- struct ceph_msg *msg)
+static void rbd_osd_req_callback(struct ceph_osd_request *osd_req)
{
struct rbd_obj_request *obj_request = osd_req->r_priv;
u16 opcode;
- dout("%s: osd_req %p msg %p\n", __func__, osd_req, msg);
+ dout("%s: osd_req %p\n", __func__, osd_req);
rbd_assert(osd_req == obj_request->osd_req);
if (obj_request_img_data_test(obj_request)) {
rbd_assert(obj_request->img_request);
@@ -1878,10 +1865,6 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_CALL:
rbd_osd_call_callback(obj_request);
break;
- case CEPH_OSD_OP_NOTIFY_ACK:
- case CEPH_OSD_OP_WATCH:
- rbd_osd_trivial_callback(obj_request);
- break;
default:
rbd_warn(NULL, "%s: unsupported op %hu",
obj_request->object_name, (unsigned short) opcode);
@@ -1896,27 +1879,17 @@ static void rbd_osd_req_format_read(struct rbd_obj_request *obj_request)
{
struct rbd_img_request *img_request = obj_request->img_request;
struct ceph_osd_request *osd_req = obj_request->osd_req;
- u64 snap_id;
- rbd_assert(osd_req != NULL);
-
- snap_id = img_request ? img_request->snap_id : CEPH_NOSNAP;
- ceph_osdc_build_request(osd_req, obj_request->offset,
- NULL, snap_id, NULL);
+ if (img_request)
+ osd_req->r_snapid = img_request->snap_id;
}
static void rbd_osd_req_format_write(struct rbd_obj_request *obj_request)
{
- struct rbd_img_request *img_request = obj_request->img_request;
struct ceph_osd_request *osd_req = obj_request->osd_req;
- struct ceph_snap_context *snapc;
- struct timespec mtime = CURRENT_TIME;
- rbd_assert(osd_req != NULL);
-
- snapc = img_request ? img_request->snapc : NULL;
- ceph_osdc_build_request(osd_req, obj_request->offset,
- snapc, CEPH_NOSNAP, &mtime);
+ osd_req->r_mtime = CURRENT_TIME;
+ osd_req->r_data_offset = obj_request->offset;
}
/*
@@ -1954,7 +1927,7 @@ static struct ceph_osd_request *rbd_osd_req_create(
osd_req = ceph_osdc_alloc_request(osdc, snapc, num_ops, false,
GFP_NOIO);
if (!osd_req)
- return NULL; /* ENOMEM */
+ goto fail;
if (op_type == OBJ_OP_WRITE || op_type == OBJ_OP_DISCARD)
osd_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
@@ -1965,9 +1938,18 @@ static struct ceph_osd_request *rbd_osd_req_create(
osd_req->r_priv = obj_request;
osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);
- ceph_oid_set_name(&osd_req->r_base_oid, obj_request->object_name);
+ if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",
+ obj_request->object_name))
+ goto fail;
+
+ if (ceph_osdc_alloc_messages(osd_req, GFP_NOIO))
+ goto fail;
return osd_req;
+
+fail:
+ ceph_osdc_put_request(osd_req);
+ return NULL;
}
/*
@@ -2003,16 +1985,25 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops,
false, GFP_NOIO);
if (!osd_req)
- return NULL; /* ENOMEM */
+ goto fail;
osd_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
osd_req->r_callback = rbd_osd_req_callback;
osd_req->r_priv = obj_request;
osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);
- ceph_oid_set_name(&osd_req->r_base_oid, obj_request->object_name);
+ if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",
+ obj_request->object_name))
+ goto fail;
+
+ if (ceph_osdc_alloc_messages(osd_req, GFP_NOIO))
+ goto fail;
return osd_req;
+
+fail:
+ ceph_osdc_put_request(osd_req);
+ return NULL;
}
@@ -2973,17 +2964,20 @@ static int rbd_img_request_submit(struct rbd_img_request *img_request)
{
struct rbd_obj_request *obj_request;
struct rbd_obj_request *next_obj_request;
+ int ret = 0;
dout("%s: img %p\n", __func__, img_request);
- for_each_obj_request_safe(img_request, obj_request, next_obj_request) {
- int ret;
+ rbd_img_request_get(img_request);
+ for_each_obj_request_safe(img_request, obj_request, next_obj_request) {
ret = rbd_img_obj_request_submit(obj_request);
if (ret)
- return ret;
+ goto out_put_ireq;
}
- return 0;
+out_put_ireq:
+ rbd_img_request_put(img_request);
+ return ret;
}
static void rbd_img_parent_read_callback(struct rbd_img_request *img_request)
@@ -3090,45 +3084,18 @@ out_err:
obj_request_done_set(obj_request);
}
-static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
-{
- struct rbd_obj_request *obj_request;
- struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
- int ret;
-
- obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0,
- OBJ_REQUEST_NODATA);
- if (!obj_request)
- return -ENOMEM;
-
- ret = -ENOMEM;
- obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
- obj_request);
- if (!obj_request->osd_req)
- goto out;
-
- osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_NOTIFY_ACK,
- notify_id, 0, 0);
- rbd_osd_req_format_read(obj_request);
+static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev);
+static void __rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev);
- ret = rbd_obj_request_submit(osdc, obj_request);
- if (ret)
- goto out;
- ret = rbd_obj_request_wait(obj_request);
-out:
- rbd_obj_request_put(obj_request);
-
- return ret;
-}
-
-static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
+static void rbd_watch_cb(void *arg, u64 notify_id, u64 cookie,
+ u64 notifier_id, void *data, size_t data_len)
{
- struct rbd_device *rbd_dev = (struct rbd_device *)data;
+ struct rbd_device *rbd_dev = arg;
+ struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
int ret;
- dout("%s: \"%s\" notify_id %llu opcode %u\n", __func__,
- rbd_dev->header_name, (unsigned long long)notify_id,
- (unsigned int)opcode);
+ dout("%s rbd_dev %p cookie %llu notify_id %llu\n", __func__, rbd_dev,
+ cookie, notify_id);
/*
* Until adequate refresh error handling is in place, there is
@@ -3140,63 +3107,31 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
if (ret)
rbd_warn(rbd_dev, "refresh failed: %d", ret);
- ret = rbd_obj_notify_ack_sync(rbd_dev, notify_id);
+ ret = ceph_osdc_notify_ack(osdc, &rbd_dev->header_oid,
+ &rbd_dev->header_oloc, notify_id, cookie,
+ NULL, 0);
if (ret)
rbd_warn(rbd_dev, "notify_ack ret %d", ret);
}
-/*
- * Send a (un)watch request and wait for the ack. Return a request
- * with a ref held on success or error.
- */
-static struct rbd_obj_request *rbd_obj_watch_request_helper(
- struct rbd_device *rbd_dev,
- bool watch)
+static void rbd_watch_errcb(void *arg, u64 cookie, int err)
{
- struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
- struct ceph_options *opts = osdc->client->options;
- struct rbd_obj_request *obj_request;
+ struct rbd_device *rbd_dev = arg;
int ret;
- obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0,
- OBJ_REQUEST_NODATA);
- if (!obj_request)
- return ERR_PTR(-ENOMEM);
-
- obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_WRITE, 1,
- obj_request);
- if (!obj_request->osd_req) {
- ret = -ENOMEM;
- goto out;
- }
-
- osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
- rbd_dev->watch_event->cookie, 0, watch);
- rbd_osd_req_format_write(obj_request);
+ rbd_warn(rbd_dev, "encountered watch error: %d", err);
- if (watch)
- ceph_osdc_set_request_linger(osdc, obj_request->osd_req);
-
- ret = rbd_obj_request_submit(osdc, obj_request);
- if (ret)
- goto out;
+ __rbd_dev_header_unwatch_sync(rbd_dev);
- ret = rbd_obj_request_wait_timeout(obj_request, opts->mount_timeout);
- if (ret)
- goto out;
-
- ret = obj_request->result;
+ ret = rbd_dev_header_watch_sync(rbd_dev);
if (ret) {
- if (watch)
- rbd_obj_request_end(obj_request);
- goto out;
+ rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
+ return;
}
- return obj_request;
-
-out:
- rbd_obj_request_put(obj_request);
- return ERR_PTR(ret);
+ ret = rbd_dev_refresh(rbd_dev);
+ if (ret)
+ rbd_warn(rbd_dev, "reregisteration refresh failed: %d", ret);
}
/*
@@ -3205,35 +3140,33 @@ out:
static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev)
{
struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
- struct rbd_obj_request *obj_request;
- int ret;
+ struct ceph_osd_linger_request *handle;
- rbd_assert(!rbd_dev->watch_event);
- rbd_assert(!rbd_dev->watch_request);
+ rbd_assert(!rbd_dev->watch_handle);
- ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev,
- &rbd_dev->watch_event);
- if (ret < 0)
- return ret;
+ handle = ceph_osdc_watch(osdc, &rbd_dev->header_oid,
+ &rbd_dev->header_oloc, rbd_watch_cb,
+ rbd_watch_errcb, rbd_dev);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
- obj_request = rbd_obj_watch_request_helper(rbd_dev, true);
- if (IS_ERR(obj_request)) {
- ceph_osdc_cancel_event(rbd_dev->watch_event);
- rbd_dev->watch_event = NULL;
- return PTR_ERR(obj_request);
- }
+ rbd_dev->watch_handle = handle;
+ return 0;
+}
- /*
- * A watch request is set to linger, so the underlying osd
- * request won't go away until we unregister it. We retain
- * a pointer to the object request during that time (in
- * rbd_dev->watch_request), so we'll keep a reference to it.
- * We'll drop that reference after we've unregistered it in
- * rbd_dev_header_unwatch_sync().
- */
- rbd_dev->watch_request = obj_request;
+static void __rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
+{
+ struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+ int ret;
- return 0;
+ if (!rbd_dev->watch_handle)
+ return;
+
+ ret = ceph_osdc_unwatch(osdc, rbd_dev->watch_handle);
+ if (ret)
+ rbd_warn(rbd_dev, "failed to unwatch: %d", ret);
+
+ rbd_dev->watch_handle = NULL;
}
/*
@@ -3241,24 +3174,7 @@ static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev)
*/
static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
{
- struct rbd_obj_request *obj_request;
-
- rbd_assert(rbd_dev->watch_event);
- rbd_assert(rbd_dev->watch_request);
-
- rbd_obj_request_end(rbd_dev->watch_request);
- rbd_obj_request_put(rbd_dev->watch_request);
- rbd_dev->watch_request = NULL;
-
- obj_request = rbd_obj_watch_request_helper(rbd_dev, false);
- if (!IS_ERR(obj_request))
- rbd_obj_request_put(obj_request);
- else
- rbd_warn(rbd_dev, "unable to tear down watch request (%ld)",
- PTR_ERR(obj_request));
-
- ceph_osdc_cancel_event(rbd_dev->watch_event);
- rbd_dev->watch_event = NULL;
+ __rbd_dev_header_unwatch_sync(rbd_dev);
dout("%s flushing notifies\n", __func__);
ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
@@ -3591,7 +3507,7 @@ static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev)
if (!ondisk)
return -ENOMEM;
- ret = rbd_obj_read_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_read_sync(rbd_dev, rbd_dev->header_oid.name,
0, size, ondisk);
if (ret < 0)
goto out;
@@ -4033,6 +3949,8 @@ static void rbd_dev_release(struct device *dev)
struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
bool need_put = !!rbd_dev->opts;
+ ceph_oid_destroy(&rbd_dev->header_oid);
+
rbd_put_client(rbd_dev->rbd_client);
rbd_spec_put(rbd_dev->spec);
kfree(rbd_dev->opts);
@@ -4063,6 +3981,9 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
INIT_LIST_HEAD(&rbd_dev->node);
init_rwsem(&rbd_dev->header_rwsem);
+ ceph_oid_init(&rbd_dev->header_oid);
+ ceph_oloc_init(&rbd_dev->header_oloc);
+
rbd_dev->dev.bus = &rbd_bus_type;
rbd_dev->dev.type = &rbd_device_type;
rbd_dev->dev.parent = &rbd_root_dev;
@@ -4111,7 +4032,7 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
__le64 size;
} __attribute__ ((packed)) size_buf = { 0 };
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_size",
&snapid, sizeof (snapid),
&size_buf, sizeof (size_buf));
@@ -4151,7 +4072,7 @@ static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev)
if (!reply_buf)
return -ENOMEM;
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_object_prefix", NULL, 0,
reply_buf, RBD_OBJ_PREFIX_LEN_MAX);
dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret);
@@ -4186,7 +4107,7 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id,
u64 unsup;
int ret;
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_features",
&snapid, sizeof (snapid),
&features_buf, sizeof (features_buf));
@@ -4248,7 +4169,7 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
}
snapid = cpu_to_le64(rbd_dev->spec->snap_id);
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_parent",
&snapid, sizeof (snapid),
reply_buf, size);
@@ -4351,7 +4272,7 @@ static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev)
u64 stripe_count;
int ret;
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_stripe_unit_count", NULL, 0,
(char *)&striping_info_buf, size);
dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret);
@@ -4599,7 +4520,7 @@ static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev)
if (!reply_buf)
return -ENOMEM;
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_snapcontext", NULL, 0,
reply_buf, size);
dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret);
@@ -4664,7 +4585,7 @@ static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev,
return ERR_PTR(-ENOMEM);
snapid = cpu_to_le64(snap_id);
- ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
+ ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_oid.name,
"rbd", "get_snapshot_name",
&snapid, sizeof (snapid),
reply_buf, size);
@@ -4975,13 +4896,13 @@ static int rbd_add_get_pool_id(struct rbd_client *rbdc, const char *pool_name)
again:
ret = ceph_pg_poolid_by_name(rbdc->client->osdc.osdmap, pool_name);
if (ret == -ENOENT && tries++ < 1) {
- ret = ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
- &newest_epoch);
+ ret = ceph_monc_get_version(&rbdc->client->monc, "osdmap",
+ &newest_epoch);
if (ret < 0)
return ret;
if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
- ceph_monc_request_next_osdmap(&rbdc->client->monc);
+ ceph_osdc_maybe_request_map(&rbdc->client->osdc);
(void) ceph_monc_wait_osdmap(&rbdc->client->monc,
newest_epoch,
opts->mount_timeout);
@@ -5260,35 +5181,26 @@ err_out_unlock:
static int rbd_dev_header_name(struct rbd_device *rbd_dev)
{
struct rbd_spec *spec = rbd_dev->spec;
- size_t size;
+ int ret;
/* Record the header object name for this rbd image. */
rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
+ rbd_dev->header_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);
if (rbd_dev->image_format == 1)
- size = strlen(spec->image_name) + sizeof (RBD_SUFFIX);
+ ret = ceph_oid_aprintf(&rbd_dev->header_oid, GFP_KERNEL, "%s%s",
+ spec->image_name, RBD_SUFFIX);
else
- size = sizeof (RBD_HEADER_PREFIX) + strlen(spec->image_id);
-
- rbd_dev->header_name = kmalloc(size, GFP_KERNEL);
- if (!rbd_dev->header_name)
- return -ENOMEM;
+ ret = ceph_oid_aprintf(&rbd_dev->header_oid, GFP_KERNEL, "%s%s",
+ RBD_HEADER_PREFIX, spec->image_id);
- if (rbd_dev->image_format == 1)
- sprintf(rbd_dev->header_name, "%s%s",
- spec->image_name, RBD_SUFFIX);
- else
- sprintf(rbd_dev->header_name, "%s%s",
- RBD_HEADER_PREFIX, spec->image_id);
- return 0;
+ return ret;
}
static void rbd_dev_image_release(struct rbd_device *rbd_dev)
{
rbd_dev_unprobe(rbd_dev);
- kfree(rbd_dev->header_name);
- rbd_dev->header_name = NULL;
rbd_dev->image_format = 0;
kfree(rbd_dev->spec->image_id);
rbd_dev->spec->image_id = NULL;
@@ -5327,7 +5239,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
pr_info("image %s/%s does not exist\n",
rbd_dev->spec->pool_name,
rbd_dev->spec->image_name);
- goto out_header_name;
+ goto err_out_format;
}
}
@@ -5373,7 +5285,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
goto err_out_probe;
dout("discovered format %u image, header name is %s\n",
- rbd_dev->image_format, rbd_dev->header_name);
+ rbd_dev->image_format, rbd_dev->header_oid.name);
return 0;
err_out_probe:
@@ -5381,9 +5293,6 @@ err_out_probe:
err_out_watch:
if (!depth)
rbd_dev_header_unwatch_sync(rbd_dev);
-out_header_name:
- kfree(rbd_dev->header_name);
- rbd_dev->header_name = NULL;
err_out_format:
rbd_dev->image_format = 0;
kfree(rbd_dev->spec->image_id);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ca13df854639..2e6d1e9c3345 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -874,8 +874,12 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *qd)
{
unsigned long flags;
- struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)hctx->driver_data;
+ int qid = hctx->queue_num;
+ struct blkfront_info *info = hctx->queue->queuedata;
+ struct blkfront_ring_info *rinfo = NULL;
+ BUG_ON(info->nr_rings <= qid);
+ rinfo = &info->rinfo[qid];
blk_mq_start_request(qd->rq);
spin_lock_irqsave(&rinfo->ring_lock, flags);
if (RING_FULL(&rinfo->ring))
@@ -901,20 +905,9 @@ out_busy:
return BLK_MQ_RQ_QUEUE_BUSY;
}
-static int blk_mq_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
- unsigned int index)
-{
- struct blkfront_info *info = (struct blkfront_info *)data;
-
- BUG_ON(info->nr_rings <= index);
- hctx->driver_data = &info->rinfo[index];
- return 0;
-}
-
static struct blk_mq_ops blkfront_mq_ops = {
.queue_rq = blkif_queue_rq,
.map_queue = blk_mq_map_queue,
- .init_hctx = blk_mq_init_hctx,
};
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
@@ -950,6 +943,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
return PTR_ERR(rq);
}
+ rq->queuedata = info;
queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
if (info->feature_discard) {
@@ -2149,6 +2143,8 @@ static int blkfront_resume(struct xenbus_device *dev)
return err;
err = talk_to_blkback(dev, info);
+ if (!err)
+ blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings);
/*
* We have to wait for the backend to switch to
@@ -2485,10 +2481,23 @@ static void blkback_changed(struct xenbus_device *dev,
break;
case XenbusStateConnected:
- if (dev->state != XenbusStateInitialised) {
+ /*
+ * talk_to_blkback sets state to XenbusStateInitialised
+ * and blkfront_connect sets it to XenbusStateConnected
+ * (if connection went OK).
+ *
+ * If the backend (or toolstack) decides to poke at backend
+ * state (and re-trigger the watch by setting the state repeatedly
+ * to XenbusStateConnected (4)) we need to deal with this.
+ * This is allowed as this is used to communicate to the guest
+ * that the size of disk has changed!
+ */
+ if ((dev->state != XenbusStateInitialised) &&
+ (dev->state != XenbusStateConnected)) {
if (talk_to_blkback(dev, info))
break;
}
+
blkfront_connect(info);
break;
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 94fb407d8561..44b1bd6baa38 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3820,6 +3820,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
while (!list_empty(&intf->waiting_rcv_msgs)) {
smi_msg = list_entry(intf->waiting_rcv_msgs.next,
struct ipmi_smi_msg, link);
+ list_del(&smi_msg->link);
if (!run_to_completion)
spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock,
flags);
@@ -3829,11 +3830,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
if (rv > 0) {
/*
* To preserve message order, quit if we
- * can't handle a message.
+ * can't handle a message. Add the message
+ * back at the head, this is safe because this
+ * tasklet is the only thing that pulls the
+ * messages.
*/
+ list_add(&smi_msg->link, &intf->waiting_rcv_msgs);
break;
} else {
- list_del(&smi_msg->link);
if (rv == 0)
/* Message handled */
ipmi_free_smi_msg(smi_msg);
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 53ddba26578c..98efbfcdb503 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -175,6 +175,7 @@ config COMMON_CLK_KEYSTONE
config COMMON_CLK_NXP
def_bool COMMON_CLK && (ARCH_LPC18XX || ARCH_LPC32XX)
select REGMAP_MMIO if ARCH_LPC32XX
+ select MFD_SYSCON if ARCH_LPC18XX
---help---
Support for clock providers on NXP platforms.
diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c
index efba7d4dbcfc..79bcb2e42060 100644
--- a/drivers/clk/clk-oxnas.c
+++ b/drivers/clk/clk-oxnas.c
@@ -144,9 +144,9 @@ static int oxnas_stdclk_probe(struct platform_device *pdev)
return -ENOMEM;
regmap = syscon_node_to_regmap(of_get_parent(np));
- if (!regmap) {
+ if (IS_ERR(regmap)) {
dev_err(&pdev->dev, "failed to have parent regmap\n");
- return -EINVAL;
+ return PTR_ERR(regmap);
}
for (i = 0; i < ARRAY_SIZE(clk_oxnas_init); i++) {
diff --git a/drivers/clk/clk-pwm.c b/drivers/clk/clk-pwm.c
index 883045814dac..1630a1f085f7 100644
--- a/drivers/clk/clk-pwm.c
+++ b/drivers/clk/clk-pwm.c
@@ -59,6 +59,7 @@ static int clk_pwm_probe(struct platform_device *pdev)
struct clk_init_data init;
struct clk_pwm *clk_pwm;
struct pwm_device *pwm;
+ struct pwm_args pargs;
const char *clk_name;
struct clk *clk;
int ret;
@@ -71,22 +72,28 @@ static int clk_pwm_probe(struct platform_device *pdev)
if (IS_ERR(pwm))
return PTR_ERR(pwm);
- if (!pwm->period) {
+ pwm_get_args(pwm, &pargs);
+ if (!pargs.period) {
dev_err(&pdev->dev, "invalid PWM period\n");
return -EINVAL;
}
if (of_property_read_u32(node, "clock-frequency", &clk_pwm->fixed_rate))
- clk_pwm->fixed_rate = NSEC_PER_SEC / pwm->period;
+ clk_pwm->fixed_rate = NSEC_PER_SEC / pargs.period;
- if (pwm->period != NSEC_PER_SEC / clk_pwm->fixed_rate &&
- pwm->period != DIV_ROUND_UP(NSEC_PER_SEC, clk_pwm->fixed_rate)) {
+ if (pargs.period != NSEC_PER_SEC / clk_pwm->fixed_rate &&
+ pargs.period != DIV_ROUND_UP(NSEC_PER_SEC, clk_pwm->fixed_rate)) {
dev_err(&pdev->dev,
"clock-frequency does not match PWM period\n");
return -EINVAL;
}
- ret = pwm_config(pwm, (pwm->period + 1) >> 1, pwm->period);
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to the
+ * atomic PWM API.
+ */
+ pwm_apply_args(pwm);
+ ret = pwm_config(pwm, (pargs.period + 1) >> 1, pargs.period);
if (ret < 0)
return ret;
diff --git a/drivers/clk/microchip/clk-pic32mzda.c b/drivers/clk/microchip/clk-pic32mzda.c
index 020a29acc5b0..51f54380474b 100644
--- a/drivers/clk/microchip/clk-pic32mzda.c
+++ b/drivers/clk/microchip/clk-pic32mzda.c
@@ -180,15 +180,15 @@ static int pic32mzda_clk_probe(struct platform_device *pdev)
/* register fixed rate clocks */
clks[POSCCLK] = clk_register_fixed_rate(&pdev->dev, "posc_clk", NULL,
- CLK_IS_ROOT, 24000000);
+ 0, 24000000);
clks[FRCCLK] = clk_register_fixed_rate(&pdev->dev, "frc_clk", NULL,
- CLK_IS_ROOT, 8000000);
+ 0, 8000000);
clks[BFRCCLK] = clk_register_fixed_rate(&pdev->dev, "bfrc_clk", NULL,
- CLK_IS_ROOT, 8000000);
+ 0, 8000000);
clks[LPRCCLK] = clk_register_fixed_rate(&pdev->dev, "lprc_clk", NULL,
- CLK_IS_ROOT, 32000);
+ 0, 32000);
clks[UPLLCLK] = clk_register_fixed_rate(&pdev->dev, "usbphy_clk", NULL,
- CLK_IS_ROOT, 24000000);
+ 0, 24000000);
/* fixed rate (optional) clock */
if (of_find_property(np, "microchip,pic32mzda-sosc", NULL)) {
pr_info("pic32-clk: dt requests SOSC.\n");
diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c
index 4bb130cd0062..05b3d73bfefa 100644
--- a/drivers/clk/rockchip/clk-cpu.c
+++ b/drivers/clk/rockchip/clk-cpu.c
@@ -321,9 +321,9 @@ struct clk *rockchip_clk_register_cpuclk(const char *name,
}
cclk = clk_register(NULL, &cpuclk->hw);
- if (IS_ERR(clk)) {
+ if (IS_ERR(cclk)) {
pr_err("%s: could not register cpuclk %s\n", __func__, name);
- ret = PTR_ERR(clk);
+ ret = PTR_ERR(cclk);
goto free_rate_table;
}
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index bc856f21f6b2..077fcdc7908b 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -41,8 +41,6 @@ static unsigned long rockchip_mmc_recalc(struct clk_hw *hw,
#define ROCKCHIP_MMC_DEGREE_MASK 0x3
#define ROCKCHIP_MMC_DELAYNUM_OFFSET 2
#define ROCKCHIP_MMC_DELAYNUM_MASK (0xff << ROCKCHIP_MMC_DELAYNUM_OFFSET)
-#define ROCKCHIP_MMC_INIT_STATE_RESET 0x1
-#define ROCKCHIP_MMC_INIT_STATE_SHIFT 1
#define PSECS_PER_SEC 1000000000000LL
@@ -154,6 +152,7 @@ struct clk *rockchip_clk_register_mmc(const char *name,
return ERR_PTR(-ENOMEM);
init.name = name;
+ init.flags = 0;
init.num_parents = num_parents;
init.parent_names = parent_names;
init.ops = &rockchip_mmc_clk_ops;
@@ -162,15 +161,6 @@ struct clk *rockchip_clk_register_mmc(const char *name,
mmc_clock->reg = reg;
mmc_clock->shift = shift;
- /*
- * Assert init_state to soft reset the CLKGEN
- * for mmc tuning phase and degree
- */
- if (mmc_clock->shift == ROCKCHIP_MMC_INIT_STATE_SHIFT)
- writel(HIWORD_UPDATE(ROCKCHIP_MMC_INIT_STATE_RESET,
- ROCKCHIP_MMC_INIT_STATE_RESET,
- mmc_clock->shift), mmc_clock->reg);
-
clk = clk_register(NULL, &mmc_clock->hw);
if (IS_ERR(clk))
kfree(mmc_clock);
diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index 291543f52caa..8059a8d3ea36 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -832,9 +832,9 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = {
RK3399_CLKGATE_CON(13), 1, GFLAGS),
/* perihp */
- GATE(0, "cpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
+ GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
RK3399_CLKGATE_CON(5), 0, GFLAGS),
- GATE(0, "gpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
+ GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
RK3399_CLKGATE_CON(5), 1, GFLAGS),
COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED,
RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS,
@@ -1466,6 +1466,8 @@ static struct rockchip_clk_branch rk3399_clk_pmu_branches[] __initdata = {
static const char *const rk3399_cru_critical_clocks[] __initconst = {
"aclk_cci_pre",
+ "aclk_gic",
+ "aclk_gic_noc",
"pclk_perilp0",
"pclk_perilp0",
"hclk_perilp0",
@@ -1508,6 +1510,7 @@ static void __init rk3399_clk_init(struct device_node *np)
ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
if (IS_ERR(ctx)) {
pr_err("%s: rockchip clk init failed\n", __func__);
+ iounmap(reg_base);
return;
}
@@ -1553,6 +1556,7 @@ static void __init rk3399_pmu_clk_init(struct device_node *np)
ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS);
if (IS_ERR(ctx)) {
pr_err("%s: rockchip pmu clk init failed\n", __func__);
+ iounmap(reg_base);
return;
}
diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c
index b8551813ec43..456cf586d2c2 100644
--- a/drivers/clk/tegra/clk-tegra210.c
+++ b/drivers/clk/tegra/clk-tegra210.c
@@ -1221,7 +1221,7 @@ static int tegra210_pll_fixed_mdiv_cfg(struct clk_hw *hw,
p = rate >= params->vco_min ? 1 : -EINVAL;
}
- if (IS_ERR_VALUE(p))
+ if (p < 0)
return -EINVAL;
cfg->m = tegra_pll_get_fixed_mdiv(hw, input_rate);
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 15d06fcf0b50..b02f9c606e0b 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -56,11 +56,21 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
/* proc_event_counts is used as the sequence number of the netlink message */
static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
-static inline void get_seq(__u32 *ts, int *cpu)
+static inline void send_msg(struct cn_msg *msg)
{
preempt_disable();
- *ts = __this_cpu_inc_return(proc_event_counts) - 1;
- *cpu = smp_processor_id();
+
+ msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
+ ((struct proc_event *)msg->data)->cpu = smp_processor_id();
+
+ /*
+ * Preemption remains disabled during send to ensure the messages are
+ * ordered according to their sequence numbers.
+ *
+ * If cn_netlink_send() fails, the data is not sent.
+ */
+ cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
+
preempt_enable();
}
@@ -77,7 +87,6 @@ void proc_fork_connector(struct task_struct *task)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_FORK;
rcu_read_lock();
@@ -92,8 +101,7 @@ void proc_fork_connector(struct task_struct *task)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- /* If cn_netlink_send() failed, the data is not sent */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_exec_connector(struct task_struct *task)
@@ -108,7 +116,6 @@ void proc_exec_connector(struct task_struct *task)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_EXEC;
ev->event_data.exec.process_pid = task->pid;
@@ -118,7 +125,7 @@ void proc_exec_connector(struct task_struct *task)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_id_connector(struct task_struct *task, int which_id)
@@ -150,14 +157,13 @@ void proc_id_connector(struct task_struct *task, int which_id)
return;
}
rcu_read_unlock();
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_sid_connector(struct task_struct *task)
@@ -172,7 +178,6 @@ void proc_sid_connector(struct task_struct *task)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_SID;
ev->event_data.sid.process_pid = task->pid;
@@ -182,7 +187,7 @@ void proc_sid_connector(struct task_struct *task)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
@@ -197,7 +202,6 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_PTRACE;
ev->event_data.ptrace.process_pid = task->pid;
@@ -215,7 +219,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_comm_connector(struct task_struct *task)
@@ -230,7 +234,6 @@ void proc_comm_connector(struct task_struct *task)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_COMM;
ev->event_data.comm.process_pid = task->pid;
@@ -241,7 +244,7 @@ void proc_comm_connector(struct task_struct *task)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_coredump_connector(struct task_struct *task)
@@ -256,7 +259,6 @@ void proc_coredump_connector(struct task_struct *task)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_COREDUMP;
ev->event_data.coredump.process_pid = task->pid;
@@ -266,7 +268,7 @@ void proc_coredump_connector(struct task_struct *task)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
void proc_exit_connector(struct task_struct *task)
@@ -281,7 +283,6 @@ void proc_exit_connector(struct task_struct *task)
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
- get_seq(&msg->seq, &ev->cpu);
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_EXIT;
ev->event_data.exit.process_pid = task->pid;
@@ -293,7 +294,7 @@ void proc_exit_connector(struct task_struct *task)
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
/*
@@ -325,7 +326,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
msg->ack = rcvd_ack + 1;
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
- cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+ send_msg(msg);
}
/**
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3646b143bbf5..0bb44d5b5df4 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -79,15 +79,16 @@ static const struct of_device_id machines[] __initconst = {
static int __init cpufreq_dt_platdev_init(void)
{
struct device_node *np = of_find_node_by_path("/");
+ const struct of_device_id *match;
if (!np)
return -ENODEV;
- if (!of_match_node(machines, np))
+ match = of_match_node(machines, np);
+ of_node_put(np);
+ if (!match)
return -ENODEV;
- of_node_put(of_root);
-
return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1,
NULL, 0));
}
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 035513b012ee..5617c7087d77 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -78,9 +78,14 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
static int cpufreq_start_governor(struct cpufreq_policy *policy);
-static inline int cpufreq_exit_governor(struct cpufreq_policy *policy)
+static inline void cpufreq_exit_governor(struct cpufreq_policy *policy)
{
- return cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+ (void)cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+}
+
+static inline void cpufreq_stop_governor(struct cpufreq_policy *policy)
+{
+ (void)cpufreq_governor(policy, CPUFREQ_GOV_STOP);
}
/**
@@ -1026,13 +1031,8 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
return 0;
down_write(&policy->rwsem);
- if (has_target()) {
- ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
- if (ret) {
- pr_err("%s: Failed to stop governor\n", __func__);
- goto unlock;
- }
- }
+ if (has_target())
+ cpufreq_stop_governor(policy);
cpumask_set_cpu(cpu, policy->cpus);
@@ -1041,8 +1041,6 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
if (ret)
pr_err("%s: Failed to start governor\n", __func__);
}
-
-unlock:
up_write(&policy->rwsem);
return ret;
}
@@ -1354,11 +1352,8 @@ static void cpufreq_offline(unsigned int cpu)
}
down_write(&policy->rwsem);
- if (has_target()) {
- ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
- if (ret)
- pr_err("%s: Failed to stop governor\n", __func__);
- }
+ if (has_target())
+ cpufreq_stop_governor(policy);
cpumask_clear_cpu(cpu, policy->cpus);
@@ -1387,12 +1382,8 @@ static void cpufreq_offline(unsigned int cpu)
if (cpufreq_driver->stop_cpu)
cpufreq_driver->stop_cpu(policy);
- /* If cpu is last user of policy, free policy */
- if (has_target()) {
- ret = cpufreq_exit_governor(policy);
- if (ret)
- pr_err("%s: Failed to exit governor\n", __func__);
- }
+ if (has_target())
+ cpufreq_exit_governor(policy);
/*
* Perform the ->exit() even during light-weight tear-down,
@@ -1626,7 +1617,6 @@ EXPORT_SYMBOL(cpufreq_generic_suspend);
void cpufreq_suspend(void)
{
struct cpufreq_policy *policy;
- int ret;
if (!cpufreq_driver)
return;
@@ -1639,14 +1629,8 @@ void cpufreq_suspend(void)
for_each_active_policy(policy) {
if (has_target()) {
down_write(&policy->rwsem);
- ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+ cpufreq_stop_governor(policy);
up_write(&policy->rwsem);
-
- if (ret) {
- pr_err("%s: Failed to stop governor for policy: %p\n",
- __func__, policy);
- continue;
- }
}
if (cpufreq_driver->suspend && cpufreq_driver->suspend(policy))
@@ -1848,7 +1832,7 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq)
{
- clamp_val(target_freq, policy->min, policy->max);
+ target_freq = clamp_val(target_freq, policy->min, policy->max);
return cpufreq_driver->fast_switch(policy, target_freq);
}
@@ -2049,16 +2033,15 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
ret = policy->governor->governor(policy, event);
- if (!ret) {
- if (event == CPUFREQ_GOV_POLICY_INIT)
+ if (event == CPUFREQ_GOV_POLICY_INIT) {
+ if (ret)
+ module_put(policy->governor->owner);
+ else
policy->governor->initialized++;
- else if (event == CPUFREQ_GOV_POLICY_EXIT)
- policy->governor->initialized--;
- }
-
- if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
- ((event == CPUFREQ_GOV_POLICY_EXIT) && !ret))
+ } else if (event == CPUFREQ_GOV_POLICY_EXIT) {
+ policy->governor->initialized--;
module_put(policy->governor->owner);
+ }
return ret;
}
@@ -2221,20 +2204,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
old_gov = policy->governor;
/* end old governor */
if (old_gov) {
- ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
- if (ret) {
- /* This can happen due to race with other operations */
- pr_debug("%s: Failed to Stop Governor: %s (%d)\n",
- __func__, old_gov->name, ret);
- return ret;
- }
-
- ret = cpufreq_exit_governor(policy);
- if (ret) {
- pr_err("%s: Failed to Exit Governor: %s (%d)\n",
- __func__, old_gov->name, ret);
- return ret;
- }
+ cpufreq_stop_governor(policy);
+ cpufreq_exit_governor(policy);
}
/* start new governor */
@@ -2290,6 +2261,10 @@ int cpufreq_update_policy(unsigned int cpu)
* -> ask driver for current freq and notify governors about a change
*/
if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
+ if (cpufreq_suspended) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
new_policy.cur = cpufreq_update_current_freq(policy);
if (WARN_ON(!new_policy.cur)) {
ret = -EIO;
@@ -2495,10 +2470,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
register_hotcpu_notifier(&cpufreq_cpu_notifier);
pr_debug("driver %s up and running\n", driver_data->name);
-
-out:
- put_online_cpus();
- return ret;
+ goto out;
err_if_unreg:
subsys_interface_unregister(&cpufreq_interface);
@@ -2508,7 +2480,9 @@ err_null_driver:
write_lock_irqsave(&cpufreq_driver_lock, flags);
cpufreq_driver = NULL;
write_unlock_irqrestore(&cpufreq_driver_lock, flags);
- goto out;
+out:
+ put_online_cpus();
+ return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_register_driver);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b76a98dd9988..1fa1a32928d7 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -372,26 +372,9 @@ static bool intel_pstate_get_ppc_enable_status(void)
return acpi_ppc;
}
-/*
- * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
- * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
- * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
- * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
- * target ratio 0x17. The _PSS control value stores in a format which can be
- * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
- * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
- * This function converts the _PSS control value to intel pstate driver format
- * for comparison and assignment.
- */
-static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
-{
- return cpu->acpi_perf_data.states[index].control >> 8;
-}
-
static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
{
struct cpudata *cpu;
- int turbo_pss_ctl;
int ret;
int i;
@@ -441,15 +424,14 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
* max frequency, which will cause a reduced performance as
* this driver uses real max turbo frequency as the max
* frequency. So correct this frequency in _PSS table to
- * correct max turbo frequency based on the turbo ratio.
+ * correct max turbo frequency based on the turbo state.
* Also need to convert to MHz as _PSS freq is in MHz.
*/
- turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
- if (turbo_pss_ctl > cpu->pstate.max_pstate)
+ if (!limits->turbo_disabled)
cpu->acpi_perf_data.states[0].core_frequency =
policy->cpuinfo.max_freq / 1000;
cpu->valid_pss_table = true;
- pr_info("_PPC limits will be enforced\n");
+ pr_debug("_PPC limits will be enforced\n");
return;
@@ -1418,6 +1400,9 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
{
struct cpudata *cpu = all_cpu_data[cpu_num];
+ if (cpu->update_util_set)
+ return;
+
/* Prevent intel_pstate_update_util() from using stale data. */
cpu->sample.time = 0;
cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
@@ -1458,15 +1443,15 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
if (!policy->cpuinfo.max_freq)
return -ENODEV;
- intel_pstate_clear_update_util_hook(policy->cpu);
+ pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
+ policy->cpuinfo.max_freq, policy->max);
cpu = all_cpu_data[0];
- if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate) {
- if (policy->max < policy->cpuinfo.max_freq &&
- policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
- pr_debug("policy->max > max non turbo frequency\n");
- policy->max = policy->cpuinfo.max_freq;
- }
+ if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+ policy->max < policy->cpuinfo.max_freq &&
+ policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
+ pr_debug("policy->max > max non turbo frequency\n");
+ policy->max = policy->cpuinfo.max_freq;
}
if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
@@ -1496,13 +1481,13 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
limits->max_sysfs_pct);
limits->max_perf_pct = max(limits->min_policy_pct,
limits->max_perf_pct);
- limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
/* Make sure min_perf_pct <= max_perf_pct */
limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
limits->min_perf = div_fp(limits->min_perf_pct, 100);
limits->max_perf = div_fp(limits->max_perf_pct, 100);
+ limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
out:
intel_pstate_set_update_util_hook(policy->cpu);
@@ -1559,8 +1544,11 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
/* cpuinfo and default policy values */
policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
- policy->cpuinfo.max_freq =
- cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+ update_turbo_state();
+ policy->cpuinfo.max_freq = limits->turbo_disabled ?
+ cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
+ policy->cpuinfo.max_freq *= cpu->pstate.scaling;
+
intel_pstate_init_acpi_perf_limits(policy);
policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
cpumask_set_cpu(policy->cpu, policy->cpus);
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 6f602c7a71bd..643f43179df1 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -307,17 +307,24 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
return 0;
}
+#define DYNAMIC_POWER "dynamic-power-coefficient"
+
static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
{
struct mtk_cpu_dvfs_info *info = policy->driver_data;
struct device_node *np = of_node_get(info->cpu_dev->of_node);
+ u32 capacitance = 0;
if (WARN_ON(!np))
return;
if (of_find_property(np, "#cooling-cells", NULL)) {
- info->cdev = of_cpufreq_cooling_register(np,
- policy->related_cpus);
+ of_property_read_u32(np, DYNAMIC_POWER, &capacitance);
+
+ info->cdev = of_cpufreq_power_cooling_register(np,
+ policy->related_cpus,
+ capacitance,
+ NULL);
if (IS_ERR(info->cdev)) {
dev_err(info->cpu_dev,
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index cead9bec4843..376e63ca94e8 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -54,7 +54,7 @@ static int omap_target(struct cpufreq_policy *policy, unsigned int index)
freq = new_freq * 1000;
ret = clk_round_rate(policy->clk, freq);
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
dev_warn(mpu_dev,
"CPUfreq: Cannot find matching frequency for %lu\n",
freq);
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 808a320e9d5d..a7ecb9a84c15 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -487,7 +487,7 @@ static int __init pcc_cpufreq_probe(void)
doorbell.space_id = reg_resource->space_id;
doorbell.bit_width = reg_resource->bit_width;
doorbell.bit_offset = reg_resource->bit_offset;
- doorbell.access_width = 64;
+ doorbell.access_width = 4;
doorbell.address = reg_resource->address;
pr_debug("probe: doorbell: space_id is %d, bit_width is %d, "
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 2b8e6ce62e81..a4d0059e232c 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -214,7 +214,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
tick_broadcast_exit();
}
- if (!cpuidle_state_is_coupled(drv, entered_state))
+ if (!cpuidle_state_is_coupled(drv, index))
local_irq_enable();
/*
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 44d30b45f3cc..5ad5f3009ae0 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -402,7 +402,7 @@ int caam_get_era(void)
ret = of_property_read_u32(caam_node, "fsl,sec-era", &prop);
of_node_put(caam_node);
- return IS_ERR_VALUE(ret) ? -ENOTSUPP : prop;
+ return ret ? -ENOTSUPP : prop;
}
EXPORT_SYMBOL(caam_get_era);
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
index 52c7395cb8d8..0d0d4529ee36 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
@@ -122,6 +122,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
unsigned int unit;
+ u32 unit_size;
int ret;
if (!ctx->u.aes.key_len)
@@ -133,11 +134,17 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
if (!req->info)
return -EINVAL;
- for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++)
- if (!(req->nbytes & (unit_size_map[unit].size - 1)))
- break;
+ unit_size = CCP_XTS_AES_UNIT_SIZE__LAST;
+ if (req->nbytes <= unit_size_map[0].size) {
+ for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++) {
+ if (!(req->nbytes & (unit_size_map[unit].size - 1))) {
+ unit_size = unit_size_map[unit].value;
+ break;
+ }
+ }
+ }
- if ((unit_size_map[unit].value == CCP_XTS_AES_UNIT_SIZE__LAST) ||
+ if ((unit_size == CCP_XTS_AES_UNIT_SIZE__LAST) ||
(ctx->u.aes.key_len != AES_KEYSIZE_128)) {
/* Use the fallback to process the request for any
* unsupported unit sizes or key sizes
@@ -158,7 +165,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
rctx->cmd.engine = CCP_ENGINE_XTS_AES_128;
rctx->cmd.u.xts.action = (encrypt) ? CCP_AES_ACTION_ENCRYPT
: CCP_AES_ACTION_DECRYPT;
- rctx->cmd.u.xts.unit_size = unit_size_map[unit].value;
+ rctx->cmd.u.xts.unit_size = unit_size;
rctx->cmd.u.xts.key = &ctx->u.aes.key_sg;
rctx->cmd.u.xts.key_len = ctx->u.aes.key_len;
rctx->cmd.u.xts.iv = &rctx->iv_sg;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 6eefaa2fe58f..63464e86f2b1 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -1986,7 +1986,7 @@ err_algs:
&dd->pdata->algs_info[i].algs_list[j]);
err_pm:
pm_runtime_disable(dev);
- if (dd->polling_mode)
+ if (!dd->polling_mode)
dma_release_channel(dd->dma_lch);
data_err:
dev_err(dev, "initialization failed.\n");
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 574e87c7f2b8..9acccad26928 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -781,7 +781,7 @@ static int hash_process_data(struct hash_device_data *device_data,
&device_data->state);
memmove(req_ctx->state.buffer,
device_data->state.buffer,
- HASH_BLOCK_SIZE / sizeof(u32));
+ HASH_BLOCK_SIZE);
if (ret) {
dev_err(device_data->dev,
"%s: hash_resume_state() failed!\n",
@@ -832,7 +832,7 @@ static int hash_process_data(struct hash_device_data *device_data,
memmove(device_data->state.buffer,
req_ctx->state.buffer,
- HASH_BLOCK_SIZE / sizeof(u32));
+ HASH_BLOCK_SIZE);
if (ret) {
dev_err(device_data->dev, "%s: hash_save_state() failed!\n",
__func__);
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 495577b6d31b..94ad5c0adbcb 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -182,7 +182,7 @@ struct crypto_alg p8_aes_cbc_alg = {
.cra_name = "cbc(aes)",
.cra_driver_name = "p8_aes_cbc",
.cra_module = THIS_MODULE,
- .cra_priority = 1000,
+ .cra_priority = 2000,
.cra_type = &crypto_blkcipher_type,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
.cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 0a3c1b04cf3c..38ed10d761d0 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -166,7 +166,7 @@ struct crypto_alg p8_aes_ctr_alg = {
.cra_name = "ctr(aes)",
.cra_driver_name = "p8_aes_ctr",
.cra_module = THIS_MODULE,
- .cra_priority = 1000,
+ .cra_priority = 2000,
.cra_type = &crypto_blkcipher_type,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
.cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index 9f4994cabcc7..b18e67d0e065 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -141,7 +141,7 @@ my $vmr = sub {
# Some ABIs specify vrsave, special-purpose register #256, as reserved
# for system use.
-my $no_vrsave = ($flavour =~ /aix|linux64le/);
+my $no_vrsave = ($flavour =~ /linux-ppc64le/);
my $mtspr = sub {
my ($f,$idx,$ra) = @_;
if ($idx == 256 && $no_vrsave) {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 1d6c803804d5..e92418facc92 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -268,8 +268,11 @@ int update_devfreq(struct devfreq *devfreq)
devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE);
err = devfreq->profile->target(devfreq->dev.parent, &freq, flags);
- if (err)
+ if (err) {
+ freqs.new = cur_freq;
+ devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
return err;
+ }
freqs.new = freq;
devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
@@ -552,6 +555,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
devfreq->profile = profile;
strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
devfreq->previous_freq = profile->initial_freq;
+ devfreq->last_status.current_frequency = profile->initial_freq;
devfreq->data = data;
devfreq->nb.notifier_call = devfreq_notifier_call;
@@ -561,23 +565,22 @@ struct devfreq *devfreq_add_device(struct device *dev,
mutex_lock(&devfreq->lock);
}
- devfreq->trans_table = devm_kzalloc(dev, sizeof(unsigned int) *
- devfreq->profile->max_state *
- devfreq->profile->max_state,
- GFP_KERNEL);
- devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) *
- devfreq->profile->max_state,
- GFP_KERNEL);
- devfreq->last_stat_updated = jiffies;
-
dev_set_name(&devfreq->dev, "%s", dev_name(dev));
err = device_register(&devfreq->dev);
if (err) {
- put_device(&devfreq->dev);
mutex_unlock(&devfreq->lock);
goto err_out;
}
+ devfreq->trans_table = devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
+ devfreq->profile->max_state *
+ devfreq->profile->max_state,
+ GFP_KERNEL);
+ devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) *
+ devfreq->profile->max_state,
+ GFP_KERNEL);
+ devfreq->last_stat_updated = jiffies;
+
srcu_init_notifier_head(&devfreq->transition_notifier_list);
mutex_unlock(&devfreq->lock);
@@ -603,7 +606,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
err_init:
list_del(&devfreq->node);
device_unregister(&devfreq->dev);
- kfree(devfreq);
err_out:
return ERR_PTR(err);
}
@@ -621,7 +623,6 @@ int devfreq_remove_device(struct devfreq *devfreq)
return -EINVAL;
device_unregister(&devfreq->dev);
- put_device(&devfreq->dev);
return 0;
}
diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c
index 6b6a5f310486..a5841403bde8 100644
--- a/drivers/devfreq/event/exynos-nocp.c
+++ b/drivers/devfreq/event/exynos-nocp.c
@@ -220,9 +220,6 @@ static int exynos_nocp_parse_dt(struct platform_device *pdev,
/* Maps the memory mapped IO to control nocp register */
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (IS_ERR(res))
- return PTR_ERR(res);
-
base = devm_ioremap_resource(dev, res);
if (IS_ERR(base))
return PTR_ERR(base);
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 4a2c07ee6677..6355ab38d630 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -33,6 +33,7 @@
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/reservation.h>
+#include <linux/mm.h>
#include <uapi/linux/dma-buf.h>
@@ -90,7 +91,7 @@ static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma)
dmabuf = file->private_data;
/* check for overflowing the buffer's size */
- if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+ if (vma->vm_pgoff + vma_pages(vma) >
dmabuf->size >> PAGE_SHIFT)
return -EINVAL;
@@ -723,11 +724,11 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
return -EINVAL;
/* check for offset overflow */
- if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff)
+ if (pgoff + vma_pages(vma) < pgoff)
return -EOVERFLOW;
/* check for overflowing the buffer's size */
- if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+ if (pgoff + vma_pages(vma) >
dmabuf->size >> PAGE_SHIFT)
return -EINVAL;
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index c0bd5722c997..9566a62ad8e3 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -35,6 +35,17 @@
#include <linux/reservation.h>
#include <linux/export.h>
+/**
+ * DOC: Reservation Object Overview
+ *
+ * The reservation object provides a mechanism to manage shared and
+ * exclusive fences associated with a buffer. A reservation object
+ * can have attached one exclusive fence (normally associated with
+ * write operations) or N shared fences (read operations). The RCU
+ * mechanism is used to protect read access to fences from locked
+ * write-side updates.
+ */
+
DEFINE_WW_CLASS(reservation_ww_class);
EXPORT_SYMBOL(reservation_ww_class);
@@ -43,9 +54,17 @@ EXPORT_SYMBOL(reservation_seqcount_class);
const char reservation_seqcount_string[] = "reservation_seqcount";
EXPORT_SYMBOL(reservation_seqcount_string);
-/*
- * Reserve space to add a shared fence to a reservation_object,
- * must be called with obj->lock held.
+
+/**
+ * reservation_object_reserve_shared - Reserve space to add a shared
+ * fence to a reservation_object.
+ * @obj: reservation object
+ *
+ * Should be called before reservation_object_add_shared_fence(). Must
+ * be called with obj->lock held.
+ *
+ * RETURNS
+ * Zero for success, or -errno
*/
int reservation_object_reserve_shared(struct reservation_object *obj)
{
@@ -180,7 +199,11 @@ done:
fence_put(old_fence);
}
-/*
+/**
+ * reservation_object_add_shared_fence - Add a fence to a shared slot
+ * @obj: the reservation object
+ * @fence: the shared fence to add
+ *
* Add a fence to a shared slot, obj->lock must be held, and
* reservation_object_reserve_shared_fence has been called.
*/
@@ -200,6 +223,13 @@ void reservation_object_add_shared_fence(struct reservation_object *obj,
}
EXPORT_SYMBOL(reservation_object_add_shared_fence);
+/**
+ * reservation_object_add_excl_fence - Add an exclusive fence.
+ * @obj: the reservation object
+ * @fence: the shared fence to add
+ *
+ * Add a fence to the exclusive slot. The obj->lock must be held.
+ */
void reservation_object_add_excl_fence(struct reservation_object *obj,
struct fence *fence)
{
@@ -233,6 +263,18 @@ void reservation_object_add_excl_fence(struct reservation_object *obj,
}
EXPORT_SYMBOL(reservation_object_add_excl_fence);
+/**
+ * reservation_object_get_fences_rcu - Get an object's shared and exclusive
+ * fences without update side lock held
+ * @obj: the reservation object
+ * @pfence_excl: the returned exclusive fence (or NULL)
+ * @pshared_count: the number of shared fences returned
+ * @pshared: the array of shared fence ptrs returned (array is krealloc'd to
+ * the required size, and must be freed by caller)
+ *
+ * RETURNS
+ * Zero or -errno
+ */
int reservation_object_get_fences_rcu(struct reservation_object *obj,
struct fence **pfence_excl,
unsigned *pshared_count,
@@ -319,6 +361,18 @@ unlock:
}
EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu);
+/**
+ * reservation_object_wait_timeout_rcu - Wait on reservation's objects
+ * shared and/or exclusive fences.
+ * @obj: the reservation object
+ * @wait_all: if true, wait on all fences, else wait on just exclusive fence
+ * @intr: if true, do interruptible wait
+ * @timeout: timeout value in jiffies or zero to return immediately
+ *
+ * RETURNS
+ * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or
+ * greater than zer on success.
+ */
long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
bool wait_all, bool intr,
unsigned long timeout)
@@ -416,6 +470,16 @@ reservation_object_test_signaled_single(struct fence *passed_fence)
return ret;
}
+/**
+ * reservation_object_test_signaled_rcu - Test if a reservation object's
+ * fences have been signaled.
+ * @obj: the reservation object
+ * @test_all: if true, test all fences, otherwise only test the exclusive
+ * fence
+ *
+ * RETURNS
+ * true if all fences signaled, else false
+ */
bool reservation_object_test_signaled_rcu(struct reservation_object *obj,
bool test_all)
{
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 8e304b1befc5..75bd6621dc5d 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -242,7 +242,7 @@ struct at_xdmac_lld {
u32 mbr_dus; /* Destination Microblock Stride Register */
};
-
+/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */
struct at_xdmac_desc {
struct at_xdmac_lld lld;
enum dma_transfer_direction direction;
@@ -253,7 +253,7 @@ struct at_xdmac_desc {
unsigned int xfer_size;
struct list_head descs_list;
struct list_head xfer_node;
-};
+} __aligned(sizeof(u64));
static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
{
@@ -1400,6 +1400,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
u32 cur_nda, check_nda, cur_ubc, mask, value;
u8 dwidth = 0;
unsigned long flags;
+ bool initd;
ret = dma_cookie_status(chan, cookie, txstate);
if (ret == DMA_COMPLETE)
@@ -1424,7 +1425,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
residue = desc->xfer_size;
/*
* Flush FIFO: only relevant when the transfer is source peripheral
- * synchronized.
+ * synchronized. Flush is needed before reading CUBC because data in
+ * the FIFO are not reported by CUBC. Reporting a residue of the
+ * transfer length while we have data in FIFO can cause issue.
+ * Usecase: atmel USART has a timeout which means I have received
+ * characters but there is no more character received for a while. On
+ * timeout, it requests the residue. If the data are in the DMA FIFO,
+ * we will return a residue of the transfer length. It means no data
+ * received. If an application is waiting for these data, it will hang
+ * since we won't have another USART timeout without receiving new
+ * data.
*/
mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
@@ -1435,34 +1445,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
}
/*
- * When processing the residue, we need to read two registers but we
- * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
- * we stand in the descriptor list and AT_XDMAC_CUBC is used
- * to know how many data are remaining for the current descriptor.
- * Since the dma channel is not paused to not loose data, between the
- * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
- * descriptor.
- * For that reason, after reading AT_XDMAC_CUBC, we check if we are
- * still using the same descriptor by reading a second time
- * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
- * read again AT_XDMAC_CUBC.
+ * The easiest way to compute the residue should be to pause the DMA
+ * but doing this can lead to miss some data as some devices don't
+ * have FIFO.
+ * We need to read several registers because:
+ * - DMA is running therefore a descriptor change is possible while
+ * reading these registers
+ * - When the block transfer is done, the value of the CUBC register
+ * is set to its initial value until the fetch of the next descriptor.
+ * This value will corrupt the residue calculation so we have to skip
+ * it.
+ *
+ * INITD -------- ------------
+ * |____________________|
+ * _______________________ _______________
+ * NDA @desc2 \/ @desc3
+ * _______________________/\_______________
+ * __________ ___________ _______________
+ * CUBC 0 \/ MAX desc1 \/ MAX desc2
+ * __________/\___________/\_______________
+ *
+ * Since descriptors are aligned on 64 bits, we can assume that
+ * the update of NDA and CUBC is atomic.
* Memory barriers are used to ensure the read order of the registers.
- * A max number of retries is set because unlikely it can never ends if
- * we are transferring a lot of data with small buffers.
+ * A max number of retries is set because unlikely it could never ends.
*/
- cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
- rmb();
- cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
- rmb();
check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-
- if (likely(cur_nda == check_nda))
- break;
-
- cur_nda = check_nda;
+ rmb();
+ initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
rmb();
cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+ rmb();
+ cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+ rmb();
+
+ if ((check_nda == cur_nda) && initd)
+ break;
}
if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
@@ -1471,6 +1490,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
}
/*
+ * Flush FIFO: only relevant when the transfer is source peripheral
+ * synchronized. Another flush is needed here because CUBC is updated
+ * when the controller sends the data write command. It can lead to
+ * report data that are not written in the memory or the device. The
+ * FIFO flush ensures that data are really written.
+ */
+ if ((desc->lld.mbr_cfg & mask) == value) {
+ at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+ while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
+ cpu_relax();
+ }
+
+ /*
* Remove size of all microblocks already transferred and the current
* one. Then add the remaining size to transfer of the current
* microblock.
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 25d1dadcddd1..d0446a75990a 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -703,8 +703,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
goto free_resources;
}
- src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0,
- PAGE_SIZE, DMA_TO_DEVICE);
+ src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src),
+ (size_t)src & ~PAGE_MASK, PAGE_SIZE,
+ DMA_TO_DEVICE);
unmap->addr[0] = src_dma;
ret = dma_mapping_error(dma_chan->device->dev, src_dma);
@@ -714,8 +715,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
}
unmap->to_cnt = 1;
- dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0,
- PAGE_SIZE, DMA_FROM_DEVICE);
+ dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest),
+ (size_t)dest & ~PAGE_MASK, PAGE_SIZE,
+ DMA_FROM_DEVICE);
unmap->addr[1] = dest_dma;
ret = dma_mapping_error(dma_chan->device->dev, dest_dma);
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index e0df233dde92..57aa227bfadb 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -461,25 +461,25 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
/* Source burst */
ret = convert_burst(sconfig->src_maxburst);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret);
/* Destination burst */
ret = convert_burst(sconfig->dst_maxburst);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret);
/* Source bus width */
ret = convert_buswidth(sconfig->src_addr_width);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret);
/* Destination bus width */
ret = convert_buswidth(sconfig->dst_addr_width);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret);
@@ -518,25 +518,25 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
/* Source burst */
ret = convert_burst(sconfig->src_maxburst);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret);
/* Destination burst */
ret = convert_burst(sconfig->dst_maxburst);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret);
/* Source bus width */
ret = convert_buswidth(sconfig->src_addr_width);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret);
/* Destination bus width */
ret = convert_buswidth(sconfig->dst_addr_width);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto fail;
promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret);
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 6aa256b0a1ed..c3ee3ad98a63 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -565,7 +565,8 @@ void edac_mc_reset_delay_period(unsigned long value)
list_for_each(item, &mc_devices) {
mci = list_entry(item, struct mem_ctl_info, link);
- edac_mod_work(&mci->work, value);
+ if (mci->op_state == OP_RUNNING_POLL)
+ edac_mod_work(&mci->work, value);
}
mutex_unlock(&mem_ctls_mutex);
}
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index b4d0bf6534cf..6744d88bdea8 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -239,8 +239,11 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = {
{ 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc },
};
-#define RIR_RNK_TGT(reg) GET_BITFIELD(reg, 16, 19)
-#define RIR_OFFSET(reg) GET_BITFIELD(reg, 2, 14)
+#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \
+ GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19))
+
+#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \
+ GET_BITFIELD(reg, 2, 15) : GET_BITFIELD(reg, 2, 14))
/* Device 16, functions 2-7 */
@@ -326,6 +329,7 @@ struct pci_id_descr {
struct pci_id_table {
const struct pci_id_descr *descr;
int n_devs;
+ enum type type;
};
struct sbridge_dev {
@@ -394,9 +398,14 @@ static const struct pci_id_descr pci_dev_descr_sbridge[] = {
{ PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0) },
};
-#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) }
+#define PCI_ID_TABLE_ENTRY(A, T) { \
+ .descr = A, \
+ .n_devs = ARRAY_SIZE(A), \
+ .type = T \
+}
+
static const struct pci_id_table pci_dev_descr_sbridge_table[] = {
- PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge),
+ PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE),
{0,} /* 0 terminated list. */
};
@@ -463,7 +472,7 @@ static const struct pci_id_descr pci_dev_descr_ibridge[] = {
};
static const struct pci_id_table pci_dev_descr_ibridge_table[] = {
- PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge),
+ PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE),
{0,} /* 0 terminated list. */
};
@@ -536,7 +545,7 @@ static const struct pci_id_descr pci_dev_descr_haswell[] = {
};
static const struct pci_id_table pci_dev_descr_haswell_table[] = {
- PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell),
+ PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL),
{0,} /* 0 terminated list. */
};
@@ -580,7 +589,7 @@ static const struct pci_id_descr pci_dev_descr_knl[] = {
};
static const struct pci_id_table pci_dev_descr_knl_table[] = {
- PCI_ID_TABLE_ENTRY(pci_dev_descr_knl),
+ PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING),
{0,}
};
@@ -648,7 +657,7 @@ static const struct pci_id_descr pci_dev_descr_broadwell[] = {
};
static const struct pci_id_table pci_dev_descr_broadwell_table[] = {
- PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell),
+ PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL),
{0,} /* 0 terminated list. */
};
@@ -1894,14 +1903,14 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
pci_read_config_dword(pvt->pci_tad[i],
rir_offset[j][k],
&reg);
- tmp_mb = RIR_OFFSET(reg) << 6;
+ tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6;
gb = div_u64_rem(tmp_mb, 1024, &mb);
edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
i, j, k,
gb, (mb*1000)/1024,
((u64)tmp_mb) << 20L,
- (u32)RIR_RNK_TGT(reg),
+ (u32)RIR_RNK_TGT(pvt->info.type, reg),
reg);
}
}
@@ -2234,7 +2243,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
pci_read_config_dword(pvt->pci_tad[ch_add + base_ch],
rir_offset[n_rir][idx],
&reg);
- *rank = RIR_RNK_TGT(reg);
+ *rank = RIR_RNK_TGT(pvt->info.type, reg);
edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n",
n_rir,
@@ -3357,12 +3366,12 @@ fail0:
#define ICPU(model, table) \
{ X86_VENDOR_INTEL, 6, model, 0, (unsigned long)&table }
-/* Order here must match "enum type" */
static const struct x86_cpu_id sbridge_cpuids[] = {
ICPU(0x2d, pci_dev_descr_sbridge_table), /* SANDY_BRIDGE */
ICPU(0x3e, pci_dev_descr_ibridge_table), /* IVY_BRIDGE */
ICPU(0x3f, pci_dev_descr_haswell_table), /* HASWELL */
ICPU(0x4f, pci_dev_descr_broadwell_table), /* BROADWELL */
+ ICPU(0x56, pci_dev_descr_broadwell_table), /* BROADWELL-DE */
ICPU(0x57, pci_dev_descr_knl_table), /* KNIGHTS_LANDING */
{ }
};
@@ -3398,7 +3407,7 @@ static int sbridge_probe(const struct x86_cpu_id *id)
mc, mc + 1, num_mc);
sbridge_dev->mc = mc++;
- rc = sbridge_register_mci(sbridge_dev, id - sbridge_cpuids);
+ rc = sbridge_register_mci(sbridge_dev, ptable->type);
if (unlikely(rc < 0))
goto fail1;
}
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index 8b3226dca1d9..caff46c0e214 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -360,6 +360,8 @@ static int palmas_usb_probe(struct platform_device *pdev)
palmas_enable_irq(palmas_usb);
/* perform initial detection */
+ if (palmas_usb->enable_gpio_vbus_detection)
+ palmas_vbus_irq_handler(palmas_usb->gpio_vbus_irq, palmas_usb);
palmas_gpio_id_detect(&palmas_usb->wq_detectid.work);
device_set_wakeup_capable(&pdev->dev, true);
return 0;
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index a850cbc48d8d..c49d50e68aee 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -174,6 +174,7 @@ static __init void reserve_regions(void)
{
efi_memory_desc_t *md;
u64 paddr, npages, size;
+ int resv;
if (efi_enabled(EFI_DBG))
pr_info("Processing EFI memory map:\n");
@@ -190,12 +191,14 @@ static __init void reserve_regions(void)
paddr = md->phys_addr;
npages = md->num_pages;
+ resv = is_reserve_region(md);
if (efi_enabled(EFI_DBG)) {
char buf[64];
- pr_info(" 0x%012llx-0x%012llx %s",
+ pr_info(" 0x%012llx-0x%012llx %s%s\n",
paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
- efi_md_typeattr_format(buf, sizeof(buf), md));
+ efi_md_typeattr_format(buf, sizeof(buf), md),
+ resv ? "*" : "");
}
memrange_efi_to_native(&paddr, &npages);
@@ -204,14 +207,9 @@ static __init void reserve_regions(void)
if (is_normal_ram(md))
early_init_dt_add_memory_arch(paddr, size);
- if (is_reserve_region(md)) {
+ if (resv)
memblock_mark_nomap(paddr, size);
- if (efi_enabled(EFI_DBG))
- pr_cont("*");
- }
- if (efi_enabled(EFI_DBG))
- pr_cont("\n");
}
set_bit(EFI_MEMMAP, &efi.flags);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 48da857f4774..cebcb405812e 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -33,6 +33,7 @@ config ARCH_REQUIRE_GPIOLIB
menuconfig GPIOLIB
bool "GPIO Support"
+ select ANON_INODES
help
This enables GPIO support through the generic GPIO library.
You only need to enable this, if you also want to enable
@@ -530,7 +531,7 @@ menu "Port-mapped I/O GPIO drivers"
config GPIO_104_DIO_48E
tristate "ACCES 104-DIO-48E GPIO support"
- depends on ISA
+ depends on ISA_BUS_API
select GPIOLIB_IRQCHIP
help
Enables GPIO support for the ACCES 104-DIO-48E series (104-DIO-48E,
@@ -540,7 +541,7 @@ config GPIO_104_DIO_48E
config GPIO_104_IDIO_16
tristate "ACCES 104-IDIO-16 GPIO support"
- depends on ISA
+ depends on ISA_BUS_API
select GPIOLIB_IRQCHIP
help
Enables GPIO support for the ACCES 104-IDIO-16 family (104-IDIO-16,
@@ -551,7 +552,7 @@ config GPIO_104_IDIO_16
config GPIO_104_IDI_48
tristate "ACCES 104-IDI-48 GPIO support"
- depends on ISA
+ depends on ISA_BUS_API
select GPIOLIB_IRQCHIP
help
Enables GPIO support for the ACCES 104-IDI-48 family (104-IDI-48A,
@@ -627,7 +628,7 @@ config GPIO_TS5500
config GPIO_WS16C48
tristate "WinSystems WS16C48 GPIO support"
- depends on ISA
+ depends on ISA_BUS_API
select GPIOLIB_IRQCHIP
help
Enables GPIO support for the WinSystems WS16C48. The base port
diff --git a/drivers/gpio/gpio-104-dio-48e.c b/drivers/gpio/gpio-104-dio-48e.c
index 1a647c07be67..fcf776971ca9 100644
--- a/drivers/gpio/gpio-104-dio-48e.c
+++ b/drivers/gpio/gpio-104-dio-48e.c
@@ -75,7 +75,7 @@ static int dio48e_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
{
struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
const unsigned io_port = offset / 8;
- const unsigned control_port = io_port / 2;
+ const unsigned int control_port = io_port / 3;
const unsigned control_addr = dio48egpio->base + 3 + control_port*4;
unsigned long flags;
unsigned control;
@@ -115,7 +115,7 @@ static int dio48e_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
{
struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
const unsigned io_port = offset / 8;
- const unsigned control_port = io_port / 2;
+ const unsigned int control_port = io_port / 3;
const unsigned mask = BIT(offset % 8);
const unsigned control_addr = dio48egpio->base + 3 + control_port*4;
const unsigned out_port = (io_port > 2) ? io_port + 1 : io_port;
diff --git a/drivers/gpio/gpio-104-idi-48.c b/drivers/gpio/gpio-104-idi-48.c
index 6c75c83baf5a..2d2763ea1a68 100644
--- a/drivers/gpio/gpio-104-idi-48.c
+++ b/drivers/gpio/gpio-104-idi-48.c
@@ -247,6 +247,7 @@ static int idi_48_probe(struct device *dev, unsigned int id)
idi48gpio->irq = irq[id];
spin_lock_init(&idi48gpio->lock);
+ spin_lock_init(&idi48gpio->ack_lock);
dev_set_drvdata(dev, idi48gpio);
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 9aabc48ff5de..953e4b829e32 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -547,11 +547,11 @@ static void bcm_kona_gpio_reset(struct bcm_kona_gpio *kona_gpio)
/* disable interrupts and clear status */
for (i = 0; i < kona_gpio->num_bank; i++) {
/* Unlock the entire bank first */
- bcm_kona_gpio_write_lock_regs(kona_gpio, i, UNLOCK_CODE);
+ bcm_kona_gpio_write_lock_regs(reg_base, i, UNLOCK_CODE);
writel(0xffffffff, reg_base + GPIO_INT_MASK(i));
writel(0xffffffff, reg_base + GPIO_INT_STATUS(i));
/* Now re-lock the bank */
- bcm_kona_gpio_write_lock_regs(kona_gpio, i, LOCK_CODE);
+ bcm_kona_gpio_write_lock_regs(reg_base, i, LOCK_CODE);
}
}
diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c
index d39014daeef9..fc5f197906ac 100644
--- a/drivers/gpio/gpio-lpc32xx.c
+++ b/drivers/gpio/gpio-lpc32xx.c
@@ -29,7 +29,6 @@
#include <mach/hardware.h>
#include <mach/platform.h>
-#include <mach/irqs.h>
#define LPC32XX_GPIO_P3_INP_STATE _GPREG(0x000)
#define LPC32XX_GPIO_P3_OUTP_SET _GPREG(0x004)
@@ -371,61 +370,16 @@ static int lpc32xx_gpio_request(struct gpio_chip *chip, unsigned pin)
static int lpc32xx_gpio_to_irq_p01(struct gpio_chip *chip, unsigned offset)
{
- return IRQ_LPC32XX_P0_P1_IRQ;
+ return -ENXIO;
}
-static const char lpc32xx_gpio_to_irq_gpio_p3_table[] = {
- IRQ_LPC32XX_GPIO_00,
- IRQ_LPC32XX_GPIO_01,
- IRQ_LPC32XX_GPIO_02,
- IRQ_LPC32XX_GPIO_03,
- IRQ_LPC32XX_GPIO_04,
- IRQ_LPC32XX_GPIO_05,
-};
-
static int lpc32xx_gpio_to_irq_gpio_p3(struct gpio_chip *chip, unsigned offset)
{
- if (offset < ARRAY_SIZE(lpc32xx_gpio_to_irq_gpio_p3_table))
- return lpc32xx_gpio_to_irq_gpio_p3_table[offset];
return -ENXIO;
}
-static const char lpc32xx_gpio_to_irq_gpi_p3_table[] = {
- IRQ_LPC32XX_GPI_00,
- IRQ_LPC32XX_GPI_01,
- IRQ_LPC32XX_GPI_02,
- IRQ_LPC32XX_GPI_03,
- IRQ_LPC32XX_GPI_04,
- IRQ_LPC32XX_GPI_05,
- IRQ_LPC32XX_GPI_06,
- IRQ_LPC32XX_GPI_07,
- IRQ_LPC32XX_GPI_08,
- IRQ_LPC32XX_GPI_09,
- -ENXIO, /* 10 */
- -ENXIO, /* 11 */
- -ENXIO, /* 12 */
- -ENXIO, /* 13 */
- -ENXIO, /* 14 */
- -ENXIO, /* 15 */
- -ENXIO, /* 16 */
- -ENXIO, /* 17 */
- -ENXIO, /* 18 */
- IRQ_LPC32XX_GPI_19,
- -ENXIO, /* 20 */
- -ENXIO, /* 21 */
- -ENXIO, /* 22 */
- -ENXIO, /* 23 */
- -ENXIO, /* 24 */
- -ENXIO, /* 25 */
- -ENXIO, /* 26 */
- -ENXIO, /* 27 */
- IRQ_LPC32XX_GPI_28,
-};
-
static int lpc32xx_gpio_to_irq_gpi_p3(struct gpio_chip *chip, unsigned offset)
{
- if (offset < ARRAY_SIZE(lpc32xx_gpio_to_irq_gpi_p3_table))
- return lpc32xx_gpio_to_irq_gpi_p3_table[offset];
return -ENXIO;
}
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index ec891a27952f..661b0e34e067 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -98,7 +98,6 @@ struct tegra_gpio_info {
const struct tegra_gpio_soc_config *soc;
struct gpio_chip gc;
struct irq_chip ic;
- struct lock_class_key lock_class;
u32 bank_count;
};
@@ -547,6 +546,12 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume)
};
+/*
+ * This lock class tells lockdep that GPIO irqs are in a different category
+ * than their parents, so it won't report false recursion.
+ */
+static struct lock_class_key gpio_lock_class;
+
static int tegra_gpio_probe(struct platform_device *pdev)
{
const struct tegra_gpio_soc_config *config;
@@ -660,7 +665,7 @@ static int tegra_gpio_probe(struct platform_device *pdev)
bank = &tgi->bank_info[GPIO_BANK(gpio)];
- irq_set_lockdep_class(irq, &tgi->lock_class);
+ irq_set_lockdep_class(irq, &gpio_lock_class);
irq_set_chip_data(irq, bank);
irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq);
}
diff --git a/drivers/gpio/gpio-xlp.c b/drivers/gpio/gpio-xlp.c
index 08897dc11915..1a33a19d95b9 100644
--- a/drivers/gpio/gpio-xlp.c
+++ b/drivers/gpio/gpio-xlp.c
@@ -393,7 +393,7 @@ static int xlp_gpio_probe(struct platform_device *pdev)
irq_base = irq_alloc_descs(-1, 0, gc->ngpio, 0);
else
irq_base = irq_alloc_descs(-1, XLP_GPIO_IRQ_BASE, gc->ngpio, 0);
- if (IS_ERR_VALUE(irq_base)) {
+ if (irq_base < 0) {
dev_err(&pdev->dev, "Failed to allocate IRQ numbers\n");
return irq_base;
}
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 75c6355b018d..e72794e463aa 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -709,7 +709,13 @@ static int zynq_gpio_probe(struct platform_device *pdev)
dev_err(&pdev->dev, "input clock not found.\n");
return PTR_ERR(gpio->clk);
}
+ ret = clk_prepare_enable(gpio->clk);
+ if (ret) {
+ dev_err(&pdev->dev, "Unable to enable clock.\n");
+ return ret;
+ }
+ pm_runtime_set_active(&pdev->dev);
pm_runtime_enable(&pdev->dev);
ret = pm_runtime_get_sync(&pdev->dev);
if (ret < 0)
@@ -747,6 +753,7 @@ err_pm_put:
pm_runtime_put(&pdev->dev);
err_pm_dis:
pm_runtime_disable(&pdev->dev);
+ clk_disable_unprepare(gpio->clk);
return ret;
}
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index d22dcc38179d..4aabddb38b59 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -16,6 +16,7 @@
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/io.h>
+#include <linux/io-mapping.h>
#include <linux/gpio/consumer.h>
#include <linux/of.h>
#include <linux/of_address.h>
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d407f904a31c..570771ed19e6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -20,6 +20,7 @@
#include <linux/cdev.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
+#include <linux/compat.h>
#include <uapi/linux/gpio.h>
#include "gpiolib.h"
@@ -316,7 +317,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct gpio_device *gdev = filp->private_data;
struct gpio_chip *chip = gdev->chip;
- int __user *ip = (int __user *)arg;
+ void __user *ip = (void __user *)arg;
/* We fail any subsequent ioctl():s when the chip is gone */
if (!chip)
@@ -388,6 +389,14 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return -EINVAL;
}
+#ifdef CONFIG_COMPAT
+static long gpio_ioctl_compat(struct file *filp, unsigned int cmd,
+ unsigned long arg)
+{
+ return gpio_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
/**
* gpio_chrdev_open() - open the chardev for ioctl operations
* @inode: inode for this chardev
@@ -431,14 +440,15 @@ static const struct file_operations gpio_fileops = {
.owner = THIS_MODULE,
.llseek = noop_llseek,
.unlocked_ioctl = gpio_ioctl,
- .compat_ioctl = gpio_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = gpio_ioctl_compat,
+#endif
};
static void gpiodevice_release(struct device *dev)
{
struct gpio_device *gdev = dev_get_drvdata(dev);
- cdev_del(&gdev->chrdev);
list_del(&gdev->list);
ida_simple_remove(&gpio_ida, gdev->id);
kfree(gdev->label);
@@ -471,7 +481,6 @@ static int gpiochip_setup_dev(struct gpio_device *gdev)
/* From this point, the .release() function cleans up gpio_device */
gdev->dev.release = gpiodevice_release;
- get_device(&gdev->dev);
pr_debug("%s: registered GPIOs %d to %d on device: %s (%s)\n",
__func__, gdev->base, gdev->base + gdev->ngpio - 1,
dev_name(&gdev->dev), gdev->chip->label ? : "generic");
@@ -618,6 +627,8 @@ int gpiochip_add_data(struct gpio_chip *chip, void *data)
goto err_free_label;
}
+ spin_unlock_irqrestore(&gpio_lock, flags);
+
for (i = 0; i < chip->ngpio; i++) {
struct gpio_desc *desc = &gdev->descs[i];
@@ -649,8 +660,6 @@ int gpiochip_add_data(struct gpio_chip *chip, void *data)
}
}
- spin_unlock_irqrestore(&gpio_lock, flags);
-
#ifdef CONFIG_PINCTRL
INIT_LIST_HEAD(&gdev->pin_ranges);
#endif
@@ -759,6 +768,8 @@ void gpiochip_remove(struct gpio_chip *chip)
* be removed, else it will be dangling until the last user is
* gone.
*/
+ cdev_del(&gdev->chrdev);
+ device_del(&gdev->dev);
put_device(&gdev->dev);
}
EXPORT_SYMBOL_GPL(gpiochip_remove);
@@ -858,7 +869,7 @@ struct gpio_chip *gpiochip_find(void *data,
spin_lock_irqsave(&gpio_lock, flags);
list_for_each_entry(gdev, &gpio_devices, list)
- if (match(gdev->chip, data))
+ if (gdev->chip && match(gdev->chip, data))
break;
/* No match? */
@@ -1356,11 +1367,18 @@ done:
/*
* This descriptor validation needs to be inserted verbatim into each
* function taking a descriptor, so we need to use a preprocessor
- * macro to avoid endless duplication.
+ * macro to avoid endless duplication. If the desc is NULL it is an
+ * optional GPIO and calls should just bail out.
*/
#define VALIDATE_DESC(desc) do { \
- if (!desc || !desc->gdev) { \
- pr_warn("%s: invalid GPIO\n", __func__); \
+ if (!desc) \
+ return 0; \
+ if (IS_ERR(desc)) { \
+ pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
+ return PTR_ERR(desc); \
+ } \
+ if (!desc->gdev) { \
+ pr_warn("%s: invalid GPIO (no device)\n", __func__); \
return -EINVAL; \
} \
if ( !desc->gdev->chip ) { \
@@ -1370,8 +1388,14 @@ done:
} } while (0)
#define VALIDATE_DESC_VOID(desc) do { \
- if (!desc || !desc->gdev) { \
- pr_warn("%s: invalid GPIO\n", __func__); \
+ if (!desc) \
+ return; \
+ if (IS_ERR(desc)) { \
+ pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
+ return; \
+ } \
+ if (!desc->gdev) { \
+ pr_warn("%s: invalid GPIO (no device)\n", __func__); \
return; \
} \
if (!desc->gdev->chip) { \
@@ -2040,7 +2064,14 @@ int gpiod_to_irq(const struct gpio_desc *desc)
struct gpio_chip *chip;
int offset;
- VALIDATE_DESC(desc);
+ /*
+ * Cannot VALIDATE_DESC() here as gpiod_to_irq() consumer semantics
+ * requires this function to not return zero on an invalid descriptor
+ * but rather a negative error number.
+ */
+ if (!desc || IS_ERR(desc) || !desc->gdev || !desc->gdev->chip)
+ return -EINVAL;
+
chip = desc->gdev->chip;
offset = gpio_chip_hwgpio(desc);
if (chip->to_irq) {
@@ -2066,17 +2097,30 @@ EXPORT_SYMBOL_GPL(gpiod_to_irq);
*/
int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
{
- if (offset >= chip->ngpio)
- return -EINVAL;
+ struct gpio_desc *desc;
+
+ desc = gpiochip_get_desc(chip, offset);
+ if (IS_ERR(desc))
+ return PTR_ERR(desc);
+
+ /* Flush direction if something changed behind our back */
+ if (chip->get_direction) {
+ int dir = chip->get_direction(chip, offset);
+
+ if (dir)
+ clear_bit(FLAG_IS_OUT, &desc->flags);
+ else
+ set_bit(FLAG_IS_OUT, &desc->flags);
+ }
- if (test_bit(FLAG_IS_OUT, &chip->gpiodev->descs[offset].flags)) {
+ if (test_bit(FLAG_IS_OUT, &desc->flags)) {
chip_err(chip,
"%s: tried to flag a GPIO set as output for IRQ\n",
__func__);
return -EIO;
}
- set_bit(FLAG_USED_AS_IRQ, &chip->gpiodev->descs[offset].flags);
+ set_bit(FLAG_USED_AS_IRQ, &desc->flags);
return 0;
}
EXPORT_SYMBOL_GPL(gpiochip_lock_as_irq);
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 2bd3e5aa43c6..be43afb08c69 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -23,7 +23,7 @@ drm-$(CONFIG_AGP) += drm_agpsupport.o
drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \
drm_plane_helper.o drm_dp_mst_topology.o drm_atomic_helper.o \
- drm_kms_helper_common.o
+ drm_kms_helper_common.o drm_dp_dual_mode_helper.o
drm_kms_helper-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o
diff --git a/drivers/gpu/drm/amd/acp/Kconfig b/drivers/gpu/drm/amd/acp/Kconfig
index ca77ec10147c..e503e3d6d920 100644
--- a/drivers/gpu/drm/amd/acp/Kconfig
+++ b/drivers/gpu/drm/amd/acp/Kconfig
@@ -2,6 +2,7 @@ menu "ACP (Audio CoProcessor) Configuration"
config DRM_AMD_ACP
bool "Enable AMD Audio CoProcessor IP support"
+ depends on DRM_AMDGPU
select MFD_CORE
select PM_GENERIC_DOMAINS if PM
help
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 2a009c398dcb..e055d5be1c3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -602,6 +602,8 @@ int amdgpu_sync_wait(struct amdgpu_sync *sync);
void amdgpu_sync_free(struct amdgpu_sync *sync);
int amdgpu_sync_init(void);
void amdgpu_sync_fini(void);
+int amdgpu_fence_slab_init(void);
+void amdgpu_fence_slab_fini(void);
/*
* GART structures, functions & helpers
@@ -1818,6 +1820,8 @@ struct amdgpu_asic_funcs {
/* MM block clocks */
int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
+ /* query virtual capabilities */
+ u32 (*get_virtual_caps)(struct amdgpu_device *adev);
};
/*
@@ -1912,8 +1916,12 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device);
/* GPU virtualization */
+#define AMDGPU_VIRT_CAPS_SRIOV_EN (1 << 0)
+#define AMDGPU_VIRT_CAPS_IS_VF (1 << 1)
struct amdgpu_virtualization {
bool supports_sr_iov;
+ bool is_virtual;
+ u32 caps;
};
/*
@@ -2202,6 +2210,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
#define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
#define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
#define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
+#define amdgpu_asic_get_virtual_caps(adev) ((adev)->asic_funcs->get_virtual_caps((adev)))
#define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev))
#define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
#define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 199f76baf22c..cf6f49fc1c75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -696,6 +696,17 @@ static uint32_t fw_type_convert(struct cgs_device *cgs_device, uint32_t fw_type)
return result;
}
+static int amdgpu_cgs_rel_firmware(struct cgs_device *cgs_device, enum cgs_ucode_id type)
+{
+ CGS_FUNC_ADEV;
+ if ((CGS_UCODE_ID_SMU == type) || (CGS_UCODE_ID_SMU_SK == type)) {
+ release_firmware(adev->pm.fw);
+ return 0;
+ }
+ /* cannot release other firmware because they are not created by cgs */
+ return -EINVAL;
+}
+
static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
enum cgs_ucode_id type,
struct cgs_firmware_info *info)
@@ -898,7 +909,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
struct cgs_acpi_method_argument *argument = NULL;
uint32_t i, count;
acpi_status status;
- int result;
+ int result = 0;
uint32_t func_no = 0xFFFFFFFF;
handle = ACPI_HANDLE(&adev->pdev->dev);
@@ -1125,6 +1136,7 @@ static const struct cgs_ops amdgpu_cgs_ops = {
amdgpu_cgs_pm_query_clock_limits,
amdgpu_cgs_set_camera_voltages,
amdgpu_cgs_get_firmware_info,
+ amdgpu_cgs_rel_firmware,
amdgpu_cgs_set_powergating_state,
amdgpu_cgs_set_clockgating_state,
amdgpu_cgs_get_active_displays_info,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 60a0c9ac11b2..cb07da41152b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -194,12 +194,12 @@ int amdgpu_connector_get_monitor_bpc(struct drm_connector *connector)
bpc = 8;
DRM_DEBUG("%s: HDMI deep color 10 bpc exceeds max tmds clock. Using %d bpc.\n",
connector->name, bpc);
- } else if (bpc > 8) {
- /* max_tmds_clock missing, but hdmi spec mandates it for deep color. */
- DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n",
- connector->name);
- bpc = 8;
}
+ } else if (bpc > 8) {
+ /* max_tmds_clock missing, but hdmi spec mandates it for deep color. */
+ DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n",
+ connector->name);
+ bpc = 8;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index bb8b149786d7..6e920086af46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -827,8 +827,10 @@ static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg)
*/
static void amdgpu_atombios_fini(struct amdgpu_device *adev)
{
- if (adev->mode_info.atom_context)
+ if (adev->mode_info.atom_context) {
kfree(adev->mode_info.atom_context->scratch);
+ kfree(adev->mode_info.atom_context->iio);
+ }
kfree(adev->mode_info.atom_context);
adev->mode_info.atom_context = NULL;
kfree(adev->mode_info.atom_card_info);
@@ -1325,6 +1327,11 @@ static int amdgpu_fini(struct amdgpu_device *adev)
adev->ip_block_status[i].valid = false;
}
+ for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
+ if (adev->ip_blocks[i].funcs->late_fini)
+ adev->ip_blocks[i].funcs->late_fini((void *)adev);
+ }
+
return 0;
}
@@ -1378,6 +1385,15 @@ static int amdgpu_resume(struct amdgpu_device *adev)
return 0;
}
+static bool amdgpu_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+ return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+ return false;
+#endif
+}
+
/**
* amdgpu_device_init - initialize the driver
*
@@ -1512,9 +1528,14 @@ int amdgpu_device_init(struct amdgpu_device *adev,
adev->virtualization.supports_sr_iov =
amdgpu_atombios_has_gpu_virtualization_table(adev);
+ /* Check if we are executing in a virtualized environment */
+ adev->virtualization.is_virtual = amdgpu_device_is_virtual();
+ adev->virtualization.caps = amdgpu_asic_get_virtual_caps(adev);
+
/* Post card if necessary */
if (!amdgpu_card_posted(adev) ||
- adev->virtualization.supports_sr_iov) {
+ (adev->virtualization.is_virtual &&
+ !(adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN))) {
if (!adev->bios) {
dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n");
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 1dab5f2b725b..f888c015f76c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -50,9 +50,11 @@
* KMS wrapper.
* - 3.0.0 - initial driver
* - 3.1.0 - allow reading more status registers (GRBM, SRBM, SDMA, CP)
+ * - 3.2.0 - GFX8: Uses EOP_TC_WB_ACTION_EN, so UMDs don't have to do the same
+ * at the end of IBs.
*/
#define KMS_DRIVER_MAJOR 3
-#define KMS_DRIVER_MINOR 1
+#define KMS_DRIVER_MINOR 2
#define KMS_DRIVER_PATCHLEVEL 0
int amdgpu_vram_limit = 0;
@@ -279,14 +281,26 @@ static const struct pci_device_id pciidlist[] = {
{0x1002, 0x98E4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_STONEY|AMD_IS_APU},
/* Polaris11 */
{0x1002, 0x67E0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
- {0x1002, 0x67E1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
+ {0x1002, 0x67E3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
{0x1002, 0x67E8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
- {0x1002, 0x67E9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
{0x1002, 0x67EB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
+ {0x1002, 0x67EF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
{0x1002, 0x67FF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
+ {0x1002, 0x67E1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
+ {0x1002, 0x67E7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
+ {0x1002, 0x67E9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS11},
/* Polaris10 */
{0x1002, 0x67C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67C2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67C4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67C7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
{0x1002, 0x67DF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67C8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67C9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67CC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+ {0x1002, 0x67CF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
{0, 0, 0}
};
@@ -563,9 +577,12 @@ static struct pci_driver amdgpu_kms_pci_driver = {
.driver.pm = &amdgpu_pm_ops,
};
+
+
static int __init amdgpu_init(void)
{
amdgpu_sync_init();
+ amdgpu_fence_slab_init();
if (vgacon_text_force()) {
DRM_ERROR("VGACON disables amdgpu kernel modesetting.\n");
return -EINVAL;
@@ -576,7 +593,6 @@ static int __init amdgpu_init(void)
driver->driver_features |= DRIVER_MODESET;
driver->num_ioctls = amdgpu_max_kms_ioctl;
amdgpu_register_atpx_handler();
-
/* let modprobe override vga console setting */
return drm_pci_init(driver, pdriver);
}
@@ -587,6 +603,7 @@ static void __exit amdgpu_exit(void)
drm_pci_exit(driver, pdriver);
amdgpu_unregister_atpx_handler();
amdgpu_sync_fini();
+ amdgpu_fence_slab_fini();
}
module_init(amdgpu_init);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index ba9c04283d01..d1558768cfb7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -55,8 +55,21 @@ struct amdgpu_fence {
};
static struct kmem_cache *amdgpu_fence_slab;
-static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0);
+int amdgpu_fence_slab_init(void)
+{
+ amdgpu_fence_slab = kmem_cache_create(
+ "amdgpu_fence", sizeof(struct amdgpu_fence), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!amdgpu_fence_slab)
+ return -ENOMEM;
+ return 0;
+}
+
+void amdgpu_fence_slab_fini(void)
+{
+ kmem_cache_destroy(amdgpu_fence_slab);
+}
/*
* Cast helper
*/
@@ -396,13 +409,6 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
*/
int amdgpu_fence_driver_init(struct amdgpu_device *adev)
{
- if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) {
- amdgpu_fence_slab = kmem_cache_create(
- "amdgpu_fence", sizeof(struct amdgpu_fence), 0,
- SLAB_HWCACHE_ALIGN, NULL);
- if (!amdgpu_fence_slab)
- return -ENOMEM;
- }
if (amdgpu_debugfs_fence_init(adev))
dev_err(adev->dev, "fence debugfs file creation failed\n");
@@ -437,13 +443,10 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
amd_sched_fini(&ring->sched);
del_timer_sync(&ring->fence_drv.fallback_timer);
for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
- fence_put(ring->fence_drv.fences[i]);
+ fence_put(ring->fence_drv.fences[j]);
kfree(ring->fence_drv.fences);
ring->fence_drv.initialized = false;
}
-
- if (atomic_dec_and_test(&amdgpu_fence_slab_ref))
- kmem_cache_destroy(amdgpu_fence_slab);
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 40a23704a981..d851ea15059f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -447,7 +447,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
dev_info.max_memory_clock = adev->pm.default_mclk * 10;
}
dev_info.enabled_rb_pipes_mask = adev->gfx.config.backend_enable_mask;
- dev_info.num_rb_pipes = adev->gfx.config.num_rbs;
+ dev_info.num_rb_pipes = adev->gfx.config.max_backends_per_se *
+ adev->gfx.config.max_shader_engines;
dev_info.num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts;
dev_info._pad = 0;
dev_info.ids_flags = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 589b36e8c5cf..0e13d80d2a95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -270,30 +270,28 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
struct drm_device *ddev = dev_get_drvdata(dev);
struct amdgpu_device *adev = ddev->dev_private;
enum amd_pm_state_type state = 0;
- long idx;
+ unsigned long idx;
int ret;
if (strlen(buf) == 1)
adev->pp_force_state_enabled = false;
- else {
- ret = kstrtol(buf, 0, &idx);
+ else if (adev->pp_enabled) {
+ struct pp_states_info data;
- if (ret) {
+ ret = kstrtoul(buf, 0, &idx);
+ if (ret || idx >= ARRAY_SIZE(data.states)) {
count = -EINVAL;
goto fail;
}
- if (adev->pp_enabled) {
- struct pp_states_info data;
- amdgpu_dpm_get_pp_num_states(adev, &data);
- state = data.states[idx];
- /* only set user selected power states */
- if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
- state != POWER_STATE_TYPE_DEFAULT) {
- amdgpu_dpm_dispatch_task(adev,
- AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL);
- adev->pp_force_state_enabled = true;
- }
+ amdgpu_dpm_get_pp_num_states(adev, &data);
+ state = data.states[idx];
+ /* only set user selected power states */
+ if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
+ state != POWER_STATE_TYPE_DEFAULT) {
+ amdgpu_dpm_dispatch_task(adev,
+ AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL);
+ adev->pp_force_state_enabled = true;
}
}
fail:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 6bd961fb43dc..82256558e0f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -183,13 +183,6 @@ static int amdgpu_pp_sw_fini(void *handle)
if (ret)
return ret;
-#ifdef CONFIG_DRM_AMD_POWERPLAY
- if (adev->pp_enabled) {
- amdgpu_pm_sysfs_fini(adev);
- amd_powerplay_fini(adev->powerplay.pp_handle);
- }
-#endif
-
return ret;
}
@@ -223,6 +216,22 @@ static int amdgpu_pp_hw_fini(void *handle)
return ret;
}
+static void amdgpu_pp_late_fini(void *handle)
+{
+#ifdef CONFIG_DRM_AMD_POWERPLAY
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+ if (adev->pp_enabled) {
+ amdgpu_pm_sysfs_fini(adev);
+ amd_powerplay_fini(adev->powerplay.pp_handle);
+ }
+
+ if (adev->powerplay.ip_funcs->late_fini)
+ adev->powerplay.ip_funcs->late_fini(
+ adev->powerplay.pp_handle);
+#endif
+}
+
static int amdgpu_pp_suspend(void *handle)
{
int ret = 0;
@@ -311,6 +320,7 @@ const struct amd_ip_funcs amdgpu_pp_ip_funcs = {
.sw_fini = amdgpu_pp_sw_fini,
.hw_init = amdgpu_pp_hw_init,
.hw_fini = amdgpu_pp_hw_fini,
+ .late_fini = amdgpu_pp_late_fini,
.suspend = amdgpu_pp_suspend,
.resume = amdgpu_pp_resume,
.is_idle = amdgpu_pp_is_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 3b02272db678..870f9494252c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -343,6 +343,7 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
ring->ring = NULL;
ring->ring_obj = NULL;
+ amdgpu_wb_free(ring->adev, ring->cond_exe_offs);
amdgpu_wb_free(ring->adev, ring->fence_offs);
amdgpu_wb_free(ring->adev, ring->rptr_offs);
amdgpu_wb_free(ring->adev, ring->wptr_offs);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 8bf84efafb04..48618ee324eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -115,6 +115,7 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev,
return r;
}
r = amdgpu_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
+ memset(sa_manager->cpu_ptr, 0, sa_manager->size);
amdgpu_bo_unreserve(sa_manager->bo);
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 01abfc21b4a2..d9c88d13f8db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -253,19 +253,20 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
{
int r;
- if (adev->uvd.vcpu_bo == NULL)
- return 0;
+ kfree(adev->uvd.saved_bo);
amd_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
- r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
- if (!r) {
- amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
- amdgpu_bo_unpin(adev->uvd.vcpu_bo);
- amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
- }
+ if (adev->uvd.vcpu_bo) {
+ r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
+ if (!r) {
+ amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
+ amdgpu_bo_unpin(adev->uvd.vcpu_bo);
+ amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
+ }
- amdgpu_bo_unref(&adev->uvd.vcpu_bo);
+ amdgpu_bo_unref(&adev->uvd.vcpu_bo);
+ }
amdgpu_ring_fini(&adev->uvd.ring);
@@ -1105,6 +1106,10 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
if (fences == 0 && handles == 0) {
if (adev->pm.dpm_enabled) {
amdgpu_dpm_enable_uvd(adev, false);
+ /* just work around for uvd clock remain high even
+ * when uvd dpm disabled on Polaris10 */
+ if (adev->asic_type == CHIP_POLARIS10)
+ amdgpu_asic_set_uvd_clocks(adev, 0, 0);
} else {
amdgpu_asic_set_uvd_clocks(adev, 0, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index ea708cb94862..9f36ed30ba11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -53,6 +53,18 @@
/* Special value that no flush is necessary */
#define AMDGPU_VM_NO_FLUSH (~0ll)
+/* Local structure. Encapsulate some VM table update parameters to reduce
+ * the number of function parameters
+ */
+struct amdgpu_vm_update_params {
+ /* address where to copy page table entries from */
+ uint64_t src;
+ /* DMA addresses to use for mapping */
+ dma_addr_t *pages_addr;
+ /* indirect buffer to fill with commands */
+ struct amdgpu_ib *ib;
+};
+
/**
* amdgpu_vm_num_pde - return the number of page directory entries
*
@@ -389,9 +401,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
* amdgpu_vm_update_pages - helper to call the right asic function
*
* @adev: amdgpu_device pointer
- * @src: address where to copy page table entries from
- * @pages_addr: DMA addresses to use for mapping
- * @ib: indirect buffer to fill with commands
+ * @vm_update_params: see amdgpu_vm_update_params definition
* @pe: addr of the page entry
* @addr: dst addr to write into pe
* @count: number of page entries to update
@@ -402,29 +412,29 @@ struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
* to setup the page table using the DMA.
*/
static void amdgpu_vm_update_pages(struct amdgpu_device *adev,
- uint64_t src,
- dma_addr_t *pages_addr,
- struct amdgpu_ib *ib,
+ struct amdgpu_vm_update_params
+ *vm_update_params,
uint64_t pe, uint64_t addr,
unsigned count, uint32_t incr,
uint32_t flags)
{
trace_amdgpu_vm_set_page(pe, addr, count, incr, flags);
- if (src) {
- src += (addr >> 12) * 8;
- amdgpu_vm_copy_pte(adev, ib, pe, src, count);
+ if (vm_update_params->src) {
+ amdgpu_vm_copy_pte(adev, vm_update_params->ib,
+ pe, (vm_update_params->src + (addr >> 12) * 8), count);
- } else if (pages_addr) {
- amdgpu_vm_write_pte(adev, ib, pages_addr, pe, addr,
- count, incr, flags);
+ } else if (vm_update_params->pages_addr) {
+ amdgpu_vm_write_pte(adev, vm_update_params->ib,
+ vm_update_params->pages_addr,
+ pe, addr, count, incr, flags);
} else if (count < 3) {
- amdgpu_vm_write_pte(adev, ib, NULL, pe, addr,
+ amdgpu_vm_write_pte(adev, vm_update_params->ib, NULL, pe, addr,
count, incr, flags);
} else {
- amdgpu_vm_set_pte_pde(adev, ib, pe, addr,
+ amdgpu_vm_set_pte_pde(adev, vm_update_params->ib, pe, addr,
count, incr, flags);
}
}
@@ -444,10 +454,12 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
struct amdgpu_ring *ring;
struct fence *fence = NULL;
struct amdgpu_job *job;
+ struct amdgpu_vm_update_params vm_update_params;
unsigned entries;
uint64_t addr;
int r;
+ memset(&vm_update_params, 0, sizeof(vm_update_params));
ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
r = reservation_object_reserve_shared(bo->tbo.resv);
@@ -465,7 +477,8 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
if (r)
goto error;
- amdgpu_vm_update_pages(adev, 0, NULL, &job->ibs[0], addr, 0, entries,
+ vm_update_params.ib = &job->ibs[0];
+ amdgpu_vm_update_pages(adev, &vm_update_params, addr, 0, entries,
0, 0);
amdgpu_ring_pad_ib(ring, &job->ibs[0]);
@@ -538,11 +551,12 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
uint64_t last_pde = ~0, last_pt = ~0;
unsigned count = 0, pt_idx, ndw;
struct amdgpu_job *job;
- struct amdgpu_ib *ib;
+ struct amdgpu_vm_update_params vm_update_params;
struct fence *fence = NULL;
int r;
+ memset(&vm_update_params, 0, sizeof(vm_update_params));
ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
/* padding, etc. */
@@ -555,7 +569,7 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
if (r)
return r;
- ib = &job->ibs[0];
+ vm_update_params.ib = &job->ibs[0];
/* walk over the address space and update the page directory */
for (pt_idx = 0; pt_idx <= vm->max_pde_used; ++pt_idx) {
@@ -575,7 +589,7 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
((last_pt + incr * count) != pt)) {
if (count) {
- amdgpu_vm_update_pages(adev, 0, NULL, ib,
+ amdgpu_vm_update_pages(adev, &vm_update_params,
last_pde, last_pt,
count, incr,
AMDGPU_PTE_VALID);
@@ -590,14 +604,15 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
}
if (count)
- amdgpu_vm_update_pages(adev, 0, NULL, ib, last_pde, last_pt,
- count, incr, AMDGPU_PTE_VALID);
+ amdgpu_vm_update_pages(adev, &vm_update_params,
+ last_pde, last_pt,
+ count, incr, AMDGPU_PTE_VALID);
- if (ib->length_dw != 0) {
- amdgpu_ring_pad_ib(ring, ib);
+ if (vm_update_params.ib->length_dw != 0) {
+ amdgpu_ring_pad_ib(ring, vm_update_params.ib);
amdgpu_sync_resv(adev, &job->sync, pd->tbo.resv,
AMDGPU_FENCE_OWNER_VM);
- WARN_ON(ib->length_dw > ndw);
+ WARN_ON(vm_update_params.ib->length_dw > ndw);
r = amdgpu_job_submit(job, ring, &vm->entity,
AMDGPU_FENCE_OWNER_VM, &fence);
if (r)
@@ -623,18 +638,15 @@ error_free:
* amdgpu_vm_frag_ptes - add fragment information to PTEs
*
* @adev: amdgpu_device pointer
- * @src: address where to copy page table entries from
- * @pages_addr: DMA addresses to use for mapping
- * @ib: IB for the update
+ * @vm_update_params: see amdgpu_vm_update_params definition
* @pe_start: first PTE to handle
* @pe_end: last PTE to handle
* @addr: addr those PTEs should point to
* @flags: hw mapping flags
*/
static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev,
- uint64_t src,
- dma_addr_t *pages_addr,
- struct amdgpu_ib *ib,
+ struct amdgpu_vm_update_params
+ *vm_update_params,
uint64_t pe_start, uint64_t pe_end,
uint64_t addr, uint32_t flags)
{
@@ -671,11 +683,11 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev,
return;
/* system pages are non continuously */
- if (src || pages_addr || !(flags & AMDGPU_PTE_VALID) ||
- (frag_start >= frag_end)) {
+ if (vm_update_params->src || vm_update_params->pages_addr ||
+ !(flags & AMDGPU_PTE_VALID) || (frag_start >= frag_end)) {
count = (pe_end - pe_start) / 8;
- amdgpu_vm_update_pages(adev, src, pages_addr, ib, pe_start,
+ amdgpu_vm_update_pages(adev, vm_update_params, pe_start,
addr, count, AMDGPU_GPU_PAGE_SIZE,
flags);
return;
@@ -684,21 +696,21 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev,
/* handle the 4K area at the beginning */
if (pe_start != frag_start) {
count = (frag_start - pe_start) / 8;
- amdgpu_vm_update_pages(adev, 0, NULL, ib, pe_start, addr,
+ amdgpu_vm_update_pages(adev, vm_update_params, pe_start, addr,
count, AMDGPU_GPU_PAGE_SIZE, flags);
addr += AMDGPU_GPU_PAGE_SIZE * count;
}
/* handle the area in the middle */
count = (frag_end - frag_start) / 8;
- amdgpu_vm_update_pages(adev, 0, NULL, ib, frag_start, addr, count,
+ amdgpu_vm_update_pages(adev, vm_update_params, frag_start, addr, count,
AMDGPU_GPU_PAGE_SIZE, flags | frag_flags);
/* handle the 4K area at the end */
if (frag_end != pe_end) {
addr += AMDGPU_GPU_PAGE_SIZE * count;
count = (pe_end - frag_end) / 8;
- amdgpu_vm_update_pages(adev, 0, NULL, ib, frag_end, addr,
+ amdgpu_vm_update_pages(adev, vm_update_params, frag_end, addr,
count, AMDGPU_GPU_PAGE_SIZE, flags);
}
}
@@ -707,8 +719,7 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev,
* amdgpu_vm_update_ptes - make sure that page tables are valid
*
* @adev: amdgpu_device pointer
- * @src: address where to copy page table entries from
- * @pages_addr: DMA addresses to use for mapping
+ * @vm_update_params: see amdgpu_vm_update_params definition
* @vm: requested vm
* @start: start of GPU address range
* @end: end of GPU address range
@@ -718,10 +729,9 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev,
* Update the page tables in the range @start - @end.
*/
static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
- uint64_t src,
- dma_addr_t *pages_addr,
+ struct amdgpu_vm_update_params
+ *vm_update_params,
struct amdgpu_vm *vm,
- struct amdgpu_ib *ib,
uint64_t start, uint64_t end,
uint64_t dst, uint32_t flags)
{
@@ -747,7 +757,7 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
if (last_pe_end != pe_start) {
- amdgpu_vm_frag_ptes(adev, src, pages_addr, ib,
+ amdgpu_vm_frag_ptes(adev, vm_update_params,
last_pe_start, last_pe_end,
last_dst, flags);
@@ -762,7 +772,7 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
dst += nptes * AMDGPU_GPU_PAGE_SIZE;
}
- amdgpu_vm_frag_ptes(adev, src, pages_addr, ib, last_pe_start,
+ amdgpu_vm_frag_ptes(adev, vm_update_params, last_pe_start,
last_pe_end, last_dst, flags);
}
@@ -794,11 +804,14 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
void *owner = AMDGPU_FENCE_OWNER_VM;
unsigned nptes, ncmds, ndw;
struct amdgpu_job *job;
- struct amdgpu_ib *ib;
+ struct amdgpu_vm_update_params vm_update_params;
struct fence *f = NULL;
int r;
ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+ memset(&vm_update_params, 0, sizeof(vm_update_params));
+ vm_update_params.src = src;
+ vm_update_params.pages_addr = pages_addr;
/* sync to everything on unmapping */
if (!(flags & AMDGPU_PTE_VALID))
@@ -815,11 +828,11 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
/* padding, etc. */
ndw = 64;
- if (src) {
+ if (vm_update_params.src) {
/* only copy commands needed */
ndw += ncmds * 7;
- } else if (pages_addr) {
+ } else if (vm_update_params.pages_addr) {
/* header for write data commands */
ndw += ncmds * 4;
@@ -838,7 +851,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
if (r)
return r;
- ib = &job->ibs[0];
+ vm_update_params.ib = &job->ibs[0];
r = amdgpu_sync_resv(adev, &job->sync, vm->page_directory->tbo.resv,
owner);
@@ -849,11 +862,11 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
if (r)
goto error_free;
- amdgpu_vm_update_ptes(adev, src, pages_addr, vm, ib, start,
+ amdgpu_vm_update_ptes(adev, &vm_update_params, vm, start,
last + 1, addr, flags);
- amdgpu_ring_pad_ib(ring, ib);
- WARN_ON(ib->length_dw > ndw);
+ amdgpu_ring_pad_ib(ring, vm_update_params.ib);
+ WARN_ON(vm_update_params.ib->length_dw > ndw);
r = amdgpu_job_submit(job, ring, &vm->entity,
AMDGPU_FENCE_OWNER_VM, &f);
if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index ea407db1fbcf..5ec1f1e9c983 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6221,6 +6221,9 @@ static int ci_dpm_sw_fini(void *handle)
ci_dpm_fini(adev);
mutex_unlock(&adev->pm.mutex);
+ release_firmware(adev->pm.fw);
+ adev->pm.fw = NULL;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 07bc795a4ca9..910431808542 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -962,6 +962,12 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev,
return true;
}
+static u32 cik_get_virtual_caps(struct amdgpu_device *adev)
+{
+ /* CIK does not support SR-IOV */
+ return 0;
+}
+
static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = {
{mmGRBM_STATUS, false},
{mmGB_ADDR_CONFIG, false},
@@ -2007,6 +2013,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
.get_xclk = &cik_get_xclk,
.set_uvd_clocks = &cik_set_uvd_clocks,
.set_vce_clocks = &cik_set_vce_clocks,
+ .get_virtual_caps = &cik_get_virtual_caps,
/* these should be moved to their own ip modules */
.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
.wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 845c21b1b2ee..be3d6f79a864 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -103,7 +103,6 @@ static void cik_ih_disable_interrupts(struct amdgpu_device *adev)
*/
static int cik_ih_irq_init(struct amdgpu_device *adev)
{
- int ret = 0;
int rb_bufsz;
u32 interrupt_cntl, ih_cntl, ih_rb_cntl;
u64 wptr_off;
@@ -156,7 +155,7 @@ static int cik_ih_irq_init(struct amdgpu_device *adev)
/* enable irqs */
cik_ih_enable_interrupts(adev);
- return ret;
+ return 0;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 518dca43b133..9dc4e24e31e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -66,6 +66,16 @@ MODULE_FIRMWARE("radeon/mullins_sdma1.bin");
u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev);
+
+static void cik_sdma_free_microcode(struct amdgpu_device *adev)
+{
+ int i;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ release_firmware(adev->sdma.instance[i].fw);
+ adev->sdma.instance[i].fw = NULL;
+ }
+}
+
/*
* sDMA - System DMA
* Starting with CIK, the GPU has new asynchronous
@@ -419,6 +429,8 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
/* Initialize the ring buffer's read and write pointers */
WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+ WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+ WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
/* set the wb address whether it's enabled or not */
WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -446,7 +458,12 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
ring->ready = true;
+ }
+
+ cik_sdma_enable(adev, true);
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
r = amdgpu_ring_test_ring(ring);
if (r) {
ring->ready = false;
@@ -529,8 +546,8 @@ static int cik_sdma_start(struct amdgpu_device *adev)
if (r)
return r;
- /* unhalt the MEs */
- cik_sdma_enable(adev, true);
+ /* halt the engine before programing */
+ cik_sdma_enable(adev, false);
/* start the gfx rings and rlc compute queues */
r = cik_sdma_gfx_resume(adev);
@@ -998,6 +1015,7 @@ static int cik_sdma_sw_fini(void *handle)
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+ cik_sdma_free_microcode(adev);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index fa4449e126e6..933e425a8154 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -1579,7 +1579,6 @@ static int cz_dpm_update_sclk_limit(struct amdgpu_device *adev)
static int cz_dpm_set_deep_sleep_sclk_threshold(struct amdgpu_device *adev)
{
- int ret = 0;
struct cz_power_info *pi = cz_get_pi(adev);
if (pi->caps_sclk_ds) {
@@ -1588,20 +1587,19 @@ static int cz_dpm_set_deep_sleep_sclk_threshold(struct amdgpu_device *adev)
CZ_MIN_DEEP_SLEEP_SCLK);
}
- return ret;
+ return 0;
}
/* ?? without dal support, is this still needed in setpowerstate list*/
static int cz_dpm_set_watermark_threshold(struct amdgpu_device *adev)
{
- int ret = 0;
struct cz_power_info *pi = cz_get_pi(adev);
cz_send_msg_to_smc_with_parameter(adev,
PPSMC_MSG_SetWatermarkFrequency,
pi->sclk_dpm.soft_max_clk);
- return ret;
+ return 0;
}
static int cz_dpm_enable_nbdpm(struct amdgpu_device *adev)
@@ -1636,7 +1634,6 @@ static void cz_dpm_nbdpm_lm_pstate_enable(struct amdgpu_device *adev,
static int cz_dpm_update_low_memory_pstate(struct amdgpu_device *adev)
{
- int ret = 0;
struct cz_power_info *pi = cz_get_pi(adev);
struct cz_ps *ps = &pi->requested_ps;
@@ -1647,21 +1644,19 @@ static int cz_dpm_update_low_memory_pstate(struct amdgpu_device *adev)
cz_dpm_nbdpm_lm_pstate_enable(adev, true);
}
- return ret;
+ return 0;
}
/* with dpm enabled */
static int cz_dpm_set_power_state(struct amdgpu_device *adev)
{
- int ret = 0;
-
cz_dpm_update_sclk_limit(adev);
cz_dpm_set_deep_sleep_sclk_threshold(adev);
cz_dpm_set_watermark_threshold(adev);
cz_dpm_enable_nbdpm(adev);
cz_dpm_update_low_memory_pstate(adev);
- return ret;
+ return 0;
}
static void cz_dpm_post_set_power_state(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index 863cb16f6126..3d23a70b6432 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -103,7 +103,6 @@ static void cz_ih_disable_interrupts(struct amdgpu_device *adev)
*/
static int cz_ih_irq_init(struct amdgpu_device *adev)
{
- int ret = 0;
int rb_bufsz;
u32 interrupt_cntl, ih_cntl, ih_rb_cntl;
u64 wptr_off;
@@ -157,7 +156,7 @@ static int cz_ih_irq_init(struct amdgpu_device *adev)
/* enable interrupts */
cz_ih_enable_interrupts(adev);
- return ret;
+ return 0;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index c11b6007af80..af26ec0bc59d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -137,7 +137,7 @@ static const u32 polaris11_golden_settings_a11[] =
mmDCI_CLK_CNTL, 0x00000080, 0x00000000,
mmFBC_DEBUG_COMP, 0x000000f0, 0x00000070,
mmFBC_DEBUG1, 0xffffffff, 0x00000008,
- mmFBC_MISC, 0x9f313fff, 0x14300008,
+ mmFBC_MISC, 0x9f313fff, 0x14302008,
mmHDMI_CONTROL, 0x313f031f, 0x00000011,
};
@@ -145,7 +145,7 @@ static const u32 polaris10_golden_settings_a11[] =
{
mmDCI_CLK_CNTL, 0x00000080, 0x00000000,
mmFBC_DEBUG_COMP, 0x000000f0, 0x00000070,
- mmFBC_MISC, 0x9f313fff, 0x14300008,
+ mmFBC_MISC, 0x9f313fff, 0x14302008,
mmHDMI_CONTROL, 0x313f031f, 0x00000011,
};
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
index 245cabf06575..ed03b75175d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
@@ -72,6 +72,11 @@ static int fiji_dpm_sw_init(void *handle)
static int fiji_dpm_sw_fini(void *handle)
{
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+ release_firmware(adev->pm.fw);
+ adev->pm.fw = NULL;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 7f18a53ab53a..fc8ff4d3ccf8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -991,6 +991,22 @@ out:
return err;
}
+static void gfx_v7_0_free_microcode(struct amdgpu_device *adev)
+{
+ release_firmware(adev->gfx.pfp_fw);
+ adev->gfx.pfp_fw = NULL;
+ release_firmware(adev->gfx.me_fw);
+ adev->gfx.me_fw = NULL;
+ release_firmware(adev->gfx.ce_fw);
+ adev->gfx.ce_fw = NULL;
+ release_firmware(adev->gfx.mec_fw);
+ adev->gfx.mec_fw = NULL;
+ release_firmware(adev->gfx.mec2_fw);
+ adev->gfx.mec2_fw = NULL;
+ release_firmware(adev->gfx.rlc_fw);
+ adev->gfx.rlc_fw = NULL;
+}
+
/**
* gfx_v7_0_tiling_mode_table_init - init the hw tiling table
*
@@ -4489,6 +4505,7 @@ static int gfx_v7_0_sw_fini(void *handle)
gfx_v7_0_cp_compute_fini(adev);
gfx_v7_0_rlc_fini(adev);
gfx_v7_0_mec_fini(adev);
+ gfx_v7_0_free_microcode(adev);
return 0;
}
@@ -4816,7 +4833,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev,
case 2:
for (i = 0; i < adev->gfx.num_compute_rings; i++) {
ring = &adev->gfx.compute_ring[i];
- if ((ring->me == me_id) & (ring->pipe == pipe_id))
+ if ((ring->me == me_id) && (ring->pipe == pipe_id))
amdgpu_fence_process(ring);
}
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 92647fbf5b8b..b2ebd4fef6cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -47,6 +47,8 @@
#include "dce/dce_10_0_d.h"
#include "dce/dce_10_0_sh_mask.h"
+#include "smu/smu_7_1_3_d.h"
+
#define GFX8_NUM_GFX_RINGS 1
#define GFX8_NUM_COMPUTE_RINGS 8
@@ -267,10 +269,13 @@ static const u32 tonga_mgcg_cgcg_init[] =
static const u32 golden_settings_polaris11_a11[] =
{
+ mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208,
mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
mmDB_DEBUG2, 0xf00fffff, 0x00000400,
mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
+ mmPA_SC_RASTER_CONFIG, 0x3f3fffff, 0x16000012,
+ mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000,
mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0001003c,
mmRLC_CGCG_CGLS_CTRL_3D, 0xffffffff, 0x0001003c,
mmSQ_CONFIG, 0x07f80000, 0x07180000,
@@ -284,8 +289,6 @@ static const u32 golden_settings_polaris11_a11[] =
static const u32 polaris11_golden_common_all[] =
{
mmGRBM_GFX_INDEX, 0xffffffff, 0xe0000000,
- mmPA_SC_RASTER_CONFIG, 0xffffffff, 0x16000012,
- mmPA_SC_RASTER_CONFIG_1, 0xffffffff, 0x00000000,
mmGB_ADDR_CONFIG, 0xffffffff, 0x22011002,
mmSPI_RESOURCE_RESERVE_CU_0, 0xffffffff, 0x00000800,
mmSPI_RESOURCE_RESERVE_CU_1, 0xffffffff, 0x00000800,
@@ -296,6 +299,8 @@ static const u32 polaris11_golden_common_all[] =
static const u32 golden_settings_polaris10_a11[] =
{
mmATC_MISC_CG, 0x000c0fc0, 0x000c0200,
+ mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208,
+ mmCB_HW_CONTROL_2, 0, 0x0f000000,
mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
mmDB_DEBUG2, 0xf00fffff, 0x00000400,
mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
@@ -690,6 +695,7 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
amdgpu_program_register_sequence(adev,
polaris10_golden_common_all,
(const u32)ARRAY_SIZE(polaris10_golden_common_all));
+ WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C);
break;
case CHIP_CARRIZO:
amdgpu_program_register_sequence(adev,
@@ -834,6 +840,26 @@ err1:
return r;
}
+
+static void gfx_v8_0_free_microcode(struct amdgpu_device *adev) {
+ release_firmware(adev->gfx.pfp_fw);
+ adev->gfx.pfp_fw = NULL;
+ release_firmware(adev->gfx.me_fw);
+ adev->gfx.me_fw = NULL;
+ release_firmware(adev->gfx.ce_fw);
+ adev->gfx.ce_fw = NULL;
+ release_firmware(adev->gfx.rlc_fw);
+ adev->gfx.rlc_fw = NULL;
+ release_firmware(adev->gfx.mec_fw);
+ adev->gfx.mec_fw = NULL;
+ if ((adev->asic_type != CHIP_STONEY) &&
+ (adev->asic_type != CHIP_TOPAZ))
+ release_firmware(adev->gfx.mec2_fw);
+ adev->gfx.mec2_fw = NULL;
+
+ kfree(adev->gfx.rlc.register_list_format);
+}
+
static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
{
const char *chip_name;
@@ -1981,7 +2007,7 @@ static int gfx_v8_0_sw_fini(void *handle)
gfx_v8_0_rlc_fini(adev);
- kfree(adev->gfx.rlc.register_list_format);
+ gfx_v8_0_free_microcode(adev);
return 0;
}
@@ -3972,11 +3998,15 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev)
amdgpu_ring_write(ring, 0x3a00161a);
amdgpu_ring_write(ring, 0x0000002e);
break;
- case CHIP_TOPAZ:
case CHIP_CARRIZO:
amdgpu_ring_write(ring, 0x00000002);
amdgpu_ring_write(ring, 0x00000000);
break;
+ case CHIP_TOPAZ:
+ amdgpu_ring_write(ring, adev->gfx.config.num_rbs == 1 ?
+ 0x00000000 : 0x00000002);
+ amdgpu_ring_write(ring, 0x00000000);
+ break;
case CHIP_STONEY:
amdgpu_ring_write(ring, 0x00000000);
amdgpu_ring_write(ring, 0x00000000);
@@ -5725,6 +5755,7 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
EOP_TC_ACTION_EN |
+ EOP_TC_WB_ACTION_EN |
EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
EVENT_INDEX(5)));
amdgpu_ring_write(ring, addr & 0xfffffffc);
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
index 460bc8ad37e6..825ccd63f2dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
@@ -72,6 +72,11 @@ static int iceland_dpm_sw_init(void *handle)
static int iceland_dpm_sw_fini(void *handle)
{
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+ release_firmware(adev->pm.fw);
+ adev->pm.fw = NULL;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index 39bfc52d0b42..3b8906ce3511 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -103,7 +103,6 @@ static void iceland_ih_disable_interrupts(struct amdgpu_device *adev)
*/
static int iceland_ih_irq_init(struct amdgpu_device *adev)
{
- int ret = 0;
int rb_bufsz;
u32 interrupt_cntl, ih_cntl, ih_rb_cntl;
u64 wptr_off;
@@ -157,7 +156,7 @@ static int iceland_ih_irq_init(struct amdgpu_device *adev)
/* enable interrupts */
iceland_ih_enable_interrupts(adev);
- return ret;
+ return 0;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index b45f54714574..a789a863d677 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2252,7 +2252,7 @@ static void kv_apply_state_adjust_rules(struct amdgpu_device *adev,
if (pi->caps_stable_p_state) {
stable_p_state_sclk = (max_limits->sclk * 75) / 100;
- for (i = table->count - 1; i >= 0; i++) {
+ for (i = table->count - 1; i >= 0; i--) {
if (stable_p_state_sclk >= table->entries[i].clk) {
stable_p_state_sclk = table->entries[i].clk;
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index f4c3130d3fdb..b556bd0a8797 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -105,6 +105,15 @@ static void sdma_v2_4_init_golden_registers(struct amdgpu_device *adev)
}
}
+static void sdma_v2_4_free_microcode(struct amdgpu_device *adev)
+{
+ int i;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ release_firmware(adev->sdma.instance[i].fw);
+ adev->sdma.instance[i].fw = NULL;
+ }
+}
+
/**
* sdma_v2_4_init_microcode - load ucode images from disk
*
@@ -461,6 +470,8 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
/* Initialize the ring buffer's read and write pointers */
WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+ WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+ WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
/* set the wb address whether it's enabled or not */
WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -489,7 +500,11 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
ring->ready = true;
+ }
+ sdma_v2_4_enable(adev, true);
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
r = amdgpu_ring_test_ring(ring);
if (r) {
ring->ready = false;
@@ -580,8 +595,8 @@ static int sdma_v2_4_start(struct amdgpu_device *adev)
return -EINVAL;
}
- /* unhalt the MEs */
- sdma_v2_4_enable(adev, true);
+ /* halt the engine before programing */
+ sdma_v2_4_enable(adev, false);
/* start the gfx rings and rlc compute queues */
r = sdma_v2_4_gfx_resume(adev);
@@ -1012,6 +1027,7 @@ static int sdma_v2_4_sw_fini(void *handle)
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+ sdma_v2_4_free_microcode(adev);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 063f08a9957a..532ea88da66a 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -109,10 +109,12 @@ static const u32 fiji_mgcg_cgcg_init[] =
static const u32 golden_settings_polaris11_a11[] =
{
mmSDMA0_CHICKEN_BITS, 0xfc910007, 0x00810007,
+ mmSDMA0_CLK_CTRL, 0xff000fff, 0x00000000,
mmSDMA0_GFX_IB_CNTL, 0x800f0111, 0x00000100,
mmSDMA0_RLC0_IB_CNTL, 0x800f0111, 0x00000100,
mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100,
mmSDMA1_CHICKEN_BITS, 0xfc910007, 0x00810007,
+ mmSDMA1_CLK_CTRL, 0xff000fff, 0x00000000,
mmSDMA1_GFX_IB_CNTL, 0x800f0111, 0x00000100,
mmSDMA1_RLC0_IB_CNTL, 0x800f0111, 0x00000100,
mmSDMA1_RLC1_IB_CNTL, 0x800f0111, 0x00000100,
@@ -234,6 +236,15 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev)
}
}
+static void sdma_v3_0_free_microcode(struct amdgpu_device *adev)
+{
+ int i;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ release_firmware(adev->sdma.instance[i].fw);
+ adev->sdma.instance[i].fw = NULL;
+ }
+}
+
/**
* sdma_v3_0_init_microcode - load ucode images from disk
*
@@ -670,6 +681,8 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
/* Initialize the ring buffer's read and write pointers */
WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+ WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+ WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
/* set the wb address whether it's enabled or not */
WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -709,7 +722,15 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
ring->ready = true;
+ }
+
+ /* unhalt the MEs */
+ sdma_v3_0_enable(adev, true);
+ /* enable sdma ring preemption */
+ sdma_v3_0_ctx_switch_enable(adev, true);
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
r = amdgpu_ring_test_ring(ring);
if (r) {
ring->ready = false;
@@ -802,10 +823,9 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
}
}
- /* unhalt the MEs */
- sdma_v3_0_enable(adev, true);
- /* enable sdma ring preemption */
- sdma_v3_0_ctx_switch_enable(adev, true);
+ /* disble sdma engine before programing it */
+ sdma_v3_0_ctx_switch_enable(adev, false);
+ sdma_v3_0_enable(adev, false);
/* start the gfx rings and rlc compute queues */
r = sdma_v3_0_gfx_resume(adev);
@@ -1245,6 +1265,7 @@ static int sdma_v3_0_sw_fini(void *handle)
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+ sdma_v3_0_free_microcode(adev);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
index b7615cefcac4..f06f6f4dc3a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
@@ -71,6 +71,11 @@ static int tonga_dpm_sw_init(void *handle)
static int tonga_dpm_sw_fini(void *handle)
{
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+ release_firmware(adev->pm.fw);
+ adev->pm.fw = NULL;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index f036af937fbc..c92055805a45 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -99,7 +99,6 @@ static void tonga_ih_disable_interrupts(struct amdgpu_device *adev)
*/
static int tonga_ih_irq_init(struct amdgpu_device *adev)
{
- int ret = 0;
int rb_bufsz;
u32 interrupt_cntl, ih_rb_cntl, ih_doorbell_rtpr;
u64 wptr_off;
@@ -165,7 +164,7 @@ static int tonga_ih_irq_init(struct amdgpu_device *adev)
/* enable interrupts */
tonga_ih_enable_interrupts(adev);
- return ret;
+ return 0;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 2c88d0b66cf3..a65c96029476 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -421,6 +421,20 @@ static bool vi_read_bios_from_rom(struct amdgpu_device *adev,
return true;
}
+static u32 vi_get_virtual_caps(struct amdgpu_device *adev)
+{
+ u32 caps = 0;
+ u32 reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER);
+
+ if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, IOV_ENABLE))
+ caps |= AMDGPU_VIRT_CAPS_SRIOV_EN;
+
+ if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, FUNC_IDENTIFIER))
+ caps |= AMDGPU_VIRT_CAPS_IS_VF;
+
+ return caps;
+}
+
static const struct amdgpu_allowed_register_entry tonga_allowed_read_registers[] = {
{mmGB_MACROTILE_MODE7, true},
};
@@ -1118,6 +1132,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
.get_xclk = &vi_get_xclk,
.set_uvd_clocks = &vi_set_uvd_clocks,
.set_vce_clocks = &vi_set_vce_clocks,
+ .get_virtual_caps = &vi_get_virtual_caps,
/* these should be moved to their own ip modules */
.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
.wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index ac005796b71c..7708d90b9da9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
pqm_uninit(&p->pqm);
/* Iterate over all process device data structure and check
- * if we should reset all wavefronts */
- list_for_each_entry(pdd, &p->per_device_data, per_device_list)
+ * if we should delete debug managers and reset all wavefronts
+ */
+ list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+ if ((pdd->dev->dbgmgr) &&
+ (pdd->dev->dbgmgr->pasid == p->pasid))
+ kfd_dbgmgr_destroy(pdd->dev->dbgmgr);
+
if (pdd->reset_wavefronts) {
pr_warn("amdkfd: Resetting all wave fronts\n");
dbgdev_wave_reset_wavefronts(pdd->dev, p);
pdd->reset_wavefronts = false;
}
+ }
mutex_unlock(&p->mutex);
@@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid)
idx = srcu_read_lock(&kfd_processes_srcu);
+ /*
+ * Look for the process that matches the pasid. If there is no such
+ * process, we either released it in amdkfd's own notifier, or there
+ * is a bug. Unfortunately, there is no way to tell...
+ */
hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes)
- if (p->pasid == pasid)
- break;
+ if (p->pasid == pasid) {
- srcu_read_unlock(&kfd_processes_srcu, idx);
+ srcu_read_unlock(&kfd_processes_srcu, idx);
- BUG_ON(p->pasid != pasid);
+ pr_debug("Unbinding process %d from IOMMU\n", pasid);
- mutex_lock(&p->mutex);
+ mutex_lock(&p->mutex);
- if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
- kfd_dbgmgr_destroy(dev->dbgmgr);
+ if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
+ kfd_dbgmgr_destroy(dev->dbgmgr);
- pqm_uninit(&p->pqm);
+ pqm_uninit(&p->pqm);
- pdd = kfd_get_process_device_data(dev, p);
+ pdd = kfd_get_process_device_data(dev, p);
- if (!pdd) {
- mutex_unlock(&p->mutex);
- return;
- }
+ if (!pdd) {
+ mutex_unlock(&p->mutex);
+ return;
+ }
- if (pdd->reset_wavefronts) {
- dbgdev_wave_reset_wavefronts(pdd->dev, p);
- pdd->reset_wavefronts = false;
- }
+ if (pdd->reset_wavefronts) {
+ dbgdev_wave_reset_wavefronts(pdd->dev, p);
+ pdd->reset_wavefronts = false;
+ }
- /*
- * Just mark pdd as unbound, because we still need it to call
- * amd_iommu_unbind_pasid() in when the process exits.
- * We don't call amd_iommu_unbind_pasid() here
- * because the IOMMU called us.
- */
- pdd->bound = false;
+ /*
+ * Just mark pdd as unbound, because we still need it
+ * to call amd_iommu_unbind_pasid() in when the
+ * process exits.
+ * We don't call amd_iommu_unbind_pasid() here
+ * because the IOMMU called us.
+ */
+ pdd->bound = false;
- mutex_unlock(&p->mutex);
+ mutex_unlock(&p->mutex);
+
+ return;
+ }
+
+ srcu_read_unlock(&kfd_processes_srcu, idx);
}
struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 74909e72a009..884c96f50c3d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -666,7 +666,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
dev->node_props.simd_count);
if (dev->mem_bank_count < dev->node_props.mem_banks_count) {
- pr_warn("kfd: mem_banks_count truncated from %d to %d\n",
+ pr_info_once("kfd: mem_banks_count truncated from %d to %d\n",
dev->node_props.mem_banks_count,
dev->mem_bank_count);
sysfs_show_32bit_prop(buffer, "mem_banks_count",
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 6080951d539d..afce1edbe250 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -157,6 +157,7 @@ struct amd_ip_funcs {
int (*hw_init)(void *handle);
/* tears down the hw state */
int (*hw_fini)(void *handle);
+ void (*late_fini)(void *handle);
/* handles IP specific hw/sw changes for suspend */
int (*suspend)(void *handle);
/* handles IP specific hw/sw changes for resume */
diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h
index 32f3e345de08..3493da5c8f0e 100644
--- a/drivers/gpu/drm/amd/include/atombios.h
+++ b/drivers/gpu/drm/amd/include/atombios.h
@@ -5538,6 +5538,78 @@ typedef struct _ATOM_ASIC_PROFILING_INFO_V3_5
ULONG ulReserved[12];
}ATOM_ASIC_PROFILING_INFO_V3_5;
+/* for Polars10/11 AVFS parameters */
+typedef struct _ATOM_ASIC_PROFILING_INFO_V3_6
+{
+ ATOM_COMMON_TABLE_HEADER asHeader;
+ ULONG ulMaxVddc;
+ ULONG ulMinVddc;
+ USHORT usLkgEuseIndex;
+ UCHAR ucLkgEfuseBitLSB;
+ UCHAR ucLkgEfuseLength;
+ ULONG ulLkgEncodeLn_MaxDivMin;
+ ULONG ulLkgEncodeMax;
+ ULONG ulLkgEncodeMin;
+ EFUSE_LINEAR_FUNC_PARAM sRoFuse;
+ ULONG ulEvvDefaultVddc;
+ ULONG ulEvvNoCalcVddc;
+ ULONG ulSpeed_Model;
+ ULONG ulSM_A0;
+ ULONG ulSM_A1;
+ ULONG ulSM_A2;
+ ULONG ulSM_A3;
+ ULONG ulSM_A4;
+ ULONG ulSM_A5;
+ ULONG ulSM_A6;
+ ULONG ulSM_A7;
+ UCHAR ucSM_A0_sign;
+ UCHAR ucSM_A1_sign;
+ UCHAR ucSM_A2_sign;
+ UCHAR ucSM_A3_sign;
+ UCHAR ucSM_A4_sign;
+ UCHAR ucSM_A5_sign;
+ UCHAR ucSM_A6_sign;
+ UCHAR ucSM_A7_sign;
+ ULONG ulMargin_RO_a;
+ ULONG ulMargin_RO_b;
+ ULONG ulMargin_RO_c;
+ ULONG ulMargin_fixed;
+ ULONG ulMargin_Fmax_mean;
+ ULONG ulMargin_plat_mean;
+ ULONG ulMargin_Fmax_sigma;
+ ULONG ulMargin_plat_sigma;
+ ULONG ulMargin_DC_sigma;
+ ULONG ulLoadLineSlop;
+ ULONG ulaTDClimitPerDPM[8];
+ ULONG ulaNoCalcVddcPerDPM[8];
+ ULONG ulAVFS_meanNsigma_Acontant0;
+ ULONG ulAVFS_meanNsigma_Acontant1;
+ ULONG ulAVFS_meanNsigma_Acontant2;
+ USHORT usAVFS_meanNsigma_DC_tol_sigma;
+ USHORT usAVFS_meanNsigma_Platform_mean;
+ USHORT usAVFS_meanNsigma_Platform_sigma;
+ ULONG ulGB_VDROOP_TABLE_CKSOFF_a0;
+ ULONG ulGB_VDROOP_TABLE_CKSOFF_a1;
+ ULONG ulGB_VDROOP_TABLE_CKSOFF_a2;
+ ULONG ulGB_VDROOP_TABLE_CKSON_a0;
+ ULONG ulGB_VDROOP_TABLE_CKSON_a1;
+ ULONG ulGB_VDROOP_TABLE_CKSON_a2;
+ ULONG ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+ USHORT usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+ ULONG ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+ ULONG ulAVFSGB_FUSE_TABLE_CKSON_m1;
+ USHORT usAVFSGB_FUSE_TABLE_CKSON_m2;
+ ULONG ulAVFSGB_FUSE_TABLE_CKSON_b;
+ USHORT usMaxVoltage_0_25mv;
+ UCHAR ucEnableGB_VDROOP_TABLE_CKSOFF;
+ UCHAR ucEnableGB_VDROOP_TABLE_CKSON;
+ UCHAR ucEnableGB_FUSE_TABLE_CKSOFF;
+ UCHAR ucEnableGB_FUSE_TABLE_CKSON;
+ USHORT usPSM_Age_ComFactor;
+ UCHAR ucEnableApplyAVFS_CKS_OFF_Voltage;
+ UCHAR ucReserved;
+}ATOM_ASIC_PROFILING_INFO_V3_6;
+
typedef struct _ATOM_SCLK_FCW_RANGE_ENTRY_V1{
ULONG ulMaxSclkFreq;
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index a461e155a160..7464daf89ca1 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -581,6 +581,9 @@ typedef int (*cgs_get_firmware_info)(struct cgs_device *cgs_device,
enum cgs_ucode_id type,
struct cgs_firmware_info *info);
+typedef int (*cgs_rel_firmware)(struct cgs_device *cgs_device,
+ enum cgs_ucode_id type);
+
typedef int(*cgs_set_powergating_state)(struct cgs_device *cgs_device,
enum amd_ip_block_type block_type,
enum amd_powergating_state state);
@@ -645,6 +648,7 @@ struct cgs_ops {
cgs_set_camera_voltages_t set_camera_voltages;
/* Firmware Info */
cgs_get_firmware_info get_firmware_info;
+ cgs_rel_firmware rel_firmware;
/* cg pg interface*/
cgs_set_powergating_state set_powergating_state;
cgs_set_clockgating_state set_clockgating_state;
@@ -738,6 +742,8 @@ struct cgs_device
CGS_CALL(set_camera_voltages,dev,mask,voltages)
#define cgs_get_firmware_info(dev, type, info) \
CGS_CALL(get_firmware_info, dev, type, info)
+#define cgs_rel_firmware(dev, type) \
+ CGS_CALL(rel_firmware, dev, type)
#define cgs_set_powergating_state(dev, block_type, state) \
CGS_CALL(set_powergating_state, dev, block_type, state)
#define cgs_set_clockgating_state(dev, block_type, state) \
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 8e345bfddb69..e629f8a9fe93 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -73,11 +73,14 @@ static int pp_sw_init(void *handle)
ret = hwmgr->hwmgr_func->backend_init(hwmgr);
if (ret)
- goto err;
+ goto err1;
pr_info("amdgpu: powerplay initialized\n");
return 0;
+err1:
+ if (hwmgr->pptable_func->pptable_fini)
+ hwmgr->pptable_func->pptable_fini(hwmgr);
err:
pr_err("amdgpu: powerplay initialization failed\n");
return ret;
@@ -100,6 +103,9 @@ static int pp_sw_fini(void *handle)
if (hwmgr->hwmgr_func->backend_fini != NULL)
ret = hwmgr->hwmgr_func->backend_fini(hwmgr);
+ if (hwmgr->pptable_func->pptable_fini)
+ hwmgr->pptable_func->pptable_fini(hwmgr);
+
return ret;
}
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
index 46410e3c7349..fb88e4e5d625 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
@@ -58,9 +58,6 @@ static void pem_fini(struct pp_eventmgr *eventmgr)
pem_unregister_interrupts(eventmgr);
pem_handle_event(eventmgr, AMD_PP_EVENT_UNINITIALIZE, &event_data);
-
- if (eventmgr != NULL)
- kfree(eventmgr);
}
int eventmgr_init(struct pp_instance *handle)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
index c94f9faa220a..92912ab20944 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
@@ -633,6 +633,8 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
data->vddci_control = FIJI_VOLTAGE_CONTROL_NONE;
data->mvdd_control = FIJI_VOLTAGE_CONTROL_NONE;
+ data->force_pcie_gen = PP_PCIEGenInvalid;
+
if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
data->voltage_control = FIJI_VOLTAGE_CONTROL_BY_SVID2;
@@ -1830,7 +1832,7 @@ static uint16_t fiji_find_closest_vddci(struct pp_hwmgr *hwmgr, uint16_t vddci)
PP_ASSERT_WITH_CODE(false,
"VDDCI is larger than max VDDCI in VDDCI Voltage Table!",
- return vddci_table->entries[i].value);
+ return vddci_table->entries[i-1].value);
}
static int fiji_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
@@ -3573,46 +3575,11 @@ static int fiji_force_dpm_highest(struct pp_hwmgr *hwmgr)
return 0;
}
-static void fiji_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr)
-{
- struct phm_ppt_v1_information *table_info =
- (struct phm_ppt_v1_information *)hwmgr->pptable;
- struct phm_clock_voltage_dependency_table *table =
- table_info->vddc_dep_on_dal_pwrl;
- struct phm_ppt_v1_clock_voltage_dependency_table *vddc_table;
- enum PP_DAL_POWERLEVEL dal_power_level = hwmgr->dal_power_level;
- uint32_t req_vddc = 0, req_volt, i;
-
- if (!table && !(dal_power_level >= PP_DAL_POWERLEVEL_ULTRALOW &&
- dal_power_level <= PP_DAL_POWERLEVEL_PERFORMANCE))
- return;
-
- for (i= 0; i < table->count; i++) {
- if (dal_power_level == table->entries[i].clk) {
- req_vddc = table->entries[i].v;
- break;
- }
- }
-
- vddc_table = table_info->vdd_dep_on_sclk;
- for (i= 0; i < vddc_table->count; i++) {
- if (req_vddc <= vddc_table->entries[i].vddc) {
- req_volt = (((uint32_t)vddc_table->entries[i].vddc) * VOLTAGE_SCALE)
- << VDDC_SHIFT;
- smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
- PPSMC_MSG_VddC_Request, req_volt);
- return;
- }
- }
- printk(KERN_ERR "DAL requested level can not"
- " found a available voltage in VDDC DPM Table \n");
-}
-
static int fiji_upload_dpmlevel_enable_mask(struct pp_hwmgr *hwmgr)
{
struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
- fiji_apply_dal_min_voltage_request(hwmgr);
+ phm_apply_dal_min_voltage_request(hwmgr);
if (!data->sclk_dpm_key_disabled) {
if (data->dpm_level_enable_mask.sclk_dpm_enable_mask)
@@ -4349,7 +4316,7 @@ static int fiji_populate_and_upload_sclk_mclk_dpm_levels(
if (data->need_update_smu7_dpm_table &
(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK)) {
- result = fiji_populate_all_memory_levels(hwmgr);
+ result = fiji_populate_all_graphic_levels(hwmgr);
PP_ASSERT_WITH_CODE((0 == result),
"Failed to populate SCLK during PopulateNewDPMClocksStates Function!",
return result);
@@ -5109,11 +5076,11 @@ static int fiji_get_pp_table(struct pp_hwmgr *hwmgr, char **table)
struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
if (!data->soft_pp_table) {
- data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
+ data->soft_pp_table = kmemdup(hwmgr->soft_pp_table,
+ hwmgr->soft_pp_table_size,
+ GFP_KERNEL);
if (!data->soft_pp_table)
return -ENOMEM;
- memcpy(data->soft_pp_table, hwmgr->soft_pp_table,
- hwmgr->soft_pp_table_size);
}
*table = (char *)&data->soft_pp_table;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index fa208ada6892..efb77eda7508 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -306,10 +306,14 @@ int phm_store_dal_configuration_data(struct pp_hwmgr *hwmgr,
{
PHM_FUNC_CHECK(hwmgr);
- if (hwmgr->hwmgr_func->store_cc6_data == NULL)
+ if (display_config == NULL)
return -EINVAL;
hwmgr->display_config = *display_config;
+
+ if (hwmgr->hwmgr_func->store_cc6_data == NULL)
+ return -EINVAL;
+
/* to do pass other display configuration in furture */
if (hwmgr->hwmgr_func->store_cc6_data)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 7d69ed635bc2..20f20e075588 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -30,6 +30,9 @@
#include "pppcielanes.h"
#include "pp_debug.h"
#include "ppatomctrl.h"
+#include "ppsmc.h"
+
+#define VOLTAGE_SCALE 4
extern int cz_hwmgr_init(struct pp_hwmgr *hwmgr);
extern int tonga_hwmgr_init(struct pp_hwmgr *hwmgr);
@@ -90,6 +93,13 @@ int hwmgr_fini(struct pp_hwmgr *hwmgr)
if (hwmgr == NULL || hwmgr->ps == NULL)
return -EINVAL;
+ /* do hwmgr finish*/
+ kfree(hwmgr->backend);
+
+ kfree(hwmgr->start_thermal_controller.function_list);
+
+ kfree(hwmgr->set_temperature_range.function_list);
+
kfree(hwmgr->ps);
kfree(hwmgr);
return 0;
@@ -459,7 +469,7 @@ uint16_t phm_find_closest_vddci(struct pp_atomctrl_voltage_table *vddci_table, u
PP_ASSERT_WITH_CODE(false,
"VDDCI is larger than max VDDCI in VDDCI Voltage Table!",
- return vddci_table->entries[i].value);
+ return vddci_table->entries[i-1].value);
}
int phm_find_boot_level(void *table,
@@ -566,3 +576,38 @@ uint32_t phm_get_lowest_enabled_level(struct pp_hwmgr *hwmgr, uint32_t mask)
return level;
}
+
+void phm_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr)
+{
+ struct phm_ppt_v1_information *table_info =
+ (struct phm_ppt_v1_information *)hwmgr->pptable;
+ struct phm_clock_voltage_dependency_table *table =
+ table_info->vddc_dep_on_dal_pwrl;
+ struct phm_ppt_v1_clock_voltage_dependency_table *vddc_table;
+ enum PP_DAL_POWERLEVEL dal_power_level = hwmgr->dal_power_level;
+ uint32_t req_vddc = 0, req_volt, i;
+
+ if (!table || table->count <= 0
+ || dal_power_level < PP_DAL_POWERLEVEL_ULTRALOW
+ || dal_power_level > PP_DAL_POWERLEVEL_PERFORMANCE)
+ return;
+
+ for (i = 0; i < table->count; i++) {
+ if (dal_power_level == table->entries[i].clk) {
+ req_vddc = table->entries[i].v;
+ break;
+ }
+ }
+
+ vddc_table = table_info->vdd_dep_on_sclk;
+ for (i = 0; i < vddc_table->count; i++) {
+ if (req_vddc <= vddc_table->entries[i].vddc) {
+ req_volt = (((uint32_t)vddc_table->entries[i].vddc) * VOLTAGE_SCALE);
+ smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+ PPSMC_MSG_VddC_Request, req_volt);
+ return;
+ }
+ }
+ printk(KERN_ERR "DAL requested level can not"
+ " found a available voltage in VDDC DPM Table \n");
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
index 347fef127ce9..2930a3355948 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
@@ -39,6 +39,7 @@ struct phm_ppt_v1_clock_voltage_dependency_record {
uint8_t phases;
uint8_t cks_enable;
uint8_t cks_voffset;
+ uint32_t sclk_offset;
};
typedef struct phm_ppt_v1_clock_voltage_dependency_record phm_ppt_v1_clock_voltage_dependency_record;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
index 93768fa1dcdc..91e25f942d90 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
@@ -189,41 +189,6 @@ int phm_get_current_pcie_lane_number(struct pp_hwmgr *hwmgr)
return decode_pcie_lane_width(link_width);
}
-void phm_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr)
-{
- struct phm_ppt_v1_information *table_info =
- (struct phm_ppt_v1_information *)hwmgr->pptable;
- struct phm_clock_voltage_dependency_table *table =
- table_info->vddc_dep_on_dal_pwrl;
- struct phm_ppt_v1_clock_voltage_dependency_table *vddc_table;
- enum PP_DAL_POWERLEVEL dal_power_level = hwmgr->dal_power_level;
- uint32_t req_vddc = 0, req_volt, i;
-
- if (!table && !(dal_power_level >= PP_DAL_POWERLEVEL_ULTRALOW &&
- dal_power_level <= PP_DAL_POWERLEVEL_PERFORMANCE))
- return;
-
- for (i = 0; i < table->count; i++) {
- if (dal_power_level == table->entries[i].clk) {
- req_vddc = table->entries[i].v;
- break;
- }
- }
-
- vddc_table = table_info->vdd_dep_on_sclk;
- for (i = 0; i < vddc_table->count; i++) {
- if (req_vddc <= vddc_table->entries[i].vddc) {
- req_volt = (((uint32_t)vddc_table->entries[i].vddc) * VOLTAGE_SCALE)
- << VDDC_SHIFT;
- smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
- PPSMC_MSG_VddC_Request, req_volt);
- return;
- }
- }
- printk(KERN_ERR "DAL requested level can not"
- " found a available voltage in VDDC DPM Table \n");
-}
-
/**
* Enable voltage control
*
@@ -767,7 +732,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
table->Smio[level] |=
data->mvdd_voltage_table.entries[level].smio_low;
}
- table->SmioMask2 = data->vddci_voltage_table.mask_low;
+ table->SmioMask2 = data->mvdd_voltage_table.mask_low;
table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count);
}
@@ -1034,7 +999,7 @@ static int polaris10_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
(dep_table->entries[i].vddc -
(uint16_t)data->vddc_vddci_delta));
- *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+ *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
}
if (POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control)
@@ -1331,7 +1296,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
}
mem_level->MclkFrequency = clock;
- mem_level->StutterEnable = 0;
mem_level->EnabledForThrottle = 1;
mem_level->EnabledForActivity = 0;
mem_level->UpHyst = 0;
@@ -1339,7 +1303,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
mem_level->VoltageDownHyst = 0;
mem_level->ActivityLevel = (uint16_t)data->mclk_activity_target;
mem_level->StutterEnable = false;
-
mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
data->display_timing.num_existing_displays = info.display_count;
@@ -1398,7 +1361,7 @@ static int polaris10_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
* a higher state by default such that we are not effected by
* up threshold or and MCLK DPM latency.
*/
- levels[0].ActivityLevel = (uint16_t)data->mclk_dpm0_activity_target;
+ levels[0].ActivityLevel = 0x1f;
CONVERT_FROM_HOST_TO_SMC_US(levels[0].ActivityLevel);
data->smc_state_table.MemoryDpmLevelCount =
@@ -1459,22 +1422,19 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
- if (!data->sclk_dpm_key_disabled) {
- /* Get MinVoltage and Frequency from DPM0,
- * already converted to SMC_UL */
- sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
- result = polaris10_get_dependency_volt_by_clk(hwmgr,
- table_info->vdd_dep_on_sclk,
- table->ACPILevel.SclkFrequency,
- &table->ACPILevel.MinVoltage, &mvdd);
- PP_ASSERT_WITH_CODE((0 == result),
- "Cannot find ACPI VDDC voltage value "
- "in Clock Dependency Table", );
- } else {
- sclk_frequency = data->vbios_boot_state.sclk_bootup_value;
- table->ACPILevel.MinVoltage =
- data->vbios_boot_state.vddc_bootup_value * VOLTAGE_SCALE;
- }
+
+ /* Get MinVoltage and Frequency from DPM0,
+ * already converted to SMC_UL */
+ sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
+ result = polaris10_get_dependency_volt_by_clk(hwmgr,
+ table_info->vdd_dep_on_sclk,
+ sclk_frequency,
+ &table->ACPILevel.MinVoltage, &mvdd);
+ PP_ASSERT_WITH_CODE((0 == result),
+ "Cannot find ACPI VDDC voltage value "
+ "in Clock Dependency Table",
+ );
+
result = polaris10_calculate_sclk_params(hwmgr, sclk_frequency, &(table->ACPILevel.SclkSetting));
PP_ASSERT_WITH_CODE(result == 0, "Error retrieving Engine Clock dividers from VBIOS.", return result);
@@ -1499,24 +1459,18 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_frac);
CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_ss_slew_rate);
- if (!data->mclk_dpm_key_disabled) {
- /* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
- table->MemoryACPILevel.MclkFrequency =
- data->dpm_table.mclk_table.dpm_levels[0].value;
- result = polaris10_get_dependency_volt_by_clk(hwmgr,
- table_info->vdd_dep_on_mclk,
- table->MemoryACPILevel.MclkFrequency,
- &table->MemoryACPILevel.MinVoltage, &mvdd);
- PP_ASSERT_WITH_CODE((0 == result),
- "Cannot find ACPI VDDCI voltage value "
- "in Clock Dependency Table",
- );
- } else {
- table->MemoryACPILevel.MclkFrequency =
- data->vbios_boot_state.mclk_bootup_value;
- table->MemoryACPILevel.MinVoltage =
- data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE;
- }
+
+ /* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
+ table->MemoryACPILevel.MclkFrequency =
+ data->dpm_table.mclk_table.dpm_levels[0].value;
+ result = polaris10_get_dependency_volt_by_clk(hwmgr,
+ table_info->vdd_dep_on_mclk,
+ table->MemoryACPILevel.MclkFrequency,
+ &table->MemoryACPILevel.MinVoltage, &mvdd);
+ PP_ASSERT_WITH_CODE((0 == result),
+ "Cannot find ACPI VDDCI voltage value "
+ "in Clock Dependency Table",
+ );
us_mvdd = 0;
if ((POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
@@ -1561,6 +1515,7 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
table_info->mm_dep_table;
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+ uint32_t vddci;
table->VceLevelCount = (uint8_t)(mm_table->count);
table->VceBootLevel = 0;
@@ -1570,9 +1525,18 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
table->VceLevel[count].MinVoltage = 0;
table->VceLevel[count].MinVoltage |=
(mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
+
+ if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+ vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+ mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+ else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+ vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+ else
+ vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+
table->VceLevel[count].MinVoltage |=
- ((mm_table->entries[count].vddc - data->vddc_vddci_delta) *
- VOLTAGE_SCALE) << VDDCI_SHIFT;
+ (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
table->VceLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
/*retrieve divider value for VBIOS */
@@ -1601,6 +1565,7 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
table_info->mm_dep_table;
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+ uint32_t vddci;
table->SamuBootLevel = 0;
table->SamuLevelCount = (uint8_t)(mm_table->count);
@@ -1611,8 +1576,16 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
VOLTAGE_SCALE) << VDDC_SHIFT;
- table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
- data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+ if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+ vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+ mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+ else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+ vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+ else
+ vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+ table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
/* retrieve divider value for VBIOS */
@@ -1695,6 +1668,7 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
table_info->mm_dep_table;
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+ uint32_t vddci;
table->UvdLevelCount = (uint8_t)(mm_table->count);
table->UvdBootLevel = 0;
@@ -1705,8 +1679,16 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
table->UvdLevel[count].DclkFrequency = mm_table->entries[count].dclk;
table->UvdLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
VOLTAGE_SCALE) << VDDC_SHIFT;
- table->UvdLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
- data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+ if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+ vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+ mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+ else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+ vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+ else
+ vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+ table->UvdLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
table->UvdLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
/* retrieve divider value for VBIOS */
@@ -1727,8 +1709,8 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].VclkFrequency);
CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].DclkFrequency);
CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].MinVoltage);
-
}
+
return result;
}
@@ -1796,12 +1778,9 @@ static int polaris10_populate_smc_initailial_state(struct pp_hwmgr *hwmgr)
static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
{
- uint32_t ro, efuse, efuse2, clock_freq, volt_without_cks,
- volt_with_cks, value;
- uint16_t clock_freq_u16;
+ uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
- uint8_t type, i, j, cks_setting, stretch_amount, stretch_amount2,
- volt_offset = 0;
+ uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
struct phm_ppt_v1_information *table_info =
(struct phm_ppt_v1_information *)(hwmgr->pptable);
struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1813,50 +1792,44 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
* if the part is SS or FF. if RO >= 1660MHz, part is FF.
*/
efuse = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
- ixSMU_EFUSE_0 + (146 * 4));
- efuse2 = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
- ixSMU_EFUSE_0 + (148 * 4));
+ ixSMU_EFUSE_0 + (67 * 4));
efuse &= 0xFF000000;
efuse = efuse >> 24;
- efuse2 &= 0xF;
-
- if (efuse2 == 1)
- ro = (2300 - 1350) * efuse / 255 + 1350;
- else
- ro = (2500 - 1000) * efuse / 255 + 1000;
- if (ro >= 1660)
- type = 0;
- else
- type = 1;
+ if (hwmgr->chip_id == CHIP_POLARIS10) {
+ min = 1000;
+ max = 2300;
+ } else {
+ min = 1100;
+ max = 2100;
+ }
- /* Populate Stretch amount */
- data->smc_state_table.ClockStretcherAmount = stretch_amount;
+ ro = efuse * (max -min)/255 + min;
/* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */
for (i = 0; i < sclk_table->count; i++) {
data->smc_state_table.Sclk_CKS_masterEn0_7 |=
sclk_table->entries[i].cks_enable << i;
- volt_without_cks = (uint32_t)((14041 *
- (sclk_table->entries[i].clk/100) / 10000 + 3571 + 75 - ro) * 1000 /
- (4026 - (13924 * (sclk_table->entries[i].clk/100) / 10000)));
- volt_with_cks = (uint32_t)((13946 *
- (sclk_table->entries[i].clk/100) / 10000 + 3320 + 45 - ro) * 1000 /
- (3664 - (11454 * (sclk_table->entries[i].clk/100) / 10000)));
+ if (hwmgr->chip_id == CHIP_POLARIS10) {
+ volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \
+ (2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000));
+ volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \
+ (2522480 - sclk_table->entries[i].clk/100 * 115764/100));
+ } else {
+ volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \
+ (2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000)));
+ volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \
+ (3422454 - sclk_table->entries[i].clk/100 * (18886376/10000)));
+ }
+
if (volt_without_cks >= volt_with_cks)
volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks +
- sclk_table->entries[i].cks_voffset) * 100 / 625) + 1);
+ sclk_table->entries[i].cks_voffset) * 100 + 624) / 625);
+
data->smc_state_table.Sclk_voltageOffset[i] = volt_offset;
}
- PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
- STRETCH_ENABLE, 0x0);
- PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
- masterReset, 0x1);
- /* PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, staticEnable, 0x1); */
- PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
- masterReset, 0x0);
-
+ data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6;
/* Populate CKS Lookup Table */
if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
stretch_amount2 = 0;
@@ -1870,69 +1843,6 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
return -EINVAL);
}
- value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
- ixPWR_CKS_CNTL);
- value &= 0xFFC2FF87;
- data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq =
- polaris10_clock_stretcher_lookup_table[stretch_amount2][0];
- data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq =
- polaris10_clock_stretcher_lookup_table[stretch_amount2][1];
- clock_freq_u16 = (uint16_t)(PP_SMC_TO_HOST_UL(data->smc_state_table.
- GraphicsLevel[data->smc_state_table.GraphicsDpmLevelCount - 1].SclkSetting.SclkFrequency) / 100);
- if (polaris10_clock_stretcher_lookup_table[stretch_amount2][0] < clock_freq_u16
- && polaris10_clock_stretcher_lookup_table[stretch_amount2][1] > clock_freq_u16) {
- /* Program PWR_CKS_CNTL. CKS_USE_FOR_LOW_FREQ */
- value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 16;
- /* Program PWR_CKS_CNTL. CKS_LDO_REFSEL */
- value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][2]) << 18;
- /* Program PWR_CKS_CNTL. CKS_STRETCH_AMOUNT */
- value |= (polaris10_clock_stretch_amount_conversion
- [polaris10_clock_stretcher_lookup_table[stretch_amount2][3]]
- [stretch_amount]) << 3;
- }
- CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq);
- CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq);
- data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting =
- polaris10_clock_stretcher_lookup_table[stretch_amount2][2] & 0x7F;
- data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting |=
- (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 7;
-
- cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
- ixPWR_CKS_CNTL, value);
-
- /* Populate DDT Lookup Table */
- for (i = 0; i < 4; i++) {
- /* Assign the minimum and maximum VID stored
- * in the last row of Clock Stretcher Voltage Table.
- */
- data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].minVID =
- (uint8_t) polaris10_clock_stretcher_ddt_table[type][i][2];
- data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].maxVID =
- (uint8_t) polaris10_clock_stretcher_ddt_table[type][i][3];
- /* Loop through each SCLK and check the frequency
- * to see if it lies within the frequency for clock stretcher.
- */
- for (j = 0; j < data->smc_state_table.GraphicsDpmLevelCount; j++) {
- cks_setting = 0;
- clock_freq = PP_SMC_TO_HOST_UL(
- data->smc_state_table.GraphicsLevel[j].SclkSetting.SclkFrequency);
- /* Check the allowed frequency against the sclk level[j].
- * Sclk's endianness has already been converted,
- * and it's in 10Khz unit,
- * as opposed to Data table, which is in Mhz unit.
- */
- if (clock_freq >= (polaris10_clock_stretcher_ddt_table[type][i][0]) * 100) {
- cks_setting |= 0x2;
- if (clock_freq < (polaris10_clock_stretcher_ddt_table[type][i][1]) * 100)
- cks_setting |= 0x1;
- }
- data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting
- |= cks_setting << (j * 2);
- }
- CONVERT_FROM_HOST_TO_SMC_US(
- data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting);
- }
-
value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL);
value &= 0xFFFFFFFE;
cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL, value);
@@ -1991,6 +1901,90 @@ static int polaris10_populate_vr_config(struct pp_hwmgr *hwmgr,
return 0;
}
+
+int polaris10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
+{
+ struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+ SMU74_Discrete_DpmTable *table = &(data->smc_state_table);
+ int result = 0;
+ struct pp_atom_ctrl__avfs_parameters avfs_params = {0};
+ AVFS_meanNsigma_t AVFS_meanNsigma = { {0} };
+ AVFS_Sclk_Offset_t AVFS_SclkOffset = { {0} };
+ uint32_t tmp, i;
+ struct pp_smumgr *smumgr = hwmgr->smumgr;
+ struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend);
+
+ struct phm_ppt_v1_information *table_info =
+ (struct phm_ppt_v1_information *)hwmgr->pptable;
+ struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
+ table_info->vdd_dep_on_sclk;
+
+
+ if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED)
+ return result;
+
+ result = atomctrl_get_avfs_information(hwmgr, &avfs_params);
+
+ if (0 == result) {
+ table->BTCGB_VDROOP_TABLE[0].a0 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a0);
+ table->BTCGB_VDROOP_TABLE[0].a1 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a1);
+ table->BTCGB_VDROOP_TABLE[0].a2 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a2);
+ table->BTCGB_VDROOP_TABLE[1].a0 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a0);
+ table->BTCGB_VDROOP_TABLE[1].a1 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a1);
+ table->BTCGB_VDROOP_TABLE[1].a2 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a2);
+ table->AVFSGB_VDROOP_TABLE[0].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_m1);
+ table->AVFSGB_VDROOP_TABLE[0].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSON_m2);
+ table->AVFSGB_VDROOP_TABLE[0].b = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_b);
+ table->AVFSGB_VDROOP_TABLE[0].m1_shift = 24;
+ table->AVFSGB_VDROOP_TABLE[0].m2_shift = 12;
+ table->AVFSGB_VDROOP_TABLE[1].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_m1);
+ table->AVFSGB_VDROOP_TABLE[1].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSOFF_m2);
+ table->AVFSGB_VDROOP_TABLE[1].b = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_b);
+ table->AVFSGB_VDROOP_TABLE[1].m1_shift = 24;
+ table->AVFSGB_VDROOP_TABLE[1].m2_shift = 12;
+ table->MaxVoltage = PP_HOST_TO_SMC_US(avfs_params.usMaxVoltage_0_25mv);
+ AVFS_meanNsigma.Aconstant[0] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant0);
+ AVFS_meanNsigma.Aconstant[1] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant1);
+ AVFS_meanNsigma.Aconstant[2] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant2);
+ AVFS_meanNsigma.DC_tol_sigma = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_DC_tol_sigma);
+ AVFS_meanNsigma.Platform_mean = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_mean);
+ AVFS_meanNsigma.PSM_Age_CompFactor = PP_HOST_TO_SMC_US(avfs_params.usPSM_Age_ComFactor);
+ AVFS_meanNsigma.Platform_sigma = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_sigma);
+
+ for (i = 0; i < NUM_VFT_COLUMNS; i++) {
+ AVFS_meanNsigma.Static_Voltage_Offset[i] = (uint8_t)(sclk_table->entries[i].cks_voffset * 100 / 625);
+ AVFS_SclkOffset.Sclk_Offset[i] = PP_HOST_TO_SMC_US((uint16_t)(sclk_table->entries[i].sclk_offset) / 100);
+ }
+
+ result = polaris10_read_smc_sram_dword(smumgr,
+ SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsMeanNSigma),
+ &tmp, data->sram_end);
+
+ polaris10_copy_bytes_to_smc(smumgr,
+ tmp,
+ (uint8_t *)&AVFS_meanNsigma,
+ sizeof(AVFS_meanNsigma_t),
+ data->sram_end);
+
+ result = polaris10_read_smc_sram_dword(smumgr,
+ SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsSclkOffsetTable),
+ &tmp, data->sram_end);
+ polaris10_copy_bytes_to_smc(smumgr,
+ tmp,
+ (uint8_t *)&AVFS_SclkOffset,
+ sizeof(AVFS_Sclk_Offset_t),
+ data->sram_end);
+
+ data->avfs_vdroop_override_setting = (avfs_params.ucEnableGB_VDROOP_TABLE_CKSON << BTCGB0_Vdroop_Enable_SHIFT) |
+ (avfs_params.ucEnableGB_VDROOP_TABLE_CKSOFF << BTCGB1_Vdroop_Enable_SHIFT) |
+ (avfs_params.ucEnableGB_FUSE_TABLE_CKSON << AVFSGB0_Vdroop_Enable_SHIFT) |
+ (avfs_params.ucEnableGB_FUSE_TABLE_CKSOFF << AVFSGB1_Vdroop_Enable_SHIFT);
+ data->apply_avfs_cks_off_voltage = (avfs_params.ucEnableApplyAVFS_CKS_OFF_Voltage == 1) ? true : false;
+ }
+ return result;
+}
+
+
/**
* Initializes the SMC table and uploads it
*
@@ -2092,6 +2086,10 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr)
return result);
}
+ result = polaris10_populate_avfs_parameters(hwmgr);
+ PP_ASSERT_WITH_CODE(0 == result, "Failed to populate AVFS Parameters!", return result;);
+
+ table->CurrSclkPllRange = 0xff;
table->GraphicsVoltageChangeEnable = 1;
table->GraphicsThermThrottleEnable = 1;
table->GraphicsInterval = 1;
@@ -2184,6 +2182,7 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr)
CONVERT_FROM_HOST_TO_SMC_UL(table->SmioMask1);
CONVERT_FROM_HOST_TO_SMC_UL(table->SmioMask2);
CONVERT_FROM_HOST_TO_SMC_UL(table->SclkStepSize);
+ CONVERT_FROM_HOST_TO_SMC_UL(table->CurrSclkPllRange);
CONVERT_FROM_HOST_TO_SMC_US(table->TemperatureLimitHigh);
CONVERT_FROM_HOST_TO_SMC_US(table->TemperatureLimitLow);
CONVERT_FROM_HOST_TO_SMC_US(table->VoltageResponseTime);
@@ -2286,6 +2285,9 @@ static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
{
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+ uint32_t soft_register_value = 0;
+ uint32_t handshake_disables_offset = data->soft_regs_start
+ + offsetof(SMU74_SoftRegisters, HandshakeDisables);
/* enable SCLK dpm */
if (!data->sclk_dpm_key_disabled)
@@ -2296,6 +2298,12 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
/* enable MCLK dpm */
if (0 == data->mclk_dpm_key_disabled) {
+/* Disable UVD - SMU handshake for MCLK. */
+ soft_register_value = cgs_read_ind_register(hwmgr->device,
+ CGS_IND_REG__SMC, handshake_disables_offset);
+ soft_register_value |= SMU7_UVD_MCLK_HANDSHAKE_DISABLE;
+ cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+ handshake_disables_offset, soft_register_value);
PP_ASSERT_WITH_CODE(
(0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -2303,7 +2311,6 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
"Failed to enable MCLK DPM during DPM Start Function!",
return -1);
-
PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x5);
@@ -2505,6 +2512,8 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
PP_ASSERT_WITH_CODE((0 == tmp_result),
"Failed to enable VR hot GPIO interrupt!", result = tmp_result);
+ smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay);
+
tmp_result = polaris10_enable_sclk_control(hwmgr);
PP_ASSERT_WITH_CODE((0 == tmp_result),
"Failed to enable SCLK control!", result = tmp_result);
@@ -2640,6 +2649,7 @@ int polaris10_set_features_platform_caps(struct pp_hwmgr *hwmgr)
phm_cap_set(hwmgr->platform_descriptor.platformCaps,
PHM_PlatformCaps_FanSpeedInTableIsRPM);
+
if (hwmgr->chip_id == CHIP_POLARIS11)
phm_cap_set(hwmgr->platform_descriptor.platformCaps,
PHM_PlatformCaps_SPLLShutdownSupport);
@@ -2672,7 +2682,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
{
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
uint16_t vv_id;
- uint16_t vddc = 0;
+ uint32_t vddc = 0;
uint16_t i, j;
uint32_t sclk = 0;
struct phm_ppt_v1_information *table_info =
@@ -2703,8 +2713,9 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
continue);
- /* need to make sure vddc is less than 2v or else, it could burn the ASIC. */
- PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0),
+ /* need to make sure vddc is less than 2v or else, it could burn the ASIC.
+ * real voltage level in unit of 0.01mv */
+ PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0),
"Invalid VDDC value", result = -EINVAL;);
/* the voltage should not be zero nor equal to leakage ID */
@@ -2930,6 +2941,31 @@ static int polaris10_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr)
return 0;
}
+int polaris10_patch_voltage_workaround(struct pp_hwmgr *hwmgr)
+{
+ struct phm_ppt_v1_information *table_info =
+ (struct phm_ppt_v1_information *)(hwmgr->pptable);
+ struct phm_ppt_v1_clock_voltage_dependency_table *dep_mclk_table =
+ table_info->vdd_dep_on_mclk;
+ struct phm_ppt_v1_voltage_lookup_table *lookup_table =
+ table_info->vddc_lookup_table;
+ uint32_t i;
+
+ if (hwmgr->chip_id == CHIP_POLARIS10 && hwmgr->hw_revision == 0xC7) {
+ if (lookup_table->entries[dep_mclk_table->entries[dep_mclk_table->count-1].vddInd].us_vdd >= 1000)
+ return 0;
+
+ for (i = 0; i < lookup_table->count; i++) {
+ if (lookup_table->entries[i].us_vdd < 0xff01 && lookup_table->entries[i].us_vdd >= 1000) {
+ dep_mclk_table->entries[dep_mclk_table->count-1].vddInd = (uint8_t) i;
+ return 0;
+ }
+ }
+ }
+ return 0;
+}
+
+
int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
{
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -2972,6 +3008,11 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
data->vddci_control = POLARIS10_VOLTAGE_CONTROL_NONE;
data->mvdd_control = POLARIS10_VOLTAGE_CONTROL_NONE;
+ data->enable_tdc_limit_feature = true;
+ data->enable_pkg_pwr_tracking_feature = true;
+ data->force_pcie_gen = PP_PCIEGenInvalid;
+ data->mclk_stutter_mode_threshold = 40000;
+
if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
data->voltage_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2;
@@ -2996,8 +3037,13 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
data->vddci_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2;
}
+ if (table_info->cac_dtp_table->usClockStretchAmount != 0)
+ phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+ PHM_PlatformCaps_ClockStretcher);
+
polaris10_set_features_platform_caps(hwmgr);
+ polaris10_patch_voltage_workaround(hwmgr);
polaris10_init_dpm_defaults(hwmgr);
/* Get leakage voltage based on leakage ID. */
@@ -3554,10 +3600,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
ATOM_Tonga_State *state_entry = (ATOM_Tonga_State *)state;
ATOM_Tonga_POWERPLAYTABLE *powerplay_table =
(ATOM_Tonga_POWERPLAYTABLE *)pp_table;
- ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table =
- (ATOM_Tonga_SCLK_Dependency_Table *)
+ PPTable_Generic_SubTable_Header *sclk_dep_table =
+ (PPTable_Generic_SubTable_Header *)
(((unsigned long)powerplay_table) +
le16_to_cpu(powerplay_table->usSclkDependencyTableOffset));
+
ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table =
(ATOM_Tonga_MCLK_Dependency_Table *)
(((unsigned long)powerplay_table) +
@@ -3609,7 +3656,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
/* Performance levels are arranged from low to high. */
performance_level->memory_clock = mclk_dep_table->entries
[state_entry->ucMemoryClockIndexLow].ulMclk;
- performance_level->engine_clock = sclk_dep_table->entries
+ if (sclk_dep_table->ucRevId == 0)
+ performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries
+ [state_entry->ucEngineClockIndexLow].ulSclk;
+ else if (sclk_dep_table->ucRevId == 1)
+ performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries
[state_entry->ucEngineClockIndexLow].ulSclk;
performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
state_entry->ucPCIEGenLow);
@@ -3620,8 +3671,14 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
[polaris10_power_state->performance_level_count++]);
performance_level->memory_clock = mclk_dep_table->entries
[state_entry->ucMemoryClockIndexHigh].ulMclk;
- performance_level->engine_clock = sclk_dep_table->entries
+
+ if (sclk_dep_table->ucRevId == 0)
+ performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries
+ [state_entry->ucEngineClockIndexHigh].ulSclk;
+ else if (sclk_dep_table->ucRevId == 1)
+ performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries
[state_entry->ucEngineClockIndexHigh].ulSclk;
+
performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
state_entry->ucPCIEGenHigh);
performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap,
@@ -3679,7 +3736,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr,
switch (state->classification.ui_label) {
case PP_StateUILabel_Performance:
data->use_pcie_performance_levels = true;
-
for (i = 0; i < ps->performance_level_count; i++) {
if (data->pcie_gen_performance.max <
ps->performance_levels[i].pcie_gen)
@@ -3695,7 +3751,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr,
ps->performance_levels[i].pcie_lane)
data->pcie_lane_performance.max =
ps->performance_levels[i].pcie_lane;
-
if (data->pcie_lane_performance.min >
ps->performance_levels[i].pcie_lane)
data->pcie_lane_performance.min =
@@ -4221,12 +4276,9 @@ int polaris10_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate)
{
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
uint32_t mm_boot_level_offset, mm_boot_level_value;
- struct phm_ppt_v1_information *table_info =
- (struct phm_ppt_v1_information *)(hwmgr->pptable);
if (!bgate) {
- data->smc_state_table.SamuBootLevel =
- (uint8_t) (table_info->mm_dep_table->count - 1);
+ data->smc_state_table.SamuBootLevel = 0;
mm_boot_level_offset = data->dpm_table_start +
offsetof(SMU74_Discrete_DpmTable, SamuBootLevel);
mm_boot_level_offset /= 4;
@@ -4361,6 +4413,15 @@ static int polaris10_notify_link_speed_change_after_state_change(
return 0;
}
+static int polaris10_notify_smc_display(struct pp_hwmgr *hwmgr)
+{
+ struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+
+ smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+ (PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2);
+ return (smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ? 0 : -EINVAL;
+}
+
static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input)
{
int tmp_result, result = 0;
@@ -4409,6 +4470,11 @@ static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *i
"Failed to program memory timing parameters!",
result = tmp_result);
+ tmp_result = polaris10_notify_smc_display(hwmgr);
+ PP_ASSERT_WITH_CODE((0 == tmp_result),
+ "Failed to notify smc display settings!",
+ result = tmp_result);
+
tmp_result = polaris10_unfreeze_sclk_mclk_dpm(hwmgr);
PP_ASSERT_WITH_CODE((0 == tmp_result),
"Failed to unfreeze SCLK MCLK DPM!",
@@ -4443,6 +4509,7 @@ static int polaris10_set_max_fan_pwm_output(struct pp_hwmgr *hwmgr, uint16_t us_
PPSMC_MSG_SetFanPwmMax, us_max_fan_pwm);
}
+
int polaris10_notify_smc_display_change(struct pp_hwmgr *hwmgr, bool has_display)
{
PPSMC_Msg msg = has_display ? (PPSMC_Msg)PPSMC_HasDisplay : (PPSMC_Msg)PPSMC_NoDisplay;
@@ -4462,8 +4529,6 @@ int polaris10_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwm
if (num_active_displays > 1) /* to do && (pHwMgr->pPECI->displayConfiguration.bMultiMonitorInSync != TRUE)) */
polaris10_notify_smc_display_change(hwmgr, false);
- else
- polaris10_notify_smc_display_change(hwmgr, true);
return 0;
}
@@ -4504,6 +4569,8 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr)
frame_time_in_us = 1000000 / refresh_rate;
pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us;
+ data->frame_time_x2 = frame_time_in_us * 2 / 100;
+
display_gap2 = pre_vbi_time_in_us * (ref_clock / 100);
cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL2, display_gap2);
@@ -4512,8 +4579,6 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr)
cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + offsetof(SMU74_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us));
- polaris10_notify_smc_display_change(hwmgr, num_active_displays != 0);
-
return 0;
}
@@ -4625,7 +4690,7 @@ int polaris10_upload_mc_firmware(struct pp_hwmgr *hwmgr)
return 0;
}
- data->need_long_memory_training = true;
+ data->need_long_memory_training = false;
/*
* PPMCME_FirmwareDescriptorEntry *pfd = NULL;
@@ -4760,11 +4825,11 @@ static int polaris10_get_pp_table(struct pp_hwmgr *hwmgr, char **table)
struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
if (!data->soft_pp_table) {
- data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
+ data->soft_pp_table = kmemdup(hwmgr->soft_pp_table,
+ hwmgr->soft_pp_table_size,
+ GFP_KERNEL);
if (!data->soft_pp_table)
return -ENOMEM;
- memcpy(data->soft_pp_table, hwmgr->soft_pp_table,
- hwmgr->soft_pp_table_size);
}
*table = (char *)&data->soft_pp_table;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
index beedf35cbfa6..afc3434822d1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
@@ -312,6 +312,10 @@ struct polaris10_hwmgr {
/* soft pptable for re-uploading into smu */
void *soft_pp_table;
+
+ uint32_t avfs_vdroop_override_setting;
+ bool apply_avfs_cks_off_voltage;
+ uint32_t frame_time_x2;
};
/* To convert to Q8.8 format for firmware */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
index 0b99ab3ba0c5..ae96f14b827c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
@@ -286,7 +286,7 @@ int polaris10_populate_pm_fuses(struct pp_hwmgr *hwmgr)
if (polaris10_copy_bytes_to_smc(hwmgr->smumgr, pm_fuse_table_offset,
(uint8_t *)&data->power_tune_table,
- sizeof(struct SMU74_Discrete_PmFuses), data->sram_end))
+ (sizeof(struct SMU74_Discrete_PmFuses) - 92), data->sram_end))
PP_ASSERT_WITH_CODE(false,
"Attempt to download PmFuseTable Failed!",
return -EINVAL);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
index aba167f7d167..b206632d4650 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
@@ -625,10 +625,14 @@ static int tf_polaris10_thermal_avfs_enable(struct pp_hwmgr *hwmgr,
int ret;
struct pp_smumgr *smumgr = (struct pp_smumgr *)(hwmgr->smumgr);
struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend);
+ struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
- if (smu_data->avfs.avfs_btc_status != AVFS_BTC_ENABLEAVFS)
+ if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED)
return 0;
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+ PPSMC_MSG_SetGBDroopSettings, data->avfs_vdroop_override_setting);
+
ret = (smum_send_msg_to_smc(smumgr, PPSMC_MSG_EnableAvfs) == 0) ?
0 : -1;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
index 58742e0d1492..a3c38bbd1e94 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
@@ -44,6 +44,20 @@ bool acpi_atcs_functions_supported(void *device, uint32_t index)
return result == 0 ? (output_buf.function_bits & (1 << (index - 1))) != 0 : false;
}
+bool acpi_atcs_notify_pcie_device_ready(void *device)
+{
+ int32_t temp_buffer = 1;
+
+ return cgs_call_acpi_method(device, CGS_ACPI_METHOD_ATCS,
+ ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION,
+ &temp_buffer,
+ NULL,
+ 0,
+ sizeof(temp_buffer),
+ 0);
+}
+
+
int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
{
struct atcs_pref_req_input atcs_input;
@@ -52,7 +66,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
int result;
struct cgs_system_info info = {0};
- if (!acpi_atcs_functions_supported(device, ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST))
+ if( 0 != acpi_atcs_notify_pcie_device_ready(device))
return -EINVAL;
info.size = sizeof(struct cgs_system_info);
@@ -77,7 +91,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST,
&atcs_input,
&atcs_output,
- 0,
+ 1,
sizeof(atcs_input),
sizeof(atcs_output));
if (result != 0)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index da9f5f1b6dc2..90b35c5c10a4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1256,7 +1256,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
}
int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
- uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage)
+ uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage)
{
int result;
@@ -1274,7 +1274,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
if (0 != result)
return result;
- *voltage = get_voltage_info_param_space.usVoltageLevel;
+ *voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel;
return result;
}
@@ -1302,3 +1302,46 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr
return 0;
}
+
+int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param)
+{
+ ATOM_ASIC_PROFILING_INFO_V3_6 *profile = NULL;
+
+ if (param == NULL)
+ return -EINVAL;
+
+ profile = (ATOM_ASIC_PROFILING_INFO_V3_6 *)
+ cgs_atom_get_data_table(hwmgr->device,
+ GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo),
+ NULL, NULL, NULL);
+ if (!profile)
+ return -1;
+
+ param->ulAVFS_meanNsigma_Acontant0 = profile->ulAVFS_meanNsigma_Acontant0;
+ param->ulAVFS_meanNsigma_Acontant1 = profile->ulAVFS_meanNsigma_Acontant1;
+ param->ulAVFS_meanNsigma_Acontant2 = profile->ulAVFS_meanNsigma_Acontant2;
+ param->usAVFS_meanNsigma_DC_tol_sigma = profile->usAVFS_meanNsigma_DC_tol_sigma;
+ param->usAVFS_meanNsigma_Platform_mean = profile->usAVFS_meanNsigma_Platform_mean;
+ param->usAVFS_meanNsigma_Platform_sigma = profile->usAVFS_meanNsigma_Platform_sigma;
+ param->ulGB_VDROOP_TABLE_CKSOFF_a0 = profile->ulGB_VDROOP_TABLE_CKSOFF_a0;
+ param->ulGB_VDROOP_TABLE_CKSOFF_a1 = profile->ulGB_VDROOP_TABLE_CKSOFF_a1;
+ param->ulGB_VDROOP_TABLE_CKSOFF_a2 = profile->ulGB_VDROOP_TABLE_CKSOFF_a2;
+ param->ulGB_VDROOP_TABLE_CKSON_a0 = profile->ulGB_VDROOP_TABLE_CKSON_a0;
+ param->ulGB_VDROOP_TABLE_CKSON_a1 = profile->ulGB_VDROOP_TABLE_CKSON_a1;
+ param->ulGB_VDROOP_TABLE_CKSON_a2 = profile->ulGB_VDROOP_TABLE_CKSON_a2;
+ param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+ param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+ param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+ param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSON_m1;
+ param->usAVFSGB_FUSE_TABLE_CKSON_m2 = profile->usAVFSGB_FUSE_TABLE_CKSON_m2;
+ param->ulAVFSGB_FUSE_TABLE_CKSON_b = profile->ulAVFSGB_FUSE_TABLE_CKSON_b;
+ param->usMaxVoltage_0_25mv = profile->usMaxVoltage_0_25mv;
+ param->ucEnableGB_VDROOP_TABLE_CKSOFF = profile->ucEnableGB_VDROOP_TABLE_CKSOFF;
+ param->ucEnableGB_VDROOP_TABLE_CKSON = profile->ucEnableGB_VDROOP_TABLE_CKSON;
+ param->ucEnableGB_FUSE_TABLE_CKSOFF = profile->ucEnableGB_FUSE_TABLE_CKSOFF;
+ param->ucEnableGB_FUSE_TABLE_CKSON = profile->ucEnableGB_FUSE_TABLE_CKSON;
+ param->usPSM_Age_ComFactor = profile->usPSM_Age_ComFactor;
+ param->ucEnableApplyAVFS_CKS_OFF_Voltage = profile->ucEnableApplyAVFS_CKS_OFF_Voltage;
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
index d24ebb566905..1e35a9625baf 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
@@ -250,6 +250,35 @@ struct pp_atomctrl_gpio_pin_assignment {
};
typedef struct pp_atomctrl_gpio_pin_assignment pp_atomctrl_gpio_pin_assignment;
+struct pp_atom_ctrl__avfs_parameters {
+ uint32_t ulAVFS_meanNsigma_Acontant0;
+ uint32_t ulAVFS_meanNsigma_Acontant1;
+ uint32_t ulAVFS_meanNsigma_Acontant2;
+ uint16_t usAVFS_meanNsigma_DC_tol_sigma;
+ uint16_t usAVFS_meanNsigma_Platform_mean;
+ uint16_t usAVFS_meanNsigma_Platform_sigma;
+ uint32_t ulGB_VDROOP_TABLE_CKSOFF_a0;
+ uint32_t ulGB_VDROOP_TABLE_CKSOFF_a1;
+ uint32_t ulGB_VDROOP_TABLE_CKSOFF_a2;
+ uint32_t ulGB_VDROOP_TABLE_CKSON_a0;
+ uint32_t ulGB_VDROOP_TABLE_CKSON_a1;
+ uint32_t ulGB_VDROOP_TABLE_CKSON_a2;
+ uint32_t ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+ uint16_t usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+ uint32_t ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+ uint32_t ulAVFSGB_FUSE_TABLE_CKSON_m1;
+ uint16_t usAVFSGB_FUSE_TABLE_CKSON_m2;
+ uint32_t ulAVFSGB_FUSE_TABLE_CKSON_b;
+ uint16_t usMaxVoltage_0_25mv;
+ uint8_t ucEnableGB_VDROOP_TABLE_CKSOFF;
+ uint8_t ucEnableGB_VDROOP_TABLE_CKSON;
+ uint8_t ucEnableGB_FUSE_TABLE_CKSOFF;
+ uint8_t ucEnableGB_FUSE_TABLE_CKSON;
+ uint16_t usPSM_Age_ComFactor;
+ uint8_t ucEnableApplyAVFS_CKS_OFF_Voltage;
+ uint8_t ucReserved;
+};
+
extern bool atomctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment);
extern int atomctrl_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
extern uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr);
@@ -276,7 +305,10 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t
extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
uint8_t level);
extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
- uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
+ uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage);
extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table);
+
+extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param);
+
#endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 1faad92b50d3..5d0f655bf160 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -1302,7 +1302,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
table->Smio[count] |=
data->mvdd_voltage_table.entries[count].smio_low;
}
- table->SmioMask2 = data->vddci_voltage_table.mask_low;
+ table->SmioMask2 = data->mvdd_voltage_table.mask_low;
CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount);
}
@@ -2847,27 +2847,6 @@ static int tonga_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
}
}
- /* Initialize Vddc DPM table based on allow Vddc values. And populate corresponding std values. */
- for (i = 0; i < allowed_vdd_sclk_table->count; i++) {
- data->dpm_table.vddc_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddc;
- /* tonga_hwmgr->dpm_table.VddcTable.dpm_levels[i].param1 = stdVoltageTable->entries[i].Leakage; */
- /* param1 is for corresponding std voltage */
- data->dpm_table.vddc_table.dpm_levels[i].enabled = 1;
- }
- data->dpm_table.vddc_table.count = allowed_vdd_sclk_table->count;
-
- if (NULL != allowed_vdd_mclk_table) {
- /* Initialize Vddci DPM table based on allow Mclk values */
- for (i = 0; i < allowed_vdd_mclk_table->count; i++) {
- data->dpm_table.vdd_ci_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddci;
- data->dpm_table.vdd_ci_table.dpm_levels[i].enabled = 1;
- data->dpm_table.mvdd_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].mvdd;
- data->dpm_table.mvdd_table.dpm_levels[i].enabled = 1;
- }
- data->dpm_table.vdd_ci_table.count = allowed_vdd_mclk_table->count;
- data->dpm_table.mvdd_table.count = allowed_vdd_mclk_table->count;
- }
-
/* setup PCIE gen speed levels*/
tonga_setup_default_pcie_tables(hwmgr);
@@ -4510,6 +4489,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
data->vdd_ci_control = TONGA_VOLTAGE_CONTROL_NONE;
data->vdd_gfx_control = TONGA_VOLTAGE_CONTROL_NONE;
data->mvdd_control = TONGA_VOLTAGE_CONTROL_NONE;
+ data->force_pcie_gen = PP_PCIEGenInvalid;
if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) {
@@ -5331,7 +5311,7 @@ static int tonga_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
(data->need_update_smu7_dpm_table &
(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
PP_ASSERT_WITH_CODE(
- true == tonga_is_dpm_running(hwmgr),
+ 0 == tonga_is_dpm_running(hwmgr),
"Trying to freeze SCLK DPM when DPM is disabled",
);
PP_ASSERT_WITH_CODE(
@@ -5344,7 +5324,7 @@ static int tonga_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
if ((0 == data->mclk_dpm_key_disabled) &&
(data->need_update_smu7_dpm_table &
DPMTABLE_OD_UPDATE_MCLK)) {
- PP_ASSERT_WITH_CODE(true == tonga_is_dpm_running(hwmgr),
+ PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
"Trying to freeze MCLK DPM when DPM is disabled",
);
PP_ASSERT_WITH_CODE(
@@ -5445,7 +5425,7 @@ static int tonga_populate_and_upload_sclk_mclk_dpm_levels(struct pp_hwmgr *hwmgr
}
if (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK)) {
- result = tonga_populate_all_memory_levels(hwmgr);
+ result = tonga_populate_all_graphic_levels(hwmgr);
PP_ASSERT_WITH_CODE((0 == result),
"Failed to populate SCLK during PopulateNewDPMClocksStates Function!",
return result);
@@ -5647,7 +5627,7 @@ static int tonga_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
(data->need_update_smu7_dpm_table &
(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
- PP_ASSERT_WITH_CODE(true == tonga_is_dpm_running(hwmgr),
+ PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
"Trying to Unfreeze SCLK DPM when DPM is disabled",
);
PP_ASSERT_WITH_CODE(
@@ -5661,7 +5641,7 @@ static int tonga_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
(data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) {
PP_ASSERT_WITH_CODE(
- true == tonga_is_dpm_running(hwmgr),
+ 0 == tonga_is_dpm_running(hwmgr),
"Trying to Unfreeze MCLK DPM when DPM is disabled",
);
PP_ASSERT_WITH_CODE(
@@ -6056,11 +6036,11 @@ static int tonga_get_pp_table(struct pp_hwmgr *hwmgr, char **table)
struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
if (!data->soft_pp_table) {
- data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
+ data->soft_pp_table = kmemdup(hwmgr->soft_pp_table,
+ hwmgr->soft_pp_table_size,
+ GFP_KERNEL);
if (!data->soft_pp_table)
return -ENOMEM;
- memcpy(data->soft_pp_table, hwmgr->soft_pp_table,
- hwmgr->soft_pp_table_size);
}
*table = (char *)&data->soft_pp_table;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h
index 1b44f4e9b8f5..f127198aafc4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h
@@ -197,6 +197,22 @@ typedef struct _ATOM_Tonga_SCLK_Dependency_Table {
ATOM_Tonga_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */
} ATOM_Tonga_SCLK_Dependency_Table;
+typedef struct _ATOM_Polaris_SCLK_Dependency_Record {
+ UCHAR ucVddInd; /* Base voltage */
+ USHORT usVddcOffset; /* Offset relative to base voltage */
+ ULONG ulSclk;
+ USHORT usEdcCurrent;
+ UCHAR ucReliabilityTemperature;
+ UCHAR ucCKSVOffsetandDisable; /* Bits 0~6: Voltage offset for CKS, Bit 7: Disable/enable for the SCLK level. */
+ ULONG ulSclkOffset;
+} ATOM_Polaris_SCLK_Dependency_Record;
+
+typedef struct _ATOM_Polaris_SCLK_Dependency_Table {
+ UCHAR ucRevId;
+ UCHAR ucNumEntries; /* Number of entries. */
+ ATOM_Polaris_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */
+} ATOM_Polaris_SCLK_Dependency_Table;
+
typedef struct _ATOM_Tonga_PCIE_Record {
UCHAR ucPCIEGenSpeed;
UCHAR usPCIELaneWidth;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
index 10e3630ee39d..dccc859f638c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
@@ -302,7 +302,7 @@ static int init_dpm_2_parameters(
(((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset));
if (0 != powerplay_table->usPPMTableOffset) {
- if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) {
+ if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) {
phm_cap_set(hwmgr->platform_descriptor.platformCaps,
PHM_PlatformCaps_EnablePlatformPowerManagement);
}
@@ -408,41 +408,78 @@ static int get_mclk_voltage_dependency_table(
static int get_sclk_voltage_dependency_table(
struct pp_hwmgr *hwmgr,
phm_ppt_v1_clock_voltage_dependency_table **pp_tonga_sclk_dep_table,
- const ATOM_Tonga_SCLK_Dependency_Table * sclk_dep_table
+ const PPTable_Generic_SubTable_Header *sclk_dep_table
)
{
uint32_t table_size, i;
phm_ppt_v1_clock_voltage_dependency_table *sclk_table;
- PP_ASSERT_WITH_CODE((0 != sclk_dep_table->ucNumEntries),
- "Invalid PowerPlay Table!", return -1);
+ if (sclk_dep_table->ucRevId < 1) {
+ const ATOM_Tonga_SCLK_Dependency_Table *tonga_table =
+ (ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table;
- table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
- * sclk_dep_table->ucNumEntries;
+ PP_ASSERT_WITH_CODE((0 != tonga_table->ucNumEntries),
+ "Invalid PowerPlay Table!", return -1);
- sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
- kzalloc(table_size, GFP_KERNEL);
+ table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
+ * tonga_table->ucNumEntries;
- if (NULL == sclk_table)
- return -ENOMEM;
+ sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
+ kzalloc(table_size, GFP_KERNEL);
- memset(sclk_table, 0x00, table_size);
-
- sclk_table->count = (uint32_t)sclk_dep_table->ucNumEntries;
-
- for (i = 0; i < sclk_dep_table->ucNumEntries; i++) {
- sclk_table->entries[i].vddInd =
- sclk_dep_table->entries[i].ucVddInd;
- sclk_table->entries[i].vdd_offset =
- sclk_dep_table->entries[i].usVddcOffset;
- sclk_table->entries[i].clk =
- sclk_dep_table->entries[i].ulSclk;
- sclk_table->entries[i].cks_enable =
- (((sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0;
- sclk_table->entries[i].cks_voffset =
- (sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x7F);
- }
+ if (NULL == sclk_table)
+ return -ENOMEM;
+
+ memset(sclk_table, 0x00, table_size);
+
+ sclk_table->count = (uint32_t)tonga_table->ucNumEntries;
+
+ for (i = 0; i < tonga_table->ucNumEntries; i++) {
+ sclk_table->entries[i].vddInd =
+ tonga_table->entries[i].ucVddInd;
+ sclk_table->entries[i].vdd_offset =
+ tonga_table->entries[i].usVddcOffset;
+ sclk_table->entries[i].clk =
+ tonga_table->entries[i].ulSclk;
+ sclk_table->entries[i].cks_enable =
+ (((tonga_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0;
+ sclk_table->entries[i].cks_voffset =
+ (tonga_table->entries[i].ucCKSVOffsetandDisable & 0x7F);
+ }
+ } else {
+ const ATOM_Polaris_SCLK_Dependency_Table *polaris_table =
+ (ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table;
+
+ PP_ASSERT_WITH_CODE((0 != polaris_table->ucNumEntries),
+ "Invalid PowerPlay Table!", return -1);
+
+ table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
+ * polaris_table->ucNumEntries;
+
+ sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
+ kzalloc(table_size, GFP_KERNEL);
+ if (NULL == sclk_table)
+ return -ENOMEM;
+
+ memset(sclk_table, 0x00, table_size);
+
+ sclk_table->count = (uint32_t)polaris_table->ucNumEntries;
+
+ for (i = 0; i < polaris_table->ucNumEntries; i++) {
+ sclk_table->entries[i].vddInd =
+ polaris_table->entries[i].ucVddInd;
+ sclk_table->entries[i].vdd_offset =
+ polaris_table->entries[i].usVddcOffset;
+ sclk_table->entries[i].clk =
+ polaris_table->entries[i].ulSclk;
+ sclk_table->entries[i].cks_enable =
+ (((polaris_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0;
+ sclk_table->entries[i].cks_voffset =
+ (polaris_table->entries[i].ucCKSVOffsetandDisable & 0x7F);
+ sclk_table->entries[i].sclk_offset = polaris_table->entries[i].ulSclkOffset;
+ }
+ }
*pp_tonga_sclk_dep_table = sclk_table;
return 0;
@@ -708,8 +745,8 @@ static int init_clock_voltage_dependency(
const ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table =
(const ATOM_Tonga_MCLK_Dependency_Table *)(((unsigned long) powerplay_table) +
le16_to_cpu(powerplay_table->usMclkDependencyTableOffset));
- const ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table =
- (const ATOM_Tonga_SCLK_Dependency_Table *)(((unsigned long) powerplay_table) +
+ const PPTable_Generic_SubTable_Header *sclk_dep_table =
+ (const PPTable_Generic_SubTable_Header *)(((unsigned long) powerplay_table) +
le16_to_cpu(powerplay_table->usSclkDependencyTableOffset));
const ATOM_Tonga_Hard_Limit_Table *pHardLimits =
(const ATOM_Tonga_Hard_Limit_Table *)(((unsigned long) powerplay_table) +
@@ -1040,48 +1077,44 @@ int tonga_pp_tables_uninitialize(struct pp_hwmgr *hwmgr)
struct phm_ppt_v1_information *pp_table_information =
(struct phm_ppt_v1_information *)(hwmgr->pptable);
- if (NULL != hwmgr->soft_pp_table) {
- kfree(hwmgr->soft_pp_table);
+ if (NULL != hwmgr->soft_pp_table)
hwmgr->soft_pp_table = NULL;
- }
- if (NULL != pp_table_information->vdd_dep_on_sclk)
- pp_table_information->vdd_dep_on_sclk = NULL;
+ kfree(pp_table_information->vdd_dep_on_sclk);
+ pp_table_information->vdd_dep_on_sclk = NULL;
- if (NULL != pp_table_information->vdd_dep_on_mclk)
- pp_table_information->vdd_dep_on_mclk = NULL;
+ kfree(pp_table_information->vdd_dep_on_mclk);
+ pp_table_information->vdd_dep_on_mclk = NULL;
- if (NULL != pp_table_information->valid_mclk_values)
- pp_table_information->valid_mclk_values = NULL;
+ kfree(pp_table_information->valid_mclk_values);
+ pp_table_information->valid_mclk_values = NULL;
- if (NULL != pp_table_information->valid_sclk_values)
- pp_table_information->valid_sclk_values = NULL;
+ kfree(pp_table_information->valid_sclk_values);
+ pp_table_information->valid_sclk_values = NULL;
- if (NULL != pp_table_information->vddc_lookup_table)
- pp_table_information->vddc_lookup_table = NULL;
+ kfree(pp_table_information->vddc_lookup_table);
+ pp_table_information->vddc_lookup_table = NULL;
- if (NULL != pp_table_information->vddgfx_lookup_table)
- pp_table_information->vddgfx_lookup_table = NULL;
+ kfree(pp_table_information->vddgfx_lookup_table);
+ pp_table_information->vddgfx_lookup_table = NULL;
- if (NULL != pp_table_information->mm_dep_table)
- pp_table_information->mm_dep_table = NULL;
+ kfree(pp_table_information->mm_dep_table);
+ pp_table_information->mm_dep_table = NULL;
- if (NULL != pp_table_information->cac_dtp_table)
- pp_table_information->cac_dtp_table = NULL;
+ kfree(pp_table_information->cac_dtp_table);
+ pp_table_information->cac_dtp_table = NULL;
- if (NULL != hwmgr->dyn_state.cac_dtp_table)
- hwmgr->dyn_state.cac_dtp_table = NULL;
+ kfree(hwmgr->dyn_state.cac_dtp_table);
+ hwmgr->dyn_state.cac_dtp_table = NULL;
- if (NULL != pp_table_information->ppm_parameter_table)
- pp_table_information->ppm_parameter_table = NULL;
+ kfree(pp_table_information->ppm_parameter_table);
+ pp_table_information->ppm_parameter_table = NULL;
- if (NULL != pp_table_information->pcie_table)
- pp_table_information->pcie_table = NULL;
+ kfree(pp_table_information->pcie_table);
+ pp_table_information->pcie_table = NULL;
- if (NULL != hwmgr->pptable) {
- kfree(hwmgr->pptable);
- hwmgr->pptable = NULL;
- }
+ kfree(hwmgr->pptable);
+ hwmgr->pptable = NULL;
return result;
}
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index fd4ce7aaeee9..77e8e33d5870 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -411,6 +411,8 @@ struct phm_cac_tdp_table {
uint8_t ucVr_I2C_Line;
uint8_t ucPlx_I2C_address;
uint8_t ucPlx_I2C_Line;
+ uint32_t usBoostPowerLimit;
+ uint8_t ucCKS_LDO_REFSEL;
};
struct phm_ppm_table {
@@ -673,7 +675,7 @@ extern int phm_get_sclk_for_voltage_evv(struct pp_hwmgr *hwmgr, phm_ppt_v1_volta
extern int phm_initializa_dynamic_state_adjustment_rule_settings(struct pp_hwmgr *hwmgr);
extern int phm_hwmgr_backend_fini(struct pp_hwmgr *hwmgr);
extern uint32_t phm_get_lowest_enabled_level(struct pp_hwmgr *hwmgr, uint32_t mask);
-
+extern void phm_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr);
#define PHM_ENTIRE_REGISTER_MASK 0xFFFFFFFFU
diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
index 0c6a413eaa5b..b8f4b73c322e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
@@ -27,6 +27,7 @@
#pragma pack(push, 1)
+#define PPSMC_MSG_SetGBDroopSettings ((uint16_t) 0x305)
#define PPSMC_SWSTATE_FLAG_DC 0x01
#define PPSMC_SWSTATE_FLAG_UVD 0x02
@@ -391,6 +392,8 @@ typedef uint16_t PPSMC_Result;
#define PPSMC_MSG_SetGpuPllDfsForSclk ((uint16_t) 0x300)
#define PPSMC_MSG_Didt_Block_Function ((uint16_t) 0x301)
+#define PPSMC_MSG_SetVBITimeout ((uint16_t) 0x306)
+
#define PPSMC_MSG_SecureSRBMWrite ((uint16_t) 0x600)
#define PPSMC_MSG_SecureSRBMRead ((uint16_t) 0x601)
#define PPSMC_MSG_SetAddress ((uint16_t) 0x800)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
index 3bd5e69b9045..3df5de2cdab0 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
@@ -26,3 +26,4 @@ extern bool acpi_atcs_functions_supported(void *device,
extern int acpi_pcie_perf_request(void *device,
uint8_t perf_req,
bool advertise);
+extern bool acpi_atcs_notify_pcie_device_ready(void *device);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74.h b/drivers/gpu/drm/amd/powerplay/inc/smu74.h
index 1a12d85b8e97..fd10a9fa843d 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74.h
@@ -34,6 +34,30 @@
#define SMU__NUM_LCLK_DPM_LEVELS 8
#define SMU__NUM_PCIE_DPM_LEVELS 8
+#define EXP_M1 35
+#define EXP_M2 92821
+#define EXP_B 66629747
+
+#define EXP_M1_1 365
+#define EXP_M2_1 658700
+#define EXP_B_1 305506134
+
+#define EXP_M1_2 189
+#define EXP_M2_2 379692
+#define EXP_B_2 194609469
+
+#define EXP_M1_3 99
+#define EXP_M2_3 217915
+#define EXP_B_3 122255994
+
+#define EXP_M1_4 51
+#define EXP_M2_4 122643
+#define EXP_B_4 74893384
+
+#define EXP_M1_5 423
+#define EXP_M2_5 1103326
+#define EXP_B_5 728122621
+
enum SID_OPTION {
SID_OPTION_HI,
SID_OPTION_LO,
@@ -548,20 +572,20 @@ struct SMU74_Firmware_Header {
uint32_t CacConfigTable;
uint32_t CacStatusTable;
-
uint32_t mcRegisterTable;
-
uint32_t mcArbDramTimingTable;
-
-
-
uint32_t PmFuseTable;
uint32_t Globals;
uint32_t ClockStretcherTable;
uint32_t VftTable;
- uint32_t Reserved[21];
+ uint32_t Reserved1;
+ uint32_t AvfsTable;
+ uint32_t AvfsCksOffGbvTable;
+ uint32_t AvfsMeanNSigma;
+ uint32_t AvfsSclkOffsetTable;
+ uint32_t Reserved[16];
uint32_t Signature;
};
@@ -701,8 +725,6 @@ VR Config info is contained in dpmTable.VRConfig */
struct SMU_ClockStretcherDataTableEntry {
uint8_t minVID;
uint8_t maxVID;
-
-
uint16_t setting;
};
typedef struct SMU_ClockStretcherDataTableEntry SMU_ClockStretcherDataTableEntry;
@@ -769,6 +791,43 @@ struct VFT_TABLE_t {
typedef struct VFT_TABLE_t VFT_TABLE_t;
+/* Total margin, root mean square of Fmax + DC + Platform */
+struct AVFS_Margin_t {
+ VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_Margin_t AVFS_Margin_t;
+
+#define BTCGB_VDROOP_TABLE_MAX_ENTRIES 2
+#define AVFSGB_VDROOP_TABLE_MAX_ENTRIES 2
+
+struct GB_VDROOP_TABLE_t {
+ int32_t a0;
+ int32_t a1;
+ int32_t a2;
+ uint32_t spare;
+};
+typedef struct GB_VDROOP_TABLE_t GB_VDROOP_TABLE_t;
+
+struct AVFS_CksOff_Gbv_t {
+ VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_CksOff_Gbv_t AVFS_CksOff_Gbv_t;
+
+struct AVFS_meanNsigma_t {
+ uint32_t Aconstant[3];
+ uint16_t DC_tol_sigma;
+ uint16_t Platform_mean;
+ uint16_t Platform_sigma;
+ uint16_t PSM_Age_CompFactor;
+ uint8_t Static_Voltage_Offset[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_meanNsigma_t AVFS_meanNsigma_t;
+
+struct AVFS_Sclk_Offset_t {
+ uint16_t Sclk_Offset[8];
+};
+typedef struct AVFS_Sclk_Offset_t AVFS_Sclk_Offset_t;
+
#endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
index 0dfe82336dc7..899d6d8108c2 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
@@ -223,6 +223,16 @@ struct SMU74_Discrete_StateInfo {
typedef struct SMU74_Discrete_StateInfo SMU74_Discrete_StateInfo;
+struct SMU_QuadraticCoeffs {
+ int32_t m1;
+ uint32_t b;
+
+ int16_t m2;
+ uint8_t m1_shift;
+ uint8_t m2_shift;
+};
+typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
+
struct SMU74_Discrete_DpmTable {
SMU74_PIDController GraphicsPIDController;
@@ -258,7 +268,15 @@ struct SMU74_Discrete_DpmTable {
uint8_t ThermOutPolarity;
uint8_t ThermOutMode;
uint8_t BootPhases;
- uint32_t Reserved[4];
+
+ uint8_t VRHotLevel;
+ uint8_t LdoRefSel;
+ uint8_t Reserved1[2];
+ uint16_t FanStartTemperature;
+ uint16_t FanStopTemperature;
+ uint16_t MaxVoltage;
+ uint16_t Reserved2;
+ uint32_t Reserved[1];
SMU74_Discrete_GraphicsLevel GraphicsLevel[SMU74_MAX_LEVELS_GRAPHICS];
SMU74_Discrete_MemoryLevel MemoryACPILevel;
@@ -347,6 +365,8 @@ struct SMU74_Discrete_DpmTable {
uint32_t CurrSclkPllRange;
sclkFcwRange_t SclkFcwRangeTable[NUM_SCLK_RANGE];
+ GB_VDROOP_TABLE_t BTCGB_VDROOP_TABLE[BTCGB_VDROOP_TABLE_MAX_ENTRIES];
+ SMU_QuadraticCoeffs AVFSGB_VDROOP_TABLE[AVFSGB_VDROOP_TABLE_MAX_ENTRIES];
};
typedef struct SMU74_Discrete_DpmTable SMU74_Discrete_DpmTable;
@@ -550,16 +570,6 @@ struct SMU7_AcpiScoreboard {
typedef struct SMU7_AcpiScoreboard SMU7_AcpiScoreboard;
-struct SMU_QuadraticCoeffs {
- int32_t m1;
- uint32_t b;
-
- int16_t m2;
- uint8_t m1_shift;
- uint8_t m2_shift;
-};
-typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
-
struct SMU74_Discrete_PmFuses {
uint8_t BapmVddCVidHiSidd[8];
uint8_t BapmVddCVidLoSidd[8];
@@ -821,6 +831,17 @@ typedef struct SMU7_GfxCuPgScoreboard SMU7_GfxCuPgScoreboard;
#define DB_PCC_SHIFT 26
#define DB_EDC_SHIFT 27
+#define BTCGB0_Vdroop_Enable_MASK 0x1
+#define BTCGB1_Vdroop_Enable_MASK 0x2
+#define AVFSGB0_Vdroop_Enable_MASK 0x4
+#define AVFSGB1_Vdroop_Enable_MASK 0x8
+
+#define BTCGB0_Vdroop_Enable_SHIFT 0
+#define BTCGB1_Vdroop_Enable_SHIFT 1
+#define AVFSGB0_Vdroop_Enable_SHIFT 2
+#define AVFSGB1_Vdroop_Enable_SHIFT 3
+
+
#pragma pack(pop)
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c
index da18f44fd1c8..87c023e518ab 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c
@@ -639,7 +639,7 @@ static int cz_smu_populate_firmware_entries(struct pp_smumgr *smumgr)
cz_smu->driver_buffer_length = 0;
- for (i = 0; i < sizeof(firmware_list)/sizeof(*firmware_list); i++) {
+ for (i = 0; i < ARRAY_SIZE(firmware_list); i++) {
firmware_type = cz_translate_firmware_enum_to_arg(smumgr,
firmware_list[i]);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index 673a75c74e18..8e52a2e82db5 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -1006,10 +1006,16 @@ static int fiji_smu_init(struct pp_smumgr *smumgr)
static int fiji_smu_fini(struct pp_smumgr *smumgr)
{
+ struct fiji_smumgr *priv = (struct fiji_smumgr *)(smumgr->backend);
+
+ smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle);
+
if (smumgr->backend) {
kfree(smumgr->backend);
smumgr->backend = NULL;
}
+
+ cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
return 0;
}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index de618ead9db8..5dba7c509710 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -52,19 +52,18 @@
static const SMU74_Discrete_GraphicsLevel avfs_graphics_level_polaris10[8] = {
/* Min pcie DeepSleep Activity CgSpll CgSpll CcPwr CcPwr Sclk Enabled Enabled Voltage Power */
/* Voltage, DpmLevel, DivId, Level, FuncCntl3, FuncCntl4, DynRm, DynRm1 Did, Padding,ForActivity, ForThrottle, UpHyst, DownHyst, DownHyst, Throttle */
- { 0x3c0fd047, 0x00, 0x03, 0x1e00, 0x00200410, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x30750000, 0, 0, 0, 0, 0, 0, 0 } },
- { 0xa00fd047, 0x01, 0x04, 0x1e00, 0x00800510, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x409c0000, 0, 0, 0, 0, 0, 0, 0 } },
- { 0x0410d047, 0x01, 0x00, 0x1e00, 0x00600410, 0x87020000, 0, 0, 0x0e, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x50c30000, 0, 0, 0, 0, 0, 0, 0 } },
- { 0x6810d047, 0x01, 0x00, 0x1e00, 0x00800410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x60ea0000, 0, 0, 0, 0, 0, 0, 0 } },
- { 0xcc10d047, 0x01, 0x00, 0x1e00, 0x00e00410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xe8fd0000, 0, 0, 0, 0, 0, 0, 0 } },
- { 0x3011d047, 0x01, 0x00, 0x1e00, 0x00400510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x70110100, 0, 0, 0, 0, 0, 0, 0 } },
- { 0x9411d047, 0x01, 0x00, 0x1e00, 0x00a00510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xf8240100, 0, 0, 0, 0, 0, 0, 0 } },
- { 0xf811d047, 0x01, 0x00, 0x1e00, 0x00000610, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x80380100, 0, 0, 0, 0, 0, 0, 0 } }
+ { 0x100ea446, 0x00, 0x03, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x30750000, 0x3000, 0, 0x2600, 0, 0, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } },
+ { 0x400ea446, 0x01, 0x04, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x409c0000, 0x2000, 0, 0x1e00, 1, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } },
+ { 0x740ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x50c30000, 0x2800, 0, 0x2000, 1, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } },
+ { 0xa40ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x60ea0000, 0x3000, 0, 0x2600, 1, 1, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } },
+ { 0xd80ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x70110100, 0x3800, 0, 0x2c00, 1, 1, 0x0004, 0x1203, 0xffff, 0x3600, 0xc9e2, 0x2e00 } },
+ { 0x3c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x80380100, 0x2000, 0, 0x1e00, 2, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } },
+ { 0x6c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x905f0100, 0x2400, 0, 0x1e00, 2, 1, 0x0004, 0x8901, 0xffff, 0x2300, 0x314c, 0x1d00 } },
+ { 0xa00fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0xa0860100, 0x2800, 0, 0x2000, 2, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } }
};
static const SMU74_Discrete_MemoryLevel avfs_memory_level_polaris10 =
- {0x50140000, 0x50140000, 0x00320000, 0x00, 0x00,
- 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x0000, 0x00, 0x00};
+ {0x100ea446, 0, 0x30750000, 0x01, 0x01, 0x01, 0x00, 0x00, 0x64, 0x00, 0x00, 0x1f00, 0x00, 0x00};
/**
* Set the address for reading/writing the SMC SRAM space.
@@ -219,6 +218,18 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr)
&& (0x20100 <= cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMC_PC_C)));
}
+static bool polaris10_is_hw_avfs_present(struct pp_smumgr *smumgr)
+{
+ uint32_t efuse;
+
+ efuse = cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMU_EFUSE_0 + (49*4));
+ efuse &= 0x00000001;
+ if (efuse)
+ return true;
+
+ return false;
+}
+
/**
* Send a message to the SMC, and wait for its response.
*
@@ -228,21 +239,27 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr)
*/
int polaris10_send_msg_to_smc(struct pp_smumgr *smumgr, uint16_t msg)
{
+ int ret;
+
if (!polaris10_is_smc_ram_running(smumgr))
return -1;
+
SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0);
- if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP))
- printk("Failed to send Previous Message.\n");
+ ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP);
+ if (ret != 1)
+ printk("\n failed to send pre message %x ret is %d \n", msg, ret);
cgs_write_register(smumgr->device, mmSMC_MESSAGE_0, msg);
SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0);
- if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP))
- printk("Failed to send Message.\n");
+ ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP);
+
+ if (ret != 1)
+ printk("\n failed to send message %x ret is %d \n", msg, ret);
return 0;
}
@@ -469,6 +486,7 @@ int polaris10_smu_fini(struct pp_smumgr *smumgr)
kfree(smumgr->backend);
smumgr->backend = NULL;
}
+ cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
return 0;
}
@@ -952,6 +970,11 @@ static int polaris10_smu_init(struct pp_smumgr *smumgr)
(cgs_handle_t)smu_data->smu_buffer.handle);
return -1;);
+ if (polaris10_is_hw_avfs_present(smumgr))
+ smu_data->avfs.avfs_btc_status = AVFS_BTC_BOOT;
+ else
+ smu_data->avfs.avfs_btc_status = AVFS_BTC_NOTSUPPORTED;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c483baf6b4fb..0728c1e3d97a 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -81,6 +81,7 @@ int smum_init(struct amd_pp_init *pp_init, struct pp_instance *handle)
int smum_fini(struct pp_smumgr *smumgr)
{
+ kfree(smumgr->device);
kfree(smumgr);
return 0;
}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index 32820b680d88..b22722eabafc 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -328,10 +328,17 @@ int tonga_write_smc_sram_dword(struct pp_smumgr *smumgr,
static int tonga_smu_fini(struct pp_smumgr *smumgr)
{
+ struct tonga_smumgr *priv = (struct tonga_smumgr *)(smumgr->backend);
+
+ smu_free_memory(smumgr->device, (void *)priv->smu_buffer.handle);
+ smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle);
+
if (smumgr->backend != NULL) {
kfree(smumgr->backend);
smumgr->backend = NULL;
}
+
+ cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
return 0;
}
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index fef1b04c2aab..0813c2f06931 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -33,8 +33,17 @@
*
*/
+static void hdlcd_crtc_cleanup(struct drm_crtc *crtc)
+{
+ struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
+
+ /* stop the controller on cleanup */
+ hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0);
+ drm_crtc_cleanup(crtc);
+}
+
static const struct drm_crtc_funcs hdlcd_crtc_funcs = {
- .destroy = drm_crtc_cleanup,
+ .destroy = hdlcd_crtc_cleanup,
.set_config = drm_atomic_helper_set_config,
.page_flip = drm_atomic_helper_page_flip,
.reset = drm_atomic_helper_crtc_reset,
@@ -97,7 +106,7 @@ static void hdlcd_crtc_mode_set_nofb(struct drm_crtc *crtc)
struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
struct drm_display_mode *m = &crtc->state->adjusted_mode;
struct videomode vm;
- unsigned int polarities, line_length, err;
+ unsigned int polarities, err;
vm.vfront_porch = m->crtc_vsync_start - m->crtc_vdisplay;
vm.vback_porch = m->crtc_vtotal - m->crtc_vsync_end;
@@ -113,23 +122,18 @@ static void hdlcd_crtc_mode_set_nofb(struct drm_crtc *crtc)
if (m->flags & DRM_MODE_FLAG_PVSYNC)
polarities |= HDLCD_POLARITY_VSYNC;
- line_length = crtc->primary->state->fb->pitches[0];
-
/* Allow max number of outstanding requests and largest burst size */
hdlcd_write(hdlcd, HDLCD_REG_BUS_OPTIONS,
HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
- hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, line_length);
- hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, line_length);
- hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, m->crtc_vdisplay - 1);
hdlcd_write(hdlcd, HDLCD_REG_V_DATA, m->crtc_vdisplay - 1);
hdlcd_write(hdlcd, HDLCD_REG_V_BACK_PORCH, vm.vback_porch - 1);
hdlcd_write(hdlcd, HDLCD_REG_V_FRONT_PORCH, vm.vfront_porch - 1);
hdlcd_write(hdlcd, HDLCD_REG_V_SYNC, vm.vsync_len - 1);
+ hdlcd_write(hdlcd, HDLCD_REG_H_DATA, m->crtc_hdisplay - 1);
hdlcd_write(hdlcd, HDLCD_REG_H_BACK_PORCH, vm.hback_porch - 1);
hdlcd_write(hdlcd, HDLCD_REG_H_FRONT_PORCH, vm.hfront_porch - 1);
hdlcd_write(hdlcd, HDLCD_REG_H_SYNC, vm.hsync_len - 1);
- hdlcd_write(hdlcd, HDLCD_REG_H_DATA, m->crtc_hdisplay - 1);
hdlcd_write(hdlcd, HDLCD_REG_POLARITIES, polarities);
err = hdlcd_set_pxl_fmt(crtc);
@@ -144,20 +148,19 @@ static void hdlcd_crtc_enable(struct drm_crtc *crtc)
struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
clk_prepare_enable(hdlcd->clk);
+ hdlcd_crtc_mode_set_nofb(crtc);
hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 1);
- drm_crtc_vblank_on(crtc);
}
static void hdlcd_crtc_disable(struct drm_crtc *crtc)
{
struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
- if (!crtc->primary->fb)
+ if (!crtc->state->active)
return;
- clk_disable_unprepare(hdlcd->clk);
hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0);
- drm_crtc_vblank_off(crtc);
+ clk_disable_unprepare(hdlcd->clk);
}
static int hdlcd_crtc_atomic_check(struct drm_crtc *crtc,
@@ -179,20 +182,17 @@ static int hdlcd_crtc_atomic_check(struct drm_crtc *crtc,
static void hdlcd_crtc_atomic_begin(struct drm_crtc *crtc,
struct drm_crtc_state *state)
{
- struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
- unsigned long flags;
-
- if (crtc->state->event) {
- struct drm_pending_vblank_event *event = crtc->state->event;
+ struct drm_pending_vblank_event *event = crtc->state->event;
+ if (event) {
crtc->state->event = NULL;
- event->pipe = drm_crtc_index(crtc);
-
- WARN_ON(drm_crtc_vblank_get(crtc) != 0);
- spin_lock_irqsave(&crtc->dev->event_lock, flags);
- list_add_tail(&event->base.link, &hdlcd->event_list);
- spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+ spin_lock_irq(&crtc->dev->event_lock);
+ if (drm_crtc_vblank_get(crtc) == 0)
+ drm_crtc_arm_vblank_event(crtc, event);
+ else
+ drm_crtc_send_vblank_event(crtc, event);
+ spin_unlock_irq(&crtc->dev->event_lock);
}
}
@@ -225,6 +225,15 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = {
static int hdlcd_plane_atomic_check(struct drm_plane *plane,
struct drm_plane_state *state)
{
+ u32 src_w, src_h;
+
+ src_w = state->src_w >> 16;
+ src_h = state->src_h >> 16;
+
+ /* we can't do any scaling of the plane source */
+ if ((src_w != state->crtc_w) || (src_h != state->crtc_h))
+ return -EINVAL;
+
return 0;
}
@@ -233,20 +242,31 @@ static void hdlcd_plane_atomic_update(struct drm_plane *plane,
{
struct hdlcd_drm_private *hdlcd;
struct drm_gem_cma_object *gem;
+ unsigned int depth, bpp;
+ u32 src_w, src_h, dest_w, dest_h;
dma_addr_t scanout_start;
- if (!plane->state->crtc || !plane->state->fb)
+ if (!plane->state->fb)
return;
- hdlcd = crtc_to_hdlcd_priv(plane->state->crtc);
+ drm_fb_get_bpp_depth(plane->state->fb->pixel_format, &depth, &bpp);
+ src_w = plane->state->src_w >> 16;
+ src_h = plane->state->src_h >> 16;
+ dest_w = plane->state->crtc_w;
+ dest_h = plane->state->crtc_h;
gem = drm_fb_cma_get_gem_obj(plane->state->fb, 0);
- scanout_start = gem->paddr;
+ scanout_start = gem->paddr + plane->state->fb->offsets[0] +
+ plane->state->crtc_y * plane->state->fb->pitches[0] +
+ plane->state->crtc_x * bpp / 8;
+
+ hdlcd = plane->dev->dev_private;
+ hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, plane->state->fb->pitches[0]);
+ hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, plane->state->fb->pitches[0]);
+ hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, dest_h - 1);
hdlcd_write(hdlcd, HDLCD_REG_FB_BASE, scanout_start);
}
static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
- .prepare_fb = NULL,
- .cleanup_fb = NULL,
.atomic_check = hdlcd_plane_atomic_check,
.atomic_update = hdlcd_plane_atomic_update,
};
@@ -294,16 +314,6 @@ static struct drm_plane *hdlcd_plane_init(struct drm_device *drm)
return plane;
}
-void hdlcd_crtc_suspend(struct drm_crtc *crtc)
-{
- hdlcd_crtc_disable(crtc);
-}
-
-void hdlcd_crtc_resume(struct drm_crtc *crtc)
-{
- hdlcd_crtc_enable(crtc);
-}
-
int hdlcd_setup_crtc(struct drm_device *drm)
{
struct hdlcd_drm_private *hdlcd = drm->dev_private;
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index b987c63ba8d6..a6ca36f0096f 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -49,8 +49,6 @@ static int hdlcd_load(struct drm_device *drm, unsigned long flags)
atomic_set(&hdlcd->dma_end_count, 0);
#endif
- INIT_LIST_HEAD(&hdlcd->event_list);
-
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
hdlcd->mmio = devm_ioremap_resource(drm->dev, res);
if (IS_ERR(hdlcd->mmio)) {
@@ -84,11 +82,7 @@ static int hdlcd_load(struct drm_device *drm, unsigned long flags)
goto setup_fail;
}
- pm_runtime_enable(drm->dev);
-
- pm_runtime_get_sync(drm->dev);
ret = drm_irq_install(drm, platform_get_irq(pdev, 0));
- pm_runtime_put_sync(drm->dev);
if (ret < 0) {
DRM_ERROR("failed to install IRQ handler\n");
goto irq_fail;
@@ -164,24 +158,9 @@ static irqreturn_t hdlcd_irq(int irq, void *arg)
atomic_inc(&hdlcd->vsync_count);
#endif
- if (irq_status & HDLCD_INTERRUPT_VSYNC) {
- bool events_sent = false;
- unsigned long flags;
- struct drm_pending_vblank_event *e, *t;
-
+ if (irq_status & HDLCD_INTERRUPT_VSYNC)
drm_crtc_handle_vblank(&hdlcd->crtc);
- spin_lock_irqsave(&drm->event_lock, flags);
- list_for_each_entry_safe(e, t, &hdlcd->event_list, base.link) {
- list_del(&e->base.link);
- drm_crtc_send_vblank_event(&hdlcd->crtc, e);
- events_sent = true;
- }
- if (events_sent)
- drm_crtc_vblank_put(&hdlcd->crtc);
- spin_unlock_irqrestore(&drm->event_lock, flags);
- }
-
/* acknowledge interrupt(s) */
hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, irq_status);
@@ -275,6 +254,7 @@ static int hdlcd_show_pxlclock(struct seq_file *m, void *arg)
static struct drm_info_list hdlcd_debugfs_list[] = {
{ "interrupt_count", hdlcd_show_underrun_count, 0 },
{ "clocks", hdlcd_show_pxlclock, 0 },
+ { "fb", drm_fb_cma_debugfs_show, 0 },
};
static int hdlcd_debugfs_init(struct drm_minor *minor)
@@ -357,6 +337,8 @@ static int hdlcd_drm_bind(struct device *dev)
return -ENOMEM;
drm->dev_private = hdlcd;
+ dev_set_drvdata(dev, drm);
+
hdlcd_setup_mode_config(drm);
ret = hdlcd_load(drm, 0);
if (ret)
@@ -366,14 +348,18 @@ static int hdlcd_drm_bind(struct device *dev)
if (ret)
goto err_unload;
- dev_set_drvdata(dev, drm);
-
ret = component_bind_all(dev, drm);
if (ret) {
DRM_ERROR("Failed to bind all components\n");
goto err_unregister;
}
+ ret = pm_runtime_set_active(dev);
+ if (ret)
+ goto err_pm_active;
+
+ pm_runtime_enable(dev);
+
ret = drm_vblank_init(drm, drm->mode_config.num_crtc);
if (ret < 0) {
DRM_ERROR("failed to initialise vblank\n");
@@ -399,16 +385,16 @@ err_fbdev:
drm_mode_config_cleanup(drm);
drm_vblank_cleanup(drm);
err_vblank:
+ pm_runtime_disable(drm->dev);
+err_pm_active:
component_unbind_all(dev, drm);
err_unregister:
drm_dev_unregister(drm);
err_unload:
- pm_runtime_get_sync(drm->dev);
drm_irq_uninstall(drm);
- pm_runtime_put_sync(drm->dev);
- pm_runtime_disable(drm->dev);
of_reserved_mem_device_release(drm->dev);
err_free:
+ dev_set_drvdata(dev, NULL);
drm_dev_unref(drm);
return ret;
@@ -495,30 +481,34 @@ MODULE_DEVICE_TABLE(of, hdlcd_of_match);
static int __maybe_unused hdlcd_pm_suspend(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
- struct drm_crtc *crtc;
+ struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
- if (pm_runtime_suspended(dev))
+ if (!hdlcd)
return 0;
- drm_modeset_lock_all(drm);
- list_for_each_entry(crtc, &drm->mode_config.crtc_list, head)
- hdlcd_crtc_suspend(crtc);
- drm_modeset_unlock_all(drm);
+ drm_kms_helper_poll_disable(drm);
+
+ hdlcd->state = drm_atomic_helper_suspend(drm);
+ if (IS_ERR(hdlcd->state)) {
+ drm_kms_helper_poll_enable(drm);
+ return PTR_ERR(hdlcd->state);
+ }
+
return 0;
}
static int __maybe_unused hdlcd_pm_resume(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
- struct drm_crtc *crtc;
+ struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
- if (!pm_runtime_suspended(dev))
+ if (!hdlcd)
return 0;
- drm_modeset_lock_all(drm);
- list_for_each_entry(crtc, &drm->mode_config.crtc_list, head)
- hdlcd_crtc_resume(crtc);
- drm_modeset_unlock_all(drm);
+ drm_atomic_helper_resume(drm, hdlcd->state);
+ drm_kms_helper_poll_enable(drm);
+ pm_runtime_set_active(dev);
+
return 0;
}
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index aa234784f053..e3950a071152 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -9,10 +9,9 @@ struct hdlcd_drm_private {
void __iomem *mmio;
struct clk *clk;
struct drm_fbdev_cma *fbdev;
- struct drm_framebuffer *fb;
- struct list_head event_list;
struct drm_crtc crtc;
struct drm_plane *plane;
+ struct drm_atomic_state *state;
#ifdef CONFIG_DEBUG_FS
atomic_t buffer_underrun_count;
atomic_t bus_error_count;
@@ -36,7 +35,5 @@ static inline u32 hdlcd_read(struct hdlcd_drm_private *hdlcd, unsigned int reg)
int hdlcd_setup_crtc(struct drm_device *dev);
void hdlcd_set_scanout(struct hdlcd_drm_private *hdlcd);
-void hdlcd_crtc_suspend(struct drm_crtc *crtc);
-void hdlcd_crtc_resume(struct drm_crtc *crtc);
#endif /* __HDLCD_DRV_H__ */
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index cf23a755f777..bd12231ab0cd 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -391,12 +391,11 @@ void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
{
struct atmel_hlcdc_crtc_state *state;
- if (crtc->state && crtc->state->mode_blob)
- drm_property_unreference_blob(crtc->state->mode_blob);
-
if (crtc->state) {
+ __drm_atomic_helper_crtc_destroy_state(crtc->state);
state = drm_crtc_state_to_atmel_hlcdc_crtc_state(crtc->state);
kfree(state);
+ crtc->state = NULL;
}
state = kzalloc(sizeof(*state), GFP_KERNEL);
@@ -415,8 +414,9 @@ atmel_hlcdc_crtc_duplicate_state(struct drm_crtc *crtc)
return NULL;
state = kmalloc(sizeof(*state), GFP_KERNEL);
- if (state)
- __drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
+ if (!state)
+ return NULL;
+ __drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
cur = drm_crtc_state_to_atmel_hlcdc_crtc_state(crtc->state);
state->output_mode = cur->output_mode;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
index 39802c0539b6..3d34fc4ca826 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
@@ -266,9 +266,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev)
if (!ret)
ret = atmel_hlcdc_check_endpoint(dev, &ep);
- of_node_put(ep_np);
- if (ret)
+ if (ret) {
+ of_node_put(ep_np);
return ret;
+ }
}
for_each_endpoint_of_node(dev->dev->of_node, ep_np) {
@@ -276,9 +277,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev)
if (!ret)
ret = atmel_hlcdc_attach_endpoint(dev, &ep);
- of_node_put(ep_np);
- if (ret)
+ if (ret) {
+ of_node_put(ep_np);
return ret;
+ }
}
return 0;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index aef3ca8a81fa..016c191221f3 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -339,6 +339,8 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane,
atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff,
factor_reg);
+ } else {
+ atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0);
}
}
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 3ff1ed7b33db..9bb99e274d23 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -351,6 +351,8 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
drm_property_unreference_blob(state->mode_blob);
state->mode_blob = NULL;
+ memset(&state->mode, 0, sizeof(state->mode));
+
if (blob) {
if (blob->length != sizeof(struct drm_mode_modeinfo) ||
drm_mode_convert_umode(&state->mode,
@@ -363,7 +365,6 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
state->mode.name, state);
} else {
- memset(&state->mode, 0, sizeof(state->mode));
state->enable = false;
DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
state);
@@ -1295,14 +1296,39 @@ EXPORT_SYMBOL(drm_atomic_add_affected_planes);
*/
void drm_atomic_legacy_backoff(struct drm_atomic_state *state)
{
+ struct drm_device *dev = state->dev;
+ unsigned crtc_mask = 0;
+ struct drm_crtc *crtc;
int ret;
+ bool global = false;
+
+ drm_for_each_crtc(crtc, dev) {
+ if (crtc->acquire_ctx != state->acquire_ctx)
+ continue;
+
+ crtc_mask |= drm_crtc_mask(crtc);
+ crtc->acquire_ctx = NULL;
+ }
+
+ if (WARN_ON(dev->mode_config.acquire_ctx == state->acquire_ctx)) {
+ global = true;
+
+ dev->mode_config.acquire_ctx = NULL;
+ }
retry:
drm_modeset_backoff(state->acquire_ctx);
- ret = drm_modeset_lock_all_ctx(state->dev, state->acquire_ctx);
+ ret = drm_modeset_lock_all_ctx(dev, state->acquire_ctx);
if (ret)
goto retry;
+
+ drm_for_each_crtc(crtc, dev)
+ if (drm_crtc_mask(crtc) & crtc_mask)
+ crtc->acquire_ctx = state->acquire_ctx;
+
+ if (global)
+ dev->mode_config.acquire_ctx = state->acquire_ctx;
}
EXPORT_SYMBOL(drm_atomic_legacy_backoff);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d2a6d958ca76..0e3cc66aa8b7 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2821,8 +2821,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
goto out;
}
- drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
-
/*
* Check whether the primary plane supports the fb pixel format.
* Drivers not implementing the universal planes API use a
@@ -4841,7 +4839,8 @@ bool drm_property_change_valid_get(struct drm_property *property,
if (value == 0)
return true;
- return _object_find(property->dev, value, property->values[0]) != NULL;
+ *ref = _object_find(property->dev, value, property->values[0]);
+ return *ref != NULL;
}
for (i = 0; i < property->num_values; i++)
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index a6e42433ef0e..26feb2f8453f 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -528,11 +528,11 @@ drm_crtc_helper_disable(struct drm_crtc *crtc)
int drm_crtc_helper_set_config(struct drm_mode_set *set)
{
struct drm_device *dev;
- struct drm_crtc *new_crtc;
- struct drm_encoder *save_encoders, *new_encoder, *encoder;
+ struct drm_crtc **save_encoder_crtcs, *new_crtc;
+ struct drm_encoder **save_connector_encoders, *new_encoder, *encoder;
bool mode_changed = false; /* if true do a full mode set */
bool fb_changed = false; /* if true and !mode_changed just do a flip */
- struct drm_connector *save_connectors, *connector;
+ struct drm_connector *connector;
int count = 0, ro, fail = 0;
const struct drm_crtc_helper_funcs *crtc_funcs;
struct drm_mode_set save_set;
@@ -574,15 +574,15 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
* Allocate space for the backup of all (non-pointer) encoder and
* connector data.
*/
- save_encoders = kzalloc(dev->mode_config.num_encoder *
- sizeof(struct drm_encoder), GFP_KERNEL);
- if (!save_encoders)
+ save_encoder_crtcs = kzalloc(dev->mode_config.num_encoder *
+ sizeof(struct drm_crtc *), GFP_KERNEL);
+ if (!save_encoder_crtcs)
return -ENOMEM;
- save_connectors = kzalloc(dev->mode_config.num_connector *
- sizeof(struct drm_connector), GFP_KERNEL);
- if (!save_connectors) {
- kfree(save_encoders);
+ save_connector_encoders = kzalloc(dev->mode_config.num_connector *
+ sizeof(struct drm_encoder *), GFP_KERNEL);
+ if (!save_connector_encoders) {
+ kfree(save_encoder_crtcs);
return -ENOMEM;
}
@@ -593,12 +593,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
*/
count = 0;
drm_for_each_encoder(encoder, dev) {
- save_encoders[count++] = *encoder;
+ save_encoder_crtcs[count++] = encoder->crtc;
}
count = 0;
drm_for_each_connector(connector, dev) {
- save_connectors[count++] = *connector;
+ save_connector_encoders[count++] = connector->encoder;
}
save_set.crtc = set->crtc;
@@ -631,8 +631,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
mode_changed = true;
}
- /* take a reference on all connectors in set */
+ /* take a reference on all unbound connectors in set, reuse the
+ * already taken reference for bound connectors
+ */
for (ro = 0; ro < set->num_connectors; ro++) {
+ if (set->connectors[ro]->encoder)
+ continue;
drm_connector_reference(set->connectors[ro]);
}
@@ -754,30 +758,28 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
}
}
- /* after fail drop reference on all connectors in save set */
- count = 0;
- drm_for_each_connector(connector, dev) {
- drm_connector_unreference(&save_connectors[count++]);
- }
-
- kfree(save_connectors);
- kfree(save_encoders);
+ kfree(save_connector_encoders);
+ kfree(save_encoder_crtcs);
return 0;
fail:
/* Restore all previous data. */
count = 0;
drm_for_each_encoder(encoder, dev) {
- *encoder = save_encoders[count++];
+ encoder->crtc = save_encoder_crtcs[count++];
}
count = 0;
drm_for_each_connector(connector, dev) {
- *connector = save_connectors[count++];
+ connector->encoder = save_connector_encoders[count++];
}
- /* after fail drop reference on all connectors in set */
+ /* after fail drop reference on all unbound connectors in set, let
+ * bound connectors keep their reference
+ */
for (ro = 0; ro < set->num_connectors; ro++) {
+ if (set->connectors[ro]->encoder)
+ continue;
drm_connector_unreference(set->connectors[ro]);
}
@@ -787,8 +789,8 @@ fail:
save_set.y, save_set.fb))
DRM_ERROR("failed to restore config after modeset failure\n");
- kfree(save_connectors);
- kfree(save_encoders);
+ kfree(save_connector_encoders);
+ kfree(save_encoder_crtcs);
return ret;
}
EXPORT_SYMBOL(drm_crtc_helper_set_config);
diff --git a/drivers/gpu/drm/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/drm_dp_dual_mode_helper.c
new file mode 100644
index 000000000000..a7b2a751f6fe
--- /dev/null
+++ b/drivers/gpu/drm/drm_dp_dual_mode_helper.c
@@ -0,0 +1,366 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <drm/drm_dp_dual_mode_helper.h>
+#include <drm/drmP.h>
+
+/**
+ * DOC: dp dual mode helpers
+ *
+ * Helper functions to deal with DP dual mode (aka. DP++) adaptors.
+ *
+ * Type 1:
+ * Adaptor registers (if any) and the sink DDC bus may be accessed via I2C.
+ *
+ * Type 2:
+ * Adaptor registers and sink DDC bus can be accessed either via I2C or
+ * I2C-over-AUX. Source devices may choose to implement either of these
+ * access methods.
+ */
+
+#define DP_DUAL_MODE_SLAVE_ADDRESS 0x40
+
+/**
+ * drm_dp_dual_mode_read - Read from the DP dual mode adaptor register(s)
+ * @adapter: I2C adapter for the DDC bus
+ * @offset: register offset
+ * @buffer: buffer for return data
+ * @size: sizo of the buffer
+ *
+ * Reads @size bytes from the DP dual mode adaptor registers
+ * starting at @offset.
+ *
+ * Returns:
+ * 0 on success, negative error code on failure
+ */
+ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter,
+ u8 offset, void *buffer, size_t size)
+{
+ struct i2c_msg msgs[] = {
+ {
+ .addr = DP_DUAL_MODE_SLAVE_ADDRESS,
+ .flags = 0,
+ .len = 1,
+ .buf = &offset,
+ },
+ {
+ .addr = DP_DUAL_MODE_SLAVE_ADDRESS,
+ .flags = I2C_M_RD,
+ .len = size,
+ .buf = buffer,
+ },
+ };
+ int ret;
+
+ ret = i2c_transfer(adapter, msgs, ARRAY_SIZE(msgs));
+ if (ret < 0)
+ return ret;
+ if (ret != ARRAY_SIZE(msgs))
+ return -EPROTO;
+
+ return 0;
+}
+EXPORT_SYMBOL(drm_dp_dual_mode_read);
+
+/**
+ * drm_dp_dual_mode_write - Write to the DP dual mode adaptor register(s)
+ * @adapter: I2C adapter for the DDC bus
+ * @offset: register offset
+ * @buffer: buffer for write data
+ * @size: sizo of the buffer
+ *
+ * Writes @size bytes to the DP dual mode adaptor registers
+ * starting at @offset.
+ *
+ * Returns:
+ * 0 on success, negative error code on failure
+ */
+ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter,
+ u8 offset, const void *buffer, size_t size)
+{
+ struct i2c_msg msg = {
+ .addr = DP_DUAL_MODE_SLAVE_ADDRESS,
+ .flags = 0,
+ .len = 1 + size,
+ .buf = NULL,
+ };
+ void *data;
+ int ret;
+
+ data = kmalloc(msg.len, GFP_TEMPORARY);
+ if (!data)
+ return -ENOMEM;
+
+ msg.buf = data;
+
+ memcpy(data, &offset, 1);
+ memcpy(data + 1, buffer, size);
+
+ ret = i2c_transfer(adapter, &msg, 1);
+
+ kfree(data);
+
+ if (ret < 0)
+ return ret;
+ if (ret != 1)
+ return -EPROTO;
+
+ return 0;
+}
+EXPORT_SYMBOL(drm_dp_dual_mode_write);
+
+static bool is_hdmi_adaptor(const char hdmi_id[DP_DUAL_MODE_HDMI_ID_LEN])
+{
+ static const char dp_dual_mode_hdmi_id[DP_DUAL_MODE_HDMI_ID_LEN] =
+ "DP-HDMI ADAPTOR\x04";
+
+ return memcmp(hdmi_id, dp_dual_mode_hdmi_id,
+ sizeof(dp_dual_mode_hdmi_id)) == 0;
+}
+
+static bool is_type2_adaptor(uint8_t adaptor_id)
+{
+ return adaptor_id == (DP_DUAL_MODE_TYPE_TYPE2 |
+ DP_DUAL_MODE_REV_TYPE2);
+}
+
+/**
+ * drm_dp_dual_mode_detect - Identify the DP dual mode adaptor
+ * @adapter: I2C adapter for the DDC bus
+ *
+ * Attempt to identify the type of the DP dual mode adaptor used.
+ *
+ * Note that when the answer is @DRM_DP_DUAL_MODE_UNKNOWN it's not
+ * certain whether we're dealing with a native HDMI port or
+ * a type 1 DVI dual mode adaptor. The driver will have to use
+ * some other hardware/driver specific mechanism to make that
+ * distinction.
+ *
+ * Returns:
+ * The type of the DP dual mode adaptor used
+ */
+enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(struct i2c_adapter *adapter)
+{
+ char hdmi_id[DP_DUAL_MODE_HDMI_ID_LEN] = {};
+ uint8_t adaptor_id = 0x00;
+ ssize_t ret;
+
+ /*
+ * Let's see if the adaptor is there the by reading the
+ * HDMI ID registers.
+ *
+ * Note that type 1 DVI adaptors are not required to implemnt
+ * any registers, and that presents a problem for detection.
+ * If the i2c transfer is nacked, we may or may not be dealing
+ * with a type 1 DVI adaptor. Some other mechanism of detecting
+ * the presence of the adaptor is required. One way would be
+ * to check the state of the CONFIG1 pin, Another method would
+ * simply require the driver to know whether the port is a DP++
+ * port or a native HDMI port. Both of these methods are entirely
+ * hardware/driver specific so we can't deal with them here.
+ */
+ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_HDMI_ID,
+ hdmi_id, sizeof(hdmi_id));
+ if (ret)
+ return DRM_DP_DUAL_MODE_UNKNOWN;
+
+ /*
+ * Sigh. Some (maybe all?) type 1 adaptors are broken and ack
+ * the offset but ignore it, and instead they just always return
+ * data from the start of the HDMI ID buffer. So for a broken
+ * type 1 HDMI adaptor a single byte read will always give us
+ * 0x44, and for a type 1 DVI adaptor it should give 0x00
+ * (assuming it implements any registers). Fortunately neither
+ * of those values will match the type 2 signature of the
+ * DP_DUAL_MODE_ADAPTOR_ID register so we can proceed with
+ * the type 2 adaptor detection safely even in the presence
+ * of broken type 1 adaptors.
+ */
+ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_ADAPTOR_ID,
+ &adaptor_id, sizeof(adaptor_id));
+ if (ret == 0) {
+ if (is_type2_adaptor(adaptor_id)) {
+ if (is_hdmi_adaptor(hdmi_id))
+ return DRM_DP_DUAL_MODE_TYPE2_HDMI;
+ else
+ return DRM_DP_DUAL_MODE_TYPE2_DVI;
+ }
+ }
+
+ if (is_hdmi_adaptor(hdmi_id))
+ return DRM_DP_DUAL_MODE_TYPE1_HDMI;
+ else
+ return DRM_DP_DUAL_MODE_TYPE1_DVI;
+}
+EXPORT_SYMBOL(drm_dp_dual_mode_detect);
+
+/**
+ * drm_dp_dual_mode_max_tmds_clock - Max TMDS clock for DP dual mode adaptor
+ * @type: DP dual mode adaptor type
+ * @adapter: I2C adapter for the DDC bus
+ *
+ * Determine the max TMDS clock the adaptor supports based on the
+ * type of the dual mode adaptor and the DP_DUAL_MODE_MAX_TMDS_CLOCK
+ * register (on type2 adaptors). As some type 1 adaptors have
+ * problems with registers (see comments in drm_dp_dual_mode_detect())
+ * we don't read the register on those, instead we simply assume
+ * a 165 MHz limit based on the specification.
+ *
+ * Returns:
+ * Maximum supported TMDS clock rate for the DP dual mode adaptor in kHz.
+ */
+int drm_dp_dual_mode_max_tmds_clock(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter)
+{
+ uint8_t max_tmds_clock;
+ ssize_t ret;
+
+ /* native HDMI so no limit */
+ if (type == DRM_DP_DUAL_MODE_NONE)
+ return 0;
+
+ /*
+ * Type 1 adaptors are limited to 165MHz
+ * Type 2 adaptors can tells us their limit
+ */
+ if (type < DRM_DP_DUAL_MODE_TYPE2_DVI)
+ return 165000;
+
+ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_MAX_TMDS_CLOCK,
+ &max_tmds_clock, sizeof(max_tmds_clock));
+ if (ret || max_tmds_clock == 0x00 || max_tmds_clock == 0xff) {
+ DRM_DEBUG_KMS("Failed to query max TMDS clock\n");
+ return 165000;
+ }
+
+ return max_tmds_clock * 5000 / 2;
+}
+EXPORT_SYMBOL(drm_dp_dual_mode_max_tmds_clock);
+
+/**
+ * drm_dp_dual_mode_get_tmds_output - Get the state of the TMDS output buffers in the DP dual mode adaptor
+ * @type: DP dual mode adaptor type
+ * @adapter: I2C adapter for the DDC bus
+ * @enabled: current state of the TMDS output buffers
+ *
+ * Get the state of the TMDS output buffers in the adaptor. For
+ * type2 adaptors this is queried from the DP_DUAL_MODE_TMDS_OEN
+ * register. As some type 1 adaptors have problems with registers
+ * (see comments in drm_dp_dual_mode_detect()) we don't read the
+ * register on those, instead we simply assume that the buffers
+ * are always enabled.
+ *
+ * Returns:
+ * 0 on success, negative error code on failure
+ */
+int drm_dp_dual_mode_get_tmds_output(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter,
+ bool *enabled)
+{
+ uint8_t tmds_oen;
+ ssize_t ret;
+
+ if (type < DRM_DP_DUAL_MODE_TYPE2_DVI) {
+ *enabled = true;
+ return 0;
+ }
+
+ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_TMDS_OEN,
+ &tmds_oen, sizeof(tmds_oen));
+ if (ret) {
+ DRM_DEBUG_KMS("Failed to query state of TMDS output buffers\n");
+ return ret;
+ }
+
+ *enabled = !(tmds_oen & DP_DUAL_MODE_TMDS_DISABLE);
+
+ return 0;
+}
+EXPORT_SYMBOL(drm_dp_dual_mode_get_tmds_output);
+
+/**
+ * drm_dp_dual_mode_set_tmds_output - Enable/disable TMDS output buffers in the DP dual mode adaptor
+ * @type: DP dual mode adaptor type
+ * @adapter: I2C adapter for the DDC bus
+ * @enable: enable (as opposed to disable) the TMDS output buffers
+ *
+ * Set the state of the TMDS output buffers in the adaptor. For
+ * type2 this is set via the DP_DUAL_MODE_TMDS_OEN register. As
+ * some type 1 adaptors have problems with registers (see comments
+ * in drm_dp_dual_mode_detect()) we avoid touching the register,
+ * making this function a no-op on type 1 adaptors.
+ *
+ * Returns:
+ * 0 on success, negative error code on failure
+ */
+int drm_dp_dual_mode_set_tmds_output(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter, bool enable)
+{
+ uint8_t tmds_oen = enable ? 0 : DP_DUAL_MODE_TMDS_DISABLE;
+ ssize_t ret;
+
+ if (type < DRM_DP_DUAL_MODE_TYPE2_DVI)
+ return 0;
+
+ ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
+ &tmds_oen, sizeof(tmds_oen));
+ if (ret) {
+ DRM_DEBUG_KMS("Failed to %s TMDS output buffers\n",
+ enable ? "enable" : "disable");
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(drm_dp_dual_mode_set_tmds_output);
+
+/**
+ * drm_dp_get_dual_mode_type_name - Get the name of the DP dual mode adaptor type as a string
+ * @type: DP dual mode adaptor type
+ *
+ * Returns:
+ * String representation of the DP dual mode adaptor type
+ */
+const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type)
+{
+ switch (type) {
+ case DRM_DP_DUAL_MODE_NONE:
+ return "none";
+ case DRM_DP_DUAL_MODE_TYPE1_DVI:
+ return "type 1 DVI";
+ case DRM_DP_DUAL_MODE_TYPE1_HDMI:
+ return "type 1 HDMI";
+ case DRM_DP_DUAL_MODE_TYPE2_DVI:
+ return "type 2 DVI";
+ case DRM_DP_DUAL_MODE_TYPE2_HDMI:
+ return "type 2 HDMI";
+ default:
+ WARN_ON(type != DRM_DP_DUAL_MODE_UNKNOWN);
+ return "unknown";
+ }
+}
+EXPORT_SYMBOL(drm_dp_get_dual_mode_type_name);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index a13edf5de2d6..6537908050d7 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2927,11 +2927,9 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
drm_dp_port_teardown_pdt(port, port->pdt);
if (!port->input && port->vcpi.vcpi > 0) {
- if (mgr->mst_state) {
- drm_dp_mst_reset_vcpi_slots(mgr, port);
- drm_dp_update_payload_part1(mgr);
- drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
- }
+ drm_dp_mst_reset_vcpi_slots(mgr, port);
+ drm_dp_update_payload_part1(mgr);
+ drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
}
kref_put(&port->kref, drm_dp_free_mst_port);
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 172cafe11c71..5075fae3c4e2 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -445,7 +445,7 @@ err_cma_destroy:
err_fb_info_destroy:
drm_fb_helper_release_fbi(helper);
err_gem_free_object:
- dev->driver->gem_free_object(&obj->base);
+ drm_gem_object_unreference_unlocked(&obj->base);
return ret;
}
EXPORT_SYMBOL(drm_fbdev_cma_create_with_funcs);
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index e1ab008b3f08..1d6c335584ec 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -121,7 +121,7 @@ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm,
return cma_obj;
error:
- drm->driver->gem_free_object(&cma_obj->base);
+ drm_gem_object_unreference_unlocked(&cma_obj->base);
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(drm_gem_cma_create);
@@ -162,18 +162,12 @@ drm_gem_cma_create_with_handle(struct drm_file *file_priv,
* and handle has the id what user can see.
*/
ret = drm_gem_handle_create(file_priv, gem_obj, handle);
- if (ret)
- goto err_handle_create;
-
/* drop reference from allocate - handle holds it now. */
drm_gem_object_unreference_unlocked(gem_obj);
+ if (ret)
+ return ERR_PTR(ret);
return cma_obj;
-
-err_handle_create:
- drm->driver->gem_free_object(gem_obj);
-
- return ERR_PTR(ret);
}
/**
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 7def3d58da18..e5e6f504d8cc 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1518,6 +1518,8 @@ int drm_mode_convert_umode(struct drm_display_mode *out,
if (out->status != MODE_OK)
goto out;
+ drm_mode_set_crtcinfo(out, CRTC_INTERLACE_HALVE_V);
+
ret = 0;
out:
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
index 522cfd447892..16353ee81651 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
@@ -225,6 +225,7 @@ struct iommu_domain *etnaviv_iommu_domain_alloc(struct etnaviv_gpu *gpu)
etnaviv_domain->domain.type = __IOMMU_DOMAIN_PAGING;
etnaviv_domain->domain.ops = &etnaviv_iommu_ops.ops;
+ etnaviv_domain->domain.pgsize_bitmap = SZ_4K;
etnaviv_domain->domain.geometry.aperture_start = GPU_MEM_START;
etnaviv_domain->domain.geometry.aperture_end = GPU_MEM_START + PT_ENTRIES * SZ_4K - 1;
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f6223f907c15..7f9901b7777b 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -31,7 +31,6 @@
#include "exynos_drm_plane.h"
#include "exynos_drm_drv.h"
#include "exynos_drm_fb.h"
-#include "exynos_drm_fbdev.h"
#include "exynos_drm_iommu.h"
/*
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 468498e3fec1..4c1fb3f8b5a6 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -34,7 +34,7 @@
struct exynos_dp_device {
struct drm_encoder encoder;
- struct drm_connector connector;
+ struct drm_connector *connector;
struct drm_bridge *ptn_bridge;
struct drm_device *drm_dev;
struct device *dev;
@@ -70,7 +70,7 @@ static int exynos_dp_poweroff(struct analogix_dp_plat_data *plat_data)
static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data)
{
struct exynos_dp_device *dp = to_dp(plat_data);
- struct drm_connector *connector = &dp->connector;
+ struct drm_connector *connector = dp->connector;
struct drm_display_mode *mode;
int num_modes = 0;
@@ -103,6 +103,7 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data,
int ret;
drm_connector_register(connector);
+ dp->connector = connector;
/* Pre-empt DP connector creation if there's a bridge */
if (dp->ptn_bridge) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index 011211e4167d..edbd98ff293e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -15,7 +15,6 @@
#include <drm/drmP.h>
#include "exynos_drm_drv.h"
#include "exynos_drm_crtc.h"
-#include "exynos_drm_fbdev.h"
static LIST_HEAD(exynos_drm_subdrv_list);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 3efe1aa89416..d47216488985 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -30,7 +30,6 @@
#include "exynos_drm_drv.h"
#include "exynos_drm_fb.h"
-#include "exynos_drm_fbdev.h"
#include "exynos_drm_crtc.h"
#include "exynos_drm_plane.h"
#include "exynos_drm_iommu.h"
@@ -120,7 +119,6 @@ static struct fimd_driver_data s3c64xx_fimd_driver_data = {
.timing_base = 0x0,
.has_clksel = 1,
.has_limited_fmt = 1,
- .has_hw_trigger = 1,
};
static struct fimd_driver_data exynos3_fimd_driver_data = {
@@ -171,14 +169,11 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = {
.lcdblk_vt_shift = 24,
.lcdblk_bypass_shift = 15,
.lcdblk_mic_bypass_shift = 11,
- .trg_type = I80_HW_TRG,
.has_shadowcon = 1,
.has_vidoutcon = 1,
.has_vtsel = 1,
.has_mic_bypass = 1,
.has_dp_clk = 1,
- .has_hw_trigger = 1,
- .has_trigger_per_te = 1,
};
struct fimd_context {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 493552368295..8564c3da0d22 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -48,13 +48,13 @@
/* registers for base address */
#define G2D_SRC_BASE_ADDR 0x0304
-#define G2D_SRC_STRIDE_REG 0x0308
+#define G2D_SRC_STRIDE 0x0308
#define G2D_SRC_COLOR_MODE 0x030C
#define G2D_SRC_LEFT_TOP 0x0310
#define G2D_SRC_RIGHT_BOTTOM 0x0314
#define G2D_SRC_PLANE2_BASE_ADDR 0x0318
#define G2D_DST_BASE_ADDR 0x0404
-#define G2D_DST_STRIDE_REG 0x0408
+#define G2D_DST_STRIDE 0x0408
#define G2D_DST_COLOR_MODE 0x040C
#define G2D_DST_LEFT_TOP 0x0410
#define G2D_DST_RIGHT_BOTTOM 0x0414
@@ -563,7 +563,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset)
switch (reg_offset) {
case G2D_SRC_BASE_ADDR:
- case G2D_SRC_STRIDE_REG:
+ case G2D_SRC_STRIDE:
case G2D_SRC_COLOR_MODE:
case G2D_SRC_LEFT_TOP:
case G2D_SRC_RIGHT_BOTTOM:
@@ -573,7 +573,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset)
reg_type = REG_TYPE_SRC_PLANE2;
break;
case G2D_DST_BASE_ADDR:
- case G2D_DST_STRIDE_REG:
+ case G2D_DST_STRIDE:
case G2D_DST_COLOR_MODE:
case G2D_DST_LEFT_TOP:
case G2D_DST_RIGHT_BOTTOM:
@@ -968,8 +968,8 @@ static int g2d_check_reg_offset(struct device *dev,
} else
buf_info->types[reg_type] = BUF_TYPE_GEM;
break;
- case G2D_SRC_STRIDE_REG:
- case G2D_DST_STRIDE_REG:
+ case G2D_SRC_STRIDE:
+ case G2D_DST_STRIDE:
if (for_addr)
goto err;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 55f1d37c666a..77f12c00abf9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -242,7 +242,7 @@ exynos_drm_plane_check_size(const struct exynos_drm_plane_config *config,
state->v_ratio == (1 << 15))
height_ok = true;
- if (width_ok & height_ok)
+ if (width_ok && height_ok)
return 0;
DRM_DEBUG_KMS("scaling mode is not supported");
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index 0ec1ad961e0d..dc723f7ead7d 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -42,9 +42,10 @@ static const struct regmap_config fsl_dcu_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .cache_type = REGCACHE_RBTREE,
+ .cache_type = REGCACHE_FLAT,
.volatile_reg = fsl_dcu_drm_is_volatile_reg,
+ .max_register = 0x11fc,
};
static int fsl_dcu_drm_irq_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 32690332d441..103546834b60 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2365,16 +2365,16 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
task = get_pid_task(file->pid, PIDTYPE_PID);
if (!task) {
ret = -ESRCH;
- goto out_put;
+ goto out_unlock;
}
seq_printf(m, "\nproc: %s\n", task->comm);
put_task_struct(task);
idr_for_each(&file_priv->context_idr, per_file_ctx,
(void *)(unsigned long)m);
}
+out_unlock:
mutex_unlock(&dev->filelist_mutex);
-out_put:
intel_runtime_pm_put(dev_priv);
mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 15615fb9bde6..b3198fcd0536 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1183,6 +1183,12 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
if (ret)
return ret;
+ ret = i915_ggtt_enable_hw(dev);
+ if (ret) {
+ DRM_ERROR("failed to enable GGTT\n");
+ goto out_ggtt;
+ }
+
/* WARNING: Apparently we must kick fbdev drivers before vgacon,
* otherwise the vga fbdev driver falls over. */
ret = i915_kick_out_firmware_fb(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index d37c0a671eed..f313b4d8344f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -734,9 +734,14 @@ int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state)
static int i915_drm_resume(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ int ret;
disable_rpm_wakeref_asserts(dev_priv);
+ ret = i915_ggtt_enable_hw(dev);
+ if (ret)
+ DRM_ERROR("failed to re-enable GGTT\n");
+
intel_csr_ucode_resume(dev_priv);
mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b87ca4fae20a..7c334e902266 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3481,7 +3481,9 @@ int intel_bios_init(struct drm_i915_private *dev_priv);
bool intel_bios_is_valid_vbt(const void *buf, size_t size);
bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv);
bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin);
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port);
bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port);
+bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port);
bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv, enum port *port);
bool intel_bios_is_port_hpd_inverted(struct drm_i915_private *dev_priv,
enum port port);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9b99490e8367..aad26851cee3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1456,7 +1456,10 @@ i915_wait_request(struct drm_i915_gem_request *req)
if (ret)
return ret;
- __i915_gem_request_retire__upto(req);
+ /* If the GPU hung, we want to keep the requests to find the guilty. */
+ if (req->reset_counter == i915_reset_counter(&dev_priv->gpu_error))
+ __i915_gem_request_retire__upto(req);
+
return 0;
}
@@ -1513,7 +1516,8 @@ i915_gem_object_retire_request(struct drm_i915_gem_object *obj,
else if (obj->last_write_req == req)
i915_gem_object_retire__write(obj);
- __i915_gem_request_retire__upto(req);
+ if (req->reset_counter == i915_reset_counter(&req->i915->gpu_error))
+ __i915_gem_request_retire__upto(req);
}
/* A nonblocking variant of the above wait. This is a highly dangerous routine
@@ -4860,9 +4864,6 @@ i915_gem_init_hw(struct drm_device *dev)
struct intel_engine_cs *engine;
int ret, j;
- if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
- return -EIO;
-
/* Double layer security blanket, see i915_gem_init() */
intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0d666b3f7e9b..92acdff9dad3 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3236,6 +3236,14 @@ out_gtt_cleanup:
return ret;
}
+int i915_ggtt_enable_hw(struct drm_device *dev)
+{
+ if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
+ return -EIO;
+
+ return 0;
+}
+
void i915_gem_restore_gtt_mappings(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = to_i915(dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d7dd3d8a8758..0008543d55f6 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -514,6 +514,7 @@ i915_page_dir_dma_addr(const struct i915_hw_ppgtt *ppgtt, const unsigned n)
}
int i915_ggtt_init_hw(struct drm_device *dev);
+int i915_ggtt_enable_hw(struct drm_device *dev);
void i915_gem_init_ggtt(struct drm_device *dev);
void i915_ggtt_cleanup_hw(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index e72dd9a8d6bf..b9022fa053d6 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -139,6 +139,11 @@ fill_detail_timing_data(struct drm_display_mode *panel_fixed_mode,
else
panel_fixed_mode->flags |= DRM_MODE_FLAG_NVSYNC;
+ panel_fixed_mode->width_mm = (dvo_timing->himage_hi << 8) |
+ dvo_timing->himage_lo;
+ panel_fixed_mode->height_mm = (dvo_timing->vimage_hi << 8) |
+ dvo_timing->vimage_lo;
+
/* Some VBTs have bogus h/vtotal values */
if (panel_fixed_mode->hsync_end > panel_fixed_mode->htotal)
panel_fixed_mode->htotal = panel_fixed_mode->hsync_end + 1;
@@ -1187,7 +1192,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
}
if (bdb->version < 106) {
expected_size = 22;
- } else if (bdb->version < 109) {
+ } else if (bdb->version < 111) {
expected_size = 27;
} else if (bdb->version < 195) {
BUILD_BUG_ON(sizeof(struct old_child_dev_config) != 33);
@@ -1546,6 +1551,45 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin)
}
/**
+ * intel_bios_is_port_present - is the specified digital port present
+ * @dev_priv: i915 device instance
+ * @port: port to check
+ *
+ * Return true if the device in %port is present.
+ */
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port)
+{
+ static const struct {
+ u16 dp, hdmi;
+ } port_mapping[] = {
+ [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, },
+ [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
+ [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
+ [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+ };
+ int i;
+
+ /* FIXME maybe deal with port A as well? */
+ if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping))
+ return false;
+
+ if (!dev_priv->vbt.child_dev_num)
+ return false;
+
+ for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
+ const union child_device_config *p_child =
+ &dev_priv->vbt.child_dev[i];
+ if ((p_child->common.dvo_port == port_mapping[port].dp ||
+ p_child->common.dvo_port == port_mapping[port].hdmi) &&
+ (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING |
+ DEVICE_TYPE_DISPLAYPORT_OUTPUT)))
+ return true;
+ }
+
+ return false;
+}
+
+/**
* intel_bios_is_port_edp - is the device in given port eDP
* @dev_priv: i915 device instance
* @port: port to check
@@ -1578,6 +1622,42 @@ bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
return false;
}
+bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port)
+{
+ static const struct {
+ u16 dp, hdmi;
+ } port_mapping[] = {
+ /*
+ * Buggy VBTs may declare DP ports as having
+ * HDMI type dvo_port :( So let's check both.
+ */
+ [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, },
+ [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
+ [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
+ [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+ };
+ int i;
+
+ if (port == PORT_A || port >= ARRAY_SIZE(port_mapping))
+ return false;
+
+ if (!dev_priv->vbt.child_dev_num)
+ return false;
+
+ for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
+ const union child_device_config *p_child =
+ &dev_priv->vbt.child_dev[i];
+
+ if ((p_child->common.dvo_port == port_mapping[port].dp ||
+ p_child->common.dvo_port == port_mapping[port].hdmi) &&
+ (p_child->common.device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) ==
+ (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS))
+ return true;
+ }
+
+ return false;
+}
+
/**
* intel_bios_is_dsi_present - is DSI present in VBT
* @dev_priv: i915 device instance
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 3fac04602a25..01e523df363b 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1601,6 +1601,12 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
enum port port = intel_ddi_get_encoder_port(intel_encoder);
int type = intel_encoder->type;
+ if (type == INTEL_OUTPUT_HDMI) {
+ struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+
+ intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
+ }
+
intel_prepare_ddi_buffer(intel_encoder);
if (type == INTEL_OUTPUT_EDP) {
@@ -1667,6 +1673,12 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder)
DPLL_CTRL2_DDI_CLK_OFF(port)));
else if (INTEL_INFO(dev)->gen < 9)
I915_WRITE(PORT_CLK_SEL(port), PORT_CLK_SEL_NONE);
+
+ if (type == INTEL_OUTPUT_HDMI) {
+ struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+
+ intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
+ }
}
static void intel_enable_ddi(struct intel_encoder *intel_encoder)
@@ -2180,8 +2192,10 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
if (intel_hdmi->infoframe_enabled(&encoder->base, pipe_config))
pipe_config->has_infoframe = true;
- break;
+ /* fall through */
case TRANS_DDI_MODE_SELECT_DVI:
+ pipe_config->lane_count = 4;
+ break;
case TRANS_DDI_MODE_SELECT_FDI:
break;
case TRANS_DDI_MODE_SELECT_DP_SST:
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 46f9be3ad5a2..04452cf3eae8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8275,12 +8275,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_encoder *encoder;
+ int i;
u32 val, final;
bool has_lvds = false;
bool has_cpu_edp = false;
bool has_panel = false;
bool has_ck505 = false;
bool can_ssc = false;
+ bool using_ssc_source = false;
/* We need to take the global config into account */
for_each_intel_encoder(dev, encoder) {
@@ -8307,8 +8309,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
can_ssc = true;
}
- DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n",
- has_panel, has_lvds, has_ck505);
+ /* Check if any DPLLs are using the SSC source */
+ for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+ u32 temp = I915_READ(PCH_DPLL(i));
+
+ if (!(temp & DPLL_VCO_ENABLE))
+ continue;
+
+ if ((temp & PLL_REF_INPUT_MASK) ==
+ PLLB_REF_INPUT_SPREADSPECTRUMIN) {
+ using_ssc_source = true;
+ break;
+ }
+ }
+
+ DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n",
+ has_panel, has_lvds, has_ck505, using_ssc_source);
/* Ironlake: try to setup display ref clock before DPLL
* enabling. This is only under driver's control after
@@ -8345,9 +8361,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
} else
final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
- } else {
- final |= DREF_SSC_SOURCE_DISABLE;
- final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
+ } else if (using_ssc_source) {
+ final |= DREF_SSC_SOURCE_ENABLE;
+ final |= DREF_SSC1_ENABLE;
}
if (final == val)
@@ -8393,7 +8409,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
POSTING_READ(PCH_DREF_CONTROL);
udelay(200);
} else {
- DRM_DEBUG_KMS("Disabling SSC entirely\n");
+ DRM_DEBUG_KMS("Disabling CPU source output\n");
val &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
@@ -8404,16 +8420,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
POSTING_READ(PCH_DREF_CONTROL);
udelay(200);
- /* Turn off the SSC source */
- val &= ~DREF_SSC_SOURCE_MASK;
- val |= DREF_SSC_SOURCE_DISABLE;
+ if (!using_ssc_source) {
+ DRM_DEBUG_KMS("Disabling SSC source\n");
- /* Turn off SSC1 */
- val &= ~DREF_SSC1_ENABLE;
+ /* Turn off the SSC source */
+ val &= ~DREF_SSC_SOURCE_MASK;
+ val |= DREF_SSC_SOURCE_DISABLE;
- I915_WRITE(PCH_DREF_CONTROL, val);
- POSTING_READ(PCH_DREF_CONTROL);
- udelay(200);
+ /* Turn off SSC1 */
+ val &= ~DREF_SSC1_ENABLE;
+
+ I915_WRITE(PCH_DREF_CONTROL, val);
+ POSTING_READ(PCH_DREF_CONTROL);
+ udelay(200);
+ }
}
BUG_ON(val != final);
@@ -8427,16 +8447,16 @@ static void lpt_reset_fdi_mphy(struct drm_i915_private *dev_priv)
tmp |= FDI_MPHY_IOSFSB_RESET_CTL;
I915_WRITE(SOUTH_CHICKEN2, tmp);
- if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) &
- FDI_MPHY_IOSFSB_RESET_STATUS, 100))
+ if (wait_for_us(I915_READ(SOUTH_CHICKEN2) &
+ FDI_MPHY_IOSFSB_RESET_STATUS, 100))
DRM_ERROR("FDI mPHY reset assert timeout\n");
tmp = I915_READ(SOUTH_CHICKEN2);
tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL;
I915_WRITE(SOUTH_CHICKEN2, tmp);
- if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) &
- FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
+ if (wait_for_us((I915_READ(SOUTH_CHICKEN2) &
+ FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
DRM_ERROR("FDI mPHY reset de-assert timeout\n");
}
@@ -9420,8 +9440,8 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
val |= LCPLL_CD_SOURCE_FCLK;
I915_WRITE(LCPLL_CTL, val);
- if (wait_for_atomic_us(I915_READ(LCPLL_CTL) &
- LCPLL_CD_SOURCE_FCLK_DONE, 1))
+ if (wait_for_us(I915_READ(LCPLL_CTL) &
+ LCPLL_CD_SOURCE_FCLK_DONE, 1))
DRM_ERROR("Switching to FCLK failed\n");
val = I915_READ(LCPLL_CTL);
@@ -9494,8 +9514,8 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
val &= ~LCPLL_CD_SOURCE_FCLK;
I915_WRITE(LCPLL_CTL, val);
- if (wait_for_atomic_us((I915_READ(LCPLL_CTL) &
- LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+ if (wait_for_us((I915_READ(LCPLL_CTL) &
+ LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
DRM_ERROR("Switching back to LCPLL failed\n");
}
@@ -12005,6 +12025,9 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
DRM_DEBUG_KMS("No valid intermediate pipe watermarks are possible\n");
return ret;
}
+ } else if (dev_priv->display.compute_intermediate_wm) {
+ if (HAS_PCH_SPLIT(dev_priv) && INTEL_GEN(dev_priv) < 9)
+ pipe_config->wm.intermediate = pipe_config->wm.optimal.ilk;
}
if (INTEL_INFO(dev)->gen >= 9) {
@@ -14551,6 +14574,8 @@ static void intel_setup_outputs(struct drm_device *dev)
if (I915_READ(PCH_DP_D) & DP_DETECTED)
intel_dp_init(dev, PCH_DP_D, PORT_D);
} else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+ bool has_edp, has_port;
+
/*
* The DP_DETECTED bit is the latched state of the DDC
* SDA pin at boot. However since eDP doesn't require DDC
@@ -14559,27 +14584,37 @@ static void intel_setup_outputs(struct drm_device *dev)
* Thus we can't rely on the DP_DETECTED bit alone to detect
* eDP ports. Consult the VBT as well as DP_DETECTED to
* detect eDP ports.
+ *
+ * Sadly the straps seem to be missing sometimes even for HDMI
+ * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap
+ * and VBT for the presence of the port. Additionally we can't
+ * trust the port type the VBT declares as we've seen at least
+ * HDMI ports that the VBT claim are DP or eDP.
*/
- if (I915_READ(VLV_HDMIB) & SDVO_DETECTED &&
- !intel_dp_is_edp(dev, PORT_B))
+ has_edp = intel_dp_is_edp(dev, PORT_B);
+ has_port = intel_bios_is_port_present(dev_priv, PORT_B);
+ if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port)
+ has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B);
+ if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp)
intel_hdmi_init(dev, VLV_HDMIB, PORT_B);
- if (I915_READ(VLV_DP_B) & DP_DETECTED ||
- intel_dp_is_edp(dev, PORT_B))
- intel_dp_init(dev, VLV_DP_B, PORT_B);
- if (I915_READ(VLV_HDMIC) & SDVO_DETECTED &&
- !intel_dp_is_edp(dev, PORT_C))
+ has_edp = intel_dp_is_edp(dev, PORT_C);
+ has_port = intel_bios_is_port_present(dev_priv, PORT_C);
+ if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port)
+ has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C);
+ if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp)
intel_hdmi_init(dev, VLV_HDMIC, PORT_C);
- if (I915_READ(VLV_DP_C) & DP_DETECTED ||
- intel_dp_is_edp(dev, PORT_C))
- intel_dp_init(dev, VLV_DP_C, PORT_C);
if (IS_CHERRYVIEW(dev)) {
- /* eDP not supported on port D, so don't check VBT */
- if (I915_READ(CHV_HDMID) & SDVO_DETECTED)
- intel_hdmi_init(dev, CHV_HDMID, PORT_D);
- if (I915_READ(CHV_DP_D) & DP_DETECTED)
+ /*
+ * eDP not supported on port D,
+ * so no need to worry about it
+ */
+ has_port = intel_bios_is_port_present(dev_priv, PORT_D);
+ if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port)
intel_dp_init(dev, CHV_DP_D, PORT_D);
+ if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port)
+ intel_hdmi_init(dev, CHV_HDMID, PORT_D);
}
intel_dsi_init(dev);
@@ -15990,6 +16025,9 @@ retry:
state->acquire_ctx = &ctx;
+ /* ignore any reset values/BIOS leftovers in the WM registers */
+ to_intel_atomic_state(state)->skip_intermediate_wm = true;
+
for_each_crtc_in_state(state, crtc, crtc_state, i) {
/*
* Force recalculation even if we restore
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f192f58708c2..40745e38d438 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -663,7 +663,7 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
msecs_to_jiffies_timeout(10));
else
- done = wait_for_atomic(C, 10) == 0;
+ done = wait_for(C, 10) == 0;
if (!done)
DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n",
has_aux_irq);
@@ -4899,13 +4899,15 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
void intel_dp_encoder_reset(struct drm_encoder *encoder)
{
- struct intel_dp *intel_dp;
+ struct drm_i915_private *dev_priv = to_i915(encoder->dev);
+ struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+ if (!HAS_DDI(dev_priv))
+ intel_dp->DP = I915_READ(intel_dp->output_reg);
if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP)
return;
- intel_dp = enc_to_intel_dp(encoder);
-
pps_lock(intel_dp);
/*
@@ -4977,9 +4979,6 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
intel_display_power_get(dev_priv, power_domain);
if (long_hpd) {
- /* indicate that we need to restart link training */
- intel_dp->train_set_valid = false;
-
intel_dp_long_pulse(intel_dp->attached_connector);
if (intel_dp->is_mst)
ret = IRQ_HANDLED;
@@ -5725,8 +5724,11 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
if (!fixed_mode && dev_priv->vbt.lfp_lvds_vbt_mode) {
fixed_mode = drm_mode_duplicate(dev,
dev_priv->vbt.lfp_lvds_vbt_mode);
- if (fixed_mode)
+ if (fixed_mode) {
fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
+ connector->display_info.width_mm = fixed_mode->width_mm;
+ connector->display_info.height_mm = fixed_mode->height_mm;
+ }
}
mutex_unlock(&dev->mode_config.mutex);
@@ -5923,9 +5925,9 @@ fail:
return false;
}
-void
-intel_dp_init(struct drm_device *dev,
- i915_reg_t output_reg, enum port port)
+bool intel_dp_init(struct drm_device *dev,
+ i915_reg_t output_reg,
+ enum port port)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_digital_port *intel_dig_port;
@@ -5935,7 +5937,7 @@ intel_dp_init(struct drm_device *dev,
intel_dig_port = kzalloc(sizeof(*intel_dig_port), GFP_KERNEL);
if (!intel_dig_port)
- return;
+ return false;
intel_connector = intel_connector_alloc();
if (!intel_connector)
@@ -5992,7 +5994,7 @@ intel_dp_init(struct drm_device *dev,
if (!intel_dp_init_connector(intel_dig_port, intel_connector))
goto err_init_connector;
- return;
+ return true;
err_init_connector:
drm_encoder_cleanup(encoder);
@@ -6000,8 +6002,7 @@ err_encoder_init:
kfree(intel_connector);
err_connector_alloc:
kfree(intel_dig_port);
-
- return;
+ return false;
}
void intel_dp_mst_suspend(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 0b8eefc2acc5..60fb39cd220b 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -85,8 +85,7 @@ static bool
intel_dp_reset_link_train(struct intel_dp *intel_dp,
uint8_t dp_train_pat)
{
- if (!intel_dp->train_set_valid)
- memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
+ memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
intel_dp_set_signal_levels(intel_dp);
return intel_dp_set_link_train(intel_dp, dp_train_pat);
}
@@ -161,23 +160,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
break;
}
- /*
- * if we used previously trained voltage and pre-emphasis values
- * and we don't get clock recovery, reset link training values
- */
- if (intel_dp->train_set_valid) {
- DRM_DEBUG_KMS("clock recovery not ok, reset");
- /* clear the flag as we are not reusing train set */
- intel_dp->train_set_valid = false;
- if (!intel_dp_reset_link_train(intel_dp,
- DP_TRAINING_PATTERN_1 |
- DP_LINK_SCRAMBLING_DISABLE)) {
- DRM_ERROR("failed to enable link training\n");
- return;
- }
- continue;
- }
-
/* Check to see if we've tried the max voltage */
for (i = 0; i < intel_dp->lane_count; i++)
if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0)
@@ -284,7 +266,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
/* Make sure clock is still ok */
if (!drm_dp_clock_recovery_ok(link_status,
intel_dp->lane_count)) {
- intel_dp->train_set_valid = false;
intel_dp_link_training_clock_recovery(intel_dp);
intel_dp_set_link_train(intel_dp,
training_pattern |
@@ -301,7 +282,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
/* Try 5 times, then try clock recovery if that fails */
if (tries > 5) {
- intel_dp->train_set_valid = false;
intel_dp_link_training_clock_recovery(intel_dp);
intel_dp_set_link_train(intel_dp,
training_pattern |
@@ -322,10 +302,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
intel_dp_set_idle_link_train(intel_dp);
- if (channel_eq) {
- intel_dp->train_set_valid = true;
+ if (channel_eq)
DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n");
- }
}
void intel_dp_stop_link_train(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 639bf0209c15..58f60b27837e 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -366,6 +366,9 @@ ibx_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
DPLL_ID_PCH_PLL_B);
}
+ if (!pll)
+ return NULL;
+
/* reference the pll */
intel_reference_shared_dpll(pll, crtc_state);
@@ -1374,8 +1377,8 @@ static void bxt_ddi_pll_enable(struct drm_i915_private *dev_priv,
I915_WRITE(BXT_PORT_PLL_ENABLE(port), temp);
POSTING_READ(BXT_PORT_PLL_ENABLE(port));
- if (wait_for_atomic_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) &
- PORT_PLL_LOCK), 200))
+ if (wait_for_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) & PORT_PLL_LOCK),
+ 200))
DRM_ERROR("PLL %d not locked\n", port);
/*
@@ -1702,9 +1705,9 @@ static const struct intel_dpll_mgr hsw_pll_mgr = {
static const struct dpll_info skl_plls[] = {
{ "DPLL 0", DPLL_ID_SKL_DPLL0, &skl_ddi_dpll0_funcs, INTEL_DPLL_ALWAYS_ON },
- { "DPPL 1", DPLL_ID_SKL_DPLL1, &skl_ddi_pll_funcs, 0 },
- { "DPPL 2", DPLL_ID_SKL_DPLL2, &skl_ddi_pll_funcs, 0 },
- { "DPPL 3", DPLL_ID_SKL_DPLL3, &skl_ddi_pll_funcs, 0 },
+ { "DPLL 1", DPLL_ID_SKL_DPLL1, &skl_ddi_pll_funcs, 0 },
+ { "DPLL 2", DPLL_ID_SKL_DPLL2, &skl_ddi_pll_funcs, 0 },
+ { "DPLL 3", DPLL_ID_SKL_DPLL3, &skl_ddi_pll_funcs, 0 },
{ NULL, -1, NULL, },
};
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 5da29a02b9e3..f7f0f01814f6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -33,6 +33,7 @@
#include <drm/drm_crtc.h>
#include <drm/drm_crtc_helper.h>
#include <drm/drm_fb_helper.h>
+#include <drm/drm_dp_dual_mode_helper.h>
#include <drm/drm_dp_mst_helper.h>
#include <drm/drm_rect.h>
#include <drm/drm_atomic.h>
@@ -753,6 +754,10 @@ struct cxsr_latency {
struct intel_hdmi {
i915_reg_t hdmi_reg;
int ddc_bus;
+ struct {
+ enum drm_dp_dual_mode_type type;
+ int max_tmds_clock;
+ } dp_dual_mode;
bool limited_color_range;
bool color_range_auto;
bool has_hdmi_sink;
@@ -858,8 +863,6 @@ struct intel_dp {
/* This is called before a link training is starterd */
void (*prepare_link_retrain)(struct intel_dp *intel_dp);
- bool train_set_valid;
-
/* Displayport compliance testing */
unsigned long compliance_test_type;
unsigned long compliance_test_data;
@@ -1279,7 +1282,7 @@ void intel_csr_ucode_suspend(struct drm_i915_private *);
void intel_csr_ucode_resume(struct drm_i915_private *);
/* intel_dp.c */
-void intel_dp_init(struct drm_device *dev, i915_reg_t output_reg, enum port port);
+bool intel_dp_init(struct drm_device *dev, i915_reg_t output_reg, enum port port);
bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
struct intel_connector *intel_connector);
void intel_dp_set_link_params(struct intel_dp *intel_dp,
@@ -1401,6 +1404,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
bool intel_hdmi_compute_config(struct intel_encoder *encoder,
struct intel_crtc_state *pipe_config);
+void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable);
/* intel_lvds.c */
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 2b22bb9bb86f..4756ef639648 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -46,6 +46,22 @@ static const struct {
},
};
+/* return pixels in terms of txbyteclkhs */
+static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count,
+ u16 burst_mode_ratio)
+{
+ return DIV_ROUND_UP(DIV_ROUND_UP(pixels * bpp * burst_mode_ratio,
+ 8 * 100), lane_count);
+}
+
+/* return pixels equvalent to txbyteclkhs */
+static u16 pixels_from_txbyteclkhs(u16 clk_hs, int bpp, int lane_count,
+ u16 burst_mode_ratio)
+{
+ return DIV_ROUND_UP((clk_hs * lane_count * 8 * 100),
+ (bpp * burst_mode_ratio));
+}
+
enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt)
{
/* It just so happens the VBT matches register contents. */
@@ -780,10 +796,19 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_display_mode *adjusted_mode =
&pipe_config->base.adjusted_mode;
+ struct drm_display_mode *adjusted_mode_sw;
+ struct intel_crtc *intel_crtc;
struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+ unsigned int lane_count = intel_dsi->lane_count;
unsigned int bpp, fmt;
enum port port;
- u16 vfp, vsync, vbp;
+ u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
+ u16 hfp_sw, hsync_sw, hbp_sw;
+ u16 crtc_htotal_sw, crtc_hsync_start_sw, crtc_hsync_end_sw,
+ crtc_hblank_start_sw, crtc_hblank_end_sw;
+
+ intel_crtc = to_intel_crtc(encoder->base.crtc);
+ adjusted_mode_sw = &intel_crtc->config->base.adjusted_mode;
/*
* Atleast one port is active as encoder->get_config called only if
@@ -808,26 +833,118 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
adjusted_mode->crtc_vtotal =
I915_READ(BXT_MIPI_TRANS_VTOTAL(port));
+ hactive = adjusted_mode->crtc_hdisplay;
+ hfp = I915_READ(MIPI_HFP_COUNT(port));
+
/*
- * TODO: Retrieve hfp, hsync and hbp. Adjust them for dual link and
- * calculate hsync_start, hsync_end, htotal and hblank_end
+ * Meaningful for video mode non-burst sync pulse mode only,
+ * can be zero for non-burst sync events and burst modes
*/
+ hsync = I915_READ(MIPI_HSYNC_PADDING_COUNT(port));
+ hbp = I915_READ(MIPI_HBP_COUNT(port));
+
+ /* harizontal values are in terms of high speed byte clock */
+ hfp = pixels_from_txbyteclkhs(hfp, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+ hsync = pixels_from_txbyteclkhs(hsync, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+ hbp = pixels_from_txbyteclkhs(hbp, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+
+ if (intel_dsi->dual_link) {
+ hfp *= 2;
+ hsync *= 2;
+ hbp *= 2;
+ }
/* vertical values are in terms of lines */
vfp = I915_READ(MIPI_VFP_COUNT(port));
vsync = I915_READ(MIPI_VSYNC_PADDING_COUNT(port));
vbp = I915_READ(MIPI_VBP_COUNT(port));
+ adjusted_mode->crtc_htotal = hactive + hfp + hsync + hbp;
+ adjusted_mode->crtc_hsync_start = hfp + adjusted_mode->crtc_hdisplay;
+ adjusted_mode->crtc_hsync_end = hsync + adjusted_mode->crtc_hsync_start;
adjusted_mode->crtc_hblank_start = adjusted_mode->crtc_hdisplay;
+ adjusted_mode->crtc_hblank_end = adjusted_mode->crtc_htotal;
- adjusted_mode->crtc_vsync_start =
- vfp + adjusted_mode->crtc_vdisplay;
- adjusted_mode->crtc_vsync_end =
- vsync + adjusted_mode->crtc_vsync_start;
+ adjusted_mode->crtc_vsync_start = vfp + adjusted_mode->crtc_vdisplay;
+ adjusted_mode->crtc_vsync_end = vsync + adjusted_mode->crtc_vsync_start;
adjusted_mode->crtc_vblank_start = adjusted_mode->crtc_vdisplay;
adjusted_mode->crtc_vblank_end = adjusted_mode->crtc_vtotal;
-}
+ /*
+ * In BXT DSI there is no regs programmed with few horizontal timings
+ * in Pixels but txbyteclkhs.. So retrieval process adds some
+ * ROUND_UP ERRORS in the process of PIXELS<==>txbyteclkhs.
+ * Actually here for the given adjusted_mode, we are calculating the
+ * value programmed to the port and then back to the horizontal timing
+ * param in pixels. This is the expected value, including roundup errors
+ * And if that is same as retrieved value from port, then
+ * (HW state) adjusted_mode's horizontal timings are corrected to
+ * match with SW state to nullify the errors.
+ */
+ /* Calculating the value programmed to the Port register */
+ hfp_sw = adjusted_mode_sw->crtc_hsync_start -
+ adjusted_mode_sw->crtc_hdisplay;
+ hsync_sw = adjusted_mode_sw->crtc_hsync_end -
+ adjusted_mode_sw->crtc_hsync_start;
+ hbp_sw = adjusted_mode_sw->crtc_htotal -
+ adjusted_mode_sw->crtc_hsync_end;
+
+ if (intel_dsi->dual_link) {
+ hfp_sw /= 2;
+ hsync_sw /= 2;
+ hbp_sw /= 2;
+ }
+
+ hfp_sw = txbyteclkhs(hfp_sw, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+ hsync_sw = txbyteclkhs(hsync_sw, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+ hbp_sw = txbyteclkhs(hbp_sw, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+
+ /* Reverse calculating the adjusted mode parameters from port reg vals*/
+ hfp_sw = pixels_from_txbyteclkhs(hfp_sw, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+ hsync_sw = pixels_from_txbyteclkhs(hsync_sw, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+ hbp_sw = pixels_from_txbyteclkhs(hbp_sw, bpp, lane_count,
+ intel_dsi->burst_mode_ratio);
+
+ if (intel_dsi->dual_link) {
+ hfp_sw *= 2;
+ hsync_sw *= 2;
+ hbp_sw *= 2;
+ }
+
+ crtc_htotal_sw = adjusted_mode_sw->crtc_hdisplay + hfp_sw +
+ hsync_sw + hbp_sw;
+ crtc_hsync_start_sw = hfp_sw + adjusted_mode_sw->crtc_hdisplay;
+ crtc_hsync_end_sw = hsync_sw + crtc_hsync_start_sw;
+ crtc_hblank_start_sw = adjusted_mode_sw->crtc_hdisplay;
+ crtc_hblank_end_sw = crtc_htotal_sw;
+
+ if (adjusted_mode->crtc_htotal == crtc_htotal_sw)
+ adjusted_mode->crtc_htotal = adjusted_mode_sw->crtc_htotal;
+
+ if (adjusted_mode->crtc_hsync_start == crtc_hsync_start_sw)
+ adjusted_mode->crtc_hsync_start =
+ adjusted_mode_sw->crtc_hsync_start;
+
+ if (adjusted_mode->crtc_hsync_end == crtc_hsync_end_sw)
+ adjusted_mode->crtc_hsync_end =
+ adjusted_mode_sw->crtc_hsync_end;
+
+ if (adjusted_mode->crtc_hblank_start == crtc_hblank_start_sw)
+ adjusted_mode->crtc_hblank_start =
+ adjusted_mode_sw->crtc_hblank_start;
+
+ if (adjusted_mode->crtc_hblank_end == crtc_hblank_end_sw)
+ adjusted_mode->crtc_hblank_end =
+ adjusted_mode_sw->crtc_hblank_end;
+}
static void intel_dsi_get_config(struct intel_encoder *encoder,
struct intel_crtc_state *pipe_config)
@@ -891,14 +1008,6 @@ static u16 txclkesc(u32 divider, unsigned int us)
}
}
-/* return pixels in terms of txbyteclkhs */
-static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count,
- u16 burst_mode_ratio)
-{
- return DIV_ROUND_UP(DIV_ROUND_UP(pixels * bpp * burst_mode_ratio,
- 8 * 100), lane_count);
-}
-
static void set_dsi_timings(struct drm_encoder *encoder,
const struct drm_display_mode *adjusted_mode)
{
@@ -1436,6 +1545,9 @@ void intel_dsi_init(struct drm_device *dev)
goto err;
}
+ connector->display_info.width_mm = fixed_mode->width_mm;
+ connector->display_info.height_mm = fixed_mode->height_mm;
+
intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
intel_dsi_add_properties(intel_connector);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index d5a7cfec589b..647127f3aaff 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -824,8 +824,7 @@ static bool intel_fbc_can_choose(struct intel_crtc *crtc)
{
struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
struct intel_fbc *fbc = &dev_priv->fbc;
- bool enable_by_default = IS_HASWELL(dev_priv) ||
- IS_BROADWELL(dev_priv);
+ bool enable_by_default = IS_BROADWELL(dev_priv);
if (intel_vgpu_active(dev_priv->dev)) {
fbc->no_fbc_reason = "VGPU is active";
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 2cdab73046f8..a8844702d11b 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -836,6 +836,22 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
}
+void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable)
+{
+ struct drm_i915_private *dev_priv = to_i915(intel_hdmi_to_dev(hdmi));
+ struct i2c_adapter *adapter =
+ intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
+
+ if (hdmi->dp_dual_mode.type < DRM_DP_DUAL_MODE_TYPE2_DVI)
+ return;
+
+ DRM_DEBUG_KMS("%s DP dual mode adaptor TMDS output\n",
+ enable ? "Enabling" : "Disabling");
+
+ drm_dp_dual_mode_set_tmds_output(hdmi->dp_dual_mode.type,
+ adapter, enable);
+}
+
static void intel_hdmi_prepare(struct intel_encoder *encoder)
{
struct drm_device *dev = encoder->base.dev;
@@ -845,6 +861,8 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder)
const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
u32 hdmi_val;
+ intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
+
hdmi_val = SDVO_ENCODING_HDMI;
if (!HAS_PCH_SPLIT(dev) && crtc->config->limited_color_range)
hdmi_val |= HDMI_COLOR_RANGE_16_235;
@@ -953,6 +971,8 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
dotclock /= pipe_config->pixel_multiplier;
pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+
+ pipe_config->lane_count = 4;
}
static void intel_enable_hdmi_audio(struct intel_encoder *encoder)
@@ -1140,6 +1160,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder)
}
intel_hdmi->set_infoframes(&encoder->base, false, NULL);
+
+ intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
}
static void g4x_disable_hdmi(struct intel_encoder *encoder)
@@ -1165,27 +1187,42 @@ static void pch_post_disable_hdmi(struct intel_encoder *encoder)
intel_disable_hdmi(encoder);
}
-static int hdmi_port_clock_limit(struct intel_hdmi *hdmi, bool respect_dvi_limit)
+static int intel_hdmi_source_max_tmds_clock(struct drm_i915_private *dev_priv)
{
- struct drm_device *dev = intel_hdmi_to_dev(hdmi);
-
- if ((respect_dvi_limit && !hdmi->has_hdmi_sink) || IS_G4X(dev))
+ if (IS_G4X(dev_priv))
return 165000;
- else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
+ else if (IS_HASWELL(dev_priv) || INTEL_INFO(dev_priv)->gen >= 8)
return 300000;
else
return 225000;
}
+static int hdmi_port_clock_limit(struct intel_hdmi *hdmi,
+ bool respect_downstream_limits)
+{
+ struct drm_device *dev = intel_hdmi_to_dev(hdmi);
+ int max_tmds_clock = intel_hdmi_source_max_tmds_clock(to_i915(dev));
+
+ if (respect_downstream_limits) {
+ if (hdmi->dp_dual_mode.max_tmds_clock)
+ max_tmds_clock = min(max_tmds_clock,
+ hdmi->dp_dual_mode.max_tmds_clock);
+ if (!hdmi->has_hdmi_sink)
+ max_tmds_clock = min(max_tmds_clock, 165000);
+ }
+
+ return max_tmds_clock;
+}
+
static enum drm_mode_status
hdmi_port_clock_valid(struct intel_hdmi *hdmi,
- int clock, bool respect_dvi_limit)
+ int clock, bool respect_downstream_limits)
{
struct drm_device *dev = intel_hdmi_to_dev(hdmi);
if (clock < 25000)
return MODE_CLOCK_LOW;
- if (clock > hdmi_port_clock_limit(hdmi, respect_dvi_limit))
+ if (clock > hdmi_port_clock_limit(hdmi, respect_downstream_limits))
return MODE_CLOCK_HIGH;
/* BXT DPLL can't generate 223-240 MHz */
@@ -1309,7 +1346,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
* within limits.
*/
if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink &&
- hdmi_port_clock_valid(intel_hdmi, clock_12bpc, false) == MODE_OK &&
+ hdmi_port_clock_valid(intel_hdmi, clock_12bpc, true) == MODE_OK &&
hdmi_12bpc_possible(pipe_config)) {
DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
desired_bpp = 12*3;
@@ -1337,6 +1374,8 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
/* Set user selected PAR to incoming mode's member */
adjusted_mode->picture_aspect_ratio = intel_hdmi->aspect_ratio;
+ pipe_config->lane_count = 4;
+
return true;
}
@@ -1349,10 +1388,57 @@ intel_hdmi_unset_edid(struct drm_connector *connector)
intel_hdmi->has_audio = false;
intel_hdmi->rgb_quant_range_selectable = false;
+ intel_hdmi->dp_dual_mode.type = DRM_DP_DUAL_MODE_NONE;
+ intel_hdmi->dp_dual_mode.max_tmds_clock = 0;
+
kfree(to_intel_connector(connector)->detect_edid);
to_intel_connector(connector)->detect_edid = NULL;
}
+static void
+intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid)
+{
+ struct drm_i915_private *dev_priv = to_i915(connector->dev);
+ struct intel_hdmi *hdmi = intel_attached_hdmi(connector);
+ enum port port = hdmi_to_dig_port(hdmi)->port;
+ struct i2c_adapter *adapter =
+ intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
+ enum drm_dp_dual_mode_type type = drm_dp_dual_mode_detect(adapter);
+
+ /*
+ * Type 1 DVI adaptors are not required to implement any
+ * registers, so we can't always detect their presence.
+ * Ideally we should be able to check the state of the
+ * CONFIG1 pin, but no such luck on our hardware.
+ *
+ * The only method left to us is to check the VBT to see
+ * if the port is a dual mode capable DP port. But let's
+ * only do that when we sucesfully read the EDID, to avoid
+ * confusing log messages about DP dual mode adaptors when
+ * there's nothing connected to the port.
+ */
+ if (type == DRM_DP_DUAL_MODE_UNKNOWN) {
+ if (has_edid &&
+ intel_bios_is_port_dp_dual_mode(dev_priv, port)) {
+ DRM_DEBUG_KMS("Assuming DP dual mode adaptor presence based on VBT\n");
+ type = DRM_DP_DUAL_MODE_TYPE1_DVI;
+ } else {
+ type = DRM_DP_DUAL_MODE_NONE;
+ }
+ }
+
+ if (type == DRM_DP_DUAL_MODE_NONE)
+ return;
+
+ hdmi->dp_dual_mode.type = type;
+ hdmi->dp_dual_mode.max_tmds_clock =
+ drm_dp_dual_mode_max_tmds_clock(type, adapter);
+
+ DRM_DEBUG_KMS("DP dual mode adaptor (%s) detected (max TMDS clock: %d kHz)\n",
+ drm_dp_get_dual_mode_type_name(type),
+ hdmi->dp_dual_mode.max_tmds_clock);
+}
+
static bool
intel_hdmi_set_edid(struct drm_connector *connector, bool force)
{
@@ -1368,6 +1454,8 @@ intel_hdmi_set_edid(struct drm_connector *connector, bool force)
intel_gmbus_get_adapter(dev_priv,
intel_hdmi->ddc_bus));
+ intel_hdmi_dp_dual_mode_detect(connector, edid != NULL);
+
intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
}
@@ -2054,6 +2142,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
enum port port = intel_dig_port->port;
uint8_t alternate_ddc_pin;
+ DRM_DEBUG_KMS("Adding HDMI connector on port %c\n",
+ port_name(port));
+
if (WARN(intel_dig_port->max_lanes < 4,
"Not enough lanes (%d) for HDMI on port %c\n",
intel_dig_port->max_lanes, port_name(port)))
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 6179b591ee84..42eac37de047 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -721,48 +721,6 @@ int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request
return ret;
}
-static int logical_ring_wait_for_space(struct drm_i915_gem_request *req,
- int bytes)
-{
- struct intel_ringbuffer *ringbuf = req->ringbuf;
- struct intel_engine_cs *engine = req->engine;
- struct drm_i915_gem_request *target;
- unsigned space;
- int ret;
-
- if (intel_ring_space(ringbuf) >= bytes)
- return 0;
-
- /* The whole point of reserving space is to not wait! */
- WARN_ON(ringbuf->reserved_in_use);
-
- list_for_each_entry(target, &engine->request_list, list) {
- /*
- * The request queue is per-engine, so can contain requests
- * from multiple ringbuffers. Here, we must ignore any that
- * aren't from the ringbuffer we're considering.
- */
- if (target->ringbuf != ringbuf)
- continue;
-
- /* Would completion of this request free enough space? */
- space = __intel_ring_space(target->postfix, ringbuf->tail,
- ringbuf->size);
- if (space >= bytes)
- break;
- }
-
- if (WARN_ON(&target->list == &engine->request_list))
- return -ENOSPC;
-
- ret = i915_wait_request(target);
- if (ret)
- return ret;
-
- ringbuf->space = space;
- return 0;
-}
-
/*
* intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
* @request: Request to advance the logical ringbuffer of.
@@ -814,92 +772,6 @@ intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
return 0;
}
-static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
-{
- uint32_t __iomem *virt;
- int rem = ringbuf->size - ringbuf->tail;
-
- virt = ringbuf->virtual_start + ringbuf->tail;
- rem /= 4;
- while (rem--)
- iowrite32(MI_NOOP, virt++);
-
- ringbuf->tail = 0;
- intel_ring_update_space(ringbuf);
-}
-
-static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
-{
- struct intel_ringbuffer *ringbuf = req->ringbuf;
- int remain_usable = ringbuf->effective_size - ringbuf->tail;
- int remain_actual = ringbuf->size - ringbuf->tail;
- int ret, total_bytes, wait_bytes = 0;
- bool need_wrap = false;
-
- if (ringbuf->reserved_in_use)
- total_bytes = bytes;
- else
- total_bytes = bytes + ringbuf->reserved_size;
-
- if (unlikely(bytes > remain_usable)) {
- /*
- * Not enough space for the basic request. So need to flush
- * out the remainder and then wait for base + reserved.
- */
- wait_bytes = remain_actual + total_bytes;
- need_wrap = true;
- } else {
- if (unlikely(total_bytes > remain_usable)) {
- /*
- * The base request will fit but the reserved space
- * falls off the end. So don't need an immediate wrap
- * and only need to effectively wait for the reserved
- * size space from the start of ringbuffer.
- */
- wait_bytes = remain_actual + ringbuf->reserved_size;
- } else if (total_bytes > ringbuf->space) {
- /* No wrapping required, just waiting. */
- wait_bytes = total_bytes;
- }
- }
-
- if (wait_bytes) {
- ret = logical_ring_wait_for_space(req, wait_bytes);
- if (unlikely(ret))
- return ret;
-
- if (need_wrap)
- __wrap_ring_buffer(ringbuf);
- }
-
- return 0;
-}
-
-/**
- * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
- *
- * @req: The request to start some new work for
- * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
- *
- * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
- * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
- * and also preallocates a request (every workload submission is still mediated through
- * requests, same as it did with legacy ringbuffer submission).
- *
- * Return: non-zero if the ringbuffer is not ready to be written to.
- */
-int intel_logical_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
-{
- int ret;
-
- ret = logical_ring_prepare(req, num_dwords * sizeof(uint32_t));
- if (ret)
- return ret;
-
- req->ringbuf->space -= num_dwords * sizeof(uint32_t);
- return 0;
-}
-
int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request)
{
/*
@@ -912,7 +784,7 @@ int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request)
*/
intel_ring_reserved_space_reserve(request->ringbuf, MIN_SPACE_FOR_ADD_REQUEST);
- return intel_logical_ring_begin(request, 0);
+ return intel_ring_begin(request, 0);
}
/**
@@ -982,7 +854,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
if (engine == &dev_priv->engine[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_logical_ring_begin(params->request, 4);
+ ret = intel_ring_begin(params->request, 4);
if (ret)
return ret;
@@ -1178,7 +1050,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
if (ret)
return ret;
- ret = intel_logical_ring_begin(req, w->count * 2 + 2);
+ ret = intel_ring_begin(req, w->count * 2 + 2);
if (ret)
return ret;
@@ -1669,7 +1541,7 @@ static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
const int num_lri_cmds = GEN8_LEGACY_PDPES * 2;
int i, ret;
- ret = intel_logical_ring_begin(req, num_lri_cmds * 2 + 2);
+ ret = intel_ring_begin(req, num_lri_cmds * 2 + 2);
if (ret)
return ret;
@@ -1716,7 +1588,7 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
req->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(req->engine);
}
- ret = intel_logical_ring_begin(req, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -1778,7 +1650,7 @@ static int gen8_emit_flush(struct drm_i915_gem_request *request,
uint32_t cmd;
int ret;
- ret = intel_logical_ring_begin(request, 4);
+ ret = intel_ring_begin(request, 4);
if (ret)
return ret;
@@ -1846,7 +1718,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
vf_flush_wa = true;
}
- ret = intel_logical_ring_begin(request, vf_flush_wa ? 12 : 6);
+ ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6);
if (ret)
return ret;
@@ -1920,7 +1792,7 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
struct intel_ringbuffer *ringbuf = request->ringbuf;
int ret;
- ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS);
+ ret = intel_ring_begin(request, 6 + WA_TAIL_DWORDS);
if (ret)
return ret;
@@ -1944,7 +1816,7 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
struct intel_ringbuffer *ringbuf = request->ringbuf;
int ret;
- ret = intel_logical_ring_begin(request, 8 + WA_TAIL_DWORDS);
+ ret = intel_ring_begin(request, 8 + WA_TAIL_DWORDS);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 461f1ef9b5c1..60a7385bc531 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -63,7 +63,6 @@ int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request);
void intel_logical_ring_stop(struct intel_engine_cs *engine);
void intel_logical_ring_cleanup(struct intel_engine_cs *engine);
int intel_logical_rings_init(struct drm_device *dev);
-int intel_logical_ring_begin(struct drm_i915_gem_request *req, int num_dwords);
int logical_ring_flush_all_caches(struct drm_i915_gem_request *req);
/**
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bc53c0dd34d0..96281e628d2a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -1082,6 +1082,8 @@ void intel_lvds_init(struct drm_device *dev)
fixed_mode = drm_mode_duplicate(dev, dev_priv->vbt.lfp_lvds_vbt_mode);
if (fixed_mode) {
fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
+ connector->display_info.width_mm = fixed_mode->width_mm;
+ connector->display_info.height_mm = fixed_mode->height_mm;
goto out;
}
}
diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c
index 23b8545ad6b0..6ba4bf7f2a89 100644
--- a/drivers/gpu/drm/i915/intel_mocs.c
+++ b/drivers/gpu/drm/i915/intel_mocs.c
@@ -239,11 +239,9 @@ static int emit_mocs_control_table(struct drm_i915_gem_request *req,
if (WARN_ON(table->size > GEN9_NUM_MOCS_ENTRIES))
return -ENODEV;
- ret = intel_logical_ring_begin(req, 2 + 2 * GEN9_NUM_MOCS_ENTRIES);
- if (ret) {
- DRM_DEBUG("intel_logical_ring_begin failed %d\n", ret);
+ ret = intel_ring_begin(req, 2 + 2 * GEN9_NUM_MOCS_ENTRIES);
+ if (ret)
return ret;
- }
intel_logical_ring_emit(ringbuf,
MI_LOAD_REGISTER_IMM(GEN9_NUM_MOCS_ENTRIES));
@@ -305,11 +303,9 @@ static int emit_mocs_l3cc_table(struct drm_i915_gem_request *req,
if (WARN_ON(table->size > GEN9_NUM_MOCS_ENTRIES))
return -ENODEV;
- ret = intel_logical_ring_begin(req, 2 + GEN9_NUM_MOCS_ENTRIES);
- if (ret) {
- DRM_DEBUG("intel_logical_ring_begin failed %d\n", ret);
+ ret = intel_ring_begin(req, 2 + GEN9_NUM_MOCS_ENTRIES);
+ if (ret)
return ret;
- }
intel_logical_ring_emit(ringbuf,
MI_LOAD_REGISTER_IMM(GEN9_NUM_MOCS_ENTRIES / 2));
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index a0788763757b..8357d571553a 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1638,6 +1638,12 @@ static int pwm_setup_backlight(struct intel_connector *connector,
return -ENODEV;
}
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(panel->backlight.pwm);
+
retval = pwm_config(panel->backlight.pwm, CRC_PMIC_PWM_PERIOD_NS,
CRC_PMIC_PWM_PERIOD_NS);
if (retval < 0) {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4b60005cda37..a7ef45da0a9e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3904,6 +3904,8 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
if (IS_HASWELL(dev) || IS_BROADWELL(dev))
hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
+ memset(active, 0, sizeof(*active));
+
active->pipe_enabled = intel_crtc->active;
if (active->pipe_enabled) {
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index c3abae4bc596..a788d1e9589b 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -280,7 +280,10 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp)
* with the 5 or 6 idle patterns.
*/
uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
- uint32_t val = 0x0;
+ uint32_t val = EDP_PSR_ENABLE;
+
+ val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
+ val |= idle_frames << EDP_PSR_IDLE_FRAME_SHIFT;
if (IS_HASWELL(dev))
val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES;
@@ -288,14 +291,50 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp)
if (dev_priv->psr.link_standby)
val |= EDP_PSR_LINK_STANDBY;
- I915_WRITE(EDP_PSR_CTL, val |
- max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
- idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
- EDP_PSR_ENABLE);
+ if (dev_priv->vbt.psr.tp1_wakeup_time > 5)
+ val |= EDP_PSR_TP1_TIME_2500us;
+ else if (dev_priv->vbt.psr.tp1_wakeup_time > 1)
+ val |= EDP_PSR_TP1_TIME_500us;
+ else if (dev_priv->vbt.psr.tp1_wakeup_time > 0)
+ val |= EDP_PSR_TP1_TIME_100us;
+ else
+ val |= EDP_PSR_TP1_TIME_0us;
+
+ if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
+ val |= EDP_PSR_TP2_TP3_TIME_2500us;
+ else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
+ val |= EDP_PSR_TP2_TP3_TIME_500us;
+ else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
+ val |= EDP_PSR_TP2_TP3_TIME_100us;
+ else
+ val |= EDP_PSR_TP2_TP3_TIME_0us;
+
+ if (intel_dp_source_supports_hbr2(intel_dp) &&
+ drm_dp_tps3_supported(intel_dp->dpcd))
+ val |= EDP_PSR_TP1_TP3_SEL;
+ else
+ val |= EDP_PSR_TP1_TP2_SEL;
+
+ I915_WRITE(EDP_PSR_CTL, val);
+
+ if (!dev_priv->psr.psr2_support)
+ return;
+
+ /* FIXME: selective update is probably totally broken because it doesn't
+ * mesh at all with our frontbuffer tracking. And the hw alone isn't
+ * good enough. */
+ val = EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE;
+
+ if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
+ val |= EDP_PSR2_TP2_TIME_2500;
+ else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
+ val |= EDP_PSR2_TP2_TIME_500;
+ else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
+ val |= EDP_PSR2_TP2_TIME_100;
+ else
+ val |= EDP_PSR2_TP2_TIME_50;
- if (dev_priv->psr.psr2_support)
- I915_WRITE(EDP_PSR2_CTL, EDP_PSR2_ENABLE |
- EDP_SU_TRACK_ENABLE | EDP_PSR2_TP2_TIME_100);
+ I915_WRITE(EDP_PSR2_CTL, val);
}
static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 245386e20c52..04402bb9d26b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -53,12 +53,6 @@ void intel_ring_update_space(struct intel_ringbuffer *ringbuf)
ringbuf->tail, ringbuf->size);
}
-int intel_ring_space(struct intel_ringbuffer *ringbuf)
-{
- intel_ring_update_space(ringbuf);
- return ringbuf->space;
-}
-
bool intel_engine_stopped(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->dev->dev_private;
@@ -1309,7 +1303,7 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
intel_ring_emit(signaller, seqno);
intel_ring_emit(signaller, 0);
intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL |
- MI_SEMAPHORE_TARGET(waiter->id));
+ MI_SEMAPHORE_TARGET(waiter->hw_id));
intel_ring_emit(signaller, 0);
}
@@ -1349,7 +1343,7 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
intel_ring_emit(signaller, upper_32_bits(gtt_offset));
intel_ring_emit(signaller, seqno);
intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL |
- MI_SEMAPHORE_TARGET(waiter->id));
+ MI_SEMAPHORE_TARGET(waiter->hw_id));
intel_ring_emit(signaller, 0);
}
@@ -1573,6 +1567,8 @@ pc_render_add_request(struct drm_i915_gem_request *req)
static void
gen6_seqno_barrier(struct intel_engine_cs *engine)
{
+ struct drm_i915_private *dev_priv = engine->dev->dev_private;
+
/* Workaround to force correct ordering between irq and seqno writes on
* ivb (and maybe also on snb) by reading from a CS register (like
* ACTHD) before reading the status page.
@@ -1584,9 +1580,13 @@ gen6_seqno_barrier(struct intel_engine_cs *engine)
* the write time to land, but that would incur a delay after every
* batch i.e. much more frequent than a delay when waiting for the
* interrupt (with the same net latency).
+ *
+ * Also note that to prevent whole machine hangs on gen7, we have to
+ * take the spinlock to guard against concurrent cacheline access.
*/
- struct drm_i915_private *dev_priv = engine->dev->dev_private;
+ spin_lock_irq(&dev_priv->uncore.lock);
POSTING_READ_FW(RING_ACTHD(engine->mmio_base));
+ spin_unlock_irq(&dev_priv->uncore.lock);
}
static u32
@@ -2312,51 +2312,6 @@ void intel_cleanup_engine(struct intel_engine_cs *engine)
engine->dev = NULL;
}
-static int ring_wait_for_space(struct intel_engine_cs *engine, int n)
-{
- struct intel_ringbuffer *ringbuf = engine->buffer;
- struct drm_i915_gem_request *request;
- unsigned space;
- int ret;
-
- if (intel_ring_space(ringbuf) >= n)
- return 0;
-
- /* The whole point of reserving space is to not wait! */
- WARN_ON(ringbuf->reserved_in_use);
-
- list_for_each_entry(request, &engine->request_list, list) {
- space = __intel_ring_space(request->postfix, ringbuf->tail,
- ringbuf->size);
- if (space >= n)
- break;
- }
-
- if (WARN_ON(&request->list == &engine->request_list))
- return -ENOSPC;
-
- ret = i915_wait_request(request);
- if (ret)
- return ret;
-
- ringbuf->space = space;
- return 0;
-}
-
-static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
-{
- uint32_t __iomem *virt;
- int rem = ringbuf->size - ringbuf->tail;
-
- virt = ringbuf->virtual_start + ringbuf->tail;
- rem /= 4;
- while (rem--)
- iowrite32(MI_NOOP, virt++);
-
- ringbuf->tail = 0;
- intel_ring_update_space(ringbuf);
-}
-
int intel_engine_idle(struct intel_engine_cs *engine)
{
struct drm_i915_gem_request *req;
@@ -2398,63 +2353,82 @@ int intel_ring_reserve_space(struct drm_i915_gem_request *request)
void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size)
{
- WARN_ON(ringbuf->reserved_size);
- WARN_ON(ringbuf->reserved_in_use);
-
+ GEM_BUG_ON(ringbuf->reserved_size);
ringbuf->reserved_size = size;
}
void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf)
{
- WARN_ON(ringbuf->reserved_in_use);
-
+ GEM_BUG_ON(!ringbuf->reserved_size);
ringbuf->reserved_size = 0;
- ringbuf->reserved_in_use = false;
}
void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf)
{
- WARN_ON(ringbuf->reserved_in_use);
-
- ringbuf->reserved_in_use = true;
- ringbuf->reserved_tail = ringbuf->tail;
+ GEM_BUG_ON(!ringbuf->reserved_size);
+ ringbuf->reserved_size = 0;
}
void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf)
{
- WARN_ON(!ringbuf->reserved_in_use);
- if (ringbuf->tail > ringbuf->reserved_tail) {
- WARN(ringbuf->tail > ringbuf->reserved_tail + ringbuf->reserved_size,
- "request reserved size too small: %d vs %d!\n",
- ringbuf->tail - ringbuf->reserved_tail, ringbuf->reserved_size);
- } else {
+ GEM_BUG_ON(ringbuf->reserved_size);
+}
+
+static int wait_for_space(struct drm_i915_gem_request *req, int bytes)
+{
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
+ struct intel_engine_cs *engine = req->engine;
+ struct drm_i915_gem_request *target;
+
+ intel_ring_update_space(ringbuf);
+ if (ringbuf->space >= bytes)
+ return 0;
+
+ /*
+ * Space is reserved in the ringbuffer for finalising the request,
+ * as that cannot be allowed to fail. During request finalisation,
+ * reserved_space is set to 0 to stop the overallocation and the
+ * assumption is that then we never need to wait (which has the
+ * risk of failing with EINTR).
+ *
+ * See also i915_gem_request_alloc() and i915_add_request().
+ */
+ GEM_BUG_ON(!ringbuf->reserved_size);
+
+ list_for_each_entry(target, &engine->request_list, list) {
+ unsigned space;
+
/*
- * The ring was wrapped while the reserved space was in use.
- * That means that some unknown amount of the ring tail was
- * no-op filled and skipped. Thus simply adding the ring size
- * to the tail and doing the above space check will not work.
- * Rather than attempt to track how much tail was skipped,
- * it is much simpler to say that also skipping the sanity
- * check every once in a while is not a big issue.
+ * The request queue is per-engine, so can contain requests
+ * from multiple ringbuffers. Here, we must ignore any that
+ * aren't from the ringbuffer we're considering.
*/
+ if (target->ringbuf != ringbuf)
+ continue;
+
+ /* Would completion of this request free enough space? */
+ space = __intel_ring_space(target->postfix, ringbuf->tail,
+ ringbuf->size);
+ if (space >= bytes)
+ break;
}
- ringbuf->reserved_size = 0;
- ringbuf->reserved_in_use = false;
+ if (WARN_ON(&target->list == &engine->request_list))
+ return -ENOSPC;
+
+ return i915_wait_request(target);
}
-static int __intel_ring_prepare(struct intel_engine_cs *engine, int bytes)
+int intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
{
- struct intel_ringbuffer *ringbuf = engine->buffer;
- int remain_usable = ringbuf->effective_size - ringbuf->tail;
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
int remain_actual = ringbuf->size - ringbuf->tail;
- int ret, total_bytes, wait_bytes = 0;
+ int remain_usable = ringbuf->effective_size - ringbuf->tail;
+ int bytes = num_dwords * sizeof(u32);
+ int total_bytes, wait_bytes;
bool need_wrap = false;
- if (ringbuf->reserved_in_use)
- total_bytes = bytes;
- else
- total_bytes = bytes + ringbuf->reserved_size;
+ total_bytes = bytes + ringbuf->reserved_size;
if (unlikely(bytes > remain_usable)) {
/*
@@ -2463,44 +2437,42 @@ static int __intel_ring_prepare(struct intel_engine_cs *engine, int bytes)
*/
wait_bytes = remain_actual + total_bytes;
need_wrap = true;
+ } else if (unlikely(total_bytes > remain_usable)) {
+ /*
+ * The base request will fit but the reserved space
+ * falls off the end. So we don't need an immediate wrap
+ * and only need to effectively wait for the reserved
+ * size space from the start of ringbuffer.
+ */
+ wait_bytes = remain_actual + ringbuf->reserved_size;
} else {
- if (unlikely(total_bytes > remain_usable)) {
- /*
- * The base request will fit but the reserved space
- * falls off the end. So don't need an immediate wrap
- * and only need to effectively wait for the reserved
- * size space from the start of ringbuffer.
- */
- wait_bytes = remain_actual + ringbuf->reserved_size;
- } else if (total_bytes > ringbuf->space) {
- /* No wrapping required, just waiting. */
- wait_bytes = total_bytes;
- }
+ /* No wrapping required, just waiting. */
+ wait_bytes = total_bytes;
}
- if (wait_bytes) {
- ret = ring_wait_for_space(engine, wait_bytes);
+ if (wait_bytes > ringbuf->space) {
+ int ret = wait_for_space(req, wait_bytes);
if (unlikely(ret))
return ret;
- if (need_wrap)
- __wrap_ring_buffer(ringbuf);
+ intel_ring_update_space(ringbuf);
+ if (unlikely(ringbuf->space < wait_bytes))
+ return -EAGAIN;
}
- return 0;
-}
+ if (unlikely(need_wrap)) {
+ GEM_BUG_ON(remain_actual > ringbuf->space);
+ GEM_BUG_ON(ringbuf->tail + remain_actual > ringbuf->size);
-int intel_ring_begin(struct drm_i915_gem_request *req,
- int num_dwords)
-{
- struct intel_engine_cs *engine = req->engine;
- int ret;
-
- ret = __intel_ring_prepare(engine, num_dwords * sizeof(uint32_t));
- if (ret)
- return ret;
+ /* Fill the tail with MI_NOOP */
+ memset(ringbuf->virtual_start + ringbuf->tail,
+ 0, remain_actual);
+ ringbuf->tail = 0;
+ ringbuf->space -= remain_actual;
+ }
- engine->buffer->space -= num_dwords * sizeof(uint32_t);
+ ringbuf->space -= bytes;
+ GEM_BUG_ON(ringbuf->space < 0);
return 0;
}
@@ -2772,6 +2744,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
engine->name = "render ring";
engine->id = RCS;
engine->exec_id = I915_EXEC_RENDER;
+ engine->hw_id = 0;
engine->mmio_base = RENDER_RING_BASE;
if (INTEL_INFO(dev)->gen >= 8) {
@@ -2923,6 +2896,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
engine->name = "bsd ring";
engine->id = VCS;
engine->exec_id = I915_EXEC_BSD;
+ engine->hw_id = 1;
engine->write_tail = ring_write_tail;
if (INTEL_INFO(dev)->gen >= 6) {
@@ -3001,6 +2975,7 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev)
engine->name = "bsd2 ring";
engine->id = VCS2;
engine->exec_id = I915_EXEC_BSD;
+ engine->hw_id = 4;
engine->write_tail = ring_write_tail;
engine->mmio_base = GEN8_BSD2_RING_BASE;
@@ -3033,6 +3008,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
engine->name = "blitter ring";
engine->id = BCS;
engine->exec_id = I915_EXEC_BLT;
+ engine->hw_id = 2;
engine->mmio_base = BLT_RING_BASE;
engine->write_tail = ring_write_tail;
@@ -3092,6 +3068,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
engine->name = "video enhancement ring";
engine->id = VECS;
engine->exec_id = I915_EXEC_VEBOX;
+ engine->hw_id = 3;
engine->mmio_base = VEBOX_RING_BASE;
engine->write_tail = ring_write_tail;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2ade194bbea9..ff126485d398 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -108,8 +108,6 @@ struct intel_ringbuffer {
int size;
int effective_size;
int reserved_size;
- int reserved_tail;
- bool reserved_in_use;
/** We track the position of the requests in the ring buffer, and
* when each is retired we increment last_retired_head as the GPU
@@ -156,7 +154,8 @@ struct intel_engine_cs {
#define I915_NUM_ENGINES 5
#define _VCS(n) (VCS + (n))
unsigned int exec_id;
- unsigned int guc_id;
+ unsigned int hw_id;
+ unsigned int guc_id; /* XXX same as hw_id? */
u32 mmio_base;
struct drm_device *dev;
struct intel_ringbuffer *buffer;
@@ -459,7 +458,6 @@ static inline void intel_ring_advance(struct intel_engine_cs *engine)
}
int __intel_ring_space(int head, int tail, int size);
void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
-int intel_ring_space(struct intel_ringbuffer *ringbuf);
bool intel_engine_stopped(struct intel_engine_cs *engine);
int __must_check intel_engine_idle(struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index 9ff1e960d617..44fb0b35eed3 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -403,9 +403,10 @@ struct lvds_dvo_timing {
u8 vsync_off:4;
u8 rsvd0:6;
u8 hsync_off_hi:2;
- u8 h_image;
- u8 v_image;
- u8 max_hv;
+ u8 himage_lo;
+ u8 vimage_lo;
+ u8 vimage_hi:4;
+ u8 himage_hi:4;
u8 h_border;
u8 v_border;
u8 rsvd1:3;
@@ -740,6 +741,7 @@ struct bdb_psr {
#define DEVICE_TYPE_INT_TV 0x1009
#define DEVICE_TYPE_HDMI 0x60D2
#define DEVICE_TYPE_DP 0x68C6
+#define DEVICE_TYPE_DP_DUAL_MODE 0x60D6
#define DEVICE_TYPE_eDP 0x78C6
#define DEVICE_TYPE_CLASS_EXTENSION (1 << 15)
@@ -774,6 +776,17 @@ struct bdb_psr {
DEVICE_TYPE_DISPLAYPORT_OUTPUT | \
DEVICE_TYPE_ANALOG_OUTPUT)
+#define DEVICE_TYPE_DP_DUAL_MODE_BITS \
+ (DEVICE_TYPE_INTERNAL_CONNECTOR | \
+ DEVICE_TYPE_MIPI_OUTPUT | \
+ DEVICE_TYPE_COMPOSITE_OUTPUT | \
+ DEVICE_TYPE_LVDS_SINGALING | \
+ DEVICE_TYPE_TMDS_DVI_SIGNALING | \
+ DEVICE_TYPE_VIDEO_SIGNALING | \
+ DEVICE_TYPE_DISPLAYPORT_OUTPUT | \
+ DEVICE_TYPE_DIGITAL_OUTPUT | \
+ DEVICE_TYPE_ANALOG_OUTPUT)
+
/* define the DVO port for HDMI output type */
#define DVO_B 1
#define DVO_C 2
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 1080019e7b17..82656654fb21 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -25,6 +25,7 @@
#include <drm/drm_fb_cma_helper.h>
#include <drm/drm_plane_helper.h>
#include <drm/drm_of.h>
+#include <video/imx-ipu-v3.h>
#include "imx-drm.h"
@@ -96,8 +97,8 @@ static struct imx_drm_crtc *imx_drm_find_crtc(struct drm_crtc *crtc)
return NULL;
}
-int imx_drm_set_bus_format_pins(struct drm_encoder *encoder, u32 bus_format,
- int hsync_pin, int vsync_pin)
+int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
+ int hsync_pin, int vsync_pin, u32 bus_flags)
{
struct imx_drm_crtc_helper_funcs *helper;
struct imx_drm_crtc *imx_crtc;
@@ -109,14 +110,17 @@ int imx_drm_set_bus_format_pins(struct drm_encoder *encoder, u32 bus_format,
helper = &imx_crtc->imx_drm_helper_funcs;
if (helper->set_interface_pix_fmt)
return helper->set_interface_pix_fmt(encoder->crtc,
- bus_format, hsync_pin, vsync_pin);
+ bus_format, hsync_pin, vsync_pin,
+ bus_flags);
return 0;
}
-EXPORT_SYMBOL_GPL(imx_drm_set_bus_format_pins);
+EXPORT_SYMBOL_GPL(imx_drm_set_bus_config);
int imx_drm_set_bus_format(struct drm_encoder *encoder, u32 bus_format)
{
- return imx_drm_set_bus_format_pins(encoder, bus_format, 2, 3);
+ return imx_drm_set_bus_config(encoder, bus_format, 2, 3,
+ DRM_BUS_FLAG_DE_HIGH |
+ DRM_BUS_FLAG_PIXDATA_NEGEDGE);
}
EXPORT_SYMBOL_GPL(imx_drm_set_bus_format);
@@ -437,6 +441,13 @@ static int compare_of(struct device *dev, void *data)
{
struct device_node *np = data;
+ /* Special case for DI, dev->of_node may not be set yet */
+ if (strcmp(dev->driver->name, "imx-ipuv3-crtc") == 0) {
+ struct ipu_client_platformdata *pdata = dev->platform_data;
+
+ return pdata->of_node == np;
+ }
+
/* Special case for LDB, one device for two channels */
if (of_node_cmp(np->name, "lvds-channel") == 0) {
np = of_get_parent(np);
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index b0241b9d1334..74320a1723b7 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -19,7 +19,8 @@ struct imx_drm_crtc_helper_funcs {
int (*enable_vblank)(struct drm_crtc *crtc);
void (*disable_vblank)(struct drm_crtc *crtc);
int (*set_interface_pix_fmt)(struct drm_crtc *crtc,
- u32 bus_format, int hsync_pin, int vsync_pin);
+ u32 bus_format, int hsync_pin, int vsync_pin,
+ u32 bus_flags);
const struct drm_crtc_helper_funcs *crtc_helper_funcs;
const struct drm_crtc_funcs *crtc_funcs;
};
@@ -41,8 +42,8 @@ void imx_drm_mode_config_init(struct drm_device *drm);
struct drm_gem_cma_object *imx_drm_fb_get_obj(struct drm_framebuffer *fb);
-int imx_drm_set_bus_format_pins(struct drm_encoder *encoder,
- u32 bus_format, int hsync_pin, int vsync_pin);
+int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
+ int hsync_pin, int vsync_pin, u32 bus_flags);
int imx_drm_set_bus_format(struct drm_encoder *encoder,
u32 bus_format);
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index a58eee59550a..beff793bb717 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -25,6 +25,7 @@
#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
#include <linux/of_device.h>
#include <linux/of_graph.h>
+#include <video/of_display_timing.h>
#include <video/of_videomode.h>
#include <linux/regmap.h>
#include <linux/videodev2.h>
@@ -59,6 +60,7 @@ struct imx_ldb_channel {
struct drm_encoder encoder;
struct drm_panel *panel;
struct device_node *child;
+ struct i2c_adapter *ddc;
int chno;
void *edid;
int edid_len;
@@ -107,6 +109,9 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
return num_modes;
}
+ if (!imx_ldb_ch->edid && imx_ldb_ch->ddc)
+ imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc);
+
if (imx_ldb_ch->edid) {
drm_mode_connector_update_edid_property(connector,
imx_ldb_ch->edid);
@@ -553,7 +558,8 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
for_each_child_of_node(np, child) {
struct imx_ldb_channel *channel;
- struct device_node *port;
+ struct device_node *ddc_node;
+ struct device_node *ep;
ret = of_property_read_u32(child, "reg", &i);
if (ret || i < 0 || i > 1)
@@ -576,33 +582,54 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
* The output port is port@4 with an external 4-port mux or
* port@2 with the internal 2-port mux.
*/
- port = of_graph_get_port_by_id(child, imx_ldb->lvds_mux ? 4 : 2);
- if (port) {
- struct device_node *endpoint, *remote;
-
- endpoint = of_get_child_by_name(port, "endpoint");
- if (endpoint) {
- remote = of_graph_get_remote_port_parent(endpoint);
- if (remote)
- channel->panel = of_drm_find_panel(remote);
- else
- return -EPROBE_DEFER;
- if (!channel->panel) {
- dev_err(dev, "panel not found: %s\n",
- remote->full_name);
- return -EPROBE_DEFER;
- }
+ ep = of_graph_get_endpoint_by_regs(child,
+ imx_ldb->lvds_mux ? 4 : 2,
+ -1);
+ if (ep) {
+ struct device_node *remote;
+
+ remote = of_graph_get_remote_port_parent(ep);
+ of_node_put(ep);
+ if (remote)
+ channel->panel = of_drm_find_panel(remote);
+ else
+ return -EPROBE_DEFER;
+ of_node_put(remote);
+ if (!channel->panel) {
+ dev_err(dev, "panel not found: %s\n",
+ remote->full_name);
+ return -EPROBE_DEFER;
}
}
- edidp = of_get_property(child, "edid", &channel->edid_len);
- if (edidp) {
- channel->edid = kmemdup(edidp, channel->edid_len,
- GFP_KERNEL);
- } else if (!channel->panel) {
- ret = of_get_drm_display_mode(child, &channel->mode, 0);
- if (!ret)
- channel->mode_valid = 1;
+ ddc_node = of_parse_phandle(child, "ddc-i2c-bus", 0);
+ if (ddc_node) {
+ channel->ddc = of_find_i2c_adapter_by_node(ddc_node);
+ of_node_put(ddc_node);
+ if (!channel->ddc) {
+ dev_warn(dev, "failed to get ddc i2c adapter\n");
+ return -EPROBE_DEFER;
+ }
+ }
+
+ if (!channel->ddc) {
+ /* if no DDC available, fallback to hardcoded EDID */
+ dev_dbg(dev, "no ddc available\n");
+
+ edidp = of_get_property(child, "edid",
+ &channel->edid_len);
+ if (edidp) {
+ channel->edid = kmemdup(edidp,
+ channel->edid_len,
+ GFP_KERNEL);
+ } else if (!channel->panel) {
+ /* fallback to display-timings node */
+ ret = of_get_drm_display_mode(child,
+ &channel->mode,
+ OF_USE_NATIVE_MODE);
+ if (!ret)
+ channel->mode_valid = 1;
+ }
}
channel->bus_format = of_get_bus_format(dev, child);
@@ -647,6 +674,7 @@ static void imx_ldb_unbind(struct device *dev, struct device *master,
channel->encoder.funcs->destroy(&channel->encoder);
kfree(channel->edid);
+ i2c_put_adapter(channel->ddc);
}
}
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index ae7a9fb3b8a2..baf788121287 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -294,8 +294,10 @@ static void imx_tve_encoder_prepare(struct drm_encoder *encoder)
switch (tve->mode) {
case TVE_MODE_VGA:
- imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_GBR888_1X24,
- tve->hsync_pin, tve->vsync_pin);
+ imx_drm_set_bus_config(encoder, MEDIA_BUS_FMT_GBR888_1X24,
+ tve->hsync_pin, tve->vsync_pin,
+ DRM_BUS_FLAG_DE_HIGH |
+ DRM_BUS_FLAG_PIXDATA_NEGEDGE);
break;
case TVE_MODE_TVOUT:
imx_drm_set_bus_format(encoder, MEDIA_BUS_FMT_YUV8_1X24);
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index dee8e8b3523b..fc040417e1e8 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -66,6 +66,7 @@ struct ipu_crtc {
struct ipu_flip_work *flip_work;
int irq;
u32 bus_format;
+ u32 bus_flags;
int di_hsync_pin;
int di_vsync_pin;
};
@@ -271,8 +272,10 @@ static int ipu_crtc_mode_set(struct drm_crtc *crtc,
else
sig_cfg.clkflags = 0;
- sig_cfg.enable_pol = 1;
- sig_cfg.clk_pol = 0;
+ sig_cfg.enable_pol = !(ipu_crtc->bus_flags & DRM_BUS_FLAG_DE_LOW);
+ /* Default to driving pixel data on negative clock edges */
+ sig_cfg.clk_pol = !!(ipu_crtc->bus_flags &
+ DRM_BUS_FLAG_PIXDATA_POSEDGE);
sig_cfg.bus_format = ipu_crtc->bus_format;
sig_cfg.v_to_h_sync = 0;
sig_cfg.hsync_pin = ipu_crtc->di_hsync_pin;
@@ -396,11 +399,12 @@ static void ipu_disable_vblank(struct drm_crtc *crtc)
}
static int ipu_set_interface_pix_fmt(struct drm_crtc *crtc,
- u32 bus_format, int hsync_pin, int vsync_pin)
+ u32 bus_format, int hsync_pin, int vsync_pin, u32 bus_flags)
{
struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
ipu_crtc->bus_format = bus_format;
+ ipu_crtc->bus_flags = bus_flags;
ipu_crtc->di_hsync_pin = hsync_pin;
ipu_crtc->di_vsync_pin = vsync_pin;
@@ -473,7 +477,7 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
ret = imx_drm_add_crtc(drm, &ipu_crtc->base, &ipu_crtc->imx_crtc,
&ipu_crtc->plane[0]->base, &ipu_crtc_helper_funcs,
- ipu_crtc->dev->of_node);
+ pdata->of_node);
if (ret) {
dev_err(ipu_crtc->dev, "adding crtc failed with %d.\n", ret);
goto err_put_resources;
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 681ec6eb77d9..a4bb44118d33 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -38,6 +38,8 @@ static const uint32_t ipu_plane_formats[] = {
DRM_FORMAT_RGBX8888,
DRM_FORMAT_BGRA8888,
DRM_FORMAT_BGRA8888,
+ DRM_FORMAT_UYVY,
+ DRM_FORMAT_VYUY,
DRM_FORMAT_YUYV,
DRM_FORMAT_YVYU,
DRM_FORMAT_YUV420,
@@ -428,7 +430,6 @@ static int ipu_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
if (crtc != plane->crtc)
dev_dbg(plane->dev->dev, "crtc change: %p -> %p\n",
plane->crtc, crtc);
- plane->crtc = crtc;
if (!ipu_plane->enabled)
ipu_plane_enable(ipu_plane);
@@ -461,7 +462,7 @@ static void ipu_plane_destroy(struct drm_plane *plane)
kfree(ipu_plane);
}
-static struct drm_plane_funcs ipu_plane_funcs = {
+static const struct drm_plane_funcs ipu_plane_funcs = {
.update_plane = ipu_update_plane,
.disable_plane = ipu_disable_plane,
.destroy = ipu_plane_destroy,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 363e2c7741e2..2d1fd02cd3d6 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -35,7 +35,6 @@ struct imx_parallel_display {
void *edid;
int edid_len;
u32 bus_format;
- int mode_valid;
struct drm_display_mode mode;
struct drm_panel *panel;
};
@@ -68,17 +67,6 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
num_modes = drm_add_edid_modes(connector, imxpd->edid);
}
- if (imxpd->mode_valid) {
- struct drm_display_mode *mode = drm_mode_create(connector->dev);
-
- if (!mode)
- return -EINVAL;
- drm_mode_copy(mode, &imxpd->mode);
- mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
- drm_mode_probed_add(connector, mode);
- num_modes++;
- }
-
if (np) {
struct drm_display_mode *mode = drm_mode_create(connector->dev);
@@ -115,8 +103,8 @@ static void imx_pd_encoder_dpms(struct drm_encoder *encoder, int mode)
static void imx_pd_encoder_prepare(struct drm_encoder *encoder)
{
struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
-
- imx_drm_set_bus_format(encoder, imxpd->bus_format);
+ imx_drm_set_bus_config(encoder, imxpd->bus_format, 2, 3,
+ imxpd->connector.display_info.bus_flags);
}
static void imx_pd_encoder_commit(struct drm_encoder *encoder)
@@ -203,7 +191,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
{
struct drm_device *drm = data;
struct device_node *np = dev->of_node;
- struct device_node *port;
+ struct device_node *ep;
const u8 *edidp;
struct imx_parallel_display *imxpd;
int ret;
@@ -230,18 +218,18 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
}
/* port@1 is the output port */
- port = of_graph_get_port_by_id(np, 1);
- if (port) {
- struct device_node *endpoint, *remote;
-
- endpoint = of_get_child_by_name(port, "endpoint");
- if (endpoint) {
- remote = of_graph_get_remote_port_parent(endpoint);
- if (remote)
- imxpd->panel = of_drm_find_panel(remote);
- if (!imxpd->panel)
- return -EPROBE_DEFER;
+ ep = of_graph_get_endpoint_by_regs(np, 1, -1);
+ if (ep) {
+ struct device_node *remote;
+
+ remote = of_graph_get_remote_port_parent(ep);
+ of_node_put(ep);
+ if (remote) {
+ imxpd->panel = of_drm_find_panel(remote);
+ of_node_put(remote);
}
+ if (!imxpd->panel)
+ return -EPROBE_DEFER;
}
imxpd->dev = dev;
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index d05ca7901315..0186e500d2a5 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -432,11 +432,6 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
unsigned long pll_rate;
unsigned int factor;
- if (!dpi) {
- dev_err(dpi->dev, "invalid argument\n");
- return -EINVAL;
- }
-
pix_rate = 1000UL * mode->clock;
if (mode->clock <= 74000)
factor = 8 * 3;
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 2d808e59fefd..769559124562 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -695,10 +695,8 @@ static void mtk_dsi_destroy_conn_enc(struct mtk_dsi *dsi)
{
drm_encoder_cleanup(&dsi->encoder);
/* Skip connector cleanup if creation was delegated to the bridge */
- if (dsi->conn.dev) {
- drm_connector_unregister(&dsi->conn);
+ if (dsi->conn.dev)
drm_connector_cleanup(&dsi->conn);
- }
}
static void mtk_dsi_ddp_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 14e64e08909e..d347dca17267 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -182,7 +182,7 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
}
}
- fvv = pllreffreq * testn / testm;
+ fvv = pllreffreq * (n + 1) / (m + 1);
fvv = (fvv - 800000) / 50000;
if (fvv > 15)
@@ -202,6 +202,14 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
WREG_DAC(MGA1064_PIX_PLLC_M, m);
WREG_DAC(MGA1064_PIX_PLLC_N, n);
WREG_DAC(MGA1064_PIX_PLLC_P, p);
+
+ if (mdev->unique_rev_id >= 0x04) {
+ WREG_DAC(0x1a, 0x09);
+ msleep(20);
+ WREG_DAC(0x1a, 0x01);
+
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index fbe304ee6c80..2aec27dbb5bb 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -408,7 +408,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
}
adreno_gpu->memptrs = msm_gem_vaddr(adreno_gpu->memptrs_bo);
- if (!adreno_gpu->memptrs) {
+ if (IS_ERR(adreno_gpu->memptrs)) {
dev_err(drm->dev, "could not vmap memptrs\n");
return -ENOMEM;
}
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index d9759bf3482e..c6cf837c5193 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -159,6 +159,10 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
dev->mode_config.fb_base = paddr;
fbi->screen_base = msm_gem_vaddr_locked(fbdev->bo);
+ if (IS_ERR(fbi->screen_base)) {
+ ret = PTR_ERR(fbi->screen_base);
+ goto fail_unlock;
+ }
fbi->screen_size = fbdev->bo->size;
fbi->fix.smem_start = paddr;
fbi->fix.smem_len = fbdev->bo->size;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 7daf4054dd2b..69836f5685b1 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -398,6 +398,8 @@ void *msm_gem_vaddr_locked(struct drm_gem_object *obj)
return ERR_CAST(pages);
msm_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+ if (msm_obj->vaddr == NULL)
+ return ERR_PTR(-ENOMEM);
}
return msm_obj->vaddr;
}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index b89ca5174863..eb4bb8b2f3a5 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -40,12 +40,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
submit->dev = dev;
submit->gpu = gpu;
+ submit->fence = NULL;
submit->pid = get_pid(task_pid(current));
/* initially, until copy_from_user() and bo lookup succeeds: */
submit->nr_bos = 0;
submit->nr_cmds = 0;
+ INIT_LIST_HEAD(&submit->node);
INIT_LIST_HEAD(&submit->bo_list);
ww_acquire_init(&submit->ticket, &reservation_ww_class);
@@ -75,6 +77,11 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
void __user *userptr =
u64_to_user_ptr(args->bos + (i * sizeof(submit_bo)));
+ /* make sure we don't have garbage flags, in case we hit
+ * error path before flags is initialized:
+ */
+ submit->bos[i].flags = 0;
+
ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
if (ret) {
ret = -EFAULT;
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index b48f73ac6389..0857710c2ff2 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -312,6 +312,9 @@ void msm_rd_dump_submit(struct msm_gem_submit *submit)
struct msm_gem_object *obj = submit->bos[idx].obj;
const char *buf = msm_gem_vaddr_locked(&obj->base);
+ if (IS_ERR(buf))
+ continue;
+
buf += iova - submit->bos[idx].iova;
rd_write_section(rd, RD_GPUADDR,
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 1f14b908b221..42f5359cf988 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -40,6 +40,10 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size)
}
ring->start = msm_gem_vaddr_locked(ring->bo);
+ if (IS_ERR(ring->start)) {
+ ret = PTR_ERR(ring->start);
+ goto fail;
+ }
ring->end = ring->start + (size / 4);
ring->cur = ring->start;
diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig
index 73241c4eb7aa..336ad4de9981 100644
--- a/drivers/gpu/drm/omapdrm/Kconfig
+++ b/drivers/gpu/drm/omapdrm/Kconfig
@@ -2,6 +2,7 @@ config DRM_OMAP
tristate "OMAP DRM"
depends on DRM
depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM
+ select OMAP2_DSS
select DRM_KMS_HELPER
select DRM_KMS_FB_HELPER
select FB_SYS_FILLRECT
diff --git a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
index 225fd8d6ab31..667ca4a24ece 100644
--- a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
+++ b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
@@ -9,6 +9,7 @@
* the Free Software Foundation.
*/
+#include <linux/gpio/consumer.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/platform_device.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
index 8c246c213e06..9594ff7a2b0c 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
@@ -14,7 +14,7 @@
* the Free Software Foundation.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
index 2fd5602880a7..671806ca7d6a 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
@@ -9,7 +9,7 @@
* the Free Software Foundation.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
index e780fd4f8b46..7c2331be8d15 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
@@ -9,7 +9,7 @@
* the Free Software Foundation.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
index 36485c2137ce..2b118071b5a1 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
@@ -14,7 +14,7 @@
#include <linux/backlight.h>
#include <linux/delay.h>
#include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/interrupt.h>
#include <linux/jiffies.h>
#include <linux/module.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
index 458f77bc473d..ac680e1de603 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
@@ -15,6 +15,7 @@
#include <linux/spi/spi.h>
#include <linux/mutex.h>
#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <video/omapdss.h>
#include <video/omap-panel-data.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
index 780cb263a318..38d2920a95e6 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
@@ -15,7 +15,7 @@
#include <linux/delay.h>
#include <linux/spi/spi.h>
#include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/of_gpio.h>
#include <video/omapdss.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
index 529a017602e4..4363fffc87e3 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
@@ -10,7 +10,7 @@
*/
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
index 31efcca801bd..deb416736aad 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
@@ -29,7 +29,7 @@
#include <linux/sched.h>
#include <linux/backlight.h>
#include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/of.h>
#include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
index 03e2beb7b4f0..d93175b03a12 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
@@ -14,7 +14,7 @@
#include <linux/delay.h>
#include <linux/spi/spi.h>
#include <linux/regulator/consumer.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 8730646a0cbb..56c43f355ce3 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -1167,7 +1167,6 @@ static int dsi_regulator_init(struct platform_device *dsidev)
{
struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
struct regulator *vdds_dsi;
- int r;
if (dsi->vdds_dsi_reg != NULL)
return 0;
@@ -1180,15 +1179,6 @@ static int dsi_regulator_init(struct platform_device *dsidev)
return PTR_ERR(vdds_dsi);
}
- if (regulator_can_change_voltage(vdds_dsi)) {
- r = regulator_set_voltage(vdds_dsi, 1800000, 1800000);
- if (r) {
- devm_regulator_put(vdds_dsi);
- DSSERR("can't set the DSI regulator voltage\n");
- return r;
- }
- }
-
dsi->vdds_dsi_reg = vdds_dsi;
return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index f95ff319e68e..3303cfad4838 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -30,6 +30,7 @@
#include <linux/delay.h>
#include <linux/seq_file.h>
#include <linux/clk.h>
+#include <linux/pinctrl/consumer.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/gfp.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
index f892ae157ff3..4d46cdf7a037 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
@@ -33,6 +33,7 @@
#include <linux/gpio.h>
#include <linux/regulator/consumer.h>
#include <linux/component.h>
+#include <linux/of.h>
#include <video/omapdss.h>
#include <sound/omap-hdmi-audio.h>
@@ -100,7 +101,6 @@ static irqreturn_t hdmi_irq_handler(int irq, void *data)
static int hdmi_init_regulator(void)
{
- int r;
struct regulator *reg;
if (hdmi.vdda_reg != NULL)
@@ -114,15 +114,6 @@ static int hdmi_init_regulator(void)
return PTR_ERR(reg);
}
- if (regulator_can_change_voltage(reg)) {
- r = regulator_set_voltage(reg, 1800000, 1800000);
- if (r) {
- devm_regulator_put(reg);
- DSSWARN("can't set the regulator voltage\n");
- return r;
- }
- }
-
hdmi.vdda_reg = reg;
return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
index fa72e735dad2..ef3afe99e487 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
@@ -211,7 +211,7 @@ static void hdmi_core_init(struct hdmi_core_video_config *video_cfg)
static void hdmi_core_powerdown_disable(struct hdmi_core_data *core)
{
DSSDBG("Enter hdmi_core_powerdown_disable\n");
- REG_FLD_MOD(core->base, HDMI_CORE_SYS_SYS_CTRL1, 0x0, 0, 0);
+ REG_FLD_MOD(core->base, HDMI_CORE_SYS_SYS_CTRL1, 0x1, 0, 0);
}
static void hdmi_core_swreset_release(struct hdmi_core_data *core)
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
index a43f7b10e113..9255c0e1e4a7 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
@@ -38,6 +38,7 @@
#include <linux/gpio.h>
#include <linux/regulator/consumer.h>
#include <linux/component.h>
+#include <linux/of.h>
#include <video/omapdss.h>
#include <sound/omap-hdmi-audio.h>
@@ -119,7 +120,6 @@ static irqreturn_t hdmi_irq_handler(int irq, void *data)
static int hdmi_init_regulator(void)
{
- int r;
struct regulator *reg;
if (hdmi.vdda_reg != NULL)
@@ -131,15 +131,6 @@ static int hdmi_init_regulator(void)
return PTR_ERR(reg);
}
- if (regulator_can_change_voltage(reg)) {
- r = regulator_set_voltage(reg, 1800000, 1800000);
- if (r) {
- devm_regulator_put(reg);
- DSSWARN("can't set the regulator voltage\n");
- return r;
- }
- }
-
hdmi.vdda_reg = reg;
return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
index 6a397520cae5..8ab2093daa12 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
@@ -51,8 +51,8 @@ static void hdmi_core_ddc_init(struct hdmi_core_data *core)
{
void __iomem *base = core->base;
const unsigned long long iclk = 266000000; /* DSS L3 ICLK */
- const unsigned ss_scl_high = 4000; /* ns */
- const unsigned ss_scl_low = 4700; /* ns */
+ const unsigned ss_scl_high = 4600; /* ns */
+ const unsigned ss_scl_low = 5400; /* ns */
const unsigned fs_scl_high = 600; /* ns */
const unsigned fs_scl_low = 1300; /* ns */
const unsigned sda_hold = 1000; /* ns */
@@ -458,7 +458,7 @@ static void hdmi_core_write_avi_infoframe(struct hdmi_core_data *core,
c = (ptr[1] >> 6) & 0x3;
m = (ptr[1] >> 4) & 0x3;
- r = (ptr[1] >> 0) & 0x3;
+ r = (ptr[1] >> 0) & 0xf;
itc = (ptr[2] >> 7) & 0x1;
ec = (ptr[2] >> 4) & 0x7;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
index 1f5d19c119ce..f98b750fc499 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
@@ -13,6 +13,7 @@
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/seq_file.h>
#include <video/omapdss.h>
#include "dss.h"
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
index 06e23a7c432c..f1015e8b8267 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
@@ -16,6 +16,7 @@
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/clk.h>
+#include <linux/seq_file.h>
#include <video/omapdss.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
index 13442b9052d1..055f62fca5dc 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
@@ -14,6 +14,7 @@
#include <linux/err.h>
#include <linux/io.h>
#include <linux/platform_device.h>
+#include <linux/seq_file.h>
#include <video/omapdss.h>
#include "dss.h"
diff --git a/drivers/gpu/drm/omapdrm/omap_debugfs.c b/drivers/gpu/drm/omapdrm/omap_debugfs.c
index 6f5fc14fc015..479bf24050f8 100644
--- a/drivers/gpu/drm/omapdrm/omap_debugfs.c
+++ b/drivers/gpu/drm/omapdrm/omap_debugfs.c
@@ -17,6 +17,8 @@
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/seq_file.h>
+
#include <drm/drm_crtc.h>
#include <drm/drm_fb_helper.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index de275a5be1db..4ceed7a9762f 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -27,6 +27,7 @@
#include <linux/module.h>
#include <linux/platform_device.h> /* platform_device() */
#include <linux/sched.h>
+#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/vmalloc.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 94ec06d3d737..f84570d1636c 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -17,6 +17,8 @@
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/seq_file.h>
+
#include <drm/drm_crtc.h>
#include <drm/drm_crtc_helper.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index b97afc281778..03698b6c806c 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -17,6 +17,7 @@
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/seq_file.h>
#include <linux/shmem_fs.h>
#include <linux/spinlock.h>
#include <linux/pfn_t.h>
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 2e216e2ea78c..259cd6e6d71c 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -589,7 +589,8 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev) || ASIC_IS_DCE8(rdev))
radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
/* use frac fb div on RS780/RS880 */
- if ((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880))
+ if (((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880))
+ && !radeon_crtc->ss_enabled)
radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
if (ASIC_IS_DCE32(rdev) && mode->clock > 165000)
radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
@@ -626,7 +627,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
if (radeon_crtc->ss.refdiv) {
radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
- if (ASIC_IS_AVIVO(rdev))
+ if (rdev->family >= CHIP_RV770)
radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
}
}
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index d0240743a17c..a7e978677937 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2164,7 +2164,7 @@ static void kv_apply_state_adjust_rules(struct radeon_device *rdev,
if (pi->caps_stable_p_state) {
stable_p_state_sclk = (max_limits->sclk * 75) / 100;
- for (i = table->count - 1; i >= 0; i++) {
+ for (i = table->count - 1; i >= 0; i--) {
if (stable_p_state_sclk >= table->entries[i].clk) {
stable_p_state_sclk = table->entries[i].clk;
break;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index e721e6b2766e..21c44b2293bc 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -630,6 +630,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc)
/*
* GPU helpers function.
*/
+
+/**
+ * radeon_device_is_virtual - check if we are running is a virtual environment
+ *
+ * Check if the asic has been passed through to a VM (all asics).
+ * Used at driver startup.
+ * Returns true if virtual or false if not.
+ */
+static bool radeon_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+ return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+ return false;
+#endif
+}
+
/**
* radeon_card_posted - check if the hw has already been initialized
*
@@ -643,6 +660,10 @@ bool radeon_card_posted(struct radeon_device *rdev)
{
uint32_t reg;
+ /* for pass through, always force asic_init */
+ if (radeon_device_is_virtual())
+ return false;
+
/* required for EFI mode on macbook2,1 which uses an r5xx asic */
if (efi_enabled(EFI_BOOT) &&
(rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
@@ -1631,7 +1652,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
radeon_agp_suspend(rdev);
pci_save_state(dev->pdev);
- if (freeze && rdev->family >= CHIP_R600) {
+ if (freeze && rdev->family >= CHIP_CEDAR) {
rdev->asic->asic_reset(rdev, true);
pci_restore_state(dev->pdev);
} else if (suspend) {
diff --git a/drivers/gpu/drm/sti/sti_crtc.c b/drivers/gpu/drm/sti/sti_crtc.c
index 505620c7c2c8..e04deedabd4a 100644
--- a/drivers/gpu/drm/sti/sti_crtc.c
+++ b/drivers/gpu/drm/sti/sti_crtc.c
@@ -51,15 +51,6 @@ static void sti_crtc_disabling(struct drm_crtc *crtc)
mixer->status = STI_MIXER_DISABLING;
}
-static bool sti_crtc_mode_fixup(struct drm_crtc *crtc,
- const struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode)
-{
- /* accept the provided drm_display_mode, do not fix it up */
- drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V);
- return true;
-}
-
static int
sti_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode)
{
@@ -230,7 +221,6 @@ static void sti_crtc_atomic_flush(struct drm_crtc *crtc,
static const struct drm_crtc_helper_funcs sti_crtc_helper_funcs = {
.enable = sti_crtc_enable,
.disable = sti_crtc_disabling,
- .mode_fixup = sti_crtc_mode_fixup,
.mode_set = drm_helper_crtc_mode_set,
.mode_set_nofb = sti_crtc_mode_set_nofb,
.mode_set_base = drm_helper_crtc_mode_set_base,
diff --git a/drivers/gpu/drm/sti/sti_vtg.c b/drivers/gpu/drm/sti/sti_vtg.c
index 32c7986b63ab..6bf4ce466d20 100644
--- a/drivers/gpu/drm/sti/sti_vtg.c
+++ b/drivers/gpu/drm/sti/sti_vtg.c
@@ -437,7 +437,7 @@ static int vtg_probe(struct platform_device *pdev)
return -EPROBE_DEFER;
} else {
vtg->irq = platform_get_irq(pdev, 0);
- if (IS_ERR_VALUE(vtg->irq)) {
+ if (vtg->irq < 0) {
DRM_ERROR("Failed to get VTG interrupt\n");
return vtg->irq;
}
@@ -447,7 +447,7 @@ static int vtg_probe(struct platform_device *pdev)
ret = devm_request_threaded_irq(dev, vtg->irq, vtg_irq,
vtg_irq_thread, IRQF_ONESHOT,
dev_name(dev), vtg);
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
DRM_ERROR("Failed to register VTG interrupt\n");
return ret;
}
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 99510e64e91a..a4b357db8856 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -1,6 +1,6 @@
config DRM_SUN4I
tristate "DRM Support for Allwinner A10 Display Engine"
- depends on DRM && ARM
+ depends on DRM && ARM && COMMON_CLK
depends on ARCH_SUNXI || COMPILE_TEST
select DRM_GEM_CMA_HELPER
select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index f7a15c1a93bf..3ab560450a82 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -190,7 +190,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
/* Get the physical address of the buffer in memory */
gem = drm_fb_cma_get_gem_obj(fb, 0);
- DRM_DEBUG_DRIVER("Using GEM @ 0x%x\n", gem->paddr);
+ DRM_DEBUG_DRIVER("Using GEM @ %pad\n", &gem->paddr);
/* Compute the start of the displayed memory */
bpp = drm_format_plane_cpp(fb->pixel_format, 0);
@@ -198,7 +198,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
paddr += (state->src_x >> 16) * bpp;
paddr += (state->src_y >> 16) * fb->pitches[0];
- DRM_DEBUG_DRIVER("Setting buffer address to 0x%x\n", paddr);
+ DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr);
/* Write the 32 lower bits of the address (in bits) */
lo_paddr = paddr << 3;
diff --git a/drivers/gpu/drm/sun4i/sun4i_dotclock.c b/drivers/gpu/drm/sun4i/sun4i_dotclock.c
index 3ff668cb463c..5b3463197c48 100644
--- a/drivers/gpu/drm/sun4i/sun4i_dotclock.c
+++ b/drivers/gpu/drm/sun4i/sun4i_dotclock.c
@@ -72,14 +72,40 @@ static unsigned long sun4i_dclk_recalc_rate(struct clk_hw *hw,
static long sun4i_dclk_round_rate(struct clk_hw *hw, unsigned long rate,
unsigned long *parent_rate)
{
- return *parent_rate / DIV_ROUND_CLOSEST(*parent_rate, rate);
+ unsigned long best_parent = 0;
+ u8 best_div = 1;
+ int i;
+
+ for (i = 6; i < 127; i++) {
+ unsigned long ideal = rate * i;
+ unsigned long rounded;
+
+ rounded = clk_hw_round_rate(clk_hw_get_parent(hw),
+ ideal);
+
+ if (rounded == ideal) {
+ best_parent = rounded;
+ best_div = i;
+ goto out;
+ }
+
+ if ((rounded < ideal) && (rounded > best_parent)) {
+ best_parent = rounded;
+ best_div = i;
+ }
+ }
+
+out:
+ *parent_rate = best_parent;
+
+ return best_parent / best_div;
}
static int sun4i_dclk_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
struct sun4i_dclk *dclk = hw_to_dclk(hw);
- int div = DIV_ROUND_CLOSEST(parent_rate, rate);
+ u8 div = parent_rate / rate;
return regmap_update_bits(dclk->regmap, SUN4I_TCON0_DCLK_REG,
GENMASK(6, 0), div);
@@ -127,10 +153,14 @@ int sun4i_dclk_create(struct device *dev, struct sun4i_tcon *tcon)
const char *clk_name, *parent_name;
struct clk_init_data init;
struct sun4i_dclk *dclk;
+ int ret;
parent_name = __clk_get_name(tcon->sclk0);
- of_property_read_string_index(dev->of_node, "clock-output-names", 0,
- &clk_name);
+ ret = of_property_read_string_index(dev->of_node,
+ "clock-output-names", 0,
+ &clk_name);
+ if (ret)
+ return ret;
dclk = devm_kzalloc(dev, sizeof(*dclk), GFP_KERNEL);
if (!dclk)
@@ -140,6 +170,7 @@ int sun4i_dclk_create(struct device *dev, struct sun4i_tcon *tcon)
init.ops = &sun4i_dclk_ops;
init.parent_names = &parent_name;
init.num_parents = 1;
+ init.flags = CLK_SET_RATE_PARENT;
dclk->regmap = tcon->regs;
dclk->hw.init = &init;
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 76e922bb60e5..257d2b4f3645 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -24,34 +24,6 @@
#include "sun4i_layer.h"
#include "sun4i_tcon.h"
-static int sun4i_drv_connector_plug_all(struct drm_device *drm)
-{
- struct drm_connector *connector, *failed;
- int ret;
-
- mutex_lock(&drm->mode_config.mutex);
- list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
- ret = drm_connector_register(connector);
- if (ret) {
- failed = connector;
- goto err;
- }
- }
- mutex_unlock(&drm->mode_config.mutex);
- return 0;
-
-err:
- list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
- if (failed == connector)
- break;
-
- drm_connector_unregister(connector);
- }
- mutex_unlock(&drm->mode_config.mutex);
-
- return ret;
-}
-
static int sun4i_drv_enable_vblank(struct drm_device *drm, unsigned int pipe)
{
struct sun4i_drv *drv = drm->dev_private;
@@ -125,6 +97,22 @@ static struct drm_driver sun4i_drv_driver = {
.disable_vblank = sun4i_drv_disable_vblank,
};
+static void sun4i_remove_framebuffers(void)
+{
+ struct apertures_struct *ap;
+
+ ap = alloc_apertures(1);
+ if (!ap)
+ return;
+
+ /* The framebuffer can be located anywhere in RAM */
+ ap->ranges[0].base = 0;
+ ap->ranges[0].size = ~0;
+
+ remove_conflicting_framebuffers(ap, "sun4i-drm-fb", false);
+ kfree(ap);
+}
+
static int sun4i_drv_bind(struct device *dev)
{
struct drm_device *drm;
@@ -172,6 +160,9 @@ static int sun4i_drv_bind(struct device *dev)
}
drm->irq_enabled = true;
+ /* Remove early framebuffers (ie. simplefb) */
+ sun4i_remove_framebuffers();
+
/* Create our framebuffer */
drv->fbdev = sun4i_framebuffer_init(drm);
if (IS_ERR(drv->fbdev)) {
@@ -187,7 +178,7 @@ static int sun4i_drv_bind(struct device *dev)
if (ret)
goto free_drm;
- ret = sun4i_drv_connector_plug_all(drm);
+ ret = drm_connector_register_all(drm);
if (ret)
goto unregister_drm;
@@ -204,6 +195,7 @@ static void sun4i_drv_unbind(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
+ drm_connector_unregister_all(drm);
drm_dev_unregister(drm);
drm_kms_helper_poll_fini(drm);
sun4i_framebuffer_free(drm);
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index ab6494818050..aaffe9e64ffb 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -54,8 +54,13 @@ static int sun4i_rgb_get_modes(struct drm_connector *connector)
static int sun4i_rgb_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
{
+ struct sun4i_rgb *rgb = drm_connector_to_sun4i_rgb(connector);
+ struct sun4i_drv *drv = rgb->drv;
+ struct sun4i_tcon *tcon = drv->tcon;
u32 hsync = mode->hsync_end - mode->hsync_start;
u32 vsync = mode->vsync_end - mode->vsync_start;
+ unsigned long rate = mode->clock * 1000;
+ long rounded_rate;
DRM_DEBUG_DRIVER("Validating modes...\n");
@@ -87,6 +92,15 @@ static int sun4i_rgb_mode_valid(struct drm_connector *connector,
DRM_DEBUG_DRIVER("Vertical parameters OK\n");
+ rounded_rate = clk_round_rate(tcon->dclk, rate);
+ if (rounded_rate < rate)
+ return MODE_CLOCK_LOW;
+
+ if (rounded_rate > rate)
+ return MODE_CLOCK_HIGH;
+
+ DRM_DEBUG_DRIVER("Clock rate OK\n");
+
return MODE_OK;
}
@@ -203,7 +217,7 @@ int sun4i_rgb_init(struct drm_device *drm)
int ret;
/* If we don't have a panel, there's no point in going on */
- if (!tcon->panel)
+ if (IS_ERR(tcon->panel))
return -ENODEV;
rgb = devm_kzalloc(drm->dev, sizeof(*rgb), GFP_KERNEL);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 9f19b0e08560..652385f09735 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -425,11 +425,11 @@ static struct drm_panel *sun4i_tcon_find_panel(struct device_node *node)
remote = of_graph_get_remote_port_parent(end_node);
if (!remote) {
- DRM_DEBUG_DRIVER("Enable to parse remote node\n");
+ DRM_DEBUG_DRIVER("Unable to parse remote node\n");
return ERR_PTR(-EINVAL);
}
- return of_drm_find_panel(remote);
+ return of_drm_find_panel(remote) ?: ERR_PTR(-EPROBE_DEFER);
}
static int sun4i_tcon_bind(struct device *dev, struct device *master,
@@ -490,7 +490,11 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master,
return 0;
}
- return sun4i_rgb_init(drm);
+ ret = sun4i_rgb_init(drm);
+ if (ret < 0)
+ goto err_free_clocks;
+
+ return 0;
err_free_clocks:
sun4i_tcon_free_clocks(tcon);
@@ -522,12 +526,13 @@ static int sun4i_tcon_probe(struct platform_device *pdev)
* Defer the probe.
*/
panel = sun4i_tcon_find_panel(node);
- if (IS_ERR(panel)) {
- /*
- * If we don't have a panel endpoint, just go on
- */
- if (PTR_ERR(panel) != -ENODEV)
- return -EPROBE_DEFER;
+
+ /*
+ * If we don't have a panel endpoint, just go on
+ */
+ if (PTR_ERR(panel) == -EPROBE_DEFER) {
+ DRM_DEBUG_DRIVER("Still waiting for our panel. Deferring...\n");
+ return -EPROBE_DEFER;
}
return component_add(&pdev->dev, &sun4i_tcon_ops);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 7716f42f8aab..6b8c5b3bf588 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -342,7 +342,7 @@ static int tfp410_probe(struct platform_device *pdev)
tfp410_mod->gpio = of_get_named_gpio_flags(node, "powerdn-gpio",
0, NULL);
- if (IS_ERR_VALUE(tfp410_mod->gpio)) {
+ if (tfp410_mod->gpio < 0) {
dev_warn(&pdev->dev, "No power down GPIO\n");
} else {
ret = gpio_request(tfp410_mod->gpio, "DVI_PDn");
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 904d0754ad78..0f18b76c7906 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -456,14 +456,6 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
WARN_ON_ONCE(dlist_next - dlist_start != vc4_state->mm.size);
- HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
- vc4_state->mm.start);
-
- if (debug_dump_regs) {
- DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
- vc4_hvs_dump_state(dev);
- }
-
if (crtc->state->event) {
unsigned long flags;
@@ -473,8 +465,20 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
spin_lock_irqsave(&dev->event_lock, flags);
vc4_crtc->event = crtc->state->event;
- spin_unlock_irqrestore(&dev->event_lock, flags);
crtc->state->event = NULL;
+
+ HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
+ vc4_state->mm.start);
+
+ spin_unlock_irqrestore(&dev->event_lock, flags);
+ } else {
+ HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
+ vc4_state->mm.start);
+ }
+
+ if (debug_dump_regs) {
+ DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
+ vc4_hvs_dump_state(dev);
}
}
@@ -500,12 +504,17 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
{
struct drm_crtc *crtc = &vc4_crtc->base;
struct drm_device *dev = crtc->dev;
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
+ struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+ u32 chan = vc4_crtc->channel;
unsigned long flags;
spin_lock_irqsave(&dev->event_lock, flags);
- if (vc4_crtc->event) {
+ if (vc4_crtc->event &&
+ (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)))) {
drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
vc4_crtc->event = NULL;
+ drm_crtc_vblank_put(crtc);
}
spin_unlock_irqrestore(&dev->event_lock, flags);
}
@@ -556,6 +565,7 @@ vc4_async_page_flip_complete(struct vc4_seqno_cb *cb)
spin_unlock_irqrestore(&dev->event_lock, flags);
}
+ drm_crtc_vblank_put(crtc);
drm_framebuffer_unreference(flip_state->fb);
kfree(flip_state);
@@ -598,6 +608,8 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
return ret;
}
+ WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
/* Immediately update the plane's legacy fb pointer, so that later
* modeset prep sees the state that will be present when the semaphore
* is released.
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 3446ece21b4a..250ed7e3754c 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -66,12 +66,12 @@ static const struct file_operations vc4_drm_fops = {
};
static const struct drm_ioctl_desc vc4_drm_ioctls[] = {
- DRM_IOCTL_DEF_DRV(VC4_SUBMIT_CL, vc4_submit_cl_ioctl, 0),
- DRM_IOCTL_DEF_DRV(VC4_WAIT_SEQNO, vc4_wait_seqno_ioctl, 0),
- DRM_IOCTL_DEF_DRV(VC4_WAIT_BO, vc4_wait_bo_ioctl, 0),
- DRM_IOCTL_DEF_DRV(VC4_CREATE_BO, vc4_create_bo_ioctl, 0),
- DRM_IOCTL_DEF_DRV(VC4_MMAP_BO, vc4_mmap_bo_ioctl, 0),
- DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, 0),
+ DRM_IOCTL_DEF_DRV(VC4_SUBMIT_CL, vc4_submit_cl_ioctl, DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(VC4_WAIT_SEQNO, vc4_wait_seqno_ioctl, DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(VC4_WAIT_BO, vc4_wait_bo_ioctl, DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(VC4_CREATE_BO, vc4_create_bo_ioctl, DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(VC4_MMAP_BO, vc4_mmap_bo_ioctl, DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, DRM_RENDER_ALLOW),
DRM_IOCTL_DEF_DRV(VC4_GET_HANG_STATE, vc4_get_hang_state_ioctl,
DRM_ROOT_ONLY),
};
@@ -91,7 +91,7 @@ static struct drm_driver vc4_drm_driver = {
.enable_vblank = vc4_enable_vblank,
.disable_vblank = vc4_disable_vblank,
- .get_vblank_counter = drm_vblank_count,
+ .get_vblank_counter = drm_vblank_no_hw_counter,
#if defined(CONFIG_DEBUG_FS)
.debugfs_init = vc4_debugfs_init,
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index cb37751bc99f..861a623bc185 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -117,10 +117,18 @@ static int vc4_atomic_commit(struct drm_device *dev,
return -ENOMEM;
/* Make sure that any outstanding modesets have finished. */
- ret = down_interruptible(&vc4->async_modeset);
- if (ret) {
- kfree(c);
- return ret;
+ if (nonblock) {
+ ret = down_trylock(&vc4->async_modeset);
+ if (ret) {
+ kfree(c);
+ return -EBUSY;
+ }
+ } else {
+ ret = down_interruptible(&vc4->async_modeset);
+ if (ret) {
+ kfree(c);
+ return ret;
+ }
}
ret = drm_atomic_helper_prepare_planes(dev, state);
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 6163b95c5411..f99eece4cc97 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -341,6 +341,10 @@
#define SCALER_DISPLACT0 0x00000030
#define SCALER_DISPLACT1 0x00000034
#define SCALER_DISPLACT2 0x00000038
+#define SCALER_DISPLACTX(x) (SCALER_DISPLACT0 + \
+ (x) * (SCALER_DISPLACT1 - \
+ SCALER_DISPLACT0))
+
#define SCALER_DISPCTRL0 0x00000040
# define SCALER_DISPCTRLX_ENABLE BIT(31)
# define SCALER_DISPCTRLX_RESET BIT(30)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 6de283c8fa3e..f0374f9b56ca 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -28,6 +28,7 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/frame.h>
#include <asm/hypervisor.h>
#include "drmP.h"
#include "vmwgfx_msg.h"
@@ -194,7 +195,7 @@ static int vmw_send_msg(struct rpc_channel *channel, const char *msg)
return -EINVAL;
}
-
+STACK_FRAME_NON_STANDARD(vmw_send_msg);
/**
@@ -304,6 +305,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
return 0;
}
+STACK_FRAME_NON_STANDARD(vmw_recv_msg);
/**
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index 498b37e39058..e1e31e9e67cd 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -85,7 +85,7 @@ static int _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
err = devm_request_irq(host->dev, host->intr_syncpt_irq,
syncpt_thresh_isr, IRQF_SHARED,
"host1x_syncpt", host);
- if (IS_ERR_VALUE(err)) {
+ if (err < 0) {
WARN_ON(1);
return err;
}
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index abb98c77bad2..99dcacf05b99 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -997,7 +997,7 @@ struct ipu_platform_reg {
};
/* These must be in the order of the corresponding device tree port nodes */
-static const struct ipu_platform_reg client_reg[] = {
+static struct ipu_platform_reg client_reg[] = {
{
.pdata = {
.csi = 0,
@@ -1048,7 +1048,7 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
mutex_unlock(&ipu_client_id_mutex);
for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
- const struct ipu_platform_reg *reg = &client_reg[i];
+ struct ipu_platform_reg *reg = &client_reg[i];
struct platform_device *pdev;
struct device_node *of_node;
@@ -1070,6 +1070,7 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
pdev->dev.parent = dev;
+ reg->pdata.of_node = of_node;
ret = platform_device_add_data(pdev, &reg->pdata,
sizeof(reg->pdata));
if (!ret)
diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c
index aad8c162a825..0cd4f7216239 100644
--- a/drivers/hid/hid-elo.c
+++ b/drivers/hid/hid-elo.c
@@ -261,7 +261,7 @@ static void elo_remove(struct hid_device *hdev)
struct elo_priv *priv = hid_get_drvdata(hdev);
hid_hw_stop(hdev);
- flush_workqueue(wq);
+ cancel_delayed_work_sync(&priv->work);
kfree(priv);
}
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index c741f5e50a66..fb6f1f447279 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -61,6 +61,7 @@ MODULE_LICENSE("GPL");
#define MT_QUIRK_ALWAYS_VALID (1 << 4)
#define MT_QUIRK_VALID_IS_INRANGE (1 << 5)
#define MT_QUIRK_VALID_IS_CONFIDENCE (1 << 6)
+#define MT_QUIRK_CONFIDENCE (1 << 7)
#define MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE (1 << 8)
#define MT_QUIRK_NO_AREA (1 << 9)
#define MT_QUIRK_IGNORE_DUPLICATES (1 << 10)
@@ -78,6 +79,7 @@ struct mt_slot {
__s32 contactid; /* the device ContactID assigned to this slot */
bool touch_state; /* is the touch valid? */
bool inrange_state; /* is the finger in proximity of the sensor? */
+ bool confidence_state; /* is the touch made by a finger? */
};
struct mt_class {
@@ -503,10 +505,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
return 1;
case HID_DG_CONFIDENCE:
if (cls->name == MT_CLS_WIN_8 &&
- field->application == HID_DG_TOUCHPAD) {
- cls->quirks &= ~MT_QUIRK_ALWAYS_VALID;
- cls->quirks |= MT_QUIRK_VALID_IS_CONFIDENCE;
- }
+ field->application == HID_DG_TOUCHPAD)
+ cls->quirks |= MT_QUIRK_CONFIDENCE;
mt_store_field(usage, td, hi);
return 1;
case HID_DG_TIPSWITCH:
@@ -619,6 +619,7 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
return;
if (td->curvalid || (td->mtclass.quirks & MT_QUIRK_ALWAYS_VALID)) {
+ int active;
int slotnum = mt_compute_slot(td, input);
struct mt_slot *s = &td->curdata;
struct input_mt *mt = input->mt;
@@ -633,10 +634,14 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
return;
}
+ if (!(td->mtclass.quirks & MT_QUIRK_CONFIDENCE))
+ s->confidence_state = 1;
+ active = (s->touch_state || s->inrange_state) &&
+ s->confidence_state;
+
input_mt_slot(input, slotnum);
- input_mt_report_slot_state(input, MT_TOOL_FINGER,
- s->touch_state || s->inrange_state);
- if (s->touch_state || s->inrange_state) {
+ input_mt_report_slot_state(input, MT_TOOL_FINGER, active);
+ if (active) {
/* this finger is in proximity of the sensor */
int wide = (s->w > s->h);
/* divided by two to match visual scale of touch */
@@ -701,6 +706,8 @@ static void mt_process_mt_event(struct hid_device *hid, struct hid_field *field,
td->curdata.touch_state = value;
break;
case HID_DG_CONFIDENCE:
+ if (quirks & MT_QUIRK_CONFIDENCE)
+ td->curdata.confidence_state = value;
if (quirks & MT_QUIRK_VALID_IS_CONFIDENCE)
td->curvalid = value;
break;
@@ -1401,6 +1408,11 @@ static const struct hid_device_id mt_devices[] = {
MT_USB_DEVICE(USB_VENDOR_ID_NOVATEK,
USB_DEVICE_ID_NOVATEK_PCT) },
+ /* Ntrig Panel */
+ { .driver_data = MT_CLS_NSMU,
+ HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+ USB_VENDOR_ID_NTRIG, 0x1b05) },
+
/* PixArt optical touch screen */
{ .driver_data = MT_CLS_INRANGE_CONTACTNUMBER,
MT_USB_DEVICE(USB_VENDOR_ID_PIXART,
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 2f1ddca6f2e0..700145b15088 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -516,13 +516,13 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
goto inval;
} else if (uref->usage_index >= field->report_count)
goto inval;
-
- else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
- (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
- uref->usage_index + uref_multi->num_values > field->report_count))
- goto inval;
}
+ if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
+ (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+ uref->usage_index + uref_multi->num_values > field->report_count))
+ goto inval;
+
switch (cmd) {
case HIDIOCGUSAGE:
uref->value = field->value[uref->usage_index];
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index c43318d3416e..2ac87d553e22 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -35,6 +35,7 @@
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/sched.h>
+#include <linux/ctype.h>
#include <linux/i8k.h>
@@ -66,11 +67,13 @@
static DEFINE_MUTEX(i8k_mutex);
static char bios_version[4];
+static char bios_machineid[16];
static struct device *i8k_hwmon_dev;
static u32 i8k_hwmon_flags;
static uint i8k_fan_mult = I8K_FAN_MULT;
static uint i8k_pwm_mult;
static uint i8k_fan_max = I8K_FAN_HIGH;
+static bool disallow_fan_type_call;
#define I8K_HWMON_HAVE_TEMP1 (1 << 0)
#define I8K_HWMON_HAVE_TEMP2 (1 << 1)
@@ -94,13 +97,13 @@ module_param(ignore_dmi, bool, 0);
MODULE_PARM_DESC(ignore_dmi, "Continue probing hardware even if DMI data does not match");
#if IS_ENABLED(CONFIG_I8K)
-static bool restricted;
+static bool restricted = true;
module_param(restricted, bool, 0);
-MODULE_PARM_DESC(restricted, "Allow fan control if SYS_ADMIN capability set");
+MODULE_PARM_DESC(restricted, "Restrict fan control and serial number to CAP_SYS_ADMIN (default: 1)");
static bool power_status;
module_param(power_status, bool, 0600);
-MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k");
+MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k (default: 0)");
#endif
static uint fan_mult;
@@ -235,14 +238,28 @@ static int i8k_get_fan_speed(int fan)
/*
* Read the fan type.
*/
-static int i8k_get_fan_type(int fan)
+static int _i8k_get_fan_type(int fan)
{
struct smm_regs regs = { .eax = I8K_SMM_GET_FAN_TYPE, };
+ if (disallow_fan_type_call)
+ return -EINVAL;
+
regs.ebx = fan & 0xff;
return i8k_smm(&regs) ? : regs.eax & 0xff;
}
+static int i8k_get_fan_type(int fan)
+{
+ /* I8K_SMM_GET_FAN_TYPE SMM call is expensive, so cache values */
+ static int types[2] = { INT_MIN, INT_MIN };
+
+ if (types[fan] == INT_MIN)
+ types[fan] = _i8k_get_fan_type(fan);
+
+ return types[fan];
+}
+
/*
* Read the fan nominal rpm for specific fan speed.
*/
@@ -387,14 +404,20 @@ i8k_ioctl_unlocked(struct file *fp, unsigned int cmd, unsigned long arg)
switch (cmd) {
case I8K_BIOS_VERSION:
+ if (!isdigit(bios_version[0]) || !isdigit(bios_version[1]) ||
+ !isdigit(bios_version[2]))
+ return -EINVAL;
+
val = (bios_version[0] << 16) |
(bios_version[1] << 8) | bios_version[2];
break;
case I8K_MACHINE_ID:
- memset(buff, 0, 16);
- strlcpy(buff, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
- sizeof(buff));
+ if (restricted && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ memset(buff, 0, sizeof(buff));
+ strlcpy(buff, bios_machineid, sizeof(buff));
break;
case I8K_FN_STATUS:
@@ -511,7 +534,7 @@ static int i8k_proc_show(struct seq_file *seq, void *offset)
seq_printf(seq, "%s %s %s %d %d %d %d %d %d %d\n",
I8K_PROC_FMT,
bios_version,
- i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+ (restricted && !capable(CAP_SYS_ADMIN)) ? "-1" : bios_machineid,
cpu_temp,
left_fan, right_fan, left_speed, right_speed,
ac_power, fn_key);
@@ -718,6 +741,9 @@ static struct attribute *i8k_attrs[] = {
static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr,
int index)
{
+ if (disallow_fan_type_call &&
+ (index == 9 || index == 12))
+ return 0;
if (index >= 0 && index <= 1 &&
!(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1))
return 0;
@@ -767,13 +793,17 @@ static int __init i8k_init_hwmon(void)
if (err >= 0)
i8k_hwmon_flags |= I8K_HWMON_HAVE_TEMP4;
- /* First fan attributes, if fan type is OK */
- err = i8k_get_fan_type(0);
+ /* First fan attributes, if fan status or type is OK */
+ err = i8k_get_fan_status(0);
+ if (err < 0)
+ err = i8k_get_fan_type(0);
if (err >= 0)
i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN1;
- /* Second fan attributes, if fan type is OK */
- err = i8k_get_fan_type(1);
+ /* Second fan attributes, if fan status or type is OK */
+ err = i8k_get_fan_status(1);
+ if (err < 0)
+ err = i8k_get_fan_type(1);
if (err >= 0)
i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2;
@@ -929,12 +959,14 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = {
MODULE_DEVICE_TABLE(dmi, i8k_dmi_table);
-static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
+/*
+ * On some machines once I8K_SMM_GET_FAN_TYPE is issued then CPU fan speed
+ * randomly going up and down due to bug in Dell SMM or BIOS. Here is blacklist
+ * of affected Dell machines for which we disallow I8K_SMM_GET_FAN_TYPE call.
+ * See bug: https://bugzilla.kernel.org/show_bug.cgi?id=100121
+ */
+static struct dmi_system_id i8k_blacklist_fan_type_dmi_table[] __initdata = {
{
- /*
- * CPU fan speed going up and down on Dell Studio XPS 8000
- * for unknown reasons.
- */
.ident = "Dell Studio XPS 8000",
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -942,16 +974,19 @@ static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
},
},
{
- /*
- * CPU fan speed going up and down on Dell Studio XPS 8100
- * for unknown reasons.
- */
.ident = "Dell Studio XPS 8100",
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"),
},
},
+ {
+ .ident = "Dell Inspiron 580",
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Inspiron 580 "),
+ },
+ },
{ }
};
@@ -966,8 +1001,7 @@ static int __init i8k_probe(void)
/*
* Get DMI information
*/
- if (!dmi_check_system(i8k_dmi_table) ||
- dmi_check_system(i8k_blacklist_dmi_table)) {
+ if (!dmi_check_system(i8k_dmi_table)) {
if (!ignore_dmi && !force)
return -ENODEV;
@@ -978,8 +1012,13 @@ static int __init i8k_probe(void)
i8k_get_dmi_data(DMI_BIOS_VERSION));
}
+ if (dmi_check_system(i8k_blacklist_fan_type_dmi_table))
+ disallow_fan_type_call = true;
+
strlcpy(bios_version, i8k_get_dmi_data(DMI_BIOS_VERSION),
sizeof(bios_version));
+ strlcpy(bios_machineid, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+ sizeof(bios_machineid));
/*
* Get SMM Dell signature
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index 952fe692d764..24e395c5907d 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -58,7 +58,7 @@ static const u8 REG_TEMP_MAX[4] = { 0x34, 0x30, 0x31, 0x32 };
*/
static int apd = -1;
module_param(apd, bint, 0);
-MODULE_PARM_DESC(init, "Set to zero to disable anti-parallel diode mode");
+MODULE_PARM_DESC(apd, "Set to zero to disable anti-parallel diode mode");
struct temperature {
s8 degrees;
diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index eb97a9241d17..15aa49d082c4 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -172,9 +172,9 @@ static void do_read_registers_on_cu(void *_data)
*/
static int read_registers(struct fam15h_power_data *data)
{
- int this_cpu, ret, cpu;
int core, this_core;
cpumask_var_t mask;
+ int ret, cpu;
ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
if (!ret)
@@ -183,7 +183,6 @@ static int read_registers(struct fam15h_power_data *data)
memset(data->cu_on, 0, sizeof(int) * MAX_CUS);
get_online_cpus();
- this_cpu = smp_processor_id();
/*
* Choose the first online core of each compute unit, and then
@@ -205,12 +204,9 @@ static int read_registers(struct fam15h_power_data *data)
cpumask_set_cpu(cpumask_any(topology_sibling_cpumask(cpu)), mask);
}
- if (cpumask_test_cpu(this_cpu, mask))
- do_read_registers_on_cu(data);
+ on_each_cpu_mask(mask, do_read_registers_on_cu, data, true);
- smp_call_function_many(mask, do_read_registers_on_cu, data, true);
put_online_cpus();
-
free_cpumask_var(mask);
return 0;
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index 0addc84ba948..69166ab3151d 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -77,7 +77,6 @@ static const u8 LM75_REG_TEMP[3] = {
struct lm75_data {
struct i2c_client *client;
struct device *hwmon_dev;
- struct thermal_zone_device *tz;
struct mutex update_lock;
u8 orig_conf;
u8 resolution; /* In bits, between 9 and 12 */
@@ -306,11 +305,9 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
if (IS_ERR(data->hwmon_dev))
return PTR_ERR(data->hwmon_dev);
- data->tz = thermal_zone_of_sensor_register(data->hwmon_dev, 0,
- data->hwmon_dev,
- &lm75_of_thermal_ops);
- if (IS_ERR(data->tz))
- data->tz = NULL;
+ devm_thermal_zone_of_sensor_register(data->hwmon_dev, 0,
+ data->hwmon_dev,
+ &lm75_of_thermal_ops);
dev_info(dev, "%s: sensor '%s'\n",
dev_name(data->hwmon_dev), client->name);
@@ -322,7 +319,6 @@ static int lm75_remove(struct i2c_client *client)
{
struct lm75_data *data = i2c_get_clientdata(client);
- thermal_zone_of_sensor_unregister(data->hwmon_dev, data->tz);
hwmon_device_unregister(data->hwmon_dev);
lm75_write_value(client, LM75_REG_CONF, data->orig_conf);
return 0;
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index c9ff08dbe10c..e30a5939dc0d 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -375,7 +375,7 @@ struct lm90_data {
int kind;
u32 flags;
- int update_interval; /* in milliseconds */
+ unsigned int update_interval; /* in milliseconds */
u8 config_orig; /* Original configuration register value */
u8 convrate_orig; /* Original conversion rate register value */
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index faa6e8dfbaaf..8ef7b713cb1a 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -259,7 +259,6 @@ struct ntc_data {
struct device *dev;
int n_comp;
char name[PLATFORM_NAME_SIZE];
- struct thermal_zone_device *tz;
};
#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO)
@@ -579,6 +578,7 @@ static const struct thermal_zone_of_device_ops ntc_of_thermal_ops = {
static int ntc_thermistor_probe(struct platform_device *pdev)
{
+ struct thermal_zone_device *tz;
const struct of_device_id *of_id =
of_match_device(of_match_ptr(ntc_match), &pdev->dev);
const struct platform_device_id *pdev_id;
@@ -677,12 +677,10 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
dev_info(&pdev->dev, "Thermistor type: %s successfully probed.\n",
pdev_id->name);
- data->tz = thermal_zone_of_sensor_register(data->dev, 0, data->dev,
- &ntc_of_thermal_ops);
- if (IS_ERR(data->tz)) {
+ tz = devm_thermal_zone_of_sensor_register(data->dev, 0, data->dev,
+ &ntc_of_thermal_ops);
+ if (IS_ERR(tz))
dev_dbg(&pdev->dev, "Failed to register to thermal fw.\n");
- data->tz = NULL;
- }
return 0;
err_after_sysfs:
@@ -700,8 +698,6 @@ static int ntc_thermistor_remove(struct platform_device *pdev)
sysfs_remove_group(&data->dev->kobj, &ntc_attr_group);
ntc_iio_channel_release(pdata);
- thermal_zone_of_sensor_unregister(data->dev, data->tz);
-
return 0;
}
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 3e23003f78b0..f9af3935b427 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -40,15 +40,18 @@ struct pwm_fan_ctx {
static int __set_pwm(struct pwm_fan_ctx *ctx, unsigned long pwm)
{
+ struct pwm_args pargs;
unsigned long duty;
int ret = 0;
+ pwm_get_args(ctx->pwm, &pargs);
+
mutex_lock(&ctx->lock);
if (ctx->pwm_value == pwm)
goto exit_set_pwm_err;
- duty = DIV_ROUND_UP(pwm * (ctx->pwm->period - 1), MAX_PWM);
- ret = pwm_config(ctx->pwm, duty, ctx->pwm->period);
+ duty = DIV_ROUND_UP(pwm * (pargs.period - 1), MAX_PWM);
+ ret = pwm_config(ctx->pwm, duty, pargs.period);
if (ret)
goto exit_set_pwm_err;
@@ -215,6 +218,7 @@ static int pwm_fan_probe(struct platform_device *pdev)
{
struct thermal_cooling_device *cdev;
struct pwm_fan_ctx *ctx;
+ struct pwm_args pargs;
struct device *hwmon;
int duty_cycle;
int ret;
@@ -233,11 +237,19 @@ static int pwm_fan_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, ctx);
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to the
+ * atomic PWM API.
+ */
+ pwm_apply_args(ctx->pwm);
+
/* Set duty cycle to maximum allowed */
- duty_cycle = ctx->pwm->period - 1;
+ pwm_get_args(ctx->pwm, &pargs);
+
+ duty_cycle = pargs.period - 1;
ctx->pwm_value = MAX_PWM;
- ret = pwm_config(ctx->pwm, duty_cycle, ctx->pwm->period);
+ ret = pwm_config(ctx->pwm, duty_cycle, pargs.period);
if (ret) {
dev_err(&pdev->dev, "Failed to configure PWM\n");
return ret;
@@ -303,14 +315,16 @@ static int pwm_fan_suspend(struct device *dev)
static int pwm_fan_resume(struct device *dev)
{
struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+ struct pwm_args pargs;
unsigned long duty;
int ret;
if (ctx->pwm_value == 0)
return 0;
- duty = DIV_ROUND_UP(ctx->pwm_value * (ctx->pwm->period - 1), MAX_PWM);
- ret = pwm_config(ctx->pwm, duty, ctx->pwm->period);
+ pwm_get_args(ctx->pwm, &pargs);
+ duty = DIV_ROUND_UP(ctx->pwm_value * (pargs.period - 1), MAX_PWM);
+ ret = pwm_config(ctx->pwm, duty, pargs.period);
if (ret)
return ret;
return pwm_enable(ctx->pwm);
diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c
index 912b449c8303..25b44e68926d 100644
--- a/drivers/hwmon/scpi-hwmon.c
+++ b/drivers/hwmon/scpi-hwmon.c
@@ -31,10 +31,8 @@ struct sensor_data {
};
struct scpi_thermal_zone {
- struct list_head list;
int sensor_id;
struct scpi_sensors *scpi_sensors;
- struct thermal_zone_device *tzd;
};
struct scpi_sensors {
@@ -92,20 +90,6 @@ scpi_show_label(struct device *dev, struct device_attribute *attr, char *buf)
return sprintf(buf, "%s\n", sensor->info.name);
}
-static void
-unregister_thermal_zones(struct platform_device *pdev,
- struct scpi_sensors *scpi_sensors)
-{
- struct list_head *pos;
-
- list_for_each(pos, &scpi_sensors->thermal_zones) {
- struct scpi_thermal_zone *zone;
-
- zone = list_entry(pos, struct scpi_thermal_zone, list);
- thermal_zone_of_sensor_unregister(&pdev->dev, zone->tzd);
- }
-}
-
static struct thermal_zone_of_device_ops scpi_sensor_ops = {
.get_temp = scpi_read_temp,
};
@@ -118,7 +102,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
struct scpi_ops *scpi_ops;
struct device *hwdev, *dev = &pdev->dev;
struct scpi_sensors *scpi_sensors;
- int ret, idx;
+ int idx, ret;
scpi_ops = get_scpi_ops();
if (!scpi_ops)
@@ -232,48 +216,35 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
INIT_LIST_HEAD(&scpi_sensors->thermal_zones);
for (i = 0; i < nr_sensors; i++) {
struct sensor_data *sensor = &scpi_sensors->data[i];
+ struct thermal_zone_device *z;
struct scpi_thermal_zone *zone;
if (sensor->info.class != TEMPERATURE)
continue;
zone = devm_kzalloc(dev, sizeof(*zone), GFP_KERNEL);
- if (!zone) {
- ret = -ENOMEM;
- goto unregister_tzd;
- }
+ if (!zone)
+ return -ENOMEM;
zone->sensor_id = i;
zone->scpi_sensors = scpi_sensors;
- zone->tzd = thermal_zone_of_sensor_register(dev,
- sensor->info.sensor_id, zone, &scpi_sensor_ops);
+ z = devm_thermal_zone_of_sensor_register(dev,
+ sensor->info.sensor_id,
+ zone,
+ &scpi_sensor_ops);
/*
* The call to thermal_zone_of_sensor_register returns
* an error for sensors that are not associated with
* any thermal zones or if the thermal subsystem is
* not configured.
*/
- if (IS_ERR(zone->tzd)) {
+ if (IS_ERR(z)) {
devm_kfree(dev, zone);
continue;
}
- list_add(&zone->list, &scpi_sensors->thermal_zones);
}
return 0;
-
-unregister_tzd:
- unregister_thermal_zones(pdev, scpi_sensors);
- return ret;
-}
-
-static int scpi_hwmon_remove(struct platform_device *pdev)
-{
- struct scpi_sensors *scpi_sensors = platform_get_drvdata(pdev);
-
- unregister_thermal_zones(pdev, scpi_sensors);
-
- return 0;
}
static const struct of_device_id scpi_of_match[] = {
@@ -288,7 +259,6 @@ static struct platform_driver scpi_hwmon_platdrv = {
.of_match_table = scpi_of_match,
},
.probe = scpi_hwmon_probe,
- .remove = scpi_hwmon_remove,
};
module_platform_driver(scpi_hwmon_platdrv);
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 5289aa0980a8..f1e96fd7f445 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -53,7 +53,6 @@
struct tmp102 {
struct i2c_client *client;
struct device *hwmon_dev;
- struct thermal_zone_device *tz;
struct mutex lock;
u16 config_orig;
unsigned long last_update;
@@ -232,10 +231,8 @@ static int tmp102_probe(struct i2c_client *client,
goto fail_restore_config;
}
tmp102->hwmon_dev = hwmon_dev;
- tmp102->tz = thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
- &tmp102_of_thermal_ops);
- if (IS_ERR(tmp102->tz))
- tmp102->tz = NULL;
+ devm_thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
+ &tmp102_of_thermal_ops);
dev_info(dev, "initialized\n");
@@ -251,7 +248,6 @@ static int tmp102_remove(struct i2c_client *client)
{
struct tmp102 *tmp102 = i2c_get_clientdata(client);
- thermal_zone_of_sensor_unregister(tmp102->hwmon_dev, tmp102->tz);
hwmon_device_unregister(tmp102->hwmon_dev);
/* Stop monitoring if device was stopped originally */
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 847d1b5f2c13..688be9e060fc 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -300,13 +300,10 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
if (local_read(&drvdata->mode) == CS_MODE_SYSFS) {
/*
* The trace run will continue with the same allocated trace
- * buffer. As such zero-out the buffer so that we don't end
- * up with stale data.
- *
- * Since the tracer is still enabled drvdata::buf
- * can't be NULL.
+ * buffer. The trace buffer is cleared in tmc_etr_enable_hw(),
+ * so we don't have to explicitly clear it. Also, since the
+ * tracer is still enabled drvdata::buf can't be NULL.
*/
- memset(drvdata->buf, 0, drvdata->size);
tmc_etr_enable_hw(drvdata);
} else {
/*
@@ -315,7 +312,7 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
*/
vaddr = drvdata->vaddr;
paddr = drvdata->paddr;
- drvdata->buf = NULL;
+ drvdata->buf = drvdata->vaddr = NULL;
}
drvdata->reading = false;
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 5443d03a1eec..d08d1ab9bba5 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -385,7 +385,6 @@ static int _coresight_build_path(struct coresight_device *csdev,
int i;
bool found = false;
struct coresight_node *node;
- struct coresight_connection *conn;
/* An activated sink has been found. Enqueue the element */
if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
@@ -394,8 +393,9 @@ static int _coresight_build_path(struct coresight_device *csdev,
/* Not a sink - recursively explore each port found on this element */
for (i = 0; i < csdev->nr_outport; i++) {
- conn = &csdev->conns[i];
- if (_coresight_build_path(conn->child_dev, path) == 0) {
+ struct coresight_device *child_dev = csdev->conns[i].child_dev;
+
+ if (child_dev && _coresight_build_path(child_dev, path) == 0) {
found = true;
break;
}
@@ -425,6 +425,7 @@ out:
struct list_head *coresight_build_path(struct coresight_device *csdev)
{
struct list_head *path;
+ int rc;
path = kzalloc(sizeof(struct list_head), GFP_KERNEL);
if (!path)
@@ -432,9 +433,10 @@ struct list_head *coresight_build_path(struct coresight_device *csdev)
INIT_LIST_HEAD(path);
- if (_coresight_build_path(csdev, path)) {
+ rc = _coresight_build_path(csdev, path);
+ if (rc) {
kfree(path);
- path = NULL;
+ return ERR_PTR(rc);
}
return path;
@@ -507,8 +509,9 @@ int coresight_enable(struct coresight_device *csdev)
goto out;
path = coresight_build_path(csdev);
- if (!path) {
+ if (IS_ERR(path)) {
pr_err("building path(s) failed\n");
+ ret = PTR_ERR(path);
goto out;
}
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 2dd40ddf04de..f167021b8c21 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -965,7 +965,7 @@ config I2C_XILINX
config I2C_XLR
tristate "Netlogic XLR and Sigma Designs I2C support"
- depends on CPU_XLR || ARCH_TANGOX
+ depends on CPU_XLR || ARCH_TANGO
help
This driver enables support for the on-chip I2C interface of
the Netlogic XLR/XLS MIPS processors and Sigma Designs SOCs.
@@ -985,6 +985,7 @@ config I2C_XLP9XX
config I2C_RCAR
tristate "Renesas R-Car I2C Controller"
+ depends on HAS_DMA
depends on ARCH_RENESAS || COMPILE_TEST
select I2C_SLAVE
help
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 921d32bfcda8..f23372669f77 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -1013,7 +1013,7 @@ static int at91_twi_configure_dma(struct at91_twi_dev *dev, u32 phy_addr)
error:
if (ret != -EPROBE_DEFER)
- dev_info(dev->dev, "can't use DMA, error %d\n", ret);
+ dev_info(dev->dev, "can't get DMA channel, continue without DMA support\n");
if (dma->chan_rx)
dma_release_channel(dma->chan_rx);
if (dma->chan_tx)
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 64b1208bca5e..4a60ad214747 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -245,6 +245,13 @@ struct i801_priv {
struct platform_device *mux_pdev;
#endif
struct platform_device *tco_pdev;
+
+ /*
+ * If set to true the host controller registers are reserved for
+ * ACPI AML use. Protected by acpi_lock.
+ */
+ bool acpi_reserved;
+ struct mutex acpi_lock;
};
#define FEATURE_SMBUS_PEC (1 << 0)
@@ -718,6 +725,12 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
int ret = 0, xact = 0;
struct i801_priv *priv = i2c_get_adapdata(adap);
+ mutex_lock(&priv->acpi_lock);
+ if (priv->acpi_reserved) {
+ mutex_unlock(&priv->acpi_lock);
+ return -EBUSY;
+ }
+
pm_runtime_get_sync(&priv->pci_dev->dev);
hwpec = (priv->features & FEATURE_SMBUS_PEC) && (flags & I2C_CLIENT_PEC)
@@ -820,6 +833,7 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
out:
pm_runtime_mark_last_busy(&priv->pci_dev->dev);
pm_runtime_put_autosuspend(&priv->pci_dev->dev);
+ mutex_unlock(&priv->acpi_lock);
return ret;
}
@@ -1257,6 +1271,83 @@ static void i801_add_tco(struct i801_priv *priv)
priv->tco_pdev = pdev;
}
+#ifdef CONFIG_ACPI
+static acpi_status
+i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
+ u64 *value, void *handler_context, void *region_context)
+{
+ struct i801_priv *priv = handler_context;
+ struct pci_dev *pdev = priv->pci_dev;
+ acpi_status status;
+
+ /*
+ * Once BIOS AML code touches the OpRegion we warn and inhibit any
+ * further access from the driver itself. This device is now owned
+ * by the system firmware.
+ */
+ mutex_lock(&priv->acpi_lock);
+
+ if (!priv->acpi_reserved) {
+ priv->acpi_reserved = true;
+
+ dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n");
+ dev_warn(&pdev->dev, "Driver SMBus register access inhibited\n");
+
+ /*
+ * BIOS is accessing the host controller so prevent it from
+ * suspending automatically from now on.
+ */
+ pm_runtime_get_sync(&pdev->dev);
+ }
+
+ if ((function & ACPI_IO_MASK) == ACPI_READ)
+ status = acpi_os_read_port(address, (u32 *)value, bits);
+ else
+ status = acpi_os_write_port(address, (u32)*value, bits);
+
+ mutex_unlock(&priv->acpi_lock);
+
+ return status;
+}
+
+static int i801_acpi_probe(struct i801_priv *priv)
+{
+ struct acpi_device *adev;
+ acpi_status status;
+
+ adev = ACPI_COMPANION(&priv->pci_dev->dev);
+ if (adev) {
+ status = acpi_install_address_space_handler(adev->handle,
+ ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler,
+ NULL, priv);
+ if (ACPI_SUCCESS(status))
+ return 0;
+ }
+
+ return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]);
+}
+
+static void i801_acpi_remove(struct i801_priv *priv)
+{
+ struct acpi_device *adev;
+
+ adev = ACPI_COMPANION(&priv->pci_dev->dev);
+ if (!adev)
+ return;
+
+ acpi_remove_address_space_handler(adev->handle,
+ ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler);
+
+ mutex_lock(&priv->acpi_lock);
+ if (priv->acpi_reserved)
+ pm_runtime_put(&priv->pci_dev->dev);
+ mutex_unlock(&priv->acpi_lock);
+}
+#else
+static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; }
+static inline void i801_acpi_remove(struct i801_priv *priv) { }
+#endif
+
static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
unsigned char temp;
@@ -1274,6 +1365,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
priv->adapter.dev.parent = &dev->dev;
ACPI_COMPANION_SET(&priv->adapter.dev, ACPI_COMPANION(&dev->dev));
priv->adapter.retries = 3;
+ mutex_init(&priv->acpi_lock);
priv->pci_dev = dev;
switch (dev->device) {
@@ -1336,10 +1428,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
return -ENODEV;
}
- err = acpi_check_resource_conflict(&dev->resource[SMBBAR]);
- if (err) {
+ if (i801_acpi_probe(priv))
return -ENODEV;
- }
err = pcim_iomap_regions(dev, 1 << SMBBAR,
dev_driver_string(&dev->dev));
@@ -1348,6 +1438,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
"Failed to request SMBus region 0x%lx-0x%Lx\n",
priv->smba,
(unsigned long long)pci_resource_end(dev, SMBBAR));
+ i801_acpi_remove(priv);
return err;
}
@@ -1412,6 +1503,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
err = i2c_add_adapter(&priv->adapter);
if (err) {
dev_err(&dev->dev, "Failed to add SMBus adapter\n");
+ i801_acpi_remove(priv);
return err;
}
@@ -1438,6 +1530,7 @@ static void i801_remove(struct pci_dev *dev)
i801_del_mux(priv);
i2c_del_adapter(&priv->adapter);
+ i801_acpi_remove(priv);
pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg);
platform_device_unregister(priv->tco_pdev);
diff --git a/drivers/i2c/busses/i2c-octeon.c b/drivers/i2c/busses/i2c-octeon.c
index aa5f01efd826..30ae35146723 100644
--- a/drivers/i2c/busses/i2c-octeon.c
+++ b/drivers/i2c/busses/i2c-octeon.c
@@ -934,8 +934,15 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target,
return result;
for (i = 0; i < length; i++) {
- /* for the last byte TWSI_CTL_AAK must not be set */
- if (i + 1 == length)
+ /*
+ * For the last byte to receive TWSI_CTL_AAK must not be set.
+ *
+ * A special case is I2C_M_RECV_LEN where we don't know the
+ * additional length yet. If recv_len is set we assume we're
+ * not reading the final byte and therefore need to set
+ * TWSI_CTL_AAK.
+ */
+ if ((i + 1 == length) && !(recv_len && i == 0))
final_read = true;
/* clear iflg to allow next event */
@@ -950,12 +957,8 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target,
data[i] = octeon_i2c_data_read(i2c);
if (recv_len && i == 0) {
- if (data[i] > I2C_SMBUS_BLOCK_MAX + 1) {
- dev_err(i2c->dev,
- "%s: read len > I2C_SMBUS_BLOCK_MAX %d\n",
- __func__, data[i]);
+ if (data[i] > I2C_SMBUS_BLOCK_MAX + 1)
return -EPROTO;
- }
length += data[i];
}
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 9aca1b4e2d8d..52407f3c9e1c 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -623,7 +623,7 @@ static struct dma_chan *rcar_i2c_request_dma_chan(struct device *dev,
char *chan_name = dir == DMA_MEM_TO_DEV ? "tx" : "rx";
int ret;
- chan = dma_request_slave_channel_reason(dev, chan_name);
+ chan = dma_request_chan(dev, chan_name);
if (IS_ERR(chan)) {
ret = PTR_ERR(chan);
dev_dbg(dev, "request_channel failed for %s (%d)\n",
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 0b1108d3c2f3..6ecfd76270f2 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -22,6 +22,7 @@
/* The I2C_RDWR ioctl code is written by Kolja Waschk <waschk@telos.de> */
+#include <linux/cdev.h>
#include <linux/device.h>
#include <linux/fs.h>
#include <linux/i2c-dev.h>
@@ -47,9 +48,10 @@ struct i2c_dev {
struct list_head list;
struct i2c_adapter *adap;
struct device *dev;
+ struct cdev cdev;
};
-#define I2C_MINORS 256
+#define I2C_MINORS MINORMASK
static LIST_HEAD(i2c_dev_list);
static DEFINE_SPINLOCK(i2c_dev_list_lock);
@@ -89,7 +91,7 @@ static struct i2c_dev *get_free_i2c_dev(struct i2c_adapter *adap)
return i2c_dev;
}
-static void return_i2c_dev(struct i2c_dev *i2c_dev)
+static void put_i2c_dev(struct i2c_dev *i2c_dev)
{
spin_lock(&i2c_dev_list_lock);
list_del(&i2c_dev->list);
@@ -552,6 +554,12 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
if (IS_ERR(i2c_dev))
return PTR_ERR(i2c_dev);
+ cdev_init(&i2c_dev->cdev, &i2cdev_fops);
+ i2c_dev->cdev.owner = THIS_MODULE;
+ res = cdev_add(&i2c_dev->cdev, MKDEV(I2C_MAJOR, adap->nr), 1);
+ if (res)
+ goto error_cdev;
+
/* register this i2c device with the driver core */
i2c_dev->dev = device_create(i2c_dev_class, &adap->dev,
MKDEV(I2C_MAJOR, adap->nr), NULL,
@@ -565,7 +573,9 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
adap->name, adap->nr);
return 0;
error:
- return_i2c_dev(i2c_dev);
+ cdev_del(&i2c_dev->cdev);
+error_cdev:
+ put_i2c_dev(i2c_dev);
return res;
}
@@ -582,7 +592,8 @@ static int i2cdev_detach_adapter(struct device *dev, void *dummy)
if (!i2c_dev) /* attach_adapter must have failed */
return 0;
- return_i2c_dev(i2c_dev);
+ cdev_del(&i2c_dev->cdev);
+ put_i2c_dev(i2c_dev);
device_destroy(i2c_dev_class, MKDEV(I2C_MAJOR, adap->nr));
pr_debug("i2c-dev: adapter [%s] unregistered\n", adap->name);
@@ -620,7 +631,7 @@ static int __init i2c_dev_init(void)
printk(KERN_INFO "i2c /dev entries driver\n");
- res = register_chrdev(I2C_MAJOR, "i2c", &i2cdev_fops);
+ res = register_chrdev_region(MKDEV(I2C_MAJOR, 0), I2C_MINORS, "i2c");
if (res)
goto out;
@@ -644,7 +655,7 @@ static int __init i2c_dev_init(void)
out_unreg_class:
class_destroy(i2c_dev_class);
out_unreg_chrdev:
- unregister_chrdev(I2C_MAJOR, "i2c");
+ unregister_chrdev_region(MKDEV(I2C_MAJOR, 0), I2C_MINORS);
out:
printk(KERN_ERR "%s: Driver Initialisation failed\n", __FILE__);
return res;
@@ -655,7 +666,7 @@ static void __exit i2c_dev_exit(void)
bus_unregister_notifier(&i2c_bus_type, &i2cdev_notifier);
i2c_for_each_dev(NULL, i2cdev_detach_adapter);
class_destroy(i2c_dev_class);
- unregister_chrdev(I2C_MAJOR, "i2c");
+ unregister_chrdev_region(MKDEV(I2C_MAJOR, 0), I2C_MINORS);
}
MODULE_AUTHOR("Frodo Looijaard <frodol@dds.nl> and "
diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 6773cadf7c9f..26e7c5187a58 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -260,6 +260,7 @@ static struct platform_driver i2c_mux_reg_driver = {
.remove = i2c_mux_reg_remove,
.driver = {
.name = "i2c-mux-reg",
+ .of_match_table = of_match_ptr(i2c_mux_reg_of_match),
},
};
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 923f56598d4b..3a9f106787d2 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -81,7 +81,7 @@ static int kxsd9_write_scale(struct iio_dev *indio_dev, int micro)
mutex_lock(&st->buf_lock);
ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
- if (ret)
+ if (ret < 0)
goto error_ret;
st->tx[0] = KXSD9_WRITE(KXSD9_REG_CTRL_C);
st->tx[1] = (ret & ~KXSD9_FS_MASK) | i;
@@ -163,7 +163,7 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev,
break;
case IIO_CHAN_INFO_SCALE:
ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
- if (ret)
+ if (ret < 0)
goto error_ret;
*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
ret = IIO_VAL_INT_PLUS_MICRO;
diff --git a/drivers/iio/accel/st_accel_buffer.c b/drivers/iio/accel/st_accel_buffer.c
index a1e642ee13d6..7fddc137e91e 100644
--- a/drivers/iio/accel/st_accel_buffer.c
+++ b/drivers/iio/accel/st_accel_buffer.c
@@ -91,7 +91,7 @@ static const struct iio_buffer_setup_ops st_accel_buffer_setup_ops = {
int st_accel_allocate_ring(struct iio_dev *indio_dev)
{
- return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+ return iio_triggered_buffer_setup(indio_dev, NULL,
&st_sensors_trigger_handler, &st_accel_buffer_setup_ops);
}
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index dc73f2d85e6d..4d95bfc4786c 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -741,6 +741,7 @@ static const struct iio_info accel_info = {
static const struct iio_trigger_ops st_accel_trigger_ops = {
.owner = THIS_MODULE,
.set_trigger_state = ST_ACCEL_TRIGGER_SET_STATE,
+ .validate_device = st_sensors_validate_device,
};
#define ST_ACCEL_TRIGGER_OPS (&st_accel_trigger_ops)
#else
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 21e19b60e2b9..2123f0ac2e2a 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -396,8 +396,8 @@ static int ad7266_probe(struct spi_device *spi)
st = iio_priv(indio_dev);
- st->reg = devm_regulator_get(&spi->dev, "vref");
- if (!IS_ERR_OR_NULL(st->reg)) {
+ st->reg = devm_regulator_get_optional(&spi->dev, "vref");
+ if (!IS_ERR(st->reg)) {
ret = regulator_enable(st->reg);
if (ret)
return ret;
@@ -408,6 +408,9 @@ static int ad7266_probe(struct spi_device *spi)
st->vref_mv = ret / 1000;
} else {
+ /* Any other error indicates that the regulator does exist */
+ if (PTR_ERR(st->reg) != -ENODEV)
+ return PTR_ERR(st->reg);
/* Use internal reference */
st->vref_mv = 2500;
}
diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c
index c55898543a47..f1693dbebb8a 100644
--- a/drivers/iio/common/st_sensors/st_sensors_buffer.c
+++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c
@@ -57,31 +57,20 @@ irqreturn_t st_sensors_trigger_handler(int irq, void *p)
struct iio_poll_func *pf = p;
struct iio_dev *indio_dev = pf->indio_dev;
struct st_sensor_data *sdata = iio_priv(indio_dev);
+ s64 timestamp;
- /* If we have a status register, check if this IRQ came from us */
- if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) {
- u8 status;
-
- len = sdata->tf->read_byte(&sdata->tb, sdata->dev,
- sdata->sensor_settings->drdy_irq.addr_stat_drdy,
- &status);
- if (len < 0)
- dev_err(sdata->dev, "could not read channel status\n");
-
- /*
- * If this was not caused by any channels on this sensor,
- * return IRQ_NONE
- */
- if (!(status & (u8)indio_dev->active_scan_mask[0]))
- return IRQ_NONE;
- }
+ /* If we do timetamping here, do it before reading the values */
+ if (sdata->hw_irq_trigger)
+ timestamp = sdata->hw_timestamp;
+ else
+ timestamp = iio_get_time_ns();
len = st_sensors_get_buffer_element(indio_dev, sdata->buffer_data);
if (len < 0)
goto st_sensors_get_buffer_element_error;
iio_push_to_buffers_with_timestamp(indio_dev, sdata->buffer_data,
- pf->timestamp);
+ timestamp);
st_sensors_get_buffer_element_error:
iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index dffe00692169..9e59c90f6a8d 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -363,6 +363,11 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
if (err < 0)
return err;
+ /* Disable DRDY, this might be still be enabled after reboot. */
+ err = st_sensors_set_dataready_irq(indio_dev, false);
+ if (err < 0)
+ return err;
+
if (sdata->current_fullscale) {
err = st_sensors_set_fullscale(indio_dev,
sdata->current_fullscale->num);
@@ -424,6 +429,9 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable)
else
drdy_mask = sdata->sensor_settings->drdy_irq.mask_int2;
+ /* Flag to the poll function that the hardware trigger is in use */
+ sdata->hw_irq_trigger = enable;
+
/* Enable/Disable the interrupt generator for data ready. */
err = st_sensors_write_data_with_mask(indio_dev,
sdata->sensor_settings->drdy_irq.addr,
diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c
index da72279fcf99..296e4ff19ae8 100644
--- a/drivers/iio/common/st_sensors/st_sensors_trigger.c
+++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c
@@ -17,6 +17,73 @@
#include <linux/iio/common/st_sensors.h>
#include "st_sensors_core.h"
+/**
+ * st_sensors_irq_handler() - top half of the IRQ-based triggers
+ * @irq: irq number
+ * @p: private handler data
+ */
+irqreturn_t st_sensors_irq_handler(int irq, void *p)
+{
+ struct iio_trigger *trig = p;
+ struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
+ struct st_sensor_data *sdata = iio_priv(indio_dev);
+
+ /* Get the time stamp as close in time as possible */
+ sdata->hw_timestamp = iio_get_time_ns();
+ return IRQ_WAKE_THREAD;
+}
+
+/**
+ * st_sensors_irq_thread() - bottom half of the IRQ-based triggers
+ * @irq: irq number
+ * @p: private handler data
+ */
+irqreturn_t st_sensors_irq_thread(int irq, void *p)
+{
+ struct iio_trigger *trig = p;
+ struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
+ struct st_sensor_data *sdata = iio_priv(indio_dev);
+ int ret;
+
+ /*
+ * If this trigger is backed by a hardware interrupt and we have a
+ * status register, check if this IRQ came from us
+ */
+ if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) {
+ u8 status;
+
+ ret = sdata->tf->read_byte(&sdata->tb, sdata->dev,
+ sdata->sensor_settings->drdy_irq.addr_stat_drdy,
+ &status);
+ if (ret < 0) {
+ dev_err(sdata->dev, "could not read channel status\n");
+ goto out_poll;
+ }
+ /*
+ * the lower bits of .active_scan_mask[0] is directly mapped
+ * to the channels on the sensor: either bit 0 for
+ * one-dimensional sensors, or e.g. x,y,z for accelerometers,
+ * gyroscopes or magnetometers. No sensor use more than 3
+ * channels, so cut the other status bits here.
+ */
+ status &= 0x07;
+
+ /*
+ * If this was not caused by any channels on this sensor,
+ * return IRQ_NONE
+ */
+ if (!indio_dev->active_scan_mask)
+ return IRQ_NONE;
+ if (!(status & (u8)indio_dev->active_scan_mask[0]))
+ return IRQ_NONE;
+ }
+
+out_poll:
+ /* It's our IRQ: proceed to handle the register polling */
+ iio_trigger_poll_chained(p);
+ return IRQ_HANDLED;
+}
+
int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
const struct iio_trigger_ops *trigger_ops)
{
@@ -30,6 +97,10 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
return -ENOMEM;
}
+ iio_trigger_set_drvdata(sdata->trig, indio_dev);
+ sdata->trig->ops = trigger_ops;
+ sdata->trig->dev.parent = sdata->dev;
+
irq = sdata->get_irq_data_ready(indio_dev);
irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
/*
@@ -77,9 +148,12 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
sdata->sensor_settings->drdy_irq.addr_stat_drdy)
irq_trig |= IRQF_SHARED;
- err = request_threaded_irq(irq,
- iio_trigger_generic_data_rdy_poll,
- NULL,
+ /* Let's create an interrupt thread masking the hard IRQ here */
+ irq_trig |= IRQF_ONESHOT;
+
+ err = request_threaded_irq(sdata->get_irq_data_ready(indio_dev),
+ st_sensors_irq_handler,
+ st_sensors_irq_thread,
irq_trig,
sdata->trig->name,
sdata->trig);
@@ -88,10 +162,6 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
goto iio_trigger_free;
}
- iio_trigger_set_drvdata(sdata->trig, indio_dev);
- sdata->trig->ops = trigger_ops;
- sdata->trig->dev.parent = sdata->dev;
-
err = iio_trigger_register(sdata->trig);
if (err < 0) {
dev_err(&indio_dev->dev, "failed to register iio trigger.\n");
@@ -119,6 +189,18 @@ void st_sensors_deallocate_trigger(struct iio_dev *indio_dev)
}
EXPORT_SYMBOL(st_sensors_deallocate_trigger);
+int st_sensors_validate_device(struct iio_trigger *trig,
+ struct iio_dev *indio_dev)
+{
+ struct iio_dev *indio = iio_trigger_get_drvdata(trig);
+
+ if (indio != indio_dev)
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL(st_sensors_validate_device);
+
MODULE_AUTHOR("Denis Ciocca <denis.ciocca@st.com>");
MODULE_DESCRIPTION("STMicroelectronics ST-sensors trigger");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index e63b957c985f..f7c71da42f15 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -247,7 +247,7 @@ config MCP4922
config STX104
tristate "Apex Embedded Systems STX104 DAC driver"
- depends on X86 && ISA
+ depends on X86 && ISA_BUS_API
help
Say yes here to build support for the 2-channel DAC on the Apex
Embedded Systems STX104 integrated analog PC/104 card. The base port
diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c
index 948f600e7059..69bde5909854 100644
--- a/drivers/iio/dac/ad5592r-base.c
+++ b/drivers/iio/dac/ad5592r-base.c
@@ -525,7 +525,7 @@ static int ad5592r_alloc_channels(struct ad5592r_state *st)
device_for_each_child_node(st->dev, child) {
ret = fwnode_property_read_u32(child, "reg", &reg);
- if (ret || reg > ARRAY_SIZE(st->channel_modes))
+ if (ret || reg >= ARRAY_SIZE(st->channel_modes))
continue;
ret = fwnode_property_read_u32(child, "adi,mode", &tmp);
diff --git a/drivers/iio/gyro/st_gyro_buffer.c b/drivers/iio/gyro/st_gyro_buffer.c
index d67b17b6a7aa..a5377044e42f 100644
--- a/drivers/iio/gyro/st_gyro_buffer.c
+++ b/drivers/iio/gyro/st_gyro_buffer.c
@@ -91,7 +91,7 @@ static const struct iio_buffer_setup_ops st_gyro_buffer_setup_ops = {
int st_gyro_allocate_ring(struct iio_dev *indio_dev)
{
- return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+ return iio_triggered_buffer_setup(indio_dev, NULL,
&st_sensors_trigger_handler, &st_gyro_buffer_setup_ops);
}
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index 52a3c87c375c..a8012955a1f6 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -409,6 +409,7 @@ static const struct iio_info gyro_info = {
static const struct iio_trigger_ops st_gyro_trigger_ops = {
.owner = THIS_MODULE,
.set_trigger_state = ST_GYRO_TRIGGER_SET_STATE,
+ .validate_device = st_sensors_validate_device,
};
#define ST_GYRO_TRIGGER_OPS (&st_gyro_trigger_ops)
#else
diff --git a/drivers/iio/humidity/am2315.c b/drivers/iio/humidity/am2315.c
index 3be6d209a159..11535911a5c6 100644
--- a/drivers/iio/humidity/am2315.c
+++ b/drivers/iio/humidity/am2315.c
@@ -165,10 +165,8 @@ static irqreturn_t am2315_trigger_handler(int irq, void *p)
struct am2315_sensor_data sensor_data;
ret = am2315_read_data(data, &sensor_data);
- if (ret < 0) {
- mutex_unlock(&data->lock);
+ if (ret < 0)
goto err;
- }
mutex_lock(&data->lock);
if (*(indio_dev->active_scan_mask) == AM2315_ALL_CHANNEL_MASK) {
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index fa4767613173..a03832a5fc95 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -55,7 +55,7 @@ static const struct {
},
{ /* IIO_HUMIDITYRELATIVE channel */
.shift = 8,
- .mask = 2,
+ .mask = 3,
},
};
@@ -164,14 +164,14 @@ static int hdc100x_get_measurement(struct hdc100x_data *data,
dev_err(&client->dev, "cannot read high byte measurement");
return ret;
}
- val = ret << 6;
+ val = ret << 8;
ret = i2c_smbus_read_byte(client);
if (ret < 0) {
dev_err(&client->dev, "cannot read low byte measurement");
return ret;
}
- val |= ret >> 2;
+ val |= ret;
return val;
}
@@ -211,18 +211,18 @@ static int hdc100x_read_raw(struct iio_dev *indio_dev,
return IIO_VAL_INT_PLUS_MICRO;
case IIO_CHAN_INFO_SCALE:
if (chan->type == IIO_TEMP) {
- *val = 165;
- *val2 = 65536 >> 2;
+ *val = 165000;
+ *val2 = 65536;
return IIO_VAL_FRACTIONAL;
} else {
- *val = 0;
- *val2 = 10000;
- return IIO_VAL_INT_PLUS_MICRO;
+ *val = 100;
+ *val2 = 65536;
+ return IIO_VAL_FRACTIONAL;
}
break;
case IIO_CHAN_INFO_OFFSET:
- *val = -3971;
- *val2 = 879096;
+ *val = -15887;
+ *val2 = 515151;
return IIO_VAL_INT_PLUS_MICRO;
default:
return -EINVAL;
diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c
index 0bf92b06d7d8..b8a290ec984e 100644
--- a/drivers/iio/imu/bmi160/bmi160_core.c
+++ b/drivers/iio/imu/bmi160/bmi160_core.c
@@ -209,11 +209,11 @@ static const struct bmi160_scale_item bmi160_scale_table[] = {
};
static const struct bmi160_odr bmi160_accel_odr[] = {
- {0x01, 0, 78125},
- {0x02, 1, 5625},
- {0x03, 3, 125},
- {0x04, 6, 25},
- {0x05, 12, 5},
+ {0x01, 0, 781250},
+ {0x02, 1, 562500},
+ {0x03, 3, 125000},
+ {0x04, 6, 250000},
+ {0x05, 12, 500000},
{0x06, 25, 0},
{0x07, 50, 0},
{0x08, 100, 0},
@@ -229,7 +229,7 @@ static const struct bmi160_odr bmi160_gyro_odr[] = {
{0x08, 100, 0},
{0x09, 200, 0},
{0x0A, 400, 0},
- {0x0B, 8000, 0},
+ {0x0B, 800, 0},
{0x0C, 1600, 0},
{0x0D, 3200, 0},
};
@@ -364,8 +364,8 @@ int bmi160_set_odr(struct bmi160_data *data, enum bmi160_sensor_type t,
return regmap_update_bits(data->regmap,
bmi160_regs[t].config,
- bmi160_odr_table[t].tbl[i].bits,
- bmi160_regs[t].config_odr_mask);
+ bmi160_regs[t].config_odr_mask,
+ bmi160_odr_table[t].tbl[i].bits);
}
static int bmi160_get_odr(struct bmi160_data *data, enum bmi160_sensor_type t,
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
index f62b8bd9ad7e..dd6fc6d21f9d 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
@@ -56,6 +56,7 @@ static int asus_acpi_get_sensor_info(struct acpi_device *adev,
int i;
acpi_status status;
union acpi_object *cpm;
+ int ret;
status = acpi_evaluate_object(adev->handle, "CNF0", NULL, &buffer);
if (ACPI_FAILURE(status))
@@ -82,10 +83,10 @@ static int asus_acpi_get_sensor_info(struct acpi_device *adev,
}
}
}
-
+ ret = cpm->package.count;
kfree(buffer.pointer);
- return cpm->package.count;
+ return ret;
}
static int acpi_i2c_check_resource(struct acpi_resource *ares, void *data)
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index ae2806aafb72..0c52dfe64977 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -210,22 +210,35 @@ static int iio_trigger_attach_poll_func(struct iio_trigger *trig,
/* Prevent the module from being removed whilst attached to a trigger */
__module_get(pf->indio_dev->info->driver_module);
+
+ /* Get irq number */
pf->irq = iio_trigger_get_irq(trig);
+ if (pf->irq < 0)
+ goto out_put_module;
+
+ /* Request irq */
ret = request_threaded_irq(pf->irq, pf->h, pf->thread,
pf->type, pf->name,
pf);
- if (ret < 0) {
- module_put(pf->indio_dev->info->driver_module);
- return ret;
- }
+ if (ret < 0)
+ goto out_put_irq;
+ /* Enable trigger in driver */
if (trig->ops && trig->ops->set_trigger_state && notinuse) {
ret = trig->ops->set_trigger_state(trig, true);
if (ret < 0)
- module_put(pf->indio_dev->info->driver_module);
+ goto out_free_irq;
}
return ret;
+
+out_free_irq:
+ free_irq(pf->irq, pf);
+out_put_irq:
+ iio_trigger_put_irq(trig, pf->irq);
+out_put_module:
+ module_put(pf->indio_dev->info->driver_module);
+ return ret;
}
static int iio_trigger_detach_poll_func(struct iio_trigger *trig,
diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c
index b4dbb3912977..651d57b8abbf 100644
--- a/drivers/iio/light/apds9960.c
+++ b/drivers/iio/light/apds9960.c
@@ -1011,6 +1011,7 @@ static int apds9960_probe(struct i2c_client *client,
iio_device_attach_buffer(indio_dev, buffer);
+ indio_dev->dev.parent = &client->dev;
indio_dev->info = &apds9960_info;
indio_dev->name = APDS9960_DRV_NAME;
indio_dev->channels = apds9960_channels;
diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c
index 72b364e4aa72..b54dcba05a82 100644
--- a/drivers/iio/light/bh1780.c
+++ b/drivers/iio/light/bh1780.c
@@ -84,7 +84,7 @@ static int bh1780_debugfs_reg_access(struct iio_dev *indio_dev,
int ret;
if (!readval)
- bh1780_write(bh1780, (u8)reg, (u8)writeval);
+ return bh1780_write(bh1780, (u8)reg, (u8)writeval);
ret = bh1780_read(bh1780, (u8)reg);
if (ret < 0)
@@ -187,7 +187,7 @@ static int bh1780_probe(struct i2c_client *client,
indio_dev->dev.parent = &client->dev;
indio_dev->info = &bh1780_info;
- indio_dev->name = id->name;
+ indio_dev->name = "bh1780";
indio_dev->channels = bh1780_channels;
indio_dev->num_channels = ARRAY_SIZE(bh1780_channels);
indio_dev->modes = INDIO_DIRECT_MODE;
@@ -226,7 +226,8 @@ static int bh1780_remove(struct i2c_client *client)
static int bh1780_runtime_suspend(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
- struct bh1780_data *bh1780 = i2c_get_clientdata(client);
+ struct iio_dev *indio_dev = i2c_get_clientdata(client);
+ struct bh1780_data *bh1780 = iio_priv(indio_dev);
int ret;
ret = bh1780_write(bh1780, BH1780_REG_CONTROL, BH1780_POFF);
@@ -241,7 +242,8 @@ static int bh1780_runtime_suspend(struct device *dev)
static int bh1780_runtime_resume(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
- struct bh1780_data *bh1780 = i2c_get_clientdata(client);
+ struct iio_dev *indio_dev = i2c_get_clientdata(client);
+ struct bh1780_data *bh1780 = iio_priv(indio_dev);
int ret;
ret = bh1780_write(bh1780, BH1780_REG_CONTROL, BH1780_PON);
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index e01e58a9bd14..f17cb2ea18f5 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -147,7 +147,6 @@ static const struct iio_chan_spec max44000_channels[] = {
{
.type = IIO_PROXIMITY,
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.scan_index = MAX44000_SCAN_INDEX_PRX,
.scan_type = {
.sign = 'u',
diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c
index ecd3bd0a9769..0a9e8fadfa9d 100644
--- a/drivers/iio/magnetometer/st_magn_buffer.c
+++ b/drivers/iio/magnetometer/st_magn_buffer.c
@@ -82,7 +82,7 @@ static const struct iio_buffer_setup_ops st_magn_buffer_setup_ops = {
int st_magn_allocate_ring(struct iio_dev *indio_dev)
{
- return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+ return iio_triggered_buffer_setup(indio_dev, NULL,
&st_sensors_trigger_handler, &st_magn_buffer_setup_ops);
}
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index 62036d2a9956..8250fc322c56 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -572,6 +572,7 @@ static const struct iio_info magn_info = {
static const struct iio_trigger_ops st_magn_trigger_ops = {
.owner = THIS_MODULE,
.set_trigger_state = ST_MAGN_TRIGGER_SET_STATE,
+ .validate_device = st_sensors_validate_device,
};
#define ST_MAGN_TRIGGER_OPS (&st_magn_trigger_ops)
#else
diff --git a/drivers/iio/pressure/bmp280.c b/drivers/iio/pressure/bmp280.c
index 2f1498e12bb2..724452d61846 100644
--- a/drivers/iio/pressure/bmp280.c
+++ b/drivers/iio/pressure/bmp280.c
@@ -879,8 +879,8 @@ static int bmp280_probe(struct i2c_client *client,
if (ret < 0)
return ret;
if (chip_id != id->driver_data) {
- dev_err(&client->dev, "bad chip id. expected %x got %x\n",
- BMP280_CHIP_ID, chip_id);
+ dev_err(&client->dev, "bad chip id. expected %lx got %x\n",
+ id->driver_data, chip_id);
return -EINVAL;
}
diff --git a/drivers/iio/pressure/st_pressure_buffer.c b/drivers/iio/pressure/st_pressure_buffer.c
index 2ff53f222352..99468d0a64e7 100644
--- a/drivers/iio/pressure/st_pressure_buffer.c
+++ b/drivers/iio/pressure/st_pressure_buffer.c
@@ -82,7 +82,7 @@ static const struct iio_buffer_setup_ops st_press_buffer_setup_ops = {
int st_press_allocate_ring(struct iio_dev *indio_dev)
{
- return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+ return iio_triggered_buffer_setup(indio_dev, NULL,
&st_sensors_trigger_handler, &st_press_buffer_setup_ops);
}
diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index 9e9b72a8f18f..92a118c3c4ac 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -28,15 +28,21 @@
#include <linux/iio/common/st_sensors.h>
#include "st_pressure.h"
+#define MCELSIUS_PER_CELSIUS 1000
+
+/* Default pressure sensitivity */
#define ST_PRESS_LSB_PER_MBAR 4096UL
#define ST_PRESS_KPASCAL_NANO_SCALE (100000000UL / \
ST_PRESS_LSB_PER_MBAR)
+
+/* Default temperature sensitivity */
#define ST_PRESS_LSB_PER_CELSIUS 480UL
-#define ST_PRESS_CELSIUS_NANO_SCALE (1000000000UL / \
- ST_PRESS_LSB_PER_CELSIUS)
+#define ST_PRESS_MILLI_CELSIUS_OFFSET 42500UL
+
#define ST_PRESS_NUMBER_DATA_CHANNELS 1
/* FULLSCALE */
+#define ST_PRESS_FS_AVL_1100MB 1100
#define ST_PRESS_FS_AVL_1260MB 1260
#define ST_PRESS_1_OUT_XL_ADDR 0x28
@@ -54,9 +60,6 @@
#define ST_PRESS_LPS331AP_PW_MASK 0x80
#define ST_PRESS_LPS331AP_FS_ADDR 0x23
#define ST_PRESS_LPS331AP_FS_MASK 0x30
-#define ST_PRESS_LPS331AP_FS_AVL_1260_VAL 0x00
-#define ST_PRESS_LPS331AP_FS_AVL_1260_GAIN ST_PRESS_KPASCAL_NANO_SCALE
-#define ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN ST_PRESS_CELSIUS_NANO_SCALE
#define ST_PRESS_LPS331AP_BDU_ADDR 0x20
#define ST_PRESS_LPS331AP_BDU_MASK 0x04
#define ST_PRESS_LPS331AP_DRDY_IRQ_ADDR 0x22
@@ -67,9 +70,14 @@
#define ST_PRESS_LPS331AP_OD_IRQ_ADDR 0x22
#define ST_PRESS_LPS331AP_OD_IRQ_MASK 0x40
#define ST_PRESS_LPS331AP_MULTIREAD_BIT true
-#define ST_PRESS_LPS331AP_TEMP_OFFSET 42500
/* CUSTOM VALUES FOR LPS001WP SENSOR */
+
+/* LPS001WP pressure resolution */
+#define ST_PRESS_LPS001WP_LSB_PER_MBAR 16UL
+/* LPS001WP temperature resolution */
+#define ST_PRESS_LPS001WP_LSB_PER_CELSIUS 64UL
+
#define ST_PRESS_LPS001WP_WAI_EXP 0xba
#define ST_PRESS_LPS001WP_ODR_ADDR 0x20
#define ST_PRESS_LPS001WP_ODR_MASK 0x30
@@ -78,6 +86,8 @@
#define ST_PRESS_LPS001WP_ODR_AVL_13HZ_VAL 0x03
#define ST_PRESS_LPS001WP_PW_ADDR 0x20
#define ST_PRESS_LPS001WP_PW_MASK 0x40
+#define ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN \
+ (100000000UL / ST_PRESS_LPS001WP_LSB_PER_MBAR)
#define ST_PRESS_LPS001WP_BDU_ADDR 0x20
#define ST_PRESS_LPS001WP_BDU_MASK 0x04
#define ST_PRESS_LPS001WP_MULTIREAD_BIT true
@@ -94,11 +104,6 @@
#define ST_PRESS_LPS25H_ODR_AVL_25HZ_VAL 0x04
#define ST_PRESS_LPS25H_PW_ADDR 0x20
#define ST_PRESS_LPS25H_PW_MASK 0x80
-#define ST_PRESS_LPS25H_FS_ADDR 0x00
-#define ST_PRESS_LPS25H_FS_MASK 0x00
-#define ST_PRESS_LPS25H_FS_AVL_1260_VAL 0x00
-#define ST_PRESS_LPS25H_FS_AVL_1260_GAIN ST_PRESS_KPASCAL_NANO_SCALE
-#define ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN ST_PRESS_CELSIUS_NANO_SCALE
#define ST_PRESS_LPS25H_BDU_ADDR 0x20
#define ST_PRESS_LPS25H_BDU_MASK 0x04
#define ST_PRESS_LPS25H_DRDY_IRQ_ADDR 0x23
@@ -109,7 +114,6 @@
#define ST_PRESS_LPS25H_OD_IRQ_ADDR 0x22
#define ST_PRESS_LPS25H_OD_IRQ_MASK 0x40
#define ST_PRESS_LPS25H_MULTIREAD_BIT true
-#define ST_PRESS_LPS25H_TEMP_OFFSET 42500
#define ST_PRESS_LPS25H_OUT_XL_ADDR 0x28
#define ST_TEMP_LPS25H_OUT_L_ADDR 0x2b
@@ -161,7 +165,9 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = {
.storagebits = 16,
.endianness = IIO_LE,
},
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+ .info_mask_separate =
+ BIT(IIO_CHAN_INFO_RAW) |
+ BIT(IIO_CHAN_INFO_SCALE),
.modified = 0,
},
{
@@ -177,7 +183,7 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = {
},
.info_mask_separate =
BIT(IIO_CHAN_INFO_RAW) |
- BIT(IIO_CHAN_INFO_OFFSET),
+ BIT(IIO_CHAN_INFO_SCALE),
.modified = 0,
},
IIO_CHAN_SOFT_TIMESTAMP(1)
@@ -212,11 +218,14 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
.addr = ST_PRESS_LPS331AP_FS_ADDR,
.mask = ST_PRESS_LPS331AP_FS_MASK,
.fs_avl = {
+ /*
+ * Pressure and temperature sensitivity values
+ * as defined in table 3 of LPS331AP datasheet.
+ */
[0] = {
.num = ST_PRESS_FS_AVL_1260MB,
- .value = ST_PRESS_LPS331AP_FS_AVL_1260_VAL,
- .gain = ST_PRESS_LPS331AP_FS_AVL_1260_GAIN,
- .gain2 = ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN,
+ .gain = ST_PRESS_KPASCAL_NANO_SCALE,
+ .gain2 = ST_PRESS_LSB_PER_CELSIUS,
},
},
},
@@ -261,7 +270,17 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
},
.fs = {
- .addr = 0,
+ .fs_avl = {
+ /*
+ * Pressure and temperature resolution values
+ * as defined in table 3 of LPS001WP datasheet.
+ */
+ [0] = {
+ .num = ST_PRESS_FS_AVL_1100MB,
+ .gain = ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN,
+ .gain2 = ST_PRESS_LPS001WP_LSB_PER_CELSIUS,
+ },
+ },
},
.bdu = {
.addr = ST_PRESS_LPS001WP_BDU_ADDR,
@@ -298,14 +317,15 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
},
.fs = {
- .addr = ST_PRESS_LPS25H_FS_ADDR,
- .mask = ST_PRESS_LPS25H_FS_MASK,
.fs_avl = {
+ /*
+ * Pressure and temperature sensitivity values
+ * as defined in table 3 of LPS25H datasheet.
+ */
[0] = {
.num = ST_PRESS_FS_AVL_1260MB,
- .value = ST_PRESS_LPS25H_FS_AVL_1260_VAL,
- .gain = ST_PRESS_LPS25H_FS_AVL_1260_GAIN,
- .gain2 = ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN,
+ .gain = ST_PRESS_KPASCAL_NANO_SCALE,
+ .gain2 = ST_PRESS_LSB_PER_CELSIUS,
},
},
},
@@ -364,26 +384,26 @@ static int st_press_read_raw(struct iio_dev *indio_dev,
return IIO_VAL_INT;
case IIO_CHAN_INFO_SCALE:
- *val = 0;
-
switch (ch->type) {
case IIO_PRESSURE:
+ *val = 0;
*val2 = press_data->current_fullscale->gain;
- break;
+ return IIO_VAL_INT_PLUS_NANO;
case IIO_TEMP:
+ *val = MCELSIUS_PER_CELSIUS;
*val2 = press_data->current_fullscale->gain2;
- break;
+ return IIO_VAL_FRACTIONAL;
default:
err = -EINVAL;
goto read_error;
}
- return IIO_VAL_INT_PLUS_NANO;
case IIO_CHAN_INFO_OFFSET:
switch (ch->type) {
case IIO_TEMP:
- *val = 425;
- *val2 = 10;
+ *val = ST_PRESS_MILLI_CELSIUS_OFFSET *
+ press_data->current_fullscale->gain2;
+ *val2 = MCELSIUS_PER_CELSIUS;
break;
default:
err = -EINVAL;
@@ -425,6 +445,7 @@ static const struct iio_info press_info = {
static const struct iio_trigger_ops st_press_trigger_ops = {
.owner = THIS_MODULE,
.set_trigger_state = ST_PRESS_TRIGGER_SET_STATE,
+ .validate_device = st_sensors_validate_device,
};
#define ST_PRESS_TRIGGER_OPS (&st_press_trigger_ops)
#else
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index f4d29d5dbd5f..e2f926cdcad2 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -64,6 +64,7 @@ struct as3935_state {
struct delayed_work work;
u32 tune_cap;
+ u8 buffer[16]; /* 8-bit data + 56-bit padding + 64-bit timestamp */
u8 buf[2] ____cacheline_aligned;
};
@@ -72,7 +73,8 @@ static const struct iio_chan_spec as3935_channels[] = {
.type = IIO_PROXIMITY,
.info_mask_separate =
BIT(IIO_CHAN_INFO_RAW) |
- BIT(IIO_CHAN_INFO_PROCESSED),
+ BIT(IIO_CHAN_INFO_PROCESSED) |
+ BIT(IIO_CHAN_INFO_SCALE),
.scan_index = 0,
.scan_type = {
.sign = 'u',
@@ -181,7 +183,12 @@ static int as3935_read_raw(struct iio_dev *indio_dev,
/* storm out of range */
if (*val == AS3935_DATA_MASK)
return -EINVAL;
- *val *= 1000;
+
+ if (m == IIO_CHAN_INFO_PROCESSED)
+ *val *= 1000;
+ break;
+ case IIO_CHAN_INFO_SCALE:
+ *val = 1000;
break;
default:
return -EINVAL;
@@ -206,10 +213,10 @@ static irqreturn_t as3935_trigger_handler(int irq, void *private)
ret = as3935_read(st, AS3935_DATA, &val);
if (ret)
goto err_read;
- val &= AS3935_DATA_MASK;
- val *= 1000;
- iio_push_to_buffers_with_timestamp(indio_dev, &val, pf->timestamp);
+ st->buffer[0] = val & AS3935_DATA_MASK;
+ iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
+ pf->timestamp);
err_read:
iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 6425c0e5d18a..2137adfbd8c3 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -85,4 +85,6 @@ source "drivers/infiniband/ulp/isert/Kconfig"
source "drivers/infiniband/sw/rdmavt/Kconfig"
+source "drivers/infiniband/hw/hfi1/Kconfig"
+
endif # INFINIBAND
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 26987d9d7e1c..edaae9f9853c 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -1,8 +1,7 @@
infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS) := rdma_cm.o
user_access-$(CONFIG_INFINIBAND_ADDR_TRANS) := rdma_ucm.o
-obj-$(CONFIG_INFINIBAND) += ib_core.o ib_mad.o ib_sa.o \
- ib_cm.o iw_cm.o ib_addr.o \
+obj-$(CONFIG_INFINIBAND) += ib_core.o ib_cm.o iw_cm.o \
$(infiniband-y)
obj-$(CONFIG_INFINIBAND_USER_MAD) += ib_umad.o
obj-$(CONFIG_INFINIBAND_USER_ACCESS) += ib_uverbs.o ib_ucm.o \
@@ -10,14 +9,11 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) += ib_uverbs.o ib_ucm.o \
ib_core-y := packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
device.o fmr_pool.o cache.o netlink.o \
- roce_gid_mgmt.o mr_pool.o
+ roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
+ multicast.o mad.o smi.o agent.o mad_rmpp.o
ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
-ib_mad-y := mad.o smi.o agent.o mad_rmpp.o
-
-ib_sa-y := sa_query.o multicast.o
-
ib_cm-y := cm.o
iw_cm-y := iwcm.o iwpm_util.o iwpm_msg.o
@@ -28,8 +24,6 @@ rdma_cm-$(CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS) += cma_configfs.o
rdma_ucm-y := ucma.o
-ib_addr-y := addr.o
-
ib_umad-y := user_mad.o
ib_ucm-y := ucm.o
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 337353d86cfa..1374541a4528 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -46,10 +46,10 @@
#include <net/ip6_route.h>
#include <rdma/ib_addr.h>
#include <rdma/ib.h>
+#include <rdma/rdma_netlink.h>
+#include <net/netlink.h>
-MODULE_AUTHOR("Sean Hefty");
-MODULE_DESCRIPTION("IB Address Translation");
-MODULE_LICENSE("Dual BSD/GPL");
+#include "core_priv.h"
struct addr_req {
struct list_head list;
@@ -62,8 +62,11 @@ struct addr_req {
struct rdma_dev_addr *addr, void *context);
unsigned long timeout;
int status;
+ u32 seq;
};
+static atomic_t ib_nl_addr_request_seq = ATOMIC_INIT(0);
+
static void process_req(struct work_struct *work);
static DEFINE_MUTEX(lock);
@@ -71,6 +74,126 @@ static LIST_HEAD(req_list);
static DECLARE_DELAYED_WORK(work, process_req);
static struct workqueue_struct *addr_wq;
+static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
+ [LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
+ .len = sizeof(struct rdma_nla_ls_gid)},
+};
+
+static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
+{
+ struct nlattr *tb[LS_NLA_TYPE_MAX] = {};
+ int ret;
+
+ if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
+ return false;
+
+ ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
+ nlmsg_len(nlh), ib_nl_addr_policy);
+ if (ret)
+ return false;
+
+ return true;
+}
+
+static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
+{
+ const struct nlattr *head, *curr;
+ union ib_gid gid;
+ struct addr_req *req;
+ int len, rem;
+ int found = 0;
+
+ head = (const struct nlattr *)nlmsg_data(nlh);
+ len = nlmsg_len(nlh);
+
+ nla_for_each_attr(curr, head, len, rem) {
+ if (curr->nla_type == LS_NLA_TYPE_DGID)
+ memcpy(&gid, nla_data(curr), nla_len(curr));
+ }
+
+ mutex_lock(&lock);
+ list_for_each_entry(req, &req_list, list) {
+ if (nlh->nlmsg_seq != req->seq)
+ continue;
+ /* We set the DGID part, the rest was set earlier */
+ rdma_addr_set_dgid(req->addr, &gid);
+ req->status = 0;
+ found = 1;
+ break;
+ }
+ mutex_unlock(&lock);
+
+ if (!found)
+ pr_info("Couldn't find request waiting for DGID: %pI6\n",
+ &gid);
+}
+
+int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
+
+ if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
+ !(NETLINK_CB(skb).sk) ||
+ !netlink_capable(skb, CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (ib_nl_is_good_ip_resp(nlh))
+ ib_nl_process_good_ip_rsep(nlh);
+
+ return skb->len;
+}
+
+static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
+ const void *daddr,
+ u32 seq, u16 family)
+{
+ struct sk_buff *skb = NULL;
+ struct nlmsghdr *nlh;
+ struct rdma_ls_ip_resolve_header *header;
+ void *data;
+ size_t size;
+ int attrtype;
+ int len;
+
+ if (family == AF_INET) {
+ size = sizeof(struct in_addr);
+ attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV4;
+ } else {
+ size = sizeof(struct in6_addr);
+ attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6;
+ }
+
+ len = nla_total_size(sizeof(size));
+ len += NLMSG_ALIGN(sizeof(*header));
+
+ skb = nlmsg_new(len, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ data = ibnl_put_msg(skb, &nlh, seq, 0, RDMA_NL_LS,
+ RDMA_NL_LS_OP_IP_RESOLVE, NLM_F_REQUEST);
+ if (!data) {
+ nlmsg_free(skb);
+ return -ENODATA;
+ }
+
+ /* Construct the family header first */
+ header = (struct rdma_ls_ip_resolve_header *)
+ skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
+ header->ifindex = dev_addr->bound_dev_if;
+ nla_put(skb, attrtype, size, daddr);
+
+ /* Repair the nlmsg header length */
+ nlmsg_end(skb, nlh);
+ ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+
+ /* Make the request retry, so when we get the response from userspace
+ * we will have something.
+ */
+ return -ENODATA;
+}
+
int rdma_addr_size(struct sockaddr *addr)
{
switch (addr->sa_family) {
@@ -199,6 +322,17 @@ static void queue_req(struct addr_req *req)
mutex_unlock(&lock);
}
+static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
+ const void *daddr, u32 seq, u16 family)
+{
+ if (ibnl_chk_listeners(RDMA_NL_GROUP_LS))
+ return -EADDRNOTAVAIL;
+
+ /* We fill in what we can, the response will fill the rest */
+ rdma_copy_addr(dev_addr, dst->dev, NULL);
+ return ib_nl_ip_send_msg(dev_addr, daddr, seq, family);
+}
+
static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
const void *daddr)
{
@@ -223,6 +357,39 @@ static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
return ret;
}
+static bool has_gateway(struct dst_entry *dst, sa_family_t family)
+{
+ struct rtable *rt;
+ struct rt6_info *rt6;
+
+ if (family == AF_INET) {
+ rt = container_of(dst, struct rtable, dst);
+ return rt->rt_uses_gateway;
+ }
+
+ rt6 = container_of(dst, struct rt6_info, dst);
+ return rt6->rt6i_flags & RTF_GATEWAY;
+}
+
+static int fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
+ const struct sockaddr *dst_in, u32 seq)
+{
+ const struct sockaddr_in *dst_in4 =
+ (const struct sockaddr_in *)dst_in;
+ const struct sockaddr_in6 *dst_in6 =
+ (const struct sockaddr_in6 *)dst_in;
+ const void *daddr = (dst_in->sa_family == AF_INET) ?
+ (const void *)&dst_in4->sin_addr.s_addr :
+ (const void *)&dst_in6->sin6_addr;
+ sa_family_t family = dst_in->sa_family;
+
+ /* Gateway + ARPHRD_INFINIBAND -> IB router */
+ if (has_gateway(dst, family) && dst->dev->type == ARPHRD_INFINIBAND)
+ return ib_nl_fetch_ha(dst, dev_addr, daddr, seq, family);
+ else
+ return dst_fetch_ha(dst, dev_addr, daddr);
+}
+
static int addr4_resolve(struct sockaddr_in *src_in,
const struct sockaddr_in *dst_in,
struct rdma_dev_addr *addr,
@@ -246,10 +413,11 @@ static int addr4_resolve(struct sockaddr_in *src_in,
src_in->sin_family = AF_INET;
src_in->sin_addr.s_addr = fl4.saddr;
- /* If there's a gateway, we're definitely in RoCE v2 (as RoCE v1 isn't
- * routable) and we could set the network type accordingly.
+ /* If there's a gateway and type of device not ARPHRD_INFINIBAND, we're
+ * definitely in RoCE v2 (as RoCE v1 isn't routable) set the network
+ * type accordingly.
*/
- if (rt->rt_uses_gateway)
+ if (rt->rt_uses_gateway && rt->dst.dev->type != ARPHRD_INFINIBAND)
addr->network = RDMA_NETWORK_IPV4;
addr->hoplimit = ip4_dst_hoplimit(&rt->dst);
@@ -291,10 +459,12 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
src_in->sin6_addr = fl6.saddr;
}
- /* If there's a gateway, we're definitely in RoCE v2 (as RoCE v1 isn't
- * routable) and we could set the network type accordingly.
+ /* If there's a gateway and type of device not ARPHRD_INFINIBAND, we're
+ * definitely in RoCE v2 (as RoCE v1 isn't routable) set the network
+ * type accordingly.
*/
- if (rt->rt6i_flags & RTF_GATEWAY)
+ if (rt->rt6i_flags & RTF_GATEWAY &&
+ ip6_dst_idev(dst)->dev->type != ARPHRD_INFINIBAND)
addr->network = RDMA_NETWORK_IPV6;
addr->hoplimit = ip6_dst_hoplimit(dst);
@@ -317,7 +487,8 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
static int addr_resolve_neigh(struct dst_entry *dst,
const struct sockaddr *dst_in,
- struct rdma_dev_addr *addr)
+ struct rdma_dev_addr *addr,
+ u32 seq)
{
if (dst->dev->flags & IFF_LOOPBACK) {
int ret;
@@ -331,17 +502,8 @@ static int addr_resolve_neigh(struct dst_entry *dst,
}
/* If the device doesn't do ARP internally */
- if (!(dst->dev->flags & IFF_NOARP)) {
- const struct sockaddr_in *dst_in4 =
- (const struct sockaddr_in *)dst_in;
- const struct sockaddr_in6 *dst_in6 =
- (const struct sockaddr_in6 *)dst_in;
-
- return dst_fetch_ha(dst, addr,
- dst_in->sa_family == AF_INET ?
- (const void *)&dst_in4->sin_addr.s_addr :
- (const void *)&dst_in6->sin6_addr);
- }
+ if (!(dst->dev->flags & IFF_NOARP))
+ return fetch_ha(dst, addr, dst_in, seq);
return rdma_copy_addr(addr, dst->dev, NULL);
}
@@ -349,7 +511,8 @@ static int addr_resolve_neigh(struct dst_entry *dst,
static int addr_resolve(struct sockaddr *src_in,
const struct sockaddr *dst_in,
struct rdma_dev_addr *addr,
- bool resolve_neigh)
+ bool resolve_neigh,
+ u32 seq)
{
struct net_device *ndev;
struct dst_entry *dst;
@@ -366,7 +529,7 @@ static int addr_resolve(struct sockaddr *src_in,
return ret;
if (resolve_neigh)
- ret = addr_resolve_neigh(&rt->dst, dst_in, addr);
+ ret = addr_resolve_neigh(&rt->dst, dst_in, addr, seq);
ndev = rt->dst.dev;
dev_hold(ndev);
@@ -383,7 +546,7 @@ static int addr_resolve(struct sockaddr *src_in,
return ret;
if (resolve_neigh)
- ret = addr_resolve_neigh(dst, dst_in, addr);
+ ret = addr_resolve_neigh(dst, dst_in, addr, seq);
ndev = dst->dev;
dev_hold(ndev);
@@ -412,7 +575,7 @@ static void process_req(struct work_struct *work)
src_in = (struct sockaddr *) &req->src_addr;
dst_in = (struct sockaddr *) &req->dst_addr;
req->status = addr_resolve(src_in, dst_in, req->addr,
- true);
+ true, req->seq);
if (req->status && time_after_eq(jiffies, req->timeout))
req->status = -ETIMEDOUT;
else if (req->status == -ENODATA)
@@ -471,8 +634,9 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
req->context = context;
req->client = client;
atomic_inc(&client->refcount);
+ req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);
- req->status = addr_resolve(src_in, dst_in, addr, true);
+ req->status = addr_resolve(src_in, dst_in, addr, true, req->seq);
switch (req->status) {
case 0:
req->timeout = jiffies;
@@ -510,7 +674,7 @@ int rdma_resolve_ip_route(struct sockaddr *src_addr,
src_in->sa_family = dst_addr->sa_family;
}
- return addr_resolve(src_in, dst_addr, addr, false);
+ return addr_resolve(src_in, dst_addr, addr, false, 0);
}
EXPORT_SYMBOL(rdma_resolve_ip_route);
@@ -634,7 +798,7 @@ static struct notifier_block nb = {
.notifier_call = netevent_callback
};
-static int __init addr_init(void)
+int addr_init(void)
{
addr_wq = create_singlethread_workqueue("ib_addr");
if (!addr_wq)
@@ -642,15 +806,13 @@ static int __init addr_init(void)
register_netevent_notifier(&nb);
rdma_addr_register_client(&self);
+
return 0;
}
-static void __exit addr_cleanup(void)
+void addr_cleanup(void)
{
rdma_addr_unregister_client(&self);
unregister_netevent_notifier(&nb);
destroy_workqueue(addr_wq);
}
-
-module_init(addr_init);
-module_exit(addr_cleanup);
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index c2e257d97eff..1a2984c28b95 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -178,6 +178,7 @@ static int write_gid(struct ib_device *ib_dev, u8 port,
{
int ret = 0;
struct net_device *old_net_dev;
+ enum ib_gid_type old_gid_type;
/* in rdma_cap_roce_gid_table, this funciton should be protected by a
* sleep-able lock.
@@ -199,6 +200,7 @@ static int write_gid(struct ib_device *ib_dev, u8 port,
}
old_net_dev = table->data_vec[ix].attr.ndev;
+ old_gid_type = table->data_vec[ix].attr.gid_type;
if (old_net_dev && old_net_dev != attr->ndev)
dev_put(old_net_dev);
/* if modify_gid failed, just delete the old gid */
@@ -207,10 +209,14 @@ static int write_gid(struct ib_device *ib_dev, u8 port,
attr = &zattr;
table->data_vec[ix].context = NULL;
}
- if (default_gid)
- table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT;
+
memcpy(&table->data_vec[ix].gid, gid, sizeof(*gid));
memcpy(&table->data_vec[ix].attr, attr, sizeof(*attr));
+ if (default_gid) {
+ table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT;
+ if (action == GID_TABLE_WRITE_ACTION_DEL)
+ table->data_vec[ix].attr.gid_type = old_gid_type;
+ }
if (table->data_vec[ix].attr.ndev &&
table->data_vec[ix].attr.ndev != old_net_dev)
dev_hold(table->data_vec[ix].attr.ndev);
@@ -405,7 +411,9 @@ int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
for (ix = 0; ix < table->sz; ix++)
if (table->data_vec[ix].attr.ndev == ndev)
- if (!del_gid(ib_dev, port, table, ix, false))
+ if (!del_gid(ib_dev, port, table, ix,
+ !!(table->data_vec[ix].props &
+ GID_TABLE_ENTRY_DEFAULT)))
deleted = true;
write_unlock_irq(&table->rwlock);
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 1d92e091e22e..c99525512b34 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -3452,14 +3452,14 @@ static int cm_establish(struct ib_cm_id *cm_id)
work->cm_event.event = IB_CM_USER_ESTABLISHED;
/* Check if the device started its remove_one */
- spin_lock_irq(&cm.lock);
+ spin_lock_irqsave(&cm.lock, flags);
if (!cm_dev->going_down) {
queue_delayed_work(cm.wq, &work->work, 0);
} else {
kfree(work);
ret = -ENODEV;
}
- spin_unlock_irq(&cm.lock);
+ spin_unlock_irqrestore(&cm.lock, flags);
out:
return ret;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f0c91ba3178a..ad1b1adcf6f0 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -708,17 +708,6 @@ static void cma_deref_id(struct rdma_id_private *id_priv)
complete(&id_priv->comp);
}
-static int cma_disable_callback(struct rdma_id_private *id_priv,
- enum rdma_cm_state state)
-{
- mutex_lock(&id_priv->handler_mutex);
- if (id_priv->state != state) {
- mutex_unlock(&id_priv->handler_mutex);
- return -EINVAL;
- }
- return 0;
-}
-
struct rdma_cm_id *rdma_create_id(struct net *net,
rdma_cm_event_handler event_handler,
void *context, enum rdma_port_space ps,
@@ -1671,11 +1660,12 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
struct rdma_cm_event event;
int ret = 0;
+ mutex_lock(&id_priv->handler_mutex);
if ((ib_event->event != IB_CM_TIMEWAIT_EXIT &&
- cma_disable_callback(id_priv, RDMA_CM_CONNECT)) ||
+ id_priv->state != RDMA_CM_CONNECT) ||
(ib_event->event == IB_CM_TIMEWAIT_EXIT &&
- cma_disable_callback(id_priv, RDMA_CM_DISCONNECT)))
- return 0;
+ id_priv->state != RDMA_CM_DISCONNECT))
+ goto out;
memset(&event, 0, sizeof event);
switch (ib_event->event) {
@@ -1870,7 +1860,7 @@ static int cma_check_req_qp_type(struct rdma_cm_id *id, struct ib_cm_event *ib_e
static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
{
- struct rdma_id_private *listen_id, *conn_id;
+ struct rdma_id_private *listen_id, *conn_id = NULL;
struct rdma_cm_event event;
struct net_device *net_dev;
int offset, ret;
@@ -1884,9 +1874,10 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
goto net_dev_put;
}
- if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) {
+ mutex_lock(&listen_id->handler_mutex);
+ if (listen_id->state != RDMA_CM_LISTEN) {
ret = -ECONNABORTED;
- goto net_dev_put;
+ goto err1;
}
memset(&event, 0, sizeof event);
@@ -1976,8 +1967,9 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
- if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
- return 0;
+ mutex_lock(&id_priv->handler_mutex);
+ if (id_priv->state != RDMA_CM_CONNECT)
+ goto out;
memset(&event, 0, sizeof event);
switch (iw_event->event) {
@@ -2029,6 +2021,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
return ret;
}
+out:
mutex_unlock(&id_priv->handler_mutex);
return ret;
}
@@ -2039,13 +2032,15 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
struct rdma_cm_id *new_cm_id;
struct rdma_id_private *listen_id, *conn_id;
struct rdma_cm_event event;
- int ret;
+ int ret = -ECONNABORTED;
struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
listen_id = cm_id->context;
- if (cma_disable_callback(listen_id, RDMA_CM_LISTEN))
- return -ECONNABORTED;
+
+ mutex_lock(&listen_id->handler_mutex);
+ if (listen_id->state != RDMA_CM_LISTEN)
+ goto out;
/* Create a new RDMA id for the new IW CM ID */
new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,
@@ -3216,8 +3211,9 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd;
int ret = 0;
- if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
- return 0;
+ mutex_lock(&id_priv->handler_mutex);
+ if (id_priv->state != RDMA_CM_CONNECT)
+ goto out;
memset(&event, 0, sizeof event);
switch (ib_event->event) {
@@ -3673,12 +3669,13 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
struct rdma_id_private *id_priv;
struct cma_multicast *mc = multicast->context;
struct rdma_cm_event event;
- int ret;
+ int ret = 0;
id_priv = mc->id_priv;
- if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) &&
- cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED))
- return 0;
+ mutex_lock(&id_priv->handler_mutex);
+ if (id_priv->state != RDMA_CM_ADDR_BOUND &&
+ id_priv->state != RDMA_CM_ADDR_RESOLVED)
+ goto out;
if (!status)
status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey));
@@ -3720,6 +3717,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
return 0;
}
+out:
mutex_unlock(&id_priv->handler_mutex);
return 0;
}
@@ -3878,12 +3876,12 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
rdma_start_port(id_priv->cma_dev->device)];
if (addr->sa_family == AF_INET) {
- if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+ if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+ mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
true);
- if (!err) {
- mc->igmp_joined = true;
- mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+ if (!err)
+ mc->igmp_joined = true;
}
} else {
if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index eab32215756b..19d499dcab76 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -137,4 +137,20 @@ static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
return _upper == upper;
}
+int addr_init(void);
+void addr_cleanup(void);
+
+int ib_mad_init(void);
+void ib_mad_cleanup(void);
+
+int ib_sa_init(void);
+void ib_sa_cleanup(void);
+
+int ib_nl_handle_resolve_resp(struct sk_buff *skb,
+ struct netlink_callback *cb);
+int ib_nl_handle_set_timeout(struct sk_buff *skb,
+ struct netlink_callback *cb);
+int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
+ struct netlink_callback *cb);
+
#endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 10979844026a..5c155fa91eec 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -661,6 +661,9 @@ int ib_query_port(struct ib_device *device,
if (err || port_attr->subnet_prefix)
return err;
+ if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND)
+ return 0;
+
err = ib_query_gid(device, port_num, 0, &gid, NULL);
if (err)
return err;
@@ -955,6 +958,29 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
}
EXPORT_SYMBOL(ib_get_net_dev_by_params);
+static struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+ [RDMA_NL_LS_OP_RESOLVE] = {
+ .dump = ib_nl_handle_resolve_resp,
+ .module = THIS_MODULE },
+ [RDMA_NL_LS_OP_SET_TIMEOUT] = {
+ .dump = ib_nl_handle_set_timeout,
+ .module = THIS_MODULE },
+ [RDMA_NL_LS_OP_IP_RESOLVE] = {
+ .dump = ib_nl_handle_ip_res_resp,
+ .module = THIS_MODULE },
+};
+
+static int ib_add_ibnl_clients(void)
+{
+ return ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ibnl_ls_cb_table),
+ ibnl_ls_cb_table);
+}
+
+static void ib_remove_ibnl_clients(void)
+{
+ ibnl_remove_client(RDMA_NL_LS);
+}
+
static int __init ib_core_init(void)
{
int ret;
@@ -983,10 +1009,42 @@ static int __init ib_core_init(void)
goto err_sysfs;
}
+ ret = addr_init();
+ if (ret) {
+ pr_warn("Could't init IB address resolution\n");
+ goto err_ibnl;
+ }
+
+ ret = ib_mad_init();
+ if (ret) {
+ pr_warn("Couldn't init IB MAD\n");
+ goto err_addr;
+ }
+
+ ret = ib_sa_init();
+ if (ret) {
+ pr_warn("Couldn't init SA\n");
+ goto err_mad;
+ }
+
+ ret = ib_add_ibnl_clients();
+ if (ret) {
+ pr_warn("Couldn't register ibnl clients\n");
+ goto err_sa;
+ }
+
ib_cache_setup();
return 0;
+err_sa:
+ ib_sa_cleanup();
+err_mad:
+ ib_mad_cleanup();
+err_addr:
+ addr_cleanup();
+err_ibnl:
+ ibnl_cleanup();
err_sysfs:
class_unregister(&ib_class);
err_comp:
@@ -999,6 +1057,10 @@ err:
static void __exit ib_core_cleanup(void)
{
ib_cache_cleanup();
+ ib_remove_ibnl_clients();
+ ib_sa_cleanup();
+ ib_mad_cleanup();
+ addr_cleanup();
ibnl_cleanup();
class_unregister(&ib_class);
destroy_workqueue(ib_comp_wq);
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 43e3fa27102b..1c41b95cefec 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -506,7 +506,7 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb,
if (!nlmsg_request) {
pr_info("%s: Could not find a matching request (seq = %u)\n",
__func__, msg_seq);
- return -EINVAL;
+ return -EINVAL;
}
pm_msg = nlmsg_request->req_buffer;
local_sockaddr = (struct sockaddr_storage *)
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 9fa5bf33f5a3..2d49228f28b2 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -47,11 +47,7 @@
#include "smi.h"
#include "opa_smi.h"
#include "agent.h"
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("kernel IB MAD API");
-MODULE_AUTHOR("Hal Rosenstock");
-MODULE_AUTHOR("Sean Hefty");
+#include "core_priv.h"
static int mad_sendq_size = IB_MAD_QP_SEND_SIZE;
static int mad_recvq_size = IB_MAD_QP_RECV_SIZE;
@@ -1642,9 +1638,9 @@ static void remove_mad_reg_req(struct ib_mad_agent_private *agent_priv)
/* Now, check to see if there are any methods still in use */
if (!check_method_table(method)) {
/* If not, release management method table */
- kfree(method);
- class->method_table[mgmt_class] = NULL;
- /* Any management classes left ? */
+ kfree(method);
+ class->method_table[mgmt_class] = NULL;
+ /* Any management classes left ? */
if (!check_class_table(class)) {
/* If not, release management class table */
kfree(class);
@@ -3316,7 +3312,7 @@ static struct ib_client mad_client = {
.remove = ib_mad_remove_device
};
-static int __init ib_mad_init_module(void)
+int ib_mad_init(void)
{
mad_recvq_size = min(mad_recvq_size, IB_MAD_QP_MAX_SIZE);
mad_recvq_size = max(mad_recvq_size, IB_MAD_QP_MIN_SIZE);
@@ -3334,10 +3330,7 @@ static int __init ib_mad_init_module(void)
return 0;
}
-static void __exit ib_mad_cleanup_module(void)
+void ib_mad_cleanup(void)
{
ib_unregister_client(&mad_client);
}
-
-module_init(ib_mad_init_module);
-module_exit(ib_mad_cleanup_module);
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index 250937cb9a1a..a83ec28a147b 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -93,6 +93,18 @@ enum {
struct mcast_member;
+/*
+* There are 4 types of join states:
+* FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember.
+*/
+enum {
+ FULLMEMBER_JOIN,
+ NONMEMBER_JOIN,
+ SENDONLY_NONMEBER_JOIN,
+ SENDONLY_FULLMEMBER_JOIN,
+ NUM_JOIN_MEMBERSHIP_TYPES,
+};
+
struct mcast_group {
struct ib_sa_mcmember_rec rec;
struct rb_node node;
@@ -102,7 +114,7 @@ struct mcast_group {
struct list_head pending_list;
struct list_head active_list;
struct mcast_member *last_join;
- int members[3];
+ int members[NUM_JOIN_MEMBERSHIP_TYPES];
atomic_t refcount;
enum mcast_group_state state;
struct ib_sa_query *query;
@@ -220,8 +232,9 @@ static void queue_join(struct mcast_member *member)
}
/*
- * A multicast group has three types of members: full member, non member, and
- * send only member. We need to keep track of the number of members of each
+ * A multicast group has four types of members: full member, non member,
+ * sendonly non member and sendonly full member.
+ * We need to keep track of the number of members of each
* type based on their join state. Adjust the number of members the belong to
* the specified join states.
*/
@@ -229,7 +242,7 @@ static void adjust_membership(struct mcast_group *group, u8 join_state, int inc)
{
int i;
- for (i = 0; i < 3; i++, join_state >>= 1)
+ for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++, join_state >>= 1)
if (join_state & 0x1)
group->members[i] += inc;
}
@@ -245,7 +258,7 @@ static u8 get_leave_state(struct mcast_group *group)
u8 leave_state = 0;
int i;
- for (i = 0; i < 3; i++)
+ for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++)
if (!group->members[i])
leave_state |= (0x1 << i);
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 3ebd108bcc5f..e95538650dc6 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -53,10 +53,6 @@
#include "sa.h"
#include "core_priv.h"
-MODULE_AUTHOR("Roland Dreier");
-MODULE_DESCRIPTION("InfiniBand subnet administration query support");
-MODULE_LICENSE("Dual BSD/GPL");
-
#define IB_SA_LOCAL_SVC_TIMEOUT_MIN 100
#define IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT 2000
#define IB_SA_LOCAL_SVC_TIMEOUT_MAX 200000
@@ -119,6 +115,12 @@ struct ib_sa_guidinfo_query {
struct ib_sa_query sa_query;
};
+struct ib_sa_classport_info_query {
+ void (*callback)(int, struct ib_class_port_info *, void *);
+ void *context;
+ struct ib_sa_query sa_query;
+};
+
struct ib_sa_mcmember_query {
void (*callback)(int, struct ib_sa_mcmember_rec *, void *);
void *context;
@@ -392,6 +394,82 @@ static const struct ib_field service_rec_table[] = {
.size_bits = 2*64 },
};
+#define CLASSPORTINFO_REC_FIELD(field) \
+ .struct_offset_bytes = offsetof(struct ib_class_port_info, field), \
+ .struct_size_bytes = sizeof((struct ib_class_port_info *)0)->field, \
+ .field_name = "ib_class_port_info:" #field
+
+static const struct ib_field classport_info_rec_table[] = {
+ { CLASSPORTINFO_REC_FIELD(base_version),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 8 },
+ { CLASSPORTINFO_REC_FIELD(class_version),
+ .offset_words = 0,
+ .offset_bits = 8,
+ .size_bits = 8 },
+ { CLASSPORTINFO_REC_FIELD(capability_mask),
+ .offset_words = 0,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 32 },
+ { CLASSPORTINFO_REC_FIELD(redirect_gid),
+ .offset_words = 2,
+ .offset_bits = 0,
+ .size_bits = 128 },
+ { CLASSPORTINFO_REC_FIELD(redirect_tcslfl),
+ .offset_words = 6,
+ .offset_bits = 0,
+ .size_bits = 32 },
+ { CLASSPORTINFO_REC_FIELD(redirect_lid),
+ .offset_words = 7,
+ .offset_bits = 0,
+ .size_bits = 16 },
+ { CLASSPORTINFO_REC_FIELD(redirect_pkey),
+ .offset_words = 7,
+ .offset_bits = 16,
+ .size_bits = 16 },
+
+ { CLASSPORTINFO_REC_FIELD(redirect_qp),
+ .offset_words = 8,
+ .offset_bits = 0,
+ .size_bits = 32 },
+ { CLASSPORTINFO_REC_FIELD(redirect_qkey),
+ .offset_words = 9,
+ .offset_bits = 0,
+ .size_bits = 32 },
+
+ { CLASSPORTINFO_REC_FIELD(trap_gid),
+ .offset_words = 10,
+ .offset_bits = 0,
+ .size_bits = 128 },
+ { CLASSPORTINFO_REC_FIELD(trap_tcslfl),
+ .offset_words = 14,
+ .offset_bits = 0,
+ .size_bits = 32 },
+
+ { CLASSPORTINFO_REC_FIELD(trap_lid),
+ .offset_words = 15,
+ .offset_bits = 0,
+ .size_bits = 16 },
+ { CLASSPORTINFO_REC_FIELD(trap_pkey),
+ .offset_words = 15,
+ .offset_bits = 16,
+ .size_bits = 16 },
+
+ { CLASSPORTINFO_REC_FIELD(trap_hlqp),
+ .offset_words = 16,
+ .offset_bits = 0,
+ .size_bits = 32 },
+ { CLASSPORTINFO_REC_FIELD(trap_qkey),
+ .offset_words = 17,
+ .offset_bits = 0,
+ .size_bits = 32 },
+};
+
#define GUIDINFO_REC_FIELD(field) \
.struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field), \
.struct_size_bytes = sizeof((struct ib_sa_guidinfo_rec *) 0)->field, \
@@ -705,8 +783,8 @@ static void ib_nl_request_timeout(struct work_struct *work)
spin_unlock_irqrestore(&ib_nl_request_lock, flags);
}
-static int ib_nl_handle_set_timeout(struct sk_buff *skb,
- struct netlink_callback *cb)
+int ib_nl_handle_set_timeout(struct sk_buff *skb,
+ struct netlink_callback *cb)
{
const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
int timeout, delta, abs_delta;
@@ -782,8 +860,8 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
return 1;
}
-static int ib_nl_handle_resolve_resp(struct sk_buff *skb,
- struct netlink_callback *cb)
+int ib_nl_handle_resolve_resp(struct sk_buff *skb,
+ struct netlink_callback *cb)
{
const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
unsigned long flags;
@@ -838,15 +916,6 @@ resp_out:
return skb->len;
}
-static struct ibnl_client_cbs ib_sa_cb_table[] = {
- [RDMA_NL_LS_OP_RESOLVE] = {
- .dump = ib_nl_handle_resolve_resp,
- .module = THIS_MODULE },
- [RDMA_NL_LS_OP_SET_TIMEOUT] = {
- .dump = ib_nl_handle_set_timeout,
- .module = THIS_MODULE },
-};
-
static void free_sm_ah(struct kref *kref)
{
struct ib_sa_sm_ah *sm_ah = container_of(kref, struct ib_sa_sm_ah, ref);
@@ -1645,6 +1714,97 @@ err1:
}
EXPORT_SYMBOL(ib_sa_guid_info_rec_query);
+/* Support get SA ClassPortInfo */
+static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query,
+ int status,
+ struct ib_sa_mad *mad)
+{
+ struct ib_sa_classport_info_query *query =
+ container_of(sa_query, struct ib_sa_classport_info_query, sa_query);
+
+ if (mad) {
+ struct ib_class_port_info rec;
+
+ ib_unpack(classport_info_rec_table,
+ ARRAY_SIZE(classport_info_rec_table),
+ mad->data, &rec);
+ query->callback(status, &rec, query->context);
+ } else {
+ query->callback(status, NULL, query->context);
+ }
+}
+
+static void ib_sa_portclass_info_rec_release(struct ib_sa_query *sa_query)
+{
+ kfree(container_of(sa_query, struct ib_sa_classport_info_query,
+ sa_query));
+}
+
+int ib_sa_classport_info_rec_query(struct ib_sa_client *client,
+ struct ib_device *device, u8 port_num,
+ int timeout_ms, gfp_t gfp_mask,
+ void (*callback)(int status,
+ struct ib_class_port_info *resp,
+ void *context),
+ void *context,
+ struct ib_sa_query **sa_query)
+{
+ struct ib_sa_classport_info_query *query;
+ struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
+ struct ib_sa_port *port;
+ struct ib_mad_agent *agent;
+ struct ib_sa_mad *mad;
+ int ret;
+
+ if (!sa_dev)
+ return -ENODEV;
+
+ port = &sa_dev->port[port_num - sa_dev->start_port];
+ agent = port->agent;
+
+ query = kzalloc(sizeof(*query), gfp_mask);
+ if (!query)
+ return -ENOMEM;
+
+ query->sa_query.port = port;
+ ret = alloc_mad(&query->sa_query, gfp_mask);
+ if (ret)
+ goto err1;
+
+ ib_sa_client_get(client);
+ query->sa_query.client = client;
+ query->callback = callback;
+ query->context = context;
+
+ mad = query->sa_query.mad_buf->mad;
+ init_mad(mad, agent);
+
+ query->sa_query.callback = callback ? ib_sa_classport_info_rec_callback : NULL;
+
+ query->sa_query.release = ib_sa_portclass_info_rec_release;
+ /* support GET only */
+ mad->mad_hdr.method = IB_MGMT_METHOD_GET;
+ mad->mad_hdr.attr_id = cpu_to_be16(IB_SA_ATTR_CLASS_PORTINFO);
+ mad->sa_hdr.comp_mask = 0;
+ *sa_query = &query->sa_query;
+
+ ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+ if (ret < 0)
+ goto err2;
+
+ return ret;
+
+err2:
+ *sa_query = NULL;
+ ib_sa_client_put(query->sa_query.client);
+ free_mad(&query->sa_query);
+
+err1:
+ kfree(query);
+ return ret;
+}
+EXPORT_SYMBOL(ib_sa_classport_info_rec_query);
+
static void send_handler(struct ib_mad_agent *agent,
struct ib_mad_send_wc *mad_send_wc)
{
@@ -1794,7 +1954,7 @@ static void ib_sa_remove_one(struct ib_device *device, void *client_data)
kfree(sa_dev);
}
-static int __init ib_sa_init(void)
+int ib_sa_init(void)
{
int ret;
@@ -1820,17 +1980,10 @@ static int __init ib_sa_init(void)
goto err3;
}
- if (ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ib_sa_cb_table),
- ib_sa_cb_table)) {
- pr_err("Failed to add netlink callback\n");
- ret = -EINVAL;
- goto err4;
- }
INIT_DELAYED_WORK(&ib_nl_timed_work, ib_nl_request_timeout);
return 0;
-err4:
- destroy_workqueue(ib_nl_wq);
+
err3:
mcast_cleanup();
err2:
@@ -1839,9 +1992,8 @@ err1:
return ret;
}
-static void __exit ib_sa_cleanup(void)
+void ib_sa_cleanup(void)
{
- ibnl_remove_client(RDMA_NL_LS);
cancel_delayed_work(&ib_nl_timed_work);
flush_workqueue(ib_nl_wq);
destroy_workqueue(ib_nl_wq);
@@ -1849,6 +2001,3 @@ static void __exit ib_sa_cleanup(void)
ib_unregister_client(&sa_client);
idr_destroy(&query_idr);
}
-
-module_init(ib_sa_init);
-module_exit(ib_sa_cleanup);
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 14606afbfaa8..a5793c8f1590 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -56,8 +56,10 @@ struct ib_port {
struct gid_attr_group *gid_attr_group;
struct attribute_group gid_group;
struct attribute_group pkey_group;
- u8 port_num;
struct attribute_group *pma_table;
+ struct attribute_group *hw_stats_ag;
+ struct rdma_hw_stats *hw_stats;
+ u8 port_num;
};
struct port_attribute {
@@ -80,6 +82,18 @@ struct port_table_attribute {
__be16 attr_id;
};
+struct hw_stats_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct kobject *kobj,
+ struct attribute *attr, char *buf);
+ ssize_t (*store)(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf,
+ size_t count);
+ int index;
+ u8 port_num;
+};
+
static ssize_t port_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
@@ -733,6 +747,220 @@ static struct attribute_group *get_counter_table(struct ib_device *dev,
return &pma_group;
}
+static int update_hw_stats(struct ib_device *dev, struct rdma_hw_stats *stats,
+ u8 port_num, int index)
+{
+ int ret;
+
+ if (time_is_after_eq_jiffies(stats->timestamp + stats->lifespan))
+ return 0;
+ ret = dev->get_hw_stats(dev, stats, port_num, index);
+ if (ret < 0)
+ return ret;
+ if (ret == stats->num_counters)
+ stats->timestamp = jiffies;
+
+ return 0;
+}
+
+static ssize_t print_hw_stat(struct rdma_hw_stats *stats, int index, char *buf)
+{
+ return sprintf(buf, "%llu\n", stats->value[index]);
+}
+
+static ssize_t show_hw_stats(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct ib_device *dev;
+ struct ib_port *port;
+ struct hw_stats_attribute *hsa;
+ struct rdma_hw_stats *stats;
+ int ret;
+
+ hsa = container_of(attr, struct hw_stats_attribute, attr);
+ if (!hsa->port_num) {
+ dev = container_of((struct device *)kobj,
+ struct ib_device, dev);
+ stats = dev->hw_stats;
+ } else {
+ port = container_of(kobj, struct ib_port, kobj);
+ dev = port->ibdev;
+ stats = port->hw_stats;
+ }
+ ret = update_hw_stats(dev, stats, hsa->port_num, hsa->index);
+ if (ret)
+ return ret;
+ return print_hw_stat(stats, hsa->index, buf);
+}
+
+static ssize_t show_stats_lifespan(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct hw_stats_attribute *hsa;
+ int msecs;
+
+ hsa = container_of(attr, struct hw_stats_attribute, attr);
+ if (!hsa->port_num) {
+ struct ib_device *dev = container_of((struct device *)kobj,
+ struct ib_device, dev);
+ msecs = jiffies_to_msecs(dev->hw_stats->lifespan);
+ } else {
+ struct ib_port *p = container_of(kobj, struct ib_port, kobj);
+ msecs = jiffies_to_msecs(p->hw_stats->lifespan);
+ }
+ return sprintf(buf, "%d\n", msecs);
+}
+
+static ssize_t set_stats_lifespan(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hw_stats_attribute *hsa;
+ int msecs;
+ int jiffies;
+ int ret;
+
+ ret = kstrtoint(buf, 10, &msecs);
+ if (ret)
+ return ret;
+ if (msecs < 0 || msecs > 10000)
+ return -EINVAL;
+ jiffies = msecs_to_jiffies(msecs);
+ hsa = container_of(attr, struct hw_stats_attribute, attr);
+ if (!hsa->port_num) {
+ struct ib_device *dev = container_of((struct device *)kobj,
+ struct ib_device, dev);
+ dev->hw_stats->lifespan = jiffies;
+ } else {
+ struct ib_port *p = container_of(kobj, struct ib_port, kobj);
+ p->hw_stats->lifespan = jiffies;
+ }
+ return count;
+}
+
+static void free_hsag(struct kobject *kobj, struct attribute_group *attr_group)
+{
+ struct attribute **attr;
+
+ sysfs_remove_group(kobj, attr_group);
+
+ for (attr = attr_group->attrs; *attr; attr++)
+ kfree(*attr);
+ kfree(attr_group);
+}
+
+static struct attribute *alloc_hsa(int index, u8 port_num, const char *name)
+{
+ struct hw_stats_attribute *hsa;
+
+ hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
+ if (!hsa)
+ return NULL;
+
+ hsa->attr.name = (char *)name;
+ hsa->attr.mode = S_IRUGO;
+ hsa->show = show_hw_stats;
+ hsa->store = NULL;
+ hsa->index = index;
+ hsa->port_num = port_num;
+
+ return &hsa->attr;
+}
+
+static struct attribute *alloc_hsa_lifespan(char *name, u8 port_num)
+{
+ struct hw_stats_attribute *hsa;
+
+ hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
+ if (!hsa)
+ return NULL;
+
+ hsa->attr.name = name;
+ hsa->attr.mode = S_IWUSR | S_IRUGO;
+ hsa->show = show_stats_lifespan;
+ hsa->store = set_stats_lifespan;
+ hsa->index = 0;
+ hsa->port_num = port_num;
+
+ return &hsa->attr;
+}
+
+static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
+ u8 port_num)
+{
+ struct attribute_group *hsag;
+ struct rdma_hw_stats *stats;
+ int i, ret;
+
+ stats = device->alloc_hw_stats(device, port_num);
+
+ if (!stats)
+ return;
+
+ if (!stats->names || stats->num_counters <= 0)
+ goto err_free_stats;
+
+ /*
+ * Two extra attribue elements here, one for the lifespan entry and
+ * one to NULL terminate the list for the sysfs core code
+ */
+ hsag = kzalloc(sizeof(*hsag) +
+ sizeof(void *) * (stats->num_counters + 2),
+ GFP_KERNEL);
+ if (!hsag)
+ goto err_free_stats;
+
+ ret = device->get_hw_stats(device, stats, port_num,
+ stats->num_counters);
+ if (ret != stats->num_counters)
+ goto err_free_hsag;
+
+ stats->timestamp = jiffies;
+
+ hsag->name = "hw_counters";
+ hsag->attrs = (void *)hsag + sizeof(*hsag);
+
+ for (i = 0; i < stats->num_counters; i++) {
+ hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]);
+ if (!hsag->attrs[i])
+ goto err;
+ sysfs_attr_init(hsag->attrs[i]);
+ }
+
+ /* treat an error here as non-fatal */
+ hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num);
+ if (hsag->attrs[i])
+ sysfs_attr_init(hsag->attrs[i]);
+
+ if (port) {
+ struct kobject *kobj = &port->kobj;
+ ret = sysfs_create_group(kobj, hsag);
+ if (ret)
+ goto err;
+ port->hw_stats_ag = hsag;
+ port->hw_stats = stats;
+ } else {
+ struct kobject *kobj = &device->dev.kobj;
+ ret = sysfs_create_group(kobj, hsag);
+ if (ret)
+ goto err;
+ device->hw_stats_ag = hsag;
+ device->hw_stats = stats;
+ }
+
+ return;
+
+err:
+ for (; i >= 0; i--)
+ kfree(hsag->attrs[i]);
+err_free_hsag:
+ kfree(hsag);
+err_free_stats:
+ kfree(stats);
+ return;
+}
+
static int add_port(struct ib_device *device, int port_num,
int (*port_callback)(struct ib_device *,
u8, struct kobject *))
@@ -835,6 +1063,14 @@ static int add_port(struct ib_device *device, int port_num,
goto err_remove_pkey;
}
+ /*
+ * If port == 0, it means we have only one port and the parent
+ * device, not this port device, should be the holder of the
+ * hw_counters
+ */
+ if (device->alloc_hw_stats && port_num)
+ setup_hw_stats(device, p, port_num);
+
list_add_tail(&p->kobj.entry, &device->port_list);
kobject_uevent(&p->kobj, KOBJ_ADD);
@@ -972,120 +1208,6 @@ static struct device_attribute *ib_class_attributes[] = {
&dev_attr_node_desc
};
-/* Show a given an attribute in the statistics group */
-static ssize_t show_protocol_stat(const struct device *device,
- struct device_attribute *attr, char *buf,
- unsigned offset)
-{
- struct ib_device *dev = container_of(device, struct ib_device, dev);
- union rdma_protocol_stats stats;
- ssize_t ret;
-
- ret = dev->get_protocol_stats(dev, &stats);
- if (ret)
- return ret;
-
- return sprintf(buf, "%llu\n",
- (unsigned long long) ((u64 *) &stats)[offset]);
-}
-
-/* generate a read-only iwarp statistics attribute */
-#define IW_STATS_ENTRY(name) \
-static ssize_t show_##name(struct device *device, \
- struct device_attribute *attr, char *buf) \
-{ \
- return show_protocol_stat(device, attr, buf, \
- offsetof(struct iw_protocol_stats, name) / \
- sizeof (u64)); \
-} \
-static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
-
-IW_STATS_ENTRY(ipInReceives);
-IW_STATS_ENTRY(ipInHdrErrors);
-IW_STATS_ENTRY(ipInTooBigErrors);
-IW_STATS_ENTRY(ipInNoRoutes);
-IW_STATS_ENTRY(ipInAddrErrors);
-IW_STATS_ENTRY(ipInUnknownProtos);
-IW_STATS_ENTRY(ipInTruncatedPkts);
-IW_STATS_ENTRY(ipInDiscards);
-IW_STATS_ENTRY(ipInDelivers);
-IW_STATS_ENTRY(ipOutForwDatagrams);
-IW_STATS_ENTRY(ipOutRequests);
-IW_STATS_ENTRY(ipOutDiscards);
-IW_STATS_ENTRY(ipOutNoRoutes);
-IW_STATS_ENTRY(ipReasmTimeout);
-IW_STATS_ENTRY(ipReasmReqds);
-IW_STATS_ENTRY(ipReasmOKs);
-IW_STATS_ENTRY(ipReasmFails);
-IW_STATS_ENTRY(ipFragOKs);
-IW_STATS_ENTRY(ipFragFails);
-IW_STATS_ENTRY(ipFragCreates);
-IW_STATS_ENTRY(ipInMcastPkts);
-IW_STATS_ENTRY(ipOutMcastPkts);
-IW_STATS_ENTRY(ipInBcastPkts);
-IW_STATS_ENTRY(ipOutBcastPkts);
-IW_STATS_ENTRY(tcpRtoAlgorithm);
-IW_STATS_ENTRY(tcpRtoMin);
-IW_STATS_ENTRY(tcpRtoMax);
-IW_STATS_ENTRY(tcpMaxConn);
-IW_STATS_ENTRY(tcpActiveOpens);
-IW_STATS_ENTRY(tcpPassiveOpens);
-IW_STATS_ENTRY(tcpAttemptFails);
-IW_STATS_ENTRY(tcpEstabResets);
-IW_STATS_ENTRY(tcpCurrEstab);
-IW_STATS_ENTRY(tcpInSegs);
-IW_STATS_ENTRY(tcpOutSegs);
-IW_STATS_ENTRY(tcpRetransSegs);
-IW_STATS_ENTRY(tcpInErrs);
-IW_STATS_ENTRY(tcpOutRsts);
-
-static struct attribute *iw_proto_stats_attrs[] = {
- &dev_attr_ipInReceives.attr,
- &dev_attr_ipInHdrErrors.attr,
- &dev_attr_ipInTooBigErrors.attr,
- &dev_attr_ipInNoRoutes.attr,
- &dev_attr_ipInAddrErrors.attr,
- &dev_attr_ipInUnknownProtos.attr,
- &dev_attr_ipInTruncatedPkts.attr,
- &dev_attr_ipInDiscards.attr,
- &dev_attr_ipInDelivers.attr,
- &dev_attr_ipOutForwDatagrams.attr,
- &dev_attr_ipOutRequests.attr,
- &dev_attr_ipOutDiscards.attr,
- &dev_attr_ipOutNoRoutes.attr,
- &dev_attr_ipReasmTimeout.attr,
- &dev_attr_ipReasmReqds.attr,
- &dev_attr_ipReasmOKs.attr,
- &dev_attr_ipReasmFails.attr,
- &dev_attr_ipFragOKs.attr,
- &dev_attr_ipFragFails.attr,
- &dev_attr_ipFragCreates.attr,
- &dev_attr_ipInMcastPkts.attr,
- &dev_attr_ipOutMcastPkts.attr,
- &dev_attr_ipInBcastPkts.attr,
- &dev_attr_ipOutBcastPkts.attr,
- &dev_attr_tcpRtoAlgorithm.attr,
- &dev_attr_tcpRtoMin.attr,
- &dev_attr_tcpRtoMax.attr,
- &dev_attr_tcpMaxConn.attr,
- &dev_attr_tcpActiveOpens.attr,
- &dev_attr_tcpPassiveOpens.attr,
- &dev_attr_tcpAttemptFails.attr,
- &dev_attr_tcpEstabResets.attr,
- &dev_attr_tcpCurrEstab.attr,
- &dev_attr_tcpInSegs.attr,
- &dev_attr_tcpOutSegs.attr,
- &dev_attr_tcpRetransSegs.attr,
- &dev_attr_tcpInErrs.attr,
- &dev_attr_tcpOutRsts.attr,
- NULL
-};
-
-static struct attribute_group iw_stats_group = {
- .name = "proto_stats",
- .attrs = iw_proto_stats_attrs,
-};
-
static void free_port_list_attributes(struct ib_device *device)
{
struct kobject *p, *t;
@@ -1093,6 +1215,10 @@ static void free_port_list_attributes(struct ib_device *device)
list_for_each_entry_safe(p, t, &device->port_list, entry) {
struct ib_port *port = container_of(p, struct ib_port, kobj);
list_del(&p->entry);
+ if (port->hw_stats) {
+ kfree(port->hw_stats);
+ free_hsag(&port->kobj, port->hw_stats_ag);
+ }
sysfs_remove_group(p, port->pma_table);
sysfs_remove_group(p, &port->pkey_group);
sysfs_remove_group(p, &port->gid_group);
@@ -1149,11 +1275,8 @@ int ib_device_register_sysfs(struct ib_device *device,
}
}
- if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats) {
- ret = sysfs_create_group(&class_dev->kobj, &iw_stats_group);
- if (ret)
- goto err_put;
- }
+ if (device->alloc_hw_stats)
+ setup_hw_stats(device, NULL, 0);
return 0;
@@ -1169,15 +1292,18 @@ err:
void ib_device_unregister_sysfs(struct ib_device *device)
{
- /* Hold kobject until ib_dealloc_device() */
- struct kobject *kobj_dev = kobject_get(&device->dev.kobj);
int i;
- if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats)
- sysfs_remove_group(kobj_dev, &iw_stats_group);
+ /* Hold kobject until ib_dealloc_device() */
+ kobject_get(&device->dev.kobj);
free_port_list_attributes(device);
+ if (device->hw_stats) {
+ kfree(device->hw_stats);
+ free_hsag(&device->dev.kobj, device->hw_stats_ag);
+ }
+
for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i)
device_remove_file(&device->dev, ib_class_attributes[i]);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 1a8babb8ee3c..825021d1008b 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1747,7 +1747,7 @@ static int create_qp(struct ib_uverbs_file *file,
struct ib_srq *srq = NULL;
struct ib_qp *qp;
char *buf;
- struct ib_qp_init_attr attr;
+ struct ib_qp_init_attr attr = {};
struct ib_uverbs_ex_create_qp_resp resp;
int ret;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 1d7d4cf442e3..6298f54b4137 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -511,12 +511,16 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
ah_attr->grh.dgid = sgid;
if (!rdma_cap_eth_ah(device, port_num)) {
- ret = ib_find_cached_gid_by_port(device, &dgid,
- IB_GID_TYPE_IB,
- port_num, NULL,
- &gid_index);
- if (ret)
- return ret;
+ if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) {
+ ret = ib_find_cached_gid_by_port(device, &dgid,
+ IB_GID_TYPE_IB,
+ port_num, NULL,
+ &gid_index);
+ if (ret)
+ return ret;
+ } else {
+ gid_index = 0;
+ }
}
ah_attr->grh.sgid_index = (u8) gid_index;
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index c7ad0a4c8b15..c0c7cf8af3f4 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/drivers/infiniband/hw/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5/
obj-$(CONFIG_INFINIBAND_NES) += nes/
obj-$(CONFIG_INFINIBAND_OCRDMA) += ocrdma/
obj-$(CONFIG_INFINIBAND_USNIC) += usnic/
+obj-$(CONFIG_INFINIBAND_HFI1) += hfi1/
diff --git a/drivers/infiniband/hw/cxgb3/cxio_hal.c b/drivers/infiniband/hw/cxgb3/cxio_hal.c
index de1c61b417d6..ada2e5009c86 100644
--- a/drivers/infiniband/hw/cxgb3/cxio_hal.c
+++ b/drivers/infiniband/hw/cxgb3/cxio_hal.c
@@ -327,7 +327,7 @@ int cxio_destroy_cq(struct cxio_rdev *rdev_p, struct t3_cq *cq)
kfree(cq->sw_queue);
dma_free_coherent(&(rdev_p->rnic_info.pdev->dev),
(1UL << (cq->size_log2))
- * sizeof(struct t3_cqe), cq->queue,
+ * sizeof(struct t3_cqe) + 1, cq->queue,
dma_unmap_addr(cq, mapping));
cxio_hal_put_cqid(rdev_p->rscp, cq->cqid);
return err;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 47cb927a0dd6..bb1a839d4d6d 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -1218,59 +1218,119 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr,
iwch_dev->rdev.rnic_info.pdev->device);
}
-static int iwch_get_mib(struct ib_device *ibdev,
- union rdma_protocol_stats *stats)
+enum counters {
+ IPINRECEIVES,
+ IPINHDRERRORS,
+ IPINADDRERRORS,
+ IPINUNKNOWNPROTOS,
+ IPINDISCARDS,
+ IPINDELIVERS,
+ IPOUTREQUESTS,
+ IPOUTDISCARDS,
+ IPOUTNOROUTES,
+ IPREASMTIMEOUT,
+ IPREASMREQDS,
+ IPREASMOKS,
+ IPREASMFAILS,
+ TCPACTIVEOPENS,
+ TCPPASSIVEOPENS,
+ TCPATTEMPTFAILS,
+ TCPESTABRESETS,
+ TCPCURRESTAB,
+ TCPINSEGS,
+ TCPOUTSEGS,
+ TCPRETRANSSEGS,
+ TCPINERRS,
+ TCPOUTRSTS,
+ TCPRTOMIN,
+ TCPRTOMAX,
+ NR_COUNTERS
+};
+
+static const char * const names[] = {
+ [IPINRECEIVES] = "ipInReceives",
+ [IPINHDRERRORS] = "ipInHdrErrors",
+ [IPINADDRERRORS] = "ipInAddrErrors",
+ [IPINUNKNOWNPROTOS] = "ipInUnknownProtos",
+ [IPINDISCARDS] = "ipInDiscards",
+ [IPINDELIVERS] = "ipInDelivers",
+ [IPOUTREQUESTS] = "ipOutRequests",
+ [IPOUTDISCARDS] = "ipOutDiscards",
+ [IPOUTNOROUTES] = "ipOutNoRoutes",
+ [IPREASMTIMEOUT] = "ipReasmTimeout",
+ [IPREASMREQDS] = "ipReasmReqds",
+ [IPREASMOKS] = "ipReasmOKs",
+ [IPREASMFAILS] = "ipReasmFails",
+ [TCPACTIVEOPENS] = "tcpActiveOpens",
+ [TCPPASSIVEOPENS] = "tcpPassiveOpens",
+ [TCPATTEMPTFAILS] = "tcpAttemptFails",
+ [TCPESTABRESETS] = "tcpEstabResets",
+ [TCPCURRESTAB] = "tcpCurrEstab",
+ [TCPINSEGS] = "tcpInSegs",
+ [TCPOUTSEGS] = "tcpOutSegs",
+ [TCPRETRANSSEGS] = "tcpRetransSegs",
+ [TCPINERRS] = "tcpInErrs",
+ [TCPOUTRSTS] = "tcpOutRsts",
+ [TCPRTOMIN] = "tcpRtoMin",
+ [TCPRTOMAX] = "tcpRtoMax",
+};
+
+static struct rdma_hw_stats *iwch_alloc_stats(struct ib_device *ibdev,
+ u8 port_num)
+{
+ BUILD_BUG_ON(ARRAY_SIZE(names) != NR_COUNTERS);
+
+ /* Our driver only supports device level stats */
+ if (port_num != 0)
+ return NULL;
+
+ return rdma_alloc_hw_stats_struct(names, NR_COUNTERS,
+ RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
+static int iwch_get_mib(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+ u8 port, int index)
{
struct iwch_dev *dev;
struct tp_mib_stats m;
int ret;
+ if (port != 0 || !stats)
+ return -ENOSYS;
+
PDBG("%s ibdev %p\n", __func__, ibdev);
dev = to_iwch_dev(ibdev);
ret = dev->rdev.t3cdev_p->ctl(dev->rdev.t3cdev_p, RDMA_GET_MIB, &m);
if (ret)
return -ENOSYS;
- memset(stats, 0, sizeof *stats);
- stats->iw.ipInReceives = ((u64) m.ipInReceive_hi << 32) +
- m.ipInReceive_lo;
- stats->iw.ipInHdrErrors = ((u64) m.ipInHdrErrors_hi << 32) +
- m.ipInHdrErrors_lo;
- stats->iw.ipInAddrErrors = ((u64) m.ipInAddrErrors_hi << 32) +
- m.ipInAddrErrors_lo;
- stats->iw.ipInUnknownProtos = ((u64) m.ipInUnknownProtos_hi << 32) +
- m.ipInUnknownProtos_lo;
- stats->iw.ipInDiscards = ((u64) m.ipInDiscards_hi << 32) +
- m.ipInDiscards_lo;
- stats->iw.ipInDelivers = ((u64) m.ipInDelivers_hi << 32) +
- m.ipInDelivers_lo;
- stats->iw.ipOutRequests = ((u64) m.ipOutRequests_hi << 32) +
- m.ipOutRequests_lo;
- stats->iw.ipOutDiscards = ((u64) m.ipOutDiscards_hi << 32) +
- m.ipOutDiscards_lo;
- stats->iw.ipOutNoRoutes = ((u64) m.ipOutNoRoutes_hi << 32) +
- m.ipOutNoRoutes_lo;
- stats->iw.ipReasmTimeout = (u64) m.ipReasmTimeout;
- stats->iw.ipReasmReqds = (u64) m.ipReasmReqds;
- stats->iw.ipReasmOKs = (u64) m.ipReasmOKs;
- stats->iw.ipReasmFails = (u64) m.ipReasmFails;
- stats->iw.tcpActiveOpens = (u64) m.tcpActiveOpens;
- stats->iw.tcpPassiveOpens = (u64) m.tcpPassiveOpens;
- stats->iw.tcpAttemptFails = (u64) m.tcpAttemptFails;
- stats->iw.tcpEstabResets = (u64) m.tcpEstabResets;
- stats->iw.tcpOutRsts = (u64) m.tcpOutRsts;
- stats->iw.tcpCurrEstab = (u64) m.tcpCurrEstab;
- stats->iw.tcpInSegs = ((u64) m.tcpInSegs_hi << 32) +
- m.tcpInSegs_lo;
- stats->iw.tcpOutSegs = ((u64) m.tcpOutSegs_hi << 32) +
- m.tcpOutSegs_lo;
- stats->iw.tcpRetransSegs = ((u64) m.tcpRetransSeg_hi << 32) +
- m.tcpRetransSeg_lo;
- stats->iw.tcpInErrs = ((u64) m.tcpInErrs_hi << 32) +
- m.tcpInErrs_lo;
- stats->iw.tcpRtoMin = (u64) m.tcpRtoMin;
- stats->iw.tcpRtoMax = (u64) m.tcpRtoMax;
- return 0;
+ stats->value[IPINRECEIVES] = ((u64)m.ipInReceive_hi << 32) + m.ipInReceive_lo;
+ stats->value[IPINHDRERRORS] = ((u64)m.ipInHdrErrors_hi << 32) + m.ipInHdrErrors_lo;
+ stats->value[IPINADDRERRORS] = ((u64)m.ipInAddrErrors_hi << 32) + m.ipInAddrErrors_lo;
+ stats->value[IPINUNKNOWNPROTOS] = ((u64)m.ipInUnknownProtos_hi << 32) + m.ipInUnknownProtos_lo;
+ stats->value[IPINDISCARDS] = ((u64)m.ipInDiscards_hi << 32) + m.ipInDiscards_lo;
+ stats->value[IPINDELIVERS] = ((u64)m.ipInDelivers_hi << 32) + m.ipInDelivers_lo;
+ stats->value[IPOUTREQUESTS] = ((u64)m.ipOutRequests_hi << 32) + m.ipOutRequests_lo;
+ stats->value[IPOUTDISCARDS] = ((u64)m.ipOutDiscards_hi << 32) + m.ipOutDiscards_lo;
+ stats->value[IPOUTNOROUTES] = ((u64)m.ipOutNoRoutes_hi << 32) + m.ipOutNoRoutes_lo;
+ stats->value[IPREASMTIMEOUT] = m.ipReasmTimeout;
+ stats->value[IPREASMREQDS] = m.ipReasmReqds;
+ stats->value[IPREASMOKS] = m.ipReasmOKs;
+ stats->value[IPREASMFAILS] = m.ipReasmFails;
+ stats->value[TCPACTIVEOPENS] = m.tcpActiveOpens;
+ stats->value[TCPPASSIVEOPENS] = m.tcpPassiveOpens;
+ stats->value[TCPATTEMPTFAILS] = m.tcpAttemptFails;
+ stats->value[TCPESTABRESETS] = m.tcpEstabResets;
+ stats->value[TCPCURRESTAB] = m.tcpOutRsts;
+ stats->value[TCPINSEGS] = m.tcpCurrEstab;
+ stats->value[TCPOUTSEGS] = ((u64)m.tcpInSegs_hi << 32) + m.tcpInSegs_lo;
+ stats->value[TCPRETRANSSEGS] = ((u64)m.tcpOutSegs_hi << 32) + m.tcpOutSegs_lo;
+ stats->value[TCPINERRS] = ((u64)m.tcpRetransSeg_hi << 32) + m.tcpRetransSeg_lo,
+ stats->value[TCPOUTRSTS] = ((u64)m.tcpInErrs_hi << 32) + m.tcpInErrs_lo;
+ stats->value[TCPRTOMIN] = m.tcpRtoMin;
+ stats->value[TCPRTOMAX] = m.tcpRtoMax;
+
+ return stats->num_counters;
}
static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
@@ -1373,7 +1433,8 @@ int iwch_register_device(struct iwch_dev *dev)
dev->ibdev.req_notify_cq = iwch_arm_cq;
dev->ibdev.post_send = iwch_post_send;
dev->ibdev.post_recv = iwch_post_receive;
- dev->ibdev.get_protocol_stats = iwch_get_mib;
+ dev->ibdev.alloc_hw_stats = iwch_alloc_stats;
+ dev->ibdev.get_hw_stats = iwch_get_mib;
dev->ibdev.uverbs_abi_ver = IWCH_UVERBS_ABI_VERSION;
dev->ibdev.get_port_immutable = iwch_port_immutable;
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 7574f394fdac..dd8a86b726d2 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -446,20 +446,59 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr,
c4iw_dev->rdev.lldi.pdev->device);
}
+enum counters {
+ IP4INSEGS,
+ IP4OUTSEGS,
+ IP4RETRANSSEGS,
+ IP4OUTRSTS,
+ IP6INSEGS,
+ IP6OUTSEGS,
+ IP6RETRANSSEGS,
+ IP6OUTRSTS,
+ NR_COUNTERS
+};
+
+static const char * const names[] = {
+ [IP4INSEGS] = "ip4InSegs",
+ [IP4OUTSEGS] = "ip4OutSegs",
+ [IP4RETRANSSEGS] = "ip4RetransSegs",
+ [IP4OUTRSTS] = "ip4OutRsts",
+ [IP6INSEGS] = "ip6InSegs",
+ [IP6OUTSEGS] = "ip6OutSegs",
+ [IP6RETRANSSEGS] = "ip6RetransSegs",
+ [IP6OUTRSTS] = "ip6OutRsts"
+};
+
+static struct rdma_hw_stats *c4iw_alloc_stats(struct ib_device *ibdev,
+ u8 port_num)
+{
+ BUILD_BUG_ON(ARRAY_SIZE(names) != NR_COUNTERS);
+
+ if (port_num != 0)
+ return NULL;
+
+ return rdma_alloc_hw_stats_struct(names, NR_COUNTERS,
+ RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
static int c4iw_get_mib(struct ib_device *ibdev,
- union rdma_protocol_stats *stats)
+ struct rdma_hw_stats *stats,
+ u8 port, int index)
{
struct tp_tcp_stats v4, v6;
struct c4iw_dev *c4iw_dev = to_c4iw_dev(ibdev);
cxgb4_get_tcp_stats(c4iw_dev->rdev.lldi.pdev, &v4, &v6);
- memset(stats, 0, sizeof *stats);
- stats->iw.tcpInSegs = v4.tcp_in_segs + v6.tcp_in_segs;
- stats->iw.tcpOutSegs = v4.tcp_out_segs + v6.tcp_out_segs;
- stats->iw.tcpRetransSegs = v4.tcp_retrans_segs + v6.tcp_retrans_segs;
- stats->iw.tcpOutRsts = v4.tcp_out_rsts + v6.tcp_out_rsts;
-
- return 0;
+ stats->value[IP4INSEGS] = v4.tcp_in_segs;
+ stats->value[IP4OUTSEGS] = v4.tcp_out_segs;
+ stats->value[IP4RETRANSSEGS] = v4.tcp_retrans_segs;
+ stats->value[IP4OUTRSTS] = v4.tcp_out_rsts;
+ stats->value[IP6INSEGS] = v6.tcp_in_segs;
+ stats->value[IP6OUTSEGS] = v6.tcp_out_segs;
+ stats->value[IP6RETRANSSEGS] = v6.tcp_retrans_segs;
+ stats->value[IP6OUTRSTS] = v6.tcp_out_rsts;
+
+ return stats->num_counters;
}
static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
@@ -562,7 +601,8 @@ int c4iw_register_device(struct c4iw_dev *dev)
dev->ibdev.req_notify_cq = c4iw_arm_cq;
dev->ibdev.post_send = c4iw_post_send;
dev->ibdev.post_recv = c4iw_post_receive;
- dev->ibdev.get_protocol_stats = c4iw_get_mib;
+ dev->ibdev.alloc_hw_stats = c4iw_alloc_stats;
+ dev->ibdev.get_hw_stats = c4iw_get_mib;
dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
dev->ibdev.get_port_immutable = c4iw_port_immutable;
dev->ibdev.drain_sq = c4iw_drain_sq;
diff --git a/drivers/staging/rdma/hfi1/Kconfig b/drivers/infiniband/hw/hfi1/Kconfig
index a925fb0db706..a925fb0db706 100644
--- a/drivers/staging/rdma/hfi1/Kconfig
+++ b/drivers/infiniband/hw/hfi1/Kconfig
diff --git a/drivers/staging/rdma/hfi1/Makefile b/drivers/infiniband/hw/hfi1/Makefile
index 8dc59382ee96..9b5382c94b0c 100644
--- a/drivers/staging/rdma/hfi1/Makefile
+++ b/drivers/infiniband/hw/hfi1/Makefile
@@ -7,7 +7,7 @@
#
obj-$(CONFIG_INFINIBAND_HFI1) += hfi1.o
-hfi1-y := affinity.o chip.o device.o diag.o driver.o efivar.o \
+hfi1-y := affinity.o chip.o device.o driver.o efivar.o \
eprom.o file_ops.o firmware.o \
init.o intr.o mad.o mmu_rb.o pcie.o pio.o pio_copy.o platform.o \
qp.o qsfp.o rc.o ruc.o sdma.o sysfs.o trace.o twsi.o \
diff --git a/drivers/staging/rdma/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 6e7050ab9e16..14d7eeb09be6 100644
--- a/drivers/staging/rdma/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -300,16 +300,15 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
const struct cpumask *node_mask,
*proc_mask = tsk_cpus_allowed(current);
struct cpu_mask_set *set = &dd->affinity->proc;
- char buf[1024];
/*
* check whether process/context affinity has already
* been set
*/
if (cpumask_weight(proc_mask) == 1) {
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask));
- hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %s",
- current->pid, current->comm, buf);
+ hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl",
+ current->pid, current->comm,
+ cpumask_pr_args(proc_mask));
/*
* Mark the pre-set CPU as used. This is atomic so we don't
* need the lock
@@ -318,9 +317,9 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
cpumask_set_cpu(cpu, &set->used);
goto done;
} else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) {
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask));
- hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %s",
- current->pid, current->comm, buf);
+ hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
+ current->pid, current->comm,
+ cpumask_pr_args(proc_mask));
goto done;
}
@@ -356,8 +355,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
cpumask_or(intrs, intrs, (dd->affinity->rcv_intr.gen ?
&dd->affinity->rcv_intr.mask :
&dd->affinity->rcv_intr.used));
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(intrs));
- hfi1_cdbg(PROC, "CPUs used by interrupts: %s", buf);
+ hfi1_cdbg(PROC, "CPUs used by interrupts: %*pbl",
+ cpumask_pr_args(intrs));
/*
* If we don't have a NUMA node requested, preference is towards
@@ -366,18 +365,16 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
if (node == -1)
node = dd->node;
node_mask = cpumask_of_node(node);
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(node_mask));
- hfi1_cdbg(PROC, "device on NUMA %u, CPUs %s", node, buf);
+ hfi1_cdbg(PROC, "device on NUMA %u, CPUs %*pbl", node,
+ cpumask_pr_args(node_mask));
/* diff will hold all unused cpus */
cpumask_andnot(diff, &set->mask, &set->used);
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(diff));
- hfi1_cdbg(PROC, "unused CPUs (all) %s", buf);
+ hfi1_cdbg(PROC, "unused CPUs (all) %*pbl", cpumask_pr_args(diff));
/* get cpumask of available CPUs on preferred NUMA */
cpumask_and(mask, diff, node_mask);
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask));
- hfi1_cdbg(PROC, "available cpus on NUMA %s", buf);
+ hfi1_cdbg(PROC, "available cpus on NUMA %*pbl", cpumask_pr_args(mask));
/*
* At first, we don't want to place processes on the same
@@ -395,8 +392,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
cpumask_andnot(diff, &set->mask, &set->used);
cpumask_andnot(mask, diff, node_mask);
}
- scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask));
- hfi1_cdbg(PROC, "possible CPUs for process %s", buf);
+ hfi1_cdbg(PROC, "possible CPUs for process %*pbl",
+ cpumask_pr_args(mask));
cpu = cpumask_first(mask);
if (cpu >= nr_cpu_ids) /* empty */
diff --git a/drivers/staging/rdma/hfi1/affinity.h b/drivers/infiniband/hw/hfi1/affinity.h
index 20f52fe74091..20f52fe74091 100644
--- a/drivers/staging/rdma/hfi1/affinity.h
+++ b/drivers/infiniband/hw/hfi1/affinity.h
diff --git a/drivers/staging/rdma/hfi1/aspm.h b/drivers/infiniband/hw/hfi1/aspm.h
index 0d58fe3b49b5..0d58fe3b49b5 100644
--- a/drivers/staging/rdma/hfi1/aspm.h
+++ b/drivers/infiniband/hw/hfi1/aspm.h
diff --git a/drivers/staging/rdma/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index dcae8e723f98..f5de85178055 100644
--- a/drivers/staging/rdma/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1037,6 +1037,7 @@ static void dc_shutdown(struct hfi1_devdata *);
static void dc_start(struct hfi1_devdata *);
static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
unsigned int *np);
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
/*
* Error interrupt table entry. This is used as input to the interrupt
@@ -6105,7 +6106,7 @@ int acquire_lcb_access(struct hfi1_devdata *dd, int sleep_ok)
}
/* this access is valid only when the link is up */
- if ((ppd->host_link_state & HLS_UP) == 0) {
+ if (ppd->host_link_state & HLS_DOWN) {
dd_dev_info(dd, "%s: link state %s not up\n",
__func__, link_state_name(ppd->host_link_state));
ret = -EBUSY;
@@ -7067,6 +7068,16 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd)
__func__, ppd->pkeys[2], FULL_MGMT_P_KEY);
ppd->pkeys[2] = FULL_MGMT_P_KEY;
(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+ hfi1_event_pkey_change(ppd->dd, ppd->port);
+}
+
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd)
+{
+ if (ppd->pkeys[2] != 0) {
+ ppd->pkeys[2] = 0;
+ (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+ hfi1_event_pkey_change(ppd->dd, ppd->port);
+ }
}
/*
@@ -7429,7 +7440,7 @@ void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
retry:
mutex_lock(&ppd->hls_lock);
/* only apply if the link is up */
- if (!(ppd->host_link_state & HLS_UP)) {
+ if (ppd->host_link_state & HLS_DOWN) {
/* still going up..wait and retry */
if (ppd->host_link_state & HLS_GOING_UP) {
if (++tries < 1000) {
@@ -7823,8 +7834,8 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg)
* save first 2 flits in the packet that caused
* the error
*/
- dd->err_info_rcvport.packet_flit1 = hdr0;
- dd->err_info_rcvport.packet_flit2 = hdr1;
+ dd->err_info_rcvport.packet_flit1 = hdr0;
+ dd->err_info_rcvport.packet_flit2 = hdr1;
}
switch (info) {
case 1:
@@ -9159,6 +9170,13 @@ int start_link(struct hfi1_pportdata *ppd)
return 0;
}
+ /*
+ * FULL_MGMT_P_KEY is cleared from the pkey table, so that the
+ * pkey table can be configured properly if the HFI unit is connected
+ * to switch port with MgmtAllowed=NO
+ */
+ clear_full_mgmt_pkey(ppd);
+
return set_link_state(ppd, HLS_DN_POLL);
}
@@ -9212,9 +9230,6 @@ void reset_qsfp(struct hfi1_pportdata *ppd)
/* Reset the QSFP */
mask = (u64)QSFP_HFI0_RESET_N;
- qsfp_mask = read_csr(dd, dd->hfi1_id ? ASIC_QSFP2_OE : ASIC_QSFP1_OE);
- qsfp_mask |= mask;
- write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_OE : ASIC_QSFP1_OE, qsfp_mask);
qsfp_mask = read_csr(dd,
dd->hfi1_id ? ASIC_QSFP2_OUT : ASIC_QSFP1_OUT);
@@ -9252,6 +9267,12 @@ static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
dd_dev_info(dd, "%s: QSFP cable temperature too low\n",
__func__);
+ /*
+ * The remaining alarms/warnings don't matter if the link is down.
+ */
+ if (ppd->host_link_state & HLS_DOWN)
+ return 0;
+
if ((qsfp_interrupt_status[1] & QSFP_HIGH_VCC_ALARM) ||
(qsfp_interrupt_status[1] & QSFP_HIGH_VCC_WARNING))
dd_dev_info(dd, "%s: QSFP supply voltage too high\n",
@@ -9346,9 +9367,8 @@ void qsfp_event(struct work_struct *work)
return;
/*
- * Turn DC back on after cables has been
- * re-inserted. Up until now, the DC has been in
- * reset to save power.
+ * Turn DC back on after cable has been re-inserted. Up until
+ * now, the DC has been in reset to save power.
*/
dc_start(dd);
@@ -9480,7 +9500,15 @@ int bringup_serdes(struct hfi1_pportdata *ppd)
return ret;
}
- /* tune the SERDES to a ballpark setting for
+ get_port_type(ppd);
+ if (ppd->port_type == PORT_TYPE_QSFP) {
+ set_qsfp_int_n(ppd, 0);
+ wait_for_qsfp_init(ppd);
+ set_qsfp_int_n(ppd, 1);
+ }
+
+ /*
+ * Tune the SerDes to a ballpark setting for
* optimal signal and bit error rate
* Needs to be done before starting the link
*/
@@ -9758,7 +9786,7 @@ static void set_send_length(struct hfi1_pportdata *ppd)
u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2)
& SEND_LEN_CHECK1_LEN_VL15_MASK) <<
SEND_LEN_CHECK1_LEN_VL15_SHIFT;
- int i;
+ int i, j;
u32 thres;
for (i = 0; i < ppd->vls_supported; i++) {
@@ -9782,7 +9810,10 @@ static void set_send_length(struct hfi1_pportdata *ppd)
sc_mtu_to_threshold(dd->vld[i].sc,
dd->vld[i].mtu,
dd->rcd[0]->rcvhdrqentsize));
- sc_set_cr_threshold(dd->vld[i].sc, thres);
+ for (j = 0; j < INIT_SC_PER_VL; j++)
+ sc_set_cr_threshold(
+ pio_select_send_context_vl(dd, j, i),
+ thres);
}
thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50),
sc_mtu_to_threshold(dd->vld[15].sc,
@@ -10074,7 +10105,7 @@ u32 driver_physical_state(struct hfi1_pportdata *ppd)
*/
u32 driver_logical_state(struct hfi1_pportdata *ppd)
{
- if (ppd->host_link_state && !(ppd->host_link_state & HLS_UP))
+ if (ppd->host_link_state && (ppd->host_link_state & HLS_DOWN))
return IB_PORT_DOWN;
switch (ppd->host_link_state & HLS_UP) {
@@ -11887,7 +11918,7 @@ static void update_synth_timer(unsigned long opaque)
hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit);
}
-mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
+ mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
}
#define C_MAX_NAME 13 /* 12 chars + one for /0 */
@@ -14578,7 +14609,7 @@ u64 create_pbc(struct hfi1_pportdata *ppd, u64 flags, int srate_mbs, u32 vl,
(reason), (ret))
/*
- * Initialize the Avago Thermal sensor.
+ * Initialize the thermal sensor.
*
* After initialization, enable polling of thermal sensor through
* SBus interface. In order for this to work, the SBus Master
diff --git a/drivers/staging/rdma/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 1948706fff1a..66a327978739 100644
--- a/drivers/staging/rdma/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -398,6 +398,12 @@
/* Lane ID for general configuration registers */
#define GENERAL_CONFIG 4
+/* LINK_TUNING_PARAMETERS fields */
+#define TUNING_METHOD_SHIFT 24
+
+/* LINK_OPTIMIZATION_SETTINGS fields */
+#define ENABLE_EXT_DEV_CONFIG_SHIFT 24
+
/* LOAD_DATA 8051 command shifts and fields */
#define LOAD_DATA_FIELD_ID_SHIFT 40
#define LOAD_DATA_FIELD_ID_MASK 0xfull
diff --git a/drivers/staging/rdma/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index 8744de6667c2..8744de6667c2 100644
--- a/drivers/staging/rdma/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
diff --git a/drivers/staging/rdma/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index e9b6bb322025..fcc9c217a97a 100644
--- a/drivers/staging/rdma/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -178,7 +178,8 @@
HFI1_CAP_PKEY_CHECK | \
HFI1_CAP_NO_INTEGRITY)
-#define HFI1_USER_SWVERSION ((HFI1_USER_SWMAJOR << 16) | HFI1_USER_SWMINOR)
+#define HFI1_USER_SWVERSION ((HFI1_USER_SWMAJOR << HFI1_SWMAJOR_SHIFT) | \
+ HFI1_USER_SWMINOR)
#ifndef HFI1_KERN_TYPE
#define HFI1_KERN_TYPE 0
@@ -349,6 +350,8 @@ struct hfi1_message_header {
#define HFI1_BECN_MASK 1
#define HFI1_BECN_SMASK BIT(HFI1_BECN_SHIFT)
+#define HFI1_PSM_IOC_BASE_SEQ 0x0
+
static inline __u64 rhf_to_cpu(const __le32 *rbuf)
{
return __le64_to_cpu(*((__le64 *)rbuf));
diff --git a/drivers/staging/rdma/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index dbab9d9cc288..dbab9d9cc288 100644
--- a/drivers/staging/rdma/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
diff --git a/drivers/staging/rdma/hfi1/debugfs.h b/drivers/infiniband/hw/hfi1/debugfs.h
index b6fb6814f1b8..b6fb6814f1b8 100644
--- a/drivers/staging/rdma/hfi1/debugfs.h
+++ b/drivers/infiniband/hw/hfi1/debugfs.h
diff --git a/drivers/staging/rdma/hfi1/device.c b/drivers/infiniband/hw/hfi1/device.c
index c05c39da83b1..bf64b5a7bfd7 100644
--- a/drivers/staging/rdma/hfi1/device.c
+++ b/drivers/infiniband/hw/hfi1/device.c
@@ -60,7 +60,8 @@ static dev_t hfi1_dev;
int hfi1_cdev_init(int minor, const char *name,
const struct file_operations *fops,
struct cdev *cdev, struct device **devp,
- bool user_accessible)
+ bool user_accessible,
+ struct kobject *parent)
{
const dev_t dev = MKDEV(MAJOR(hfi1_dev), minor);
struct device *device = NULL;
@@ -68,6 +69,7 @@ int hfi1_cdev_init(int minor, const char *name,
cdev_init(cdev, fops);
cdev->owner = THIS_MODULE;
+ cdev->kobj.parent = parent;
kobject_set_name(&cdev->kobj, name);
ret = cdev_add(cdev, dev, 1);
@@ -82,13 +84,13 @@ int hfi1_cdev_init(int minor, const char *name,
else
device = device_create(class, NULL, dev, NULL, "%s", name);
- if (!IS_ERR(device))
- goto done;
- ret = PTR_ERR(device);
- device = NULL;
- pr_err("Could not create device for minor %d, %s (err %d)\n",
- minor, name, -ret);
- cdev_del(cdev);
+ if (IS_ERR(device)) {
+ ret = PTR_ERR(device);
+ device = NULL;
+ pr_err("Could not create device for minor %d, %s (err %d)\n",
+ minor, name, -ret);
+ cdev_del(cdev);
+ }
done:
*devp = device;
return ret;
diff --git a/drivers/staging/rdma/hfi1/device.h b/drivers/infiniband/hw/hfi1/device.h
index 5bb3e83cf2da..c3ec19cb0ac9 100644
--- a/drivers/staging/rdma/hfi1/device.h
+++ b/drivers/infiniband/hw/hfi1/device.h
@@ -50,7 +50,8 @@
int hfi1_cdev_init(int minor, const char *name,
const struct file_operations *fops,
struct cdev *cdev, struct device **devp,
- bool user_accessible);
+ bool user_accessible,
+ struct kobject *parent);
void hfi1_cdev_cleanup(struct cdev *cdev, struct device **devp);
const char *class_name(void);
int __init dev_init(void);
diff --git a/drivers/staging/rdma/hfi1/dma.c b/drivers/infiniband/hw/hfi1/dma.c
index 7e8dab892848..7e8dab892848 100644
--- a/drivers/staging/rdma/hfi1/dma.c
+++ b/drivers/infiniband/hw/hfi1/dma.c
diff --git a/drivers/staging/rdma/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 700c6fa3a633..c75b0ae688f8 100644
--- a/drivers/staging/rdma/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -1161,7 +1161,7 @@ int hfi1_set_lid(struct hfi1_pportdata *ppd, u32 lid, u8 lmc)
ppd->lmc = lmc;
hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_LIDLMC, 0);
- dd_dev_info(dd, "IB%u:%u got a lid: 0x%x\n", dd->unit, ppd->port, lid);
+ dd_dev_info(dd, "port %u: got a lid: 0x%x\n", ppd->port, lid);
return 0;
}
diff --git a/drivers/staging/rdma/hfi1/efivar.c b/drivers/infiniband/hw/hfi1/efivar.c
index 106349fc1fb9..106349fc1fb9 100644
--- a/drivers/staging/rdma/hfi1/efivar.c
+++ b/drivers/infiniband/hw/hfi1/efivar.c
diff --git a/drivers/staging/rdma/hfi1/efivar.h b/drivers/infiniband/hw/hfi1/efivar.h
index 94e9e70de568..94e9e70de568 100644
--- a/drivers/staging/rdma/hfi1/efivar.h
+++ b/drivers/infiniband/hw/hfi1/efivar.h
diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c
new file mode 100644
index 000000000000..36b77943cbfd
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/eprom.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright(c) 2015, 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * - Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * - Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+#include <linux/delay.h>
+#include "hfi.h"
+#include "common.h"
+#include "eprom.h"
+
+#define CMD_SHIFT 24
+#define CMD_RELEASE_POWERDOWN_NOID ((0xab << CMD_SHIFT))
+
+/* controller interface speeds */
+#define EP_SPEED_FULL 0x2 /* full speed */
+
+/*
+ * How long to wait for the EPROM to become available, in ms.
+ * The spec 32 Mb EPROM takes around 40s to erase then write.
+ * Double it for safety.
+ */
+#define EPROM_TIMEOUT 80000 /* ms */
+/*
+ * Initialize the EPROM handler.
+ */
+int eprom_init(struct hfi1_devdata *dd)
+{
+ int ret = 0;
+
+ /* only the discrete chip has an EPROM */
+ if (dd->pcidev->device != PCI_DEVICE_ID_INTEL0)
+ return 0;
+
+ /*
+ * It is OK if both HFIs reset the EPROM as long as they don't
+ * do it at the same time.
+ */
+ ret = acquire_chip_resource(dd, CR_EPROM, EPROM_TIMEOUT);
+ if (ret) {
+ dd_dev_err(dd,
+ "%s: unable to acquire EPROM resource, no EPROM support\n",
+ __func__);
+ goto done_asic;
+ }
+
+ /* reset EPROM to be sure it is in a good state */
+
+ /* set reset */
+ write_csr(dd, ASIC_EEP_CTL_STAT, ASIC_EEP_CTL_STAT_EP_RESET_SMASK);
+ /* clear reset, set speed */
+ write_csr(dd, ASIC_EEP_CTL_STAT,
+ EP_SPEED_FULL << ASIC_EEP_CTL_STAT_RATE_SPI_SHIFT);
+
+ /* wake the device with command "release powerdown NoID" */
+ write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_RELEASE_POWERDOWN_NOID);
+
+ dd->eprom_available = true;
+ release_chip_resource(dd, CR_EPROM);
+done_asic:
+ return ret;
+}
diff --git a/drivers/staging/rdma/hfi1/eprom.h b/drivers/infiniband/hw/hfi1/eprom.h
index d41f0b1afb15..d41f0b1afb15 100644
--- a/drivers/staging/rdma/hfi1/eprom.h
+++ b/drivers/infiniband/hw/hfi1/eprom.h
diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index c1c5bf82addb..c702a009608f 100644
--- a/drivers/staging/rdma/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -72,8 +72,6 @@
*/
static int hfi1_file_open(struct inode *, struct file *);
static int hfi1_file_close(struct inode *, struct file *);
-static ssize_t hfi1_file_write(struct file *, const char __user *,
- size_t, loff_t *);
static ssize_t hfi1_write_iter(struct kiocb *, struct iov_iter *);
static unsigned int hfi1_poll(struct file *, struct poll_table_struct *);
static int hfi1_file_mmap(struct file *, struct vm_area_struct *);
@@ -86,8 +84,7 @@ static int get_ctxt_info(struct file *, void __user *, __u32);
static int get_base_info(struct file *, void __user *, __u32);
static int setup_ctxt(struct file *);
static int setup_subctxt(struct hfi1_ctxtdata *);
-static int get_user_context(struct file *, struct hfi1_user_info *,
- int, unsigned);
+static int get_user_context(struct file *, struct hfi1_user_info *, int);
static int find_shared_ctxt(struct file *, const struct hfi1_user_info *);
static int allocate_ctxt(struct file *, struct hfi1_devdata *,
struct hfi1_user_info *);
@@ -97,13 +94,15 @@ static int user_event_ack(struct hfi1_ctxtdata *, int, unsigned long);
static int set_ctxt_pkey(struct hfi1_ctxtdata *, unsigned, u16);
static int manage_rcvq(struct hfi1_ctxtdata *, unsigned, int);
static int vma_fault(struct vm_area_struct *, struct vm_fault *);
+static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
+ unsigned long arg);
static const struct file_operations hfi1_file_ops = {
.owner = THIS_MODULE,
- .write = hfi1_file_write,
.write_iter = hfi1_write_iter,
.open = hfi1_file_open,
.release = hfi1_file_close,
+ .unlocked_ioctl = hfi1_file_ioctl,
.poll = hfi1_poll,
.mmap = hfi1_file_mmap,
.llseek = noop_llseek,
@@ -169,6 +168,13 @@ static inline int is_valid_mmap(u64 token)
static int hfi1_file_open(struct inode *inode, struct file *fp)
{
+ struct hfi1_devdata *dd = container_of(inode->i_cdev,
+ struct hfi1_devdata,
+ user_cdev);
+
+ /* Just take a ref now. Not all opens result in a context assign */
+ kobject_get(&dd->kobj);
+
/* The real work is performed later in assign_ctxt() */
fp->private_data = kzalloc(sizeof(struct hfi1_filedata), GFP_KERNEL);
if (fp->private_data) /* no cpu affinity by default */
@@ -176,127 +182,62 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
return fp->private_data ? 0 : -ENOMEM;
}
-static ssize_t hfi1_file_write(struct file *fp, const char __user *data,
- size_t count, loff_t *offset)
+static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
+ unsigned long arg)
{
- const struct hfi1_cmd __user *ucmd;
struct hfi1_filedata *fd = fp->private_data;
struct hfi1_ctxtdata *uctxt = fd->uctxt;
- struct hfi1_cmd cmd;
struct hfi1_user_info uinfo;
struct hfi1_tid_info tinfo;
+ int ret = 0;
unsigned long addr;
- ssize_t consumed = 0, copy = 0, ret = 0;
- void *dest = NULL;
- __u64 user_val = 0;
- int uctxt_required = 1;
- int must_be_root = 0;
-
- /* FIXME: This interface cannot continue out of staging */
- if (WARN_ON_ONCE(!ib_safe_file_access(fp)))
- return -EACCES;
-
- if (count < sizeof(cmd)) {
- ret = -EINVAL;
- goto bail;
- }
-
- ucmd = (const struct hfi1_cmd __user *)data;
- if (copy_from_user(&cmd, ucmd, sizeof(cmd))) {
- ret = -EFAULT;
- goto bail;
- }
-
- consumed = sizeof(cmd);
-
- switch (cmd.type) {
- case HFI1_CMD_ASSIGN_CTXT:
- uctxt_required = 0; /* assigned user context not required */
- copy = sizeof(uinfo);
- dest = &uinfo;
- break;
- case HFI1_CMD_SDMA_STATUS_UPD:
- case HFI1_CMD_CREDIT_UPD:
- copy = 0;
- break;
- case HFI1_CMD_TID_UPDATE:
- case HFI1_CMD_TID_FREE:
- case HFI1_CMD_TID_INVAL_READ:
- copy = sizeof(tinfo);
- dest = &tinfo;
- break;
- case HFI1_CMD_USER_INFO:
- case HFI1_CMD_RECV_CTRL:
- case HFI1_CMD_POLL_TYPE:
- case HFI1_CMD_ACK_EVENT:
- case HFI1_CMD_CTXT_INFO:
- case HFI1_CMD_SET_PKEY:
- case HFI1_CMD_CTXT_RESET:
- copy = 0;
- user_val = cmd.addr;
- break;
- case HFI1_CMD_EP_INFO:
- case HFI1_CMD_EP_ERASE_CHIP:
- case HFI1_CMD_EP_ERASE_RANGE:
- case HFI1_CMD_EP_READ_RANGE:
- case HFI1_CMD_EP_WRITE_RANGE:
- uctxt_required = 0; /* assigned user context not required */
- must_be_root = 1; /* validate user */
- copy = 0;
- break;
- default:
- ret = -EINVAL;
- goto bail;
- }
+ int uval = 0;
+ unsigned long ul_uval = 0;
+ u16 uval16 = 0;
+
+ hfi1_cdbg(IOCTL, "IOCTL recv: 0x%x", cmd);
+ if (cmd != HFI1_IOCTL_ASSIGN_CTXT &&
+ cmd != HFI1_IOCTL_GET_VERS &&
+ !uctxt)
+ return -EINVAL;
- /* If the command comes with user data, copy it. */
- if (copy) {
- if (copy_from_user(dest, (void __user *)cmd.addr, copy)) {
- ret = -EFAULT;
- goto bail;
- }
- consumed += copy;
- }
+ switch (cmd) {
+ case HFI1_IOCTL_ASSIGN_CTXT:
+ if (uctxt)
+ return -EINVAL;
- /*
- * Make sure there is a uctxt when needed.
- */
- if (uctxt_required && !uctxt) {
- ret = -EINVAL;
- goto bail;
- }
-
- /* only root can do these operations */
- if (must_be_root && !capable(CAP_SYS_ADMIN)) {
- ret = -EPERM;
- goto bail;
- }
+ if (copy_from_user(&uinfo,
+ (struct hfi1_user_info __user *)arg,
+ sizeof(uinfo)))
+ return -EFAULT;
- switch (cmd.type) {
- case HFI1_CMD_ASSIGN_CTXT:
ret = assign_ctxt(fp, &uinfo);
if (ret < 0)
- goto bail;
- ret = setup_ctxt(fp);
+ return ret;
+ setup_ctxt(fp);
if (ret)
- goto bail;
+ return ret;
ret = user_init(fp);
break;
- case HFI1_CMD_CTXT_INFO:
- ret = get_ctxt_info(fp, (void __user *)(unsigned long)
- user_val, cmd.len);
+ case HFI1_IOCTL_CTXT_INFO:
+ ret = get_ctxt_info(fp, (void __user *)(unsigned long)arg,
+ sizeof(struct hfi1_ctxt_info));
break;
- case HFI1_CMD_USER_INFO:
- ret = get_base_info(fp, (void __user *)(unsigned long)
- user_val, cmd.len);
+ case HFI1_IOCTL_USER_INFO:
+ ret = get_base_info(fp, (void __user *)(unsigned long)arg,
+ sizeof(struct hfi1_base_info));
break;
- case HFI1_CMD_SDMA_STATUS_UPD:
- break;
- case HFI1_CMD_CREDIT_UPD:
+ case HFI1_IOCTL_CREDIT_UPD:
if (uctxt && uctxt->sc)
sc_return_credits(uctxt->sc);
break;
- case HFI1_CMD_TID_UPDATE:
+
+ case HFI1_IOCTL_TID_UPDATE:
+ if (copy_from_user(&tinfo,
+ (struct hfi11_tid_info __user *)arg,
+ sizeof(tinfo)))
+ return -EFAULT;
+
ret = hfi1_user_exp_rcv_setup(fp, &tinfo);
if (!ret) {
/*
@@ -305,57 +246,82 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data,
* These fields are adjacent in the structure so
* we can copy them at the same time.
*/
- addr = (unsigned long)cmd.addr +
- offsetof(struct hfi1_tid_info, tidcnt);
+ addr = arg + offsetof(struct hfi1_tid_info, tidcnt);
if (copy_to_user((void __user *)addr, &tinfo.tidcnt,
sizeof(tinfo.tidcnt) +
sizeof(tinfo.length)))
ret = -EFAULT;
}
break;
- case HFI1_CMD_TID_INVAL_READ:
- ret = hfi1_user_exp_rcv_invalid(fp, &tinfo);
+
+ case HFI1_IOCTL_TID_FREE:
+ if (copy_from_user(&tinfo,
+ (struct hfi11_tid_info __user *)arg,
+ sizeof(tinfo)))
+ return -EFAULT;
+
+ ret = hfi1_user_exp_rcv_clear(fp, &tinfo);
if (ret)
break;
- addr = (unsigned long)cmd.addr +
- offsetof(struct hfi1_tid_info, tidcnt);
+ addr = arg + offsetof(struct hfi1_tid_info, tidcnt);
if (copy_to_user((void __user *)addr, &tinfo.tidcnt,
sizeof(tinfo.tidcnt)))
ret = -EFAULT;
break;
- case HFI1_CMD_TID_FREE:
- ret = hfi1_user_exp_rcv_clear(fp, &tinfo);
+
+ case HFI1_IOCTL_TID_INVAL_READ:
+ if (copy_from_user(&tinfo,
+ (struct hfi11_tid_info __user *)arg,
+ sizeof(tinfo)))
+ return -EFAULT;
+
+ ret = hfi1_user_exp_rcv_invalid(fp, &tinfo);
if (ret)
break;
- addr = (unsigned long)cmd.addr +
- offsetof(struct hfi1_tid_info, tidcnt);
+ addr = arg + offsetof(struct hfi1_tid_info, tidcnt);
if (copy_to_user((void __user *)addr, &tinfo.tidcnt,
sizeof(tinfo.tidcnt)))
ret = -EFAULT;
break;
- case HFI1_CMD_RECV_CTRL:
- ret = manage_rcvq(uctxt, fd->subctxt, (int)user_val);
+
+ case HFI1_IOCTL_RECV_CTRL:
+ ret = get_user(uval, (int __user *)arg);
+ if (ret != 0)
+ return -EFAULT;
+ ret = manage_rcvq(uctxt, fd->subctxt, uval);
break;
- case HFI1_CMD_POLL_TYPE:
- uctxt->poll_type = (typeof(uctxt->poll_type))user_val;
+
+ case HFI1_IOCTL_POLL_TYPE:
+ ret = get_user(uval, (int __user *)arg);
+ if (ret != 0)
+ return -EFAULT;
+ uctxt->poll_type = (typeof(uctxt->poll_type))uval;
break;
- case HFI1_CMD_ACK_EVENT:
- ret = user_event_ack(uctxt, fd->subctxt, user_val);
+
+ case HFI1_IOCTL_ACK_EVENT:
+ ret = get_user(ul_uval, (unsigned long __user *)arg);
+ if (ret != 0)
+ return -EFAULT;
+ ret = user_event_ack(uctxt, fd->subctxt, ul_uval);
break;
- case HFI1_CMD_SET_PKEY:
+
+ case HFI1_IOCTL_SET_PKEY:
+ ret = get_user(uval16, (u16 __user *)arg);
+ if (ret != 0)
+ return -EFAULT;
if (HFI1_CAP_IS_USET(PKEY_CHECK))
- ret = set_ctxt_pkey(uctxt, fd->subctxt, user_val);
+ ret = set_ctxt_pkey(uctxt, fd->subctxt, uval16);
else
- ret = -EPERM;
+ return -EPERM;
break;
- case HFI1_CMD_CTXT_RESET: {
+
+ case HFI1_IOCTL_CTXT_RESET: {
struct send_context *sc;
struct hfi1_devdata *dd;
- if (!uctxt || !uctxt->dd || !uctxt->sc) {
- ret = -EINVAL;
- break;
- }
+ if (!uctxt || !uctxt->dd || !uctxt->sc)
+ return -EINVAL;
+
/*
* There is no protection here. User level has to
* guarantee that no one will be writing to the send
@@ -373,10 +339,9 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data,
wait_event_interruptible_timeout(
sc->halt_wait, (sc->flags & SCF_HALTED),
msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT));
- if (!(sc->flags & SCF_HALTED)) {
- ret = -ENOLCK;
- break;
- }
+ if (!(sc->flags & SCF_HALTED))
+ return -ENOLCK;
+
/*
* If the send context was halted due to a Freeze,
* wait until the device has been "unfrozen" before
@@ -387,18 +352,16 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data,
dd->event_queue,
!(ACCESS_ONCE(dd->flags) & HFI1_FROZEN),
msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT));
- if (dd->flags & HFI1_FROZEN) {
- ret = -ENOLCK;
- break;
- }
- if (dd->flags & HFI1_FORCED_FREEZE) {
+ if (dd->flags & HFI1_FROZEN)
+ return -ENOLCK;
+
+ if (dd->flags & HFI1_FORCED_FREEZE)
/*
* Don't allow context reset if we are into
* forced freeze
*/
- ret = -ENODEV;
- break;
- }
+ return -ENODEV;
+
sc_disable(sc);
ret = sc_enable(sc);
hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB,
@@ -410,18 +373,17 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data,
sc_return_credits(sc);
break;
}
- case HFI1_CMD_EP_INFO:
- case HFI1_CMD_EP_ERASE_CHIP:
- case HFI1_CMD_EP_ERASE_RANGE:
- case HFI1_CMD_EP_READ_RANGE:
- case HFI1_CMD_EP_WRITE_RANGE:
- ret = handle_eprom_command(fp, &cmd);
+
+ case HFI1_IOCTL_GET_VERS:
+ uval = HFI1_USER_SWVERSION;
+ if (put_user(uval, (int __user *)arg))
+ return -EFAULT;
break;
+
+ default:
+ return -EINVAL;
}
- if (ret >= 0)
- ret = consumed;
-bail:
return ret;
}
@@ -738,7 +700,9 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
{
struct hfi1_filedata *fdata = fp->private_data;
struct hfi1_ctxtdata *uctxt = fdata->uctxt;
- struct hfi1_devdata *dd;
+ struct hfi1_devdata *dd = container_of(inode->i_cdev,
+ struct hfi1_devdata,
+ user_cdev);
unsigned long flags, *ev;
fp->private_data = NULL;
@@ -747,7 +711,6 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
goto done;
hfi1_cdbg(PROC, "freeing ctxt %u:%u", uctxt->ctxt, fdata->subctxt);
- dd = uctxt->dd;
mutex_lock(&hfi1_mutex);
flush_wc();
@@ -813,6 +776,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
mutex_unlock(&hfi1_mutex);
hfi1_free_ctxtdata(dd, uctxt);
done:
+ kobject_put(&dd->kobj);
kfree(fdata);
return 0;
}
@@ -836,7 +800,7 @@ static u64 kvirt_to_phys(void *addr)
static int assign_ctxt(struct file *fp, struct hfi1_user_info *uinfo)
{
int i_minor, ret = 0;
- unsigned swmajor, swminor, alg = HFI1_ALG_ACROSS;
+ unsigned int swmajor, swminor;
swmajor = uinfo->userversion >> 16;
if (swmajor != HFI1_USER_SWMAJOR) {
@@ -846,9 +810,6 @@ static int assign_ctxt(struct file *fp, struct hfi1_user_info *uinfo)
swminor = uinfo->userversion & 0xffff;
- if (uinfo->hfi1_alg < HFI1_ALG_COUNT)
- alg = uinfo->hfi1_alg;
-
mutex_lock(&hfi1_mutex);
/* First, lets check if we need to setup a shared context? */
if (uinfo->subctxt_cnt) {
@@ -868,7 +829,7 @@ static int assign_ctxt(struct file *fp, struct hfi1_user_info *uinfo)
*/
if (!ret) {
i_minor = iminor(file_inode(fp)) - HFI1_USER_MINOR_BASE;
- ret = get_user_context(fp, uinfo, i_minor - 1, alg);
+ ret = get_user_context(fp, uinfo, i_minor);
}
done_unlock:
mutex_unlock(&hfi1_mutex);
@@ -876,71 +837,26 @@ done:
return ret;
}
-/* return true if the device available for general use */
-static int usable_device(struct hfi1_devdata *dd)
-{
- struct hfi1_pportdata *ppd = dd->pport;
-
- return driver_lstate(ppd) == IB_PORT_ACTIVE;
-}
-
static int get_user_context(struct file *fp, struct hfi1_user_info *uinfo,
- int devno, unsigned alg)
+ int devno)
{
struct hfi1_devdata *dd = NULL;
- int ret = 0, devmax, npresent, nup, dev;
+ int devmax, npresent, nup;
devmax = hfi1_count_units(&npresent, &nup);
- if (!npresent) {
- ret = -ENXIO;
- goto done;
- }
- if (!nup) {
- ret = -ENETDOWN;
- goto done;
- }
- if (devno >= 0) {
- dd = hfi1_lookup(devno);
- if (!dd)
- ret = -ENODEV;
- else if (!dd->freectxts)
- ret = -EBUSY;
- } else {
- struct hfi1_devdata *pdd;
-
- if (alg == HFI1_ALG_ACROSS) {
- unsigned free = 0U;
-
- for (dev = 0; dev < devmax; dev++) {
- pdd = hfi1_lookup(dev);
- if (!pdd)
- continue;
- if (!usable_device(pdd))
- continue;
- if (pdd->freectxts &&
- pdd->freectxts > free) {
- dd = pdd;
- free = pdd->freectxts;
- }
- }
- } else {
- for (dev = 0; dev < devmax; dev++) {
- pdd = hfi1_lookup(dev);
- if (!pdd)
- continue;
- if (!usable_device(pdd))
- continue;
- if (pdd->freectxts) {
- dd = pdd;
- break;
- }
- }
- }
- if (!dd)
- ret = -EBUSY;
- }
-done:
- return ret ? ret : allocate_ctxt(fp, dd, uinfo);
+ if (!npresent)
+ return -ENXIO;
+
+ if (!nup)
+ return -ENETDOWN;
+
+ dd = hfi1_lookup(devno);
+ if (!dd)
+ return -ENODEV;
+ else if (!dd->freectxts)
+ return -EBUSY;
+
+ return allocate_ctxt(fp, dd, uinfo);
}
static int find_shared_ctxt(struct file *fp,
@@ -1546,170 +1462,10 @@ done:
return ret;
}
-static int ui_open(struct inode *inode, struct file *filp)
-{
- struct hfi1_devdata *dd;
-
- dd = container_of(inode->i_cdev, struct hfi1_devdata, ui_cdev);
- filp->private_data = dd; /* for other methods */
- return 0;
-}
-
-static int ui_release(struct inode *inode, struct file *filp)
-{
- /* nothing to do */
- return 0;
-}
-
-static loff_t ui_lseek(struct file *filp, loff_t offset, int whence)
-{
- struct hfi1_devdata *dd = filp->private_data;
-
- return fixed_size_llseek(filp, offset, whence,
- (dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE);
-}
-
-/* NOTE: assumes unsigned long is 8 bytes */
-static ssize_t ui_read(struct file *filp, char __user *buf, size_t count,
- loff_t *f_pos)
-{
- struct hfi1_devdata *dd = filp->private_data;
- void __iomem *base = dd->kregbase;
- unsigned long total, csr_off,
- barlen = (dd->kregend - dd->kregbase);
- u64 data;
-
- /* only read 8 byte quantities */
- if ((count % 8) != 0)
- return -EINVAL;
- /* offset must be 8-byte aligned */
- if ((*f_pos % 8) != 0)
- return -EINVAL;
- /* destination buffer must be 8-byte aligned */
- if ((unsigned long)buf % 8 != 0)
- return -EINVAL;
- /* must be in range */
- if (*f_pos + count > (barlen + DC8051_DATA_MEM_SIZE))
- return -EINVAL;
- /* only set the base if we are not starting past the BAR */
- if (*f_pos < barlen)
- base += *f_pos;
- csr_off = *f_pos;
- for (total = 0; total < count; total += 8, csr_off += 8) {
- /* accessing LCB CSRs requires more checks */
- if (is_lcb_offset(csr_off)) {
- if (read_lcb_csr(dd, csr_off, (u64 *)&data))
- break; /* failed */
- }
- /*
- * Cannot read ASIC GPIO/QSFP* clear and force CSRs without a
- * false parity error. Avoid the whole issue by not reading
- * them. These registers are defined as having a read value
- * of 0.
- */
- else if (csr_off == ASIC_GPIO_CLEAR ||
- csr_off == ASIC_GPIO_FORCE ||
- csr_off == ASIC_QSFP1_CLEAR ||
- csr_off == ASIC_QSFP1_FORCE ||
- csr_off == ASIC_QSFP2_CLEAR ||
- csr_off == ASIC_QSFP2_FORCE)
- data = 0;
- else if (csr_off >= barlen) {
- /*
- * read_8051_data can read more than just 8 bytes at
- * a time. However, folding this into the loop and
- * handling the reads in 8 byte increments allows us
- * to smoothly transition from chip memory to 8051
- * memory.
- */
- if (read_8051_data(dd,
- (u32)(csr_off - barlen),
- sizeof(data), &data))
- break; /* failed */
- } else
- data = readq(base + total);
- if (put_user(data, (unsigned long __user *)(buf + total)))
- break;
- }
- *f_pos += total;
- return total;
-}
-
-/* NOTE: assumes unsigned long is 8 bytes */
-static ssize_t ui_write(struct file *filp, const char __user *buf,
- size_t count, loff_t *f_pos)
-{
- struct hfi1_devdata *dd = filp->private_data;
- void __iomem *base;
- unsigned long total, data, csr_off;
- int in_lcb;
-
- /* only write 8 byte quantities */
- if ((count % 8) != 0)
- return -EINVAL;
- /* offset must be 8-byte aligned */
- if ((*f_pos % 8) != 0)
- return -EINVAL;
- /* source buffer must be 8-byte aligned */
- if ((unsigned long)buf % 8 != 0)
- return -EINVAL;
- /* must be in range */
- if (*f_pos + count > dd->kregend - dd->kregbase)
- return -EINVAL;
-
- base = (void __iomem *)dd->kregbase + *f_pos;
- csr_off = *f_pos;
- in_lcb = 0;
- for (total = 0; total < count; total += 8, csr_off += 8) {
- if (get_user(data, (unsigned long __user *)(buf + total)))
- break;
- /* accessing LCB CSRs requires a special procedure */
- if (is_lcb_offset(csr_off)) {
- if (!in_lcb) {
- int ret = acquire_lcb_access(dd, 1);
-
- if (ret)
- break;
- in_lcb = 1;
- }
- } else {
- if (in_lcb) {
- release_lcb_access(dd, 1);
- in_lcb = 0;
- }
- }
- writeq(data, base + total);
- }
- if (in_lcb)
- release_lcb_access(dd, 1);
- *f_pos += total;
- return total;
-}
-
-static const struct file_operations ui_file_ops = {
- .owner = THIS_MODULE,
- .llseek = ui_lseek,
- .read = ui_read,
- .write = ui_write,
- .open = ui_open,
- .release = ui_release,
-};
-
-#define UI_OFFSET 192 /* device minor offset for UI devices */
-static int create_ui = 1;
-
-static struct cdev wildcard_cdev;
-static struct device *wildcard_device;
-
-static atomic_t user_count = ATOMIC_INIT(0);
-
static void user_remove(struct hfi1_devdata *dd)
{
- if (atomic_dec_return(&user_count) == 0)
- hfi1_cdev_cleanup(&wildcard_cdev, &wildcard_device);
hfi1_cdev_cleanup(&dd->user_cdev, &dd->user_device);
- hfi1_cdev_cleanup(&dd->ui_cdev, &dd->ui_device);
}
static int user_add(struct hfi1_devdata *dd)
@@ -1717,34 +1473,13 @@ static int user_add(struct hfi1_devdata *dd)
char name[10];
int ret;
- if (atomic_inc_return(&user_count) == 1) {
- ret = hfi1_cdev_init(0, class_name(), &hfi1_file_ops,
- &wildcard_cdev, &wildcard_device,
- true);
- if (ret)
- goto done;
- }
-
snprintf(name, sizeof(name), "%s_%d", class_name(), dd->unit);
- ret = hfi1_cdev_init(dd->unit + 1, name, &hfi1_file_ops,
+ ret = hfi1_cdev_init(dd->unit, name, &hfi1_file_ops,
&dd->user_cdev, &dd->user_device,
- true);
+ true, &dd->kobj);
if (ret)
- goto done;
+ user_remove(dd);
- if (create_ui) {
- snprintf(name, sizeof(name),
- "%s_ui%d", class_name(), dd->unit);
- ret = hfi1_cdev_init(dd->unit + UI_OFFSET, name, &ui_file_ops,
- &dd->ui_cdev, &dd->ui_device,
- false);
- if (ret)
- goto done;
- }
-
- return 0;
-done:
- user_remove(dd);
return ret;
}
@@ -1753,13 +1488,7 @@ done:
*/
int hfi1_device_create(struct hfi1_devdata *dd)
{
- int r, ret;
-
- r = user_add(dd);
- ret = hfi1_diag_add(dd);
- if (r && !ret)
- ret = r;
- return ret;
+ return user_add(dd);
}
/*
@@ -1769,5 +1498,4 @@ int hfi1_device_create(struct hfi1_devdata *dd)
void hfi1_device_remove(struct hfi1_devdata *dd)
{
user_remove(dd);
- hfi1_diag_remove(dd);
}
diff --git a/drivers/staging/rdma/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index ed680fda611d..ed680fda611d 100644
--- a/drivers/staging/rdma/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
diff --git a/drivers/staging/rdma/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 7b78d56de7f5..4417a0fd3ef9 100644
--- a/drivers/staging/rdma/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -453,6 +453,7 @@ struct rvt_sge_state;
#define HLS_LINK_COOLDOWN BIT(__HLS_LINK_COOLDOWN_BP)
#define HLS_UP (HLS_UP_INIT | HLS_UP_ARMED | HLS_UP_ACTIVE)
+#define HLS_DOWN ~(HLS_UP)
/* use this MTU size if none other is given */
#define HFI1_DEFAULT_ACTIVE_MTU 10240
@@ -1168,6 +1169,7 @@ struct hfi1_devdata {
atomic_t aspm_disabled_cnt;
struct hfi1_affinity *affinity;
+ struct kobject kobj;
};
/* 8051 firmware version helper */
@@ -1882,9 +1884,8 @@ static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd)
get_unit_name((dd)->unit), ##__VA_ARGS__)
#define hfi1_dev_porterr(dd, port, fmt, ...) \
- dev_err(&(dd)->pcidev->dev, "%s: IB%u:%u " fmt, \
- get_unit_name((dd)->unit), (dd)->unit, (port), \
- ##__VA_ARGS__)
+ dev_err(&(dd)->pcidev->dev, "%s: port %u: " fmt, \
+ get_unit_name((dd)->unit), (port), ##__VA_ARGS__)
/*
* this is used for formatting hw error messages...
diff --git a/drivers/staging/rdma/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 502b7cf4647d..eed971ccd2a1 100644
--- a/drivers/staging/rdma/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -732,12 +732,12 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
lastfail = hfi1_create_rcvhdrq(dd, rcd);
if (!lastfail)
lastfail = hfi1_setup_eagerbufs(rcd);
- if (lastfail)
+ if (lastfail) {
dd_dev_err(dd,
"failed to allocate kernel ctxt's rcvhdrq and/or egr bufs\n");
+ ret = lastfail;
+ }
}
- if (lastfail)
- ret = lastfail;
/* Allocate enough memory for user event notification. */
len = PAGE_ALIGN(dd->chip_rcv_contexts * HFI1_MAX_SHARED_CTXTS *
@@ -989,8 +989,10 @@ static void release_asic_data(struct hfi1_devdata *dd)
dd->asic_data = NULL;
}
-void hfi1_free_devdata(struct hfi1_devdata *dd)
+static void __hfi1_free_devdata(struct kobject *kobj)
{
+ struct hfi1_devdata *dd =
+ container_of(kobj, struct hfi1_devdata, kobj);
unsigned long flags;
spin_lock_irqsave(&hfi1_devs_lock, flags);
@@ -1007,6 +1009,15 @@ void hfi1_free_devdata(struct hfi1_devdata *dd)
rvt_dealloc_device(&dd->verbs_dev.rdi);
}
+static struct kobj_type hfi1_devdata_type = {
+ .release = __hfi1_free_devdata,
+};
+
+void hfi1_free_devdata(struct hfi1_devdata *dd)
+{
+ kobject_put(&dd->kobj);
+}
+
/*
* Allocate our primary per-unit data structure. Must be done via verbs
* allocator, because the verbs cleanup process both does cleanup and
@@ -1102,6 +1113,7 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
&pdev->dev,
"Could not alloc cpulist info, cpu affinity might be wrong\n");
}
+ kobject_init(&dd->kobj, &hfi1_devdata_type);
return dd;
bail:
@@ -1300,7 +1312,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
spin_lock(&ppd->cc_state_lock);
cc_state = get_cc_state(ppd);
- rcu_assign_pointer(ppd->cc_state, NULL);
+ RCU_INIT_POINTER(ppd->cc_state, NULL);
spin_unlock(&ppd->cc_state_lock);
if (cc_state)
@@ -1325,7 +1337,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
(void *)dd->rcvhdrtail_dummy_kvaddr,
dd->rcvhdrtail_dummy_physaddr);
- dd->rcvhdrtail_dummy_kvaddr = NULL;
+ dd->rcvhdrtail_dummy_kvaddr = NULL;
}
for (ctxt = 0; tmp && ctxt < dd->num_rcv_contexts; ctxt++) {
@@ -1371,7 +1383,7 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
int ret = 0, j, pidx, initfail;
- struct hfi1_devdata *dd = NULL;
+ struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
struct hfi1_pportdata *ppd;
/* First, lock the non-writable module parameters */
diff --git a/drivers/staging/rdma/hfi1/intr.c b/drivers/infiniband/hw/hfi1/intr.c
index 65348d16ab2f..65348d16ab2f 100644
--- a/drivers/staging/rdma/hfi1/intr.c
+++ b/drivers/infiniband/hw/hfi1/intr.c
diff --git a/drivers/staging/rdma/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h
index 2ec6ef38d389..2ec6ef38d389 100644
--- a/drivers/staging/rdma/hfi1/iowait.h
+++ b/drivers/infiniband/hw/hfi1/iowait.h
diff --git a/drivers/staging/rdma/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index ed58cf21e790..fca07a1d6c28 100644
--- a/drivers/staging/rdma/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -78,6 +78,16 @@ static inline void clear_opa_smp_data(struct opa_smp *smp)
memset(data, 0, size);
}
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port)
+{
+ struct ib_event event;
+
+ event.event = IB_EVENT_PKEY_CHANGE;
+ event.device = &dd->verbs_dev.rdi.ibdev;
+ event.element.port_num = port;
+ ib_dispatch_event(&event);
+}
+
static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
{
struct ib_mad_send_buf *send_buf;
@@ -1403,6 +1413,12 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
if (key == okey)
continue;
/*
+ * Don't update pkeys[2], if an HFI port without MgmtAllowed
+ * by neighbor is a switch.
+ */
+ if (i == 2 && !ppd->mgmt_allowed && ppd->neighbor_type == 1)
+ continue;
+ /*
* The SM gives us the complete PKey table. We have
* to ensure that we put the PKeys in the matching
* slots.
@@ -1412,15 +1428,10 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
}
if (changed) {
- struct ib_event event;
-
(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
-
- event.event = IB_EVENT_PKEY_CHANGE;
- event.device = &dd->verbs_dev.rdi.ibdev;
- event.element.port_num = port;
- ib_dispatch_event(&event);
+ hfi1_event_pkey_change(dd, port);
}
+
return 0;
}
@@ -3363,6 +3374,50 @@ static int __subn_get_opa_cong_setting(struct opa_smp *smp, u32 am,
return reply((struct ib_mad_hdr *)smp);
}
+/*
+ * Apply congestion control information stored in the ppd to the
+ * active structure.
+ */
+static void apply_cc_state(struct hfi1_pportdata *ppd)
+{
+ struct cc_state *old_cc_state, *new_cc_state;
+
+ new_cc_state = kzalloc(sizeof(*new_cc_state), GFP_KERNEL);
+ if (!new_cc_state)
+ return;
+
+ /*
+ * Hold the lock for updating *and* to prevent ppd information
+ * from changing during the update.
+ */
+ spin_lock(&ppd->cc_state_lock);
+
+ old_cc_state = get_cc_state(ppd);
+ if (!old_cc_state) {
+ /* never active, or shutting down */
+ spin_unlock(&ppd->cc_state_lock);
+ kfree(new_cc_state);
+ return;
+ }
+
+ *new_cc_state = *old_cc_state;
+
+ new_cc_state->cct.ccti_limit = ppd->total_cct_entry - 1;
+ memcpy(new_cc_state->cct.entries, ppd->ccti_entries,
+ ppd->total_cct_entry * sizeof(struct ib_cc_table_entry));
+
+ new_cc_state->cong_setting.port_control = IB_CC_CCS_PC_SL_BASED;
+ new_cc_state->cong_setting.control_map = ppd->cc_sl_control_map;
+ memcpy(new_cc_state->cong_setting.entries, ppd->congestion_entries,
+ OPA_MAX_SLS * sizeof(struct opa_congestion_setting_entry));
+
+ rcu_assign_pointer(ppd->cc_state, new_cc_state);
+
+ spin_unlock(&ppd->cc_state_lock);
+
+ call_rcu(&old_cc_state->rcu, cc_state_reclaim);
+}
+
static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
struct ib_device *ibdev, u8 port,
u32 *resp_len)
@@ -3374,6 +3429,11 @@ static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
struct opa_congestion_setting_entry_shadow *entries;
int i;
+ /*
+ * Save details from packet into the ppd. Hold the cc_state_lock so
+ * our information is consistent with anyone trying to apply the state.
+ */
+ spin_lock(&ppd->cc_state_lock);
ppd->cc_sl_control_map = be32_to_cpu(p->control_map);
entries = ppd->congestion_entries;
@@ -3384,6 +3444,10 @@ static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
p->entries[i].trigger_threshold;
entries[i].ccti_min = p->entries[i].ccti_min;
}
+ spin_unlock(&ppd->cc_state_lock);
+
+ /* now apply the information */
+ apply_cc_state(ppd);
return __subn_get_opa_cong_setting(smp, am, data, ibdev, port,
resp_len);
@@ -3526,7 +3590,6 @@ static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
int i, j;
u32 sentry, eentry;
u16 ccti_limit;
- struct cc_state *old_cc_state, *new_cc_state;
/* sanity check n_blocks, start_block */
if (n_blocks == 0 ||
@@ -3546,45 +3609,20 @@ static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
return reply((struct ib_mad_hdr *)smp);
}
- new_cc_state = kzalloc(sizeof(*new_cc_state), GFP_KERNEL);
- if (!new_cc_state)
- goto getit;
-
+ /*
+ * Save details from packet into the ppd. Hold the cc_state_lock so
+ * our information is consistent with anyone trying to apply the state.
+ */
spin_lock(&ppd->cc_state_lock);
-
- old_cc_state = get_cc_state(ppd);
-
- if (!old_cc_state) {
- spin_unlock(&ppd->cc_state_lock);
- kfree(new_cc_state);
- return reply((struct ib_mad_hdr *)smp);
- }
-
- *new_cc_state = *old_cc_state;
-
- new_cc_state->cct.ccti_limit = ccti_limit;
-
- entries = ppd->ccti_entries;
ppd->total_cct_entry = ccti_limit + 1;
-
+ entries = ppd->ccti_entries;
for (j = 0, i = sentry; i < eentry; j++, i++)
entries[i].entry = be16_to_cpu(p->ccti_entries[j].entry);
-
- memcpy(new_cc_state->cct.entries, entries,
- eentry * sizeof(struct ib_cc_table_entry));
-
- new_cc_state->cong_setting.port_control = IB_CC_CCS_PC_SL_BASED;
- new_cc_state->cong_setting.control_map = ppd->cc_sl_control_map;
- memcpy(new_cc_state->cong_setting.entries, ppd->congestion_entries,
- OPA_MAX_SLS * sizeof(struct opa_congestion_setting_entry));
-
- rcu_assign_pointer(ppd->cc_state, new_cc_state);
-
spin_unlock(&ppd->cc_state_lock);
- call_rcu(&old_cc_state->rcu, cc_state_reclaim);
+ /* now apply the information */
+ apply_cc_state(ppd);
-getit:
return __subn_get_opa_cc_table(smp, am, data, ibdev, port, resp_len);
}
diff --git a/drivers/staging/rdma/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h
index 55ee08675333..8b734aaae88a 100644
--- a/drivers/staging/rdma/hfi1/mad.h
+++ b/drivers/infiniband/hw/hfi1/mad.h
@@ -434,4 +434,6 @@ struct sc2vlnt {
COUNTER_MASK(1, 3) | \
COUNTER_MASK(1, 4))
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
+
#endif /* _HFI1_MAD_H */
diff --git a/drivers/staging/rdma/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index 2b0e91d3093d..b7a80aa1ae30 100644
--- a/drivers/staging/rdma/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -45,6 +45,7 @@
*
*/
#include <linux/list.h>
+#include <linux/rculist.h>
#include <linux/mmu_notifier.h>
#include <linux/interval_tree_generic.h>
@@ -97,7 +98,6 @@ static unsigned long mmu_node_last(struct mmu_rb_node *node)
int hfi1_mmu_rb_register(struct rb_root *root, struct mmu_rb_ops *ops)
{
struct mmu_rb_handler *handlr;
- unsigned long flags;
if (!ops->invalidate)
return -EINVAL;
@@ -111,9 +111,9 @@ int hfi1_mmu_rb_register(struct rb_root *root, struct mmu_rb_ops *ops)
INIT_HLIST_NODE(&handlr->mn.hlist);
spin_lock_init(&handlr->lock);
handlr->mn.ops = &mn_opts;
- spin_lock_irqsave(&mmu_rb_lock, flags);
- list_add_tail(&handlr->list, &mmu_rb_handlers);
- spin_unlock_irqrestore(&mmu_rb_lock, flags);
+ spin_lock(&mmu_rb_lock);
+ list_add_tail_rcu(&handlr->list, &mmu_rb_handlers);
+ spin_unlock(&mmu_rb_lock);
return mmu_notifier_register(&handlr->mn, current->mm);
}
@@ -130,9 +130,10 @@ void hfi1_mmu_rb_unregister(struct rb_root *root)
if (current->mm)
mmu_notifier_unregister(&handler->mn, current->mm);
- spin_lock_irqsave(&mmu_rb_lock, flags);
- list_del(&handler->list);
- spin_unlock_irqrestore(&mmu_rb_lock, flags);
+ spin_lock(&mmu_rb_lock);
+ list_del_rcu(&handler->list);
+ spin_unlock(&mmu_rb_lock);
+ synchronize_rcu();
spin_lock_irqsave(&handler->lock, flags);
if (!RB_EMPTY_ROOT(root)) {
@@ -271,16 +272,15 @@ void hfi1_mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node)
static struct mmu_rb_handler *find_mmu_handler(struct rb_root *root)
{
struct mmu_rb_handler *handler;
- unsigned long flags;
- spin_lock_irqsave(&mmu_rb_lock, flags);
- list_for_each_entry(handler, &mmu_rb_handlers, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(handler, &mmu_rb_handlers, list) {
if (handler->root == root)
goto unlock;
}
handler = NULL;
unlock:
- spin_unlock_irqrestore(&mmu_rb_lock, flags);
+ rcu_read_unlock();
return handler;
}
diff --git a/drivers/staging/rdma/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h
index 7a57b9c49d27..7a57b9c49d27 100644
--- a/drivers/staging/rdma/hfi1/mmu_rb.h
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.h
diff --git a/drivers/staging/rdma/hfi1/opa_compat.h b/drivers/infiniband/hw/hfi1/opa_compat.h
index 6ef3c1cbdcd7..6ef3c1cbdcd7 100644
--- a/drivers/staging/rdma/hfi1/opa_compat.h
+++ b/drivers/infiniband/hw/hfi1/opa_compat.h
diff --git a/drivers/staging/rdma/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 0bac21e6a658..0bac21e6a658 100644
--- a/drivers/staging/rdma/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
diff --git a/drivers/staging/rdma/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index c67b9ad3fcf4..d4022450b73f 100644
--- a/drivers/staging/rdma/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -995,7 +995,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause)
/* counter is reset if occupancy count changes */
if (reg != reg_prev)
loop = 0;
- if (loop > 500) {
+ if (loop > 50000) {
/* timed out - bounce the link */
dd_dev_err(dd,
"%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
@@ -1798,6 +1798,21 @@ static void pio_map_rcu_callback(struct rcu_head *list)
}
/*
+ * Set credit return threshold for the kernel send context
+ */
+static void set_threshold(struct hfi1_devdata *dd, int scontext, int i)
+{
+ u32 thres;
+
+ thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext],
+ 50),
+ sc_mtu_to_threshold(dd->kernel_send_context[scontext],
+ dd->vld[i].mtu,
+ dd->rcd[0]->rcvhdrqentsize));
+ sc_set_cr_threshold(dd->kernel_send_context[scontext], thres);
+}
+
+/*
* pio_map_init - called when #vls change
* @dd: hfi1_devdata
* @port: port number
@@ -1835,8 +1850,7 @@ int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts)
struct pio_vl_map *oldmap, *newmap;
if (!vl_scontexts) {
- /* send context 0 reserved for VL15 */
- for (i = 1; i < dd->num_send_contexts; i++)
+ for (i = 0; i < dd->num_send_contexts; i++)
if (dd->send_contexts[i].type == SC_KERNEL)
num_kernel_send_contexts++;
/* truncate divide */
@@ -1873,11 +1887,16 @@ int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts)
if (!newmap->map[i])
goto bail;
newmap->map[i]->mask = (1 << ilog2(sz)) - 1;
- /* assign send contexts */
+ /*
+ * assign send contexts and
+ * adjust credit return threshold
+ */
for (j = 0; j < sz; j++) {
- if (dd->kernel_send_context[scontext])
+ if (dd->kernel_send_context[scontext]) {
newmap->map[i]->ksc[j] =
dd->kernel_send_context[scontext];
+ set_threshold(dd, scontext, i);
+ }
if (++scontext >= first_scontext +
vl_scontexts[i])
/* wrap back to first send context */
diff --git a/drivers/staging/rdma/hfi1/pio.h b/drivers/infiniband/hw/hfi1/pio.h
index 53a08edb7f64..464cbd27b975 100644
--- a/drivers/staging/rdma/hfi1/pio.h
+++ b/drivers/infiniband/hw/hfi1/pio.h
@@ -49,10 +49,10 @@
/* send context types */
#define SC_KERNEL 0
-#define SC_ACK 1
-#define SC_USER 2
-#define SC_VL15 3
-#define SC_MAX 4
+#define SC_VL15 1
+#define SC_ACK 2
+#define SC_USER 3 /* must be the last one: it may take all left */
+#define SC_MAX 4 /* count of send context types */
/* invalid send context index */
#define INVALID_SCI 0xff
diff --git a/drivers/staging/rdma/hfi1/pio_copy.c b/drivers/infiniband/hw/hfi1/pio_copy.c
index 8c25e1b58849..8c25e1b58849 100644
--- a/drivers/staging/rdma/hfi1/pio_copy.c
+++ b/drivers/infiniband/hw/hfi1/pio_copy.c
diff --git a/drivers/staging/rdma/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index 8fe8a205b5bb..03df9322f862 100644
--- a/drivers/staging/rdma/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -87,6 +87,17 @@ void free_platform_config(struct hfi1_devdata *dd)
*/
}
+void get_port_type(struct hfi1_pportdata *ppd)
+{
+ int ret;
+
+ ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0,
+ PORT_TABLE_PORT_TYPE, &ppd->port_type,
+ 4);
+ if (ret)
+ ppd->port_type = PORT_TYPE_UNKNOWN;
+}
+
int set_qsfp_tx(struct hfi1_pportdata *ppd, int on)
{
u8 tx_ctrl_byte = on ? 0x0 : 0xF;
@@ -529,7 +540,8 @@ static void apply_tunings(
/* Enable external device config if channel is limiting active */
read_8051_config(ppd->dd, LINK_OPTIMIZATION_SETTINGS,
GENERAL_CONFIG, &config_data);
- config_data |= limiting_active;
+ config_data &= ~(0xff << ENABLE_EXT_DEV_CONFIG_SHIFT);
+ config_data |= ((u32)limiting_active << ENABLE_EXT_DEV_CONFIG_SHIFT);
ret = load_8051_config(ppd->dd, LINK_OPTIMIZATION_SETTINGS,
GENERAL_CONFIG, config_data);
if (ret != HCMD_SUCCESS)
@@ -542,7 +554,8 @@ static void apply_tunings(
/* Pass tuning method to 8051 */
read_8051_config(ppd->dd, LINK_TUNING_PARAMETERS, GENERAL_CONFIG,
&config_data);
- config_data |= tuning_method;
+ config_data &= ~(0xff << TUNING_METHOD_SHIFT);
+ config_data |= ((u32)tuning_method << TUNING_METHOD_SHIFT);
ret = load_8051_config(ppd->dd, LINK_TUNING_PARAMETERS, GENERAL_CONFIG,
config_data);
if (ret != HCMD_SUCCESS)
@@ -564,8 +577,8 @@ static void apply_tunings(
ret = read_8051_config(ppd->dd, DC_HOST_COMM_SETTINGS,
GENERAL_CONFIG, &config_data);
/* Clear, then set the external device config field */
- config_data &= ~(0xFF << 24);
- config_data |= (external_device_config << 24);
+ config_data &= ~(u32)0xFF;
+ config_data |= external_device_config;
ret = load_8051_config(ppd->dd, DC_HOST_COMM_SETTINGS,
GENERAL_CONFIG, config_data);
if (ret != HCMD_SUCCESS)
@@ -784,12 +797,6 @@ void tune_serdes(struct hfi1_pportdata *ppd)
return;
}
- ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0,
- PORT_TABLE_PORT_TYPE, &ppd->port_type,
- 4);
- if (ret)
- ppd->port_type = PORT_TYPE_UNKNOWN;
-
switch (ppd->port_type) {
case PORT_TYPE_DISCONNECTED:
ppd->offline_disabled_reason =
diff --git a/drivers/staging/rdma/hfi1/platform.h b/drivers/infiniband/hw/hfi1/platform.h
index 19620cf546d5..e2c21613c326 100644
--- a/drivers/staging/rdma/hfi1/platform.h
+++ b/drivers/infiniband/hw/hfi1/platform.h
@@ -298,6 +298,7 @@ enum link_tuning_encoding {
/* platform.c */
void get_platform_config(struct hfi1_devdata *dd);
void free_platform_config(struct hfi1_devdata *dd);
+void get_port_type(struct hfi1_pportdata *ppd);
int set_qsfp_tx(struct hfi1_pportdata *ppd, int on);
void tune_serdes(struct hfi1_pportdata *ppd);
diff --git a/drivers/staging/rdma/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index 91eb42316df9..1a942ffba4cb 100644
--- a/drivers/staging/rdma/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -49,7 +49,6 @@
#include <linux/vmalloc.h>
#include <linux/hash.h>
#include <linux/module.h>
-#include <linux/random.h>
#include <linux/seq_file.h>
#include <rdma/rdma_vt.h>
#include <rdma/rdmavt_qp.h>
@@ -161,9 +160,6 @@ static inline int opa_mtu_enum_to_int(int mtu)
* This function is what we would push to the core layer if we wanted to be a
* "first class citizen". Instead we hide this here and rely on Verbs ULPs
* to blindly pass the MTU enum value from the PathRecord to us.
- *
- * The actual flag used to determine "8k MTU" will change and is currently
- * unknown.
*/
static inline int verbs_mtu_enum_to_int(struct ib_device *dev, enum ib_mtu mtu)
{
@@ -516,6 +512,7 @@ static void iowait_wakeup(struct iowait *wait, int reason)
static void iowait_sdma_drained(struct iowait *wait)
{
struct rvt_qp *qp = iowait_to_qp(wait);
+ unsigned long flags;
/*
* This happens when the send engine notes
@@ -523,12 +520,12 @@ static void iowait_sdma_drained(struct iowait *wait)
* do the flush work until that QP's
* sdma work has finished.
*/
- spin_lock(&qp->s_lock);
+ spin_lock_irqsave(&qp->s_lock, flags);
if (qp->s_flags & RVT_S_WAIT_DMA) {
qp->s_flags &= ~RVT_S_WAIT_DMA;
hfi1_schedule_send(qp);
}
- spin_unlock(&qp->s_lock);
+ spin_unlock_irqrestore(&qp->s_lock, flags);
}
/**
diff --git a/drivers/staging/rdma/hfi1/qp.h b/drivers/infiniband/hw/hfi1/qp.h
index e7bc8d6cf681..e7bc8d6cf681 100644
--- a/drivers/staging/rdma/hfi1/qp.h
+++ b/drivers/infiniband/hw/hfi1/qp.h
diff --git a/drivers/staging/rdma/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index 2441669f0817..9fb561682c66 100644
--- a/drivers/staging/rdma/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -579,7 +579,8 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len)
if (ppd->qsfp_info.cache_valid) {
if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
- sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]);
+ snprintf(lenstr, sizeof(lenstr), "%dM ",
+ cache[QSFP_MOD_LEN_OFFS]);
power_byte = cache[QSFP_MOD_PWR_OFFS];
sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n",
diff --git a/drivers/staging/rdma/hfi1/qsfp.h b/drivers/infiniband/hw/hfi1/qsfp.h
index dadc66c442b9..dadc66c442b9 100644
--- a/drivers/staging/rdma/hfi1/qsfp.h
+++ b/drivers/infiniband/hw/hfi1/qsfp.h
diff --git a/drivers/staging/rdma/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 792f15eb8efe..792f15eb8efe 100644
--- a/drivers/staging/rdma/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
diff --git a/drivers/staging/rdma/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index a659aec3c3c6..a659aec3c3c6 100644
--- a/drivers/staging/rdma/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
diff --git a/drivers/staging/rdma/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index abb8ebc1fcac..f9befc05b349 100644
--- a/drivers/staging/rdma/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -134,6 +134,7 @@ static const char * const sdma_state_names[] = {
[sdma_state_s99_running] = "s99_Running",
};
+#ifdef CONFIG_SDMA_VERBOSITY
static const char * const sdma_event_names[] = {
[sdma_event_e00_go_hw_down] = "e00_GoHwDown",
[sdma_event_e10_go_hw_start] = "e10_GoHwStart",
@@ -150,6 +151,7 @@ static const char * const sdma_event_names[] = {
[sdma_event_e85_link_down] = "e85_LinkDown",
[sdma_event_e90_sw_halted] = "e90_SwHalted",
};
+#endif
static const struct sdma_set_state_action sdma_action_table[] = {
[sdma_state_s00_hw_down] = {
@@ -376,7 +378,7 @@ static inline void complete_tx(struct sdma_engine *sde,
sdma_txclean(sde->dd, tx);
if (complete)
(*complete)(tx, res);
- if (iowait_sdma_dec(wait) && wait)
+ if (wait && iowait_sdma_dec(wait))
iowait_drain_wakeup(wait);
}
diff --git a/drivers/staging/rdma/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h
index 8f50c99fe711..8f50c99fe711 100644
--- a/drivers/staging/rdma/hfi1/sdma.h
+++ b/drivers/infiniband/hw/hfi1/sdma.h
diff --git a/drivers/staging/rdma/hfi1/sdma_txreq.h b/drivers/infiniband/hw/hfi1/sdma_txreq.h
index bf7d777d756e..bf7d777d756e 100644
--- a/drivers/staging/rdma/hfi1/sdma_txreq.h
+++ b/drivers/infiniband/hw/hfi1/sdma_txreq.h
diff --git a/drivers/staging/rdma/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c
index 8cd6df8634ad..91fc2aed6aed 100644
--- a/drivers/staging/rdma/hfi1/sysfs.c
+++ b/drivers/infiniband/hw/hfi1/sysfs.c
@@ -721,8 +721,8 @@ int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num,
}
dd_dev_info(dd,
- "IB%u: Congestion Control Agent enabled for port %d\n",
- dd->unit, port_num);
+ "Congestion Control Agent enabled for port %d\n",
+ port_num);
return 0;
diff --git a/drivers/staging/rdma/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c
index 8b62fefcf903..4cfb13771897 100644
--- a/drivers/staging/rdma/hfi1/trace.c
+++ b/drivers/infiniband/hw/hfi1/trace.c
@@ -66,6 +66,7 @@ u8 ibhdr_exhdr_len(struct hfi1_ib_header *hdr)
#define RETH_PRN "reth vaddr 0x%.16llx rkey 0x%.8x dlen 0x%.8x"
#define AETH_PRN "aeth syn 0x%.2x %s msn 0x%.8x"
#define DETH_PRN "deth qkey 0x%.8x sqpn 0x%.6x"
+#define IETH_PRN "ieth rkey 0x%.8x"
#define ATOMICACKETH_PRN "origdata %lld"
#define ATOMICETH_PRN "vaddr 0x%llx rkey 0x%.8x sdata %lld cdata %lld"
@@ -166,6 +167,12 @@ const char *parse_everbs_hdrs(
be32_to_cpu(eh->ud.deth[0]),
be32_to_cpu(eh->ud.deth[1]) & RVT_QPN_MASK);
break;
+ /* ieth */
+ case OP(RC, SEND_LAST_WITH_INVALIDATE):
+ case OP(RC, SEND_ONLY_WITH_INVALIDATE):
+ trace_seq_printf(p, IETH_PRN,
+ be32_to_cpu(eh->ieth));
+ break;
}
trace_seq_putc(p, 0);
return ret;
@@ -207,19 +214,6 @@ const char *print_u32_array(
return ret;
}
-const char *print_u64_array(
- struct trace_seq *p,
- u64 *arr, int len)
-{
- int i;
- const char *ret = trace_seq_buffer_ptr(p);
-
- for (i = 0; i < len; i++)
- trace_seq_printf(p, "%s0x%016llx", i == 0 ? "" : " ", arr[i]);
- trace_seq_putc(p, 0);
- return ret;
-}
-
__hfi1_trace_fn(PKT);
__hfi1_trace_fn(PROC);
__hfi1_trace_fn(SDMA);
@@ -233,3 +227,4 @@ __hfi1_trace_fn(FIRMWARE);
__hfi1_trace_fn(RCVCTRL);
__hfi1_trace_fn(TID);
__hfi1_trace_fn(MMU);
+__hfi1_trace_fn(IOCTL);
diff --git a/drivers/staging/rdma/hfi1/trace.h b/drivers/infiniband/hw/hfi1/trace.h
index 963dc948c38a..28c1d0832886 100644
--- a/drivers/staging/rdma/hfi1/trace.h
+++ b/drivers/infiniband/hw/hfi1/trace.h
@@ -74,8 +74,8 @@ __print_symbolic(etype, \
TRACE_EVENT(hfi1_rcvhdr,
TP_PROTO(struct hfi1_devdata *dd,
- u64 eflags,
u32 ctxt,
+ u64 eflags,
u32 etype,
u32 hlen,
u32 tlen,
@@ -392,6 +392,8 @@ __print_symbolic(opcode, \
ib_opcode_name(RC_ATOMIC_ACKNOWLEDGE), \
ib_opcode_name(RC_COMPARE_SWAP), \
ib_opcode_name(RC_FETCH_ADD), \
+ ib_opcode_name(RC_SEND_LAST_WITH_INVALIDATE), \
+ ib_opcode_name(RC_SEND_ONLY_WITH_INVALIDATE), \
ib_opcode_name(UC_SEND_FIRST), \
ib_opcode_name(UC_SEND_MIDDLE), \
ib_opcode_name(UC_SEND_LAST), \
@@ -1341,6 +1343,7 @@ __hfi1_trace_def(FIRMWARE);
__hfi1_trace_def(RCVCTRL);
__hfi1_trace_def(TID);
__hfi1_trace_def(MMU);
+__hfi1_trace_def(IOCTL);
#define hfi1_cdbg(which, fmt, ...) \
__hfi1_trace_##which(__func__, fmt, ##__VA_ARGS__)
diff --git a/drivers/staging/rdma/hfi1/twsi.c b/drivers/infiniband/hw/hfi1/twsi.c
index e82e52a63d35..e82e52a63d35 100644
--- a/drivers/staging/rdma/hfi1/twsi.c
+++ b/drivers/infiniband/hw/hfi1/twsi.c
diff --git a/drivers/staging/rdma/hfi1/twsi.h b/drivers/infiniband/hw/hfi1/twsi.h
index 5b8a5b5e7eae..5b8a5b5e7eae 100644
--- a/drivers/staging/rdma/hfi1/twsi.h
+++ b/drivers/infiniband/hw/hfi1/twsi.h
diff --git a/drivers/staging/rdma/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index df773d433297..df773d433297 100644
--- a/drivers/staging/rdma/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
diff --git a/drivers/staging/rdma/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 1e503ad0bebb..1e503ad0bebb 100644
--- a/drivers/staging/rdma/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
diff --git a/drivers/staging/rdma/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 1b640a35b3fe..1b640a35b3fe 100644
--- a/drivers/staging/rdma/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
diff --git a/drivers/staging/rdma/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
index 9bc8d9fba87e..9bc8d9fba87e 100644
--- a/drivers/staging/rdma/hfi1/user_exp_rcv.h
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
diff --git a/drivers/staging/rdma/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 88e10b5f55f1..88e10b5f55f1 100644
--- a/drivers/staging/rdma/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
diff --git a/drivers/staging/rdma/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 0014c9c0e967..47ffd273ecbd 100644
--- a/drivers/staging/rdma/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -166,6 +166,8 @@ static unsigned initial_pkt_count = 8;
#define SDMA_IOWAIT_TIMEOUT 1000 /* in milliseconds */
+struct sdma_mmu_node;
+
struct user_sdma_iovec {
struct list_head list;
struct iovec iov;
@@ -178,9 +180,10 @@ struct user_sdma_iovec {
* which we last left off.
*/
u64 offset;
+ struct sdma_mmu_node *node;
};
-#define SDMA_CACHE_NODE_EVICT BIT(0)
+#define SDMA_CACHE_NODE_EVICT 0
struct sdma_mmu_node {
struct mmu_rb_node rb;
@@ -507,6 +510,7 @@ int hfi1_user_sdma_process_request(struct file *fp, struct iovec *iovec,
struct sdma_req_info info;
struct user_sdma_request *req;
u8 opcode, sc, vl;
+ int req_queued = 0;
if (iovec[idx].iov_len < sizeof(info) + sizeof(req->hdr)) {
hfi1_cdbg(
@@ -703,6 +707,7 @@ int hfi1_user_sdma_process_request(struct file *fp, struct iovec *iovec,
set_comp_state(pq, cq, info.comp_idx, QUEUED, 0);
atomic_inc(&pq->n_reqs);
+ req_queued = 1;
/* Send the first N packets in the request to buy us some time */
ret = user_sdma_send_pkts(req, pcount);
if (unlikely(ret < 0 && ret != -EBUSY)) {
@@ -747,7 +752,8 @@ int hfi1_user_sdma_process_request(struct file *fp, struct iovec *iovec,
return 0;
free_req:
user_sdma_free_request(req, true);
- pq_update(pq);
+ if (req_queued)
+ pq_update(pq);
set_comp_state(pq, cq, info.comp_idx, ERROR, req->status);
return ret;
}
@@ -1153,6 +1159,7 @@ retry:
}
iovec->pages = node->pages;
iovec->npages = npages;
+ iovec->node = node;
ret = hfi1_mmu_rb_insert(&req->pq->sdma_rb_root, &node->rb);
if (ret) {
@@ -1348,11 +1355,11 @@ static int set_txreq_header(struct user_sdma_request *req,
*/
SDMA_DBG(req, "TID offset %ubytes %uunits om%u",
req->tidoffset, req->tidoffset / req->omfactor,
- !!(req->omfactor - KDETH_OM_SMALL));
+ req->omfactor != KDETH_OM_SMALL);
KDETH_SET(hdr->kdeth.ver_tid_offset, OFFSET,
req->tidoffset / req->omfactor);
KDETH_SET(hdr->kdeth.ver_tid_offset, OM,
- !!(req->omfactor - KDETH_OM_SMALL));
+ req->omfactor != KDETH_OM_SMALL);
}
done:
trace_hfi1_sdma_user_header(pq->dd, pq->ctxt, pq->subctxt,
@@ -1519,18 +1526,13 @@ static void user_sdma_free_request(struct user_sdma_request *req, bool unpin)
}
if (req->data_iovs) {
struct sdma_mmu_node *node;
- struct mmu_rb_node *mnode;
int i;
for (i = 0; i < req->data_iovs; i++) {
- mnode = hfi1_mmu_rb_search(
- &req->pq->sdma_rb_root,
- (unsigned long)req->iovs[i].iov.iov_base,
- req->iovs[i].iov.iov_len);
- if (!mnode || IS_ERR(mnode))
+ node = req->iovs[i].node;
+ if (!node)
continue;
- node = container_of(mnode, struct sdma_mmu_node, rb);
if (unpin)
hfi1_mmu_rb_remove(&req->pq->sdma_rb_root,
&node->rb);
diff --git a/drivers/staging/rdma/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h
index b9240e351161..b9240e351161 100644
--- a/drivers/staging/rdma/hfi1/user_sdma.h
+++ b/drivers/infiniband/hw/hfi1/user_sdma.h
diff --git a/drivers/staging/rdma/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 9cdc85fa366f..849c4b9399d4 100644
--- a/drivers/staging/rdma/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -52,7 +52,6 @@
#include <linux/utsname.h>
#include <linux/rculist.h>
#include <linux/mm.h>
-#include <linux/random.h>
#include <linux/vmalloc.h>
#include "hfi.h"
@@ -336,6 +335,8 @@ const u8 hdr_len_by_opcode[256] = {
[IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE] = 12 + 8 + 4,
[IB_OPCODE_RC_COMPARE_SWAP] = 12 + 8 + 28,
[IB_OPCODE_RC_FETCH_ADD] = 12 + 8 + 28,
+ [IB_OPCODE_RC_SEND_LAST_WITH_INVALIDATE] = 12 + 8 + 4,
+ [IB_OPCODE_RC_SEND_ONLY_WITH_INVALIDATE] = 12 + 8 + 4,
/* UC */
[IB_OPCODE_UC_SEND_FIRST] = 12 + 8,
[IB_OPCODE_UC_SEND_MIDDLE] = 12 + 8,
@@ -946,7 +947,6 @@ static int pio_wait(struct rvt_qp *qp,
dev->n_piowait += !!(flag & RVT_S_WAIT_PIO);
dev->n_piodrain += !!(flag & RVT_S_WAIT_PIO_DRAIN);
- dev->n_piowait++;
qp->s_flags |= flag;
was_empty = list_empty(&sc->piowait);
list_add_tail(&priv->s_iowait.list, &sc->piowait);
diff --git a/drivers/staging/rdma/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 3ee223983b20..488356775627 100644
--- a/drivers/staging/rdma/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -152,6 +152,7 @@ union ib_ehdrs {
} at;
__be32 imm_data;
__be32 aeth;
+ __be32 ieth;
struct ib_atomic_eth atomic_eth;
} __packed;
diff --git a/drivers/staging/rdma/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c
index bc95c4112c61..d8fb056526f8 100644
--- a/drivers/staging/rdma/hfi1/verbs_txreq.c
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
@@ -92,11 +92,10 @@ void hfi1_put_txreq(struct verbs_txreq *tx)
struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
struct rvt_qp *qp)
+ __must_hold(&qp->s_lock)
{
struct verbs_txreq *tx = ERR_PTR(-EBUSY);
- unsigned long flags;
- spin_lock_irqsave(&qp->s_lock, flags);
write_seqlock(&dev->iowait_lock);
if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
struct hfi1_qp_priv *priv;
@@ -116,7 +115,6 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
}
out:
write_sequnlock(&dev->iowait_lock);
- spin_unlock_irqrestore(&qp->s_lock, flags);
return tx;
}
diff --git a/drivers/staging/rdma/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index 1cf69b2fe4a5..a1d6e0807f97 100644
--- a/drivers/staging/rdma/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -73,6 +73,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
struct rvt_qp *qp)
+ __must_hold(&qp->slock)
{
struct verbs_txreq *tx;
struct hfi1_qp_priv *priv = qp->priv;
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index 8b9532034558..b738acdb9b02 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -113,6 +113,8 @@
#define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types)
#define IW_CFG_FPM_QP_COUNT 32768
+#define I40IW_MAX_PAGES_PER_FMR 512
+#define I40IW_MIN_PAGES_PER_FMR 1
#define I40IW_MTU_TO_MSS 40
#define I40IW_DEFAULT_MSS 1460
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 4a740f7a0519..33959ed14563 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -79,6 +79,7 @@ static int i40iw_query_device(struct ib_device *ibdev,
props->max_qp_init_rd_atom = props->max_qp_rd_atom;
props->atomic_cap = IB_ATOMIC_NONE;
props->max_map_per_fmr = 1;
+ props->max_fast_reg_page_list_len = I40IW_MAX_PAGES_PER_FMR;
return 0;
}
@@ -1527,7 +1528,7 @@ static struct ib_mr *i40iw_alloc_mr(struct ib_pd *pd,
mutex_lock(&iwdev->pbl_mutex);
status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt);
mutex_unlock(&iwdev->pbl_mutex);
- if (!status)
+ if (status)
goto err1;
if (palloc->level != I40IW_LEVEL_1)
@@ -2149,6 +2150,7 @@ static int i40iw_post_send(struct ib_qp *ibqp,
struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev;
struct i40iw_fast_reg_stag_info info;
+ memset(&info, 0, sizeof(info));
info.access_rights = I40IW_ACCESS_FLAGS_LOCALREAD;
info.access_rights |= i40iw_get_user_access(flags);
info.stag_key = reg_wr(ib_wr)->key & 0xff;
@@ -2158,10 +2160,14 @@ static int i40iw_post_send(struct ib_qp *ibqp,
info.addr_type = I40IW_ADDR_TYPE_VA_BASED;
info.va = (void *)(uintptr_t)iwmr->ibmr.iova;
info.total_len = iwmr->ibmr.length;
+ info.reg_addr_pa = *(u64 *)palloc->level1.addr;
info.first_pm_pbl_index = palloc->level1.idx;
info.local_fence = ib_wr->send_flags & IB_SEND_FENCE;
info.signaled = ib_wr->send_flags & IB_SEND_SIGNALED;
+ if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR)
+ info.chunk_size = 1;
+
if (page_shift == 21)
info.page_size = 1; /* 2M page */
@@ -2327,13 +2333,16 @@ static int i40iw_req_notify_cq(struct ib_cq *ibcq,
{
struct i40iw_cq *iwcq;
struct i40iw_cq_uk *ukcq;
- enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_SOLICITED;
+ unsigned long flags;
+ enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_EVENT;
iwcq = (struct i40iw_cq *)ibcq;
ukcq = &iwcq->sc_cq.cq_uk;
- if (notify_flags == IB_CQ_NEXT_COMP)
- cq_notify = IW_CQ_COMPL_EVENT;
+ if (notify_flags == IB_CQ_SOLICITED)
+ cq_notify = IW_CQ_COMPL_SOLICITED;
+ spin_lock_irqsave(&iwcq->lock, flags);
ukcq->ops.iw_cq_request_notification(ukcq, cq_notify);
+ spin_unlock_irqrestore(&iwcq->lock, flags);
return 0;
}
@@ -2361,58 +2370,130 @@ static int i40iw_port_immutable(struct ib_device *ibdev, u8 port_num,
return 0;
}
+static const char * const i40iw_hw_stat_names[] = {
+ // 32bit names
+ [I40IW_HW_STAT_INDEX_IP4RXDISCARD] = "ip4InDiscards",
+ [I40IW_HW_STAT_INDEX_IP4RXTRUNC] = "ip4InTruncatedPkts",
+ [I40IW_HW_STAT_INDEX_IP4TXNOROUTE] = "ip4OutNoRoutes",
+ [I40IW_HW_STAT_INDEX_IP6RXDISCARD] = "ip6InDiscards",
+ [I40IW_HW_STAT_INDEX_IP6RXTRUNC] = "ip6InTruncatedPkts",
+ [I40IW_HW_STAT_INDEX_IP6TXNOROUTE] = "ip6OutNoRoutes",
+ [I40IW_HW_STAT_INDEX_TCPRTXSEG] = "tcpRetransSegs",
+ [I40IW_HW_STAT_INDEX_TCPRXOPTERR] = "tcpInOptErrors",
+ [I40IW_HW_STAT_INDEX_TCPRXPROTOERR] = "tcpInProtoErrors",
+ // 64bit names
+ [I40IW_HW_STAT_INDEX_IP4RXOCTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4InOctets",
+ [I40IW_HW_STAT_INDEX_IP4RXPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4InPkts",
+ [I40IW_HW_STAT_INDEX_IP4RXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4InReasmRqd",
+ [I40IW_HW_STAT_INDEX_IP4RXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4InMcastPkts",
+ [I40IW_HW_STAT_INDEX_IP4TXOCTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4OutOctets",
+ [I40IW_HW_STAT_INDEX_IP4TXPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4OutPkts",
+ [I40IW_HW_STAT_INDEX_IP4TXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4OutSegRqd",
+ [I40IW_HW_STAT_INDEX_IP4TXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip4OutMcastPkts",
+ [I40IW_HW_STAT_INDEX_IP6RXOCTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6InOctets",
+ [I40IW_HW_STAT_INDEX_IP6RXPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6InPkts",
+ [I40IW_HW_STAT_INDEX_IP6RXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6InReasmRqd",
+ [I40IW_HW_STAT_INDEX_IP6RXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6InMcastPkts",
+ [I40IW_HW_STAT_INDEX_IP6TXOCTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6OutOctets",
+ [I40IW_HW_STAT_INDEX_IP6TXPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6OutPkts",
+ [I40IW_HW_STAT_INDEX_IP6TXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6OutSegRqd",
+ [I40IW_HW_STAT_INDEX_IP6TXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "ip6OutMcastPkts",
+ [I40IW_HW_STAT_INDEX_TCPRXSEGS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "tcpInSegs",
+ [I40IW_HW_STAT_INDEX_TCPTXSEG + I40IW_HW_STAT_INDEX_MAX_32] =
+ "tcpOutSegs",
+ [I40IW_HW_STAT_INDEX_RDMARXRDS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwInRdmaReads",
+ [I40IW_HW_STAT_INDEX_RDMARXSNDS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwInRdmaSends",
+ [I40IW_HW_STAT_INDEX_RDMARXWRS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwInRdmaWrites",
+ [I40IW_HW_STAT_INDEX_RDMATXRDS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwOutRdmaReads",
+ [I40IW_HW_STAT_INDEX_RDMATXSNDS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwOutRdmaSends",
+ [I40IW_HW_STAT_INDEX_RDMATXWRS + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwOutRdmaWrites",
+ [I40IW_HW_STAT_INDEX_RDMAVBND + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwRdmaBnd",
+ [I40IW_HW_STAT_INDEX_RDMAVINV + I40IW_HW_STAT_INDEX_MAX_32] =
+ "iwRdmaInv"
+};
+
/**
- * i40iw_get_protocol_stats - Populates the rdma_stats structure
- * @ibdev: ib dev struct
- * @stats: iw protocol stats struct
+ * i40iw_alloc_hw_stats - Allocate a hw stats structure
+ * @ibdev: device pointer from stack
+ * @port_num: port number
*/
-static int i40iw_get_protocol_stats(struct ib_device *ibdev,
- union rdma_protocol_stats *stats)
+static struct rdma_hw_stats *i40iw_alloc_hw_stats(struct ib_device *ibdev,
+ u8 port_num)
+{
+ struct i40iw_device *iwdev = to_iwdev(ibdev);
+ struct i40iw_sc_dev *dev = &iwdev->sc_dev;
+ int num_counters = I40IW_HW_STAT_INDEX_MAX_32 +
+ I40IW_HW_STAT_INDEX_MAX_64;
+ unsigned long lifespan = RDMA_HW_STATS_DEFAULT_LIFESPAN;
+
+ BUILD_BUG_ON(ARRAY_SIZE(i40iw_hw_stat_names) !=
+ (I40IW_HW_STAT_INDEX_MAX_32 +
+ I40IW_HW_STAT_INDEX_MAX_64));
+
+ /*
+ * PFs get the default update lifespan, but VFs only update once
+ * per second
+ */
+ if (!dev->is_pf)
+ lifespan = 1000;
+ return rdma_alloc_hw_stats_struct(i40iw_hw_stat_names, num_counters,
+ lifespan);
+}
+
+/**
+ * i40iw_get_hw_stats - Populates the rdma_hw_stats structure
+ * @ibdev: device pointer from stack
+ * @stats: stats pointer from stack
+ * @port_num: port number
+ * @index: which hw counter the stack is requesting we update
+ */
+static int i40iw_get_hw_stats(struct ib_device *ibdev,
+ struct rdma_hw_stats *stats,
+ u8 port_num, int index)
{
struct i40iw_device *iwdev = to_iwdev(ibdev);
struct i40iw_sc_dev *dev = &iwdev->sc_dev;
struct i40iw_dev_pestat *devstat = &dev->dev_pestat;
struct i40iw_dev_hw_stats *hw_stats = &devstat->hw_stats;
- struct timespec curr_time;
- static struct timespec last_rd_time = {0, 0};
unsigned long flags;
- curr_time = current_kernel_time();
- memset(stats, 0, sizeof(*stats));
-
if (dev->is_pf) {
spin_lock_irqsave(&devstat->stats_lock, flags);
devstat->ops.iw_hw_stat_read_all(devstat,
&devstat->hw_stats);
spin_unlock_irqrestore(&devstat->stats_lock, flags);
} else {
- if (((u64)curr_time.tv_sec - (u64)last_rd_time.tv_sec) > 1)
- if (i40iw_vchnl_vf_get_pe_stats(dev, &devstat->hw_stats))
- return -ENOSYS;
+ if (i40iw_vchnl_vf_get_pe_stats(dev, &devstat->hw_stats))
+ return -ENOSYS;
}
- stats->iw.ipInReceives = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4RXPKTS] +
- hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6RXPKTS];
- stats->iw.ipInTruncatedPkts = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP4RXTRUNC] +
- hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP6RXTRUNC];
- stats->iw.ipInDiscards = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP4RXDISCARD] +
- hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP6RXDISCARD];
- stats->iw.ipOutNoRoutes = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP4TXNOROUTE] +
- hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP6TXNOROUTE];
- stats->iw.ipReasmReqds = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4RXFRAGS] +
- hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6RXFRAGS];
- stats->iw.ipFragCreates = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4TXFRAGS] +
- hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6TXFRAGS];
- stats->iw.ipInMcastPkts = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4RXMCPKTS] +
- hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6RXMCPKTS];
- stats->iw.ipOutMcastPkts = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4TXMCPKTS] +
- hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6TXMCPKTS];
- stats->iw.tcpOutSegs = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_TCPTXSEG];
- stats->iw.tcpInSegs = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_TCPRXSEGS];
- stats->iw.tcpRetransSegs = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_TCPRTXSEG];
-
- last_rd_time = curr_time;
- return 0;
+ memcpy(&stats->value[0], &hw_stats, sizeof(*hw_stats));
+
+ return stats->num_counters;
}
/**
@@ -2551,7 +2632,8 @@ static struct i40iw_ib_device *i40iw_init_rdma_device(struct i40iw_device *iwdev
iwibdev->ibdev.get_dma_mr = i40iw_get_dma_mr;
iwibdev->ibdev.reg_user_mr = i40iw_reg_user_mr;
iwibdev->ibdev.dereg_mr = i40iw_dereg_mr;
- iwibdev->ibdev.get_protocol_stats = i40iw_get_protocol_stats;
+ iwibdev->ibdev.alloc_hw_stats = i40iw_alloc_hw_stats;
+ iwibdev->ibdev.get_hw_stats = i40iw_get_hw_stats;
iwibdev->ibdev.query_device = i40iw_query_device;
iwibdev->ibdev.create_ah = i40iw_create_ah;
iwibdev->ibdev.destroy_ah = i40iw_destroy_ah;
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 105246fba2e7..5fc623362731 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
ah->av.ib.g_slid = ah_attr->src_path_bits;
+ ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
if (ah_attr->ah_flags & IB_AH_GRH) {
ah->av.ib.g_slid |= 0x80;
ah->av.ib.gid_index = ah_attr->grh.sgid_index;
@@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
!(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
--ah->av.ib.stat_rate;
}
- ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
return &ah->ibah;
}
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index d68f506c1922..9c2e53d28f98 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -527,7 +527,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
spin_unlock(&tun_qp->tx_lock);
if (ret)
- goto out;
+ goto end;
tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr);
if (tun_qp->tx_ring[tun_tx_ix].ah)
@@ -596,9 +596,15 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
wr.wr.send_flags = IB_SEND_SIGNALED;
ret = ib_post_send(src_qp, &wr.wr, &bad_wr);
-out:
- if (ret)
- ib_destroy_ah(ah);
+ if (!ret)
+ return 0;
+ out:
+ spin_lock(&tun_qp->tx_lock);
+ tun_qp->tx_ix_tail++;
+ spin_unlock(&tun_qp->tx_lock);
+ tun_qp->tx_ring[tun_tx_ix].ah = NULL;
+end:
+ ib_destroy_ah(ah);
return ret;
}
@@ -1326,9 +1332,15 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
ret = ib_post_send(send_qp, &wr.wr, &bad_wr);
+ if (!ret)
+ return 0;
+
+ spin_lock(&sqp->tx_lock);
+ sqp->tx_ix_tail++;
+ spin_unlock(&sqp->tx_lock);
+ sqp->tx_ring[wire_tx_ix].ah = NULL;
out:
- if (ret)
- ib_destroy_ah(ah);
+ ib_destroy_ah(ah);
return ret;
}
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b01ef6eee6e8..42a46078d7d5 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
else
props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
- if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
- props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
}
+ if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
+ props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
@@ -1704,6 +1704,9 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
int is_bonded = mlx4_is_bonded(dev);
+ if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
+ return ERR_PTR(-EINVAL);
+
if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
(flow_attr->type != IB_FLOW_ATTR_NORMAL))
return ERR_PTR(-EOPNOTSUPP);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6c5ac5d8f32f..29acda249612 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -139,7 +139,7 @@ struct mlx4_ib_mr {
u32 max_pages;
struct mlx4_mr mmr;
struct ib_umem *umem;
- void *pages_alloc;
+ size_t page_map_size;
};
struct mlx4_ib_mw {
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 631272172a0b..5d73989d9771 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -277,20 +277,23 @@ mlx4_alloc_priv_pages(struct ib_device *device,
struct mlx4_ib_mr *mr,
int max_pages)
{
- int size = max_pages * sizeof(u64);
- int add_size;
int ret;
- add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0);
+ /* Ensure that size is aligned to DMA cacheline
+ * requirements.
+ * max_pages is limited to MLX4_MAX_FAST_REG_PAGES
+ * so page_map_size will never cross PAGE_SIZE.
+ */
+ mr->page_map_size = roundup(max_pages * sizeof(u64),
+ MLX4_MR_PAGES_ALIGN);
- mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL);
- if (!mr->pages_alloc)
+ /* Prevent cross page boundary allocation. */
+ mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL);
+ if (!mr->pages)
return -ENOMEM;
- mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN);
-
mr->page_map = dma_map_single(device->dma_device, mr->pages,
- size, DMA_TO_DEVICE);
+ mr->page_map_size, DMA_TO_DEVICE);
if (dma_mapping_error(device->dma_device, mr->page_map)) {
ret = -ENOMEM;
@@ -298,9 +301,9 @@ mlx4_alloc_priv_pages(struct ib_device *device,
}
return 0;
-err:
- kfree(mr->pages_alloc);
+err:
+ free_page((unsigned long)mr->pages);
return ret;
}
@@ -309,11 +312,10 @@ mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
{
if (mr->pages) {
struct ib_device *device = mr->ibmr.device;
- int size = mr->max_pages * sizeof(u64);
dma_unmap_single(device->dma_device, mr->page_map,
- size, DMA_TO_DEVICE);
- kfree(mr->pages_alloc);
+ mr->page_map_size, DMA_TO_DEVICE);
+ free_page((unsigned long)mr->pages);
mr->pages = NULL;
}
}
@@ -537,14 +539,12 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
mr->npages = 0;
ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
- sizeof(u64) * mr->max_pages,
- DMA_TO_DEVICE);
+ mr->page_map_size, DMA_TO_DEVICE);
rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page);
ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
- sizeof(u64) * mr->max_pages,
- DMA_TO_DEVICE);
+ mr->page_map_size, DMA_TO_DEVICE);
return rc;
}
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 81b0e1fbec1d..8db8405c1e99 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -362,7 +362,7 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
sizeof (struct mlx4_wqe_raddr_seg);
case MLX4_IB_QPT_RC:
return sizeof (struct mlx4_wqe_ctrl_seg) +
- sizeof (struct mlx4_wqe_atomic_seg) +
+ sizeof (struct mlx4_wqe_masked_atomic_seg) +
sizeof (struct mlx4_wqe_raddr_seg);
case MLX4_IB_QPT_SMI:
case MLX4_IB_QPT_GSI:
@@ -1191,8 +1191,10 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
{
err = create_qp_common(to_mdev(pd->device), pd, init_attr,
udata, 0, &qp, gfp);
- if (err)
+ if (err) {
+ kfree(qp);
return ERR_PTR(err);
+ }
qp->ibqp.qp_num = qp->mqp.qpn;
qp->xrcdn = xrcdn;
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index dabcc65bd65e..9c0e67bd2ba7 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -822,7 +822,8 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
int eqn;
int err;
- if (entries < 0)
+ if (entries < 0 ||
+ (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))))
return ERR_PTR(-EINVAL);
if (check_cq_create_flags(attr->flags))
@@ -1168,11 +1169,16 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
return -ENOSYS;
}
- if (entries < 1)
+ if (entries < 1 ||
+ entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) {
+ mlx5_ib_warn(dev, "wrong entries number %d, max %d\n",
+ entries,
+ 1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz));
return -EINVAL;
+ }
entries = roundup_pow_of_two(entries + 1);
- if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
+ if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
return -EINVAL;
if (entries == ibcq->cqe + 1)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 1534af113058..364aab9f3c9e 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -121,7 +121,7 @@ static void pma_cnt_ext_assign(struct ib_pma_portcounters_ext *pma_cnt_ext,
pma_cnt_ext->port_xmit_data =
cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets,
transmitted_ib_multicast.octets) >> 2);
- pma_cnt_ext->port_xmit_data =
+ pma_cnt_ext->port_rcv_data =
cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets,
received_ib_multicast.octets) >> 2);
pma_cnt_ext->port_xmit_packets =
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c72797cd9e4f..b48ad85315dc 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -524,6 +524,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
MLX5_CAP_ETH(dev->mdev, scatter_fcs))
props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS;
+ if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
+ props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
+
props->vendor_part_id = mdev->pdev->device;
props->hw_ver = mdev->pdev->revision;
@@ -915,7 +918,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
- resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
+ if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
+ resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
resp.cache_line_size = L1_CACHE_BYTES;
resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
@@ -988,7 +992,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
if (field_avail(typeof(resp), cqe_version, udata->outlen))
resp.response_length += sizeof(resp.cqe_version);
- if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+ /*
+ * We don't want to expose information from the PCI bar that is located
+ * after 4096 bytes, so if the arch only supports larger pages, let's
+ * pretend we don't support reading the HCA's core clock. This is also
+ * forced by mmap function.
+ */
+ if (PAGE_SIZE <= 4096 &&
+ field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
resp.comp_mask |=
MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
resp.hca_core_clock_offset =
@@ -1798,7 +1809,7 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
{
struct mlx5_ib_dev *dev =
container_of(device, struct mlx5_ib_dev, ib_dev.dev);
- return sprintf(buf, "%d.%d.%d\n", fw_rev_maj(dev->mdev),
+ return sprintf(buf, "%d.%d.%04d\n", fw_rev_maj(dev->mdev),
fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
}
@@ -1866,14 +1877,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
break;
case MLX5_DEV_EVENT_PORT_DOWN:
+ case MLX5_DEV_EVENT_PORT_INITIALIZED:
ibev.event = IB_EVENT_PORT_ERR;
port = (u8)param;
break;
- case MLX5_DEV_EVENT_PORT_INITIALIZED:
- /* not used by ULPs */
- return;
-
case MLX5_DEV_EVENT_LID_CHANGE:
ibev.event = IB_EVENT_LID_CHANGE;
port = (u8)param;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 504117657d41..ce0a7ab35a22 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -235,6 +235,8 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
qp->rq.max_gs = 0;
qp->rq.wqe_cnt = 0;
qp->rq.wqe_shift = 0;
+ cap->max_recv_wr = 0;
+ cap->max_recv_sge = 0;
} else {
if (ucmd) {
qp->rq.wqe_cnt = ucmd->rq_wqe_count;
@@ -1851,13 +1853,15 @@ static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
const struct ib_ah_attr *ah,
struct mlx5_qp_path *path, u8 port, int attr_mask,
- u32 path_flags, const struct ib_qp_attr *attr)
+ u32 path_flags, const struct ib_qp_attr *attr,
+ bool alt)
{
enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port);
int err;
if (attr_mask & IB_QP_PKEY_INDEX)
- path->pkey_index = attr->pkey_index;
+ path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index :
+ attr->pkey_index);
if (ah->ah_flags & IB_AH_GRH) {
if (ah->grh.sgid_index >=
@@ -1877,9 +1881,9 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
ah->grh.sgid_index);
path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4;
} else {
- path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
- path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 :
- 0;
+ path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
+ path->fl_free_ar |=
+ (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x40 : 0;
path->rlid = cpu_to_be16(ah->dlid);
path->grh_mlid = ah->src_path_bits & 0x7f;
if (ah->ah_flags & IB_AH_GRH)
@@ -1903,7 +1907,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
path->port = port;
if (attr_mask & IB_QP_TIMEOUT)
- path->ackto_lt = attr->timeout << 3;
+ path->ackto_lt = (alt ? attr->alt_timeout : attr->timeout) << 3;
if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt)
return modify_raw_packet_eth_prio(dev->mdev,
@@ -2264,7 +2268,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
context->log_pg_sz_remote_qpn = cpu_to_be32(attr->dest_qp_num);
if (attr_mask & IB_QP_PKEY_INDEX)
- context->pri_path.pkey_index = attr->pkey_index;
+ context->pri_path.pkey_index = cpu_to_be16(attr->pkey_index);
/* todo implement counter_index functionality */
@@ -2277,7 +2281,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
if (attr_mask & IB_QP_AV) {
err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path,
attr_mask & IB_QP_PORT ? attr->port_num : qp->port,
- attr_mask, 0, attr);
+ attr_mask, 0, attr, false);
if (err)
goto out;
}
@@ -2288,7 +2292,9 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
if (attr_mask & IB_QP_ALT_PATH) {
err = mlx5_set_path(dev, qp, &attr->alt_ah_attr,
&context->alt_path,
- attr->alt_port_num, attr_mask, 0, attr);
+ attr->alt_port_num,
+ attr_mask | IB_QP_PKEY_INDEX | IB_QP_TIMEOUT,
+ 0, attr, true);
if (err)
goto out;
}
@@ -3326,10 +3332,11 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr)
return MLX5_FENCE_MODE_SMALL_AND_FENCE;
else
return fence;
-
- } else {
- return 0;
+ } else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
+ return MLX5_FENCE_MODE_FENCE;
}
+
+ return 0;
}
static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
@@ -4013,11 +4020,12 @@ static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) {
to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path);
to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path);
- qp_attr->alt_pkey_index = context->alt_path.pkey_index & 0x7f;
+ qp_attr->alt_pkey_index =
+ be16_to_cpu(context->alt_path.pkey_index);
qp_attr->alt_port_num = qp_attr->alt_ah_attr.port_num;
}
- qp_attr->pkey_index = context->pri_path.pkey_index & 0x7f;
+ qp_attr->pkey_index = be16_to_cpu(context->pri_path.pkey_index);
qp_attr->port_num = context->pri_path.port;
/* qp_attr->en_sqd_async_notify is only applicable in modify qp */
@@ -4079,17 +4087,19 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
qp_attr->cap.max_recv_sge = qp->rq.max_gs;
if (!ibqp->uobject) {
- qp_attr->cap.max_send_wr = qp->sq.wqe_cnt;
+ qp_attr->cap.max_send_wr = qp->sq.max_post;
qp_attr->cap.max_send_sge = qp->sq.max_gs;
+ qp_init_attr->qp_context = ibqp->qp_context;
} else {
qp_attr->cap.max_send_wr = 0;
qp_attr->cap.max_send_sge = 0;
}
- /* We don't support inline sends for kernel QPs (yet), and we
- * don't know what userspace's value should be.
- */
- qp_attr->cap.max_inline_data = 0;
+ qp_init_attr->qp_type = ibqp->qp_type;
+ qp_init_attr->recv_cq = ibqp->recv_cq;
+ qp_init_attr->send_cq = ibqp->send_cq;
+ qp_init_attr->srq = ibqp->srq;
+ qp_attr->cap.max_inline_data = qp->max_inline_data;
qp_init_attr->cap = qp_attr->cap;
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index ff946d5f59e4..382466a90da7 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -2178,6 +2178,11 @@ static ssize_t qib_write(struct file *fp, const char __user *data,
switch (cmd.type) {
case QIB_CMD_ASSIGN_CTXT:
+ if (rcd) {
+ ret = -EINVAL;
+ goto bail;
+ }
+
ret = qib_assign_ctxt(fp, &cmd.cmd.user_info);
if (ret)
goto bail;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 82d7c4bf5970..ce4034071f9c 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -1308,21 +1308,6 @@ static const struct qib_hwerror_msgs qib_7322p_error_msgs[] = {
SYM_LSB(IntMask, fldname##17IntMask)), \
.msg = #fldname "_C", .sz = sizeof(#fldname "_C") }
-static const struct qib_hwerror_msgs qib_7322_intr_msgs[] = {
- INTR_AUTO_P(SDmaInt),
- INTR_AUTO_P(SDmaProgressInt),
- INTR_AUTO_P(SDmaIdleInt),
- INTR_AUTO_P(SDmaCleanupDone),
- INTR_AUTO_C(RcvUrg),
- INTR_AUTO_P(ErrInt),
- INTR_AUTO(ErrInt), /* non-port-specific errs */
- INTR_AUTO(AssertGPIOInt),
- INTR_AUTO_P(SendDoneInt),
- INTR_AUTO(SendBufAvailInt),
- INTR_AUTO_C(RcvAvail),
- { .mask = 0, .sz = 0 }
-};
-
#define TXSYMPTOM_AUTO_P(fldname) \
{ .mask = SYM_MASK(SendHdrErrSymptom_0, fldname), \
.msg = #fldname, .sz = sizeof(#fldname) }
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index 0bd18375d7df..d2ac29861af5 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1172,11 +1172,13 @@ static int pma_get_classportinfo(struct ib_pma_mad *pmp,
* Set the most significant bit of CM2 to indicate support for
* congestion statistics
*/
- p->reserved[0] = dd->psxmitwait_supported << 7;
+ ib_set_cpi_capmask2(p,
+ dd->psxmitwait_supported <<
+ (31 - IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE));
/*
* Expected response time is 4.096 usec. * 2^18 == 1.073741824 sec.
*/
- p->resp_time_value = 18;
+ ib_set_cpi_resp_time(p, 18);
return reply((struct ib_smp *) pmp);
}
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index 6888f03c6d61..4f878151f81f 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -159,6 +159,7 @@ struct qib_other_headers {
} at;
__be32 imm_data;
__be32 aeth;
+ __be32 ieth;
struct ib_atomic_eth atomic_eth;
} u;
} __packed;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 7209fbc03ccb..a0b6ebee4d8a 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -36,7 +36,6 @@
#include <linux/dma-mapping.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>
-#include <linux/dma-attrs.h>
#include <linux/iommu.h>
#include <linux/workqueue.h>
#include <linux/list.h>
@@ -112,10 +111,6 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
int i;
int flags;
dma_addr_t pa;
- DEFINE_DMA_ATTRS(attrs);
-
- if (dmasync)
- dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
if (!can_do_mlock())
return -EPERM;
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index b1ffc8b4a6c0..6ca6fa80dd6e 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -525,6 +525,7 @@ int rvt_driver_cq_init(struct rvt_dev_info *rdi)
return PTR_ERR(task);
}
+ set_user_nice(task, MIN_NICE);
cpu = cpumask_first(cpumask_of_node(rdi->dparms.node));
kthread_bind(task, cpu);
wake_up_process(task);
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 0ff765bfd619..0f4d4500f45e 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -124,11 +124,13 @@ static int rvt_init_mregion(struct rvt_mregion *mr, struct ib_pd *pd,
int count)
{
int m, i = 0;
+ struct rvt_dev_info *dev = ib_to_rvt(pd->device);
mr->mapsz = 0;
m = (count + RVT_SEGSZ - 1) / RVT_SEGSZ;
for (; i < m; i++) {
- mr->map[i] = kzalloc(sizeof(*mr->map[0]), GFP_KERNEL);
+ mr->map[i] = kzalloc_node(sizeof(*mr->map[0]), GFP_KERNEL,
+ dev->dparms.node);
if (!mr->map[i]) {
rvt_deinit_mregion(mr);
return -ENOMEM;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 0f12c211c385..41ba7e9cadaa 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -369,8 +369,8 @@ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
/* wrap to first map page, invert bit 0 */
offset = qpt->incr | ((offset & 1) ^ 1);
}
- /* there can be no bits at shift and below */
- WARN_ON(offset & (rdi->dparms.qos_shift - 1));
+ /* there can be no set bits in low-order QoS bits */
+ WARN_ON(offset & (BIT(rdi->dparms.qos_shift) - 1));
qpn = mk_qpn(qpt, map, offset);
}
@@ -397,6 +397,7 @@ static void free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
static void rvt_clear_mr_refs(struct rvt_qp *qp, int clr_sends)
{
unsigned n;
+ struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags))
rvt_put_ss(&qp->s_rdma_read_sge);
@@ -431,7 +432,7 @@ static void rvt_clear_mr_refs(struct rvt_qp *qp, int clr_sends)
if (qp->ibqp.qp_type != IB_QPT_RC)
return;
- for (n = 0; n < ARRAY_SIZE(qp->s_ack_queue); n++) {
+ for (n = 0; n < rvt_max_atomic(rdi); n++) {
struct rvt_ack_entry *e = &qp->s_ack_queue[n];
if (e->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST &&
@@ -501,6 +502,12 @@ static void rvt_remove_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp)
*/
static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
enum ib_qp_type type)
+ __releases(&qp->s_lock)
+ __releases(&qp->s_hlock)
+ __releases(&qp->r_lock)
+ __acquires(&qp->r_lock)
+ __acquires(&qp->s_hlock)
+ __acquires(&qp->s_lock)
{
if (qp->state != IB_QPS_RESET) {
qp->state = IB_QPS_RESET;
@@ -569,7 +576,6 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
qp->s_ssn = 1;
qp->s_lsn = 0;
qp->s_mig_state = IB_MIG_MIGRATED;
- memset(qp->s_ack_queue, 0, sizeof(qp->s_ack_queue));
qp->r_head_ack_queue = 0;
qp->s_tail_ack_queue = 0;
qp->s_num_rd_atomic = 0;
@@ -653,9 +659,9 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
if (gfp == GFP_NOIO)
swq = __vmalloc(
(init_attr->cap.max_send_wr + 1) * sz,
- gfp, PAGE_KERNEL);
+ gfp | __GFP_ZERO, PAGE_KERNEL);
else
- swq = vmalloc_node(
+ swq = vzalloc_node(
(init_attr->cap.max_send_wr + 1) * sz,
rdi->dparms.node);
if (!swq)
@@ -677,14 +683,26 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
goto bail_swq;
RCU_INIT_POINTER(qp->next, NULL);
+ if (init_attr->qp_type == IB_QPT_RC) {
+ qp->s_ack_queue =
+ kzalloc_node(
+ sizeof(*qp->s_ack_queue) *
+ rvt_max_atomic(rdi),
+ gfp,
+ rdi->dparms.node);
+ if (!qp->s_ack_queue)
+ goto bail_qp;
+ }
/*
* Driver needs to set up it's private QP structure and do any
* initialization that is needed.
*/
priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp);
- if (!priv)
+ if (IS_ERR(priv)) {
+ ret = priv;
goto bail_qp;
+ }
qp->priv = priv;
qp->timeout_jiffies =
usecs_to_jiffies((4096UL * (1UL << qp->timeout)) /
@@ -704,9 +722,9 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
qp->r_rq.wq = __vmalloc(
sizeof(struct rvt_rwq) +
qp->r_rq.size * sz,
- gfp, PAGE_KERNEL);
+ gfp | __GFP_ZERO, PAGE_KERNEL);
else
- qp->r_rq.wq = vmalloc_node(
+ qp->r_rq.wq = vzalloc_node(
sizeof(struct rvt_rwq) +
qp->r_rq.size * sz,
rdi->dparms.node);
@@ -857,6 +875,7 @@ bail_driver_priv:
rdi->driver_f.qp_priv_free(rdi, qp);
bail_qp:
+ kfree(qp->s_ack_queue);
kfree(qp);
bail_swq:
@@ -1284,6 +1303,7 @@ int rvt_destroy_qp(struct ib_qp *ibqp)
vfree(qp->r_rq.wq);
vfree(qp->s_wq);
rdi->driver_f.qp_priv_free(rdi, qp);
+ kfree(qp->s_ack_queue);
kfree(qp);
return 0;
}
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index e1cc2cc42f25..30c4fda7a05a 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -501,9 +501,7 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb)
!rdi->driver_f.quiesce_qp ||
!rdi->driver_f.notify_error_qp ||
!rdi->driver_f.mtu_from_qp ||
- !rdi->driver_f.mtu_to_path_mtu ||
- !rdi->driver_f.shut_down_port ||
- !rdi->driver_f.cap_mask_chg)
+ !rdi->driver_f.mtu_to_path_mtu)
return -EINVAL;
break;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index caec8e9c4666..4f7d9b48df64 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -92,6 +92,9 @@ enum {
IPOIB_FLAG_UMCAST = 10,
IPOIB_STOP_NEIGH_GC = 11,
IPOIB_NEIGH_TBL_FLUSH = 12,
+ IPOIB_FLAG_DEV_ADDR_SET = 13,
+ IPOIB_FLAG_DEV_ADDR_CTRL = 14,
+ IPOIB_FLAG_GOING_DOWN = 15,
IPOIB_MAX_BACKOFF_SECONDS = 16,
@@ -392,6 +395,7 @@ struct ipoib_dev_priv {
struct ipoib_ethtool_st ethtool;
struct timer_list poll_timer;
unsigned max_send_sge;
+ bool sm_fullmember_sendonly_support;
};
struct ipoib_ah {
@@ -476,6 +480,7 @@ void ipoib_reap_ah(struct work_struct *work);
void ipoib_mark_paths_invalid(struct net_device *dev);
void ipoib_flush_paths(struct net_device *dev);
+int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv);
struct ipoib_dev_priv *ipoib_intf_alloc(const char *format);
int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index b2f42835d76d..951d9abcca8b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1486,6 +1486,10 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
{
struct net_device *dev = to_net_dev(d);
int ret;
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+ if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags))
+ return -EPERM;
if (!rtnl_trylock())
return restart_syscall();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 418e5a1c8744..dc6d241b9406 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -997,6 +997,106 @@ static inline int update_child_pkey(struct ipoib_dev_priv *priv)
return 0;
}
+/*
+ * returns true if the device address of the ipoib interface has changed and the
+ * new address is a valid one (i.e in the gid table), return false otherwise.
+ */
+static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
+{
+ union ib_gid search_gid;
+ union ib_gid gid0;
+ union ib_gid *netdev_gid;
+ int err;
+ u16 index;
+ u8 port;
+ bool ret = false;
+
+ netdev_gid = (union ib_gid *)(priv->dev->dev_addr + 4);
+ if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL))
+ return false;
+
+ netif_addr_lock_bh(priv->dev);
+
+ /* The subnet prefix may have changed, update it now so we won't have
+ * to do it later
+ */
+ priv->local_gid.global.subnet_prefix = gid0.global.subnet_prefix;
+ netdev_gid->global.subnet_prefix = gid0.global.subnet_prefix;
+ search_gid.global.subnet_prefix = gid0.global.subnet_prefix;
+
+ search_gid.global.interface_id = priv->local_gid.global.interface_id;
+
+ netif_addr_unlock_bh(priv->dev);
+
+ err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB,
+ priv->dev, &port, &index);
+
+ netif_addr_lock_bh(priv->dev);
+
+ if (search_gid.global.interface_id !=
+ priv->local_gid.global.interface_id)
+ /* There was a change while we were looking up the gid, bail
+ * here and let the next work sort this out
+ */
+ goto out;
+
+ /* The next section of code needs some background:
+ * Per IB spec the port GUID can't change if the HCA is powered on.
+ * port GUID is the basis for GID at index 0 which is the basis for
+ * the default device address of a ipoib interface.
+ *
+ * so it seems the flow should be:
+ * if user_changed_dev_addr && gid in gid tbl
+ * set bit dev_addr_set
+ * return true
+ * else
+ * return false
+ *
+ * The issue is that there are devices that don't follow the spec,
+ * they change the port GUID when the HCA is powered, so in order
+ * not to break userspace applications, We need to check if the
+ * user wanted to control the device address and we assume that
+ * if he sets the device address back to be based on GID index 0,
+ * he no longer wishs to control it.
+ *
+ * If the user doesn't control the the device address,
+ * IPOIB_FLAG_DEV_ADDR_SET is set and ib_find_gid failed it means
+ * the port GUID has changed and GID at index 0 has changed
+ * so we need to change priv->local_gid and priv->dev->dev_addr
+ * to reflect the new GID.
+ */
+ if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
+ if (!err && port == priv->port) {
+ set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
+ if (index == 0)
+ clear_bit(IPOIB_FLAG_DEV_ADDR_CTRL,
+ &priv->flags);
+ else
+ set_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags);
+ ret = true;
+ } else {
+ ret = false;
+ }
+ } else {
+ if (!err && port == priv->port) {
+ ret = true;
+ } else {
+ if (!test_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags)) {
+ memcpy(&priv->local_gid, &gid0,
+ sizeof(priv->local_gid));
+ memcpy(priv->dev->dev_addr + 4, &gid0,
+ sizeof(priv->local_gid));
+ ret = true;
+ }
+ }
+ }
+
+out:
+ netif_addr_unlock_bh(priv->dev);
+
+ return ret;
+}
+
static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
enum ipoib_flush_level level,
int nesting)
@@ -1018,6 +1118,9 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) &&
level != IPOIB_FLUSH_HEAVY) {
+ /* Make sure the dev_addr is set even if not flushing */
+ if (level == IPOIB_FLUSH_LIGHT)
+ ipoib_dev_addr_changed_valid(priv);
ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
return;
}
@@ -1029,7 +1132,8 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
update_parent_pkey(priv);
else
update_child_pkey(priv);
- }
+ } else if (level == IPOIB_FLUSH_LIGHT)
+ ipoib_dev_addr_changed_valid(priv);
ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n");
return;
}
@@ -1081,7 +1185,8 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
if (level >= IPOIB_FLUSH_NORMAL)
ipoib_ib_dev_up(dev);
- ipoib_mcast_restart_task(&priv->restart_task);
+ if (ipoib_dev_addr_changed_valid(priv))
+ ipoib_mcast_restart_task(&priv->restart_task);
}
}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index b940ef1c19c7..5f58c41ef787 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -99,6 +99,7 @@ static struct net_device *ipoib_get_net_dev_by_params(
struct ib_device *dev, u8 port, u16 pkey,
const union ib_gid *gid, const struct sockaddr *addr,
void *client_data);
+static int ipoib_set_mac(struct net_device *dev, void *addr);
static struct ib_client ipoib_client = {
.name = "ipoib",
@@ -117,6 +118,8 @@ int ipoib_open(struct net_device *dev)
set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
+ priv->sm_fullmember_sendonly_support = false;
+
if (ipoib_ib_dev_open(dev)) {
if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
return 0;
@@ -629,6 +632,77 @@ void ipoib_mark_paths_invalid(struct net_device *dev)
spin_unlock_irq(&priv->lock);
}
+struct classport_info_context {
+ struct ipoib_dev_priv *priv;
+ struct completion done;
+ struct ib_sa_query *sa_query;
+};
+
+static void classport_info_query_cb(int status, struct ib_class_port_info *rec,
+ void *context)
+{
+ struct classport_info_context *cb_ctx = context;
+ struct ipoib_dev_priv *priv;
+
+ WARN_ON(!context);
+
+ priv = cb_ctx->priv;
+
+ if (status || !rec) {
+ pr_debug("device: %s failed query classport_info status: %d\n",
+ priv->dev->name, status);
+ /* keeps the default, will try next mcast_restart */
+ priv->sm_fullmember_sendonly_support = false;
+ goto out;
+ }
+
+ if (ib_get_cpi_capmask2(rec) &
+ IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT) {
+ pr_debug("device: %s enabled fullmember-sendonly for sendonly MCG\n",
+ priv->dev->name);
+ priv->sm_fullmember_sendonly_support = true;
+ } else {
+ pr_debug("device: %s disabled fullmember-sendonly for sendonly MCG\n",
+ priv->dev->name);
+ priv->sm_fullmember_sendonly_support = false;
+ }
+
+out:
+ complete(&cb_ctx->done);
+}
+
+int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv)
+{
+ struct classport_info_context *callback_context;
+ int ret;
+
+ callback_context = kmalloc(sizeof(*callback_context), GFP_KERNEL);
+ if (!callback_context)
+ return -ENOMEM;
+
+ callback_context->priv = priv;
+ init_completion(&callback_context->done);
+
+ ret = ib_sa_classport_info_rec_query(&ipoib_sa_client,
+ priv->ca, priv->port, 3000,
+ GFP_KERNEL,
+ classport_info_query_cb,
+ callback_context,
+ &callback_context->sa_query);
+ if (ret < 0) {
+ pr_info("%s failed to send ib_sa_classport_info query, ret: %d\n",
+ priv->dev->name, ret);
+ kfree(callback_context);
+ return ret;
+ }
+
+ /* waiting for the callback to finish before returnning */
+ wait_for_completion(&callback_context->done);
+ kfree(callback_context);
+
+ return ret;
+}
+
void ipoib_flush_paths(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -1132,7 +1206,9 @@ struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr)
neigh = NULL;
goto out_unlock;
}
- neigh->alive = jiffies;
+
+ if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE))
+ neigh->alive = jiffies;
goto out_unlock;
}
}
@@ -1649,6 +1725,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = {
.ndo_get_vf_config = ipoib_get_vf_config,
.ndo_get_vf_stats = ipoib_get_vf_stats,
.ndo_set_vf_guid = ipoib_set_vf_guid,
+ .ndo_set_mac_address = ipoib_set_mac,
};
static const struct net_device_ops ipoib_netdev_ops_vf = {
@@ -1771,6 +1848,70 @@ int ipoib_add_umcast_attr(struct net_device *dev)
return device_create_file(&dev->dev, &dev_attr_umcast);
}
+static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid)
+{
+ struct ipoib_dev_priv *child_priv;
+ struct net_device *netdev = priv->dev;
+
+ netif_addr_lock_bh(netdev);
+
+ memcpy(&priv->local_gid.global.interface_id,
+ &gid->global.interface_id,
+ sizeof(gid->global.interface_id));
+ memcpy(netdev->dev_addr + 4, &priv->local_gid, sizeof(priv->local_gid));
+ clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
+
+ netif_addr_unlock_bh(netdev);
+
+ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+ down_read(&priv->vlan_rwsem);
+ list_for_each_entry(child_priv, &priv->child_intfs, list)
+ set_base_guid(child_priv, gid);
+ up_read(&priv->vlan_rwsem);
+ }
+}
+
+static int ipoib_check_lladdr(struct net_device *dev,
+ struct sockaddr_storage *ss)
+{
+ union ib_gid *gid = (union ib_gid *)(ss->__data + 4);
+ int ret = 0;
+
+ netif_addr_lock_bh(dev);
+
+ /* Make sure the QPN, reserved and subnet prefix match the current
+ * lladdr, it also makes sure the lladdr is unicast.
+ */
+ if (memcmp(dev->dev_addr, ss->__data,
+ 4 + sizeof(gid->global.subnet_prefix)) ||
+ gid->global.interface_id == 0)
+ ret = -EINVAL;
+
+ netif_addr_unlock_bh(dev);
+
+ return ret;
+}
+
+static int ipoib_set_mac(struct net_device *dev, void *addr)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct sockaddr_storage *ss = addr;
+ int ret;
+
+ if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev))
+ return -EBUSY;
+
+ ret = ipoib_check_lladdr(dev, ss);
+ if (ret)
+ return ret;
+
+ set_base_guid(priv, (union ib_gid *)(ss->__data + 4));
+
+ queue_work(ipoib_workqueue, &priv->flush_light);
+
+ return 0;
+}
+
static ssize_t create_child(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
@@ -1894,6 +2035,7 @@ static struct net_device *ipoib_add_port(const char *format,
goto device_init_failed;
} else
memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+ set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
result = ipoib_dev_init(priv->dev, hca, port);
if (result < 0) {
@@ -2001,6 +2143,9 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
ib_unregister_event_handler(&priv->event_handler);
flush_workqueue(ipoib_workqueue);
+ /* mark interface in the middle of destruction */
+ set_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags);
+
rtnl_lock();
dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
rtnl_unlock();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 25889311b1e9..d3394b6add24 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -64,6 +64,9 @@ struct ipoib_mcast_iter {
unsigned int send_only;
};
+/* join state that allows creating mcg with sendonly member request */
+#define SENDONLY_FULLMEMBER_JOIN 8
+
/*
* This should be called with the priv->lock held
*/
@@ -326,12 +329,23 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work)
struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
carrier_on_task);
struct ib_port_attr attr;
+ int ret;
if (ib_query_port(priv->ca, priv->port, &attr) ||
attr.state != IB_PORT_ACTIVE) {
ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
return;
}
+ /*
+ * Check if can send sendonly MCG's with sendonly-fullmember join state.
+ * It done here after the successfully join to the broadcast group,
+ * because the broadcast group must always be joined first and is always
+ * re-joined if the SM changes substantially.
+ */
+ ret = ipoib_check_sm_sendonly_fullmember_support(priv);
+ if (ret < 0)
+ pr_debug("%s failed query sm support for sendonly-fullmember (ret: %d)\n",
+ priv->dev->name, ret);
/*
* Take rtnl_lock to avoid racing with ipoib_stop() and
@@ -515,22 +529,20 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
rec.hop_limit = priv->broadcast->mcmember.hop_limit;
/*
- * Send-only IB Multicast joins do not work at the core
- * IB layer yet, so we can't use them here. However,
- * we are emulating an Ethernet multicast send, which
- * does not require a multicast subscription and will
- * still send properly. The most appropriate thing to
+ * Send-only IB Multicast joins work at the core IB layer but
+ * require specific SM support.
+ * We can use such joins here only if the current SM supports that feature.
+ * However, if not, we emulate an Ethernet multicast send,
+ * which does not require a multicast subscription and will
+ * still send properly. The most appropriate thing to
* do is to create the group if it doesn't exist as that
* most closely emulates the behavior, from a user space
- * application perspecitive, of Ethernet multicast
- * operation. For now, we do a full join, maybe later
- * when the core IB layers support send only joins we
- * will use them.
+ * application perspective, of Ethernet multicast operation.
*/
-#if 0
- if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
- rec.join_state = 4;
-#endif
+ if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
+ priv->sm_fullmember_sendonly_support)
+ /* SM supports sendonly-fullmember, otherwise fallback to full-member */
+ rec.join_state = SENDONLY_FULLMEMBER_JOIN;
}
spin_unlock_irq(&priv->lock);
@@ -570,11 +582,13 @@ void ipoib_mcast_join_task(struct work_struct *work)
return;
}
priv->local_lid = port_attr.lid;
+ netif_addr_lock_bh(dev);
- if (ib_query_gid(priv->ca, priv->port, 0, &priv->local_gid, NULL))
- ipoib_warn(priv, "ib_query_gid() failed\n");
- else
- memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+ if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
+ netif_addr_unlock_bh(dev);
+ return;
+ }
+ netif_addr_unlock_bh(dev);
spin_lock_irq(&priv->lock);
if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index b809c373e40e..1e7cbbaa15bd 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -307,5 +307,8 @@ void ipoib_event(struct ib_event_handler *handler,
queue_work(ipoib_workqueue, &priv->flush_normal);
} else if (record->event == IB_EVENT_PKEY_CHANGE) {
queue_work(ipoib_workqueue, &priv->flush_heavy);
+ } else if (record->event == IB_EVENT_GID_CHANGE &&
+ !test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
+ queue_work(ipoib_workqueue, &priv->flush_light);
}
}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index fca1a882de27..a2f9f29c6ab5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -68,6 +68,8 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
priv->pkey = pkey;
memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
+ memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid));
+ set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
priv->dev->broadcast[8] = pkey >> 8;
priv->dev->broadcast[9] = pkey & 0xff;
@@ -129,6 +131,9 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
ppriv = netdev_priv(pdev);
+ if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
+ return -EPERM;
+
snprintf(intf_name, sizeof intf_name, "%s.%04x",
ppriv->dev->name, pkey);
priv = ipoib_intf_alloc(intf_name);
@@ -181,6 +186,9 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
ppriv = netdev_priv(pdev);
+ if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
+ return -EPERM;
+
if (!rtnl_trylock())
return restart_syscall();
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 897b5a4993e8..a990c04208c9 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2596,9 +2596,19 @@ static void isert_free_conn(struct iscsi_conn *conn)
isert_put_conn(isert_conn);
}
+static void isert_get_rx_pdu(struct iscsi_conn *conn)
+{
+ struct completion comp;
+
+ init_completion(&comp);
+
+ wait_for_completion_interruptible(&comp);
+}
+
static struct iscsit_transport iser_target_transport = {
.name = "IB/iSER",
.transport_type = ISCSI_INFINIBAND,
+ .rdma_shutdown = true,
.priv_size = sizeof(struct isert_cmd),
.owner = THIS_MODULE,
.iscsit_setup_np = isert_setup_np,
@@ -2614,6 +2624,7 @@ static struct iscsit_transport iser_target_transport = {
.iscsit_queue_data_in = isert_put_datain,
.iscsit_queue_status = isert_put_response,
.iscsit_aborted_task = isert_aborted_task,
+ .iscsit_get_rx_pdu = isert_get_rx_pdu,
.iscsit_get_sup_prot_ops = isert_get_sup_prot_ops,
};
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 646de170ec12..3322ed750172 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1457,7 +1457,6 @@ static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch,
{
unsigned int sg_offset = 0;
- state->desc = req->indirect_desc;
state->fr.next = req->fr_list;
state->fr.end = req->fr_list + ch->target->mr_per_cmd;
state->sg = scat;
@@ -1489,7 +1488,6 @@ static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch,
struct scatterlist *sg;
int i;
- state->desc = req->indirect_desc;
for_each_sg(scat, sg, count, i) {
srp_map_desc(state, ib_sg_dma_address(dev->dev, sg),
ib_sg_dma_len(dev->dev, sg),
@@ -1655,6 +1653,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
target->indirect_size, DMA_TO_DEVICE);
memset(&state, 0, sizeof(state));
+ state.desc = req->indirect_desc;
if (dev->use_fast_reg)
ret = srp_map_sg_fr(&state, ch, req, scat, count);
else if (dev->use_fmr)
@@ -3526,7 +3525,7 @@ static void srp_add_one(struct ib_device *device)
int mr_page_shift, p;
u64 max_pages_per_mr;
- srp_dev = kmalloc(sizeof *srp_dev, GFP_KERNEL);
+ srp_dev = kzalloc(sizeof(*srp_dev), GFP_KERNEL);
if (!srp_dev)
return;
@@ -3586,8 +3585,6 @@ static void srp_add_one(struct ib_device *device)
IB_ACCESS_REMOTE_WRITE);
if (IS_ERR(srp_dev->global_mr))
goto err_pd;
- } else {
- srp_dev->global_mr = NULL;
}
for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 2843f1ae75bd..4a4155640d51 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -254,8 +254,8 @@ static void srpt_get_class_port_info(struct ib_dm_mad *mad)
memset(cif, 0, sizeof(*cif));
cif->base_version = 1;
cif->class_version = 1;
- cif->resp_time_value = 20;
+ ib_set_cpi_resp_time(cif, 20);
mad->mad_hdr.status = 0;
}
@@ -1638,8 +1638,7 @@ retry:
*/
qp_init->cap.max_send_wr = srp_sq_size / 2;
qp_init->cap.max_rdma_ctxs = srp_sq_size / 2;
- qp_init->cap.max_send_sge = max(sdev->device->attrs.max_sge_rd,
- sdev->device->attrs.max_sge);
+ qp_init->cap.max_send_sge = SRPT_DEF_SG_PER_WQE;
qp_init->port_num = ch->sport->port;
ch->qp = ib_create_qp(sdev->pd, qp_init);
@@ -1767,14 +1766,6 @@ static void __srpt_close_all_ch(struct srpt_device *sdev)
}
}
-/**
- * srpt_shutdown_session() - Whether or not a session may be shut down.
- */
-static int srpt_shutdown_session(struct se_session *se_sess)
-{
- return 1;
-}
-
static void srpt_free_ch(struct kref *kref)
{
struct srpt_rdma_ch *ch = container_of(kref, struct srpt_rdma_ch, kref);
@@ -3064,7 +3055,6 @@ static const struct target_core_fabric_ops srpt_template = {
.tpg_get_inst_index = srpt_tpg_get_inst_index,
.release_cmd = srpt_release_cmd,
.check_stop_free = srpt_check_stop_free,
- .shutdown_session = srpt_shutdown_session,
.close_session = srpt_close_session,
.sess_get_index = srpt_sess_get_index,
.sess_get_initiator_sid = NULL,
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index fee6bfd7ca21..389030487da7 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -106,6 +106,7 @@ enum {
SRP_LOGIN_RSP_MULTICHAN_MAINTAINED = 0x2,
SRPT_DEF_SG_TABLESIZE = 128,
+ SRPT_DEF_SG_PER_WQE = 16,
MIN_SRPT_SQ_SIZE = 16,
DEF_SRPT_SQ_SIZE = 4096,
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 1142a93dd90b..3438e98c145a 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -87,7 +87,7 @@
#define DRIVER_AUTHOR "Marko Friedemann <mfr@bmx-chemnitz.de>"
#define DRIVER_DESC "X-Box pad driver"
-#define XPAD_PKT_LEN 32
+#define XPAD_PKT_LEN 64
/* xbox d-pads should map to buttons, as is required for DDR pads
but we map them to axes when possible to simplify things */
@@ -129,6 +129,7 @@ static const struct xpad_device {
{ 0x045e, 0x028e, "Microsoft X-Box 360 pad", 0, XTYPE_XBOX360 },
{ 0x045e, 0x02d1, "Microsoft X-Box One pad", 0, XTYPE_XBOXONE },
{ 0x045e, 0x02dd, "Microsoft X-Box One pad (Firmware 2015)", 0, XTYPE_XBOXONE },
+ { 0x045e, 0x02e3, "Microsoft X-Box One Elite pad", 0, XTYPE_XBOXONE },
{ 0x045e, 0x0291, "Xbox 360 Wireless Receiver (XBOX)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
{ 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
@@ -173,9 +174,11 @@ static const struct xpad_device {
{ 0x0e6f, 0x0006, "Edge wireless Controller", 0, XTYPE_XBOX },
{ 0x0e6f, 0x0105, "HSM3 Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0e6f, 0x0113, "Afterglow AX.1 Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x0e6f, 0x0139, "Afterglow Prismatic Wired Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0201, "Pelican PL-3601 'TSZ' Wired Xbox 360 Controller", 0, XTYPE_XBOX360 },
{ 0x0e6f, 0x0213, "Afterglow Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
{ 0x0e6f, 0x021f, "Rock Candy Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0301, "Logic3 Controller", 0, XTYPE_XBOX360 },
{ 0x0e6f, 0x0401, "Logic3 Controller", 0, XTYPE_XBOX360 },
{ 0x0e8f, 0x0201, "SmartJoy Frag Xpad/PS2 adaptor", 0, XTYPE_XBOX },
@@ -183,6 +186,7 @@ static const struct xpad_device {
{ 0x0f0d, 0x000a, "Hori Co. DOA4 FightStick", 0, XTYPE_XBOX360 },
{ 0x0f0d, 0x000d, "Hori Fighting Stick EX2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0f0d, 0x0016, "Hori Real Arcade Pro.EX", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
+ { 0x0f0d, 0x0067, "HORIPAD ONE", 0, XTYPE_XBOXONE },
{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
{ 0x102c, 0xff0c, "Joytech Wireless Advanced Controller", 0, XTYPE_XBOX },
@@ -199,6 +203,7 @@ static const struct xpad_device {
{ 0x162e, 0xbeef, "Joytech Neo-Se Take2", 0, XTYPE_XBOX360 },
{ 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 },
{ 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x542a, "Xbox ONE spectra", 0, XTYPE_XBOXONE },
{ 0x24c6, 0x5d04, "Razer Sabertooth", 0, XTYPE_XBOX360 },
{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -212,6 +217,8 @@ static const struct xpad_device {
{ 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 },
{ 0x24c6, 0x5303, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x541a, "PowerA Xbox One Mini Wired Controller", 0, XTYPE_XBOXONE },
+ { 0x24c6, 0x543a, "PowerA Xbox One wired controller", 0, XTYPE_XBOXONE },
{ 0x24c6, 0x5500, "Hori XBOX 360 EX 2 with Turbo", 0, XTYPE_XBOX360 },
{ 0x24c6, 0x5501, "Hori Real Arcade Pro VX-SA", 0, XTYPE_XBOX360 },
{ 0x24c6, 0x5506, "Hori SOULCALIBUR V Stick", 0, XTYPE_XBOX360 },
@@ -307,13 +314,16 @@ static struct usb_device_id xpad_table[] = {
{ USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */
XPAD_XBOXONE_VENDOR(0x0738), /* Mad Catz FightStick TE 2 */
XPAD_XBOX360_VENDOR(0x0e6f), /* 0x0e6f X-Box 360 controllers */
+ XPAD_XBOXONE_VENDOR(0x0e6f), /* 0x0e6f X-Box One controllers */
XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */
XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */
XPAD_XBOX360_VENDOR(0x1bad), /* Harminix Rock Band Guitar and Drums */
XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */
+ XPAD_XBOXONE_VENDOR(0x0f0d), /* Hori Controllers */
XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */
XPAD_XBOX360_VENDOR(0x24c6), /* PowerA Controllers */
+ XPAD_XBOXONE_VENDOR(0x24c6), /* PowerA Controllers */
XPAD_XBOX360_VENDOR(0x1532), /* Razer Sabertooth */
XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */
@@ -457,6 +467,10 @@ static void xpad_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *d
static void xpad360_process_packet(struct usb_xpad *xpad, struct input_dev *dev,
u16 cmd, unsigned char *data)
{
+ /* valid pad data */
+ if (data[0] != 0x00)
+ return;
+
/* digital pad */
if (xpad->mapping & MAP_DPAD_TO_BUTTONS) {
/* dpad as buttons (left, right, up, down) */
@@ -756,6 +770,7 @@ static bool xpad_prepare_next_out_packet(struct usb_xpad *xpad)
if (packet) {
memcpy(xpad->odata, packet->data, packet->len);
xpad->irq_out->transfer_buffer_length = packet->len;
+ packet->pending = false;
return true;
}
@@ -797,7 +812,6 @@ static void xpad_irq_out(struct urb *urb)
switch (status) {
case 0:
/* success */
- xpad->out_packets[xpad->last_out_packet].pending = false;
xpad->irq_out_active = xpad_prepare_next_out_packet(xpad);
break;
@@ -1017,17 +1031,17 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
case XTYPE_XBOXONE:
packet->data[0] = 0x09; /* activate rumble */
- packet->data[1] = 0x08;
+ packet->data[1] = 0x00;
packet->data[2] = xpad->odata_serial++;
- packet->data[3] = 0x08; /* continuous effect */
- packet->data[4] = 0x00; /* simple rumble mode */
- packet->data[5] = 0x03; /* L and R actuator only */
- packet->data[6] = 0x00; /* TODO: LT actuator */
- packet->data[7] = 0x00; /* TODO: RT actuator */
+ packet->data[3] = 0x09;
+ packet->data[4] = 0x00;
+ packet->data[5] = 0x0F;
+ packet->data[6] = 0x00;
+ packet->data[7] = 0x00;
packet->data[8] = strong / 512; /* left actuator */
packet->data[9] = weak / 512; /* right actuator */
- packet->data[10] = 0x80; /* length of pulse */
- packet->data[11] = 0x00; /* stop period of pulse */
+ packet->data[10] = 0xFF;
+ packet->data[11] = 0x00;
packet->data[12] = 0x00;
packet->len = 13;
packet->pending = true;
@@ -1423,16 +1437,6 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
break;
}
- if (xpad_device[i].xtype == XTYPE_XBOXONE &&
- intf->cur_altsetting->desc.bInterfaceNumber != 0) {
- /*
- * The Xbox One controller lists three interfaces all with the
- * same interface class, subclass and protocol. Differentiate by
- * interface number.
- */
- return -ENODEV;
- }
-
xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL);
if (!xpad)
return -ENOMEM;
@@ -1464,6 +1468,8 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) {
if (intf->cur_altsetting->desc.bInterfaceProtocol == 129)
xpad->xtype = XTYPE_XBOX360W;
+ else if (intf->cur_altsetting->desc.bInterfaceProtocol == 208)
+ xpad->xtype = XTYPE_XBOXONE;
else
xpad->xtype = XTYPE_XBOX360;
} else {
@@ -1478,6 +1484,17 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
xpad->mapping |= MAP_STICKS_TO_NULL;
}
+ if (xpad->xtype == XTYPE_XBOXONE &&
+ intf->cur_altsetting->desc.bInterfaceNumber != 0) {
+ /*
+ * The Xbox One controller lists three interfaces all with the
+ * same interface class, subclass and protocol. Differentiate by
+ * interface number.
+ */
+ error = -ENODEV;
+ goto err_free_in_urb;
+ }
+
error = xpad_init_output(intf, xpad);
if (error)
goto err_free_in_urb;
diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c
index 6d96bff32a0e..29ddeb7be84b 100644
--- a/drivers/input/misc/max77693-haptic.c
+++ b/drivers/input/misc/max77693-haptic.c
@@ -70,10 +70,13 @@ struct max77693_haptic {
static int max77693_haptic_set_duty_cycle(struct max77693_haptic *haptic)
{
- int delta = (haptic->pwm_dev->period + haptic->pwm_duty) / 2;
+ struct pwm_args pargs;
+ int delta;
int error;
- error = pwm_config(haptic->pwm_dev, delta, haptic->pwm_dev->period);
+ pwm_get_args(haptic->pwm_dev, &pargs);
+ delta = (pargs.period + haptic->pwm_duty) / 2;
+ error = pwm_config(haptic->pwm_dev, delta, pargs.period);
if (error) {
dev_err(haptic->dev, "failed to configure pwm: %d\n", error);
return error;
@@ -234,6 +237,7 @@ static int max77693_haptic_play_effect(struct input_dev *dev, void *data,
struct ff_effect *effect)
{
struct max77693_haptic *haptic = input_get_drvdata(dev);
+ struct pwm_args pargs;
u64 period_mag_multi;
haptic->magnitude = effect->u.rumble.strong_magnitude;
@@ -245,7 +249,8 @@ static int max77693_haptic_play_effect(struct input_dev *dev, void *data,
* The formula to convert magnitude to pwm_duty as follows:
* - pwm_duty = (magnitude * pwm_period) / MAX_MAGNITUDE(0xFFFF)
*/
- period_mag_multi = (u64)haptic->pwm_dev->period * haptic->magnitude;
+ pwm_get_args(haptic->pwm_dev, &pargs);
+ period_mag_multi = (u64)pargs.period * haptic->magnitude;
haptic->pwm_duty = (unsigned int)(period_mag_multi >>
MAX_MAGNITUDE_SHIFT);
@@ -329,6 +334,12 @@ static int max77693_haptic_probe(struct platform_device *pdev)
return PTR_ERR(haptic->pwm_dev);
}
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to the
+ * atomic PWM API.
+ */
+ pwm_apply_args(haptic->pwm_dev);
+
haptic->motor_reg = devm_regulator_get(&pdev->dev, "haptic");
if (IS_ERR(haptic->motor_reg)) {
dev_err(&pdev->dev, "failed to get regulator\n");
diff --git a/drivers/input/misc/max8997_haptic.c b/drivers/input/misc/max8997_haptic.c
index 8d6326d7e7be..99bc762881d5 100644
--- a/drivers/input/misc/max8997_haptic.c
+++ b/drivers/input/misc/max8997_haptic.c
@@ -306,6 +306,12 @@ static int max8997_haptic_probe(struct platform_device *pdev)
error);
goto err_free_mem;
}
+
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(chip->pwm);
break;
default:
diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
index f2261ab54701..5f9655d49a65 100644
--- a/drivers/input/misc/pwm-beeper.c
+++ b/drivers/input/misc/pwm-beeper.c
@@ -20,21 +20,40 @@
#include <linux/platform_device.h>
#include <linux/pwm.h>
#include <linux/slab.h>
+#include <linux/workqueue.h>
struct pwm_beeper {
struct input_dev *input;
struct pwm_device *pwm;
+ struct work_struct work;
unsigned long period;
};
#define HZ_TO_NANOSECONDS(x) (1000000000UL/(x))
+static void __pwm_beeper_set(struct pwm_beeper *beeper)
+{
+ unsigned long period = beeper->period;
+
+ if (period) {
+ pwm_config(beeper->pwm, period / 2, period);
+ pwm_enable(beeper->pwm);
+ } else
+ pwm_disable(beeper->pwm);
+}
+
+static void pwm_beeper_work(struct work_struct *work)
+{
+ struct pwm_beeper *beeper =
+ container_of(work, struct pwm_beeper, work);
+
+ __pwm_beeper_set(beeper);
+}
+
static int pwm_beeper_event(struct input_dev *input,
unsigned int type, unsigned int code, int value)
{
- int ret = 0;
struct pwm_beeper *beeper = input_get_drvdata(input);
- unsigned long period;
if (type != EV_SND || value < 0)
return -EINVAL;
@@ -49,22 +68,31 @@ static int pwm_beeper_event(struct input_dev *input,
return -EINVAL;
}
- if (value == 0) {
- pwm_disable(beeper->pwm);
- } else {
- period = HZ_TO_NANOSECONDS(value);
- ret = pwm_config(beeper->pwm, period / 2, period);
- if (ret)
- return ret;
- ret = pwm_enable(beeper->pwm);
- if (ret)
- return ret;
- beeper->period = period;
- }
+ if (value == 0)
+ beeper->period = 0;
+ else
+ beeper->period = HZ_TO_NANOSECONDS(value);
+
+ schedule_work(&beeper->work);
return 0;
}
+static void pwm_beeper_stop(struct pwm_beeper *beeper)
+{
+ cancel_work_sync(&beeper->work);
+
+ if (beeper->period)
+ pwm_disable(beeper->pwm);
+}
+
+static void pwm_beeper_close(struct input_dev *input)
+{
+ struct pwm_beeper *beeper = input_get_drvdata(input);
+
+ pwm_beeper_stop(beeper);
+}
+
static int pwm_beeper_probe(struct platform_device *pdev)
{
unsigned long pwm_id = (unsigned long)dev_get_platdata(&pdev->dev);
@@ -87,6 +115,14 @@ static int pwm_beeper_probe(struct platform_device *pdev)
goto err_free;
}
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(beeper->pwm);
+
+ INIT_WORK(&beeper->work, pwm_beeper_work);
+
beeper->input = input_allocate_device();
if (!beeper->input) {
dev_err(&pdev->dev, "Failed to allocate input device\n");
@@ -106,6 +142,7 @@ static int pwm_beeper_probe(struct platform_device *pdev)
beeper->input->sndbit[0] = BIT(SND_TONE) | BIT(SND_BELL);
beeper->input->event = pwm_beeper_event;
+ beeper->input->close = pwm_beeper_close;
input_set_drvdata(beeper->input, beeper);
@@ -135,7 +172,6 @@ static int pwm_beeper_remove(struct platform_device *pdev)
input_unregister_device(beeper->input);
- pwm_disable(beeper->pwm);
pwm_free(beeper->pwm);
kfree(beeper);
@@ -147,8 +183,7 @@ static int __maybe_unused pwm_beeper_suspend(struct device *dev)
{
struct pwm_beeper *beeper = dev_get_drvdata(dev);
- if (beeper->period)
- pwm_disable(beeper->pwm);
+ pwm_beeper_stop(beeper);
return 0;
}
@@ -157,10 +192,8 @@ static int __maybe_unused pwm_beeper_resume(struct device *dev)
{
struct pwm_beeper *beeper = dev_get_drvdata(dev);
- if (beeper->period) {
- pwm_config(beeper->pwm, beeper->period / 2, beeper->period);
- pwm_enable(beeper->pwm);
- }
+ if (beeper->period)
+ __pwm_beeper_set(beeper);
return 0;
}
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index abe1a927b332..65ebbd111702 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -981,9 +981,15 @@ static long uinput_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
}
#ifdef CONFIG_COMPAT
+
+#define UI_SET_PHYS_COMPAT _IOW(UINPUT_IOCTL_BASE, 108, compat_uptr_t)
+
static long uinput_compat_ioctl(struct file *file,
unsigned int cmd, unsigned long arg)
{
+ if (cmd == UI_SET_PHYS_COMPAT)
+ cmd = UI_SET_PHYS;
+
return uinput_ioctl_handler(file, cmd, arg, compat_ptr(arg));
}
#endif
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 78f93cf68840..be5b399da5d3 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1568,13 +1568,7 @@ static int elantech_set_properties(struct elantech_data *etd)
case 5:
etd->hw_version = 3;
break;
- case 6:
- case 7:
- case 8:
- case 9:
- case 10:
- case 13:
- case 14:
+ case 6 ... 14:
etd->hw_version = 4;
break;
default:
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index a3f0f5a47490..0f586780ceb4 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -355,18 +355,11 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
return -ENXIO;
}
- if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
- psmouse_dbg(psmouse, "VMMouse port in use.\n");
- return -EBUSY;
- }
-
/* Check if the device is present */
response = ~VMMOUSE_PROTO_MAGIC;
VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2);
- if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) {
- release_region(VMMOUSE_PROTO_PORT, 4);
+ if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU)
return -ENXIO;
- }
if (set_properties) {
psmouse->vendor = VMMOUSE_VENDOR;
@@ -374,8 +367,6 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
psmouse->model = version;
}
- release_region(VMMOUSE_PROTO_PORT, 4);
-
return 0;
}
@@ -394,7 +385,6 @@ static void vmmouse_disconnect(struct psmouse *psmouse)
psmouse_reset(psmouse);
input_unregister_device(priv->abs_dev);
kfree(priv);
- release_region(VMMOUSE_PROTO_PORT, 4);
}
/**
@@ -438,15 +428,10 @@ int vmmouse_init(struct psmouse *psmouse)
struct input_dev *rel_dev = psmouse->dev, *abs_dev;
int error;
- if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
- psmouse_dbg(psmouse, "VMMouse port in use.\n");
- return -EBUSY;
- }
-
psmouse_reset(psmouse);
error = vmmouse_enable(psmouse);
if (error)
- goto release_region;
+ return error;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
abs_dev = input_allocate_device();
@@ -502,8 +487,5 @@ init_fail:
kfree(priv);
psmouse->private = NULL;
-release_region:
- release_region(VMMOUSE_PROTO_PORT, 4);
-
return error;
}
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
index 485794376ee5..d07dd29d4848 100644
--- a/drivers/input/touchscreen/sun4i-ts.c
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -115,7 +115,6 @@
struct sun4i_ts_data {
struct device *dev;
struct input_dev *input;
- struct thermal_zone_device *tz;
void __iomem *base;
unsigned int irq;
bool ignore_fifo_data;
@@ -366,10 +365,7 @@ static int sun4i_ts_probe(struct platform_device *pdev)
if (IS_ERR(hwmon))
return PTR_ERR(hwmon);
- ts->tz = thermal_zone_of_sensor_register(ts->dev, 0, ts,
- &sun4i_ts_tz_ops);
- if (IS_ERR(ts->tz))
- ts->tz = NULL;
+ devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, &sun4i_ts_tz_ops);
writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC);
@@ -377,7 +373,6 @@ static int sun4i_ts_probe(struct platform_device *pdev)
error = input_register_device(ts->input);
if (error) {
writel(0, ts->base + TP_INT_FIFOC);
- thermal_zone_of_sensor_unregister(ts->dev, ts->tz);
return error;
}
}
@@ -394,8 +389,6 @@ static int sun4i_ts_remove(struct platform_device *pdev)
if (ts->input)
input_unregister_device(ts->input);
- thermal_zone_of_sensor_unregister(ts->dev, ts->tz);
-
/* Deactivate all IRQs */
writel(0, ts->base + TP_INT_FIFOC);
diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c
index bab3c6acf6a2..0c9191cf324d 100644
--- a/drivers/input/touchscreen/wacom_w8001.c
+++ b/drivers/input/touchscreen/wacom_w8001.c
@@ -27,7 +27,7 @@ MODULE_AUTHOR("Jaya Kumar <jayakumar.lkml@gmail.com>");
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_LICENSE("GPL");
-#define W8001_MAX_LENGTH 11
+#define W8001_MAX_LENGTH 13
#define W8001_LEAD_MASK 0x80
#define W8001_LEAD_BYTE 0x80
#define W8001_TAB_MASK 0x40
@@ -339,6 +339,15 @@ static irqreturn_t w8001_interrupt(struct serio *serio,
w8001->idx = 0;
parse_multi_touch(w8001);
break;
+
+ default:
+ /*
+ * ThinkPad X60 Tablet PC (pen only device) sometimes
+ * sends invalid data packets that are larger than
+ * W8001_PKTLEN_TPCPEN. Let's start over again.
+ */
+ if (!w8001->touch_dev && w8001->idx > W8001_PKTLEN_TPCPEN - 1)
+ w8001->idx = 0;
}
return IRQ_HANDLED;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 9e0034196e10..d091defc3426 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1107,13 +1107,13 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
break;
}
+ devid = e->devid;
DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n",
hid, uid,
PCI_BUS_NUM(devid),
PCI_SLOT(devid),
PCI_FUNC(devid));
- devid = e->devid;
flags = e->flags;
ret = add_acpi_hid_device(hid, uid, &devid, false);
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index ebab33e77d67..5f6b3bcab078 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1477,7 +1477,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
- if (IS_ERR_VALUE(asid))
+ if (asid < 0)
return asid;
cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
@@ -1508,7 +1508,7 @@ static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
- if (IS_ERR_VALUE(vmid))
+ if (vmid < 0)
return vmid;
cfg->vmid = (u16)vmid;
@@ -1569,7 +1569,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
smmu_domain->pgtbl_ops = pgtbl_ops;
ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
free_io_pgtable_ops(pgtbl_ops);
return ret;
@@ -1642,7 +1642,7 @@ static void arm_smmu_detach_dev(struct device *dev)
struct arm_smmu_group *smmu_group = arm_smmu_group_get(dev);
smmu_group->ste.bypass = true;
- if (IS_ERR_VALUE(arm_smmu_install_ste_for_group(smmu_group)))
+ if (arm_smmu_install_ste_for_group(smmu_group) < 0)
dev_warn(dev, "failed to install bypass STE\n");
smmu_group->domain = NULL;
@@ -1694,7 +1694,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
smmu_group->ste.bypass = domain->type == IOMMU_DOMAIN_DMA;
ret = arm_smmu_install_ste_for_group(smmu_group);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
smmu_group->domain = NULL;
out_unlock:
@@ -1941,6 +1941,7 @@ static struct iommu_ops arm_smmu_ops = {
.attach_dev = arm_smmu_attach_dev,
.map = arm_smmu_map,
.unmap = arm_smmu_unmap,
+ .map_sg = default_iommu_map_sg,
.iova_to_phys = arm_smmu_iova_to_phys,
.add_device = arm_smmu_add_device,
.remove_device = arm_smmu_remove_device,
@@ -2235,7 +2236,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
arm_smmu_evtq_handler,
arm_smmu_evtq_thread,
0, "arm-smmu-v3-evtq", smmu);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
dev_warn(smmu->dev, "failed to enable evtq irq\n");
}
@@ -2244,7 +2245,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
ret = devm_request_irq(smmu->dev, irq,
arm_smmu_cmdq_sync_handler, 0,
"arm-smmu-v3-cmdq-sync", smmu);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
dev_warn(smmu->dev, "failed to enable cmdq-sync irq\n");
}
@@ -2252,7 +2253,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
if (irq) {
ret = devm_request_irq(smmu->dev, irq, arm_smmu_gerror_handler,
0, "arm-smmu-v3-gerror", smmu);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
dev_warn(smmu->dev, "failed to enable gerror irq\n");
}
@@ -2264,7 +2265,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
arm_smmu_priq_thread,
0, "arm-smmu-v3-priq",
smmu);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
dev_warn(smmu->dev,
"failed to enable priq irq\n");
else
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e206ce7a4e4b..9345a3fcb706 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -950,7 +950,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
smmu->num_context_banks);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
goto out_unlock;
cfg->cbndx = ret;
@@ -989,7 +989,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
"arm-smmu-context-fault", domain);
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
cfg->irptndx, irq);
cfg->irptndx = INVALID_IRPTNDX;
@@ -1099,7 +1099,7 @@ static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
for (i = 0; i < cfg->num_streamids; ++i) {
int idx = __arm_smmu_alloc_bitmap(smmu->smr_map, 0,
smmu->num_mapping_groups);
- if (IS_ERR_VALUE(idx)) {
+ if (idx < 0) {
dev_err(smmu->dev, "failed to allocate free SMR\n");
goto err_free_smrs;
}
@@ -1233,7 +1233,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
/* Ensure that the domain is finalised */
ret = arm_smmu_init_domain_context(domain, smmu);
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
return ret;
/*
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b2bfb9594508..cfe410eedaf0 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -33,6 +33,7 @@
#include <linux/dma-mapping.h>
#include <linux/mempool.h>
#include <linux/memory.h>
+#include <linux/cpu.h>
#include <linux/timer.h>
#include <linux/io.h>
#include <linux/iova.h>
@@ -390,6 +391,7 @@ struct dmar_domain {
* domain ids are 16 bit wide according
* to VT-d spec, section 9.3 */
+ bool has_iotlb_device;
struct list_head devices; /* all devices' list */
struct iova_domain iovad; /* iova's that belong to this domain */
@@ -456,27 +458,32 @@ static LIST_HEAD(dmar_rmrr_units);
static void flush_unmaps_timeout(unsigned long data);
-static DEFINE_TIMER(unmap_timer, flush_unmaps_timeout, 0, 0);
+struct deferred_flush_entry {
+ unsigned long iova_pfn;
+ unsigned long nrpages;
+ struct dmar_domain *domain;
+ struct page *freelist;
+};
#define HIGH_WATER_MARK 250
-struct deferred_flush_tables {
+struct deferred_flush_table {
int next;
- struct iova *iova[HIGH_WATER_MARK];
- struct dmar_domain *domain[HIGH_WATER_MARK];
- struct page *freelist[HIGH_WATER_MARK];
+ struct deferred_flush_entry entries[HIGH_WATER_MARK];
};
-static struct deferred_flush_tables *deferred_flush;
+struct deferred_flush_data {
+ spinlock_t lock;
+ int timer_on;
+ struct timer_list timer;
+ long size;
+ struct deferred_flush_table *tables;
+};
+
+DEFINE_PER_CPU(struct deferred_flush_data, deferred_flush);
/* bitmap for indexing intel_iommus */
static int g_num_of_iommus;
-static DEFINE_SPINLOCK(async_umap_flush_lock);
-static LIST_HEAD(unmaps_to_do);
-
-static int timer_on;
-static long list_size;
-
static void domain_exit(struct dmar_domain *domain);
static void domain_remove_dev_info(struct dmar_domain *domain);
static void dmar_remove_one_dev_info(struct dmar_domain *domain,
@@ -1458,10 +1465,35 @@ iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
return NULL;
}
+static void domain_update_iotlb(struct dmar_domain *domain)
+{
+ struct device_domain_info *info;
+ bool has_iotlb_device = false;
+
+ assert_spin_locked(&device_domain_lock);
+
+ list_for_each_entry(info, &domain->devices, link) {
+ struct pci_dev *pdev;
+
+ if (!info->dev || !dev_is_pci(info->dev))
+ continue;
+
+ pdev = to_pci_dev(info->dev);
+ if (pdev->ats_enabled) {
+ has_iotlb_device = true;
+ break;
+ }
+ }
+
+ domain->has_iotlb_device = has_iotlb_device;
+}
+
static void iommu_enable_dev_iotlb(struct device_domain_info *info)
{
struct pci_dev *pdev;
+ assert_spin_locked(&device_domain_lock);
+
if (!info || !dev_is_pci(info->dev))
return;
@@ -1481,6 +1513,7 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info)
#endif
if (info->ats_supported && !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) {
info->ats_enabled = 1;
+ domain_update_iotlb(info->domain);
info->ats_qdep = pci_ats_queue_depth(pdev);
}
}
@@ -1489,6 +1522,8 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
{
struct pci_dev *pdev;
+ assert_spin_locked(&device_domain_lock);
+
if (!dev_is_pci(info->dev))
return;
@@ -1497,6 +1532,7 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
if (info->ats_enabled) {
pci_disable_ats(pdev);
info->ats_enabled = 0;
+ domain_update_iotlb(info->domain);
}
#ifdef CONFIG_INTEL_IOMMU_SVM
if (info->pri_enabled) {
@@ -1517,6 +1553,9 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
unsigned long flags;
struct device_domain_info *info;
+ if (!domain->has_iotlb_device)
+ return;
+
spin_lock_irqsave(&device_domain_lock, flags);
list_for_each_entry(info, &domain->devices, link) {
if (!info->ats_enabled)
@@ -1734,6 +1773,7 @@ static struct dmar_domain *alloc_domain(int flags)
memset(domain, 0, sizeof(*domain));
domain->nid = -1;
domain->flags = flags;
+ domain->has_iotlb_device = false;
INIT_LIST_HEAD(&domain->devices);
return domain;
@@ -1918,8 +1958,12 @@ static void domain_exit(struct dmar_domain *domain)
return;
/* Flush any lazy unmaps that may reference this domain */
- if (!intel_iommu_strict)
- flush_unmaps_timeout(0);
+ if (!intel_iommu_strict) {
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ flush_unmaps_timeout(cpu);
+ }
/* Remove associated devices and clear attached or cached domains */
rcu_read_lock();
@@ -3077,7 +3121,7 @@ static int __init init_dmars(void)
bool copied_tables = false;
struct device *dev;
struct intel_iommu *iommu;
- int i, ret;
+ int i, ret, cpu;
/*
* for each drhd
@@ -3110,11 +3154,20 @@ static int __init init_dmars(void)
goto error;
}
- deferred_flush = kzalloc(g_num_of_iommus *
- sizeof(struct deferred_flush_tables), GFP_KERNEL);
- if (!deferred_flush) {
- ret = -ENOMEM;
- goto free_g_iommus;
+ for_each_possible_cpu(cpu) {
+ struct deferred_flush_data *dfd = per_cpu_ptr(&deferred_flush,
+ cpu);
+
+ dfd->tables = kzalloc(g_num_of_iommus *
+ sizeof(struct deferred_flush_table),
+ GFP_KERNEL);
+ if (!dfd->tables) {
+ ret = -ENOMEM;
+ goto free_g_iommus;
+ }
+
+ spin_lock_init(&dfd->lock);
+ setup_timer(&dfd->timer, flush_unmaps_timeout, cpu);
}
for_each_active_iommu(iommu, drhd) {
@@ -3169,11 +3222,6 @@ static int __init init_dmars(void)
}
}
- iommu_flush_write_buffer(iommu);
- iommu_set_root_entry(iommu);
- iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
- iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
-
if (!ecap_pass_through(iommu->ecap))
hw_pass_through = 0;
#ifdef CONFIG_INTEL_IOMMU_SVM
@@ -3182,6 +3230,18 @@ static int __init init_dmars(void)
#endif
}
+ /*
+ * Now that qi is enabled on all iommus, set the root entry and flush
+ * caches. This is required on some Intel X58 chipsets, otherwise the
+ * flush_context function will loop forever and the boot hangs.
+ */
+ for_each_active_iommu(iommu, drhd) {
+ iommu_flush_write_buffer(iommu);
+ iommu_set_root_entry(iommu);
+ iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+ }
+
if (iommu_pass_through)
iommu_identity_mapping |= IDENTMAP_ALL;
@@ -3291,19 +3351,20 @@ free_iommu:
disable_dmar_iommu(iommu);
free_dmar_iommu(iommu);
}
- kfree(deferred_flush);
free_g_iommus:
+ for_each_possible_cpu(cpu)
+ kfree(per_cpu_ptr(&deferred_flush, cpu)->tables);
kfree(g_iommus);
error:
return ret;
}
/* This takes a number of _MM_ pages, not VTD pages */
-static struct iova *intel_alloc_iova(struct device *dev,
+static unsigned long intel_alloc_iova(struct device *dev,
struct dmar_domain *domain,
unsigned long nrpages, uint64_t dma_mask)
{
- struct iova *iova = NULL;
+ unsigned long iova_pfn = 0;
/* Restrict dma_mask to the width that the iommu can handle */
dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
@@ -3316,19 +3377,19 @@ static struct iova *intel_alloc_iova(struct device *dev,
* DMA_BIT_MASK(32) and if that fails then try allocating
* from higher range
*/
- iova = alloc_iova(&domain->iovad, nrpages,
- IOVA_PFN(DMA_BIT_MASK(32)), 1);
- if (iova)
- return iova;
+ iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
+ IOVA_PFN(DMA_BIT_MASK(32)));
+ if (iova_pfn)
+ return iova_pfn;
}
- iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1);
- if (unlikely(!iova)) {
+ iova_pfn = alloc_iova_fast(&domain->iovad, nrpages, IOVA_PFN(dma_mask));
+ if (unlikely(!iova_pfn)) {
pr_err("Allocating %ld-page iova for %s failed",
nrpages, dev_name(dev));
- return NULL;
+ return 0;
}
- return iova;
+ return iova_pfn;
}
static struct dmar_domain *__get_valid_domain_for_dev(struct device *dev)
@@ -3426,7 +3487,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
{
struct dmar_domain *domain;
phys_addr_t start_paddr;
- struct iova *iova;
+ unsigned long iova_pfn;
int prot = 0;
int ret;
struct intel_iommu *iommu;
@@ -3444,8 +3505,8 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
iommu = domain_get_iommu(domain);
size = aligned_nrpages(paddr, size);
- iova = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size), dma_mask);
- if (!iova)
+ iova_pfn = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size), dma_mask);
+ if (!iova_pfn)
goto error;
/*
@@ -3463,7 +3524,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
* might have two guest_addr mapping to the same host paddr, but this
* is not a big problem
*/
- ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova->pfn_lo),
+ ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova_pfn),
mm_to_dma_pfn(paddr_pfn), size, prot);
if (ret)
goto error;
@@ -3471,18 +3532,18 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
/* it's a non-present to present mapping. Only flush if caching mode */
if (cap_caching_mode(iommu->cap))
iommu_flush_iotlb_psi(iommu, domain,
- mm_to_dma_pfn(iova->pfn_lo),
+ mm_to_dma_pfn(iova_pfn),
size, 0, 1);
else
iommu_flush_write_buffer(iommu);
- start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT;
+ start_paddr = (phys_addr_t)iova_pfn << PAGE_SHIFT;
start_paddr += paddr & ~PAGE_MASK;
return start_paddr;
error:
- if (iova)
- __free_iova(&domain->iovad, iova);
+ if (iova_pfn)
+ free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
pr_err("Device %s request: %zx@%llx dir %d --- failed\n",
dev_name(dev), size, (unsigned long long)paddr, dir);
return 0;
@@ -3497,91 +3558,120 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page,
dir, *dev->dma_mask);
}
-static void flush_unmaps(void)
+static void flush_unmaps(struct deferred_flush_data *flush_data)
{
int i, j;
- timer_on = 0;
+ flush_data->timer_on = 0;
/* just flush them all */
for (i = 0; i < g_num_of_iommus; i++) {
struct intel_iommu *iommu = g_iommus[i];
+ struct deferred_flush_table *flush_table =
+ &flush_data->tables[i];
if (!iommu)
continue;
- if (!deferred_flush[i].next)
+ if (!flush_table->next)
continue;
/* In caching mode, global flushes turn emulation expensive */
if (!cap_caching_mode(iommu->cap))
iommu->flush.flush_iotlb(iommu, 0, 0, 0,
DMA_TLB_GLOBAL_FLUSH);
- for (j = 0; j < deferred_flush[i].next; j++) {
+ for (j = 0; j < flush_table->next; j++) {
unsigned long mask;
- struct iova *iova = deferred_flush[i].iova[j];
- struct dmar_domain *domain = deferred_flush[i].domain[j];
+ struct deferred_flush_entry *entry =
+ &flush_table->entries[j];
+ unsigned long iova_pfn = entry->iova_pfn;
+ unsigned long nrpages = entry->nrpages;
+ struct dmar_domain *domain = entry->domain;
+ struct page *freelist = entry->freelist;
/* On real hardware multiple invalidations are expensive */
if (cap_caching_mode(iommu->cap))
iommu_flush_iotlb_psi(iommu, domain,
- iova->pfn_lo, iova_size(iova),
- !deferred_flush[i].freelist[j], 0);
+ mm_to_dma_pfn(iova_pfn),
+ nrpages, !freelist, 0);
else {
- mask = ilog2(mm_to_dma_pfn(iova_size(iova)));
- iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
- (uint64_t)iova->pfn_lo << PAGE_SHIFT, mask);
+ mask = ilog2(nrpages);
+ iommu_flush_dev_iotlb(domain,
+ (uint64_t)iova_pfn << PAGE_SHIFT, mask);
}
- __free_iova(&deferred_flush[i].domain[j]->iovad, iova);
- if (deferred_flush[i].freelist[j])
- dma_free_pagelist(deferred_flush[i].freelist[j]);
+ free_iova_fast(&domain->iovad, iova_pfn, nrpages);
+ if (freelist)
+ dma_free_pagelist(freelist);
}
- deferred_flush[i].next = 0;
+ flush_table->next = 0;
}
- list_size = 0;
+ flush_data->size = 0;
}
-static void flush_unmaps_timeout(unsigned long data)
+static void flush_unmaps_timeout(unsigned long cpuid)
{
+ struct deferred_flush_data *flush_data = per_cpu_ptr(&deferred_flush, cpuid);
unsigned long flags;
- spin_lock_irqsave(&async_umap_flush_lock, flags);
- flush_unmaps();
- spin_unlock_irqrestore(&async_umap_flush_lock, flags);
+ spin_lock_irqsave(&flush_data->lock, flags);
+ flush_unmaps(flush_data);
+ spin_unlock_irqrestore(&flush_data->lock, flags);
}
-static void add_unmap(struct dmar_domain *dom, struct iova *iova, struct page *freelist)
+static void add_unmap(struct dmar_domain *dom, unsigned long iova_pfn,
+ unsigned long nrpages, struct page *freelist)
{
unsigned long flags;
- int next, iommu_id;
+ int entry_id, iommu_id;
struct intel_iommu *iommu;
+ struct deferred_flush_entry *entry;
+ struct deferred_flush_data *flush_data;
+ unsigned int cpuid;
+
+ cpuid = get_cpu();
+ flush_data = per_cpu_ptr(&deferred_flush, cpuid);
+
+ /* Flush all CPUs' entries to avoid deferring too much. If
+ * this becomes a bottleneck, can just flush us, and rely on
+ * flush timer for the rest.
+ */
+ if (flush_data->size == HIGH_WATER_MARK) {
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ flush_unmaps_timeout(cpu);
+ }
- spin_lock_irqsave(&async_umap_flush_lock, flags);
- if (list_size == HIGH_WATER_MARK)
- flush_unmaps();
+ spin_lock_irqsave(&flush_data->lock, flags);
iommu = domain_get_iommu(dom);
iommu_id = iommu->seq_id;
- next = deferred_flush[iommu_id].next;
- deferred_flush[iommu_id].domain[next] = dom;
- deferred_flush[iommu_id].iova[next] = iova;
- deferred_flush[iommu_id].freelist[next] = freelist;
- deferred_flush[iommu_id].next++;
+ entry_id = flush_data->tables[iommu_id].next;
+ ++(flush_data->tables[iommu_id].next);
- if (!timer_on) {
- mod_timer(&unmap_timer, jiffies + msecs_to_jiffies(10));
- timer_on = 1;
+ entry = &flush_data->tables[iommu_id].entries[entry_id];
+ entry->domain = dom;
+ entry->iova_pfn = iova_pfn;
+ entry->nrpages = nrpages;
+ entry->freelist = freelist;
+
+ if (!flush_data->timer_on) {
+ mod_timer(&flush_data->timer, jiffies + msecs_to_jiffies(10));
+ flush_data->timer_on = 1;
}
- list_size++;
- spin_unlock_irqrestore(&async_umap_flush_lock, flags);
+ flush_data->size++;
+ spin_unlock_irqrestore(&flush_data->lock, flags);
+
+ put_cpu();
}
-static void intel_unmap(struct device *dev, dma_addr_t dev_addr)
+static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
{
struct dmar_domain *domain;
unsigned long start_pfn, last_pfn;
- struct iova *iova;
+ unsigned long nrpages;
+ unsigned long iova_pfn;
struct intel_iommu *iommu;
struct page *freelist;
@@ -3593,13 +3683,11 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr)
iommu = domain_get_iommu(domain);
- iova = find_iova(&domain->iovad, IOVA_PFN(dev_addr));
- if (WARN_ONCE(!iova, "Driver unmaps unmatched page at PFN %llx\n",
- (unsigned long long)dev_addr))
- return;
+ iova_pfn = IOVA_PFN(dev_addr);
- start_pfn = mm_to_dma_pfn(iova->pfn_lo);
- last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1;
+ nrpages = aligned_nrpages(dev_addr, size);
+ start_pfn = mm_to_dma_pfn(iova_pfn);
+ last_pfn = start_pfn + nrpages - 1;
pr_debug("Device %s unmapping: pfn %lx-%lx\n",
dev_name(dev), start_pfn, last_pfn);
@@ -3608,12 +3696,12 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr)
if (intel_iommu_strict) {
iommu_flush_iotlb_psi(iommu, domain, start_pfn,
- last_pfn - start_pfn + 1, !freelist, 0);
+ nrpages, !freelist, 0);
/* free iova */
- __free_iova(&domain->iovad, iova);
+ free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages));
dma_free_pagelist(freelist);
} else {
- add_unmap(domain, iova, freelist);
+ add_unmap(domain, iova_pfn, nrpages, freelist);
/*
* queue up the release of the unmap to save the 1/6th of the
* cpu used up by the iotlb flush operation...
@@ -3625,7 +3713,7 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- intel_unmap(dev, dev_addr);
+ intel_unmap(dev, dev_addr, size);
}
static void *intel_alloc_coherent(struct device *dev, size_t size,
@@ -3684,7 +3772,7 @@ static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
size = PAGE_ALIGN(size);
order = get_order(size);
- intel_unmap(dev, dma_handle);
+ intel_unmap(dev, dma_handle, size);
if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
__free_pages(page, order);
}
@@ -3693,7 +3781,16 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- intel_unmap(dev, sglist[0].dma_address);
+ dma_addr_t startaddr = sg_dma_address(sglist) & PAGE_MASK;
+ unsigned long nrpages = 0;
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i) {
+ nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg));
+ }
+
+ intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
}
static int intel_nontranslate_map_sg(struct device *hddev,
@@ -3717,7 +3814,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
struct dmar_domain *domain;
size_t size = 0;
int prot = 0;
- struct iova *iova = NULL;
+ unsigned long iova_pfn;
int ret;
struct scatterlist *sg;
unsigned long start_vpfn;
@@ -3736,9 +3833,9 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
for_each_sg(sglist, sg, nelems, i)
size += aligned_nrpages(sg->offset, sg->length);
- iova = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size),
+ iova_pfn = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size),
*dev->dma_mask);
- if (!iova) {
+ if (!iova_pfn) {
sglist->dma_length = 0;
return 0;
}
@@ -3753,13 +3850,13 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
prot |= DMA_PTE_WRITE;
- start_vpfn = mm_to_dma_pfn(iova->pfn_lo);
+ start_vpfn = mm_to_dma_pfn(iova_pfn);
ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot);
if (unlikely(ret)) {
dma_pte_free_pagetable(domain, start_vpfn,
start_vpfn + size - 1);
- __free_iova(&domain->iovad, iova);
+ free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
return 0;
}
@@ -4498,6 +4595,46 @@ static struct notifier_block intel_iommu_memory_nb = {
.priority = 0
};
+static void free_all_cpu_cached_iovas(unsigned int cpu)
+{
+ int i;
+
+ for (i = 0; i < g_num_of_iommus; i++) {
+ struct intel_iommu *iommu = g_iommus[i];
+ struct dmar_domain *domain;
+ u16 did;
+
+ if (!iommu)
+ continue;
+
+ for (did = 0; did < cap_ndoms(iommu->cap); did++) {
+ domain = get_iommu_domain(iommu, did);
+
+ if (!domain)
+ continue;
+ free_cpu_cached_iovas(cpu, &domain->iovad);
+ }
+ }
+}
+
+static int intel_iommu_cpu_notifier(struct notifier_block *nfb,
+ unsigned long action, void *v)
+{
+ unsigned int cpu = (unsigned long)v;
+
+ switch (action) {
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ free_all_cpu_cached_iovas(cpu);
+ flush_unmaps_timeout(cpu);
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block intel_iommu_cpu_nb = {
+ .notifier_call = intel_iommu_cpu_notifier,
+};
static ssize_t intel_iommu_show_version(struct device *dev,
struct device_attribute *attr,
@@ -4631,7 +4768,6 @@ int __init intel_iommu_init(void)
up_write(&dmar_global_lock);
pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
- init_timer(&unmap_timer);
#ifdef CONFIG_SWIOTLB
swiotlb = 0;
#endif
@@ -4648,6 +4784,7 @@ int __init intel_iommu_init(void)
bus_register_notifier(&pci_bus_type, &device_nb);
if (si_domain && !hw_pass_through)
register_memory_notifier(&intel_iommu_memory_nb);
+ register_hotcpu_notifier(&intel_iommu_cpu_nb);
intel_iommu_enabled = 1;
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index fa0adef32bd6..e23001bfcfee 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -20,6 +20,17 @@
#include <linux/iova.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/bitops.h>
+
+static bool iova_rcache_insert(struct iova_domain *iovad,
+ unsigned long pfn,
+ unsigned long size);
+static unsigned long iova_rcache_get(struct iova_domain *iovad,
+ unsigned long size,
+ unsigned long limit_pfn);
+static void init_iova_rcaches(struct iova_domain *iovad);
+static void free_iova_rcaches(struct iova_domain *iovad);
void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
@@ -38,6 +49,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
iovad->granule = granule;
iovad->start_pfn = start_pfn;
iovad->dma_32bit_pfn = pfn_32bit;
+ init_iova_rcaches(iovad);
}
EXPORT_SYMBOL_GPL(init_iova_domain);
@@ -291,33 +303,18 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
}
EXPORT_SYMBOL_GPL(alloc_iova);
-/**
- * find_iova - find's an iova for a given pfn
- * @iovad: - iova domain in question.
- * @pfn: - page frame number
- * This function finds and returns an iova belonging to the
- * given doamin which matches the given pfn.
- */
-struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
+static struct iova *
+private_find_iova(struct iova_domain *iovad, unsigned long pfn)
{
- unsigned long flags;
- struct rb_node *node;
+ struct rb_node *node = iovad->rbroot.rb_node;
+
+ assert_spin_locked(&iovad->iova_rbtree_lock);
- /* Take the lock so that no other thread is manipulating the rbtree */
- spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
- node = iovad->rbroot.rb_node;
while (node) {
struct iova *iova = container_of(node, struct iova, node);
/* If pfn falls within iova's range, return iova */
if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
- spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
- /* We are not holding the lock while this iova
- * is referenced by the caller as the same thread
- * which called this function also calls __free_iova()
- * and it is by design that only one thread can possibly
- * reference a particular iova and hence no conflict.
- */
return iova;
}
@@ -327,9 +324,35 @@ struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
node = node->rb_right;
}
- spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return NULL;
}
+
+static void private_free_iova(struct iova_domain *iovad, struct iova *iova)
+{
+ assert_spin_locked(&iovad->iova_rbtree_lock);
+ __cached_rbnode_delete_update(iovad, iova);
+ rb_erase(&iova->node, &iovad->rbroot);
+ free_iova_mem(iova);
+}
+
+/**
+ * find_iova - finds an iova for a given pfn
+ * @iovad: - iova domain in question.
+ * @pfn: - page frame number
+ * This function finds and returns an iova belonging to the
+ * given doamin which matches the given pfn.
+ */
+struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+ unsigned long flags;
+ struct iova *iova;
+
+ /* Take the lock so that no other thread is manipulating the rbtree */
+ spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+ iova = private_find_iova(iovad, pfn);
+ spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+ return iova;
+}
EXPORT_SYMBOL_GPL(find_iova);
/**
@@ -344,10 +367,8 @@ __free_iova(struct iova_domain *iovad, struct iova *iova)
unsigned long flags;
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
- __cached_rbnode_delete_update(iovad, iova);
- rb_erase(&iova->node, &iovad->rbroot);
+ private_free_iova(iovad, iova);
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
- free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(__free_iova);
@@ -370,6 +391,65 @@ free_iova(struct iova_domain *iovad, unsigned long pfn)
EXPORT_SYMBOL_GPL(free_iova);
/**
+ * alloc_iova_fast - allocates an iova from rcache
+ * @iovad: - iova domain in question
+ * @size: - size of page frames to allocate
+ * @limit_pfn: - max limit address
+ * This function tries to satisfy an iova allocation from the rcache,
+ * and falls back to regular allocation on failure.
+*/
+unsigned long
+alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
+ unsigned long limit_pfn)
+{
+ bool flushed_rcache = false;
+ unsigned long iova_pfn;
+ struct iova *new_iova;
+
+ iova_pfn = iova_rcache_get(iovad, size, limit_pfn);
+ if (iova_pfn)
+ return iova_pfn;
+
+retry:
+ new_iova = alloc_iova(iovad, size, limit_pfn, true);
+ if (!new_iova) {
+ unsigned int cpu;
+
+ if (flushed_rcache)
+ return 0;
+
+ /* Try replenishing IOVAs by flushing rcache. */
+ flushed_rcache = true;
+ preempt_disable();
+ for_each_online_cpu(cpu)
+ free_cpu_cached_iovas(cpu, iovad);
+ preempt_enable();
+ goto retry;
+ }
+
+ return new_iova->pfn_lo;
+}
+EXPORT_SYMBOL_GPL(alloc_iova_fast);
+
+/**
+ * free_iova_fast - free iova pfn range into rcache
+ * @iovad: - iova domain in question.
+ * @pfn: - pfn that is allocated previously
+ * @size: - # of pages in range
+ * This functions frees an iova range by trying to put it into the rcache,
+ * falling back to regular iova deallocation via free_iova() if this fails.
+ */
+void
+free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
+{
+ if (iova_rcache_insert(iovad, pfn, size))
+ return;
+
+ free_iova(iovad, pfn);
+}
+EXPORT_SYMBOL_GPL(free_iova_fast);
+
+/**
* put_iova_domain - destroys the iova doamin
* @iovad: - iova domain in question.
* All the iova's in that domain are destroyed.
@@ -379,6 +459,7 @@ void put_iova_domain(struct iova_domain *iovad)
struct rb_node *node;
unsigned long flags;
+ free_iova_rcaches(iovad);
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
node = rb_first(&iovad->rbroot);
while (node) {
@@ -550,5 +631,297 @@ error:
return NULL;
}
+/*
+ * Magazine caches for IOVA ranges. For an introduction to magazines,
+ * see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab
+ * Allocator to Many CPUs and Arbitrary Resources" by Bonwick and Adams.
+ * For simplicity, we use a static magazine size and don't implement the
+ * dynamic size tuning described in the paper.
+ */
+
+#define IOVA_MAG_SIZE 128
+
+struct iova_magazine {
+ unsigned long size;
+ unsigned long pfns[IOVA_MAG_SIZE];
+};
+
+struct iova_cpu_rcache {
+ spinlock_t lock;
+ struct iova_magazine *loaded;
+ struct iova_magazine *prev;
+};
+
+static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
+{
+ return kzalloc(sizeof(struct iova_magazine), flags);
+}
+
+static void iova_magazine_free(struct iova_magazine *mag)
+{
+ kfree(mag);
+}
+
+static void
+iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad)
+{
+ unsigned long flags;
+ int i;
+
+ if (!mag)
+ return;
+
+ spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+
+ for (i = 0 ; i < mag->size; ++i) {
+ struct iova *iova = private_find_iova(iovad, mag->pfns[i]);
+
+ BUG_ON(!iova);
+ private_free_iova(iovad, iova);
+ }
+
+ spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+ mag->size = 0;
+}
+
+static bool iova_magazine_full(struct iova_magazine *mag)
+{
+ return (mag && mag->size == IOVA_MAG_SIZE);
+}
+
+static bool iova_magazine_empty(struct iova_magazine *mag)
+{
+ return (!mag || mag->size == 0);
+}
+
+static unsigned long iova_magazine_pop(struct iova_magazine *mag,
+ unsigned long limit_pfn)
+{
+ BUG_ON(iova_magazine_empty(mag));
+
+ if (mag->pfns[mag->size - 1] >= limit_pfn)
+ return 0;
+
+ return mag->pfns[--mag->size];
+}
+
+static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
+{
+ BUG_ON(iova_magazine_full(mag));
+
+ mag->pfns[mag->size++] = pfn;
+}
+
+static void init_iova_rcaches(struct iova_domain *iovad)
+{
+ struct iova_cpu_rcache *cpu_rcache;
+ struct iova_rcache *rcache;
+ unsigned int cpu;
+ int i;
+
+ for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ rcache = &iovad->rcaches[i];
+ spin_lock_init(&rcache->lock);
+ rcache->depot_size = 0;
+ rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), cache_line_size());
+ if (WARN_ON(!rcache->cpu_rcaches))
+ continue;
+ for_each_possible_cpu(cpu) {
+ cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+ spin_lock_init(&cpu_rcache->lock);
+ cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
+ cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
+ }
+ }
+}
+
+/*
+ * Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and
+ * return true on success. Can fail if rcache is full and we can't free
+ * space, and free_iova() (our only caller) will then return the IOVA
+ * range to the rbtree instead.
+ */
+static bool __iova_rcache_insert(struct iova_domain *iovad,
+ struct iova_rcache *rcache,
+ unsigned long iova_pfn)
+{
+ struct iova_magazine *mag_to_free = NULL;
+ struct iova_cpu_rcache *cpu_rcache;
+ bool can_insert = false;
+ unsigned long flags;
+
+ cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
+ spin_lock_irqsave(&cpu_rcache->lock, flags);
+
+ if (!iova_magazine_full(cpu_rcache->loaded)) {
+ can_insert = true;
+ } else if (!iova_magazine_full(cpu_rcache->prev)) {
+ swap(cpu_rcache->prev, cpu_rcache->loaded);
+ can_insert = true;
+ } else {
+ struct iova_magazine *new_mag = iova_magazine_alloc(GFP_ATOMIC);
+
+ if (new_mag) {
+ spin_lock(&rcache->lock);
+ if (rcache->depot_size < MAX_GLOBAL_MAGS) {
+ rcache->depot[rcache->depot_size++] =
+ cpu_rcache->loaded;
+ } else {
+ mag_to_free = cpu_rcache->loaded;
+ }
+ spin_unlock(&rcache->lock);
+
+ cpu_rcache->loaded = new_mag;
+ can_insert = true;
+ }
+ }
+
+ if (can_insert)
+ iova_magazine_push(cpu_rcache->loaded, iova_pfn);
+
+ spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+ put_cpu_ptr(rcache->cpu_rcaches);
+
+ if (mag_to_free) {
+ iova_magazine_free_pfns(mag_to_free, iovad);
+ iova_magazine_free(mag_to_free);
+ }
+
+ return can_insert;
+}
+
+static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn,
+ unsigned long size)
+{
+ unsigned int log_size = order_base_2(size);
+
+ if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+ return false;
+
+ return __iova_rcache_insert(iovad, &iovad->rcaches[log_size], pfn);
+}
+
+/*
+ * Caller wants to allocate a new IOVA range from 'rcache'. If we can
+ * satisfy the request, return a matching non-NULL range and remove
+ * it from the 'rcache'.
+ */
+static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
+ unsigned long limit_pfn)
+{
+ struct iova_cpu_rcache *cpu_rcache;
+ unsigned long iova_pfn = 0;
+ bool has_pfn = false;
+ unsigned long flags;
+
+ cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
+ spin_lock_irqsave(&cpu_rcache->lock, flags);
+
+ if (!iova_magazine_empty(cpu_rcache->loaded)) {
+ has_pfn = true;
+ } else if (!iova_magazine_empty(cpu_rcache->prev)) {
+ swap(cpu_rcache->prev, cpu_rcache->loaded);
+ has_pfn = true;
+ } else {
+ spin_lock(&rcache->lock);
+ if (rcache->depot_size > 0) {
+ iova_magazine_free(cpu_rcache->loaded);
+ cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
+ has_pfn = true;
+ }
+ spin_unlock(&rcache->lock);
+ }
+
+ if (has_pfn)
+ iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
+
+ spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+ put_cpu_ptr(rcache->cpu_rcaches);
+
+ return iova_pfn;
+}
+
+/*
+ * Try to satisfy IOVA allocation range from rcache. Fail if requested
+ * size is too big or the DMA limit we are given isn't satisfied by the
+ * top element in the magazine.
+ */
+static unsigned long iova_rcache_get(struct iova_domain *iovad,
+ unsigned long size,
+ unsigned long limit_pfn)
+{
+ unsigned int log_size = order_base_2(size);
+
+ if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+ return 0;
+
+ return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn);
+}
+
+/*
+ * Free a cpu's rcache.
+ */
+static void free_cpu_iova_rcache(unsigned int cpu, struct iova_domain *iovad,
+ struct iova_rcache *rcache)
+{
+ struct iova_cpu_rcache *cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_rcache->lock, flags);
+
+ iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
+ iova_magazine_free(cpu_rcache->loaded);
+
+ iova_magazine_free_pfns(cpu_rcache->prev, iovad);
+ iova_magazine_free(cpu_rcache->prev);
+
+ spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+}
+
+/*
+ * free rcache data structures.
+ */
+static void free_iova_rcaches(struct iova_domain *iovad)
+{
+ struct iova_rcache *rcache;
+ unsigned long flags;
+ unsigned int cpu;
+ int i, j;
+
+ for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ rcache = &iovad->rcaches[i];
+ for_each_possible_cpu(cpu)
+ free_cpu_iova_rcache(cpu, iovad, rcache);
+ spin_lock_irqsave(&rcache->lock, flags);
+ free_percpu(rcache->cpu_rcaches);
+ for (j = 0; j < rcache->depot_size; ++j) {
+ iova_magazine_free_pfns(rcache->depot[j], iovad);
+ iova_magazine_free(rcache->depot[j]);
+ }
+ spin_unlock_irqrestore(&rcache->lock, flags);
+ }
+}
+
+/*
+ * free all the IOVA ranges cached by a cpu (used when cpu is unplugged)
+ */
+void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
+{
+ struct iova_cpu_rcache *cpu_rcache;
+ struct iova_rcache *rcache;
+ unsigned long flags;
+ int i;
+
+ for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ rcache = &iovad->rcaches[i];
+ cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+ spin_lock_irqsave(&cpu_rcache->lock, flags);
+ iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
+ iova_magazine_free_pfns(cpu_rcache->prev, iovad);
+ spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+ }
+}
+
MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index c7d6156ff536..25b4627cb57f 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -815,7 +815,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
dte_addr = virt_to_phys(rk_domain->dt);
for (i = 0; i < iommu->num_mmu; i++) {
rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr);
- rk_iommu_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
+ rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
}
diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c
index eb5eb0cd414d..2223b3f15d68 100644
--- a/drivers/irqchip/irq-clps711x.c
+++ b/drivers/irqchip/irq-clps711x.c
@@ -182,7 +182,7 @@ static int __init _clps711x_intc_init(struct device_node *np,
writel_relaxed(0, clps711x_intc->intmr[2]);
err = irq_alloc_descs(-1, 0, ARRAY_SIZE(clps711x_irqs), numa_node_id());
- if (IS_ERR_VALUE(err))
+ if (err < 0)
goto out_iounmap;
clps711x_intc->ops.map = clps711x_intc_irq_map;
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 6bd881be24ea..5eb1f9e17a98 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
#define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0)
#define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2)
#define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0)
@@ -82,6 +83,7 @@ struct its_node {
u64 flags;
u32 ite_size;
u32 device_ids;
+ int numa_node;
};
#define ITS_ITT_ALIGN SZ_256
@@ -613,11 +615,23 @@ static void its_unmask_irq(struct irq_data *d)
static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
bool force)
{
- unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+ unsigned int cpu;
+ const struct cpumask *cpu_mask = cpu_online_mask;
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
struct its_collection *target_col;
u32 id = its_get_event_id(d);
+ /* lpi cannot be routed to a redistributor that is on a foreign node */
+ if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+ if (its_dev->its->numa_node >= 0) {
+ cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+ if (!cpumask_intersects(mask_val, cpu_mask))
+ return -EINVAL;
+ }
+ }
+
+ cpu = cpumask_any_and(mask_val, cpu_mask);
+
if (cpu >= nr_cpu_ids)
return -EINVAL;
@@ -1101,6 +1115,16 @@ static void its_cpu_init_collection(void)
list_for_each_entry(its, &its_nodes, entry) {
u64 target;
+ /* avoid cross node collections and its mapping */
+ if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+ struct device_node *cpu_node;
+
+ cpu_node = of_get_cpu_node(cpu, NULL);
+ if (its->numa_node != NUMA_NO_NODE &&
+ its->numa_node != of_node_to_nid(cpu_node))
+ continue;
+ }
+
/*
* We now have to bind each collection to its target
* redistributor.
@@ -1351,9 +1375,14 @@ static void its_irq_domain_activate(struct irq_domain *domain,
{
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
u32 event = its_get_event_id(d);
+ const struct cpumask *cpu_mask = cpu_online_mask;
+
+ /* get the cpu_mask of local node */
+ if (its_dev->its->numa_node >= 0)
+ cpu_mask = cpumask_of_node(its_dev->its->numa_node);
/* Bind the LPI to the first possible CPU */
- its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+ its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
/* Map the GIC IRQ and event to the device */
its_send_mapvi(its_dev, d->hwirq, event);
@@ -1443,6 +1472,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
}
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+ struct its_node *its = data;
+
+ its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
static const struct gic_quirk its_quirks[] = {
#ifdef CONFIG_CAVIUM_ERRATUM_22375
{
@@ -1452,6 +1488,14 @@ static const struct gic_quirk its_quirks[] = {
.init = its_enable_quirk_cavium_22375,
},
#endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+ {
+ .desc = "ITS: Cavium erratum 23144",
+ .iidr = 0xa100034c, /* ThunderX pass 1.x */
+ .mask = 0xffff0fff,
+ .init = its_enable_quirk_cavium_23144,
+ },
+#endif
{
}
};
@@ -1514,6 +1558,7 @@ static int __init its_probe(struct device_node *node,
its->base = its_base;
its->phys_base = res.start;
its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+ its->numa_node = of_node_to_nid(node);
its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
if (!its->cmd_base) {
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index fb042ba9a3db..2c5ba0e704bf 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -155,7 +155,7 @@ static void gic_enable_redist(bool enable)
while (count--) {
val = readl_relaxed(rbase + GICR_WAKER);
- if (enable ^ (val & GICR_WAKER_ChildrenAsleep))
+ if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
break;
cpu_relax();
udelay(1);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index b4e647179346..fbc4ae2afd29 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1123,7 +1123,7 @@ static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
numa_node_id());
- if (IS_ERR_VALUE(irq_base)) {
+ if (irq_base < 0) {
WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
irq_start);
irq_base = irq_start;
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 9688d2e2a636..9e25d8ce08e5 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -402,7 +402,7 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
nr_irqs -= hwirq_base; /* calculate # of irqs to allocate */
irq_base = irq_alloc_descs(-1, hwirq_base, nr_irqs, numa_node_id());
- if (IS_ERR_VALUE(irq_base)) {
+ if (irq_base < 0) {
pr_err("failed to allocate IRQ numbers\n");
return -EINVAL;
}
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index c089f49b63fb..8a4adbeb2b8c 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -746,6 +746,12 @@ static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
/* verify that it doesn't conflict with an IPI irq */
if (test_bit(spec->hwirq, ipi_resrv))
return -EBUSY;
+
+ hwirq = GIC_SHARED_TO_HWIRQ(spec->hwirq);
+
+ return irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+ &gic_level_irq_controller,
+ NULL);
} else {
base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
if (base_hwirq == gic_shared_intrs) {
@@ -867,10 +873,14 @@ static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq,
&gic_level_irq_controller,
NULL);
if (ret)
- return ret;
+ goto error;
}
return 0;
+
+error:
+ irq_domain_free_irqs_parent(d, virq, nr_irqs);
+ return ret;
}
void gic_dev_domain_free(struct irq_domain *d, unsigned int virq,
@@ -968,7 +978,7 @@ static void __init __gic_init(unsigned long gic_base_addr,
unsigned int cpu_vec, unsigned int irqbase,
struct device_node *node)
{
- unsigned int gicconfig;
+ unsigned int gicconfig, cpu;
unsigned int v[2];
__gic_base_addr = gic_base_addr;
@@ -985,6 +995,14 @@ static void __init __gic_init(unsigned long gic_base_addr,
gic_vpes = gic_vpes + 1;
if (cpu_has_veic) {
+ /* Set EIC mode for all VPEs */
+ for_each_present_cpu(cpu) {
+ gic_write(GIC_REG(VPE_LOCAL, GIC_VPE_OTHER_ADDR),
+ mips_cm_vp_id(cpu));
+ gic_write(GIC_REG(VPE_OTHER, GIC_VPE_CTL),
+ GIC_VPE_CTL_EIC_MODE_MSK);
+ }
+
/* Always use vector 1 in EIC mode */
gic_cpu_pin = 0;
timer_cpu_pin = gic_cpu_pin;
diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c
index e7155db01d55..73addb4b625b 100644
--- a/drivers/irqchip/irq-pic32-evic.c
+++ b/drivers/irqchip/irq-pic32-evic.c
@@ -91,7 +91,7 @@ static int pic32_set_type_edge(struct irq_data *data,
/* set polarity for external interrupts only */
for (i = 0; i < ARRAY_SIZE(priv->ext_irqs); i++) {
if (priv->ext_irqs[i] == data->hwirq) {
- ret = pic32_set_ext_polarity(i + 1, flow_type);
+ ret = pic32_set_ext_polarity(i, flow_type);
if (ret)
return ret;
}
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 1ccd2abed65f..1518ba31a80c 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -232,7 +232,7 @@ static int __init shirq_init(struct spear_shirq **shirq_blocks, int block_nr,
nr_irqs += shirq_blocks[i]->nr_irqs;
virq_base = irq_alloc_descs(-1, 0, nr_irqs, 0);
- if (IS_ERR_VALUE(virq_base)) {
+ if (virq_base < 0) {
pr_err("%s: irq desc alloc failed\n", __func__);
goto err_unmap;
}
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 3495d5d6547f..3bce44893021 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -53,11 +53,12 @@ static void led_timer_function(unsigned long data)
if (!led_cdev->blink_delay_on || !led_cdev->blink_delay_off) {
led_set_brightness_nosleep(led_cdev, LED_OFF);
+ led_cdev->flags &= ~LED_BLINK_SW;
return;
}
if (led_cdev->flags & LED_BLINK_ONESHOT_STOP) {
- led_cdev->flags &= ~LED_BLINK_ONESHOT_STOP;
+ led_cdev->flags &= ~(LED_BLINK_ONESHOT_STOP | LED_BLINK_SW);
return;
}
@@ -151,6 +152,7 @@ static void led_set_software_blink(struct led_classdev *led_cdev,
return;
}
+ led_cdev->flags |= LED_BLINK_SW;
mod_timer(&led_cdev->blink_timer, jiffies + 1);
}
@@ -219,6 +221,7 @@ void led_stop_software_blink(struct led_classdev *led_cdev)
del_timer_sync(&led_cdev->blink_timer);
led_cdev->blink_delay_on = 0;
led_cdev->blink_delay_off = 0;
+ led_cdev->flags &= ~LED_BLINK_SW;
}
EXPORT_SYMBOL_GPL(led_stop_software_blink);
@@ -226,10 +229,10 @@ void led_set_brightness(struct led_classdev *led_cdev,
enum led_brightness brightness)
{
/*
- * In case blinking is on delay brightness setting
+ * If software blink is active, delay brightness setting
* until the next timer tick.
*/
- if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) {
+ if (led_cdev->flags & LED_BLINK_SW) {
/*
* If we need to disable soft blinking delegate this to the
* work queue task to avoid problems in case we are called
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 4783bacb2e9d..a9145aa7f36a 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -91,6 +91,7 @@ static int led_pwm_add(struct device *dev, struct led_pwm_priv *priv,
struct led_pwm *led, struct device_node *child)
{
struct led_pwm_data *led_data = &priv->leds[priv->num_leds];
+ struct pwm_args pargs;
int ret;
led_data->active_low = led->active_low;
@@ -117,7 +118,15 @@ static int led_pwm_add(struct device *dev, struct led_pwm_priv *priv,
else
led_data->cdev.brightness_set_blocking = led_pwm_set_blocking;
- led_data->period = pwm_get_period(led_data->pwm);
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to the
+ * atomic PWM API.
+ */
+ pwm_apply_args(led_data->pwm);
+
+ pwm_get_args(led_data->pwm, &pargs);
+
+ led_data->period = pargs.period;
if (!led_data->period && (led->pwm_period_ns > 0))
led_data->period = led->pwm_period_ns;
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 410c39c62dc7..c9f386213e9e 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -19,6 +19,7 @@
#include <linux/sched.h>
#include <linux/leds.h>
#include <linux/reboot.h>
+#include <linux/suspend.h>
#include "../leds.h"
static int panic_heartbeats;
@@ -154,6 +155,30 @@ static struct led_trigger heartbeat_led_trigger = {
.deactivate = heartbeat_trig_deactivate,
};
+static int heartbeat_pm_notifier(struct notifier_block *nb,
+ unsigned long pm_event, void *unused)
+{
+ int rc;
+
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ case PM_HIBERNATION_PREPARE:
+ case PM_RESTORE_PREPARE:
+ led_trigger_unregister(&heartbeat_led_trigger);
+ break;
+ case PM_POST_SUSPEND:
+ case PM_POST_HIBERNATION:
+ case PM_POST_RESTORE:
+ rc = led_trigger_register(&heartbeat_led_trigger);
+ if (rc)
+ pr_err("could not re-register heartbeat trigger\n");
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
static int heartbeat_reboot_notifier(struct notifier_block *nb,
unsigned long code, void *unused)
{
@@ -168,6 +193,10 @@ static int heartbeat_panic_notifier(struct notifier_block *nb,
return NOTIFY_DONE;
}
+static struct notifier_block heartbeat_pm_nb = {
+ .notifier_call = heartbeat_pm_notifier,
+};
+
static struct notifier_block heartbeat_reboot_nb = {
.notifier_call = heartbeat_reboot_notifier,
};
@@ -184,12 +213,14 @@ static int __init heartbeat_trig_init(void)
atomic_notifier_chain_register(&panic_notifier_list,
&heartbeat_panic_nb);
register_reboot_notifier(&heartbeat_reboot_nb);
+ register_pm_notifier(&heartbeat_pm_nb);
}
return rc;
}
static void __exit heartbeat_trig_exit(void)
{
+ unregister_pm_notifier(&heartbeat_pm_nb);
unregister_reboot_notifier(&heartbeat_reboot_nb);
atomic_notifier_chain_unregister(&panic_notifier_list,
&heartbeat_panic_nb);
diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
index b73c6e7d28e4..6f2c8522e14a 100644
--- a/drivers/mcb/mcb-core.c
+++ b/drivers/mcb/mcb-core.c
@@ -61,21 +61,36 @@ static int mcb_probe(struct device *dev)
struct mcb_driver *mdrv = to_mcb_driver(dev->driver);
struct mcb_device *mdev = to_mcb_device(dev);
const struct mcb_device_id *found_id;
+ struct module *carrier_mod;
+ int ret;
found_id = mcb_match_id(mdrv->id_table, mdev);
if (!found_id)
return -ENODEV;
- return mdrv->probe(mdev, found_id);
+ carrier_mod = mdev->dev.parent->driver->owner;
+ if (!try_module_get(carrier_mod))
+ return -EINVAL;
+
+ get_device(dev);
+ ret = mdrv->probe(mdev, found_id);
+ if (ret)
+ module_put(carrier_mod);
+
+ return ret;
}
static int mcb_remove(struct device *dev)
{
struct mcb_driver *mdrv = to_mcb_driver(dev->driver);
struct mcb_device *mdev = to_mcb_device(dev);
+ struct module *carrier_mod;
mdrv->remove(mdev);
+ carrier_mod = mdev->dev.parent->driver->owner;
+ module_put(carrier_mod);
+
put_device(&mdev->dev);
return 0;
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 8eeab72b93e2..ca4abe1ccd8d 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -64,7 +64,6 @@
#include "btree.h"
#include <linux/blkdev.h>
-#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/random.h>
#include <trace/events/bcache.h>
@@ -288,7 +287,6 @@ do { \
if (kthread_should_stop()) \
return 0; \
\
- try_to_freeze(); \
schedule(); \
mutex_lock(&(ca)->set->bucket_lock); \
} \
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 22b9e34ceb75..eab505ee0027 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -27,7 +27,6 @@
#include <linux/slab.h>
#include <linux/bitops.h>
-#include <linux/freezer.h>
#include <linux/hash.h>
#include <linux/kthread.h>
#include <linux/prefetch.h>
@@ -1787,7 +1786,6 @@ again:
mutex_unlock(&c->bucket_lock);
- try_to_freeze();
schedule();
}
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index b9346cd9cda1..60123677b382 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -12,7 +12,6 @@
#include "writeback.h"
#include <linux/delay.h>
-#include <linux/freezer.h>
#include <linux/kthread.h>
#include <trace/events/bcache.h>
@@ -228,7 +227,6 @@ static void read_dirty(struct cached_dev *dc)
*/
while (!kthread_should_stop()) {
- try_to_freeze();
w = bch_keybuf_next(&dc->writeback_keys);
if (!w)
@@ -433,7 +431,6 @@ static int bch_writeback_thread(void *arg)
if (kthread_should_stop())
return 0;
- try_to_freeze();
schedule();
continue;
}
diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c
index 9e1731c565e7..e191e295c951 100644
--- a/drivers/media/i2c/adp1653.c
+++ b/drivers/media/i2c/adp1653.c
@@ -95,7 +95,7 @@ static int adp1653_get_fault(struct adp1653_flash *flash)
int rval;
fault = i2c_smbus_read_byte_data(client, ADP1653_REG_FAULT);
- if (IS_ERR_VALUE(fault))
+ if (fault < 0)
return fault;
flash->fault |= fault;
@@ -105,13 +105,13 @@ static int adp1653_get_fault(struct adp1653_flash *flash)
/* Clear faults. */
rval = i2c_smbus_write_byte_data(client, ADP1653_REG_OUT_SEL, 0);
- if (IS_ERR_VALUE(rval))
+ if (rval < 0)
return rval;
flash->led_mode->val = V4L2_FLASH_LED_MODE_NONE;
rval = adp1653_update_hw(flash);
- if (IS_ERR_VALUE(rval))
+ if (rval)
return rval;
return flash->fault;
@@ -158,7 +158,7 @@ static int adp1653_get_ctrl(struct v4l2_ctrl *ctrl)
int rval;
rval = adp1653_get_fault(flash);
- if (IS_ERR_VALUE(rval))
+ if (rval)
return rval;
ctrl->cur.val = 0;
@@ -184,7 +184,7 @@ static int adp1653_set_ctrl(struct v4l2_ctrl *ctrl)
int rval;
rval = adp1653_get_fault(flash);
- if (IS_ERR_VALUE(rval))
+ if (rval)
return rval;
if ((rval & (ADP1653_REG_FAULT_FLT_SCP |
ADP1653_REG_FAULT_FLT_OT |
diff --git a/drivers/media/platform/s5p-tv/mixer_drv.c b/drivers/media/platform/s5p-tv/mixer_drv.c
index 5ef67774971d..8a5d19469ddc 100644
--- a/drivers/media/platform/s5p-tv/mixer_drv.c
+++ b/drivers/media/platform/s5p-tv/mixer_drv.c
@@ -146,7 +146,7 @@ int mxr_power_get(struct mxr_device *mdev)
/* returning 1 means that power is already enabled,
* so zero success be returned */
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
return ret;
return 0;
}
diff --git a/drivers/media/usb/dvb-usb-v2/af9015.c b/drivers/media/usb/dvb-usb-v2/af9015.c
index 95a7388e89d4..09e0f58f6bb7 100644
--- a/drivers/media/usb/dvb-usb-v2/af9015.c
+++ b/drivers/media/usb/dvb-usb-v2/af9015.c
@@ -398,6 +398,8 @@ error:
}
#define AF9015_EEPROM_SIZE 256
+/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
+#define GOLDEN_RATIO_PRIME_32 0x9e370001UL
/* hash (and dump) eeprom */
static int af9015_eeprom_hash(struct dvb_usb_device *d)
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index d7723ce772b3..c04bc6afb965 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -1274,8 +1274,6 @@ struct uvc_xu_control_mapping32 {
static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
const struct uvc_xu_control_mapping32 __user *up)
{
- struct uvc_menu_info __user *umenus;
- struct uvc_menu_info __user *kmenus;
compat_caddr_t p;
if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
@@ -1292,17 +1290,7 @@ static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
if (__get_user(p, &up->menu_info))
return -EFAULT;
- umenus = compat_ptr(p);
- if (!access_ok(VERIFY_READ, umenus, kp->menu_count * sizeof(*umenus)))
- return -EFAULT;
-
- kmenus = compat_alloc_user_space(kp->menu_count * sizeof(*kmenus));
- if (kmenus == NULL)
- return -EFAULT;
- kp->menu_info = kmenus;
-
- if (copy_in_user(kmenus, umenus, kp->menu_count * sizeof(*umenus)))
- return -EFAULT;
+ kp->menu_info = compat_ptr(p);
return 0;
}
@@ -1310,10 +1298,6 @@ static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
static int uvc_v4l2_put_xu_mapping(const struct uvc_xu_control_mapping *kp,
struct uvc_xu_control_mapping32 __user *up)
{
- struct uvc_menu_info __user *umenus;
- struct uvc_menu_info __user *kmenus = kp->menu_info;
- compat_caddr_t p;
-
if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
__copy_to_user(up, kp, offsetof(typeof(*up), menu_info)) ||
__put_user(kp->menu_count, &up->menu_count))
@@ -1322,16 +1306,6 @@ static int uvc_v4l2_put_xu_mapping(const struct uvc_xu_control_mapping *kp,
if (__clear_user(up->reserved, sizeof(up->reserved)))
return -EFAULT;
- if (kp->menu_count == 0)
- return 0;
-
- if (get_user(p, &up->menu_info))
- return -EFAULT;
- umenus = compat_ptr(p);
-
- if (copy_in_user(umenus, kmenus, kp->menu_count * sizeof(*umenus)))
- return -EFAULT;
-
return 0;
}
@@ -1346,8 +1320,6 @@ struct uvc_xu_control_query32 {
static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
const struct uvc_xu_control_query32 __user *up)
{
- u8 __user *udata;
- u8 __user *kdata;
compat_caddr_t p;
if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
@@ -1361,17 +1333,7 @@ static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
if (__get_user(p, &up->data))
return -EFAULT;
- udata = compat_ptr(p);
- if (!access_ok(VERIFY_READ, udata, kp->size))
- return -EFAULT;
-
- kdata = compat_alloc_user_space(kp->size);
- if (kdata == NULL)
- return -EFAULT;
- kp->data = kdata;
-
- if (copy_in_user(kdata, udata, kp->size))
- return -EFAULT;
+ kp->data = compat_ptr(p);
return 0;
}
@@ -1379,26 +1341,10 @@ static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
static int uvc_v4l2_put_xu_query(const struct uvc_xu_control_query *kp,
struct uvc_xu_control_query32 __user *up)
{
- u8 __user *udata;
- u8 __user *kdata = kp->data;
- compat_caddr_t p;
-
if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
__copy_to_user(up, kp, offsetof(typeof(*up), data)))
return -EFAULT;
- if (kp->size == 0)
- return 0;
-
- if (get_user(p, &up->data))
- return -EFAULT;
- udata = compat_ptr(p);
- if (!access_ok(VERIFY_READ, udata, kp->size))
- return -EFAULT;
-
- if (copy_in_user(udata, kdata, kp->size))
- return -EFAULT;
-
return 0;
}
@@ -1408,47 +1354,44 @@ static int uvc_v4l2_put_xu_query(const struct uvc_xu_control_query *kp,
static long uvc_v4l2_compat_ioctl32(struct file *file,
unsigned int cmd, unsigned long arg)
{
+ struct uvc_fh *handle = file->private_data;
union {
struct uvc_xu_control_mapping xmap;
struct uvc_xu_control_query xqry;
} karg;
void __user *up = compat_ptr(arg);
- mm_segment_t old_fs;
long ret;
switch (cmd) {
case UVCIOC_CTRL_MAP32:
- cmd = UVCIOC_CTRL_MAP;
ret = uvc_v4l2_get_xu_mapping(&karg.xmap, up);
+ if (ret)
+ return ret;
+ ret = uvc_ioctl_ctrl_map(handle->chain, &karg.xmap);
+ if (ret)
+ return ret;
+ ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up);
+ if (ret)
+ return ret;
+
break;
case UVCIOC_CTRL_QUERY32:
- cmd = UVCIOC_CTRL_QUERY;
ret = uvc_v4l2_get_xu_query(&karg.xqry, up);
+ if (ret)
+ return ret;
+ ret = uvc_xu_ctrl_query(handle->chain, &karg.xqry);
+ if (ret)
+ return ret;
+ ret = uvc_v4l2_put_xu_query(&karg.xqry, up);
+ if (ret)
+ return ret;
break;
default:
return -ENOIOCTLCMD;
}
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- ret = video_ioctl2(file, cmd, (unsigned long)&karg);
- set_fs(old_fs);
-
- if (ret < 0)
- return ret;
-
- switch (cmd) {
- case UVCIOC_CTRL_MAP:
- ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up);
- break;
-
- case UVCIOC_CTRL_QUERY:
- ret = uvc_v4l2_put_xu_query(&karg.xqry, up);
- break;
- }
-
return ret;
}
#endif
diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c
index ca94bded3386..8bef4331bd51 100644
--- a/drivers/media/v4l2-core/v4l2-mc.c
+++ b/drivers/media/v4l2-core/v4l2-mc.c
@@ -1,7 +1,7 @@
/*
* Media Controller ancillary functions
*
- * Copyright (c) 2016 Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+ * Copyright (c) 2016 Mauro Carvalho Chehab <mchehab@kernel.org>
* Copyright (C) 2016 Shuah Khan <shuahkh@osg.samsung.com>
* Copyright (C) 2006-2010 Nokia Corporation
* Copyright (c) 2016 Intel Corporation.
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index c61a284133e0..81ddb17575a9 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -51,6 +51,7 @@ config TI_EMIF
config OMAP_GPMC
bool
+ select GPIOLIB
help
This driver is for the General Purpose Memory Controller (GPMC)
present on Texas Instruments SoCs (e.g. OMAP2+). GPMC allows
diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c
index 2a691da8c1c7..904b4af5f142 100644
--- a/drivers/memory/fsl_ifc.c
+++ b/drivers/memory/fsl_ifc.c
@@ -59,11 +59,11 @@ int fsl_ifc_find(phys_addr_t addr_base)
{
int i = 0;
- if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->regs)
+ if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->gregs)
return -ENODEV;
for (i = 0; i < fsl_ifc_ctrl_dev->banks; i++) {
- u32 cspr = ifc_in32(&fsl_ifc_ctrl_dev->regs->cspr_cs[i].cspr);
+ u32 cspr = ifc_in32(&fsl_ifc_ctrl_dev->gregs->cspr_cs[i].cspr);
if (cspr & CSPR_V && (cspr & CSPR_BA) ==
convert_ifc_address(addr_base))
return i;
@@ -75,7 +75,7 @@ EXPORT_SYMBOL(fsl_ifc_find);
static int fsl_ifc_ctrl_init(struct fsl_ifc_ctrl *ctrl)
{
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_global __iomem *ifc = ctrl->gregs;
/*
* Clear all the common status and event registers
@@ -104,7 +104,7 @@ static int fsl_ifc_ctrl_remove(struct platform_device *dev)
irq_dispose_mapping(ctrl->nand_irq);
irq_dispose_mapping(ctrl->irq);
- iounmap(ctrl->regs);
+ iounmap(ctrl->gregs);
dev_set_drvdata(&dev->dev, NULL);
kfree(ctrl);
@@ -122,7 +122,7 @@ static DEFINE_SPINLOCK(nand_irq_lock);
static u32 check_nand_stat(struct fsl_ifc_ctrl *ctrl)
{
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs;
unsigned long flags;
u32 stat;
@@ -157,7 +157,7 @@ static irqreturn_t fsl_ifc_nand_irq(int irqno, void *data)
static irqreturn_t fsl_ifc_ctrl_irq(int irqno, void *data)
{
struct fsl_ifc_ctrl *ctrl = data;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_global __iomem *ifc = ctrl->gregs;
u32 err_axiid, err_srcid, status, cs_err, err_addr;
irqreturn_t ret = IRQ_NONE;
@@ -215,6 +215,7 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev)
{
int ret = 0;
int version, banks;
+ void __iomem *addr;
dev_info(&dev->dev, "Freescale Integrated Flash Controller\n");
@@ -225,22 +226,13 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev)
dev_set_drvdata(&dev->dev, fsl_ifc_ctrl_dev);
/* IOMAP the entire IFC region */
- fsl_ifc_ctrl_dev->regs = of_iomap(dev->dev.of_node, 0);
- if (!fsl_ifc_ctrl_dev->regs) {
+ fsl_ifc_ctrl_dev->gregs = of_iomap(dev->dev.of_node, 0);
+ if (!fsl_ifc_ctrl_dev->gregs) {
dev_err(&dev->dev, "failed to get memory region\n");
ret = -ENODEV;
goto err;
}
- version = ifc_in32(&fsl_ifc_ctrl_dev->regs->ifc_rev) &
- FSL_IFC_VERSION_MASK;
- banks = (version == FSL_IFC_VERSION_1_0_0) ? 4 : 8;
- dev_info(&dev->dev, "IFC version %d.%d, %d banks\n",
- version >> 24, (version >> 16) & 0xf, banks);
-
- fsl_ifc_ctrl_dev->version = version;
- fsl_ifc_ctrl_dev->banks = banks;
-
if (of_property_read_bool(dev->dev.of_node, "little-endian")) {
fsl_ifc_ctrl_dev->little_endian = true;
dev_dbg(&dev->dev, "IFC REGISTERS are LITTLE endian\n");
@@ -249,8 +241,9 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev)
dev_dbg(&dev->dev, "IFC REGISTERS are BIG endian\n");
}
- version = ioread32be(&fsl_ifc_ctrl_dev->regs->ifc_rev) &
+ version = ifc_in32(&fsl_ifc_ctrl_dev->gregs->ifc_rev) &
FSL_IFC_VERSION_MASK;
+
banks = (version == FSL_IFC_VERSION_1_0_0) ? 4 : 8;
dev_info(&dev->dev, "IFC version %d.%d, %d banks\n",
version >> 24, (version >> 16) & 0xf, banks);
@@ -258,6 +251,13 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev)
fsl_ifc_ctrl_dev->version = version;
fsl_ifc_ctrl_dev->banks = banks;
+ addr = fsl_ifc_ctrl_dev->gregs;
+ if (version >= FSL_IFC_VERSION_2_0_0)
+ addr += PGOFFSET_64K;
+ else
+ addr += PGOFFSET_4K;
+ fsl_ifc_ctrl_dev->rregs = addr;
+
/* get the Controller level irq */
fsl_ifc_ctrl_dev->irq = irq_of_parse_and_map(dev->dev.of_node, 0);
if (fsl_ifc_ctrl_dev->irq == 0) {
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 21825ddce4a3..15508df24e5d 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -21,15 +21,15 @@
#include <linux/spinlock.h>
#include <linux/io.h>
#include <linux/module.h>
+#include <linux/gpio/driver.h>
#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
#include <linux/platform_device.h>
#include <linux/of.h>
#include <linux/of_address.h>
-#include <linux/of_mtd.h>
#include <linux/of_device.h>
#include <linux/of_platform.h>
#include <linux/omap-gpmc.h>
-#include <linux/mtd/nand.h>
#include <linux/pm_runtime.h>
#include <linux/platform_data/mtd-nand-omap2.h>
@@ -81,6 +81,8 @@
#define GPMC_CONFIG_LIMITEDADDRESS BIT(1)
+#define GPMC_STATUS_EMPTYWRITEBUFFERSTATUS BIT(0)
+
#define GPMC_CONFIG2_CSEXTRADELAY BIT(7)
#define GPMC_CONFIG3_ADVEXTRADELAY BIT(7)
#define GPMC_CONFIG4_OEEXTRADELAY BIT(7)
@@ -92,6 +94,14 @@
#define GPMC_CS_SIZE 0x30
#define GPMC_BCH_SIZE 0x10
+/*
+ * The first 1MB of GPMC address space is typically mapped to
+ * the internal ROM. Never allocate the first page, to
+ * facilitate bug detection; even if we didn't boot from ROM.
+ * As GPMC minimum partition size is 16MB we can only start from
+ * there.
+ */
+#define GPMC_MEM_START 0x1000000
#define GPMC_MEM_END 0x3FFFFFFF
#define GPMC_CHUNK_SHIFT 24 /* 16 MB */
@@ -125,7 +135,6 @@
#define GPMC_CONFIG_RDY_BSY 0x00000001
#define GPMC_CONFIG_DEV_SIZE 0x00000002
#define GPMC_CONFIG_DEV_TYPE 0x00000003
-#define GPMC_SET_IRQ_STATUS 0x00000004
#define GPMC_CONFIG1_WRAPBURST_SUPP (1 << 31)
#define GPMC_CONFIG1_READMULTIPLE_SUPP (1 << 30)
@@ -174,16 +183,12 @@
#define GPMC_CONFIG_WRITEPROTECT 0x00000010
#define WR_RD_PIN_MONITORING 0x00600000
-#define GPMC_ENABLE_IRQ 0x0000000d
-
/* ECC commands */
#define GPMC_ECC_READ 0 /* Reset Hardware ECC for read */
#define GPMC_ECC_WRITE 1 /* Reset Hardware ECC for write */
#define GPMC_ECC_READSYN 2 /* Reset before syndrom is read back */
-/* XXX: Only NAND irq has been considered,currently these are the only ones used
- */
-#define GPMC_NR_IRQ 2
+#define GPMC_NR_NAND_IRQS 2 /* number of NAND specific IRQs */
enum gpmc_clk_domain {
GPMC_CD_FCLK,
@@ -199,11 +204,6 @@ struct gpmc_cs_data {
struct resource mem;
};
-struct gpmc_client_irq {
- unsigned irq;
- u32 bitmask;
-};
-
/* Structure to save gpmc cs context */
struct gpmc_cs_config {
u32 config1;
@@ -231,9 +231,15 @@ struct omap3_gpmc_regs {
struct gpmc_cs_config cs_context[GPMC_CS_NUM];
};
-static struct gpmc_client_irq gpmc_client_irq[GPMC_NR_IRQ];
-static struct irq_chip gpmc_irq_chip;
-static int gpmc_irq_start;
+struct gpmc_device {
+ struct device *dev;
+ int irq;
+ struct irq_chip irq_chip;
+ struct gpio_chip gpio_chip;
+ int nirqs;
+};
+
+static struct irq_domain *gpmc_irq_domain;
static struct resource gpmc_mem_root;
static struct gpmc_cs_data gpmc_cs[GPMC_CS_NUM];
@@ -241,8 +247,6 @@ static DEFINE_SPINLOCK(gpmc_mem_lock);
/* Define chip-selects as reserved by default until probe completes */
static unsigned int gpmc_cs_num = GPMC_CS_NUM;
static unsigned int gpmc_nr_waitpins;
-static struct device *gpmc_dev;
-static int gpmc_irq;
static resource_size_t phys_base, mem_size;
static unsigned gpmc_capability;
static void __iomem *gpmc_base;
@@ -394,7 +398,7 @@ static void gpmc_cs_bool_timings(int cs, const struct gpmc_bool_timings *p)
gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
GPMC_CONFIG4_OEEXTRADELAY, p->oe_extra_delay);
gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
- GPMC_CONFIG4_OEEXTRADELAY, p->we_extra_delay);
+ GPMC_CONFIG4_WEEXTRADELAY, p->we_extra_delay);
gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG6,
GPMC_CONFIG6_CYCLE2CYCLESAMECSEN,
p->cycle2cyclesamecsen);
@@ -1054,14 +1058,6 @@ int gpmc_configure(int cmd, int wval)
u32 regval;
switch (cmd) {
- case GPMC_ENABLE_IRQ:
- gpmc_write_reg(GPMC_IRQENABLE, wval);
- break;
-
- case GPMC_SET_IRQ_STATUS:
- gpmc_write_reg(GPMC_IRQSTATUS, wval);
- break;
-
case GPMC_CONFIG_WP:
regval = gpmc_read_reg(GPMC_CONFIG);
if (wval)
@@ -1084,7 +1080,7 @@ void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs)
{
int i;
- reg->gpmc_status = gpmc_base + GPMC_STATUS;
+ reg->gpmc_status = NULL; /* deprecated */
reg->gpmc_nand_command = gpmc_base + GPMC_CS0_OFFSET +
GPMC_CS_NAND_COMMAND + GPMC_CS_SIZE * cs;
reg->gpmc_nand_address = gpmc_base + GPMC_CS0_OFFSET +
@@ -1118,87 +1114,201 @@ void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs)
}
}
-int gpmc_get_client_irq(unsigned irq_config)
+static bool gpmc_nand_writebuffer_empty(void)
{
- int i;
+ if (gpmc_read_reg(GPMC_STATUS) & GPMC_STATUS_EMPTYWRITEBUFFERSTATUS)
+ return true;
- if (hweight32(irq_config) > 1)
+ return false;
+}
+
+static struct gpmc_nand_ops nand_ops = {
+ .nand_writebuffer_empty = gpmc_nand_writebuffer_empty,
+};
+
+/**
+ * gpmc_omap_get_nand_ops - Get the GPMC NAND interface
+ * @regs: the GPMC NAND register map exclusive for NAND use.
+ * @cs: GPMC chip select number on which the NAND sits. The
+ * register map returned will be specific to this chip select.
+ *
+ * Returns NULL on error e.g. invalid cs.
+ */
+struct gpmc_nand_ops *gpmc_omap_get_nand_ops(struct gpmc_nand_regs *reg, int cs)
+{
+ if (cs >= gpmc_cs_num)
+ return NULL;
+
+ gpmc_update_nand_reg(reg, cs);
+
+ return &nand_ops;
+}
+EXPORT_SYMBOL_GPL(gpmc_omap_get_nand_ops);
+
+int gpmc_get_client_irq(unsigned irq_config)
+{
+ if (!gpmc_irq_domain) {
+ pr_warn("%s called before GPMC IRQ domain available\n",
+ __func__);
return 0;
+ }
- for (i = 0; i < GPMC_NR_IRQ; i++)
- if (gpmc_client_irq[i].bitmask & irq_config)
- return gpmc_client_irq[i].irq;
+ /* we restrict this to NAND IRQs only */
+ if (irq_config >= GPMC_NR_NAND_IRQS)
+ return 0;
- return 0;
+ return irq_create_mapping(gpmc_irq_domain, irq_config);
}
-static int gpmc_irq_endis(unsigned irq, bool endis)
+static int gpmc_irq_endis(unsigned long hwirq, bool endis)
{
- int i;
u32 regval;
- for (i = 0; i < GPMC_NR_IRQ; i++)
- if (irq == gpmc_client_irq[i].irq) {
- regval = gpmc_read_reg(GPMC_IRQENABLE);
- if (endis)
- regval |= gpmc_client_irq[i].bitmask;
- else
- regval &= ~gpmc_client_irq[i].bitmask;
- gpmc_write_reg(GPMC_IRQENABLE, regval);
- break;
- }
+ /* bits GPMC_NR_NAND_IRQS to 8 are reserved */
+ if (hwirq >= GPMC_NR_NAND_IRQS)
+ hwirq += 8 - GPMC_NR_NAND_IRQS;
+
+ regval = gpmc_read_reg(GPMC_IRQENABLE);
+ if (endis)
+ regval |= BIT(hwirq);
+ else
+ regval &= ~BIT(hwirq);
+ gpmc_write_reg(GPMC_IRQENABLE, regval);
return 0;
}
static void gpmc_irq_disable(struct irq_data *p)
{
- gpmc_irq_endis(p->irq, false);
+ gpmc_irq_endis(p->hwirq, false);
}
static void gpmc_irq_enable(struct irq_data *p)
{
- gpmc_irq_endis(p->irq, true);
+ gpmc_irq_endis(p->hwirq, true);
}
-static void gpmc_irq_noop(struct irq_data *data) { }
+static void gpmc_irq_mask(struct irq_data *d)
+{
+ gpmc_irq_endis(d->hwirq, false);
+}
-static unsigned int gpmc_irq_noop_ret(struct irq_data *data) { return 0; }
+static void gpmc_irq_unmask(struct irq_data *d)
+{
+ gpmc_irq_endis(d->hwirq, true);
+}
-static int gpmc_setup_irq(void)
+static void gpmc_irq_edge_config(unsigned long hwirq, bool rising_edge)
{
- int i;
u32 regval;
- if (!gpmc_irq)
+ /* NAND IRQs polarity is not configurable */
+ if (hwirq < GPMC_NR_NAND_IRQS)
+ return;
+
+ /* WAITPIN starts at BIT 8 */
+ hwirq += 8 - GPMC_NR_NAND_IRQS;
+
+ regval = gpmc_read_reg(GPMC_CONFIG);
+ if (rising_edge)
+ regval &= ~BIT(hwirq);
+ else
+ regval |= BIT(hwirq);
+
+ gpmc_write_reg(GPMC_CONFIG, regval);
+}
+
+static void gpmc_irq_ack(struct irq_data *d)
+{
+ unsigned int hwirq = d->hwirq;
+
+ /* skip reserved bits */
+ if (hwirq >= GPMC_NR_NAND_IRQS)
+ hwirq += 8 - GPMC_NR_NAND_IRQS;
+
+ /* Setting bit to 1 clears (or Acks) the interrupt */
+ gpmc_write_reg(GPMC_IRQSTATUS, BIT(hwirq));
+}
+
+static int gpmc_irq_set_type(struct irq_data *d, unsigned int trigger)
+{
+ /* can't set type for NAND IRQs */
+ if (d->hwirq < GPMC_NR_NAND_IRQS)
return -EINVAL;
- gpmc_irq_start = irq_alloc_descs(-1, 0, GPMC_NR_IRQ, 0);
- if (gpmc_irq_start < 0) {
- pr_err("irq_alloc_descs failed\n");
- return gpmc_irq_start;
+ /* We can support either rising or falling edge at a time */
+ if (trigger == IRQ_TYPE_EDGE_FALLING)
+ gpmc_irq_edge_config(d->hwirq, false);
+ else if (trigger == IRQ_TYPE_EDGE_RISING)
+ gpmc_irq_edge_config(d->hwirq, true);
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+static int gpmc_irq_map(struct irq_domain *d, unsigned int virq,
+ irq_hw_number_t hw)
+{
+ struct gpmc_device *gpmc = d->host_data;
+
+ irq_set_chip_data(virq, gpmc);
+ if (hw < GPMC_NR_NAND_IRQS) {
+ irq_modify_status(virq, IRQ_NOREQUEST, IRQ_NOAUTOEN);
+ irq_set_chip_and_handler(virq, &gpmc->irq_chip,
+ handle_simple_irq);
+ } else {
+ irq_set_chip_and_handler(virq, &gpmc->irq_chip,
+ handle_edge_irq);
}
- gpmc_irq_chip.name = "gpmc";
- gpmc_irq_chip.irq_startup = gpmc_irq_noop_ret;
- gpmc_irq_chip.irq_enable = gpmc_irq_enable;
- gpmc_irq_chip.irq_disable = gpmc_irq_disable;
- gpmc_irq_chip.irq_shutdown = gpmc_irq_noop;
- gpmc_irq_chip.irq_ack = gpmc_irq_noop;
- gpmc_irq_chip.irq_mask = gpmc_irq_noop;
- gpmc_irq_chip.irq_unmask = gpmc_irq_noop;
-
- gpmc_client_irq[0].bitmask = GPMC_IRQ_FIFOEVENTENABLE;
- gpmc_client_irq[1].bitmask = GPMC_IRQ_COUNT_EVENT;
-
- for (i = 0; i < GPMC_NR_IRQ; i++) {
- gpmc_client_irq[i].irq = gpmc_irq_start + i;
- irq_set_chip_and_handler(gpmc_client_irq[i].irq,
- &gpmc_irq_chip, handle_simple_irq);
- irq_modify_status(gpmc_client_irq[i].irq, IRQ_NOREQUEST,
- IRQ_NOAUTOEN);
+ return 0;
+}
+
+static const struct irq_domain_ops gpmc_irq_domain_ops = {
+ .map = gpmc_irq_map,
+ .xlate = irq_domain_xlate_twocell,
+};
+
+static irqreturn_t gpmc_handle_irq(int irq, void *data)
+{
+ int hwirq, virq;
+ u32 regval, regvalx;
+ struct gpmc_device *gpmc = data;
+
+ regval = gpmc_read_reg(GPMC_IRQSTATUS);
+ regvalx = regval;
+
+ if (!regval)
+ return IRQ_NONE;
+
+ for (hwirq = 0; hwirq < gpmc->nirqs; hwirq++) {
+ /* skip reserved status bits */
+ if (hwirq == GPMC_NR_NAND_IRQS)
+ regvalx >>= 8 - GPMC_NR_NAND_IRQS;
+
+ if (regvalx & BIT(hwirq)) {
+ virq = irq_find_mapping(gpmc_irq_domain, hwirq);
+ if (!virq) {
+ dev_warn(gpmc->dev,
+ "spurious irq detected hwirq %d, virq %d\n",
+ hwirq, virq);
+ }
+
+ generic_handle_irq(virq);
+ }
}
+ gpmc_write_reg(GPMC_IRQSTATUS, regval);
+
+ return IRQ_HANDLED;
+}
+
+static int gpmc_setup_irq(struct gpmc_device *gpmc)
+{
+ u32 regval;
+ int rc;
+
/* Disable interrupts */
gpmc_write_reg(GPMC_IRQENABLE, 0);
@@ -1206,22 +1316,45 @@ static int gpmc_setup_irq(void)
regval = gpmc_read_reg(GPMC_IRQSTATUS);
gpmc_write_reg(GPMC_IRQSTATUS, regval);
- return request_irq(gpmc_irq, gpmc_handle_irq, 0, "gpmc", NULL);
+ gpmc->irq_chip.name = "gpmc";
+ gpmc->irq_chip.irq_enable = gpmc_irq_enable;
+ gpmc->irq_chip.irq_disable = gpmc_irq_disable;
+ gpmc->irq_chip.irq_ack = gpmc_irq_ack;
+ gpmc->irq_chip.irq_mask = gpmc_irq_mask;
+ gpmc->irq_chip.irq_unmask = gpmc_irq_unmask;
+ gpmc->irq_chip.irq_set_type = gpmc_irq_set_type;
+
+ gpmc_irq_domain = irq_domain_add_linear(gpmc->dev->of_node,
+ gpmc->nirqs,
+ &gpmc_irq_domain_ops,
+ gpmc);
+ if (!gpmc_irq_domain) {
+ dev_err(gpmc->dev, "IRQ domain add failed\n");
+ return -ENODEV;
+ }
+
+ rc = request_irq(gpmc->irq, gpmc_handle_irq, 0, "gpmc", gpmc);
+ if (rc) {
+ dev_err(gpmc->dev, "failed to request irq %d: %d\n",
+ gpmc->irq, rc);
+ irq_domain_remove(gpmc_irq_domain);
+ gpmc_irq_domain = NULL;
+ }
+
+ return rc;
}
-static int gpmc_free_irq(void)
+static int gpmc_free_irq(struct gpmc_device *gpmc)
{
- int i;
+ int hwirq;
- if (gpmc_irq)
- free_irq(gpmc_irq, NULL);
+ free_irq(gpmc->irq, gpmc);
- for (i = 0; i < GPMC_NR_IRQ; i++) {
- irq_set_handler(gpmc_client_irq[i].irq, NULL);
- irq_set_chip(gpmc_client_irq[i].irq, &no_irq_chip);
- }
+ for (hwirq = 0; hwirq < gpmc->nirqs; hwirq++)
+ irq_dispose_mapping(irq_find_mapping(gpmc_irq_domain, hwirq));
- irq_free_descs(gpmc_irq_start, GPMC_NR_IRQ);
+ irq_domain_remove(gpmc_irq_domain);
+ gpmc_irq_domain = NULL;
return 0;
}
@@ -1242,12 +1375,7 @@ static void gpmc_mem_init(void)
{
int cs;
- /*
- * The first 1MB of GPMC address space is typically mapped to
- * the internal ROM. Never allocate the first page, to
- * facilitate bug detection; even if we didn't boot from ROM.
- */
- gpmc_mem_root.start = SZ_1M;
+ gpmc_mem_root.start = GPMC_MEM_START;
gpmc_mem_root.end = GPMC_MEM_END;
/* Reserve all regions that has been set up by bootloader */
@@ -1796,105 +1924,6 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np,
of_property_read_bool(np, "gpmc,time-para-granularity");
}
-#if IS_ENABLED(CONFIG_MTD_NAND)
-
-static const char * const nand_xfer_types[] = {
- [NAND_OMAP_PREFETCH_POLLED] = "prefetch-polled",
- [NAND_OMAP_POLLED] = "polled",
- [NAND_OMAP_PREFETCH_DMA] = "prefetch-dma",
- [NAND_OMAP_PREFETCH_IRQ] = "prefetch-irq",
-};
-
-static int gpmc_probe_nand_child(struct platform_device *pdev,
- struct device_node *child)
-{
- u32 val;
- const char *s;
- struct gpmc_timings gpmc_t;
- struct omap_nand_platform_data *gpmc_nand_data;
-
- if (of_property_read_u32(child, "reg", &val) < 0) {
- dev_err(&pdev->dev, "%s has no 'reg' property\n",
- child->full_name);
- return -ENODEV;
- }
-
- gpmc_nand_data = devm_kzalloc(&pdev->dev, sizeof(*gpmc_nand_data),
- GFP_KERNEL);
- if (!gpmc_nand_data)
- return -ENOMEM;
-
- gpmc_nand_data->cs = val;
- gpmc_nand_data->of_node = child;
-
- /* Detect availability of ELM module */
- gpmc_nand_data->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0);
- if (gpmc_nand_data->elm_of_node == NULL)
- gpmc_nand_data->elm_of_node =
- of_parse_phandle(child, "elm_id", 0);
-
- /* select ecc-scheme for NAND */
- if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) {
- pr_err("%s: ti,nand-ecc-opt not found\n", __func__);
- return -ENODEV;
- }
-
- if (!strcmp(s, "sw"))
- gpmc_nand_data->ecc_opt = OMAP_ECC_HAM1_CODE_SW;
- else if (!strcmp(s, "ham1") ||
- !strcmp(s, "hw") || !strcmp(s, "hw-romcode"))
- gpmc_nand_data->ecc_opt =
- OMAP_ECC_HAM1_CODE_HW;
- else if (!strcmp(s, "bch4"))
- if (gpmc_nand_data->elm_of_node)
- gpmc_nand_data->ecc_opt =
- OMAP_ECC_BCH4_CODE_HW;
- else
- gpmc_nand_data->ecc_opt =
- OMAP_ECC_BCH4_CODE_HW_DETECTION_SW;
- else if (!strcmp(s, "bch8"))
- if (gpmc_nand_data->elm_of_node)
- gpmc_nand_data->ecc_opt =
- OMAP_ECC_BCH8_CODE_HW;
- else
- gpmc_nand_data->ecc_opt =
- OMAP_ECC_BCH8_CODE_HW_DETECTION_SW;
- else if (!strcmp(s, "bch16"))
- if (gpmc_nand_data->elm_of_node)
- gpmc_nand_data->ecc_opt =
- OMAP_ECC_BCH16_CODE_HW;
- else
- pr_err("%s: BCH16 requires ELM support\n", __func__);
- else
- pr_err("%s: ti,nand-ecc-opt invalid value\n", __func__);
-
- /* select data transfer mode for NAND controller */
- if (!of_property_read_string(child, "ti,nand-xfer-type", &s))
- for (val = 0; val < ARRAY_SIZE(nand_xfer_types); val++)
- if (!strcasecmp(s, nand_xfer_types[val])) {
- gpmc_nand_data->xfer_type = val;
- break;
- }
-
- gpmc_nand_data->flash_bbt = of_get_nand_on_flash_bbt(child);
-
- val = of_get_nand_bus_width(child);
- if (val == 16)
- gpmc_nand_data->devsize = NAND_BUSWIDTH_16;
-
- gpmc_read_timings_dt(child, &gpmc_t);
- gpmc_nand_init(gpmc_nand_data, &gpmc_t);
-
- return 0;
-}
-#else
-static int gpmc_probe_nand_child(struct platform_device *pdev,
- struct device_node *child)
-{
- return 0;
-}
-#endif
-
#if IS_ENABLED(CONFIG_MTD_ONENAND)
static int gpmc_probe_onenand_child(struct platform_device *pdev,
struct device_node *child)
@@ -1950,6 +1979,8 @@ static int gpmc_probe_generic_child(struct platform_device *pdev,
const char *name;
int ret, cs;
u32 val;
+ struct gpio_desc *waitpin_desc = NULL;
+ struct gpmc_device *gpmc = platform_get_drvdata(pdev);
if (of_property_read_u32(child, "reg", &cs) < 0) {
dev_err(&pdev->dev, "%s has no 'reg' property\n",
@@ -2010,23 +2041,80 @@ static int gpmc_probe_generic_child(struct platform_device *pdev,
if (ret < 0) {
dev_err(&pdev->dev, "cannot remap GPMC CS %d to %pa\n",
cs, &res.start);
+ if (res.start < GPMC_MEM_START) {
+ dev_info(&pdev->dev,
+ "GPMC CS %d start cannot be lesser than 0x%x\n",
+ cs, GPMC_MEM_START);
+ } else if (res.end > GPMC_MEM_END) {
+ dev_info(&pdev->dev,
+ "GPMC CS %d end cannot be greater than 0x%x\n",
+ cs, GPMC_MEM_END);
+ }
goto err;
}
- ret = of_property_read_u32(child, "bank-width", &gpmc_s.device_width);
- if (ret < 0)
- goto err;
+ if (of_node_cmp(child->name, "nand") == 0) {
+ /* Warn about older DT blobs with no compatible property */
+ if (!of_property_read_bool(child, "compatible")) {
+ dev_warn(&pdev->dev,
+ "Incompatible NAND node: missing compatible");
+ ret = -EINVAL;
+ goto err;
+ }
+ }
+
+ if (of_device_is_compatible(child, "ti,omap2-nand")) {
+ /* NAND specific setup */
+ val = 8;
+ of_property_read_u32(child, "nand-bus-width", &val);
+ switch (val) {
+ case 8:
+ gpmc_s.device_width = GPMC_DEVWIDTH_8BIT;
+ break;
+ case 16:
+ gpmc_s.device_width = GPMC_DEVWIDTH_16BIT;
+ break;
+ default:
+ dev_err(&pdev->dev, "%s: invalid 'nand-bus-width'\n",
+ child->name);
+ ret = -EINVAL;
+ goto err;
+ }
+
+ /* disable write protect */
+ gpmc_configure(GPMC_CONFIG_WP, 0);
+ gpmc_s.device_nand = true;
+ } else {
+ ret = of_property_read_u32(child, "bank-width",
+ &gpmc_s.device_width);
+ if (ret < 0)
+ goto err;
+ }
+
+ /* Reserve wait pin if it is required and valid */
+ if (gpmc_s.wait_on_read || gpmc_s.wait_on_write) {
+ unsigned int wait_pin = gpmc_s.wait_pin;
+
+ waitpin_desc = gpiochip_request_own_desc(&gpmc->gpio_chip,
+ wait_pin, "WAITPIN");
+ if (IS_ERR(waitpin_desc)) {
+ dev_err(&pdev->dev, "invalid wait-pin: %d\n", wait_pin);
+ ret = PTR_ERR(waitpin_desc);
+ goto err;
+ }
+ }
gpmc_cs_show_timings(cs, "before gpmc_cs_program_settings");
+
ret = gpmc_cs_program_settings(cs, &gpmc_s);
if (ret < 0)
- goto err;
+ goto err_cs;
ret = gpmc_cs_set_timings(cs, &gpmc_t, &gpmc_s);
if (ret) {
dev_err(&pdev->dev, "failed to set gpmc timings for: %s\n",
child->name);
- goto err;
+ goto err_cs;
}
/* Clear limited address i.e. enable A26-A11 */
@@ -2057,16 +2145,81 @@ err_child_fail:
dev_err(&pdev->dev, "failed to create gpmc child %s\n", child->name);
ret = -ENODEV;
+err_cs:
+ if (waitpin_desc)
+ gpiochip_free_own_desc(waitpin_desc);
+
err:
gpmc_cs_free(cs);
return ret;
}
+static int gpmc_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+ return 1; /* we're input only */
+}
+
+static int gpmc_gpio_direction_input(struct gpio_chip *chip,
+ unsigned int offset)
+{
+ return 0; /* we're input only */
+}
+
+static int gpmc_gpio_direction_output(struct gpio_chip *chip,
+ unsigned int offset, int value)
+{
+ return -EINVAL; /* we're input only */
+}
+
+static void gpmc_gpio_set(struct gpio_chip *chip, unsigned int offset,
+ int value)
+{
+}
+
+static int gpmc_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+ u32 reg;
+
+ offset += 8;
+
+ reg = gpmc_read_reg(GPMC_STATUS) & BIT(offset);
+
+ return !!reg;
+}
+
+static int gpmc_gpio_init(struct gpmc_device *gpmc)
+{
+ int ret;
+
+ gpmc->gpio_chip.parent = gpmc->dev;
+ gpmc->gpio_chip.owner = THIS_MODULE;
+ gpmc->gpio_chip.label = DEVICE_NAME;
+ gpmc->gpio_chip.ngpio = gpmc_nr_waitpins;
+ gpmc->gpio_chip.get_direction = gpmc_gpio_get_direction;
+ gpmc->gpio_chip.direction_input = gpmc_gpio_direction_input;
+ gpmc->gpio_chip.direction_output = gpmc_gpio_direction_output;
+ gpmc->gpio_chip.set = gpmc_gpio_set;
+ gpmc->gpio_chip.get = gpmc_gpio_get;
+ gpmc->gpio_chip.base = -1;
+
+ ret = gpiochip_add(&gpmc->gpio_chip);
+ if (ret < 0) {
+ dev_err(gpmc->dev, "could not register gpio chip: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void gpmc_gpio_exit(struct gpmc_device *gpmc)
+{
+ gpiochip_remove(&gpmc->gpio_chip);
+}
+
static int gpmc_probe_dt(struct platform_device *pdev)
{
int ret;
- struct device_node *child;
const struct of_device_id *of_id =
of_match_device(gpmc_dt_ids, &pdev->dev);
@@ -2094,17 +2247,26 @@ static int gpmc_probe_dt(struct platform_device *pdev)
return ret;
}
+ return 0;
+}
+
+static int gpmc_probe_dt_children(struct platform_device *pdev)
+{
+ int ret;
+ struct device_node *child;
+
for_each_available_child_of_node(pdev->dev.of_node, child) {
if (!child->name)
continue;
- if (of_node_cmp(child->name, "nand") == 0)
- ret = gpmc_probe_nand_child(pdev, child);
- else if (of_node_cmp(child->name, "onenand") == 0)
+ if (of_node_cmp(child->name, "onenand") == 0)
ret = gpmc_probe_onenand_child(pdev, child);
else
ret = gpmc_probe_generic_child(pdev, child);
+
+ if (ret)
+ return ret;
}
return 0;
@@ -2114,6 +2276,11 @@ static int gpmc_probe_dt(struct platform_device *pdev)
{
return 0;
}
+
+static int gpmc_probe_dt_children(struct platform_device *pdev)
+{
+ return 0;
+}
#endif
static int gpmc_probe(struct platform_device *pdev)
@@ -2121,6 +2288,14 @@ static int gpmc_probe(struct platform_device *pdev)
int rc;
u32 l;
struct resource *res;
+ struct gpmc_device *gpmc;
+
+ gpmc = devm_kzalloc(&pdev->dev, sizeof(*gpmc), GFP_KERNEL);
+ if (!gpmc)
+ return -ENOMEM;
+
+ gpmc->dev = &pdev->dev;
+ platform_set_drvdata(pdev, gpmc);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (res == NULL)
@@ -2134,15 +2309,16 @@ static int gpmc_probe(struct platform_device *pdev)
return PTR_ERR(gpmc_base);
res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
- if (res == NULL)
- dev_warn(&pdev->dev, "Failed to get resource: irq\n");
- else
- gpmc_irq = res->start;
+ if (!res) {
+ dev_err(&pdev->dev, "Failed to get resource: irq\n");
+ return -ENOENT;
+ }
+
+ gpmc->irq = res->start;
gpmc_l3_clk = devm_clk_get(&pdev->dev, "fck");
if (IS_ERR(gpmc_l3_clk)) {
dev_err(&pdev->dev, "Failed to get GPMC fck\n");
- gpmc_irq = 0;
return PTR_ERR(gpmc_l3_clk);
}
@@ -2151,11 +2327,18 @@ static int gpmc_probe(struct platform_device *pdev)
return -EINVAL;
}
+ if (pdev->dev.of_node) {
+ rc = gpmc_probe_dt(pdev);
+ if (rc)
+ return rc;
+ } else {
+ gpmc_cs_num = GPMC_CS_NUM;
+ gpmc_nr_waitpins = GPMC_NR_WAITPINS;
+ }
+
pm_runtime_enable(&pdev->dev);
pm_runtime_get_sync(&pdev->dev);
- gpmc_dev = &pdev->dev;
-
l = gpmc_read_reg(GPMC_REVISION);
/*
@@ -2174,36 +2357,51 @@ static int gpmc_probe(struct platform_device *pdev)
gpmc_capability = GPMC_HAS_WR_ACCESS | GPMC_HAS_WR_DATA_MUX_BUS;
if (GPMC_REVISION_MAJOR(l) > 0x5)
gpmc_capability |= GPMC_HAS_MUX_AAD;
- dev_info(gpmc_dev, "GPMC revision %d.%d\n", GPMC_REVISION_MAJOR(l),
+ dev_info(gpmc->dev, "GPMC revision %d.%d\n", GPMC_REVISION_MAJOR(l),
GPMC_REVISION_MINOR(l));
gpmc_mem_init();
-
- if (gpmc_setup_irq() < 0)
- dev_warn(gpmc_dev, "gpmc_setup_irq failed\n");
-
- if (!pdev->dev.of_node) {
- gpmc_cs_num = GPMC_CS_NUM;
- gpmc_nr_waitpins = GPMC_NR_WAITPINS;
+ rc = gpmc_gpio_init(gpmc);
+ if (rc)
+ goto gpio_init_failed;
+
+ gpmc->nirqs = GPMC_NR_NAND_IRQS + gpmc_nr_waitpins;
+ rc = gpmc_setup_irq(gpmc);
+ if (rc) {
+ dev_err(gpmc->dev, "gpmc_setup_irq failed\n");
+ goto setup_irq_failed;
}
- rc = gpmc_probe_dt(pdev);
+ rc = gpmc_probe_dt_children(pdev);
if (rc < 0) {
- pm_runtime_put_sync(&pdev->dev);
- dev_err(gpmc_dev, "failed to probe DT parameters\n");
- return rc;
+ dev_err(gpmc->dev, "failed to probe DT children\n");
+ goto dt_children_failed;
}
return 0;
+
+dt_children_failed:
+ gpmc_free_irq(gpmc);
+setup_irq_failed:
+ gpmc_gpio_exit(gpmc);
+gpio_init_failed:
+ gpmc_mem_exit();
+ pm_runtime_put_sync(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+
+ return rc;
}
static int gpmc_remove(struct platform_device *pdev)
{
- gpmc_free_irq();
+ struct gpmc_device *gpmc = platform_get_drvdata(pdev);
+
+ gpmc_free_irq(gpmc);
+ gpmc_gpio_exit(gpmc);
gpmc_mem_exit();
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
- gpmc_dev = NULL;
+
return 0;
}
@@ -2249,25 +2447,6 @@ static __exit void gpmc_exit(void)
postcore_initcall(gpmc_init);
module_exit(gpmc_exit);
-static irqreturn_t gpmc_handle_irq(int irq, void *dev)
-{
- int i;
- u32 regval;
-
- regval = gpmc_read_reg(GPMC_IRQSTATUS);
-
- if (!regval)
- return IRQ_NONE;
-
- for (i = 0; i < GPMC_NR_IRQ; i++)
- if (regval & gpmc_client_irq[i].bitmask)
- generic_handle_irq(gpmc_client_irq[i].irq);
-
- gpmc_write_reg(GPMC_IRQSTATUS, regval);
-
- return IRQ_HANDLED;
-}
-
static struct omap3_gpmc_regs gpmc_context;
void omap3_gpmc_save_context(void)
diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c
index 199d261990be..f32fbb8e8129 100644
--- a/drivers/mfd/max77620.c
+++ b/drivers/mfd/max77620.c
@@ -203,6 +203,7 @@ static int max77620_get_fps_period_reg_value(struct max77620_chip *chip,
break;
case MAX77620:
fps_min_period = MAX77620_FPS_PERIOD_MIN_US;
+ break;
default:
return -EINVAL;
}
@@ -236,6 +237,7 @@ static int max77620_config_fps(struct max77620_chip *chip,
break;
case MAX77620:
fps_max_period = MAX77620_FPS_PERIOD_MAX_US;
+ break;
default:
return -EINVAL;
}
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 40e51b0baa46..b46c0cfc27d9 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -696,7 +696,7 @@ int twl4030_init_irq(struct device *dev, int irq_num)
nr_irqs = TWL4030_PWR_NR_IRQS + TWL4030_CORE_NR_IRQS;
irq_base = irq_alloc_descs(-1, 0, nr_irqs, 0);
- if (IS_ERR_VALUE(irq_base)) {
+ if (irq_base < 0) {
dev_err(dev, "Fail to allocate IRQ descs\n");
return irq_base;
}
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index eed254da63a8..641c1a566687 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -730,7 +730,7 @@ static void mei_cl_wake_all(struct mei_cl *cl)
/* synchronized under device mutex */
if (waitqueue_active(&cl->wait)) {
cl_dbg(dev, cl, "Waking up ctrl write clients!\n");
- wake_up_interruptible(&cl->wait);
+ wake_up(&cl->wait);
}
}
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index ddc96206288a..e62fde3ac431 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -618,6 +618,10 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
ioc_err = __mmc_blk_ioctl_cmd(card, md, idata);
+ /* Always switch back to main area after RPMB access */
+ if (md->area_type & MMC_BLK_DATA_AREA_RPMB)
+ mmc_blk_part_switch(card, dev_get_drvdata(&card->dev));
+
mmc_put_card(card);
err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata);
@@ -685,6 +689,10 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev,
for (i = 0; i < num_of_cmds && !ioc_err; i++)
ioc_err = __mmc_blk_ioctl_cmd(card, md, idata[i]);
+ /* Always switch back to main area after RPMB access */
+ if (md->area_type & MMC_BLK_DATA_AREA_RPMB)
+ mmc_blk_part_switch(card, dev_get_drvdata(&card->dev));
+
mmc_put_card(card);
/* copy to user if data and response */
@@ -748,16 +756,25 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
if (mmc_card_mmc(card)) {
u8 part_config = card->ext_csd.part_config;
+ if (md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+ mmc_retune_pause(card->host);
+
part_config &= ~EXT_CSD_PART_CONFIG_ACC_MASK;
part_config |= md->part_type;
ret = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
EXT_CSD_PART_CONFIG, part_config,
card->ext_csd.part_time);
- if (ret)
+ if (ret) {
+ if (md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+ mmc_retune_unpause(card->host);
return ret;
+ }
card->ext_csd.part_config = part_config;
+
+ if (main_md->part_curr == EXT_CSD_PART_CONFIG_ACC_RPMB)
+ mmc_retune_unpause(card->host);
}
main_md->part_curr = md->part_type;
@@ -2519,11 +2536,12 @@ static const struct mmc_fixup blk_fixups[] =
MMC_QUIRK_BLK_NO_CMD23),
/*
- * Some Micron MMC cards needs longer data read timeout than
- * indicated in CSD.
+ * Some MMC cards need longer data read timeout than indicated in CSD.
*/
MMC_FIXUP(CID_NAME_ANY, CID_MANFID_MICRON, 0x200, add_quirk_mmc,
MMC_QUIRK_LONG_READ_TIME),
+ MMC_FIXUP("008GE0", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+ MMC_QUIRK_LONG_READ_TIME),
/*
* On these Samsung MoviNAND parts, performing secure erase or
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 99275e40bf2f..8b4dfd45433b 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -875,11 +875,11 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card)
/*
* Some cards require longer data read timeout than indicated in CSD.
* Address this by setting the read timeout to a "reasonably high"
- * value. For the cards tested, 300ms has proven enough. If necessary,
+ * value. For the cards tested, 600ms has proven enough. If necessary,
* this value can be increased if other problematic cards require this.
*/
if (mmc_card_long_read_time(card) && data->flags & MMC_DATA_READ) {
- data->timeout_ns = 300000000;
+ data->timeout_ns = 600000000;
data->timeout_clks = 0;
}
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index e0a3ee16c0d3..1be42fab1a30 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -68,8 +68,32 @@ void mmc_retune_enable(struct mmc_host *host)
jiffies + host->retune_period * HZ);
}
+/*
+ * Pause re-tuning for a small set of operations. The pause begins after the
+ * next command and after first doing re-tuning.
+ */
+void mmc_retune_pause(struct mmc_host *host)
+{
+ if (!host->retune_paused) {
+ host->retune_paused = 1;
+ mmc_retune_needed(host);
+ mmc_retune_hold(host);
+ }
+}
+EXPORT_SYMBOL(mmc_retune_pause);
+
+void mmc_retune_unpause(struct mmc_host *host)
+{
+ if (host->retune_paused) {
+ host->retune_paused = 0;
+ mmc_retune_release(host);
+ }
+}
+EXPORT_SYMBOL(mmc_retune_unpause);
+
void mmc_retune_disable(struct mmc_host *host)
{
+ mmc_retune_unpause(host);
host->can_retune = 0;
del_timer_sync(&host->retune_timer);
host->retune_now = 0;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index b81b08f81325..5d438ad3ee32 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1276,7 +1276,7 @@ static int mmc_select_hs200(struct mmc_card *card)
* switch to HS200 mode if bus width is set successfully.
*/
err = mmc_select_bus_width(card);
- if (!IS_ERR_VALUE(err)) {
+ if (err >= 0) {
val = EXT_CSD_TIMING_HS200 |
card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
@@ -1583,7 +1583,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
} else if (mmc_card_hs(card)) {
/* Select the desired bus width optionally */
err = mmc_select_bus_width(card);
- if (!IS_ERR_VALUE(err)) {
+ if (err >= 0) {
err = mmc_select_hs_ddr(card);
if (err)
goto free_card;
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 8c20b81cafd8..358b0dc853b0 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -66,6 +66,70 @@ static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
/* Make sure we use phases which we can enumerate with */
if (!IS_ERR(priv->sample_clk))
clk_set_phase(priv->sample_clk, priv->default_sample_phase);
+
+ /*
+ * Set the drive phase offset based on speed mode to achieve hold times.
+ *
+ * NOTE: this is _not_ a value that is dynamically tuned and is also
+ * _not_ a value that will vary from board to board. It is a value
+ * that could vary between different SoC models if they had massively
+ * different output clock delays inside their dw_mmc IP block (delay_o),
+ * but since it's OK to overshoot a little we don't need to do complex
+ * calculations and can pick values that will just work for everyone.
+ *
+ * When picking values we'll stick with picking 0/90/180/270 since
+ * those can be made very accurately on all known Rockchip SoCs.
+ *
+ * Note that these values match values from the DesignWare Databook
+ * tables for the most part except for SDR12 and "ID mode". For those
+ * two modes the databook calculations assume a clock in of 50MHz. As
+ * seen above, we always use a clock in rate that is exactly the
+ * card's input clock (times RK3288_CLKGEN_DIV, but that gets divided
+ * back out before the controller sees it).
+ *
+ * From measurement of a single device, it appears that delay_o is
+ * about .5 ns. Since we try to leave a bit of margin, it's expected
+ * that numbers here will be fine even with much larger delay_o
+ * (the 1.4 ns assumed by the DesignWare Databook would result in the
+ * same results, for instance).
+ */
+ if (!IS_ERR(priv->drv_clk)) {
+ int phase;
+
+ /*
+ * In almost all cases a 90 degree phase offset will provide
+ * sufficient hold times across all valid input clock rates
+ * assuming delay_o is not absurd for a given SoC. We'll use
+ * that as a default.
+ */
+ phase = 90;
+
+ switch (ios->timing) {
+ case MMC_TIMING_MMC_DDR52:
+ /*
+ * Since clock in rate with MMC_DDR52 is doubled when
+ * bus width is 8 we need to double the phase offset
+ * to get the same timings.
+ */
+ if (ios->bus_width == MMC_BUS_WIDTH_8)
+ phase = 180;
+ break;
+ case MMC_TIMING_UHS_SDR104:
+ case MMC_TIMING_MMC_HS200:
+ /*
+ * In the case of 150 MHz clock (typical max for
+ * Rockchip SoCs), 90 degree offset will add a delay
+ * of 1.67 ns. That will meet min hold time of .8 ns
+ * as long as clock output delay is < .87 ns. On
+ * SoCs measured this seems to be OK, but it doesn't
+ * hurt to give margin here, so we use 180.
+ */
+ phase = 180;
+ break;
+ }
+
+ clk_set_phase(priv->drv_clk, phase);
+ }
}
#define NUM_PHASES 360
@@ -233,10 +297,10 @@ static int dw_mci_rockchip_init(struct dw_mci *host)
/* Common capabilities of RK3288 SoC */
static unsigned long dw_mci_rk3288_dwmmc_caps[4] = {
- MMC_CAP_ERASE,
- MMC_CAP_ERASE,
- MMC_CAP_ERASE,
- MMC_CAP_ERASE,
+ MMC_CAP_ERASE | MMC_CAP_CMD23,
+ MMC_CAP_ERASE | MMC_CAP_CMD23,
+ MMC_CAP_ERASE | MMC_CAP_CMD23,
+ MMC_CAP_ERASE | MMC_CAP_CMD23,
};
static const struct dw_mci_drv_data rk2928_drv_data = {
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 9dd1bd358434..2cc6123b1df9 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1431,7 +1431,7 @@ static int dw_mci_get_ro(struct mmc_host *mmc)
int gpio_ro = mmc_gpio_get_ro(mmc);
/* Use platform get_ro function, else try on board write protect */
- if (!IS_ERR_VALUE(gpio_ro))
+ if (gpio_ro >= 0)
read_only = gpio_ro;
else
read_only =
@@ -1454,7 +1454,7 @@ static int dw_mci_get_cd(struct mmc_host *mmc)
if ((mmc->caps & MMC_CAP_NEEDS_POLL) ||
(mmc->caps & MMC_CAP_NONREMOVABLE))
present = 1;
- else if (!IS_ERR_VALUE(gpio_cd))
+ else if (gpio_cd >= 0)
present = gpio_cd;
else
present = (mci_readl(slot->host, CDETECT) & (1 << slot->id))
@@ -2595,13 +2595,13 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
/* Useful defaults if platform data is unset. */
if (host->use_dma == TRANS_MODE_IDMAC) {
mmc->max_segs = host->ring_size;
- mmc->max_blk_size = 65536;
+ mmc->max_blk_size = 65535;
mmc->max_seg_size = 0x1000;
mmc->max_req_size = mmc->max_seg_size * host->ring_size;
mmc->max_blk_count = mmc->max_req_size / 512;
} else if (host->use_dma == TRANS_MODE_EDMAC) {
mmc->max_segs = 64;
- mmc->max_blk_size = 65536;
+ mmc->max_blk_size = 65535;
mmc->max_blk_count = 65535;
mmc->max_req_size =
mmc->max_blk_size * mmc->max_blk_count;
@@ -2609,7 +2609,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
} else {
/* TRANS_MODE_PIO */
mmc->max_segs = 64;
- mmc->max_blk_size = 65536; /* BLKSIZ is 16 bits */
+ mmc->max_blk_size = 65535; /* BLKSIZ is 16 bits */
mmc->max_blk_count = 512;
mmc->max_req_size = mmc->max_blk_size *
mmc->max_blk_count;
@@ -2927,7 +2927,7 @@ static void dw_mci_enable_cd(struct dw_mci *host)
if (slot->mmc->caps & MMC_CAP_NEEDS_POLL)
return;
- if (IS_ERR_VALUE(mmc_gpio_get_cd(slot->mmc)))
+ if (mmc_gpio_get_cd(slot->mmc) < 0)
break;
}
if (i == host->num_slots)
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index b2d70ba6caa7..458ffb7637e5 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -274,7 +274,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
.chip = &sdhci_acpi_chip_int,
.caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
- MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+ MMC_CAP_WAIT_WHILE_BUSY,
.caps2 = MMC_CAP2_HC_ERASE_SZ,
.flags = SDHCI_ACPI_RUNTIME_PM,
.quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
@@ -289,7 +289,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sdio = {
SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
.quirks2 = SDHCI_QUIRK2_HOST_OFF_CARD_ON,
.caps = MMC_CAP_NONREMOVABLE | MMC_CAP_POWER_OFF_CARD |
- MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+ MMC_CAP_WAIT_WHILE_BUSY,
.flags = SDHCI_ACPI_RUNTIME_PM,
.pm_caps = MMC_PM_KEEP_POWER,
.probe_slot = sdhci_acpi_sdio_probe_slot,
@@ -301,7 +301,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sd = {
.quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
.quirks2 = SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON |
SDHCI_QUIRK2_STOP_WITH_TC,
- .caps = MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+ .caps = MMC_CAP_WAIT_WHILE_BUSY,
.probe_slot = sdhci_acpi_sd_probe_slot,
};
@@ -378,7 +378,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
acpi_handle handle = ACPI_HANDLE(dev);
- struct acpi_device *device;
+ struct acpi_device *device, *child;
struct sdhci_acpi_host *c;
struct sdhci_host *host;
struct resource *iomem;
@@ -390,6 +390,11 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
if (acpi_bus_get_device(handle, &device))
return -ENODEV;
+ /* Power on the SDHCI controller and its children */
+ acpi_device_fix_up_power(device);
+ list_for_each_entry(child, &device->children, node)
+ acpi_device_fix_up_power(child);
+
if (acpi_bus_get_status(device) || !device->status.present)
return -ENODEV;
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 2d300d87cda8..9d3ae1f4bd3c 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1011,7 +1011,7 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
if (ret)
return ret;
- if (!IS_ERR_VALUE(mmc_gpio_get_cd(host->mmc)))
+ if (mmc_gpio_get_cd(host->mmc) >= 0)
host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
return 0;
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 25f779e09d8e..d4cef713d246 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -289,7 +289,7 @@ static int sdhci_at91_probe(struct platform_device *pdev)
* to enable polling via device tree with broken-cd property.
*/
if (!(host->mmc->caps & MMC_CAP_NONREMOVABLE) &&
- IS_ERR_VALUE(mmc_gpio_get_cd(host->mmc))) {
+ mmc_gpio_get_cd(host->mmc) < 0) {
host->mmc->caps |= MMC_CAP_NEEDS_POLL;
host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
}
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 97d4eebd6bf5..a4dbf7421edc 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -356,7 +356,6 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
{
slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
- MMC_CAP_BUS_WIDTH_TEST |
MMC_CAP_WAIT_WHILE_BUSY;
slot->host->mmc->caps2 |= MMC_CAP2_HC_ERASE_SZ;
slot->hw_reset = sdhci_pci_int_hw_reset;
@@ -372,15 +371,13 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
{
slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE |
- MMC_CAP_BUS_WIDTH_TEST |
MMC_CAP_WAIT_WHILE_BUSY;
return 0;
}
static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
{
- slot->host->mmc->caps |= MMC_CAP_BUS_WIDTH_TEST |
- MMC_CAP_WAIT_WHILE_BUSY;
+ slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
slot->cd_con_id = NULL;
slot->cd_idx = 0;
slot->cd_override_level = true;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index e010ea4eb6f5..0e3d7c056cb1 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1624,7 +1624,7 @@ static int sdhci_get_cd(struct mmc_host *mmc)
* Try slot gpio detect, if defined it take precedence
* over build in controller functionality
*/
- if (!IS_ERR_VALUE(gpio_cd))
+ if (gpio_cd >= 0)
return !!gpio_cd;
/* If polling, assume that the card is always present. */
@@ -3077,7 +3077,7 @@ int sdhci_add_host(struct sdhci_host *host)
if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) &&
!(mmc->caps & MMC_CAP_NONREMOVABLE) &&
- IS_ERR_VALUE(mmc_gpio_get_cd(host->mmc)))
+ mmc_gpio_get_cd(host->mmc) < 0)
mmc->caps |= MMC_CAP_NEEDS_POLL;
/* If there are external regulators, get them */
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 7fc8b7aa83f0..2ee4c21ec55e 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -970,8 +970,8 @@ static const struct sunxi_mmc_clk_delay sun9i_mmc_clk_delays[] = {
[SDXC_CLK_400K] = { .output = 180, .sample = 180 },
[SDXC_CLK_25M] = { .output = 180, .sample = 75 },
[SDXC_CLK_50M] = { .output = 150, .sample = 120 },
- [SDXC_CLK_50M_DDR] = { .output = 90, .sample = 120 },
- [SDXC_CLK_50M_DDR_8BIT] = { .output = 90, .sample = 120 },
+ [SDXC_CLK_50M_DDR] = { .output = 54, .sample = 36 },
+ [SDXC_CLK_50M_DDR_8BIT] = { .output = 72, .sample = 72 },
};
static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
@@ -1129,11 +1129,6 @@ static int sunxi_mmc_probe(struct platform_device *pdev)
MMC_CAP_1_8V_DDR |
MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ;
- /* TODO MMC DDR is not working on A80 */
- if (of_device_is_compatible(pdev->dev.of_node,
- "allwinner,sun9i-a80-mmc"))
- mmc->caps &= ~MMC_CAP_1_8V_DDR;
-
ret = mmc_of_parse(mmc);
if (ret)
goto error_free_dma;
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index 3b3dabce58de..bbfa1f129266 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -115,6 +115,7 @@ config MTD_MAP_BANK_WIDTH_16
config MTD_MAP_BANK_WIDTH_32
bool "Support 256-bit buswidth" if MTD_CFI_GEOMETRY
+ select MTD_COMPLEX_MAPPINGS if HAS_IOMEM
default n
help
If you wish to support CFI devices on a physical bus which is
diff --git a/drivers/mtd/devices/bcm47xxsflash.c b/drivers/mtd/devices/bcm47xxsflash.c
index 347bb83db864..1c65c15b31a1 100644
--- a/drivers/mtd/devices/bcm47xxsflash.c
+++ b/drivers/mtd/devices/bcm47xxsflash.c
@@ -2,6 +2,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/delay.h>
+#include <linux/ioport.h>
#include <linux/mtd/mtd.h>
#include <linux/platform_device.h>
#include <linux/bcma/bcma.h>
@@ -109,8 +110,7 @@ static int bcm47xxsflash_read(struct mtd_info *mtd, loff_t from, size_t len,
if ((from + len) > mtd->size)
return -EINVAL;
- memcpy_fromio(buf, (void __iomem *)KSEG0ADDR(b47s->window + from),
- len);
+ memcpy_fromio(buf, b47s->window + from, len);
*retlen = len;
return len;
@@ -275,15 +275,33 @@ static void bcm47xxsflash_bcma_cc_write(struct bcm47xxsflash *b47s, u16 offset,
static int bcm47xxsflash_bcma_probe(struct platform_device *pdev)
{
- struct bcma_sflash *sflash = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct bcma_sflash *sflash = dev_get_platdata(dev);
struct bcm47xxsflash *b47s;
+ struct resource *res;
int err;
- b47s = devm_kzalloc(&pdev->dev, sizeof(*b47s), GFP_KERNEL);
+ b47s = devm_kzalloc(dev, sizeof(*b47s), GFP_KERNEL);
if (!b47s)
return -ENOMEM;
sflash->priv = b47s;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "invalid resource\n");
+ return -EINVAL;
+ }
+ if (!devm_request_mem_region(dev, res->start, resource_size(res),
+ res->name)) {
+ dev_err(dev, "can't request region for resource %pR\n", res);
+ return -EBUSY;
+ }
+ b47s->window = ioremap_cache(res->start, resource_size(res));
+ if (!b47s->window) {
+ dev_err(dev, "ioremap failed for resource %pR\n", res);
+ return -ENOMEM;
+ }
+
b47s->bcma_cc = container_of(sflash, struct bcma_drv_cc, sflash);
b47s->cc_read = bcm47xxsflash_bcma_cc_read;
b47s->cc_write = bcm47xxsflash_bcma_cc_write;
@@ -297,7 +315,6 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev)
break;
}
- b47s->window = sflash->window;
b47s->blocksize = sflash->blocksize;
b47s->numblocks = sflash->numblocks;
b47s->size = sflash->size;
@@ -306,6 +323,7 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev)
err = mtd_device_parse_register(&b47s->mtd, probes, NULL, NULL, 0);
if (err) {
pr_err("Failed to register MTD device: %d\n", err);
+ iounmap(b47s->window);
return err;
}
@@ -321,6 +339,7 @@ static int bcm47xxsflash_bcma_remove(struct platform_device *pdev)
struct bcm47xxsflash *b47s = sflash->priv;
mtd_device_unregister(&b47s->mtd);
+ iounmap(b47s->window);
return 0;
}
diff --git a/drivers/mtd/devices/bcm47xxsflash.h b/drivers/mtd/devices/bcm47xxsflash.h
index fe93daf4f489..1564b62b412e 100644
--- a/drivers/mtd/devices/bcm47xxsflash.h
+++ b/drivers/mtd/devices/bcm47xxsflash.h
@@ -65,7 +65,8 @@ struct bcm47xxsflash {
enum bcm47xxsflash_type type;
- u32 window;
+ void __iomem *window;
+
u32 blocksize;
u16 numblocks;
u32 size;
diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c
index e7b2e439696c..b833e6cc684c 100644
--- a/drivers/mtd/devices/docg3.c
+++ b/drivers/mtd/devices/docg3.c
@@ -67,16 +67,40 @@ module_param(reliable_mode, uint, 0);
MODULE_PARM_DESC(reliable_mode, "Set the docg3 mode (0=normal MLC, 1=fast, "
"2=reliable) : MLC normal operations are in normal mode");
-/**
- * struct docg3_oobinfo - DiskOnChip G3 OOB layout
- * @eccbytes: 8 bytes are used (1 for Hamming ECC, 7 for BCH ECC)
- * @eccpos: ecc positions (byte 7 is Hamming ECC, byte 8-14 are BCH ECC)
- * @oobfree: free pageinfo bytes (byte 0 until byte 6, byte 15
- */
-static struct nand_ecclayout docg3_oobinfo = {
- .eccbytes = 8,
- .eccpos = {7, 8, 9, 10, 11, 12, 13, 14},
- .oobfree = {{0, 7}, {15, 1} },
+static int docg3_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ /* byte 7 is Hamming ECC, byte 8-14 are BCH ECC */
+ oobregion->offset = 7;
+ oobregion->length = 8;
+
+ return 0;
+}
+
+static int docg3_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 1)
+ return -ERANGE;
+
+ /* free bytes: byte 0 until byte 6, byte 15 */
+ if (!section) {
+ oobregion->offset = 0;
+ oobregion->length = 7;
+ } else {
+ oobregion->offset = 15;
+ oobregion->length = 1;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_docg3_ops = {
+ .ecc = docg3_ooblayout_ecc,
+ .free = docg3_ooblayout_free,
};
static inline u8 doc_readb(struct docg3 *docg3, u16 reg)
@@ -1857,7 +1881,7 @@ static int __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
mtd->_read_oob = doc_read_oob;
mtd->_write_oob = doc_write_oob;
mtd->_block_isbad = doc_block_isbad;
- mtd->ecclayout = &docg3_oobinfo;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_docg3_ops);
mtd->oobavail = 8;
mtd->ecc_strength = DOC_ECC_BCH_T;
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index c9c3b7fa3051..9d6854467651 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -131,6 +131,28 @@ static int m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
/* convert the dummy cycles to the number of bytes */
dummy /= 8;
+ if (spi_flash_read_supported(spi)) {
+ struct spi_flash_read_message msg;
+ int ret;
+
+ memset(&msg, 0, sizeof(msg));
+
+ msg.buf = buf;
+ msg.from = from;
+ msg.len = len;
+ msg.read_opcode = nor->read_opcode;
+ msg.addr_width = nor->addr_width;
+ msg.dummy_bytes = dummy;
+ /* TODO: Support other combinations */
+ msg.opcode_nbits = SPI_NBITS_SINGLE;
+ msg.addr_nbits = SPI_NBITS_SINGLE;
+ msg.data_nbits = m25p80_rx_nbits(nor);
+
+ ret = spi_flash_read(spi, &msg);
+ *retlen = msg.retlen;
+ return ret;
+ }
+
spi_message_init(&m);
memset(t, 0, (sizeof t));
diff --git a/drivers/mtd/devices/pmc551.c b/drivers/mtd/devices/pmc551.c
index 708b7e8c8b18..220f9200fa52 100644
--- a/drivers/mtd/devices/pmc551.c
+++ b/drivers/mtd/devices/pmc551.c
@@ -353,7 +353,7 @@ static int pmc551_write(struct mtd_info *mtd, loff_t to, size_t len,
* mechanism
* returns the size of the memory region found.
*/
-static int fixup_pmc551(struct pci_dev *dev)
+static int __init fixup_pmc551(struct pci_dev *dev)
{
#ifdef CONFIG_MTD_PMC551_BUGFIX
u32 dram_data;
diff --git a/drivers/mtd/maps/ck804xrom.c b/drivers/mtd/maps/ck804xrom.c
index 0455166f05fa..4f206a99164c 100644
--- a/drivers/mtd/maps/ck804xrom.c
+++ b/drivers/mtd/maps/ck804xrom.c
@@ -112,8 +112,8 @@ static void ck804xrom_cleanup(struct ck804xrom_window *window)
}
-static int ck804xrom_init_one(struct pci_dev *pdev,
- const struct pci_device_id *ent)
+static int __init ck804xrom_init_one(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
{
static char *rom_probe_types[] = { "cfi_probe", "jedec_probe", NULL };
u8 byte;
diff --git a/drivers/mtd/maps/esb2rom.c b/drivers/mtd/maps/esb2rom.c
index 76ed651b515b..9646b0766ce0 100644
--- a/drivers/mtd/maps/esb2rom.c
+++ b/drivers/mtd/maps/esb2rom.c
@@ -144,8 +144,8 @@ static void esb2rom_cleanup(struct esb2rom_window *window)
pci_dev_put(window->pdev);
}
-static int esb2rom_init_one(struct pci_dev *pdev,
- const struct pci_device_id *ent)
+static int __init esb2rom_init_one(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
{
static char *rom_probe_types[] = { "cfi_probe", "jedec_probe", NULL };
struct esb2rom_window *window = &esb2rom_window;
diff --git a/drivers/mtd/maps/ichxrom.c b/drivers/mtd/maps/ichxrom.c
index 8636bba42200..e17d02ae03f0 100644
--- a/drivers/mtd/maps/ichxrom.c
+++ b/drivers/mtd/maps/ichxrom.c
@@ -84,8 +84,8 @@ static void ichxrom_cleanup(struct ichxrom_window *window)
}
-static int ichxrom_init_one(struct pci_dev *pdev,
- const struct pci_device_id *ent)
+static int __init ichxrom_init_one(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
{
static char *rom_probe_types[] = { "cfi_probe", "jedec_probe", NULL };
struct ichxrom_window *window = &ichxrom_window;
diff --git a/drivers/mtd/maps/uclinux.c b/drivers/mtd/maps/uclinux.c
index c1af83db5202..00a8190797ec 100644
--- a/drivers/mtd/maps/uclinux.c
+++ b/drivers/mtd/maps/uclinux.c
@@ -4,11 +4,13 @@
* uclinux.c -- generic memory mapped MTD driver for uclinux
*
* (C) Copyright 2002, Greg Ungerer (gerg@snapgear.com)
+ *
+ * License: GPL
*/
/****************************************************************************/
-#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/kernel.h>
@@ -117,27 +119,6 @@ static int __init uclinux_mtd_init(void)
return(0);
}
-
-/****************************************************************************/
-
-static void __exit uclinux_mtd_cleanup(void)
-{
- if (uclinux_ram_mtdinfo) {
- mtd_device_unregister(uclinux_ram_mtdinfo);
- map_destroy(uclinux_ram_mtdinfo);
- uclinux_ram_mtdinfo = NULL;
- }
- if (uclinux_ram_map.virt)
- uclinux_ram_map.virt = 0;
-}
-
-/****************************************************************************/
-
-module_init(uclinux_mtd_init);
-module_exit(uclinux_mtd_cleanup);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Greg Ungerer <gerg@snapgear.com>");
-MODULE_DESCRIPTION("Generic MTD for uClinux");
+device_initcall(uclinux_mtd_init);
/****************************************************************************/
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 6d19835b80a9..2a47a3f0e730 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -465,35 +465,108 @@ static int mtdchar_readoob(struct file *file, struct mtd_info *mtd,
}
/*
- * Copies (and truncates, if necessary) data from the larger struct,
- * nand_ecclayout, to the smaller, deprecated layout struct,
- * nand_ecclayout_user. This is necessary only to support the deprecated
- * API ioctl ECCGETLAYOUT while allowing all new functionality to use
- * nand_ecclayout flexibly (i.e. the struct may change size in new
- * releases without requiring major rewrites).
+ * Copies (and truncates, if necessary) OOB layout information to the
+ * deprecated layout struct, nand_ecclayout_user. This is necessary only to
+ * support the deprecated API ioctl ECCGETLAYOUT while allowing all new
+ * functionality to use mtd_ooblayout_ops flexibly (i.e. mtd_ooblayout_ops
+ * can describe any kind of OOB layout with almost zero overhead from a
+ * memory usage point of view).
*/
-static int shrink_ecclayout(const struct nand_ecclayout *from,
- struct nand_ecclayout_user *to)
+static int shrink_ecclayout(struct mtd_info *mtd,
+ struct nand_ecclayout_user *to)
{
- int i;
+ struct mtd_oob_region oobregion;
+ int i, section = 0, ret;
- if (!from || !to)
+ if (!mtd || !to)
return -EINVAL;
memset(to, 0, sizeof(*to));
- to->eccbytes = min((int)from->eccbytes, MTD_MAX_ECCPOS_ENTRIES);
- for (i = 0; i < to->eccbytes; i++)
- to->eccpos[i] = from->eccpos[i];
+ to->eccbytes = 0;
+ for (i = 0; i < MTD_MAX_ECCPOS_ENTRIES;) {
+ u32 eccpos;
+
+ ret = mtd_ooblayout_ecc(mtd, section, &oobregion);
+ if (ret < 0) {
+ if (ret != -ERANGE)
+ return ret;
+
+ break;
+ }
+
+ eccpos = oobregion.offset;
+ for (; i < MTD_MAX_ECCPOS_ENTRIES &&
+ eccpos < oobregion.offset + oobregion.length; i++) {
+ to->eccpos[i] = eccpos++;
+ to->eccbytes++;
+ }
+ }
for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES; i++) {
- if (from->oobfree[i].length == 0 &&
- from->oobfree[i].offset == 0)
+ ret = mtd_ooblayout_free(mtd, i, &oobregion);
+ if (ret < 0) {
+ if (ret != -ERANGE)
+ return ret;
+
+ break;
+ }
+
+ to->oobfree[i].offset = oobregion.offset;
+ to->oobfree[i].length = oobregion.length;
+ to->oobavail += to->oobfree[i].length;
+ }
+
+ return 0;
+}
+
+static int get_oobinfo(struct mtd_info *mtd, struct nand_oobinfo *to)
+{
+ struct mtd_oob_region oobregion;
+ int i, section = 0, ret;
+
+ if (!mtd || !to)
+ return -EINVAL;
+
+ memset(to, 0, sizeof(*to));
+
+ to->eccbytes = 0;
+ for (i = 0; i < ARRAY_SIZE(to->eccpos);) {
+ u32 eccpos;
+
+ ret = mtd_ooblayout_ecc(mtd, section, &oobregion);
+ if (ret < 0) {
+ if (ret != -ERANGE)
+ return ret;
+
break;
- to->oobavail += from->oobfree[i].length;
- to->oobfree[i] = from->oobfree[i];
+ }
+
+ if (oobregion.length + i > ARRAY_SIZE(to->eccpos))
+ return -EINVAL;
+
+ eccpos = oobregion.offset;
+ for (; eccpos < oobregion.offset + oobregion.length; i++) {
+ to->eccpos[i] = eccpos++;
+ to->eccbytes++;
+ }
}
+ for (i = 0; i < 8; i++) {
+ ret = mtd_ooblayout_free(mtd, i, &oobregion);
+ if (ret < 0) {
+ if (ret != -ERANGE)
+ return ret;
+
+ break;
+ }
+
+ to->oobfree[i][0] = oobregion.offset;
+ to->oobfree[i][1] = oobregion.length;
+ }
+
+ to->useecc = MTD_NANDECC_AUTOPLACE;
+
return 0;
}
@@ -815,16 +888,12 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
{
struct nand_oobinfo oi;
- if (!mtd->ecclayout)
+ if (!mtd->ooblayout)
return -EOPNOTSUPP;
- if (mtd->ecclayout->eccbytes > ARRAY_SIZE(oi.eccpos))
- return -EINVAL;
- oi.useecc = MTD_NANDECC_AUTOPLACE;
- memcpy(&oi.eccpos, mtd->ecclayout->eccpos, sizeof(oi.eccpos));
- memcpy(&oi.oobfree, mtd->ecclayout->oobfree,
- sizeof(oi.oobfree));
- oi.eccbytes = mtd->ecclayout->eccbytes;
+ ret = get_oobinfo(mtd, &oi);
+ if (ret)
+ return ret;
if (copy_to_user(argp, &oi, sizeof(struct nand_oobinfo)))
return -EFAULT;
@@ -913,14 +982,14 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
{
struct nand_ecclayout_user *usrlay;
- if (!mtd->ecclayout)
+ if (!mtd->ooblayout)
return -EOPNOTSUPP;
usrlay = kmalloc(sizeof(*usrlay), GFP_KERNEL);
if (!usrlay)
return -ENOMEM;
- shrink_ecclayout(mtd->ecclayout, usrlay);
+ shrink_ecclayout(mtd, usrlay);
if (copy_to_user(argp, usrlay, sizeof(*usrlay)))
ret = -EFAULT;
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index 239a8c806b67..d573606b91c2 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -777,7 +777,7 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[], /* subdevices to c
}
- concat->mtd.ecclayout = subdev[0]->ecclayout;
+ mtd_set_ooblayout(&concat->mtd, subdev[0]->ooblayout);
concat->num_subdev = num_devs;
concat->mtd.name = name;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index bee180bd11e7..e3936b847c6b 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1016,6 +1016,366 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
}
EXPORT_SYMBOL_GPL(mtd_write_oob);
+/**
+ * mtd_ooblayout_ecc - Get the OOB region definition of a specific ECC section
+ * @mtd: MTD device structure
+ * @section: ECC section. Depending on the layout you may have all the ECC
+ * bytes stored in a single contiguous section, or one section
+ * per ECC chunk (and sometime several sections for a single ECC
+ * ECC chunk)
+ * @oobecc: OOB region struct filled with the appropriate ECC position
+ * information
+ *
+ * This functions return ECC section information in the OOB area. I you want
+ * to get all the ECC bytes information, then you should call
+ * mtd_ooblayout_ecc(mtd, section++, oobecc) until it returns -ERANGE.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobecc)
+{
+ memset(oobecc, 0, sizeof(*oobecc));
+
+ if (!mtd || section < 0)
+ return -EINVAL;
+
+ if (!mtd->ooblayout || !mtd->ooblayout->ecc)
+ return -ENOTSUPP;
+
+ return mtd->ooblayout->ecc(mtd, section, oobecc);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_ecc);
+
+/**
+ * mtd_ooblayout_free - Get the OOB region definition of a specific free
+ * section
+ * @mtd: MTD device structure
+ * @section: Free section you are interested in. Depending on the layout
+ * you may have all the free bytes stored in a single contiguous
+ * section, or one section per ECC chunk plus an extra section
+ * for the remaining bytes (or other funky layout).
+ * @oobfree: OOB region struct filled with the appropriate free position
+ * information
+ *
+ * This functions return free bytes position in the OOB area. I you want
+ * to get all the free bytes information, then you should call
+ * mtd_ooblayout_free(mtd, section++, oobfree) until it returns -ERANGE.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobfree)
+{
+ memset(oobfree, 0, sizeof(*oobfree));
+
+ if (!mtd || section < 0)
+ return -EINVAL;
+
+ if (!mtd->ooblayout || !mtd->ooblayout->free)
+ return -ENOTSUPP;
+
+ return mtd->ooblayout->free(mtd, section, oobfree);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_free);
+
+/**
+ * mtd_ooblayout_find_region - Find the region attached to a specific byte
+ * @mtd: mtd info structure
+ * @byte: the byte we are searching for
+ * @sectionp: pointer where the section id will be stored
+ * @oobregion: used to retrieve the ECC position
+ * @iter: iterator function. Should be either mtd_ooblayout_free or
+ * mtd_ooblayout_ecc depending on the region type you're searching for
+ *
+ * This functions returns the section id and oobregion information of a
+ * specific byte. For example, say you want to know where the 4th ECC byte is
+ * stored, you'll use:
+ *
+ * mtd_ooblayout_find_region(mtd, 3, &section, &oobregion, mtd_ooblayout_ecc);
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+static int mtd_ooblayout_find_region(struct mtd_info *mtd, int byte,
+ int *sectionp, struct mtd_oob_region *oobregion,
+ int (*iter)(struct mtd_info *,
+ int section,
+ struct mtd_oob_region *oobregion))
+{
+ int pos = 0, ret, section = 0;
+
+ memset(oobregion, 0, sizeof(*oobregion));
+
+ while (1) {
+ ret = iter(mtd, section, oobregion);
+ if (ret)
+ return ret;
+
+ if (pos + oobregion->length > byte)
+ break;
+
+ pos += oobregion->length;
+ section++;
+ }
+
+ /*
+ * Adjust region info to make it start at the beginning at the
+ * 'start' ECC byte.
+ */
+ oobregion->offset += byte - pos;
+ oobregion->length -= byte - pos;
+ *sectionp = section;
+
+ return 0;
+}
+
+/**
+ * mtd_ooblayout_find_eccregion - Find the ECC region attached to a specific
+ * ECC byte
+ * @mtd: mtd info structure
+ * @eccbyte: the byte we are searching for
+ * @sectionp: pointer where the section id will be stored
+ * @oobregion: OOB region information
+ *
+ * Works like mtd_ooblayout_find_region() except it searches for a specific ECC
+ * byte.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_find_eccregion(struct mtd_info *mtd, int eccbyte,
+ int *section,
+ struct mtd_oob_region *oobregion)
+{
+ return mtd_ooblayout_find_region(mtd, eccbyte, section, oobregion,
+ mtd_ooblayout_ecc);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_find_eccregion);
+
+/**
+ * mtd_ooblayout_get_bytes - Extract OOB bytes from the oob buffer
+ * @mtd: mtd info structure
+ * @buf: destination buffer to store OOB bytes
+ * @oobbuf: OOB buffer
+ * @start: first byte to retrieve
+ * @nbytes: number of bytes to retrieve
+ * @iter: section iterator
+ *
+ * Extract bytes attached to a specific category (ECC or free)
+ * from the OOB buffer and copy them into buf.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+static int mtd_ooblayout_get_bytes(struct mtd_info *mtd, u8 *buf,
+ const u8 *oobbuf, int start, int nbytes,
+ int (*iter)(struct mtd_info *,
+ int section,
+ struct mtd_oob_region *oobregion))
+{
+ struct mtd_oob_region oobregion = { };
+ int section = 0, ret;
+
+ ret = mtd_ooblayout_find_region(mtd, start, &section,
+ &oobregion, iter);
+
+ while (!ret) {
+ int cnt;
+
+ cnt = oobregion.length > nbytes ? nbytes : oobregion.length;
+ memcpy(buf, oobbuf + oobregion.offset, cnt);
+ buf += cnt;
+ nbytes -= cnt;
+
+ if (!nbytes)
+ break;
+
+ ret = iter(mtd, ++section, &oobregion);
+ }
+
+ return ret;
+}
+
+/**
+ * mtd_ooblayout_set_bytes - put OOB bytes into the oob buffer
+ * @mtd: mtd info structure
+ * @buf: source buffer to get OOB bytes from
+ * @oobbuf: OOB buffer
+ * @start: first OOB byte to set
+ * @nbytes: number of OOB bytes to set
+ * @iter: section iterator
+ *
+ * Fill the OOB buffer with data provided in buf. The category (ECC or free)
+ * is selected by passing the appropriate iterator.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+static int mtd_ooblayout_set_bytes(struct mtd_info *mtd, const u8 *buf,
+ u8 *oobbuf, int start, int nbytes,
+ int (*iter)(struct mtd_info *,
+ int section,
+ struct mtd_oob_region *oobregion))
+{
+ struct mtd_oob_region oobregion = { };
+ int section = 0, ret;
+
+ ret = mtd_ooblayout_find_region(mtd, start, &section,
+ &oobregion, iter);
+
+ while (!ret) {
+ int cnt;
+
+ cnt = oobregion.length > nbytes ? nbytes : oobregion.length;
+ memcpy(oobbuf + oobregion.offset, buf, cnt);
+ buf += cnt;
+ nbytes -= cnt;
+
+ if (!nbytes)
+ break;
+
+ ret = iter(mtd, ++section, &oobregion);
+ }
+
+ return ret;
+}
+
+/**
+ * mtd_ooblayout_count_bytes - count the number of bytes in a OOB category
+ * @mtd: mtd info structure
+ * @iter: category iterator
+ *
+ * Count the number of bytes in a given category.
+ *
+ * Returns a positive value on success, a negative error code otherwise.
+ */
+static int mtd_ooblayout_count_bytes(struct mtd_info *mtd,
+ int (*iter)(struct mtd_info *,
+ int section,
+ struct mtd_oob_region *oobregion))
+{
+ struct mtd_oob_region oobregion = { };
+ int section = 0, ret, nbytes = 0;
+
+ while (1) {
+ ret = iter(mtd, section++, &oobregion);
+ if (ret) {
+ if (ret == -ERANGE)
+ ret = nbytes;
+ break;
+ }
+
+ nbytes += oobregion.length;
+ }
+
+ return ret;
+}
+
+/**
+ * mtd_ooblayout_get_eccbytes - extract ECC bytes from the oob buffer
+ * @mtd: mtd info structure
+ * @eccbuf: destination buffer to store ECC bytes
+ * @oobbuf: OOB buffer
+ * @start: first ECC byte to retrieve
+ * @nbytes: number of ECC bytes to retrieve
+ *
+ * Works like mtd_ooblayout_get_bytes(), except it acts on ECC bytes.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_get_eccbytes(struct mtd_info *mtd, u8 *eccbuf,
+ const u8 *oobbuf, int start, int nbytes)
+{
+ return mtd_ooblayout_get_bytes(mtd, eccbuf, oobbuf, start, nbytes,
+ mtd_ooblayout_ecc);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_get_eccbytes);
+
+/**
+ * mtd_ooblayout_set_eccbytes - set ECC bytes into the oob buffer
+ * @mtd: mtd info structure
+ * @eccbuf: source buffer to get ECC bytes from
+ * @oobbuf: OOB buffer
+ * @start: first ECC byte to set
+ * @nbytes: number of ECC bytes to set
+ *
+ * Works like mtd_ooblayout_set_bytes(), except it acts on ECC bytes.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_set_eccbytes(struct mtd_info *mtd, const u8 *eccbuf,
+ u8 *oobbuf, int start, int nbytes)
+{
+ return mtd_ooblayout_set_bytes(mtd, eccbuf, oobbuf, start, nbytes,
+ mtd_ooblayout_ecc);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_set_eccbytes);
+
+/**
+ * mtd_ooblayout_get_databytes - extract data bytes from the oob buffer
+ * @mtd: mtd info structure
+ * @databuf: destination buffer to store ECC bytes
+ * @oobbuf: OOB buffer
+ * @start: first ECC byte to retrieve
+ * @nbytes: number of ECC bytes to retrieve
+ *
+ * Works like mtd_ooblayout_get_bytes(), except it acts on free bytes.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_get_databytes(struct mtd_info *mtd, u8 *databuf,
+ const u8 *oobbuf, int start, int nbytes)
+{
+ return mtd_ooblayout_get_bytes(mtd, databuf, oobbuf, start, nbytes,
+ mtd_ooblayout_free);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_get_databytes);
+
+/**
+ * mtd_ooblayout_get_eccbytes - set data bytes into the oob buffer
+ * @mtd: mtd info structure
+ * @eccbuf: source buffer to get data bytes from
+ * @oobbuf: OOB buffer
+ * @start: first ECC byte to set
+ * @nbytes: number of ECC bytes to set
+ *
+ * Works like mtd_ooblayout_get_bytes(), except it acts on free bytes.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_set_databytes(struct mtd_info *mtd, const u8 *databuf,
+ u8 *oobbuf, int start, int nbytes)
+{
+ return mtd_ooblayout_set_bytes(mtd, databuf, oobbuf, start, nbytes,
+ mtd_ooblayout_free);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_set_databytes);
+
+/**
+ * mtd_ooblayout_count_freebytes - count the number of free bytes in OOB
+ * @mtd: mtd info structure
+ *
+ * Works like mtd_ooblayout_count_bytes(), except it count free bytes.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_count_freebytes(struct mtd_info *mtd)
+{
+ return mtd_ooblayout_count_bytes(mtd, mtd_ooblayout_free);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_count_freebytes);
+
+/**
+ * mtd_ooblayout_count_freebytes - count the number of ECC bytes in OOB
+ * @mtd: mtd info structure
+ *
+ * Works like mtd_ooblayout_count_bytes(), except it count ECC bytes.
+ *
+ * Returns zero on success, a negative error code otherwise.
+ */
+int mtd_ooblayout_count_eccbytes(struct mtd_info *mtd)
+{
+ return mtd_ooblayout_count_bytes(mtd, mtd_ooblayout_ecc);
+}
+EXPORT_SYMBOL_GPL(mtd_ooblayout_count_eccbytes);
+
/*
* Method to access the protection register area, present in some flash
* devices. The user data is one time programmable but the factory data is read
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 08de4b2cf0f5..1f13e32556f8 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -317,6 +317,27 @@ static int part_block_markbad(struct mtd_info *mtd, loff_t ofs)
return res;
}
+static int part_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct mtd_part *part = mtd_to_part(mtd);
+
+ return mtd_ooblayout_ecc(part->master, section, oobregion);
+}
+
+static int part_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct mtd_part *part = mtd_to_part(mtd);
+
+ return mtd_ooblayout_free(part->master, section, oobregion);
+}
+
+static const struct mtd_ooblayout_ops part_ooblayout_ops = {
+ .ecc = part_ooblayout_ecc,
+ .free = part_ooblayout_free,
+};
+
static inline void free_partition(struct mtd_part *p)
{
kfree(p->mtd.name);
@@ -533,7 +554,7 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
part->name);
}
- slave->mtd.ecclayout = master->ecclayout;
+ mtd_set_ooblayout(&slave->mtd, &part_ooblayout_ops);
slave->mtd.ecc_step_size = master->ecc_step_size;
slave->mtd.ecc_strength = master->ecc_strength;
slave->mtd.bitflip_threshold = master->bitflip_threshold;
diff --git a/drivers/mtd/nand/ams-delta.c b/drivers/mtd/nand/ams-delta.c
index 68b58c85789c..78e12cc8bac2 100644
--- a/drivers/mtd/nand/ams-delta.c
+++ b/drivers/mtd/nand/ams-delta.c
@@ -224,6 +224,7 @@ static int ams_delta_init(struct platform_device *pdev)
/* 25 us command delay time */
this->chip_delay = 30;
this->ecc.mode = NAND_ECC_SOFT;
+ this->ecc.algo = NAND_ECC_HAMMING;
platform_set_drvdata(pdev, io_base);
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 20cbaabb2959..68b9160108c9 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -36,7 +36,6 @@
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_gpio.h>
-#include <linux/of_mtd.h>
#include <linux/mtd/mtd.h>
#include <linux/mtd/nand.h>
#include <linux/mtd/partitions.h>
@@ -68,34 +67,44 @@ struct atmel_nand_caps {
uint8_t pmecc_max_correction;
};
-struct atmel_nand_nfc_caps {
- uint32_t rb_mask;
-};
-
-/* oob layout for large page size
+/*
+ * oob layout for large page size
* bad block info is on bytes 0 and 1
* the bytes have to be consecutives to avoid
* several NAND_CMD_RNDOUT during read
- */
-static struct nand_ecclayout atmel_oobinfo_large = {
- .eccbytes = 4,
- .eccpos = {60, 61, 62, 63},
- .oobfree = {
- {2, 58}
- },
-};
-
-/* oob layout for small page size
+ *
+ * oob layout for small page size
* bad block info is on bytes 4 and 5
* the bytes have to be consecutives to avoid
* several NAND_CMD_RNDOUT during read
*/
-static struct nand_ecclayout atmel_oobinfo_small = {
- .eccbytes = 4,
- .eccpos = {0, 1, 2, 3},
- .oobfree = {
- {6, 10}
- },
+static int atmel_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = 4;
+ oobregion->offset = 0;
+
+ return 0;
+}
+
+static int atmel_ooblayout_free_sp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 6;
+ oobregion->length = mtd->oobsize - oobregion->offset;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops atmel_ooblayout_sp_ops = {
+ .ecc = atmel_ooblayout_ecc_sp,
+ .free = atmel_ooblayout_free_sp,
};
struct atmel_nfc {
@@ -116,7 +125,6 @@ struct atmel_nfc {
/* Point to the sram bank which include readed data via NFC */
void *data_in_sram;
bool will_write_sram;
- const struct atmel_nand_nfc_caps *caps;
};
static struct atmel_nfc nand_nfc;
@@ -163,8 +171,6 @@ struct atmel_nand_host {
int *pmecc_delta;
};
-static struct nand_ecclayout atmel_pmecc_oobinfo;
-
/*
* Enable NAND.
*/
@@ -434,14 +440,13 @@ err_buf:
static void atmel_read_buf(struct mtd_info *mtd, u8 *buf, int len)
{
struct nand_chip *chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(chip);
if (use_dma && len > mtd->oobsize)
/* only use DMA for bigger than oob size: better performances */
if (atmel_nand_dma_op(mtd, buf, len, 1) == 0)
return;
- if (host->board.bus_width_16)
+ if (chip->options & NAND_BUSWIDTH_16)
atmel_read_buf16(mtd, buf, len);
else
atmel_read_buf8(mtd, buf, len);
@@ -450,14 +455,13 @@ static void atmel_read_buf(struct mtd_info *mtd, u8 *buf, int len)
static void atmel_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
{
struct nand_chip *chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(chip);
if (use_dma && len > mtd->oobsize)
/* only use DMA for bigger than oob size: better performances */
if (atmel_nand_dma_op(mtd, (void *)buf, len, 0) == 0)
return;
- if (host->board.bus_width_16)
+ if (chip->options & NAND_BUSWIDTH_16)
atmel_write_buf16(mtd, buf, len);
else
atmel_write_buf8(mtd, buf, len);
@@ -483,22 +487,6 @@ static int pmecc_get_ecc_bytes(int cap, int sector_size)
return (m * cap + 7) / 8;
}
-static void pmecc_config_ecc_layout(struct nand_ecclayout *layout,
- int oobsize, int ecc_len)
-{
- int i;
-
- layout->eccbytes = ecc_len;
-
- /* ECC will occupy the last ecc_len bytes continuously */
- for (i = 0; i < ecc_len; i++)
- layout->eccpos[i] = oobsize - ecc_len + i;
-
- layout->oobfree[0].offset = PMECC_OOB_RESERVED_BYTES;
- layout->oobfree[0].length =
- oobsize - ecc_len - layout->oobfree[0].offset;
-}
-
static void __iomem *pmecc_get_alpha_to(struct atmel_nand_host *host)
{
int table_size;
@@ -836,13 +824,16 @@ static void pmecc_correct_data(struct mtd_info *mtd, uint8_t *buf, uint8_t *ecc,
dev_dbg(host->dev, "Bit flip in data area, byte_pos: %d, bit_pos: %d, 0x%02x -> 0x%02x\n",
pos, bit_pos, err_byte, *(buf + byte_pos));
} else {
+ struct mtd_oob_region oobregion;
+
/* Bit flip in OOB area */
tmp = sector_num * nand_chip->ecc.bytes
+ (byte_pos - sector_size);
err_byte = ecc[tmp];
ecc[tmp] ^= (1 << bit_pos);
- pos = tmp + nand_chip->ecc.layout->eccpos[0];
+ mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ pos = tmp + oobregion.offset;
dev_dbg(host->dev, "Bit flip in OOB, oob_byte_pos: %d, bit_pos: %d, 0x%02x -> 0x%02x\n",
pos, bit_pos, err_byte, ecc[tmp]);
}
@@ -863,17 +854,6 @@ static int pmecc_correction(struct mtd_info *mtd, u32 pmecc_stat, uint8_t *buf,
uint8_t *buf_pos;
int max_bitflips = 0;
- /* If can correct bitfilps from erased page, do the normal check */
- if (host->caps->pmecc_correct_erase_page)
- goto normal_check;
-
- for (i = 0; i < nand_chip->ecc.total; i++)
- if (ecc[i] != 0xff)
- goto normal_check;
- /* Erased page, return OK */
- return 0;
-
-normal_check:
for (i = 0; i < nand_chip->ecc.steps; i++) {
err_nbr = 0;
if (pmecc_stat & 0x1) {
@@ -884,16 +864,30 @@ normal_check:
pmecc_get_sigma(mtd);
err_nbr = pmecc_err_location(mtd);
- if (err_nbr == -1) {
+ if (err_nbr >= 0) {
+ pmecc_correct_data(mtd, buf_pos, ecc, i,
+ nand_chip->ecc.bytes,
+ err_nbr);
+ } else if (!host->caps->pmecc_correct_erase_page) {
+ u8 *ecc_pos = ecc + (i * nand_chip->ecc.bytes);
+
+ /* Try to detect erased pages */
+ err_nbr = nand_check_erased_ecc_chunk(buf_pos,
+ host->pmecc_sector_size,
+ ecc_pos,
+ nand_chip->ecc.bytes,
+ NULL, 0,
+ nand_chip->ecc.strength);
+ }
+
+ if (err_nbr < 0) {
dev_err(host->dev, "PMECC: Too many errors\n");
mtd->ecc_stats.failed++;
return -EIO;
- } else {
- pmecc_correct_data(mtd, buf_pos, ecc, i,
- nand_chip->ecc.bytes, err_nbr);
- mtd->ecc_stats.corrected += err_nbr;
- max_bitflips = max_t(int, max_bitflips, err_nbr);
}
+
+ mtd->ecc_stats.corrected += err_nbr;
+ max_bitflips = max_t(int, max_bitflips, err_nbr);
}
pmecc_stat >>= 1;
}
@@ -931,7 +925,6 @@ static int atmel_nand_pmecc_read_page(struct mtd_info *mtd,
struct atmel_nand_host *host = nand_get_controller_data(chip);
int eccsize = chip->ecc.size * chip->ecc.steps;
uint8_t *oob = chip->oob_poi;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
uint32_t stat;
unsigned long end_time;
int bitflips = 0;
@@ -953,7 +946,11 @@ static int atmel_nand_pmecc_read_page(struct mtd_info *mtd,
stat = pmecc_readl_relaxed(host->ecc, ISR);
if (stat != 0) {
- bitflips = pmecc_correction(mtd, stat, buf, &oob[eccpos[0]]);
+ struct mtd_oob_region oobregion;
+
+ mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ bitflips = pmecc_correction(mtd, stat, buf,
+ &oob[oobregion.offset]);
if (bitflips < 0)
/* uncorrectable errors */
return 0;
@@ -967,8 +964,8 @@ static int atmel_nand_pmecc_write_page(struct mtd_info *mtd,
int page)
{
struct atmel_nand_host *host = nand_get_controller_data(chip);
- uint32_t *eccpos = chip->ecc.layout->eccpos;
- int i, j;
+ struct mtd_oob_region oobregion = { };
+ int i, j, section = 0;
unsigned long end_time;
if (!host->nfc || !host->nfc->write_by_sram) {
@@ -987,11 +984,14 @@ static int atmel_nand_pmecc_write_page(struct mtd_info *mtd,
for (i = 0; i < chip->ecc.steps; i++) {
for (j = 0; j < chip->ecc.bytes; j++) {
- int pos;
+ if (!oobregion.length)
+ mtd_ooblayout_ecc(mtd, section, &oobregion);
- pos = i * chip->ecc.bytes + j;
- chip->oob_poi[eccpos[pos]] =
+ chip->oob_poi[oobregion.offset] =
pmecc_readb_ecc_relaxed(host->ecc, i, j);
+ oobregion.length--;
+ oobregion.offset++;
+ section++;
}
}
chip->write_buf(mtd, chip->oob_poi, mtd->oobsize);
@@ -1003,8 +1003,9 @@ static void atmel_pmecc_core_init(struct mtd_info *mtd)
{
struct nand_chip *nand_chip = mtd_to_nand(mtd);
struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
+ int eccbytes = mtd_ooblayout_count_eccbytes(mtd);
uint32_t val = 0;
- struct nand_ecclayout *ecc_layout;
+ struct mtd_oob_region oobregion;
pmecc_writel(host->ecc, CTRL, PMECC_CTRL_RST);
pmecc_writel(host->ecc, CTRL, PMECC_CTRL_DISABLE);
@@ -1054,11 +1055,11 @@ static void atmel_pmecc_core_init(struct mtd_info *mtd)
| PMECC_CFG_AUTO_DISABLE);
pmecc_writel(host->ecc, CFG, val);
- ecc_layout = nand_chip->ecc.layout;
pmecc_writel(host->ecc, SAREA, mtd->oobsize - 1);
- pmecc_writel(host->ecc, SADDR, ecc_layout->eccpos[0]);
+ mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ pmecc_writel(host->ecc, SADDR, oobregion.offset);
pmecc_writel(host->ecc, EADDR,
- ecc_layout->eccpos[ecc_layout->eccbytes - 1]);
+ oobregion.offset + eccbytes - 1);
/* See datasheet about PMECC Clock Control Register */
pmecc_writel(host->ecc, CLK, 2);
pmecc_writel(host->ecc, IDR, 0xff);
@@ -1206,6 +1207,7 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
dev_warn(host->dev,
"Can't get I/O resource regs for PMECC controller, rolling back on software ECC\n");
nand_chip->ecc.mode = NAND_ECC_SOFT;
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
return 0;
}
@@ -1280,11 +1282,8 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
err_no = -EINVAL;
goto err;
}
- pmecc_config_ecc_layout(&atmel_pmecc_oobinfo,
- mtd->oobsize,
- nand_chip->ecc.total);
- nand_chip->ecc.layout = &atmel_pmecc_oobinfo;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
break;
default:
dev_warn(host->dev,
@@ -1292,6 +1291,7 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
/* page size not handled by HW ECC */
/* switching back to soft ECC */
nand_chip->ecc.mode = NAND_ECC_SOFT;
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
return 0;
}
@@ -1359,12 +1359,12 @@ static int atmel_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
{
int eccsize = chip->ecc.size;
int eccbytes = chip->ecc.bytes;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
uint8_t *p = buf;
uint8_t *oob = chip->oob_poi;
uint8_t *ecc_pos;
int stat;
unsigned int max_bitflips = 0;
+ struct mtd_oob_region oobregion = {};
/*
* Errata: ALE is incorrectly wired up to the ECC controller
@@ -1382,19 +1382,20 @@ static int atmel_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
chip->read_buf(mtd, p, eccsize);
/* move to ECC position if needed */
- if (eccpos[0] != 0) {
- /* This only works on large pages
- * because the ECC controller waits for
- * NAND_CMD_RNDOUTSTART after the
- * NAND_CMD_RNDOUT.
- * anyway, for small pages, the eccpos[0] == 0
+ mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ if (oobregion.offset != 0) {
+ /*
+ * This only works on large pages because the ECC controller
+ * waits for NAND_CMD_RNDOUTSTART after the NAND_CMD_RNDOUT.
+ * Anyway, for small pages, the first ECC byte is at offset
+ * 0 in the OOB area.
*/
chip->cmdfunc(mtd, NAND_CMD_RNDOUT,
- mtd->writesize + eccpos[0], -1);
+ mtd->writesize + oobregion.offset, -1);
}
/* the ECC controller needs to read the ECC just after the data */
- ecc_pos = oob + eccpos[0];
+ ecc_pos = oob + oobregion.offset;
chip->read_buf(mtd, ecc_pos, eccbytes);
/* check if there's an error */
@@ -1504,58 +1505,17 @@ static void atmel_nand_hwctl(struct mtd_info *mtd, int mode)
ecc_writel(host->ecc, CR, ATMEL_ECC_RST);
}
-static int atmel_of_init_port(struct atmel_nand_host *host,
- struct device_node *np)
+static int atmel_of_init_ecc(struct atmel_nand_host *host,
+ struct device_node *np)
{
- u32 val;
u32 offset[2];
- int ecc_mode;
- struct atmel_nand_data *board = &host->board;
- enum of_gpio_flags flags = 0;
-
- host->caps = (struct atmel_nand_caps *)
- of_device_get_match_data(host->dev);
-
- if (of_property_read_u32(np, "atmel,nand-addr-offset", &val) == 0) {
- if (val >= 32) {
- dev_err(host->dev, "invalid addr-offset %u\n", val);
- return -EINVAL;
- }
- board->ale = val;
- }
-
- if (of_property_read_u32(np, "atmel,nand-cmd-offset", &val) == 0) {
- if (val >= 32) {
- dev_err(host->dev, "invalid cmd-offset %u\n", val);
- return -EINVAL;
- }
- board->cle = val;
- }
-
- ecc_mode = of_get_nand_ecc_mode(np);
-
- board->ecc_mode = ecc_mode < 0 ? NAND_ECC_SOFT : ecc_mode;
-
- board->on_flash_bbt = of_get_nand_on_flash_bbt(np);
-
- board->has_dma = of_property_read_bool(np, "atmel,nand-has-dma");
-
- if (of_get_nand_bus_width(np) == 16)
- board->bus_width_16 = 1;
-
- board->rdy_pin = of_get_gpio_flags(np, 0, &flags);
- board->rdy_pin_active_low = (flags == OF_GPIO_ACTIVE_LOW);
-
- board->enable_pin = of_get_gpio(np, 1);
- board->det_pin = of_get_gpio(np, 2);
+ u32 val;
host->has_pmecc = of_property_read_bool(np, "atmel,has-pmecc");
- /* load the nfc driver if there is */
- of_platform_populate(np, NULL, NULL, host->dev);
-
- if (!(board->ecc_mode == NAND_ECC_HW) || !host->has_pmecc)
- return 0; /* Not using PMECC */
+ /* Not using PMECC */
+ if (!(host->nand_chip.ecc.mode == NAND_ECC_HW) || !host->has_pmecc)
+ return 0;
/* use PMECC, get correction capability, sector size and lookup
* table offset.
@@ -1596,16 +1556,65 @@ static int atmel_of_init_port(struct atmel_nand_host *host,
/* Will build a lookup table and initialize the offset later */
return 0;
}
+
if (!offset[0] && !offset[1]) {
dev_err(host->dev, "Invalid PMECC lookup table offset\n");
return -EINVAL;
}
+
host->pmecc_lookup_table_offset_512 = offset[0];
host->pmecc_lookup_table_offset_1024 = offset[1];
return 0;
}
+static int atmel_of_init_port(struct atmel_nand_host *host,
+ struct device_node *np)
+{
+ u32 val;
+ struct atmel_nand_data *board = &host->board;
+ enum of_gpio_flags flags = 0;
+
+ host->caps = (struct atmel_nand_caps *)
+ of_device_get_match_data(host->dev);
+
+ if (of_property_read_u32(np, "atmel,nand-addr-offset", &val) == 0) {
+ if (val >= 32) {
+ dev_err(host->dev, "invalid addr-offset %u\n", val);
+ return -EINVAL;
+ }
+ board->ale = val;
+ }
+
+ if (of_property_read_u32(np, "atmel,nand-cmd-offset", &val) == 0) {
+ if (val >= 32) {
+ dev_err(host->dev, "invalid cmd-offset %u\n", val);
+ return -EINVAL;
+ }
+ board->cle = val;
+ }
+
+ board->has_dma = of_property_read_bool(np, "atmel,nand-has-dma");
+
+ board->rdy_pin = of_get_gpio_flags(np, 0, &flags);
+ board->rdy_pin_active_low = (flags == OF_GPIO_ACTIVE_LOW);
+
+ board->enable_pin = of_get_gpio(np, 1);
+ board->det_pin = of_get_gpio(np, 2);
+
+ /* load the nfc driver if there is */
+ of_platform_populate(np, NULL, NULL, host->dev);
+
+ /*
+ * Initialize ECC mode to NAND_ECC_SOFT so that we have a correct value
+ * even if the nand-ecc-mode property is not defined.
+ */
+ host->nand_chip.ecc.mode = NAND_ECC_SOFT;
+ host->nand_chip.ecc.algo = NAND_ECC_HAMMING;
+
+ return 0;
+}
+
static int atmel_hw_nand_init_params(struct platform_device *pdev,
struct atmel_nand_host *host)
{
@@ -1618,6 +1627,7 @@ static int atmel_hw_nand_init_params(struct platform_device *pdev,
dev_err(host->dev,
"Can't get I/O resource regs, use software ECC\n");
nand_chip->ecc.mode = NAND_ECC_SOFT;
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
return 0;
}
@@ -1631,25 +1641,26 @@ static int atmel_hw_nand_init_params(struct platform_device *pdev,
/* set ECC page size and oob layout */
switch (mtd->writesize) {
case 512:
- nand_chip->ecc.layout = &atmel_oobinfo_small;
+ mtd_set_ooblayout(mtd, &atmel_ooblayout_sp_ops);
ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_528);
break;
case 1024:
- nand_chip->ecc.layout = &atmel_oobinfo_large;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_1056);
break;
case 2048:
- nand_chip->ecc.layout = &atmel_oobinfo_large;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_2112);
break;
case 4096:
- nand_chip->ecc.layout = &atmel_oobinfo_large;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_4224);
break;
default:
/* page size not handled by HW ECC */
/* switching back to soft ECC */
nand_chip->ecc.mode = NAND_ECC_SOFT;
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
return 0;
}
@@ -1699,9 +1710,9 @@ static irqreturn_t hsmc_interrupt(int irq, void *dev_id)
nfc_writel(host->nfc->hsmc_regs, IDR, NFC_SR_XFR_DONE);
ret = IRQ_HANDLED;
}
- if (pending & host->nfc->caps->rb_mask) {
+ if (pending & NFC_SR_RB_EDGE) {
complete(&host->nfc->comp_ready);
- nfc_writel(host->nfc->hsmc_regs, IDR, host->nfc->caps->rb_mask);
+ nfc_writel(host->nfc->hsmc_regs, IDR, NFC_SR_RB_EDGE);
ret = IRQ_HANDLED;
}
if (pending & NFC_SR_CMD_DONE) {
@@ -1719,7 +1730,7 @@ static void nfc_prepare_interrupt(struct atmel_nand_host *host, u32 flag)
if (flag & NFC_SR_XFR_DONE)
init_completion(&host->nfc->comp_xfer_done);
- if (flag & host->nfc->caps->rb_mask)
+ if (flag & NFC_SR_RB_EDGE)
init_completion(&host->nfc->comp_ready);
if (flag & NFC_SR_CMD_DONE)
@@ -1737,7 +1748,7 @@ static int nfc_wait_interrupt(struct atmel_nand_host *host, u32 flag)
if (flag & NFC_SR_XFR_DONE)
comp[index++] = &host->nfc->comp_xfer_done;
- if (flag & host->nfc->caps->rb_mask)
+ if (flag & NFC_SR_RB_EDGE)
comp[index++] = &host->nfc->comp_ready;
if (flag & NFC_SR_CMD_DONE)
@@ -1805,7 +1816,7 @@ static int nfc_device_ready(struct mtd_info *mtd)
dev_err(host->dev, "Lost the interrupt flags: 0x%08x\n",
mask & status);
- return status & host->nfc->caps->rb_mask;
+ return status & NFC_SR_RB_EDGE;
}
static void nfc_select_chip(struct mtd_info *mtd, int chip)
@@ -1978,8 +1989,8 @@ static void nfc_nand_command(struct mtd_info *mtd, unsigned int command,
}
/* fall through */
default:
- nfc_prepare_interrupt(host, host->nfc->caps->rb_mask);
- nfc_wait_interrupt(host, host->nfc->caps->rb_mask);
+ nfc_prepare_interrupt(host, NFC_SR_RB_EDGE);
+ nfc_wait_interrupt(host, NFC_SR_RB_EDGE);
}
}
@@ -2147,6 +2158,19 @@ static int atmel_nand_probe(struct platform_device *pdev)
} else {
memcpy(&host->board, dev_get_platdata(&pdev->dev),
sizeof(struct atmel_nand_data));
+ nand_chip->ecc.mode = host->board.ecc_mode;
+
+ /*
+ * When using software ECC every supported avr32 board means
+ * Hamming algorithm. If that ever changes we'll need to add
+ * ecc_algo field to the struct atmel_nand_data.
+ */
+ if (nand_chip->ecc.mode == NAND_ECC_SOFT)
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
+
+ /* 16-bit bus width */
+ if (host->board.bus_width_16)
+ nand_chip->options |= NAND_BUSWIDTH_16;
}
/* link the private data structures */
@@ -2188,11 +2212,8 @@ static int atmel_nand_probe(struct platform_device *pdev)
nand_chip->cmd_ctrl = atmel_nand_cmd_ctrl;
}
- nand_chip->ecc.mode = host->board.ecc_mode;
nand_chip->chip_delay = 40; /* 40us command delay time */
- if (host->board.bus_width_16) /* 16-bit bus width */
- nand_chip->options |= NAND_BUSWIDTH_16;
nand_chip->read_buf = atmel_read_buf;
nand_chip->write_buf = atmel_write_buf;
@@ -2225,11 +2246,6 @@ static int atmel_nand_probe(struct platform_device *pdev)
}
}
- if (host->board.on_flash_bbt || on_flash_bbt) {
- dev_info(&pdev->dev, "Use On Flash BBT\n");
- nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
- }
-
if (!host->board.has_dma)
use_dma = 0;
@@ -2256,6 +2272,18 @@ static int atmel_nand_probe(struct platform_device *pdev)
goto err_scan_ident;
}
+ if (host->board.on_flash_bbt || on_flash_bbt)
+ nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+ if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
+ dev_info(&pdev->dev, "Use On Flash BBT\n");
+
+ if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) {
+ res = atmel_of_init_ecc(host, pdev->dev.of_node);
+ if (res)
+ goto err_hw_ecc;
+ }
+
if (nand_chip->ecc.mode == NAND_ECC_HW) {
if (host->has_pmecc)
res = atmel_pmecc_nand_init_params(pdev, host);
@@ -2393,11 +2421,6 @@ static int atmel_nand_nfc_probe(struct platform_device *pdev)
}
}
- nfc->caps = (const struct atmel_nand_nfc_caps *)
- of_device_get_match_data(&pdev->dev);
- if (!nfc->caps)
- return -ENODEV;
-
nfc_writel(nfc->hsmc_regs, IDR, 0xffffffff);
nfc_readl(nfc->hsmc_regs, SR); /* clear the NFC_SR */
@@ -2426,17 +2449,8 @@ static int atmel_nand_nfc_remove(struct platform_device *pdev)
return 0;
}
-static const struct atmel_nand_nfc_caps sama5d3_nfc_caps = {
- .rb_mask = NFC_SR_RB_EDGE0,
-};
-
-static const struct atmel_nand_nfc_caps sama5d4_nfc_caps = {
- .rb_mask = NFC_SR_RB_EDGE3,
-};
-
static const struct of_device_id atmel_nand_nfc_match[] = {
- { .compatible = "atmel,sama5d3-nfc", .data = &sama5d3_nfc_caps },
- { .compatible = "atmel,sama5d4-nfc", .data = &sama5d4_nfc_caps },
+ { .compatible = "atmel,sama5d3-nfc" },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, atmel_nand_nfc_match);
diff --git a/drivers/mtd/nand/atmel_nand_nfc.h b/drivers/mtd/nand/atmel_nand_nfc.h
index 0bbc1fa97dba..4d5d26221a7e 100644
--- a/drivers/mtd/nand/atmel_nand_nfc.h
+++ b/drivers/mtd/nand/atmel_nand_nfc.h
@@ -42,8 +42,7 @@
#define NFC_SR_UNDEF (1 << 21)
#define NFC_SR_AWB (1 << 22)
#define NFC_SR_ASE (1 << 23)
-#define NFC_SR_RB_EDGE0 (1 << 24)
-#define NFC_SR_RB_EDGE3 (1 << 27)
+#define NFC_SR_RB_EDGE (1 << 24)
#define ATMEL_HSMC_NFC_IER 0x0c
#define ATMEL_HSMC_NFC_IDR 0x10
diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c
index 341ea4904164..9bf6d9915694 100644
--- a/drivers/mtd/nand/au1550nd.c
+++ b/drivers/mtd/nand/au1550nd.c
@@ -459,6 +459,7 @@ static int au1550nd_probe(struct platform_device *pdev)
/* 30 us command delay time */
this->chip_delay = 30;
this->ecc.mode = NAND_ECC_SOFT;
+ this->ecc.algo = NAND_ECC_HAMMING;
if (pd->devwidth)
this->options |= NAND_BUSWIDTH_16;
diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c
index 7f6b30e615b7..37da4236ab90 100644
--- a/drivers/mtd/nand/bf5xx_nand.c
+++ b/drivers/mtd/nand/bf5xx_nand.c
@@ -109,28 +109,33 @@ static const unsigned short bfin_nfc_pin_req[] =
0};
#ifdef CONFIG_MTD_NAND_BF5XX_BOOTROM_ECC
-static struct nand_ecclayout bootrom_ecclayout = {
- .eccbytes = 24,
- .eccpos = {
- 0x8 * 0, 0x8 * 0 + 1, 0x8 * 0 + 2,
- 0x8 * 1, 0x8 * 1 + 1, 0x8 * 1 + 2,
- 0x8 * 2, 0x8 * 2 + 1, 0x8 * 2 + 2,
- 0x8 * 3, 0x8 * 3 + 1, 0x8 * 3 + 2,
- 0x8 * 4, 0x8 * 4 + 1, 0x8 * 4 + 2,
- 0x8 * 5, 0x8 * 5 + 1, 0x8 * 5 + 2,
- 0x8 * 6, 0x8 * 6 + 1, 0x8 * 6 + 2,
- 0x8 * 7, 0x8 * 7 + 1, 0x8 * 7 + 2
- },
- .oobfree = {
- { 0x8 * 0 + 3, 5 },
- { 0x8 * 1 + 3, 5 },
- { 0x8 * 2 + 3, 5 },
- { 0x8 * 3 + 3, 5 },
- { 0x8 * 4 + 3, 5 },
- { 0x8 * 5 + 3, 5 },
- { 0x8 * 6 + 3, 5 },
- { 0x8 * 7 + 3, 5 },
- }
+static int bootrom_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 7)
+ return -ERANGE;
+
+ oobregion->offset = section * 8;
+ oobregion->length = 3;
+
+ return 0;
+}
+
+static int bootrom_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 7)
+ return -ERANGE;
+
+ oobregion->offset = (section * 8) + 3;
+ oobregion->length = 5;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops bootrom_ooblayout_ops = {
+ .ecc = bootrom_ooblayout_ecc,
+ .free = bootrom_ooblayout_free,
};
#endif
@@ -800,7 +805,7 @@ static int bf5xx_nand_probe(struct platform_device *pdev)
/* setup hardware ECC data struct */
if (hardware_ecc) {
#ifdef CONFIG_MTD_NAND_BF5XX_BOOTROM_ECC
- chip->ecc.layout = &bootrom_ecclayout;
+ mtd_set_ooblayout(mtd, &bootrom_ooblayout_ops);
#endif
chip->read_buf = bf5xx_nand_dma_read_buf;
chip->write_buf = bf5xx_nand_dma_write_buf;
@@ -812,6 +817,7 @@ static int bf5xx_nand_probe(struct platform_device *pdev)
chip->ecc.write_page_raw = bf5xx_nand_write_page_raw;
} else {
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
}
/* scan hardware nand chip and setup mtd info data struct */
diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c
index e0528397306a..b76ad7c0144f 100644
--- a/drivers/mtd/nand/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/brcmnand/brcmnand.c
@@ -32,7 +32,6 @@
#include <linux/mtd/nand.h>
#include <linux/mtd/partitions.h>
#include <linux/of.h>
-#include <linux/of_mtd.h>
#include <linux/of_platform.h>
#include <linux/slab.h>
#include <linux/list.h>
@@ -601,7 +600,7 @@ static void brcmnand_wr_corr_thresh(struct brcmnand_host *host, u8 val)
static inline int brcmnand_cmd_shift(struct brcmnand_controller *ctrl)
{
- if (ctrl->nand_version < 0x0700)
+ if (ctrl->nand_version < 0x0602)
return 24;
return 0;
}
@@ -781,127 +780,183 @@ static inline bool is_hamming_ecc(struct brcmnand_cfg *cfg)
}
/*
- * Returns a nand_ecclayout strucutre for the given layout/configuration.
- * Returns NULL on failure.
+ * Set mtd->ooblayout to the appropriate mtd_ooblayout_ops given
+ * the layout/configuration.
+ * Returns -ERRCODE on failure.
*/
-static struct nand_ecclayout *brcmnand_create_layout(int ecc_level,
- struct brcmnand_host *host)
+static int brcmnand_hamming_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct brcmnand_host *host = nand_get_controller_data(chip);
struct brcmnand_cfg *cfg = &host->hwcfg;
- int i, j;
- struct nand_ecclayout *layout;
- int req;
- int sectors;
- int sas;
- int idx1, idx2;
-
- layout = devm_kzalloc(&host->pdev->dev, sizeof(*layout), GFP_KERNEL);
- if (!layout)
- return NULL;
-
- sectors = cfg->page_size / (512 << cfg->sector_size_1k);
- sas = cfg->spare_area_size << cfg->sector_size_1k;
-
- /* Hamming */
- if (is_hamming_ecc(cfg)) {
- for (i = 0, idx1 = 0, idx2 = 0; i < sectors; i++) {
- /* First sector of each page may have BBI */
- if (i == 0) {
- layout->oobfree[idx2].offset = i * sas + 1;
- /* Small-page NAND use byte 6 for BBI */
- if (cfg->page_size == 512)
- layout->oobfree[idx2].offset--;
- layout->oobfree[idx2].length = 5;
- } else {
- layout->oobfree[idx2].offset = i * sas;
- layout->oobfree[idx2].length = 6;
- }
- idx2++;
- layout->eccpos[idx1++] = i * sas + 6;
- layout->eccpos[idx1++] = i * sas + 7;
- layout->eccpos[idx1++] = i * sas + 8;
- layout->oobfree[idx2].offset = i * sas + 9;
- layout->oobfree[idx2].length = 7;
- idx2++;
- /* Leave zero-terminated entry for OOBFREE */
- if (idx1 >= MTD_MAX_ECCPOS_ENTRIES_LARGE ||
- idx2 >= MTD_MAX_OOBFREE_ENTRIES_LARGE - 1)
- break;
- }
+ int sas = cfg->spare_area_size << cfg->sector_size_1k;
+ int sectors = cfg->page_size / (512 << cfg->sector_size_1k);
- return layout;
- }
+ if (section >= sectors)
+ return -ERANGE;
- /*
- * CONTROLLER_VERSION:
- * < v5.0: ECC_REQ = ceil(BCH_T * 13/8)
- * >= v5.0: ECC_REQ = ceil(BCH_T * 14/8)
- * But we will just be conservative.
- */
- req = DIV_ROUND_UP(ecc_level * 14, 8);
- if (req >= sas) {
- dev_err(&host->pdev->dev,
- "error: ECC too large for OOB (ECC bytes %d, spare sector %d)\n",
- req, sas);
- return NULL;
- }
+ oobregion->offset = (section * sas) + 6;
+ oobregion->length = 3;
+
+ return 0;
+}
+
+static int brcmnand_hamming_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct brcmnand_host *host = nand_get_controller_data(chip);
+ struct brcmnand_cfg *cfg = &host->hwcfg;
+ int sas = cfg->spare_area_size << cfg->sector_size_1k;
+ int sectors = cfg->page_size / (512 << cfg->sector_size_1k);
- layout->eccbytes = req * sectors;
- for (i = 0, idx1 = 0, idx2 = 0; i < sectors; i++) {
- for (j = sas - req; j < sas && idx1 <
- MTD_MAX_ECCPOS_ENTRIES_LARGE; j++, idx1++)
- layout->eccpos[idx1] = i * sas + j;
+ if (section >= sectors * 2)
+ return -ERANGE;
+
+ oobregion->offset = (section / 2) * sas;
+
+ if (section & 1) {
+ oobregion->offset += 9;
+ oobregion->length = 7;
+ } else {
+ oobregion->length = 6;
/* First sector of each page may have BBI */
- if (i == 0) {
- if (cfg->page_size == 512 && (sas - req >= 6)) {
- /* Small-page NAND use byte 6 for BBI */
- layout->oobfree[idx2].offset = 0;
- layout->oobfree[idx2].length = 5;
- idx2++;
- if (sas - req > 6) {
- layout->oobfree[idx2].offset = 6;
- layout->oobfree[idx2].length =
- sas - req - 6;
- idx2++;
- }
- } else if (sas > req + 1) {
- layout->oobfree[idx2].offset = i * sas + 1;
- layout->oobfree[idx2].length = sas - req - 1;
- idx2++;
- }
- } else if (sas > req) {
- layout->oobfree[idx2].offset = i * sas;
- layout->oobfree[idx2].length = sas - req;
- idx2++;
+ if (!section) {
+ /*
+ * Small-page NAND use byte 6 for BBI while large-page
+ * NAND use byte 0.
+ */
+ if (cfg->page_size > 512)
+ oobregion->offset++;
+ oobregion->length--;
}
- /* Leave zero-terminated entry for OOBFREE */
- if (idx1 >= MTD_MAX_ECCPOS_ENTRIES_LARGE ||
- idx2 >= MTD_MAX_OOBFREE_ENTRIES_LARGE - 1)
- break;
}
- return layout;
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops brcmnand_hamming_ooblayout_ops = {
+ .ecc = brcmnand_hamming_ooblayout_ecc,
+ .free = brcmnand_hamming_ooblayout_free,
+};
+
+static int brcmnand_bch_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct brcmnand_host *host = nand_get_controller_data(chip);
+ struct brcmnand_cfg *cfg = &host->hwcfg;
+ int sas = cfg->spare_area_size << cfg->sector_size_1k;
+ int sectors = cfg->page_size / (512 << cfg->sector_size_1k);
+
+ if (section >= sectors)
+ return -ERANGE;
+
+ oobregion->offset = (section * (sas + 1)) - chip->ecc.bytes;
+ oobregion->length = chip->ecc.bytes;
+
+ return 0;
+}
+
+static int brcmnand_bch_ooblayout_free_lp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct brcmnand_host *host = nand_get_controller_data(chip);
+ struct brcmnand_cfg *cfg = &host->hwcfg;
+ int sas = cfg->spare_area_size << cfg->sector_size_1k;
+ int sectors = cfg->page_size / (512 << cfg->sector_size_1k);
+
+ if (section >= sectors)
+ return -ERANGE;
+
+ if (sas <= chip->ecc.bytes)
+ return 0;
+
+ oobregion->offset = section * sas;
+ oobregion->length = sas - chip->ecc.bytes;
+
+ if (!section) {
+ oobregion->offset++;
+ oobregion->length--;
+ }
+
+ return 0;
}
-static struct nand_ecclayout *brcmstb_choose_ecc_layout(
- struct brcmnand_host *host)
+static int brcmnand_bch_ooblayout_free_sp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct brcmnand_host *host = nand_get_controller_data(chip);
+ struct brcmnand_cfg *cfg = &host->hwcfg;
+ int sas = cfg->spare_area_size << cfg->sector_size_1k;
+
+ if (section > 1 || sas - chip->ecc.bytes < 6 ||
+ (section && sas - chip->ecc.bytes == 6))
+ return -ERANGE;
+
+ if (!section) {
+ oobregion->offset = 0;
+ oobregion->length = 5;
+ } else {
+ oobregion->offset = 6;
+ oobregion->length = sas - chip->ecc.bytes - 6;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops brcmnand_bch_lp_ooblayout_ops = {
+ .ecc = brcmnand_bch_ooblayout_ecc,
+ .free = brcmnand_bch_ooblayout_free_lp,
+};
+
+static const struct mtd_ooblayout_ops brcmnand_bch_sp_ooblayout_ops = {
+ .ecc = brcmnand_bch_ooblayout_ecc,
+ .free = brcmnand_bch_ooblayout_free_sp,
+};
+
+static int brcmstb_choose_ecc_layout(struct brcmnand_host *host)
{
- struct nand_ecclayout *layout;
struct brcmnand_cfg *p = &host->hwcfg;
+ struct mtd_info *mtd = nand_to_mtd(&host->chip);
+ struct nand_ecc_ctrl *ecc = &host->chip.ecc;
unsigned int ecc_level = p->ecc_level;
+ int sas = p->spare_area_size << p->sector_size_1k;
+ int sectors = p->page_size / (512 << p->sector_size_1k);
if (p->sector_size_1k)
ecc_level <<= 1;
- layout = brcmnand_create_layout(ecc_level, host);
- if (!layout) {
+ if (is_hamming_ecc(p)) {
+ ecc->bytes = 3 * sectors;
+ mtd_set_ooblayout(mtd, &brcmnand_hamming_ooblayout_ops);
+ return 0;
+ }
+
+ /*
+ * CONTROLLER_VERSION:
+ * < v5.0: ECC_REQ = ceil(BCH_T * 13/8)
+ * >= v5.0: ECC_REQ = ceil(BCH_T * 14/8)
+ * But we will just be conservative.
+ */
+ ecc->bytes = DIV_ROUND_UP(ecc_level * 14, 8);
+ if (p->page_size == 512)
+ mtd_set_ooblayout(mtd, &brcmnand_bch_sp_ooblayout_ops);
+ else
+ mtd_set_ooblayout(mtd, &brcmnand_bch_lp_ooblayout_ops);
+
+ if (ecc->bytes >= sas) {
dev_err(&host->pdev->dev,
- "no proper ecc_layout for this NAND cfg\n");
- return NULL;
+ "error: ECC too large for OOB (ECC bytes %d, spare sector %d)\n",
+ ecc->bytes, sas);
+ return -EINVAL;
}
- return layout;
+ return 0;
}
static void brcmnand_wp(struct mtd_info *mtd, int wp)
@@ -1870,9 +1925,31 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
cfg->col_adr_bytes = 2;
cfg->blk_adr_bytes = get_blk_adr_bytes(mtd->size, mtd->writesize);
+ if (chip->ecc.mode != NAND_ECC_HW) {
+ dev_err(ctrl->dev, "only HW ECC supported; selected: %d\n",
+ chip->ecc.mode);
+ return -EINVAL;
+ }
+
+ if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+ if (chip->ecc.strength == 1 && chip->ecc.size == 512)
+ /* Default to Hamming for 1-bit ECC, if unspecified */
+ chip->ecc.algo = NAND_ECC_HAMMING;
+ else
+ /* Otherwise, BCH */
+ chip->ecc.algo = NAND_ECC_BCH;
+ }
+
+ if (chip->ecc.algo == NAND_ECC_HAMMING && (chip->ecc.strength != 1 ||
+ chip->ecc.size != 512)) {
+ dev_err(ctrl->dev, "invalid Hamming params: %d bits per %d bytes\n",
+ chip->ecc.strength, chip->ecc.size);
+ return -EINVAL;
+ }
+
switch (chip->ecc.size) {
case 512:
- if (chip->ecc.strength == 1) /* Hamming */
+ if (chip->ecc.algo == NAND_ECC_HAMMING)
cfg->ecc_level = 15;
else
cfg->ecc_level = chip->ecc.strength;
@@ -2001,8 +2078,8 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
*/
chip->options |= NAND_USE_BOUNCE_BUFFER;
- if (of_get_nand_on_flash_bbt(dn))
- chip->bbt_options |= NAND_BBT_USE_FLASH | NAND_BBT_NO_OOB;
+ if (chip->bbt_options & NAND_BBT_USE_FLASH)
+ chip->bbt_options |= NAND_BBT_NO_OOB;
if (brcmnand_setup_dev(host))
return -ENXIO;
@@ -2011,9 +2088,9 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
/* only use our internal HW threshold */
mtd->bitflip_threshold = 1;
- chip->ecc.layout = brcmstb_choose_ecc_layout(host);
- if (!chip->ecc.layout)
- return -ENXIO;
+ ret = brcmstb_choose_ecc_layout(host);
+ if (ret)
+ return ret;
if (nand_scan_tail(mtd))
return -ENXIO;
@@ -2115,6 +2192,7 @@ static const struct of_device_id brcmnand_of_match[] = {
{ .compatible = "brcm,brcmnand-v5.0" },
{ .compatible = "brcm,brcmnand-v6.0" },
{ .compatible = "brcm,brcmnand-v6.1" },
+ { .compatible = "brcm,brcmnand-v6.2" },
{ .compatible = "brcm,brcmnand-v7.0" },
{ .compatible = "brcm,brcmnand-v7.1" },
{},
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index e553aff68987..0b0c93702abb 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -459,10 +459,37 @@ static int cafe_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
return max_bitflips;
}
-static struct nand_ecclayout cafe_oobinfo_2048 = {
- .eccbytes = 14,
- .eccpos = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13},
- .oobfree = {{14, 50}}
+static int cafe_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 0;
+ oobregion->length = chip->ecc.total;
+
+ return 0;
+}
+
+static int cafe_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = chip->ecc.total;
+ oobregion->length = mtd->oobsize - chip->ecc.total;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops cafe_ooblayout_ops = {
+ .ecc = cafe_ooblayout_ecc,
+ .free = cafe_ooblayout_free,
};
/* Ick. The BBT code really ought to be able to work this bit out
@@ -494,12 +521,6 @@ static struct nand_bbt_descr cafe_bbt_mirror_descr_2048 = {
.pattern = cafe_mirror_pattern_2048
};
-static struct nand_ecclayout cafe_oobinfo_512 = {
- .eccbytes = 14,
- .eccpos = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13},
- .oobfree = {{14, 2}}
-};
-
static struct nand_bbt_descr cafe_bbt_main_descr_512 = {
.options = NAND_BBT_LASTBLOCK | NAND_BBT_CREATE | NAND_BBT_WRITE
| NAND_BBT_2BIT | NAND_BBT_VERSION,
@@ -743,12 +764,11 @@ static int cafe_nand_probe(struct pci_dev *pdev,
cafe->ctl2 |= 1<<29; /* 2KiB page size */
/* Set up ECC according to the type of chip we found */
+ mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
if (mtd->writesize == 2048) {
- cafe->nand.ecc.layout = &cafe_oobinfo_2048;
cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
} else if (mtd->writesize == 512) {
- cafe->nand.ecc.layout = &cafe_oobinfo_512;
cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
} else {
diff --git a/drivers/mtd/nand/cmx270_nand.c b/drivers/mtd/nand/cmx270_nand.c
index 6f97ebba52c4..49133783ca53 100644
--- a/drivers/mtd/nand/cmx270_nand.c
+++ b/drivers/mtd/nand/cmx270_nand.c
@@ -187,6 +187,7 @@ static int __init cmx270_init(void)
/* 15 us command delay time */
this->chip_delay = 20;
this->ecc.mode = NAND_ECC_SOFT;
+ this->ecc.algo = NAND_ECC_HAMMING;
/* read/write functions */
this->read_byte = cmx270_read_byte;
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 8cb821b6686e..cc07ba0f044d 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -34,7 +34,6 @@
#include <linux/slab.h>
#include <linux/of_device.h>
#include <linux/of.h>
-#include <linux/of_mtd.h>
#include <linux/platform_data/mtd-davinci.h>
#include <linux/platform_data/mtd-davinci-aemif.h>
@@ -54,7 +53,6 @@
*/
struct davinci_nand_info {
struct nand_chip chip;
- struct nand_ecclayout ecclayout;
struct device *dev;
struct clk *clk;
@@ -480,63 +478,46 @@ static int nand_davinci_dev_ready(struct mtd_info *mtd)
* ten ECC bytes plus the manufacturer's bad block marker byte, and
* and not overlapping the default BBT markers.
*/
-static struct nand_ecclayout hwecc4_small = {
- .eccbytes = 10,
- .eccpos = { 0, 1, 2, 3, 4,
- /* offset 5 holds the badblock marker */
- 6, 7,
- 13, 14, 15, },
- .oobfree = {
- {.offset = 8, .length = 5, },
- {.offset = 16, },
- },
-};
+static int hwecc4_ooblayout_small_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 2)
+ return -ERANGE;
+
+ if (!section) {
+ oobregion->offset = 0;
+ oobregion->length = 5;
+ } else if (section == 1) {
+ oobregion->offset = 6;
+ oobregion->length = 2;
+ } else {
+ oobregion->offset = 13;
+ oobregion->length = 3;
+ }
-/* An ECC layout for using 4-bit ECC with large-page (2048bytes) flash,
- * storing ten ECC bytes plus the manufacturer's bad block marker byte,
- * and not overlapping the default BBT markers.
- */
-static struct nand_ecclayout hwecc4_2048 = {
- .eccbytes = 40,
- .eccpos = {
- /* at the end of spare sector */
- 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
- 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
- 44, 45, 46, 47, 48, 49, 50, 51, 52, 53,
- 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
- },
- .oobfree = {
- /* 2 bytes at offset 0 hold manufacturer badblock markers */
- {.offset = 2, .length = 22, },
- /* 5 bytes at offset 8 hold BBT markers */
- /* 8 bytes at offset 16 hold JFFS2 clean markers */
- },
-};
+ return 0;
+}
-/*
- * An ECC layout for using 4-bit ECC with large-page (4096bytes) flash,
- * storing ten ECC bytes plus the manufacturer's bad block marker byte,
- * and not overlapping the default BBT markers.
- */
-static struct nand_ecclayout hwecc4_4096 = {
- .eccbytes = 80,
- .eccpos = {
- /* at the end of spare sector */
- 48, 49, 50, 51, 52, 53, 54, 55, 56, 57,
- 58, 59, 60, 61, 62, 63, 64, 65, 66, 67,
- 68, 69, 70, 71, 72, 73, 74, 75, 76, 77,
- 78, 79, 80, 81, 82, 83, 84, 85, 86, 87,
- 88, 89, 90, 91, 92, 93, 94, 95, 96, 97,
- 98, 99, 100, 101, 102, 103, 104, 105, 106, 107,
- 108, 109, 110, 111, 112, 113, 114, 115, 116, 117,
- 118, 119, 120, 121, 122, 123, 124, 125, 126, 127,
- },
- .oobfree = {
- /* 2 bytes at offset 0 hold manufacturer badblock markers */
- {.offset = 2, .length = 46, },
- /* 5 bytes at offset 8 hold BBT markers */
- /* 8 bytes at offset 16 hold JFFS2 clean markers */
- },
+static int hwecc4_ooblayout_small_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 1)
+ return -ERANGE;
+
+ if (!section) {
+ oobregion->offset = 8;
+ oobregion->length = 5;
+ } else {
+ oobregion->offset = 16;
+ oobregion->length = mtd->oobsize - 16;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops hwecc4_small_ooblayout_ops = {
+ .ecc = hwecc4_ooblayout_small_ecc,
+ .free = hwecc4_ooblayout_small_free,
};
#if defined(CONFIG_OF)
@@ -577,8 +558,6 @@ static struct davinci_nand_pdata
"ti,davinci-mask-chipsel", &prop))
pdata->mask_chipsel = prop;
if (!of_property_read_string(pdev->dev.of_node,
- "nand-ecc-mode", &mode) ||
- !of_property_read_string(pdev->dev.of_node,
"ti,davinci-ecc-mode", &mode)) {
if (!strncmp("none", mode, 4))
pdata->ecc_mode = NAND_ECC_NONE;
@@ -591,14 +570,11 @@ static struct davinci_nand_pdata
"ti,davinci-ecc-bits", &prop))
pdata->ecc_bits = prop;
- prop = of_get_nand_bus_width(pdev->dev.of_node);
- if (0 < prop || !of_property_read_u32(pdev->dev.of_node,
- "ti,davinci-nand-buswidth", &prop))
- if (prop == 16)
- pdata->options |= NAND_BUSWIDTH_16;
+ if (!of_property_read_u32(pdev->dev.of_node,
+ "ti,davinci-nand-buswidth", &prop) && prop == 16)
+ pdata->options |= NAND_BUSWIDTH_16;
+
if (of_property_read_bool(pdev->dev.of_node,
- "nand-on-flash-bbt") ||
- of_property_read_bool(pdev->dev.of_node,
"ti,davinci-nand-use-bbt"))
pdata->bbt_options = NAND_BBT_USE_FLASH;
@@ -628,7 +604,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
void __iomem *base;
int ret;
uint32_t val;
- nand_ecc_modes_t ecc_mode;
struct mtd_info *mtd;
pdata = nand_davinci_get_pdata(pdev);
@@ -712,13 +687,53 @@ static int nand_davinci_probe(struct platform_device *pdev)
info->chip.write_buf = nand_davinci_write_buf;
/* Use board-specific ECC config */
- ecc_mode = pdata->ecc_mode;
+ info->chip.ecc.mode = pdata->ecc_mode;
ret = -EINVAL;
- switch (ecc_mode) {
+
+ info->clk = devm_clk_get(&pdev->dev, "aemif");
+ if (IS_ERR(info->clk)) {
+ ret = PTR_ERR(info->clk);
+ dev_dbg(&pdev->dev, "unable to get AEMIF clock, err %d\n", ret);
+ return ret;
+ }
+
+ ret = clk_prepare_enable(info->clk);
+ if (ret < 0) {
+ dev_dbg(&pdev->dev, "unable to enable AEMIF clock, err %d\n",
+ ret);
+ goto err_clk_enable;
+ }
+
+ spin_lock_irq(&davinci_nand_lock);
+
+ /* put CSxNAND into NAND mode */
+ val = davinci_nand_readl(info, NANDFCR_OFFSET);
+ val |= BIT(info->core_chipsel);
+ davinci_nand_writel(info, NANDFCR_OFFSET, val);
+
+ spin_unlock_irq(&davinci_nand_lock);
+
+ /* Scan to find existence of the device(s) */
+ ret = nand_scan_ident(mtd, pdata->mask_chipsel ? 2 : 1, NULL);
+ if (ret < 0) {
+ dev_dbg(&pdev->dev, "no NAND chip(s) found\n");
+ goto err;
+ }
+
+ switch (info->chip.ecc.mode) {
case NAND_ECC_NONE:
+ pdata->ecc_bits = 0;
+ break;
case NAND_ECC_SOFT:
pdata->ecc_bits = 0;
+ /*
+ * This driver expects Hamming based ECC when ecc_mode is set
+ * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+ * avoid adding an extra ->ecc_algo field to
+ * davinci_nand_pdata.
+ */
+ info->chip.ecc.algo = NAND_ECC_HAMMING;
break;
case NAND_ECC_HW:
if (pdata->ecc_bits == 4) {
@@ -754,37 +769,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
default:
return -EINVAL;
}
- info->chip.ecc.mode = ecc_mode;
-
- info->clk = devm_clk_get(&pdev->dev, "aemif");
- if (IS_ERR(info->clk)) {
- ret = PTR_ERR(info->clk);
- dev_dbg(&pdev->dev, "unable to get AEMIF clock, err %d\n", ret);
- return ret;
- }
-
- ret = clk_prepare_enable(info->clk);
- if (ret < 0) {
- dev_dbg(&pdev->dev, "unable to enable AEMIF clock, err %d\n",
- ret);
- goto err_clk_enable;
- }
-
- spin_lock_irq(&davinci_nand_lock);
-
- /* put CSxNAND into NAND mode */
- val = davinci_nand_readl(info, NANDFCR_OFFSET);
- val |= BIT(info->core_chipsel);
- davinci_nand_writel(info, NANDFCR_OFFSET, val);
-
- spin_unlock_irq(&davinci_nand_lock);
-
- /* Scan to find existence of the device(s) */
- ret = nand_scan_ident(mtd, pdata->mask_chipsel ? 2 : 1, NULL);
- if (ret < 0) {
- dev_dbg(&pdev->dev, "no NAND chip(s) found\n");
- goto err;
- }
/* Update ECC layout if needed ... for 1-bit HW ECC, the default
* is OK, but it allocates 6 bytes when only 3 are needed (for
@@ -805,26 +789,14 @@ static int nand_davinci_probe(struct platform_device *pdev)
* table marker fits in the free bytes.
*/
if (chunks == 1) {
- info->ecclayout = hwecc4_small;
- info->ecclayout.oobfree[1].length = mtd->oobsize - 16;
- goto syndrome_done;
- }
- if (chunks == 4) {
- info->ecclayout = hwecc4_2048;
- info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
- goto syndrome_done;
- }
- if (chunks == 8) {
- info->ecclayout = hwecc4_4096;
+ mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
+ } else if (chunks == 4 || chunks == 8) {
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
- goto syndrome_done;
+ } else {
+ ret = -EIO;
+ goto err;
}
-
- ret = -EIO;
- goto err;
-
-syndrome_done:
- info->chip.ecc.layout = &info->ecclayout;
}
ret = nand_scan_tail(mtd);
@@ -850,7 +822,7 @@ err:
err_clk_enable:
spin_lock_irq(&davinci_nand_lock);
- if (ecc_mode == NAND_ECC_HW_SYNDROME)
+ if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
ecc4_busy = false;
spin_unlock_irq(&davinci_nand_lock);
return ret;
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 30bf5f690f78..0476ae8776d9 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -1374,13 +1374,41 @@ static void denali_hw_init(struct denali_nand_info *denali)
* correction
*/
#define ECC_8BITS 14
-static struct nand_ecclayout nand_8bit_oob = {
- .eccbytes = 14,
-};
-
#define ECC_15BITS 26
-static struct nand_ecclayout nand_15bit_oob = {
- .eccbytes = 26,
+
+static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct denali_nand_info *denali = mtd_to_denali(mtd);
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = denali->bbtskipbytes;
+ oobregion->length = chip->ecc.total;
+
+ return 0;
+}
+
+static int denali_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct denali_nand_info *denali = mtd_to_denali(mtd);
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = chip->ecc.total + denali->bbtskipbytes;
+ oobregion->length = mtd->oobsize - oobregion->offset;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops denali_ooblayout_ops = {
+ .ecc = denali_ooblayout_ecc,
+ .free = denali_ooblayout_free,
};
static uint8_t bbt_pattern[] = {'B', 'b', 't', '0' };
@@ -1561,7 +1589,6 @@ int denali_init(struct denali_nand_info *denali)
ECC_SECTOR_SIZE)))) {
/* if MLC OOB size is large enough, use 15bit ECC*/
denali->nand.ecc.strength = 15;
- denali->nand.ecc.layout = &nand_15bit_oob;
denali->nand.ecc.bytes = ECC_15BITS;
iowrite32(15, denali->flash_reg + ECC_CORRECTION);
} else if (mtd->oobsize < (denali->bbtskipbytes +
@@ -1571,20 +1598,13 @@ int denali_init(struct denali_nand_info *denali)
goto failed_req_irq;
} else {
denali->nand.ecc.strength = 8;
- denali->nand.ecc.layout = &nand_8bit_oob;
denali->nand.ecc.bytes = ECC_8BITS;
iowrite32(8, denali->flash_reg + ECC_CORRECTION);
}
+ mtd_set_ooblayout(mtd, &denali_ooblayout_ops);
denali->nand.ecc.bytes *= denali->devnum;
denali->nand.ecc.strength *= denali->devnum;
- denali->nand.ecc.layout->eccbytes *=
- mtd->writesize / ECC_SECTOR_SIZE;
- denali->nand.ecc.layout->oobfree[0].offset =
- denali->bbtskipbytes + denali->nand.ecc.layout->eccbytes;
- denali->nand.ecc.layout->oobfree[0].length =
- mtd->oobsize - denali->nand.ecc.layout->eccbytes -
- denali->bbtskipbytes;
/*
* Let driver know the total blocks number and how many blocks
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index 547c1002941d..a023ab9e9cbf 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -950,20 +950,50 @@ static int doc200x_correct_data(struct mtd_info *mtd, u_char *dat,
//u_char mydatabuf[528];
-/* The strange out-of-order .oobfree list below is a (possibly unneeded)
- * attempt to retain compatibility. It used to read:
- * .oobfree = { {8, 8} }
- * Since that leaves two bytes unusable, it was changed. But the following
- * scheme might affect existing jffs2 installs by moving the cleanmarker:
- * .oobfree = { {6, 10} }
- * jffs2 seems to handle the above gracefully, but the current scheme seems
- * safer. The only problem with it is that any code that parses oobfree must
- * be able to handle out-of-order segments.
- */
-static struct nand_ecclayout doc200x_oobinfo = {
- .eccbytes = 6,
- .eccpos = {0, 1, 2, 3, 4, 5},
- .oobfree = {{8, 8}, {6, 2}}
+static int doc200x_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 0;
+ oobregion->length = 6;
+
+ return 0;
+}
+
+static int doc200x_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 1)
+ return -ERANGE;
+
+ /*
+ * The strange out-of-order free bytes definition is a (possibly
+ * unneeded) attempt to retain compatibility. It used to read:
+ * .oobfree = { {8, 8} }
+ * Since that leaves two bytes unusable, it was changed. But the
+ * following scheme might affect existing jffs2 installs by moving the
+ * cleanmarker:
+ * .oobfree = { {6, 10} }
+ * jffs2 seems to handle the above gracefully, but the current scheme
+ * seems safer. The only problem with it is that any code retrieving
+ * free bytes position must be able to handle out-of-order segments.
+ */
+ if (!section) {
+ oobregion->offset = 8;
+ oobregion->length = 8;
+ } else {
+ oobregion->offset = 6;
+ oobregion->length = 2;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops doc200x_ooblayout_ops = {
+ .ecc = doc200x_ooblayout_ecc,
+ .free = doc200x_ooblayout_free,
};
/* Find the (I)NFTL Media Header, and optionally also the mirror media header.
@@ -1537,6 +1567,7 @@ static int __init doc_probe(unsigned long physadr)
nand->bbt_md = nand->bbt_td + 1;
mtd->owner = THIS_MODULE;
+ mtd_set_ooblayout(mtd, &doc200x_ooblayout_ops);
nand_set_controller_data(nand, doc);
nand->select_chip = doc200x_select_chip;
@@ -1548,7 +1579,6 @@ static int __init doc_probe(unsigned long physadr)
nand->ecc.calculate = doc200x_calculate_ecc;
nand->ecc.correct = doc200x_correct_data;
- nand->ecc.layout = &doc200x_oobinfo;
nand->ecc.mode = NAND_ECC_HW_SYNDROME;
nand->ecc.size = 512;
nand->ecc.bytes = 6;
diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c
index d86a60e1bbcb..47316998017f 100644
--- a/drivers/mtd/nand/docg4.c
+++ b/drivers/mtd/nand/docg4.c
@@ -222,10 +222,33 @@ struct docg4_priv {
* Bytes 8 - 14 are hw-generated ecc covering entire page + oob bytes 0 - 14.
* Byte 15 (the last) is used by the driver as a "page written" flag.
*/
-static struct nand_ecclayout docg4_oobinfo = {
- .eccbytes = 9,
- .eccpos = {7, 8, 9, 10, 11, 12, 13, 14, 15},
- .oobfree = { {.offset = 2, .length = 5} }
+static int docg4_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 7;
+ oobregion->length = 9;
+
+ return 0;
+}
+
+static int docg4_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 2;
+ oobregion->length = 5;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops docg4_ooblayout_ops = {
+ .ecc = docg4_ooblayout_ecc,
+ .free = docg4_ooblayout_free,
};
/*
@@ -1209,6 +1232,7 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
mtd->writesize = DOCG4_PAGE_SIZE;
mtd->erasesize = DOCG4_BLOCK_SIZE;
mtd->oobsize = DOCG4_OOB_SIZE;
+ mtd_set_ooblayout(mtd, &docg4_ooblayout_ops);
nand->chipsize = DOCG4_CHIP_SIZE;
nand->chip_shift = DOCG4_CHIP_SHIFT;
nand->bbt_erase_shift = nand->phys_erase_shift = DOCG4_ERASE_SHIFT;
@@ -1217,7 +1241,6 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
nand->pagemask = 0x3ffff;
nand->badblockpos = NAND_LARGE_BADBLOCK_POS;
nand->badblockbits = 8;
- nand->ecc.layout = &docg4_oobinfo;
nand->ecc.mode = NAND_ECC_HW_SYNDROME;
nand->ecc.size = DOCG4_PAGE_SIZE;
nand->ecc.prepad = 8;
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 059d5f7ec124..60a88f24c6b3 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -79,32 +79,53 @@ struct fsl_elbc_fcm_ctrl {
/* These map to the positions used by the FCM hardware ECC generator */
-/* Small Page FLASH with FMR[ECCM] = 0 */
-static struct nand_ecclayout fsl_elbc_oob_sp_eccm0 = {
- .eccbytes = 3,
- .eccpos = {6, 7, 8},
- .oobfree = { {0, 5}, {9, 7} },
-};
+static int fsl_elbc_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct fsl_elbc_mtd *priv = nand_get_controller_data(chip);
-/* Small Page FLASH with FMR[ECCM] = 1 */
-static struct nand_ecclayout fsl_elbc_oob_sp_eccm1 = {
- .eccbytes = 3,
- .eccpos = {8, 9, 10},
- .oobfree = { {0, 5}, {6, 2}, {11, 5} },
-};
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
-/* Large Page FLASH with FMR[ECCM] = 0 */
-static struct nand_ecclayout fsl_elbc_oob_lp_eccm0 = {
- .eccbytes = 12,
- .eccpos = {6, 7, 8, 22, 23, 24, 38, 39, 40, 54, 55, 56},
- .oobfree = { {1, 5}, {9, 13}, {25, 13}, {41, 13}, {57, 7} },
-};
+ oobregion->offset = (16 * section) + 6;
+ if (priv->fmr & FMR_ECCM)
+ oobregion->offset += 2;
-/* Large Page FLASH with FMR[ECCM] = 1 */
-static struct nand_ecclayout fsl_elbc_oob_lp_eccm1 = {
- .eccbytes = 12,
- .eccpos = {8, 9, 10, 24, 25, 26, 40, 41, 42, 56, 57, 58},
- .oobfree = { {1, 7}, {11, 13}, {27, 13}, {43, 13}, {59, 5} },
+ oobregion->length = chip->ecc.bytes;
+
+ return 0;
+}
+
+static int fsl_elbc_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct fsl_elbc_mtd *priv = nand_get_controller_data(chip);
+
+ if (section > chip->ecc.steps)
+ return -ERANGE;
+
+ if (!section) {
+ oobregion->offset = 0;
+ if (mtd->writesize > 512)
+ oobregion->offset++;
+ oobregion->length = (priv->fmr & FMR_ECCM) ? 7 : 5;
+ } else {
+ oobregion->offset = (16 * section) -
+ ((priv->fmr & FMR_ECCM) ? 5 : 7);
+ if (section < chip->ecc.steps)
+ oobregion->length = 13;
+ else
+ oobregion->length = mtd->oobsize - oobregion->offset;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops fsl_elbc_ooblayout_ops = {
+ .ecc = fsl_elbc_ooblayout_ecc,
+ .free = fsl_elbc_ooblayout_free,
};
/*
@@ -657,8 +678,8 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
chip->ecc.bytes);
dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.total = %d\n",
chip->ecc.total);
- dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.layout = %p\n",
- chip->ecc.layout);
+ dev_dbg(priv->dev, "fsl_elbc_init: mtd->ooblayout = %p\n",
+ mtd->ooblayout);
dev_dbg(priv->dev, "fsl_elbc_init: mtd->flags = %08x\n", mtd->flags);
dev_dbg(priv->dev, "fsl_elbc_init: mtd->size = %lld\n", mtd->size);
dev_dbg(priv->dev, "fsl_elbc_init: mtd->erasesize = %d\n",
@@ -675,14 +696,6 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
} else if (mtd->writesize == 2048) {
priv->page_size = 1;
setbits32(&lbc->bank[priv->bank].or, OR_FCM_PGS);
- /* adjust ecc setup if needed */
- if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
- BR_DECC_CHK_GEN) {
- chip->ecc.size = 512;
- chip->ecc.layout = (priv->fmr & FMR_ECCM) ?
- &fsl_elbc_oob_lp_eccm1 :
- &fsl_elbc_oob_lp_eccm0;
- }
} else {
dev_err(priv->dev,
"fsl_elbc_init: page size %d is not supported\n",
@@ -780,15 +793,14 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
BR_DECC_CHK_GEN) {
chip->ecc.mode = NAND_ECC_HW;
- /* put in small page settings and adjust later if needed */
- chip->ecc.layout = (priv->fmr & FMR_ECCM) ?
- &fsl_elbc_oob_sp_eccm1 : &fsl_elbc_oob_sp_eccm0;
+ mtd_set_ooblayout(mtd, &fsl_elbc_ooblayout_ops);
chip->ecc.size = 512;
chip->ecc.bytes = 3;
chip->ecc.strength = 1;
} else {
/* otherwise fall back to default software ECC */
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
}
return 0;
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 43f5a3a4873f..4e9e5fd8faf3 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -67,136 +67,6 @@ struct fsl_ifc_nand_ctrl {
static struct fsl_ifc_nand_ctrl *ifc_nand_ctrl;
-/* 512-byte page with 4-bit ECC, 8-bit */
-static struct nand_ecclayout oob_512_8bit_ecc4 = {
- .eccbytes = 8,
- .eccpos = {8, 9, 10, 11, 12, 13, 14, 15},
- .oobfree = { {0, 5}, {6, 2} },
-};
-
-/* 512-byte page with 4-bit ECC, 16-bit */
-static struct nand_ecclayout oob_512_16bit_ecc4 = {
- .eccbytes = 8,
- .eccpos = {8, 9, 10, 11, 12, 13, 14, 15},
- .oobfree = { {2, 6}, },
-};
-
-/* 2048-byte page size with 4-bit ECC */
-static struct nand_ecclayout oob_2048_ecc4 = {
- .eccbytes = 32,
- .eccpos = {
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- },
- .oobfree = { {2, 6}, {40, 24} },
-};
-
-/* 4096-byte page size with 4-bit ECC */
-static struct nand_ecclayout oob_4096_ecc4 = {
- .eccbytes = 64,
- .eccpos = {
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 64, 65, 66, 67, 68, 69, 70, 71,
- },
- .oobfree = { {2, 6}, {72, 56} },
-};
-
-/* 4096-byte page size with 8-bit ECC -- requires 218-byte OOB */
-static struct nand_ecclayout oob_4096_ecc8 = {
- .eccbytes = 128,
- .eccpos = {
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 64, 65, 66, 67, 68, 69, 70, 71,
- 72, 73, 74, 75, 76, 77, 78, 79,
- 80, 81, 82, 83, 84, 85, 86, 87,
- 88, 89, 90, 91, 92, 93, 94, 95,
- 96, 97, 98, 99, 100, 101, 102, 103,
- 104, 105, 106, 107, 108, 109, 110, 111,
- 112, 113, 114, 115, 116, 117, 118, 119,
- 120, 121, 122, 123, 124, 125, 126, 127,
- 128, 129, 130, 131, 132, 133, 134, 135,
- },
- .oobfree = { {2, 6}, {136, 82} },
-};
-
-/* 8192-byte page size with 4-bit ECC */
-static struct nand_ecclayout oob_8192_ecc4 = {
- .eccbytes = 128,
- .eccpos = {
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 64, 65, 66, 67, 68, 69, 70, 71,
- 72, 73, 74, 75, 76, 77, 78, 79,
- 80, 81, 82, 83, 84, 85, 86, 87,
- 88, 89, 90, 91, 92, 93, 94, 95,
- 96, 97, 98, 99, 100, 101, 102, 103,
- 104, 105, 106, 107, 108, 109, 110, 111,
- 112, 113, 114, 115, 116, 117, 118, 119,
- 120, 121, 122, 123, 124, 125, 126, 127,
- 128, 129, 130, 131, 132, 133, 134, 135,
- },
- .oobfree = { {2, 6}, {136, 208} },
-};
-
-/* 8192-byte page size with 8-bit ECC -- requires 218-byte OOB */
-static struct nand_ecclayout oob_8192_ecc8 = {
- .eccbytes = 256,
- .eccpos = {
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 64, 65, 66, 67, 68, 69, 70, 71,
- 72, 73, 74, 75, 76, 77, 78, 79,
- 80, 81, 82, 83, 84, 85, 86, 87,
- 88, 89, 90, 91, 92, 93, 94, 95,
- 96, 97, 98, 99, 100, 101, 102, 103,
- 104, 105, 106, 107, 108, 109, 110, 111,
- 112, 113, 114, 115, 116, 117, 118, 119,
- 120, 121, 122, 123, 124, 125, 126, 127,
- 128, 129, 130, 131, 132, 133, 134, 135,
- 136, 137, 138, 139, 140, 141, 142, 143,
- 144, 145, 146, 147, 148, 149, 150, 151,
- 152, 153, 154, 155, 156, 157, 158, 159,
- 160, 161, 162, 163, 164, 165, 166, 167,
- 168, 169, 170, 171, 172, 173, 174, 175,
- 176, 177, 178, 179, 180, 181, 182, 183,
- 184, 185, 186, 187, 188, 189, 190, 191,
- 192, 193, 194, 195, 196, 197, 198, 199,
- 200, 201, 202, 203, 204, 205, 206, 207,
- 208, 209, 210, 211, 212, 213, 214, 215,
- 216, 217, 218, 219, 220, 221, 222, 223,
- 224, 225, 226, 227, 228, 229, 230, 231,
- 232, 233, 234, 235, 236, 237, 238, 239,
- 240, 241, 242, 243, 244, 245, 246, 247,
- 248, 249, 250, 251, 252, 253, 254, 255,
- 256, 257, 258, 259, 260, 261, 262, 263,
- },
- .oobfree = { {2, 6}, {264, 80} },
-};
-
/*
* Generic flash bbt descriptors
*/
@@ -223,6 +93,57 @@ static struct nand_bbt_descr bbt_mirror_descr = {
.pattern = mirror_pattern,
};
+static int fsl_ifc_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 8;
+ oobregion->length = chip->ecc.total;
+
+ return 0;
+}
+
+static int fsl_ifc_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section > 1)
+ return -ERANGE;
+
+ if (mtd->writesize == 512 &&
+ !(chip->options & NAND_BUSWIDTH_16)) {
+ if (!section) {
+ oobregion->offset = 0;
+ oobregion->length = 5;
+ } else {
+ oobregion->offset = 6;
+ oobregion->length = 2;
+ }
+
+ return 0;
+ }
+
+ if (!section) {
+ oobregion->offset = 2;
+ oobregion->length = 6;
+ } else {
+ oobregion->offset = chip->ecc.total + 8;
+ oobregion->length = mtd->oobsize - oobregion->offset;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops fsl_ifc_ooblayout_ops = {
+ .ecc = fsl_ifc_ooblayout_ecc,
+ .free = fsl_ifc_ooblayout_free,
+};
+
/*
* Set up the IFC hardware block and page address fields, and the ifc nand
* structure addr field to point to the correct IFC buffer in memory
@@ -232,7 +153,7 @@ static void set_addr(struct mtd_info *mtd, int column, int page_addr, int oob)
struct nand_chip *chip = mtd_to_nand(mtd);
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs;
int buf_num;
ifc_nand_ctrl->page = page_addr;
@@ -257,18 +178,22 @@ static int is_blank(struct mtd_info *mtd, unsigned int bufnum)
u8 __iomem *addr = priv->vbase + bufnum * (mtd->writesize * 2);
u32 __iomem *mainarea = (u32 __iomem *)addr;
u8 __iomem *oob = addr + mtd->writesize;
- int i;
+ struct mtd_oob_region oobregion = { };
+ int i, section = 0;
for (i = 0; i < mtd->writesize / 4; i++) {
if (__raw_readl(&mainarea[i]) != 0xffffffff)
return 0;
}
- for (i = 0; i < chip->ecc.layout->eccbytes; i++) {
- int pos = chip->ecc.layout->eccpos[i];
+ mtd_ooblayout_ecc(mtd, section++, &oobregion);
+ while (oobregion.length) {
+ for (i = 0; i < oobregion.length; i++) {
+ if (__raw_readb(&oob[oobregion.offset + i]) != 0xff)
+ return 0;
+ }
- if (__raw_readb(&oob[pos]) != 0xff)
- return 0;
+ mtd_ooblayout_ecc(mtd, section++, &oobregion);
}
return 1;
@@ -295,7 +220,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
struct fsl_ifc_nand_ctrl *nctrl = ifc_nand_ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs;
u32 eccstat[4];
int i;
@@ -371,7 +296,7 @@ static void fsl_ifc_do_read(struct nand_chip *chip,
{
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs;
/* Program FIR/IFC_NAND_FCR0 for Small/Large page */
if (mtd->writesize > 512) {
@@ -411,7 +336,7 @@ static void fsl_ifc_cmdfunc(struct mtd_info *mtd, unsigned int command,
struct nand_chip *chip = mtd_to_nand(mtd);
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs;
/* clear the read buffer */
ifc_nand_ctrl->read_bytes = 0;
@@ -723,7 +648,7 @@ static int fsl_ifc_wait(struct mtd_info *mtd, struct nand_chip *chip)
{
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs;
u32 nand_fsr;
/* Use READ_STATUS command, but wait for the device to be ready */
@@ -808,8 +733,8 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
chip->ecc.bytes);
dev_dbg(priv->dev, "%s: nand->ecc.total = %d\n", __func__,
chip->ecc.total);
- dev_dbg(priv->dev, "%s: nand->ecc.layout = %p\n", __func__,
- chip->ecc.layout);
+ dev_dbg(priv->dev, "%s: mtd->ooblayout = %p\n", __func__,
+ mtd->ooblayout);
dev_dbg(priv->dev, "%s: mtd->flags = %08x\n", __func__, mtd->flags);
dev_dbg(priv->dev, "%s: mtd->size = %lld\n", __func__, mtd->size);
dev_dbg(priv->dev, "%s: mtd->erasesize = %d\n", __func__,
@@ -825,39 +750,42 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv)
{
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_runtime __iomem *ifc_runtime = ctrl->rregs;
+ struct fsl_ifc_global __iomem *ifc_global = ctrl->gregs;
uint32_t csor = 0, csor_8k = 0, csor_ext = 0;
uint32_t cs = priv->bank;
/* Save CSOR and CSOR_ext */
- csor = ifc_in32(&ifc->csor_cs[cs].csor);
- csor_ext = ifc_in32(&ifc->csor_cs[cs].csor_ext);
+ csor = ifc_in32(&ifc_global->csor_cs[cs].csor);
+ csor_ext = ifc_in32(&ifc_global->csor_cs[cs].csor_ext);
/* chage PageSize 8K and SpareSize 1K*/
csor_8k = (csor & ~(CSOR_NAND_PGS_MASK)) | 0x0018C000;
- ifc_out32(csor_8k, &ifc->csor_cs[cs].csor);
- ifc_out32(0x0000400, &ifc->csor_cs[cs].csor_ext);
+ ifc_out32(csor_8k, &ifc_global->csor_cs[cs].csor);
+ ifc_out32(0x0000400, &ifc_global->csor_cs[cs].csor_ext);
/* READID */
ifc_out32((IFC_FIR_OP_CW0 << IFC_NAND_FIR0_OP0_SHIFT) |
- (IFC_FIR_OP_UA << IFC_NAND_FIR0_OP1_SHIFT) |
- (IFC_FIR_OP_RB << IFC_NAND_FIR0_OP2_SHIFT),
- &ifc->ifc_nand.nand_fir0);
+ (IFC_FIR_OP_UA << IFC_NAND_FIR0_OP1_SHIFT) |
+ (IFC_FIR_OP_RB << IFC_NAND_FIR0_OP2_SHIFT),
+ &ifc_runtime->ifc_nand.nand_fir0);
ifc_out32(NAND_CMD_READID << IFC_NAND_FCR0_CMD0_SHIFT,
- &ifc->ifc_nand.nand_fcr0);
- ifc_out32(0x0, &ifc->ifc_nand.row3);
+ &ifc_runtime->ifc_nand.nand_fcr0);
+ ifc_out32(0x0, &ifc_runtime->ifc_nand.row3);
- ifc_out32(0x0, &ifc->ifc_nand.nand_fbcr);
+ ifc_out32(0x0, &ifc_runtime->ifc_nand.nand_fbcr);
/* Program ROW0/COL0 */
- ifc_out32(0x0, &ifc->ifc_nand.row0);
- ifc_out32(0x0, &ifc->ifc_nand.col0);
+ ifc_out32(0x0, &ifc_runtime->ifc_nand.row0);
+ ifc_out32(0x0, &ifc_runtime->ifc_nand.col0);
/* set the chip select for NAND Transaction */
- ifc_out32(cs << IFC_NAND_CSEL_SHIFT, &ifc->ifc_nand.nand_csel);
+ ifc_out32(cs << IFC_NAND_CSEL_SHIFT,
+ &ifc_runtime->ifc_nand.nand_csel);
/* start read seq */
- ifc_out32(IFC_NAND_SEQ_STRT_FIR_STRT, &ifc->ifc_nand.nandseq_strt);
+ ifc_out32(IFC_NAND_SEQ_STRT_FIR_STRT,
+ &ifc_runtime->ifc_nand.nandseq_strt);
/* wait for command complete flag or timeout */
wait_event_timeout(ctrl->nand_wait, ctrl->nand_stat,
@@ -867,17 +795,17 @@ static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv)
printk(KERN_ERR "fsl-ifc: Failed to Initialise SRAM\n");
/* Restore CSOR and CSOR_ext */
- ifc_out32(csor, &ifc->csor_cs[cs].csor);
- ifc_out32(csor_ext, &ifc->csor_cs[cs].csor_ext);
+ ifc_out32(csor, &ifc_global->csor_cs[cs].csor);
+ ifc_out32(csor_ext, &ifc_global->csor_cs[cs].csor_ext);
}
static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
{
struct fsl_ifc_ctrl *ctrl = priv->ctrl;
- struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+ struct fsl_ifc_global __iomem *ifc_global = ctrl->gregs;
+ struct fsl_ifc_runtime __iomem *ifc_runtime = ctrl->rregs;
struct nand_chip *chip = &priv->chip;
struct mtd_info *mtd = nand_to_mtd(&priv->chip);
- struct nand_ecclayout *layout;
u32 csor;
/* Fill in fsl_ifc_mtd structure */
@@ -886,7 +814,8 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
/* fill in nand_chip structure */
/* set up function call table */
- if ((ifc_in32(&ifc->cspr_cs[priv->bank].cspr)) & CSPR_PORT_SIZE_16)
+ if ((ifc_in32(&ifc_global->cspr_cs[priv->bank].cspr))
+ & CSPR_PORT_SIZE_16)
chip->read_byte = fsl_ifc_read_byte16;
else
chip->read_byte = fsl_ifc_read_byte;
@@ -900,13 +829,14 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
chip->bbt_td = &bbt_main_descr;
chip->bbt_md = &bbt_mirror_descr;
- ifc_out32(0x0, &ifc->ifc_nand.ncfgr);
+ ifc_out32(0x0, &ifc_runtime->ifc_nand.ncfgr);
/* set up nand options */
chip->bbt_options = NAND_BBT_USE_FLASH;
chip->options = NAND_NO_SUBPAGE_WRITE;
- if (ifc_in32(&ifc->cspr_cs[priv->bank].cspr) & CSPR_PORT_SIZE_16) {
+ if (ifc_in32(&ifc_global->cspr_cs[priv->bank].cspr)
+ & CSPR_PORT_SIZE_16) {
chip->read_byte = fsl_ifc_read_byte16;
chip->options |= NAND_BUSWIDTH_16;
} else {
@@ -919,20 +849,11 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
chip->ecc.read_page = fsl_ifc_read_page;
chip->ecc.write_page = fsl_ifc_write_page;
- csor = ifc_in32(&ifc->csor_cs[priv->bank].csor);
-
- /* Hardware generates ECC per 512 Bytes */
- chip->ecc.size = 512;
- chip->ecc.bytes = 8;
- chip->ecc.strength = 4;
+ csor = ifc_in32(&ifc_global->csor_cs[priv->bank].csor);
switch (csor & CSOR_NAND_PGS_MASK) {
case CSOR_NAND_PGS_512:
- if (chip->options & NAND_BUSWIDTH_16) {
- layout = &oob_512_16bit_ecc4;
- } else {
- layout = &oob_512_8bit_ecc4;
-
+ if (!(chip->options & NAND_BUSWIDTH_16)) {
/* Avoid conflict with bad block marker */
bbt_main_descr.offs = 0;
bbt_mirror_descr.offs = 0;
@@ -942,35 +863,16 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
break;
case CSOR_NAND_PGS_2K:
- layout = &oob_2048_ecc4;
priv->bufnum_mask = 3;
break;
case CSOR_NAND_PGS_4K:
- if ((csor & CSOR_NAND_ECC_MODE_MASK) ==
- CSOR_NAND_ECC_MODE_4) {
- layout = &oob_4096_ecc4;
- } else {
- layout = &oob_4096_ecc8;
- chip->ecc.bytes = 16;
- chip->ecc.strength = 8;
- }
-
priv->bufnum_mask = 1;
break;
case CSOR_NAND_PGS_8K:
- if ((csor & CSOR_NAND_ECC_MODE_MASK) ==
- CSOR_NAND_ECC_MODE_4) {
- layout = &oob_8192_ecc4;
- } else {
- layout = &oob_8192_ecc8;
- chip->ecc.bytes = 16;
- chip->ecc.strength = 8;
- }
-
priv->bufnum_mask = 0;
- break;
+ break;
default:
dev_err(priv->dev, "bad csor %#x: bad page size\n", csor);
@@ -980,9 +882,20 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
/* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
if (csor & CSOR_NAND_ECC_DEC_EN) {
chip->ecc.mode = NAND_ECC_HW;
- chip->ecc.layout = layout;
+ mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
+
+ /* Hardware generates ECC per 512 Bytes */
+ chip->ecc.size = 512;
+ if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
+ chip->ecc.bytes = 8;
+ chip->ecc.strength = 4;
+ } else {
+ chip->ecc.bytes = 16;
+ chip->ecc.strength = 8;
+ }
} else {
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
}
if (ctrl->version == FSL_IFC_VERSION_1_1_0)
@@ -1007,10 +920,10 @@ static int fsl_ifc_chip_remove(struct fsl_ifc_mtd *priv)
return 0;
}
-static int match_bank(struct fsl_ifc_regs __iomem *ifc, int bank,
+static int match_bank(struct fsl_ifc_global __iomem *ifc_global, int bank,
phys_addr_t addr)
{
- u32 cspr = ifc_in32(&ifc->cspr_cs[bank].cspr);
+ u32 cspr = ifc_in32(&ifc_global->cspr_cs[bank].cspr);
if (!(cspr & CSPR_V))
return 0;
@@ -1024,7 +937,7 @@ static DEFINE_MUTEX(fsl_ifc_nand_mutex);
static int fsl_ifc_nand_probe(struct platform_device *dev)
{
- struct fsl_ifc_regs __iomem *ifc;
+ struct fsl_ifc_runtime __iomem *ifc;
struct fsl_ifc_mtd *priv;
struct resource res;
static const char *part_probe_types[]
@@ -1034,9 +947,9 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
struct device_node *node = dev->dev.of_node;
struct mtd_info *mtd;
- if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->regs)
+ if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->rregs)
return -ENODEV;
- ifc = fsl_ifc_ctrl_dev->regs;
+ ifc = fsl_ifc_ctrl_dev->rregs;
/* get, allocate and map the memory resource */
ret = of_address_to_resource(node, 0, &res);
@@ -1047,7 +960,7 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
/* find which chip select it is connected to */
for (bank = 0; bank < fsl_ifc_ctrl_dev->banks; bank++) {
- if (match_bank(ifc, bank, res.start))
+ if (match_bank(fsl_ifc_ctrl_dev->gregs, bank, res.start))
break;
}
diff --git a/drivers/mtd/nand/fsl_upm.c b/drivers/mtd/nand/fsl_upm.c
index cafd12de7276..d85fa2555b68 100644
--- a/drivers/mtd/nand/fsl_upm.c
+++ b/drivers/mtd/nand/fsl_upm.c
@@ -170,6 +170,7 @@ static int fun_chip_init(struct fsl_upm_nand *fun,
fun->chip.read_buf = fun_read_buf;
fun->chip.write_buf = fun_write_buf;
fun->chip.ecc.mode = NAND_ECC_SOFT;
+ fun->chip.ecc.algo = NAND_ECC_HAMMING;
if (fun->mchip_count > 1)
fun->chip.select_chip = fun_select_chip;
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 1bdcd4fa26d4..d4f454a4b35e 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -39,210 +39,41 @@
#include <linux/amba/bus.h>
#include <mtd/mtd-abi.h>
-static struct nand_ecclayout fsmc_ecc1_128_layout = {
- .eccbytes = 24,
- .eccpos = {2, 3, 4, 18, 19, 20, 34, 35, 36, 50, 51, 52,
- 66, 67, 68, 82, 83, 84, 98, 99, 100, 114, 115, 116},
- .oobfree = {
- {.offset = 8, .length = 8},
- {.offset = 24, .length = 8},
- {.offset = 40, .length = 8},
- {.offset = 56, .length = 8},
- {.offset = 72, .length = 8},
- {.offset = 88, .length = 8},
- {.offset = 104, .length = 8},
- {.offset = 120, .length = 8}
- }
-};
+static int fsmc_ecc1_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
-static struct nand_ecclayout fsmc_ecc1_64_layout = {
- .eccbytes = 12,
- .eccpos = {2, 3, 4, 18, 19, 20, 34, 35, 36, 50, 51, 52},
- .oobfree = {
- {.offset = 8, .length = 8},
- {.offset = 24, .length = 8},
- {.offset = 40, .length = 8},
- {.offset = 56, .length = 8},
- }
-};
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
-static struct nand_ecclayout fsmc_ecc1_16_layout = {
- .eccbytes = 3,
- .eccpos = {2, 3, 4},
- .oobfree = {
- {.offset = 8, .length = 8},
- }
-};
+ oobregion->offset = (section * 16) + 2;
+ oobregion->length = 3;
-/*
- * ECC4 layout for NAND of pagesize 8192 bytes & OOBsize 256 bytes. 13*16 bytes
- * of OB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block and 46
- * bytes are free for use.
- */
-static struct nand_ecclayout fsmc_ecc4_256_layout = {
- .eccbytes = 208,
- .eccpos = { 2, 3, 4, 5, 6, 7, 8,
- 9, 10, 11, 12, 13, 14,
- 18, 19, 20, 21, 22, 23, 24,
- 25, 26, 27, 28, 29, 30,
- 34, 35, 36, 37, 38, 39, 40,
- 41, 42, 43, 44, 45, 46,
- 50, 51, 52, 53, 54, 55, 56,
- 57, 58, 59, 60, 61, 62,
- 66, 67, 68, 69, 70, 71, 72,
- 73, 74, 75, 76, 77, 78,
- 82, 83, 84, 85, 86, 87, 88,
- 89, 90, 91, 92, 93, 94,
- 98, 99, 100, 101, 102, 103, 104,
- 105, 106, 107, 108, 109, 110,
- 114, 115, 116, 117, 118, 119, 120,
- 121, 122, 123, 124, 125, 126,
- 130, 131, 132, 133, 134, 135, 136,
- 137, 138, 139, 140, 141, 142,
- 146, 147, 148, 149, 150, 151, 152,
- 153, 154, 155, 156, 157, 158,
- 162, 163, 164, 165, 166, 167, 168,
- 169, 170, 171, 172, 173, 174,
- 178, 179, 180, 181, 182, 183, 184,
- 185, 186, 187, 188, 189, 190,
- 194, 195, 196, 197, 198, 199, 200,
- 201, 202, 203, 204, 205, 206,
- 210, 211, 212, 213, 214, 215, 216,
- 217, 218, 219, 220, 221, 222,
- 226, 227, 228, 229, 230, 231, 232,
- 233, 234, 235, 236, 237, 238,
- 242, 243, 244, 245, 246, 247, 248,
- 249, 250, 251, 252, 253, 254
- },
- .oobfree = {
- {.offset = 15, .length = 3},
- {.offset = 31, .length = 3},
- {.offset = 47, .length = 3},
- {.offset = 63, .length = 3},
- {.offset = 79, .length = 3},
- {.offset = 95, .length = 3},
- {.offset = 111, .length = 3},
- {.offset = 127, .length = 3},
- {.offset = 143, .length = 3},
- {.offset = 159, .length = 3},
- {.offset = 175, .length = 3},
- {.offset = 191, .length = 3},
- {.offset = 207, .length = 3},
- {.offset = 223, .length = 3},
- {.offset = 239, .length = 3},
- {.offset = 255, .length = 1}
- }
-};
+ return 0;
+}
-/*
- * ECC4 layout for NAND of pagesize 4096 bytes & OOBsize 224 bytes. 13*8 bytes
- * of OOB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block & 118
- * bytes are free for use.
- */
-static struct nand_ecclayout fsmc_ecc4_224_layout = {
- .eccbytes = 104,
- .eccpos = { 2, 3, 4, 5, 6, 7, 8,
- 9, 10, 11, 12, 13, 14,
- 18, 19, 20, 21, 22, 23, 24,
- 25, 26, 27, 28, 29, 30,
- 34, 35, 36, 37, 38, 39, 40,
- 41, 42, 43, 44, 45, 46,
- 50, 51, 52, 53, 54, 55, 56,
- 57, 58, 59, 60, 61, 62,
- 66, 67, 68, 69, 70, 71, 72,
- 73, 74, 75, 76, 77, 78,
- 82, 83, 84, 85, 86, 87, 88,
- 89, 90, 91, 92, 93, 94,
- 98, 99, 100, 101, 102, 103, 104,
- 105, 106, 107, 108, 109, 110,
- 114, 115, 116, 117, 118, 119, 120,
- 121, 122, 123, 124, 125, 126
- },
- .oobfree = {
- {.offset = 15, .length = 3},
- {.offset = 31, .length = 3},
- {.offset = 47, .length = 3},
- {.offset = 63, .length = 3},
- {.offset = 79, .length = 3},
- {.offset = 95, .length = 3},
- {.offset = 111, .length = 3},
- {.offset = 127, .length = 97}
- }
-};
+static int fsmc_ecc1_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
-/*
- * ECC4 layout for NAND of pagesize 4096 bytes & OOBsize 128 bytes. 13*8 bytes
- * of OOB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block & 22
- * bytes are free for use.
- */
-static struct nand_ecclayout fsmc_ecc4_128_layout = {
- .eccbytes = 104,
- .eccpos = { 2, 3, 4, 5, 6, 7, 8,
- 9, 10, 11, 12, 13, 14,
- 18, 19, 20, 21, 22, 23, 24,
- 25, 26, 27, 28, 29, 30,
- 34, 35, 36, 37, 38, 39, 40,
- 41, 42, 43, 44, 45, 46,
- 50, 51, 52, 53, 54, 55, 56,
- 57, 58, 59, 60, 61, 62,
- 66, 67, 68, 69, 70, 71, 72,
- 73, 74, 75, 76, 77, 78,
- 82, 83, 84, 85, 86, 87, 88,
- 89, 90, 91, 92, 93, 94,
- 98, 99, 100, 101, 102, 103, 104,
- 105, 106, 107, 108, 109, 110,
- 114, 115, 116, 117, 118, 119, 120,
- 121, 122, 123, 124, 125, 126
- },
- .oobfree = {
- {.offset = 15, .length = 3},
- {.offset = 31, .length = 3},
- {.offset = 47, .length = 3},
- {.offset = 63, .length = 3},
- {.offset = 79, .length = 3},
- {.offset = 95, .length = 3},
- {.offset = 111, .length = 3},
- {.offset = 127, .length = 1}
- }
-};
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
-/*
- * ECC4 layout for NAND of pagesize 2048 bytes & OOBsize 64 bytes. 13*4 bytes of
- * OOB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block and 10
- * bytes are free for use.
- */
-static struct nand_ecclayout fsmc_ecc4_64_layout = {
- .eccbytes = 52,
- .eccpos = { 2, 3, 4, 5, 6, 7, 8,
- 9, 10, 11, 12, 13, 14,
- 18, 19, 20, 21, 22, 23, 24,
- 25, 26, 27, 28, 29, 30,
- 34, 35, 36, 37, 38, 39, 40,
- 41, 42, 43, 44, 45, 46,
- 50, 51, 52, 53, 54, 55, 56,
- 57, 58, 59, 60, 61, 62,
- },
- .oobfree = {
- {.offset = 15, .length = 3},
- {.offset = 31, .length = 3},
- {.offset = 47, .length = 3},
- {.offset = 63, .length = 1},
- }
-};
+ oobregion->offset = (section * 16) + 8;
-/*
- * ECC4 layout for NAND of pagesize 512 bytes & OOBsize 16 bytes. 13 bytes of
- * OOB size is reserved for ECC, Byte no. 4 & 5 reserved for bad block and One
- * byte is free for use.
- */
-static struct nand_ecclayout fsmc_ecc4_16_layout = {
- .eccbytes = 13,
- .eccpos = { 0, 1, 2, 3, 6, 7, 8,
- 9, 10, 11, 12, 13, 14
- },
- .oobfree = {
- {.offset = 15, .length = 1},
- }
+ if (section < chip->ecc.steps - 1)
+ oobregion->length = 8;
+ else
+ oobregion->length = mtd->oobsize - oobregion->offset;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops fsmc_ecc1_ooblayout_ops = {
+ .ecc = fsmc_ecc1_ooblayout_ecc,
+ .free = fsmc_ecc1_ooblayout_free,
};
/*
@@ -250,28 +81,46 @@ static struct nand_ecclayout fsmc_ecc4_16_layout = {
* There are 13 bytes of ecc for every 512 byte block and it has to be read
* consecutively and immediately after the 512 byte data block for hardware to
* generate the error bit offsets in 512 byte data.
- * Managing the ecc bytes in the following way makes it easier for software to
- * read ecc bytes consecutive to data bytes. This way is similar to
- * oobfree structure maintained already in generic nand driver
*/
-static struct fsmc_eccplace fsmc_ecc4_lp_place = {
- .eccplace = {
- {.offset = 2, .length = 13},
- {.offset = 18, .length = 13},
- {.offset = 34, .length = 13},
- {.offset = 50, .length = 13},
- {.offset = 66, .length = 13},
- {.offset = 82, .length = 13},
- {.offset = 98, .length = 13},
- {.offset = 114, .length = 13}
- }
-};
+static int fsmc_ecc4_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
-static struct fsmc_eccplace fsmc_ecc4_sp_place = {
- .eccplace = {
- {.offset = 0, .length = 4},
- {.offset = 6, .length = 9}
- }
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->length = chip->ecc.bytes;
+
+ if (!section && mtd->writesize <= 512)
+ oobregion->offset = 0;
+ else
+ oobregion->offset = (section * 16) + 2;
+
+ return 0;
+}
+
+static int fsmc_ecc4_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 15;
+
+ if (section < chip->ecc.steps - 1)
+ oobregion->length = 3;
+ else
+ oobregion->length = mtd->oobsize - oobregion->offset;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops fsmc_ecc4_ooblayout_ops = {
+ .ecc = fsmc_ecc4_ooblayout_ecc,
+ .free = fsmc_ecc4_ooblayout_free,
};
/**
@@ -283,7 +132,6 @@ static struct fsmc_eccplace fsmc_ecc4_sp_place = {
* @partitions: Partition info for a NAND Flash.
* @nr_partitions: Total number of partition of a NAND flash.
*
- * @ecc_place: ECC placing locations in oobfree type format.
* @bank: Bank number for probed device.
* @clk: Clock structure for FSMC.
*
@@ -303,7 +151,6 @@ struct fsmc_nand_data {
struct mtd_partition *partitions;
unsigned int nr_partitions;
- struct fsmc_eccplace *ecc_place;
unsigned int bank;
struct device *dev;
enum access_mode mode;
@@ -710,8 +557,6 @@ static void fsmc_write_buf_dma(struct mtd_info *mtd, const uint8_t *buf,
static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
uint8_t *buf, int oob_required, int page)
{
- struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
- struct fsmc_eccplace *ecc_place = host->ecc_place;
int i, j, s, stat, eccsize = chip->ecc.size;
int eccbytes = chip->ecc.bytes;
int eccsteps = chip->ecc.steps;
@@ -734,9 +579,15 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
chip->read_buf(mtd, p, eccsize);
for (j = 0; j < eccbytes;) {
- off = ecc_place->eccplace[group].offset;
- len = ecc_place->eccplace[group].length;
- group++;
+ struct mtd_oob_region oobregion;
+ int ret;
+
+ ret = mtd_ooblayout_ecc(mtd, group++, &oobregion);
+ if (ret)
+ return ret;
+
+ off = oobregion.offset;
+ len = oobregion.length;
/*
* length is intentionally kept a higher multiple of 2
@@ -1084,24 +935,10 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
if (AMBA_REV_BITS(host->pid) >= 8) {
switch (mtd->oobsize) {
case 16:
- nand->ecc.layout = &fsmc_ecc4_16_layout;
- host->ecc_place = &fsmc_ecc4_sp_place;
- break;
case 64:
- nand->ecc.layout = &fsmc_ecc4_64_layout;
- host->ecc_place = &fsmc_ecc4_lp_place;
- break;
case 128:
- nand->ecc.layout = &fsmc_ecc4_128_layout;
- host->ecc_place = &fsmc_ecc4_lp_place;
- break;
case 224:
- nand->ecc.layout = &fsmc_ecc4_224_layout;
- host->ecc_place = &fsmc_ecc4_lp_place;
- break;
case 256:
- nand->ecc.layout = &fsmc_ecc4_256_layout;
- host->ecc_place = &fsmc_ecc4_lp_place;
break;
default:
dev_warn(&pdev->dev, "No oob scheme defined for oobsize %d\n",
@@ -1109,6 +946,8 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
ret = -EINVAL;
goto err_probe;
}
+
+ mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
} else {
switch (nand->ecc.mode) {
case NAND_ECC_HW:
@@ -1119,9 +958,11 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
nand->ecc.strength = 1;
break;
- case NAND_ECC_SOFT_BCH:
- dev_info(&pdev->dev, "Using 4-bit SW BCH ECC scheme\n");
- break;
+ case NAND_ECC_SOFT:
+ if (nand->ecc.algo == NAND_ECC_BCH) {
+ dev_info(&pdev->dev, "Using 4-bit SW BCH ECC scheme\n");
+ break;
+ }
default:
dev_err(&pdev->dev, "Unsupported ECC mode!\n");
@@ -1132,16 +973,13 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
* Don't set layout for BCH4 SW ECC. This will be
* generated later in nand_bch_init() later.
*/
- if (nand->ecc.mode != NAND_ECC_SOFT_BCH) {
+ if (nand->ecc.mode == NAND_ECC_HW) {
switch (mtd->oobsize) {
case 16:
- nand->ecc.layout = &fsmc_ecc1_16_layout;
- break;
case 64:
- nand->ecc.layout = &fsmc_ecc1_64_layout;
- break;
case 128:
- nand->ecc.layout = &fsmc_ecc1_128_layout;
+ mtd_set_ooblayout(mtd,
+ &fsmc_ecc1_ooblayout_ops);
break;
default:
dev_warn(&pdev->dev,
diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c
index ded658fc7d73..6317f6836022 100644
--- a/drivers/mtd/nand/gpio.c
+++ b/drivers/mtd/nand/gpio.c
@@ -273,6 +273,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
nand_set_flash_node(chip, pdev->dev.of_node);
chip->IO_ADDR_W = chip->IO_ADDR_R;
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
chip->options = gpiomtd->plat.options;
chip->chip_delay = gpiomtd->plat.chip_delay;
chip->cmd_ctrl = gpio_nand_cmd_ctrl;
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index 8122c699ccf2..6e461560c6a8 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -25,7 +25,6 @@
#include <linux/mtd/partitions.h>
#include <linux/of.h>
#include <linux/of_device.h>
-#include <linux/of_mtd.h>
#include "gpmi-nand.h"
#include "bch-regs.h"
@@ -47,10 +46,44 @@ static struct nand_bbt_descr gpmi_bbt_descr = {
* We may change the layout if we can get the ECC info from the datasheet,
* else we will use all the (page + OOB).
*/
-static struct nand_ecclayout gpmi_hw_ecclayout = {
- .eccbytes = 0,
- .eccpos = { 0, },
- .oobfree = { {.offset = 0, .length = 0} }
+static int gpmi_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct gpmi_nand_data *this = nand_get_controller_data(chip);
+ struct bch_geometry *geo = &this->bch_geometry;
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 0;
+ oobregion->length = geo->page_size - mtd->writesize;
+
+ return 0;
+}
+
+static int gpmi_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct gpmi_nand_data *this = nand_get_controller_data(chip);
+ struct bch_geometry *geo = &this->bch_geometry;
+
+ if (section)
+ return -ERANGE;
+
+ /* The available oob size we have. */
+ if (geo->page_size < mtd->writesize + mtd->oobsize) {
+ oobregion->offset = geo->page_size - mtd->writesize;
+ oobregion->length = mtd->oobsize - oobregion->offset;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops gpmi_ooblayout_ops = {
+ .ecc = gpmi_ooblayout_ecc,
+ .free = gpmi_ooblayout_free,
};
static const struct gpmi_devdata gpmi_devdata_imx23 = {
@@ -141,7 +174,6 @@ static int set_geometry_by_ecc_info(struct gpmi_nand_data *this)
struct bch_geometry *geo = &this->bch_geometry;
struct nand_chip *chip = &this->nand;
struct mtd_info *mtd = nand_to_mtd(chip);
- struct nand_oobfree *of = gpmi_hw_ecclayout.oobfree;
unsigned int block_mark_bit_offset;
if (!(chip->ecc_strength_ds > 0 && chip->ecc_step_ds > 0))
@@ -229,12 +261,6 @@ static int set_geometry_by_ecc_info(struct gpmi_nand_data *this)
geo->page_size = mtd->writesize + geo->metadata_size +
(geo->gf_len * geo->ecc_strength * geo->ecc_chunk_count) / 8;
- /* The available oob size we have. */
- if (geo->page_size < mtd->writesize + mtd->oobsize) {
- of->offset = geo->page_size - mtd->writesize;
- of->length = mtd->oobsize - of->offset;
- }
-
geo->payload_size = mtd->writesize;
geo->auxiliary_status_offset = ALIGN(geo->metadata_size, 4);
@@ -797,6 +823,7 @@ static void gpmi_free_dma_buffer(struct gpmi_nand_data *this)
this->cmd_buffer = NULL;
this->data_buffer_dma = NULL;
+ this->raw_buffer = NULL;
this->page_buffer_virt = NULL;
this->page_buffer_size = 0;
}
@@ -1037,14 +1064,87 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
/* Loop over status bytes, accumulating ECC status. */
status = auxiliary_virt + nfc_geo->auxiliary_status_offset;
+ read_page_swap_end(this, buf, nfc_geo->payload_size,
+ this->payload_virt, this->payload_phys,
+ nfc_geo->payload_size,
+ payload_virt, payload_phys);
+
for (i = 0; i < nfc_geo->ecc_chunk_count; i++, status++) {
if ((*status == STATUS_GOOD) || (*status == STATUS_ERASED))
continue;
if (*status == STATUS_UNCORRECTABLE) {
+ int eccbits = nfc_geo->ecc_strength * nfc_geo->gf_len;
+ u8 *eccbuf = this->raw_buffer;
+ int offset, bitoffset;
+ int eccbytes;
+ int flips;
+
+ /* Read ECC bytes into our internal raw_buffer */
+ offset = nfc_geo->metadata_size * 8;
+ offset += ((8 * nfc_geo->ecc_chunk_size) + eccbits) * (i + 1);
+ offset -= eccbits;
+ bitoffset = offset % 8;
+ eccbytes = DIV_ROUND_UP(offset + eccbits, 8);
+ offset /= 8;
+ eccbytes -= offset;
+ chip->cmdfunc(mtd, NAND_CMD_RNDOUT, offset, -1);
+ chip->read_buf(mtd, eccbuf, eccbytes);
+
+ /*
+ * ECC data are not byte aligned and we may have
+ * in-band data in the first and last byte of
+ * eccbuf. Set non-eccbits to one so that
+ * nand_check_erased_ecc_chunk() does not count them
+ * as bitflips.
+ */
+ if (bitoffset)
+ eccbuf[0] |= GENMASK(bitoffset - 1, 0);
+
+ bitoffset = (bitoffset + eccbits) % 8;
+ if (bitoffset)
+ eccbuf[eccbytes - 1] |= GENMASK(7, bitoffset);
+
+ /*
+ * The ECC hardware has an uncorrectable ECC status
+ * code in case we have bitflips in an erased page. As
+ * nothing was written into this subpage the ECC is
+ * obviously wrong and we can not trust it. We assume
+ * at this point that we are reading an erased page and
+ * try to correct the bitflips in buffer up to
+ * ecc_strength bitflips. If this is a page with random
+ * data, we exceed this number of bitflips and have a
+ * ECC failure. Otherwise we use the corrected buffer.
+ */
+ if (i == 0) {
+ /* The first block includes metadata */
+ flips = nand_check_erased_ecc_chunk(
+ buf + i * nfc_geo->ecc_chunk_size,
+ nfc_geo->ecc_chunk_size,
+ eccbuf, eccbytes,
+ auxiliary_virt,
+ nfc_geo->metadata_size,
+ nfc_geo->ecc_strength);
+ } else {
+ flips = nand_check_erased_ecc_chunk(
+ buf + i * nfc_geo->ecc_chunk_size,
+ nfc_geo->ecc_chunk_size,
+ eccbuf, eccbytes,
+ NULL, 0,
+ nfc_geo->ecc_strength);
+ }
+
+ if (flips > 0) {
+ max_bitflips = max_t(unsigned int, max_bitflips,
+ flips);
+ mtd->ecc_stats.corrected += flips;
+ continue;
+ }
+
mtd->ecc_stats.failed++;
continue;
}
+
mtd->ecc_stats.corrected += *status;
max_bitflips = max_t(unsigned int, max_bitflips, *status);
}
@@ -1064,11 +1164,6 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
chip->oob_poi[0] = ((uint8_t *) auxiliary_virt)[0];
}
- read_page_swap_end(this, buf, nfc_geo->payload_size,
- this->payload_virt, this->payload_phys,
- nfc_geo->payload_size,
- payload_virt, payload_phys);
-
return max_bitflips;
}
@@ -1327,18 +1422,19 @@ static int gpmi_ecc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
static int
gpmi_ecc_write_oob(struct mtd_info *mtd, struct nand_chip *chip, int page)
{
- struct nand_oobfree *of = mtd->ecclayout->oobfree;
+ struct mtd_oob_region of = { };
int status = 0;
/* Do we have available oob area? */
- if (!of->length)
+ mtd_ooblayout_free(mtd, 0, &of);
+ if (!of.length)
return -EPERM;
if (!nand_is_slc(chip))
return -EPERM;
- chip->cmdfunc(mtd, NAND_CMD_SEQIN, mtd->writesize + of->offset, page);
- chip->write_buf(mtd, chip->oob_poi + of->offset, of->length);
+ chip->cmdfunc(mtd, NAND_CMD_SEQIN, mtd->writesize + of.offset, page);
+ chip->write_buf(mtd, chip->oob_poi + of.offset, of.length);
chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
status = chip->waitfunc(mtd, chip);
@@ -1840,6 +1936,7 @@ static void gpmi_nand_exit(struct gpmi_nand_data *this)
static int gpmi_init_last(struct gpmi_nand_data *this)
{
struct nand_chip *chip = &this->nand;
+ struct mtd_info *mtd = nand_to_mtd(chip);
struct nand_ecc_ctrl *ecc = &chip->ecc;
struct bch_geometry *bch_geo = &this->bch_geometry;
int ret;
@@ -1861,7 +1958,7 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
ecc->mode = NAND_ECC_HW;
ecc->size = bch_geo->ecc_chunk_size;
ecc->strength = bch_geo->ecc_strength;
- ecc->layout = &gpmi_hw_ecclayout;
+ mtd_set_ooblayout(mtd, &gpmi_ooblayout_ops);
/*
* We only enable the subpage read when:
@@ -1914,16 +2011,6 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
/* Set up swap_block_mark, must be set before the gpmi_set_geometry() */
this->swap_block_mark = !GPMI_IS_MX23(this);
- if (of_get_nand_on_flash_bbt(this->dev->of_node)) {
- chip->bbt_options |= NAND_BBT_USE_FLASH | NAND_BBT_NO_OOB;
-
- if (of_property_read_bool(this->dev->of_node,
- "fsl,no-blockmark-swap"))
- this->swap_block_mark = false;
- }
- dev_dbg(this->dev, "Blockmark swapping %sabled\n",
- this->swap_block_mark ? "en" : "dis");
-
/*
* Allocate a temporary DMA buffer for reading ID in the
* nand_scan_ident().
@@ -1938,6 +2025,16 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
if (ret)
goto err_out;
+ if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+ chip->bbt_options |= NAND_BBT_NO_OOB;
+
+ if (of_property_read_bool(this->dev->of_node,
+ "fsl,no-blockmark-swap"))
+ this->swap_block_mark = false;
+ }
+ dev_dbg(this->dev, "Blockmark swapping %sabled\n",
+ this->swap_block_mark ? "en" : "dis");
+
ret = gpmi_init_last(this);
if (ret)
goto err_out;
diff --git a/drivers/mtd/nand/hisi504_nand.c b/drivers/mtd/nand/hisi504_nand.c
index 96502b624cfb..9432546f4cd4 100644
--- a/drivers/mtd/nand/hisi504_nand.c
+++ b/drivers/mtd/nand/hisi504_nand.c
@@ -19,7 +19,6 @@
* GNU General Public License for more details.
*/
#include <linux/of.h>
-#include <linux/of_mtd.h>
#include <linux/mtd/mtd.h>
#include <linux/sizes.h>
#include <linux/clk.h>
@@ -631,8 +630,28 @@ static void hisi_nfc_host_init(struct hinfc_host *host)
hinfc_write(host, HINFC504_INTEN_DMA, HINFC504_INTEN);
}
-static struct nand_ecclayout nand_ecc_2K_16bits = {
- .oobfree = { {2, 6} },
+static int hisi_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ /* FIXME: add ECC bytes position */
+ return -ENOTSUPP;
+}
+
+static int hisi_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 2;
+ oobregion->length = 6;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops hisi_ooblayout_ops = {
+ .ecc = hisi_ooblayout_ecc,
+ .free = hisi_ooblayout_free,
};
static int hisi_nfc_ecc_probe(struct hinfc_host *host)
@@ -642,10 +661,9 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
struct device *dev = host->dev;
struct nand_chip *chip = &host->chip;
struct mtd_info *mtd = nand_to_mtd(chip);
- struct device_node *np = host->dev->of_node;
- size = of_get_nand_ecc_step_size(np);
- strength = of_get_nand_ecc_strength(np);
+ size = chip->ecc.size;
+ strength = chip->ecc.strength;
if (size != 1024) {
dev_err(dev, "error ecc size: %d\n", size);
return -EINVAL;
@@ -668,7 +686,7 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
case 16:
ecc_bits = 6;
if (mtd->writesize == 2048)
- chip->ecc.layout = &nand_ecc_2K_16bits;
+ mtd_set_ooblayout(mtd, &hisi_ooblayout_ops);
/* TODO: add more page size support */
break;
@@ -695,7 +713,7 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
static int hisi_nfc_probe(struct platform_device *pdev)
{
- int ret = 0, irq, buswidth, flag, max_chips = HINFC504_MAX_CHIP;
+ int ret = 0, irq, flag, max_chips = HINFC504_MAX_CHIP;
struct device *dev = &pdev->dev;
struct hinfc_host *host;
struct nand_chip *chip;
@@ -747,12 +765,6 @@ static int hisi_nfc_probe(struct platform_device *pdev)
chip->read_buf = hisi_nfc_read_buf;
chip->chip_delay = HINFC504_CHIP_DELAY;
- chip->ecc.mode = of_get_nand_ecc_mode(np);
-
- buswidth = of_get_nand_bus_width(np);
- if (buswidth == 16)
- chip->options |= NAND_BUSWIDTH_16;
-
hisi_nfc_host_init(host);
ret = devm_request_irq(dev, irq, hinfc_irq_handle, 0x0, "nandc", host);
diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c
index 673ceb2a0b44..5551c36adbdf 100644
--- a/drivers/mtd/nand/jz4740_nand.c
+++ b/drivers/mtd/nand/jz4740_nand.c
@@ -221,7 +221,6 @@ static int jz_nand_correct_ecc_rs(struct mtd_info *mtd, uint8_t *dat,
struct jz_nand *nand = mtd_to_jz_nand(mtd);
int i, error_count, index;
uint32_t reg, status, error;
- uint32_t t;
unsigned int timeout = 1000;
for (i = 0; i < 9; ++i)
@@ -476,7 +475,7 @@ static int jz_nand_probe(struct platform_device *pdev)
}
if (pdata && pdata->ident_callback) {
- pdata->ident_callback(pdev, chip, &pdata->partitions,
+ pdata->ident_callback(pdev, mtd, &pdata->partitions,
&pdata->num_partitions);
}
diff --git a/drivers/mtd/nand/jz4780_bch.c b/drivers/mtd/nand/jz4780_bch.c
index 755499c6650e..d74f4ba4a6f4 100644
--- a/drivers/mtd/nand/jz4780_bch.c
+++ b/drivers/mtd/nand/jz4780_bch.c
@@ -287,7 +287,6 @@ static struct jz4780_bch *jz4780_bch_get(struct device_node *np)
bch = platform_get_drvdata(pdev);
clk_prepare_enable(bch->clk);
- bch->dev = &pdev->dev;
return bch;
}
diff --git a/drivers/mtd/nand/jz4780_nand.c b/drivers/mtd/nand/jz4780_nand.c
index e1c016c9d32d..daf3c4217f4d 100644
--- a/drivers/mtd/nand/jz4780_nand.c
+++ b/drivers/mtd/nand/jz4780_nand.c
@@ -17,7 +17,6 @@
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/gpio/consumer.h>
-#include <linux/of_mtd.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/mtd/mtd.h>
@@ -56,8 +55,6 @@ struct jz4780_nand_chip {
struct nand_chip chip;
struct list_head chip_list;
- struct nand_ecclayout ecclayout;
-
struct gpio_desc *busy_gpio;
struct gpio_desc *wp_gpio;
unsigned int reading: 1;
@@ -165,8 +162,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
struct nand_chip *chip = &nand->chip;
struct mtd_info *mtd = nand_to_mtd(chip);
struct jz4780_nand_controller *nfc = to_jz4780_nand_controller(chip->controller);
- struct nand_ecclayout *layout = &nand->ecclayout;
- u32 start, i;
+ int eccbytes;
chip->ecc.bytes = fls((1 + 8) * chip->ecc.size) *
(chip->ecc.strength / 8);
@@ -183,7 +179,6 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
chip->ecc.correct = jz4780_nand_ecc_correct;
/* fall through */
case NAND_ECC_SOFT:
- case NAND_ECC_SOFT_BCH:
dev_info(dev, "using %s (strength %d, size %d, bytes %d)\n",
(nfc->bch) ? "hardware BCH" : "software ECC",
chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
@@ -201,23 +196,17 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
return 0;
/* Generate ECC layout. ECC codes are right aligned in the OOB area. */
- layout->eccbytes = mtd->writesize / chip->ecc.size * chip->ecc.bytes;
+ eccbytes = mtd->writesize / chip->ecc.size * chip->ecc.bytes;
- if (layout->eccbytes > mtd->oobsize - 2) {
+ if (eccbytes > mtd->oobsize - 2) {
dev_err(dev,
"invalid ECC config: required %d ECC bytes, but only %d are available",
- layout->eccbytes, mtd->oobsize - 2);
+ eccbytes, mtd->oobsize - 2);
return -EINVAL;
}
- start = mtd->oobsize - layout->eccbytes;
- for (i = 0; i < layout->eccbytes; i++)
- layout->eccpos[i] = start + i;
-
- layout->oobfree[0].offset = 2;
- layout->oobfree[0].length = mtd->oobsize - layout->eccbytes - 2;
+ mtd->ooblayout = &nand_ooblayout_lp_ops;
- chip->ecc.layout = layout;
return 0;
}
diff --git a/drivers/mtd/nand/lpc32xx_mlc.c b/drivers/mtd/nand/lpc32xx_mlc.c
index d8c3e7afcc0b..852388171f20 100644
--- a/drivers/mtd/nand/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/lpc32xx_mlc.c
@@ -35,7 +35,6 @@
#include <linux/completion.h>
#include <linux/interrupt.h>
#include <linux/of.h>
-#include <linux/of_mtd.h>
#include <linux/of_gpio.h>
#include <linux/mtd/lpc32xx_mlc.h>
#include <linux/io.h>
@@ -139,22 +138,37 @@ struct lpc32xx_nand_cfg_mlc {
unsigned num_parts;
};
-static struct nand_ecclayout lpc32xx_nand_oob = {
- .eccbytes = 40,
- .eccpos = { 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
- 54, 55, 56, 57, 58, 59, 60, 61, 62, 63 },
- .oobfree = {
- { .offset = 0,
- .length = 6, },
- { .offset = 16,
- .length = 6, },
- { .offset = 32,
- .length = 6, },
- { .offset = 48,
- .length = 6, },
- },
+static int lpc32xx_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand_chip = mtd_to_nand(mtd);
+
+ if (section >= nand_chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = ((section + 1) * 16) - nand_chip->ecc.bytes;
+ oobregion->length = nand_chip->ecc.bytes;
+
+ return 0;
+}
+
+static int lpc32xx_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand_chip = mtd_to_nand(mtd);
+
+ if (section >= nand_chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = 16 * section;
+ oobregion->length = 16 - nand_chip->ecc.bytes;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops lpc32xx_ooblayout_ops = {
+ .ecc = lpc32xx_ooblayout_ecc,
+ .free = lpc32xx_ooblayout_free,
};
static struct nand_bbt_descr lpc32xx_nand_bbt = {
@@ -713,6 +727,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
nand_chip->ecc.write_oob = lpc32xx_write_oob;
nand_chip->ecc.read_oob = lpc32xx_read_oob;
nand_chip->ecc.strength = 4;
+ nand_chip->ecc.bytes = 10;
nand_chip->waitfunc = lpc32xx_waitfunc;
nand_chip->options = NAND_NO_SUBPAGE_WRITE;
@@ -751,7 +766,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
nand_chip->ecc.mode = NAND_ECC_HW;
nand_chip->ecc.size = 512;
- nand_chip->ecc.layout = &lpc32xx_nand_oob;
+ mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
host->mlcsubpages = mtd->writesize / 512;
/* initially clear interrupt status */
diff --git a/drivers/mtd/nand/lpc32xx_slc.c b/drivers/mtd/nand/lpc32xx_slc.c
index 3b8f3735f3e8..8d3edc34958e 100644
--- a/drivers/mtd/nand/lpc32xx_slc.c
+++ b/drivers/mtd/nand/lpc32xx_slc.c
@@ -35,7 +35,6 @@
#include <linux/mtd/nand_ecc.h>
#include <linux/gpio.h>
#include <linux/of.h>
-#include <linux/of_mtd.h>
#include <linux/of_gpio.h>
#include <linux/mtd/lpc32xx_slc.h>
@@ -146,13 +145,38 @@
* NAND ECC Layout for small page NAND devices
* Note: For large and huge page devices, the default layouts are used
*/
-static struct nand_ecclayout lpc32xx_nand_oob_16 = {
- .eccbytes = 6,
- .eccpos = {10, 11, 12, 13, 14, 15},
- .oobfree = {
- { .offset = 0, .length = 4 },
- { .offset = 6, .length = 4 },
- },
+static int lpc32xx_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = 6;
+ oobregion->offset = 10;
+
+ return 0;
+}
+
+static int lpc32xx_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 1)
+ return -ERANGE;
+
+ if (!section) {
+ oobregion->offset = 0;
+ oobregion->length = 4;
+ } else {
+ oobregion->offset = 6;
+ oobregion->length = 4;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops lpc32xx_ooblayout_ops = {
+ .ecc = lpc32xx_ooblayout_ecc,
+ .free = lpc32xx_ooblayout_free,
};
static u8 bbt_pattern[] = {'B', 'b', 't', '0' };
@@ -194,7 +218,6 @@ struct lpc32xx_nand_cfg_slc {
uint32_t rwidth;
uint32_t rhold;
uint32_t rsetup;
- bool use_bbt;
int wp_gpio;
struct mtd_partition *parts;
unsigned num_parts;
@@ -604,7 +627,8 @@ static int lpc32xx_nand_read_page_syndrome(struct mtd_info *mtd,
int oob_required, int page)
{
struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
- int stat, i, status;
+ struct mtd_oob_region oobregion = { };
+ int stat, i, status, error;
uint8_t *oobecc, tmpecc[LPC32XX_ECC_SAVE_SIZE];
/* Issue read command */
@@ -620,7 +644,11 @@ static int lpc32xx_nand_read_page_syndrome(struct mtd_info *mtd,
lpc32xx_slc_ecc_copy(tmpecc, (uint32_t *) host->ecc_buf, chip->ecc.steps);
/* Pointer to ECC data retrieved from NAND spare area */
- oobecc = chip->oob_poi + chip->ecc.layout->eccpos[0];
+ error = mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ if (error)
+ return error;
+
+ oobecc = chip->oob_poi + oobregion.offset;
for (i = 0; i < chip->ecc.steps; i++) {
stat = chip->ecc.correct(mtd, buf, oobecc,
@@ -666,7 +694,8 @@ static int lpc32xx_nand_write_page_syndrome(struct mtd_info *mtd,
int oob_required, int page)
{
struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
- uint8_t *pb = chip->oob_poi + chip->ecc.layout->eccpos[0];
+ struct mtd_oob_region oobregion = { };
+ uint8_t *pb;
int error;
/* Write data, calculate ECC on outbound data */
@@ -678,6 +707,11 @@ static int lpc32xx_nand_write_page_syndrome(struct mtd_info *mtd,
* The calculated ECC needs some manual work done to it before
* committing it to NAND. Process the calculated ECC and place
* the resultant values directly into the OOB buffer. */
+ error = mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ if (error)
+ return error;
+
+ pb = chip->oob_poi + oobregion.offset;
lpc32xx_slc_ecc_copy(pb, (uint32_t *)host->ecc_buf, chip->ecc.steps);
/* Write ECC data to device */
@@ -747,7 +781,6 @@ static struct lpc32xx_nand_cfg_slc *lpc32xx_parse_dt(struct device *dev)
return NULL;
}
- ncfg->use_bbt = of_get_nand_on_flash_bbt(np);
ncfg->wp_gpio = of_get_named_gpio(np, "gpios", 0);
return ncfg;
@@ -875,26 +908,22 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
* custom BBT marker layout.
*/
if (mtd->writesize <= 512)
- chip->ecc.layout = &lpc32xx_nand_oob_16;
+ mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
/* These sizes remain the same regardless of page size */
chip->ecc.size = 256;
chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
chip->ecc.prepad = chip->ecc.postpad = 0;
- /* Avoid extra scan if using BBT, setup BBT support */
- if (host->ncfg->use_bbt) {
- chip->bbt_options |= NAND_BBT_USE_FLASH;
-
- /*
- * Use a custom BBT marker setup for small page FLASH that
- * won't interfere with the ECC layout. Large and huge page
- * FLASH use the standard layout.
- */
- if (mtd->writesize <= 512) {
- chip->bbt_td = &bbt_smallpage_main_descr;
- chip->bbt_md = &bbt_smallpage_mirror_descr;
- }
+ /*
+ * Use a custom BBT marker setup for small page FLASH that
+ * won't interfere with the ECC layout. Large and huge page
+ * FLASH use the standard layout.
+ */
+ if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
+ mtd->writesize <= 512) {
+ chip->bbt_td = &bbt_smallpage_main_descr;
+ chip->bbt_md = &bbt_smallpage_mirror_descr;
}
/*
diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c
index 5d7843ffff6a..7eacb2f545f5 100644
--- a/drivers/mtd/nand/mpc5121_nfc.c
+++ b/drivers/mtd/nand/mpc5121_nfc.c
@@ -710,6 +710,7 @@ static int mpc5121_nfc_probe(struct platform_device *op)
chip->select_chip = mpc5121_nfc_select_chip;
chip->bbt_options = NAND_BBT_USE_FLASH;
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
/* Support external chip-select logic on ADS5121 board */
if (of_machine_is_compatible("fsl,mpc5121ads")) {
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 854c832597aa..5173fadc9a4e 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -34,7 +34,6 @@
#include <linux/completion.h>
#include <linux/of.h>
#include <linux/of_device.h>
-#include <linux/of_mtd.h>
#include <asm/mach/flash.h>
#include <linux/platform_data/mtd-mxc_nand.h>
@@ -149,7 +148,7 @@ struct mxc_nand_devtype_data {
int (*check_int)(struct mxc_nand_host *);
void (*irq_control)(struct mxc_nand_host *, int);
u32 (*get_ecc_status)(struct mxc_nand_host *);
- struct nand_ecclayout *ecclayout_512, *ecclayout_2k, *ecclayout_4k;
+ const struct mtd_ooblayout_ops *ooblayout;
void (*select_chip)(struct mtd_info *mtd, int chip);
int (*correct_data)(struct mtd_info *mtd, u_char *dat,
u_char *read_ecc, u_char *calc_ecc);
@@ -200,73 +199,6 @@ struct mxc_nand_host {
struct mxc_nand_platform_data pdata;
};
-/* OOB placement block for use with hardware ecc generation */
-static struct nand_ecclayout nandv1_hw_eccoob_smallpage = {
- .eccbytes = 5,
- .eccpos = {6, 7, 8, 9, 10},
- .oobfree = {{0, 5}, {12, 4}, }
-};
-
-static struct nand_ecclayout nandv1_hw_eccoob_largepage = {
- .eccbytes = 20,
- .eccpos = {6, 7, 8, 9, 10, 22, 23, 24, 25, 26,
- 38, 39, 40, 41, 42, 54, 55, 56, 57, 58},
- .oobfree = {{2, 4}, {11, 10}, {27, 10}, {43, 10}, {59, 5}, }
-};
-
-/* OOB description for 512 byte pages with 16 byte OOB */
-static struct nand_ecclayout nandv2_hw_eccoob_smallpage = {
- .eccbytes = 1 * 9,
- .eccpos = {
- 7, 8, 9, 10, 11, 12, 13, 14, 15
- },
- .oobfree = {
- {.offset = 0, .length = 5}
- }
-};
-
-/* OOB description for 2048 byte pages with 64 byte OOB */
-static struct nand_ecclayout nandv2_hw_eccoob_largepage = {
- .eccbytes = 4 * 9,
- .eccpos = {
- 7, 8, 9, 10, 11, 12, 13, 14, 15,
- 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 39, 40, 41, 42, 43, 44, 45, 46, 47,
- 55, 56, 57, 58, 59, 60, 61, 62, 63
- },
- .oobfree = {
- {.offset = 2, .length = 4},
- {.offset = 16, .length = 7},
- {.offset = 32, .length = 7},
- {.offset = 48, .length = 7}
- }
-};
-
-/* OOB description for 4096 byte pages with 128 byte OOB */
-static struct nand_ecclayout nandv2_hw_eccoob_4k = {
- .eccbytes = 8 * 9,
- .eccpos = {
- 7, 8, 9, 10, 11, 12, 13, 14, 15,
- 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 39, 40, 41, 42, 43, 44, 45, 46, 47,
- 55, 56, 57, 58, 59, 60, 61, 62, 63,
- 71, 72, 73, 74, 75, 76, 77, 78, 79,
- 87, 88, 89, 90, 91, 92, 93, 94, 95,
- 103, 104, 105, 106, 107, 108, 109, 110, 111,
- 119, 120, 121, 122, 123, 124, 125, 126, 127,
- },
- .oobfree = {
- {.offset = 2, .length = 4},
- {.offset = 16, .length = 7},
- {.offset = 32, .length = 7},
- {.offset = 48, .length = 7},
- {.offset = 64, .length = 7},
- {.offset = 80, .length = 7},
- {.offset = 96, .length = 7},
- {.offset = 112, .length = 7},
- }
-};
-
static const char * const part_probes[] = {
"cmdlinepart", "RedBoot", "ofpart", NULL };
@@ -942,6 +874,99 @@ static void mxc_do_addr_cycle(struct mtd_info *mtd, int column, int page_addr)
}
}
+static int mxc_v1_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand_chip = mtd_to_nand(mtd);
+
+ if (section >= nand_chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 6;
+ oobregion->length = nand_chip->ecc.bytes;
+
+ return 0;
+}
+
+static int mxc_v1_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand_chip = mtd_to_nand(mtd);
+
+ if (section > nand_chip->ecc.steps)
+ return -ERANGE;
+
+ if (!section) {
+ if (mtd->writesize <= 512) {
+ oobregion->offset = 0;
+ oobregion->length = 5;
+ } else {
+ oobregion->offset = 2;
+ oobregion->length = 4;
+ }
+ } else {
+ oobregion->offset = ((section - 1) * 16) +
+ nand_chip->ecc.bytes + 6;
+ if (section < nand_chip->ecc.steps)
+ oobregion->length = (section * 16) + 6 -
+ oobregion->offset;
+ else
+ oobregion->length = mtd->oobsize - oobregion->offset;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops mxc_v1_ooblayout_ops = {
+ .ecc = mxc_v1_ooblayout_ecc,
+ .free = mxc_v1_ooblayout_free,
+};
+
+static int mxc_v2_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand_chip = mtd_to_nand(mtd);
+ int stepsize = nand_chip->ecc.bytes == 9 ? 16 : 26;
+
+ if (section >= nand_chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = (section * stepsize) + 7;
+ oobregion->length = nand_chip->ecc.bytes;
+
+ return 0;
+}
+
+static int mxc_v2_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand_chip = mtd_to_nand(mtd);
+ int stepsize = nand_chip->ecc.bytes == 9 ? 16 : 26;
+
+ if (section > nand_chip->ecc.steps)
+ return -ERANGE;
+
+ if (!section) {
+ if (mtd->writesize <= 512) {
+ oobregion->offset = 0;
+ oobregion->length = 5;
+ } else {
+ oobregion->offset = 2;
+ oobregion->length = 4;
+ }
+ } else {
+ oobregion->offset = section * stepsize;
+ oobregion->length = 7;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops mxc_v2_ooblayout_ops = {
+ .ecc = mxc_v2_ooblayout_ecc,
+ .free = mxc_v2_ooblayout_free,
+};
+
/*
* v2 and v3 type controllers can do 4bit or 8bit ecc depending
* on how much oob the nand chip has. For 8bit ecc we need at least
@@ -959,23 +984,6 @@ static int get_eccsize(struct mtd_info *mtd)
return 8;
}
-static void ecc_8bit_layout_4k(struct nand_ecclayout *layout)
-{
- int i, j;
-
- layout->eccbytes = 8*18;
- for (i = 0; i < 8; i++)
- for (j = 0; j < 18; j++)
- layout->eccpos[i*18 + j] = i*26 + j + 7;
-
- layout->oobfree[0].offset = 2;
- layout->oobfree[0].length = 4;
- for (i = 1; i < 8; i++) {
- layout->oobfree[i].offset = i*26;
- layout->oobfree[i].length = 7;
- }
-}
-
static void preset_v1(struct mtd_info *mtd)
{
struct nand_chip *nand_chip = mtd_to_nand(mtd);
@@ -1269,9 +1277,7 @@ static const struct mxc_nand_devtype_data imx21_nand_devtype_data = {
.check_int = check_int_v1_v2,
.irq_control = irq_control_v1_v2,
.get_ecc_status = get_ecc_status_v1,
- .ecclayout_512 = &nandv1_hw_eccoob_smallpage,
- .ecclayout_2k = &nandv1_hw_eccoob_largepage,
- .ecclayout_4k = &nandv1_hw_eccoob_smallpage, /* XXX: needs fix */
+ .ooblayout = &mxc_v1_ooblayout_ops,
.select_chip = mxc_nand_select_chip_v1_v3,
.correct_data = mxc_nand_correct_data_v1,
.irqpending_quirk = 1,
@@ -1294,9 +1300,7 @@ static const struct mxc_nand_devtype_data imx27_nand_devtype_data = {
.check_int = check_int_v1_v2,
.irq_control = irq_control_v1_v2,
.get_ecc_status = get_ecc_status_v1,
- .ecclayout_512 = &nandv1_hw_eccoob_smallpage,
- .ecclayout_2k = &nandv1_hw_eccoob_largepage,
- .ecclayout_4k = &nandv1_hw_eccoob_smallpage, /* XXX: needs fix */
+ .ooblayout = &mxc_v1_ooblayout_ops,
.select_chip = mxc_nand_select_chip_v1_v3,
.correct_data = mxc_nand_correct_data_v1,
.irqpending_quirk = 0,
@@ -1320,9 +1324,7 @@ static const struct mxc_nand_devtype_data imx25_nand_devtype_data = {
.check_int = check_int_v1_v2,
.irq_control = irq_control_v1_v2,
.get_ecc_status = get_ecc_status_v2,
- .ecclayout_512 = &nandv2_hw_eccoob_smallpage,
- .ecclayout_2k = &nandv2_hw_eccoob_largepage,
- .ecclayout_4k = &nandv2_hw_eccoob_4k,
+ .ooblayout = &mxc_v2_ooblayout_ops,
.select_chip = mxc_nand_select_chip_v2,
.correct_data = mxc_nand_correct_data_v2_v3,
.irqpending_quirk = 0,
@@ -1346,9 +1348,7 @@ static const struct mxc_nand_devtype_data imx51_nand_devtype_data = {
.check_int = check_int_v3,
.irq_control = irq_control_v3,
.get_ecc_status = get_ecc_status_v3,
- .ecclayout_512 = &nandv2_hw_eccoob_smallpage,
- .ecclayout_2k = &nandv2_hw_eccoob_largepage,
- .ecclayout_4k = &nandv2_hw_eccoob_smallpage, /* XXX: needs fix */
+ .ooblayout = &mxc_v2_ooblayout_ops,
.select_chip = mxc_nand_select_chip_v1_v3,
.correct_data = mxc_nand_correct_data_v2_v3,
.irqpending_quirk = 0,
@@ -1373,9 +1373,7 @@ static const struct mxc_nand_devtype_data imx53_nand_devtype_data = {
.check_int = check_int_v3,
.irq_control = irq_control_v3,
.get_ecc_status = get_ecc_status_v3,
- .ecclayout_512 = &nandv2_hw_eccoob_smallpage,
- .ecclayout_2k = &nandv2_hw_eccoob_largepage,
- .ecclayout_4k = &nandv2_hw_eccoob_smallpage, /* XXX: needs fix */
+ .ooblayout = &mxc_v2_ooblayout_ops,
.select_chip = mxc_nand_select_chip_v1_v3,
.correct_data = mxc_nand_correct_data_v2_v3,
.irqpending_quirk = 0,
@@ -1461,25 +1459,12 @@ MODULE_DEVICE_TABLE(of, mxcnd_dt_ids);
static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
{
struct device_node *np = host->dev->of_node;
- struct mxc_nand_platform_data *pdata = &host->pdata;
const struct of_device_id *of_id =
of_match_device(mxcnd_dt_ids, host->dev);
- int buswidth;
if (!np)
return 1;
- if (of_get_nand_ecc_mode(np) >= 0)
- pdata->hw_ecc = 1;
-
- pdata->flash_bbt = of_get_nand_on_flash_bbt(np);
-
- buswidth = of_get_nand_bus_width(np);
- if (buswidth < 0)
- return buswidth;
-
- pdata->width = buswidth / 8;
-
host->devtype_data = of_id->data;
return 0;
@@ -1576,27 +1561,22 @@ static int mxcnd_probe(struct platform_device *pdev)
this->select_chip = host->devtype_data->select_chip;
this->ecc.size = 512;
- this->ecc.layout = host->devtype_data->ecclayout_512;
+ mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
if (host->pdata.hw_ecc) {
- this->ecc.calculate = mxc_nand_calculate_ecc;
- this->ecc.hwctl = mxc_nand_enable_hwecc;
- this->ecc.correct = host->devtype_data->correct_data;
this->ecc.mode = NAND_ECC_HW;
} else {
this->ecc.mode = NAND_ECC_SOFT;
+ this->ecc.algo = NAND_ECC_HAMMING;
}
/* NAND bus width determines access functions used by upper layer */
if (host->pdata.width == 2)
this->options |= NAND_BUSWIDTH_16;
- if (host->pdata.flash_bbt) {
- this->bbt_td = &bbt_main_descr;
- this->bbt_md = &bbt_mirror_descr;
- /* update flash based bbt */
+ /* update flash based bbt */
+ if (host->pdata.flash_bbt)
this->bbt_options |= NAND_BBT_USE_FLASH;
- }
init_completion(&host->op_completion);
@@ -1637,6 +1617,26 @@ static int mxcnd_probe(struct platform_device *pdev)
goto escan;
}
+ switch (this->ecc.mode) {
+ case NAND_ECC_HW:
+ this->ecc.calculate = mxc_nand_calculate_ecc;
+ this->ecc.hwctl = mxc_nand_enable_hwecc;
+ this->ecc.correct = host->devtype_data->correct_data;
+ break;
+
+ case NAND_ECC_SOFT:
+ break;
+
+ default:
+ err = -EINVAL;
+ goto escan;
+ }
+
+ if (this->bbt_options & NAND_BBT_USE_FLASH) {
+ this->bbt_td = &bbt_main_descr;
+ this->bbt_md = &bbt_mirror_descr;
+ }
+
/* allocate the right size buffer now */
devm_kfree(&pdev->dev, (void *)host->data_buf);
host->data_buf = devm_kzalloc(&pdev->dev, mtd->writesize + mtd->oobsize,
@@ -1649,12 +1649,11 @@ static int mxcnd_probe(struct platform_device *pdev)
/* Call preset again, with correct writesize this time */
host->devtype_data->preset(mtd);
- if (mtd->writesize == 2048)
- this->ecc.layout = host->devtype_data->ecclayout_2k;
- else if (mtd->writesize == 4096) {
- this->ecc.layout = host->devtype_data->ecclayout_4k;
- if (get_eccsize(mtd) == 8)
- ecc_8bit_layout_4k(this->ecc.layout);
+ if (!this->ecc.bytes) {
+ if (host->eccsize == 8)
+ this->ecc.bytes = 18;
+ else if (host->eccsize == 4)
+ this->ecc.bytes = 9;
}
/*
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index ba4f603e0537..0b0dc29d2af7 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -45,56 +45,98 @@
#include <linux/bitops.h>
#include <linux/io.h>
#include <linux/mtd/partitions.h>
-#include <linux/of_mtd.h>
+#include <linux/of.h>
+
+static int nand_get_device(struct mtd_info *mtd, int new_state);
+
+static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
+ struct mtd_oob_ops *ops);
/* Define default oob placement schemes for large and small page devices */
-static struct nand_ecclayout nand_oob_8 = {
- .eccbytes = 3,
- .eccpos = {0, 1, 2},
- .oobfree = {
- {.offset = 3,
- .length = 2},
- {.offset = 6,
- .length = 2} }
-};
+static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
-static struct nand_ecclayout nand_oob_16 = {
- .eccbytes = 6,
- .eccpos = {0, 1, 2, 3, 6, 7},
- .oobfree = {
- {.offset = 8,
- . length = 8} }
-};
+ if (section > 1)
+ return -ERANGE;
-static struct nand_ecclayout nand_oob_64 = {
- .eccbytes = 24,
- .eccpos = {
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63},
- .oobfree = {
- {.offset = 2,
- .length = 38} }
-};
+ if (!section) {
+ oobregion->offset = 0;
+ oobregion->length = 4;
+ } else {
+ oobregion->offset = 6;
+ oobregion->length = ecc->total - 4;
+ }
+
+ return 0;
+}
+
+static int nand_ooblayout_free_sp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 1)
+ return -ERANGE;
+
+ if (mtd->oobsize == 16) {
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = 8;
+ oobregion->offset = 8;
+ } else {
+ oobregion->length = 2;
+ if (!section)
+ oobregion->offset = 3;
+ else
+ oobregion->offset = 6;
+ }
+
+ return 0;
+}
-static struct nand_ecclayout nand_oob_128 = {
- .eccbytes = 48,
- .eccpos = {
- 80, 81, 82, 83, 84, 85, 86, 87,
- 88, 89, 90, 91, 92, 93, 94, 95,
- 96, 97, 98, 99, 100, 101, 102, 103,
- 104, 105, 106, 107, 108, 109, 110, 111,
- 112, 113, 114, 115, 116, 117, 118, 119,
- 120, 121, 122, 123, 124, 125, 126, 127},
- .oobfree = {
- {.offset = 2,
- .length = 78} }
+const struct mtd_ooblayout_ops nand_ooblayout_sp_ops = {
+ .ecc = nand_ooblayout_ecc_sp,
+ .free = nand_ooblayout_free_sp,
};
+EXPORT_SYMBOL_GPL(nand_ooblayout_sp_ops);
-static int nand_get_device(struct mtd_info *mtd, int new_state);
+static int nand_ooblayout_ecc_lp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
-static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
- struct mtd_oob_ops *ops);
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = ecc->total;
+ oobregion->offset = mtd->oobsize - oobregion->length;
+
+ return 0;
+}
+
+static int nand_ooblayout_free_lp(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = mtd->oobsize - ecc->total - 2;
+ oobregion->offset = 2;
+
+ return 0;
+}
+
+const struct mtd_ooblayout_ops nand_ooblayout_lp_ops = {
+ .ecc = nand_ooblayout_ecc_lp,
+ .free = nand_ooblayout_free_lp,
+};
+EXPORT_SYMBOL_GPL(nand_ooblayout_lp_ops);
static int check_offs_len(struct mtd_info *mtd,
loff_t ofs, uint64_t len)
@@ -1279,13 +1321,12 @@ static int nand_read_page_raw_syndrome(struct mtd_info *mtd,
static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
uint8_t *buf, int oob_required, int page)
{
- int i, eccsize = chip->ecc.size;
+ int i, eccsize = chip->ecc.size, ret;
int eccbytes = chip->ecc.bytes;
int eccsteps = chip->ecc.steps;
uint8_t *p = buf;
uint8_t *ecc_calc = chip->buffers->ecccalc;
uint8_t *ecc_code = chip->buffers->ecccode;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
unsigned int max_bitflips = 0;
chip->ecc.read_page_raw(mtd, chip, buf, 1, page);
@@ -1293,8 +1334,10 @@ static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize)
chip->ecc.calculate(mtd, p, &ecc_calc[i]);
- for (i = 0; i < chip->ecc.total; i++)
- ecc_code[i] = chip->oob_poi[eccpos[i]];
+ ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
eccsteps = chip->ecc.steps;
p = buf;
@@ -1326,14 +1369,14 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
uint32_t data_offs, uint32_t readlen, uint8_t *bufpoi,
int page)
{
- int start_step, end_step, num_steps;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
+ int start_step, end_step, num_steps, ret;
uint8_t *p;
int data_col_addr, i, gaps = 0;
int datafrag_len, eccfrag_len, aligned_len, aligned_pos;
int busw = (chip->options & NAND_BUSWIDTH_16) ? 2 : 1;
- int index;
+ int index, section = 0;
unsigned int max_bitflips = 0;
+ struct mtd_oob_region oobregion = { };
/* Column address within the page aligned to ECC size (256bytes) */
start_step = data_offs / chip->ecc.size;
@@ -1361,12 +1404,13 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
* The performance is faster if we position offsets according to
* ecc.pos. Let's make sure that there are no gaps in ECC positions.
*/
- for (i = 0; i < eccfrag_len - 1; i++) {
- if (eccpos[i + index] + 1 != eccpos[i + index + 1]) {
- gaps = 1;
- break;
- }
- }
+ ret = mtd_ooblayout_find_eccregion(mtd, index, &section, &oobregion);
+ if (ret)
+ return ret;
+
+ if (oobregion.length < eccfrag_len)
+ gaps = 1;
+
if (gaps) {
chip->cmdfunc(mtd, NAND_CMD_RNDOUT, mtd->writesize, -1);
chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
@@ -1375,20 +1419,23 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
* Send the command to read the particular ECC bytes take care
* about buswidth alignment in read_buf.
*/
- aligned_pos = eccpos[index] & ~(busw - 1);
+ aligned_pos = oobregion.offset & ~(busw - 1);
aligned_len = eccfrag_len;
- if (eccpos[index] & (busw - 1))
+ if (oobregion.offset & (busw - 1))
aligned_len++;
- if (eccpos[index + (num_steps * chip->ecc.bytes)] & (busw - 1))
+ if ((oobregion.offset + (num_steps * chip->ecc.bytes)) &
+ (busw - 1))
aligned_len++;
chip->cmdfunc(mtd, NAND_CMD_RNDOUT,
- mtd->writesize + aligned_pos, -1);
+ mtd->writesize + aligned_pos, -1);
chip->read_buf(mtd, &chip->oob_poi[aligned_pos], aligned_len);
}
- for (i = 0; i < eccfrag_len; i++)
- chip->buffers->ecccode[i] = chip->oob_poi[eccpos[i + index]];
+ ret = mtd_ooblayout_get_eccbytes(mtd, chip->buffers->ecccode,
+ chip->oob_poi, index, eccfrag_len);
+ if (ret)
+ return ret;
p = bufpoi + data_col_addr;
for (i = 0; i < eccfrag_len ; i += chip->ecc.bytes, p += chip->ecc.size) {
@@ -1429,13 +1476,12 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
uint8_t *buf, int oob_required, int page)
{
- int i, eccsize = chip->ecc.size;
+ int i, eccsize = chip->ecc.size, ret;
int eccbytes = chip->ecc.bytes;
int eccsteps = chip->ecc.steps;
uint8_t *p = buf;
uint8_t *ecc_calc = chip->buffers->ecccalc;
uint8_t *ecc_code = chip->buffers->ecccode;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
unsigned int max_bitflips = 0;
for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) {
@@ -1445,8 +1491,10 @@ static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
}
chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
- for (i = 0; i < chip->ecc.total; i++)
- ecc_code[i] = chip->oob_poi[eccpos[i]];
+ ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
eccsteps = chip->ecc.steps;
p = buf;
@@ -1491,12 +1539,11 @@ static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
static int nand_read_page_hwecc_oob_first(struct mtd_info *mtd,
struct nand_chip *chip, uint8_t *buf, int oob_required, int page)
{
- int i, eccsize = chip->ecc.size;
+ int i, eccsize = chip->ecc.size, ret;
int eccbytes = chip->ecc.bytes;
int eccsteps = chip->ecc.steps;
uint8_t *p = buf;
uint8_t *ecc_code = chip->buffers->ecccode;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
uint8_t *ecc_calc = chip->buffers->ecccalc;
unsigned int max_bitflips = 0;
@@ -1505,8 +1552,10 @@ static int nand_read_page_hwecc_oob_first(struct mtd_info *mtd,
chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page);
- for (i = 0; i < chip->ecc.total; i++)
- ecc_code[i] = chip->oob_poi[eccpos[i]];
+ ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) {
int stat;
@@ -1607,14 +1656,17 @@ static int nand_read_page_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
/**
* nand_transfer_oob - [INTERN] Transfer oob to client buffer
- * @chip: nand chip structure
+ * @mtd: mtd info structure
* @oob: oob destination address
* @ops: oob ops structure
* @len: size of oob to transfer
*/
-static uint8_t *nand_transfer_oob(struct nand_chip *chip, uint8_t *oob,
+static uint8_t *nand_transfer_oob(struct mtd_info *mtd, uint8_t *oob,
struct mtd_oob_ops *ops, size_t len)
{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ int ret;
+
switch (ops->mode) {
case MTD_OPS_PLACE_OOB:
@@ -1622,31 +1674,12 @@ static uint8_t *nand_transfer_oob(struct nand_chip *chip, uint8_t *oob,
memcpy(oob, chip->oob_poi + ops->ooboffs, len);
return oob + len;
- case MTD_OPS_AUTO_OOB: {
- struct nand_oobfree *free = chip->ecc.layout->oobfree;
- uint32_t boffs = 0, roffs = ops->ooboffs;
- size_t bytes = 0;
-
- for (; free->length && len; free++, len -= bytes) {
- /* Read request not from offset 0? */
- if (unlikely(roffs)) {
- if (roffs >= free->length) {
- roffs -= free->length;
- continue;
- }
- boffs = free->offset + roffs;
- bytes = min_t(size_t, len,
- (free->length - roffs));
- roffs = 0;
- } else {
- bytes = min_t(size_t, len, free->length);
- boffs = free->offset;
- }
- memcpy(oob, chip->oob_poi + boffs, bytes);
- oob += bytes;
- }
- return oob;
- }
+ case MTD_OPS_AUTO_OOB:
+ ret = mtd_ooblayout_get_databytes(mtd, oob, chip->oob_poi,
+ ops->ooboffs, len);
+ BUG_ON(ret);
+ return oob + len;
+
default:
BUG();
}
@@ -1780,7 +1813,7 @@ read_retry:
int toread = min(oobreadlen, max_oobsize);
if (toread) {
- oob = nand_transfer_oob(chip,
+ oob = nand_transfer_oob(mtd,
oob, ops, toread);
oobreadlen -= toread;
}
@@ -1893,13 +1926,13 @@ static int nand_read(struct mtd_info *mtd, loff_t from, size_t len,
* @chip: nand chip info structure
* @page: page number to read
*/
-static int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
- int page)
+int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page)
{
chip->cmdfunc(mtd, NAND_CMD_READOOB, 0, page);
chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
return 0;
}
+EXPORT_SYMBOL(nand_read_oob_std);
/**
* nand_read_oob_syndrome - [REPLACEABLE] OOB data read function for HW ECC
@@ -1908,8 +1941,8 @@ static int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
* @chip: nand chip info structure
* @page: page number to read
*/
-static int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
- int page)
+int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
+ int page)
{
int length = mtd->oobsize;
int chunk = chip->ecc.bytes + chip->ecc.prepad + chip->ecc.postpad;
@@ -1937,6 +1970,7 @@ static int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
return 0;
}
+EXPORT_SYMBOL(nand_read_oob_syndrome);
/**
* nand_write_oob_std - [REPLACEABLE] the most common OOB data write function
@@ -1944,8 +1978,7 @@ static int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
* @chip: nand chip info structure
* @page: page number to write
*/
-static int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
- int page)
+int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page)
{
int status = 0;
const uint8_t *buf = chip->oob_poi;
@@ -1960,6 +1993,7 @@ static int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
return status & NAND_STATUS_FAIL ? -EIO : 0;
}
+EXPORT_SYMBOL(nand_write_oob_std);
/**
* nand_write_oob_syndrome - [REPLACEABLE] OOB data write function for HW ECC
@@ -1968,8 +2002,8 @@ static int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
* @chip: nand chip info structure
* @page: page number to write
*/
-static int nand_write_oob_syndrome(struct mtd_info *mtd,
- struct nand_chip *chip, int page)
+int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
+ int page)
{
int chunk = chip->ecc.bytes + chip->ecc.prepad + chip->ecc.postpad;
int eccsize = chip->ecc.size, length = mtd->oobsize;
@@ -2019,6 +2053,7 @@ static int nand_write_oob_syndrome(struct mtd_info *mtd,
return status & NAND_STATUS_FAIL ? -EIO : 0;
}
+EXPORT_SYMBOL(nand_write_oob_syndrome);
/**
* nand_do_read_oob - [INTERN] NAND read out-of-band
@@ -2078,7 +2113,7 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from,
break;
len = min(len, readlen);
- buf = nand_transfer_oob(chip, buf, ops, len);
+ buf = nand_transfer_oob(mtd, buf, ops, len);
if (chip->options & NAND_NEED_READRDY) {
/* Apply delay or wait for ready/busy pin */
@@ -2237,19 +2272,20 @@ static int nand_write_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
const uint8_t *buf, int oob_required,
int page)
{
- int i, eccsize = chip->ecc.size;
+ int i, eccsize = chip->ecc.size, ret;
int eccbytes = chip->ecc.bytes;
int eccsteps = chip->ecc.steps;
uint8_t *ecc_calc = chip->buffers->ecccalc;
const uint8_t *p = buf;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
/* Software ECC calculation */
for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize)
chip->ecc.calculate(mtd, p, &ecc_calc[i]);
- for (i = 0; i < chip->ecc.total; i++)
- chip->oob_poi[eccpos[i]] = ecc_calc[i];
+ ret = mtd_ooblayout_set_eccbytes(mtd, ecc_calc, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
return chip->ecc.write_page_raw(mtd, chip, buf, 1, page);
}
@@ -2266,12 +2302,11 @@ static int nand_write_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
const uint8_t *buf, int oob_required,
int page)
{
- int i, eccsize = chip->ecc.size;
+ int i, eccsize = chip->ecc.size, ret;
int eccbytes = chip->ecc.bytes;
int eccsteps = chip->ecc.steps;
uint8_t *ecc_calc = chip->buffers->ecccalc;
const uint8_t *p = buf;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) {
chip->ecc.hwctl(mtd, NAND_ECC_WRITE);
@@ -2279,8 +2314,10 @@ static int nand_write_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
chip->ecc.calculate(mtd, p, &ecc_calc[i]);
}
- for (i = 0; i < chip->ecc.total; i++)
- chip->oob_poi[eccpos[i]] = ecc_calc[i];
+ ret = mtd_ooblayout_set_eccbytes(mtd, ecc_calc, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
chip->write_buf(mtd, chip->oob_poi, mtd->oobsize);
@@ -2308,11 +2345,10 @@ static int nand_write_subpage_hwecc(struct mtd_info *mtd,
int ecc_size = chip->ecc.size;
int ecc_bytes = chip->ecc.bytes;
int ecc_steps = chip->ecc.steps;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
uint32_t start_step = offset / ecc_size;
uint32_t end_step = (offset + data_len - 1) / ecc_size;
int oob_bytes = mtd->oobsize / ecc_steps;
- int step, i;
+ int step, ret;
for (step = 0; step < ecc_steps; step++) {
/* configure controller for WRITE access */
@@ -2340,8 +2376,10 @@ static int nand_write_subpage_hwecc(struct mtd_info *mtd,
/* copy calculated ECC for whole page to chip->buffer->oob */
/* this include masked-value(0xFF) for unwritten subpages */
ecc_calc = chip->buffers->ecccalc;
- for (i = 0; i < chip->ecc.total; i++)
- chip->oob_poi[eccpos[i]] = ecc_calc[i];
+ ret = mtd_ooblayout_set_eccbytes(mtd, ecc_calc, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
/* write OOB buffer to NAND device */
chip->write_buf(mtd, chip->oob_poi, mtd->oobsize);
@@ -2478,6 +2516,7 @@ static uint8_t *nand_fill_oob(struct mtd_info *mtd, uint8_t *oob, size_t len,
struct mtd_oob_ops *ops)
{
struct nand_chip *chip = mtd_to_nand(mtd);
+ int ret;
/*
* Initialise to all 0xFF, to avoid the possibility of left over OOB
@@ -2492,31 +2531,12 @@ static uint8_t *nand_fill_oob(struct mtd_info *mtd, uint8_t *oob, size_t len,
memcpy(chip->oob_poi + ops->ooboffs, oob, len);
return oob + len;
- case MTD_OPS_AUTO_OOB: {
- struct nand_oobfree *free = chip->ecc.layout->oobfree;
- uint32_t boffs = 0, woffs = ops->ooboffs;
- size_t bytes = 0;
-
- for (; free->length && len; free++, len -= bytes) {
- /* Write request not from offset 0? */
- if (unlikely(woffs)) {
- if (woffs >= free->length) {
- woffs -= free->length;
- continue;
- }
- boffs = free->offset + woffs;
- bytes = min_t(size_t, len,
- (free->length - woffs));
- woffs = 0;
- } else {
- bytes = min_t(size_t, len, free->length);
- boffs = free->offset;
- }
- memcpy(chip->oob_poi + boffs, oob, bytes);
- oob += bytes;
- }
- return oob;
- }
+ case MTD_OPS_AUTO_OOB:
+ ret = mtd_ooblayout_set_databytes(mtd, oob, chip->oob_poi,
+ ops->ooboffs, len);
+ BUG_ON(ret);
+ return oob + len;
+
default:
BUG();
}
@@ -3951,10 +3971,115 @@ ident_done:
return type;
}
+static const char * const nand_ecc_modes[] = {
+ [NAND_ECC_NONE] = "none",
+ [NAND_ECC_SOFT] = "soft",
+ [NAND_ECC_HW] = "hw",
+ [NAND_ECC_HW_SYNDROME] = "hw_syndrome",
+ [NAND_ECC_HW_OOB_FIRST] = "hw_oob_first",
+};
+
+static int of_get_nand_ecc_mode(struct device_node *np)
+{
+ const char *pm;
+ int err, i;
+
+ err = of_property_read_string(np, "nand-ecc-mode", &pm);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i < ARRAY_SIZE(nand_ecc_modes); i++)
+ if (!strcasecmp(pm, nand_ecc_modes[i]))
+ return i;
+
+ /*
+ * For backward compatibility we support few obsoleted values that don't
+ * have their mappings into nand_ecc_modes_t anymore (they were merged
+ * with other enums).
+ */
+ if (!strcasecmp(pm, "soft_bch"))
+ return NAND_ECC_SOFT;
+
+ return -ENODEV;
+}
+
+static const char * const nand_ecc_algos[] = {
+ [NAND_ECC_HAMMING] = "hamming",
+ [NAND_ECC_BCH] = "bch",
+};
+
+static int of_get_nand_ecc_algo(struct device_node *np)
+{
+ const char *pm;
+ int err, i;
+
+ err = of_property_read_string(np, "nand-ecc-algo", &pm);
+ if (!err) {
+ for (i = NAND_ECC_HAMMING; i < ARRAY_SIZE(nand_ecc_algos); i++)
+ if (!strcasecmp(pm, nand_ecc_algos[i]))
+ return i;
+ return -ENODEV;
+ }
+
+ /*
+ * For backward compatibility we also read "nand-ecc-mode" checking
+ * for some obsoleted values that were specifying ECC algorithm.
+ */
+ err = of_property_read_string(np, "nand-ecc-mode", &pm);
+ if (err < 0)
+ return err;
+
+ if (!strcasecmp(pm, "soft"))
+ return NAND_ECC_HAMMING;
+ else if (!strcasecmp(pm, "soft_bch"))
+ return NAND_ECC_BCH;
+
+ return -ENODEV;
+}
+
+static int of_get_nand_ecc_step_size(struct device_node *np)
+{
+ int ret;
+ u32 val;
+
+ ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
+ return ret ? ret : val;
+}
+
+static int of_get_nand_ecc_strength(struct device_node *np)
+{
+ int ret;
+ u32 val;
+
+ ret = of_property_read_u32(np, "nand-ecc-strength", &val);
+ return ret ? ret : val;
+}
+
+static int of_get_nand_bus_width(struct device_node *np)
+{
+ u32 val;
+
+ if (of_property_read_u32(np, "nand-bus-width", &val))
+ return 8;
+
+ switch (val) {
+ case 8:
+ case 16:
+ return val;
+ default:
+ return -EIO;
+ }
+}
+
+static bool of_get_nand_on_flash_bbt(struct device_node *np)
+{
+ return of_property_read_bool(np, "nand-on-flash-bbt");
+}
+
static int nand_dt_init(struct nand_chip *chip)
{
struct device_node *dn = nand_get_flash_node(chip);
- int ecc_mode, ecc_strength, ecc_step;
+ int ecc_mode, ecc_algo, ecc_strength, ecc_step;
if (!dn)
return 0;
@@ -3966,6 +4091,7 @@ static int nand_dt_init(struct nand_chip *chip)
chip->bbt_options |= NAND_BBT_USE_FLASH;
ecc_mode = of_get_nand_ecc_mode(dn);
+ ecc_algo = of_get_nand_ecc_algo(dn);
ecc_strength = of_get_nand_ecc_strength(dn);
ecc_step = of_get_nand_ecc_step_size(dn);
@@ -3978,6 +4104,9 @@ static int nand_dt_init(struct nand_chip *chip)
if (ecc_mode >= 0)
chip->ecc.mode = ecc_mode;
+ if (ecc_algo >= 0)
+ chip->ecc.algo = ecc_algo;
+
if (ecc_strength >= 0)
chip->ecc.strength = ecc_strength;
@@ -4054,6 +4183,82 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
}
EXPORT_SYMBOL(nand_scan_ident);
+static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+ if (WARN_ON(ecc->mode != NAND_ECC_SOFT))
+ return -EINVAL;
+
+ switch (ecc->algo) {
+ case NAND_ECC_HAMMING:
+ ecc->calculate = nand_calculate_ecc;
+ ecc->correct = nand_correct_data;
+ ecc->read_page = nand_read_page_swecc;
+ ecc->read_subpage = nand_read_subpage;
+ ecc->write_page = nand_write_page_swecc;
+ ecc->read_page_raw = nand_read_page_raw;
+ ecc->write_page_raw = nand_write_page_raw;
+ ecc->read_oob = nand_read_oob_std;
+ ecc->write_oob = nand_write_oob_std;
+ if (!ecc->size)
+ ecc->size = 256;
+ ecc->bytes = 3;
+ ecc->strength = 1;
+ return 0;
+ case NAND_ECC_BCH:
+ if (!mtd_nand_has_bch()) {
+ WARN(1, "CONFIG_MTD_NAND_ECC_BCH not enabled\n");
+ return -EINVAL;
+ }
+ ecc->calculate = nand_bch_calculate_ecc;
+ ecc->correct = nand_bch_correct_data;
+ ecc->read_page = nand_read_page_swecc;
+ ecc->read_subpage = nand_read_subpage;
+ ecc->write_page = nand_write_page_swecc;
+ ecc->read_page_raw = nand_read_page_raw;
+ ecc->write_page_raw = nand_write_page_raw;
+ ecc->read_oob = nand_read_oob_std;
+ ecc->write_oob = nand_write_oob_std;
+ /*
+ * Board driver should supply ecc.size and ecc.strength
+ * values to select how many bits are correctable.
+ * Otherwise, default to 4 bits for large page devices.
+ */
+ if (!ecc->size && (mtd->oobsize >= 64)) {
+ ecc->size = 512;
+ ecc->strength = 4;
+ }
+
+ /*
+ * if no ecc placement scheme was provided pickup the default
+ * large page one.
+ */
+ if (!mtd->ooblayout) {
+ /* handle large page devices only */
+ if (mtd->oobsize < 64) {
+ WARN(1, "OOB layout is required when using software BCH on small pages\n");
+ return -EINVAL;
+ }
+
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+ }
+
+ /* See nand_bch_init() for details. */
+ ecc->bytes = 0;
+ ecc->priv = nand_bch_init(mtd);
+ if (!ecc->priv) {
+ WARN(1, "BCH ECC initialization failed!\n");
+ return -EINVAL;
+ }
+ return 0;
+ default:
+ WARN(1, "Unsupported ECC algorithm!\n");
+ return -EINVAL;
+ }
+}
+
/*
* Check if the chip configuration meet the datasheet requirements.
@@ -4098,14 +4303,15 @@ static bool nand_ecc_strength_good(struct mtd_info *mtd)
*/
int nand_scan_tail(struct mtd_info *mtd)
{
- int i;
struct nand_chip *chip = mtd_to_nand(mtd);
struct nand_ecc_ctrl *ecc = &chip->ecc;
struct nand_buffers *nbuf;
+ int ret;
/* New bad blocks should be marked in OOB, flash-based BBT, or both */
- BUG_ON((chip->bbt_options & NAND_BBT_NO_OOB_BBM) &&
- !(chip->bbt_options & NAND_BBT_USE_FLASH));
+ if (WARN_ON((chip->bbt_options & NAND_BBT_NO_OOB_BBM) &&
+ !(chip->bbt_options & NAND_BBT_USE_FLASH)))
+ return -EINVAL;
if (!(chip->options & NAND_OWN_BUFFERS)) {
nbuf = kzalloc(sizeof(*nbuf) + mtd->writesize
@@ -4128,24 +4334,22 @@ int nand_scan_tail(struct mtd_info *mtd)
/*
* If no default placement scheme is given, select an appropriate one.
*/
- if (!ecc->layout && (ecc->mode != NAND_ECC_SOFT_BCH)) {
+ if (!mtd->ooblayout &&
+ !(ecc->mode == NAND_ECC_SOFT && ecc->algo == NAND_ECC_BCH)) {
switch (mtd->oobsize) {
case 8:
- ecc->layout = &nand_oob_8;
- break;
case 16:
- ecc->layout = &nand_oob_16;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_sp_ops);
break;
case 64:
- ecc->layout = &nand_oob_64;
- break;
case 128:
- ecc->layout = &nand_oob_128;
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
break;
default:
- pr_warn("No oob scheme defined for oobsize %d\n",
- mtd->oobsize);
- BUG();
+ WARN(1, "No oob scheme defined for oobsize %d\n",
+ mtd->oobsize);
+ ret = -EINVAL;
+ goto err_free;
}
}
@@ -4161,8 +4365,9 @@ int nand_scan_tail(struct mtd_info *mtd)
case NAND_ECC_HW_OOB_FIRST:
/* Similar to NAND_ECC_HW, but a separate read_page handle */
if (!ecc->calculate || !ecc->correct || !ecc->hwctl) {
- pr_warn("No ECC functions supplied; hardware ECC not possible\n");
- BUG();
+ WARN(1, "No ECC functions supplied; hardware ECC not possible\n");
+ ret = -EINVAL;
+ goto err_free;
}
if (!ecc->read_page)
ecc->read_page = nand_read_page_hwecc_oob_first;
@@ -4192,8 +4397,9 @@ int nand_scan_tail(struct mtd_info *mtd)
ecc->read_page == nand_read_page_hwecc ||
!ecc->write_page ||
ecc->write_page == nand_write_page_hwecc)) {
- pr_warn("No ECC functions supplied; hardware ECC not possible\n");
- BUG();
+ WARN(1, "No ECC functions supplied; hardware ECC not possible\n");
+ ret = -EINVAL;
+ goto err_free;
}
/* Use standard syndrome read/write page function? */
if (!ecc->read_page)
@@ -4211,61 +4417,22 @@ int nand_scan_tail(struct mtd_info *mtd)
if (mtd->writesize >= ecc->size) {
if (!ecc->strength) {
- pr_warn("Driver must set ecc.strength when using hardware ECC\n");
- BUG();
+ WARN(1, "Driver must set ecc.strength when using hardware ECC\n");
+ ret = -EINVAL;
+ goto err_free;
}
break;
}
pr_warn("%d byte HW ECC not possible on %d byte page size, fallback to SW ECC\n",
ecc->size, mtd->writesize);
ecc->mode = NAND_ECC_SOFT;
+ ecc->algo = NAND_ECC_HAMMING;
case NAND_ECC_SOFT:
- ecc->calculate = nand_calculate_ecc;
- ecc->correct = nand_correct_data;
- ecc->read_page = nand_read_page_swecc;
- ecc->read_subpage = nand_read_subpage;
- ecc->write_page = nand_write_page_swecc;
- ecc->read_page_raw = nand_read_page_raw;
- ecc->write_page_raw = nand_write_page_raw;
- ecc->read_oob = nand_read_oob_std;
- ecc->write_oob = nand_write_oob_std;
- if (!ecc->size)
- ecc->size = 256;
- ecc->bytes = 3;
- ecc->strength = 1;
- break;
-
- case NAND_ECC_SOFT_BCH:
- if (!mtd_nand_has_bch()) {
- pr_warn("CONFIG_MTD_NAND_ECC_BCH not enabled\n");
- BUG();
- }
- ecc->calculate = nand_bch_calculate_ecc;
- ecc->correct = nand_bch_correct_data;
- ecc->read_page = nand_read_page_swecc;
- ecc->read_subpage = nand_read_subpage;
- ecc->write_page = nand_write_page_swecc;
- ecc->read_page_raw = nand_read_page_raw;
- ecc->write_page_raw = nand_write_page_raw;
- ecc->read_oob = nand_read_oob_std;
- ecc->write_oob = nand_write_oob_std;
- /*
- * Board driver should supply ecc.size and ecc.strength values
- * to select how many bits are correctable. Otherwise, default
- * to 4 bits for large page devices.
- */
- if (!ecc->size && (mtd->oobsize >= 64)) {
- ecc->size = 512;
- ecc->strength = 4;
- }
-
- /* See nand_bch_init() for details. */
- ecc->bytes = 0;
- ecc->priv = nand_bch_init(mtd);
- if (!ecc->priv) {
- pr_warn("BCH ECC initialization failed!\n");
- BUG();
+ ret = nand_set_ecc_soft_ops(mtd);
+ if (ret) {
+ ret = -EINVAL;
+ goto err_free;
}
break;
@@ -4283,8 +4450,9 @@ int nand_scan_tail(struct mtd_info *mtd)
break;
default:
- pr_warn("Invalid NAND_ECC_MODE %d\n", ecc->mode);
- BUG();
+ WARN(1, "Invalid NAND_ECC_MODE %d\n", ecc->mode);
+ ret = -EINVAL;
+ goto err_free;
}
/* For many systems, the standard OOB write also works for raw */
@@ -4293,20 +4461,9 @@ int nand_scan_tail(struct mtd_info *mtd)
if (!ecc->write_oob_raw)
ecc->write_oob_raw = ecc->write_oob;
- /*
- * The number of bytes available for a client to place data into
- * the out of band area.
- */
- mtd->oobavail = 0;
- if (ecc->layout) {
- for (i = 0; ecc->layout->oobfree[i].length; i++)
- mtd->oobavail += ecc->layout->oobfree[i].length;
- }
-
- /* ECC sanity check: warn if it's too weak */
- if (!nand_ecc_strength_good(mtd))
- pr_warn("WARNING: %s: the ECC used on your system is too weak compared to the one required by the NAND chip\n",
- mtd->name);
+ /* propagate ecc info to mtd_info */
+ mtd->ecc_strength = ecc->strength;
+ mtd->ecc_step_size = ecc->size;
/*
* Set the number of read / write steps for one page depending on ECC
@@ -4314,11 +4471,27 @@ int nand_scan_tail(struct mtd_info *mtd)
*/
ecc->steps = mtd->writesize / ecc->size;
if (ecc->steps * ecc->size != mtd->writesize) {
- pr_warn("Invalid ECC parameters\n");
- BUG();
+ WARN(1, "Invalid ECC parameters\n");
+ ret = -EINVAL;
+ goto err_free;
}
ecc->total = ecc->steps * ecc->bytes;
+ /*
+ * The number of bytes available for a client to place data into
+ * the out of band area.
+ */
+ ret = mtd_ooblayout_count_freebytes(mtd);
+ if (ret < 0)
+ ret = 0;
+
+ mtd->oobavail = ret;
+
+ /* ECC sanity check: warn if it's too weak */
+ if (!nand_ecc_strength_good(mtd))
+ pr_warn("WARNING: %s: the ECC used on your system is too weak compared to the one required by the NAND chip\n",
+ mtd->name);
+
/* Allow subpage writes up to ecc.steps. Not possible for MLC flash */
if (!(chip->options & NAND_NO_SUBPAGE_WRITE) && nand_is_slc(chip)) {
switch (ecc->steps) {
@@ -4343,7 +4516,6 @@ int nand_scan_tail(struct mtd_info *mtd)
/* Large page NAND with SOFT_ECC should support subpage reads */
switch (ecc->mode) {
case NAND_ECC_SOFT:
- case NAND_ECC_SOFT_BCH:
if (chip->page_shift > 9)
chip->options |= NAND_SUBPAGE_READ;
break;
@@ -4375,10 +4547,6 @@ int nand_scan_tail(struct mtd_info *mtd)
mtd->_block_markbad = nand_block_markbad;
mtd->writebufsize = mtd->writesize;
- /* propagate ecc info to mtd_info */
- mtd->ecclayout = ecc->layout;
- mtd->ecc_strength = ecc->strength;
- mtd->ecc_step_size = ecc->size;
/*
* Initialize bitflip_threshold to its default prior scan_bbt() call.
* scan_bbt() might invoke mtd_read(), thus bitflip_threshold must be
@@ -4393,6 +4561,10 @@ int nand_scan_tail(struct mtd_info *mtd)
/* Build bad block table */
return chip->scan_bbt(mtd);
+err_free:
+ if (!(chip->options & NAND_OWN_BUFFERS))
+ kfree(chip->buffers);
+ return ret;
}
EXPORT_SYMBOL(nand_scan_tail);
@@ -4436,7 +4608,8 @@ void nand_release(struct mtd_info *mtd)
{
struct nand_chip *chip = mtd_to_nand(mtd);
- if (chip->ecc.mode == NAND_ECC_SOFT_BCH)
+ if (chip->ecc.mode == NAND_ECC_SOFT &&
+ chip->ecc.algo == NAND_ECC_BCH)
nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
mtd_device_unregister(mtd);
diff --git a/drivers/mtd/nand/nand_bch.c b/drivers/mtd/nand/nand_bch.c
index b585bae37929..44763f87eae4 100644
--- a/drivers/mtd/nand/nand_bch.c
+++ b/drivers/mtd/nand/nand_bch.c
@@ -32,13 +32,11 @@
/**
* struct nand_bch_control - private NAND BCH control structure
* @bch: BCH control structure
- * @ecclayout: private ecc layout for this BCH configuration
* @errloc: error location array
* @eccmask: XOR ecc mask, allows erased pages to be decoded as valid
*/
struct nand_bch_control {
struct bch_control *bch;
- struct nand_ecclayout ecclayout;
unsigned int *errloc;
unsigned char *eccmask;
};
@@ -124,7 +122,6 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
{
struct nand_chip *nand = mtd_to_nand(mtd);
unsigned int m, t, eccsteps, i;
- struct nand_ecclayout *layout = nand->ecc.layout;
struct nand_bch_control *nbc = NULL;
unsigned char *erased_page;
unsigned int eccsize = nand->ecc.size;
@@ -161,34 +158,10 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
eccsteps = mtd->writesize/eccsize;
- /* if no ecc placement scheme was provided, build one */
- if (!layout) {
-
- /* handle large page devices only */
- if (mtd->oobsize < 64) {
- printk(KERN_WARNING "must provide an oob scheme for "
- "oobsize %d\n", mtd->oobsize);
- goto fail;
- }
-
- layout = &nbc->ecclayout;
- layout->eccbytes = eccsteps*eccbytes;
-
- /* reserve 2 bytes for bad block marker */
- if (layout->eccbytes+2 > mtd->oobsize) {
- printk(KERN_WARNING "no suitable oob scheme available "
- "for oobsize %d eccbytes %u\n", mtd->oobsize,
- eccbytes);
- goto fail;
- }
- /* put ecc bytes at oob tail */
- for (i = 0; i < layout->eccbytes; i++)
- layout->eccpos[i] = mtd->oobsize-layout->eccbytes+i;
-
- layout->oobfree[0].offset = 2;
- layout->oobfree[0].length = mtd->oobsize-2-layout->eccbytes;
-
- nand->ecc.layout = layout;
+ /* Check that we have an oob layout description. */
+ if (!mtd->ooblayout) {
+ pr_warn("missing oob scheme");
+ goto fail;
}
/* sanity checks */
@@ -196,7 +169,18 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
printk(KERN_WARNING "eccsize %u is too large\n", eccsize);
goto fail;
}
- if (layout->eccbytes != (eccsteps*eccbytes)) {
+
+ /*
+ * ecc->steps and ecc->total might be used by mtd->ooblayout->ecc(),
+ * which is called by mtd_ooblayout_count_eccbytes().
+ * Make sure they are properly initialized before calling
+ * mtd_ooblayout_count_eccbytes().
+ * FIXME: we should probably rework the sequencing in nand_scan_tail()
+ * to avoid setting those fields twice.
+ */
+ nand->ecc.steps = eccsteps;
+ nand->ecc.total = eccsteps * eccbytes;
+ if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
printk(KERN_WARNING "invalid ecc layout\n");
goto fail;
}
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index a58169a28741..1eb934414eb5 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -569,7 +569,7 @@ static void nandsim_debugfs_remove(struct nandsim *ns)
*
* RETURNS: 0 if success, -ENOMEM if memory alloc fails.
*/
-static int alloc_device(struct nandsim *ns)
+static int __init alloc_device(struct nandsim *ns)
{
struct file *cfile;
int i, err;
@@ -654,7 +654,7 @@ static void free_device(struct nandsim *ns)
}
}
-static char *get_partition_name(int i)
+static char __init *get_partition_name(int i)
{
return kasprintf(GFP_KERNEL, "NAND simulator partition %d", i);
}
@@ -664,7 +664,7 @@ static char *get_partition_name(int i)
*
* RETURNS: 0 if success, -ERRNO if failure.
*/
-static int init_nandsim(struct mtd_info *mtd)
+static int __init init_nandsim(struct mtd_info *mtd)
{
struct nand_chip *chip = mtd_to_nand(mtd);
struct nandsim *ns = nand_get_controller_data(chip);
@@ -2261,6 +2261,7 @@ static int __init ns_init_module(void)
chip->read_buf = ns_nand_read_buf;
chip->read_word = ns_nand_read_word;
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
/* The NAND_SKIP_BBTSCAN option is necessary for 'overridesize' */
/* and 'badblocks' parameters to work */
chip->options |= NAND_SKIP_BBTSCAN;
@@ -2338,7 +2339,8 @@ static int __init ns_init_module(void)
retval = -EINVAL;
goto error;
}
- chip->ecc.mode = NAND_ECC_SOFT_BCH;
+ chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_BCH;
chip->ecc.size = 512;
chip->ecc.strength = bch;
chip->ecc.bytes = eccbytes;
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index dbc5b571c2bb..8f64011d32ef 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -261,6 +261,7 @@ static int nuc900_nand_probe(struct platform_device *pdev)
chip->chip_delay = 50;
chip->options = 0;
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
nuc900_nand->reg = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 0749ca1a1456..08e158895635 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -12,6 +12,7 @@
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/jiffies.h>
@@ -28,6 +29,7 @@
#include <linux/mtd/nand_bch.h>
#include <linux/platform_data/elm.h>
+#include <linux/omap-gpmc.h>
#include <linux/platform_data/mtd-nand-omap2.h>
#define DRIVER_NAME "omap2-nand"
@@ -151,13 +153,17 @@ static struct nand_hw_control omap_gpmc_controller = {
};
struct omap_nand_info {
- struct omap_nand_platform_data *pdata;
struct nand_chip nand;
struct platform_device *pdev;
int gpmc_cs;
- unsigned long phys_base;
+ bool dev_ready;
+ enum nand_io xfer_type;
+ int devsize;
enum omap_ecc ecc_opt;
+ struct device_node *elm_of_node;
+
+ unsigned long phys_base;
struct completion comp;
struct dma_chan *dma;
int gpmc_irq_fifo;
@@ -168,12 +174,14 @@ struct omap_nand_info {
} iomode;
u_char *buf;
int buf_len;
+ /* Interface to GPMC */
struct gpmc_nand_regs reg;
- /* generated at runtime depending on ECC algorithm and layout selected */
- struct nand_ecclayout oobinfo;
+ struct gpmc_nand_ops *ops;
+ bool flash_bbt;
/* fields specific for BCHx_HW ECC scheme */
struct device *elm_dev;
- struct device_node *of_node;
+ /* NAND ready gpio */
+ struct gpio_desc *ready_gpiod;
};
static inline struct omap_nand_info *mtd_to_omap(struct mtd_info *mtd)
@@ -208,7 +216,7 @@ static int omap_prefetch_enable(int cs, int fifo_th, int dma_mode,
*/
val = ((cs << PREFETCH_CONFIG1_CS_SHIFT) |
PREFETCH_FIFOTHRESHOLD(fifo_th) | ENABLE_PREFETCH |
- (dma_mode << DMA_MPU_MODE_SHIFT) | (0x1 & is_write));
+ (dma_mode << DMA_MPU_MODE_SHIFT) | (is_write & 0x1));
writel(val, info->reg.gpmc_prefetch_config1);
/* Start the prefetch engine */
@@ -288,14 +296,13 @@ static void omap_write_buf8(struct mtd_info *mtd, const u_char *buf, int len)
{
struct omap_nand_info *info = mtd_to_omap(mtd);
u_char *p = (u_char *)buf;
- u32 status = 0;
+ bool status;
while (len--) {
iowrite8(*p++, info->nand.IO_ADDR_W);
/* wait until buffer is available for write */
do {
- status = readl(info->reg.gpmc_status) &
- STATUS_BUFF_EMPTY;
+ status = info->ops->nand_writebuffer_empty();
} while (!status);
}
}
@@ -323,7 +330,7 @@ static void omap_write_buf16(struct mtd_info *mtd, const u_char * buf, int len)
{
struct omap_nand_info *info = mtd_to_omap(mtd);
u16 *p = (u16 *) buf;
- u32 status = 0;
+ bool status;
/* FIXME try bursts of writesw() or DMA ... */
len >>= 1;
@@ -331,8 +338,7 @@ static void omap_write_buf16(struct mtd_info *mtd, const u_char * buf, int len)
iowrite16(*p++, info->nand.IO_ADDR_W);
/* wait until buffer is available for write */
do {
- status = readl(info->reg.gpmc_status) &
- STATUS_BUFF_EMPTY;
+ status = info->ops->nand_writebuffer_empty();
} while (!status);
}
}
@@ -467,17 +473,8 @@ static inline int omap_nand_dma_transfer(struct mtd_info *mtd, void *addr,
int ret;
u32 val;
- if (addr >= high_memory) {
- struct page *p1;
-
- if (((size_t)addr & PAGE_MASK) !=
- ((size_t)(addr + len - 1) & PAGE_MASK))
- goto out_copy;
- p1 = vmalloc_to_page(addr);
- if (!p1)
- goto out_copy;
- addr = page_address(p1) + ((size_t)addr & ~PAGE_MASK);
- }
+ if (!virt_addr_valid(addr))
+ goto out_copy;
sg_init_one(&sg, addr, len);
n = dma_map_sg(info->dma->device->dev, &sg, 1, dir);
@@ -497,6 +494,11 @@ static inline int omap_nand_dma_transfer(struct mtd_info *mtd, void *addr,
tx->callback_param = &info->comp;
dmaengine_submit(tx);
+ init_completion(&info->comp);
+
+ /* setup and start DMA using dma_addr */
+ dma_async_issue_pending(info->dma);
+
/* configure and start prefetch transfer */
ret = omap_prefetch_enable(info->gpmc_cs,
PREFETCH_FIFOTHRESHOLD_MAX, 0x1, len, is_write, info);
@@ -504,10 +506,6 @@ static inline int omap_nand_dma_transfer(struct mtd_info *mtd, void *addr,
/* PFPW engine is busy, use cpu copy method */
goto out_copy_unmap;
- init_completion(&info->comp);
- dma_async_issue_pending(info->dma);
-
- /* setup and start DMA using dma_addr */
wait_for_completion(&info->comp);
tim = 0;
limit = (loops_per_jiffy * msecs_to_jiffies(OMAP_NAND_TIMEOUT_MS));
@@ -1017,21 +1015,16 @@ static int omap_wait(struct mtd_info *mtd, struct nand_chip *chip)
}
/**
- * omap_dev_ready - calls the platform specific dev_ready function
+ * omap_dev_ready - checks the NAND Ready GPIO line
* @mtd: MTD device structure
+ *
+ * Returns true if ready and false if busy.
*/
static int omap_dev_ready(struct mtd_info *mtd)
{
- unsigned int val = 0;
struct omap_nand_info *info = mtd_to_omap(mtd);
- val = readl(info->reg.gpmc_status);
-
- if ((val & 0x100) == 0x100) {
- return 1;
- } else {
- return 0;
- }
+ return gpiod_get_value(info->ready_gpiod);
}
/**
@@ -1495,9 +1488,8 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
static int omap_write_page_bch(struct mtd_info *mtd, struct nand_chip *chip,
const uint8_t *buf, int oob_required, int page)
{
- int i;
+ int ret;
uint8_t *ecc_calc = chip->buffers->ecccalc;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
/* Enable GPMC ecc engine */
chip->ecc.hwctl(mtd, NAND_ECC_WRITE);
@@ -1508,8 +1500,10 @@ static int omap_write_page_bch(struct mtd_info *mtd, struct nand_chip *chip,
/* Update ecc vector from GPMC result registers */
chip->ecc.calculate(mtd, buf, &ecc_calc[0]);
- for (i = 0; i < chip->ecc.total; i++)
- chip->oob_poi[eccpos[i]] = ecc_calc[i];
+ ret = mtd_ooblayout_set_eccbytes(mtd, ecc_calc, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
/* Write ecc vector to OOB area */
chip->write_buf(mtd, chip->oob_poi, mtd->oobsize);
@@ -1536,10 +1530,7 @@ static int omap_read_page_bch(struct mtd_info *mtd, struct nand_chip *chip,
{
uint8_t *ecc_calc = chip->buffers->ecccalc;
uint8_t *ecc_code = chip->buffers->ecccode;
- uint32_t *eccpos = chip->ecc.layout->eccpos;
- uint8_t *oob = &chip->oob_poi[eccpos[0]];
- uint32_t oob_pos = mtd->writesize + chip->ecc.layout->eccpos[0];
- int stat;
+ int stat, ret;
unsigned int max_bitflips = 0;
/* Enable GPMC ecc engine */
@@ -1549,13 +1540,18 @@ static int omap_read_page_bch(struct mtd_info *mtd, struct nand_chip *chip,
chip->read_buf(mtd, buf, mtd->writesize);
/* Read oob bytes */
- chip->cmdfunc(mtd, NAND_CMD_RNDOUT, oob_pos, -1);
- chip->read_buf(mtd, oob, chip->ecc.total);
+ chip->cmdfunc(mtd, NAND_CMD_RNDOUT,
+ mtd->writesize + BADBLOCK_MARKER_LENGTH, -1);
+ chip->read_buf(mtd, chip->oob_poi + BADBLOCK_MARKER_LENGTH,
+ chip->ecc.total);
/* Calculate ecc bytes */
chip->ecc.calculate(mtd, buf, ecc_calc);
- memcpy(ecc_code, &chip->oob_poi[eccpos[0]], chip->ecc.total);
+ ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
stat = chip->ecc.correct(mtd, buf, ecc_code, ecc_calc);
@@ -1630,7 +1626,7 @@ static bool omap2_nand_ecc_check(struct omap_nand_info *info,
"CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
return false;
}
- if (ecc_needs_elm && !is_elm_present(info, pdata->elm_of_node)) {
+ if (ecc_needs_elm && !is_elm_present(info, info->elm_of_node)) {
dev_err(&info->pdev->dev, "ELM not available\n");
return false;
}
@@ -1638,43 +1634,227 @@ static bool omap2_nand_ecc_check(struct omap_nand_info *info,
return true;
}
+static const char * const nand_xfer_types[] = {
+ [NAND_OMAP_PREFETCH_POLLED] = "prefetch-polled",
+ [NAND_OMAP_POLLED] = "polled",
+ [NAND_OMAP_PREFETCH_DMA] = "prefetch-dma",
+ [NAND_OMAP_PREFETCH_IRQ] = "prefetch-irq",
+};
+
+static int omap_get_dt_info(struct device *dev, struct omap_nand_info *info)
+{
+ struct device_node *child = dev->of_node;
+ int i;
+ const char *s;
+ u32 cs;
+
+ if (of_property_read_u32(child, "reg", &cs) < 0) {
+ dev_err(dev, "reg not found in DT\n");
+ return -EINVAL;
+ }
+
+ info->gpmc_cs = cs;
+
+ /* detect availability of ELM module. Won't be present pre-OMAP4 */
+ info->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0);
+ if (!info->elm_of_node)
+ dev_dbg(dev, "ti,elm-id not in DT\n");
+
+ /* select ecc-scheme for NAND */
+ if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) {
+ dev_err(dev, "ti,nand-ecc-opt not found\n");
+ return -EINVAL;
+ }
+
+ if (!strcmp(s, "sw")) {
+ info->ecc_opt = OMAP_ECC_HAM1_CODE_SW;
+ } else if (!strcmp(s, "ham1") ||
+ !strcmp(s, "hw") || !strcmp(s, "hw-romcode")) {
+ info->ecc_opt = OMAP_ECC_HAM1_CODE_HW;
+ } else if (!strcmp(s, "bch4")) {
+ if (info->elm_of_node)
+ info->ecc_opt = OMAP_ECC_BCH4_CODE_HW;
+ else
+ info->ecc_opt = OMAP_ECC_BCH4_CODE_HW_DETECTION_SW;
+ } else if (!strcmp(s, "bch8")) {
+ if (info->elm_of_node)
+ info->ecc_opt = OMAP_ECC_BCH8_CODE_HW;
+ else
+ info->ecc_opt = OMAP_ECC_BCH8_CODE_HW_DETECTION_SW;
+ } else if (!strcmp(s, "bch16")) {
+ info->ecc_opt = OMAP_ECC_BCH16_CODE_HW;
+ } else {
+ dev_err(dev, "unrecognized value for ti,nand-ecc-opt\n");
+ return -EINVAL;
+ }
+
+ /* select data transfer mode */
+ if (!of_property_read_string(child, "ti,nand-xfer-type", &s)) {
+ for (i = 0; i < ARRAY_SIZE(nand_xfer_types); i++) {
+ if (!strcasecmp(s, nand_xfer_types[i])) {
+ info->xfer_type = i;
+ return 0;
+ }
+ }
+
+ dev_err(dev, "unrecognized value for ti,nand-xfer-type\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int omap_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct omap_nand_info *info = mtd_to_omap(mtd);
+ struct nand_chip *chip = &info->nand;
+ int off = BADBLOCK_MARKER_LENGTH;
+
+ if (info->ecc_opt == OMAP_ECC_HAM1_CODE_HW &&
+ !(chip->options & NAND_BUSWIDTH_16))
+ off = 1;
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = off;
+ oobregion->length = chip->ecc.total;
+
+ return 0;
+}
+
+static int omap_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct omap_nand_info *info = mtd_to_omap(mtd);
+ struct nand_chip *chip = &info->nand;
+ int off = BADBLOCK_MARKER_LENGTH;
+
+ if (info->ecc_opt == OMAP_ECC_HAM1_CODE_HW &&
+ !(chip->options & NAND_BUSWIDTH_16))
+ off = 1;
+
+ if (section)
+ return -ERANGE;
+
+ off += chip->ecc.total;
+ if (off >= mtd->oobsize)
+ return -ERANGE;
+
+ oobregion->offset = off;
+ oobregion->length = mtd->oobsize - off;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops omap_ooblayout_ops = {
+ .ecc = omap_ooblayout_ecc,
+ .free = omap_ooblayout_free,
+};
+
+static int omap_sw_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ int off = BADBLOCK_MARKER_LENGTH;
+
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
+
+ /*
+ * When SW correction is employed, one OMAP specific marker byte is
+ * reserved after each ECC step.
+ */
+ oobregion->offset = off + (section * (chip->ecc.bytes + 1));
+ oobregion->length = chip->ecc.bytes;
+
+ return 0;
+}
+
+static int omap_sw_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ int off = BADBLOCK_MARKER_LENGTH;
+
+ if (section)
+ return -ERANGE;
+
+ /*
+ * When SW correction is employed, one OMAP specific marker byte is
+ * reserved after each ECC step.
+ */
+ off += ((chip->ecc.bytes + 1) * chip->ecc.steps);
+ if (off >= mtd->oobsize)
+ return -ERANGE;
+
+ oobregion->offset = off;
+ oobregion->length = mtd->oobsize - off;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops omap_sw_ooblayout_ops = {
+ .ecc = omap_sw_ooblayout_ecc,
+ .free = omap_sw_ooblayout_free,
+};
+
static int omap_nand_probe(struct platform_device *pdev)
{
struct omap_nand_info *info;
- struct omap_nand_platform_data *pdata;
+ struct omap_nand_platform_data *pdata = NULL;
struct mtd_info *mtd;
struct nand_chip *nand_chip;
- struct nand_ecclayout *ecclayout;
int err;
- int i;
dma_cap_mask_t mask;
unsigned sig;
- unsigned oob_index;
struct resource *res;
-
- pdata = dev_get_platdata(&pdev->dev);
- if (pdata == NULL) {
- dev_err(&pdev->dev, "platform data missing\n");
- return -ENODEV;
- }
+ struct device *dev = &pdev->dev;
+ int min_oobbytes = BADBLOCK_MARKER_LENGTH;
+ int oobbytes_per_step;
info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
GFP_KERNEL);
if (!info)
return -ENOMEM;
+ info->pdev = pdev;
+
+ if (dev->of_node) {
+ if (omap_get_dt_info(dev, info))
+ return -EINVAL;
+ } else {
+ pdata = dev_get_platdata(&pdev->dev);
+ if (!pdata) {
+ dev_err(&pdev->dev, "platform data missing\n");
+ return -EINVAL;
+ }
+
+ info->gpmc_cs = pdata->cs;
+ info->reg = pdata->reg;
+ info->ecc_opt = pdata->ecc_opt;
+ if (pdata->dev_ready)
+ dev_info(&pdev->dev, "pdata->dev_ready is deprecated\n");
+
+ info->xfer_type = pdata->xfer_type;
+ info->devsize = pdata->devsize;
+ info->elm_of_node = pdata->elm_of_node;
+ info->flash_bbt = pdata->flash_bbt;
+ }
+
platform_set_drvdata(pdev, info);
+ info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
+ if (!info->ops) {
+ dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
+ return -ENODEV;
+ }
- info->pdev = pdev;
- info->gpmc_cs = pdata->cs;
- info->reg = pdata->reg;
- info->of_node = pdata->of_node;
- info->ecc_opt = pdata->ecc_opt;
nand_chip = &info->nand;
mtd = nand_to_mtd(nand_chip);
mtd->dev.parent = &pdev->dev;
nand_chip->ecc.priv = NULL;
- nand_set_flash_node(nand_chip, pdata->of_node);
+ nand_set_flash_node(nand_chip, dev->of_node);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
@@ -1688,6 +1868,13 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
nand_chip->cmd_ctrl = omap_hwcontrol;
+ info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
+ GPIOD_IN);
+ if (IS_ERR(info->ready_gpiod)) {
+ dev_err(dev, "failed to get ready gpio\n");
+ return PTR_ERR(info->ready_gpiod);
+ }
+
/*
* If RDY/BSY line is connected to OMAP then use the omap ready
* function and the generic nand_wait function which reads the status
@@ -1695,7 +1882,7 @@ static int omap_nand_probe(struct platform_device *pdev)
* chip delay which is slightly more than tR (AC Timing) of the NAND
* device and read status register until you get a failure or success
*/
- if (pdata->dev_ready) {
+ if (info->ready_gpiod) {
nand_chip->dev_ready = omap_dev_ready;
nand_chip->chip_delay = 0;
} else {
@@ -1703,21 +1890,25 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->chip_delay = 50;
}
- if (pdata->flash_bbt)
- nand_chip->bbt_options |= NAND_BBT_USE_FLASH | NAND_BBT_NO_OOB;
- else
- nand_chip->options |= NAND_SKIP_BBTSCAN;
+ if (info->flash_bbt)
+ nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
/* scan NAND device connected to chip controller */
- nand_chip->options |= pdata->devsize & NAND_BUSWIDTH_16;
+ nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
if (nand_scan_ident(mtd, 1, NULL)) {
- dev_err(&info->pdev->dev, "scan failed, may be bus-width mismatch\n");
+ dev_err(&info->pdev->dev,
+ "scan failed, may be bus-width mismatch\n");
err = -ENXIO;
goto return_error;
}
+ if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
+ nand_chip->bbt_options |= NAND_BBT_NO_OOB;
+ else
+ nand_chip->options |= NAND_SKIP_BBTSCAN;
+
/* re-populate low-level callbacks based on xfer modes */
- switch (pdata->xfer_type) {
+ switch (info->xfer_type) {
case NAND_OMAP_PREFETCH_POLLED:
nand_chip->read_buf = omap_read_buf_pref;
nand_chip->write_buf = omap_write_buf_pref;
@@ -1797,7 +1988,7 @@ static int omap_nand_probe(struct platform_device *pdev)
default:
dev_err(&pdev->dev,
- "xfer_type(%d) not supported!\n", pdata->xfer_type);
+ "xfer_type(%d) not supported!\n", info->xfer_type);
err = -EINVAL;
goto return_error;
}
@@ -1809,16 +2000,15 @@ static int omap_nand_probe(struct platform_device *pdev)
/*
* Bail out earlier to let NAND_ECC_SOFT code create its own
- * ecclayout instead of using ours.
+ * ooblayout instead of using ours.
*/
if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
nand_chip->ecc.mode = NAND_ECC_SOFT;
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
goto scan_tail;
}
/* populate MTD interface based on ECC scheme */
- ecclayout = &info->oobinfo;
- nand_chip->ecc.layout = ecclayout;
switch (info->ecc_opt) {
case OMAP_ECC_HAM1_CODE_HW:
pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n");
@@ -1829,19 +2019,12 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->ecc.calculate = omap_calculate_ecc;
nand_chip->ecc.hwctl = omap_enable_hwecc;
nand_chip->ecc.correct = omap_correct_data;
- /* define ECC layout */
- ecclayout->eccbytes = nand_chip->ecc.bytes *
- (mtd->writesize /
- nand_chip->ecc.size);
- if (nand_chip->options & NAND_BUSWIDTH_16)
- oob_index = BADBLOCK_MARKER_LENGTH;
- else
- oob_index = 1;
- for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
- ecclayout->eccpos[i] = oob_index;
- /* no reserved-marker in ecclayout for this ecc-scheme */
- ecclayout->oobfree->offset =
- ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
+ mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
+ oobbytes_per_step = nand_chip->ecc.bytes;
+
+ if (!(nand_chip->options & NAND_BUSWIDTH_16))
+ min_oobbytes = 1;
+
break;
case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
@@ -1853,19 +2036,9 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->ecc.hwctl = omap_enable_hwecc_bch;
nand_chip->ecc.correct = nand_bch_correct_data;
nand_chip->ecc.calculate = omap_calculate_ecc_bch;
- /* define ECC layout */
- ecclayout->eccbytes = nand_chip->ecc.bytes *
- (mtd->writesize /
- nand_chip->ecc.size);
- oob_index = BADBLOCK_MARKER_LENGTH;
- for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
- ecclayout->eccpos[i] = oob_index;
- if (((i + 1) % nand_chip->ecc.bytes) == 0)
- oob_index++;
- }
- /* include reserved-marker in ecclayout->oobfree calculation */
- ecclayout->oobfree->offset = 1 +
- ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
+ mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
+ /* Reserve one byte for the OMAP marker */
+ oobbytes_per_step = nand_chip->ecc.bytes + 1;
/* software bch library is used for locating errors */
nand_chip->ecc.priv = nand_bch_init(mtd);
if (!nand_chip->ecc.priv) {
@@ -1887,16 +2060,8 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->ecc.calculate = omap_calculate_ecc_bch;
nand_chip->ecc.read_page = omap_read_page_bch;
nand_chip->ecc.write_page = omap_write_page_bch;
- /* define ECC layout */
- ecclayout->eccbytes = nand_chip->ecc.bytes *
- (mtd->writesize /
- nand_chip->ecc.size);
- oob_index = BADBLOCK_MARKER_LENGTH;
- for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
- ecclayout->eccpos[i] = oob_index;
- /* reserved marker already included in ecclayout->eccbytes */
- ecclayout->oobfree->offset =
- ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
+ mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
+ oobbytes_per_step = nand_chip->ecc.bytes;
err = elm_config(info->elm_dev, BCH4_ECC,
mtd->writesize / nand_chip->ecc.size,
@@ -1914,19 +2079,9 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->ecc.hwctl = omap_enable_hwecc_bch;
nand_chip->ecc.correct = nand_bch_correct_data;
nand_chip->ecc.calculate = omap_calculate_ecc_bch;
- /* define ECC layout */
- ecclayout->eccbytes = nand_chip->ecc.bytes *
- (mtd->writesize /
- nand_chip->ecc.size);
- oob_index = BADBLOCK_MARKER_LENGTH;
- for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
- ecclayout->eccpos[i] = oob_index;
- if (((i + 1) % nand_chip->ecc.bytes) == 0)
- oob_index++;
- }
- /* include reserved-marker in ecclayout->oobfree calculation */
- ecclayout->oobfree->offset = 1 +
- ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
+ mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
+ /* Reserve one byte for the OMAP marker */
+ oobbytes_per_step = nand_chip->ecc.bytes + 1;
/* software bch library is used for locating errors */
nand_chip->ecc.priv = nand_bch_init(mtd);
if (!nand_chip->ecc.priv) {
@@ -1948,6 +2103,8 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->ecc.calculate = omap_calculate_ecc_bch;
nand_chip->ecc.read_page = omap_read_page_bch;
nand_chip->ecc.write_page = omap_write_page_bch;
+ mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
+ oobbytes_per_step = nand_chip->ecc.bytes;
err = elm_config(info->elm_dev, BCH8_ECC,
mtd->writesize / nand_chip->ecc.size,
@@ -1955,16 +2112,6 @@ static int omap_nand_probe(struct platform_device *pdev)
if (err < 0)
goto return_error;
- /* define ECC layout */
- ecclayout->eccbytes = nand_chip->ecc.bytes *
- (mtd->writesize /
- nand_chip->ecc.size);
- oob_index = BADBLOCK_MARKER_LENGTH;
- for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
- ecclayout->eccpos[i] = oob_index;
- /* reserved marker already included in ecclayout->eccbytes */
- ecclayout->oobfree->offset =
- ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
break;
case OMAP_ECC_BCH16_CODE_HW:
@@ -1978,6 +2125,8 @@ static int omap_nand_probe(struct platform_device *pdev)
nand_chip->ecc.calculate = omap_calculate_ecc_bch;
nand_chip->ecc.read_page = omap_read_page_bch;
nand_chip->ecc.write_page = omap_write_page_bch;
+ mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
+ oobbytes_per_step = nand_chip->ecc.bytes;
err = elm_config(info->elm_dev, BCH16_ECC,
mtd->writesize / nand_chip->ecc.size,
@@ -1985,16 +2134,6 @@ static int omap_nand_probe(struct platform_device *pdev)
if (err < 0)
goto return_error;
- /* define ECC layout */
- ecclayout->eccbytes = nand_chip->ecc.bytes *
- (mtd->writesize /
- nand_chip->ecc.size);
- oob_index = BADBLOCK_MARKER_LENGTH;
- for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
- ecclayout->eccpos[i] = oob_index;
- /* reserved marker already included in ecclayout->eccbytes */
- ecclayout->oobfree->offset =
- ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
break;
default:
dev_err(&info->pdev->dev, "invalid or unsupported ECC scheme\n");
@@ -2002,13 +2141,13 @@ static int omap_nand_probe(struct platform_device *pdev)
goto return_error;
}
- /* all OOB bytes from oobfree->offset till end off OOB are free */
- ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset;
/* check if NAND device's OOB is enough to store ECC signatures */
- if (mtd->oobsize < (ecclayout->eccbytes + BADBLOCK_MARKER_LENGTH)) {
+ min_oobbytes += (oobbytes_per_step *
+ (mtd->writesize / nand_chip->ecc.size));
+ if (mtd->oobsize < min_oobbytes) {
dev_err(&info->pdev->dev,
"not enough OOB bytes required = %d, available=%d\n",
- ecclayout->eccbytes, mtd->oobsize);
+ min_oobbytes, mtd->oobsize);
err = -EINVAL;
goto return_error;
}
@@ -2020,7 +2159,10 @@ scan_tail:
goto return_error;
}
- mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
+ if (dev->of_node)
+ mtd_device_register(mtd, NULL, 0);
+ else
+ mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
platform_set_drvdata(pdev, mtd);
@@ -2051,11 +2193,17 @@ static int omap_nand_remove(struct platform_device *pdev)
return 0;
}
+static const struct of_device_id omap_nand_ids[] = {
+ { .compatible = "ti,omap2-nand", },
+ {},
+};
+
static struct platform_driver omap_nand_driver = {
.probe = omap_nand_probe,
.remove = omap_nand_remove,
.driver = {
.name = DRIVER_NAME,
+ .of_match_table = of_match_ptr(omap_nand_ids),
},
};
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index d4614bfbfed6..40a7c4a2cf0d 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -130,6 +130,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
nc->cmd_ctrl = orion_nand_cmd_ctrl;
nc->read_buf = orion_nand_read_buf;
nc->ecc.mode = NAND_ECC_SOFT;
+ nc->ecc.algo = NAND_ECC_HAMMING;
if (board->chip_delay)
nc->chip_delay = board->chip_delay;
diff --git a/drivers/mtd/nand/pasemi_nand.c b/drivers/mtd/nand/pasemi_nand.c
index 3ab53ca53cca..5de7591b0510 100644
--- a/drivers/mtd/nand/pasemi_nand.c
+++ b/drivers/mtd/nand/pasemi_nand.c
@@ -92,8 +92,9 @@ int pasemi_device_ready(struct mtd_info *mtd)
static int pasemi_nand_probe(struct platform_device *ofdev)
{
+ struct device *dev = &ofdev->dev;
struct pci_dev *pdev;
- struct device_node *np = ofdev->dev.of_node;
+ struct device_node *np = dev->of_node;
struct resource res;
struct nand_chip *chip;
int err = 0;
@@ -107,13 +108,11 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
if (pasemi_nand_mtd)
return -ENODEV;
- pr_debug("pasemi_nand at %pR\n", &res);
+ dev_dbg(dev, "pasemi_nand at %pR\n", &res);
/* Allocate memory for MTD device structure and private data */
chip = kzalloc(sizeof(struct nand_chip), GFP_KERNEL);
if (!chip) {
- printk(KERN_WARNING
- "Unable to allocate PASEMI NAND MTD device structure\n");
err = -ENOMEM;
goto out;
}
@@ -121,7 +120,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
pasemi_nand_mtd = nand_to_mtd(chip);
/* Link the private data with the MTD structure */
- pasemi_nand_mtd->dev.parent = &ofdev->dev;
+ pasemi_nand_mtd->dev.parent = dev;
chip->IO_ADDR_R = of_iomap(np, 0);
chip->IO_ADDR_W = chip->IO_ADDR_R;
@@ -151,6 +150,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
chip->write_buf = pasemi_write_buf;
chip->chip_delay = 0;
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
/* Enable the following for a flash based bad block table */
chip->bbt_options = NAND_BBT_USE_FLASH;
@@ -162,13 +162,13 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
}
if (mtd_device_register(pasemi_nand_mtd, NULL, 0)) {
- printk(KERN_ERR "pasemi_nand: Unable to register MTD device\n");
+ dev_err(dev, "Unable to register MTD device\n");
err = -ENODEV;
goto out_lpc;
}
- printk(KERN_INFO "PA Semi NAND flash at %08llx, control at I/O %x\n",
- res.start, lpcctl);
+ dev_info(dev, "PA Semi NAND flash at %pR, control at I/O %x\n", &res,
+ lpcctl);
return 0;
diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c
index e4e50da30444..415a53a0deeb 100644
--- a/drivers/mtd/nand/plat_nand.c
+++ b/drivers/mtd/nand/plat_nand.c
@@ -74,6 +74,7 @@ static int plat_nand_probe(struct platform_device *pdev)
data->chip.ecc.hwctl = pdata->ctrl.hwcontrol;
data->chip.ecc.mode = NAND_ECC_SOFT;
+ data->chip.ecc.algo = NAND_ECC_HAMMING;
platform_set_drvdata(pdev, data);
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index d6508856da99..436dd6dc11f4 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -29,7 +29,6 @@
#include <linux/slab.h>
#include <linux/of.h>
#include <linux/of_device.h>
-#include <linux/of_mtd.h>
#include <linux/platform_data/mtd-nand-pxa3xx.h>
#define CHIP_DELAY_TIMEOUT msecs_to_jiffies(200)
@@ -324,6 +323,62 @@ static struct pxa3xx_nand_flash builtin_flash_types[] = {
{ 0xba20, 16, 16, &timing[3] },
};
+static int pxa3xx_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct pxa3xx_nand_host *host = nand_get_controller_data(chip);
+ struct pxa3xx_nand_info *info = host->info_data;
+ int nchunks = mtd->writesize / info->chunk_size;
+
+ if (section >= nchunks)
+ return -ERANGE;
+
+ oobregion->offset = ((info->ecc_size + info->spare_size) * section) +
+ info->spare_size;
+ oobregion->length = info->ecc_size;
+
+ return 0;
+}
+
+static int pxa3xx_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct pxa3xx_nand_host *host = nand_get_controller_data(chip);
+ struct pxa3xx_nand_info *info = host->info_data;
+ int nchunks = mtd->writesize / info->chunk_size;
+
+ if (section >= nchunks)
+ return -ERANGE;
+
+ if (!info->spare_size)
+ return 0;
+
+ oobregion->offset = section * (info->ecc_size + info->spare_size);
+ oobregion->length = info->spare_size;
+ if (!section) {
+ /*
+ * Bootrom looks in bytes 0 & 5 for bad blocks for the
+ * 4KB page / 4bit BCH combination.
+ */
+ if (mtd->writesize == 4096 && info->chunk_size == 2048) {
+ oobregion->offset += 6;
+ oobregion->length -= 6;
+ } else {
+ oobregion->offset += 2;
+ oobregion->length -= 2;
+ }
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops pxa3xx_ooblayout_ops = {
+ .ecc = pxa3xx_ooblayout_ecc,
+ .free = pxa3xx_ooblayout_free,
+};
+
static u8 bbt_pattern[] = {'M', 'V', 'B', 'b', 't', '0' };
static u8 bbt_mirror_pattern[] = {'1', 't', 'b', 'B', 'V', 'M' };
@@ -347,41 +402,6 @@ static struct nand_bbt_descr bbt_mirror_descr = {
.pattern = bbt_mirror_pattern
};
-static struct nand_ecclayout ecc_layout_2KB_bch4bit = {
- .eccbytes = 32,
- .eccpos = {
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63},
- .oobfree = { {2, 30} }
-};
-
-static struct nand_ecclayout ecc_layout_4KB_bch4bit = {
- .eccbytes = 64,
- .eccpos = {
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 96, 97, 98, 99, 100, 101, 102, 103,
- 104, 105, 106, 107, 108, 109, 110, 111,
- 112, 113, 114, 115, 116, 117, 118, 119,
- 120, 121, 122, 123, 124, 125, 126, 127},
- /* Bootrom looks in bytes 0 & 5 for bad blocks */
- .oobfree = { {6, 26}, { 64, 32} }
-};
-
-static struct nand_ecclayout ecc_layout_4KB_bch8bit = {
- .eccbytes = 128,
- .eccpos = {
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63},
- .oobfree = { }
-};
-
#define NDTR0_tCH(c) (min((c), 7) << 19)
#define NDTR0_tCS(c) (min((c), 7) << 16)
#define NDTR0_tWH(c) (min((c), 7) << 11)
@@ -1546,9 +1566,12 @@ static void pxa3xx_nand_free_buff(struct pxa3xx_nand_info *info)
}
static int pxa_ecc_init(struct pxa3xx_nand_info *info,
- struct nand_ecc_ctrl *ecc,
+ struct mtd_info *mtd,
int strength, int ecc_stepsize, int page_size)
{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
+
if (strength == 1 && ecc_stepsize == 512 && page_size == 2048) {
info->nfullchunks = 1;
info->ntotalchunks = 1;
@@ -1582,7 +1605,7 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
info->ecc_size = 32;
ecc->mode = NAND_ECC_HW;
ecc->size = info->chunk_size;
- ecc->layout = &ecc_layout_2KB_bch4bit;
+ mtd_set_ooblayout(mtd, &pxa3xx_ooblayout_ops);
ecc->strength = 16;
} else if (strength == 4 && ecc_stepsize == 512 && page_size == 4096) {
@@ -1594,7 +1617,7 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
info->ecc_size = 32;
ecc->mode = NAND_ECC_HW;
ecc->size = info->chunk_size;
- ecc->layout = &ecc_layout_4KB_bch4bit;
+ mtd_set_ooblayout(mtd, &pxa3xx_ooblayout_ops);
ecc->strength = 16;
/*
@@ -1612,7 +1635,7 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
info->ecc_size = 32;
ecc->mode = NAND_ECC_HW;
ecc->size = info->chunk_size;
- ecc->layout = &ecc_layout_4KB_bch8bit;
+ mtd_set_ooblayout(mtd, &pxa3xx_ooblayout_ops);
ecc->strength = 16;
} else {
dev_err(&info->pdev->dev,
@@ -1651,6 +1674,12 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
if (info->variant == PXA3XX_NAND_VARIANT_ARMADA370)
nand_writel(info, NDECCCTRL, 0x0);
+ if (pdata->flash_bbt)
+ chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+ chip->ecc.strength = pdata->ecc_strength;
+ chip->ecc.size = pdata->ecc_step_size;
+
if (nand_scan_ident(mtd, 1, NULL))
return -ENODEV;
@@ -1663,13 +1692,12 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
}
}
- if (pdata->flash_bbt) {
+ if (chip->bbt_options & NAND_BBT_USE_FLASH) {
/*
* We'll use a bad block table stored in-flash and don't
* allow writing the bad block marker to the flash.
*/
- chip->bbt_options |= NAND_BBT_USE_FLASH |
- NAND_BBT_NO_OOB_BBM;
+ chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
chip->bbt_td = &bbt_main_descr;
chip->bbt_md = &bbt_mirror_descr;
}
@@ -1689,10 +1717,9 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
}
}
- if (pdata->ecc_strength && pdata->ecc_step_size) {
- ecc_strength = pdata->ecc_strength;
- ecc_step = pdata->ecc_step_size;
- } else {
+ ecc_strength = chip->ecc.strength;
+ ecc_step = chip->ecc.size;
+ if (!ecc_strength || !ecc_step) {
ecc_strength = chip->ecc_strength_ds;
ecc_step = chip->ecc_step_ds;
}
@@ -1703,7 +1730,7 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
ecc_step = 512;
}
- ret = pxa_ecc_init(info, &chip->ecc, ecc_strength,
+ ret = pxa_ecc_init(info, mtd, ecc_strength,
ecc_step, mtd->writesize);
if (ret)
return ret;
@@ -1903,15 +1930,6 @@ static int pxa3xx_nand_probe_dt(struct platform_device *pdev)
if (of_get_property(np, "marvell,nand-keep-config", NULL))
pdata->keep_config = 1;
of_property_read_u32(np, "num-cs", &pdata->num_cs);
- pdata->flash_bbt = of_get_nand_on_flash_bbt(np);
-
- pdata->ecc_strength = of_get_nand_ecc_strength(np);
- if (pdata->ecc_strength < 0)
- pdata->ecc_strength = 0;
-
- pdata->ecc_step_size = of_get_nand_ecc_step_size(np);
- if (pdata->ecc_step_size < 0)
- pdata->ecc_step_size = 0;
pdev->dev.platform_data = pdata;
diff --git a/drivers/mtd/nand/qcom_nandc.c b/drivers/mtd/nand/qcom_nandc.c
index f550a57e6eea..de7d28e62d4e 100644
--- a/drivers/mtd/nand/qcom_nandc.c
+++ b/drivers/mtd/nand/qcom_nandc.c
@@ -21,7 +21,6 @@
#include <linux/mtd/partitions.h>
#include <linux/of.h>
#include <linux/of_device.h>
-#include <linux/of_mtd.h>
#include <linux/delay.h>
/* NANDc reg offsets */
@@ -1437,7 +1436,6 @@ static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
struct nand_ecc_ctrl *ecc = &chip->ecc;
u8 *oob = chip->oob_poi;
- int free_boff;
int data_size, oob_size;
int ret, status = 0;
@@ -1451,12 +1449,11 @@ static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
/* calculate the data and oob size for the last codeword/step */
data_size = ecc->size - ((ecc->steps - 1) << 2);
- oob_size = ecc->steps << 2;
-
- free_boff = ecc->layout->oobfree[0].offset;
+ oob_size = mtd->oobavail;
/* override new oob content to last codeword */
- memcpy(nandc->data_buffer + data_size, oob + free_boff, oob_size);
+ mtd_ooblayout_get_databytes(mtd, nandc->data_buffer + data_size, oob,
+ 0, mtd->oobavail);
set_address(host, host->cw_size * (ecc->steps - 1), page);
update_rw_regs(host, 1, false);
@@ -1710,61 +1707,52 @@ static void qcom_nandc_select_chip(struct mtd_info *mtd, int chipnr)
* This layout is read as is when ECC is disabled. When ECC is enabled, the
* inaccessible Bad Block byte(s) are ignored when we write to a page/oob,
* and assumed as 0xffs when we read a page/oob. The ECC, unused and
- * dummy/real bad block bytes are grouped as ecc bytes in nand_ecclayout (i.e,
- * ecc->bytes is the sum of the three).
+ * dummy/real bad block bytes are grouped as ecc bytes (i.e, ecc->bytes is
+ * the sum of the three).
*/
-
-static struct nand_ecclayout *
-qcom_nand_create_layout(struct qcom_nand_host *host)
+static int qcom_nand_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
{
- struct nand_chip *chip = &host->chip;
- struct mtd_info *mtd = nand_to_mtd(chip);
- struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct qcom_nand_host *host = to_qcom_nand_host(chip);
struct nand_ecc_ctrl *ecc = &chip->ecc;
- struct nand_ecclayout *layout;
- int i, j, steps, pos = 0, shift = 0;
- layout = devm_kzalloc(nandc->dev, sizeof(*layout), GFP_KERNEL);
- if (!layout)
- return NULL;
-
- steps = mtd->writesize / ecc->size;
- layout->eccbytes = steps * ecc->bytes;
+ if (section > 1)
+ return -ERANGE;
- layout->oobfree[0].offset = (steps - 1) * ecc->bytes + host->bbm_size;
- layout->oobfree[0].length = steps << 2;
-
- /*
- * the oob bytes in the first n - 1 codewords are all grouped together
- * in the format:
- * DUMMY_BBM + UNUSED + ECC
- */
- for (i = 0; i < steps - 1; i++) {
- for (j = 0; j < ecc->bytes; j++)
- layout->eccpos[pos++] = i * ecc->bytes + j;
+ if (!section) {
+ oobregion->length = (ecc->bytes * (ecc->steps - 1)) +
+ host->bbm_size;
+ oobregion->offset = 0;
+ } else {
+ oobregion->length = host->ecc_bytes_hw + host->spare_bytes;
+ oobregion->offset = mtd->oobsize - oobregion->length;
}
- /*
- * the oob bytes in the last codeword are grouped in the format:
- * BBM + FREE OOB + UNUSED + ECC
- */
+ return 0;
+}
- /* fill up the bbm positions */
- for (j = 0; j < host->bbm_size; j++)
- layout->eccpos[pos++] = i * ecc->bytes + j;
+static int qcom_nand_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct qcom_nand_host *host = to_qcom_nand_host(chip);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
- /*
- * fill up the ecc and reserved positions, their indices are offseted
- * by the free oob region
- */
- shift = layout->oobfree[0].length + host->bbm_size;
+ if (section)
+ return -ERANGE;
- for (j = 0; j < (host->ecc_bytes_hw + host->spare_bytes); j++)
- layout->eccpos[pos++] = i * ecc->bytes + shift + j;
+ oobregion->length = ecc->steps * 4;
+ oobregion->offset = ((ecc->steps - 1) * ecc->bytes) + host->bbm_size;
- return layout;
+ return 0;
}
+static const struct mtd_ooblayout_ops qcom_nand_ooblayout_ops = {
+ .ecc = qcom_nand_ooblayout_ecc,
+ .free = qcom_nand_ooblayout_free,
+};
+
static int qcom_nand_host_setup(struct qcom_nand_host *host)
{
struct nand_chip *chip = &host->chip;
@@ -1851,9 +1839,7 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
ecc->mode = NAND_ECC_HW;
- ecc->layout = qcom_nand_create_layout(host);
- if (!ecc->layout)
- return -ENOMEM;
+ mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
cwperpage = mtd->writesize / ecc->size;
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 9c9397b54b2c..d9309cf0ce2e 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -84,11 +84,33 @@
/* new oob placement block for use with hardware ecc generation
*/
+static int s3c2410_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 0;
+ oobregion->length = 3;
+
+ return 0;
+}
+
+static int s3c2410_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 8;
+ oobregion->length = 8;
+
+ return 0;
+}
-static struct nand_ecclayout nand_hw_eccoob = {
- .eccbytes = 3,
- .eccpos = {0, 1, 2},
- .oobfree = {{8, 8}}
+static const struct mtd_ooblayout_ops s3c2410_ooblayout_ops = {
+ .ecc = s3c2410_ooblayout_ecc,
+ .free = s3c2410_ooblayout_free,
};
/* controller and mtd information */
@@ -542,7 +564,8 @@ static int s3c2410_nand_correct_data(struct mtd_info *mtd, u_char *dat,
diff0 |= (diff1 << 8);
diff0 |= (diff2 << 16);
- if ((diff0 & ~(1<<fls(diff0))) == 0)
+ /* equal to "(diff0 & ~(1 << __ffs(diff0)))" */
+ if ((diff0 & (diff0 - 1)) == 0)
return 1;
return -1;
@@ -859,6 +882,7 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
}
#else
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
#endif
if (set->disable_ecc)
@@ -919,7 +943,7 @@ static void s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
} else {
chip->ecc.size = 512;
chip->ecc.bytes = 3;
- chip->ecc.layout = &nand_hw_eccoob;
+ mtd_set_ooblayout(nand_to_mtd(chip), &s3c2410_ooblayout_ops);
}
}
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 4814402902f9..6fa3bcd59769 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -31,7 +31,6 @@
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_device.h>
-#include <linux/of_mtd.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/sh_dma.h>
@@ -43,26 +42,73 @@
#include <linux/mtd/partitions.h>
#include <linux/mtd/sh_flctl.h>
-static struct nand_ecclayout flctl_4secc_oob_16 = {
- .eccbytes = 10,
- .eccpos = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9},
- .oobfree = {
- {.offset = 12,
- . length = 4} },
+static int flctl_4secc_ooblayout_sp_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 0;
+ oobregion->length = chip->ecc.bytes;
+
+ return 0;
+}
+
+static int flctl_4secc_ooblayout_sp_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->offset = 12;
+ oobregion->length = 4;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops flctl_4secc_oob_smallpage_ops = {
+ .ecc = flctl_4secc_ooblayout_sp_ecc,
+ .free = flctl_4secc_ooblayout_sp_free,
};
-static struct nand_ecclayout flctl_4secc_oob_64 = {
- .eccbytes = 4 * 10,
- .eccpos = {
- 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
- 54, 55, 56, 57, 58, 59, 60, 61, 62, 63 },
- .oobfree = {
- {.offset = 2, .length = 4},
- {.offset = 16, .length = 6},
- {.offset = 32, .length = 6},
- {.offset = 48, .length = 6} },
+static int flctl_4secc_ooblayout_lp_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 6;
+ oobregion->length = chip->ecc.bytes;
+
+ return 0;
+}
+
+static int flctl_4secc_ooblayout_lp_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+
+ if (section >= chip->ecc.steps)
+ return -ERANGE;
+
+ oobregion->offset = section * 16;
+ oobregion->length = 6;
+
+ if (!section) {
+ oobregion->offset += 2;
+ oobregion->length -= 2;
+ }
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops flctl_4secc_oob_largepage_ops = {
+ .ecc = flctl_4secc_ooblayout_lp_ecc,
+ .free = flctl_4secc_ooblayout_lp_free,
};
static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
@@ -987,10 +1033,10 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
if (flctl->hwecc) {
if (mtd->writesize == 512) {
- chip->ecc.layout = &flctl_4secc_oob_16;
+ mtd_set_ooblayout(mtd, &flctl_4secc_oob_smallpage_ops);
chip->badblock_pattern = &flctl_4secc_smallpage;
} else {
- chip->ecc.layout = &flctl_4secc_oob_64;
+ mtd_set_ooblayout(mtd, &flctl_4secc_oob_largepage_ops);
chip->badblock_pattern = &flctl_4secc_largepage;
}
@@ -1005,6 +1051,7 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
flctl->flcmncr_base |= _4ECCEN;
} else {
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
}
return 0;
@@ -1044,8 +1091,6 @@ static struct sh_flctl_platform_data *flctl_parse_dt(struct device *dev)
const struct of_device_id *match;
struct flctl_soc_config *config;
struct sh_flctl_platform_data *pdata;
- struct device_node *dn = dev->of_node;
- int ret;
match = of_match_device(of_flctl_match, dev);
if (match)
@@ -1065,15 +1110,6 @@ static struct sh_flctl_platform_data *flctl_parse_dt(struct device *dev)
pdata->has_hwecc = config->has_hwecc;
pdata->use_holden = config->use_holden;
- /* parse user defined options */
- ret = of_get_nand_bus_width(dn);
- if (ret == 16)
- pdata->flcmncr_val |= SEL_16BIT;
- else if (ret != 8) {
- dev_err(dev, "%s: invalid bus width\n", __func__);
- return NULL;
- }
-
return pdata;
}
@@ -1136,15 +1172,14 @@ static int flctl_probe(struct platform_device *pdev)
nand->chip_delay = 20;
nand->read_byte = flctl_read_byte;
+ nand->read_word = flctl_read_word;
nand->write_buf = flctl_write_buf;
nand->read_buf = flctl_read_buf;
nand->select_chip = flctl_select_chip;
nand->cmdfunc = flctl_cmdfunc;
- if (pdata->flcmncr_val & SEL_16BIT) {
+ if (pdata->flcmncr_val & SEL_16BIT)
nand->options |= NAND_BUSWIDTH_16;
- nand->read_word = flctl_read_word;
- }
pm_runtime_enable(&pdev->dev);
pm_runtime_resume(&pdev->dev);
@@ -1155,6 +1190,16 @@ static int flctl_probe(struct platform_device *pdev)
if (ret)
goto err_chip;
+ if (nand->options & NAND_BUSWIDTH_16) {
+ /*
+ * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
+ * Add the SEL_16BIT flag in pdata->flcmncr_val and re-assign
+ * flctl->flcmncr_base to pdata->flcmncr_val.
+ */
+ pdata->flcmncr_val |= SEL_16BIT;
+ flctl->flcmncr_base = pdata->flcmncr_val;
+ }
+
ret = flctl_chip_init_tail(flctl_mtd);
if (ret)
goto err_chip;
diff --git a/drivers/mtd/nand/sharpsl.c b/drivers/mtd/nand/sharpsl.c
index b7d1b55a160b..064ca1757589 100644
--- a/drivers/mtd/nand/sharpsl.c
+++ b/drivers/mtd/nand/sharpsl.c
@@ -148,6 +148,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev)
/* Link the private data with the MTD structure */
mtd = nand_to_mtd(this);
mtd->dev.parent = &pdev->dev;
+ mtd_set_ooblayout(mtd, data->ecc_layout);
platform_set_drvdata(pdev, sharpsl);
@@ -170,7 +171,6 @@ static int sharpsl_nand_probe(struct platform_device *pdev)
this->ecc.bytes = 3;
this->ecc.strength = 1;
this->badblock_pattern = data->badblock_pattern;
- this->ecc.layout = data->ecc_layout;
this->ecc.hwctl = sharpsl_nand_enable_hwecc;
this->ecc.calculate = sharpsl_nand_calculate_ecc;
this->ecc.correct = nand_correct_data;
diff --git a/drivers/mtd/nand/sm_common.c b/drivers/mtd/nand/sm_common.c
index c514740f9a83..5939dff253c2 100644
--- a/drivers/mtd/nand/sm_common.c
+++ b/drivers/mtd/nand/sm_common.c
@@ -12,14 +12,47 @@
#include <linux/sizes.h>
#include "sm_common.h"
-static struct nand_ecclayout nand_oob_sm = {
- .eccbytes = 6,
- .eccpos = {8, 9, 10, 13, 14, 15},
- .oobfree = {
- {.offset = 0 , .length = 4}, /* reserved */
- {.offset = 6 , .length = 2}, /* LBA1 */
- {.offset = 11, .length = 2} /* LBA2 */
+static int oob_sm_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 1)
+ return -ERANGE;
+
+ oobregion->length = 3;
+ oobregion->offset = ((section + 1) * 8) - 3;
+
+ return 0;
+}
+
+static int oob_sm_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ switch (section) {
+ case 0:
+ /* reserved */
+ oobregion->offset = 0;
+ oobregion->length = 4;
+ break;
+ case 1:
+ /* LBA1 */
+ oobregion->offset = 6;
+ oobregion->length = 2;
+ break;
+ case 2:
+ /* LBA2 */
+ oobregion->offset = 11;
+ oobregion->length = 2;
+ break;
+ default:
+ return -ERANGE;
}
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops oob_sm_ops = {
+ .ecc = oob_sm_ooblayout_ecc,
+ .free = oob_sm_ooblayout_free,
};
/* NOTE: This layout is is not compatabable with SmartMedia, */
@@ -28,15 +61,43 @@ static struct nand_ecclayout nand_oob_sm = {
/* If you use smftl, it will bypass this and work correctly */
/* If you not, then you break SmartMedia compliance anyway */
-static struct nand_ecclayout nand_oob_sm_small = {
- .eccbytes = 3,
- .eccpos = {0, 1, 2},
- .oobfree = {
- {.offset = 3 , .length = 2}, /* reserved */
- {.offset = 6 , .length = 2}, /* LBA1 */
+static int oob_sm_small_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section)
+ return -ERANGE;
+
+ oobregion->length = 3;
+ oobregion->offset = 0;
+
+ return 0;
+}
+
+static int oob_sm_small_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ switch (section) {
+ case 0:
+ /* reserved */
+ oobregion->offset = 3;
+ oobregion->length = 2;
+ break;
+ case 1:
+ /* LBA1 */
+ oobregion->offset = 6;
+ oobregion->length = 2;
+ break;
+ default:
+ return -ERANGE;
}
-};
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops oob_sm_small_ops = {
+ .ecc = oob_sm_small_ooblayout_ecc,
+ .free = oob_sm_small_ooblayout_free,
+};
static int sm_block_markbad(struct mtd_info *mtd, loff_t ofs)
{
@@ -121,9 +182,9 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
/* ECC layout */
if (mtd->writesize == SM_SECTOR_SIZE)
- chip->ecc.layout = &nand_oob_sm;
+ mtd_set_ooblayout(mtd, &oob_sm_ops);
else if (mtd->writesize == SM_SMALL_PAGE)
- chip->ecc.layout = &nand_oob_sm_small;
+ mtd_set_ooblayout(mtd, &oob_sm_small_ops);
else
return -ENODEV;
diff --git a/drivers/mtd/nand/socrates_nand.c b/drivers/mtd/nand/socrates_nand.c
index e3305f9dd6fb..888fd314c62a 100644
--- a/drivers/mtd/nand/socrates_nand.c
+++ b/drivers/mtd/nand/socrates_nand.c
@@ -180,6 +180,7 @@ static int socrates_nand_probe(struct platform_device *ofdev)
nand_chip->dev_ready = socrates_nand_device_ready;
nand_chip->ecc.mode = NAND_ECC_SOFT; /* enable ECC */
+ nand_chip->ecc.algo = NAND_ECC_HAMMING;
/* TODO: I have no idea what real delay is. */
nand_chip->chip_delay = 20; /* 20us command delay time */
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index 1c03eee44f3d..a83a690688b4 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -30,7 +30,6 @@
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_gpio.h>
-#include <linux/of_mtd.h>
#include <linux/mtd/mtd.h>
#include <linux/mtd/nand.h>
#include <linux/mtd/partitions.h>
@@ -39,7 +38,7 @@
#include <linux/dmaengine.h>
#include <linux/gpio.h>
#include <linux/interrupt.h>
-#include <linux/io.h>
+#include <linux/iopoll.h>
#define NFC_REG_CTL 0x0000
#define NFC_REG_ST 0x0004
@@ -155,7 +154,7 @@
/* define bit use in NFC_ECC_ST */
#define NFC_ECC_ERR(x) BIT(x)
#define NFC_ECC_PAT_FOUND(x) BIT(x + 16)
-#define NFC_ECC_ERR_CNT(b, x) (((x) >> ((b) * 8)) & 0xff)
+#define NFC_ECC_ERR_CNT(b, x) (((x) >> (((b) % 4) * 8)) & 0xff)
#define NFC_DEFAULT_TIMEOUT_MS 1000
@@ -212,12 +211,9 @@ struct sunxi_nand_chip_sel {
* sunxi HW ECC infos: stores information related to HW ECC support
*
* @mode: the sunxi ECC mode field deduced from ECC requirements
- * @layout: the OOB layout depending on the ECC requirements and the
- * selected ECC mode
*/
struct sunxi_nand_hw_ecc {
int mode;
- struct nand_ecclayout layout;
};
/*
@@ -239,6 +235,10 @@ struct sunxi_nand_chip {
u32 timing_cfg;
u32 timing_ctl;
int selected;
+ int addr_cycles;
+ u32 addr[2];
+ int cmd_cycles;
+ u8 cmd[2];
int nsels;
struct sunxi_nand_chip_sel sels[0];
};
@@ -298,54 +298,71 @@ static irqreturn_t sunxi_nfc_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}
-static int sunxi_nfc_wait_int(struct sunxi_nfc *nfc, u32 flags,
- unsigned int timeout_ms)
+static int sunxi_nfc_wait_events(struct sunxi_nfc *nfc, u32 events,
+ bool use_polling, unsigned int timeout_ms)
{
- init_completion(&nfc->complete);
+ int ret;
- writel(flags, nfc->regs + NFC_REG_INT);
+ if (events & ~NFC_INT_MASK)
+ return -EINVAL;
if (!timeout_ms)
timeout_ms = NFC_DEFAULT_TIMEOUT_MS;
- if (!wait_for_completion_timeout(&nfc->complete,
- msecs_to_jiffies(timeout_ms))) {
- dev_err(nfc->dev, "wait interrupt timedout\n");
- return -ETIMEDOUT;
+ if (!use_polling) {
+ init_completion(&nfc->complete);
+
+ writel(events, nfc->regs + NFC_REG_INT);
+
+ ret = wait_for_completion_timeout(&nfc->complete,
+ msecs_to_jiffies(timeout_ms));
+
+ writel(0, nfc->regs + NFC_REG_INT);
+ } else {
+ u32 status;
+
+ ret = readl_poll_timeout(nfc->regs + NFC_REG_ST, status,
+ (status & events) == events, 1,
+ timeout_ms * 1000);
}
- return 0;
+ writel(events & NFC_INT_MASK, nfc->regs + NFC_REG_ST);
+
+ if (ret)
+ dev_err(nfc->dev, "wait interrupt timedout\n");
+
+ return ret;
}
static int sunxi_nfc_wait_cmd_fifo_empty(struct sunxi_nfc *nfc)
{
- unsigned long timeout = jiffies +
- msecs_to_jiffies(NFC_DEFAULT_TIMEOUT_MS);
+ u32 status;
+ int ret;
- do {
- if (!(readl(nfc->regs + NFC_REG_ST) & NFC_CMD_FIFO_STATUS))
- return 0;
- } while (time_before(jiffies, timeout));
+ ret = readl_poll_timeout(nfc->regs + NFC_REG_ST, status,
+ !(status & NFC_CMD_FIFO_STATUS), 1,
+ NFC_DEFAULT_TIMEOUT_MS * 1000);
+ if (ret)
+ dev_err(nfc->dev, "wait for empty cmd FIFO timedout\n");
- dev_err(nfc->dev, "wait for empty cmd FIFO timedout\n");
- return -ETIMEDOUT;
+ return ret;
}
static int sunxi_nfc_rst(struct sunxi_nfc *nfc)
{
- unsigned long timeout = jiffies +
- msecs_to_jiffies(NFC_DEFAULT_TIMEOUT_MS);
+ u32 ctl;
+ int ret;
writel(0, nfc->regs + NFC_REG_ECC_CTL);
writel(NFC_RESET, nfc->regs + NFC_REG_CTL);
- do {
- if (!(readl(nfc->regs + NFC_REG_CTL) & NFC_RESET))
- return 0;
- } while (time_before(jiffies, timeout));
+ ret = readl_poll_timeout(nfc->regs + NFC_REG_CTL, ctl,
+ !(ctl & NFC_RESET), 1,
+ NFC_DEFAULT_TIMEOUT_MS * 1000);
+ if (ret)
+ dev_err(nfc->dev, "wait for NAND controller reset timedout\n");
- dev_err(nfc->dev, "wait for NAND controller reset timedout\n");
- return -ETIMEDOUT;
+ return ret;
}
static int sunxi_nfc_dev_ready(struct mtd_info *mtd)
@@ -354,7 +371,6 @@ static int sunxi_nfc_dev_ready(struct mtd_info *mtd)
struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
struct sunxi_nand_rb *rb;
- unsigned long timeo = (sunxi_nand->nand.state == FL_ERASING ? 400 : 20);
int ret;
if (sunxi_nand->selected < 0)
@@ -366,12 +382,6 @@ static int sunxi_nfc_dev_ready(struct mtd_info *mtd)
case RB_NATIVE:
ret = !!(readl(nfc->regs + NFC_REG_ST) &
NFC_RB_STATE(rb->info.nativeid));
- if (ret)
- break;
-
- sunxi_nfc_wait_int(nfc, NFC_RB_B2R, timeo);
- ret = !!(readl(nfc->regs + NFC_REG_ST) &
- NFC_RB_STATE(rb->info.nativeid));
break;
case RB_GPIO:
ret = gpio_get_value(rb->info.gpio);
@@ -407,7 +417,7 @@ static void sunxi_nfc_select_chip(struct mtd_info *mtd, int chip)
sel = &sunxi_nand->sels[chip];
ctl |= NFC_CE_SEL(sel->cs) | NFC_EN |
- NFC_PAGE_SHIFT(nand->page_shift - 10);
+ NFC_PAGE_SHIFT(nand->page_shift);
if (sel->rb.type == RB_NONE) {
nand->dev_ready = NULL;
} else {
@@ -452,7 +462,7 @@ static void sunxi_nfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
tmp = NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD;
writel(tmp, nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_int(nfc, NFC_CMD_INT_FLAG, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
if (ret)
break;
@@ -487,7 +497,7 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
NFC_ACCESS_DIR;
writel(tmp, nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_int(nfc, NFC_CMD_INT_FLAG, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
if (ret)
break;
@@ -511,32 +521,54 @@ static void sunxi_nfc_cmd_ctrl(struct mtd_info *mtd, int dat,
struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
int ret;
- u32 tmp;
ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
if (ret)
return;
- if (ctrl & NAND_CTRL_CHANGE) {
- tmp = readl(nfc->regs + NFC_REG_CTL);
- if (ctrl & NAND_NCE)
- tmp |= NFC_CE_CTL;
- else
- tmp &= ~NFC_CE_CTL;
- writel(tmp, nfc->regs + NFC_REG_CTL);
- }
+ if (dat == NAND_CMD_NONE && (ctrl & NAND_NCE) &&
+ !(ctrl & (NAND_CLE | NAND_ALE))) {
+ u32 cmd = 0;
- if (dat == NAND_CMD_NONE)
- return;
+ if (!sunxi_nand->addr_cycles && !sunxi_nand->cmd_cycles)
+ return;
- if (ctrl & NAND_CLE) {
- writel(NFC_SEND_CMD1 | dat, nfc->regs + NFC_REG_CMD);
- } else {
- writel(dat, nfc->regs + NFC_REG_ADDR_LOW);
- writel(NFC_SEND_ADR, nfc->regs + NFC_REG_CMD);
+ if (sunxi_nand->cmd_cycles--)
+ cmd |= NFC_SEND_CMD1 | sunxi_nand->cmd[0];
+
+ if (sunxi_nand->cmd_cycles--) {
+ cmd |= NFC_SEND_CMD2;
+ writel(sunxi_nand->cmd[1],
+ nfc->regs + NFC_REG_RCMD_SET);
+ }
+
+ sunxi_nand->cmd_cycles = 0;
+
+ if (sunxi_nand->addr_cycles) {
+ cmd |= NFC_SEND_ADR |
+ NFC_ADR_NUM(sunxi_nand->addr_cycles);
+ writel(sunxi_nand->addr[0],
+ nfc->regs + NFC_REG_ADDR_LOW);
+ }
+
+ if (sunxi_nand->addr_cycles > 4)
+ writel(sunxi_nand->addr[1],
+ nfc->regs + NFC_REG_ADDR_HIGH);
+
+ writel(cmd, nfc->regs + NFC_REG_CMD);
+ sunxi_nand->addr[0] = 0;
+ sunxi_nand->addr[1] = 0;
+ sunxi_nand->addr_cycles = 0;
+ sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
}
- sunxi_nfc_wait_int(nfc, NFC_CMD_INT_FLAG, 0);
+ if (ctrl & NAND_CLE) {
+ sunxi_nand->cmd[sunxi_nand->cmd_cycles++] = dat;
+ } else if (ctrl & NAND_ALE) {
+ sunxi_nand->addr[sunxi_nand->addr_cycles / 4] |=
+ dat << ((sunxi_nand->addr_cycles % 4) * 8);
+ sunxi_nand->addr_cycles++;
+ }
}
/* These seed values have been extracted from Allwinner's BSP */
@@ -717,7 +749,8 @@ static void sunxi_nfc_hw_ecc_enable(struct mtd_info *mtd)
ecc_ctl = readl(nfc->regs + NFC_REG_ECC_CTL);
ecc_ctl &= ~(NFC_ECC_MODE_MSK | NFC_ECC_PIPELINE |
NFC_ECC_BLOCK_SIZE_MSK);
- ecc_ctl |= NFC_ECC_EN | NFC_ECC_MODE(data->mode) | NFC_ECC_EXCEPTION;
+ ecc_ctl |= NFC_ECC_EN | NFC_ECC_MODE(data->mode) | NFC_ECC_EXCEPTION |
+ NFC_ECC_PIPELINE;
writel(ecc_ctl, nfc->regs + NFC_REG_ECC_CTL);
}
@@ -739,18 +772,106 @@ static inline void sunxi_nfc_user_data_to_buf(u32 user_data, u8 *buf)
buf[3] = user_data >> 24;
}
+static inline u32 sunxi_nfc_buf_to_user_data(const u8 *buf)
+{
+ return buf[0] | (buf[1] << 8) | (buf[2] << 16) | (buf[3] << 24);
+}
+
+static void sunxi_nfc_hw_ecc_get_prot_oob_bytes(struct mtd_info *mtd, u8 *oob,
+ int step, bool bbm, int page)
+{
+ struct nand_chip *nand = mtd_to_nand(mtd);
+ struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+
+ sunxi_nfc_user_data_to_buf(readl(nfc->regs + NFC_REG_USER_DATA(step)),
+ oob);
+
+ /* De-randomize the Bad Block Marker. */
+ if (bbm && (nand->options & NAND_NEED_SCRAMBLING))
+ sunxi_nfc_randomize_bbm(mtd, page, oob);
+}
+
+static void sunxi_nfc_hw_ecc_set_prot_oob_bytes(struct mtd_info *mtd,
+ const u8 *oob, int step,
+ bool bbm, int page)
+{
+ struct nand_chip *nand = mtd_to_nand(mtd);
+ struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+ u8 user_data[4];
+
+ /* Randomize the Bad Block Marker. */
+ if (bbm && (nand->options & NAND_NEED_SCRAMBLING)) {
+ memcpy(user_data, oob, sizeof(user_data));
+ sunxi_nfc_randomize_bbm(mtd, page, user_data);
+ oob = user_data;
+ }
+
+ writel(sunxi_nfc_buf_to_user_data(oob),
+ nfc->regs + NFC_REG_USER_DATA(step));
+}
+
+static void sunxi_nfc_hw_ecc_update_stats(struct mtd_info *mtd,
+ unsigned int *max_bitflips, int ret)
+{
+ if (ret < 0) {
+ mtd->ecc_stats.failed++;
+ } else {
+ mtd->ecc_stats.corrected += ret;
+ *max_bitflips = max_t(unsigned int, *max_bitflips, ret);
+ }
+}
+
+static int sunxi_nfc_hw_ecc_correct(struct mtd_info *mtd, u8 *data, u8 *oob,
+ int step, bool *erased)
+{
+ struct nand_chip *nand = mtd_to_nand(mtd);
+ struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+ struct nand_ecc_ctrl *ecc = &nand->ecc;
+ u32 status, tmp;
+
+ *erased = false;
+
+ status = readl(nfc->regs + NFC_REG_ECC_ST);
+
+ if (status & NFC_ECC_ERR(step))
+ return -EBADMSG;
+
+ if (status & NFC_ECC_PAT_FOUND(step)) {
+ u8 pattern;
+
+ if (unlikely(!(readl(nfc->regs + NFC_REG_PAT_ID) & 0x1))) {
+ pattern = 0x0;
+ } else {
+ pattern = 0xff;
+ *erased = true;
+ }
+
+ if (data)
+ memset(data, pattern, ecc->size);
+
+ if (oob)
+ memset(oob, pattern, ecc->bytes + 4);
+
+ return 0;
+ }
+
+ tmp = readl(nfc->regs + NFC_REG_ECC_ERR_CNT(step));
+
+ return NFC_ECC_ERR_CNT(step, tmp);
+}
+
static int sunxi_nfc_hw_ecc_read_chunk(struct mtd_info *mtd,
u8 *data, int data_off,
u8 *oob, int oob_off,
int *cur_off,
unsigned int *max_bitflips,
- bool bbm, int page)
+ bool bbm, bool oob_required, int page)
{
struct nand_chip *nand = mtd_to_nand(mtd);
struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
struct nand_ecc_ctrl *ecc = &nand->ecc;
int raw_mode = 0;
- u32 status;
+ bool erased;
int ret;
if (*cur_off != data_off)
@@ -769,34 +890,19 @@ static int sunxi_nfc_hw_ecc_read_chunk(struct mtd_info *mtd,
writel(NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ECC_OP,
nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_int(nfc, NFC_CMD_INT_FLAG, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
sunxi_nfc_randomizer_disable(mtd);
if (ret)
return ret;
*cur_off = oob_off + ecc->bytes + 4;
- status = readl(nfc->regs + NFC_REG_ECC_ST);
- if (status & NFC_ECC_PAT_FOUND(0)) {
- u8 pattern = 0xff;
-
- if (unlikely(!(readl(nfc->regs + NFC_REG_PAT_ID) & 0x1)))
- pattern = 0x0;
-
- memset(data, pattern, ecc->size);
- memset(oob, pattern, ecc->bytes + 4);
-
+ ret = sunxi_nfc_hw_ecc_correct(mtd, data, oob_required ? oob : NULL, 0,
+ &erased);
+ if (erased)
return 1;
- }
-
- ret = NFC_ECC_ERR_CNT(0, readl(nfc->regs + NFC_REG_ECC_ERR_CNT(0)));
-
- memcpy_fromio(data, nfc->regs + NFC_RAM0_BASE, ecc->size);
-
- nand->cmdfunc(mtd, NAND_CMD_RNDOUT, oob_off, -1);
- sunxi_nfc_randomizer_read_buf(mtd, oob, ecc->bytes + 4, true, page);
- if (status & NFC_ECC_ERR(0)) {
+ if (ret < 0) {
/*
* Re-read the data with the randomizer disabled to identify
* bitflips in erased pages.
@@ -804,35 +910,34 @@ static int sunxi_nfc_hw_ecc_read_chunk(struct mtd_info *mtd,
if (nand->options & NAND_NEED_SCRAMBLING) {
nand->cmdfunc(mtd, NAND_CMD_RNDOUT, data_off, -1);
nand->read_buf(mtd, data, ecc->size);
- nand->cmdfunc(mtd, NAND_CMD_RNDOUT, oob_off, -1);
- nand->read_buf(mtd, oob, ecc->bytes + 4);
+ } else {
+ memcpy_fromio(data, nfc->regs + NFC_RAM0_BASE,
+ ecc->size);
}
+ nand->cmdfunc(mtd, NAND_CMD_RNDOUT, oob_off, -1);
+ nand->read_buf(mtd, oob, ecc->bytes + 4);
+
ret = nand_check_erased_ecc_chunk(data, ecc->size,
oob, ecc->bytes + 4,
NULL, 0, ecc->strength);
if (ret >= 0)
raw_mode = 1;
} else {
- /*
- * The engine protects 4 bytes of OOB data per chunk.
- * Retrieve the corrected OOB bytes.
- */
- sunxi_nfc_user_data_to_buf(readl(nfc->regs + NFC_REG_USER_DATA(0)),
- oob);
+ memcpy_fromio(data, nfc->regs + NFC_RAM0_BASE, ecc->size);
- /* De-randomize the Bad Block Marker. */
- if (bbm && nand->options & NAND_NEED_SCRAMBLING)
- sunxi_nfc_randomize_bbm(mtd, page, oob);
- }
+ if (oob_required) {
+ nand->cmdfunc(mtd, NAND_CMD_RNDOUT, oob_off, -1);
+ sunxi_nfc_randomizer_read_buf(mtd, oob, ecc->bytes + 4,
+ true, page);
- if (ret < 0) {
- mtd->ecc_stats.failed++;
- } else {
- mtd->ecc_stats.corrected += ret;
- *max_bitflips = max_t(unsigned int, *max_bitflips, ret);
+ sunxi_nfc_hw_ecc_get_prot_oob_bytes(mtd, oob, 0,
+ bbm, page);
+ }
}
+ sunxi_nfc_hw_ecc_update_stats(mtd, max_bitflips, ret);
+
return raw_mode;
}
@@ -848,7 +953,7 @@ static void sunxi_nfc_hw_ecc_read_extra_oob(struct mtd_info *mtd,
if (len <= 0)
return;
- if (*cur_off != offset)
+ if (!cur_off || *cur_off != offset)
nand->cmdfunc(mtd, NAND_CMD_RNDOUT,
offset + mtd->writesize, -1);
@@ -858,12 +963,8 @@ static void sunxi_nfc_hw_ecc_read_extra_oob(struct mtd_info *mtd,
sunxi_nfc_randomizer_read_buf(mtd, oob + offset, len,
false, page);
- *cur_off = mtd->oobsize + mtd->writesize;
-}
-
-static inline u32 sunxi_nfc_buf_to_user_data(const u8 *buf)
-{
- return buf[0] | (buf[1] << 8) | (buf[2] << 16) | (buf[3] << 24);
+ if (cur_off)
+ *cur_off = mtd->oobsize + mtd->writesize;
}
static int sunxi_nfc_hw_ecc_write_chunk(struct mtd_info *mtd,
@@ -882,19 +983,6 @@ static int sunxi_nfc_hw_ecc_write_chunk(struct mtd_info *mtd,
sunxi_nfc_randomizer_write_buf(mtd, data, ecc->size, false, page);
- /* Fill OOB data in */
- if ((nand->options & NAND_NEED_SCRAMBLING) && bbm) {
- u8 user_data[4];
-
- memcpy(user_data, oob, 4);
- sunxi_nfc_randomize_bbm(mtd, page, user_data);
- writel(sunxi_nfc_buf_to_user_data(user_data),
- nfc->regs + NFC_REG_USER_DATA(0));
- } else {
- writel(sunxi_nfc_buf_to_user_data(oob),
- nfc->regs + NFC_REG_USER_DATA(0));
- }
-
if (data_off + ecc->size != oob_off)
nand->cmdfunc(mtd, NAND_CMD_RNDIN, oob_off, -1);
@@ -903,11 +991,13 @@ static int sunxi_nfc_hw_ecc_write_chunk(struct mtd_info *mtd,
return ret;
sunxi_nfc_randomizer_enable(mtd);
+ sunxi_nfc_hw_ecc_set_prot_oob_bytes(mtd, oob, 0, bbm, page);
+
writel(NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD |
NFC_ACCESS_DIR | NFC_ECC_OP,
nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_int(nfc, NFC_CMD_INT_FLAG, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
sunxi_nfc_randomizer_disable(mtd);
if (ret)
return ret;
@@ -929,13 +1019,14 @@ static void sunxi_nfc_hw_ecc_write_extra_oob(struct mtd_info *mtd,
if (len <= 0)
return;
- if (*cur_off != offset)
+ if (!cur_off || *cur_off != offset)
nand->cmdfunc(mtd, NAND_CMD_RNDIN,
offset + mtd->writesize, -1);
sunxi_nfc_randomizer_write_buf(mtd, oob + offset, len, false, page);
- *cur_off = mtd->oobsize + mtd->writesize;
+ if (cur_off)
+ *cur_off = mtd->oobsize + mtd->writesize;
}
static int sunxi_nfc_hw_ecc_read_page(struct mtd_info *mtd,
@@ -958,7 +1049,7 @@ static int sunxi_nfc_hw_ecc_read_page(struct mtd_info *mtd,
ret = sunxi_nfc_hw_ecc_read_chunk(mtd, data, data_off, oob,
oob_off + mtd->writesize,
&cur_off, &max_bitflips,
- !i, page);
+ !i, oob_required, page);
if (ret < 0)
return ret;
else if (ret)
@@ -974,6 +1065,39 @@ static int sunxi_nfc_hw_ecc_read_page(struct mtd_info *mtd,
return max_bitflips;
}
+static int sunxi_nfc_hw_ecc_read_subpage(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ u32 data_offs, u32 readlen,
+ u8 *bufpoi, int page)
+{
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
+ int ret, i, cur_off = 0;
+ unsigned int max_bitflips = 0;
+
+ sunxi_nfc_hw_ecc_enable(mtd);
+
+ chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page);
+ for (i = data_offs / ecc->size;
+ i < DIV_ROUND_UP(data_offs + readlen, ecc->size); i++) {
+ int data_off = i * ecc->size;
+ int oob_off = i * (ecc->bytes + 4);
+ u8 *data = bufpoi + data_off;
+ u8 *oob = chip->oob_poi + oob_off;
+
+ ret = sunxi_nfc_hw_ecc_read_chunk(mtd, data, data_off,
+ oob,
+ oob_off + mtd->writesize,
+ &cur_off, &max_bitflips, !i,
+ false, page);
+ if (ret < 0)
+ return ret;
+ }
+
+ sunxi_nfc_hw_ecc_disable(mtd);
+
+ return max_bitflips;
+}
+
static int sunxi_nfc_hw_ecc_write_page(struct mtd_info *mtd,
struct nand_chip *chip,
const uint8_t *buf, int oob_required,
@@ -1026,7 +1150,9 @@ static int sunxi_nfc_hw_syndrome_ecc_read_page(struct mtd_info *mtd,
ret = sunxi_nfc_hw_ecc_read_chunk(mtd, data, data_off, oob,
oob_off, &cur_off,
- &max_bitflips, !i, page);
+ &max_bitflips, !i,
+ oob_required,
+ page);
if (ret < 0)
return ret;
else if (ret)
@@ -1074,6 +1200,40 @@ static int sunxi_nfc_hw_syndrome_ecc_write_page(struct mtd_info *mtd,
return 0;
}
+static int sunxi_nfc_hw_common_ecc_read_oob(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ int page)
+{
+ chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page);
+
+ chip->pagebuf = -1;
+
+ return chip->ecc.read_page(mtd, chip, chip->buffers->databuf, 1, page);
+}
+
+static int sunxi_nfc_hw_common_ecc_write_oob(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ int page)
+{
+ int ret, status;
+
+ chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0, page);
+
+ chip->pagebuf = -1;
+
+ memset(chip->buffers->databuf, 0xff, mtd->writesize);
+ ret = chip->ecc.write_page(mtd, chip, chip->buffers->databuf, 1, page);
+ if (ret)
+ return ret;
+
+ /* Send command to program the OOB data */
+ chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+
+ status = chip->waitfunc(mtd, chip);
+
+ return status & NAND_STATUS_FAIL ? -EIO : 0;
+}
+
static const s32 tWB_lut[] = {6, 12, 16, 20};
static const s32 tRHW_lut[] = {4, 8, 12, 20};
@@ -1101,6 +1261,7 @@ static int sunxi_nand_chip_set_timings(struct sunxi_nand_chip *chip,
struct sunxi_nfc *nfc = to_sunxi_nfc(chip->nand.controller);
u32 min_clk_period = 0;
s32 tWB, tADL, tWHR, tRHW, tCAD;
+ long real_clk_rate;
/* T1 <=> tCLS */
if (timings->tCLS_min > min_clk_period)
@@ -1163,6 +1324,18 @@ static int sunxi_nand_chip_set_timings(struct sunxi_nand_chip *chip,
min_clk_period = DIV_ROUND_UP(timings->tWC_min, 2);
/* T16 - T19 + tCAD */
+ if (timings->tWB_max > (min_clk_period * 20))
+ min_clk_period = DIV_ROUND_UP(timings->tWB_max, 20);
+
+ if (timings->tADL_min > (min_clk_period * 32))
+ min_clk_period = DIV_ROUND_UP(timings->tADL_min, 32);
+
+ if (timings->tWHR_min > (min_clk_period * 32))
+ min_clk_period = DIV_ROUND_UP(timings->tWHR_min, 32);
+
+ if (timings->tRHW_min > (min_clk_period * 20))
+ min_clk_period = DIV_ROUND_UP(timings->tRHW_min, 20);
+
tWB = sunxi_nand_lookup_timing(tWB_lut, timings->tWB_max,
min_clk_period);
if (tWB < 0) {
@@ -1198,23 +1371,26 @@ static int sunxi_nand_chip_set_timings(struct sunxi_nand_chip *chip,
/* TODO: A83 has some more bits for CDQSS, CS, CLHZ, CCS, WC */
chip->timing_cfg = NFC_TIMING_CFG(tWB, tADL, tWHR, tRHW, tCAD);
- /*
- * ONFI specification 3.1, paragraph 4.15.2 dictates that EDO data
- * output cycle timings shall be used if the host drives tRC less than
- * 30 ns.
- */
- chip->timing_ctl = (timings->tRC_min < 30000) ? NFC_TIMING_CTL_EDO : 0;
-
/* Convert min_clk_period from picoseconds to nanoseconds */
min_clk_period = DIV_ROUND_UP(min_clk_period, 1000);
/*
- * Convert min_clk_period into a clk frequency, then get the
- * appropriate rate for the NAND controller IP given this formula
- * (specified in the datasheet):
- * nand clk_rate = 2 * min_clk_rate
+ * Unlike what is stated in Allwinner datasheet, the clk_rate should
+ * be set to (1 / min_clk_period), and not (2 / min_clk_period).
+ * This new formula was verified with a scope and validated by
+ * Allwinner engineers.
*/
- chip->clk_rate = (2 * NSEC_PER_SEC) / min_clk_period;
+ chip->clk_rate = NSEC_PER_SEC / min_clk_period;
+ real_clk_rate = clk_round_rate(nfc->mod_clk, chip->clk_rate);
+
+ /*
+ * ONFI specification 3.1, paragraph 4.15.2 dictates that EDO data
+ * output cycle timings shall be used if the host drives tRC less than
+ * 30 ns.
+ */
+ min_clk_period = NSEC_PER_SEC / real_clk_rate;
+ chip->timing_ctl = ((min_clk_period * 2) < 30) ?
+ NFC_TIMING_CTL_EDO : 0;
return 0;
}
@@ -1257,6 +1433,57 @@ static int sunxi_nand_chip_init_timings(struct sunxi_nand_chip *chip,
return sunxi_nand_chip_set_timings(chip, timings);
}
+static int sunxi_nand_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &nand->ecc;
+
+ if (section >= ecc->steps)
+ return -ERANGE;
+
+ oobregion->offset = section * (ecc->bytes + 4) + 4;
+ oobregion->length = ecc->bytes;
+
+ return 0;
+}
+
+static int sunxi_nand_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *nand = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &nand->ecc;
+
+ if (section > ecc->steps)
+ return -ERANGE;
+
+ /*
+ * The first 2 bytes are used for BB markers, hence we
+ * only have 2 bytes available in the first user data
+ * section.
+ */
+ if (!section && ecc->mode == NAND_ECC_HW) {
+ oobregion->offset = 2;
+ oobregion->length = 2;
+
+ return 0;
+ }
+
+ oobregion->offset = section * (ecc->bytes + 4);
+
+ if (section < ecc->steps)
+ oobregion->length = 4;
+ else
+ oobregion->offset = mtd->oobsize - oobregion->offset;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops sunxi_nand_ooblayout_ops = {
+ .ecc = sunxi_nand_ooblayout_ecc,
+ .free = sunxi_nand_ooblayout_free,
+};
+
static int sunxi_nand_hw_common_ecc_ctrl_init(struct mtd_info *mtd,
struct nand_ecc_ctrl *ecc,
struct device_node *np)
@@ -1266,7 +1493,6 @@ static int sunxi_nand_hw_common_ecc_ctrl_init(struct mtd_info *mtd,
struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
struct sunxi_nand_hw_ecc *data;
- struct nand_ecclayout *layout;
int nsectors;
int ret;
int i;
@@ -1295,7 +1521,6 @@ static int sunxi_nand_hw_common_ecc_ctrl_init(struct mtd_info *mtd,
/* HW ECC always work with even numbers of ECC bytes */
ecc->bytes = ALIGN(ecc->bytes, 2);
- layout = &data->layout;
nsectors = mtd->writesize / ecc->size;
if (mtd->oobsize < ((ecc->bytes + 4) * nsectors)) {
@@ -1303,9 +1528,9 @@ static int sunxi_nand_hw_common_ecc_ctrl_init(struct mtd_info *mtd,
goto err;
}
- layout->eccbytes = (ecc->bytes * nsectors);
-
- ecc->layout = layout;
+ ecc->read_oob = sunxi_nfc_hw_common_ecc_read_oob;
+ ecc->write_oob = sunxi_nfc_hw_common_ecc_write_oob;
+ mtd_set_ooblayout(mtd, &sunxi_nand_ooblayout_ops);
ecc->priv = data;
return 0;
@@ -1325,9 +1550,6 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct mtd_info *mtd,
struct nand_ecc_ctrl *ecc,
struct device_node *np)
{
- struct nand_ecclayout *layout;
- int nsectors;
- int i, j;
int ret;
ret = sunxi_nand_hw_common_ecc_ctrl_init(mtd, ecc, np);
@@ -1336,40 +1558,9 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct mtd_info *mtd,
ecc->read_page = sunxi_nfc_hw_ecc_read_page;
ecc->write_page = sunxi_nfc_hw_ecc_write_page;
- layout = ecc->layout;
- nsectors = mtd->writesize / ecc->size;
-
- for (i = 0; i < nsectors; i++) {
- if (i) {
- layout->oobfree[i].offset =
- layout->oobfree[i - 1].offset +
- layout->oobfree[i - 1].length +
- ecc->bytes;
- layout->oobfree[i].length = 4;
- } else {
- /*
- * The first 2 bytes are used for BB markers, hence we
- * only have 2 bytes available in the first user data
- * section.
- */
- layout->oobfree[i].length = 2;
- layout->oobfree[i].offset = 2;
- }
-
- for (j = 0; j < ecc->bytes; j++)
- layout->eccpos[(ecc->bytes * i) + j] =
- layout->oobfree[i].offset +
- layout->oobfree[i].length + j;
- }
-
- if (mtd->oobsize > (ecc->bytes + 4) * nsectors) {
- layout->oobfree[nsectors].offset =
- layout->oobfree[nsectors - 1].offset +
- layout->oobfree[nsectors - 1].length +
- ecc->bytes;
- layout->oobfree[nsectors].length = mtd->oobsize -
- ((ecc->bytes + 4) * nsectors);
- }
+ ecc->read_oob_raw = nand_read_oob_std;
+ ecc->write_oob_raw = nand_write_oob_std;
+ ecc->read_subpage = sunxi_nfc_hw_ecc_read_subpage;
return 0;
}
@@ -1378,9 +1569,6 @@ static int sunxi_nand_hw_syndrome_ecc_ctrl_init(struct mtd_info *mtd,
struct nand_ecc_ctrl *ecc,
struct device_node *np)
{
- struct nand_ecclayout *layout;
- int nsectors;
- int i;
int ret;
ret = sunxi_nand_hw_common_ecc_ctrl_init(mtd, ecc, np);
@@ -1390,15 +1578,8 @@ static int sunxi_nand_hw_syndrome_ecc_ctrl_init(struct mtd_info *mtd,
ecc->prepad = 4;
ecc->read_page = sunxi_nfc_hw_syndrome_ecc_read_page;
ecc->write_page = sunxi_nfc_hw_syndrome_ecc_write_page;
-
- layout = ecc->layout;
- nsectors = mtd->writesize / ecc->size;
-
- for (i = 0; i < (ecc->bytes * nsectors); i++)
- layout->eccpos[i] = i;
-
- layout->oobfree[0].length = mtd->oobsize - i;
- layout->oobfree[0].offset = i;
+ ecc->read_oob_raw = nand_read_oob_syndrome;
+ ecc->write_oob_raw = nand_write_oob_syndrome;
return 0;
}
@@ -1411,7 +1592,6 @@ static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
sunxi_nand_hw_common_ecc_ctrl_cleanup(ecc);
break;
case NAND_ECC_NONE:
- kfree(ecc->layout);
default:
break;
}
@@ -1432,8 +1612,6 @@ static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
return -EINVAL;
switch (ecc->mode) {
- case NAND_ECC_SOFT_BCH:
- break;
case NAND_ECC_HW:
ret = sunxi_nand_hw_ecc_ctrl_init(mtd, ecc, np);
if (ret)
@@ -1445,10 +1623,6 @@ static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
return ret;
break;
case NAND_ECC_NONE:
- ecc->layout = kzalloc(sizeof(*ecc->layout), GFP_KERNEL);
- if (!ecc->layout)
- return -ENOMEM;
- ecc->layout->oobfree[0].length = mtd->oobsize;
case NAND_ECC_SOFT:
break;
default:
@@ -1536,21 +1710,6 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
}
}
- timings = onfi_async_timing_mode_to_sdr_timings(0);
- if (IS_ERR(timings)) {
- ret = PTR_ERR(timings);
- dev_err(dev,
- "could not retrieve timings for ONFI mode 0: %d\n",
- ret);
- return ret;
- }
-
- ret = sunxi_nand_chip_set_timings(chip, timings);
- if (ret) {
- dev_err(dev, "could not configure chip timings: %d\n", ret);
- return ret;
- }
-
nand = &chip->nand;
/* Default tR value specified in the ONFI spec (chapter 4.15.1) */
nand->chip_delay = 200;
@@ -1570,6 +1729,21 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
mtd = nand_to_mtd(nand);
mtd->dev.parent = dev;
+ timings = onfi_async_timing_mode_to_sdr_timings(0);
+ if (IS_ERR(timings)) {
+ ret = PTR_ERR(timings);
+ dev_err(dev,
+ "could not retrieve timings for ONFI mode 0: %d\n",
+ ret);
+ return ret;
+ }
+
+ ret = sunxi_nand_chip_set_timings(chip, timings);
+ if (ret) {
+ dev_err(dev, "could not configure chip timings: %d\n", ret);
+ return ret;
+ }
+
ret = nand_scan_ident(mtd, nsels, NULL);
if (ret)
return ret;
@@ -1580,6 +1754,8 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
if (nand->options & NAND_NEED_SCRAMBLING)
nand->options |= NAND_NO_SUBPAGE_WRITE;
+ nand->options |= NAND_SUBPAGE_READ;
+
ret = sunxi_nand_chip_init_timings(chip, np);
if (ret) {
dev_err(dev, "could not configure chip timings: %d\n", ret);
@@ -1728,6 +1904,8 @@ static int sunxi_nfc_remove(struct platform_device *pdev)
struct sunxi_nfc *nfc = platform_get_drvdata(pdev);
sunxi_nand_chips_cleanup(nfc);
+ clk_disable_unprepare(nfc->mod_clk);
+ clk_disable_unprepare(nfc->ahb_clk);
return 0;
}
diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c
index 293feb19b0b1..3ad514c44dcb 100644
--- a/drivers/mtd/nand/vf610_nfc.c
+++ b/drivers/mtd/nand/vf610_nfc.c
@@ -33,7 +33,6 @@
#include <linux/mtd/mtd.h>
#include <linux/mtd/nand.h>
#include <linux/mtd/partitions.h>
-#include <linux/of_mtd.h>
#include <linux/of_device.h>
#include <linux/pinctrl/consumer.h>
#include <linux/platform_device.h>
@@ -175,34 +174,6 @@ static inline struct vf610_nfc *mtd_to_nfc(struct mtd_info *mtd)
return container_of(mtd_to_nand(mtd), struct vf610_nfc, chip);
}
-static struct nand_ecclayout vf610_nfc_ecc45 = {
- .eccbytes = 45,
- .eccpos = {19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63},
- .oobfree = {
- {.offset = 2,
- .length = 17} }
-};
-
-static struct nand_ecclayout vf610_nfc_ecc60 = {
- .eccbytes = 60,
- .eccpos = { 4, 5, 6, 7, 8, 9, 10, 11,
- 12, 13, 14, 15, 16, 17, 18, 19,
- 20, 21, 22, 23, 24, 25, 26, 27,
- 28, 29, 30, 31, 32, 33, 34, 35,
- 36, 37, 38, 39, 40, 41, 42, 43,
- 44, 45, 46, 47, 48, 49, 50, 51,
- 52, 53, 54, 55, 56, 57, 58, 59,
- 60, 61, 62, 63 },
- .oobfree = {
- {.offset = 2,
- .length = 2} }
-};
-
static inline u32 vf610_nfc_read(struct vf610_nfc *nfc, uint reg)
{
return readl(nfc->regs + reg);
@@ -781,14 +752,16 @@ static int vf610_nfc_probe(struct platform_device *pdev)
if (mtd->oobsize > 64)
mtd->oobsize = 64;
+ /*
+ * mtd->ecclayout is not specified here because we're using the
+ * default large page ECC layout defined in NAND core.
+ */
if (chip->ecc.strength == 32) {
nfc->ecc_mode = ECC_60_BYTE;
chip->ecc.bytes = 60;
- chip->ecc.layout = &vf610_nfc_ecc60;
} else if (chip->ecc.strength == 24) {
nfc->ecc_mode = ECC_45_BYTE;
chip->ecc.bytes = 45;
- chip->ecc.layout = &vf610_nfc_ecc45;
} else {
dev_err(nfc->dev, "Unsupported ECC strength\n");
err = -ENXIO;
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index af28bb3ae7cf..a4b029a417f0 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -68,21 +68,33 @@ MODULE_PARM_DESC(otp, "Corresponding behaviour of OneNAND in OTP"
* flexonenand_oob_128 - oob info for Flex-Onenand with 4KB page
* For now, we expose only 64 out of 80 ecc bytes
*/
-static struct nand_ecclayout flexonenand_oob_128 = {
- .eccbytes = 64,
- .eccpos = {
- 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
- 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
- 70, 71, 72, 73, 74, 75, 76, 77, 78, 79,
- 86, 87, 88, 89, 90, 91, 92, 93, 94, 95,
- 102, 103, 104, 105
- },
- .oobfree = {
- {2, 4}, {18, 4}, {34, 4}, {50, 4},
- {66, 4}, {82, 4}, {98, 4}, {114, 4}
- }
+static int flexonenand_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 7)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 6;
+ oobregion->length = 10;
+
+ return 0;
+}
+
+static int flexonenand_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 7)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 2;
+ oobregion->length = 4;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops flexonenand_ooblayout_ops = {
+ .ecc = flexonenand_ooblayout_ecc,
+ .free = flexonenand_ooblayout_free,
};
/*
@@ -91,56 +103,77 @@ static struct nand_ecclayout flexonenand_oob_128 = {
* Based on specification:
* 4Gb M-die OneNAND Flash (KFM4G16Q4M, KFN8G16Q4M). Rev. 1.3, Apr. 2010
*
- * For eccpos we expose only 64 bytes out of 72 (see struct nand_ecclayout)
- *
- * oobfree uses the spare area fields marked as
- * "Managed by internal ECC logic for Logical Sector Number area"
*/
-static struct nand_ecclayout onenand_oob_128 = {
- .eccbytes = 64,
- .eccpos = {
- 7, 8, 9, 10, 11, 12, 13, 14, 15,
- 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 39, 40, 41, 42, 43, 44, 45, 46, 47,
- 55, 56, 57, 58, 59, 60, 61, 62, 63,
- 71, 72, 73, 74, 75, 76, 77, 78, 79,
- 87, 88, 89, 90, 91, 92, 93, 94, 95,
- 103, 104, 105, 106, 107, 108, 109, 110, 111,
- 119
- },
- .oobfree = {
- {2, 3}, {18, 3}, {34, 3}, {50, 3},
- {66, 3}, {82, 3}, {98, 3}, {114, 3}
- }
+static int onenand_ooblayout_128_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 7)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 7;
+ oobregion->length = 9;
+
+ return 0;
+}
+
+static int onenand_ooblayout_128_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section >= 8)
+ return -ERANGE;
+
+ /*
+ * free bytes are using the spare area fields marked as
+ * "Managed by internal ECC logic for Logical Sector Number area"
+ */
+ oobregion->offset = (section * 16) + 2;
+ oobregion->length = 3;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops onenand_oob_128_ooblayout_ops = {
+ .ecc = onenand_ooblayout_128_ecc,
+ .free = onenand_ooblayout_128_free,
};
/**
- * onenand_oob_64 - oob info for large (2KB) page
+ * onenand_oob_32_64 - oob info for large (2KB) page
*/
-static struct nand_ecclayout onenand_oob_64 = {
- .eccbytes = 20,
- .eccpos = {
- 8, 9, 10, 11, 12,
- 24, 25, 26, 27, 28,
- 40, 41, 42, 43, 44,
- 56, 57, 58, 59, 60,
- },
- .oobfree = {
- {2, 3}, {14, 2}, {18, 3}, {30, 2},
- {34, 3}, {46, 2}, {50, 3}, {62, 2}
+static int onenand_ooblayout_32_64_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 3)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 8;
+ oobregion->length = 5;
+
+ return 0;
+}
+
+static int onenand_ooblayout_32_64_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ int sections = (mtd->oobsize / 32) * 2;
+
+ if (section >= sections)
+ return -ERANGE;
+
+ if (section & 1) {
+ oobregion->offset = ((section - 1) * 16) + 14;
+ oobregion->length = 2;
+ } else {
+ oobregion->offset = (section * 16) + 2;
+ oobregion->length = 3;
}
-};
-/**
- * onenand_oob_32 - oob info for middle (1KB) page
- */
-static struct nand_ecclayout onenand_oob_32 = {
- .eccbytes = 10,
- .eccpos = {
- 8, 9, 10, 11, 12,
- 24, 25, 26, 27, 28,
- },
- .oobfree = { {2, 3}, {14, 2}, {18, 3}, {30, 2} }
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops onenand_oob_32_64_ooblayout_ops = {
+ .ecc = onenand_ooblayout_32_64_ecc,
+ .free = onenand_ooblayout_32_64_free,
};
static const unsigned char ffchars[] = {
@@ -1024,34 +1057,15 @@ static int onenand_transfer_auto_oob(struct mtd_info *mtd, uint8_t *buf, int col
int thislen)
{
struct onenand_chip *this = mtd->priv;
- struct nand_oobfree *free;
- int readcol = column;
- int readend = column + thislen;
- int lastgap = 0;
- unsigned int i;
- uint8_t *oob_buf = this->oob_buf;
-
- free = this->ecclayout->oobfree;
- for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES && free->length; i++, free++) {
- if (readcol >= lastgap)
- readcol += free->offset - lastgap;
- if (readend >= lastgap)
- readend += free->offset - lastgap;
- lastgap = free->offset + free->length;
- }
- this->read_bufferram(mtd, ONENAND_SPARERAM, oob_buf, 0, mtd->oobsize);
- free = this->ecclayout->oobfree;
- for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES && free->length; i++, free++) {
- int free_end = free->offset + free->length;
- if (free->offset < readend && free_end > readcol) {
- int st = max_t(int,free->offset,readcol);
- int ed = min_t(int,free_end,readend);
- int n = ed - st;
- memcpy(buf, oob_buf + st, n);
- buf += n;
- } else if (column == 0)
- break;
- }
+ int ret;
+
+ this->read_bufferram(mtd, ONENAND_SPARERAM, this->oob_buf, 0,
+ mtd->oobsize);
+ ret = mtd_ooblayout_get_databytes(mtd, buf, this->oob_buf,
+ column, thislen);
+ if (ret)
+ return ret;
+
return 0;
}
@@ -1808,34 +1822,7 @@ static int onenand_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
static int onenand_fill_auto_oob(struct mtd_info *mtd, u_char *oob_buf,
const u_char *buf, int column, int thislen)
{
- struct onenand_chip *this = mtd->priv;
- struct nand_oobfree *free;
- int writecol = column;
- int writeend = column + thislen;
- int lastgap = 0;
- unsigned int i;
-
- free = this->ecclayout->oobfree;
- for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES && free->length; i++, free++) {
- if (writecol >= lastgap)
- writecol += free->offset - lastgap;
- if (writeend >= lastgap)
- writeend += free->offset - lastgap;
- lastgap = free->offset + free->length;
- }
- free = this->ecclayout->oobfree;
- for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES && free->length; i++, free++) {
- int free_end = free->offset + free->length;
- if (free->offset < writeend && free_end > writecol) {
- int st = max_t(int,free->offset,writecol);
- int ed = min_t(int,free_end,writeend);
- int n = ed - st;
- memcpy(oob_buf + st, buf, n);
- buf += n;
- } else if (column == 0)
- break;
- }
- return 0;
+ return mtd_ooblayout_set_databytes(mtd, buf, oob_buf, column, thislen);
}
/**
@@ -4003,22 +3990,22 @@ int onenand_scan(struct mtd_info *mtd, int maxchips)
switch (mtd->oobsize) {
case 128:
if (FLEXONENAND(this)) {
- this->ecclayout = &flexonenand_oob_128;
+ mtd_set_ooblayout(mtd, &flexonenand_ooblayout_ops);
mtd->subpage_sft = 0;
} else {
- this->ecclayout = &onenand_oob_128;
+ mtd_set_ooblayout(mtd, &onenand_oob_128_ooblayout_ops);
mtd->subpage_sft = 2;
}
if (ONENAND_IS_NOP_1(this))
mtd->subpage_sft = 0;
break;
case 64:
- this->ecclayout = &onenand_oob_64;
+ mtd_set_ooblayout(mtd, &onenand_oob_32_64_ooblayout_ops);
mtd->subpage_sft = 2;
break;
case 32:
- this->ecclayout = &onenand_oob_32;
+ mtd_set_ooblayout(mtd, &onenand_oob_32_64_ooblayout_ops);
mtd->subpage_sft = 1;
break;
@@ -4027,7 +4014,7 @@ int onenand_scan(struct mtd_info *mtd, int maxchips)
__func__, mtd->oobsize);
mtd->subpage_sft = 0;
/* To prevent kernel oops */
- this->ecclayout = &onenand_oob_32;
+ mtd_set_ooblayout(mtd, &onenand_oob_32_64_ooblayout_ops);
break;
}
@@ -4037,12 +4024,12 @@ int onenand_scan(struct mtd_info *mtd, int maxchips)
* The number of bytes available for a client to place data into
* the out of band area
*/
- mtd->oobavail = 0;
- for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES &&
- this->ecclayout->oobfree[i].length; i++)
- mtd->oobavail += this->ecclayout->oobfree[i].length;
+ ret = mtd_ooblayout_count_freebytes(mtd);
+ if (ret < 0)
+ ret = 0;
+
+ mtd->oobavail = ret;
- mtd->ecclayout = this->ecclayout;
mtd->ecc_strength = 1;
/* Fill in remaining MTD driver data */
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 157841dc3e99..c52e45594bfd 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -832,6 +832,7 @@ static const struct flash_info spi_nor_ids[] = {
/* GigaDevice */
{ "gd25q32", INFO(0xc84016, 0, 64 * 1024, 64, SECT_4K) },
{ "gd25q64", INFO(0xc84017, 0, 64 * 1024, 128, SECT_4K) },
+ { "gd25lq64c", INFO(0xc86017, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
{ "gd25q128", INFO(0xc84018, 0, 64 * 1024, 256, SECT_4K) },
/* Intel/Numonyx -- xxxs33b */
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index a7d1febf667a..ef3618299494 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -149,6 +149,8 @@ static struct device_attribute dev_bgt_enabled =
__ATTR(bgt_enabled, S_IRUGO, dev_attribute_show, NULL);
static struct device_attribute dev_mtd_num =
__ATTR(mtd_num, S_IRUGO, dev_attribute_show, NULL);
+static struct device_attribute dev_ro_mode =
+ __ATTR(ro_mode, S_IRUGO, dev_attribute_show, NULL);
/**
* ubi_volume_notify - send a volume change notification.
@@ -385,6 +387,8 @@ static ssize_t dev_attribute_show(struct device *dev,
ret = sprintf(buf, "%d\n", ubi->thread_enabled);
else if (attr == &dev_mtd_num)
ret = sprintf(buf, "%d\n", ubi->mtd->index);
+ else if (attr == &dev_ro_mode)
+ ret = sprintf(buf, "%d\n", ubi->ro_mode);
else
ret = -EINVAL;
@@ -404,6 +408,7 @@ static struct attribute *ubi_dev_attrs[] = {
&dev_min_io_size.attr,
&dev_bgt_enabled.attr,
&dev_mtd_num.attr,
+ &dev_ro_mode.attr,
NULL
};
ATTRIBUTE_GROUPS(ubi_dev);
@@ -1142,11 +1147,17 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway)
*/
static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev)
{
- struct kstat stat;
int err, minor;
+ struct path path;
+ struct kstat stat;
/* Probably this is an MTD character device node path */
- err = vfs_stat(mtd_dev, &stat);
+ err = kern_path(mtd_dev, LOOKUP_FOLLOW, &path);
+ if (err)
+ return ERR_PTR(err);
+
+ err = vfs_getattr(&path, &stat);
+ path_put(&path);
if (err)
return ERR_PTR(err);
@@ -1155,6 +1166,7 @@ static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev)
return ERR_PTR(-EINVAL);
minor = MINOR(stat.rdev);
+
if (minor & 1)
/*
* Just do not think the "/dev/mtdrX" devices support is need,
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index c4cb15a3098c..f101a4985a7c 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -352,7 +352,8 @@ static ssize_t dfs_file_write(struct file *file, const char __user *user_buf,
} else if (dent == d->dfs_emulate_power_cut) {
if (kstrtoint(buf, 0, &val) != 0)
count = -EINVAL;
- d->emulate_power_cut = val;
+ else
+ d->emulate_power_cut = val;
goto out;
}
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 5b9834cf2820..ebf517271d29 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -426,8 +426,25 @@ retry:
pnum, vol_id, lnum);
err = -EBADMSG;
} else {
- err = -EINVAL;
- ubi_ro_mode(ubi);
+ /*
+ * Ending up here in the non-Fastmap case
+ * is a clear bug as the VID header had to
+ * be present at scan time to have it referenced.
+ * With fastmap the story is more complicated.
+ * Fastmap has the mapping info without the need
+ * of a full scan. So the LEB could have been
+ * unmapped, Fastmap cannot know this and keeps
+ * the LEB referenced.
+ * This is valid and works as the layer above UBI
+ * has to do bookkeeping about used/referenced
+ * LEBs in any case.
+ */
+ if (ubi->fast_attach) {
+ err = -EBADMSG;
+ } else {
+ err = -EINVAL;
+ ubi_ro_mode(ubi);
+ }
}
}
goto out_free;
@@ -558,6 +575,7 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0;
struct ubi_volume *vol = ubi->volumes[idx];
struct ubi_vid_hdr *vid_hdr;
+ uint32_t crc;
vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
if (!vid_hdr)
@@ -582,14 +600,8 @@ retry:
goto out_put;
}
- vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
- err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
- if (err) {
- up_read(&ubi->fm_eba_sem);
- goto write_error;
- }
+ ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
- data_size = offset + len;
mutex_lock(&ubi->buf_mutex);
memset(ubi->peb_buf + offset, 0xFF, len);
@@ -604,6 +616,19 @@ retry:
memcpy(ubi->peb_buf + offset, buf, len);
+ data_size = offset + len;
+ crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size);
+ vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+ vid_hdr->copy_flag = 1;
+ vid_hdr->data_size = cpu_to_be32(data_size);
+ vid_hdr->data_crc = cpu_to_be32(crc);
+ err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
+ if (err) {
+ mutex_unlock(&ubi->buf_mutex);
+ up_read(&ubi->fm_eba_sem);
+ goto write_error;
+ }
+
err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size);
if (err) {
mutex_unlock(&ubi->buf_mutex);
@@ -1202,32 +1227,6 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
}
cond_resched();
-
- /*
- * We've written the data and are going to read it back to make
- * sure it was written correctly.
- */
- memset(ubi->peb_buf, 0xFF, aldata_size);
- err = ubi_io_read_data(ubi, ubi->peb_buf, to, 0, aldata_size);
- if (err) {
- if (err != UBI_IO_BITFLIPS) {
- ubi_warn(ubi, "error %d while reading data back from PEB %d",
- err, to);
- if (is_error_sane(err))
- err = MOVE_TARGET_RD_ERR;
- } else
- err = MOVE_TARGET_BITFLIPS;
- goto out_unlock_buf;
- }
-
- cond_resched();
-
- if (crc != crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size)) {
- ubi_warn(ubi, "read data back from PEB %d and it is different",
- to);
- err = -EINVAL;
- goto out_unlock_buf;
- }
}
ubi_assert(vol->eba_tbl[lnum] == from);
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 263b439e21a8..990898b9dc72 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -1058,6 +1058,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
ubi_msg(ubi, "fastmap WL pool size: %d",
ubi->fm_wl_pool.max_size);
ubi->fm_disabled = 0;
+ ubi->fast_attach = 1;
ubi_free_vid_hdr(ubi, vh);
kfree(ech);
diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c
index 437757c89b9e..a9e2cef7c95c 100644
--- a/drivers/mtd/ubi/kapi.c
+++ b/drivers/mtd/ubi/kapi.c
@@ -302,6 +302,7 @@ EXPORT_SYMBOL_GPL(ubi_open_volume_nm);
struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode)
{
int error, ubi_num, vol_id;
+ struct path path;
struct kstat stat;
dbg_gen("open volume %s, mode %d", pathname, mode);
@@ -309,7 +310,12 @@ struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode)
if (!pathname || !*pathname)
return ERR_PTR(-EINVAL);
- error = vfs_stat(pathname, &stat);
+ error = kern_path(pathname, LOOKUP_FOLLOW, &path);
+ if (error)
+ return ERR_PTR(error);
+
+ error = vfs_getattr(&path, &stat);
+ path_put(&path);
if (error)
return ERR_PTR(error);
@@ -705,7 +711,7 @@ int ubi_leb_map(struct ubi_volume_desc *desc, int lnum)
struct ubi_volume *vol = desc->vol;
struct ubi_device *ubi = vol->ubi;
- dbg_gen("unmap LEB %d:%d", vol->vol_id, lnum);
+ dbg_gen("map LEB %d:%d", vol->vol_id, lnum);
if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME)
return -EROFS;
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index dadc6a9d5755..61d4e99755a4 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -466,6 +466,7 @@ struct ubi_debug_info {
* @fm_eba_sem: allows ubi_update_fastmap() to block EBA table changes
* @fm_work: fastmap work queue
* @fm_work_scheduled: non-zero if fastmap work was scheduled
+ * @fast_attach: non-zero if UBI was attached by fastmap
*
* @used: RB-tree of used physical eraseblocks
* @erroneous: RB-tree of erroneous used physical eraseblocks
@@ -574,6 +575,7 @@ struct ubi_device {
size_t fm_size;
struct work_struct fm_work;
int fm_work_scheduled;
+ int fast_attach;
/* Wear-leveling sub-system's stuff */
struct rb_root used;
diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c
index 1ae17bb9b889..10059dfdc1b6 100644
--- a/drivers/mtd/ubi/vmt.c
+++ b/drivers/mtd/ubi/vmt.c
@@ -405,7 +405,7 @@ int ubi_remove_volume(struct ubi_volume_desc *desc, int no_vtbl)
if (!no_vtbl)
self_check_volumes(ubi);
- return err;
+ return 0;
out_err:
ubi_err(ubi, "cannot remove volume %d, error %d", vol_id, err);
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 17ec948ac40e..959c7b12e0b1 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1534,6 +1534,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
INIT_LIST_HEAD(&ubi->pq[i]);
ubi->pq_head = 0;
+ ubi->free_count = 0;
list_for_each_entry_safe(aeb, tmp, &ai->erase, u.list) {
cond_resched();
@@ -1552,7 +1553,6 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
found_pebs++;
}
- ubi->free_count = 0;
list_for_each_entry(aeb, &ai->free, u.list) {
cond_resched();
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index b9304a295f86..ca81f46ea1aa 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -657,6 +657,20 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val)
}
}
+static int __agg_active_ports(struct aggregator *agg)
+{
+ struct port *port;
+ int active = 0;
+
+ for (port = agg->lag_ports; port;
+ port = port->next_port_in_aggregator) {
+ if (port->is_enabled)
+ active++;
+ }
+
+ return active;
+}
+
/**
* __get_agg_bandwidth - get the total bandwidth of an aggregator
* @aggregator: the aggregator we're looking at
@@ -664,39 +678,40 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val)
*/
static u32 __get_agg_bandwidth(struct aggregator *aggregator)
{
+ int nports = __agg_active_ports(aggregator);
u32 bandwidth = 0;
- if (aggregator->num_of_ports) {
+ if (nports) {
switch (__get_link_speed(aggregator->lag_ports)) {
case AD_LINK_SPEED_1MBPS:
- bandwidth = aggregator->num_of_ports;
+ bandwidth = nports;
break;
case AD_LINK_SPEED_10MBPS:
- bandwidth = aggregator->num_of_ports * 10;
+ bandwidth = nports * 10;
break;
case AD_LINK_SPEED_100MBPS:
- bandwidth = aggregator->num_of_ports * 100;
+ bandwidth = nports * 100;
break;
case AD_LINK_SPEED_1000MBPS:
- bandwidth = aggregator->num_of_ports * 1000;
+ bandwidth = nports * 1000;
break;
case AD_LINK_SPEED_2500MBPS:
- bandwidth = aggregator->num_of_ports * 2500;
+ bandwidth = nports * 2500;
break;
case AD_LINK_SPEED_10000MBPS:
- bandwidth = aggregator->num_of_ports * 10000;
+ bandwidth = nports * 10000;
break;
case AD_LINK_SPEED_20000MBPS:
- bandwidth = aggregator->num_of_ports * 20000;
+ bandwidth = nports * 20000;
break;
case AD_LINK_SPEED_40000MBPS:
- bandwidth = aggregator->num_of_ports * 40000;
+ bandwidth = nports * 40000;
break;
case AD_LINK_SPEED_56000MBPS:
- bandwidth = aggregator->num_of_ports * 56000;
+ bandwidth = nports * 56000;
break;
case AD_LINK_SPEED_100000MBPS:
- bandwidth = aggregator->num_of_ports * 100000;
+ bandwidth = nports * 100000;
break;
default:
bandwidth = 0; /* to silence the compiler */
@@ -1530,10 +1545,10 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best,
switch (__get_agg_selection_mode(curr->lag_ports)) {
case BOND_AD_COUNT:
- if (curr->num_of_ports > best->num_of_ports)
+ if (__agg_active_ports(curr) > __agg_active_ports(best))
return curr;
- if (curr->num_of_ports < best->num_of_ports)
+ if (__agg_active_ports(curr) < __agg_active_ports(best))
return best;
/*FALLTHROUGH*/
@@ -1561,8 +1576,14 @@ static int agg_device_up(const struct aggregator *agg)
if (!port)
return 0;
- return netif_running(port->slave->dev) &&
- netif_carrier_ok(port->slave->dev);
+ for (port = agg->lag_ports; port;
+ port = port->next_port_in_aggregator) {
+ if (netif_running(port->slave->dev) &&
+ netif_carrier_ok(port->slave->dev))
+ return 1;
+ }
+
+ return 0;
}
/**
@@ -1610,7 +1631,7 @@ static void ad_agg_selection_logic(struct aggregator *agg,
agg->is_active = 0;
- if (agg->num_of_ports && agg_device_up(agg))
+ if (__agg_active_ports(agg) && agg_device_up(agg))
best = ad_agg_selection_test(best, agg);
}
@@ -1622,7 +1643,7 @@ static void ad_agg_selection_logic(struct aggregator *agg,
* answering partner.
*/
if (active && active->lag_ports &&
- active->lag_ports->is_enabled &&
+ __agg_active_ports(active) &&
(__agg_has_partner(active) ||
(!__agg_has_partner(active) &&
!__agg_has_partner(best)))) {
@@ -2133,7 +2154,7 @@ void bond_3ad_unbind_slave(struct slave *slave)
else
temp_aggregator->lag_ports = temp_port->next_port_in_aggregator;
temp_aggregator->num_of_ports--;
- if (temp_aggregator->num_of_ports == 0) {
+ if (__agg_active_ports(temp_aggregator) == 0) {
select_new_active_agg = temp_aggregator->is_active;
ad_clear_agg(temp_aggregator);
if (select_new_active_agg) {
@@ -2432,7 +2453,9 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave)
*/
void bond_3ad_handle_link_change(struct slave *slave, char link)
{
+ struct aggregator *agg;
struct port *port;
+ bool dummy;
port = &(SLAVE_AD_INFO(slave)->port);
@@ -2459,6 +2482,9 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
port->is_enabled = false;
ad_update_actor_keys(port, true);
}
+ agg = __get_first_agg(port);
+ ad_agg_selection_logic(agg, &dummy);
+
netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n",
port->actor_port_number,
link == BOND_LINK_UP ? "UP" : "DOWN");
@@ -2499,7 +2525,7 @@ int bond_3ad_set_carrier(struct bonding *bond)
active = __get_active_agg(&(SLAVE_AD_INFO(first_slave)->aggregator));
if (active) {
/* are enough slaves available to consider link up? */
- if (active->num_of_ports < bond->params.min_links) {
+ if (__agg_active_ports(active) < bond->params.min_links) {
if (netif_carrier_ok(bond->dev)) {
netif_carrier_off(bond->dev);
goto out;
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 8b3275d7792a..8f5e93cb7975 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -712,9 +712,10 @@ static int at91_poll_rx(struct net_device *dev, int quota)
/* upper group completed, look again in lower */
if (priv->rx_next > get_mb_rx_low_last(priv) &&
- quota > 0 && mb > get_mb_rx_last(priv)) {
+ mb > get_mb_rx_last(priv)) {
priv->rx_next = get_mb_rx_first(priv);
- goto again;
+ if (quota > 0)
+ goto again;
}
return received;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index f91b094288da..e3dccd3200d5 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -332,9 +332,23 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl);
- for (i = 0; i < frame->can_dlc; i += 2) {
- priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2,
- frame->data[i] | (frame->data[i + 1] << 8));
+ if (priv->type == BOSCH_D_CAN) {
+ u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
+
+ for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+ data = (u32)frame->data[i];
+ data |= (u32)frame->data[i + 1] << 8;
+ data |= (u32)frame->data[i + 2] << 16;
+ data |= (u32)frame->data[i + 3] << 24;
+ priv->write_reg32(priv, dreg, data);
+ }
+ } else {
+ for (i = 0; i < frame->can_dlc; i += 2) {
+ priv->write_reg(priv,
+ C_CAN_IFACE(DATA1_REG, iface) + i / 2,
+ frame->data[i] |
+ (frame->data[i + 1] << 8));
+ }
}
}
@@ -402,10 +416,20 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
} else {
int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
- for (i = 0; i < frame->can_dlc; i += 2, dreg ++) {
- data = priv->read_reg(priv, dreg);
- frame->data[i] = data;
- frame->data[i + 1] = data >> 8;
+ if (priv->type == BOSCH_D_CAN) {
+ for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+ data = priv->read_reg32(priv, dreg);
+ frame->data[i] = data;
+ frame->data[i + 1] = data >> 8;
+ frame->data[i + 2] = data >> 16;
+ frame->data[i + 3] = data >> 24;
+ }
+ } else {
+ for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+ data = priv->read_reg(priv, dreg);
+ frame->data[i] = data;
+ frame->data[i + 1] = data >> 8;
+ }
}
}
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 910c12e2638e..ad535a854e5c 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -798,6 +798,9 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[])
* - control mode with CAN_CTRLMODE_FD set
*/
+ if (!data)
+ return 0;
+
if (data[IFLA_CAN_CTRLMODE]) {
struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
@@ -1008,6 +1011,11 @@ static int can_newlink(struct net *src_net, struct net_device *dev,
return -EOPNOTSUPP;
}
+static void can_dellink(struct net_device *dev, struct list_head *head)
+{
+ return;
+}
+
static struct rtnl_link_ops can_link_ops __read_mostly = {
.kind = "can",
.maxtype = IFLA_CAN_MAX,
@@ -1016,6 +1024,7 @@ static struct rtnl_link_ops can_link_ops __read_mostly = {
.validate = can_validate,
.newlink = can_newlink,
.changelink = can_changelink,
+ .dellink = can_dellink,
.get_size = can_get_size,
.fill_info = can_fill_info,
.get_xstats_size = can_get_xstats_size,
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index bcb272f6c68a..8483a40e7e9e 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -16,7 +16,8 @@ config CAN_ESD_USB2
config CAN_GS_USB
tristate "Geschwister Schneider UG interfaces"
---help---
- This driver supports the Geschwister Schneider USB/CAN devices.
+ This driver supports the Geschwister Schneider and bytewerk.org
+ candleLight USB CAN interfaces USB/CAN devices
If unsure choose N,
choose Y for built in support,
M to compile as module (module will be named: gs_usb).
@@ -46,6 +47,8 @@ config CAN_KVASER_USB
- Kvaser USBcan R
- Kvaser Leaf Light v2
- Kvaser Mini PCI Express HS
+ - Kvaser Mini PCI Express 2xHS
+ - Kvaser USBcan Light 2xHS
- Kvaser USBcan II HS/HS
- Kvaser USBcan II HS/LS
- Kvaser USBcan Rugged ("USBcan Rev B")
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 1556d4286235..acb0c8490673 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1,7 +1,9 @@
-/* CAN driver for Geschwister Schneider USB/CAN devices.
+/* CAN driver for Geschwister Schneider USB/CAN devices
+ * and bytewerk.org candleLight USB CAN interfaces.
*
- * Copyright (C) 2013 Geschwister Schneider Technologie-,
+ * Copyright (C) 2013-2016 Geschwister Schneider Technologie-,
* Entwicklungs- und Vertriebs UG (Haftungsbeschränkt).
+ * Copyright (C) 2016 Hubert Denkmair
*
* Many thanks to all socketcan devs!
*
@@ -29,6 +31,9 @@
#define USB_GSUSB_1_VENDOR_ID 0x1d50
#define USB_GSUSB_1_PRODUCT_ID 0x606f
+#define USB_CANDLELIGHT_VENDOR_ID 0x1209
+#define USB_CANDLELIGHT_PRODUCT_ID 0x2323
+
#define GSUSB_ENDPOINT_IN 1
#define GSUSB_ENDPOINT_OUT 2
@@ -952,6 +957,8 @@ static void gs_usb_disconnect(struct usb_interface *intf)
static const struct usb_device_id gs_usb_table[] = {
{ USB_DEVICE_INTERFACE_NUMBER(USB_GSUSB_1_VENDOR_ID,
USB_GSUSB_1_PRODUCT_ID, 0) },
+ { USB_DEVICE_INTERFACE_NUMBER(USB_CANDLELIGHT_VENDOR_ID,
+ USB_CANDLELIGHT_PRODUCT_ID, 0) },
{} /* Terminating entry */
};
@@ -969,5 +976,6 @@ module_usb_driver(gs_usb_driver);
MODULE_AUTHOR("Maximilian Schneider <mws@schneidersoft.net>");
MODULE_DESCRIPTION(
"Socket CAN device driver for Geschwister Schneider Technologie-, "
-"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces.");
+"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces\n"
+"and bytewerk.org candleLight USB CAN interfaces.");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 022bfa13ebfa..6f1f3b675ff5 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -59,11 +59,14 @@
#define USB_CAN_R_PRODUCT_ID 39
#define USB_LEAF_LITE_V2_PRODUCT_ID 288
#define USB_MINI_PCIE_HS_PRODUCT_ID 289
+#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290
+#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID 291
+#define USB_MINI_PCIE_2HS_PRODUCT_ID 292
static inline bool kvaser_is_leaf(const struct usb_device_id *id)
{
return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
- id->idProduct <= USB_MINI_PCIE_HS_PRODUCT_ID;
+ id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
}
/* Kvaser USBCan-II devices */
@@ -537,6 +540,9 @@ static const struct usb_device_id kvaser_usb_table[] = {
.driver_info = KVASER_HAS_TXRX_ERRORS },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
/* USBCANII family IDs */
{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index e0fb0f1122db..20760e10211a 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -509,8 +509,8 @@ static int au1000_mii_probe(struct net_device *dev)
* on the current MAC's MII bus
*/
for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++)
- if (mdiobus_get_phy(aup->mii_bus, aup->phy_addr)) {
- phydev = mdiobus_get_phy(aup->mii_bus, aup->phy_addr);
+ if (mdiobus_get_phy(aup->mii_bus, phy_addr)) {
+ phydev = mdiobus_get_phy(aup->mii_bus, phy_addr);
if (!aup->phy_search_highest_addr)
/* break out with first one found */
break;
diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c
index 16419f550eff..058460bdd5a6 100644
--- a/drivers/net/ethernet/arc/emac_mdio.c
+++ b/drivers/net/ethernet/arc/emac_mdio.c
@@ -141,7 +141,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv)
priv->bus = bus;
bus->priv = priv;
bus->parent = priv->dev;
- bus->name = "Synopsys MII Bus",
+ bus->name = "Synopsys MII Bus";
bus->read = &arc_mdio_read;
bus->write = &arc_mdio_write;
bus->reset = &arc_mdio_reset;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 9fe8b5e310d1..e708e360a9e3 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -86,9 +86,22 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
while (!cur_buf->skb && next != rxq->read_idx) {
struct alx_rfd *rfd = &rxq->rfd[cur];
- skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+ /*
+ * When DMA RX address is set to something like
+ * 0x....fc0, it will be very likely to cause DMA
+ * RFD overflow issue.
+ *
+ * To work around it, we apply rx skb with 64 bytes
+ * longer space, and offset the address whenever
+ * 0x....fc0 is detected.
+ */
+ skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp);
if (!skb)
break;
+
+ if (((unsigned long)skb->data & 0xfff) == 0xfc0)
+ skb_reserve(skb, 64);
+
dma = dma_map_single(&alx->hw.pdev->dev,
skb->data, alx->rxbuf_size,
DMA_FROM_DEVICE);
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index ee5f431ab32a..a6333d38ecc0 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -267,15 +267,16 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
while (ring->start != ring->end) {
int slot_idx = ring->start % BGMAC_TX_RING_SLOTS;
struct bgmac_slot_info *slot = &ring->slots[slot_idx];
- u32 ctl1;
+ u32 ctl0, ctl1;
int len;
if (slot_idx == empty_slot)
break;
+ ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0);
ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1);
len = ctl1 & BGMAC_DESC_CTL1_LEN;
- if (ctl1 & BGMAC_DESC_CTL0_SOF)
+ if (ctl0 & BGMAC_DESC_CTL0_SOF)
/* Unmap no longer used buffer */
dma_unmap_single(dma_dev, slot->dma_addr, len,
DMA_TO_DEVICE);
@@ -1312,7 +1313,8 @@ static int bgmac_open(struct net_device *net_dev)
phy_start(bgmac->phy_dev);
- netif_carrier_on(net_dev);
+ netif_start_queue(net_dev);
+
return 0;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 0a5b770cefaa..a59d55e25d5f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12895,52 +12895,71 @@ static int __bnx2x_vlan_configure_vid(struct bnx2x *bp, u16 vid, bool add)
return rc;
}
-int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp)
+static int bnx2x_vlan_configure_vid_list(struct bnx2x *bp)
{
struct bnx2x_vlan_entry *vlan;
int rc = 0;
- if (!bp->vlan_cnt) {
- DP(NETIF_MSG_IFUP, "No need to re-configure vlan filters\n");
- return 0;
- }
-
+ /* Configure all non-configured entries */
list_for_each_entry(vlan, &bp->vlan_reg, link) {
- /* Prepare for cleanup in case of errors */
- if (rc) {
- vlan->hw = false;
- continue;
- }
-
- if (!vlan->hw)
+ if (vlan->hw)
continue;
- DP(NETIF_MSG_IFUP, "Re-configuring vlan 0x%04x\n", vlan->vid);
+ if (bp->vlan_cnt >= bp->vlan_credit)
+ return -ENOBUFS;
rc = __bnx2x_vlan_configure_vid(bp, vlan->vid, true);
if (rc) {
- BNX2X_ERR("Unable to configure VLAN %d\n", vlan->vid);
- vlan->hw = false;
- rc = -EINVAL;
- continue;
+ BNX2X_ERR("Unable to config VLAN %d\n", vlan->vid);
+ return rc;
}
+
+ DP(NETIF_MSG_IFUP, "HW configured for VLAN %d\n", vlan->vid);
+ vlan->hw = true;
+ bp->vlan_cnt++;
}
- return rc;
+ return 0;
+}
+
+static void bnx2x_vlan_configure(struct bnx2x *bp, bool set_rx_mode)
+{
+ bool need_accept_any_vlan;
+
+ need_accept_any_vlan = !!bnx2x_vlan_configure_vid_list(bp);
+
+ if (bp->accept_any_vlan != need_accept_any_vlan) {
+ bp->accept_any_vlan = need_accept_any_vlan;
+ DP(NETIF_MSG_IFUP, "Accept all VLAN %s\n",
+ bp->accept_any_vlan ? "raised" : "cleared");
+ if (set_rx_mode) {
+ if (IS_PF(bp))
+ bnx2x_set_rx_mode_inner(bp);
+ else
+ bnx2x_vfpf_storm_rx_mode(bp);
+ }
+ }
+}
+
+int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp)
+{
+ struct bnx2x_vlan_entry *vlan;
+
+ /* The hw forgot all entries after reload */
+ list_for_each_entry(vlan, &bp->vlan_reg, link)
+ vlan->hw = false;
+ bp->vlan_cnt = 0;
+
+ /* Don't set rx mode here. Our caller will do it. */
+ bnx2x_vlan_configure(bp, false);
+
+ return 0;
}
static int bnx2x_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
{
struct bnx2x *bp = netdev_priv(dev);
struct bnx2x_vlan_entry *vlan;
- bool hw = false;
- int rc = 0;
-
- if (!netif_running(bp->dev)) {
- DP(NETIF_MSG_IFUP,
- "Ignoring VLAN configuration the interface is down\n");
- return -EFAULT;
- }
DP(NETIF_MSG_IFUP, "Adding VLAN %d\n", vid);
@@ -12948,93 +12967,47 @@ static int bnx2x_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
if (!vlan)
return -ENOMEM;
- bp->vlan_cnt++;
- if (bp->vlan_cnt > bp->vlan_credit && !bp->accept_any_vlan) {
- DP(NETIF_MSG_IFUP, "Accept all VLAN raised\n");
- bp->accept_any_vlan = true;
- if (IS_PF(bp))
- bnx2x_set_rx_mode_inner(bp);
- else
- bnx2x_vfpf_storm_rx_mode(bp);
- } else if (bp->vlan_cnt <= bp->vlan_credit) {
- rc = __bnx2x_vlan_configure_vid(bp, vid, true);
- hw = true;
- }
-
vlan->vid = vid;
- vlan->hw = hw;
+ vlan->hw = false;
+ list_add_tail(&vlan->link, &bp->vlan_reg);
- if (!rc) {
- list_add(&vlan->link, &bp->vlan_reg);
- } else {
- bp->vlan_cnt--;
- kfree(vlan);
- }
-
- DP(NETIF_MSG_IFUP, "Adding VLAN result %d\n", rc);
+ if (netif_running(dev))
+ bnx2x_vlan_configure(bp, true);
- return rc;
+ return 0;
}
static int bnx2x_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
{
struct bnx2x *bp = netdev_priv(dev);
struct bnx2x_vlan_entry *vlan;
+ bool found = false;
int rc = 0;
- if (!netif_running(bp->dev)) {
- DP(NETIF_MSG_IFUP,
- "Ignoring VLAN configuration the interface is down\n");
- return -EFAULT;
- }
-
DP(NETIF_MSG_IFUP, "Removing VLAN %d\n", vid);
- if (!bp->vlan_cnt) {
- BNX2X_ERR("Unable to kill VLAN %d\n", vid);
- return -EINVAL;
- }
-
list_for_each_entry(vlan, &bp->vlan_reg, link)
- if (vlan->vid == vid)
+ if (vlan->vid == vid) {
+ found = true;
break;
+ }
- if (vlan->vid != vid) {
+ if (!found) {
BNX2X_ERR("Unable to kill VLAN %d - not found\n", vid);
return -EINVAL;
}
- if (vlan->hw)
+ if (netif_running(dev) && vlan->hw) {
rc = __bnx2x_vlan_configure_vid(bp, vid, false);
+ DP(NETIF_MSG_IFUP, "HW deconfigured for VLAN %d\n", vid);
+ bp->vlan_cnt--;
+ }
list_del(&vlan->link);
kfree(vlan);
- bp->vlan_cnt--;
-
- if (bp->vlan_cnt <= bp->vlan_credit && bp->accept_any_vlan) {
- /* Configure all non-configured entries */
- list_for_each_entry(vlan, &bp->vlan_reg, link) {
- if (vlan->hw)
- continue;
-
- rc = __bnx2x_vlan_configure_vid(bp, vlan->vid, true);
- if (rc) {
- BNX2X_ERR("Unable to config VLAN %d\n",
- vlan->vid);
- continue;
- }
- DP(NETIF_MSG_IFUP, "HW configured for VLAN %d\n",
- vlan->vid);
- vlan->hw = true;
- }
- DP(NETIF_MSG_IFUP, "Accept all VLAN Removed\n");
- bp->accept_any_vlan = false;
- if (IS_PF(bp))
- bnx2x_set_rx_mode_inner(bp);
- else
- bnx2x_vfpf_storm_rx_mode(bp);
- }
+ if (netif_running(dev))
+ bnx2x_vlan_configure(bp, true);
DP(NETIF_MSG_IFUP, "Removing VLAN result %d\n", rc);
@@ -13941,14 +13914,14 @@ static int bnx2x_init_one(struct pci_dev *pdev,
bp->doorbells = bnx2x_vf_doorbells(bp);
rc = bnx2x_vf_pci_alloc(bp);
if (rc)
- goto init_one_exit;
+ goto init_one_freemem;
} else {
doorbell_size = BNX2X_L2_MAX_CID(bp) * (1 << BNX2X_DB_SHIFT);
if (doorbell_size > pci_resource_len(pdev, 2)) {
dev_err(&bp->pdev->dev,
"Cannot map doorbells, bar size too small, aborting\n");
rc = -ENOMEM;
- goto init_one_exit;
+ goto init_one_freemem;
}
bp->doorbells = ioremap_nocache(pci_resource_start(pdev, 2),
doorbell_size);
@@ -13957,19 +13930,19 @@ static int bnx2x_init_one(struct pci_dev *pdev,
dev_err(&bp->pdev->dev,
"Cannot map doorbell space, aborting\n");
rc = -ENOMEM;
- goto init_one_exit;
+ goto init_one_freemem;
}
if (IS_VF(bp)) {
rc = bnx2x_vfpf_acquire(bp, tx_count, rx_count);
if (rc)
- goto init_one_exit;
+ goto init_one_freemem;
}
/* Enable SRIOV if capability found in configuration space */
rc = bnx2x_iov_init_one(bp, int_mode, BNX2X_MAX_NUM_OF_VFS);
if (rc)
- goto init_one_exit;
+ goto init_one_freemem;
/* calc qm_cid_count */
bp->qm_cid_count = bnx2x_set_qm_cid_count(bp);
@@ -13988,7 +13961,7 @@ static int bnx2x_init_one(struct pci_dev *pdev,
rc = bnx2x_set_int_mode(bp);
if (rc) {
dev_err(&pdev->dev, "Cannot set interrupts\n");
- goto init_one_exit;
+ goto init_one_freemem;
}
BNX2X_DEV_INFO("set interrupts successfully\n");
@@ -13996,7 +13969,7 @@ static int bnx2x_init_one(struct pci_dev *pdev,
rc = register_netdev(dev);
if (rc) {
dev_err(&pdev->dev, "Cannot register net device\n");
- goto init_one_exit;
+ goto init_one_freemem;
}
BNX2X_DEV_INFO("device name after netdev register %s\n", dev->name);
@@ -14029,6 +14002,9 @@ static int bnx2x_init_one(struct pci_dev *pdev,
return 0;
+init_one_freemem:
+ bnx2x_free_mem_bp(bp);
+
init_one_exit:
bnx2x_disable_pcie_error_reporting(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 72a2efff8e49..c777cde85ce4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -286,7 +286,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
txr->tx_prod = prod;
+ tx_buf->is_push = 1;
netdev_tx_sent_queue(txq, skb->len);
+ wmb(); /* Sync is_push and byte queue before pushing data */
push_len = (length + sizeof(*tx_push) + 7) / 8;
if (push_len > 16) {
@@ -298,7 +300,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
push_len);
}
- tx_buf->is_push = 1;
goto tx_done;
}
@@ -1112,19 +1113,13 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
- if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) {
- netdev_features_t features = skb->dev->features;
+ if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
+ (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
u16 vlan_proto = tpa_info->metadata >>
RX_CMP_FLAGS2_METADATA_TPID_SFT;
+ u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_VID_MASK;
- if (((features & NETIF_F_HW_VLAN_CTAG_RX) &&
- vlan_proto == ETH_P_8021Q) ||
- ((features & NETIF_F_HW_VLAN_STAG_RX) &&
- vlan_proto == ETH_P_8021AD)) {
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto),
- tpa_info->metadata &
- RX_CMP_FLAGS2_METADATA_VID_MASK);
- }
+ __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
}
skb_checksum_none_assert(skb);
@@ -1277,19 +1272,14 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
skb->protocol = eth_type_trans(skb, dev);
- if (rxcmp1->rx_cmp_flags2 &
- cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) {
- netdev_features_t features = skb->dev->features;
+ if ((rxcmp1->rx_cmp_flags2 &
+ cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) &&
+ (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
+ u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_VID_MASK;
u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
- if (((features & NETIF_F_HW_VLAN_CTAG_RX) &&
- vlan_proto == ETH_P_8021Q) ||
- ((features & NETIF_F_HW_VLAN_STAG_RX) &&
- vlan_proto == ETH_P_8021AD))
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto),
- meta_data &
- RX_CMP_FLAGS2_METADATA_VID_MASK);
+ __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
}
skb_checksum_none_assert(skb);
@@ -5466,6 +5456,20 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
if (!bnxt_rfs_capable(bp))
features &= ~NETIF_F_NTUPLE;
+
+ /* Both CTAG and STAG VLAN accelaration on the RX side have to be
+ * turned on or off together.
+ */
+ if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
+ (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+ if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+ features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_STAG_RX);
+ else
+ features |= NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_STAG_RX;
+ }
+
return features;
}
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 95f17f8cadac..16ed20357c5c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -499,6 +499,7 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
u32 rr_quantum;
u8 sq_idx = sq->sq_num;
u8 pqs_vnic;
+ int svf;
if (sq->sqs_mode)
pqs_vnic = nic->pqs_vf[vnic];
@@ -511,10 +512,19 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
/* 24 bytes for FCS, IPG and preamble */
rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
- tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+ if (!sq->sqs_mode) {
+ tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+ } else {
+ for (svf = 0; svf < MAX_SQS_PER_VF; svf++) {
+ if (nic->vf_sqs[pqs_vnic][svf] == vnic)
+ break;
+ }
+ tl4 = (MAX_LMAC_PER_BGX * NIC_TL4_PER_LMAC);
+ tl4 += (lmac * NIC_TL4_PER_LMAC * MAX_SQS_PER_VF);
+ tl4 += (svf * NIC_TL4_PER_LMAC);
+ tl4 += (bgx * NIC_TL4_PER_BGX);
+ }
tl4 += sq_idx;
- if (sq->sqs_mode)
- tl4 += vnic * 8;
tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3);
nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 |
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 3ed21988626b..63a39ac97d53 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -551,7 +551,9 @@ static int bgx_xaui_check_link(struct lmac *lmac)
}
/* Clear rcvflt bit (latching high) and read it back */
- bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+ if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT)
+ bgx_reg_modify(bgx, lmacid,
+ BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
if (bgx->use_training) {
@@ -570,13 +572,6 @@ static int bgx_xaui_check_link(struct lmac *lmac)
return -1;
}
- /* Wait for MAC RX to be ready */
- if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
- SMU_RX_CTL_STATUS, true)) {
- dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
- return -1;
- }
-
/* Wait for BGX RX to be idle */
if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
@@ -589,29 +584,30 @@ static int bgx_xaui_check_link(struct lmac *lmac)
return -1;
}
- if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
- dev_err(&bgx->pdev->dev, "Receive fault\n");
- return -1;
- }
-
- /* Receive link is latching low. Force it high and verify it */
- bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
- if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
- SPU_STATUS1_RCV_LNK, false)) {
- dev_err(&bgx->pdev->dev, "SPU receive link down\n");
- return -1;
- }
-
+ /* Clear receive packet disable */
cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
cfg &= ~SPU_MISC_CTL_RX_DIS;
bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
- return 0;
+
+ /* Check for MAC RX faults */
+ cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL);
+ /* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */
+ cfg &= SMU_RX_CTL_STATUS;
+ if (!cfg)
+ return 0;
+
+ /* Rx local/remote fault seen.
+ * Do lmac reinit to see if condition recovers
+ */
+ bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type);
+
+ return -1;
}
static void bgx_poll_for_link(struct work_struct *work)
{
struct lmac *lmac;
- u64 link;
+ u64 spu_link, smu_link;
lmac = container_of(work, struct lmac, dwork.work);
@@ -621,8 +617,11 @@ static void bgx_poll_for_link(struct work_struct *work)
bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
SPU_STATUS1_RCV_LNK, false);
- link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
- if (link & SPU_STATUS1_RCV_LNK) {
+ spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+ smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL);
+
+ if ((spu_link & SPU_STATUS1_RCV_LNK) &&
+ !(smu_link & SMU_RX_CTL_STATUS)) {
lmac->link_up = 1;
if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
lmac->last_speed = 40000;
@@ -636,9 +635,15 @@ static void bgx_poll_for_link(struct work_struct *work)
}
if (lmac->last_link != lmac->link_up) {
+ if (lmac->link_up) {
+ if (bgx_xaui_check_link(lmac)) {
+ /* Errors, clear link_up state */
+ lmac->link_up = 0;
+ lmac->last_speed = SPEED_UNKNOWN;
+ lmac->last_duplex = DUPLEX_UNKNOWN;
+ }
+ }
lmac->last_link = lmac->link_up;
- if (lmac->link_up)
- bgx_xaui_check_link(lmac);
}
queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
@@ -710,7 +715,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
{
struct lmac *lmac;
- u64 cmrx_cfg;
+ u64 cfg;
lmac = &bgx->lmac[lmacid];
if (lmac->check_link) {
@@ -719,9 +724,33 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
destroy_workqueue(lmac->check_link);
}
- cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
- cmrx_cfg &= ~(1 << 15);
- bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+ /* Disable packet reception */
+ cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+ cfg &= ~CMR_PKT_RX_EN;
+ bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+ /* Give chance for Rx/Tx FIFO to get drained */
+ bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true);
+ bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true);
+
+ /* Disable packet transmission */
+ cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+ cfg &= ~CMR_PKT_TX_EN;
+ bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+ /* Disable serdes lanes */
+ if (!lmac->is_sgmii)
+ bgx_reg_modify(bgx, lmacid,
+ BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+ else
+ bgx_reg_modify(bgx, lmacid,
+ BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN);
+
+ /* Disable LMAC */
+ cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+ cfg &= ~CMR_EN;
+ bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
bgx_flush_dmac_addrs(bgx, lmacid);
if ((bgx->lmac_type != BGX_MODE_XFI) &&
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 149e179363a1..42010d2e5ddf 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -41,6 +41,7 @@
#define BGX_CMRX_RX_STAT10 0xC0
#define BGX_CMRX_RX_BP_DROP 0xC8
#define BGX_CMRX_RX_DMAC_CTL 0x0E8
+#define BGX_CMRX_RX_FIFO_LEN 0x108
#define BGX_CMR_RX_DMACX_CAM 0x200
#define RX_DMACX_CAM_EN BIT_ULL(48)
#define RX_DMACX_CAM_LMACID(x) (x << 49)
@@ -50,6 +51,7 @@
#define BGX_CMR_CHAN_MSK_AND 0x450
#define BGX_CMR_BIST_STATUS 0x460
#define BGX_CMR_RX_LMACS 0x468
+#define BGX_CMRX_TX_FIFO_LEN 0x518
#define BGX_CMRX_TX_STAT0 0x600
#define BGX_CMRX_TX_STAT1 0x608
#define BGX_CMRX_TX_STAT2 0x610
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index a2cdfc1261dc..50812a1d67bd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -144,6 +144,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
CH_PCI_ID_TABLE_FENTRY(0x5015), /* T502-bt */
CH_PCI_ID_TABLE_FENTRY(0x5016), /* T580-OCP-SO */
CH_PCI_ID_TABLE_FENTRY(0x5017), /* T520-OCP-SO */
+ CH_PCI_ID_TABLE_FENTRY(0x5018), /* T540-BT */
CH_PCI_ID_TABLE_FENTRY(0x5080), /* Custom T540-cr */
CH_PCI_ID_TABLE_FENTRY(0x5081), /* Custom T540-LL-cr */
CH_PCI_ID_TABLE_FENTRY(0x5082), /* Custom T504-cr */
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 41b010645100..4edb98c3c6c7 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1195,7 +1195,7 @@ static int ethoc_probe(struct platform_device *pdev)
priv->mdio = mdiobus_alloc();
if (!priv->mdio) {
ret = -ENOMEM;
- goto free;
+ goto free2;
}
priv->mdio->name = "ethoc-mdio";
@@ -1208,7 +1208,7 @@ static int ethoc_probe(struct platform_device *pdev)
ret = mdiobus_register(priv->mdio);
if (ret) {
dev_err(&netdev->dev, "failed to register MDIO bus\n");
- goto free;
+ goto free2;
}
ret = ethoc_mdio_probe(netdev);
@@ -1241,9 +1241,10 @@ error2:
error:
mdiobus_unregister(priv->mdio);
mdiobus_free(priv->mdio);
-free:
+free2:
if (priv->clk)
clk_disable_unprepare(priv->clk);
+free:
free_netdev(netdev);
out:
return ret;
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 085f9125cf42..06f031715b57 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -205,8 +205,10 @@ static int nps_enet_poll(struct napi_struct *napi, int budget)
* re-adding ourselves to the poll list.
*/
- if (priv->tx_skb && !tx_ctrl_ct)
+ if (priv->tx_skb && !tx_ctrl_ct) {
+ nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, 0);
napi_reschedule(napi);
+ }
}
return work_done;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index ca2cccc594fd..fea0f330ddbd 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1197,10 +1197,8 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
fec16_to_cpu(bdp->cbd_datlen),
DMA_TO_DEVICE);
bdp->cbd_bufaddr = cpu_to_fec32(0);
- if (!skb) {
- bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
- continue;
- }
+ if (!skb)
+ goto skb_done;
/* Check for errors. */
if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -1239,7 +1237,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
/* Free the sk buffer associated with this last transmit */
dev_kfree_skb_any(skb);
-
+skb_done:
/* Make sure the update to bdp and tx_skbuff are performed
* before dirty_tx
*/
@@ -2418,24 +2416,24 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
return -EOPNOTSUPP;
if (ec->rx_max_coalesced_frames > 255) {
- pr_err("Rx coalesced frames exceed hardware limiation");
+ pr_err("Rx coalesced frames exceed hardware limitation\n");
return -EINVAL;
}
if (ec->tx_max_coalesced_frames > 255) {
- pr_err("Tx coalesced frame exceed hardware limiation");
+ pr_err("Tx coalesced frame exceed hardware limitation\n");
return -EINVAL;
}
cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
if (cycle > 0xFFFF) {
- pr_err("Rx coalesed usec exceeed hardware limiation");
+ pr_err("Rx coalesced usec exceed hardware limitation\n");
return -EINVAL;
}
cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
if (cycle > 0xFFFF) {
- pr_err("Rx coalesed usec exceeed hardware limiation");
+ pr_err("Rx coalesced usec exceed hardware limitation\n");
return -EINVAL;
}
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index bcb9dccada4d..1de2e1e51c2b 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -615,7 +615,7 @@ struct fman {
struct fman_cfg *cfg;
struct muram_info *muram;
/* cam section in muram */
- int cam_offset;
+ unsigned long cam_offset;
size_t cam_size;
/* Fifo in MURAM */
int fifo_offset;
diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.c b/drivers/net/ethernet/freescale/fman/fman_muram.c
index 4eb0e9ac7182..47394c45b6e8 100644
--- a/drivers/net/ethernet/freescale/fman/fman_muram.c
+++ b/drivers/net/ethernet/freescale/fman/fman_muram.c
@@ -129,7 +129,7 @@ unsigned long fman_muram_offset_to_vbase(struct muram_info *muram,
*
* Return: address of the allocated memory; NULL otherwise.
*/
-int fman_muram_alloc(struct muram_info *muram, size_t size)
+unsigned long fman_muram_alloc(struct muram_info *muram, size_t size)
{
unsigned long vaddr;
@@ -150,7 +150,7 @@ int fman_muram_alloc(struct muram_info *muram, size_t size)
*
* Free an allocated memory from FM-MURAM partition.
*/
-void fman_muram_free_mem(struct muram_info *muram, u32 offset, size_t size)
+void fman_muram_free_mem(struct muram_info *muram, unsigned long offset, size_t size)
{
unsigned long addr = fman_muram_offset_to_vbase(muram, offset);
diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.h b/drivers/net/ethernet/freescale/fman/fman_muram.h
index dbf0af9e5bb5..889649ad8931 100644
--- a/drivers/net/ethernet/freescale/fman/fman_muram.h
+++ b/drivers/net/ethernet/freescale/fman/fman_muram.h
@@ -44,8 +44,8 @@ struct muram_info *fman_muram_init(phys_addr_t base, size_t size);
unsigned long fman_muram_offset_to_vbase(struct muram_info *muram,
unsigned long offset);
-int fman_muram_alloc(struct muram_info *muram, size_t size);
+unsigned long fman_muram_alloc(struct muram_info *muram, size_t size);
-void fman_muram_free_mem(struct muram_info *muram, u32 offset, size_t size);
+void fman_muram_free_mem(struct muram_info *muram, unsigned long offset, size_t size);
#endif /* __FM_MURAM_EXT */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 7615e0668acb..2e6785b6e8be 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2440,7 +2440,8 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
tx_queue->tx_ring_size);
if (likely(!nr_frags)) {
- lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT);
+ if (likely(!do_tstamp))
+ lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT);
} else {
u32 lstatus_start = lstatus;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3d746c887873..67a648c7d3a9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -46,7 +46,6 @@ static u32 hns_nic_get_link(struct net_device *net_dev)
u32 link_stat = priv->link;
struct hnae_handle *h;
- assert(priv && priv->ae_handle);
h = priv->ae_handle;
if (priv->phy) {
@@ -646,8 +645,6 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev,
{
struct hns_nic_priv *priv = netdev_priv(net_dev);
- assert(priv);
-
strncpy(drvinfo->version, HNAE_DRIVER_VERSION,
sizeof(drvinfo->version));
drvinfo->version[sizeof(drvinfo->version) - 1] = '\0';
@@ -720,8 +717,6 @@ static int hns_set_pauseparam(struct net_device *net_dev,
struct hnae_handle *h;
struct hnae_ae_ops *ops;
- assert(priv || priv->ae_handle);
-
h = priv->ae_handle;
ops = h->dev->ops;
@@ -780,8 +775,6 @@ static int hns_set_coalesce(struct net_device *net_dev,
struct hnae_ae_ops *ops;
int ret;
- assert(priv || priv->ae_handle);
-
ops = priv->ae_handle->dev->ops;
if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs)
@@ -1111,8 +1104,6 @@ void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
struct hns_nic_priv *priv = netdev_priv(net_dev);
struct hnae_ae_ops *ops;
- assert(priv || priv->ae_handle);
-
ops = priv->ae_handle->dev->ops;
cmd->version = HNS_CHIP_VERSION;
@@ -1135,8 +1126,6 @@ static int hns_get_regs_len(struct net_device *net_dev)
struct hns_nic_priv *priv = netdev_priv(net_dev);
struct hnae_ae_ops *ops;
- assert(priv || priv->ae_handle);
-
ops = priv->ae_handle->dev->ops;
if (!ops->get_regs_len) {
netdev_err(net_dev, "ops->get_regs_len is null!\n");
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 864cb21351a4..ecdb6854a898 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2121,7 +2121,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
struct ibmvnic_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
- struct ibmvnic_error_buff *error_buff;
+ struct ibmvnic_error_buff *error_buff, *tmp;
unsigned long flags;
bool found = false;
int i;
@@ -2133,7 +2133,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
}
spin_lock_irqsave(&adapter->error_list_lock, flags);
- list_for_each_entry(error_buff, &adapter->errors, list)
+ list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
if (error_buff->error_id == crq->request_error_rsp.error_id) {
found = true;
list_del(&error_buff->list);
@@ -3141,14 +3141,14 @@ static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq,
static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
{
- struct ibmvnic_inflight_cmd *inflight_cmd;
+ struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
struct device *dev = &adapter->vdev->dev;
- struct ibmvnic_error_buff *error_buff;
+ struct ibmvnic_error_buff *error_buff, *tmp2;
unsigned long flags;
unsigned long flags2;
spin_lock_irqsave(&adapter->inflight_lock, flags);
- list_for_each_entry(inflight_cmd, &adapter->inflight, list) {
+ list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) {
switch (inflight_cmd->crq.generic.cmd) {
case LOGIN:
dma_unmap_single(dev, adapter->login_buf_token,
@@ -3165,8 +3165,8 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
break;
case REQUEST_ERROR_INFO:
spin_lock_irqsave(&adapter->error_list_lock, flags2);
- list_for_each_entry(error_buff, &adapter->errors,
- list) {
+ list_for_each_entry_safe(error_buff, tmp2,
+ &adapter->errors, list) {
dma_unmap_single(dev, error_buff->dma,
error_buff->len,
DMA_FROM_DEVICE);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 75e60897b7e7..73f745205a1c 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -154,6 +154,16 @@ void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
writel(val, hw->hw_addr + reg);
}
+static bool e1000e_vlan_used(struct e1000_adapter *adapter)
+{
+ u16 vid;
+
+ for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
+ return true;
+
+ return false;
+}
+
/**
* e1000_regdump - register printout routine
* @hw: pointer to the HW structure
@@ -2789,7 +2799,7 @@ static void e1000e_vlan_filter_enable(struct e1000_adapter *adapter)
}
/**
- * e1000e_vlan_strip_enable - helper to disable HW VLAN stripping
+ * e1000e_vlan_strip_disable - helper to disable HW VLAN stripping
* @adapter: board private structure to initialize
**/
static void e1000e_vlan_strip_disable(struct e1000_adapter *adapter)
@@ -3443,7 +3453,8 @@ static void e1000e_set_rx_mode(struct net_device *netdev)
ew32(RCTL, rctl);
- if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+ if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX ||
+ e1000e_vlan_used(adapter))
e1000e_vlan_strip_enable(adapter);
else
e1000e_vlan_strip_disable(adapter);
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c
index 01fccec632ec..466939f8f0cf 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.c
+++ b/drivers/net/ethernet/marvell/mvneta_bm.c
@@ -189,6 +189,7 @@ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
hwbm_pool->construct = mvneta_bm_construct;
hwbm_pool->priv = new_pool;
+ spin_lock_init(&hwbm_pool->lock);
/* Create new pool */
err = mvneta_bm_pool_create(priv, new_pool);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c984462fad2a..d1cdc2d76151 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -133,6 +133,8 @@ static int mtk_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg)
static void mtk_phy_link_adjust(struct net_device *dev)
{
struct mtk_mac *mac = netdev_priv(dev);
+ u16 lcl_adv = 0, rmt_adv = 0;
+ u8 flowctrl;
u32 mcr = MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG |
MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN |
MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN |
@@ -150,11 +152,30 @@ static void mtk_phy_link_adjust(struct net_device *dev)
if (mac->phy_dev->link)
mcr |= MAC_MCR_FORCE_LINK;
- if (mac->phy_dev->duplex)
+ if (mac->phy_dev->duplex) {
mcr |= MAC_MCR_FORCE_DPX;
- if (mac->phy_dev->pause)
- mcr |= MAC_MCR_FORCE_RX_FC | MAC_MCR_FORCE_TX_FC;
+ if (mac->phy_dev->pause)
+ rmt_adv = LPA_PAUSE_CAP;
+ if (mac->phy_dev->asym_pause)
+ rmt_adv |= LPA_PAUSE_ASYM;
+
+ if (mac->phy_dev->advertising & ADVERTISED_Pause)
+ lcl_adv |= ADVERTISE_PAUSE_CAP;
+ if (mac->phy_dev->advertising & ADVERTISED_Asym_Pause)
+ lcl_adv |= ADVERTISE_PAUSE_ASYM;
+
+ flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
+
+ if (flowctrl & FLOW_CTRL_TX)
+ mcr |= MAC_MCR_FORCE_TX_FC;
+ if (flowctrl & FLOW_CTRL_RX)
+ mcr |= MAC_MCR_FORCE_RX_FC;
+
+ netif_dbg(mac->hw, link, dev, "rx pause %s, tx pause %s\n",
+ flowctrl & FLOW_CTRL_RX ? "enabled" : "disabled",
+ flowctrl & FLOW_CTRL_TX ? "enabled" : "disabled");
+ }
mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
@@ -208,10 +229,16 @@ static int mtk_phy_connect(struct mtk_mac *mac)
u32 val, ge_mode;
np = of_parse_phandle(mac->of_node, "phy-handle", 0);
+ if (!np && of_phy_is_fixed_link(mac->of_node))
+ if (!of_phy_register_fixed_link(mac->of_node))
+ np = of_node_get(mac->of_node);
if (!np)
return -ENODEV;
switch (of_get_phy_mode(np)) {
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_ID:
case PHY_INTERFACE_MODE_RGMII:
ge_mode = 0;
break;
@@ -236,7 +263,8 @@ static int mtk_phy_connect(struct mtk_mac *mac)
mac->phy_dev->autoneg = AUTONEG_ENABLE;
mac->phy_dev->speed = 0;
mac->phy_dev->duplex = 0;
- mac->phy_dev->supported &= PHY_BASIC_FEATURES;
+ mac->phy_dev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause |
+ SUPPORTED_Asym_Pause;
mac->phy_dev->advertising = mac->phy_dev->supported |
ADVERTISED_Autoneg;
phy_start_aneg(mac->phy_dev);
@@ -280,7 +308,7 @@ static int mtk_mdio_init(struct mtk_eth *eth)
return 0;
err_free_bus:
- kfree(eth->mii_bus);
+ mdiobus_free(eth->mii_bus);
err_put_node:
of_node_put(mii_np);
@@ -295,7 +323,7 @@ static void mtk_mdio_cleanup(struct mtk_eth *eth)
mdiobus_unregister(eth->mii_bus);
of_node_put(eth->mii_bus->dev.of_node);
- kfree(eth->mii_bus);
+ mdiobus_free(eth->mii_bus);
}
static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
@@ -453,20 +481,23 @@ static inline void mtk_rx_get_desc(struct mtk_rx_dma *rxd,
/* the qdma core needs scratch memory to be setup */
static int mtk_init_fq_dma(struct mtk_eth *eth)
{
- dma_addr_t phy_ring_head, phy_ring_tail;
+ dma_addr_t phy_ring_tail;
int cnt = MTK_DMA_SIZE;
dma_addr_t dma_addr;
int i;
eth->scratch_ring = dma_alloc_coherent(eth->dev,
cnt * sizeof(struct mtk_tx_dma),
- &phy_ring_head,
+ &eth->phy_scratch_ring,
GFP_ATOMIC | __GFP_ZERO);
if (unlikely(!eth->scratch_ring))
return -ENOMEM;
eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE,
GFP_KERNEL);
+ if (unlikely(!eth->scratch_head))
+ return -ENOMEM;
+
dma_addr = dma_map_single(eth->dev,
eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE,
DMA_FROM_DEVICE);
@@ -474,19 +505,19 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
return -ENOMEM;
memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
- phy_ring_tail = phy_ring_head +
+ phy_ring_tail = eth->phy_scratch_ring +
(sizeof(struct mtk_tx_dma) * (cnt - 1));
for (i = 0; i < cnt; i++) {
eth->scratch_ring[i].txd1 =
(dma_addr + (i * MTK_QDMA_PAGE_SIZE));
if (i < cnt - 1)
- eth->scratch_ring[i].txd2 = (phy_ring_head +
+ eth->scratch_ring[i].txd2 = (eth->phy_scratch_ring +
((i + 1) * sizeof(struct mtk_tx_dma)));
eth->scratch_ring[i].txd3 = TX_DMA_SDL(MTK_QDMA_PAGE_SIZE);
}
- mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD);
+ mtk_w32(eth, eth->phy_scratch_ring, MTK_QDMA_FQ_HEAD);
mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL);
mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT);
mtk_w32(eth, MTK_QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN);
@@ -643,7 +674,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
err_dma:
do {
- tx_buf = mtk_desc_to_tx_buf(ring, txd);
+ tx_buf = mtk_desc_to_tx_buf(ring, itxd);
/* unmap dma */
mtk_tx_unmap(&dev->dev, tx_buf);
@@ -673,6 +704,20 @@ static inline int mtk_cal_txd_req(struct sk_buff *skb)
return nfrags;
}
+static int mtk_queue_stopped(struct mtk_eth *eth)
+{
+ int i;
+
+ for (i = 0; i < MTK_MAC_COUNT; i++) {
+ if (!eth->netdev[i])
+ continue;
+ if (netif_queue_stopped(eth->netdev[i]))
+ return 1;
+ }
+
+ return 0;
+}
+
static void mtk_wake_queue(struct mtk_eth *eth)
{
int i;
@@ -738,12 +783,9 @@ static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
if (mtk_tx_map(skb, dev, tx_num, ring, gso) < 0)
goto drop;
- if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) {
+ if (unlikely(atomic_read(&ring->free_count) <= ring->thresh))
mtk_stop_queue(eth);
- if (unlikely(atomic_read(&ring->free_count) >
- ring->thresh))
- mtk_wake_queue(eth);
- }
+
spin_unlock_irqrestore(&eth->page_lock, flags);
return NETDEV_TX_OK;
@@ -798,6 +840,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
DMA_FROM_DEVICE);
if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
skb_free_frag(new_data);
+ netdev->stats.rx_dropped++;
goto release_desc;
}
@@ -805,6 +848,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
skb = build_skb(data, ring->frag_size);
if (unlikely(!skb)) {
put_page(virt_to_head_page(new_data));
+ netdev->stats.rx_dropped++;
goto release_desc;
}
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
@@ -893,7 +937,6 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
}
mtk_tx_unmap(eth->dev, tx_buf);
- ring->last_free->txd2 = next_cpu;
ring->last_free = desc;
atomic_inc(&ring->free_count);
@@ -918,7 +961,8 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
if (!total)
return 0;
- if (atomic_read(&ring->free_count) > ring->thresh)
+ if (mtk_queue_stopped(eth) &&
+ (atomic_read(&ring->free_count) > ring->thresh))
mtk_wake_queue(eth);
return total;
@@ -999,9 +1043,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
atomic_set(&ring->free_count, MTK_DMA_SIZE - 2);
ring->next_free = &ring->dma[0];
- ring->last_free = &ring->dma[MTK_DMA_SIZE - 2];
- ring->thresh = max((unsigned long)MTK_DMA_SIZE >> 2,
- MAX_SKB_FRAGS);
+ ring->last_free = &ring->dma[MTK_DMA_SIZE - 1];
+ ring->thresh = MAX_SKB_FRAGS;
/* make sure that all changes to the dma ring are flushed before we
* continue
@@ -1179,6 +1222,14 @@ static void mtk_dma_free(struct mtk_eth *eth)
for (i = 0; i < MTK_MAC_COUNT; i++)
if (eth->netdev[i])
netdev_reset_queue(eth->netdev[i]);
+ if (eth->scratch_ring) {
+ dma_free_coherent(eth->dev,
+ MTK_DMA_SIZE * sizeof(struct mtk_tx_dma),
+ eth->scratch_ring,
+ eth->phy_scratch_ring);
+ eth->scratch_ring = NULL;
+ eth->phy_scratch_ring = 0;
+ }
mtk_tx_clean(eth);
mtk_rx_clean(eth);
kfree(eth->scratch_head);
@@ -1241,7 +1292,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
mtk_w32(eth,
MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN |
MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS |
- MTK_RX_BT_32DWORDS,
+ MTK_RX_BT_32DWORDS | MTK_NDP_CO_PRO,
MTK_QDMA_GLO_CFG);
return 0;
@@ -1355,7 +1406,7 @@ static int __init mtk_hw_init(struct mtk_eth *eth)
/* disable delay and normal interrupt */
mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
- mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+ mtk_irq_disable(eth, ~0);
mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
mtk_w32(eth, 0, MTK_RST_GL);
@@ -1669,7 +1720,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
SET_NETDEV_DEV(eth->netdev[id], eth->dev);
- eth->netdev[id]->watchdog_timeo = HZ;
+ eth->netdev[id]->watchdog_timeo = 5 * HZ;
eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
eth->netdev[id]->base_addr = (unsigned long)eth->base;
eth->netdev[id]->vlan_features = MTK_HW_FEATURES &
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index eed626d56ea4..a5eb7c62306b 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -91,6 +91,7 @@
#define MTK_QDMA_GLO_CFG 0x1A04
#define MTK_RX_2B_OFFSET BIT(31)
#define MTK_RX_BT_32DWORDS (3 << 11)
+#define MTK_NDP_CO_PRO BIT(10)
#define MTK_TX_WB_DDONE BIT(6)
#define MTK_DMA_SIZE_16DWORDS (2 << 4)
#define MTK_RX_DMA_BUSY BIT(3)
@@ -357,6 +358,7 @@ struct mtk_rx_ring {
* @rx_ring: Pointer to the memore holding info about the RX ring
* @rx_napi: The NAPI struct
* @scratch_ring: Newer SoCs need memory for a second HW managed TX ring
+ * @phy_scratch_ring: physical address of scratch_ring
* @scratch_head: The scratch memory that scratch_ring points to.
* @clk_ethif: The ethif clock
* @clk_esw: The switch clock
@@ -384,6 +386,7 @@ struct mtk_eth {
struct mtk_rx_ring rx_ring;
struct napi_struct rx_napi;
struct mtk_tx_dma *scratch_ring;
+ dma_addr_t phy_scratch_ring;
void *scratch_head;
struct clk *clk_ethif;
struct clk *clk_esw;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e94ca1c3fc7c..f04a423ff79d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2597,7 +2597,6 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
priv->cmd.free_head = 0;
sema_init(&priv->cmd.event_sem, priv->cmd.max_cmds);
- spin_lock_init(&priv->cmd.context_lock);
for (priv->cmd.token_mask = 1;
priv->cmd.token_mask < priv->cmd.max_cmds;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c761194bb323..fc95affaf76b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -362,7 +362,7 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
for (i = 0; i < NUM_MAIN_STATS; i++, bitmap_iterator_inc(&it))
if (bitmap_iterator_test(&it))
- data[index++] = ((unsigned long *)&priv->stats)[i];
+ data[index++] = ((unsigned long *)&dev->stats)[i];
for (i = 0; i < NUM_PORT_STATS; i++, bitmap_iterator_inc(&it))
if (bitmap_iterator_test(&it))
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 92e0624f4cf0..0c0dfd6cdca6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -406,14 +406,18 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev,
mutex_lock(&mdev->state_lock);
if (mdev->device_up && priv->port_up) {
err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
- if (err)
+ if (err) {
en_err(priv, "Failed configuring VLAN filter\n");
+ goto out;
+ }
}
- if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
- en_dbg(HW, priv, "failed adding vlan %d\n", vid);
- mutex_unlock(&mdev->state_lock);
+ err = mlx4_register_vlan(mdev->dev, priv->port, vid, &idx);
+ if (err)
+ en_dbg(HW, priv, "Failed adding vlan %d\n", vid);
- return 0;
+out:
+ mutex_unlock(&mdev->state_lock);
+ return err;
}
static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
@@ -421,7 +425,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
- int err;
+ int err = 0;
en_dbg(HW, priv, "Killing VID:%d\n", vid);
@@ -438,7 +442,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
}
mutex_unlock(&mdev->state_lock);
- return 0;
+ return err;
}
static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
@@ -1296,15 +1300,16 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
}
-static struct net_device_stats *mlx4_en_get_stats(struct net_device *dev)
+static struct rtnl_link_stats64 *
+mlx4_en_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
spin_lock_bh(&priv->stats_lock);
- memcpy(&priv->ret_stats, &priv->stats, sizeof(priv->stats));
+ netdev_stats_to_stats64(stats, &dev->stats);
spin_unlock_bh(&priv->stats_lock);
- return &priv->ret_stats;
+ return stats;
}
static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
@@ -1876,7 +1881,6 @@ static void mlx4_en_clear_stats(struct net_device *dev)
if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
en_dbg(HW, priv, "Failed dumping statistics\n");
- memset(&priv->stats, 0, sizeof(priv->stats));
memset(&priv->pstats, 0, sizeof(priv->pstats));
memset(&priv->pkstats, 0, sizeof(priv->pkstats));
memset(&priv->port_stats, 0, sizeof(priv->port_stats));
@@ -1892,6 +1896,11 @@ static void mlx4_en_clear_stats(struct net_device *dev)
priv->tx_ring[i]->bytes = 0;
priv->tx_ring[i]->packets = 0;
priv->tx_ring[i]->tx_csum = 0;
+ priv->tx_ring[i]->tx_dropped = 0;
+ priv->tx_ring[i]->queue_stopped = 0;
+ priv->tx_ring[i]->wake_queue = 0;
+ priv->tx_ring[i]->tso_packets = 0;
+ priv->tx_ring[i]->xmit_more = 0;
}
for (i = 0; i < priv->rx_ring_num; i++) {
priv->rx_ring[i]->bytes = 0;
@@ -2027,11 +2036,20 @@ err:
return -ENOMEM;
}
+static void mlx4_en_shutdown(struct net_device *dev)
+{
+ rtnl_lock();
+ netif_device_detach(dev);
+ mlx4_en_close(dev);
+ rtnl_unlock();
+}
void mlx4_en_destroy_netdev(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ bool shutdown = mdev->dev->persist->interface_state &
+ MLX4_INTERFACE_STATE_SHUTDOWN;
en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
@@ -2039,7 +2057,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
if (priv->registered) {
devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev,
priv->port));
- unregister_netdev(dev);
+ if (shutdown)
+ mlx4_en_shutdown(dev);
+ else
+ unregister_netdev(dev);
}
if (priv->allocated)
@@ -2064,7 +2085,8 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
kfree(priv->tx_ring);
kfree(priv->tx_cq);
- free_netdev(dev);
+ if (!shutdown)
+ free_netdev(dev);
}
static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
@@ -2442,9 +2464,14 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
* strip that feature if this is an IPv6 encapsulated frame.
*/
if (skb->encapsulation &&
- (skb->ip_summed == CHECKSUM_PARTIAL) &&
- (ip_hdr(skb)->version != 4))
- features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ (skb->ip_summed == CHECKSUM_PARTIAL)) {
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+
+ if (!priv->vxlan_port ||
+ (ip_hdr(skb)->version != 4) ||
+ (udp_hdr(skb)->dest != priv->vxlan_port))
+ features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
return features;
}
@@ -2482,7 +2509,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
.ndo_stop = mlx4_en_close,
.ndo_start_xmit = mlx4_en_xmit,
.ndo_select_queue = mlx4_en_select_queue,
- .ndo_get_stats = mlx4_en_get_stats,
+ .ndo_get_stats64 = mlx4_en_get_stats64,
.ndo_set_rx_mode = mlx4_en_set_rx_mode,
.ndo_set_mac_address = mlx4_en_set_mac,
.ndo_validate_addr = eth_validate_addr,
@@ -2514,7 +2541,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
.ndo_stop = mlx4_en_close,
.ndo_start_xmit = mlx4_en_xmit,
.ndo_select_queue = mlx4_en_select_queue,
- .ndo_get_stats = mlx4_en_get_stats,
+ .ndo_get_stats64 = mlx4_en_get_stats64,
.ndo_set_rx_mode = mlx4_en_set_rx_mode,
.ndo_set_mac_address = mlx4_en_set_mac,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 20b6c2e678b8..5aa8b751f417 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -152,8 +152,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
struct mlx4_counter tmp_counter_stats;
struct mlx4_en_stat_out_mbox *mlx4_en_stats;
struct mlx4_en_stat_out_flow_control_mbox *flowstats;
- struct mlx4_en_priv *priv = netdev_priv(mdev->pndev[port]);
- struct net_device_stats *stats = &priv->stats;
+ struct net_device *dev = mdev->pndev[port];
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
struct mlx4_cmd_mailbox *mailbox;
u64 in_mod = reset << 8 | port;
int err;
@@ -188,6 +189,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
}
stats->tx_packets = 0;
stats->tx_bytes = 0;
+ stats->tx_dropped = 0;
priv->port_stats.tx_chksum_offload = 0;
priv->port_stats.queue_stopped = 0;
priv->port_stats.wake_queue = 0;
@@ -199,6 +201,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
stats->tx_packets += ring->packets;
stats->tx_bytes += ring->bytes;
+ stats->tx_dropped += ring->tx_dropped;
priv->port_stats.tx_chksum_offload += ring->tx_csum;
priv->port_stats.queue_stopped += ring->queue_stopped;
priv->port_stats.wake_queue += ring->wake_queue;
@@ -237,21 +240,12 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
stats->multicast = en_stats_adder(&mlx4_en_stats->MCAST_prio_0,
&mlx4_en_stats->MCAST_prio_1,
NUM_PRIORITIES);
- stats->collisions = 0;
stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP) +
sw_rx_dropped;
stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
- stats->rx_over_errors = 0;
stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
- stats->rx_frame_errors = 0;
stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
- stats->rx_missed_errors = 0;
- stats->tx_aborted_errors = 0;
- stats->tx_carrier_errors = 0;
- stats->tx_fifo_errors = 0;
- stats->tx_heartbeat_errors = 0;
- stats->tx_window_errors = 0;
- stats->tx_dropped = be32_to_cpu(mlx4_en_stats->TDROP);
+ stats->tx_dropped += be32_to_cpu(mlx4_en_stats->TDROP);
/* RX stats */
priv->pkstats.rx_multicast_packets = stats->multicast;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f6e61570cb2c..76aa4d27183c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -726,12 +726,12 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
bool inline_ok;
u32 ring_cons;
- if (!priv->port_up)
- goto tx_drop;
-
tx_ind = skb_get_queue_mapping(skb);
ring = priv->tx_ring[tx_ind];
+ if (!priv->port_up)
+ goto tx_drop;
+
/* fetch ring->cons far ahead before needing it to avoid stall */
ring_cons = ACCESS_ONCE(ring->cons);
@@ -1030,7 +1030,7 @@ tx_drop_unmap:
tx_drop:
dev_kfree_skb_any(skb);
- priv->stats.tx_dropped++;
+ ring->tx_dropped++;
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12c77a70abdb..546fab0ecc3b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3222,6 +3222,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
INIT_LIST_HEAD(&priv->pgdir_list);
mutex_init(&priv->pgdir_mutex);
+ spin_lock_init(&priv->cmd.context_lock);
INIT_LIST_HEAD(&priv->bf_list);
mutex_init(&priv->bf_mutex);
@@ -4134,8 +4135,11 @@ static void mlx4_shutdown(struct pci_dev *pdev)
mlx4_info(persist->dev, "mlx4_shutdown was called\n");
mutex_lock(&persist->interface_state_mutex);
- if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
+ if (persist->interface_state & MLX4_INTERFACE_STATE_UP) {
+ /* Notify mlx4 clients that the kernel is being shut down */
+ persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN;
mlx4_unload_one(pdev);
+ }
mutex_unlock(&persist->interface_state_mutex);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index cc84e09f324a..467d47ed2c39 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -270,6 +270,7 @@ struct mlx4_en_tx_ring {
unsigned long tx_csum;
unsigned long tso_packets;
unsigned long xmit_more;
+ unsigned int tx_dropped;
struct mlx4_bf bf;
unsigned long queue_stopped;
@@ -482,8 +483,6 @@ struct mlx4_en_priv {
struct mlx4_en_port_profile *prof;
struct net_device *dev;
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
- struct net_device_stats stats;
- struct net_device_stats ret_stats;
struct mlx4_en_port_state port_state;
spinlock_t stats_lock;
struct ethtool_flow_id ethtool_rules[MAX_NUM_OF_FS_RULES];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index dcd2df6518de..0b4986268cc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -545,6 +545,7 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(ALLOC_FLOW_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_FLOW_COUNTER);
MLX5_COMMAND_STR_CASE(QUERY_FLOW_COUNTER);
+ MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
default: return "unknown command opcode";
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e8a6c3325b39..baa991a23475 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -401,7 +401,7 @@ enum mlx5e_traffic_types {
};
enum {
- MLX5E_STATE_ASYNC_EVENTS_ENABLE,
+ MLX5E_STATE_ASYNC_EVENTS_ENABLED,
MLX5E_STATE_OPENED,
MLX5E_STATE_DESTROYING,
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fc7dcc03b1de..e667a870e0c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -184,7 +184,9 @@ static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
#define MLX5E_NUM_SQ_STATS(priv) \
(NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \
test_bit(MLX5E_STATE_OPENED, &priv->state))
-#define MLX5E_NUM_PFC_COUNTERS(priv) hweight8(mlx5e_query_pfc_combined(priv))
+#define MLX5E_NUM_PFC_COUNTERS(priv) \
+ (hweight8(mlx5e_query_pfc_combined(priv)) * \
+ NUM_PPORT_PER_PRIO_PFC_COUNTERS)
static int mlx5e_get_sset_count(struct net_device *dev, int sset)
{
@@ -211,42 +213,41 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
/* SW counters */
for (i = 0; i < NUM_SW_COUNTERS; i++)
- strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].name);
+ strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format);
/* Q counters */
for (i = 0; i < MLX5E_NUM_Q_CNTRS(priv); i++)
- strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].name);
+ strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format);
/* VPORT counters */
for (i = 0; i < NUM_VPORT_COUNTERS; i++)
strcpy(data + (idx++) * ETH_GSTRING_LEN,
- vport_stats_desc[i].name);
+ vport_stats_desc[i].format);
/* PPORT counters */
for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
strcpy(data + (idx++) * ETH_GSTRING_LEN,
- pport_802_3_stats_desc[i].name);
+ pport_802_3_stats_desc[i].format);
for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
strcpy(data + (idx++) * ETH_GSTRING_LEN,
- pport_2863_stats_desc[i].name);
+ pport_2863_stats_desc[i].format);
for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
strcpy(data + (idx++) * ETH_GSTRING_LEN,
- pport_2819_stats_desc[i].name);
+ pport_2819_stats_desc[i].format);
for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
- sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s",
- prio,
- pport_per_prio_traffic_stats_desc[i].name);
+ sprintf(data + (idx++) * ETH_GSTRING_LEN,
+ pport_per_prio_traffic_stats_desc[i].format, prio);
}
pfc_combined = mlx5e_query_pfc_combined(priv);
for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
- sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s",
- prio, pport_per_prio_pfc_stats_desc[i].name);
+ sprintf(data + (idx++) * ETH_GSTRING_LEN,
+ pport_per_prio_pfc_stats_desc[i].format, prio);
}
}
@@ -256,16 +257,15 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
/* per channel counters */
for (i = 0; i < priv->params.num_channels; i++)
for (j = 0; j < NUM_RQ_STATS; j++)
- sprintf(data + (idx++) * ETH_GSTRING_LEN, "rx%d_%s", i,
- rq_stats_desc[j].name);
+ sprintf(data + (idx++) * ETH_GSTRING_LEN,
+ rq_stats_desc[j].format, i);
for (tc = 0; tc < priv->params.num_tc; tc++)
for (i = 0; i < priv->params.num_channels; i++)
for (j = 0; j < NUM_SQ_STATS; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
- "tx%d_%s",
- priv->channeltc_to_txq_map[i][tc],
- sq_stats_desc[j].name);
+ sq_stats_desc[j].format,
+ priv->channeltc_to_txq_map[i][tc]);
}
static void mlx5e_get_strings(struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fd4392999eee..cb6defd71fc1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -105,11 +105,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
s->rx_packets += rq_stats->packets;
s->rx_bytes += rq_stats->bytes;
- s->lro_packets += rq_stats->lro_packets;
- s->lro_bytes += rq_stats->lro_bytes;
+ s->rx_lro_packets += rq_stats->lro_packets;
+ s->rx_lro_bytes += rq_stats->lro_bytes;
s->rx_csum_none += rq_stats->csum_none;
- s->rx_csum_sw += rq_stats->csum_sw;
- s->rx_csum_inner += rq_stats->csum_inner;
+ s->rx_csum_complete += rq_stats->csum_complete;
+ s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
s->rx_wqe_err += rq_stats->wqe_err;
s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
s->rx_mpwqe_frag += rq_stats->mpwqe_frag;
@@ -122,24 +122,23 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
s->tx_packets += sq_stats->packets;
s->tx_bytes += sq_stats->bytes;
- s->tso_packets += sq_stats->tso_packets;
- s->tso_bytes += sq_stats->tso_bytes;
- s->tso_inner_packets += sq_stats->tso_inner_packets;
- s->tso_inner_bytes += sq_stats->tso_inner_bytes;
+ s->tx_tso_packets += sq_stats->tso_packets;
+ s->tx_tso_bytes += sq_stats->tso_bytes;
+ s->tx_tso_inner_packets += sq_stats->tso_inner_packets;
+ s->tx_tso_inner_bytes += sq_stats->tso_inner_bytes;
s->tx_queue_stopped += sq_stats->stopped;
s->tx_queue_wake += sq_stats->wake;
s->tx_queue_dropped += sq_stats->dropped;
- s->tx_csum_inner += sq_stats->csum_offload_inner;
- tx_offload_none += sq_stats->csum_offload_none;
+ s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
+ tx_offload_none += sq_stats->csum_none;
}
}
/* Update calculated offload counters */
- s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner;
- s->rx_csum_good = s->rx_packets - s->rx_csum_none -
- s->rx_csum_sw;
+ s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
+ s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete;
- s->link_down_events = MLX5_GET(ppcnt_reg,
+ s->link_down_events_phy = MLX5_GET(ppcnt_reg,
priv->stats.pport.phy_counters,
counter_set.phys_layer_cntrs.link_down_events);
}
@@ -244,7 +243,7 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
{
struct mlx5e_priv *priv = vpriv;
- if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state))
+ if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
return;
switch (event) {
@@ -260,12 +259,12 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
{
- set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+ set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
}
static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
{
- clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+ clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
}
@@ -580,7 +579,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
int err;
- err = mlx5_alloc_map_uar(mdev, &sq->uar, true);
+ err = mlx5_alloc_map_uar(mdev, &sq->uar, !!MLX5_CAP_GEN(mdev, bf));
if (err)
return err;
@@ -3192,10 +3191,7 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv)
flush_workqueue(priv->wq);
if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) {
netif_device_detach(netdev);
- mutex_lock(&priv->state_lock);
- if (test_bit(MLX5E_STATE_OPENED, &priv->state))
- mlx5e_close_locked(netdev);
- mutex_unlock(&priv->state_lock);
+ mlx5e_close(netdev);
} else {
unregister_netdev(netdev);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index bd947704b59c..022acc2e8922 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -689,7 +689,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
if (is_first_ethertype_ip(skb)) {
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
- rq->stats.csum_sw++;
+ rq->stats.csum_complete++;
return;
}
@@ -699,7 +699,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
if (cqe_is_tunneled(cqe)) {
skb->csum_level = 1;
skb->encapsulation = 1;
- rq->stats.csum_inner++;
+ rq->stats.csum_unnecessary_inner++;
}
return;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 83bc32b25849..fcd490cc5610 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -42,9 +42,11 @@
be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
#define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
+#define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
struct counter_desc {
- char name[ETH_GSTRING_LEN];
+ char format[ETH_GSTRING_LEN];
int offset; /* Byte offset */
};
@@ -53,18 +55,18 @@ struct mlx5e_sw_stats {
u64 rx_bytes;
u64 tx_packets;
u64 tx_bytes;
- u64 tso_packets;
- u64 tso_bytes;
- u64 tso_inner_packets;
- u64 tso_inner_bytes;
- u64 lro_packets;
- u64 lro_bytes;
- u64 rx_csum_good;
+ u64 tx_tso_packets;
+ u64 tx_tso_bytes;
+ u64 tx_tso_inner_packets;
+ u64 tx_tso_inner_bytes;
+ u64 rx_lro_packets;
+ u64 rx_lro_bytes;
+ u64 rx_csum_unnecessary;
u64 rx_csum_none;
- u64 rx_csum_sw;
- u64 rx_csum_inner;
- u64 tx_csum_offload;
- u64 tx_csum_inner;
+ u64 rx_csum_complete;
+ u64 rx_csum_unnecessary_inner;
+ u64 tx_csum_partial;
+ u64 tx_csum_partial_inner;
u64 tx_queue_stopped;
u64 tx_queue_wake;
u64 tx_queue_dropped;
@@ -76,7 +78,7 @@ struct mlx5e_sw_stats {
u64 rx_cqe_compress_pkts;
/* Special handling counters */
- u64 link_down_events;
+ u64 link_down_events_phy;
};
static const struct counter_desc sw_stats_desc[] = {
@@ -84,18 +86,18 @@ static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_good) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_packets) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_bytes) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_sw) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_inner) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_offload) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_inner) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
@@ -105,7 +107,7 @@ static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
};
struct mlx5e_qcounter_stats {
@@ -125,12 +127,6 @@ struct mlx5e_vport_stats {
};
static const struct counter_desc vport_stats_desc[] = {
- { "rx_vport_error_packets",
- VPORT_COUNTER_OFF(received_errors.packets) },
- { "rx_vport_error_bytes", VPORT_COUNTER_OFF(received_errors.octets) },
- { "tx_vport_error_packets",
- VPORT_COUNTER_OFF(transmit_errors.packets) },
- { "tx_vport_error_bytes", VPORT_COUNTER_OFF(transmit_errors.octets) },
{ "rx_vport_unicast_packets",
VPORT_COUNTER_OFF(received_eth_unicast.packets) },
{ "rx_vport_unicast_bytes",
@@ -192,94 +188,68 @@ struct mlx5e_pport_stats {
};
static const struct counter_desc pport_802_3_stats_desc[] = {
- { "frames_tx", PPORT_802_3_OFF(a_frames_transmitted_ok) },
- { "frames_rx", PPORT_802_3_OFF(a_frames_received_ok) },
- { "check_seq_err", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
- { "alignment_err", PPORT_802_3_OFF(a_alignment_errors) },
- { "octets_tx", PPORT_802_3_OFF(a_octets_transmitted_ok) },
- { "octets_received", PPORT_802_3_OFF(a_octets_received_ok) },
- { "multicast_xmitted", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
- { "broadcast_xmitted", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
- { "multicast_rx", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
- { "broadcast_rx", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
- { "in_range_len_errors", PPORT_802_3_OFF(a_in_range_length_errors) },
- { "out_of_range_len", PPORT_802_3_OFF(a_out_of_range_length_field) },
- { "too_long_errors", PPORT_802_3_OFF(a_frame_too_long_errors) },
- { "symbol_err", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
- { "mac_control_tx", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
- { "mac_control_rx", PPORT_802_3_OFF(a_mac_control_frames_received) },
- { "unsupported_op_rx",
- PPORT_802_3_OFF(a_unsupported_opcodes_received) },
- { "pause_ctrl_rx", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
- { "pause_ctrl_tx",
- PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
+ { "tx_packets_phy", PPORT_802_3_OFF(a_frames_transmitted_ok) },
+ { "rx_packets_phy", PPORT_802_3_OFF(a_frames_received_ok) },
+ { "rx_crc_errors_phy", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
+ { "tx_bytes_phy", PPORT_802_3_OFF(a_octets_transmitted_ok) },
+ { "rx_bytes_phy", PPORT_802_3_OFF(a_octets_received_ok) },
+ { "tx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
+ { "tx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
+ { "rx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
+ { "rx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
+ { "rx_in_range_len_errors_phy", PPORT_802_3_OFF(a_in_range_length_errors) },
+ { "rx_out_of_range_len_phy", PPORT_802_3_OFF(a_out_of_range_length_field) },
+ { "rx_oversize_pkts_phy", PPORT_802_3_OFF(a_frame_too_long_errors) },
+ { "rx_symbol_err_phy", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
+ { "tx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
+ { "rx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_received) },
+ { "rx_unsupported_op_phy", PPORT_802_3_OFF(a_unsupported_opcodes_received) },
+ { "rx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
+ { "tx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
};
static const struct counter_desc pport_2863_stats_desc[] = {
- { "in_octets", PPORT_2863_OFF(if_in_octets) },
- { "in_ucast_pkts", PPORT_2863_OFF(if_in_ucast_pkts) },
- { "in_discards", PPORT_2863_OFF(if_in_discards) },
- { "in_errors", PPORT_2863_OFF(if_in_errors) },
- { "in_unknown_protos", PPORT_2863_OFF(if_in_unknown_protos) },
- { "out_octets", PPORT_2863_OFF(if_out_octets) },
- { "out_ucast_pkts", PPORT_2863_OFF(if_out_ucast_pkts) },
- { "out_discards", PPORT_2863_OFF(if_out_discards) },
- { "out_errors", PPORT_2863_OFF(if_out_errors) },
- { "in_multicast_pkts", PPORT_2863_OFF(if_in_multicast_pkts) },
- { "in_broadcast_pkts", PPORT_2863_OFF(if_in_broadcast_pkts) },
- { "out_multicast_pkts", PPORT_2863_OFF(if_out_multicast_pkts) },
- { "out_broadcast_pkts", PPORT_2863_OFF(if_out_broadcast_pkts) },
+ { "rx_discards_phy", PPORT_2863_OFF(if_in_discards) },
+ { "tx_discards_phy", PPORT_2863_OFF(if_out_discards) },
+ { "tx_errors_phy", PPORT_2863_OFF(if_out_errors) },
};
static const struct counter_desc pport_2819_stats_desc[] = {
- { "drop_events", PPORT_2819_OFF(ether_stats_drop_events) },
- { "octets", PPORT_2819_OFF(ether_stats_octets) },
- { "pkts", PPORT_2819_OFF(ether_stats_pkts) },
- { "broadcast_pkts", PPORT_2819_OFF(ether_stats_broadcast_pkts) },
- { "multicast_pkts", PPORT_2819_OFF(ether_stats_multicast_pkts) },
- { "crc_align_errors", PPORT_2819_OFF(ether_stats_crc_align_errors) },
- { "undersize_pkts", PPORT_2819_OFF(ether_stats_undersize_pkts) },
- { "oversize_pkts", PPORT_2819_OFF(ether_stats_oversize_pkts) },
- { "fragments", PPORT_2819_OFF(ether_stats_fragments) },
- { "jabbers", PPORT_2819_OFF(ether_stats_jabbers) },
- { "collisions", PPORT_2819_OFF(ether_stats_collisions) },
- { "p64octets", PPORT_2819_OFF(ether_stats_pkts64octets) },
- { "p65to127octets", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
- { "p128to255octets", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
- { "p256to511octets", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
- { "p512to1023octets", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
- { "p1024to1518octets",
- PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
- { "p1519to2047octets",
- PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
- { "p2048to4095octets",
- PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
- { "p4096to8191octets",
- PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
- { "p8192to10239octets",
- PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
+ { "rx_undersize_pkts_phy", PPORT_2819_OFF(ether_stats_undersize_pkts) },
+ { "rx_fragments_phy", PPORT_2819_OFF(ether_stats_fragments) },
+ { "rx_jabbers_phy", PPORT_2819_OFF(ether_stats_jabbers) },
+ { "rx_64_bytes_phy", PPORT_2819_OFF(ether_stats_pkts64octets) },
+ { "rx_65_to_127_bytes_phy", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
+ { "rx_128_to_255_bytes_phy", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
+ { "rx_256_to_511_bytes_phy", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
+ { "rx_512_to_1023_bytes_phy", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
+ { "rx_1024_to_1518_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
+ { "rx_1519_to_2047_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
+ { "rx_2048_to_4095_bytes_phy", PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
+ { "rx_4096_to_8191_bytes_phy", PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
+ { "rx_8192_to_10239_bytes_phy", PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
};
static const struct counter_desc pport_per_prio_traffic_stats_desc[] = {
- { "rx_octets", PPORT_PER_PRIO_OFF(rx_octets) },
- { "rx_frames", PPORT_PER_PRIO_OFF(rx_frames) },
- { "tx_octets", PPORT_PER_PRIO_OFF(tx_octets) },
- { "tx_frames", PPORT_PER_PRIO_OFF(tx_frames) },
+ { "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) },
+ { "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) },
+ { "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) },
+ { "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) },
};
static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
- { "rx_pause", PPORT_PER_PRIO_OFF(rx_pause) },
- { "rx_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
- { "tx_pause", PPORT_PER_PRIO_OFF(tx_pause) },
- { "tx_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
- { "rx_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
+ { "rx_prio%d_pause", PPORT_PER_PRIO_OFF(rx_pause) },
+ { "rx_prio%d_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
+ { "tx_prio%d_pause", PPORT_PER_PRIO_OFF(tx_pause) },
+ { "tx_prio%d_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
+ { "rx_prio%d_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
};
struct mlx5e_rq_stats {
u64 packets;
u64 bytes;
- u64 csum_sw;
- u64 csum_inner;
+ u64 csum_complete;
+ u64 csum_unnecessary_inner;
u64 csum_none;
u64 lro_packets;
u64 lro_bytes;
@@ -292,19 +262,19 @@ struct mlx5e_rq_stats {
};
static const struct counter_desc rq_stats_desc[] = {
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_sw) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_inner) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_none) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, wqe_err) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_frag) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
- { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_frag) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
};
struct mlx5e_sq_stats {
@@ -315,28 +285,28 @@ struct mlx5e_sq_stats {
u64 tso_bytes;
u64 tso_inner_packets;
u64 tso_inner_bytes;
- u64 csum_offload_inner;
+ u64 csum_partial_inner;
u64 nop;
/* less likely accessed in data path */
- u64 csum_offload_none;
+ u64 csum_none;
u64 stopped;
u64 wake;
u64 dropped;
};
static const struct counter_desc sq_stats_desc[] = {
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_inner) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, nop) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_none) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, stopped) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, wake) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, dropped) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, packets) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, bytes) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_packets) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
};
#define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 229ab16fb8d3..5a750b9cd006 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -192,12 +192,12 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
if (skb->encapsulation) {
eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM |
MLX5_ETH_WQE_L4_INNER_CSUM;
- sq->stats.csum_offload_inner++;
+ sq->stats.csum_partial_inner++;
} else {
eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
}
} else
- sq->stats.csum_offload_none++;
+ sq->stats.csum_none++;
if (sq->cc != sq->prev_cc) {
sq->prev_cc = sq->cc;
@@ -317,7 +317,8 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
while ((sq->pc & wq->sz_m1) > sq->edge)
mlx5e_send_nop(sq, false);
- sq->bf_budget = bf ? sq->bf_budget - 1 : 0;
+ if (bf)
+ sq->bf_budget--;
sq->stats.packets++;
sq->stats.bytes += num_bytes;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b84a6918a700..aebbd6ccb9fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -383,7 +383,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
match_v,
MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
0, &dest);
- if (IS_ERR_OR_NULL(flow_rule)) {
+ if (IS_ERR(flow_rule)) {
pr_warn(
"FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
dmac_v, dmac_c, vport, PTR_ERR(flow_rule));
@@ -457,7 +457,7 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0);
- if (IS_ERR_OR_NULL(fdb)) {
+ if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
esw_warn(dev, "Failed to create FDB Table err %d\n", err);
goto out;
@@ -474,7 +474,7 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 3);
eth_broadcast_addr(dmac);
g = mlx5_create_flow_group(fdb, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create flow group err(%d)\n", err);
goto out;
@@ -489,7 +489,7 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
eth_zero_addr(dmac);
dmac[0] = 0x01;
g = mlx5_create_flow_group(fdb, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create allmulti flow group err(%d)\n", err);
goto out;
@@ -506,7 +506,7 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 1);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1);
g = mlx5_create_flow_group(fdb, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create promisc flow group err(%d)\n", err);
goto out;
@@ -529,7 +529,7 @@ out:
}
}
- kfree(flow_group_in);
+ kvfree(flow_group_in);
return err;
}
@@ -651,6 +651,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
esw_fdb_set_vport_rule(esw,
mac,
vport_idx);
+ iter_vaddr->mc_promisc = true;
break;
case MLX5_ACTION_DEL:
if (!iter_vaddr)
@@ -1060,7 +1061,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
return;
acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
- if (IS_ERR_OR_NULL(acl)) {
+ if (IS_ERR(acl)) {
err = PTR_ERR(acl);
esw_warn(dev, "Failed to create E-Switch vport[%d] egress flow Table, err(%d)\n",
vport->vport, err);
@@ -1075,7 +1076,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
vlan_grp = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR_OR_NULL(vlan_grp)) {
+ if (IS_ERR(vlan_grp)) {
err = PTR_ERR(vlan_grp);
esw_warn(dev, "Failed to create E-Switch vport[%d] egress allowed vlans flow group, err(%d)\n",
vport->vport, err);
@@ -1086,7 +1087,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
drop_grp = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR_OR_NULL(drop_grp)) {
+ if (IS_ERR(drop_grp)) {
err = PTR_ERR(drop_grp);
esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
vport->vport, err);
@@ -1097,7 +1098,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
vport->egress.drop_grp = drop_grp;
vport->egress.allowed_vlans_grp = vlan_grp;
out:
- kfree(flow_group_in);
+ kvfree(flow_group_in);
if (err && !IS_ERR_OR_NULL(vlan_grp))
mlx5_destroy_flow_group(vlan_grp);
if (err && !IS_ERR_OR_NULL(acl))
@@ -1174,7 +1175,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
return;
acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
- if (IS_ERR_OR_NULL(acl)) {
+ if (IS_ERR(acl)) {
err = PTR_ERR(acl);
esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n",
vport->vport, err);
@@ -1192,7 +1193,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n",
vport->vport, err);
@@ -1207,7 +1208,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n",
vport->vport, err);
@@ -1223,7 +1224,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n",
vport->vport, err);
@@ -1236,7 +1237,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR_OR_NULL(g)) {
+ if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n",
vport->vport, err);
@@ -1259,7 +1260,7 @@ out:
mlx5_destroy_flow_table(vport->ingress.acl);
}
- kfree(flow_group_in);
+ kvfree(flow_group_in);
}
static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
@@ -1363,7 +1364,7 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
match_v,
MLX5_FLOW_CONTEXT_ACTION_ALLOW,
0, NULL);
- if (IS_ERR_OR_NULL(vport->ingress.allow_rule)) {
+ if (IS_ERR(vport->ingress.allow_rule)) {
err = PTR_ERR(vport->ingress.allow_rule);
pr_warn("vport[%d] configure ingress allow rule, err(%d)\n",
vport->vport, err);
@@ -1380,7 +1381,7 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
match_v,
MLX5_FLOW_CONTEXT_ACTION_DROP,
0, NULL);
- if (IS_ERR_OR_NULL(vport->ingress.drop_rule)) {
+ if (IS_ERR(vport->ingress.drop_rule)) {
err = PTR_ERR(vport->ingress.drop_rule);
pr_warn("vport[%d] configure ingress drop rule, err(%d)\n",
vport->vport, err);
@@ -1439,7 +1440,7 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
match_v,
MLX5_FLOW_CONTEXT_ACTION_ALLOW,
0, NULL);
- if (IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
+ if (IS_ERR(vport->egress.allowed_vlan)) {
err = PTR_ERR(vport->egress.allowed_vlan);
pr_warn("vport[%d] configure egress allowed vlan rule failed, err(%d)\n",
vport->vport, err);
@@ -1457,7 +1458,7 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
match_v,
MLX5_FLOW_CONTEXT_ACTION_DROP,
0, NULL);
- if (IS_ERR_OR_NULL(vport->egress.drop_rule)) {
+ if (IS_ERR(vport->egress.drop_rule)) {
err = PTR_ERR(vport->egress.drop_rule);
pr_warn("vport[%d] configure egress drop rule failed, err(%d)\n",
vport->vport, err);
@@ -1491,14 +1492,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
/* Sync with current vport context */
vport->enabled_events = enable_events;
- esw_vport_change_handle_locked(vport);
-
vport->enabled = true;
/* only PF is trusted by default */
vport->trusted = (vport_num) ? false : true;
-
- arm_vport_context_events_cmd(esw->dev, vport_num, enable_events);
+ esw_vport_change_handle_locked(vport);
esw->enabled_vports++;
esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num);
@@ -1728,11 +1726,24 @@ void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
(esw && MLX5_CAP_GEN(esw->dev, vport_group_manager) && mlx5_core_is_pf(esw->dev))
#define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
+static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
+{
+ ((u8 *)node_guid)[7] = mac[0];
+ ((u8 *)node_guid)[6] = mac[1];
+ ((u8 *)node_guid)[5] = mac[2];
+ ((u8 *)node_guid)[4] = 0xff;
+ ((u8 *)node_guid)[3] = 0xfe;
+ ((u8 *)node_guid)[2] = mac[3];
+ ((u8 *)node_guid)[1] = mac[4];
+ ((u8 *)node_guid)[0] = mac[5];
+}
+
int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
int vport, u8 mac[ETH_ALEN])
{
- int err = 0;
struct mlx5_vport *evport;
+ u64 node_guid;
+ int err = 0;
if (!ESW_ALLOWED(esw))
return -EPERM;
@@ -1756,11 +1767,17 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
return err;
}
+ node_guid_gen_from_mac(&node_guid, mac);
+ err = mlx5_modify_nic_vport_node_guid(esw->dev, vport, node_guid);
+ if (err)
+ mlx5_core_warn(esw->dev,
+ "Failed to set vport %d node guid, err = %d. RDMA_CM will not function properly for this VF.\n",
+ vport, err);
+
mutex_lock(&esw->state_lock);
if (evport->enabled)
err = esw_vport_ingress_config(esw, evport);
mutex_unlock(&esw->state_lock);
-
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8b5f0b2c0d5c..e912a3d2505e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1292,8 +1292,8 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft)
ft->id);
return err;
}
- root->root_ft = new_root_ft;
}
+ root->root_ft = new_root_ft;
return 0;
}
@@ -1767,6 +1767,9 @@ static void cleanup_root_ns(struct mlx5_core_dev *dev)
void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
{
+ if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+ return;
+
cleanup_root_ns(dev);
cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns);
cleanup_single_prio_root_ns(dev, dev->priv.esw_egress_root_ns);
@@ -1828,29 +1831,36 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
{
int err = 0;
+ if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+ return 0;
+
err = mlx5_init_fc_stats(dev);
if (err)
return err;
- if (MLX5_CAP_GEN(dev, nic_flow_table)) {
+ if (MLX5_CAP_GEN(dev, nic_flow_table) &&
+ MLX5_CAP_FLOWTABLE_NIC_RX(dev, ft_support)) {
err = init_root_ns(dev);
if (err)
goto err;
}
+
if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
- err = init_fdb_root_ns(dev);
- if (err)
- goto err;
- }
- if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
- err = init_egress_acl_root_ns(dev);
- if (err)
- goto err;
- }
- if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
- err = init_ingress_acl_root_ns(dev);
- if (err)
- goto err;
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
+ err = init_fdb_root_ns(dev);
+ if (err)
+ goto err;
+ }
+ if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
+ err = init_egress_acl_root_ns(dev);
+ if (err)
+ goto err;
+ }
+ if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
+ err = init_ingress_acl_root_ns(dev);
+ if (err)
+ goto err;
+ }
}
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a19b59348dd6..c65f4a13e17e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1508,8 +1508,9 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
{ PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4 VF */
{ PCI_VDEVICE(MELLANOX, 0x1015) }, /* ConnectX-4LX */
{ PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */
- { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5 */
+ { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */
{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */
+ { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */
{ 0, }
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index b720a274220d..b82d65802d96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -418,7 +418,7 @@ int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn)
if (out.hdr.status)
err = mlx5_cmd_status_to_err(&out.hdr);
else
- *xrcdn = be32_to_cpu(out.xrcdn);
+ *xrcdn = be32_to_cpu(out.xrcdn) & 0xffffff;
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index b69dadcfb897..daf44cd4c566 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -508,6 +508,44 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
}
EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
+int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+ u32 vport, u64 node_guid)
+{
+ int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
+ void *nic_vport_context;
+ u8 *guid;
+ void *in;
+ int err;
+
+ if (!vport)
+ return -EINVAL;
+ if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+ return -EACCES;
+ if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
+ return -ENOTSUPP;
+
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(modify_nic_vport_context_in, in,
+ field_select.node_guid, 1);
+ MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
+ MLX5_SET(modify_nic_vport_context_in, in, other_vport, !!vport);
+
+ nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
+ in, nic_vport_context);
+ guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
+ node_guid);
+ MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
+
+ err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+
+ kvfree(in);
+
+ return err;
+}
+
int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
u16 *qkey_viol_cntr)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index f2fd1ef16da7..05de77267d58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -105,6 +105,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
struct mlx5e_vxlan *vxlan;
int err;
+ if (mlx5e_vxlan_lookup_port(priv, port))
+ goto free_work;
+
if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
goto free_work;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index ce21ee5b2357..821a087c7ae2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -75,14 +75,14 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
if (err) {
- mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+ mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
return err;
}
err = mlx5_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq),
&wq_ctrl->buf, param->buf_numa_node);
if (err) {
- mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+ mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
goto err_db_free;
}
@@ -111,14 +111,14 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
if (err) {
- mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+ mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
return err;
}
err = mlx5_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq),
&wq_ctrl->buf, param->buf_numa_node);
if (err) {
- mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+ mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
goto err_db_free;
}
@@ -148,13 +148,14 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
if (err) {
- mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+ mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
return err;
}
- err = mlx5_buf_alloc(mdev, mlx5_wq_ll_get_byte_size(wq), &wq_ctrl->buf);
+ err = mlx5_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq),
+ &wq_ctrl->buf, param->buf_numa_node);
if (err) {
- mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+ mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
goto err_db_free;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 4a7273771028..660429ebfbe1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -247,15 +247,23 @@ static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl);
}
-static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
+static int __mlxsw_sp_port_swid_set(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+ u8 swid)
{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char pspa_pl[MLXSW_REG_PSPA_LEN];
- mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sp_port->local_port);
+ mlxsw_reg_pspa_pack(pspa_pl, swid, local_port);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl);
}
+static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+
+ return __mlxsw_sp_port_swid_set(mlxsw_sp, mlxsw_sp_port->local_port,
+ swid);
+}
+
static int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
bool enable)
{
@@ -305,9 +313,9 @@ mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port)
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl);
}
-static int __mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
- u8 local_port, u8 *p_module,
- u8 *p_width, u8 *p_lane)
+static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
+ u8 local_port, u8 *p_module,
+ u8 *p_width, u8 *p_lane)
{
char pmlp_pl[MLXSW_REG_PMLP_LEN];
int err;
@@ -322,16 +330,6 @@ static int __mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
return 0;
}
-static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
- u8 local_port, u8 *p_module,
- u8 *p_width)
-{
- u8 lane;
-
- return __mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, p_module,
- p_width, &lane);
-}
-
static int mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port,
u8 module, u8 width, u8 lane)
{
@@ -410,7 +408,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
}
mlxsw_sp_txhdr_construct(skb, &tx_info);
- len = skb->len;
+ /* TX header is consumed by HW on the way so we shouldn't count its
+ * bytes as being sent.
+ */
+ len = skb->len - MLXSW_TXHDR_LEN;
+
/* Due to a race we might fail here because of a full queue. In that
* unlikely case we simply drop the packet.
*/
@@ -949,17 +951,11 @@ static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name,
size_t len)
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
- u8 module, width, lane;
+ u8 module = mlxsw_sp_port->mapping.module;
+ u8 width = mlxsw_sp_port->mapping.width;
+ u8 lane = mlxsw_sp_port->mapping.lane;
int err;
- err = __mlxsw_sp_port_module_info_get(mlxsw_sp_port->mlxsw_sp,
- mlxsw_sp_port->local_port,
- &module, &width, &lane);
- if (err) {
- netdev_err(dev, "Failed to retrieve module information\n");
- return err;
- }
-
if (!mlxsw_sp_port->split)
err = snprintf(name, len, "p%d", module + 1);
else
@@ -1681,8 +1677,8 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
return 0;
}
-static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
- bool split, u8 module, u8 width)
+static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+ bool split, u8 module, u8 width, u8 lane)
{
struct mlxsw_sp_port *mlxsw_sp_port;
struct net_device *dev;
@@ -1697,6 +1693,9 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
mlxsw_sp_port->local_port = local_port;
mlxsw_sp_port->split = split;
+ mlxsw_sp_port->mapping.module = module;
+ mlxsw_sp_port->mapping.width = width;
+ mlxsw_sp_port->mapping.lane = lane;
bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE);
mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL);
if (!mlxsw_sp_port->active_vlans) {
@@ -1839,28 +1838,6 @@ err_port_active_vlans_alloc:
return err;
}
-static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
- bool split, u8 module, u8 width, u8 lane)
-{
- int err;
-
- err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
- lane);
- if (err)
- return err;
-
- err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module,
- width);
- if (err)
- goto err_port_create;
-
- return 0;
-
-err_port_create:
- mlxsw_sp_port_module_unmap(mlxsw_sp, local_port);
- return err;
-}
-
static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
{
struct net_device *dev = mlxsw_sp_port->dev;
@@ -1909,8 +1886,8 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
{
+ u8 module, width, lane;
size_t alloc_size;
- u8 module, width;
int i;
int err;
@@ -1921,13 +1898,14 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
- &width);
+ &width, &lane);
if (err)
goto err_port_module_info_get;
if (!width)
continue;
mlxsw_sp->port_to_module[i] = module;
- err = __mlxsw_sp_port_create(mlxsw_sp, i, false, module, width);
+ err = mlxsw_sp_port_create(mlxsw_sp, i, false, module, width,
+ lane);
if (err)
goto err_port_create;
}
@@ -1948,12 +1926,85 @@ static u8 mlxsw_sp_cluster_base_port_get(u8 local_port)
return local_port - offset;
}
+static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
+ u8 module, unsigned int count)
+{
+ u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
+ int err, i;
+
+ for (i = 0; i < count; i++) {
+ err = mlxsw_sp_port_module_map(mlxsw_sp, base_port + i, module,
+ width, i * width);
+ if (err)
+ goto err_port_module_map;
+ }
+
+ for (i = 0; i < count; i++) {
+ err = __mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i, 0);
+ if (err)
+ goto err_port_swid_set;
+ }
+
+ for (i = 0; i < count; i++) {
+ err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
+ module, width, i * width);
+ if (err)
+ goto err_port_create;
+ }
+
+ return 0;
+
+err_port_create:
+ for (i--; i >= 0; i--)
+ mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+ i = count;
+err_port_swid_set:
+ for (i--; i >= 0; i--)
+ __mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i,
+ MLXSW_PORT_SWID_DISABLED_PORT);
+ i = count;
+err_port_module_map:
+ for (i--; i >= 0; i--)
+ mlxsw_sp_port_module_unmap(mlxsw_sp, base_port + i);
+ return err;
+}
+
+static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp,
+ u8 base_port, unsigned int count)
+{
+ u8 local_port, module, width = MLXSW_PORT_MODULE_MAX_WIDTH;
+ int i;
+
+ /* Split by four means we need to re-create two ports, otherwise
+ * only one.
+ */
+ count = count / 2;
+
+ for (i = 0; i < count; i++) {
+ local_port = base_port + i * 2;
+ module = mlxsw_sp->port_to_module[local_port];
+
+ mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
+ 0);
+ }
+
+ for (i = 0; i < count; i++)
+ __mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i * 2, 0);
+
+ for (i = 0; i < count; i++) {
+ local_port = base_port + i * 2;
+ module = mlxsw_sp->port_to_module[local_port];
+
+ mlxsw_sp_port_create(mlxsw_sp, local_port, false, module,
+ width, 0);
+ }
+}
+
static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
unsigned int count)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
struct mlxsw_sp_port *mlxsw_sp_port;
- u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
u8 module, cur_width, base_port;
int i;
int err;
@@ -1965,18 +2016,14 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
return -EINVAL;
}
+ module = mlxsw_sp_port->mapping.module;
+ cur_width = mlxsw_sp_port->mapping.width;
+
if (count != 2 && count != 4) {
netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n");
return -EINVAL;
}
- err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
- &cur_width);
- if (err) {
- netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
- return err;
- }
-
if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) {
netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n");
return -EINVAL;
@@ -2001,25 +2048,16 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
for (i = 0; i < count; i++)
mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
- for (i = 0; i < count; i++) {
- err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
- module, width, i * width);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Failed to create split port\n");
- goto err_port_create;
- }
+ err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n");
+ goto err_port_split_create;
}
return 0;
-err_port_create:
- for (i--; i >= 0; i--)
- mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
- for (i = 0; i < count / 2; i++) {
- module = mlxsw_sp->port_to_module[base_port + i * 2];
- mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
- module, MLXSW_PORT_MODULE_MAX_WIDTH, 0);
- }
+err_port_split_create:
+ mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
return err;
}
@@ -2027,10 +2065,9 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
struct mlxsw_sp_port *mlxsw_sp_port;
- u8 module, cur_width, base_port;
+ u8 cur_width, base_port;
unsigned int count;
int i;
- int err;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port) {
@@ -2044,12 +2081,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
return -EINVAL;
}
- err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
- &cur_width);
- if (err) {
- netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
- return err;
- }
+ cur_width = mlxsw_sp_port->mapping.width;
count = cur_width == 1 ? 4 : 2;
base_port = mlxsw_sp_cluster_base_port_get(local_port);
@@ -2061,14 +2093,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
for (i = 0; i < count; i++)
mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
- for (i = 0; i < count / 2; i++) {
- module = mlxsw_sp->port_to_module[base_port + i * 2];
- err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
- module, MLXSW_PORT_MODULE_MAX_WIDTH,
- 0);
- if (err)
- dev_err(mlxsw_sp->bus_info->dev, "Failed to reinstantiate port\n");
- }
+ mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index e2c022d3e2f3..13b30eaa13d4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -229,6 +229,11 @@ struct mlxsw_sp_port {
struct ieee_maxrate *maxrate;
struct ieee_pfc *pfc;
} dcb;
+ struct {
+ u8 module;
+ u8 width;
+ u8 lane;
+ } mapping;
/* 802.1Q bridge VLANs */
unsigned long *active_vlans;
unsigned long *untagged_vlans;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 3842eab9449a..25f658b3849a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -316,7 +316,10 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
}
}
mlxsw_sx_txhdr_construct(skb, &tx_info);
- len = skb->len;
+ /* TX header is consumed by HW on the way so we shouldn't count its
+ * bytes as being sent.
+ */
+ len = skb->len - MLXSW_TXHDR_LEN;
/* Due to a race we might fail here because of a full queue. In that
* unlikely case we simply drop the packet.
*/
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index fa47c14c743a..ba26bb356b8d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2015,7 +2015,7 @@ static void nfp_net_open_stack(struct nfp_net *nn)
netif_tx_wake_all_queues(nn->netdev);
- enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+ enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
nfp_net_read_link_status(nn);
}
@@ -2044,7 +2044,7 @@ static int nfp_net_netdev_open(struct net_device *netdev)
NFP_NET_IRQ_LSC_IDX, nn->lsc_handler);
if (err)
goto err_free_exn;
- disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+ disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings),
GFP_KERNEL);
@@ -2133,7 +2133,7 @@ static void nfp_net_close_stack(struct nfp_net *nn)
{
unsigned int r;
- disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+ disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
netif_carrier_off(nn->netdev);
nn->link_up = false;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index cbf58e1f9333..21ec1c2df2c7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -192,9 +192,10 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
struct dcbx_app_priority_entry *p_tbl,
u32 pri_tc_tbl, int count, bool dcbx_enabled)
{
- u8 tc, priority, priority_map;
+ u8 tc, priority_map;
enum dcbx_protocol_type type;
u16 protocol_id;
+ int priority;
bool enable;
int i;
@@ -221,7 +222,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
* indication, but we only got here if there was an
* app tlv for the protocol, so dcbx must be enabled.
*/
- enable = !!(type == DCBX_PROTOCOL_ETH);
+ enable = !(type == DCBX_PROTOCOL_ETH);
qed_dcbx_update_app_info(p_data, p_hwfn, enable, true,
priority, tc, type);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 089016f46f26..2d89e8c16b32 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -155,12 +155,14 @@ void qed_resc_free(struct qed_dev *cdev)
}
}
-static int qed_init_qm_info(struct qed_hwfn *p_hwfn)
+static int qed_init_qm_info(struct qed_hwfn *p_hwfn, bool b_sleepable)
{
u8 num_vports, vf_offset = 0, i, vport_id, num_ports, curr_queue = 0;
struct qed_qm_info *qm_info = &p_hwfn->qm_info;
struct init_qm_port_params *p_qm_port;
u16 num_pqs, multi_cos_tcs = 1;
+ u8 pf_wfq = qm_info->pf_wfq;
+ u32 pf_rl = qm_info->pf_rl;
u16 num_vfs = 0;
#ifdef CONFIG_QED_SRIOV
@@ -182,23 +184,28 @@ static int qed_init_qm_info(struct qed_hwfn *p_hwfn)
/* PQs will be arranged as follows: First per-TC PQ then pure-LB quete.
*/
- qm_info->qm_pq_params = kzalloc(sizeof(*qm_info->qm_pq_params) *
- num_pqs, GFP_KERNEL);
+ qm_info->qm_pq_params = kcalloc(num_pqs,
+ sizeof(struct init_qm_pq_params),
+ b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
if (!qm_info->qm_pq_params)
goto alloc_err;
- qm_info->qm_vport_params = kzalloc(sizeof(*qm_info->qm_vport_params) *
- num_vports, GFP_KERNEL);
+ qm_info->qm_vport_params = kcalloc(num_vports,
+ sizeof(struct init_qm_vport_params),
+ b_sleepable ? GFP_KERNEL
+ : GFP_ATOMIC);
if (!qm_info->qm_vport_params)
goto alloc_err;
- qm_info->qm_port_params = kzalloc(sizeof(*qm_info->qm_port_params) *
- MAX_NUM_PORTS, GFP_KERNEL);
+ qm_info->qm_port_params = kcalloc(MAX_NUM_PORTS,
+ sizeof(struct init_qm_port_params),
+ b_sleepable ? GFP_KERNEL
+ : GFP_ATOMIC);
if (!qm_info->qm_port_params)
goto alloc_err;
- qm_info->wfq_data = kcalloc(num_vports, sizeof(*qm_info->wfq_data),
- GFP_KERNEL);
+ qm_info->wfq_data = kcalloc(num_vports, sizeof(struct qed_wfq_data),
+ b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
if (!qm_info->wfq_data)
goto alloc_err;
@@ -264,10 +271,10 @@ static int qed_init_qm_info(struct qed_hwfn *p_hwfn)
for (i = 0; i < qm_info->num_vports; i++)
qm_info->qm_vport_params[i].vport_wfq = 1;
- qm_info->pf_wfq = 0;
- qm_info->pf_rl = 0;
qm_info->vport_rl_en = 1;
qm_info->vport_wfq_en = 1;
+ qm_info->pf_rl = pf_rl;
+ qm_info->pf_wfq = pf_wfq;
return 0;
@@ -299,7 +306,7 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
qed_qm_info_free(p_hwfn);
/* initialize qed's qm data structure */
- rc = qed_init_qm_info(p_hwfn);
+ rc = qed_init_qm_info(p_hwfn, false);
if (rc)
return rc;
@@ -388,7 +395,7 @@ int qed_resc_alloc(struct qed_dev *cdev)
goto alloc_err;
/* Prepare and process QM requirements */
- rc = qed_init_qm_info(p_hwfn);
+ rc = qed_init_qm_info(p_hwfn, true);
if (rc)
goto alloc_err;
@@ -581,7 +588,14 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
hw_mode |= 1 << MODE_ASIC;
+ if (p_hwfn->cdev->num_hwfns > 1)
+ hw_mode |= 1 << MODE_100G;
+
p_hwfn->hw_info.hw_mode = hw_mode;
+
+ DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP),
+ "Configuring function for hw_mode: 0x%08x\n",
+ p_hwfn->hw_info.hw_mode);
}
/* Init run time data for all PFs on an engine. */
@@ -821,6 +835,11 @@ int qed_hw_init(struct qed_dev *cdev,
u32 load_code, param;
int rc, mfw_rc, i;
+ if ((int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
+ DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n");
+ return -EINVAL;
+ }
+
if (IS_PF(cdev)) {
rc = qed_init_fw_data(cdev, bin_fw_data);
if (rc != 0)
@@ -2086,6 +2105,13 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, u32 min_pf_rate)
{
int i;
+ if (cdev->num_hwfns > 1) {
+ DP_VERBOSE(cdev,
+ NETIF_MSG_LINK,
+ "WFQ configuration is not supported for this device\n");
+ return;
+ }
+
for_each_hwfn(cdev, i) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 9afc15fdbb02..e29ed5a69566 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -3700,6 +3700,7 @@ struct public_port {
#define MEDIA_DA_TWINAX 0x3
#define MEDIA_BASE_T 0x4
#define MEDIA_SFP_1G_FIBER 0x5
+#define MEDIA_MODULE_FIBER 0x6
#define MEDIA_KR 0xf0
#define MEDIA_NOT_PRESENT 0xff
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 8fba87dd48af..aada4c7e095f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -72,6 +72,7 @@ int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn,
p_ramrod->mtu = cpu_to_le16(p_params->mtu);
p_ramrod->inner_vlan_removal_en = p_params->remove_inner_vlan;
p_ramrod->drop_ttl0_en = p_params->drop_ttl0;
+ p_ramrod->untagged = p_params->only_untagged;
SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_UCAST_DROP_ALL, 1);
SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_MCAST_DROP_ALL, 1);
@@ -247,10 +248,6 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn,
SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_DROP_ALL,
!!(accept_filter & QED_ACCEPT_NONE));
- SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL,
- (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) &&
- !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED)));
-
SET_FIELD(state, ETH_VPORT_TX_MODE_MCAST_DROP_ALL,
!!(accept_filter & QED_ACCEPT_NONE));
@@ -1748,7 +1745,8 @@ static int qed_start_vport(struct qed_dev *cdev,
start.vport_id, start.mtu);
}
- qed_reset_vport_stats(cdev);
+ if (params->clear_stats)
+ qed_reset_vport_stats(cdev);
return 0;
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 8b22f87033ce..c7e01b303540 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -413,15 +413,17 @@ static int qed_set_int_mode(struct qed_dev *cdev, bool force_mode)
/* Fallthrough */
case QED_INT_MODE_MSI:
- rc = pci_enable_msi(cdev->pdev);
- if (!rc) {
- int_params->out.int_mode = QED_INT_MODE_MSI;
- goto out;
- }
+ if (cdev->num_hwfns == 1) {
+ rc = pci_enable_msi(cdev->pdev);
+ if (!rc) {
+ int_params->out.int_mode = QED_INT_MODE_MSI;
+ goto out;
+ }
- DP_NOTICE(cdev, "Failed to enable MSI\n");
- if (force_mode)
- goto out;
+ DP_NOTICE(cdev, "Failed to enable MSI\n");
+ if (force_mode)
+ goto out;
+ }
/* Fallthrough */
case QED_INT_MODE_INTA:
@@ -1083,6 +1085,7 @@ static int qed_get_port_type(u32 media_type)
case MEDIA_SFPP_10G_FIBER:
case MEDIA_SFP_1G_FIBER:
case MEDIA_XFP_FIBER:
+ case MEDIA_MODULE_FIBER:
case MEDIA_KR:
port_type = PORT_FIBRE;
break;
@@ -1103,6 +1106,39 @@ static int qed_get_port_type(u32 media_type)
return port_type;
}
+static int qed_get_link_data(struct qed_hwfn *hwfn,
+ struct qed_mcp_link_params *params,
+ struct qed_mcp_link_state *link,
+ struct qed_mcp_link_capabilities *link_caps)
+{
+ void *p;
+
+ if (!IS_PF(hwfn->cdev)) {
+ qed_vf_get_link_params(hwfn, params);
+ qed_vf_get_link_state(hwfn, link);
+ qed_vf_get_link_caps(hwfn, link_caps);
+
+ return 0;
+ }
+
+ p = qed_mcp_get_link_params(hwfn);
+ if (!p)
+ return -ENXIO;
+ memcpy(params, p, sizeof(*params));
+
+ p = qed_mcp_get_link_state(hwfn);
+ if (!p)
+ return -ENXIO;
+ memcpy(link, p, sizeof(*link));
+
+ p = qed_mcp_get_link_capabilities(hwfn);
+ if (!p)
+ return -ENXIO;
+ memcpy(link_caps, p, sizeof(*link_caps));
+
+ return 0;
+}
+
static void qed_fill_link(struct qed_hwfn *hwfn,
struct qed_link_output *if_link)
{
@@ -1114,15 +1150,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
memset(if_link, 0, sizeof(*if_link));
/* Prepare source inputs */
- if (IS_PF(hwfn->cdev)) {
- memcpy(&params, qed_mcp_get_link_params(hwfn), sizeof(params));
- memcpy(&link, qed_mcp_get_link_state(hwfn), sizeof(link));
- memcpy(&link_caps, qed_mcp_get_link_capabilities(hwfn),
- sizeof(link_caps));
- } else {
- qed_vf_get_link_params(hwfn, &params);
- qed_vf_get_link_state(hwfn, &link);
- qed_vf_get_link_caps(hwfn, &link_caps);
+ if (qed_get_link_data(hwfn, &params, &link, &link_caps)) {
+ dev_warn(&hwfn->cdev->pdev->dev, "no link data available\n");
+ return;
}
/* Set the link parameters to pass to protocol driver */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index acac6626a1b2..b122f6013b6c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -213,19 +213,15 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
SET_FIELD(db.params, CORE_DB_DATA_AGG_VAL_SEL,
DQ_XCM_CORE_SPQ_PROD_CMD);
db.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
-
- /* validate producer is up to-date */
- rmb();
-
db.spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
- /* do not reorder */
- barrier();
+ /* make sure the SPQE is updated before the doorbell */
+ wmb();
DOORBELL(p_hwfn, qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY), *(u32 *)&db);
/* make sure doorbell is rang */
- mmiowb();
+ wmb();
DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
"Doorbelled [0x%08x, CID 0x%08x] with Flags: %02x agg_params: %02x, prod: %04x\n",
@@ -614,7 +610,9 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn,
*p_en2 = *p_ent;
- kfree(p_ent);
+ /* EBLOCK responsible to free the allocated p_ent */
+ if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK)
+ kfree(p_ent);
p_ent = p_en2;
}
@@ -749,6 +747,15 @@ int qed_spq_post(struct qed_hwfn *p_hwfn,
* Thus, after gaining the answer perform the cleanup here.
*/
rc = qed_spq_block(p_hwfn, p_ent, fw_return_code);
+
+ if (p_ent->queue == &p_spq->unlimited_pending) {
+ /* This is an allocated p_ent which does not need to
+ * return to pool.
+ */
+ kfree(p_ent);
+ return rc;
+ }
+
if (rc)
goto spq_post_fail2;
@@ -844,8 +851,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
found->comp_cb.function(p_hwfn, found->comp_cb.cookie, p_data,
fw_return_code);
- if (found->comp_mode != QED_SPQ_MODE_EBLOCK)
- /* EBLOCK is responsible for freeing its own entry */
+ if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) ||
+ (found->queue == &p_spq->unlimited_pending))
+ /* EBLOCK is responsible for returning its own entry into the
+ * free list, unless it originally added the entry into the
+ * unlimited pending list.
+ */
qed_spq_return_entry(p_hwfn, found);
/* Attempt to post pending requests */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index c8667c65e685..c90b2b6ad969 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -12,11 +12,13 @@
#include "qed_vf.h"
#define QED_VF_ARRAY_LENGTH (3)
+#ifdef CONFIG_QED_SRIOV
#define IS_VF(cdev) ((cdev)->b_is_vf)
#define IS_PF(cdev) (!((cdev)->b_is_vf))
-#ifdef CONFIG_QED_SRIOV
#define IS_PF_SRIOV(p_hwfn) (!!((p_hwfn)->cdev->p_iov_info))
#else
+#define IS_VF(cdev) (0)
+#define IS_PF(cdev) (1)
#define IS_PF_SRIOV(p_hwfn) (0)
#endif
#define IS_PF_SRIOV_ALLOC(p_hwfn) (!!((p_hwfn)->pf_iov_info))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 1bc75358cbc4..ad3cae3b7243 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -230,7 +230,10 @@ static int qede_get_sset_count(struct net_device *dev, int stringset)
case ETH_SS_PRIV_FLAGS:
return QEDE_PRI_FLAG_LEN;
case ETH_SS_TEST:
- return QEDE_ETHTOOL_TEST_MAX;
+ if (!IS_VF(edev))
+ return QEDE_ETHTOOL_TEST_MAX;
+ else
+ return 0;
default:
DP_VERBOSE(edev, QED_MSG_DEBUG,
"Unsupported stringset 0x%08x\n", stringset);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 337e839ca586..f8e11f953acb 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -87,7 +87,9 @@ static const struct pci_device_id qede_pci_tbl[] = {
{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_100), QEDE_PRIVATE_PF},
{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_50), QEDE_PRIVATE_PF},
{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_25), QEDE_PRIVATE_PF},
+#ifdef CONFIG_QED_SRIOV
{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF},
+#endif
{ 0 }
};
@@ -1824,7 +1826,7 @@ static int qede_set_vf_rate(struct net_device *dev, int vfidx,
{
struct qede_dev *edev = netdev_priv(dev);
- return edev->ops->iov->set_rate(edev->cdev, vfidx, max_tx_rate,
+ return edev->ops->iov->set_rate(edev->cdev, vfidx, min_tx_rate,
max_tx_rate);
}
@@ -2091,6 +2093,29 @@ static void qede_vlan_mark_nonconfigured(struct qede_dev *edev)
edev->accept_any_vlan = false;
}
+int qede_set_features(struct net_device *dev, netdev_features_t features)
+{
+ struct qede_dev *edev = netdev_priv(dev);
+ netdev_features_t changes = features ^ dev->features;
+ bool need_reload = false;
+
+ /* No action needed if hardware GRO is disabled during driver load */
+ if (changes & NETIF_F_GRO) {
+ if (dev->features & NETIF_F_GRO)
+ need_reload = !edev->gro_disable;
+ else
+ need_reload = edev->gro_disable;
+ }
+
+ if (need_reload && netif_running(edev->ndev)) {
+ dev->features = features;
+ qede_reload(edev, NULL, NULL);
+ return 1;
+ }
+
+ return 0;
+}
+
#ifdef CONFIG_QEDE_VXLAN
static void qede_add_vxlan_port(struct net_device *dev,
sa_family_t sa_family, __be16 port)
@@ -2175,6 +2200,7 @@ static const struct net_device_ops qede_netdev_ops = {
#endif
.ndo_vlan_rx_add_vid = qede_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = qede_vlan_rx_kill_vid,
+ .ndo_set_features = qede_set_features,
.ndo_get_stats64 = qede_get_stats64,
#ifdef CONFIG_QED_SRIOV
.ndo_set_vf_link_state = qede_set_vf_link_state,
@@ -3205,7 +3231,7 @@ static int qede_stop_queues(struct qede_dev *edev)
return rc;
}
-static int qede_start_queues(struct qede_dev *edev)
+static int qede_start_queues(struct qede_dev *edev, bool clear_stats)
{
int rc, tc, i;
int vlan_removal_en = 1;
@@ -3436,6 +3462,7 @@ out:
enum qede_load_mode {
QEDE_LOAD_NORMAL,
+ QEDE_LOAD_RELOAD,
};
static int qede_load(struct qede_dev *edev, enum qede_load_mode mode)
@@ -3474,7 +3501,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode)
goto err3;
DP_INFO(edev, "Setup IRQs succeeded\n");
- rc = qede_start_queues(edev);
+ rc = qede_start_queues(edev, mode != QEDE_LOAD_RELOAD);
if (rc)
goto err4;
DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n");
@@ -3529,7 +3556,7 @@ void qede_reload(struct qede_dev *edev,
if (func)
func(edev, args);
- qede_load(edev, QEDE_LOAD_NORMAL);
+ qede_load(edev, QEDE_LOAD_RELOAD);
mutex_lock(&edev->qede_lock);
qede_config_rx_mode(edev->ndev);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 7bd6f25b4625..607bb7d4514d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -2220,7 +2220,7 @@ void qlcnic_83xx_process_rcv_ring_diag(struct qlcnic_host_sds_ring *sds_ring)
if (!opcode)
return;
- ring = QLCNIC_FETCH_RING_ID(qlcnic_83xx_hndl(sts_data[0]));
+ ring = QLCNIC_FETCH_RING_ID(sts_data[0]);
qlcnic_83xx_process_rcv_diag(adapter, ring, sts_data);
desc = &sds_ring->desc_head[consumer];
desc->status_desc_data[0] = cpu_to_le64(STATUS_OWNER_PHANTOM);
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 83d72106471c..fd5d1c93b55b 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -4846,7 +4846,6 @@ static void ql_eeh_close(struct net_device *ndev)
}
/* Disabling the timer */
- del_timer_sync(&qdev->timer);
ql_cancel_all_work_sync(qdev);
for (i = 0; i < qdev->rss_ring_count; i++)
@@ -4873,6 +4872,7 @@ static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev,
return PCI_ERS_RESULT_CAN_RECOVER;
case pci_channel_io_frozen:
netif_device_detach(ndev);
+ del_timer_sync(&qdev->timer);
if (netif_running(ndev))
ql_eeh_close(ndev);
pci_disable_device(pdev);
@@ -4880,6 +4880,7 @@ static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev,
case pci_channel_io_perm_failure:
dev_err(&pdev->dev,
"%s: pci_channel_io_perm_failure.\n", __func__);
+ del_timer_sync(&qdev->timer);
ql_eeh_close(ndev);
set_bit(QL_EEH_FATAL, &qdev->flags);
return PCI_ERS_RESULT_DISCONNECT;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 1681084cc96f..1f309127457d 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -619,6 +619,17 @@ fail:
return rc;
}
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+
+ /* All our existing PIO buffers went away */
+ efx_for_each_channel(channel, efx)
+ efx_for_each_channel_tx_queue(tx_queue, channel)
+ tx_queue->piobuf = NULL;
+}
+
#else /* !EFX_USE_PIO */
static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
@@ -635,6 +646,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx)
{
}
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+}
+
#endif /* EFX_USE_PIO */
static void efx_ef10_remove(struct efx_nic *efx)
@@ -1018,6 +1033,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
nic_data->must_realloc_vis = true;
nic_data->must_restore_filters = true;
nic_data->must_restore_piobufs = true;
+ efx_ef10_forget_old_piobufs(efx);
nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
/* Driver-created vswitches and vports must be re-created */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 0705ec869487..097f363f1630 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1726,14 +1726,33 @@ static int efx_probe_filters(struct efx_nic *efx)
#ifdef CONFIG_RFS_ACCEL
if (efx->type->offload_features & NETIF_F_NTUPLE) {
- efx->rps_flow_id = kcalloc(efx->type->max_rx_ip_filters,
- sizeof(*efx->rps_flow_id),
- GFP_KERNEL);
- if (!efx->rps_flow_id) {
+ struct efx_channel *channel;
+ int i, success = 1;
+
+ efx_for_each_channel(channel, efx) {
+ channel->rps_flow_id =
+ kcalloc(efx->type->max_rx_ip_filters,
+ sizeof(*channel->rps_flow_id),
+ GFP_KERNEL);
+ if (!channel->rps_flow_id)
+ success = 0;
+ else
+ for (i = 0;
+ i < efx->type->max_rx_ip_filters;
+ ++i)
+ channel->rps_flow_id[i] =
+ RPS_FLOW_ID_INVALID;
+ }
+
+ if (!success) {
+ efx_for_each_channel(channel, efx)
+ kfree(channel->rps_flow_id);
efx->type->filter_table_remove(efx);
rc = -ENOMEM;
goto out_unlock;
}
+
+ efx->rps_expire_index = efx->rps_expire_channel = 0;
}
#endif
out_unlock:
@@ -1744,7 +1763,10 @@ out_unlock:
static void efx_remove_filters(struct efx_nic *efx)
{
#ifdef CONFIG_RFS_ACCEL
- kfree(efx->rps_flow_id);
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ kfree(channel->rps_flow_id);
#endif
down_write(&efx->filter_sem);
efx->type->filter_table_remove(efx);
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 133e9e35be9e..4c83739d158f 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -104,7 +104,8 @@ int efx_farch_test_registers(struct efx_nic *efx,
const struct efx_farch_register_test *regs,
size_t n_regs)
{
- unsigned address = 0, i, j;
+ unsigned address = 0;
+ int i, j;
efx_oword_t mask, imask, original, reg, buf;
for (i = 0; i < n_regs; ++i) {
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index 7f295c4d7b80..2a9228a6e4a0 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -189,11 +189,12 @@ static u32 mcdi_to_ethtool_cap(u32 media, u32 cap)
case MC_CMD_MEDIA_XFP:
case MC_CMD_MEDIA_SFP_PLUS:
- result |= SUPPORTED_FIBRE;
- break;
-
case MC_CMD_MEDIA_QSFP_PLUS:
result |= SUPPORTED_FIBRE;
+ if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+ result |= SUPPORTED_1000baseT_Full;
+ if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
+ result |= SUPPORTED_10000baseT_Full;
if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
result |= SUPPORTED_40000baseCR4_Full;
break;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 38c422321cda..d13ddf9703ff 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -403,6 +403,8 @@ enum efx_sync_events_state {
* @event_test_cpu: Last CPU to handle interrupt or test event for this channel
* @irq_count: Number of IRQs since last adaptive moderation decision
* @irq_mod_score: IRQ moderation score
+ * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS,
+ * indexed by filter ID
* @n_rx_tobe_disc: Count of RX_TOBE_DISC errors
* @n_rx_ip_hdr_chksum_err: Count of RX IP header checksum errors
* @n_rx_tcp_udp_chksum_err: Count of RX TCP and UDP checksum errors
@@ -446,6 +448,8 @@ struct efx_channel {
unsigned int irq_mod_score;
#ifdef CONFIG_RFS_ACCEL
unsigned int rfs_filters_added;
+#define RPS_FLOW_ID_INVALID 0xFFFFFFFF
+ u32 *rps_flow_id;
#endif
unsigned n_rx_tobe_disc;
@@ -889,9 +893,9 @@ struct vfdi_status;
* @filter_sem: Filter table rw_semaphore, for freeing the table
* @filter_lock: Filter table lock, for mere content changes
* @filter_state: Architecture-dependent filter table state
- * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS,
- * indexed by filter ID
- * @rps_expire_index: Next index to check for expiry in @rps_flow_id
+ * @rps_expire_channel: Next channel to check for expiry
+ * @rps_expire_index: Next index to check for expiry in
+ * @rps_expire_channel's @rps_flow_id
* @active_queues: Count of RX and TX queues that haven't been flushed and drained.
* @rxq_flush_pending: Count of number of receive queues that need to be flushed.
* Decremented when the efx_flush_rx_queue() is called.
@@ -1035,7 +1039,7 @@ struct efx_nic {
spinlock_t filter_lock;
void *filter_state;
#ifdef CONFIG_RFS_ACCEL
- u32 *rps_flow_id;
+ unsigned int rps_expire_channel;
unsigned int rps_expire_index;
#endif
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 8956995b2fe7..02b0b5272c14 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -842,33 +842,18 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_channel *channel;
struct efx_filter_spec spec;
- const __be16 *ports;
- __be16 ether_type;
- int nhoff;
+ struct flow_keys fk;
int rc;
- /* The core RPS/RFS code has already parsed and validated
- * VLAN, IP and transport headers. We assume they are in the
- * header area.
- */
-
- if (skb->protocol == htons(ETH_P_8021Q)) {
- const struct vlan_hdr *vh =
- (const struct vlan_hdr *)skb->data;
+ if (flow_id == RPS_FLOW_ID_INVALID)
+ return -EINVAL;
- /* We can't filter on the IP 5-tuple and the vlan
- * together, so just strip the vlan header and filter
- * on the IP part.
- */
- EFX_BUG_ON_PARANOID(skb_headlen(skb) < sizeof(*vh));
- ether_type = vh->h_vlan_encapsulated_proto;
- nhoff = sizeof(struct vlan_hdr);
- } else {
- ether_type = skb->protocol;
- nhoff = 0;
- }
+ if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+ return -EPROTONOSUPPORT;
- if (ether_type != htons(ETH_P_IP) && ether_type != htons(ETH_P_IPV6))
+ if (fk.basic.n_proto != htons(ETH_P_IP) && fk.basic.n_proto != htons(ETH_P_IPV6))
+ return -EPROTONOSUPPORT;
+ if (fk.control.flags & FLOW_DIS_IS_FRAGMENT)
return -EPROTONOSUPPORT;
efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT,
@@ -878,56 +863,41 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT;
- spec.ether_type = ether_type;
-
- if (ether_type == htons(ETH_P_IP)) {
- const struct iphdr *ip =
- (const struct iphdr *)(skb->data + nhoff);
-
- EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip));
- if (ip_is_fragment(ip))
- return -EPROTONOSUPPORT;
- spec.ip_proto = ip->protocol;
- spec.rem_host[0] = ip->saddr;
- spec.loc_host[0] = ip->daddr;
- EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
- ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
+ spec.ether_type = fk.basic.n_proto;
+ spec.ip_proto = fk.basic.ip_proto;
+
+ if (fk.basic.n_proto == htons(ETH_P_IP)) {
+ spec.rem_host[0] = fk.addrs.v4addrs.src;
+ spec.loc_host[0] = fk.addrs.v4addrs.dst;
} else {
- const struct ipv6hdr *ip6 =
- (const struct ipv6hdr *)(skb->data + nhoff);
-
- EFX_BUG_ON_PARANOID(skb_headlen(skb) <
- nhoff + sizeof(*ip6) + 4);
- spec.ip_proto = ip6->nexthdr;
- memcpy(spec.rem_host, &ip6->saddr, sizeof(ip6->saddr));
- memcpy(spec.loc_host, &ip6->daddr, sizeof(ip6->daddr));
- ports = (const __be16 *)(ip6 + 1);
+ memcpy(spec.rem_host, &fk.addrs.v6addrs.src, sizeof(struct in6_addr));
+ memcpy(spec.loc_host, &fk.addrs.v6addrs.dst, sizeof(struct in6_addr));
}
- spec.rem_port = ports[0];
- spec.loc_port = ports[1];
+ spec.rem_port = fk.ports.src;
+ spec.loc_port = fk.ports.dst;
rc = efx->type->filter_rfs_insert(efx, &spec);
if (rc < 0)
return rc;
/* Remember this so we can check whether to expire the filter later */
- efx->rps_flow_id[rc] = flow_id;
- channel = efx_get_channel(efx, skb_get_rx_queue(skb));
+ channel = efx_get_channel(efx, rxq_index);
+ channel->rps_flow_id[rc] = flow_id;
++channel->rfs_filters_added;
- if (ether_type == htons(ETH_P_IP))
+ if (spec.ether_type == htons(ETH_P_IP))
netif_info(efx, rx_status, efx->net_dev,
"steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
(spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
- spec.rem_host, ntohs(ports[0]), spec.loc_host,
- ntohs(ports[1]), rxq_index, flow_id, rc);
+ spec.rem_host, ntohs(spec.rem_port), spec.loc_host,
+ ntohs(spec.loc_port), rxq_index, flow_id, rc);
else
netif_info(efx, rx_status, efx->net_dev,
"steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
(spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
- spec.rem_host, ntohs(ports[0]), spec.loc_host,
- ntohs(ports[1]), rxq_index, flow_id, rc);
+ spec.rem_host, ntohs(spec.rem_port), spec.loc_host,
+ ntohs(spec.loc_port), rxq_index, flow_id, rc);
return rc;
}
@@ -935,24 +905,34 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned int quota)
{
bool (*expire_one)(struct efx_nic *efx, u32 flow_id, unsigned int index);
- unsigned int index, size;
+ unsigned int channel_idx, index, size;
u32 flow_id;
if (!spin_trylock_bh(&efx->filter_lock))
return false;
expire_one = efx->type->filter_rfs_expire_one;
+ channel_idx = efx->rps_expire_channel;
index = efx->rps_expire_index;
size = efx->type->max_rx_ip_filters;
while (quota--) {
- flow_id = efx->rps_flow_id[index];
- if (expire_one(efx, flow_id, index))
+ struct efx_channel *channel = efx_get_channel(efx, channel_idx);
+ flow_id = channel->rps_flow_id[index];
+
+ if (flow_id != RPS_FLOW_ID_INVALID &&
+ expire_one(efx, flow_id, index)) {
netif_info(efx, rx_status, efx->net_dev,
- "expired filter %d [flow %u]\n",
- index, flow_id);
- if (++index == size)
+ "expired filter %d [queue %u flow %u]\n",
+ index, channel_idx, flow_id);
+ channel->rps_flow_id[index] = RPS_FLOW_ID_INVALID;
+ }
+ if (++index == size) {
+ if (++channel_idx == efx->n_channels)
+ channel_idx = 0;
index = 0;
+ }
}
+ efx->rps_expire_channel = channel_idx;
efx->rps_expire_index = index;
spin_unlock_bh(&efx->filter_lock);
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 8af25563f627..b5ab5e120bca 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -116,7 +116,6 @@ struct smsc911x_data {
struct phy_device *phy_dev;
struct mii_bus *mii_bus;
- int phy_irq[PHY_MAX_ADDR];
unsigned int using_extphy;
int last_duplex;
int last_carrier;
@@ -1073,7 +1072,6 @@ static int smsc911x_mii_init(struct platform_device *pdev,
pdata->mii_bus->priv = pdata;
pdata->mii_bus->read = smsc911x_mii_read;
pdata->mii_bus->write = smsc911x_mii_write;
- memcpy(pdata->mii_bus->irq, pdata->phy_irq, sizeof(pdata->mii_bus));
pdata->mii_bus->parent = &pdev->dev;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 4f7283d05588..44da877d2483 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -156,7 +156,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
struct netdev_hw_addr *ha;
netdev_for_each_uc_addr(ha, dev) {
- dwmac4_set_umac_addr(ioaddr, ha->addr, reg);
+ dwmac4_set_umac_addr(hw, ha->addr, reg);
reg++;
}
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eac45d0c75e2..a473c182c91d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3450,8 +3450,6 @@ int stmmac_resume(struct device *dev)
if (!netif_running(ndev))
return 0;
- spin_lock_irqsave(&priv->lock, flags);
-
/* Power Down bit, into the PM register, is cleared
* automatically as soon as a magic packet or a Wake-up frame
* is received. Anyway, it's better to manually clear
@@ -3459,7 +3457,9 @@ int stmmac_resume(struct device *dev)
* from another devices (e.g. serial console).
*/
if (device_may_wakeup(priv->device)) {
+ spin_lock_irqsave(&priv->lock, flags);
priv->hw->mac->pmt(priv->hw, 0);
+ spin_unlock_irqrestore(&priv->lock, flags);
priv->irq_wake = 0;
} else {
pinctrl_pm_select_default_state(priv->device);
@@ -3473,6 +3473,8 @@ int stmmac_resume(struct device *dev)
netif_device_attach(ndev);
+ spin_lock_irqsave(&priv->lock, flags);
+
priv->cur_rx = 0;
priv->dirty_rx = 0;
priv->dirty_tx = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 3f83c369f56c..ec295851812b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -297,7 +297,7 @@ int stmmac_mdio_register(struct net_device *ndev)
return -ENOMEM;
if (mdio_bus_data->irqs)
- memcpy(new_bus->irq, mdio_bus_data, sizeof(new_bus->irq));
+ memcpy(new_bus->irq, mdio_bus_data->irqs, sizeof(new_bus->irq));
#ifdef CONFIG_OF
if (priv->device->of_node)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 4b08a2f52b3e..53190894f17a 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1339,7 +1339,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
if (priv->coal_intvl != 0) {
struct ethtool_coalesce coal;
- coal.rx_coalesce_usecs = (priv->coal_intvl << 4);
+ coal.rx_coalesce_usecs = priv->coal_intvl;
cpsw_set_coalesce(ndev, &coal);
}
@@ -2505,8 +2505,6 @@ static int cpsw_probe(struct platform_device *pdev)
clean_ale_ret:
cpsw_ale_destroy(priv->ale);
clean_dma_ret:
- cpdma_chan_destroy(priv->txch);
- cpdma_chan_destroy(priv->rxch);
cpdma_ctlr_destroy(priv->dma);
clean_runtime_disable_ret:
pm_runtime_disable(&pdev->dev);
@@ -2534,8 +2532,6 @@ static int cpsw_remove(struct platform_device *pdev)
unregister_netdev(ndev);
cpsw_ale_destroy(priv->ale);
- cpdma_chan_destroy(priv->txch);
- cpdma_chan_destroy(priv->rxch);
cpdma_ctlr_destroy(priv->dma);
pm_runtime_disable(&pdev->dev);
device_for_each_child(&pdev->dev, NULL, cpsw_remove_child_device);
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 0a15acc075b3..11213a38c795 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -462,7 +462,7 @@ static void tile_tx_timestamp(struct sk_buff *skb, int instance)
if (unlikely((shtx->tx_flags & SKBTX_HW_TSTAMP) != 0)) {
struct mpipe_data *md = &mpipe_data[instance];
struct skb_shared_hwtstamps shhwtstamps;
- struct timespec ts;
+ struct timespec64 ts;
shtx->tx_flags |= SKBTX_IN_PROGRESS;
gxio_mpipe_get_timestamp(&md->context, &ts);
@@ -886,9 +886,9 @@ static struct ptp_clock_info ptp_mpipe_caps = {
/* Sync mPIPE's timestamp up with Linux system time and register PTP clock. */
static void register_ptp_clock(struct net_device *dev, struct mpipe_data *md)
{
- struct timespec ts;
+ struct timespec64 ts;
- getnstimeofday(&ts);
+ ktime_get_ts64(&ts);
gxio_mpipe_set_timestamp(&md->context, &ts);
mutex_init(&md->ptp_lock);
diff --git a/drivers/net/fddi/skfp/Makefile b/drivers/net/fddi/skfp/Makefile
index b0be0234abf6..a957a1c7e5ba 100644
--- a/drivers/net/fddi/skfp/Makefile
+++ b/drivers/net/fddi/skfp/Makefile
@@ -17,4 +17,4 @@ skfp-objs := skfddi.o hwmtm.o fplustm.o smt.o cfm.o \
# projects. To keep the source common for all those drivers (and
# thus simplify fixes to it), please do not clean it up!
-ccflags-y := -Idrivers/net/skfp -DPCI -DMEM_MAPPED_IO -Wno-strict-prototypes
+ccflags-y := -DPCI -DMEM_MAPPED_IO -Wno-strict-prototypes
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cadefe4fdaa2..cc39cefeae45 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -958,8 +958,8 @@ tx_error:
dev->stats.collisions++;
else if (err == -ENETUNREACH)
dev->stats.tx_carrier_errors++;
- else
- dev->stats.tx_errors++;
+
+ dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
@@ -1048,8 +1048,8 @@ tx_error:
dev->stats.collisions++;
else if (err == -ENETUNREACH)
dev->stats.tx_carrier_errors++;
- else
- dev->stats.tx_errors++;
+
+ dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
#endif
@@ -1508,6 +1508,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
{
struct nlattr *tb[IFLA_MAX + 1];
struct net_device *dev;
+ LIST_HEAD(list_kill);
int err;
memset(tb, 0, sizeof(tb));
@@ -1519,8 +1520,10 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
err = geneve_configure(net, dev, &geneve_remote_unspec,
0, 0, 0, 0, htons(dst_port), true,
GENEVE_F_UDP_ZERO_CSUM6_RX);
- if (err)
- goto err;
+ if (err) {
+ free_netdev(dev);
+ return ERR_PTR(err);
+ }
/* openvswitch users expect packet sizes to be unrestricted,
* so set the largest MTU we can.
@@ -1529,10 +1532,15 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
if (err)
goto err;
+ err = rtnl_configure_link(dev, NULL);
+ if (err < 0)
+ goto err;
+
return dev;
err:
- free_netdev(dev);
+ geneve_dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 47ee2c840b55..0e7eff7f1cd2 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -605,12 +605,41 @@ static void macsec_encrypt_done(struct crypto_async_request *base, int err)
dev_put(dev);
}
+static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
+ unsigned char **iv,
+ struct scatterlist **sg)
+{
+ size_t size, iv_offset, sg_offset;
+ struct aead_request *req;
+ void *tmp;
+
+ size = sizeof(struct aead_request) + crypto_aead_reqsize(tfm);
+ iv_offset = size;
+ size += GCM_AES_IV_LEN;
+
+ size = ALIGN(size, __alignof__(struct scatterlist));
+ sg_offset = size;
+ size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1);
+
+ tmp = kmalloc(size, GFP_ATOMIC);
+ if (!tmp)
+ return NULL;
+
+ *iv = (unsigned char *)(tmp + iv_offset);
+ *sg = (struct scatterlist *)(tmp + sg_offset);
+ req = tmp;
+
+ aead_request_set_tfm(req, tfm);
+
+ return req;
+}
+
static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
struct net_device *dev)
{
int ret;
- struct scatterlist sg[MAX_SKB_FRAGS + 1];
- unsigned char iv[GCM_AES_IV_LEN];
+ struct scatterlist *sg;
+ unsigned char *iv;
struct ethhdr *eth;
struct macsec_eth_header *hh;
size_t unprotected_len;
@@ -668,8 +697,6 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
macsec_fill_sectag(hh, secy, pn);
macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN);
- macsec_fill_iv(iv, secy->sci, pn);
-
skb_put(skb, secy->icv_len);
if (skb->len - ETH_HLEN > macsec_priv(dev)->real_dev->mtu) {
@@ -684,13 +711,15 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
return ERR_PTR(-EINVAL);
}
- req = aead_request_alloc(tx_sa->key.tfm, GFP_ATOMIC);
+ req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg);
if (!req) {
macsec_txsa_put(tx_sa);
kfree_skb(skb);
return ERR_PTR(-ENOMEM);
}
+ macsec_fill_iv(iv, secy->sci, pn);
+
sg_init_table(sg, MAX_SKB_FRAGS + 1);
skb_to_sgvec(skb, sg, 0, skb->len);
@@ -861,7 +890,6 @@ static void macsec_decrypt_done(struct crypto_async_request *base, int err)
out:
macsec_rxsa_put(rx_sa);
dev_put(dev);
- return;
}
static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
@@ -871,8 +899,8 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
struct macsec_secy *secy)
{
int ret;
- struct scatterlist sg[MAX_SKB_FRAGS + 1];
- unsigned char iv[GCM_AES_IV_LEN];
+ struct scatterlist *sg;
+ unsigned char *iv;
struct aead_request *req;
struct macsec_eth_header *hdr;
u16 icv_len = secy->icv_len;
@@ -882,7 +910,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
if (!skb)
return ERR_PTR(-ENOMEM);
- req = aead_request_alloc(rx_sa->key.tfm, GFP_ATOMIC);
+ req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg);
if (!req) {
kfree_skb(skb);
return ERR_PTR(-ENOMEM);
@@ -1234,7 +1262,7 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
struct crypto_aead *tfm;
int ret;
- tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+ tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
if (!tfm || IS_ERR(tfm))
return NULL;
@@ -3361,6 +3389,7 @@ static void __exit macsec_exit(void)
genl_unregister_family(&macsec_fam);
rtnl_link_unregister(&macsec_link_ops);
unregister_netdevice_notifier(&macsec_notifier);
+ rcu_barrier();
}
module_init(macsec_init);
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 2d2e4339f0df..9ec7f7353434 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <linux/of.h>
#include <linux/gpio.h>
+#include <linux/idr.h>
#define MII_REGS_NUM 29
@@ -286,6 +287,8 @@ err_regs:
}
EXPORT_SYMBOL_GPL(fixed_phy_add);
+static DEFINE_IDA(phy_fixed_ida);
+
static void fixed_phy_del(int phy_addr)
{
struct fixed_mdio_bus *fmb = &platform_fmb;
@@ -297,14 +300,12 @@ static void fixed_phy_del(int phy_addr)
if (gpio_is_valid(fp->link_gpio))
gpio_free(fp->link_gpio);
kfree(fp);
+ ida_simple_remove(&phy_fixed_ida, phy_addr);
return;
}
}
}
-static int phy_fixed_addr;
-static DEFINE_SPINLOCK(phy_fixed_addr_lock);
-
struct phy_device *fixed_phy_register(unsigned int irq,
struct fixed_phy_status *status,
int link_gpio,
@@ -319,17 +320,15 @@ struct phy_device *fixed_phy_register(unsigned int irq,
return ERR_PTR(-EPROBE_DEFER);
/* Get the next available PHY address, up to PHY_MAX_ADDR */
- spin_lock(&phy_fixed_addr_lock);
- if (phy_fixed_addr == PHY_MAX_ADDR) {
- spin_unlock(&phy_fixed_addr_lock);
- return ERR_PTR(-ENOSPC);
- }
- phy_addr = phy_fixed_addr++;
- spin_unlock(&phy_fixed_addr_lock);
+ phy_addr = ida_simple_get(&phy_fixed_ida, 0, PHY_MAX_ADDR, GFP_KERNEL);
+ if (phy_addr < 0)
+ return ERR_PTR(phy_addr);
ret = fixed_phy_add(irq, phy_addr, status, link_gpio);
- if (ret < 0)
+ if (ret < 0) {
+ ida_simple_remove(&phy_fixed_ida, phy_addr);
return ERR_PTR(ret);
+ }
phy = get_phy_device(fmb->mii_bus, phy_addr, false);
if (IS_ERR(phy)) {
@@ -434,6 +433,7 @@ static void __exit fixed_mdio_bus_exit(void)
list_del(&fp->node);
kfree(fp);
}
+ ida_destroy(&phy_fixed_ida);
}
module_exit(fixed_mdio_bus_exit);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 280e8795b463..ec2c1eee6405 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -285,6 +285,48 @@ static int marvell_config_aneg(struct phy_device *phydev)
return 0;
}
+static int m88e1111_config_aneg(struct phy_device *phydev)
+{
+ int err;
+
+ /* The Marvell PHY has an errata which requires
+ * that certain registers get written in order
+ * to restart autonegotiation
+ */
+ err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+ err = marvell_set_polarity(phydev, phydev->mdix);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, MII_M1111_PHY_LED_CONTROL,
+ MII_M1111_PHY_LED_DIRECT);
+ if (err < 0)
+ return err;
+
+ err = genphy_config_aneg(phydev);
+ if (err < 0)
+ return err;
+
+ if (phydev->autoneg != AUTONEG_ENABLE) {
+ int bmcr;
+
+ /* A write to speed/duplex bits (that is performed by
+ * genphy_config_aneg() call above) must be followed by
+ * a software reset. Otherwise, the write has no effect.
+ */
+ bmcr = phy_read(phydev, MII_BMCR);
+ if (bmcr < 0)
+ return bmcr;
+
+ err = phy_write(phydev, MII_BMCR, bmcr | BMCR_RESET);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
#ifdef CONFIG_OF_MDIO
/*
* Set and/or override some configuration registers based on the
@@ -407,15 +449,7 @@ static int m88e1121_config_aneg(struct phy_device *phydev)
if (err < 0)
return err;
- oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE);
-
- phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE);
- phy_write(phydev, MII_88E1121_PHY_LED_CTRL, MII_88E1121_PHY_LED_DEF);
- phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage);
-
- err = genphy_config_aneg(phydev);
-
- return err;
+ return genphy_config_aneg(phydev);
}
static int m88e1318_config_aneg(struct phy_device *phydev)
@@ -636,6 +670,28 @@ static int m88e1111_config_init(struct phy_device *phydev)
return phy_write(phydev, MII_BMCR, BMCR_RESET);
}
+static int m88e1121_config_init(struct phy_device *phydev)
+{
+ int err, oldpage;
+
+ oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE);
+
+ err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE);
+ if (err < 0)
+ return err;
+
+ /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
+ err = phy_write(phydev, MII_88E1121_PHY_LED_CTRL,
+ MII_88E1121_PHY_LED_DEF);
+ if (err < 0)
+ return err;
+
+ phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage);
+
+ /* Set marvell,reg-init configuration from device tree */
+ return marvell_config_init(phydev);
+}
+
static int m88e1510_config_init(struct phy_device *phydev)
{
int err;
@@ -668,7 +724,7 @@ static int m88e1510_config_init(struct phy_device *phydev)
return err;
}
- return marvell_config_init(phydev);
+ return m88e1121_config_init(phydev);
}
static int m88e1118_config_aneg(struct phy_device *phydev)
@@ -1161,7 +1217,7 @@ static struct phy_driver marvell_drivers[] = {
.flags = PHY_HAS_INTERRUPT,
.probe = marvell_probe,
.config_init = &m88e1111_config_init,
- .config_aneg = &marvell_config_aneg,
+ .config_aneg = &m88e1111_config_aneg,
.read_status = &marvell_read_status,
.ack_interrupt = &marvell_ack_interrupt,
.config_intr = &marvell_config_intr,
@@ -1196,7 +1252,7 @@ static struct phy_driver marvell_drivers[] = {
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.probe = marvell_probe,
- .config_init = &marvell_config_init,
+ .config_init = &m88e1121_config_init,
.config_aneg = &m88e1121_config_aneg,
.read_status = &marvell_read_status,
.ack_interrupt = &marvell_ack_interrupt,
@@ -1215,7 +1271,7 @@ static struct phy_driver marvell_drivers[] = {
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.probe = marvell_probe,
- .config_init = &marvell_config_init,
+ .config_init = &m88e1121_config_init,
.config_aneg = &m88e1318_config_aneg,
.read_status = &marvell_read_status,
.ack_interrupt = &marvell_ack_interrupt,
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 2e21e9366f76..b62c4aaee40b 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -75,22 +75,13 @@ static int smsc_phy_reset(struct phy_device *phydev)
* in all capable mode before using it.
*/
if ((rc & MII_LAN83C185_MODE_MASK) == MII_LAN83C185_MODE_POWERDOWN) {
- int timeout = 50000;
-
- /* set "all capable" mode and reset the phy */
+ /* set "all capable" mode */
rc |= MII_LAN83C185_MODE_ALL;
phy_write(phydev, MII_LAN83C185_SPECIAL_MODES, rc);
- phy_write(phydev, MII_BMCR, BMCR_RESET);
-
- /* wait end of reset (max 500 ms) */
- do {
- udelay(10);
- if (timeout-- == 0)
- return -1;
- rc = phy_read(phydev, MII_BMCR);
- } while (rc & BMCR_RESET);
}
- return 0;
+
+ /* reset the phy */
+ return genphy_soft_reset(phydev);
}
static int lan911x_config_init(struct phy_device *phydev)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index a0f64cba86ba..fdee77207323 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -990,7 +990,7 @@ static void team_port_disable(struct team *team,
#define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
-static void __team_compute_features(struct team *team)
+static void ___team_compute_features(struct team *team)
{
struct team_port *port;
u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
@@ -1021,15 +1021,20 @@ static void __team_compute_features(struct team *team)
team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+}
+static void __team_compute_features(struct team *team)
+{
+ ___team_compute_features(team);
netdev_change_features(team->dev);
}
static void team_compute_features(struct team *team)
{
mutex_lock(&team->lock);
- __team_compute_features(team);
+ ___team_compute_features(team);
mutex_unlock(&team->lock);
+ netdev_change_features(team->dev);
}
static int team_port_enter(struct team *team, struct team_port *port)
@@ -1198,8 +1203,10 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
goto err_dev_open;
}
+ netif_addr_lock_bh(dev);
dev_uc_sync_multiple(port_dev, dev);
dev_mc_sync_multiple(port_dev, dev);
+ netif_addr_unlock_bh(dev);
err = vlan_vids_add_by_dev(port_dev, dev);
if (err) {
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 36cd7f016a8d..9bbe0161a2f4 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -473,7 +473,7 @@ static void read_bulk_callback(struct urb *urb)
goto goon;
}
- if (!count || count < 4)
+ if (count < 4)
goto goon;
rx_status = buf[count - 2];
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 3f9f6ed3eec4..4e257b8d8f3e 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -31,7 +31,7 @@
#define NETNEXT_VERSION "08"
/* Information for net */
-#define NET_VERSION "3"
+#define NET_VERSION "4"
#define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -116,6 +116,7 @@
#define USB_TX_DMA 0xd434
#define USB_TOLERANCE 0xd490
#define USB_LPM_CTRL 0xd41a
+#define USB_BMU_RESET 0xd4b0
#define USB_UPS_CTRL 0xd800
#define USB_MISC_0 0xd81a
#define USB_POWER_CUT 0xd80a
@@ -338,6 +339,10 @@
#define TEST_MODE_DISABLE 0x00000001
#define TX_SIZE_ADJUST1 0x00000100
+/* USB_BMU_RESET */
+#define BMU_RESET_EP_IN 0x01
+#define BMU_RESET_EP_OUT 0x02
+
/* USB_UPS_CTRL */
#define POWER_CUT 0x0100
@@ -2169,7 +2174,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp)
static void r8153_set_rx_early_size(struct r8152 *tp)
{
u32 mtu = tp->netdev->mtu;
- u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 4;
+ u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 8;
ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data);
}
@@ -2456,6 +2461,17 @@ static void r8153_teredo_off(struct r8152 *tp)
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0);
}
+static void rtl_reset_bmu(struct r8152 *tp)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_BMU_RESET);
+ ocp_data &= ~(BMU_RESET_EP_IN | BMU_RESET_EP_OUT);
+ ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_RESET, ocp_data);
+ ocp_data |= BMU_RESET_EP_IN | BMU_RESET_EP_OUT;
+ ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_RESET, ocp_data);
+}
+
static void r8152_aldps_en(struct r8152 *tp, bool enable)
{
if (enable) {
@@ -2681,6 +2697,7 @@ static void r8153_first_init(struct r8152 *tp)
r8153_hw_phy_cfg(tp);
rtl8152_nic_reset(tp);
+ rtl_reset_bmu(tp);
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
ocp_data &= ~NOW_IS_OOB;
@@ -2742,6 +2759,7 @@ static void r8153_enter_oob(struct r8152 *tp)
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
rtl_disable(tp);
+ rtl_reset_bmu(tp);
for (i = 0; i < 1000; i++) {
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
@@ -2803,6 +2821,7 @@ static void rtl8153_disable(struct r8152 *tp)
{
r8153_aldps_en(tp, false);
rtl_disable(tp);
+ rtl_reset_bmu(tp);
r8153_aldps_en(tp, true);
usb_enable_lpm(tp->udev);
}
@@ -3382,15 +3401,11 @@ static void r8153_init(struct r8152 *tp)
r8153_power_cut_en(tp, false);
r8153_u1u2en(tp, true);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, ALDPS_SPDWN_RATIO);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, EEE_SPDWN_RATIO);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3,
- PKT_AVAIL_SPDWN_EN | SUSPEND_SPDWN_EN |
- U1U2_SPDWN_EN | L1_SPDWN_EN);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4,
- PWRSAVE_SPDWN_EN | RXDV_SPDWN_EN | TX10MIDLE_EN |
- TP100_SPDWN_EN | TP500_SPDWN_EN | TP1000_SPDWN_EN |
- EEE_SPDWN_EN);
+ /* MAC clock speed down */
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
r8153_enable_eee(tp);
r8153_aldps_en(tp, true);
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index d9d2806a47b1..dc989a8b5afb 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -61,6 +61,8 @@
#define SUSPEND_ALLMODES (SUSPEND_SUSPEND0 | SUSPEND_SUSPEND1 | \
SUSPEND_SUSPEND2 | SUSPEND_SUSPEND3)
+#define CARRIER_CHECK_DELAY (2 * HZ)
+
struct smsc95xx_priv {
u32 mac_cr;
u32 hash_hi;
@@ -69,6 +71,9 @@ struct smsc95xx_priv {
spinlock_t mac_cr_lock;
u8 features;
u8 suspend_flags;
+ bool link_ok;
+ struct delayed_work carrier_check;
+ struct usbnet *dev;
};
static bool turbo_mode = true;
@@ -624,6 +629,44 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
intdata);
}
+static void set_carrier(struct usbnet *dev, bool link)
+{
+ struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
+
+ if (pdata->link_ok == link)
+ return;
+
+ pdata->link_ok = link;
+
+ if (link)
+ usbnet_link_change(dev, 1, 0);
+ else
+ usbnet_link_change(dev, 0, 0);
+}
+
+static void check_carrier(struct work_struct *work)
+{
+ struct smsc95xx_priv *pdata = container_of(work, struct smsc95xx_priv,
+ carrier_check.work);
+ struct usbnet *dev = pdata->dev;
+ int ret;
+
+ if (pdata->suspend_flags != 0)
+ return;
+
+ ret = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, MII_BMSR);
+ if (ret < 0) {
+ netdev_warn(dev->net, "Failed to read MII_BMSR\n");
+ return;
+ }
+ if (ret & BMSR_LSTATUS)
+ set_carrier(dev, 1);
+ else
+ set_carrier(dev, 0);
+
+ schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY);
+}
+
/* Enable or disable Tx & Rx checksum offload engines */
static int smsc95xx_set_features(struct net_device *netdev,
netdev_features_t features)
@@ -1165,13 +1208,20 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
dev->net->flags |= IFF_MULTICAST;
dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM;
dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
+
+ pdata->dev = dev;
+ INIT_DELAYED_WORK(&pdata->carrier_check, check_carrier);
+ schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY);
+
return 0;
}
static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
{
struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
+
if (pdata) {
+ cancel_delayed_work(&pdata->carrier_check);
netif_dbg(dev, ifdown, dev->net, "free pdata\n");
kfree(pdata);
pdata = NULL;
@@ -1695,6 +1745,7 @@ static int smsc95xx_resume(struct usb_interface *intf)
/* do this first to ensure it's cleared even in error case */
pdata->suspend_flags = 0;
+ schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY);
if (suspend_flags & SUSPEND_ALLMODES) {
/* clear wake-up sources */
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 49d84e540343..e0638e556fe7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1925,24 +1925,11 @@ static int virtnet_probe(struct virtio_device *vdev)
virtio_device_ready(vdev);
- /* Last of all, set up some receive buffers. */
- for (i = 0; i < vi->curr_queue_pairs; i++) {
- try_fill_recv(vi, &vi->rq[i], GFP_KERNEL);
-
- /* If we didn't even get one input buffer, we're useless. */
- if (vi->rq[i].vq->num_free ==
- virtqueue_get_vring_size(vi->rq[i].vq)) {
- free_unused_bufs(vi);
- err = -ENOMEM;
- goto free_recv_bufs;
- }
- }
-
vi->nb.notifier_call = &virtnet_cpu_callback;
err = register_hotcpu_notifier(&vi->nb);
if (err) {
pr_debug("virtio_net: registering cpu notifier failed\n");
- goto free_recv_bufs;
+ goto free_unregister_netdev;
}
/* Assume link up if device can't report link status,
@@ -1960,10 +1947,9 @@ static int virtnet_probe(struct virtio_device *vdev)
return 0;
-free_recv_bufs:
+free_unregister_netdev:
vi->vdev->config->reset(vdev);
- free_receive_bufs(vi);
unregister_netdev(dev);
free_vqs:
cancel_delayed_work_sync(&vi->refill);
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index db8022ae415b..08885bc8d6db 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1369,7 +1369,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd;
segCnt = rcdlro->segCnt;
- BUG_ON(segCnt <= 1);
+ WARN_ON_ONCE(segCnt == 0);
mss = rcdlro->mss;
if (unlikely(segCnt <= 1))
segCnt = 0;
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index c4825392d64b..3d2b64e63408 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.7.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.8.0-k"
/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040700
+#define VMXNET3_DRIVER_VERSION_NUM 0x01040800
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index dff08842f26d..8bd8c7e1ee87 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -304,7 +304,7 @@ static int vrf_rt6_create(struct net_device *dev)
dst_hold(&rt6->dst);
rt6->rt6i_table = rt6i_table;
- rt6->dst.output = vrf_output6;
+ rt6->dst.output = vrf_output6;
rcu_assign_pointer(vrf->rt6, rt6);
rc = 0;
@@ -403,7 +403,7 @@ static int vrf_rtable_create(struct net_device *dev)
if (!rth)
return -ENOMEM;
- rth->dst.output = vrf_output;
+ rth->dst.output = vrf_output;
rth->rt_table_id = vrf->tb_id;
rcu_assign_pointer(vrf->rth, rth);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 8ff30c3bdfce..b3b9db68f758 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2952,30 +2952,6 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
return 0;
}
-struct net_device *vxlan_dev_create(struct net *net, const char *name,
- u8 name_assign_type, struct vxlan_config *conf)
-{
- struct nlattr *tb[IFLA_MAX+1];
- struct net_device *dev;
- int err;
-
- memset(&tb, 0, sizeof(tb));
-
- dev = rtnl_create_link(net, name, name_assign_type,
- &vxlan_link_ops, tb);
- if (IS_ERR(dev))
- return dev;
-
- err = vxlan_dev_configure(net, dev, conf);
- if (err < 0) {
- free_netdev(dev);
- return ERR_PTR(err);
- }
-
- return dev;
-}
-EXPORT_SYMBOL_GPL(vxlan_dev_create);
-
static int vxlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
@@ -3086,6 +3062,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
+ if (tb[IFLA_MTU])
+ conf.mtu = nla_get_u32(tb[IFLA_MTU]);
+
err = vxlan_dev_configure(src_net, dev, &conf);
switch (err) {
case -ENODEV:
@@ -3265,6 +3244,40 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
.get_link_net = vxlan_get_link_net,
};
+struct net_device *vxlan_dev_create(struct net *net, const char *name,
+ u8 name_assign_type,
+ struct vxlan_config *conf)
+{
+ struct nlattr *tb[IFLA_MAX + 1];
+ struct net_device *dev;
+ int err;
+
+ memset(&tb, 0, sizeof(tb));
+
+ dev = rtnl_create_link(net, name, name_assign_type,
+ &vxlan_link_ops, tb);
+ if (IS_ERR(dev))
+ return dev;
+
+ err = vxlan_dev_configure(net, dev, conf);
+ if (err < 0) {
+ free_netdev(dev);
+ return ERR_PTR(err);
+ }
+
+ err = rtnl_configure_link(dev, NULL);
+ if (err < 0) {
+ LIST_HEAD(list_kill);
+
+ vxlan_dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+ return ERR_PTR(err);
+ }
+
+ return dev;
+}
+EXPORT_SYMBOL_GPL(vxlan_dev_create);
+
static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn,
struct net_device *dev)
{
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 49af62428c88..a92a0ba829f5 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -1083,7 +1083,7 @@ int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name,
}
ath10k_dbg_dump(ar, ATH10K_DBG_BOOT, "features", "",
- ar->running_fw->fw_file.fw_features,
+ fw_file->fw_features,
sizeof(fw_file->fw_features));
break;
case ATH10K_FW_IE_FW_IMAGE:
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index cc979a4faeb0..813cdd2621a1 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1904,7 +1904,6 @@ static void ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb)
return;
}
}
- ath10k_htt_rx_msdu_buff_replenish(htt);
}
static void ath10k_htt_rx_tx_fetch_resp_id_confirm(struct ath10k *ar,
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 6dd1d26b357f..4040f9413e86 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -679,10 +679,10 @@ static int ath10k_peer_create(struct ath10k *ar,
peer = ath10k_peer_find(ar, vdev_id, addr);
if (!peer) {
+ spin_unlock_bh(&ar->data_lock);
ath10k_warn(ar, "failed to find peer %pM on vdev %i after creation\n",
addr, vdev_id);
ath10k_wmi_peer_delete(ar, vdev_id, addr);
- spin_unlock_bh(&ar->data_lock);
return -ENOENT;
}
diff --git a/drivers/net/wireless/ath/ath9k/reg.h b/drivers/net/wireless/ath/ath9k/reg.h
index 9272ca90632b..80ff69f99229 100644
--- a/drivers/net/wireless/ath/ath9k/reg.h
+++ b/drivers/net/wireless/ath/ath9k/reg.h
@@ -1122,12 +1122,12 @@ enum {
#define AR9300_NUM_GPIO 16
#define AR9330_NUM_GPIO 16
#define AR9340_NUM_GPIO 23
-#define AR9462_NUM_GPIO 10
+#define AR9462_NUM_GPIO 14
#define AR9485_NUM_GPIO 12
#define AR9531_NUM_GPIO 18
#define AR9550_NUM_GPIO 24
#define AR9561_NUM_GPIO 23
-#define AR9565_NUM_GPIO 12
+#define AR9565_NUM_GPIO 14
#define AR9580_NUM_GPIO 16
#define AR7010_NUM_GPIO 16
@@ -1139,12 +1139,12 @@ enum {
#define AR9300_GPIO_MASK 0x0000F4FF
#define AR9330_GPIO_MASK 0x0000F4FF
#define AR9340_GPIO_MASK 0x0000000F
-#define AR9462_GPIO_MASK 0x000003FF
+#define AR9462_GPIO_MASK 0x00003FFF
#define AR9485_GPIO_MASK 0x00000FFF
#define AR9531_GPIO_MASK 0x0000000F
#define AR9550_GPIO_MASK 0x0000000F
#define AR9561_GPIO_MASK 0x0000000F
-#define AR9565_GPIO_MASK 0x00000FFF
+#define AR9565_GPIO_MASK 0x00003FFF
#define AR9580_GPIO_MASK 0x0000F4FF
#define AR7010_GPIO_MASK 0x0000FFFF
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index d0631b6cfd53..62f475e31077 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -2540,12 +2540,14 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
const u8 *mac, struct station_info *sinfo)
{
struct brcmf_if *ifp = netdev_priv(ndev);
+ struct brcmf_scb_val_le scb_val;
s32 err = 0;
struct brcmf_sta_info_le sta_info_le;
u32 sta_flags;
u32 is_tdls_peer;
s32 total_rssi;
s32 count_rssi;
+ int rssi;
u32 i;
brcmf_dbg(TRACE, "Enter, MAC %pM\n", mac);
@@ -2629,6 +2631,20 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
total_rssi /= count_rssi;
sinfo->signal = total_rssi;
+ } else if (test_bit(BRCMF_VIF_STATUS_CONNECTED,
+ &ifp->vif->sme_state)) {
+ memset(&scb_val, 0, sizeof(scb_val));
+ err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_RSSI,
+ &scb_val, sizeof(scb_val));
+ if (err) {
+ brcmf_err("Could not get rssi (%d)\n", err);
+ goto done;
+ } else {
+ rssi = le32_to_cpu(scb_val.val);
+ sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+ sinfo->signal = rssi;
+ brcmf_dbg(CONN, "RSSI %d dBm\n", rssi);
+ }
}
}
done:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
index 68f1ce02f4bf..2b9a2bc429d6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
@@ -1157,6 +1157,8 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
brcmu_pkt_buf_free_skb(skb);
return;
}
+
+ skb->protocol = eth_type_trans(skb, ifp->ndev);
brcmf_netif_rx(ifp, skb);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index e5f267b21316..18a8474b5760 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3851,8 +3851,8 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
if (idx != 0)
return -ENOENT;
- if (fw_has_capa(&mvm->fw->ucode_capa,
- IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
+ if (!fw_has_capa(&mvm->fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
return -ENOENT;
mutex_lock(&mvm->mutex);
@@ -3898,8 +3898,8 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
- if (fw_has_capa(&mvm->fw->ucode_capa,
- IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
+ if (!fw_has_capa(&mvm->fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
return;
/* if beacon filtering isn't on mac80211 does it anyway */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index ac2c5718e454..2c61516d06ff 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -581,7 +581,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
struct iwl_rx_mpdu_desc *desc)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
- struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+ struct iwl_mvm_sta *mvm_sta;
struct iwl_mvm_baid_data *baid_data;
struct iwl_mvm_reorder_buffer *buffer;
struct sk_buff *tail;
@@ -604,6 +604,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
if (WARN_ON(IS_ERR_OR_NULL(sta)))
return false;
+ mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+
/* not a data packet */
if (!ieee80211_is_data_qos(hdr->frame_control) ||
is_multicast_ether_addr(hdr->addr1))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 6f609dd5c222..e78fc567ff7d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1222,7 +1222,7 @@ static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type)
return -EIO;
}
-#define SCAN_TIMEOUT (16 * HZ)
+#define SCAN_TIMEOUT (20 * HZ)
void iwl_mvm_scan_timeout(unsigned long data)
{
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index fea4d3437e2f..b23ab4a4504f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1852,12 +1852,18 @@ static struct iwl_mvm_sta *iwl_mvm_get_key_sta(struct iwl_mvm *mvm,
mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
u8 sta_id = mvmvif->ap_sta_id;
+ sta = rcu_dereference_check(mvm->fw_id_to_mac_id[sta_id],
+ lockdep_is_held(&mvm->mutex));
+
/*
* It is possible that the 'sta' parameter is NULL,
* for example when a GTK is removed - the sta_id will then
* be the AP ID, and no station was passed by mac80211.
*/
- return iwl_mvm_sta_from_staid_protected(mvm, sta_id);
+ if (IS_ERR_OR_NULL(sta))
+ return NULL;
+
+ return iwl_mvm_sta_from_mac80211(sta);
}
return NULL;
@@ -1955,6 +1961,14 @@ static int iwl_mvm_send_sta_igtk(struct iwl_mvm *mvm,
struct ieee80211_key_seq seq;
const u8 *pn;
+ switch (keyconf->cipher) {
+ case WLAN_CIPHER_SUITE_AES_CMAC:
+ igtk_cmd.ctrl_flags |= cpu_to_le32(STA_KEY_FLG_CCM);
+ break;
+ default:
+ return -EINVAL;
+ }
+
memcpy(igtk_cmd.IGTK, keyconf->key, keyconf->keylen);
ieee80211_get_key_rx_seq(keyconf, 0, &seq);
pn = seq.aes_cmac.pn;
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 9ed0ed1bf514..4dd5adcdd29b 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2776,6 +2776,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2,
if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER] ||
!info->attrs[HWSIM_ATTR_FLAGS] ||
!info->attrs[HWSIM_ATTR_COOKIE] ||
+ !info->attrs[HWSIM_ATTR_SIGNAL] ||
!info->attrs[HWSIM_ATTR_TX_INFO])
goto out;
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index fe19ace0d6a0..b04cf30f3959 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -1149,7 +1149,7 @@ static void rtl8192eu_phy_iqcalibrate(struct rtl8xxxu_priv *priv,
for (i = 0; i < retry; i++) {
path_b_ok = rtl8192eu_rx_iqk_path_b(priv);
- if (path_a_ok == 0x03) {
+ if (path_b_ok == 0x03) {
val32 = rtl8xxxu_read32(priv,
REG_RX_POWER_BEFORE_IQK_B_2);
result[t][6] = (val32 >> 16) & 0x3ff;
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 0f48048b8654..3a0faa8fe9d4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(channel5g_80m);
void rtl_addr_delay(u32 addr)
{
if (addr == 0xfe)
- msleep(50);
+ mdelay(50);
else if (addr == 0xfd)
msleep(5);
else if (addr == 0xfc)
@@ -75,7 +75,7 @@ void rtl_rfreg_delay(struct ieee80211_hw *hw, enum radio_path rfpath, u32 addr,
rtl_addr_delay(addr);
} else {
rtl_set_rfreg(hw, rfpath, addr, mask, data);
- usleep_range(1, 2);
+ udelay(1);
}
}
EXPORT_SYMBOL(rtl_rfreg_delay);
@@ -86,7 +86,7 @@ void rtl_bb_delay(struct ieee80211_hw *hw, u32 addr, u32 data)
rtl_addr_delay(addr);
} else {
rtl_set_bbreg(hw, addr, MASKDWORD, data);
- usleep_range(1, 2);
+ udelay(1);
}
}
EXPORT_SYMBOL(rtl_bb_delay);
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 020ac1a4b408..cea9443c22a6 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -382,7 +382,7 @@ static int wlcore_probe_of(struct spi_device *spi, struct wl12xx_spi_glue *glue,
ret = of_property_read_u32(dt_node, "ref-clock-frequency",
&pdev_data->ref_clock_freq);
- if (IS_ERR_VALUE(ret)) {
+ if (ret) {
dev_err(glue->dev,
"can't get reference clock frequency (%d)\n", ret);
return ret;
@@ -425,7 +425,7 @@ static int wl1271_probe(struct spi_device *spi)
}
ret = wlcore_probe_of(spi, glue, &pdev_data);
- if (IS_ERR_VALUE(ret)) {
+ if (ret) {
dev_err(glue->dev,
"can't get device tree parameters (%d)\n", ret);
return ret;
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index f7718ec685fa..cea8350fbc7e 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -344,6 +344,8 @@ struct device *nd_pfn_create(struct nd_region *nd_region)
int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
{
u64 checksum, offset;
+ unsigned long align;
+ enum nd_pfn_mode mode;
struct nd_namespace_io *nsio;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
struct nd_namespace_common *ndns = nd_pfn->ndns;
@@ -386,22 +388,50 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
return -ENXIO;
}
+ align = le32_to_cpu(pfn_sb->align);
+ offset = le64_to_cpu(pfn_sb->dataoff);
+ if (align == 0)
+ align = 1UL << ilog2(offset);
+ mode = le32_to_cpu(pfn_sb->mode);
+
if (!nd_pfn->uuid) {
- /* from probe we allocate */
+ /*
+ * When probing a namepace via nd_pfn_probe() the uuid
+ * is NULL (see: nd_pfn_devinit()) we init settings from
+ * pfn_sb
+ */
nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
if (!nd_pfn->uuid)
return -ENOMEM;
+ nd_pfn->align = align;
+ nd_pfn->mode = mode;
} else {
- /* from init we validate */
+ /*
+ * When probing a pfn / dax instance we validate the
+ * live settings against the pfn_sb
+ */
if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
return -ENODEV;
+
+ /*
+ * If the uuid validates, but other settings mismatch
+ * return EINVAL because userspace has managed to change
+ * the configuration without specifying new
+ * identification.
+ */
+ if (nd_pfn->align != align || nd_pfn->mode != mode) {
+ dev_err(&nd_pfn->dev,
+ "init failed, settings mismatch\n");
+ dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
+ nd_pfn->align, align, nd_pfn->mode,
+ mode);
+ return -EINVAL;
+ }
}
- if (nd_pfn->align == 0)
- nd_pfn->align = le32_to_cpu(pfn_sb->align);
- if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) {
+ if (align > nvdimm_namespace_capacity(ndns)) {
dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
- nd_pfn->align, nvdimm_namespace_capacity(ndns));
+ align, nvdimm_namespace_capacity(ndns));
return -EINVAL;
}
@@ -411,7 +441,6 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
* namespace has changed since the pfn superblock was
* established.
*/
- offset = le64_to_cpu(pfn_sb->dataoff);
nsio = to_nd_namespace_io(&ndns->dev);
if (offset >= resource_size(&nsio->res)) {
dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
@@ -419,10 +448,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
return -EBUSY;
}
- if ((nd_pfn->align && !IS_ALIGNED(offset, nd_pfn->align))
+ if ((align && !IS_ALIGNED(offset, align))
|| !IS_ALIGNED(offset, PAGE_SIZE)) {
- dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n",
- offset);
+ dev_err(&nd_pfn->dev,
+ "bad offset: %#llx dax disabled align: %#lx\n",
+ offset, align);
return -ENXIO;
}
@@ -502,7 +532,6 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
res->start += start_pad;
res->end -= end_trunc;
- nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset < SZ_8K)
return ERR_PTR(-EINVAL);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 042baec56931..608fc4464574 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -164,14 +164,22 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
}
static long pmem_direct_access(struct block_device *bdev, sector_t sector,
- void __pmem **kaddr, pfn_t *pfn)
+ void __pmem **kaddr, pfn_t *pfn, long size)
{
struct pmem_device *pmem = bdev->bd_queue->queuedata;
resource_size_t offset = sector * 512 + pmem->data_offset;
+ if (unlikely(is_bad_pmem(&pmem->bb, sector, size)))
+ return -EIO;
*kaddr = pmem->virt_addr + offset;
*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+ /*
+ * If badblocks are present, limit known good range to the
+ * requested range.
+ */
+ if (unlikely(pmem->bb.count))
+ return size;
return pmem->size - pmem->pfn_pad - offset;
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2de248bd462b..1a51584a382b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -95,6 +95,15 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
break;
}
break;
+ case NVME_CTRL_DEAD:
+ switch (old_state) {
+ case NVME_CTRL_DELETING:
+ changed = true;
+ /* FALLTHRU */
+ default:
+ break;
+ }
+ break;
default:
break;
}
@@ -720,10 +729,14 @@ static void nvme_init_integrity(struct nvme_ns *ns)
switch (ns->pi_type) {
case NVME_NS_DPS_PI_TYPE3:
integrity.profile = &t10_pi_type3_crc;
+ integrity.tag_size = sizeof(u16) + sizeof(u32);
+ integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
case NVME_NS_DPS_PI_TYPE1:
case NVME_NS_DPS_PI_TYPE2:
integrity.profile = &t10_pi_type1_crc;
+ integrity.tag_size = sizeof(u16);
+ integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
default:
integrity.profile = NULL;
@@ -1212,6 +1225,9 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
return ctrl->ops->reset_ctrl(ctrl);
case NVME_IOCTL_SUBSYS_RESET:
return nvme_reset_subsystem(ctrl);
+ case NVME_IOCTL_RESCAN:
+ nvme_queue_scan(ctrl);
+ return 0;
default:
return -ENOTTY;
}
@@ -1239,6 +1255,17 @@ static ssize_t nvme_sysfs_reset(struct device *dev,
}
static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
+static ssize_t nvme_sysfs_rescan(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+ nvme_queue_scan(ctrl);
+ return count;
+}
+static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
+
static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -1342,6 +1369,7 @@ nvme_show_int_function(cntlid);
static struct attribute *nvme_dev_attrs[] = {
&dev_attr_reset_controller.attr,
+ &dev_attr_rescan_controller.attr,
&dev_attr_model.attr,
&dev_attr_serial.attr,
&dev_attr_firmware_rev.attr,
@@ -1580,6 +1608,15 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns, *next;
+ /*
+ * The dead states indicates the controller was not gracefully
+ * disconnected. In that case, we won't be able to flush any data while
+ * removing the namespaces' disks; fail all the queues now to avoid
+ * potentially having to clean up the failed sync later.
+ */
+ if (ctrl->state == NVME_CTRL_DEAD)
+ nvme_kill_queues(ctrl);
+
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list)
nvme_ns_remove(ns);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 114b92873894..1daa0482de0e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -72,6 +72,7 @@ enum nvme_ctrl_state {
NVME_CTRL_LIVE,
NVME_CTRL_RESETTING,
NVME_CTRL_DELETING,
+ NVME_CTRL_DEAD,
};
struct nvme_ctrl {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 0f093f14d348..befac5b19490 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1394,7 +1394,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
struct pci_dev *pdev = to_pci_dev(dev->dev);
int result, i, vecs, nr_io_queues, size;
- nr_io_queues = num_possible_cpus();
+ nr_io_queues = num_online_cpus();
result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
if (result < 0)
return result;
@@ -1551,12 +1551,12 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
static void nvme_disable_io_queues(struct nvme_dev *dev)
{
- int pass;
+ int pass, queues = dev->online_queues - 1;
unsigned long timeout;
u8 opcode = nvme_admin_delete_sq;
for (pass = 0; pass < 2; pass++) {
- int sent = 0, i = dev->queue_count - 1;
+ int sent = 0, i = queues;
reinit_completion(&dev->ioq_wait);
retry:
@@ -1679,9 +1679,14 @@ static int nvme_pci_enable(struct nvme_dev *dev)
static void nvme_dev_unmap(struct nvme_dev *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+ int bars;
+
if (dev->bar)
iounmap(dev->bar);
- pci_release_regions(to_pci_dev(dev->dev));
+
+ bars = pci_select_bars(pdev, IORESOURCE_MEM);
+ pci_release_selected_regions(pdev, bars);
}
static void nvme_pci_disable(struct nvme_dev *dev)
@@ -1857,7 +1862,7 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work)
nvme_kill_queues(&dev->ctrl);
if (pci_get_drvdata(pdev))
- pci_stop_and_remove_bus_device_locked(pdev);
+ device_release_driver(&pdev->dev);
nvme_put_ctrl(&dev->ctrl);
}
@@ -1924,7 +1929,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
return 0;
release:
- pci_release_regions(pdev);
+ pci_release_selected_regions(pdev, bars);
return -ENODEV;
}
@@ -2017,6 +2022,10 @@ static void nvme_remove(struct pci_dev *pdev)
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
pci_set_drvdata(pdev, NULL);
+
+ if (!pci_device_is_present(pdev))
+ nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
+
flush_work(&dev->reset_work);
nvme_uninit_ctrl(&dev->ctrl);
nvme_dev_disable(dev, true);
@@ -2060,14 +2069,17 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
* shutdown the controller to quiesce. The controller will be restarted
* after the slot reset through driver's slot_reset callback.
*/
- dev_warn(dev->ctrl.device, "error detected: state:%d\n", state);
switch (state) {
case pci_channel_io_normal:
return PCI_ERS_RESULT_CAN_RECOVER;
case pci_channel_io_frozen:
+ dev_warn(dev->ctrl.device,
+ "frozen state error detected, reset controller\n");
nvme_dev_disable(dev, false);
return PCI_ERS_RESULT_NEED_RESET;
case pci_channel_io_perm_failure:
+ dev_warn(dev->ctrl.device,
+ "failure state error detected, request disconnect\n");
return PCI_ERS_RESULT_DISCONNECT;
}
return PCI_ERS_RESULT_NEED_RESET;
@@ -2102,6 +2114,12 @@ static const struct pci_device_id nvme_id_table[] = {
{ PCI_VDEVICE(INTEL, 0x0953),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DISCARD_ZEROES, },
+ { PCI_VDEVICE(INTEL, 0x0a53),
+ .driver_data = NVME_QUIRK_STRIPE_SIZE |
+ NVME_QUIRK_DISCARD_ZEROES, },
+ { PCI_VDEVICE(INTEL, 0x0a54),
+ .driver_data = NVME_QUIRK_STRIPE_SIZE |
+ NVME_QUIRK_DISCARD_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index bb4ea123547f..965911d9b36a 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -113,7 +113,7 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj,
rc = nvmem_reg_read(nvmem, pos, buf, count);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
return count;
@@ -147,7 +147,7 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj,
rc = nvmem_reg_write(nvmem, pos, buf, count);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
return count;
@@ -366,7 +366,7 @@ static int nvmem_add_cells(struct nvmem_device *nvmem,
}
rval = nvmem_cell_info_to_nvmem_cell(nvmem, &info[i], cells[i]);
- if (IS_ERR_VALUE(rval)) {
+ if (rval) {
kfree(cells[i]);
goto err;
}
@@ -963,7 +963,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem,
rc = nvmem_reg_read(nvmem, cell->offset, buf, cell->bytes);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
/* shift bits in-place */
@@ -998,7 +998,7 @@ void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len)
return ERR_PTR(-ENOMEM);
rc = __nvmem_cell_read(nvmem, cell, buf, len);
- if (IS_ERR_VALUE(rc)) {
+ if (rc) {
kfree(buf);
return ERR_PTR(rc);
}
@@ -1083,7 +1083,7 @@ int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len)
if (cell->bit_offset || cell->nbits)
kfree(buf);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
return len;
@@ -1111,11 +1111,11 @@ ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem,
return -EINVAL;
rc = nvmem_cell_info_to_nvmem_cell(nvmem, info, &cell);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
rc = __nvmem_cell_read(nvmem, &cell, buf, &len);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
return len;
@@ -1141,7 +1141,7 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem,
return -EINVAL;
rc = nvmem_cell_info_to_nvmem_cell(nvmem, info, &cell);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
return nvmem_cell_write(&cell, buf, cell.bytes);
@@ -1170,7 +1170,7 @@ int nvmem_device_read(struct nvmem_device *nvmem,
rc = nvmem_reg_read(nvmem, offset, buf, bytes);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
return bytes;
@@ -1198,7 +1198,7 @@ int nvmem_device_write(struct nvmem_device *nvmem,
rc = nvmem_reg_write(nvmem, offset, buf, bytes);
- if (IS_ERR_VALUE(rc))
+ if (rc)
return rc;
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index bee3fa96b981..d7efd9d458aa 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -10,7 +10,6 @@ obj-$(CONFIG_OF_UNITTEST) += unittest.o
obj-$(CONFIG_OF_MDIO) += of_mdio.o
obj-$(CONFIG_OF_PCI) += of_pci.o
obj-$(CONFIG_OF_PCI_IRQ) += of_pci_irq.o
-obj-$(CONFIG_OF_MTD) += of_mtd.o
obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
obj-$(CONFIG_OF_RESOLVE) += resolver.o
obj-$(CONFIG_OF_OVERLAY) += overlay.o
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 14f2f8c7c260..33daffc4392c 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -395,7 +395,7 @@ static int unflatten_dt_nodes(const void *blob,
struct device_node **nodepp)
{
struct device_node *root;
- int offset = 0, depth = 0;
+ int offset = 0, depth = 0, initial_depth = 0;
#define FDT_MAX_DEPTH 64
unsigned int fpsizes[FDT_MAX_DEPTH];
struct device_node *nps[FDT_MAX_DEPTH];
@@ -405,11 +405,22 @@ static int unflatten_dt_nodes(const void *blob,
if (nodepp)
*nodepp = NULL;
+ /*
+ * We're unflattening device sub-tree if @dad is valid. There are
+ * possibly multiple nodes in the first level of depth. We need
+ * set @depth to 1 to make fdt_next_node() happy as it bails
+ * immediately when negative @depth is found. Otherwise, the device
+ * nodes except the first one won't be unflattened successfully.
+ */
+ if (dad)
+ depth = initial_depth = 1;
+
root = dad;
fpsizes[depth] = dad ? strlen(of_node_full_name(dad)) : 0;
nps[depth] = dad;
+
for (offset = 0;
- offset >= 0 && depth >= 0;
+ offset >= 0 && depth >= initial_depth;
offset = fdt_next_node(blob, offset, &depth)) {
if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH))
continue;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index e7bfc175b8e1..6ec743faabe8 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -386,13 +386,13 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
EXPORT_SYMBOL_GPL(of_irq_to_resource);
/**
- * of_irq_get - Decode a node's IRQ and return it as a Linux irq number
+ * of_irq_get - Decode a node's IRQ and return it as a Linux IRQ number
* @dev: pointer to device tree node
- * @index: zero-based index of the irq
- *
- * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
- * is not yet created.
+ * @index: zero-based index of the IRQ
*
+ * Returns Linux IRQ number on success, or 0 on the IRQ mapping failure, or
+ * -EPROBE_DEFER if the IRQ domain is not yet created, or error code in case
+ * of any other failure.
*/
int of_irq_get(struct device_node *dev, int index)
{
@@ -413,12 +413,13 @@ int of_irq_get(struct device_node *dev, int index)
EXPORT_SYMBOL_GPL(of_irq_get);
/**
- * of_irq_get_byname - Decode a node's IRQ and return it as a Linux irq number
+ * of_irq_get_byname - Decode a node's IRQ and return it as a Linux IRQ number
* @dev: pointer to device tree node
- * @name: irq name
+ * @name: IRQ name
*
- * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
- * is not yet created, or error code in case of any other failure.
+ * Returns Linux IRQ number on success, or 0 on the IRQ mapping failure, or
+ * -EPROBE_DEFER if the IRQ domain is not yet created, or error code in case
+ * of any other failure.
*/
int of_irq_get_byname(struct device_node *dev, const char *name)
{
diff --git a/drivers/of/of_mtd.c b/drivers/of/of_mtd.c
deleted file mode 100644
index b7361ed70537..000000000000
--- a/drivers/of/of_mtd.c
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * Copyright 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
- *
- * OF helpers for mtd.
- *
- * This file is released under the GPLv2
- *
- */
-#include <linux/kernel.h>
-#include <linux/of_mtd.h>
-#include <linux/mtd/nand.h>
-#include <linux/export.h>
-
-/**
- * It maps 'enum nand_ecc_modes_t' found in include/linux/mtd/nand.h
- * into the device tree binding of 'nand-ecc', so that MTD
- * device driver can get nand ecc from device tree.
- */
-static const char *nand_ecc_modes[] = {
- [NAND_ECC_NONE] = "none",
- [NAND_ECC_SOFT] = "soft",
- [NAND_ECC_HW] = "hw",
- [NAND_ECC_HW_SYNDROME] = "hw_syndrome",
- [NAND_ECC_HW_OOB_FIRST] = "hw_oob_first",
- [NAND_ECC_SOFT_BCH] = "soft_bch",
-};
-
-/**
- * of_get_nand_ecc_mode - Get nand ecc mode for given device_node
- * @np: Pointer to the given device_node
- *
- * The function gets ecc mode string from property 'nand-ecc-mode',
- * and return its index in nand_ecc_modes table, or errno in error case.
- */
-int of_get_nand_ecc_mode(struct device_node *np)
-{
- const char *pm;
- int err, i;
-
- err = of_property_read_string(np, "nand-ecc-mode", &pm);
- if (err < 0)
- return err;
-
- for (i = 0; i < ARRAY_SIZE(nand_ecc_modes); i++)
- if (!strcasecmp(pm, nand_ecc_modes[i]))
- return i;
-
- return -ENODEV;
-}
-EXPORT_SYMBOL_GPL(of_get_nand_ecc_mode);
-
-/**
- * of_get_nand_ecc_step_size - Get ECC step size associated to
- * the required ECC strength (see below).
- * @np: Pointer to the given device_node
- *
- * return the ECC step size, or errno in error case.
- */
-int of_get_nand_ecc_step_size(struct device_node *np)
-{
- int ret;
- u32 val;
-
- ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
- return ret ? ret : val;
-}
-EXPORT_SYMBOL_GPL(of_get_nand_ecc_step_size);
-
-/**
- * of_get_nand_ecc_strength - Get required ECC strength over the
- * correspnding step size as defined by 'nand-ecc-size'
- * @np: Pointer to the given device_node
- *
- * return the ECC strength, or errno in error case.
- */
-int of_get_nand_ecc_strength(struct device_node *np)
-{
- int ret;
- u32 val;
-
- ret = of_property_read_u32(np, "nand-ecc-strength", &val);
- return ret ? ret : val;
-}
-EXPORT_SYMBOL_GPL(of_get_nand_ecc_strength);
-
-/**
- * of_get_nand_bus_width - Get nand bus witdh for given device_node
- * @np: Pointer to the given device_node
- *
- * return bus width option, or errno in error case.
- */
-int of_get_nand_bus_width(struct device_node *np)
-{
- u32 val;
-
- if (of_property_read_u32(np, "nand-bus-width", &val))
- return 8;
-
- switch(val) {
- case 8:
- case 16:
- return val;
- default:
- return -EIO;
- }
-}
-EXPORT_SYMBOL_GPL(of_get_nand_bus_width);
-
-/**
- * of_get_nand_on_flash_bbt - Get nand on flash bbt for given device_node
- * @np: Pointer to the given device_node
- *
- * return true if present false other wise
- */
-bool of_get_nand_on_flash_bbt(struct device_node *np)
-{
- return of_property_read_bool(np, "nand-on-flash-bbt");
-}
-EXPORT_SYMBOL_GPL(of_get_nand_on_flash_bbt);
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index ed01c0172e4a..216648233874 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -127,8 +127,15 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
}
/* Need adjust the alignment to satisfy the CMA requirement */
- if (IS_ENABLED(CONFIG_CMA) && of_flat_dt_is_compatible(node, "shared-dma-pool"))
- align = max(align, (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+ if (IS_ENABLED(CONFIG_CMA)
+ && of_flat_dt_is_compatible(node, "shared-dma-pool")
+ && of_get_flat_dt_prop(node, "reusable", NULL)
+ && !of_get_flat_dt_prop(node, "no-map", NULL)) {
+ unsigned long order =
+ max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
+
+ align = max(align, (phys_addr_t)PAGE_SIZE << order);
+ }
prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
if (prop) {
diff --git a/drivers/pci/vc.c b/drivers/pci/vc.c
index dfbab61a1b47..1fa3a3219c45 100644
--- a/drivers/pci/vc.c
+++ b/drivers/pci/vc.c
@@ -221,9 +221,9 @@ static int pci_vc_do_save_buffer(struct pci_dev *dev, int pos,
else
pci_write_config_word(dev, pos + PCI_VC_PORT_CTRL,
*(u16 *)buf);
- buf += 2;
+ buf += 4;
}
- len += 2;
+ len += 4;
/*
* If we have any Low Priority VCs and a VC Arbitration Table Offset
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f2d01d4d9364..140436a046c0 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -950,17 +950,14 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
/* For SPIs, we need to track the affinity per IRQ */
if (using_spi) {
- if (i >= pdev->num_resources) {
- of_node_put(dn);
+ if (i >= pdev->num_resources)
break;
- }
irqs[i] = cpu;
}
/* Keep track of the CPUs containing this PMU type */
cpumask_set_cpu(cpu, &pmu->supported_cpus);
- of_node_put(dn);
i++;
} while (1);
@@ -995,9 +992,6 @@ int arm_pmu_device_probe(struct platform_device *pdev,
armpmu_init(pmu);
- if (!__oprofile_cpu_pmu)
- __oprofile_cpu_pmu = pmu;
-
pmu->plat_device = pdev;
if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
@@ -1016,8 +1010,8 @@ int arm_pmu_device_probe(struct platform_device *pdev,
if (!ret)
ret = init_fn(pmu);
} else {
- ret = probe_current_pmu(pmu, probe_table);
cpumask_setall(&pmu->supported_cpus);
+ ret = probe_current_pmu(pmu, probe_table);
}
if (ret) {
@@ -1033,6 +1027,9 @@ int arm_pmu_device_probe(struct platform_device *pdev,
if (ret)
goto out_destroy;
+ if (!__oprofile_cpu_pmu)
+ __oprofile_cpu_pmu = pmu;
+
pr_info("enabled with %s PMU driver, %d counters available\n",
pmu->name, pmu->num_events);
@@ -1043,6 +1040,7 @@ out_destroy:
out_free:
pr_info("%s: failed to register PMU devices!\n",
of_node_full_name(node));
+ kfree(pmu->irq_affinity);
kfree(pmu);
return ret;
}
diff --git a/drivers/phy/phy-bcm-ns-usb2.c b/drivers/phy/phy-bcm-ns-usb2.c
index 95ab6b2a0de5..58dff80e9386 100644
--- a/drivers/phy/phy-bcm-ns-usb2.c
+++ b/drivers/phy/phy-bcm-ns-usb2.c
@@ -109,8 +109,8 @@ static int bcm_ns_usb2_probe(struct platform_device *pdev)
}
usb2->phy = devm_phy_create(dev, NULL, &ops);
- if (IS_ERR(dev))
- return PTR_ERR(dev);
+ if (IS_ERR(usb2->phy))
+ return PTR_ERR(usb2->phy);
phy_set_drvdata(usb2->phy, usb2);
platform_set_drvdata(pdev, usb2);
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index cc093ebfda94..8b851f718123 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -233,8 +233,12 @@ static inline int __is_running(const struct exynos_mipi_phy_desc *data,
struct exynos_mipi_video_phy *state)
{
u32 val;
+ int ret;
+
+ ret = regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val);
+ if (ret)
+ return 0;
- regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val);
return val & data->resetn_val;
}
diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c
index 3acd2a1808df..213e2e15339c 100644
--- a/drivers/phy/phy-miphy28lp.c
+++ b/drivers/phy/phy-miphy28lp.c
@@ -1143,7 +1143,8 @@ static int miphy28lp_probe_resets(struct device_node *node,
struct miphy28lp_dev *miphy_dev = miphy_phy->phydev;
int err;
- miphy_phy->miphy_rst = of_reset_control_get(node, "miphy-sw-rst");
+ miphy_phy->miphy_rst =
+ of_reset_control_get_shared(node, "miphy-sw-rst");
if (IS_ERR(miphy_phy->miphy_rst)) {
dev_err(miphy_dev->dev,
diff --git a/drivers/phy/phy-rcar-gen3-usb2.c b/drivers/phy/phy-rcar-gen3-usb2.c
index 76bb88f0700a..4be3f5dbbc9f 100644
--- a/drivers/phy/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/phy-rcar-gen3-usb2.c
@@ -144,12 +144,6 @@ static void rcar_gen3_init_for_peri(struct rcar_gen3_chan *ch)
extcon_set_cable_state_(ch->extcon, EXTCON_USB, true);
}
-static bool rcar_gen3_check_vbus(struct rcar_gen3_chan *ch)
-{
- return !!(readl(ch->base + USB2_ADPCTRL) &
- USB2_ADPCTRL_OTGSESSVLD);
-}
-
static bool rcar_gen3_check_id(struct rcar_gen3_chan *ch)
{
return !!(readl(ch->base + USB2_ADPCTRL) & USB2_ADPCTRL_IDDIG);
@@ -157,13 +151,7 @@ static bool rcar_gen3_check_id(struct rcar_gen3_chan *ch)
static void rcar_gen3_device_recognition(struct rcar_gen3_chan *ch)
{
- bool is_host = true;
-
- /* B-device? */
- if (rcar_gen3_check_id(ch) && rcar_gen3_check_vbus(ch))
- is_host = false;
-
- if (is_host)
+ if (!rcar_gen3_check_id(ch))
rcar_gen3_init_for_host(ch);
else
rcar_gen3_init_for_peri(ch);
diff --git a/drivers/phy/phy-rockchip-dp.c b/drivers/phy/phy-rockchip-dp.c
index 793ecb6d87bc..8b267a746576 100644
--- a/drivers/phy/phy-rockchip-dp.c
+++ b/drivers/phy/phy-rockchip-dp.c
@@ -90,7 +90,7 @@ static int rockchip_dp_phy_probe(struct platform_device *pdev)
return -ENODEV;
dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL);
- if (IS_ERR(dp))
+ if (!dp)
return -ENOMEM;
dp->dev = dev;
diff --git a/drivers/phy/phy-stih407-usb.c b/drivers/phy/phy-stih407-usb.c
index 1d5ae5f8ef69..b1f44ab669fb 100644
--- a/drivers/phy/phy-stih407-usb.c
+++ b/drivers/phy/phy-stih407-usb.c
@@ -105,13 +105,13 @@ static int stih407_usb2_picophy_probe(struct platform_device *pdev)
phy_dev->dev = dev;
dev_set_drvdata(dev, phy_dev);
- phy_dev->rstc = devm_reset_control_get(dev, "global");
+ phy_dev->rstc = devm_reset_control_get_shared(dev, "global");
if (IS_ERR(phy_dev->rstc)) {
dev_err(dev, "failed to ctrl picoPHY reset\n");
return PTR_ERR(phy_dev->rstc);
}
- phy_dev->rstport = devm_reset_control_get(dev, "port");
+ phy_dev->rstport = devm_reset_control_get_exclusive(dev, "port");
if (IS_ERR(phy_dev->rstport)) {
dev_err(dev, "failed to ctrl picoPHY reset\n");
return PTR_ERR(phy_dev->rstport);
diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c
index bae54f7a1f48..de3101fbbf40 100644
--- a/drivers/phy/phy-sun4i-usb.c
+++ b/drivers/phy/phy-sun4i-usb.c
@@ -175,7 +175,7 @@ static void sun4i_usb_phy_write(struct sun4i_usb_phy *phy, u32 addr, u32 data,
{
struct sun4i_usb_phy_data *phy_data = to_sun4i_usb_phy_data(phy);
u32 temp, usbc_bit = BIT(phy->index * 2);
- void *phyctl = phy_data->base + phy_data->cfg->phyctl_offset;
+ void __iomem *phyctl = phy_data->base + phy_data->cfg->phyctl_offset;
int i;
mutex_lock(&phy_data->mutex);
@@ -514,9 +514,9 @@ static int sun4i_usb_phy_remove(struct platform_device *pdev)
if (data->vbus_power_nb_registered)
power_supply_unreg_notifier(&data->vbus_power_nb);
- if (data->id_det_irq >= 0)
+ if (data->id_det_irq > 0)
devm_free_irq(dev, data->id_det_irq, data);
- if (data->vbus_det_irq >= 0)
+ if (data->vbus_det_irq > 0)
devm_free_irq(dev, data->vbus_det_irq, data);
cancel_delayed_work_sync(&data->detect);
@@ -645,11 +645,11 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev)
data->id_det_irq = gpiod_to_irq(data->id_det_gpio);
data->vbus_det_irq = gpiod_to_irq(data->vbus_det_gpio);
- if ((data->id_det_gpio && data->id_det_irq < 0) ||
- (data->vbus_det_gpio && data->vbus_det_irq < 0))
+ if ((data->id_det_gpio && data->id_det_irq <= 0) ||
+ (data->vbus_det_gpio && data->vbus_det_irq <= 0))
data->phy0_poll = true;
- if (data->id_det_irq >= 0) {
+ if (data->id_det_irq > 0) {
ret = devm_request_irq(dev, data->id_det_irq,
sun4i_usb_phy0_id_vbus_det_irq,
IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
@@ -660,7 +660,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev)
}
}
- if (data->vbus_det_irq >= 0) {
+ if (data->vbus_det_irq > 0) {
ret = devm_request_irq(dev, data->vbus_det_irq,
sun4i_usb_phy0_id_vbus_det_irq,
IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c
index 0a477d24cf76..bf46844dc387 100644
--- a/drivers/phy/phy-ti-pipe3.c
+++ b/drivers/phy/phy-ti-pipe3.c
@@ -293,11 +293,18 @@ static int ti_pipe3_init(struct phy *x)
ret = ti_pipe3_dpll_wait_lock(phy);
}
- /* Program the DPLL only if not locked */
+ /* SATA has issues if re-programmed when locked */
val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS);
- if (!(val & PLL_LOCK))
- if (ti_pipe3_dpll_program(phy))
- return -EINVAL;
+ if ((val & PLL_LOCK) && of_device_is_compatible(phy->dev->of_node,
+ "ti,phy-pipe3-sata"))
+ return ret;
+
+ /* Program the DPLL */
+ ret = ti_pipe3_dpll_program(phy);
+ if (ret) {
+ ti_pipe3_disable_clocks(phy);
+ return -EINVAL;
+ }
return ret;
}
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index 6b6af6cba454..d9b10a39a2cf 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -463,7 +463,8 @@ static int twl4030_phy_power_on(struct phy *phy)
twl4030_usb_set_mode(twl, twl->usb_mode);
if (twl->usb_mode == T2_USB_MODE_ULPI)
twl4030_i2c_access(twl, 0);
- schedule_delayed_work(&twl->id_workaround_work, 0);
+ twl->linkstat = MUSB_UNKNOWN;
+ schedule_delayed_work(&twl->id_workaround_work, HZ);
return 0;
}
@@ -537,6 +538,7 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
struct twl4030_usb *twl = _twl;
enum musb_vbus_id_status status;
bool status_changed = false;
+ int err;
status = twl4030_usb_linkstat(twl);
@@ -567,7 +569,9 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
pm_runtime_mark_last_busy(twl->dev);
pm_runtime_put_autosuspend(twl->dev);
}
- musb_mailbox(status);
+ err = musb_mailbox(status);
+ if (err)
+ twl->linkstat = MUSB_UNKNOWN;
}
/* don't schedule during sleep - irq works right then */
@@ -595,7 +599,8 @@ static int twl4030_phy_init(struct phy *phy)
struct twl4030_usb *twl = phy_get_drvdata(phy);
pm_runtime_get_sync(twl->dev);
- schedule_delayed_work(&twl->id_workaround_work, 0);
+ twl->linkstat = MUSB_UNKNOWN;
+ schedule_delayed_work(&twl->id_workaround_work, HZ);
pm_runtime_mark_last_busy(twl->dev);
pm_runtime_put_autosuspend(twl->dev);
@@ -763,7 +768,8 @@ static int twl4030_usb_remove(struct platform_device *pdev)
if (cable_present(twl->linkstat))
pm_runtime_put_noidle(twl->dev);
pm_runtime_mark_last_busy(twl->dev);
- pm_runtime_put_sync_suspend(twl->dev);
+ pm_runtime_dont_use_autosuspend(&pdev->dev);
+ pm_runtime_put_sync(twl->dev);
pm_runtime_disable(twl->dev);
/* autogate 60MHz ULPI clock,
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index e4bc1151e04f..42a5c1dddfef 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -23,7 +23,7 @@ obj-$(CONFIG_PINCTRL_PISTACHIO) += pinctrl-pistachio.o
obj-$(CONFIG_PINCTRL_ROCKCHIP) += pinctrl-rockchip.o
obj-$(CONFIG_PINCTRL_SINGLE) += pinctrl-single.o
obj-$(CONFIG_PINCTRL_SIRF) += sirf/
-obj-$(CONFIG_PINCTRL_TEGRA) += tegra/
+obj-$(CONFIG_ARCH_TEGRA) += tegra/
obj-$(CONFIG_PINCTRL_TZ1090) += pinctrl-tz1090.o
obj-$(CONFIG_PINCTRL_TZ1090_PDC) += pinctrl-tz1090-pdc.o
obj-$(CONFIG_PINCTRL_U300) += pinctrl-u300.o
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 47ccfcc8a647..eccb47480e1d 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -209,9 +209,9 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
pin_reg = &info->pin_regs[pin_id];
if (pin_reg->mux_reg == -1) {
- dev_err(ipctl->dev, "Pin(%s) does not support mux function\n",
+ dev_dbg(ipctl->dev, "Pin(%s) does not support mux function\n",
info->pins[pin_id].name);
- return -EINVAL;
+ continue;
}
if (info->flags & SHARE_MUX_CONF_REG) {
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 55182fc58c6a..7abfd42e8ffd 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -153,8 +153,10 @@ struct byt_community {
.name = (n), \
.pins = (p), \
.npins = ARRAY_SIZE((p)), \
- .has_simple_funcs = 1, \
- .simple_funcs = (f), \
+ .has_simple_funcs = 1, \
+ { \
+ .simple_funcs = (f), \
+ }, \
.nfuncs = ARRAY_SIZE((f)), \
}
#define PIN_GROUP_MIXED(n, p, f) \
@@ -163,7 +165,9 @@ struct byt_community {
.pins = (p), \
.npins = ARRAY_SIZE((p)), \
.has_simple_funcs = 0, \
- .mixed_funcs = (f), \
+ { \
+ .mixed_funcs = (f), \
+ }, \
.nfuncs = ARRAY_SIZE((f)), \
}
@@ -397,9 +401,9 @@ static const struct byt_simple_func_mux byt_score_sata_mux[] = {
static const unsigned int byt_score_plt_clk0_pins[] = { 96 };
static const unsigned int byt_score_plt_clk1_pins[] = { 97 };
static const unsigned int byt_score_plt_clk2_pins[] = { 98 };
-static const unsigned int byt_score_plt_clk4_pins[] = { 99 };
-static const unsigned int byt_score_plt_clk5_pins[] = { 100 };
-static const unsigned int byt_score_plt_clk3_pins[] = { 101 };
+static const unsigned int byt_score_plt_clk3_pins[] = { 99 };
+static const unsigned int byt_score_plt_clk4_pins[] = { 100 };
+static const unsigned int byt_score_plt_clk5_pins[] = { 101 };
static const struct byt_simple_func_mux byt_score_plt_clk_mux[] = {
SIMPLE_FUNC("plt_clk", 1),
};
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 207b13b618cf..a607655d7830 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1256,9 +1256,10 @@ static void mtk_eint_irq_handler(struct irq_desc *desc)
const struct mtk_desc_pin *pin;
chained_irq_enter(chip, desc);
- for (eint_num = 0; eint_num < pctl->devdata->ap_num; eint_num += 32) {
+ for (eint_num = 0;
+ eint_num < pctl->devdata->ap_num;
+ eint_num += 32, reg += 4) {
status = readl(reg);
- reg += 4;
while (status) {
offset = __ffs(status);
index = eint_num + offset;
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index ccbfc325c778..38faceff2f08 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -854,7 +854,7 @@ static int nmk_gpio_get_dir(struct gpio_chip *chip, unsigned offset)
clk_enable(nmk_chip->clk);
- dir = !!(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset));
+ dir = !(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset));
clk_disable(nmk_chip->clk);
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index cf9bafa10acf..bfdf720db270 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1580,6 +1580,9 @@ static inline void pcs_irq_set(struct pcs_soc_data *pcs_soc,
else
mask &= ~soc_mask;
pcs->write(mask, pcswi->reg);
+
+ /* flush posted write */
+ mask = pcs->read(pcswi->reg);
raw_spin_unlock(&pcs->lock);
}
diff --git a/drivers/pinctrl/tegra/Makefile b/drivers/pinctrl/tegra/Makefile
index a927379b6794..d9ea2be69cc4 100644
--- a/drivers/pinctrl/tegra/Makefile
+++ b/drivers/pinctrl/tegra/Makefile
@@ -1,4 +1,4 @@
-obj-y += pinctrl-tegra.o
+obj-$(CONFIG_PINCTRL_TEGRA) += pinctrl-tegra.o
obj-$(CONFIG_PINCTRL_TEGRA20) += pinctrl-tegra20.o
obj-$(CONFIG_PINCTRL_TEGRA30) += pinctrl-tegra30.o
obj-$(CONFIG_PINCTRL_TEGRA114) += pinctrl-tegra114.o
diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig
index d03df4a60d05..76bdae1a93bb 100644
--- a/drivers/platform/chrome/Kconfig
+++ b/drivers/platform/chrome/Kconfig
@@ -64,4 +64,14 @@ config CROS_EC_PROTO
help
ChromeOS EC communication protocol helpers.
+config CROS_KBD_LED_BACKLIGHT
+ tristate "Backlight LED support for Chrome OS keyboards"
+ depends on LEDS_CLASS && ACPI
+ help
+ This option enables support for the keyboard backlight LEDs on
+ select Chrome OS systems.
+
+ To compile this driver as a module, choose M here: the
+ module will be called cros_kbd_led_backlight.
+
endif # CHROMEOS_PLATFORMS
diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index bc498bda8211..4f3462783a3c 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -1,8 +1,9 @@
-obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o
-obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o
-cros_ec_devs-objs := cros_ec_dev.o cros_ec_sysfs.o \
- cros_ec_lightbar.o cros_ec_vbc.o
-obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_devs.o
-obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpc.o
-obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o
+obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o
+obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o
+cros_ec_devs-objs := cros_ec_dev.o cros_ec_sysfs.o \
+ cros_ec_lightbar.o cros_ec_vbc.o
+obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_devs.o
+obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpc.o
+obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o
+obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o
diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c
index 2b441e9ae593..e8a44a9bc916 100644
--- a/drivers/platform/chrome/chromeos_laptop.c
+++ b/drivers/platform/chrome/chromeos_laptop.c
@@ -34,6 +34,7 @@
#define ATMEL_TS_I2C_ADDR 0x4a
#define ATMEL_TS_I2C_BL_ADDR 0x26
#define CYAPA_TP_I2C_ADDR 0x67
+#define ELAN_TP_I2C_ADDR 0x15
#define ISL_ALS_I2C_ADDR 0x44
#define TAOS_ALS_I2C_ADDR 0x29
@@ -73,7 +74,7 @@ struct i2c_peripheral {
int tries;
};
-#define MAX_I2C_PERIPHERALS 3
+#define MAX_I2C_PERIPHERALS 4
struct chromeos_laptop {
struct i2c_peripheral i2c_peripherals[MAX_I2C_PERIPHERALS];
@@ -86,6 +87,11 @@ static struct i2c_board_info cyapa_device = {
.flags = I2C_CLIENT_WAKE,
};
+static struct i2c_board_info elantech_device = {
+ I2C_BOARD_INFO("elan_i2c", ELAN_TP_I2C_ADDR),
+ .flags = I2C_CLIENT_WAKE,
+};
+
static struct i2c_board_info isl_als_device = {
I2C_BOARD_INFO("isl29018", ISL_ALS_I2C_ADDR),
};
@@ -306,6 +312,16 @@ static int setup_atmel_224s_tp(enum i2c_adapter_type type)
return (!tp) ? -EAGAIN : 0;
}
+static int setup_elantech_tp(enum i2c_adapter_type type)
+{
+ if (tp)
+ return 0;
+
+ /* add elantech touchpad */
+ tp = add_i2c_device("trackpad", type, &elantech_device);
+ return (!tp) ? -EAGAIN : 0;
+}
+
static int setup_atmel_1664s_ts(enum i2c_adapter_type type)
{
const unsigned short addr_list[] = { ATMEL_TS_I2C_BL_ADDR,
@@ -445,6 +461,8 @@ static struct chromeos_laptop dell_chromebook_11 = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 },
+ /* Elan Touchpad option. */
+ { .add = setup_elantech_tp, I2C_ADAPTER_DESIGNWARE_0 },
},
};
@@ -475,6 +493,8 @@ static struct chromeos_laptop acer_c720 = {
{ .add = setup_atmel_1664s_ts, I2C_ADAPTER_DESIGNWARE_1 },
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 },
+ /* Elan Touchpad option. */
+ { .add = setup_elantech_tp, I2C_ADAPTER_DESIGNWARE_0 },
/* Light Sensor. */
{ .add = setup_isl29018_als, I2C_ADAPTER_DESIGNWARE_1 },
},
diff --git a/drivers/platform/chrome/chromeos_pstore.c b/drivers/platform/chrome/chromeos_pstore.c
index 34749200e4ab..308a853ac4f1 100644
--- a/drivers/platform/chrome/chromeos_pstore.c
+++ b/drivers/platform/chrome/chromeos_pstore.c
@@ -8,6 +8,7 @@
* the Free Software Foundation, version 2 of the License.
*/
+#include <linux/acpi.h>
#include <linux/dmi.h>
#include <linux/module.h>
#include <linux/platform_device.h>
@@ -58,7 +59,7 @@ MODULE_DEVICE_TABLE(dmi, chromeos_pstore_dmi_table);
static struct ramoops_platform_data chromeos_ramoops_data = {
.mem_size = 0x100000,
.mem_address = 0xf00000,
- .record_size = 0x20000,
+ .record_size = 0x40000,
.console_size = 0x20000,
.ftrace_size = 0x20000,
.dump_oops = 1,
@@ -71,9 +72,59 @@ static struct platform_device chromeos_ramoops = {
},
};
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id cros_ramoops_acpi_match[] = {
+ { "GOOG9999", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, cros_ramoops_acpi_match);
+
+static struct platform_driver chromeos_ramoops_acpi = {
+ .driver = {
+ .name = "chromeos_pstore",
+ .acpi_match_table = ACPI_PTR(cros_ramoops_acpi_match),
+ },
+};
+
+static int __init chromeos_probe_acpi(struct platform_device *pdev)
+{
+ struct resource *res;
+ resource_size_t len;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENOMEM;
+
+ len = resource_size(res);
+ if (!res->start || !len)
+ return -ENOMEM;
+
+ pr_info("chromeos ramoops using acpi device.\n");
+
+ chromeos_ramoops_data.mem_size = len;
+ chromeos_ramoops_data.mem_address = res->start;
+
+ return 0;
+}
+
+static bool __init chromeos_check_acpi(void)
+{
+ if (!platform_driver_probe(&chromeos_ramoops_acpi, chromeos_probe_acpi))
+ return true;
+ return false;
+}
+#else
+static inline bool chromeos_check_acpi(void) { return false; }
+#endif
+
static int __init chromeos_pstore_init(void)
{
- if (dmi_check_system(chromeos_pstore_dmi_table))
+ bool acpi_dev_found;
+
+ /* First check ACPI for non-hardcoded values from firmware. */
+ acpi_dev_found = chromeos_check_acpi();
+
+ if (acpi_dev_found || dmi_check_system(chromeos_pstore_dmi_table))
return platform_device_register(&chromeos_ramoops);
return -ENODEV;
diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c
index d45cd254ed1c..6d8ee3b15872 100644
--- a/drivers/platform/chrome/cros_ec_dev.c
+++ b/drivers/platform/chrome/cros_ec_dev.c
@@ -137,6 +137,10 @@ static long ec_device_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg)
if (copy_from_user(&u_cmd, arg, sizeof(u_cmd)))
return -EFAULT;
+ if ((u_cmd.outsize > EC_MAX_MSG_BYTES) ||
+ (u_cmd.insize > EC_MAX_MSG_BYTES))
+ return -EINVAL;
+
s_cmd = kmalloc(sizeof(*s_cmd) + max(u_cmd.outsize, u_cmd.insize),
GFP_KERNEL);
if (!s_cmd)
@@ -208,6 +212,9 @@ static const struct file_operations fops = {
.release = ec_device_release,
.read = ec_device_read,
.unlocked_ioctl = ec_device_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ec_device_ioctl,
+#endif
};
static void __remove(struct device *dev)
diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c
index ff7640575c75..8df3d447cacf 100644
--- a/drivers/platform/chrome/cros_ec_lightbar.c
+++ b/drivers/platform/chrome/cros_ec_lightbar.c
@@ -412,9 +412,13 @@ static umode_t cros_ec_lightbar_attrs_are_visible(struct kobject *kobj,
struct device *dev = container_of(kobj, struct device, kobj);
struct cros_ec_dev *ec = container_of(dev,
struct cros_ec_dev, class_dev);
- struct platform_device *pdev = container_of(ec->dev,
- struct platform_device, dev);
- if (pdev->id != 0)
+ struct platform_device *pdev = to_platform_device(ec->dev);
+ struct cros_ec_platform *pdata = pdev->dev.platform_data;
+ int is_cros_ec;
+
+ is_cros_ec = strcmp(pdata->ec_name, CROS_EC_DEV_NAME);
+
+ if (is_cros_ec != 0)
return 0;
/* Only instantiate this stuff if the EC has a lightbar */
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index 990308ca384f..b6e161f71b26 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -298,8 +298,8 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev)
ec_dev->max_response = EC_PROTO2_MAX_PARAM_SIZE;
ec_dev->max_passthru = 0;
ec_dev->pkt_xfer = NULL;
- ec_dev->din_size = EC_MSG_BYTES;
- ec_dev->dout_size = EC_MSG_BYTES;
+ ec_dev->din_size = EC_PROTO2_MSG_BYTES;
+ ec_dev->dout_size = EC_PROTO2_MSG_BYTES;
} else {
/*
* It's possible for a test to occur too early when
diff --git a/drivers/platform/chrome/cros_kbd_led_backlight.c b/drivers/platform/chrome/cros_kbd_led_backlight.c
new file mode 100644
index 000000000000..ca3e4da852b4
--- /dev/null
+++ b/drivers/platform/chrome/cros_kbd_led_backlight.c
@@ -0,0 +1,122 @@
+/*
+ * Keyboard backlight LED driver for Chrome OS.
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/acpi.h>
+#include <linux/leds.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+/* Keyboard LED ACPI Device must be defined in firmware */
+#define ACPI_KEYBOARD_BACKLIGHT_DEVICE "\\_SB.KBLT"
+#define ACPI_KEYBOARD_BACKLIGHT_READ ACPI_KEYBOARD_BACKLIGHT_DEVICE ".KBQC"
+#define ACPI_KEYBOARD_BACKLIGHT_WRITE ACPI_KEYBOARD_BACKLIGHT_DEVICE ".KBCM"
+
+#define ACPI_KEYBOARD_BACKLIGHT_MAX 100
+
+static void keyboard_led_set_brightness(struct led_classdev *cdev,
+ enum led_brightness brightness)
+{
+ union acpi_object param;
+ struct acpi_object_list input;
+ acpi_status status;
+
+ param.type = ACPI_TYPE_INTEGER;
+ param.integer.value = brightness;
+ input.count = 1;
+ input.pointer = &param;
+
+ status = acpi_evaluate_object(NULL, ACPI_KEYBOARD_BACKLIGHT_WRITE,
+ &input, NULL);
+ if (ACPI_FAILURE(status))
+ dev_err(cdev->dev, "Error setting keyboard LED value: %d\n",
+ status);
+}
+
+static enum led_brightness
+keyboard_led_get_brightness(struct led_classdev *cdev)
+{
+ unsigned long long brightness;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(NULL, ACPI_KEYBOARD_BACKLIGHT_READ,
+ NULL, &brightness);
+ if (ACPI_FAILURE(status)) {
+ dev_err(cdev->dev, "Error getting keyboard LED value: %d\n",
+ status);
+ return -EIO;
+ }
+
+ return brightness;
+}
+
+static int keyboard_led_probe(struct platform_device *pdev)
+{
+ struct led_classdev *cdev;
+ acpi_handle handle;
+ acpi_status status;
+ int error;
+
+ /* Look for the keyboard LED ACPI Device */
+ status = acpi_get_handle(ACPI_ROOT_OBJECT,
+ ACPI_KEYBOARD_BACKLIGHT_DEVICE,
+ &handle);
+ if (ACPI_FAILURE(status)) {
+ dev_err(&pdev->dev, "Unable to find ACPI device %s: %d\n",
+ ACPI_KEYBOARD_BACKLIGHT_DEVICE, status);
+ return -ENXIO;
+ }
+
+ cdev = devm_kzalloc(&pdev->dev, sizeof(*cdev), GFP_KERNEL);
+ if (!cdev)
+ return -ENOMEM;
+
+ cdev->name = "chromeos::kbd_backlight";
+ cdev->max_brightness = ACPI_KEYBOARD_BACKLIGHT_MAX;
+ cdev->flags |= LED_CORE_SUSPENDRESUME;
+ cdev->brightness_set = keyboard_led_set_brightness;
+ cdev->brightness_get = keyboard_led_get_brightness;
+
+ error = devm_led_classdev_register(&pdev->dev, cdev);
+ if (error)
+ return error;
+
+ return 0;
+}
+
+static const struct acpi_device_id keyboard_led_id[] = {
+ { "GOOG0002", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, keyboard_led_id);
+
+static struct platform_driver keyboard_led_driver = {
+ .driver = {
+ .name = "chromeos-keyboard-leds",
+ .acpi_match_table = ACPI_PTR(keyboard_led_id),
+ },
+ .probe = keyboard_led_probe,
+};
+module_platform_driver(keyboard_led_driver);
+
+MODULE_AUTHOR("Simon Que <sque@chromium.org>");
+MODULE_DESCRIPTION("ChromeOS Keyboard backlight LED Driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:chromeos-keyboard-leds");
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index ed2004be13cf..3ec0025d19e7 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -103,7 +103,6 @@ config DELL_SMBIOS
config DELL_LAPTOP
tristate "Dell Laptop Extras"
- depends on X86
depends on DELL_SMBIOS
depends on DMI
depends on BACKLIGHT_CLASS_DEVICE
@@ -505,7 +504,7 @@ config THINKPAD_ACPI_HOTKEY_POLL
config SENSORS_HDAPS
tristate "Thinkpad Hard Drive Active Protection System (hdaps)"
- depends on INPUT && X86
+ depends on INPUT
select INPUT_POLLDEV
default n
help
@@ -749,7 +748,7 @@ config TOSHIBA_WMI
config ACPI_CMPC
tristate "CMPC Laptop Extras"
- depends on X86 && ACPI
+ depends on ACPI
depends on RFKILL || RFKILL=n
select INPUT
select BACKLIGHT_CLASS_DEVICE
@@ -846,9 +845,21 @@ config INTEL_IMR
If you are running on a Galileo/Quark say Y here.
+config INTEL_PMC_CORE
+ bool "Intel PMC Core driver"
+ depends on PCI
+ ---help---
+ The Intel Platform Controller Hub for Intel Core SoCs provides access
+ to Power Management Controller registers via a PCI interface. This
+ driver can utilize debugging capabilities and supported features as
+ exposed by the Power Management Controller.
+
+ Supported features:
+ - SLP_S0_RESIDENCY counter.
+
config IBM_RTL
tristate "Device driver to enable PRTL support"
- depends on X86 && PCI
+ depends on PCI
---help---
Enable support for IBM Premium Real Time Mode (PRTM).
This module will allow you the enter and exit PRTM in the BIOS via
@@ -882,7 +893,6 @@ config XO15_EBOOK
config SAMSUNG_LAPTOP
tristate "Samsung Laptop driver"
- depends on X86
depends on RFKILL || RFKILL = n
depends on ACPI_VIDEO || ACPI_VIDEO = n
depends on BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 448443c3baba..9b11b4073e03 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -69,3 +69,4 @@ obj-$(CONFIG_INTEL_PUNIT_IPC) += intel_punit_ipc.o
obj-$(CONFIG_INTEL_TELEMETRY) += intel_telemetry_core.o \
intel_telemetry_pltdrv.o \
intel_telemetry_debugfs.o
+obj-$(CONFIG_INTEL_PMC_CORE) += intel_pmc_core.o
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index f2b5d0a8adf0..15f131146501 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -771,12 +771,14 @@ static int asus_read_brightness(struct backlight_device *bd)
{
struct asus_laptop *asus = bl_get_data(bd);
unsigned long long value;
- acpi_status rv = AE_OK;
+ acpi_status rv;
rv = acpi_evaluate_integer(asus->handle, METHOD_BRIGHTNESS_GET,
NULL, &value);
- if (ACPI_FAILURE(rv))
+ if (ACPI_FAILURE(rv)) {
pr_warn("Error reading brightness\n");
+ return 0;
+ }
return value;
}
@@ -865,7 +867,7 @@ static ssize_t infos_show(struct device *dev, struct device_attribute *attr,
int len = 0;
unsigned long long temp;
char buf[16]; /* enough for all info */
- acpi_status rv = AE_OK;
+ acpi_status rv;
/*
* We use the easy way, we don't care of off and count,
@@ -946,11 +948,10 @@ static ssize_t sysfs_acpi_set(struct asus_laptop *asus,
const char *method)
{
int rv, value;
- int out = 0;
rv = parse_arg(buf, count, &value);
- if (rv > 0)
- out = value ? 1 : 0;
+ if (rv <= 0)
+ return rv;
if (write_acpi_int(asus->handle, method, value))
return -ENODEV;
@@ -1265,7 +1266,7 @@ static DEVICE_ATTR_RO(ls_value);
static int asus_gps_status(struct asus_laptop *asus)
{
unsigned long long status;
- acpi_status rv = AE_OK;
+ acpi_status rv;
rv = acpi_evaluate_integer(asus->handle, METHOD_GPS_STATUS,
NULL, &status);
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index a96630d52346..a26dca3640ea 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -114,6 +114,7 @@ MODULE_LICENSE("GPL");
#define ASUS_WMI_DEVID_LED6 0x00020016
/* Backlight and Brightness */
+#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */
#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011
#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012
#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021
@@ -1730,6 +1731,7 @@ ASUS_WMI_CREATE_DEVICE_ATTR(touchpad, 0644, ASUS_WMI_DEVID_TOUCHPAD);
ASUS_WMI_CREATE_DEVICE_ATTR(camera, 0644, ASUS_WMI_DEVID_CAMERA);
ASUS_WMI_CREATE_DEVICE_ATTR(cardr, 0644, ASUS_WMI_DEVID_CARDREADER);
ASUS_WMI_CREATE_DEVICE_ATTR(lid_resume, 0644, ASUS_WMI_DEVID_LID_RESUME);
+ASUS_WMI_CREATE_DEVICE_ATTR(als_enable, 0644, ASUS_WMI_DEVID_ALS_ENABLE);
static ssize_t store_cpufv(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
@@ -1756,6 +1758,7 @@ static struct attribute *platform_attributes[] = {
&dev_attr_cardr.attr,
&dev_attr_touchpad.attr,
&dev_attr_lid_resume.attr,
+ &dev_attr_als_enable.attr,
NULL
};
@@ -1776,6 +1779,8 @@ static umode_t asus_sysfs_is_visible(struct kobject *kobj,
devid = ASUS_WMI_DEVID_TOUCHPAD;
else if (attr == &dev_attr_lid_resume.attr)
devid = ASUS_WMI_DEVID_LID_RESUME;
+ else if (attr == &dev_attr_als_enable.attr)
+ devid = ASUS_WMI_DEVID_ALS_ENABLE;
if (devid != -1)
ok = !(asus_wmi_get_devstate_simple(asus, devid) < 0);
diff --git a/drivers/platform/x86/dell-rbtn.c b/drivers/platform/x86/dell-rbtn.c
index b51a2008d782..dcd9f40a4b18 100644
--- a/drivers/platform/x86/dell-rbtn.c
+++ b/drivers/platform/x86/dell-rbtn.c
@@ -28,6 +28,7 @@ struct rbtn_data {
enum rbtn_type type;
struct rfkill *rfkill;
struct input_dev *input_dev;
+ bool suspended;
};
@@ -235,9 +236,55 @@ static const struct acpi_device_id rbtn_ids[] = {
{ "", 0 },
};
+#ifdef CONFIG_PM_SLEEP
+static void ACPI_SYSTEM_XFACE rbtn_clear_suspended_flag(void *context)
+{
+ struct rbtn_data *rbtn_data = context;
+
+ rbtn_data->suspended = false;
+}
+
+static int rbtn_suspend(struct device *dev)
+{
+ struct acpi_device *device = to_acpi_device(dev);
+ struct rbtn_data *rbtn_data = acpi_driver_data(device);
+
+ rbtn_data->suspended = true;
+
+ return 0;
+}
+
+static int rbtn_resume(struct device *dev)
+{
+ struct acpi_device *device = to_acpi_device(dev);
+ struct rbtn_data *rbtn_data = acpi_driver_data(device);
+ acpi_status status;
+
+ /*
+ * Upon resume, some BIOSes send an ACPI notification thet triggers
+ * an unwanted input event. In order to ignore it, we use a flag
+ * that we set at suspend and clear once we have received the extra
+ * ACPI notification. Since ACPI notifications are delivered
+ * asynchronously to drivers, we clear the flag from the workqueue
+ * used to deliver the notifications. This should be enough
+ * to have the flag cleared only after we received the extra
+ * notification, if any.
+ */
+ status = acpi_os_execute(OSL_NOTIFY_HANDLER,
+ rbtn_clear_suspended_flag, rbtn_data);
+ if (ACPI_FAILURE(status))
+ rbtn_clear_suspended_flag(rbtn_data);
+
+ return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(rbtn_pm_ops, rbtn_suspend, rbtn_resume);
+
static struct acpi_driver rbtn_driver = {
.name = "dell-rbtn",
.ids = rbtn_ids,
+ .drv.pm = &rbtn_pm_ops,
.ops = {
.add = rbtn_add,
.remove = rbtn_remove,
@@ -399,6 +446,15 @@ static void rbtn_notify(struct acpi_device *device, u32 event)
{
struct rbtn_data *rbtn_data = device->driver_data;
+ /*
+ * Some BIOSes send a notification at resume.
+ * Ignore it to prevent unwanted input events.
+ */
+ if (rbtn_data->suspended) {
+ dev_dbg(&device->dev, "ACPI notification ignored\n");
+ return;
+ }
+
if (event != 0x80) {
dev_info(&device->dev, "Received unknown event (0x%x)\n",
event);
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index ffc84cc7b1c7..ce41bc34288d 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -69,7 +69,7 @@
#include <linux/kfifo.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
#include <linux/leds.h>
#endif
#include <acpi/video.h>
@@ -100,13 +100,14 @@
/* FUNC interface - responses */
#define UNSUPPORTED_CMD 0x80000000
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
/* FUNC interface - LED control */
#define FUNC_LED_OFF 0x1
#define FUNC_LED_ON 0x30001
#define KEYBOARD_LAMPS 0x100
#define LOGOLAMP_POWERON 0x2000
#define LOGOLAMP_ALWAYS 0x4000
+#define RADIO_LED_ON 0x20
#endif
/* Hotkey details */
@@ -174,13 +175,14 @@ struct fujitsu_hotkey_t {
int rfkill_state;
int logolamp_registered;
int kblamps_registered;
+ int radio_led_registered;
};
static struct fujitsu_hotkey_t *fujitsu_hotkey;
static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event);
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
static enum led_brightness logolamp_get(struct led_classdev *cdev);
static void logolamp_set(struct led_classdev *cdev,
enum led_brightness brightness);
@@ -200,6 +202,16 @@ static struct led_classdev kblamps_led = {
.brightness_get = kblamps_get,
.brightness_set = kblamps_set
};
+
+static enum led_brightness radio_led_get(struct led_classdev *cdev);
+static void radio_led_set(struct led_classdev *cdev,
+ enum led_brightness brightness);
+
+static struct led_classdev radio_led = {
+ .name = "fujitsu::radio_led",
+ .brightness_get = radio_led_get,
+ .brightness_set = radio_led_set
+};
#endif
#ifdef CONFIG_FUJITSU_LAPTOP_DEBUG
@@ -249,7 +261,7 @@ static int call_fext_func(int cmd, int arg0, int arg1, int arg2)
return value;
}
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
/* LED class callbacks */
static void logolamp_set(struct led_classdev *cdev,
@@ -275,6 +287,15 @@ static void kblamps_set(struct led_classdev *cdev,
call_fext_func(FUNC_LEDS, 0x1, KEYBOARD_LAMPS, FUNC_LED_OFF);
}
+static void radio_led_set(struct led_classdev *cdev,
+ enum led_brightness brightness)
+{
+ if (brightness >= LED_FULL)
+ call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON);
+ else
+ call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
+}
+
static enum led_brightness logolamp_get(struct led_classdev *cdev)
{
enum led_brightness brightness = LED_OFF;
@@ -299,6 +320,16 @@ static enum led_brightness kblamps_get(struct led_classdev *cdev)
return brightness;
}
+
+static enum led_brightness radio_led_get(struct led_classdev *cdev)
+{
+ enum led_brightness brightness = LED_OFF;
+
+ if (call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0) & RADIO_LED_ON)
+ brightness = LED_FULL;
+
+ return brightness;
+}
#endif
/* Hardware access for LCD brightness control */
@@ -872,7 +903,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
/* Suspect this is a keymap of the application panel, print it */
pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) {
result = led_classdev_register(&fujitsu->pf_device->dev,
&logolamp_led);
@@ -895,6 +926,23 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
result);
}
}
+
+ /*
+ * BTNI bit 24 seems to indicate the presence of a radio toggle
+ * button in place of a slide switch, and all such machines appear
+ * to also have an RF LED. Therefore use bit 24 as an indicator
+ * that an RF LED is present.
+ */
+ if (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) & BIT(24)) {
+ result = led_classdev_register(&fujitsu->pf_device->dev,
+ &radio_led);
+ if (result == 0) {
+ fujitsu_hotkey->radio_led_registered = 1;
+ } else {
+ pr_err("Could not register LED handler for radio LED, error %i\n",
+ result);
+ }
+ }
#endif
return result;
@@ -915,12 +963,15 @@ static int acpi_fujitsu_hotkey_remove(struct acpi_device *device)
struct fujitsu_hotkey_t *fujitsu_hotkey = acpi_driver_data(device);
struct input_dev *input = fujitsu_hotkey->input;
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
if (fujitsu_hotkey->logolamp_registered)
led_classdev_unregister(&logolamp_led);
if (fujitsu_hotkey->kblamps_registered)
led_classdev_unregister(&kblamps_led);
+
+ if (fujitsu_hotkey->radio_led_registered)
+ led_classdev_unregister(&radio_led);
#endif
input_unregister_device(input);
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index be3bc2f4edd4..d1a091b93192 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -48,7 +48,10 @@
#define CFG_CAMERA_BIT (19)
#if IS_ENABLED(CONFIG_ACPI_WMI)
-static const char ideapad_wmi_fnesc_event[] = "26CAB2E5-5CF1-46AE-AAC3-4A12B6BA50E6";
+static const char *const ideapad_wmi_fnesc_events[] = {
+ "26CAB2E5-5CF1-46AE-AAC3-4A12B6BA50E6", /* Yoga 3 */
+ "56322276-8493-4CE8-A783-98C991274F5E", /* Yoga 700 */
+};
#endif
enum {
@@ -93,6 +96,7 @@ struct ideapad_private {
struct dentry *debug;
unsigned long cfg;
bool has_hw_rfkill_switch;
+ const char *fnesc_guid;
};
static bool no_bt_rfkill;
@@ -563,6 +567,7 @@ static void ideapad_sysfs_exit(struct ideapad_private *priv)
static const struct key_entry ideapad_keymap[] = {
{ KE_KEY, 6, { KEY_SWITCHVIDEOMODE } },
{ KE_KEY, 7, { KEY_CAMERA } },
+ { KE_KEY, 8, { KEY_MICMUTE } },
{ KE_KEY, 11, { KEY_F16 } },
{ KE_KEY, 13, { KEY_WLAN } },
{ KE_KEY, 16, { KEY_PROG1 } },
@@ -805,6 +810,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
break;
case 13:
case 11:
+ case 8:
case 7:
case 6:
ideapad_input_report(priv, vpc_bit);
@@ -989,8 +995,16 @@ static int ideapad_acpi_add(struct platform_device *pdev)
ACPI_DEVICE_NOTIFY, ideapad_acpi_notify, priv);
if (ret)
goto notification_failed;
+
#if IS_ENABLED(CONFIG_ACPI_WMI)
- ret = wmi_install_notify_handler(ideapad_wmi_fnesc_event, ideapad_wmi_notify, priv);
+ for (i = 0; i < ARRAY_SIZE(ideapad_wmi_fnesc_events); i++) {
+ ret = wmi_install_notify_handler(ideapad_wmi_fnesc_events[i],
+ ideapad_wmi_notify, priv);
+ if (ret == AE_OK) {
+ priv->fnesc_guid = ideapad_wmi_fnesc_events[i];
+ break;
+ }
+ }
if (ret != AE_OK && ret != AE_NOT_EXIST)
goto notification_failed_wmi;
#endif
@@ -1020,7 +1034,8 @@ static int ideapad_acpi_remove(struct platform_device *pdev)
int i;
#if IS_ENABLED(CONFIG_ACPI_WMI)
- wmi_remove_notify_handler(ideapad_wmi_fnesc_event);
+ if (priv->fnesc_guid)
+ wmi_remove_notify_handler(priv->fnesc_guid);
#endif
acpi_remove_notify_handler(priv->adev->handle,
ACPI_DEVICE_NOTIFY, ideapad_acpi_notify);
diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index 0a919d81662c..cbe01021c939 100644
--- a/drivers/platform/x86/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
@@ -306,33 +306,32 @@ static int sensor_set_auxtrip(acpi_handle handle, int index, int value)
#define to_intel_menlow_attr(_attr) \
container_of(_attr, struct intel_menlow_attribute, attr)
-static ssize_t aux0_show(struct device *dev,
- struct device_attribute *dev_attr, char *buf)
+static ssize_t aux_show(struct device *dev, struct device_attribute *dev_attr,
+ char *buf, int idx)
{
struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr);
unsigned long long value;
int result;
- result = sensor_get_auxtrip(attr->handle, 0, &value);
+ result = sensor_get_auxtrip(attr->handle, idx, &value);
return result ? result : sprintf(buf, "%lu", DECI_KELVIN_TO_CELSIUS(value));
}
-static ssize_t aux1_show(struct device *dev,
+static ssize_t aux0_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
- struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr);
- unsigned long long value;
- int result;
-
- result = sensor_get_auxtrip(attr->handle, 1, &value);
+ return aux_show(dev, dev_attr, buf, 0);
+}
- return result ? result : sprintf(buf, "%lu", DECI_KELVIN_TO_CELSIUS(value));
+static ssize_t aux1_show(struct device *dev,
+ struct device_attribute *dev_attr, char *buf)
+{
+ return aux_show(dev, dev_attr, buf, 1);
}
-static ssize_t aux0_store(struct device *dev,
- struct device_attribute *dev_attr,
- const char *buf, size_t count)
+static ssize_t aux_store(struct device *dev, struct device_attribute *dev_attr,
+ const char *buf, size_t count, int idx)
{
struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr);
int value;
@@ -345,27 +344,23 @@ static ssize_t aux0_store(struct device *dev,
if (value < 0)
return -EINVAL;
- result = sensor_set_auxtrip(attr->handle, 0, CELSIUS_TO_DECI_KELVIN(value));
+ result = sensor_set_auxtrip(attr->handle, idx,
+ CELSIUS_TO_DECI_KELVIN(value));
return result ? result : count;
}
-static ssize_t aux1_store(struct device *dev,
+static ssize_t aux0_store(struct device *dev,
struct device_attribute *dev_attr,
const char *buf, size_t count)
{
- struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr);
- int value;
- int result;
-
- /*Sanity check; should be a positive integer */
- if (!sscanf(buf, "%d", &value))
- return -EINVAL;
-
- if (value < 0)
- return -EINVAL;
+ return aux_store(dev, dev_attr, buf, count, 0);
+}
- result = sensor_set_auxtrip(attr->handle, 1, CELSIUS_TO_DECI_KELVIN(value));
- return result ? result : count;
+static ssize_t aux1_store(struct device *dev,
+ struct device_attribute *dev_attr,
+ const char *buf, size_t count)
+{
+ return aux_store(dev, dev_attr, buf, count, 1);
}
/* BIOS can enable/disable the thermal user application in dabney platform */
diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
new file mode 100644
index 000000000000..2776bec89c88
--- /dev/null
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -0,0 +1,200 @@
+/*
+ * Intel Core SoC Power Management Controller Driver
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com>
+ * Vishwanath Somayaji <vishwanath.somayaji@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+#include <linux/seq_file.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/pmc_core.h>
+
+#include "intel_pmc_core.h"
+
+static struct pmc_dev pmc;
+
+static const struct pci_device_id pmc_pci_ids[] = {
+ { PCI_VDEVICE(INTEL, SPT_PMC_PCI_DEVICE_ID), (kernel_ulong_t)NULL },
+ { 0, },
+};
+
+static inline u32 pmc_core_reg_read(struct pmc_dev *pmcdev, int reg_offset)
+{
+ return readl(pmcdev->regbase + reg_offset);
+}
+
+static inline u32 pmc_core_adjust_slp_s0_step(u32 value)
+{
+ return value * SPT_PMC_SLP_S0_RES_COUNTER_STEP;
+}
+
+/**
+ * intel_pmc_slp_s0_counter_read() - Read SLP_S0 residency.
+ * @data: Out param that contains current SLP_S0 count.
+ *
+ * This API currently supports Intel Skylake SoC and Sunrise
+ * Point Platform Controller Hub. Future platform support
+ * should be added for platforms that support low power modes
+ * beyond Package C10 state.
+ *
+ * SLP_S0_RESIDENCY counter counts in 100 us granularity per
+ * step hence function populates the multiplied value in out
+ * parameter @data.
+ *
+ * Return: an error code or 0 on success.
+ */
+int intel_pmc_slp_s0_counter_read(u32 *data)
+{
+ struct pmc_dev *pmcdev = &pmc;
+ u32 value;
+
+ if (!pmcdev->has_slp_s0_res)
+ return -EACCES;
+
+ value = pmc_core_reg_read(pmcdev, SPT_PMC_SLP_S0_RES_COUNTER_OFFSET);
+ *data = pmc_core_adjust_slp_s0_step(value);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(intel_pmc_slp_s0_counter_read);
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+static int pmc_core_dev_state_show(struct seq_file *s, void *unused)
+{
+ struct pmc_dev *pmcdev = s->private;
+ u32 counter_val;
+
+ counter_val = pmc_core_reg_read(pmcdev,
+ SPT_PMC_SLP_S0_RES_COUNTER_OFFSET);
+ seq_printf(s, "%u\n", pmc_core_adjust_slp_s0_step(counter_val));
+
+ return 0;
+}
+
+static int pmc_core_dev_state_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, pmc_core_dev_state_show, inode->i_private);
+}
+
+static const struct file_operations pmc_core_dev_state_ops = {
+ .open = pmc_core_dev_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
+{
+ debugfs_remove_recursive(pmcdev->dbgfs_dir);
+}
+
+static int pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
+{
+ struct dentry *dir, *file;
+
+ dir = debugfs_create_dir("pmc_core", NULL);
+ if (!dir)
+ return -ENOMEM;
+
+ pmcdev->dbgfs_dir = dir;
+ file = debugfs_create_file("slp_s0_residency_usec", S_IFREG | S_IRUGO,
+ dir, pmcdev, &pmc_core_dev_state_ops);
+
+ if (!file) {
+ pmc_core_dbgfs_unregister(pmcdev);
+ return -ENODEV;
+ }
+
+ return 0;
+}
+#else
+static inline int pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
+{
+ return 0;
+}
+
+static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static const struct x86_cpu_id intel_pmc_core_ids[] = {
+ { X86_VENDOR_INTEL, 6, 0x4e, X86_FEATURE_MWAIT,
+ (kernel_ulong_t)NULL}, /* Skylake CPUID Signature */
+ { X86_VENDOR_INTEL, 6, 0x5e, X86_FEATURE_MWAIT,
+ (kernel_ulong_t)NULL}, /* Skylake CPUID Signature */
+ {}
+};
+
+static int pmc_core_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+ struct device *ptr_dev = &dev->dev;
+ struct pmc_dev *pmcdev = &pmc;
+ const struct x86_cpu_id *cpu_id;
+ int err;
+
+ cpu_id = x86_match_cpu(intel_pmc_core_ids);
+ if (!cpu_id) {
+ dev_dbg(&dev->dev, "PMC Core: cpuid mismatch.\n");
+ return -EINVAL;
+ }
+
+ err = pcim_enable_device(dev);
+ if (err < 0) {
+ dev_dbg(&dev->dev, "PMC Core: failed to enable Power Management Controller.\n");
+ return err;
+ }
+
+ err = pci_read_config_dword(dev,
+ SPT_PMC_BASE_ADDR_OFFSET,
+ &pmcdev->base_addr);
+ if (err < 0) {
+ dev_dbg(&dev->dev, "PMC Core: failed to read PCI config space.\n");
+ return err;
+ }
+ dev_dbg(&dev->dev, "PMC Core: PWRMBASE is %#x\n", pmcdev->base_addr);
+
+ pmcdev->regbase = devm_ioremap_nocache(ptr_dev,
+ pmcdev->base_addr,
+ SPT_PMC_MMIO_REG_LEN);
+ if (!pmcdev->regbase) {
+ dev_dbg(&dev->dev, "PMC Core: ioremap failed.\n");
+ return -ENOMEM;
+ }
+
+ err = pmc_core_dbgfs_register(pmcdev);
+ if (err < 0) {
+ dev_err(&dev->dev, "PMC Core: debugfs register failed.\n");
+ return err;
+ }
+
+ pmc.has_slp_s0_res = true;
+ return 0;
+}
+
+static struct pci_driver intel_pmc_core_driver = {
+ .name = "intel_pmc_core",
+ .id_table = pmc_pci_ids,
+ .probe = pmc_core_probe,
+};
+
+builtin_pci_driver(intel_pmc_core_driver);
diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h
new file mode 100644
index 000000000000..a9dadaf787c1
--- /dev/null
+++ b/drivers/platform/x86/intel_pmc_core.h
@@ -0,0 +1,51 @@
+/*
+ * Intel Core SoC Power Management Controller Header File
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com>
+ * Vishwanath Somayaji <vishwanath.somayaji@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef PMC_CORE_H
+#define PMC_CORE_H
+
+/* Sunrise Point Power Management Controller PCI Device ID */
+#define SPT_PMC_PCI_DEVICE_ID 0x9d21
+#define SPT_PMC_BASE_ADDR_OFFSET 0x48
+#define SPT_PMC_SLP_S0_RES_COUNTER_OFFSET 0x13c
+#define SPT_PMC_MMIO_REG_LEN 0x100
+#define SPT_PMC_SLP_S0_RES_COUNTER_STEP 0x64
+
+/**
+ * struct pmc_dev - pmc device structure
+ * @base_addr: comtains pmc base address
+ * @regbase: pointer to io-remapped memory location
+ * @dbgfs_dir: path to debug fs interface
+ * @feature_available: flag to indicate whether
+ * the feature is available
+ * on a particular platform or not.
+ *
+ * pmc_dev contains info about power management controller device.
+ */
+struct pmc_dev {
+ u32 base_addr;
+ void __iomem *regbase;
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+ struct dentry *dbgfs_dir;
+#endif /* CONFIG_DEBUG_FS */
+ bool has_slp_s0_res;
+};
+
+#endif /* PMC_CORE_H */
diff --git a/drivers/platform/x86/intel_telemetry_core.c b/drivers/platform/x86/intel_telemetry_core.c
index a695a436a1c3..0d4c3808a6d8 100644
--- a/drivers/platform/x86/intel_telemetry_core.c
+++ b/drivers/platform/x86/intel_telemetry_core.c
@@ -25,7 +25,7 @@
struct telemetry_core_config {
struct telemetry_plt_config *plt_config;
- struct telemetry_core_ops *telem_ops;
+ const struct telemetry_core_ops *telem_ops;
};
static struct telemetry_core_config telm_core_conf;
@@ -95,7 +95,7 @@ static int telemetry_def_reset_events(void)
return 0;
}
-static struct telemetry_core_ops telm_defpltops = {
+static const struct telemetry_core_ops telm_defpltops = {
.set_sampling_period = telemetry_def_set_sampling_period,
.get_sampling_period = telemetry_def_get_sampling_period,
.get_trace_verbosity = telemetry_def_get_trace_verbosity,
@@ -332,7 +332,7 @@ EXPORT_SYMBOL_GPL(telemetry_set_trace_verbosity);
*
* Return: 0 success, < 0 for failure
*/
-int telemetry_set_pltdata(struct telemetry_core_ops *ops,
+int telemetry_set_pltdata(const struct telemetry_core_ops *ops,
struct telemetry_plt_config *pltconfig)
{
if (ops)
diff --git a/drivers/platform/x86/intel_telemetry_pltdrv.c b/drivers/platform/x86/intel_telemetry_pltdrv.c
index 781bd10ca7ac..09c84a2b1c2c 100644
--- a/drivers/platform/x86/intel_telemetry_pltdrv.c
+++ b/drivers/platform/x86/intel_telemetry_pltdrv.c
@@ -1081,7 +1081,7 @@ out:
return ret;
}
-static struct telemetry_core_ops telm_pltops = {
+static const struct telemetry_core_ops telm_pltops = {
.get_trace_verbosity = telemetry_plt_get_trace_verbosity,
.set_trace_verbosity = telemetry_plt_set_trace_verbosity,
.set_sampling_period = telemetry_plt_set_sampling_period,
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index e9caa347a9bf..1dba3598cfcb 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -1446,6 +1446,9 @@ static void sony_nc_function_cleanup(struct platform_device *pd)
{
unsigned int i, result, bitmask, handle;
+ if (!handles)
+ return;
+
/* get enabled events and disable them */
sony_nc_int_call(sony_nc_acpi_handle, "SN01", NULL, &bitmask);
sony_nc_int_call(sony_nc_acpi_handle, "SN03", &bitmask, &result);
diff --git a/drivers/platform/x86/surfacepro3_button.c b/drivers/platform/x86/surfacepro3_button.c
index 700e0fa0eec2..6505c97705e1 100644
--- a/drivers/platform/x86/surfacepro3_button.c
+++ b/drivers/platform/x86/surfacepro3_button.c
@@ -24,6 +24,8 @@
#define SURFACE_BUTTON_OBJ_NAME "VGBI"
#define SURFACE_BUTTON_DEVICE_NAME "Surface Pro 3/4 Buttons"
+#define SURFACE_BUTTON_NOTIFY_TABLET_MODE 0xc8
+
#define SURFACE_BUTTON_NOTIFY_PRESS_POWER 0xc6
#define SURFACE_BUTTON_NOTIFY_RELEASE_POWER 0xc7
@@ -33,7 +35,7 @@
#define SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_UP 0xc0
#define SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_UP 0xc1
-#define SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_DOWN 0xc2
+#define SURFACE_BUTTON_NOTIFY_PRESS_VOLUME_DOWN 0xc2
#define SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_DOWN 0xc3
ACPI_MODULE_NAME("surface pro 3 button");
@@ -105,9 +107,12 @@ static void surface_button_notify(struct acpi_device *device, u32 event)
case SURFACE_BUTTON_NOTIFY_RELEASE_VOLUME_DOWN:
key_code = KEY_VOLUMEDOWN;
break;
+ case SURFACE_BUTTON_NOTIFY_TABLET_MODE:
+ dev_warn_once(&device->dev, "Tablet mode is not supported\n");
+ break;
default:
dev_info_ratelimited(&device->dev,
- "Unsupported event [0x%x]\n", event);
+ "Unsupported event [0x%x]\n", event);
break;
}
input = button->input;
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9255ff3ee81a..b65ce7519411 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -2043,6 +2043,7 @@ static int hotkey_autosleep_ack;
static u32 hotkey_orig_mask; /* events the BIOS had enabled */
static u32 hotkey_all_mask; /* all events supported in fw */
+static u32 hotkey_adaptive_all_mask; /* all adaptive events supported in fw */
static u32 hotkey_reserved_mask; /* events better left disabled */
static u32 hotkey_driver_mask; /* events needed by the driver */
static u32 hotkey_user_mask; /* events visible to userspace */
@@ -2742,6 +2743,17 @@ static ssize_t hotkey_all_mask_show(struct device *dev,
static DEVICE_ATTR_RO(hotkey_all_mask);
+/* sysfs hotkey all_mask ----------------------------------------------- */
+static ssize_t hotkey_adaptive_all_mask_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "0x%08x\n",
+ hotkey_adaptive_all_mask | hotkey_source_mask);
+}
+
+static DEVICE_ATTR_RO(hotkey_adaptive_all_mask);
+
/* sysfs hotkey recommended_mask --------------------------------------- */
static ssize_t hotkey_recommended_mask_show(struct device *dev,
struct device_attribute *attr,
@@ -2985,6 +2997,7 @@ static struct attribute *hotkey_attributes[] __initdata = {
&dev_attr_wakeup_hotunplug_complete.attr,
&dev_attr_hotkey_mask.attr,
&dev_attr_hotkey_all_mask.attr,
+ &dev_attr_hotkey_adaptive_all_mask.attr,
&dev_attr_hotkey_recommended_mask.attr,
#ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL
&dev_attr_hotkey_source_mask.attr,
@@ -3321,20 +3334,6 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
if (!tp_features.hotkey)
return 1;
- /*
- * Check if we have an adaptive keyboard, like on the
- * Lenovo Carbon X1 2014 (2nd Gen).
- */
- if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) {
- if ((hkeyv >> 8) == 2) {
- tp_features.has_adaptive_kbd = true;
- res = sysfs_create_group(&tpacpi_pdev->dev.kobj,
- &adaptive_kbd_attr_group);
- if (res)
- goto err_exit;
- }
- }
-
quirks = tpacpi_check_quirks(tpacpi_hotkey_qtable,
ARRAY_SIZE(tpacpi_hotkey_qtable));
@@ -3357,30 +3356,70 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
A30, R30, R31, T20-22, X20-21, X22-24. Detected by checking
for HKEY interface version 0x100 */
if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) {
- if ((hkeyv >> 8) != 1) {
- pr_err("unknown version of the HKEY interface: 0x%x\n",
- hkeyv);
- pr_err("please report this to %s\n", TPACPI_MAIL);
- } else {
+ vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_HKEY,
+ "firmware HKEY interface version: 0x%x\n",
+ hkeyv);
+
+ switch (hkeyv >> 8) {
+ case 1:
/*
* MHKV 0x100 in A31, R40, R40e,
* T4x, X31, and later
*/
- vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_HKEY,
- "firmware HKEY interface version: 0x%x\n",
- hkeyv);
/* Paranoia check AND init hotkey_all_mask */
if (!acpi_evalf(hkey_handle, &hotkey_all_mask,
"MHKA", "qd")) {
- pr_err("missing MHKA handler, "
- "please report this to %s\n",
+ pr_err("missing MHKA handler, please report this to %s\n",
+ TPACPI_MAIL);
+ /* Fallback: pre-init for FN+F3,F4,F12 */
+ hotkey_all_mask = 0x080cU;
+ } else {
+ tp_features.hotkey_mask = 1;
+ }
+ break;
+
+ case 2:
+ /*
+ * MHKV 0x200 in X1, T460s, X260, T560, X1 Tablet (2016)
+ */
+
+ /* Paranoia check AND init hotkey_all_mask */
+ if (!acpi_evalf(hkey_handle, &hotkey_all_mask,
+ "MHKA", "dd", 1)) {
+ pr_err("missing MHKA handler, please report this to %s\n",
TPACPI_MAIL);
/* Fallback: pre-init for FN+F3,F4,F12 */
hotkey_all_mask = 0x080cU;
} else {
tp_features.hotkey_mask = 1;
}
+
+ /*
+ * Check if we have an adaptive keyboard, like on the
+ * Lenovo Carbon X1 2014 (2nd Gen).
+ */
+ if (acpi_evalf(hkey_handle, &hotkey_adaptive_all_mask,
+ "MHKA", "dd", 2)) {
+ if (hotkey_adaptive_all_mask != 0) {
+ tp_features.has_adaptive_kbd = true;
+ res = sysfs_create_group(
+ &tpacpi_pdev->dev.kobj,
+ &adaptive_kbd_attr_group);
+ if (res)
+ goto err_exit;
+ }
+ } else {
+ tp_features.has_adaptive_kbd = false;
+ hotkey_adaptive_all_mask = 0x0U;
+ }
+ break;
+
+ default:
+ pr_err("unknown version of the HKEY interface: 0x%x\n",
+ hkeyv);
+ pr_err("please report this to %s\n", TPACPI_MAIL);
+ break;
}
}
@@ -5001,6 +5040,8 @@ static int kbdlight_set_level(int level)
return 0;
}
+static int kbdlight_set_level_and_update(int level);
+
static int kbdlight_get_level(void)
{
int status = 0;
@@ -5068,7 +5109,7 @@ static void kbdlight_set_worker(struct work_struct *work)
container_of(work, struct tpacpi_led_classdev, work);
if (likely(tpacpi_lifecycle == TPACPI_LIFE_RUNNING))
- kbdlight_set_level(data->new_state);
+ kbdlight_set_level_and_update(data->new_state);
}
static void kbdlight_sysfs_set(struct led_classdev *led_cdev,
@@ -5099,7 +5140,6 @@ static struct tpacpi_led_classdev tpacpi_led_kbdlight = {
.max_brightness = 2,
.brightness_set = &kbdlight_sysfs_set,
.brightness_get = &kbdlight_sysfs_get,
- .flags = LED_CORE_SUSPENDRESUME,
}
};
@@ -5137,6 +5177,20 @@ static void kbdlight_exit(void)
flush_workqueue(tpacpi_wq);
}
+static int kbdlight_set_level_and_update(int level)
+{
+ int ret;
+ struct led_classdev *led_cdev;
+
+ ret = kbdlight_set_level(level);
+ led_cdev = &tpacpi_led_kbdlight.led_classdev;
+
+ if (ret == 0 && !(led_cdev->flags & LED_SUSPENDED))
+ led_cdev->brightness = level;
+
+ return ret;
+}
+
static int kbdlight_read(struct seq_file *m)
{
int level;
@@ -5177,13 +5231,35 @@ static int kbdlight_write(char *buf)
if (level == -1)
return -EINVAL;
- return kbdlight_set_level(level);
+ return kbdlight_set_level_and_update(level);
+}
+
+static void kbdlight_suspend(void)
+{
+ struct led_classdev *led_cdev;
+
+ if (!tp_features.kbdlight)
+ return;
+
+ led_cdev = &tpacpi_led_kbdlight.led_classdev;
+ led_update_brightness(led_cdev);
+ led_classdev_suspend(led_cdev);
+}
+
+static void kbdlight_resume(void)
+{
+ if (!tp_features.kbdlight)
+ return;
+
+ led_classdev_resume(&tpacpi_led_kbdlight.led_classdev);
}
static struct ibm_struct kbdlight_driver_data = {
.name = "kbdlight",
.read = kbdlight_read,
.write = kbdlight_write,
+ .suspend = kbdlight_suspend,
+ .resume = kbdlight_resume,
.exit = kbdlight_exit,
};
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 456987c88baa..b13cd074c52a 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -565,11 +565,12 @@ static int power_supply_read_temp(struct thermal_zone_device *tzd,
WARN_ON(tzd == NULL);
psy = tzd->devdata;
- ret = psy->desc->get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+ ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+ if (ret)
+ return ret;
/* Convert tenths of degree Celsius to milli degree Celsius. */
- if (!ret)
- *temp = val.intval * 100;
+ *temp = val.intval * 100;
return ret;
}
@@ -612,10 +613,12 @@ static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd,
int ret;
psy = tcd->devdata;
- ret = psy->desc->get_property(psy,
- POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
- if (!ret)
- *state = val.intval;
+ ret = power_supply_get_property(psy,
+ POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
+ if (ret)
+ return ret;
+
+ *state = val.intval;
return ret;
}
@@ -628,10 +631,12 @@ static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd,
int ret;
psy = tcd->devdata;
- ret = psy->desc->get_property(psy,
- POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
- if (!ret)
- *state = val.intval;
+ ret = power_supply_get_property(psy,
+ POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
+ if (ret)
+ return ret;
+
+ *state = val.intval;
return ret;
}
diff --git a/drivers/power/tps65217_charger.c b/drivers/power/tps65217_charger.c
index d9f56730c735..73dfae41def8 100644
--- a/drivers/power/tps65217_charger.c
+++ b/drivers/power/tps65217_charger.c
@@ -197,6 +197,7 @@ static int tps65217_charger_probe(struct platform_device *pdev)
{
struct tps65217 *tps = dev_get_drvdata(pdev->dev.parent);
struct tps65217_charger *charger;
+ struct power_supply_config cfg = {};
int ret;
dev_dbg(&pdev->dev, "%s\n", __func__);
@@ -208,9 +209,12 @@ static int tps65217_charger_probe(struct platform_device *pdev)
charger->tps = tps;
charger->dev = &pdev->dev;
+ cfg.of_node = pdev->dev.of_node;
+ cfg.drv_data = charger;
+
charger->ac = devm_power_supply_register(&pdev->dev,
&tps65217_charger_desc,
- NULL);
+ &cfg);
if (IS_ERR(charger->ac)) {
dev_err(&pdev->dev, "failed: power supply register\n");
return PTR_ERR(charger->ac);
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 579fd65299a0..d637c933c8a9 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -208,14 +208,10 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
break;
case PTP_SYS_OFFSET:
- sysoff = kmalloc(sizeof(*sysoff), GFP_KERNEL);
- if (!sysoff) {
- err = -ENOMEM;
- break;
- }
- if (copy_from_user(sysoff, (void __user *)arg,
- sizeof(*sysoff))) {
- err = -EFAULT;
+ sysoff = memdup_user((void __user *)arg, sizeof(*sysoff));
+ if (IS_ERR(sysoff)) {
+ err = PTR_ERR(sysoff);
+ sysoff = NULL;
break;
}
if (sysoff->n_samples > PTP_MAX_SAMPLES) {
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 680fbc795a0a..ed337a8c34ab 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -75,6 +75,7 @@ static void free_pwms(struct pwm_chip *chip)
for (i = 0; i < chip->npwm; i++) {
struct pwm_device *pwm = &chip->pwms[i];
+
radix_tree_delete(&pwm_tree, pwm->pwm);
}
@@ -128,13 +129,6 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label)
set_bit(PWMF_REQUESTED, &pwm->flags);
pwm->label = label;
- /*
- * FIXME: This should be removed once all PWM users properly make use
- * of struct pwm_args to initialize the PWM device. As long as this is
- * here, the PWM state and hardware state can get out of sync.
- */
- pwm_apply_args(pwm);
-
return 0;
}
@@ -233,6 +227,19 @@ void *pwm_get_chip_data(struct pwm_device *pwm)
}
EXPORT_SYMBOL_GPL(pwm_get_chip_data);
+static bool pwm_ops_check(const struct pwm_ops *ops)
+{
+ /* driver supports legacy, non-atomic operation */
+ if (ops->config && ops->enable && ops->disable)
+ return true;
+
+ /* driver supports atomic operation */
+ if (ops->apply)
+ return true;
+
+ return false;
+}
+
/**
* pwmchip_add_with_polarity() - register a new PWM chip
* @chip: the PWM chip to add
@@ -251,8 +258,10 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip,
unsigned int i;
int ret;
- if (!chip || !chip->dev || !chip->ops || !chip->ops->config ||
- !chip->ops->enable || !chip->ops->disable || !chip->npwm)
+ if (!chip || !chip->dev || !chip->ops || !chip->npwm)
+ return -EINVAL;
+
+ if (!pwm_ops_check(chip->ops))
return -EINVAL;
mutex_lock(&pwm_lock);
@@ -261,7 +270,7 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip,
if (ret < 0)
goto out;
- chip->pwms = kzalloc(chip->npwm * sizeof(*pwm), GFP_KERNEL);
+ chip->pwms = kcalloc(chip->npwm, sizeof(*pwm), GFP_KERNEL);
if (!chip->pwms) {
ret = -ENOMEM;
goto out;
@@ -275,8 +284,10 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip,
pwm->chip = chip;
pwm->pwm = chip->base + i;
pwm->hwpwm = i;
- pwm->polarity = polarity;
- mutex_init(&pwm->lock);
+ pwm->state.polarity = polarity;
+
+ if (chip->ops->get_state)
+ chip->ops->get_state(chip, pwm, &pwm->state);
radix_tree_insert(&pwm_tree, pwm->pwm, pwm);
}
@@ -436,107 +447,139 @@ void pwm_free(struct pwm_device *pwm)
EXPORT_SYMBOL_GPL(pwm_free);
/**
- * pwm_config() - change a PWM device configuration
+ * pwm_apply_state() - atomically apply a new state to a PWM device
* @pwm: PWM device
- * @duty_ns: "on" time (in nanoseconds)
- * @period_ns: duration (in nanoseconds) of one cycle
- *
- * Returns: 0 on success or a negative error code on failure.
+ * @state: new state to apply. This can be adjusted by the PWM driver
+ * if the requested config is not achievable, for example,
+ * ->duty_cycle and ->period might be approximated.
*/
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
+int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state)
{
int err;
- if (!pwm || duty_ns < 0 || period_ns <= 0 || duty_ns > period_ns)
+ if (!pwm || !state || !state->period ||
+ state->duty_cycle > state->period)
return -EINVAL;
- err = pwm->chip->ops->config(pwm->chip, pwm, duty_ns, period_ns);
- if (err)
- return err;
-
- pwm->duty_cycle = duty_ns;
- pwm->period = period_ns;
+ if (!memcmp(state, &pwm->state, sizeof(*state)))
+ return 0;
- return 0;
-}
-EXPORT_SYMBOL_GPL(pwm_config);
+ if (pwm->chip->ops->apply) {
+ err = pwm->chip->ops->apply(pwm->chip, pwm, state);
+ if (err)
+ return err;
-/**
- * pwm_set_polarity() - configure the polarity of a PWM signal
- * @pwm: PWM device
- * @polarity: new polarity of the PWM signal
- *
- * Note that the polarity cannot be configured while the PWM device is
- * enabled.
- *
- * Returns: 0 on success or a negative error code on failure.
- */
-int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity)
-{
- int err;
+ pwm->state = *state;
+ } else {
+ /*
+ * FIXME: restore the initial state in case of error.
+ */
+ if (state->polarity != pwm->state.polarity) {
+ if (!pwm->chip->ops->set_polarity)
+ return -ENOTSUPP;
+
+ /*
+ * Changing the polarity of a running PWM is
+ * only allowed when the PWM driver implements
+ * ->apply().
+ */
+ if (pwm->state.enabled) {
+ pwm->chip->ops->disable(pwm->chip, pwm);
+ pwm->state.enabled = false;
+ }
+
+ err = pwm->chip->ops->set_polarity(pwm->chip, pwm,
+ state->polarity);
+ if (err)
+ return err;
+
+ pwm->state.polarity = state->polarity;
+ }
- if (!pwm || !pwm->chip->ops)
- return -EINVAL;
+ if (state->period != pwm->state.period ||
+ state->duty_cycle != pwm->state.duty_cycle) {
+ err = pwm->chip->ops->config(pwm->chip, pwm,
+ state->duty_cycle,
+ state->period);
+ if (err)
+ return err;
- if (!pwm->chip->ops->set_polarity)
- return -ENOSYS;
+ pwm->state.duty_cycle = state->duty_cycle;
+ pwm->state.period = state->period;
+ }
- mutex_lock(&pwm->lock);
+ if (state->enabled != pwm->state.enabled) {
+ if (state->enabled) {
+ err = pwm->chip->ops->enable(pwm->chip, pwm);
+ if (err)
+ return err;
+ } else {
+ pwm->chip->ops->disable(pwm->chip, pwm);
+ }
- if (pwm_is_enabled(pwm)) {
- err = -EBUSY;
- goto unlock;
+ pwm->state.enabled = state->enabled;
+ }
}
- err = pwm->chip->ops->set_polarity(pwm->chip, pwm, polarity);
- if (err)
- goto unlock;
-
- pwm->polarity = polarity;
-
-unlock:
- mutex_unlock(&pwm->lock);
- return err;
+ return 0;
}
-EXPORT_SYMBOL_GPL(pwm_set_polarity);
+EXPORT_SYMBOL_GPL(pwm_apply_state);
/**
- * pwm_enable() - start a PWM output toggling
+ * pwm_adjust_config() - adjust the current PWM config to the PWM arguments
* @pwm: PWM device
*
- * Returns: 0 on success or a negative error code on failure.
+ * This function will adjust the PWM config to the PWM arguments provided
+ * by the DT or PWM lookup table. This is particularly useful to adapt
+ * the bootloader config to the Linux one.
*/
-int pwm_enable(struct pwm_device *pwm)
+int pwm_adjust_config(struct pwm_device *pwm)
{
- int err = 0;
+ struct pwm_state state;
+ struct pwm_args pargs;
- if (!pwm)
- return -EINVAL;
+ pwm_get_args(pwm, &pargs);
+ pwm_get_state(pwm, &state);
- mutex_lock(&pwm->lock);
+ /*
+ * If the current period is zero it means that either the PWM driver
+ * does not support initial state retrieval or the PWM has not yet
+ * been configured.
+ *
+ * In either case, we setup the new period and polarity, and assign a
+ * duty cycle of 0.
+ */
+ if (!state.period) {
+ state.duty_cycle = 0;
+ state.period = pargs.period;
+ state.polarity = pargs.polarity;
- if (!test_and_set_bit(PWMF_ENABLED, &pwm->flags)) {
- err = pwm->chip->ops->enable(pwm->chip, pwm);
- if (err)
- clear_bit(PWMF_ENABLED, &pwm->flags);
+ return pwm_apply_state(pwm, &state);
}
- mutex_unlock(&pwm->lock);
+ /*
+ * Adjust the PWM duty cycle/period based on the period value provided
+ * in PWM args.
+ */
+ if (pargs.period != state.period) {
+ u64 dutycycle = (u64)state.duty_cycle * pargs.period;
- return err;
-}
-EXPORT_SYMBOL_GPL(pwm_enable);
+ do_div(dutycycle, state.period);
+ state.duty_cycle = dutycycle;
+ state.period = pargs.period;
+ }
-/**
- * pwm_disable() - stop a PWM output toggling
- * @pwm: PWM device
- */
-void pwm_disable(struct pwm_device *pwm)
-{
- if (pwm && test_and_clear_bit(PWMF_ENABLED, &pwm->flags))
- pwm->chip->ops->disable(pwm->chip, pwm);
+ /*
+ * If the polarity changed, we should also change the duty cycle.
+ */
+ if (pargs.polarity != state.polarity) {
+ state.polarity = pargs.polarity;
+ state.duty_cycle = state.period - state.duty_cycle;
+ }
+
+ return pwm_apply_state(pwm, &state);
}
-EXPORT_SYMBOL_GPL(pwm_disable);
+EXPORT_SYMBOL_GPL(pwm_adjust_config);
static struct pwm_chip *of_node_to_pwmchip(struct device_node *np)
{
@@ -754,13 +797,13 @@ struct pwm_device *pwm_get(struct device *dev, const char *con_id)
if (!chip)
goto out;
- pwm->args.period = chosen->period;
- pwm->args.polarity = chosen->polarity;
-
pwm = pwm_request_from_chip(chip, chosen->index, con_id ?: dev_id);
if (IS_ERR(pwm))
goto out;
+ pwm->args.period = chosen->period;
+ pwm->args.polarity = chosen->polarity;
+
out:
mutex_unlock(&pwm_lookup_lock);
return pwm;
@@ -907,15 +950,23 @@ static void pwm_dbg_show(struct pwm_chip *chip, struct seq_file *s)
for (i = 0; i < chip->npwm; i++) {
struct pwm_device *pwm = &chip->pwms[i];
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
seq_printf(s, " pwm-%-3d (%-20.20s):", i, pwm->label);
if (test_bit(PWMF_REQUESTED, &pwm->flags))
seq_puts(s, " requested");
- if (pwm_is_enabled(pwm))
+ if (state.enabled)
seq_puts(s, " enabled");
+ seq_printf(s, " period: %u ns", state.period);
+ seq_printf(s, " duty: %u ns", state.duty_cycle);
+ seq_printf(s, " polarity: %s",
+ state.polarity ? "inverse" : "normal");
+
seq_puts(s, "\n");
}
}
diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c
index f994c7eaf41c..14fc011faa32 100644
--- a/drivers/pwm/pwm-atmel-hlcdc.c
+++ b/drivers/pwm/pwm-atmel-hlcdc.c
@@ -272,7 +272,7 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev)
chip->chip.of_pwm_n_cells = 3;
chip->chip.can_sleep = 1;
- ret = pwmchip_add(&chip->chip);
+ ret = pwmchip_add_with_polarity(&chip->chip, PWM_POLARITY_INVERSED);
if (ret) {
clk_disable_unprepare(hlcdc->periph_clk);
return ret;
diff --git a/drivers/pwm/pwm-crc.c b/drivers/pwm/pwm-crc.c
index 7101c7020bf4..bd0ebd04856a 100644
--- a/drivers/pwm/pwm-crc.c
+++ b/drivers/pwm/pwm-crc.c
@@ -75,7 +75,7 @@ static int crc_pwm_config(struct pwm_chip *c, struct pwm_device *pwm,
return -EINVAL;
}
- if (pwm->period != period_ns) {
+ if (pwm_get_period(pwm) != period_ns) {
int clk_div;
/* changing the clk divisor, need to disable fisrt */
diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c
index 9861fed4e67d..19dc64cab2f0 100644
--- a/drivers/pwm/pwm-lpc18xx-sct.c
+++ b/drivers/pwm/pwm-lpc18xx-sct.c
@@ -249,7 +249,7 @@ static int lpc18xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
LPC18XX_PWM_EVSTATEMSK(lpc18xx_data->duty_event),
LPC18XX_PWM_EVSTATEMSK_ALL);
- if (pwm->polarity == PWM_POLARITY_NORMAL) {
+ if (pwm_get_polarity(pwm) == PWM_POLARITY_NORMAL) {
set_event = lpc18xx_pwm->period_event;
clear_event = lpc18xx_data->duty_event;
res_action = LPC18XX_PWM_RES_SET;
diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c
index b7e6ecba7d5c..3e95090cd7cf 100644
--- a/drivers/pwm/pwm-omap-dmtimer.c
+++ b/drivers/pwm/pwm-omap-dmtimer.c
@@ -192,7 +192,7 @@ static int pwm_omap_dmtimer_config(struct pwm_chip *chip,
load_value, load_value, match_value, match_value);
omap->pdata->set_pwm(omap->dm_timer,
- pwm->polarity == PWM_POLARITY_INVERSED,
+ pwm_get_polarity(pwm) == PWM_POLARITY_INVERSED,
true,
PWM_OMAP_DMTIMER_TRIGGER_OVERFLOW_AND_COMPARE);
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index 7b8ac0678137..1c85ecc9e7ac 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -157,7 +157,7 @@ static int rcar_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
return div;
/* Let the core driver set pwm->period if disabled and duty_ns == 0 */
- if (!test_bit(PWMF_ENABLED, &pwm->flags) && !duty_ns)
+ if (!pwm_is_enabled(pwm) && !duty_ns)
return 0;
rcar_pwm_update(rp, RCAR_PWMCR_SYNC, RCAR_PWMCR_SYNC, RCAR_PWMCR);
diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c
index 67af9f62361f..03a99a53c39e 100644
--- a/drivers/pwm/pwm-sun4i.c
+++ b/drivers/pwm/pwm-sun4i.c
@@ -354,7 +354,8 @@ static int sun4i_pwm_probe(struct platform_device *pdev)
val = sun4i_pwm_readl(pwm, PWM_CTRL_REG);
for (i = 0; i < pwm->chip.npwm; i++)
if (!(val & BIT_CH(PWM_ACT_STATE, i)))
- pwm->chip.pwms[i].polarity = PWM_POLARITY_INVERSED;
+ pwm_set_polarity(&pwm->chip.pwms[i],
+ PWM_POLARITY_INVERSED);
clk_disable_unprepare(pwm->clk);
return 0;
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 9c90886f4123..01695d48dd54 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -26,6 +26,7 @@
struct pwm_export {
struct device child;
struct pwm_device *pwm;
+ struct mutex lock;
};
static struct pwm_export *child_to_pwm_export(struct device *child)
@@ -45,15 +46,20 @@ static ssize_t period_show(struct device *child,
char *buf)
{
const struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_state state;
- return sprintf(buf, "%u\n", pwm_get_period(pwm));
+ pwm_get_state(pwm, &state);
+
+ return sprintf(buf, "%u\n", state.period);
}
static ssize_t period_store(struct device *child,
struct device_attribute *attr,
const char *buf, size_t size)
{
- struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_export *export = child_to_pwm_export(child);
+ struct pwm_device *pwm = export->pwm;
+ struct pwm_state state;
unsigned int val;
int ret;
@@ -61,7 +67,11 @@ static ssize_t period_store(struct device *child,
if (ret)
return ret;
- ret = pwm_config(pwm, pwm_get_duty_cycle(pwm), val);
+ mutex_lock(&export->lock);
+ pwm_get_state(pwm, &state);
+ state.period = val;
+ ret = pwm_apply_state(pwm, &state);
+ mutex_unlock(&export->lock);
return ret ? : size;
}
@@ -71,15 +81,20 @@ static ssize_t duty_cycle_show(struct device *child,
char *buf)
{
const struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
- return sprintf(buf, "%u\n", pwm_get_duty_cycle(pwm));
+ return sprintf(buf, "%u\n", state.duty_cycle);
}
static ssize_t duty_cycle_store(struct device *child,
struct device_attribute *attr,
const char *buf, size_t size)
{
- struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_export *export = child_to_pwm_export(child);
+ struct pwm_device *pwm = export->pwm;
+ struct pwm_state state;
unsigned int val;
int ret;
@@ -87,7 +102,11 @@ static ssize_t duty_cycle_store(struct device *child,
if (ret)
return ret;
- ret = pwm_config(pwm, val, pwm_get_period(pwm));
+ mutex_lock(&export->lock);
+ pwm_get_state(pwm, &state);
+ state.duty_cycle = val;
+ ret = pwm_apply_state(pwm, &state);
+ mutex_unlock(&export->lock);
return ret ? : size;
}
@@ -97,33 +116,46 @@ static ssize_t enable_show(struct device *child,
char *buf)
{
const struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
- return sprintf(buf, "%d\n", pwm_is_enabled(pwm));
+ return sprintf(buf, "%d\n", state.enabled);
}
static ssize_t enable_store(struct device *child,
struct device_attribute *attr,
const char *buf, size_t size)
{
- struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_export *export = child_to_pwm_export(child);
+ struct pwm_device *pwm = export->pwm;
+ struct pwm_state state;
int val, ret;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
+ mutex_lock(&export->lock);
+
+ pwm_get_state(pwm, &state);
+
switch (val) {
case 0:
- pwm_disable(pwm);
+ state.enabled = false;
break;
case 1:
- ret = pwm_enable(pwm);
+ state.enabled = true;
break;
default:
ret = -EINVAL;
- break;
+ goto unlock;
}
+ ret = pwm_apply_state(pwm, &state);
+
+unlock:
+ mutex_unlock(&export->lock);
return ret ? : size;
}
@@ -133,8 +165,11 @@ static ssize_t polarity_show(struct device *child,
{
const struct pwm_device *pwm = child_to_pwm_device(child);
const char *polarity = "unknown";
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
- switch (pwm_get_polarity(pwm)) {
+ switch (state.polarity) {
case PWM_POLARITY_NORMAL:
polarity = "normal";
break;
@@ -151,8 +186,10 @@ static ssize_t polarity_store(struct device *child,
struct device_attribute *attr,
const char *buf, size_t size)
{
- struct pwm_device *pwm = child_to_pwm_device(child);
+ struct pwm_export *export = child_to_pwm_export(child);
+ struct pwm_device *pwm = export->pwm;
enum pwm_polarity polarity;
+ struct pwm_state state;
int ret;
if (sysfs_streq(buf, "normal"))
@@ -162,7 +199,11 @@ static ssize_t polarity_store(struct device *child,
else
return -EINVAL;
- ret = pwm_set_polarity(pwm, polarity);
+ mutex_lock(&export->lock);
+ pwm_get_state(pwm, &state);
+ state.polarity = polarity;
+ ret = pwm_apply_state(pwm, &state);
+ mutex_unlock(&export->lock);
return ret ? : size;
}
@@ -203,6 +244,7 @@ static int pwm_export_child(struct device *parent, struct pwm_device *pwm)
}
export->pwm = pwm;
+ mutex_init(&export->lock);
export->child.release = pwm_export_release;
export->child.parent = parent;
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 63cd5e68c864..3a6d0290c54c 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -296,7 +296,7 @@ static int anatop_regulator_probe(struct platform_device *pdev)
if (!sreg->sel && !strcmp(sreg->name, "vddpu"))
sreg->sel = 22;
- if (!sreg->sel) {
+ if (!sreg->bypass && !sreg->sel) {
dev_err(&pdev->dev, "Failed to read a valid default voltage selector.\n");
return -EINVAL;
}
diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c
index 321e804aeab0..a1b49a6d538f 100644
--- a/drivers/regulator/max77620-regulator.c
+++ b/drivers/regulator/max77620-regulator.c
@@ -123,6 +123,9 @@ static int max77620_regulator_set_fps_src(struct max77620_regulator *pmic,
unsigned int val;
int ret;
+ if (!rinfo)
+ return 0;
+
switch (fps_src) {
case MAX77620_FPS_SRC_0:
case MAX77620_FPS_SRC_1:
@@ -171,6 +174,9 @@ static int max77620_regulator_set_fps_slots(struct max77620_regulator *pmic,
int pd = rpdata->active_fps_pd_slot;
int ret = 0;
+ if (!rinfo)
+ return 0;
+
if (is_suspend) {
pu = rpdata->suspend_fps_pu_slot;
pd = rpdata->suspend_fps_pd_slot;
@@ -680,7 +686,6 @@ static struct max77620_regulator_info max77620_regs_info[MAX77620_NUM_REGS] = {
RAIL_SD(SD1, sd1, "in-sd1", SD1, 600000, 1550000, 12500, 0x22, SD1),
RAIL_SD(SD2, sd2, "in-sd2", SDX, 600000, 3787500, 12500, 0xFF, NONE),
RAIL_SD(SD3, sd3, "in-sd3", SDX, 600000, 3787500, 12500, 0xFF, NONE),
- RAIL_SD(SD4, sd4, "in-sd4", SDX, 600000, 3787500, 12500, 0xFF, NONE),
RAIL_LDO(LDO0, ldo0, "in-ldo0-1", N, 800000, 2375000, 25000),
RAIL_LDO(LDO1, ldo1, "in-ldo0-1", N, 800000, 2375000, 25000),
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index 56a17ec5b5ef..526bf23dcb49 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -140,6 +140,19 @@ static const struct regulator_ops rpm_smps_ldo_ops = {
.enable = rpm_reg_enable,
.disable = rpm_reg_disable,
.is_enabled = rpm_reg_is_enabled,
+ .list_voltage = regulator_list_voltage_linear_range,
+
+ .get_voltage = rpm_reg_get_voltage,
+ .set_voltage = rpm_reg_set_voltage,
+
+ .set_load = rpm_reg_set_load,
+};
+
+static const struct regulator_ops rpm_smps_ldo_ops_fixed = {
+ .enable = rpm_reg_enable,
+ .disable = rpm_reg_disable,
+ .is_enabled = rpm_reg_is_enabled,
+ .list_voltage = regulator_list_voltage_linear_range,
.get_voltage = rpm_reg_get_voltage,
.set_voltage = rpm_reg_set_voltage,
@@ -247,7 +260,7 @@ static const struct regulator_desc pm8941_nldo = {
static const struct regulator_desc pm8941_lnldo = {
.fixed_uV = 1740000,
.n_voltages = 1,
- .ops = &rpm_smps_ldo_ops,
+ .ops = &rpm_smps_ldo_ops_fixed,
};
static const struct regulator_desc pm8941_switch = {
diff --git a/drivers/regulator/tps51632-regulator.c b/drivers/regulator/tps51632-regulator.c
index 572816e30095..c139890c1514 100644
--- a/drivers/regulator/tps51632-regulator.c
+++ b/drivers/regulator/tps51632-regulator.c
@@ -94,11 +94,14 @@ static int tps51632_dcdc_set_ramp_delay(struct regulator_dev *rdev,
int ramp_delay)
{
struct tps51632_chip *tps = rdev_get_drvdata(rdev);
- int bit = ramp_delay/6000;
+ int bit;
int ret;
- if (bit)
- bit--;
+ if (ramp_delay == 0)
+ bit = 0;
+ else
+ bit = DIV_ROUND_UP(ramp_delay, 6000) - 1;
+
ret = regmap_write(tps->regmap, TPS51632_SLEW_REGS, BIT(bit));
if (ret < 0)
dev_err(tps->dev, "SLEW reg write failed, err %d\n", ret);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index b83908670a9a..bed53c46dd90 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -31,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode);
static blk_qc_t dcssblk_make_request(struct request_queue *q,
struct bio *bio);
static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
- void __pmem **kaddr, pfn_t *pfn);
+ void __pmem **kaddr, pfn_t *pfn, long size);
static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
@@ -884,7 +884,7 @@ fail:
static long
dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
- void __pmem **kaddr, pfn_t *pfn)
+ void __pmem **kaddr, pfn_t *pfn, long size)
{
struct dcssblk_dev_info *dev_info;
unsigned long offset, dev_sz;
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index d4c285688ce9..3ddc85e6efd6 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1122,7 +1122,7 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
} else {
struct scsi_cmnd *SCp;
- SCp = scsi_host_find_tag(SDp->host, SCSI_NO_TAG);
+ SCp = SDp->current_cmnd;
if(unlikely(SCp == NULL)) {
sdev_printk(KERN_ERR, SDp,
"no saved request for untagged cmd\n");
@@ -1826,7 +1826,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
slot->tag, slot);
} else {
slot->tag = SCSI_NO_TAG;
- /* must populate current_cmnd for scsi_host_find_tag to work */
+ /* save current command for reselection */
SCp->device->current_cmnd = SCp;
}
/* sanity check: some of the commands generated by the mid-layer
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 8f90d9e77104..969c312de1be 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -621,6 +621,11 @@ struct aac_driver_ident
#define AAC_QUIRK_SCSI_32 0x0020
/*
+ * SRC based adapters support the AifReqEvent functions
+ */
+#define AAC_QUIRK_SRC 0x0040
+
+/*
* The adapter interface specs all queues to be located in the same
* physically contiguous block. The host structure that defines the
* commuication queues will assume they are each a separate physically
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index a943bd230bc2..79871f3519ff 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -236,10 +236,10 @@ static struct aac_driver_ident aac_drivers[] = {
{ aac_rx_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec Catch All */
{ aac_rkt_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec Rocket Catch All */
{ aac_nark_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec NEMER/ARK Catch All */
- { aac_src_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 6 (Tupelo) */
- { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 7 (Denali) */
- { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 8 */
- { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 } /* Adaptec PMC Series 9 */
+ { aac_src_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 6 (Tupelo) */
+ { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 7 (Denali) */
+ { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 8 */
+ { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC } /* Adaptec PMC Series 9 */
};
/**
@@ -1299,7 +1299,8 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
else
shost->this_id = shost->max_id;
- aac_intr_normal(aac, 0, 2, 0, NULL);
+ if (aac_drivers[index].quirks & AAC_QUIRK_SRC)
+ aac_intr_normal(aac, 0, 2, 0, NULL);
/*
* dmb - we may need to move the setting of these parms somewhere else once
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 6a4df5a315e9..6bff13e7afc7 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -7975,13 +7975,14 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
ActiveCableEventData =
(Mpi26EventDataActiveCableExcept_t *) mpi_reply->EventData;
if (ActiveCableEventData->ReasonCode ==
- MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER)
+ MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) {
pr_info(MPT3SAS_FMT "Currently an active cable with ReceptacleID %d",
ioc->name, ActiveCableEventData->ReceptacleID);
pr_info("cannot be powered and devices connected to this active cable");
pr_info("will not be seen. This active cable");
pr_info("requires %d mW of power",
ActiveCableEventData->ActiveCablePowerRequirement);
+ }
break;
default: /* ignore the rest */
diff --git a/drivers/scsi/qla2xxx/Kconfig b/drivers/scsi/qla2xxx/Kconfig
index 10aa18ba05fd..67c0d5aa3212 100644
--- a/drivers/scsi/qla2xxx/Kconfig
+++ b/drivers/scsi/qla2xxx/Kconfig
@@ -36,3 +36,12 @@ config TCM_QLA2XXX
default n
---help---
Say Y here to enable the TCM_QLA2XXX fabric module for QLogic 24xx+ series target mode HBAs
+
+if TCM_QLA2XXX
+config TCM_QLA2XXX_DEBUG
+ bool "TCM_QLA2XXX fabric module DEBUG mode for QLogic 24xx+ series target mode HBAs"
+ default n
+ ---help---
+ Say Y here to enable the TCM_QLA2XXX fabric module DEBUG for QLogic 24xx+ series target mode HBAs
+ This will include code to enable the SCSI command jammer
+endif
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 8a44d1541eb4..ca39deb4ff5b 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -637,8 +637,10 @@ static void qlt_free_session_done(struct work_struct *work)
}
/* ha->tgt.sess_lock supposed to be held on entry */
-void qlt_unreg_sess(struct qla_tgt_sess *sess)
+static void qlt_release_session(struct kref *kref)
{
+ struct qla_tgt_sess *sess =
+ container_of(kref, struct qla_tgt_sess, sess_kref);
struct scsi_qla_host *vha = sess->vha;
if (sess->se_sess)
@@ -651,8 +653,16 @@ void qlt_unreg_sess(struct qla_tgt_sess *sess)
INIT_WORK(&sess->free_work, qlt_free_session_done);
schedule_work(&sess->free_work);
}
-EXPORT_SYMBOL(qlt_unreg_sess);
+void qlt_put_sess(struct qla_tgt_sess *sess)
+{
+ if (!sess)
+ return;
+
+ assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
+ kref_put(&sess->sess_kref, qlt_release_session);
+}
+EXPORT_SYMBOL(qlt_put_sess);
static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd)
{
@@ -857,12 +867,9 @@ static void qlt_del_sess_work_fn(struct delayed_work *work)
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004,
"Timeout: sess %p about to be deleted\n",
sess);
- if (sess->se_sess) {
+ if (sess->se_sess)
ha->tgt.tgt_ops->shutdown_sess(sess);
- ha->tgt.tgt_ops->put_sess(sess);
- } else {
- qlt_unreg_sess(sess);
- }
+ qlt_put_sess(sess);
} else {
schedule_delayed_work(&tgt->sess_del_work,
sess->expires - elapsed);
@@ -917,7 +924,7 @@ static struct qla_tgt_sess *qlt_create_sess(
}
}
- kref_get(&sess->se_sess->sess_kref);
+ kref_get(&sess->sess_kref);
ha->tgt.tgt_ops->update_sess(sess, fcport->d_id, fcport->loop_id,
(fcport->flags & FCF_CONF_COMP_SUPPORTED));
@@ -947,6 +954,7 @@ static struct qla_tgt_sess *qlt_create_sess(
sess->s_id = fcport->d_id;
sess->loop_id = fcport->loop_id;
sess->local = local;
+ kref_init(&sess->sess_kref);
INIT_LIST_HEAD(&sess->del_list_entry);
/* Under normal circumstances we want to logout from firmware when
@@ -991,7 +999,7 @@ static struct qla_tgt_sess *qlt_create_sess(
* Take an extra reference to ->sess_kref here to handle qla_tgt_sess
* access across ->tgt.sess_lock reaquire.
*/
- kref_get(&sess->se_sess->sess_kref);
+ kref_get(&sess->sess_kref);
}
return sess;
@@ -1035,7 +1043,7 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
return;
} else {
- kref_get(&sess->se_sess->sess_kref);
+ kref_get(&sess->sess_kref);
if (sess->deleted) {
qlt_undelete_sess(sess);
@@ -1060,7 +1068,7 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
fcport->port_name, sess->loop_id);
sess->local = 0;
}
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}
@@ -3817,7 +3825,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
* Drop extra session reference from qla_tgt_handle_cmd_for_atio*(
*/
spin_lock_irqsave(&ha->tgt.sess_lock, flags);
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
return;
@@ -3836,7 +3844,7 @@ out_term:
spin_unlock_irqrestore(&ha->hardware_lock, flags);
spin_lock_irqsave(&ha->tgt.sess_lock, flags);
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}
@@ -3936,13 +3944,13 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
if (!cmd) {
spin_lock_irqsave(&ha->hardware_lock, flags);
qlt_send_busy(vha, &op->atio, SAM_STAT_BUSY);
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->hardware_lock, flags);
kfree(op);
return;
}
/*
- * __qlt_do_work() will call ha->tgt.tgt_ops->put_sess() to release
+ * __qlt_do_work() will call qlt_put_sess() to release
* the extra reference taken above by qlt_make_local_sess()
*/
__qlt_do_work(cmd);
@@ -4003,13 +4011,13 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
/*
* Do kref_get() before returning + dropping qla_hw_data->hardware_lock.
*/
- kref_get(&sess->se_sess->sess_kref);
+ kref_get(&sess->sess_kref);
cmd = qlt_get_tag(vha, sess, atio);
if (!cmd) {
ql_dbg(ql_dbg_io, vha, 0x3062,
"qla_target(%d): Allocation of cmd failed\n", vha->vp_idx);
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
return -ENOMEM;
}
@@ -5911,7 +5919,7 @@ static void qlt_abort_work(struct qla_tgt *tgt,
goto out_term2;
}
- kref_get(&sess->se_sess->sess_kref);
+ kref_get(&sess->sess_kref);
}
spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -5924,7 +5932,7 @@ static void qlt_abort_work(struct qla_tgt *tgt,
goto out_term;
spin_unlock_irqrestore(&ha->hardware_lock, flags);
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
return;
@@ -5935,8 +5943,7 @@ out_term:
qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false);
spin_unlock_irqrestore(&ha->hardware_lock, flags);
- if (sess)
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
}
@@ -5976,7 +5983,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
goto out_term;
}
- kref_get(&sess->se_sess->sess_kref);
+ kref_get(&sess->sess_kref);
}
iocb = a;
@@ -5988,14 +5995,13 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
if (rc != 0)
goto out_term;
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
return;
out_term:
qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
- if (sess)
- ha->tgt.tgt_ops->put_sess(sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index d857feeb6514..f26c5f60eedd 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -738,7 +738,6 @@ struct qla_tgt_func_tmpl {
struct qla_tgt_sess *(*find_sess_by_s_id)(struct scsi_qla_host *,
const uint8_t *);
void (*clear_nacl_from_fcport_map)(struct qla_tgt_sess *);
- void (*put_sess)(struct qla_tgt_sess *);
void (*shutdown_sess)(struct qla_tgt_sess *);
};
@@ -930,6 +929,7 @@ struct qla_tgt_sess {
int generation;
struct se_session *se_sess;
+ struct kref sess_kref;
struct scsi_qla_host *vha;
struct qla_tgt *tgt;
@@ -1101,7 +1101,7 @@ extern int qlt_remove_target(struct qla_hw_data *, struct scsi_qla_host *);
extern int qlt_lport_register(void *, u64, u64, u64,
int (*callback)(struct scsi_qla_host *, void *, u64, u64));
extern void qlt_lport_deregister(struct scsi_qla_host *);
-extern void qlt_unreg_sess(struct qla_tgt_sess *);
+void qlt_put_sess(struct qla_tgt_sess *sess);
extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *);
extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int);
extern int __init qlt_init(void);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index c1461d225f08..6643f6fc7795 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -339,22 +339,6 @@ static void tcm_qla2xxx_release_cmd(struct se_cmd *se_cmd)
qlt_free_cmd(cmd);
}
-static int tcm_qla2xxx_shutdown_session(struct se_session *se_sess)
-{
- struct qla_tgt_sess *sess = se_sess->fabric_sess_ptr;
- struct scsi_qla_host *vha;
- unsigned long flags;
-
- BUG_ON(!sess);
- vha = sess->vha;
-
- spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
- target_sess_cmd_list_set_waiting(se_sess);
- spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
-
- return 1;
-}
-
static void tcm_qla2xxx_close_session(struct se_session *se_sess)
{
struct qla_tgt_sess *sess = se_sess->fabric_sess_ptr;
@@ -365,7 +349,8 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess)
vha = sess->vha;
spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
- qlt_unreg_sess(sess);
+ target_sess_cmd_list_set_waiting(se_sess);
+ qlt_put_sess(sess);
spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
}
@@ -457,6 +442,10 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
struct se_cmd *se_cmd = &cmd->se_cmd;
struct se_session *se_sess;
struct qla_tgt_sess *sess;
+#ifdef CONFIG_TCM_QLA2XXX_DEBUG
+ struct se_portal_group *se_tpg;
+ struct tcm_qla2xxx_tpg *tpg;
+#endif
int flags = TARGET_SCF_ACK_KREF;
if (bidi)
@@ -477,6 +466,15 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
return -EINVAL;
}
+#ifdef CONFIG_TCM_QLA2XXX_DEBUG
+ se_tpg = se_sess->se_tpg;
+ tpg = container_of(se_tpg, struct tcm_qla2xxx_tpg, se_tpg);
+ if (unlikely(tpg->tpg_attrib.jam_host)) {
+ /* return, and dont run target_submit_cmd,discarding command */
+ return 0;
+ }
+#endif
+
cmd->vha->tgt_counters.qla_core_sbt_cmd++;
return target_submit_cmd(se_cmd, se_sess, cdb, &cmd->sense_buffer[0],
cmd->unpacked_lun, data_length, fcp_task_attr,
@@ -758,23 +756,6 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess)
tcm_qla2xxx_clear_sess_lookup(lport, nacl, sess);
}
-static void tcm_qla2xxx_release_session(struct kref *kref)
-{
- struct se_session *se_sess = container_of(kref,
- struct se_session, sess_kref);
-
- qlt_unreg_sess(se_sess->fabric_sess_ptr);
-}
-
-static void tcm_qla2xxx_put_sess(struct qla_tgt_sess *sess)
-{
- if (!sess)
- return;
-
- assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
- kref_put(&sess->se_sess->sess_kref, tcm_qla2xxx_release_session);
-}
-
static void tcm_qla2xxx_shutdown_sess(struct qla_tgt_sess *sess)
{
assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
@@ -844,6 +825,9 @@ DEF_QLA_TPG_ATTRIB(cache_dynamic_acls);
DEF_QLA_TPG_ATTRIB(demo_mode_write_protect);
DEF_QLA_TPG_ATTRIB(prod_mode_write_protect);
DEF_QLA_TPG_ATTRIB(demo_mode_login_only);
+#ifdef CONFIG_TCM_QLA2XXX_DEBUG
+DEF_QLA_TPG_ATTRIB(jam_host);
+#endif
static struct configfs_attribute *tcm_qla2xxx_tpg_attrib_attrs[] = {
&tcm_qla2xxx_tpg_attrib_attr_generate_node_acls,
@@ -851,6 +835,9 @@ static struct configfs_attribute *tcm_qla2xxx_tpg_attrib_attrs[] = {
&tcm_qla2xxx_tpg_attrib_attr_demo_mode_write_protect,
&tcm_qla2xxx_tpg_attrib_attr_prod_mode_write_protect,
&tcm_qla2xxx_tpg_attrib_attr_demo_mode_login_only,
+#ifdef CONFIG_TCM_QLA2XXX_DEBUG
+ &tcm_qla2xxx_tpg_attrib_attr_jam_host,
+#endif
NULL,
};
@@ -1023,6 +1010,7 @@ static struct se_portal_group *tcm_qla2xxx_make_tpg(
tpg->tpg_attrib.demo_mode_write_protect = 1;
tpg->tpg_attrib.cache_dynamic_acls = 1;
tpg->tpg_attrib.demo_mode_login_only = 1;
+ tpg->tpg_attrib.jam_host = 0;
ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);
if (ret < 0) {
@@ -1579,7 +1567,6 @@ static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
.find_sess_by_s_id = tcm_qla2xxx_find_sess_by_s_id,
.find_sess_by_loop_id = tcm_qla2xxx_find_sess_by_loop_id,
.clear_nacl_from_fcport_map = tcm_qla2xxx_clear_nacl_from_fcport_map,
- .put_sess = tcm_qla2xxx_put_sess,
.shutdown_sess = tcm_qla2xxx_shutdown_sess,
};
@@ -1847,7 +1834,6 @@ static const struct target_core_fabric_ops tcm_qla2xxx_ops = {
.tpg_get_inst_index = tcm_qla2xxx_tpg_get_inst_index,
.check_stop_free = tcm_qla2xxx_check_stop_free,
.release_cmd = tcm_qla2xxx_release_cmd,
- .shutdown_session = tcm_qla2xxx_shutdown_session,
.close_session = tcm_qla2xxx_close_session,
.sess_get_index = tcm_qla2xxx_sess_get_index,
.sess_get_initiator_sid = NULL,
@@ -1890,7 +1876,6 @@ static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
.tpg_get_inst_index = tcm_qla2xxx_tpg_get_inst_index,
.check_stop_free = tcm_qla2xxx_check_stop_free,
.release_cmd = tcm_qla2xxx_release_cmd,
- .shutdown_session = tcm_qla2xxx_shutdown_session,
.close_session = tcm_qla2xxx_close_session,
.sess_get_index = tcm_qla2xxx_sess_get_index,
.sess_get_initiator_sid = NULL,
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 3bbf4cb6fd97..37e026a4823d 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -34,6 +34,7 @@ struct tcm_qla2xxx_tpg_attrib {
int prod_mode_write_protect;
int demo_mode_login_only;
int fabric_prot_type;
+ int jam_host;
};
struct tcm_qla2xxx_tpg {
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 3408578b08d6..ff41c310c900 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -230,6 +230,7 @@ static struct {
{"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
{"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC},
{"Promise", "", NULL, BLIST_SPARSELUN},
+ {"QEMU", "QEMU CD-ROM", NULL, BLIST_SKIP_VPD_PAGES},
{"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024},
{"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024},
{"QUANTUM", "XP34301", "1071", BLIST_NOTQ},
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index a8b610eaa0ca..106a6adbd6f1 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1128,7 +1128,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
*/
void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
{
- scmd->device->host->host_failed--;
scmd->eh_eflags = 0;
list_move_tail(&scmd->eh_entry, done_q);
}
@@ -2227,6 +2226,9 @@ int scsi_error_handler(void *data)
else
scsi_unjam_host(shost);
+ /* All scmds have been handled */
+ shost->host_failed = 0;
+
/*
* Note - if the above fails completely, the action is to take
* individual devices offline and flush the queue of any
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b2e332af0f51..c71344aebdbb 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -821,9 +821,12 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
}
/*
- * If we finished all bytes in the request we are done now.
+ * special case: failed zero length commands always need to
+ * drop down into the retry code. Otherwise, if we finished
+ * all bytes in the request we are done now.
*/
- if (!scsi_end_request(req, error, good_bytes, 0))
+ if (!(blk_rq_bytes(req) == 0 && error) &&
+ !scsi_end_request(req, error, good_bytes, 0))
return;
/*
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 428c03ef02b2..60bff78e9ead 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1398,11 +1398,15 @@ static int media_not_present(struct scsi_disk *sdkp,
**/
static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
{
- struct scsi_disk *sdkp = scsi_disk(disk);
- struct scsi_device *sdp = sdkp->device;
+ struct scsi_disk *sdkp = scsi_disk_get(disk);
+ struct scsi_device *sdp;
struct scsi_sense_hdr *sshdr = NULL;
int retval;
+ if (!sdkp)
+ return 0;
+
+ sdp = sdkp->device;
SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n"));
/*
@@ -1459,6 +1463,7 @@ out:
kfree(sshdr);
retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0;
sdp->changed = 0;
+ scsi_disk_put(sdkp);
return retval;
}
@@ -2862,10 +2867,10 @@ static int sd_revalidate_disk(struct gendisk *disk)
if (sdkp->opt_xfer_blocks &&
sdkp->opt_xfer_blocks <= dev_max &&
sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
- sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_SIZE)
- rw_max = q->limits.io_opt =
- sdkp->opt_xfer_blocks * sdp->sector_size;
- else
+ logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) {
+ q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
+ rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
+ } else
rw_max = BLK_DEF_MAX_SECTORS;
/* Combine with controller limits */
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 654630bb7d0e..765a6f1ac1b7 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -151,6 +151,11 @@ static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blo
return blocks << (ilog2(sdev->sector_size) - 9);
}
+static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks)
+{
+ return blocks * sdev->sector_size;
+}
+
/*
* A DIF-capable target device can be formatted with different
* protection schemes. Currently 0 through 3 are defined:
diff --git a/drivers/soc/mediatek/mtk-pmic-wrap.c b/drivers/soc/mediatek/mtk-pmic-wrap.c
index 3c3e56df526e..a003ba26ca6e 100644
--- a/drivers/soc/mediatek/mtk-pmic-wrap.c
+++ b/drivers/soc/mediatek/mtk-pmic-wrap.c
@@ -1059,7 +1059,7 @@ static const struct pmic_wrapper_type pwrap_mt2701 = {
.regs = mt2701_regs,
.type = PWRAP_MT2701,
.arb_en_all = 0x3f,
- .int_en_all = ~(BIT(31) | BIT(2)),
+ .int_en_all = ~(u32)(BIT(31) | BIT(2)),
.spi_w = PWRAP_MAN_CMD_SPI_WRITE_NEW,
.wdt_src = PWRAP_WDT_SRC_MASK_ALL,
.has_bridge = 0,
@@ -1071,7 +1071,7 @@ static struct pmic_wrapper_type pwrap_mt8135 = {
.regs = mt8135_regs,
.type = PWRAP_MT8135,
.arb_en_all = 0x1ff,
- .int_en_all = ~(BIT(31) | BIT(1)),
+ .int_en_all = ~(u32)(BIT(31) | BIT(1)),
.spi_w = PWRAP_MAN_CMD_SPI_WRITE,
.wdt_src = PWRAP_WDT_SRC_MASK_ALL,
.has_bridge = 1,
@@ -1083,7 +1083,7 @@ static struct pmic_wrapper_type pwrap_mt8173 = {
.regs = mt8173_regs,
.type = PWRAP_MT8173,
.arb_en_all = 0x3f,
- .int_en_all = ~(BIT(31) | BIT(1)),
+ .int_en_all = ~(u32)(BIT(31) | BIT(1)),
.spi_w = PWRAP_MAN_CMD_SPI_WRITE,
.wdt_src = PWRAP_WDT_SRC_MASK_NO_STAUPD,
.has_bridge = 0,
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 9d8c84bb1544..4b931ec8d90b 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -410,7 +410,6 @@ config SPI_OMAP_UWIRE
config SPI_OMAP24XX
tristate "McSPI driver for OMAP"
depends on HAS_DMA
- depends on ARM || ARM64 || AVR32 || HEXAGON || MIPS || SUPERH
depends on ARCH_OMAP2PLUS || COMPILE_TEST
help
SPI master controller for OMAP24XX and later Multichannel SPI
@@ -432,10 +431,23 @@ config SPI_OMAP_100K
config SPI_ORION
tristate "Orion SPI master"
- depends on PLAT_ORION || COMPILE_TEST
+ depends on PLAT_ORION || ARCH_MVEBU || COMPILE_TEST
help
This enables using the SPI master controller on the Orion chips.
+config SPI_PIC32
+ tristate "Microchip PIC32 series SPI"
+ depends on MACH_PIC32 || COMPILE_TEST
+ help
+ SPI driver for Microchip PIC32 SPI master controller.
+
+config SPI_PIC32_SQI
+ tristate "Microchip PIC32 Quad SPI driver"
+ depends on MACH_PIC32 || COMPILE_TEST
+ depends on HAS_DMA
+ help
+ SPI driver for PIC32 Quad SPI controller.
+
config SPI_PL022
tristate "ARM AMBA PL022 SSP controller"
depends on ARM_AMBA
@@ -469,7 +481,6 @@ config SPI_PXA2XX_PCI
config SPI_ROCKCHIP
tristate "Rockchip SPI controller driver"
- depends on ARM || ARM64 || AVR32 || HEXAGON || MIPS || SUPERH
help
This selects a driver for Rockchip SPI controller.
@@ -569,7 +580,7 @@ config SPI_SIRF
config SPI_ST_SSC4
tristate "STMicroelectronics SPI SSC-based driver"
- depends on ARCH_STI
+ depends on ARCH_STI || COMPILE_TEST
help
STMicroelectronics SoCs support for SPI. If you say yes to
this option, support will be included for the SSC driven SPI.
@@ -656,7 +667,7 @@ config SPI_XILINX
config SPI_XLP
tristate "Netlogic XLP SPI controller driver"
- depends on CPU_XLP || COMPILE_TEST
+ depends on CPU_XLP || ARCH_VULCAN || COMPILE_TEST
help
Enable support for the SPI controller on the Netlogic XLP SoCs.
Currently supported XLP variants are XLP8XX, XLP3XX, XLP2XX, XLP9XX
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index fbb255c5a608..3c74d003535b 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -62,6 +62,8 @@ obj-$(CONFIG_SPI_OMAP_100K) += spi-omap-100k.o
obj-$(CONFIG_SPI_OMAP24XX) += spi-omap2-mcspi.o
obj-$(CONFIG_SPI_TI_QSPI) += spi-ti-qspi.o
obj-$(CONFIG_SPI_ORION) += spi-orion.o
+obj-$(CONFIG_SPI_PIC32) += spi-pic32.o
+obj-$(CONFIG_SPI_PIC32_SQI) += spi-pic32-sqi.o
obj-$(CONFIG_SPI_PL022) += spi-pl022.o
obj-$(CONFIG_SPI_PPC4xx) += spi-ppc4xx.o
spi-pxa2xx-platform-objs := spi-pxa2xx.o spi-pxa2xx-dma.o
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
index c968ab210a51..2b1456e5e221 100644
--- a/drivers/spi/spi-axi-spi-engine.c
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -525,7 +525,6 @@ static int spi_engine_probe(struct platform_device *pdev)
if (ret)
goto err_ref_clk_disable;
- master->dev.parent = &pdev->dev;
master->dev.of_node = pdev->dev.of_node;
master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_3WIRE;
master->bits_per_word_mask = SPI_BPW_MASK(8);
diff --git a/drivers/spi/spi-bcm53xx.c b/drivers/spi/spi-bcm53xx.c
index cc3f938f0a6b..afb51699dbb5 100644
--- a/drivers/spi/spi-bcm53xx.c
+++ b/drivers/spi/spi-bcm53xx.c
@@ -10,6 +10,7 @@
#include "spi-bcm53xx.h"
#define BCM53XXSPI_MAX_SPI_BAUD 13500000 /* 216 MHz? */
+#define BCM53XXSPI_FLASH_WINDOW SZ_32M
/* The longest observed required wait was 19 ms */
#define BCM53XXSPI_SPE_TIMEOUT_MS 80
@@ -17,8 +18,10 @@
struct bcm53xxspi {
struct bcma_device *core;
struct spi_master *master;
+ void __iomem *mmio_base;
size_t read_offset;
+ bool bspi; /* Boot SPI mode with memory mapping */
};
static inline u32 bcm53xxspi_read(struct bcm53xxspi *b53spi, u16 offset)
@@ -32,6 +35,50 @@ static inline void bcm53xxspi_write(struct bcm53xxspi *b53spi, u16 offset,
bcma_write32(b53spi->core, offset, value);
}
+static void bcm53xxspi_disable_bspi(struct bcm53xxspi *b53spi)
+{
+ struct device *dev = &b53spi->core->dev;
+ unsigned long deadline;
+ u32 tmp;
+
+ if (!b53spi->bspi)
+ return;
+
+ tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL);
+ if (tmp & 0x1)
+ return;
+
+ deadline = jiffies + usecs_to_jiffies(200);
+ do {
+ tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_BUSY_STATUS);
+ if (!(tmp & 0x1)) {
+ bcm53xxspi_write(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL,
+ 0x1);
+ ndelay(200);
+ b53spi->bspi = false;
+ return;
+ }
+ udelay(1);
+ } while (!time_after_eq(jiffies, deadline));
+
+ dev_warn(dev, "Timeout disabling BSPI\n");
+}
+
+static void bcm53xxspi_enable_bspi(struct bcm53xxspi *b53spi)
+{
+ u32 tmp;
+
+ if (b53spi->bspi)
+ return;
+
+ tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL);
+ if (!(tmp & 0x1))
+ return;
+
+ bcm53xxspi_write(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL, 0x0);
+ b53spi->bspi = true;
+}
+
static inline unsigned int bcm53xxspi_calc_timeout(size_t len)
{
/* Do some magic calculation based on length and buad. Add 10% and 1. */
@@ -176,6 +223,8 @@ static int bcm53xxspi_transfer_one(struct spi_master *master,
u8 *buf;
size_t left;
+ bcm53xxspi_disable_bspi(b53spi);
+
if (t->tx_buf) {
buf = (u8 *)t->tx_buf;
left = t->len;
@@ -206,6 +255,22 @@ static int bcm53xxspi_transfer_one(struct spi_master *master,
return 0;
}
+static int bcm53xxspi_flash_read(struct spi_device *spi,
+ struct spi_flash_read_message *msg)
+{
+ struct bcm53xxspi *b53spi = spi_master_get_devdata(spi->master);
+ int ret = 0;
+
+ if (msg->from + msg->len > BCM53XXSPI_FLASH_WINDOW)
+ return -EINVAL;
+
+ bcm53xxspi_enable_bspi(b53spi);
+ memcpy_fromio(msg->buf, b53spi->mmio_base + msg->from, msg->len);
+ msg->retlen = msg->len;
+
+ return ret;
+}
+
/**************************************************
* BCMA
**************************************************/
@@ -222,6 +287,7 @@ MODULE_DEVICE_TABLE(bcma, bcm53xxspi_bcma_tbl);
static int bcm53xxspi_bcma_probe(struct bcma_device *core)
{
+ struct device *dev = &core->dev;
struct bcm53xxspi *b53spi;
struct spi_master *master;
int err;
@@ -231,7 +297,7 @@ static int bcm53xxspi_bcma_probe(struct bcma_device *core)
return -ENOTSUPP;
}
- master = spi_alloc_master(&core->dev, sizeof(*b53spi));
+ master = spi_alloc_master(dev, sizeof(*b53spi));
if (!master)
return -ENOMEM;
@@ -239,11 +305,19 @@ static int bcm53xxspi_bcma_probe(struct bcma_device *core)
b53spi->master = master;
b53spi->core = core;
+ if (core->addr_s[0])
+ b53spi->mmio_base = devm_ioremap(dev, core->addr_s[0],
+ BCM53XXSPI_FLASH_WINDOW);
+ b53spi->bspi = true;
+ bcm53xxspi_disable_bspi(b53spi);
+
master->transfer_one = bcm53xxspi_transfer_one;
+ if (b53spi->mmio_base)
+ master->spi_flash_read = bcm53xxspi_flash_read;
bcma_set_drvdata(core, b53spi);
- err = devm_spi_register_master(&core->dev, master);
+ err = devm_spi_register_master(dev, master);
if (err) {
spi_master_put(master);
bcma_set_drvdata(core, NULL);
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 121a4135b540..1c57ce64abba 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -19,44 +19,46 @@
#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/spi/spi.h>
/* Name of this driver */
#define CDNS_SPI_NAME "cdns-spi"
/* Register offset definitions */
-#define CDNS_SPI_CR_OFFSET 0x00 /* Configuration Register, RW */
-#define CDNS_SPI_ISR_OFFSET 0x04 /* Interrupt Status Register, RO */
-#define CDNS_SPI_IER_OFFSET 0x08 /* Interrupt Enable Register, WO */
-#define CDNS_SPI_IDR_OFFSET 0x0c /* Interrupt Disable Register, WO */
-#define CDNS_SPI_IMR_OFFSET 0x10 /* Interrupt Enabled Mask Register, RO */
-#define CDNS_SPI_ER_OFFSET 0x14 /* Enable/Disable Register, RW */
-#define CDNS_SPI_DR_OFFSET 0x18 /* Delay Register, RW */
-#define CDNS_SPI_TXD_OFFSET 0x1C /* Data Transmit Register, WO */
-#define CDNS_SPI_RXD_OFFSET 0x20 /* Data Receive Register, RO */
-#define CDNS_SPI_SICR_OFFSET 0x24 /* Slave Idle Count Register, RW */
-#define CDNS_SPI_THLD_OFFSET 0x28 /* Transmit FIFO Watermark Register,RW */
-
+#define CDNS_SPI_CR 0x00 /* Configuration Register, RW */
+#define CDNS_SPI_ISR 0x04 /* Interrupt Status Register, RO */
+#define CDNS_SPI_IER 0x08 /* Interrupt Enable Register, WO */
+#define CDNS_SPI_IDR 0x0c /* Interrupt Disable Register, WO */
+#define CDNS_SPI_IMR 0x10 /* Interrupt Enabled Mask Register, RO */
+#define CDNS_SPI_ER 0x14 /* Enable/Disable Register, RW */
+#define CDNS_SPI_DR 0x18 /* Delay Register, RW */
+#define CDNS_SPI_TXD 0x1C /* Data Transmit Register, WO */
+#define CDNS_SPI_RXD 0x20 /* Data Receive Register, RO */
+#define CDNS_SPI_SICR 0x24 /* Slave Idle Count Register, RW */
+#define CDNS_SPI_THLD 0x28 /* Transmit FIFO Watermark Register,RW */
+
+#define SPI_AUTOSUSPEND_TIMEOUT 3000
/*
* SPI Configuration Register bit Masks
*
* This register contains various control bits that affect the operation
* of the SPI controller
*/
-#define CDNS_SPI_CR_MANSTRT_MASK 0x00010000 /* Manual TX Start */
-#define CDNS_SPI_CR_CPHA_MASK 0x00000004 /* Clock Phase Control */
-#define CDNS_SPI_CR_CPOL_MASK 0x00000002 /* Clock Polarity Control */
-#define CDNS_SPI_CR_SSCTRL_MASK 0x00003C00 /* Slave Select Mask */
-#define CDNS_SPI_CR_PERI_SEL_MASK 0x00000200 /* Peripheral Select Decode */
-#define CDNS_SPI_CR_BAUD_DIV_MASK 0x00000038 /* Baud Rate Divisor Mask */
-#define CDNS_SPI_CR_MSTREN_MASK 0x00000001 /* Master Enable Mask */
-#define CDNS_SPI_CR_MANSTRTEN_MASK 0x00008000 /* Manual TX Enable Mask */
-#define CDNS_SPI_CR_SSFORCE_MASK 0x00004000 /* Manual SS Enable Mask */
-#define CDNS_SPI_CR_BAUD_DIV_4_MASK 0x00000008 /* Default Baud Div Mask */
-#define CDNS_SPI_CR_DEFAULT_MASK (CDNS_SPI_CR_MSTREN_MASK | \
- CDNS_SPI_CR_SSCTRL_MASK | \
- CDNS_SPI_CR_SSFORCE_MASK | \
- CDNS_SPI_CR_BAUD_DIV_4_MASK)
+#define CDNS_SPI_CR_MANSTRT 0x00010000 /* Manual TX Start */
+#define CDNS_SPI_CR_CPHA 0x00000004 /* Clock Phase Control */
+#define CDNS_SPI_CR_CPOL 0x00000002 /* Clock Polarity Control */
+#define CDNS_SPI_CR_SSCTRL 0x00003C00 /* Slave Select Mask */
+#define CDNS_SPI_CR_PERI_SEL 0x00000200 /* Peripheral Select Decode */
+#define CDNS_SPI_CR_BAUD_DIV 0x00000038 /* Baud Rate Divisor Mask */
+#define CDNS_SPI_CR_MSTREN 0x00000001 /* Master Enable Mask */
+#define CDNS_SPI_CR_MANSTRTEN 0x00008000 /* Manual TX Enable Mask */
+#define CDNS_SPI_CR_SSFORCE 0x00004000 /* Manual SS Enable Mask */
+#define CDNS_SPI_CR_BAUD_DIV_4 0x00000008 /* Default Baud Div Mask */
+#define CDNS_SPI_CR_DEFAULT (CDNS_SPI_CR_MSTREN | \
+ CDNS_SPI_CR_SSCTRL | \
+ CDNS_SPI_CR_SSFORCE | \
+ CDNS_SPI_CR_BAUD_DIV_4)
/*
* SPI Configuration Register - Baud rate and slave select
@@ -77,21 +79,21 @@
* All the four interrupt registers (Status/Mask/Enable/Disable) have the same
* bit definitions.
*/
-#define CDNS_SPI_IXR_TXOW_MASK 0x00000004 /* SPI TX FIFO Overwater */
-#define CDNS_SPI_IXR_MODF_MASK 0x00000002 /* SPI Mode Fault */
-#define CDNS_SPI_IXR_RXNEMTY_MASK 0x00000010 /* SPI RX FIFO Not Empty */
-#define CDNS_SPI_IXR_DEFAULT_MASK (CDNS_SPI_IXR_TXOW_MASK | \
- CDNS_SPI_IXR_MODF_MASK)
-#define CDNS_SPI_IXR_TXFULL_MASK 0x00000008 /* SPI TX Full */
-#define CDNS_SPI_IXR_ALL_MASK 0x0000007F /* SPI all interrupts */
+#define CDNS_SPI_IXR_TXOW 0x00000004 /* SPI TX FIFO Overwater */
+#define CDNS_SPI_IXR_MODF 0x00000002 /* SPI Mode Fault */
+#define CDNS_SPI_IXR_RXNEMTY 0x00000010 /* SPI RX FIFO Not Empty */
+#define CDNS_SPI_IXR_DEFAULT (CDNS_SPI_IXR_TXOW | \
+ CDNS_SPI_IXR_MODF)
+#define CDNS_SPI_IXR_TXFULL 0x00000008 /* SPI TX Full */
+#define CDNS_SPI_IXR_ALL 0x0000007F /* SPI all interrupts */
/*
* SPI Enable Register bit Masks
*
* This register is used to enable or disable the SPI controller
*/
-#define CDNS_SPI_ER_ENABLE_MASK 0x00000001 /* SPI Enable Bit Mask */
-#define CDNS_SPI_ER_DISABLE_MASK 0x0 /* SPI Disable Bit Mask */
+#define CDNS_SPI_ER_ENABLE 0x00000001 /* SPI Enable Bit Mask */
+#define CDNS_SPI_ER_DISABLE 0x0 /* SPI Disable Bit Mask */
/* SPI FIFO depth in bytes */
#define CDNS_SPI_FIFO_DEPTH 128
@@ -149,56 +151,51 @@ static inline void cdns_spi_write(struct cdns_spi *xspi, u32 offset, u32 val)
*/
static void cdns_spi_init_hw(struct cdns_spi *xspi)
{
- u32 ctrl_reg = CDNS_SPI_CR_DEFAULT_MASK;
+ u32 ctrl_reg = CDNS_SPI_CR_DEFAULT;
if (xspi->is_decoded_cs)
- ctrl_reg |= CDNS_SPI_CR_PERI_SEL_MASK;
+ ctrl_reg |= CDNS_SPI_CR_PERI_SEL;
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_DISABLE_MASK);
- cdns_spi_write(xspi, CDNS_SPI_IDR_OFFSET,
- CDNS_SPI_IXR_ALL_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE);
+ cdns_spi_write(xspi, CDNS_SPI_IDR, CDNS_SPI_IXR_ALL);
/* Clear the RX FIFO */
- while (cdns_spi_read(xspi, CDNS_SPI_ISR_OFFSET) &
- CDNS_SPI_IXR_RXNEMTY_MASK)
- cdns_spi_read(xspi, CDNS_SPI_RXD_OFFSET);
-
- cdns_spi_write(xspi, CDNS_SPI_ISR_OFFSET,
- CDNS_SPI_IXR_ALL_MASK);
- cdns_spi_write(xspi, CDNS_SPI_CR_OFFSET, ctrl_reg);
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_ENABLE_MASK);
+ while (cdns_spi_read(xspi, CDNS_SPI_ISR) & CDNS_SPI_IXR_RXNEMTY)
+ cdns_spi_read(xspi, CDNS_SPI_RXD);
+
+ cdns_spi_write(xspi, CDNS_SPI_ISR, CDNS_SPI_IXR_ALL);
+ cdns_spi_write(xspi, CDNS_SPI_CR, ctrl_reg);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_ENABLE);
}
/**
* cdns_spi_chipselect - Select or deselect the chip select line
* @spi: Pointer to the spi_device structure
- * @is_on: Select(0) or deselect (1) the chip select line
+ * @is_high: Select(0) or deselect (1) the chip select line
*/
static void cdns_spi_chipselect(struct spi_device *spi, bool is_high)
{
struct cdns_spi *xspi = spi_master_get_devdata(spi->master);
u32 ctrl_reg;
- ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR_OFFSET);
+ ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR);
if (is_high) {
/* Deselect the slave */
- ctrl_reg |= CDNS_SPI_CR_SSCTRL_MASK;
+ ctrl_reg |= CDNS_SPI_CR_SSCTRL;
} else {
/* Select the slave */
- ctrl_reg &= ~CDNS_SPI_CR_SSCTRL_MASK;
+ ctrl_reg &= ~CDNS_SPI_CR_SSCTRL;
if (!(xspi->is_decoded_cs))
ctrl_reg |= ((~(CDNS_SPI_SS0 << spi->chip_select)) <<
CDNS_SPI_SS_SHIFT) &
- CDNS_SPI_CR_SSCTRL_MASK;
+ CDNS_SPI_CR_SSCTRL;
else
ctrl_reg |= (spi->chip_select << CDNS_SPI_SS_SHIFT) &
- CDNS_SPI_CR_SSCTRL_MASK;
+ CDNS_SPI_CR_SSCTRL;
}
- cdns_spi_write(xspi, CDNS_SPI_CR_OFFSET, ctrl_reg);
+ cdns_spi_write(xspi, CDNS_SPI_CR, ctrl_reg);
}
/**
@@ -212,14 +209,15 @@ static void cdns_spi_config_clock_mode(struct spi_device *spi)
struct cdns_spi *xspi = spi_master_get_devdata(spi->master);
u32 ctrl_reg, new_ctrl_reg;
- new_ctrl_reg = ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR_OFFSET);
+ new_ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR);
+ ctrl_reg = new_ctrl_reg;
/* Set the SPI clock phase and clock polarity */
- new_ctrl_reg &= ~(CDNS_SPI_CR_CPHA_MASK | CDNS_SPI_CR_CPOL_MASK);
+ new_ctrl_reg &= ~(CDNS_SPI_CR_CPHA | CDNS_SPI_CR_CPOL);
if (spi->mode & SPI_CPHA)
- new_ctrl_reg |= CDNS_SPI_CR_CPHA_MASK;
+ new_ctrl_reg |= CDNS_SPI_CR_CPHA;
if (spi->mode & SPI_CPOL)
- new_ctrl_reg |= CDNS_SPI_CR_CPOL_MASK;
+ new_ctrl_reg |= CDNS_SPI_CR_CPOL;
if (new_ctrl_reg != ctrl_reg) {
/*
@@ -228,11 +226,9 @@ static void cdns_spi_config_clock_mode(struct spi_device *spi)
* polarity as it will cause the SPI slave to see spurious clock
* transitions. To workaround the issue toggle the ER register.
*/
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_DISABLE_MASK);
- cdns_spi_write(xspi, CDNS_SPI_CR_OFFSET, new_ctrl_reg);
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_ENABLE_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE);
+ cdns_spi_write(xspi, CDNS_SPI_CR, new_ctrl_reg);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_ENABLE);
}
}
@@ -251,7 +247,7 @@ static void cdns_spi_config_clock_mode(struct spi_device *spi)
* controller.
*/
static void cdns_spi_config_clock_freq(struct spi_device *spi,
- struct spi_transfer *transfer)
+ struct spi_transfer *transfer)
{
struct cdns_spi *xspi = spi_master_get_devdata(spi->master);
u32 ctrl_reg, baud_rate_val;
@@ -259,7 +255,7 @@ static void cdns_spi_config_clock_freq(struct spi_device *spi,
frequency = clk_get_rate(xspi->ref_clk);
- ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR_OFFSET);
+ ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR);
/* Set the clock frequency */
if (xspi->speed_hz != transfer->speed_hz) {
@@ -269,12 +265,12 @@ static void cdns_spi_config_clock_freq(struct spi_device *spi,
(frequency / (2 << baud_rate_val)) > transfer->speed_hz)
baud_rate_val++;
- ctrl_reg &= ~CDNS_SPI_CR_BAUD_DIV_MASK;
+ ctrl_reg &= ~CDNS_SPI_CR_BAUD_DIV;
ctrl_reg |= baud_rate_val << CDNS_SPI_BAUD_DIV_SHIFT;
xspi->speed_hz = frequency / (2 << baud_rate_val);
}
- cdns_spi_write(xspi, CDNS_SPI_CR_OFFSET, ctrl_reg);
+ cdns_spi_write(xspi, CDNS_SPI_CR, ctrl_reg);
}
/**
@@ -313,10 +309,9 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi)
while ((trans_cnt < CDNS_SPI_FIFO_DEPTH) &&
(xspi->tx_bytes > 0)) {
if (xspi->txbuf)
- cdns_spi_write(xspi, CDNS_SPI_TXD_OFFSET,
- *xspi->txbuf++);
+ cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
else
- cdns_spi_write(xspi, CDNS_SPI_TXD_OFFSET, 0);
+ cdns_spi_write(xspi, CDNS_SPI_TXD, 0);
xspi->tx_bytes--;
trans_cnt++;
@@ -344,19 +339,18 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id)
u32 intr_status, status;
status = IRQ_NONE;
- intr_status = cdns_spi_read(xspi, CDNS_SPI_ISR_OFFSET);
- cdns_spi_write(xspi, CDNS_SPI_ISR_OFFSET, intr_status);
+ intr_status = cdns_spi_read(xspi, CDNS_SPI_ISR);
+ cdns_spi_write(xspi, CDNS_SPI_ISR, intr_status);
- if (intr_status & CDNS_SPI_IXR_MODF_MASK) {
+ if (intr_status & CDNS_SPI_IXR_MODF) {
/* Indicate that transfer is completed, the SPI subsystem will
* identify the error as the remaining bytes to be
* transferred is non-zero
*/
- cdns_spi_write(xspi, CDNS_SPI_IDR_OFFSET,
- CDNS_SPI_IXR_DEFAULT_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_IDR, CDNS_SPI_IXR_DEFAULT);
spi_finalize_current_transfer(master);
status = IRQ_HANDLED;
- } else if (intr_status & CDNS_SPI_IXR_TXOW_MASK) {
+ } else if (intr_status & CDNS_SPI_IXR_TXOW) {
unsigned long trans_cnt;
trans_cnt = xspi->rx_bytes - xspi->tx_bytes;
@@ -365,7 +359,7 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id)
while (trans_cnt) {
u8 data;
- data = cdns_spi_read(xspi, CDNS_SPI_RXD_OFFSET);
+ data = cdns_spi_read(xspi, CDNS_SPI_RXD);
if (xspi->rxbuf)
*xspi->rxbuf++ = data;
@@ -378,8 +372,8 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id)
cdns_spi_fill_tx_fifo(xspi);
} else {
/* Transfer is completed */
- cdns_spi_write(xspi, CDNS_SPI_IDR_OFFSET,
- CDNS_SPI_IXR_DEFAULT_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_IDR,
+ CDNS_SPI_IXR_DEFAULT);
spi_finalize_current_transfer(master);
}
status = IRQ_HANDLED;
@@ -387,6 +381,7 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id)
return status;
}
+
static int cdns_prepare_message(struct spi_master *master,
struct spi_message *msg)
{
@@ -421,8 +416,7 @@ static int cdns_transfer_one(struct spi_master *master,
cdns_spi_fill_tx_fifo(xspi);
- cdns_spi_write(xspi, CDNS_SPI_IER_OFFSET,
- CDNS_SPI_IXR_DEFAULT_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT);
return transfer->len;
}
@@ -439,8 +433,7 @@ static int cdns_prepare_transfer_hardware(struct spi_master *master)
{
struct cdns_spi *xspi = spi_master_get_devdata(master);
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_ENABLE_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_ENABLE);
return 0;
}
@@ -458,8 +451,7 @@ static int cdns_unprepare_transfer_hardware(struct spi_master *master)
{
struct cdns_spi *xspi = spi_master_get_devdata(master);
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_DISABLE_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE);
return 0;
}
@@ -481,7 +473,7 @@ static int cdns_spi_probe(struct platform_device *pdev)
u32 num_cs;
master = spi_alloc_master(&pdev->dev, sizeof(*xspi));
- if (master == NULL)
+ if (!master)
return -ENOMEM;
xspi = spi_master_get_devdata(master);
@@ -521,6 +513,11 @@ static int cdns_spi_probe(struct platform_device *pdev)
goto clk_dis_apb;
}
+ pm_runtime_enable(&pdev->dev);
+ pm_runtime_use_autosuspend(&pdev->dev);
+ pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+ pm_runtime_set_active(&pdev->dev);
+
ret = of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs);
if (ret < 0)
master->num_chipselect = CDNS_SPI_DEFAULT_NUM_CS;
@@ -535,11 +532,14 @@ static int cdns_spi_probe(struct platform_device *pdev)
/* SPI controller initializations */
cdns_spi_init_hw(xspi);
+ pm_runtime_mark_last_busy(&pdev->dev);
+ pm_runtime_put_autosuspend(&pdev->dev);
+
irq = platform_get_irq(pdev, 0);
if (irq <= 0) {
ret = -ENXIO;
dev_err(&pdev->dev, "irq number is invalid\n");
- goto remove_master;
+ goto clk_dis_all;
}
ret = devm_request_irq(&pdev->dev, irq, cdns_spi_irq,
@@ -547,7 +547,7 @@ static int cdns_spi_probe(struct platform_device *pdev)
if (ret != 0) {
ret = -ENXIO;
dev_err(&pdev->dev, "request_irq failed\n");
- goto remove_master;
+ goto clk_dis_all;
}
master->prepare_transfer_hardware = cdns_prepare_transfer_hardware;
@@ -555,6 +555,7 @@ static int cdns_spi_probe(struct platform_device *pdev)
master->transfer_one = cdns_transfer_one;
master->unprepare_transfer_hardware = cdns_unprepare_transfer_hardware;
master->set_cs = cdns_spi_chipselect;
+ master->auto_runtime_pm = true;
master->mode_bits = SPI_CPOL | SPI_CPHA;
/* Set to default valid value */
@@ -572,6 +573,8 @@ static int cdns_spi_probe(struct platform_device *pdev)
return ret;
clk_dis_all:
+ pm_runtime_set_suspended(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
clk_disable_unprepare(xspi->ref_clk);
clk_dis_apb:
clk_disable_unprepare(xspi->pclk);
@@ -595,11 +598,12 @@ static int cdns_spi_remove(struct platform_device *pdev)
struct spi_master *master = platform_get_drvdata(pdev);
struct cdns_spi *xspi = spi_master_get_devdata(master);
- cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
- CDNS_SPI_ER_DISABLE_MASK);
+ cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE);
clk_disable_unprepare(xspi->ref_clk);
clk_disable_unprepare(xspi->pclk);
+ pm_runtime_set_suspended(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
spi_unregister_master(master);
@@ -613,21 +617,14 @@ static int cdns_spi_remove(struct platform_device *pdev)
* This function disables the SPI controller and
* changes the driver state to "suspend"
*
- * Return: Always 0
+ * Return: 0 on success and error value on error
*/
static int __maybe_unused cdns_spi_suspend(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
struct spi_master *master = platform_get_drvdata(pdev);
- struct cdns_spi *xspi = spi_master_get_devdata(master);
-
- spi_master_suspend(master);
-
- clk_disable_unprepare(xspi->ref_clk);
-
- clk_disable_unprepare(xspi->pclk);
- return 0;
+ return spi_master_suspend(master);
}
/**
@@ -642,8 +639,23 @@ static int __maybe_unused cdns_spi_resume(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
struct spi_master *master = platform_get_drvdata(pdev);
+
+ return spi_master_resume(master);
+}
+
+/**
+ * cdns_spi_runtime_resume - Runtime resume method for the SPI driver
+ * @dev: Address of the platform_device structure
+ *
+ * This function enables the clocks
+ *
+ * Return: 0 on success and error value on error
+ */
+static int __maybe_unused cnds_runtime_resume(struct device *dev)
+{
+ struct spi_master *master = dev_get_drvdata(dev);
struct cdns_spi *xspi = spi_master_get_devdata(master);
- int ret = 0;
+ int ret;
ret = clk_prepare_enable(xspi->pclk);
if (ret) {
@@ -657,13 +669,33 @@ static int __maybe_unused cdns_spi_resume(struct device *dev)
clk_disable(xspi->pclk);
return ret;
}
- spi_master_resume(master);
+ return 0;
+}
+
+/**
+ * cdns_spi_runtime_suspend - Runtime suspend method for the SPI driver
+ * @dev: Address of the platform_device structure
+ *
+ * This function disables the clocks
+ *
+ * Return: Always 0
+ */
+static int __maybe_unused cnds_runtime_suspend(struct device *dev)
+{
+ struct spi_master *master = dev_get_drvdata(dev);
+ struct cdns_spi *xspi = spi_master_get_devdata(master);
+
+ clk_disable_unprepare(xspi->ref_clk);
+ clk_disable_unprepare(xspi->pclk);
return 0;
}
-static SIMPLE_DEV_PM_OPS(cdns_spi_dev_pm_ops, cdns_spi_suspend,
- cdns_spi_resume);
+static const struct dev_pm_ops cdns_spi_dev_pm_ops = {
+ SET_RUNTIME_PM_OPS(cnds_runtime_suspend,
+ cnds_runtime_resume, NULL)
+ SET_SYSTEM_SLEEP_PM_OPS(cdns_spi_suspend, cdns_spi_resume)
+};
static const struct of_device_id cdns_spi_of_match[] = {
{ .compatible = "xlnx,zynq-spi-r1p6" },
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index fddb7a3be322..d36c11b73a35 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -23,7 +23,6 @@
#include <linux/clk.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
-#include <linux/edma.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_gpio.h>
@@ -33,8 +32,6 @@
#include <linux/platform_data/spi-davinci.h>
-#define SPI_NO_RESOURCE ((resource_size_t)-1)
-
#define CS_DEFAULT 0xFF
#define SPIFMT_PHASE_MASK BIT(16)
@@ -130,8 +127,6 @@ struct davinci_spi {
struct dma_chan *dma_rx;
struct dma_chan *dma_tx;
- int dma_rx_chnum;
- int dma_tx_chnum;
struct davinci_spi_platform_data pdata;
@@ -797,35 +792,19 @@ static irqreturn_t davinci_spi_irq(s32 irq, void *data)
static int davinci_spi_request_dma(struct davinci_spi *dspi)
{
- dma_cap_mask_t mask;
struct device *sdev = dspi->bitbang.master->dev.parent;
- int r;
-
- dma_cap_zero(mask);
- dma_cap_set(DMA_SLAVE, mask);
- dspi->dma_rx = dma_request_channel(mask, edma_filter_fn,
- &dspi->dma_rx_chnum);
- if (!dspi->dma_rx) {
- dev_err(sdev, "request RX DMA channel failed\n");
- r = -ENODEV;
- goto rx_dma_failed;
- }
+ dspi->dma_rx = dma_request_chan(sdev, "rx");
+ if (IS_ERR(dspi->dma_rx))
+ return PTR_ERR(dspi->dma_rx);
- dspi->dma_tx = dma_request_channel(mask, edma_filter_fn,
- &dspi->dma_tx_chnum);
- if (!dspi->dma_tx) {
- dev_err(sdev, "request TX DMA channel failed\n");
- r = -ENODEV;
- goto tx_dma_failed;
+ dspi->dma_tx = dma_request_chan(sdev, "tx");
+ if (IS_ERR(dspi->dma_tx)) {
+ dma_release_channel(dspi->dma_rx);
+ return PTR_ERR(dspi->dma_tx);
}
return 0;
-
-tx_dma_failed:
- dma_release_channel(dspi->dma_rx);
-rx_dma_failed:
- return r;
}
#if defined(CONFIG_OF)
@@ -936,8 +915,6 @@ static int davinci_spi_probe(struct platform_device *pdev)
struct davinci_spi *dspi;
struct davinci_spi_platform_data *pdata;
struct resource *r;
- resource_size_t dma_rx_chan = SPI_NO_RESOURCE;
- resource_size_t dma_tx_chan = SPI_NO_RESOURCE;
int ret = 0;
u32 spipc0;
@@ -1044,27 +1021,15 @@ static int davinci_spi_probe(struct platform_device *pdev)
}
}
- r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
- if (r)
- dma_rx_chan = r->start;
- r = platform_get_resource(pdev, IORESOURCE_DMA, 1);
- if (r)
- dma_tx_chan = r->start;
-
dspi->bitbang.txrx_bufs = davinci_spi_bufs;
- if (dma_rx_chan != SPI_NO_RESOURCE &&
- dma_tx_chan != SPI_NO_RESOURCE) {
- dspi->dma_rx_chnum = dma_rx_chan;
- dspi->dma_tx_chnum = dma_tx_chan;
-
- ret = davinci_spi_request_dma(dspi);
- if (ret)
- goto free_clk;
-
- dev_info(&pdev->dev, "DMA: supported\n");
- dev_info(&pdev->dev, "DMA: RX channel: %pa, TX channel: %pa, event queue: %d\n",
- &dma_rx_chan, &dma_tx_chan,
- pdata->dma_event_q);
+
+ ret = davinci_spi_request_dma(dspi);
+ if (ret == -EPROBE_DEFER) {
+ goto free_clk;
+ } else if (ret) {
+ dev_info(&pdev->dev, "DMA is not supported (%d)\n", ret);
+ dspi->dma_rx = NULL;
+ dspi->dma_tx = NULL;
}
dspi->get_rx = davinci_spi_rx_buf_u8;
@@ -1102,8 +1067,10 @@ static int davinci_spi_probe(struct platform_device *pdev)
return ret;
free_dma:
- dma_release_channel(dspi->dma_rx);
- dma_release_channel(dspi->dma_tx);
+ if (dspi->dma_rx) {
+ dma_release_channel(dspi->dma_rx);
+ dma_release_channel(dspi->dma_tx);
+ }
free_clk:
clk_disable_unprepare(dspi->clk);
free_master:
@@ -1134,6 +1101,11 @@ static int davinci_spi_remove(struct platform_device *pdev)
clk_disable_unprepare(dspi->clk);
spi_master_put(master);
+ if (dspi->dma_rx) {
+ dma_release_channel(dspi->dma_rx);
+ dma_release_channel(dspi->dma_tx);
+ }
+
return 0;
}
diff --git a/drivers/spi/spi-dln2.c b/drivers/spi/spi-dln2.c
index 3b7d91d94fea..b62a99caacc0 100644
--- a/drivers/spi/spi-dln2.c
+++ b/drivers/spi/spi-dln2.c
@@ -683,6 +683,7 @@ static int dln2_spi_probe(struct platform_device *pdev)
struct spi_master *master;
struct dln2_spi *dln2;
struct dln2_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
int ret;
master = spi_alloc_master(&pdev->dev, sizeof(*dln2));
@@ -700,6 +701,7 @@ static int dln2_spi_probe(struct platform_device *pdev)
}
dln2->master = master;
+ dln2->master->dev.of_node = dev->of_node;
dln2->pdev = pdev;
dln2->port = pdata->port;
/* cs/mode can never be 0xff, so the first transfer will set them */
diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c
index 332ccb0539a7..ef7db75c92c1 100644
--- a/drivers/spi/spi-dw-pci.c
+++ b/drivers/spi/spi-dw-pci.c
@@ -67,7 +67,7 @@ static int spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
dws->irq = pdev->irq;
/*
- * Specific handling for paltforms, like dma setup,
+ * Specific handling for platforms, like dma setup,
* clock rate, FIFO depth.
*/
if (desc) {
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index bb00be8d1851..17a6387e20b5 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -567,7 +567,7 @@ static void ep93xx_spi_dma_transfer(struct ep93xx_spi *espi)
txd = ep93xx_spi_dma_prepare(espi, DMA_MEM_TO_DEV);
if (IS_ERR(txd)) {
ep93xx_spi_dma_finish(espi, DMA_DEV_TO_MEM);
- dev_err(&espi->pdev->dev, "DMA TX failed: %ld\n", PTR_ERR(rxd));
+ dev_err(&espi->pdev->dev, "DMA TX failed: %ld\n", PTR_ERR(txd));
msg->status = PTR_ERR(txd);
return;
}
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index c1a2d747b246..9e9dadb52b3d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -121,18 +121,22 @@ enum dspi_trans_mode {
struct fsl_dspi_devtype_data {
enum dspi_trans_mode trans_mode;
+ u8 max_clock_factor;
};
static const struct fsl_dspi_devtype_data vf610_data = {
.trans_mode = DSPI_EOQ_MODE,
+ .max_clock_factor = 2,
};
static const struct fsl_dspi_devtype_data ls1021a_v1_data = {
.trans_mode = DSPI_TCFQ_MODE,
+ .max_clock_factor = 8,
};
static const struct fsl_dspi_devtype_data ls2085a_data = {
.trans_mode = DSPI_TCFQ_MODE,
+ .max_clock_factor = 8,
};
struct fsl_dspi {
@@ -726,6 +730,9 @@ static int dspi_probe(struct platform_device *pdev)
}
clk_prepare_enable(dspi->clk);
+ master->max_speed_hz =
+ clk_get_rate(dspi->clk) / dspi->devtype_data->max_clock_factor;
+
init_waitqueue_head(&dspi->waitq);
platform_set_drvdata(pdev, master);
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 7cb0c1921495..8d85a3c343da 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -245,7 +245,12 @@ static int fsl_espi_bufs(struct spi_device *spi, struct spi_transfer *t)
if (ret)
return ret;
- wait_for_completion(&mpc8xxx_spi->done);
+ /* Won't hang up forever, SPI bus sometimes got lost interrupts... */
+ ret = wait_for_completion_timeout(&mpc8xxx_spi->done, 2 * HZ);
+ if (ret == 0)
+ dev_err(mpc8xxx_spi->dev,
+ "Transaction hanging up (left %d bytes)\n",
+ mpc8xxx_spi->count);
/* disable rx ints */
mpc8xxx_spi_write_reg(&reg_base->mask, 0);
@@ -539,16 +544,31 @@ void fsl_espi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
if (events & SPIE_NE) {
u32 rx_data, tmp;
u8 rx_data_8;
+ int rx_nr_bytes = 4;
+ int ret;
/* Spin until RX is done */
- while (SPIE_RXCNT(events) < min(4, mspi->len)) {
- cpu_relax();
- events = mpc8xxx_spi_read_reg(&reg_base->event);
+ if (SPIE_RXCNT(events) < min(4, mspi->len)) {
+ ret = spin_event_timeout(
+ !(SPIE_RXCNT(events =
+ mpc8xxx_spi_read_reg(&reg_base->event)) <
+ min(4, mspi->len)),
+ 10000, 0); /* 10 msec */
+ if (!ret)
+ dev_err(mspi->dev,
+ "tired waiting for SPIE_RXCNT\n");
}
if (mspi->len >= 4) {
rx_data = mpc8xxx_spi_read_reg(&reg_base->receive);
+ } else if (mspi->len <= 0) {
+ dev_err(mspi->dev,
+ "unexpected RX(SPIE_NE) interrupt occurred,\n"
+ "(local rxlen %d bytes, reg rxlen %d bytes)\n",
+ min(4, mspi->len), SPIE_RXCNT(events));
+ rx_nr_bytes = 0;
} else {
+ rx_nr_bytes = mspi->len;
tmp = mspi->len;
rx_data = 0;
while (tmp--) {
@@ -559,7 +579,7 @@ void fsl_espi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
rx_data <<= (4 - mspi->len) * 8;
}
- mspi->len -= 4;
+ mspi->len -= rx_nr_bytes;
if (mspi->rx)
mspi->get_rx(rx_data, mspi);
diff --git a/drivers/spi/spi-octeon.c b/drivers/spi/spi-octeon.c
index 07e4ce8273df..3b170093989f 100644
--- a/drivers/spi/spi-octeon.c
+++ b/drivers/spi/spi-octeon.c
@@ -175,6 +175,7 @@ err:
static int octeon_spi_probe(struct platform_device *pdev)
{
struct resource *res_mem;
+ void __iomem *reg_base;
struct spi_master *master;
struct octeon_spi *p;
int err = -ENOENT;
@@ -186,19 +187,13 @@ static int octeon_spi_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, master);
res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
- if (res_mem == NULL) {
- dev_err(&pdev->dev, "found no memory resource\n");
- err = -ENXIO;
- goto fail;
- }
- if (!devm_request_mem_region(&pdev->dev, res_mem->start,
- resource_size(res_mem), res_mem->name)) {
- dev_err(&pdev->dev, "request_mem_region failed\n");
+ reg_base = devm_ioremap_resource(&pdev->dev, res_mem);
+ if (IS_ERR(reg_base)) {
+ err = PTR_ERR(reg_base);
goto fail;
}
- p->register_base = (u64)devm_ioremap(&pdev->dev, res_mem->start,
- resource_size(res_mem));
+
+ p->register_base = (u64)reg_base;
master->num_chipselect = 4;
master->mode_bits = SPI_CPHA |
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 0caa3c8bef46..1d237e93a289 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -23,7 +23,6 @@
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
-#include <linux/omap-dma.h>
#include <linux/pinctrl/consumer.h>
#include <linux/platform_device.h>
#include <linux/err.h>
@@ -103,9 +102,6 @@ struct omap2_mcspi_dma {
struct dma_chan *dma_tx;
struct dma_chan *dma_rx;
- int dma_tx_sync_dev;
- int dma_rx_sync_dev;
-
struct completion dma_tx_completion;
struct completion dma_rx_completion;
@@ -964,8 +960,7 @@ static int omap2_mcspi_request_dma(struct spi_device *spi)
struct spi_master *master = spi->master;
struct omap2_mcspi *mcspi;
struct omap2_mcspi_dma *mcspi_dma;
- dma_cap_mask_t mask;
- unsigned sig;
+ int ret = 0;
mcspi = spi_master_get_devdata(master);
mcspi_dma = mcspi->dma_channels + spi->chip_select;
@@ -973,34 +968,25 @@ static int omap2_mcspi_request_dma(struct spi_device *spi)
init_completion(&mcspi_dma->dma_rx_completion);
init_completion(&mcspi_dma->dma_tx_completion);
- dma_cap_zero(mask);
- dma_cap_set(DMA_SLAVE, mask);
- sig = mcspi_dma->dma_rx_sync_dev;
-
- mcspi_dma->dma_rx =
- dma_request_slave_channel_compat(mask, omap_dma_filter_fn,
- &sig, &master->dev,
- mcspi_dma->dma_rx_ch_name);
- if (!mcspi_dma->dma_rx)
+ mcspi_dma->dma_rx = dma_request_chan(&master->dev,
+ mcspi_dma->dma_rx_ch_name);
+ if (IS_ERR(mcspi_dma->dma_rx)) {
+ ret = PTR_ERR(mcspi_dma->dma_rx);
+ mcspi_dma->dma_rx = NULL;
goto no_dma;
+ }
- sig = mcspi_dma->dma_tx_sync_dev;
- mcspi_dma->dma_tx =
- dma_request_slave_channel_compat(mask, omap_dma_filter_fn,
- &sig, &master->dev,
- mcspi_dma->dma_tx_ch_name);
-
- if (!mcspi_dma->dma_tx) {
+ mcspi_dma->dma_tx = dma_request_chan(&master->dev,
+ mcspi_dma->dma_tx_ch_name);
+ if (IS_ERR(mcspi_dma->dma_tx)) {
+ ret = PTR_ERR(mcspi_dma->dma_tx);
+ mcspi_dma->dma_tx = NULL;
dma_release_channel(mcspi_dma->dma_rx);
mcspi_dma->dma_rx = NULL;
- goto no_dma;
}
- return 0;
-
no_dma:
- dev_warn(&spi->dev, "not using DMA for McSPI\n");
- return -EAGAIN;
+ return ret;
}
static int omap2_mcspi_setup(struct spi_device *spi)
@@ -1039,8 +1025,9 @@ static int omap2_mcspi_setup(struct spi_device *spi)
if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx) {
ret = omap2_mcspi_request_dma(spi);
- if (ret < 0 && ret != -EAGAIN)
- return ret;
+ if (ret)
+ dev_warn(&spi->dev, "not using DMA for McSPI (%d)\n",
+ ret);
}
ret = pm_runtime_get_sync(mcspi->dev);
@@ -1434,42 +1421,8 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
}
for (i = 0; i < master->num_chipselect; i++) {
- char *dma_rx_ch_name = mcspi->dma_channels[i].dma_rx_ch_name;
- char *dma_tx_ch_name = mcspi->dma_channels[i].dma_tx_ch_name;
- struct resource *dma_res;
-
- sprintf(dma_rx_ch_name, "rx%d", i);
- if (!pdev->dev.of_node) {
- dma_res =
- platform_get_resource_byname(pdev,
- IORESOURCE_DMA,
- dma_rx_ch_name);
- if (!dma_res) {
- dev_dbg(&pdev->dev,
- "cannot get DMA RX channel\n");
- status = -ENODEV;
- break;
- }
-
- mcspi->dma_channels[i].dma_rx_sync_dev =
- dma_res->start;
- }
- sprintf(dma_tx_ch_name, "tx%d", i);
- if (!pdev->dev.of_node) {
- dma_res =
- platform_get_resource_byname(pdev,
- IORESOURCE_DMA,
- dma_tx_ch_name);
- if (!dma_res) {
- dev_dbg(&pdev->dev,
- "cannot get DMA TX channel\n");
- status = -ENODEV;
- break;
- }
-
- mcspi->dma_channels[i].dma_tx_sync_dev =
- dma_res->start;
- }
+ sprintf(mcspi->dma_channels[i].dma_rx_ch_name, "rx%d", i);
+ sprintf(mcspi->dma_channels[i].dma_tx_ch_name, "tx%d", i);
}
if (status < 0)
diff --git a/drivers/spi/spi-pic32-sqi.c b/drivers/spi/spi-pic32-sqi.c
new file mode 100644
index 000000000000..ca3c8d94b290
--- /dev/null
+++ b/drivers/spi/spi-pic32-sqi.c
@@ -0,0 +1,727 @@
+/*
+ * PIC32 Quad SPI controller driver.
+ *
+ * Purna Chandra Mandal <purna.mandal@microchip.com>
+ * Copyright (c) 2016, Microchip Technology Inc.
+ *
+ * This program is free software; you can distribute it and/or modify it
+ * under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+
+/* SQI registers */
+#define PESQI_XIP_CONF1_REG 0x00
+#define PESQI_XIP_CONF2_REG 0x04
+#define PESQI_CONF_REG 0x08
+#define PESQI_CTRL_REG 0x0C
+#define PESQI_CLK_CTRL_REG 0x10
+#define PESQI_CMD_THRES_REG 0x14
+#define PESQI_INT_THRES_REG 0x18
+#define PESQI_INT_ENABLE_REG 0x1C
+#define PESQI_INT_STAT_REG 0x20
+#define PESQI_TX_DATA_REG 0x24
+#define PESQI_RX_DATA_REG 0x28
+#define PESQI_STAT1_REG 0x2C
+#define PESQI_STAT2_REG 0x30
+#define PESQI_BD_CTRL_REG 0x34
+#define PESQI_BD_CUR_ADDR_REG 0x38
+#define PESQI_BD_BASE_ADDR_REG 0x40
+#define PESQI_BD_STAT_REG 0x44
+#define PESQI_BD_POLL_CTRL_REG 0x48
+#define PESQI_BD_TX_DMA_STAT_REG 0x4C
+#define PESQI_BD_RX_DMA_STAT_REG 0x50
+#define PESQI_THRES_REG 0x54
+#define PESQI_INT_SIGEN_REG 0x58
+
+/* PESQI_CONF_REG fields */
+#define PESQI_MODE 0x7
+#define PESQI_MODE_BOOT 0
+#define PESQI_MODE_PIO 1
+#define PESQI_MODE_DMA 2
+#define PESQI_MODE_XIP 3
+#define PESQI_MODE_SHIFT 0
+#define PESQI_CPHA BIT(3)
+#define PESQI_CPOL BIT(4)
+#define PESQI_LSBF BIT(5)
+#define PESQI_RXLATCH BIT(7)
+#define PESQI_SERMODE BIT(8)
+#define PESQI_WP_EN BIT(9)
+#define PESQI_HOLD_EN BIT(10)
+#define PESQI_BURST_EN BIT(12)
+#define PESQI_CS_CTRL_HW BIT(15)
+#define PESQI_SOFT_RESET BIT(16)
+#define PESQI_LANES_SHIFT 20
+#define PESQI_SINGLE_LANE 0
+#define PESQI_DUAL_LANE 1
+#define PESQI_QUAD_LANE 2
+#define PESQI_CSEN_SHIFT 24
+#define PESQI_EN BIT(23)
+
+/* PESQI_CLK_CTRL_REG fields */
+#define PESQI_CLK_EN BIT(0)
+#define PESQI_CLK_STABLE BIT(1)
+#define PESQI_CLKDIV_SHIFT 8
+#define PESQI_CLKDIV 0xff
+
+/* PESQI_INT_THR/CMD_THR_REG */
+#define PESQI_TXTHR_MASK 0x1f
+#define PESQI_TXTHR_SHIFT 8
+#define PESQI_RXTHR_MASK 0x1f
+#define PESQI_RXTHR_SHIFT 0
+
+/* PESQI_INT_EN/INT_STAT/INT_SIG_EN_REG */
+#define PESQI_TXEMPTY BIT(0)
+#define PESQI_TXFULL BIT(1)
+#define PESQI_TXTHR BIT(2)
+#define PESQI_RXEMPTY BIT(3)
+#define PESQI_RXFULL BIT(4)
+#define PESQI_RXTHR BIT(5)
+#define PESQI_BDDONE BIT(9) /* BD processing complete */
+#define PESQI_PKTCOMP BIT(10) /* packet processing complete */
+#define PESQI_DMAERR BIT(11) /* error */
+
+/* PESQI_BD_CTRL_REG */
+#define PESQI_DMA_EN BIT(0) /* enable DMA engine */
+#define PESQI_POLL_EN BIT(1) /* enable polling */
+#define PESQI_BDP_START BIT(2) /* start BD processor */
+
+/* PESQI controller buffer descriptor */
+struct buf_desc {
+ u32 bd_ctrl; /* control */
+ u32 bd_status; /* reserved */
+ u32 bd_addr; /* DMA buffer addr */
+ u32 bd_nextp; /* next item in chain */
+};
+
+/* bd_ctrl */
+#define BD_BUFLEN 0x1ff
+#define BD_CBD_INT_EN BIT(16) /* Current BD is processed */
+#define BD_PKT_INT_EN BIT(17) /* All BDs of PKT processed */
+#define BD_LIFM BIT(18) /* last data of pkt */
+#define BD_LAST BIT(19) /* end of list */
+#define BD_DATA_RECV BIT(20) /* receive data */
+#define BD_DDR BIT(21) /* DDR mode */
+#define BD_DUAL BIT(22) /* Dual SPI */
+#define BD_QUAD BIT(23) /* Quad SPI */
+#define BD_LSBF BIT(25) /* LSB First */
+#define BD_STAT_CHECK BIT(27) /* Status poll */
+#define BD_DEVSEL_SHIFT 28 /* CS */
+#define BD_CS_DEASSERT BIT(30) /* de-assert CS after current BD */
+#define BD_EN BIT(31) /* BD owned by H/W */
+
+/**
+ * struct ring_desc - Representation of SQI ring descriptor
+ * @list: list element to add to free or used list.
+ * @bd: PESQI controller buffer descriptor
+ * @bd_dma: DMA address of PESQI controller buffer descriptor
+ * @xfer_len: transfer length
+ */
+struct ring_desc {
+ struct list_head list;
+ struct buf_desc *bd;
+ dma_addr_t bd_dma;
+ u32 xfer_len;
+};
+
+/* Global constants */
+#define PESQI_BD_BUF_LEN_MAX 256
+#define PESQI_BD_COUNT 256 /* max 64KB data per spi message */
+
+struct pic32_sqi {
+ void __iomem *regs;
+ struct clk *sys_clk;
+ struct clk *base_clk; /* drives spi clock */
+ struct spi_master *master;
+ int irq;
+ struct completion xfer_done;
+ struct ring_desc *ring;
+ void *bd;
+ dma_addr_t bd_dma;
+ struct list_head bd_list_free; /* free */
+ struct list_head bd_list_used; /* allocated */
+ struct spi_device *cur_spi;
+ u32 cur_speed;
+ u8 cur_mode;
+};
+
+static inline void pic32_setbits(void __iomem *reg, u32 set)
+{
+ writel(readl(reg) | set, reg);
+}
+
+static inline void pic32_clrbits(void __iomem *reg, u32 clr)
+{
+ writel(readl(reg) & ~clr, reg);
+}
+
+static int pic32_sqi_set_clk_rate(struct pic32_sqi *sqi, u32 sck)
+{
+ u32 val, div;
+
+ /* div = base_clk / (2 * spi_clk) */
+ div = clk_get_rate(sqi->base_clk) / (2 * sck);
+ div &= PESQI_CLKDIV;
+
+ val = readl(sqi->regs + PESQI_CLK_CTRL_REG);
+ /* apply new divider */
+ val &= ~(PESQI_CLK_STABLE | (PESQI_CLKDIV << PESQI_CLKDIV_SHIFT));
+ val |= div << PESQI_CLKDIV_SHIFT;
+ writel(val, sqi->regs + PESQI_CLK_CTRL_REG);
+
+ /* wait for stability */
+ return readl_poll_timeout(sqi->regs + PESQI_CLK_CTRL_REG, val,
+ val & PESQI_CLK_STABLE, 1, 5000);
+}
+
+static inline void pic32_sqi_enable_int(struct pic32_sqi *sqi)
+{
+ u32 mask = PESQI_DMAERR | PESQI_BDDONE | PESQI_PKTCOMP;
+
+ writel(mask, sqi->regs + PESQI_INT_ENABLE_REG);
+ /* INT_SIGEN works as interrupt-gate to INTR line */
+ writel(mask, sqi->regs + PESQI_INT_SIGEN_REG);
+}
+
+static inline void pic32_sqi_disable_int(struct pic32_sqi *sqi)
+{
+ writel(0, sqi->regs + PESQI_INT_ENABLE_REG);
+ writel(0, sqi->regs + PESQI_INT_SIGEN_REG);
+}
+
+static irqreturn_t pic32_sqi_isr(int irq, void *dev_id)
+{
+ struct pic32_sqi *sqi = dev_id;
+ u32 enable, status;
+
+ enable = readl(sqi->regs + PESQI_INT_ENABLE_REG);
+ status = readl(sqi->regs + PESQI_INT_STAT_REG);
+
+ /* check spurious interrupt */
+ if (!status)
+ return IRQ_NONE;
+
+ if (status & PESQI_DMAERR) {
+ enable = 0;
+ goto irq_done;
+ }
+
+ if (status & PESQI_TXTHR)
+ enable &= ~(PESQI_TXTHR | PESQI_TXFULL | PESQI_TXEMPTY);
+
+ if (status & PESQI_RXTHR)
+ enable &= ~(PESQI_RXTHR | PESQI_RXFULL | PESQI_RXEMPTY);
+
+ if (status & PESQI_BDDONE)
+ enable &= ~PESQI_BDDONE;
+
+ /* packet processing completed */
+ if (status & PESQI_PKTCOMP) {
+ /* mask all interrupts */
+ enable = 0;
+ /* complete trasaction */
+ complete(&sqi->xfer_done);
+ }
+
+irq_done:
+ /* interrupts are sticky, so mask when handled */
+ writel(enable, sqi->regs + PESQI_INT_ENABLE_REG);
+
+ return IRQ_HANDLED;
+}
+
+static struct ring_desc *ring_desc_get(struct pic32_sqi *sqi)
+{
+ struct ring_desc *rdesc;
+
+ if (list_empty(&sqi->bd_list_free))
+ return NULL;
+
+ rdesc = list_first_entry(&sqi->bd_list_free, struct ring_desc, list);
+ list_del(&rdesc->list);
+ list_add_tail(&rdesc->list, &sqi->bd_list_used);
+ return rdesc;
+}
+
+static void ring_desc_put(struct pic32_sqi *sqi, struct ring_desc *rdesc)
+{
+ list_del(&rdesc->list);
+ list_add(&rdesc->list, &sqi->bd_list_free);
+}
+
+static int pic32_sqi_one_transfer(struct pic32_sqi *sqi,
+ struct spi_message *mesg,
+ struct spi_transfer *xfer)
+{
+ struct spi_device *spi = mesg->spi;
+ struct scatterlist *sg, *sgl;
+ struct ring_desc *rdesc;
+ struct buf_desc *bd;
+ int nents, i;
+ u32 bd_ctrl;
+ u32 nbits;
+
+ /* Device selection */
+ bd_ctrl = spi->chip_select << BD_DEVSEL_SHIFT;
+
+ /* half-duplex: select transfer buffer, direction and lane */
+ if (xfer->rx_buf) {
+ bd_ctrl |= BD_DATA_RECV;
+ nbits = xfer->rx_nbits;
+ sgl = xfer->rx_sg.sgl;
+ nents = xfer->rx_sg.nents;
+ } else {
+ nbits = xfer->tx_nbits;
+ sgl = xfer->tx_sg.sgl;
+ nents = xfer->tx_sg.nents;
+ }
+
+ if (nbits & SPI_NBITS_QUAD)
+ bd_ctrl |= BD_QUAD;
+ else if (nbits & SPI_NBITS_DUAL)
+ bd_ctrl |= BD_DUAL;
+
+ /* LSB first */
+ if (spi->mode & SPI_LSB_FIRST)
+ bd_ctrl |= BD_LSBF;
+
+ /* ownership to hardware */
+ bd_ctrl |= BD_EN;
+
+ for_each_sg(sgl, sg, nents, i) {
+ /* get ring descriptor */
+ rdesc = ring_desc_get(sqi);
+ if (!rdesc)
+ break;
+
+ bd = rdesc->bd;
+
+ /* BD CTRL: length */
+ rdesc->xfer_len = sg_dma_len(sg);
+ bd->bd_ctrl = bd_ctrl;
+ bd->bd_ctrl |= rdesc->xfer_len;
+
+ /* BD STAT */
+ bd->bd_status = 0;
+
+ /* BD BUFFER ADDRESS */
+ bd->bd_addr = sg->dma_address;
+ }
+
+ return 0;
+}
+
+static int pic32_sqi_prepare_hardware(struct spi_master *master)
+{
+ struct pic32_sqi *sqi = spi_master_get_devdata(master);
+
+ /* enable spi interface */
+ pic32_setbits(sqi->regs + PESQI_CONF_REG, PESQI_EN);
+ /* enable spi clk */
+ pic32_setbits(sqi->regs + PESQI_CLK_CTRL_REG, PESQI_CLK_EN);
+
+ return 0;
+}
+
+static bool pic32_sqi_can_dma(struct spi_master *master,
+ struct spi_device *spi,
+ struct spi_transfer *x)
+{
+ /* Do DMA irrespective of transfer size */
+ return true;
+}
+
+static int pic32_sqi_one_message(struct spi_master *master,
+ struct spi_message *msg)
+{
+ struct spi_device *spi = msg->spi;
+ struct ring_desc *rdesc, *next;
+ struct spi_transfer *xfer;
+ struct pic32_sqi *sqi;
+ int ret = 0, mode;
+ u32 val;
+
+ sqi = spi_master_get_devdata(master);
+
+ reinit_completion(&sqi->xfer_done);
+ msg->actual_length = 0;
+
+ /* We can't handle spi_transfer specific "speed_hz", "bits_per_word"
+ * and "delay_usecs". But spi_device specific speed and mode change
+ * can be handled at best during spi chip-select switch.
+ */
+ if (sqi->cur_spi != spi) {
+ /* set spi speed */
+ if (sqi->cur_speed != spi->max_speed_hz) {
+ sqi->cur_speed = spi->max_speed_hz;
+ ret = pic32_sqi_set_clk_rate(sqi, spi->max_speed_hz);
+ if (ret)
+ dev_warn(&spi->dev, "set_clk, %d\n", ret);
+ }
+
+ /* set spi mode */
+ mode = spi->mode & (SPI_MODE_3 | SPI_LSB_FIRST);
+ if (sqi->cur_mode != mode) {
+ val = readl(sqi->regs + PESQI_CONF_REG);
+ val &= ~(PESQI_CPOL | PESQI_CPHA | PESQI_LSBF);
+ if (mode & SPI_CPOL)
+ val |= PESQI_CPOL;
+ if (mode & SPI_LSB_FIRST)
+ val |= PESQI_LSBF;
+ val |= PESQI_CPHA;
+ writel(val, sqi->regs + PESQI_CONF_REG);
+
+ sqi->cur_mode = mode;
+ }
+ sqi->cur_spi = spi;
+ }
+
+ /* prepare hardware desc-list(BD) for transfer(s) */
+ list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+ ret = pic32_sqi_one_transfer(sqi, msg, xfer);
+ if (ret) {
+ dev_err(&spi->dev, "xfer %p err\n", xfer);
+ goto xfer_out;
+ }
+ }
+
+ /* BDs are prepared and chained. Now mark LAST_BD, CS_DEASSERT at last
+ * element of the list.
+ */
+ rdesc = list_last_entry(&sqi->bd_list_used, struct ring_desc, list);
+ rdesc->bd->bd_ctrl |= BD_LAST | BD_CS_DEASSERT |
+ BD_LIFM | BD_PKT_INT_EN;
+
+ /* set base address BD list for DMA engine */
+ rdesc = list_first_entry(&sqi->bd_list_used, struct ring_desc, list);
+ writel(rdesc->bd_dma, sqi->regs + PESQI_BD_BASE_ADDR_REG);
+
+ /* enable interrupt */
+ pic32_sqi_enable_int(sqi);
+
+ /* enable DMA engine */
+ val = PESQI_DMA_EN | PESQI_POLL_EN | PESQI_BDP_START;
+ writel(val, sqi->regs + PESQI_BD_CTRL_REG);
+
+ /* wait for xfer completion */
+ ret = wait_for_completion_timeout(&sqi->xfer_done, 5 * HZ);
+ if (ret <= 0) {
+ dev_err(&sqi->master->dev, "wait timedout/interrupted\n");
+ ret = -EIO;
+ msg->status = ret;
+ } else {
+ /* success */
+ msg->status = 0;
+ ret = 0;
+ }
+
+ /* disable DMA */
+ writel(0, sqi->regs + PESQI_BD_CTRL_REG);
+
+ pic32_sqi_disable_int(sqi);
+
+xfer_out:
+ list_for_each_entry_safe_reverse(rdesc, next,
+ &sqi->bd_list_used, list) {
+ /* Update total byte transferred */
+ msg->actual_length += rdesc->xfer_len;
+ /* release ring descr */
+ ring_desc_put(sqi, rdesc);
+ }
+ spi_finalize_current_message(spi->master);
+
+ return ret;
+}
+
+static int pic32_sqi_unprepare_hardware(struct spi_master *master)
+{
+ struct pic32_sqi *sqi = spi_master_get_devdata(master);
+
+ /* disable clk */
+ pic32_clrbits(sqi->regs + PESQI_CLK_CTRL_REG, PESQI_CLK_EN);
+ /* disable spi */
+ pic32_clrbits(sqi->regs + PESQI_CONF_REG, PESQI_EN);
+
+ return 0;
+}
+
+static int ring_desc_ring_alloc(struct pic32_sqi *sqi)
+{
+ struct ring_desc *rdesc;
+ struct buf_desc *bd;
+ int i;
+
+ /* allocate coherent DMAable memory for hardware buffer descriptors. */
+ sqi->bd = dma_zalloc_coherent(&sqi->master->dev,
+ sizeof(*bd) * PESQI_BD_COUNT,
+ &sqi->bd_dma, GFP_DMA32);
+ if (!sqi->bd) {
+ dev_err(&sqi->master->dev, "failed allocating dma buffer\n");
+ return -ENOMEM;
+ }
+
+ /* allocate software ring descriptors */
+ sqi->ring = kcalloc(PESQI_BD_COUNT, sizeof(*rdesc), GFP_KERNEL);
+ if (!sqi->ring) {
+ dma_free_coherent(&sqi->master->dev,
+ sizeof(*bd) * PESQI_BD_COUNT,
+ sqi->bd, sqi->bd_dma);
+ return -ENOMEM;
+ }
+
+ bd = (struct buf_desc *)sqi->bd;
+
+ INIT_LIST_HEAD(&sqi->bd_list_free);
+ INIT_LIST_HEAD(&sqi->bd_list_used);
+
+ /* initialize ring-desc */
+ for (i = 0, rdesc = sqi->ring; i < PESQI_BD_COUNT; i++, rdesc++) {
+ INIT_LIST_HEAD(&rdesc->list);
+ rdesc->bd = &bd[i];
+ rdesc->bd_dma = sqi->bd_dma + (void *)&bd[i] - (void *)bd;
+ list_add_tail(&rdesc->list, &sqi->bd_list_free);
+ }
+
+ /* Prepare BD: chain to next BD(s) */
+ for (i = 0, rdesc = sqi->ring; i < PESQI_BD_COUNT - 1; i++)
+ bd[i].bd_nextp = rdesc[i + 1].bd_dma;
+ bd[PESQI_BD_COUNT - 1].bd_nextp = 0;
+
+ return 0;
+}
+
+static void ring_desc_ring_free(struct pic32_sqi *sqi)
+{
+ dma_free_coherent(&sqi->master->dev,
+ sizeof(struct buf_desc) * PESQI_BD_COUNT,
+ sqi->bd, sqi->bd_dma);
+ kfree(sqi->ring);
+}
+
+static void pic32_sqi_hw_init(struct pic32_sqi *sqi)
+{
+ unsigned long flags;
+ u32 val;
+
+ /* Soft-reset of PESQI controller triggers interrupt.
+ * We are not yet ready to handle them so disable CPU
+ * interrupt for the time being.
+ */
+ local_irq_save(flags);
+
+ /* assert soft-reset */
+ writel(PESQI_SOFT_RESET, sqi->regs + PESQI_CONF_REG);
+
+ /* wait until clear */
+ readl_poll_timeout_atomic(sqi->regs + PESQI_CONF_REG, val,
+ !(val & PESQI_SOFT_RESET), 1, 5000);
+
+ /* disable all interrupts */
+ pic32_sqi_disable_int(sqi);
+
+ /* Now it is safe to enable back CPU interrupt */
+ local_irq_restore(flags);
+
+ /* tx and rx fifo interrupt threshold */
+ val = readl(sqi->regs + PESQI_CMD_THRES_REG);
+ val &= ~(PESQI_TXTHR_MASK << PESQI_TXTHR_SHIFT);
+ val &= ~(PESQI_RXTHR_MASK << PESQI_RXTHR_SHIFT);
+ val |= (1U << PESQI_TXTHR_SHIFT) | (1U << PESQI_RXTHR_SHIFT);
+ writel(val, sqi->regs + PESQI_CMD_THRES_REG);
+
+ val = readl(sqi->regs + PESQI_INT_THRES_REG);
+ val &= ~(PESQI_TXTHR_MASK << PESQI_TXTHR_SHIFT);
+ val &= ~(PESQI_RXTHR_MASK << PESQI_RXTHR_SHIFT);
+ val |= (1U << PESQI_TXTHR_SHIFT) | (1U << PESQI_RXTHR_SHIFT);
+ writel(val, sqi->regs + PESQI_INT_THRES_REG);
+
+ /* default configuration */
+ val = readl(sqi->regs + PESQI_CONF_REG);
+
+ /* set mode: DMA */
+ val &= ~PESQI_MODE;
+ val |= PESQI_MODE_DMA << PESQI_MODE_SHIFT;
+ writel(val, sqi->regs + PESQI_CONF_REG);
+
+ /* DATAEN - SQIID0-ID3 */
+ val |= PESQI_QUAD_LANE << PESQI_LANES_SHIFT;
+
+ /* burst/INCR4 enable */
+ val |= PESQI_BURST_EN;
+
+ /* CSEN - all CS */
+ val |= 3U << PESQI_CSEN_SHIFT;
+ writel(val, sqi->regs + PESQI_CONF_REG);
+
+ /* write poll count */
+ writel(0, sqi->regs + PESQI_BD_POLL_CTRL_REG);
+
+ sqi->cur_speed = 0;
+ sqi->cur_mode = -1;
+}
+
+static int pic32_sqi_probe(struct platform_device *pdev)
+{
+ struct spi_master *master;
+ struct pic32_sqi *sqi;
+ struct resource *reg;
+ int ret;
+
+ master = spi_alloc_master(&pdev->dev, sizeof(*sqi));
+ if (!master)
+ return -ENOMEM;
+
+ sqi = spi_master_get_devdata(master);
+ sqi->master = master;
+
+ reg = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ sqi->regs = devm_ioremap_resource(&pdev->dev, reg);
+ if (IS_ERR(sqi->regs)) {
+ ret = PTR_ERR(sqi->regs);
+ goto err_free_master;
+ }
+
+ /* irq */
+ sqi->irq = platform_get_irq(pdev, 0);
+ if (sqi->irq < 0) {
+ dev_err(&pdev->dev, "no irq found\n");
+ ret = sqi->irq;
+ goto err_free_master;
+ }
+
+ /* clocks */
+ sqi->sys_clk = devm_clk_get(&pdev->dev, "reg_ck");
+ if (IS_ERR(sqi->sys_clk)) {
+ ret = PTR_ERR(sqi->sys_clk);
+ dev_err(&pdev->dev, "no sys_clk ?\n");
+ goto err_free_master;
+ }
+
+ sqi->base_clk = devm_clk_get(&pdev->dev, "spi_ck");
+ if (IS_ERR(sqi->base_clk)) {
+ ret = PTR_ERR(sqi->base_clk);
+ dev_err(&pdev->dev, "no base clk ?\n");
+ goto err_free_master;
+ }
+
+ ret = clk_prepare_enable(sqi->sys_clk);
+ if (ret) {
+ dev_err(&pdev->dev, "sys clk enable failed\n");
+ goto err_free_master;
+ }
+
+ ret = clk_prepare_enable(sqi->base_clk);
+ if (ret) {
+ dev_err(&pdev->dev, "base clk enable failed\n");
+ clk_disable_unprepare(sqi->sys_clk);
+ goto err_free_master;
+ }
+
+ init_completion(&sqi->xfer_done);
+
+ /* initialize hardware */
+ pic32_sqi_hw_init(sqi);
+
+ /* allocate buffers & descriptors */
+ ret = ring_desc_ring_alloc(sqi);
+ if (ret) {
+ dev_err(&pdev->dev, "ring alloc failed\n");
+ goto err_disable_clk;
+ }
+
+ /* install irq handlers */
+ ret = request_irq(sqi->irq, pic32_sqi_isr, 0,
+ dev_name(&pdev->dev), sqi);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "request_irq(%d), failed\n", sqi->irq);
+ goto err_free_ring;
+ }
+
+ /* register master */
+ master->num_chipselect = 2;
+ master->max_speed_hz = clk_get_rate(sqi->base_clk);
+ master->dma_alignment = 32;
+ master->max_dma_len = PESQI_BD_BUF_LEN_MAX;
+ master->dev.of_node = of_node_get(pdev->dev.of_node);
+ master->mode_bits = SPI_MODE_3 | SPI_MODE_0 | SPI_TX_DUAL |
+ SPI_RX_DUAL | SPI_TX_QUAD | SPI_RX_QUAD;
+ master->flags = SPI_MASTER_HALF_DUPLEX;
+ master->can_dma = pic32_sqi_can_dma;
+ master->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
+ master->transfer_one_message = pic32_sqi_one_message;
+ master->prepare_transfer_hardware = pic32_sqi_prepare_hardware;
+ master->unprepare_transfer_hardware = pic32_sqi_unprepare_hardware;
+
+ ret = devm_spi_register_master(&pdev->dev, master);
+ if (ret) {
+ dev_err(&master->dev, "failed registering spi master\n");
+ free_irq(sqi->irq, sqi);
+ goto err_free_ring;
+ }
+
+ platform_set_drvdata(pdev, sqi);
+
+ return 0;
+
+err_free_ring:
+ ring_desc_ring_free(sqi);
+
+err_disable_clk:
+ clk_disable_unprepare(sqi->base_clk);
+ clk_disable_unprepare(sqi->sys_clk);
+
+err_free_master:
+ spi_master_put(master);
+ return ret;
+}
+
+static int pic32_sqi_remove(struct platform_device *pdev)
+{
+ struct pic32_sqi *sqi = platform_get_drvdata(pdev);
+
+ /* release resources */
+ free_irq(sqi->irq, sqi);
+ ring_desc_ring_free(sqi);
+
+ /* disable clk */
+ clk_disable_unprepare(sqi->base_clk);
+ clk_disable_unprepare(sqi->sys_clk);
+
+ return 0;
+}
+
+static const struct of_device_id pic32_sqi_of_ids[] = {
+ {.compatible = "microchip,pic32mzda-sqi",},
+ {},
+};
+MODULE_DEVICE_TABLE(of, pic32_sqi_of_ids);
+
+static struct platform_driver pic32_sqi_driver = {
+ .driver = {
+ .name = "sqi-pic32",
+ .of_match_table = of_match_ptr(pic32_sqi_of_ids),
+ },
+ .probe = pic32_sqi_probe,
+ .remove = pic32_sqi_remove,
+};
+
+module_platform_driver(pic32_sqi_driver);
+
+MODULE_AUTHOR("Purna Chandra Mandal <purna.mandal@microchip.com>");
+MODULE_DESCRIPTION("Microchip SPI driver for PIC32 SQI controller.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-pic32.c b/drivers/spi/spi-pic32.c
new file mode 100644
index 000000000000..73db87f805a1
--- /dev/null
+++ b/drivers/spi/spi-pic32.c
@@ -0,0 +1,878 @@
+/*
+ * Microchip PIC32 SPI controller driver.
+ *
+ * Purna Chandra Mandal <purna.mandal@microchip.com>
+ * Copyright (c) 2016, Microchip Technology Inc.
+ *
+ * This program is free software; you can distribute it and/or modify it
+ * under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_gpio.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+/* SPI controller registers */
+struct pic32_spi_regs {
+ u32 ctrl;
+ u32 ctrl_clr;
+ u32 ctrl_set;
+ u32 ctrl_inv;
+ u32 status;
+ u32 status_clr;
+ u32 status_set;
+ u32 status_inv;
+ u32 buf;
+ u32 dontuse[3];
+ u32 baud;
+ u32 dontuse2[3];
+ u32 ctrl2;
+ u32 ctrl2_clr;
+ u32 ctrl2_set;
+ u32 ctrl2_inv;
+};
+
+/* Bit fields of SPI Control Register */
+#define CTRL_RX_INT_SHIFT 0 /* Rx interrupt generation */
+#define RX_FIFO_EMTPY 0
+#define RX_FIFO_NOT_EMPTY 1 /* not empty */
+#define RX_FIFO_HALF_FULL 2 /* full by half or more */
+#define RX_FIFO_FULL 3 /* completely full */
+
+#define CTRL_TX_INT_SHIFT 2 /* TX interrupt generation */
+#define TX_FIFO_ALL_EMPTY 0 /* completely empty */
+#define TX_FIFO_EMTPY 1 /* empty */
+#define TX_FIFO_HALF_EMPTY 2 /* empty by half or more */
+#define TX_FIFO_NOT_FULL 3 /* atleast one empty */
+
+#define CTRL_MSTEN BIT(5) /* enable master mode */
+#define CTRL_CKP BIT(6) /* active low */
+#define CTRL_CKE BIT(8) /* Tx on falling edge */
+#define CTRL_SMP BIT(9) /* Rx at middle or end of tx */
+#define CTRL_BPW_MASK 0x03 /* bits per word/sample */
+#define CTRL_BPW_SHIFT 10
+#define PIC32_BPW_8 0
+#define PIC32_BPW_16 1
+#define PIC32_BPW_32 2
+#define CTRL_SIDL BIT(13) /* sleep when idle */
+#define CTRL_ON BIT(15) /* enable macro */
+#define CTRL_ENHBUF BIT(16) /* enable enhanced buffering */
+#define CTRL_MCLKSEL BIT(23) /* select clock source */
+#define CTRL_MSSEN BIT(28) /* macro driven /SS */
+#define CTRL_FRMEN BIT(31) /* enable framing mode */
+
+/* Bit fields of SPI Status Register */
+#define STAT_RF_EMPTY BIT(5) /* RX Fifo empty */
+#define STAT_RX_OV BIT(6) /* err, s/w needs to clear */
+#define STAT_TX_UR BIT(8) /* UR in Framed SPI modes */
+#define STAT_FRM_ERR BIT(12) /* Multiple Frame Sync pulse */
+#define STAT_TF_LVL_MASK 0x1F
+#define STAT_TF_LVL_SHIFT 16
+#define STAT_RF_LVL_MASK 0x1F
+#define STAT_RF_LVL_SHIFT 24
+
+/* Bit fields of SPI Baud Register */
+#define BAUD_MASK 0x1ff
+
+/* Bit fields of SPI Control2 Register */
+#define CTRL2_TX_UR_EN BIT(10) /* Enable int on Tx under-run */
+#define CTRL2_RX_OV_EN BIT(11) /* Enable int on Rx over-run */
+#define CTRL2_FRM_ERR_EN BIT(12) /* Enable frame err int */
+
+/* Minimum DMA transfer size */
+#define PIC32_DMA_LEN_MIN 64
+
+struct pic32_spi {
+ dma_addr_t dma_base;
+ struct pic32_spi_regs __iomem *regs;
+ int fault_irq;
+ int rx_irq;
+ int tx_irq;
+ u32 fifo_n_byte; /* FIFO depth in bytes */
+ struct clk *clk;
+ struct spi_master *master;
+ /* Current controller setting */
+ u32 speed_hz; /* spi-clk rate */
+ u32 mode;
+ u32 bits_per_word;
+ u32 fifo_n_elm; /* FIFO depth in words */
+#define PIC32F_DMA_PREP 0 /* DMA chnls configured */
+ unsigned long flags;
+ /* Current transfer state */
+ struct completion xfer_done;
+ /* PIO transfer specific */
+ const void *tx;
+ const void *tx_end;
+ const void *rx;
+ const void *rx_end;
+ int len;
+ void (*rx_fifo)(struct pic32_spi *);
+ void (*tx_fifo)(struct pic32_spi *);
+};
+
+static inline void pic32_spi_enable(struct pic32_spi *pic32s)
+{
+ writel(CTRL_ON | CTRL_SIDL, &pic32s->regs->ctrl_set);
+}
+
+static inline void pic32_spi_disable(struct pic32_spi *pic32s)
+{
+ writel(CTRL_ON | CTRL_SIDL, &pic32s->regs->ctrl_clr);
+
+ /* avoid SPI registers read/write at immediate next CPU clock */
+ ndelay(20);
+}
+
+static void pic32_spi_set_clk_rate(struct pic32_spi *pic32s, u32 spi_ck)
+{
+ u32 div;
+
+ /* div = (clk_in / 2 * spi_ck) - 1 */
+ div = DIV_ROUND_CLOSEST(clk_get_rate(pic32s->clk), 2 * spi_ck) - 1;
+
+ writel(div & BAUD_MASK, &pic32s->regs->baud);
+}
+
+static inline u32 pic32_rx_fifo_level(struct pic32_spi *pic32s)
+{
+ u32 sr = readl(&pic32s->regs->status);
+
+ return (sr >> STAT_RF_LVL_SHIFT) & STAT_RF_LVL_MASK;
+}
+
+static inline u32 pic32_tx_fifo_level(struct pic32_spi *pic32s)
+{
+ u32 sr = readl(&pic32s->regs->status);
+
+ return (sr >> STAT_TF_LVL_SHIFT) & STAT_TF_LVL_MASK;
+}
+
+/* Return the max entries we can fill into tx fifo */
+static u32 pic32_tx_max(struct pic32_spi *pic32s, int n_bytes)
+{
+ u32 tx_left, tx_room, rxtx_gap;
+
+ tx_left = (pic32s->tx_end - pic32s->tx) / n_bytes;
+ tx_room = pic32s->fifo_n_elm - pic32_tx_fifo_level(pic32s);
+
+ /*
+ * Another concern is about the tx/rx mismatch, we
+ * though to use (pic32s->fifo_n_byte - rxfl - txfl) as
+ * one maximum value for tx, but it doesn't cover the
+ * data which is out of tx/rx fifo and inside the
+ * shift registers. So a ctrl from sw point of
+ * view is taken.
+ */
+ rxtx_gap = ((pic32s->rx_end - pic32s->rx) -
+ (pic32s->tx_end - pic32s->tx)) / n_bytes;
+ return min3(tx_left, tx_room, (u32)(pic32s->fifo_n_elm - rxtx_gap));
+}
+
+/* Return the max entries we should read out of rx fifo */
+static u32 pic32_rx_max(struct pic32_spi *pic32s, int n_bytes)
+{
+ u32 rx_left = (pic32s->rx_end - pic32s->rx) / n_bytes;
+
+ return min_t(u32, rx_left, pic32_rx_fifo_level(pic32s));
+}
+
+#define BUILD_SPI_FIFO_RW(__name, __type, __bwl) \
+static void pic32_spi_rx_##__name(struct pic32_spi *pic32s) \
+{ \
+ __type v; \
+ u32 mx = pic32_rx_max(pic32s, sizeof(__type)); \
+ for (; mx; mx--) { \
+ v = read##__bwl(&pic32s->regs->buf); \
+ if (pic32s->rx_end - pic32s->len) \
+ *(__type *)(pic32s->rx) = v; \
+ pic32s->rx += sizeof(__type); \
+ } \
+} \
+ \
+static void pic32_spi_tx_##__name(struct pic32_spi *pic32s) \
+{ \
+ __type v; \
+ u32 mx = pic32_tx_max(pic32s, sizeof(__type)); \
+ for (; mx ; mx--) { \
+ v = (__type)~0U; \
+ if (pic32s->tx_end - pic32s->len) \
+ v = *(__type *)(pic32s->tx); \
+ write##__bwl(v, &pic32s->regs->buf); \
+ pic32s->tx += sizeof(__type); \
+ } \
+}
+
+BUILD_SPI_FIFO_RW(byte, u8, b);
+BUILD_SPI_FIFO_RW(word, u16, w);
+BUILD_SPI_FIFO_RW(dword, u32, l);
+
+static void pic32_err_stop(struct pic32_spi *pic32s, const char *msg)
+{
+ /* disable all interrupts */
+ disable_irq_nosync(pic32s->fault_irq);
+ disable_irq_nosync(pic32s->rx_irq);
+ disable_irq_nosync(pic32s->tx_irq);
+
+ /* Show err message and abort xfer with err */
+ dev_err(&pic32s->master->dev, "%s\n", msg);
+ if (pic32s->master->cur_msg)
+ pic32s->master->cur_msg->status = -EIO;
+ complete(&pic32s->xfer_done);
+}
+
+static irqreturn_t pic32_spi_fault_irq(int irq, void *dev_id)
+{
+ struct pic32_spi *pic32s = dev_id;
+ u32 status;
+
+ status = readl(&pic32s->regs->status);
+
+ /* Error handling */
+ if (status & (STAT_RX_OV | STAT_TX_UR)) {
+ writel(STAT_RX_OV, &pic32s->regs->status_clr);
+ writel(STAT_TX_UR, &pic32s->regs->status_clr);
+ pic32_err_stop(pic32s, "err_irq: fifo ov/ur-run\n");
+ return IRQ_HANDLED;
+ }
+
+ if (status & STAT_FRM_ERR) {
+ pic32_err_stop(pic32s, "err_irq: frame error");
+ return IRQ_HANDLED;
+ }
+
+ if (!pic32s->master->cur_msg) {
+ pic32_err_stop(pic32s, "err_irq: no mesg");
+ return IRQ_NONE;
+ }
+
+ return IRQ_NONE;
+}
+
+static irqreturn_t pic32_spi_rx_irq(int irq, void *dev_id)
+{
+ struct pic32_spi *pic32s = dev_id;
+
+ pic32s->rx_fifo(pic32s);
+
+ /* rx complete ? */
+ if (pic32s->rx_end == pic32s->rx) {
+ /* disable all interrupts */
+ disable_irq_nosync(pic32s->fault_irq);
+ disable_irq_nosync(pic32s->rx_irq);
+
+ /* complete current xfer */
+ complete(&pic32s->xfer_done);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t pic32_spi_tx_irq(int irq, void *dev_id)
+{
+ struct pic32_spi *pic32s = dev_id;
+
+ pic32s->tx_fifo(pic32s);
+
+ /* tx complete? disable tx interrupt */
+ if (pic32s->tx_end == pic32s->tx)
+ disable_irq_nosync(pic32s->tx_irq);
+
+ return IRQ_HANDLED;
+}
+
+static void pic32_spi_dma_rx_notify(void *data)
+{
+ struct pic32_spi *pic32s = data;
+
+ complete(&pic32s->xfer_done);
+}
+
+static int pic32_spi_dma_transfer(struct pic32_spi *pic32s,
+ struct spi_transfer *xfer)
+{
+ struct spi_master *master = pic32s->master;
+ struct dma_async_tx_descriptor *desc_rx;
+ struct dma_async_tx_descriptor *desc_tx;
+ dma_cookie_t cookie;
+ int ret;
+
+ if (!master->dma_rx || !master->dma_tx)
+ return -ENODEV;
+
+ desc_rx = dmaengine_prep_slave_sg(master->dma_rx,
+ xfer->rx_sg.sgl,
+ xfer->rx_sg.nents,
+ DMA_FROM_DEVICE,
+ DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+ if (!desc_rx) {
+ ret = -EINVAL;
+ goto err_dma;
+ }
+
+ desc_tx = dmaengine_prep_slave_sg(master->dma_tx,
+ xfer->tx_sg.sgl,
+ xfer->tx_sg.nents,
+ DMA_TO_DEVICE,
+ DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+ if (!desc_tx) {
+ ret = -EINVAL;
+ goto err_dma;
+ }
+
+ /* Put callback on the RX transfer, that should finish last */
+ desc_rx->callback = pic32_spi_dma_rx_notify;
+ desc_rx->callback_param = pic32s;
+
+ cookie = dmaengine_submit(desc_rx);
+ ret = dma_submit_error(cookie);
+ if (ret)
+ goto err_dma;
+
+ cookie = dmaengine_submit(desc_tx);
+ ret = dma_submit_error(cookie);
+ if (ret)
+ goto err_dma_tx;
+
+ dma_async_issue_pending(master->dma_rx);
+ dma_async_issue_pending(master->dma_tx);
+
+ return 0;
+
+err_dma_tx:
+ dmaengine_terminate_all(master->dma_rx);
+err_dma:
+ return ret;
+}
+
+static int pic32_spi_dma_config(struct pic32_spi *pic32s, u32 dma_width)
+{
+ int buf_offset = offsetof(struct pic32_spi_regs, buf);
+ struct spi_master *master = pic32s->master;
+ struct dma_slave_config cfg;
+ int ret;
+
+ cfg.device_fc = true;
+ cfg.src_addr = pic32s->dma_base + buf_offset;
+ cfg.dst_addr = pic32s->dma_base + buf_offset;
+ cfg.src_maxburst = pic32s->fifo_n_elm / 2; /* fill one-half */
+ cfg.dst_maxburst = pic32s->fifo_n_elm / 2; /* drain one-half */
+ cfg.src_addr_width = dma_width;
+ cfg.dst_addr_width = dma_width;
+ /* tx channel */
+ cfg.slave_id = pic32s->tx_irq;
+ cfg.direction = DMA_MEM_TO_DEV;
+ ret = dmaengine_slave_config(master->dma_tx, &cfg);
+ if (ret) {
+ dev_err(&master->dev, "tx channel setup failed\n");
+ return ret;
+ }
+ /* rx channel */
+ cfg.slave_id = pic32s->rx_irq;
+ cfg.direction = DMA_DEV_TO_MEM;
+ ret = dmaengine_slave_config(master->dma_rx, &cfg);
+ if (ret)
+ dev_err(&master->dev, "rx channel setup failed\n");
+
+ return ret;
+}
+
+static int pic32_spi_set_word_size(struct pic32_spi *pic32s, u8 bits_per_word)
+{
+ enum dma_slave_buswidth dmawidth;
+ u32 buswidth, v;
+
+ switch (bits_per_word) {
+ case 8:
+ pic32s->rx_fifo = pic32_spi_rx_byte;
+ pic32s->tx_fifo = pic32_spi_tx_byte;
+ buswidth = PIC32_BPW_8;
+ dmawidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
+ break;
+ case 16:
+ pic32s->rx_fifo = pic32_spi_rx_word;
+ pic32s->tx_fifo = pic32_spi_tx_word;
+ buswidth = PIC32_BPW_16;
+ dmawidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
+ break;
+ case 32:
+ pic32s->rx_fifo = pic32_spi_rx_dword;
+ pic32s->tx_fifo = pic32_spi_tx_dword;
+ buswidth = PIC32_BPW_32;
+ dmawidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
+ break;
+ default:
+ /* not supported */
+ return -EINVAL;
+ }
+
+ /* calculate maximum number of words fifos can hold */
+ pic32s->fifo_n_elm = DIV_ROUND_UP(pic32s->fifo_n_byte,
+ bits_per_word / 8);
+ /* set word size */
+ v = readl(&pic32s->regs->ctrl);
+ v &= ~(CTRL_BPW_MASK << CTRL_BPW_SHIFT);
+ v |= buswidth << CTRL_BPW_SHIFT;
+ writel(v, &pic32s->regs->ctrl);
+
+ /* re-configure dma width, if required */
+ if (test_bit(PIC32F_DMA_PREP, &pic32s->flags))
+ pic32_spi_dma_config(pic32s, dmawidth);
+
+ return 0;
+}
+
+static int pic32_spi_prepare_hardware(struct spi_master *master)
+{
+ struct pic32_spi *pic32s = spi_master_get_devdata(master);
+
+ pic32_spi_enable(pic32s);
+
+ return 0;
+}
+
+static int pic32_spi_prepare_message(struct spi_master *master,
+ struct spi_message *msg)
+{
+ struct pic32_spi *pic32s = spi_master_get_devdata(master);
+ struct spi_device *spi = msg->spi;
+ u32 val;
+
+ /* set device specific bits_per_word */
+ if (pic32s->bits_per_word != spi->bits_per_word) {
+ pic32_spi_set_word_size(pic32s, spi->bits_per_word);
+ pic32s->bits_per_word = spi->bits_per_word;
+ }
+
+ /* device specific speed change */
+ if (pic32s->speed_hz != spi->max_speed_hz) {
+ pic32_spi_set_clk_rate(pic32s, spi->max_speed_hz);
+ pic32s->speed_hz = spi->max_speed_hz;
+ }
+
+ /* device specific mode change */
+ if (pic32s->mode != spi->mode) {
+ val = readl(&pic32s->regs->ctrl);
+ /* active low */
+ if (spi->mode & SPI_CPOL)
+ val |= CTRL_CKP;
+ else
+ val &= ~CTRL_CKP;
+ /* tx on rising edge */
+ if (spi->mode & SPI_CPHA)
+ val &= ~CTRL_CKE;
+ else
+ val |= CTRL_CKE;
+
+ /* rx at end of tx */
+ val |= CTRL_SMP;
+ writel(val, &pic32s->regs->ctrl);
+ pic32s->mode = spi->mode;
+ }
+
+ return 0;
+}
+
+static bool pic32_spi_can_dma(struct spi_master *master,
+ struct spi_device *spi,
+ struct spi_transfer *xfer)
+{
+ struct pic32_spi *pic32s = spi_master_get_devdata(master);
+
+ /* skip using DMA on small size transfer to avoid overhead.*/
+ return (xfer->len >= PIC32_DMA_LEN_MIN) &&
+ test_bit(PIC32F_DMA_PREP, &pic32s->flags);
+}
+
+static int pic32_spi_one_transfer(struct spi_master *master,
+ struct spi_device *spi,
+ struct spi_transfer *transfer)
+{
+ struct pic32_spi *pic32s;
+ bool dma_issued = false;
+ int ret;
+
+ pic32s = spi_master_get_devdata(master);
+
+ /* handle transfer specific word size change */
+ if (transfer->bits_per_word &&
+ (transfer->bits_per_word != pic32s->bits_per_word)) {
+ ret = pic32_spi_set_word_size(pic32s, transfer->bits_per_word);
+ if (ret)
+ return ret;
+ pic32s->bits_per_word = transfer->bits_per_word;
+ }
+
+ /* handle transfer specific speed change */
+ if (transfer->speed_hz && (transfer->speed_hz != pic32s->speed_hz)) {
+ pic32_spi_set_clk_rate(pic32s, transfer->speed_hz);
+ pic32s->speed_hz = transfer->speed_hz;
+ }
+
+ reinit_completion(&pic32s->xfer_done);
+
+ /* transact by DMA mode */
+ if (transfer->rx_sg.nents && transfer->tx_sg.nents) {
+ ret = pic32_spi_dma_transfer(pic32s, transfer);
+ if (ret) {
+ dev_err(&spi->dev, "dma submit error\n");
+ return ret;
+ }
+
+ /* DMA issued */
+ dma_issued = true;
+ } else {
+ /* set current transfer information */
+ pic32s->tx = (const void *)transfer->tx_buf;
+ pic32s->rx = (const void *)transfer->rx_buf;
+ pic32s->tx_end = pic32s->tx + transfer->len;
+ pic32s->rx_end = pic32s->rx + transfer->len;
+ pic32s->len = transfer->len;
+
+ /* transact by interrupt driven PIO */
+ enable_irq(pic32s->fault_irq);
+ enable_irq(pic32s->rx_irq);
+ enable_irq(pic32s->tx_irq);
+ }
+
+ /* wait for completion */
+ ret = wait_for_completion_timeout(&pic32s->xfer_done, 2 * HZ);
+ if (ret <= 0) {
+ dev_err(&spi->dev, "wait error/timedout\n");
+ if (dma_issued) {
+ dmaengine_terminate_all(master->dma_rx);
+ dmaengine_terminate_all(master->dma_rx);
+ }
+ ret = -ETIMEDOUT;
+ } else {
+ ret = 0;
+ }
+
+ return ret;
+}
+
+static int pic32_spi_unprepare_message(struct spi_master *master,
+ struct spi_message *msg)
+{
+ /* nothing to do */
+ return 0;
+}
+
+static int pic32_spi_unprepare_hardware(struct spi_master *master)
+{
+ struct pic32_spi *pic32s = spi_master_get_devdata(master);
+
+ pic32_spi_disable(pic32s);
+
+ return 0;
+}
+
+/* This may be called multiple times by same spi dev */
+static int pic32_spi_setup(struct spi_device *spi)
+{
+ if (!spi->max_speed_hz) {
+ dev_err(&spi->dev, "No max speed HZ parameter\n");
+ return -EINVAL;
+ }
+
+ /* PIC32 spi controller can drive /CS during transfer depending
+ * on tx fifo fill-level. /CS will stay asserted as long as TX
+ * fifo is non-empty, else will be deasserted indicating
+ * completion of the ongoing transfer. This might result into
+ * unreliable/erroneous SPI transactions.
+ * To avoid that we will always handle /CS by toggling GPIO.
+ */
+ if (!gpio_is_valid(spi->cs_gpio))
+ return -EINVAL;
+
+ gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
+
+ return 0;
+}
+
+static void pic32_spi_cleanup(struct spi_device *spi)
+{
+ /* de-activate cs-gpio */
+ gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
+}
+
+static void pic32_spi_dma_prep(struct pic32_spi *pic32s, struct device *dev)
+{
+ struct spi_master *master = pic32s->master;
+ dma_cap_mask_t mask;
+
+ dma_cap_zero(mask);
+ dma_cap_set(DMA_SLAVE, mask);
+
+ master->dma_rx = dma_request_slave_channel_compat(mask, NULL, NULL,
+ dev, "spi-rx");
+ if (!master->dma_rx) {
+ dev_warn(dev, "RX channel not found.\n");
+ goto out_err;
+ }
+
+ master->dma_tx = dma_request_slave_channel_compat(mask, NULL, NULL,
+ dev, "spi-tx");
+ if (!master->dma_tx) {
+ dev_warn(dev, "TX channel not found.\n");
+ goto out_err;
+ }
+
+ if (pic32_spi_dma_config(pic32s, DMA_SLAVE_BUSWIDTH_1_BYTE))
+ goto out_err;
+
+ /* DMA chnls allocated and prepared */
+ set_bit(PIC32F_DMA_PREP, &pic32s->flags);
+
+ return;
+
+out_err:
+ if (master->dma_rx)
+ dma_release_channel(master->dma_rx);
+
+ if (master->dma_tx)
+ dma_release_channel(master->dma_tx);
+}
+
+static void pic32_spi_dma_unprep(struct pic32_spi *pic32s)
+{
+ if (!test_bit(PIC32F_DMA_PREP, &pic32s->flags))
+ return;
+
+ clear_bit(PIC32F_DMA_PREP, &pic32s->flags);
+ if (pic32s->master->dma_rx)
+ dma_release_channel(pic32s->master->dma_rx);
+
+ if (pic32s->master->dma_tx)
+ dma_release_channel(pic32s->master->dma_tx);
+}
+
+static void pic32_spi_hw_init(struct pic32_spi *pic32s)
+{
+ u32 ctrl;
+
+ /* disable hardware */
+ pic32_spi_disable(pic32s);
+
+ ctrl = readl(&pic32s->regs->ctrl);
+ /* enable enhanced fifo of 128bit deep */
+ ctrl |= CTRL_ENHBUF;
+ pic32s->fifo_n_byte = 16;
+
+ /* disable framing mode */
+ ctrl &= ~CTRL_FRMEN;
+
+ /* enable master mode while disabled */
+ ctrl |= CTRL_MSTEN;
+
+ /* set tx fifo threshold interrupt */
+ ctrl &= ~(0x3 << CTRL_TX_INT_SHIFT);
+ ctrl |= (TX_FIFO_HALF_EMPTY << CTRL_TX_INT_SHIFT);
+
+ /* set rx fifo threshold interrupt */
+ ctrl &= ~(0x3 << CTRL_RX_INT_SHIFT);
+ ctrl |= (RX_FIFO_NOT_EMPTY << CTRL_RX_INT_SHIFT);
+
+ /* select clk source */
+ ctrl &= ~CTRL_MCLKSEL;
+
+ /* set manual /CS mode */
+ ctrl &= ~CTRL_MSSEN;
+
+ writel(ctrl, &pic32s->regs->ctrl);
+
+ /* enable error reporting */
+ ctrl = CTRL2_TX_UR_EN | CTRL2_RX_OV_EN | CTRL2_FRM_ERR_EN;
+ writel(ctrl, &pic32s->regs->ctrl2_set);
+}
+
+static int pic32_spi_hw_probe(struct platform_device *pdev,
+ struct pic32_spi *pic32s)
+{
+ struct resource *mem;
+ int ret;
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pic32s->regs = devm_ioremap_resource(&pdev->dev, mem);
+ if (IS_ERR(pic32s->regs))
+ return PTR_ERR(pic32s->regs);
+
+ pic32s->dma_base = mem->start;
+
+ /* get irq resources: err-irq, rx-irq, tx-irq */
+ pic32s->fault_irq = platform_get_irq_byname(pdev, "fault");
+ if (pic32s->fault_irq < 0) {
+ dev_err(&pdev->dev, "fault-irq not found\n");
+ return pic32s->fault_irq;
+ }
+
+ pic32s->rx_irq = platform_get_irq_byname(pdev, "rx");
+ if (pic32s->rx_irq < 0) {
+ dev_err(&pdev->dev, "rx-irq not found\n");
+ return pic32s->rx_irq;
+ }
+
+ pic32s->tx_irq = platform_get_irq_byname(pdev, "tx");
+ if (pic32s->tx_irq < 0) {
+ dev_err(&pdev->dev, "tx-irq not found\n");
+ return pic32s->tx_irq;
+ }
+
+ /* get clock */
+ pic32s->clk = devm_clk_get(&pdev->dev, "mck0");
+ if (IS_ERR(pic32s->clk)) {
+ dev_err(&pdev->dev, "clk not found\n");
+ ret = PTR_ERR(pic32s->clk);
+ goto err_unmap_mem;
+ }
+
+ ret = clk_prepare_enable(pic32s->clk);
+ if (ret)
+ goto err_unmap_mem;
+
+ pic32_spi_hw_init(pic32s);
+
+ return 0;
+
+err_unmap_mem:
+ dev_err(&pdev->dev, "%s failed, err %d\n", __func__, ret);
+ return ret;
+}
+
+static int pic32_spi_probe(struct platform_device *pdev)
+{
+ struct spi_master *master;
+ struct pic32_spi *pic32s;
+ int ret;
+
+ master = spi_alloc_master(&pdev->dev, sizeof(*pic32s));
+ if (!master)
+ return -ENOMEM;
+
+ pic32s = spi_master_get_devdata(master);
+ pic32s->master = master;
+
+ ret = pic32_spi_hw_probe(pdev, pic32s);
+ if (ret)
+ goto err_master;
+
+ master->dev.of_node = of_node_get(pdev->dev.of_node);
+ master->mode_bits = SPI_MODE_3 | SPI_MODE_0 | SPI_CS_HIGH;
+ master->num_chipselect = 1; /* single chip-select */
+ master->max_speed_hz = clk_get_rate(pic32s->clk);
+ master->setup = pic32_spi_setup;
+ master->cleanup = pic32_spi_cleanup;
+ master->flags = SPI_MASTER_MUST_TX | SPI_MASTER_MUST_RX;
+ master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16) |
+ SPI_BPW_MASK(32);
+ master->transfer_one = pic32_spi_one_transfer;
+ master->prepare_message = pic32_spi_prepare_message;
+ master->unprepare_message = pic32_spi_unprepare_message;
+ master->prepare_transfer_hardware = pic32_spi_prepare_hardware;
+ master->unprepare_transfer_hardware = pic32_spi_unprepare_hardware;
+
+ /* optional DMA support */
+ pic32_spi_dma_prep(pic32s, &pdev->dev);
+ if (test_bit(PIC32F_DMA_PREP, &pic32s->flags))
+ master->can_dma = pic32_spi_can_dma;
+
+ init_completion(&pic32s->xfer_done);
+ pic32s->mode = -1;
+
+ /* install irq handlers (with irq-disabled) */
+ irq_set_status_flags(pic32s->fault_irq, IRQ_NOAUTOEN);
+ ret = devm_request_irq(&pdev->dev, pic32s->fault_irq,
+ pic32_spi_fault_irq, IRQF_NO_THREAD,
+ dev_name(&pdev->dev), pic32s);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "request fault-irq %d\n", pic32s->rx_irq);
+ goto err_bailout;
+ }
+
+ /* receive interrupt handler */
+ irq_set_status_flags(pic32s->rx_irq, IRQ_NOAUTOEN);
+ ret = devm_request_irq(&pdev->dev, pic32s->rx_irq,
+ pic32_spi_rx_irq, IRQF_NO_THREAD,
+ dev_name(&pdev->dev), pic32s);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "request rx-irq %d\n", pic32s->rx_irq);
+ goto err_bailout;
+ }
+
+ /* transmit interrupt handler */
+ irq_set_status_flags(pic32s->tx_irq, IRQ_NOAUTOEN);
+ ret = devm_request_irq(&pdev->dev, pic32s->tx_irq,
+ pic32_spi_tx_irq, IRQF_NO_THREAD,
+ dev_name(&pdev->dev), pic32s);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "request tx-irq %d\n", pic32s->tx_irq);
+ goto err_bailout;
+ }
+
+ /* register master */
+ ret = devm_spi_register_master(&pdev->dev, master);
+ if (ret) {
+ dev_err(&master->dev, "failed registering spi master\n");
+ goto err_bailout;
+ }
+
+ platform_set_drvdata(pdev, pic32s);
+
+ return 0;
+
+err_bailout:
+ clk_disable_unprepare(pic32s->clk);
+err_master:
+ spi_master_put(master);
+ return ret;
+}
+
+static int pic32_spi_remove(struct platform_device *pdev)
+{
+ struct pic32_spi *pic32s;
+
+ pic32s = platform_get_drvdata(pdev);
+ pic32_spi_disable(pic32s);
+ clk_disable_unprepare(pic32s->clk);
+ pic32_spi_dma_unprep(pic32s);
+
+ return 0;
+}
+
+static const struct of_device_id pic32_spi_of_match[] = {
+ {.compatible = "microchip,pic32mzda-spi",},
+ {},
+};
+MODULE_DEVICE_TABLE(of, pic32_spi_of_match);
+
+static struct platform_driver pic32_spi_driver = {
+ .driver = {
+ .name = "spi-pic32",
+ .of_match_table = of_match_ptr(pic32_spi_of_match),
+ },
+ .probe = pic32_spi_probe,
+ .remove = pic32_spi_remove,
+};
+
+module_platform_driver(pic32_spi_driver);
+
+MODULE_AUTHOR("Purna Chandra Mandal <purna.mandal@microchip.com>");
+MODULE_DESCRIPTION("Microchip SPI driver for PIC32 SPI controller.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index 365fc22c3572..a18a03d0afb7 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -33,12 +33,10 @@ static int pxa2xx_spi_map_dma_buffer(struct driver_data *drv_data,
dmadev = drv_data->tx_chan->device->dev;
sgt = &drv_data->tx_sgt;
buf = drv_data->tx;
- drv_data->tx_map_len = len;
} else {
dmadev = drv_data->rx_chan->device->dev;
sgt = &drv_data->rx_sgt;
buf = drv_data->rx;
- drv_data->rx_map_len = len;
}
nents = DIV_ROUND_UP(len, SZ_2K);
@@ -55,11 +53,7 @@ static int pxa2xx_spi_map_dma_buffer(struct driver_data *drv_data,
for_each_sg(sgt->sgl, sg, sgt->nents, i) {
size_t bytes = min_t(size_t, len, SZ_2K);
- if (buf)
- sg_set_buf(sg, pbuf, bytes);
- else
- sg_set_buf(sg, drv_data->dummy, bytes);
-
+ sg_set_buf(sg, pbuf, bytes);
pbuf += bytes;
len -= bytes;
}
@@ -133,9 +127,6 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data,
if (!error) {
pxa2xx_spi_unmap_dma_buffers(drv_data);
- drv_data->tx += drv_data->tx_map_len;
- drv_data->rx += drv_data->rx_map_len;
-
msg->actual_length += drv_data->len;
msg->state = pxa2xx_spi_next_transfer(drv_data);
} else {
@@ -267,19 +258,22 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data)
int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst)
{
struct dma_async_tx_descriptor *tx_desc, *rx_desc;
+ int err = 0;
tx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_MEM_TO_DEV);
if (!tx_desc) {
dev_err(&drv_data->pdev->dev,
"failed to get DMA TX descriptor\n");
- return -EBUSY;
+ err = -EBUSY;
+ goto err_tx;
}
rx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_DEV_TO_MEM);
if (!rx_desc) {
dev_err(&drv_data->pdev->dev,
"failed to get DMA RX descriptor\n");
- return -EBUSY;
+ err = -EBUSY;
+ goto err_rx;
}
/* We are ready when RX completes */
@@ -289,6 +283,12 @@ int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst)
dmaengine_submit(rx_desc);
dmaengine_submit(tx_desc);
return 0;
+
+err_rx:
+ dmaengine_terminate_async(drv_data->tx_chan);
+err_tx:
+ pxa2xx_spi_unmap_dma_buffers(drv_data);
+ return err;
}
void pxa2xx_spi_dma_start(struct driver_data *drv_data)
@@ -308,10 +308,6 @@ int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
dma_cap_zero(mask);
dma_cap_set(DMA_SLAVE, mask);
- drv_data->dummy = devm_kzalloc(dev, SZ_2K, GFP_KERNEL);
- if (!drv_data->dummy)
- return -ENOMEM;
-
drv_data->tx_chan = dma_request_slave_channel_compat(mask,
pdata->dma_filter, pdata->tx_param, dev, "tx");
if (!drv_data->tx_chan)
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 4fd7f9802f1b..5202de94f792 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -173,8 +173,8 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
ssp->type = c->type;
snprintf(buf, sizeof(buf), "pxa2xx-spi.%d", ssp->port_id);
- ssp->clk = clk_register_fixed_rate(&dev->dev, buf , NULL,
- CLK_IS_ROOT, c->max_clk_rate);
+ ssp->clk = clk_register_fixed_rate(&dev->dev, buf , NULL, 0,
+ c->max_clk_rate);
if (IS_ERR(ssp->clk))
return PTR_ERR(ssp->clk);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 86138e4101b0..fe07c0592b44 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -570,9 +570,8 @@ static void giveback(struct driver_data *drv_data)
/* see if the next and current messages point
* to the same chip
*/
- if (next_msg && next_msg->spi != msg->spi)
- next_msg = NULL;
- if (!next_msg || msg->state == ERROR_STATE)
+ if ((next_msg && next_msg->spi != msg->spi) ||
+ msg->state == ERROR_STATE)
cs_deassert(drv_data);
}
@@ -928,6 +927,7 @@ static void pump_transfers(unsigned long data)
u32 dma_thresh = drv_data->cur_chip->dma_threshold;
u32 dma_burst = drv_data->cur_chip->dma_burst_size;
u32 change_mask = pxa2xx_spi_get_ssrc1_change_mask(drv_data);
+ int err;
/* Get current state information */
message = drv_data->cur_msg;
@@ -1047,7 +1047,12 @@ static void pump_transfers(unsigned long data)
/* Ensure we have the correct interrupt handler */
drv_data->transfer_handler = pxa2xx_spi_dma_transfer;
- pxa2xx_spi_dma_prepare(drv_data, dma_burst);
+ err = pxa2xx_spi_dma_prepare(drv_data, dma_burst);
+ if (err) {
+ message->status = err;
+ giveback(drv_data);
+ return;
+ }
/* Clear status and start DMA engine */
cr1 = chip->cr1 | dma_thresh | drv_data->dma_cr1;
@@ -1543,7 +1548,6 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
drv_data->pdev = pdev;
drv_data->ssp = ssp;
- master->dev.parent = &pdev->dev;
master->dev.of_node = pdev->dev.of_node;
/* the spi->mode bits understood by this driver: */
master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
@@ -1556,6 +1560,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer;
master->fw_translate_cs = pxa2xx_spi_fw_translate_cs;
master->auto_runtime_pm = true;
+ master->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
drv_data->ssp_type = ssp->type;
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index a1ef88948144..e6b09000ff14 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -56,7 +56,6 @@ struct driver_data {
struct sg_table tx_sgt;
int rx_nents;
int tx_nents;
- void *dummy;
atomic_t dma_running;
/* Current message transfer state info */
@@ -69,8 +68,6 @@ struct driver_data {
void *rx;
void *rx_end;
int dma_mapped;
- size_t rx_map_len;
- size_t tx_map_len;
u8 n_bytes;
int (*write)(struct driver_data *drv_data);
int (*read)(struct driver_data *drv_data);
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index 810a7fae3479..c338ef1136f6 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -937,6 +937,10 @@ static int spi_qup_pm_suspend_runtime(struct device *device)
config = readl(controller->base + QUP_CONFIG);
config |= QUP_CONFIG_CLOCK_AUTO_GATE;
writel_relaxed(config, controller->base + QUP_CONFIG);
+
+ clk_disable_unprepare(controller->cclk);
+ clk_disable_unprepare(controller->iclk);
+
return 0;
}
@@ -945,6 +949,15 @@ static int spi_qup_pm_resume_runtime(struct device *device)
struct spi_master *master = dev_get_drvdata(device);
struct spi_qup *controller = spi_master_get_devdata(master);
u32 config;
+ int ret;
+
+ ret = clk_prepare_enable(controller->iclk);
+ if (ret)
+ return ret;
+
+ ret = clk_prepare_enable(controller->cclk);
+ if (ret)
+ return ret;
/* Disable clocks auto gaiting */
config = readl_relaxed(controller->base + QUP_CONFIG);
@@ -1017,6 +1030,8 @@ static int spi_qup_remove(struct platform_device *pdev)
pm_runtime_put_noidle(&pdev->dev);
pm_runtime_disable(&pdev->dev);
+ spi_master_put(master);
+
return 0;
}
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 6c6c0013ec7a..1026e180eed7 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -578,7 +578,7 @@ static int rockchip_spi_transfer_one(
struct spi_device *spi,
struct spi_transfer *xfer)
{
- int ret = 1;
+ int ret = 0;
struct rockchip_spi *rs = spi_master_get_devdata(master);
WARN_ON(readl_relaxed(rs->regs + ROCKCHIP_SPI_SSIENR) &&
@@ -627,6 +627,8 @@ static int rockchip_spi_transfer_one(
spi_enable_chip(rs, 1);
ret = rockchip_spi_prepare_dma(rs);
}
+ /* successful DMA prepare means the transfer is in progress */
+ ret = ret ? ret : 1;
} else {
spi_enable_chip(rs, 1);
ret = rockchip_spi_pio_transfer(rs);
@@ -744,10 +746,8 @@ static int rockchip_spi_probe(struct platform_device *pdev)
rs->dma_rx.ch = dma_request_chan(rs->dev, "rx");
if (IS_ERR(rs->dma_rx.ch)) {
if (PTR_ERR(rs->dma_rx.ch) == -EPROBE_DEFER) {
- dma_release_channel(rs->dma_tx.ch);
- rs->dma_tx.ch = NULL;
ret = -EPROBE_DEFER;
- goto err_get_fifo_len;
+ goto err_free_dma_tx;
}
dev_warn(rs->dev, "Failed to request RX DMA channel\n");
rs->dma_rx.ch = NULL;
@@ -775,10 +775,11 @@ static int rockchip_spi_probe(struct platform_device *pdev)
err_register_master:
pm_runtime_disable(&pdev->dev);
- if (rs->dma_tx.ch)
- dma_release_channel(rs->dma_tx.ch);
if (rs->dma_rx.ch)
dma_release_channel(rs->dma_rx.ch);
+err_free_dma_tx:
+ if (rs->dma_tx.ch)
+ dma_release_channel(rs->dma_tx.ch);
err_get_fifo_len:
clk_disable_unprepare(rs->spiclk);
err_spiclk_enable:
diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c
index f17c0abe299f..d5adf9f31602 100644
--- a/drivers/spi/spi-st-ssc4.c
+++ b/drivers/spi/spi-st-ssc4.c
@@ -345,12 +345,13 @@ static int spi_st_probe(struct platform_device *pdev)
spi_st->clk = devm_clk_get(&pdev->dev, "ssc");
if (IS_ERR(spi_st->clk)) {
dev_err(&pdev->dev, "Unable to request clock\n");
- return PTR_ERR(spi_st->clk);
+ ret = PTR_ERR(spi_st->clk);
+ goto put_master;
}
ret = spi_st_clk_enable(spi_st);
if (ret)
- return ret;
+ goto put_master;
init_completion(&spi_st->done);
@@ -408,7 +409,8 @@ static int spi_st_probe(struct platform_device *pdev)
clk_disable:
spi_st_clk_disable(spi_st);
-
+put_master:
+ spi_master_put(master);
return ret;
}
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index 1ddd9e2309b6..cf007f3b83ec 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -173,13 +173,17 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
{
struct sun4i_spi *sspi = spi_master_get_devdata(master);
unsigned int mclk_rate, div, timeout;
+ unsigned int start, end, tx_time;
unsigned int tx_len = 0;
int ret = 0;
u32 reg;
/* We don't support transfer larger than the FIFO */
if (tfr->len > SUN4I_FIFO_DEPTH)
- return -EINVAL;
+ return -EMSGSIZE;
+
+ if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH)
+ return -EMSGSIZE;
reinit_completion(&sspi->done);
sspi->tx_buf = tfr->tx_buf;
@@ -269,8 +273,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len));
sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len));
- /* Fill the TX FIFO */
- sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH);
+ /*
+ * Fill the TX FIFO
+ * Filling the FIFO fully causes timeout for some reason
+ * at least on spi2 on A10s
+ */
+ sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1);
/* Enable the interrupts */
sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC);
@@ -279,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
reg = sun4i_spi_read(sspi, SUN4I_CTL_REG);
sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH);
+ tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+ start = jiffies;
timeout = wait_for_completion_timeout(&sspi->done,
- msecs_to_jiffies(1000));
+ msecs_to_jiffies(tx_time));
+ end = jiffies;
if (!timeout) {
+ dev_warn(&master->dev,
+ "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+ dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+ jiffies_to_msecs(end - start), tx_time);
ret = -ETIMEDOUT;
goto out;
}
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index 42e2c4bd690a..7fce79a60608 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
{
struct sun6i_spi *sspi = spi_master_get_devdata(master);
unsigned int mclk_rate, div, timeout;
+ unsigned int start, end, tx_time;
unsigned int tx_len = 0;
int ret = 0;
u32 reg;
@@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
+ tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+ start = jiffies;
timeout = wait_for_completion_timeout(&sspi->done,
- msecs_to_jiffies(1000));
+ msecs_to_jiffies(tx_time));
+ end = jiffies;
if (!timeout) {
+ dev_warn(&master->dev,
+ "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+ dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+ jiffies_to_msecs(end - start), tx_time);
ret = -ETIMEDOUT;
goto out;
}
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 443f664534e1..29ea8d2f9824 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -646,6 +646,13 @@ free_master:
static int ti_qspi_remove(struct platform_device *pdev)
{
+ struct ti_qspi *qspi = platform_get_drvdata(pdev);
+ int rc;
+
+ rc = spi_master_suspend(qspi->master);
+ if (rc)
+ return rc;
+
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index aab9b492c627..18aeaceee286 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -360,7 +360,7 @@ static int zynqmp_prepare_transfer_hardware(struct spi_master *master)
ret = clk_enable(xqspi->refclk);
if (ret)
- goto clk_err;
+ return ret;
ret = clk_enable(xqspi->pclk);
if (ret)
@@ -369,6 +369,7 @@ static int zynqmp_prepare_transfer_hardware(struct spi_master *master)
zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, GQSPI_EN_MASK);
return 0;
clk_err:
+ clk_disable(xqspi->refclk);
return ret;
}
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 0239b45eed92..77e6e45951f4 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -717,9 +717,11 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
if (vmalloced_buf) {
desc_len = min_t(int, max_seg_size, PAGE_SIZE);
sgs = DIV_ROUND_UP(len + offset_in_page(buf), desc_len);
- } else {
+ } else if (virt_addr_valid(buf)) {
desc_len = min_t(int, max_seg_size, master->max_dma_len);
sgs = DIV_ROUND_UP(len, desc_len);
+ } else {
+ return -EINVAL;
}
ret = sg_alloc_table(sgt, sgs, GFP_KERNEL);
@@ -933,7 +935,7 @@ static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
* spi_transfer_one_message - Default implementation of transfer_one_message()
*
* This is a standard implementation of transfer_one_message() for
- * drivers which impelment a transfer_one() operation. It provides
+ * drivers which implement a transfer_one() operation. It provides
* standard handling of delays and chip select management.
*/
static int spi_transfer_one_message(struct spi_master *master,
@@ -1764,6 +1766,7 @@ struct spi_master *spi_alloc_master(struct device *dev, unsigned size)
master->num_chipselect = 1;
master->dev.class = &spi_master_class;
master->dev.parent = dev;
+ pm_suspend_ignore_children(&master->dev, true);
spi_master_set_devdata(master, &master[1]);
return master;
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 5bac28a3944e..7c197d1a1231 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -66,8 +66,6 @@ source "drivers/staging/nvec/Kconfig"
source "drivers/staging/media/Kconfig"
-source "drivers/staging/rdma/Kconfig"
-
source "drivers/staging/android/Kconfig"
source "drivers/staging/board/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index a954242b0f2c..a470c7276142 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -23,7 +23,6 @@ obj-$(CONFIG_FB_XGI) += xgifb/
obj-$(CONFIG_USB_EMXX) += emxx_udc/
obj-$(CONFIG_SPEAKUP) += speakup/
obj-$(CONFIG_MFD_NVEC) += nvec/
-obj-$(CONFIG_STAGING_RDMA) += rdma/
obj-$(CONFIG_ANDROID) += android/
obj-$(CONFIG_STAGING_BOARD) += board/
obj-$(CONFIG_LTE_GDM724X) += gdm724x/
diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c
index a8f533af9eca..ec12181822e6 100644
--- a/drivers/staging/iio/accel/sca3000_core.c
+++ b/drivers/staging/iio/accel/sca3000_core.c
@@ -594,7 +594,7 @@ static ssize_t sca3000_read_frequency(struct device *dev,
goto error_ret_mut;
ret = sca3000_read_ctrl_reg(st, SCA3000_REG_CTRL_SEL_OUT_CTRL);
mutex_unlock(&st->lock);
- if (ret)
+ if (ret < 0)
goto error_ret;
val = ret;
if (base_freq > 0)
diff --git a/drivers/staging/iio/adc/ad7606_spi.c b/drivers/staging/iio/adc/ad7606_spi.c
index 825da0769936..9587fa86dc69 100644
--- a/drivers/staging/iio/adc/ad7606_spi.c
+++ b/drivers/staging/iio/adc/ad7606_spi.c
@@ -21,7 +21,7 @@ static int ad7606_spi_read_block(struct device *dev,
{
struct spi_device *spi = to_spi_device(dev);
int i, ret;
- unsigned short *data;
+ unsigned short *data = buf;
__be16 *bdata = buf;
ret = spi_read(spi, buf, count * 2);
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 9f43976f4ef2..170ac980abcb 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -444,10 +444,10 @@ static ssize_t ad5933_store(struct device *dev,
st->settling_cycles = val;
/* 2x, 4x handling, see datasheet */
- if (val > 511)
- val = (val >> 1) | (1 << 9);
- else if (val > 1022)
+ if (val > 1022)
val = (val >> 2) | (3 << 9);
+ else if (val > 511)
+ val = (val >> 1) | (1 << 9);
dat = cpu_to_be16(val);
ret = ad5933_i2c_write(st->client,
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index bbfee53cfcf5..845e49a52430 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -2521,12 +2521,13 @@ kiblnd_passive_connect(struct rdma_cm_id *cmid, void *priv, int priv_nob)
return 0;
failed:
- if (ni)
+ if (ni) {
lnet_ni_decref(ni);
+ rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni);
+ rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni);
+ }
rej.ibr_version = version;
- rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni);
- rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni);
kiblnd_reject(cmid, &rej);
return -ECONNREFUSED;
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index ce1f949430f1..3f2f30b6542c 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -976,8 +976,8 @@ static inline __u64 ll_file_maxbytes(struct inode *inode)
}
/* llite/xattr.c */
-int ll_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
+int ll_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value, size_t size, int flags);
ssize_t ll_getxattr(struct dentry *dentry, struct inode *inode,
const char *name, void *buffer, size_t size);
ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size);
diff --git a/drivers/staging/lustre/lustre/llite/xattr.c b/drivers/staging/lustre/lustre/llite/xattr.c
index ed4de04381c3..608014b0dbcd 100644
--- a/drivers/staging/lustre/lustre/llite/xattr.c
+++ b/drivers/staging/lustre/lustre/llite/xattr.c
@@ -211,11 +211,9 @@ int ll_setxattr_common(struct inode *inode, const char *name,
return 0;
}
-int ll_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+int ll_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value, size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
LASSERT(inode);
LASSERT(name);
diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c
index 163f21a1298d..e389009fca42 100644
--- a/drivers/staging/mt29f_spinand/mt29f_spinand.c
+++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c
@@ -42,23 +42,33 @@ static inline struct spinand_state *mtd_to_state(struct mtd_info *mtd)
static int enable_hw_ecc;
static int enable_read_hw_ecc;
-static struct nand_ecclayout spinand_oob_64 = {
- .eccbytes = 24,
- .eccpos = {
- 1, 2, 3, 4, 5, 6,
- 17, 18, 19, 20, 21, 22,
- 33, 34, 35, 36, 37, 38,
- 49, 50, 51, 52, 53, 54, },
- .oobfree = {
- {.offset = 8,
- .length = 8},
- {.offset = 24,
- .length = 8},
- {.offset = 40,
- .length = 8},
- {.offset = 56,
- .length = 8},
- }
+static int spinand_ooblayout_64_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 3)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 1;
+ oobregion->length = 6;
+
+ return 0;
+}
+
+static int spinand_ooblayout_64_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ if (section > 3)
+ return -ERANGE;
+
+ oobregion->offset = (section * 16) + 8;
+ oobregion->length = 8;
+
+ return 0;
+}
+
+static const struct mtd_ooblayout_ops spinand_oob_64_ops = {
+ .ecc = spinand_ooblayout_64_ecc,
+ .free = spinand_ooblayout_64_free,
};
#endif
@@ -886,11 +896,11 @@ static int spinand_probe(struct spi_device *spi_nand)
chip->ecc.strength = 1;
chip->ecc.total = chip->ecc.steps * chip->ecc.bytes;
- chip->ecc.layout = &spinand_oob_64;
chip->ecc.read_page = spinand_read_page_hwecc;
chip->ecc.write_page = spinand_write_page_hwecc;
#else
chip->ecc.mode = NAND_ECC_SOFT;
+ chip->ecc.algo = NAND_ECC_HAMMING;
if (spinand_disable_ecc(spi_nand) < 0)
dev_info(&spi_nand->dev, "%s: disable ecc failed!\n",
__func__);
@@ -912,6 +922,9 @@ static int spinand_probe(struct spi_device *spi_nand)
mtd->dev.parent = &spi_nand->dev;
mtd->oobsize = 64;
+#ifdef CONFIG_MTD_SPINAND_ONDIEECC
+ mtd_set_ooblayout(mtd, &spinand_oob_64_ops);
+#endif
if (nand_scan(mtd, 1))
return -ENXIO;
diff --git a/drivers/staging/rdma/Kconfig b/drivers/staging/rdma/Kconfig
deleted file mode 100644
index f1f3ecadf0fb..000000000000
--- a/drivers/staging/rdma/Kconfig
+++ /dev/null
@@ -1,27 +0,0 @@
-menuconfig STAGING_RDMA
- tristate "RDMA staging drivers"
- depends on INFINIBAND
- depends on PCI || BROKEN
- depends on HAS_IOMEM
- depends on NET
- depends on INET
- default n
- ---help---
- This option allows you to select a number of RDMA drivers that
- fall into one of two categories: deprecated drivers being held
- here before finally being removed or new drivers that still need
- some work before being moved to the normal RDMA driver area.
-
- If you wish to work on these drivers, to help improve them, or
- to report problems you have with them, please use the
- linux-rdma@vger.kernel.org mailing list.
-
- If in doubt, say N here.
-
-
-# Please keep entries in alphabetic order
-if STAGING_RDMA
-
-source "drivers/staging/rdma/hfi1/Kconfig"
-
-endif
diff --git a/drivers/staging/rdma/Makefile b/drivers/staging/rdma/Makefile
deleted file mode 100644
index 8c7fc1de48a7..000000000000
--- a/drivers/staging/rdma/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# Entries for RDMA_STAGING tree
-obj-$(CONFIG_INFINIBAND_HFI1) += hfi1/
diff --git a/drivers/staging/rdma/hfi1/TODO b/drivers/staging/rdma/hfi1/TODO
deleted file mode 100644
index 4c6f1d7d2eaf..000000000000
--- a/drivers/staging/rdma/hfi1/TODO
+++ /dev/null
@@ -1,6 +0,0 @@
-July, 2015
-
-- Remove unneeded file entries in sysfs
-- Remove software processing of IB protocol and place in library for use
- by qib, ipath (if still present), hfi1, and eventually soft-roce
-- Replace incorrect uAPI
diff --git a/drivers/staging/rdma/hfi1/diag.c b/drivers/staging/rdma/hfi1/diag.c
deleted file mode 100644
index bb2409ad891a..000000000000
--- a/drivers/staging/rdma/hfi1/diag.c
+++ /dev/null
@@ -1,1925 +0,0 @@
-/*
- * Copyright(c) 2015, 2016 Intel Corporation.
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * - Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * - Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * - Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-/*
- * This file contains support for diagnostic functions. It is accessed by
- * opening the hfi1_diag device, normally minor number 129. Diagnostic use
- * of the chip may render the chip or board unusable until the driver
- * is unloaded, or in some cases, until the system is rebooted.
- *
- * Accesses to the chip through this interface are not similar to going
- * through the /sys/bus/pci resource mmap interface.
- */
-
-#include <linux/io.h>
-#include <linux/pci.h>
-#include <linux/poll.h>
-#include <linux/vmalloc.h>
-#include <linux/export.h>
-#include <linux/fs.h>
-#include <linux/uaccess.h>
-#include <linux/module.h>
-#include <rdma/ib_smi.h>
-#include "hfi.h"
-#include "device.h"
-#include "common.h"
-#include "verbs_txreq.h"
-#include "trace.h"
-
-#undef pr_fmt
-#define pr_fmt(fmt) DRIVER_NAME ": " fmt
-#define snoop_dbg(fmt, ...) \
- hfi1_cdbg(SNOOP, fmt, ##__VA_ARGS__)
-
-/* Snoop option mask */
-#define SNOOP_DROP_SEND BIT(0)
-#define SNOOP_USE_METADATA BIT(1)
-#define SNOOP_SET_VL0TOVL15 BIT(2)
-
-static u8 snoop_flags;
-
-/*
- * Extract packet length from LRH header.
- * This is in Dwords so multiply by 4 to get size in bytes
- */
-#define HFI1_GET_PKT_LEN(x) (((be16_to_cpu((x)->lrh[2]) & 0xFFF)) << 2)
-
-enum hfi1_filter_status {
- HFI1_FILTER_HIT,
- HFI1_FILTER_ERR,
- HFI1_FILTER_MISS
-};
-
-/* snoop processing functions */
-rhf_rcv_function_ptr snoop_rhf_rcv_functions[8] = {
- [RHF_RCV_TYPE_EXPECTED] = snoop_recv_handler,
- [RHF_RCV_TYPE_EAGER] = snoop_recv_handler,
- [RHF_RCV_TYPE_IB] = snoop_recv_handler,
- [RHF_RCV_TYPE_ERROR] = snoop_recv_handler,
- [RHF_RCV_TYPE_BYPASS] = snoop_recv_handler,
- [RHF_RCV_TYPE_INVALID5] = process_receive_invalid,
- [RHF_RCV_TYPE_INVALID6] = process_receive_invalid,
- [RHF_RCV_TYPE_INVALID7] = process_receive_invalid
-};
-
-/* Snoop packet structure */
-struct snoop_packet {
- struct list_head list;
- u32 total_len;
- u8 data[];
-};
-
-/* Do not make these an enum or it will blow up the capture_md */
-#define PKT_DIR_EGRESS 0x0
-#define PKT_DIR_INGRESS 0x1
-
-/* Packet capture metadata returned to the user with the packet. */
-struct capture_md {
- u8 port;
- u8 dir;
- u8 reserved[6];
- union {
- u64 pbc;
- u64 rhf;
- } u;
-};
-
-static atomic_t diagpkt_count = ATOMIC_INIT(0);
-static struct cdev diagpkt_cdev;
-static struct device *diagpkt_device;
-
-static ssize_t diagpkt_write(struct file *fp, const char __user *data,
- size_t count, loff_t *off);
-
-static const struct file_operations diagpkt_file_ops = {
- .owner = THIS_MODULE,
- .write = diagpkt_write,
- .llseek = noop_llseek,
-};
-
-/*
- * This is used for communication with user space for snoop extended IOCTLs
- */
-struct hfi1_link_info {
- __be64 node_guid;
- u8 port_mode;
- u8 port_state;
- u16 link_speed_active;
- u16 link_width_active;
- u16 vl15_init;
- u8 port_number;
- /*
- * Add padding to make this a full IB SMP payload. Note: changing the
- * size of this structure will make the IOCTLs created with _IOWR
- * change.
- * Be sure to run tests on all IOCTLs when making changes to this
- * structure.
- */
- u8 res[47];
-};
-
-/*
- * This starts our ioctl sequence numbers *way* off from the ones
- * defined in ib_core.
- */
-#define SNOOP_CAPTURE_VERSION 0x1
-
-#define IB_IOCTL_MAGIC 0x1b /* See Documentation/ioctl-number.txt */
-#define HFI1_SNOOP_IOC_MAGIC IB_IOCTL_MAGIC
-#define HFI1_SNOOP_IOC_BASE_SEQ 0x80
-
-#define HFI1_SNOOP_IOCGETLINKSTATE \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ)
-#define HFI1_SNOOP_IOCSETLINKSTATE \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 1)
-#define HFI1_SNOOP_IOCCLEARQUEUE \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 2)
-#define HFI1_SNOOP_IOCCLEARFILTER \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 3)
-#define HFI1_SNOOP_IOCSETFILTER \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 4)
-#define HFI1_SNOOP_IOCGETVERSION \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 5)
-#define HFI1_SNOOP_IOCSET_OPTS \
- _IO(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 6)
-
-/*
- * These offsets +6/+7 could change, but these are already known and used
- * IOCTL numbers so don't change them without a good reason.
- */
-#define HFI1_SNOOP_IOCGETLINKSTATE_EXTRA \
- _IOWR(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 6, \
- struct hfi1_link_info)
-#define HFI1_SNOOP_IOCSETLINKSTATE_EXTRA \
- _IOWR(HFI1_SNOOP_IOC_MAGIC, HFI1_SNOOP_IOC_BASE_SEQ + 7, \
- struct hfi1_link_info)
-
-static int hfi1_snoop_open(struct inode *in, struct file *fp);
-static ssize_t hfi1_snoop_read(struct file *fp, char __user *data,
- size_t pkt_len, loff_t *off);
-static ssize_t hfi1_snoop_write(struct file *fp, const char __user *data,
- size_t count, loff_t *off);
-static long hfi1_ioctl(struct file *fp, unsigned int cmd, unsigned long arg);
-static unsigned int hfi1_snoop_poll(struct file *fp,
- struct poll_table_struct *wait);
-static int hfi1_snoop_release(struct inode *in, struct file *fp);
-
-struct hfi1_packet_filter_command {
- int opcode;
- int length;
- void *value_ptr;
-};
-
-/* Can't re-use PKT_DIR_*GRESS here because 0 means no packets for this */
-#define HFI1_SNOOP_INGRESS 0x1
-#define HFI1_SNOOP_EGRESS 0x2
-
-enum hfi1_packet_filter_opcodes {
- FILTER_BY_LID,
- FILTER_BY_DLID,
- FILTER_BY_MAD_MGMT_CLASS,
- FILTER_BY_QP_NUMBER,
- FILTER_BY_PKT_TYPE,
- FILTER_BY_SERVICE_LEVEL,
- FILTER_BY_PKEY,
- FILTER_BY_DIRECTION,
-};
-
-static const struct file_operations snoop_file_ops = {
- .owner = THIS_MODULE,
- .open = hfi1_snoop_open,
- .read = hfi1_snoop_read,
- .unlocked_ioctl = hfi1_ioctl,
- .poll = hfi1_snoop_poll,
- .write = hfi1_snoop_write,
- .release = hfi1_snoop_release
-};
-
-struct hfi1_filter_array {
- int (*filter)(void *, void *, void *);
-};
-
-static int hfi1_filter_lid(void *ibhdr, void *packet_data, void *value);
-static int hfi1_filter_dlid(void *ibhdr, void *packet_data, void *value);
-static int hfi1_filter_mad_mgmt_class(void *ibhdr, void *packet_data,
- void *value);
-static int hfi1_filter_qp_number(void *ibhdr, void *packet_data, void *value);
-static int hfi1_filter_ibpacket_type(void *ibhdr, void *packet_data,
- void *value);
-static int hfi1_filter_ib_service_level(void *ibhdr, void *packet_data,
- void *value);
-static int hfi1_filter_ib_pkey(void *ibhdr, void *packet_data, void *value);
-static int hfi1_filter_direction(void *ibhdr, void *packet_data, void *value);
-
-static const struct hfi1_filter_array hfi1_filters[] = {
- { hfi1_filter_lid },
- { hfi1_filter_dlid },
- { hfi1_filter_mad_mgmt_class },
- { hfi1_filter_qp_number },
- { hfi1_filter_ibpacket_type },
- { hfi1_filter_ib_service_level },
- { hfi1_filter_ib_pkey },
- { hfi1_filter_direction },
-};
-
-#define HFI1_MAX_FILTERS ARRAY_SIZE(hfi1_filters)
-#define HFI1_DIAG_MINOR_BASE 129
-
-static int hfi1_snoop_add(struct hfi1_devdata *dd, const char *name);
-
-int hfi1_diag_add(struct hfi1_devdata *dd)
-{
- char name[16];
- int ret = 0;
-
- snprintf(name, sizeof(name), "%s_diagpkt%d", class_name(),
- dd->unit);
- /*
- * Do this for each device as opposed to the normal diagpkt
- * interface which is one per host
- */
- ret = hfi1_snoop_add(dd, name);
- if (ret)
- dd_dev_err(dd, "Unable to init snoop/capture device");
-
- snprintf(name, sizeof(name), "%s_diagpkt", class_name());
- if (atomic_inc_return(&diagpkt_count) == 1) {
- ret = hfi1_cdev_init(HFI1_DIAGPKT_MINOR, name,
- &diagpkt_file_ops, &diagpkt_cdev,
- &diagpkt_device, false);
- }
-
- return ret;
-}
-
-/* this must be called w/ dd->snoop_in_lock held */
-static void drain_snoop_list(struct list_head *queue)
-{
- struct list_head *pos, *q;
- struct snoop_packet *packet;
-
- list_for_each_safe(pos, q, queue) {
- packet = list_entry(pos, struct snoop_packet, list);
- list_del(pos);
- kfree(packet);
- }
-}
-
-static void hfi1_snoop_remove(struct hfi1_devdata *dd)
-{
- unsigned long flags = 0;
-
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- drain_snoop_list(&dd->hfi1_snoop.queue);
- hfi1_cdev_cleanup(&dd->hfi1_snoop.cdev, &dd->hfi1_snoop.class_dev);
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
-}
-
-void hfi1_diag_remove(struct hfi1_devdata *dd)
-{
- hfi1_snoop_remove(dd);
- if (atomic_dec_and_test(&diagpkt_count))
- hfi1_cdev_cleanup(&diagpkt_cdev, &diagpkt_device);
- hfi1_cdev_cleanup(&dd->diag_cdev, &dd->diag_device);
-}
-
-/*
- * Allocated structure shared between the credit return mechanism and
- * diagpkt_send().
- */
-struct diagpkt_wait {
- struct completion credits_returned;
- int code;
- atomic_t count;
-};
-
-/*
- * When each side is finished with the structure, they call this.
- * The last user frees the structure.
- */
-static void put_diagpkt_wait(struct diagpkt_wait *wait)
-{
- if (atomic_dec_and_test(&wait->count))
- kfree(wait);
-}
-
-/*
- * Callback from the credit return code. Set the complete, which
- * will let diapkt_send() continue.
- */
-static void diagpkt_complete(void *arg, int code)
-{
- struct diagpkt_wait *wait = (struct diagpkt_wait *)arg;
-
- wait->code = code;
- complete(&wait->credits_returned);
- put_diagpkt_wait(wait); /* finished with the structure */
-}
-
-/**
- * diagpkt_send - send a packet
- * @dp: diag packet descriptor
- */
-static ssize_t diagpkt_send(struct diag_pkt *dp)
-{
- struct hfi1_devdata *dd;
- struct send_context *sc;
- struct pio_buf *pbuf;
- u32 *tmpbuf = NULL;
- ssize_t ret = 0;
- u32 pkt_len, total_len;
- pio_release_cb credit_cb = NULL;
- void *credit_arg = NULL;
- struct diagpkt_wait *wait = NULL;
- int trycount = 0;
-
- dd = hfi1_lookup(dp->unit);
- if (!dd || !(dd->flags & HFI1_PRESENT) || !dd->kregbase) {
- ret = -ENODEV;
- goto bail;
- }
- if (!(dd->flags & HFI1_INITTED)) {
- /* no hardware, freeze, etc. */
- ret = -ENODEV;
- goto bail;
- }
-
- if (dp->version != _DIAG_PKT_VERS) {
- dd_dev_err(dd, "Invalid version %u for diagpkt_write\n",
- dp->version);
- ret = -EINVAL;
- goto bail;
- }
-
- /* send count must be an exact number of dwords */
- if (dp->len & 3) {
- ret = -EINVAL;
- goto bail;
- }
-
- /* there is only port 1 */
- if (dp->port != 1) {
- ret = -EINVAL;
- goto bail;
- }
-
- /* need a valid context */
- if (dp->sw_index >= dd->num_send_contexts) {
- ret = -EINVAL;
- goto bail;
- }
- /* can only use kernel contexts */
- if (dd->send_contexts[dp->sw_index].type != SC_KERNEL &&
- dd->send_contexts[dp->sw_index].type != SC_VL15) {
- ret = -EINVAL;
- goto bail;
- }
- /* must be allocated */
- sc = dd->send_contexts[dp->sw_index].sc;
- if (!sc) {
- ret = -EINVAL;
- goto bail;
- }
- /* must be enabled */
- if (!(sc->flags & SCF_ENABLED)) {
- ret = -EINVAL;
- goto bail;
- }
-
- /* allocate a buffer and copy the data in */
- tmpbuf = vmalloc(dp->len);
- if (!tmpbuf) {
- ret = -ENOMEM;
- goto bail;
- }
-
- if (copy_from_user(tmpbuf,
- (const void __user *)(unsigned long)dp->data,
- dp->len)) {
- ret = -EFAULT;
- goto bail;
- }
-
- /*
- * pkt_len is how much data we have to write, includes header and data.
- * total_len is length of the packet in Dwords plus the PBC should not
- * include the CRC.
- */
- pkt_len = dp->len >> 2;
- total_len = pkt_len + 2; /* PBC + packet */
-
- /* if 0, fill in a default */
- if (dp->pbc == 0) {
- struct hfi1_pportdata *ppd = dd->pport;
-
- hfi1_cdbg(PKT, "Generating PBC");
- dp->pbc = create_pbc(ppd, 0, 0, 0, total_len);
- } else {
- hfi1_cdbg(PKT, "Using passed in PBC");
- }
-
- hfi1_cdbg(PKT, "Egress PBC content is 0x%llx", dp->pbc);
-
- /*
- * The caller wants to wait until the packet is sent and to
- * check for errors. The best we can do is wait until
- * the buffer credits are returned and check if any packet
- * error has occurred. If there are any late errors, this
- * could miss it. If there are other senders who generate
- * an error, this may find it. However, in general, it
- * should catch most.
- */
- if (dp->flags & F_DIAGPKT_WAIT) {
- /* always force a credit return */
- dp->pbc |= PBC_CREDIT_RETURN;
- /* turn on credit return interrupts */
- sc_add_credit_return_intr(sc);
- wait = kmalloc(sizeof(*wait), GFP_KERNEL);
- if (!wait) {
- ret = -ENOMEM;
- goto bail;
- }
- init_completion(&wait->credits_returned);
- atomic_set(&wait->count, 2);
- wait->code = PRC_OK;
-
- credit_cb = diagpkt_complete;
- credit_arg = wait;
- }
-
-retry:
- pbuf = sc_buffer_alloc(sc, total_len, credit_cb, credit_arg);
- if (!pbuf) {
- if (trycount == 0) {
- /* force a credit return and try again */
- sc_return_credits(sc);
- trycount = 1;
- goto retry;
- }
- /*
- * No send buffer means no credit callback. Undo
- * the wait set-up that was done above. We free wait
- * because the callback will never be called.
- */
- if (dp->flags & F_DIAGPKT_WAIT) {
- sc_del_credit_return_intr(sc);
- kfree(wait);
- wait = NULL;
- }
- ret = -ENOSPC;
- goto bail;
- }
-
- pio_copy(dd, pbuf, dp->pbc, tmpbuf, pkt_len);
- /* no flush needed as the HW knows the packet size */
-
- ret = sizeof(*dp);
-
- if (dp->flags & F_DIAGPKT_WAIT) {
- /* wait for credit return */
- ret = wait_for_completion_interruptible(
- &wait->credits_returned);
- /*
- * If the wait returns an error, the wait was interrupted,
- * e.g. with a ^C in the user program. The callback is
- * still pending. This is OK as the wait structure is
- * kmalloc'ed and the structure will free itself when
- * all users are done with it.
- *
- * A context disable occurs on a send context restart, so
- * include that in the list of errors below to check for.
- * NOTE: PRC_FILL_ERR is at best informational and cannot
- * be depended on.
- */
- if (!ret && (((wait->code & PRC_STATUS_ERR) ||
- (wait->code & PRC_FILL_ERR) ||
- (wait->code & PRC_SC_DISABLE))))
- ret = -EIO;
-
- put_diagpkt_wait(wait); /* finished with the structure */
- sc_del_credit_return_intr(sc);
- }
-
-bail:
- vfree(tmpbuf);
- return ret;
-}
-
-static ssize_t diagpkt_write(struct file *fp, const char __user *data,
- size_t count, loff_t *off)
-{
- struct hfi1_devdata *dd;
- struct send_context *sc;
- u8 vl;
-
- struct diag_pkt dp;
-
- if (count != sizeof(dp))
- return -EINVAL;
-
- if (copy_from_user(&dp, data, sizeof(dp)))
- return -EFAULT;
-
- /*
- * The Send Context is derived from the PbcVL value
- * if PBC is populated
- */
- if (dp.pbc) {
- dd = hfi1_lookup(dp.unit);
- if (!dd)
- return -ENODEV;
- vl = (dp.pbc >> PBC_VL_SHIFT) & PBC_VL_MASK;
- sc = dd->vld[vl].sc;
- if (sc) {
- dp.sw_index = sc->sw_index;
- hfi1_cdbg(
- PKT,
- "Packet sent over VL %d via Send Context %u(%u)",
- vl, sc->sw_index, sc->hw_context);
- }
- }
-
- return diagpkt_send(&dp);
-}
-
-static int hfi1_snoop_add(struct hfi1_devdata *dd, const char *name)
-{
- int ret = 0;
-
- dd->hfi1_snoop.mode_flag = 0;
- spin_lock_init(&dd->hfi1_snoop.snoop_lock);
- INIT_LIST_HEAD(&dd->hfi1_snoop.queue);
- init_waitqueue_head(&dd->hfi1_snoop.waitq);
-
- ret = hfi1_cdev_init(HFI1_SNOOP_CAPTURE_BASE + dd->unit, name,
- &snoop_file_ops,
- &dd->hfi1_snoop.cdev, &dd->hfi1_snoop.class_dev,
- false);
-
- if (ret) {
- dd_dev_err(dd, "Couldn't create %s device: %d", name, ret);
- hfi1_cdev_cleanup(&dd->hfi1_snoop.cdev,
- &dd->hfi1_snoop.class_dev);
- }
-
- return ret;
-}
-
-static struct hfi1_devdata *hfi1_dd_from_sc_inode(struct inode *in)
-{
- int unit = iminor(in) - HFI1_SNOOP_CAPTURE_BASE;
- struct hfi1_devdata *dd;
-
- dd = hfi1_lookup(unit);
- return dd;
-}
-
-/* clear or restore send context integrity checks */
-static void adjust_integrity_checks(struct hfi1_devdata *dd)
-{
- struct send_context *sc;
- unsigned long sc_flags;
- int i;
-
- spin_lock_irqsave(&dd->sc_lock, sc_flags);
- for (i = 0; i < dd->num_send_contexts; i++) {
- int enable;
-
- sc = dd->send_contexts[i].sc;
-
- if (!sc)
- continue; /* not allocated */
-
- enable = likely(!HFI1_CAP_IS_KSET(NO_INTEGRITY)) &&
- dd->hfi1_snoop.mode_flag != HFI1_PORT_SNOOP_MODE;
-
- set_pio_integrity(sc);
-
- if (enable) /* take HFI_CAP_* flags into account */
- hfi1_init_ctxt(sc);
- }
- spin_unlock_irqrestore(&dd->sc_lock, sc_flags);
-}
-
-static int hfi1_snoop_open(struct inode *in, struct file *fp)
-{
- int ret;
- int mode_flag = 0;
- unsigned long flags = 0;
- struct hfi1_devdata *dd;
- struct list_head *queue;
-
- mutex_lock(&hfi1_mutex);
-
- dd = hfi1_dd_from_sc_inode(in);
- if (!dd) {
- ret = -ENODEV;
- goto bail;
- }
-
- /*
- * File mode determines snoop or capture. Some existing user
- * applications expect the capture device to be able to be opened RDWR
- * because they expect a dedicated capture device. For this reason we
- * support a module param to force capture mode even if the file open
- * mode matches snoop.
- */
- if ((fp->f_flags & O_ACCMODE) == O_RDONLY) {
- snoop_dbg("Capture Enabled");
- mode_flag = HFI1_PORT_CAPTURE_MODE;
- } else if ((fp->f_flags & O_ACCMODE) == O_RDWR) {
- snoop_dbg("Snoop Enabled");
- mode_flag = HFI1_PORT_SNOOP_MODE;
- } else {
- snoop_dbg("Invalid");
- ret = -EINVAL;
- goto bail;
- }
- queue = &dd->hfi1_snoop.queue;
-
- /*
- * We are not supporting snoop and capture at the same time.
- */
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- if (dd->hfi1_snoop.mode_flag) {
- ret = -EBUSY;
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- goto bail;
- }
-
- dd->hfi1_snoop.mode_flag = mode_flag;
- drain_snoop_list(queue);
-
- dd->hfi1_snoop.filter_callback = NULL;
- dd->hfi1_snoop.filter_value = NULL;
-
- /*
- * Send side packet integrity checks are not helpful when snooping so
- * disable and re-enable when we stop snooping.
- */
- if (mode_flag == HFI1_PORT_SNOOP_MODE) {
- /* clear after snoop mode is on */
- adjust_integrity_checks(dd); /* clear */
-
- /*
- * We also do not want to be doing the DLID LMC check for
- * ingressed packets.
- */
- dd->hfi1_snoop.dcc_cfg = read_csr(dd, DCC_CFG_PORT_CONFIG1);
- write_csr(dd, DCC_CFG_PORT_CONFIG1,
- (dd->hfi1_snoop.dcc_cfg >> 32) << 32);
- }
-
- /*
- * As soon as we set these function pointers the recv and send handlers
- * are active. This is a race condition so we must make sure to drain
- * the queue and init filter values above. Technically we should add
- * locking here but all that will happen is on recv a packet will get
- * allocated and get stuck on the snoop_lock before getting added to the
- * queue. Same goes for send.
- */
- dd->rhf_rcv_function_map = snoop_rhf_rcv_functions;
- dd->process_pio_send = snoop_send_pio_handler;
- dd->process_dma_send = snoop_send_pio_handler;
- dd->pio_inline_send = snoop_inline_pio_send;
-
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- ret = 0;
-
-bail:
- mutex_unlock(&hfi1_mutex);
-
- return ret;
-}
-
-static int hfi1_snoop_release(struct inode *in, struct file *fp)
-{
- unsigned long flags = 0;
- struct hfi1_devdata *dd;
- int mode_flag;
-
- dd = hfi1_dd_from_sc_inode(in);
- if (!dd)
- return -ENODEV;
-
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
-
- /* clear the snoop mode before re-adjusting send context CSRs */
- mode_flag = dd->hfi1_snoop.mode_flag;
- dd->hfi1_snoop.mode_flag = 0;
-
- /*
- * Drain the queue and clear the filters we are done with it. Don't
- * forget to restore the packet integrity checks
- */
- drain_snoop_list(&dd->hfi1_snoop.queue);
- if (mode_flag == HFI1_PORT_SNOOP_MODE) {
- /* restore after snoop mode is clear */
- adjust_integrity_checks(dd); /* restore */
-
- /*
- * Also should probably reset the DCC_CONFIG1 register for DLID
- * checking on incoming packets again. Use the value saved when
- * opening the snoop device.
- */
- write_csr(dd, DCC_CFG_PORT_CONFIG1, dd->hfi1_snoop.dcc_cfg);
- }
-
- dd->hfi1_snoop.filter_callback = NULL;
- kfree(dd->hfi1_snoop.filter_value);
- dd->hfi1_snoop.filter_value = NULL;
-
- /*
- * User is done snooping and capturing, return control to the normal
- * handler. Re-enable SDMA handling.
- */
- dd->rhf_rcv_function_map = dd->normal_rhf_rcv_functions;
- dd->process_pio_send = hfi1_verbs_send_pio;
- dd->process_dma_send = hfi1_verbs_send_dma;
- dd->pio_inline_send = pio_copy;
-
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
-
- snoop_dbg("snoop/capture device released");
-
- return 0;
-}
-
-static unsigned int hfi1_snoop_poll(struct file *fp,
- struct poll_table_struct *wait)
-{
- int ret = 0;
- unsigned long flags = 0;
-
- struct hfi1_devdata *dd;
-
- dd = hfi1_dd_from_sc_inode(fp->f_inode);
- if (!dd)
- return -ENODEV;
-
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
-
- poll_wait(fp, &dd->hfi1_snoop.waitq, wait);
- if (!list_empty(&dd->hfi1_snoop.queue))
- ret |= POLLIN | POLLRDNORM;
-
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- return ret;
-}
-
-static ssize_t hfi1_snoop_write(struct file *fp, const char __user *data,
- size_t count, loff_t *off)
-{
- struct diag_pkt dpkt;
- struct hfi1_devdata *dd;
- size_t ret;
- u8 byte_two, sl, sc5, sc4, vl, byte_one;
- struct send_context *sc;
- u32 len;
- u64 pbc;
- struct hfi1_ibport *ibp;
- struct hfi1_pportdata *ppd;
-
- dd = hfi1_dd_from_sc_inode(fp->f_inode);
- if (!dd)
- return -ENODEV;
-
- ppd = dd->pport;
- snoop_dbg("received %lu bytes from user", count);
-
- memset(&dpkt, 0, sizeof(struct diag_pkt));
- dpkt.version = _DIAG_PKT_VERS;
- dpkt.unit = dd->unit;
- dpkt.port = 1;
-
- if (likely(!(snoop_flags & SNOOP_USE_METADATA))) {
- /*
- * We need to generate the PBC and not let diagpkt_send do it,
- * to do this we need the VL and the length in dwords.
- * The VL can be determined by using the SL and looking up the
- * SC. Then the SC can be converted into VL. The exception to
- * this is those packets which are from an SMI queue pair.
- * Since we can't detect anything about the QP here we have to
- * rely on the SC. If its 0xF then we assume its SMI and
- * do not look at the SL.
- */
- if (copy_from_user(&byte_one, data, 1))
- return -EINVAL;
-
- if (copy_from_user(&byte_two, data + 1, 1))
- return -EINVAL;
-
- sc4 = (byte_one >> 4) & 0xf;
- if (sc4 == 0xF) {
- snoop_dbg("Detected VL15 packet ignoring SL in packet");
- vl = sc4;
- } else {
- sl = (byte_two >> 4) & 0xf;
- ibp = to_iport(&dd->verbs_dev.rdi.ibdev, 1);
- sc5 = ibp->sl_to_sc[sl];
- vl = sc_to_vlt(dd, sc5);
- if (vl != sc4) {
- snoop_dbg("VL %d does not match SC %d of packet",
- vl, sc4);
- return -EINVAL;
- }
- }
-
- sc = dd->vld[vl].sc; /* Look up the context based on VL */
- if (sc) {
- dpkt.sw_index = sc->sw_index;
- snoop_dbg("Sending on context %u(%u)", sc->sw_index,
- sc->hw_context);
- } else {
- snoop_dbg("Could not find context for vl %d", vl);
- return -EINVAL;
- }
-
- len = (count >> 2) + 2; /* Add in PBC */
- pbc = create_pbc(ppd, 0, 0, vl, len);
- } else {
- if (copy_from_user(&pbc, data, sizeof(pbc)))
- return -EINVAL;
- vl = (pbc >> PBC_VL_SHIFT) & PBC_VL_MASK;
- sc = dd->vld[vl].sc; /* Look up the context based on VL */
- if (sc) {
- dpkt.sw_index = sc->sw_index;
- } else {
- snoop_dbg("Could not find context for vl %d", vl);
- return -EINVAL;
- }
- data += sizeof(pbc);
- count -= sizeof(pbc);
- }
- dpkt.len = count;
- dpkt.data = (unsigned long)data;
-
- snoop_dbg("PBC: vl=0x%llx Length=0x%llx",
- (pbc >> 12) & 0xf,
- (pbc & 0xfff));
-
- dpkt.pbc = pbc;
- ret = diagpkt_send(&dpkt);
- /*
- * diagpkt_send only returns number of bytes in the diagpkt so patch
- * that up here before returning.
- */
- if (ret == sizeof(dpkt))
- return count;
-
- return ret;
-}
-
-static ssize_t hfi1_snoop_read(struct file *fp, char __user *data,
- size_t pkt_len, loff_t *off)
-{
- ssize_t ret = 0;
- unsigned long flags = 0;
- struct snoop_packet *packet = NULL;
- struct hfi1_devdata *dd;
-
- dd = hfi1_dd_from_sc_inode(fp->f_inode);
- if (!dd)
- return -ENODEV;
-
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
-
- while (list_empty(&dd->hfi1_snoop.queue)) {
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
-
- if (fp->f_flags & O_NONBLOCK)
- return -EAGAIN;
-
- if (wait_event_interruptible(
- dd->hfi1_snoop.waitq,
- !list_empty(&dd->hfi1_snoop.queue)))
- return -EINTR;
-
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- }
-
- if (!list_empty(&dd->hfi1_snoop.queue)) {
- packet = list_entry(dd->hfi1_snoop.queue.next,
- struct snoop_packet, list);
- list_del(&packet->list);
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- if (pkt_len >= packet->total_len) {
- if (copy_to_user(data, packet->data,
- packet->total_len))
- ret = -EFAULT;
- else
- ret = packet->total_len;
- } else {
- ret = -EINVAL;
- }
-
- kfree(packet);
- } else {
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- }
-
- return ret;
-}
-
-/**
- * hfi1_assign_snoop_link_credits -- Set up credits for VL15 and others
- * @ppd : ptr to hfi1 port data
- * @value : options from user space
- *
- * Assumes the rest of the CM credit registers are zero from a
- * previous global or credit reset.
- * Leave shared count at zero for both global and all vls.
- * In snoop mode ideally we don't use shared credits
- * Reserve 8.5k for VL15
- * If total credits less than 8.5kbytes return error.
- * Divide the rest of the credits across VL0 to VL7 and if
- * each of these levels has less than 34 credits (at least 2048 + 128 bytes)
- * return with an error.
- * The credit registers will be reset to zero on link negotiation or link up
- * so this function should be activated from user space only if the port has
- * gone past link negotiation and link up.
- *
- * Return -- 0 if successful else error condition
- *
- */
-static long hfi1_assign_snoop_link_credits(struct hfi1_pportdata *ppd,
- int value)
-{
-#define OPA_MIN_PER_VL_CREDITS 34 /* 2048 + 128 bytes */
- struct buffer_control t;
- int i;
- struct hfi1_devdata *dd = ppd->dd;
- u16 total_credits = (value >> 16) & 0xffff;
- u16 vl15_credits = dd->vl15_init / 2;
- u16 per_vl_credits;
- __be16 be_per_vl_credits;
-
- if (!(ppd->host_link_state & HLS_UP))
- goto err_exit;
- if (total_credits < vl15_credits)
- goto err_exit;
-
- per_vl_credits = (total_credits - vl15_credits) / TXE_NUM_DATA_VL;
-
- if (per_vl_credits < OPA_MIN_PER_VL_CREDITS)
- goto err_exit;
-
- memset(&t, 0, sizeof(t));
- be_per_vl_credits = cpu_to_be16(per_vl_credits);
-
- for (i = 0; i < TXE_NUM_DATA_VL; i++)
- t.vl[i].dedicated = be_per_vl_credits;
-
- t.vl[15].dedicated = cpu_to_be16(vl15_credits);
- return set_buffer_control(ppd, &t);
-
-err_exit:
- snoop_dbg("port_state = 0x%x, total_credits = %d, vl15_credits = %d",
- ppd->host_link_state, total_credits, vl15_credits);
-
- return -EINVAL;
-}
-
-static long hfi1_ioctl(struct file *fp, unsigned int cmd, unsigned long arg)
-{
- struct hfi1_devdata *dd;
- void *filter_value = NULL;
- long ret = 0;
- int value = 0;
- u8 phys_state = 0;
- u8 link_state = 0;
- u16 dev_state = 0;
- unsigned long flags = 0;
- unsigned long *argp = NULL;
- struct hfi1_packet_filter_command filter_cmd = {0};
- int mode_flag = 0;
- struct hfi1_pportdata *ppd = NULL;
- unsigned int index;
- struct hfi1_link_info link_info;
- int read_cmd, write_cmd, read_ok, write_ok;
-
- dd = hfi1_dd_from_sc_inode(fp->f_inode);
- if (!dd)
- return -ENODEV;
-
- mode_flag = dd->hfi1_snoop.mode_flag;
- read_cmd = _IOC_DIR(cmd) & _IOC_READ;
- write_cmd = _IOC_DIR(cmd) & _IOC_WRITE;
- write_ok = access_ok(VERIFY_WRITE, (void __user *)arg, _IOC_SIZE(cmd));
- read_ok = access_ok(VERIFY_READ, (void __user *)arg, _IOC_SIZE(cmd));
-
- if ((read_cmd && !write_ok) || (write_cmd && !read_ok))
- return -EFAULT;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if ((mode_flag & HFI1_PORT_CAPTURE_MODE) &&
- (cmd != HFI1_SNOOP_IOCCLEARQUEUE) &&
- (cmd != HFI1_SNOOP_IOCCLEARFILTER) &&
- (cmd != HFI1_SNOOP_IOCSETFILTER))
- /* Capture devices are allowed only 3 operations
- * 1.Clear capture queue
- * 2.Clear capture filter
- * 3.Set capture filter
- * Other are invalid.
- */
- return -EINVAL;
-
- switch (cmd) {
- case HFI1_SNOOP_IOCSETLINKSTATE_EXTRA:
- memset(&link_info, 0, sizeof(link_info));
-
- if (copy_from_user(&link_info,
- (struct hfi1_link_info __user *)arg,
- sizeof(link_info)))
- return -EFAULT;
-
- value = link_info.port_state;
- index = link_info.port_number;
- if (index > dd->num_pports - 1)
- return -EINVAL;
-
- ppd = &dd->pport[index];
- if (!ppd)
- return -EINVAL;
-
- /* What we want to transition to */
- phys_state = (value >> 4) & 0xF;
- link_state = value & 0xF;
- snoop_dbg("Setting link state 0x%x", value);
-
- switch (link_state) {
- case IB_PORT_NOP:
- if (phys_state == 0)
- break;
- /* fall through */
- case IB_PORT_DOWN:
- switch (phys_state) {
- case 0:
- dev_state = HLS_DN_DOWNDEF;
- break;
- case 2:
- dev_state = HLS_DN_POLL;
- break;
- case 3:
- dev_state = HLS_DN_DISABLE;
- break;
- default:
- return -EINVAL;
- }
- ret = set_link_state(ppd, dev_state);
- break;
- case IB_PORT_ARMED:
- ret = set_link_state(ppd, HLS_UP_ARMED);
- if (!ret)
- send_idle_sma(dd, SMA_IDLE_ARM);
- break;
- case IB_PORT_ACTIVE:
- ret = set_link_state(ppd, HLS_UP_ACTIVE);
- if (!ret)
- send_idle_sma(dd, SMA_IDLE_ACTIVE);
- break;
- default:
- return -EINVAL;
- }
-
- if (ret)
- break;
- /* fall through */
- case HFI1_SNOOP_IOCGETLINKSTATE:
- case HFI1_SNOOP_IOCGETLINKSTATE_EXTRA:
- if (cmd == HFI1_SNOOP_IOCGETLINKSTATE_EXTRA) {
- memset(&link_info, 0, sizeof(link_info));
- if (copy_from_user(&link_info,
- (struct hfi1_link_info __user *)arg,
- sizeof(link_info)))
- return -EFAULT;
- index = link_info.port_number;
- } else {
- ret = __get_user(index, (int __user *)arg);
- if (ret != 0)
- break;
- }
-
- if (index > dd->num_pports - 1)
- return -EINVAL;
-
- ppd = &dd->pport[index];
- if (!ppd)
- return -EINVAL;
-
- value = hfi1_ibphys_portstate(ppd);
- value <<= 4;
- value |= driver_lstate(ppd);
-
- snoop_dbg("Link port | Link State: %d", value);
-
- if ((cmd == HFI1_SNOOP_IOCGETLINKSTATE_EXTRA) ||
- (cmd == HFI1_SNOOP_IOCSETLINKSTATE_EXTRA)) {
- link_info.port_state = value;
- link_info.node_guid = cpu_to_be64(ppd->guid);
- link_info.link_speed_active =
- ppd->link_speed_active;
- link_info.link_width_active =
- ppd->link_width_active;
- if (copy_to_user((struct hfi1_link_info __user *)arg,
- &link_info, sizeof(link_info)))
- return -EFAULT;
- } else {
- ret = __put_user(value, (int __user *)arg);
- }
- break;
-
- case HFI1_SNOOP_IOCCLEARQUEUE:
- snoop_dbg("Clearing snoop queue");
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- drain_snoop_list(&dd->hfi1_snoop.queue);
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- break;
-
- case HFI1_SNOOP_IOCCLEARFILTER:
- snoop_dbg("Clearing filter");
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- if (dd->hfi1_snoop.filter_callback) {
- /* Drain packets first */
- drain_snoop_list(&dd->hfi1_snoop.queue);
- dd->hfi1_snoop.filter_callback = NULL;
- }
- kfree(dd->hfi1_snoop.filter_value);
- dd->hfi1_snoop.filter_value = NULL;
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- break;
-
- case HFI1_SNOOP_IOCSETFILTER:
- snoop_dbg("Setting filter");
- /* just copy command structure */
- argp = (unsigned long *)arg;
- if (copy_from_user(&filter_cmd, (void __user *)argp,
- sizeof(filter_cmd)))
- return -EFAULT;
-
- if (filter_cmd.opcode >= HFI1_MAX_FILTERS) {
- pr_alert("Invalid opcode in request\n");
- return -EINVAL;
- }
-
- snoop_dbg("Opcode %d Len %d Ptr %p",
- filter_cmd.opcode, filter_cmd.length,
- filter_cmd.value_ptr);
-
- filter_value = kcalloc(filter_cmd.length, sizeof(u8),
- GFP_KERNEL);
- if (!filter_value)
- return -ENOMEM;
-
- /* copy remaining data from userspace */
- if (copy_from_user((u8 *)filter_value,
- (void __user *)filter_cmd.value_ptr,
- filter_cmd.length)) {
- kfree(filter_value);
- return -EFAULT;
- }
- /* Drain packets first */
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- drain_snoop_list(&dd->hfi1_snoop.queue);
- dd->hfi1_snoop.filter_callback =
- hfi1_filters[filter_cmd.opcode].filter;
- /* just in case we see back to back sets */
- kfree(dd->hfi1_snoop.filter_value);
- dd->hfi1_snoop.filter_value = filter_value;
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- break;
- case HFI1_SNOOP_IOCGETVERSION:
- value = SNOOP_CAPTURE_VERSION;
- snoop_dbg("Getting version: %d", value);
- ret = __put_user(value, (int __user *)arg);
- break;
- case HFI1_SNOOP_IOCSET_OPTS:
- snoop_flags = 0;
- ret = __get_user(value, (int __user *)arg);
- if (ret != 0)
- break;
-
- snoop_dbg("Setting snoop option %d", value);
- if (value & SNOOP_DROP_SEND)
- snoop_flags |= SNOOP_DROP_SEND;
- if (value & SNOOP_USE_METADATA)
- snoop_flags |= SNOOP_USE_METADATA;
- if (value & (SNOOP_SET_VL0TOVL15)) {
- ppd = &dd->pport[0]; /* first port will do */
- ret = hfi1_assign_snoop_link_credits(ppd, value);
- }
- break;
- default:
- return -ENOTTY;
- }
-
- return ret;
-}
-
-static void snoop_list_add_tail(struct snoop_packet *packet,
- struct hfi1_devdata *dd)
-{
- unsigned long flags = 0;
-
- spin_lock_irqsave(&dd->hfi1_snoop.snoop_lock, flags);
- if (likely((dd->hfi1_snoop.mode_flag & HFI1_PORT_SNOOP_MODE) ||
- (dd->hfi1_snoop.mode_flag & HFI1_PORT_CAPTURE_MODE))) {
- list_add_tail(&packet->list, &dd->hfi1_snoop.queue);
- snoop_dbg("Added packet to list");
- }
-
- /*
- * Technically we can could have closed the snoop device while waiting
- * on the above lock and it is gone now. The snoop mode_flag will
- * prevent us from adding the packet to the queue though.
- */
-
- spin_unlock_irqrestore(&dd->hfi1_snoop.snoop_lock, flags);
- wake_up_interruptible(&dd->hfi1_snoop.waitq);
-}
-
-static inline int hfi1_filter_check(void *val, const char *msg)
-{
- if (!val) {
- snoop_dbg("Error invalid %s value for filter", msg);
- return HFI1_FILTER_ERR;
- }
- return 0;
-}
-
-static int hfi1_filter_lid(void *ibhdr, void *packet_data, void *value)
-{
- struct hfi1_ib_header *hdr;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- if (*((u16 *)value) == be16_to_cpu(hdr->lrh[3])) /* matches slid */
- return HFI1_FILTER_HIT; /* matched */
-
- return HFI1_FILTER_MISS; /* Not matched */
-}
-
-static int hfi1_filter_dlid(void *ibhdr, void *packet_data, void *value)
-{
- struct hfi1_ib_header *hdr;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- if (*((u16 *)value) == be16_to_cpu(hdr->lrh[1]))
- return HFI1_FILTER_HIT;
-
- return HFI1_FILTER_MISS;
-}
-
-/* Not valid for outgoing packets, send handler passes null for data*/
-static int hfi1_filter_mad_mgmt_class(void *ibhdr, void *packet_data,
- void *value)
-{
- struct hfi1_ib_header *hdr;
- struct hfi1_other_headers *ohdr = NULL;
- struct ib_smp *smp = NULL;
- u32 qpn = 0;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(packet_data, "packet_data");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- /* Check for GRH */
- if ((be16_to_cpu(hdr->lrh[0]) & 3) == HFI1_LRH_BTH)
- ohdr = &hdr->u.oth; /* LRH + BTH + DETH */
- else
- ohdr = &hdr->u.l.oth; /* LRH + GRH + BTH + DETH */
-
- qpn = be32_to_cpu(ohdr->bth[1]) & 0x00FFFFFF;
- if (qpn <= 1) {
- smp = (struct ib_smp *)packet_data;
- if (*((u8 *)value) == smp->mgmt_class)
- return HFI1_FILTER_HIT;
- else
- return HFI1_FILTER_MISS;
- }
- return HFI1_FILTER_ERR;
-}
-
-static int hfi1_filter_qp_number(void *ibhdr, void *packet_data, void *value)
-{
- struct hfi1_ib_header *hdr;
- struct hfi1_other_headers *ohdr = NULL;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- /* Check for GRH */
- if ((be16_to_cpu(hdr->lrh[0]) & 3) == HFI1_LRH_BTH)
- ohdr = &hdr->u.oth; /* LRH + BTH + DETH */
- else
- ohdr = &hdr->u.l.oth; /* LRH + GRH + BTH + DETH */
- if (*((u32 *)value) == (be32_to_cpu(ohdr->bth[1]) & 0x00FFFFFF))
- return HFI1_FILTER_HIT;
-
- return HFI1_FILTER_MISS;
-}
-
-static int hfi1_filter_ibpacket_type(void *ibhdr, void *packet_data,
- void *value)
-{
- u32 lnh = 0;
- u8 opcode = 0;
- struct hfi1_ib_header *hdr;
- struct hfi1_other_headers *ohdr = NULL;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- lnh = (be16_to_cpu(hdr->lrh[0]) & 3);
-
- if (lnh == HFI1_LRH_BTH)
- ohdr = &hdr->u.oth;
- else if (lnh == HFI1_LRH_GRH)
- ohdr = &hdr->u.l.oth;
- else
- return HFI1_FILTER_ERR;
-
- opcode = be32_to_cpu(ohdr->bth[0]) >> 24;
-
- if (*((u8 *)value) == ((opcode >> 5) & 0x7))
- return HFI1_FILTER_HIT;
-
- return HFI1_FILTER_MISS;
-}
-
-static int hfi1_filter_ib_service_level(void *ibhdr, void *packet_data,
- void *value)
-{
- struct hfi1_ib_header *hdr;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- if ((*((u8 *)value)) == ((be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF))
- return HFI1_FILTER_HIT;
-
- return HFI1_FILTER_MISS;
-}
-
-static int hfi1_filter_ib_pkey(void *ibhdr, void *packet_data, void *value)
-{
- u32 lnh = 0;
- struct hfi1_ib_header *hdr;
- struct hfi1_other_headers *ohdr = NULL;
- int ret;
-
- ret = hfi1_filter_check(ibhdr, "header");
- if (ret)
- return ret;
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- hdr = (struct hfi1_ib_header *)ibhdr;
-
- lnh = (be16_to_cpu(hdr->lrh[0]) & 3);
- if (lnh == HFI1_LRH_BTH)
- ohdr = &hdr->u.oth;
- else if (lnh == HFI1_LRH_GRH)
- ohdr = &hdr->u.l.oth;
- else
- return HFI1_FILTER_ERR;
-
- /* P_key is 16-bit entity, however top most bit indicates
- * type of membership. 0 for limited and 1 for Full.
- * Limited members cannot accept information from other
- * Limited members, but communication is allowed between
- * every other combination of membership.
- * Hence we'll omit comparing top-most bit while filtering
- */
-
- if ((*(u16 *)value & 0x7FFF) ==
- ((be32_to_cpu(ohdr->bth[0])) & 0x7FFF))
- return HFI1_FILTER_HIT;
-
- return HFI1_FILTER_MISS;
-}
-
-/*
- * If packet_data is NULL then this is coming from one of the send functions.
- * Thus we know if its an ingressed or egressed packet.
- */
-static int hfi1_filter_direction(void *ibhdr, void *packet_data, void *value)
-{
- u8 user_dir = *(u8 *)value;
- int ret;
-
- ret = hfi1_filter_check(value, "user");
- if (ret)
- return ret;
-
- if (packet_data) {
- /* Incoming packet */
- if (user_dir & HFI1_SNOOP_INGRESS)
- return HFI1_FILTER_HIT;
- } else {
- /* Outgoing packet */
- if (user_dir & HFI1_SNOOP_EGRESS)
- return HFI1_FILTER_HIT;
- }
-
- return HFI1_FILTER_MISS;
-}
-
-/*
- * Allocate a snoop packet. The structure that is stored in the ring buffer, not
- * to be confused with an hfi packet type.
- */
-static struct snoop_packet *allocate_snoop_packet(u32 hdr_len,
- u32 data_len,
- u32 md_len)
-{
- struct snoop_packet *packet;
-
- packet = kzalloc(sizeof(*packet) + hdr_len + data_len
- + md_len,
- GFP_ATOMIC | __GFP_NOWARN);
- if (likely(packet))
- INIT_LIST_HEAD(&packet->list);
-
- return packet;
-}
-
-/*
- * Instead of having snoop and capture code intermixed with the recv functions,
- * both the interrupt handler and hfi1_ib_rcv() we are going to hijack the call
- * and land in here for snoop/capture but if not enabled the call will go
- * through as before. This gives us a single point to constrain all of the snoop
- * snoop recv logic. There is nothing special that needs to happen for bypass
- * packets. This routine should not try to look into the packet. It just copied
- * it. There is no guarantee for filters when it comes to bypass packets as
- * there is no specific support. Bottom line is this routine does now even know
- * what a bypass packet is.
- */
-int snoop_recv_handler(struct hfi1_packet *packet)
-{
- struct hfi1_pportdata *ppd = packet->rcd->ppd;
- struct hfi1_ib_header *hdr = packet->hdr;
- int header_size = packet->hlen;
- void *data = packet->ebuf;
- u32 tlen = packet->tlen;
- struct snoop_packet *s_packet = NULL;
- int ret;
- int snoop_mode = 0;
- u32 md_len = 0;
- struct capture_md md;
-
- snoop_dbg("PACKET IN: hdr size %d tlen %d data %p", header_size, tlen,
- data);
-
- trace_snoop_capture(ppd->dd, header_size, hdr, tlen - header_size,
- data);
-
- if (!ppd->dd->hfi1_snoop.filter_callback) {
- snoop_dbg("filter not set");
- ret = HFI1_FILTER_HIT;
- } else {
- ret = ppd->dd->hfi1_snoop.filter_callback(hdr, data,
- ppd->dd->hfi1_snoop.filter_value);
- }
-
- switch (ret) {
- case HFI1_FILTER_ERR:
- snoop_dbg("Error in filter call");
- break;
- case HFI1_FILTER_MISS:
- snoop_dbg("Filter Miss");
- break;
- case HFI1_FILTER_HIT:
-
- if (ppd->dd->hfi1_snoop.mode_flag & HFI1_PORT_SNOOP_MODE)
- snoop_mode = 1;
- if ((snoop_mode == 0) ||
- unlikely(snoop_flags & SNOOP_USE_METADATA))
- md_len = sizeof(struct capture_md);
-
- s_packet = allocate_snoop_packet(header_size,
- tlen - header_size,
- md_len);
-
- if (unlikely(!s_packet)) {
- dd_dev_warn_ratelimited(ppd->dd, "Unable to allocate snoop/capture packet\n");
- break;
- }
-
- if (md_len > 0) {
- memset(&md, 0, sizeof(struct capture_md));
- md.port = 1;
- md.dir = PKT_DIR_INGRESS;
- md.u.rhf = packet->rhf;
- memcpy(s_packet->data, &md, md_len);
- }
-
- /* We should always have a header */
- if (hdr) {
- memcpy(s_packet->data + md_len, hdr, header_size);
- } else {
- dd_dev_err(ppd->dd, "Unable to copy header to snoop/capture packet\n");
- kfree(s_packet);
- break;
- }
-
- /*
- * Packets with no data are possible. If there is no data needed
- * to take care of the last 4 bytes which are normally included
- * with data buffers and are included in tlen. Since we kzalloc
- * the buffer we do not need to set any values but if we decide
- * not to use kzalloc we should zero them.
- */
- if (data)
- memcpy(s_packet->data + header_size + md_len, data,
- tlen - header_size);
-
- s_packet->total_len = tlen + md_len;
- snoop_list_add_tail(s_packet, ppd->dd);
-
- /*
- * If we are snooping the packet not capturing then throw away
- * after adding to the list.
- */
- snoop_dbg("Capturing packet");
- if (ppd->dd->hfi1_snoop.mode_flag & HFI1_PORT_SNOOP_MODE) {
- snoop_dbg("Throwing packet away");
- /*
- * If we are dropping the packet we still may need to
- * handle the case where error flags are set, this is
- * normally done by the type specific handler but that
- * won't be called in this case.
- */
- if (unlikely(rhf_err_flags(packet->rhf)))
- handle_eflags(packet);
-
- /* throw the packet on the floor */
- return RHF_RCV_CONTINUE;
- }
- break;
- default:
- break;
- }
-
- /*
- * We do not care what type of packet came in here - just pass it off
- * to the normal handler.
- */
- return ppd->dd->normal_rhf_rcv_functions[rhf_rcv_type(packet->rhf)]
- (packet);
-}
-
-/*
- * Handle snooping and capturing packets when sdma is being used.
- */
-int snoop_send_dma_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
- u64 pbc)
-{
- pr_alert("Snooping/Capture of Send DMA Packets Is Not Supported!\n");
- snoop_dbg("Unsupported Operation");
- return hfi1_verbs_send_dma(qp, ps, 0);
-}
-
-/*
- * Handle snooping and capturing packets when pio is being used. Does not handle
- * bypass packets. The only way to send a bypass packet currently is to use the
- * diagpkt interface. When that interface is enable snoop/capture is not.
- */
-int snoop_send_pio_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
- u64 pbc)
-{
- u32 hdrwords = qp->s_hdrwords;
- struct rvt_sge_state *ss = qp->s_cur_sge;
- u32 len = qp->s_cur_size;
- u32 dwords = (len + 3) >> 2;
- u32 plen = hdrwords + dwords + 2; /* includes pbc */
- struct hfi1_pportdata *ppd = ps->ppd;
- struct snoop_packet *s_packet = NULL;
- u32 *hdr = (u32 *)&ps->s_txreq->phdr.hdr;
- u32 length = 0;
- struct rvt_sge_state temp_ss;
- void *data = NULL;
- void *data_start = NULL;
- int ret;
- int snoop_mode = 0;
- int md_len = 0;
- struct capture_md md;
- u32 vl;
- u32 hdr_len = hdrwords << 2;
- u32 tlen = HFI1_GET_PKT_LEN(&ps->s_txreq->phdr.hdr);
-
- md.u.pbc = 0;
-
- snoop_dbg("PACKET OUT: hdrword %u len %u plen %u dwords %u tlen %u",
- hdrwords, len, plen, dwords, tlen);
- if (ppd->dd->hfi1_snoop.mode_flag & HFI1_PORT_SNOOP_MODE)
- snoop_mode = 1;
- if ((snoop_mode == 0) ||
- unlikely(snoop_flags & SNOOP_USE_METADATA))
- md_len = sizeof(struct capture_md);
-
- /* not using ss->total_len as arg 2 b/c that does not count CRC */
- s_packet = allocate_snoop_packet(hdr_len, tlen - hdr_len, md_len);
-
- if (unlikely(!s_packet)) {
- dd_dev_warn_ratelimited(ppd->dd, "Unable to allocate snoop/capture packet\n");
- goto out;
- }
-
- s_packet->total_len = tlen + md_len;
-
- if (md_len > 0) {
- memset(&md, 0, sizeof(struct capture_md));
- md.port = 1;
- md.dir = PKT_DIR_EGRESS;
- if (likely(pbc == 0)) {
- vl = be16_to_cpu(ps->s_txreq->phdr.hdr.lrh[0]) >> 12;
- md.u.pbc = create_pbc(ppd, 0, qp->s_srate, vl, plen);
- } else {
- md.u.pbc = 0;
- }
- memcpy(s_packet->data, &md, md_len);
- } else {
- md.u.pbc = pbc;
- }
-
- /* Copy header */
- if (likely(hdr)) {
- memcpy(s_packet->data + md_len, hdr, hdr_len);
- } else {
- dd_dev_err(ppd->dd,
- "Unable to copy header to snoop/capture packet\n");
- kfree(s_packet);
- goto out;
- }
-
- if (ss) {
- data = s_packet->data + hdr_len + md_len;
- data_start = data;
-
- /*
- * Copy SGE State
- * The update_sge() function below will not modify the
- * individual SGEs in the array. It will make a copy each time
- * and operate on that. So we only need to copy this instance
- * and it won't impact PIO.
- */
- temp_ss = *ss;
- length = len;
-
- snoop_dbg("Need to copy %d bytes", length);
- while (length) {
- void *addr = temp_ss.sge.vaddr;
- u32 slen = temp_ss.sge.length;
-
- if (slen > length) {
- slen = length;
- snoop_dbg("slen %d > len %d", slen, length);
- }
- snoop_dbg("copy %d to %p", slen, addr);
- memcpy(data, addr, slen);
- update_sge(&temp_ss, slen);
- length -= slen;
- data += slen;
- snoop_dbg("data is now %p bytes left %d", data, length);
- }
- snoop_dbg("Completed SGE copy");
- }
-
- /*
- * Why do the filter check down here? Because the event tracing has its
- * own filtering and we need to have the walked the SGE list.
- */
- if (!ppd->dd->hfi1_snoop.filter_callback) {
- snoop_dbg("filter not set\n");
- ret = HFI1_FILTER_HIT;
- } else {
- ret = ppd->dd->hfi1_snoop.filter_callback(
- &ps->s_txreq->phdr.hdr,
- NULL,
- ppd->dd->hfi1_snoop.filter_value);
- }
-
- switch (ret) {
- case HFI1_FILTER_ERR:
- snoop_dbg("Error in filter call");
- /* fall through */
- case HFI1_FILTER_MISS:
- snoop_dbg("Filter Miss");
- kfree(s_packet);
- break;
- case HFI1_FILTER_HIT:
- snoop_dbg("Capturing packet");
- snoop_list_add_tail(s_packet, ppd->dd);
-
- if (unlikely((snoop_flags & SNOOP_DROP_SEND) &&
- (ppd->dd->hfi1_snoop.mode_flag &
- HFI1_PORT_SNOOP_MODE))) {
- unsigned long flags;
-
- snoop_dbg("Dropping packet");
- if (qp->s_wqe) {
- spin_lock_irqsave(&qp->s_lock, flags);
- hfi1_send_complete(
- qp,
- qp->s_wqe,
- IB_WC_SUCCESS);
- spin_unlock_irqrestore(&qp->s_lock, flags);
- } else if (qp->ibqp.qp_type == IB_QPT_RC) {
- spin_lock_irqsave(&qp->s_lock, flags);
- hfi1_rc_send_complete(qp,
- &ps->s_txreq->phdr.hdr);
- spin_unlock_irqrestore(&qp->s_lock, flags);
- }
-
- /*
- * If snoop is dropping the packet we need to put the
- * txreq back because no one else will.
- */
- hfi1_put_txreq(ps->s_txreq);
- return 0;
- }
- break;
- default:
- kfree(s_packet);
- break;
- }
-out:
- return hfi1_verbs_send_pio(qp, ps, md.u.pbc);
-}
-
-/*
- * Callers of this must pass a hfi1_ib_header type for the from ptr. Currently
- * this can be used anywhere, but the intention is for inline ACKs for RC and
- * CCA packets. We don't restrict this usage though.
- */
-void snoop_inline_pio_send(struct hfi1_devdata *dd, struct pio_buf *pbuf,
- u64 pbc, const void *from, size_t count)
-{
- int snoop_mode = 0;
- int md_len = 0;
- struct capture_md md;
- struct snoop_packet *s_packet = NULL;
-
- /*
- * count is in dwords so we need to convert to bytes.
- * We also need to account for CRC which would be tacked on by hardware.
- */
- int packet_len = (count << 2) + 4;
- int ret;
-
- snoop_dbg("ACK OUT: len %d", packet_len);
-
- if (!dd->hfi1_snoop.filter_callback) {
- snoop_dbg("filter not set");
- ret = HFI1_FILTER_HIT;
- } else {
- ret = dd->hfi1_snoop.filter_callback(
- (struct hfi1_ib_header *)from,
- NULL,
- dd->hfi1_snoop.filter_value);
- }
-
- switch (ret) {
- case HFI1_FILTER_ERR:
- snoop_dbg("Error in filter call");
- /* fall through */
- case HFI1_FILTER_MISS:
- snoop_dbg("Filter Miss");
- break;
- case HFI1_FILTER_HIT:
- snoop_dbg("Capturing packet");
- if (dd->hfi1_snoop.mode_flag & HFI1_PORT_SNOOP_MODE)
- snoop_mode = 1;
- if ((snoop_mode == 0) ||
- unlikely(snoop_flags & SNOOP_USE_METADATA))
- md_len = sizeof(struct capture_md);
-
- s_packet = allocate_snoop_packet(packet_len, 0, md_len);
-
- if (unlikely(!s_packet)) {
- dd_dev_warn_ratelimited(dd, "Unable to allocate snoop/capture packet\n");
- goto inline_pio_out;
- }
-
- s_packet->total_len = packet_len + md_len;
-
- /* Fill in the metadata for the packet */
- if (md_len > 0) {
- memset(&md, 0, sizeof(struct capture_md));
- md.port = 1;
- md.dir = PKT_DIR_EGRESS;
- md.u.pbc = pbc;
- memcpy(s_packet->data, &md, md_len);
- }
-
- /* Add the packet data which is a single buffer */
- memcpy(s_packet->data + md_len, from, packet_len);
-
- snoop_list_add_tail(s_packet, dd);
-
- if (unlikely((snoop_flags & SNOOP_DROP_SEND) && snoop_mode)) {
- snoop_dbg("Dropping packet");
- return;
- }
- break;
- default:
- break;
- }
-
-inline_pio_out:
- pio_copy(dd, pbuf, pbc, from, count);
-}
diff --git a/drivers/staging/rdma/hfi1/eprom.c b/drivers/staging/rdma/hfi1/eprom.c
deleted file mode 100644
index bd8771570f81..000000000000
--- a/drivers/staging/rdma/hfi1/eprom.c
+++ /dev/null
@@ -1,471 +0,0 @@
-/*
- * Copyright(c) 2015, 2016 Intel Corporation.
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * - Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * - Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * - Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-#include <linux/delay.h>
-#include "hfi.h"
-#include "common.h"
-#include "eprom.h"
-
-/*
- * The EPROM is logically divided into three partitions:
- * partition 0: the first 128K, visible from PCI ROM BAR
- * partition 1: 4K config file (sector size)
- * partition 2: the rest
- */
-#define P0_SIZE (128 * 1024)
-#define P1_SIZE (4 * 1024)
-#define P1_START P0_SIZE
-#define P2_START (P0_SIZE + P1_SIZE)
-
-/* erase sizes supported by the controller */
-#define SIZE_4KB (4 * 1024)
-#define MASK_4KB (SIZE_4KB - 1)
-
-#define SIZE_32KB (32 * 1024)
-#define MASK_32KB (SIZE_32KB - 1)
-
-#define SIZE_64KB (64 * 1024)
-#define MASK_64KB (SIZE_64KB - 1)
-
-/* controller page size, in bytes */
-#define EP_PAGE_SIZE 256
-#define EEP_PAGE_MASK (EP_PAGE_SIZE - 1)
-
-/* controller commands */
-#define CMD_SHIFT 24
-#define CMD_NOP (0)
-#define CMD_PAGE_PROGRAM(addr) ((0x02 << CMD_SHIFT) | addr)
-#define CMD_READ_DATA(addr) ((0x03 << CMD_SHIFT) | addr)
-#define CMD_READ_SR1 ((0x05 << CMD_SHIFT))
-#define CMD_WRITE_ENABLE ((0x06 << CMD_SHIFT))
-#define CMD_SECTOR_ERASE_4KB(addr) ((0x20 << CMD_SHIFT) | addr)
-#define CMD_SECTOR_ERASE_32KB(addr) ((0x52 << CMD_SHIFT) | addr)
-#define CMD_CHIP_ERASE ((0x60 << CMD_SHIFT))
-#define CMD_READ_MANUF_DEV_ID ((0x90 << CMD_SHIFT))
-#define CMD_RELEASE_POWERDOWN_NOID ((0xab << CMD_SHIFT))
-#define CMD_SECTOR_ERASE_64KB(addr) ((0xd8 << CMD_SHIFT) | addr)
-
-/* controller interface speeds */
-#define EP_SPEED_FULL 0x2 /* full speed */
-
-/* controller status register 1 bits */
-#define SR1_BUSY 0x1ull /* the BUSY bit in SR1 */
-
-/* sleep length while waiting for controller */
-#define WAIT_SLEEP_US 100 /* must be larger than 5 (see usage) */
-#define COUNT_DELAY_SEC(n) ((n) * (1000000 / WAIT_SLEEP_US))
-
-/* GPIO pins */
-#define EPROM_WP_N BIT_ULL(14) /* EPROM write line */
-
-/*
- * How long to wait for the EPROM to become available, in ms.
- * The spec 32 Mb EPROM takes around 40s to erase then write.
- * Double it for safety.
- */
-#define EPROM_TIMEOUT 80000 /* ms */
-
-/*
- * Turn on external enable line that allows writing on the flash.
- */
-static void write_enable(struct hfi1_devdata *dd)
-{
- /* raise signal */
- write_csr(dd, ASIC_GPIO_OUT, read_csr(dd, ASIC_GPIO_OUT) | EPROM_WP_N);
- /* raise enable */
- write_csr(dd, ASIC_GPIO_OE, read_csr(dd, ASIC_GPIO_OE) | EPROM_WP_N);
-}
-
-/*
- * Turn off external enable line that allows writing on the flash.
- */
-static void write_disable(struct hfi1_devdata *dd)
-{
- /* lower signal */
- write_csr(dd, ASIC_GPIO_OUT, read_csr(dd, ASIC_GPIO_OUT) & ~EPROM_WP_N);
- /* lower enable */
- write_csr(dd, ASIC_GPIO_OE, read_csr(dd, ASIC_GPIO_OE) & ~EPROM_WP_N);
-}
-
-/*
- * Wait for the device to become not busy. Must be called after all
- * write or erase operations.
- */
-static int wait_for_not_busy(struct hfi1_devdata *dd)
-{
- unsigned long count = 0;
- u64 reg;
- int ret = 0;
-
- /* starts page mode */
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_READ_SR1);
- while (1) {
- udelay(WAIT_SLEEP_US);
- usleep_range(WAIT_SLEEP_US - 5, WAIT_SLEEP_US + 5);
- count++;
- reg = read_csr(dd, ASIC_EEP_DATA);
- if ((reg & SR1_BUSY) == 0)
- break;
- /* 200s is the largest time for a 128Mb device */
- if (count > COUNT_DELAY_SEC(200)) {
- dd_dev_err(dd, "waited too long for SPI FLASH busy to clear - failing\n");
- ret = -ETIMEDOUT;
- break; /* break, not goto - must stop page mode */
- }
- }
-
- /* stop page mode with a NOP */
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_NOP);
-
- return ret;
-}
-
-/*
- * Read the device ID from the SPI controller.
- */
-static u32 read_device_id(struct hfi1_devdata *dd)
-{
- /* read the Manufacture Device ID */
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_READ_MANUF_DEV_ID);
- return (u32)read_csr(dd, ASIC_EEP_DATA);
-}
-
-/*
- * Erase the whole flash.
- */
-static int erase_chip(struct hfi1_devdata *dd)
-{
- int ret;
-
- write_enable(dd);
-
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_WRITE_ENABLE);
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_CHIP_ERASE);
- ret = wait_for_not_busy(dd);
-
- write_disable(dd);
-
- return ret;
-}
-
-/*
- * Erase a range.
- */
-static int erase_range(struct hfi1_devdata *dd, u32 start, u32 len)
-{
- u32 end = start + len;
- int ret = 0;
-
- if (end < start)
- return -EINVAL;
-
- /* check the end points for the minimum erase */
- if ((start & MASK_4KB) || (end & MASK_4KB)) {
- dd_dev_err(dd,
- "%s: non-aligned range (0x%x,0x%x) for a 4KB erase\n",
- __func__, start, end);
- return -EINVAL;
- }
-
- write_enable(dd);
-
- while (start < end) {
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_WRITE_ENABLE);
- /* check in order of largest to smallest */
- if (((start & MASK_64KB) == 0) && (start + SIZE_64KB <= end)) {
- write_csr(dd, ASIC_EEP_ADDR_CMD,
- CMD_SECTOR_ERASE_64KB(start));
- start += SIZE_64KB;
- } else if (((start & MASK_32KB) == 0) &&
- (start + SIZE_32KB <= end)) {
- write_csr(dd, ASIC_EEP_ADDR_CMD,
- CMD_SECTOR_ERASE_32KB(start));
- start += SIZE_32KB;
- } else { /* 4KB will work */
- write_csr(dd, ASIC_EEP_ADDR_CMD,
- CMD_SECTOR_ERASE_4KB(start));
- start += SIZE_4KB;
- }
- ret = wait_for_not_busy(dd);
- if (ret)
- goto done;
- }
-
-done:
- write_disable(dd);
-
- return ret;
-}
-
-/*
- * Read a 256 byte (64 dword) EPROM page.
- * All callers have verified the offset is at a page boundary.
- */
-static void read_page(struct hfi1_devdata *dd, u32 offset, u32 *result)
-{
- int i;
-
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_READ_DATA(offset));
- for (i = 0; i < EP_PAGE_SIZE / sizeof(u32); i++)
- result[i] = (u32)read_csr(dd, ASIC_EEP_DATA);
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_NOP); /* close open page */
-}
-
-/*
- * Read length bytes starting at offset. Copy to user address addr.
- */
-static int read_length(struct hfi1_devdata *dd, u32 start, u32 len, u64 addr)
-{
- u32 offset;
- u32 buffer[EP_PAGE_SIZE / sizeof(u32)];
- int ret = 0;
-
- /* reject anything not on an EPROM page boundary */
- if ((start & EEP_PAGE_MASK) || (len & EEP_PAGE_MASK))
- return -EINVAL;
-
- for (offset = 0; offset < len; offset += EP_PAGE_SIZE) {
- read_page(dd, start + offset, buffer);
- if (copy_to_user((void __user *)(addr + offset),
- buffer, EP_PAGE_SIZE)) {
- ret = -EFAULT;
- goto done;
- }
- }
-
-done:
- return ret;
-}
-
-/*
- * Write a 256 byte (64 dword) EPROM page.
- * All callers have verified the offset is at a page boundary.
- */
-static int write_page(struct hfi1_devdata *dd, u32 offset, u32 *data)
-{
- int i;
-
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_WRITE_ENABLE);
- write_csr(dd, ASIC_EEP_DATA, data[0]);
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_PAGE_PROGRAM(offset));
- for (i = 1; i < EP_PAGE_SIZE / sizeof(u32); i++)
- write_csr(dd, ASIC_EEP_DATA, data[i]);
- /* will close the open page */
- return wait_for_not_busy(dd);
-}
-
-/*
- * Write length bytes starting at offset. Read from user address addr.
- */
-static int write_length(struct hfi1_devdata *dd, u32 start, u32 len, u64 addr)
-{
- u32 offset;
- u32 buffer[EP_PAGE_SIZE / sizeof(u32)];
- int ret = 0;
-
- /* reject anything not on an EPROM page boundary */
- if ((start & EEP_PAGE_MASK) || (len & EEP_PAGE_MASK))
- return -EINVAL;
-
- write_enable(dd);
-
- for (offset = 0; offset < len; offset += EP_PAGE_SIZE) {
- if (copy_from_user(buffer, (void __user *)(addr + offset),
- EP_PAGE_SIZE)) {
- ret = -EFAULT;
- goto done;
- }
- ret = write_page(dd, start + offset, buffer);
- if (ret)
- goto done;
- }
-
-done:
- write_disable(dd);
- return ret;
-}
-
-/* convert an range composite to a length, in bytes */
-static inline u32 extract_rlen(u32 composite)
-{
- return (composite & 0xffff) * EP_PAGE_SIZE;
-}
-
-/* convert an range composite to a start, in bytes */
-static inline u32 extract_rstart(u32 composite)
-{
- return (composite >> 16) * EP_PAGE_SIZE;
-}
-
-/*
- * Perform the given operation on the EPROM. Called from user space. The
- * user credentials have already been checked.
- *
- * Return 0 on success, -ERRNO on error
- */
-int handle_eprom_command(struct file *fp, const struct hfi1_cmd *cmd)
-{
- struct hfi1_devdata *dd;
- u32 dev_id;
- u32 rlen; /* range length */
- u32 rstart; /* range start */
- int i_minor;
- int ret = 0;
-
- /*
- * Map the device file to device data using the relative minor.
- * The device file minor number is the unit number + 1. 0 is
- * the generic device file - reject it.
- */
- i_minor = iminor(file_inode(fp)) - HFI1_USER_MINOR_BASE;
- if (i_minor <= 0)
- return -EINVAL;
- dd = hfi1_lookup(i_minor - 1);
- if (!dd) {
- pr_err("%s: cannot find unit %d!\n", __func__, i_minor);
- return -EINVAL;
- }
-
- /* some devices do not have an EPROM */
- if (!dd->eprom_available)
- return -EOPNOTSUPP;
-
- ret = acquire_chip_resource(dd, CR_EPROM, EPROM_TIMEOUT);
- if (ret) {
- dd_dev_err(dd, "%s: unable to acquire EPROM resource\n",
- __func__);
- goto done_asic;
- }
-
- dd_dev_info(dd, "%s: cmd: type %d, len 0x%x, addr 0x%016llx\n",
- __func__, cmd->type, cmd->len, cmd->addr);
-
- switch (cmd->type) {
- case HFI1_CMD_EP_INFO:
- if (cmd->len != sizeof(u32)) {
- ret = -ERANGE;
- break;
- }
- dev_id = read_device_id(dd);
- /* addr points to a u32 user buffer */
- if (copy_to_user((void __user *)cmd->addr, &dev_id,
- sizeof(u32)))
- ret = -EFAULT;
- break;
-
- case HFI1_CMD_EP_ERASE_CHIP:
- ret = erase_chip(dd);
- break;
-
- case HFI1_CMD_EP_ERASE_RANGE:
- rlen = extract_rlen(cmd->len);
- rstart = extract_rstart(cmd->len);
- ret = erase_range(dd, rstart, rlen);
- break;
-
- case HFI1_CMD_EP_READ_RANGE:
- rlen = extract_rlen(cmd->len);
- rstart = extract_rstart(cmd->len);
- ret = read_length(dd, rstart, rlen, cmd->addr);
- break;
-
- case HFI1_CMD_EP_WRITE_RANGE:
- rlen = extract_rlen(cmd->len);
- rstart = extract_rstart(cmd->len);
- ret = write_length(dd, rstart, rlen, cmd->addr);
- break;
-
- default:
- dd_dev_err(dd, "%s: unexpected command %d\n",
- __func__, cmd->type);
- ret = -EINVAL;
- break;
- }
-
- release_chip_resource(dd, CR_EPROM);
-done_asic:
- return ret;
-}
-
-/*
- * Initialize the EPROM handler.
- */
-int eprom_init(struct hfi1_devdata *dd)
-{
- int ret = 0;
-
- /* only the discrete chip has an EPROM */
- if (dd->pcidev->device != PCI_DEVICE_ID_INTEL0)
- return 0;
-
- /*
- * It is OK if both HFIs reset the EPROM as long as they don't
- * do it at the same time.
- */
- ret = acquire_chip_resource(dd, CR_EPROM, EPROM_TIMEOUT);
- if (ret) {
- dd_dev_err(dd,
- "%s: unable to acquire EPROM resource, no EPROM support\n",
- __func__);
- goto done_asic;
- }
-
- /* reset EPROM to be sure it is in a good state */
-
- /* set reset */
- write_csr(dd, ASIC_EEP_CTL_STAT, ASIC_EEP_CTL_STAT_EP_RESET_SMASK);
- /* clear reset, set speed */
- write_csr(dd, ASIC_EEP_CTL_STAT,
- EP_SPEED_FULL << ASIC_EEP_CTL_STAT_RATE_SPI_SHIFT);
-
- /* wake the device with command "release powerdown NoID" */
- write_csr(dd, ASIC_EEP_ADDR_CMD, CMD_RELEASE_POWERDOWN_NOID);
-
- dd->eprom_available = true;
- release_chip_resource(dd, CR_EPROM);
-done_asic:
- return ret;
-}
diff --git a/drivers/staging/rtl8188eu/core/rtw_efuse.c b/drivers/staging/rtl8188eu/core/rtw_efuse.c
index c17870cddb5b..fbce1f7e68ca 100644
--- a/drivers/staging/rtl8188eu/core/rtw_efuse.c
+++ b/drivers/staging/rtl8188eu/core/rtw_efuse.c
@@ -102,7 +102,7 @@ efuse_phymap_to_logical(u8 *phymap, u16 _offset, u16 _size_byte, u8 *pbuf)
if (!efuseTbl)
return;
- eFuseWord = (u16 **)rtw_malloc2d(EFUSE_MAX_SECTION_88E, EFUSE_MAX_WORD_UNIT, sizeof(*eFuseWord));
+ eFuseWord = (u16 **)rtw_malloc2d(EFUSE_MAX_SECTION_88E, EFUSE_MAX_WORD_UNIT, sizeof(u16));
if (!eFuseWord) {
DBG_88E("%s: alloc eFuseWord fail!\n", __func__);
goto eFuseWord_failed;
diff --git a/drivers/staging/rtl8188eu/hal/usb_halinit.c b/drivers/staging/rtl8188eu/hal/usb_halinit.c
index 87ea3b844951..363f3a34ddce 100644
--- a/drivers/staging/rtl8188eu/hal/usb_halinit.c
+++ b/drivers/staging/rtl8188eu/hal/usb_halinit.c
@@ -2072,7 +2072,8 @@ void rtl8188eu_set_hal_ops(struct adapter *adapt)
{
struct hal_ops *halfunc = &adapt->HalFunc;
- adapt->HalData = kzalloc(sizeof(*adapt->HalData), GFP_KERNEL);
+
+ adapt->HalData = kzalloc(sizeof(struct hal_data_8188e), GFP_KERNEL);
if (!adapt->HalData)
DBG_88E("cant not alloc memory for HAL DATA\n");
diff --git a/drivers/target/iscsi/Kconfig b/drivers/target/iscsi/Kconfig
index 8345fb457a40..bbdbf9c4e93a 100644
--- a/drivers/target/iscsi/Kconfig
+++ b/drivers/target/iscsi/Kconfig
@@ -7,3 +7,5 @@ config ISCSI_TARGET
help
Say M here to enable the ConfigFS enabled Linux-iSCSI.org iSCSI
Target Mode Stack.
+
+source "drivers/target/iscsi/cxgbit/Kconfig"
diff --git a/drivers/target/iscsi/Makefile b/drivers/target/iscsi/Makefile
index 0f43be9c3453..0f18295e05bc 100644
--- a/drivers/target/iscsi/Makefile
+++ b/drivers/target/iscsi/Makefile
@@ -18,3 +18,4 @@ iscsi_target_mod-y += iscsi_target_parameters.o \
iscsi_target_transport.o
obj-$(CONFIG_ISCSI_TARGET) += iscsi_target_mod.o
+obj-$(CONFIG_ISCSI_TARGET_CXGB4) += cxgbit/
diff --git a/drivers/target/iscsi/cxgbit/Kconfig b/drivers/target/iscsi/cxgbit/Kconfig
new file mode 100644
index 000000000000..c9b6a3c758b1
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/Kconfig
@@ -0,0 +1,7 @@
+config ISCSI_TARGET_CXGB4
+ tristate "Chelsio iSCSI target offload driver"
+ depends on ISCSI_TARGET && CHELSIO_T4 && INET
+ select CHELSIO_T4_UWIRE
+ ---help---
+ To compile this driver as module, choose M here: the module
+ will be called cxgbit.
diff --git a/drivers/target/iscsi/cxgbit/Makefile b/drivers/target/iscsi/cxgbit/Makefile
new file mode 100644
index 000000000000..bd56c073dff6
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/Makefile
@@ -0,0 +1,6 @@
+ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4
+ccflags-y += -Idrivers/target/iscsi
+
+obj-$(CONFIG_ISCSI_TARGET_CXGB4) += cxgbit.o
+
+cxgbit-y := cxgbit_main.o cxgbit_cm.o cxgbit_target.o cxgbit_ddp.o
diff --git a/drivers/target/iscsi/cxgbit/cxgbit.h b/drivers/target/iscsi/cxgbit/cxgbit.h
new file mode 100644
index 000000000000..625c7f6de6b2
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/cxgbit.h
@@ -0,0 +1,353 @@
+/*
+ * Copyright (c) 2016 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CXGBIT_H__
+#define __CXGBIT_H__
+
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/idr.h>
+#include <linux/completion.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/inet.h>
+#include <linux/wait.h>
+#include <linux/kref.h>
+#include <linux/timer.h>
+#include <linux/io.h>
+
+#include <asm/byteorder.h>
+
+#include <net/net_namespace.h>
+
+#include <target/iscsi/iscsi_transport.h>
+#include <iscsi_target_parameters.h>
+#include <iscsi_target_login.h>
+
+#include "t4_regs.h"
+#include "t4_msg.h"
+#include "cxgb4.h"
+#include "cxgb4_uld.h"
+#include "l2t.h"
+#include "cxgb4_ppm.h"
+#include "cxgbit_lro.h"
+
+extern struct mutex cdev_list_lock;
+extern struct list_head cdev_list_head;
+struct cxgbit_np;
+
+struct cxgbit_sock;
+
+struct cxgbit_cmd {
+ struct scatterlist sg;
+ struct cxgbi_task_tag_info ttinfo;
+ bool setup_ddp;
+ bool release;
+};
+
+#define CXGBIT_MAX_ISO_PAYLOAD \
+ min_t(u32, MAX_SKB_FRAGS * PAGE_SIZE, 65535)
+
+struct cxgbit_iso_info {
+ u8 flags;
+ u32 mpdu;
+ u32 len;
+ u32 burst_len;
+};
+
+enum cxgbit_skcb_flags {
+ SKCBF_TX_NEED_HDR = (1 << 0), /* packet needs a header */
+ SKCBF_TX_FLAG_COMPL = (1 << 1), /* wr completion flag */
+ SKCBF_TX_ISO = (1 << 2), /* iso cpl in tx skb */
+ SKCBF_RX_LRO = (1 << 3), /* lro skb */
+};
+
+struct cxgbit_skb_rx_cb {
+ u8 opcode;
+ void *pdu_cb;
+ void (*backlog_fn)(struct cxgbit_sock *, struct sk_buff *);
+};
+
+struct cxgbit_skb_tx_cb {
+ u8 submode;
+ u32 extra_len;
+};
+
+union cxgbit_skb_cb {
+ struct {
+ u8 flags;
+ union {
+ struct cxgbit_skb_tx_cb tx;
+ struct cxgbit_skb_rx_cb rx;
+ };
+ };
+
+ struct {
+ /* This member must be first. */
+ struct l2t_skb_cb l2t;
+ struct sk_buff *wr_next;
+ };
+};
+
+#define CXGBIT_SKB_CB(skb) ((union cxgbit_skb_cb *)&((skb)->cb[0]))
+#define cxgbit_skcb_flags(skb) (CXGBIT_SKB_CB(skb)->flags)
+#define cxgbit_skcb_submode(skb) (CXGBIT_SKB_CB(skb)->tx.submode)
+#define cxgbit_skcb_tx_wr_next(skb) (CXGBIT_SKB_CB(skb)->wr_next)
+#define cxgbit_skcb_tx_extralen(skb) (CXGBIT_SKB_CB(skb)->tx.extra_len)
+#define cxgbit_skcb_rx_opcode(skb) (CXGBIT_SKB_CB(skb)->rx.opcode)
+#define cxgbit_skcb_rx_backlog_fn(skb) (CXGBIT_SKB_CB(skb)->rx.backlog_fn)
+#define cxgbit_rx_pdu_cb(skb) (CXGBIT_SKB_CB(skb)->rx.pdu_cb)
+
+static inline void *cplhdr(struct sk_buff *skb)
+{
+ return skb->data;
+}
+
+enum cxgbit_cdev_flags {
+ CDEV_STATE_UP = 0,
+ CDEV_ISO_ENABLE,
+ CDEV_DDP_ENABLE,
+};
+
+#define NP_INFO_HASH_SIZE 32
+
+struct np_info {
+ struct np_info *next;
+ struct cxgbit_np *cnp;
+ unsigned int stid;
+};
+
+struct cxgbit_list_head {
+ struct list_head list;
+ /* device lock */
+ spinlock_t lock;
+};
+
+struct cxgbit_device {
+ struct list_head list;
+ struct cxgb4_lld_info lldi;
+ struct np_info *np_hash_tab[NP_INFO_HASH_SIZE];
+ /* np lock */
+ spinlock_t np_lock;
+ u8 selectq[MAX_NPORTS][2];
+ struct cxgbit_list_head cskq;
+ u32 mdsl;
+ struct kref kref;
+ unsigned long flags;
+};
+
+struct cxgbit_wr_wait {
+ struct completion completion;
+ int ret;
+};
+
+enum cxgbit_csk_state {
+ CSK_STATE_IDLE = 0,
+ CSK_STATE_LISTEN,
+ CSK_STATE_CONNECTING,
+ CSK_STATE_ESTABLISHED,
+ CSK_STATE_ABORTING,
+ CSK_STATE_CLOSING,
+ CSK_STATE_MORIBUND,
+ CSK_STATE_DEAD,
+};
+
+enum cxgbit_csk_flags {
+ CSK_TX_DATA_SENT = 0,
+ CSK_LOGIN_PDU_DONE,
+ CSK_LOGIN_DONE,
+ CSK_DDP_ENABLE,
+};
+
+struct cxgbit_sock_common {
+ struct cxgbit_device *cdev;
+ struct sockaddr_storage local_addr;
+ struct sockaddr_storage remote_addr;
+ struct cxgbit_wr_wait wr_wait;
+ enum cxgbit_csk_state state;
+ unsigned long flags;
+};
+
+struct cxgbit_np {
+ struct cxgbit_sock_common com;
+ wait_queue_head_t accept_wait;
+ struct iscsi_np *np;
+ struct completion accept_comp;
+ struct list_head np_accept_list;
+ /* np accept lock */
+ spinlock_t np_accept_lock;
+ struct kref kref;
+ unsigned int stid;
+};
+
+struct cxgbit_sock {
+ struct cxgbit_sock_common com;
+ struct cxgbit_np *cnp;
+ struct iscsi_conn *conn;
+ struct l2t_entry *l2t;
+ struct dst_entry *dst;
+ struct list_head list;
+ struct sk_buff_head rxq;
+ struct sk_buff_head txq;
+ struct sk_buff_head ppodq;
+ struct sk_buff_head backlogq;
+ struct sk_buff_head skbq;
+ struct sk_buff *wr_pending_head;
+ struct sk_buff *wr_pending_tail;
+ struct sk_buff *skb;
+ struct sk_buff *lro_skb;
+ struct sk_buff *lro_hskb;
+ struct list_head accept_node;
+ /* socket lock */
+ spinlock_t lock;
+ wait_queue_head_t waitq;
+ wait_queue_head_t ack_waitq;
+ bool lock_owner;
+ struct kref kref;
+ u32 max_iso_npdu;
+ u32 wr_cred;
+ u32 wr_una_cred;
+ u32 wr_max_cred;
+ u32 snd_una;
+ u32 tid;
+ u32 snd_nxt;
+ u32 rcv_nxt;
+ u32 smac_idx;
+ u32 tx_chan;
+ u32 mtu;
+ u32 write_seq;
+ u32 rx_credits;
+ u32 snd_win;
+ u32 rcv_win;
+ u16 mss;
+ u16 emss;
+ u16 plen;
+ u16 rss_qid;
+ u16 txq_idx;
+ u16 ctrlq_idx;
+ u8 tos;
+ u8 port_id;
+#define CXGBIT_SUBMODE_HCRC 0x1
+#define CXGBIT_SUBMODE_DCRC 0x2
+ u8 submode;
+#ifdef CONFIG_CHELSIO_T4_DCB
+ u8 dcb_priority;
+#endif
+ u8 snd_wscale;
+};
+
+void _cxgbit_free_cdev(struct kref *kref);
+void _cxgbit_free_csk(struct kref *kref);
+void _cxgbit_free_cnp(struct kref *kref);
+
+static inline void cxgbit_get_cdev(struct cxgbit_device *cdev)
+{
+ kref_get(&cdev->kref);
+}
+
+static inline void cxgbit_put_cdev(struct cxgbit_device *cdev)
+{
+ kref_put(&cdev->kref, _cxgbit_free_cdev);
+}
+
+static inline void cxgbit_get_csk(struct cxgbit_sock *csk)
+{
+ kref_get(&csk->kref);
+}
+
+static inline void cxgbit_put_csk(struct cxgbit_sock *csk)
+{
+ kref_put(&csk->kref, _cxgbit_free_csk);
+}
+
+static inline void cxgbit_get_cnp(struct cxgbit_np *cnp)
+{
+ kref_get(&cnp->kref);
+}
+
+static inline void cxgbit_put_cnp(struct cxgbit_np *cnp)
+{
+ kref_put(&cnp->kref, _cxgbit_free_cnp);
+}
+
+static inline void cxgbit_sock_reset_wr_list(struct cxgbit_sock *csk)
+{
+ csk->wr_pending_tail = NULL;
+ csk->wr_pending_head = NULL;
+}
+
+static inline struct sk_buff *cxgbit_sock_peek_wr(const struct cxgbit_sock *csk)
+{
+ return csk->wr_pending_head;
+}
+
+static inline void
+cxgbit_sock_enqueue_wr(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ cxgbit_skcb_tx_wr_next(skb) = NULL;
+
+ skb_get(skb);
+
+ if (!csk->wr_pending_head)
+ csk->wr_pending_head = skb;
+ else
+ cxgbit_skcb_tx_wr_next(csk->wr_pending_tail) = skb;
+ csk->wr_pending_tail = skb;
+}
+
+static inline struct sk_buff *cxgbit_sock_dequeue_wr(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb = csk->wr_pending_head;
+
+ if (likely(skb)) {
+ csk->wr_pending_head = cxgbit_skcb_tx_wr_next(skb);
+ cxgbit_skcb_tx_wr_next(skb) = NULL;
+ }
+ return skb;
+}
+
+typedef void (*cxgbit_cplhandler_func)(struct cxgbit_device *,
+ struct sk_buff *);
+
+int cxgbit_setup_np(struct iscsi_np *, struct sockaddr_storage *);
+int cxgbit_setup_conn_digest(struct cxgbit_sock *);
+int cxgbit_accept_np(struct iscsi_np *, struct iscsi_conn *);
+void cxgbit_free_np(struct iscsi_np *);
+void cxgbit_free_conn(struct iscsi_conn *);
+extern cxgbit_cplhandler_func cxgbit_cplhandlers[NUM_CPL_CMDS];
+int cxgbit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
+int cxgbit_rx_data_ack(struct cxgbit_sock *);
+int cxgbit_l2t_send(struct cxgbit_device *, struct sk_buff *,
+ struct l2t_entry *);
+void cxgbit_push_tx_frames(struct cxgbit_sock *);
+int cxgbit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
+int cxgbit_xmit_pdu(struct iscsi_conn *, struct iscsi_cmd *,
+ struct iscsi_datain_req *, const void *, u32);
+void cxgbit_get_r2t_ttt(struct iscsi_conn *, struct iscsi_cmd *,
+ struct iscsi_r2t *);
+u32 cxgbit_send_tx_flowc_wr(struct cxgbit_sock *);
+int cxgbit_ofld_send(struct cxgbit_device *, struct sk_buff *);
+void cxgbit_get_rx_pdu(struct iscsi_conn *);
+int cxgbit_validate_params(struct iscsi_conn *);
+struct cxgbit_device *cxgbit_find_device(struct net_device *, u8 *);
+
+/* DDP */
+int cxgbit_ddp_init(struct cxgbit_device *);
+int cxgbit_setup_conn_pgidx(struct cxgbit_sock *, u32);
+int cxgbit_reserve_ttt(struct cxgbit_sock *, struct iscsi_cmd *);
+void cxgbit_release_cmd(struct iscsi_conn *, struct iscsi_cmd *);
+
+static inline
+struct cxgbi_ppm *cdev2ppm(struct cxgbit_device *cdev)
+{
+ return (struct cxgbi_ppm *)(*cdev->lldi.iscsi_ppm);
+}
+#endif /* __CXGBIT_H__ */
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
new file mode 100644
index 000000000000..0ae0b131abfc
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -0,0 +1,2086 @@
+/*
+ * Copyright (c) 2016 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/timer.h>
+#include <linux/notifier.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/if_vlan.h>
+
+#include <net/neighbour.h>
+#include <net/netevent.h>
+#include <net/route.h>
+#include <net/tcp.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+
+#include "cxgbit.h"
+#include "clip_tbl.h"
+
+static void cxgbit_init_wr_wait(struct cxgbit_wr_wait *wr_waitp)
+{
+ wr_waitp->ret = 0;
+ reinit_completion(&wr_waitp->completion);
+}
+
+static void
+cxgbit_wake_up(struct cxgbit_wr_wait *wr_waitp, const char *func, u8 ret)
+{
+ if (ret == CPL_ERR_NONE)
+ wr_waitp->ret = 0;
+ else
+ wr_waitp->ret = -EIO;
+
+ if (wr_waitp->ret)
+ pr_err("%s: err:%u", func, ret);
+
+ complete(&wr_waitp->completion);
+}
+
+static int
+cxgbit_wait_for_reply(struct cxgbit_device *cdev,
+ struct cxgbit_wr_wait *wr_waitp, u32 tid, u32 timeout,
+ const char *func)
+{
+ int ret;
+
+ if (!test_bit(CDEV_STATE_UP, &cdev->flags)) {
+ wr_waitp->ret = -EIO;
+ goto out;
+ }
+
+ ret = wait_for_completion_timeout(&wr_waitp->completion, timeout * HZ);
+ if (!ret) {
+ pr_info("%s - Device %s not responding tid %u\n",
+ func, pci_name(cdev->lldi.pdev), tid);
+ wr_waitp->ret = -ETIMEDOUT;
+ }
+out:
+ if (wr_waitp->ret)
+ pr_info("%s: FW reply %d tid %u\n",
+ pci_name(cdev->lldi.pdev), wr_waitp->ret, tid);
+ return wr_waitp->ret;
+}
+
+/* Returns whether a CPL status conveys negative advice.
+ */
+static int cxgbit_is_neg_adv(unsigned int status)
+{
+ return status == CPL_ERR_RTX_NEG_ADVICE ||
+ status == CPL_ERR_PERSIST_NEG_ADVICE ||
+ status == CPL_ERR_KEEPALV_NEG_ADVICE;
+}
+
+static int cxgbit_np_hashfn(const struct cxgbit_np *cnp)
+{
+ return ((unsigned long)cnp >> 10) & (NP_INFO_HASH_SIZE - 1);
+}
+
+static struct np_info *
+cxgbit_np_hash_add(struct cxgbit_device *cdev, struct cxgbit_np *cnp,
+ unsigned int stid)
+{
+ struct np_info *p = kzalloc(sizeof(*p), GFP_KERNEL);
+
+ if (p) {
+ int bucket = cxgbit_np_hashfn(cnp);
+
+ p->cnp = cnp;
+ p->stid = stid;
+ spin_lock(&cdev->np_lock);
+ p->next = cdev->np_hash_tab[bucket];
+ cdev->np_hash_tab[bucket] = p;
+ spin_unlock(&cdev->np_lock);
+ }
+
+ return p;
+}
+
+static int
+cxgbit_np_hash_find(struct cxgbit_device *cdev, struct cxgbit_np *cnp)
+{
+ int stid = -1, bucket = cxgbit_np_hashfn(cnp);
+ struct np_info *p;
+
+ spin_lock(&cdev->np_lock);
+ for (p = cdev->np_hash_tab[bucket]; p; p = p->next) {
+ if (p->cnp == cnp) {
+ stid = p->stid;
+ break;
+ }
+ }
+ spin_unlock(&cdev->np_lock);
+
+ return stid;
+}
+
+static int cxgbit_np_hash_del(struct cxgbit_device *cdev, struct cxgbit_np *cnp)
+{
+ int stid = -1, bucket = cxgbit_np_hashfn(cnp);
+ struct np_info *p, **prev = &cdev->np_hash_tab[bucket];
+
+ spin_lock(&cdev->np_lock);
+ for (p = *prev; p; prev = &p->next, p = p->next) {
+ if (p->cnp == cnp) {
+ stid = p->stid;
+ *prev = p->next;
+ kfree(p);
+ break;
+ }
+ }
+ spin_unlock(&cdev->np_lock);
+
+ return stid;
+}
+
+void _cxgbit_free_cnp(struct kref *kref)
+{
+ struct cxgbit_np *cnp;
+
+ cnp = container_of(kref, struct cxgbit_np, kref);
+ kfree(cnp);
+}
+
+static int
+cxgbit_create_server6(struct cxgbit_device *cdev, unsigned int stid,
+ struct cxgbit_np *cnp)
+{
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
+ &cnp->com.local_addr;
+ int addr_type;
+ int ret;
+
+ pr_debug("%s: dev = %s; stid = %u; sin6_port = %u\n",
+ __func__, cdev->lldi.ports[0]->name, stid, sin6->sin6_port);
+
+ addr_type = ipv6_addr_type((const struct in6_addr *)
+ &sin6->sin6_addr);
+ if (addr_type != IPV6_ADDR_ANY) {
+ ret = cxgb4_clip_get(cdev->lldi.ports[0],
+ (const u32 *)&sin6->sin6_addr.s6_addr, 1);
+ if (ret) {
+ pr_err("Unable to find clip table entry. laddr %pI6. Error:%d.\n",
+ sin6->sin6_addr.s6_addr, ret);
+ return -ENOMEM;
+ }
+ }
+
+ cxgbit_get_cnp(cnp);
+ cxgbit_init_wr_wait(&cnp->com.wr_wait);
+
+ ret = cxgb4_create_server6(cdev->lldi.ports[0],
+ stid, &sin6->sin6_addr,
+ sin6->sin6_port,
+ cdev->lldi.rxq_ids[0]);
+ if (!ret)
+ ret = cxgbit_wait_for_reply(cdev, &cnp->com.wr_wait,
+ 0, 10, __func__);
+ else if (ret > 0)
+ ret = net_xmit_errno(ret);
+ else
+ cxgbit_put_cnp(cnp);
+
+ if (ret) {
+ if (ret != -ETIMEDOUT)
+ cxgb4_clip_release(cdev->lldi.ports[0],
+ (const u32 *)&sin6->sin6_addr.s6_addr, 1);
+
+ pr_err("create server6 err %d stid %d laddr %pI6 lport %d\n",
+ ret, stid, sin6->sin6_addr.s6_addr,
+ ntohs(sin6->sin6_port));
+ }
+
+ return ret;
+}
+
+static int
+cxgbit_create_server4(struct cxgbit_device *cdev, unsigned int stid,
+ struct cxgbit_np *cnp)
+{
+ struct sockaddr_in *sin = (struct sockaddr_in *)
+ &cnp->com.local_addr;
+ int ret;
+
+ pr_debug("%s: dev = %s; stid = %u; sin_port = %u\n",
+ __func__, cdev->lldi.ports[0]->name, stid, sin->sin_port);
+
+ cxgbit_get_cnp(cnp);
+ cxgbit_init_wr_wait(&cnp->com.wr_wait);
+
+ ret = cxgb4_create_server(cdev->lldi.ports[0],
+ stid, sin->sin_addr.s_addr,
+ sin->sin_port, 0,
+ cdev->lldi.rxq_ids[0]);
+ if (!ret)
+ ret = cxgbit_wait_for_reply(cdev,
+ &cnp->com.wr_wait,
+ 0, 10, __func__);
+ else if (ret > 0)
+ ret = net_xmit_errno(ret);
+ else
+ cxgbit_put_cnp(cnp);
+
+ if (ret)
+ pr_err("create server failed err %d stid %d laddr %pI4 lport %d\n",
+ ret, stid, &sin->sin_addr, ntohs(sin->sin_port));
+ return ret;
+}
+
+struct cxgbit_device *cxgbit_find_device(struct net_device *ndev, u8 *port_id)
+{
+ struct cxgbit_device *cdev;
+ u8 i;
+
+ list_for_each_entry(cdev, &cdev_list_head, list) {
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+
+ for (i = 0; i < lldi->nports; i++) {
+ if (lldi->ports[i] == ndev) {
+ if (port_id)
+ *port_id = i;
+ return cdev;
+ }
+ }
+ }
+
+ return NULL;
+}
+
+static struct net_device *cxgbit_get_real_dev(struct net_device *ndev)
+{
+ if (ndev->priv_flags & IFF_BONDING) {
+ pr_err("Bond devices are not supported. Interface:%s\n",
+ ndev->name);
+ return NULL;
+ }
+
+ if (is_vlan_dev(ndev))
+ return vlan_dev_real_dev(ndev);
+
+ return ndev;
+}
+
+static struct net_device *cxgbit_ipv4_netdev(__be32 saddr)
+{
+ struct net_device *ndev;
+
+ ndev = __ip_dev_find(&init_net, saddr, false);
+ if (!ndev)
+ return NULL;
+
+ return cxgbit_get_real_dev(ndev);
+}
+
+static struct net_device *cxgbit_ipv6_netdev(struct in6_addr *addr6)
+{
+ struct net_device *ndev = NULL;
+ bool found = false;
+
+ if (IS_ENABLED(CONFIG_IPV6)) {
+ for_each_netdev_rcu(&init_net, ndev)
+ if (ipv6_chk_addr(&init_net, addr6, ndev, 1)) {
+ found = true;
+ break;
+ }
+ }
+ if (!found)
+ return NULL;
+ return cxgbit_get_real_dev(ndev);
+}
+
+static struct cxgbit_device *cxgbit_find_np_cdev(struct cxgbit_np *cnp)
+{
+ struct sockaddr_storage *sockaddr = &cnp->com.local_addr;
+ int ss_family = sockaddr->ss_family;
+ struct net_device *ndev = NULL;
+ struct cxgbit_device *cdev = NULL;
+
+ rcu_read_lock();
+ if (ss_family == AF_INET) {
+ struct sockaddr_in *sin;
+
+ sin = (struct sockaddr_in *)sockaddr;
+ ndev = cxgbit_ipv4_netdev(sin->sin_addr.s_addr);
+ } else if (ss_family == AF_INET6) {
+ struct sockaddr_in6 *sin6;
+
+ sin6 = (struct sockaddr_in6 *)sockaddr;
+ ndev = cxgbit_ipv6_netdev(&sin6->sin6_addr);
+ }
+ if (!ndev)
+ goto out;
+
+ cdev = cxgbit_find_device(ndev, NULL);
+out:
+ rcu_read_unlock();
+ return cdev;
+}
+
+static bool cxgbit_inaddr_any(struct cxgbit_np *cnp)
+{
+ struct sockaddr_storage *sockaddr = &cnp->com.local_addr;
+ int ss_family = sockaddr->ss_family;
+ int addr_type;
+
+ if (ss_family == AF_INET) {
+ struct sockaddr_in *sin;
+
+ sin = (struct sockaddr_in *)sockaddr;
+ if (sin->sin_addr.s_addr == htonl(INADDR_ANY))
+ return true;
+ } else if (ss_family == AF_INET6) {
+ struct sockaddr_in6 *sin6;
+
+ sin6 = (struct sockaddr_in6 *)sockaddr;
+ addr_type = ipv6_addr_type((const struct in6_addr *)
+ &sin6->sin6_addr);
+ if (addr_type == IPV6_ADDR_ANY)
+ return true;
+ }
+ return false;
+}
+
+static int
+__cxgbit_setup_cdev_np(struct cxgbit_device *cdev, struct cxgbit_np *cnp)
+{
+ int stid, ret;
+ int ss_family = cnp->com.local_addr.ss_family;
+
+ if (!test_bit(CDEV_STATE_UP, &cdev->flags))
+ return -EINVAL;
+
+ stid = cxgb4_alloc_stid(cdev->lldi.tids, ss_family, cnp);
+ if (stid < 0)
+ return -EINVAL;
+
+ if (!cxgbit_np_hash_add(cdev, cnp, stid)) {
+ cxgb4_free_stid(cdev->lldi.tids, stid, ss_family);
+ return -EINVAL;
+ }
+
+ if (ss_family == AF_INET)
+ ret = cxgbit_create_server4(cdev, stid, cnp);
+ else
+ ret = cxgbit_create_server6(cdev, stid, cnp);
+
+ if (ret) {
+ if (ret != -ETIMEDOUT)
+ cxgb4_free_stid(cdev->lldi.tids, stid,
+ ss_family);
+ cxgbit_np_hash_del(cdev, cnp);
+ return ret;
+ }
+ return ret;
+}
+
+static int cxgbit_setup_cdev_np(struct cxgbit_np *cnp)
+{
+ struct cxgbit_device *cdev;
+ int ret = -1;
+
+ mutex_lock(&cdev_list_lock);
+ cdev = cxgbit_find_np_cdev(cnp);
+ if (!cdev)
+ goto out;
+
+ if (cxgbit_np_hash_find(cdev, cnp) >= 0)
+ goto out;
+
+ if (__cxgbit_setup_cdev_np(cdev, cnp))
+ goto out;
+
+ cnp->com.cdev = cdev;
+ ret = 0;
+out:
+ mutex_unlock(&cdev_list_lock);
+ return ret;
+}
+
+static int cxgbit_setup_all_np(struct cxgbit_np *cnp)
+{
+ struct cxgbit_device *cdev;
+ int ret;
+ u32 count = 0;
+
+ mutex_lock(&cdev_list_lock);
+ list_for_each_entry(cdev, &cdev_list_head, list) {
+ if (cxgbit_np_hash_find(cdev, cnp) >= 0) {
+ mutex_unlock(&cdev_list_lock);
+ return -1;
+ }
+ }
+
+ list_for_each_entry(cdev, &cdev_list_head, list) {
+ ret = __cxgbit_setup_cdev_np(cdev, cnp);
+ if (ret == -ETIMEDOUT)
+ break;
+ if (ret != 0)
+ continue;
+ count++;
+ }
+ mutex_unlock(&cdev_list_lock);
+
+ return count ? 0 : -1;
+}
+
+int cxgbit_setup_np(struct iscsi_np *np, struct sockaddr_storage *ksockaddr)
+{
+ struct cxgbit_np *cnp;
+ int ret;
+
+ if ((ksockaddr->ss_family != AF_INET) &&
+ (ksockaddr->ss_family != AF_INET6))
+ return -EINVAL;
+
+ cnp = kzalloc(sizeof(*cnp), GFP_KERNEL);
+ if (!cnp)
+ return -ENOMEM;
+
+ init_waitqueue_head(&cnp->accept_wait);
+ init_completion(&cnp->com.wr_wait.completion);
+ init_completion(&cnp->accept_comp);
+ INIT_LIST_HEAD(&cnp->np_accept_list);
+ spin_lock_init(&cnp->np_accept_lock);
+ kref_init(&cnp->kref);
+ memcpy(&np->np_sockaddr, ksockaddr,
+ sizeof(struct sockaddr_storage));
+ memcpy(&cnp->com.local_addr, &np->np_sockaddr,
+ sizeof(cnp->com.local_addr));
+
+ cnp->np = np;
+ cnp->com.cdev = NULL;
+
+ if (cxgbit_inaddr_any(cnp))
+ ret = cxgbit_setup_all_np(cnp);
+ else
+ ret = cxgbit_setup_cdev_np(cnp);
+
+ if (ret) {
+ cxgbit_put_cnp(cnp);
+ return -EINVAL;
+ }
+
+ np->np_context = cnp;
+ cnp->com.state = CSK_STATE_LISTEN;
+ return 0;
+}
+
+static void
+cxgbit_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn,
+ struct cxgbit_sock *csk)
+{
+ conn->login_family = np->np_sockaddr.ss_family;
+ conn->login_sockaddr = csk->com.remote_addr;
+ conn->local_sockaddr = csk->com.local_addr;
+}
+
+int cxgbit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
+{
+ struct cxgbit_np *cnp = np->np_context;
+ struct cxgbit_sock *csk;
+ int ret = 0;
+
+accept_wait:
+ ret = wait_for_completion_interruptible(&cnp->accept_comp);
+ if (ret)
+ return -ENODEV;
+
+ spin_lock_bh(&np->np_thread_lock);
+ if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) {
+ spin_unlock_bh(&np->np_thread_lock);
+ /**
+ * No point in stalling here when np_thread
+ * is in state RESET/SHUTDOWN/EXIT - bail
+ **/
+ return -ENODEV;
+ }
+ spin_unlock_bh(&np->np_thread_lock);
+
+ spin_lock_bh(&cnp->np_accept_lock);
+ if (list_empty(&cnp->np_accept_list)) {
+ spin_unlock_bh(&cnp->np_accept_lock);
+ goto accept_wait;
+ }
+
+ csk = list_first_entry(&cnp->np_accept_list,
+ struct cxgbit_sock,
+ accept_node);
+
+ list_del_init(&csk->accept_node);
+ spin_unlock_bh(&cnp->np_accept_lock);
+ conn->context = csk;
+ csk->conn = conn;
+
+ cxgbit_set_conn_info(np, conn, csk);
+ return 0;
+}
+
+static int
+__cxgbit_free_cdev_np(struct cxgbit_device *cdev, struct cxgbit_np *cnp)
+{
+ int stid, ret;
+ bool ipv6 = false;
+
+ stid = cxgbit_np_hash_del(cdev, cnp);
+ if (stid < 0)
+ return -EINVAL;
+ if (!test_bit(CDEV_STATE_UP, &cdev->flags))
+ return -EINVAL;
+
+ if (cnp->np->np_sockaddr.ss_family == AF_INET6)
+ ipv6 = true;
+
+ cxgbit_get_cnp(cnp);
+ cxgbit_init_wr_wait(&cnp->com.wr_wait);
+ ret = cxgb4_remove_server(cdev->lldi.ports[0], stid,
+ cdev->lldi.rxq_ids[0], ipv6);
+
+ if (ret > 0)
+ ret = net_xmit_errno(ret);
+
+ if (ret) {
+ cxgbit_put_cnp(cnp);
+ return ret;
+ }
+
+ ret = cxgbit_wait_for_reply(cdev, &cnp->com.wr_wait,
+ 0, 10, __func__);
+ if (ret == -ETIMEDOUT)
+ return ret;
+
+ if (ipv6 && cnp->com.cdev) {
+ struct sockaddr_in6 *sin6;
+
+ sin6 = (struct sockaddr_in6 *)&cnp->com.local_addr;
+ cxgb4_clip_release(cdev->lldi.ports[0],
+ (const u32 *)&sin6->sin6_addr.s6_addr,
+ 1);
+ }
+
+ cxgb4_free_stid(cdev->lldi.tids, stid,
+ cnp->com.local_addr.ss_family);
+ return 0;
+}
+
+static void cxgbit_free_all_np(struct cxgbit_np *cnp)
+{
+ struct cxgbit_device *cdev;
+ int ret;
+
+ mutex_lock(&cdev_list_lock);
+ list_for_each_entry(cdev, &cdev_list_head, list) {
+ ret = __cxgbit_free_cdev_np(cdev, cnp);
+ if (ret == -ETIMEDOUT)
+ break;
+ }
+ mutex_unlock(&cdev_list_lock);
+}
+
+static void cxgbit_free_cdev_np(struct cxgbit_np *cnp)
+{
+ struct cxgbit_device *cdev;
+ bool found = false;
+
+ mutex_lock(&cdev_list_lock);
+ list_for_each_entry(cdev, &cdev_list_head, list) {
+ if (cdev == cnp->com.cdev) {
+ found = true;
+ break;
+ }
+ }
+ if (!found)
+ goto out;
+
+ __cxgbit_free_cdev_np(cdev, cnp);
+out:
+ mutex_unlock(&cdev_list_lock);
+}
+
+void cxgbit_free_np(struct iscsi_np *np)
+{
+ struct cxgbit_np *cnp = np->np_context;
+
+ cnp->com.state = CSK_STATE_DEAD;
+ if (cnp->com.cdev)
+ cxgbit_free_cdev_np(cnp);
+ else
+ cxgbit_free_all_np(cnp);
+
+ np->np_context = NULL;
+ cxgbit_put_cnp(cnp);
+}
+
+static void cxgbit_send_halfclose(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+ struct cpl_close_con_req *req;
+ unsigned int len = roundup(sizeof(struct cpl_close_con_req), 16);
+
+ skb = alloc_skb(len, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ req = (struct cpl_close_con_req *)__skb_put(skb, len);
+ memset(req, 0, len);
+
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ INIT_TP_WR(req, csk->tid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ,
+ csk->tid));
+ req->rsvd = 0;
+
+ cxgbit_skcb_flags(skb) |= SKCBF_TX_FLAG_COMPL;
+ __skb_queue_tail(&csk->txq, skb);
+ cxgbit_push_tx_frames(csk);
+}
+
+static void cxgbit_arp_failure_discard(void *handle, struct sk_buff *skb)
+{
+ pr_debug("%s cxgbit_device %p\n", __func__, handle);
+ kfree_skb(skb);
+}
+
+static void cxgbit_abort_arp_failure(void *handle, struct sk_buff *skb)
+{
+ struct cxgbit_device *cdev = handle;
+ struct cpl_abort_req *req = cplhdr(skb);
+
+ pr_debug("%s cdev %p\n", __func__, cdev);
+ req->cmd = CPL_ABORT_NO_RST;
+ cxgbit_ofld_send(cdev, skb);
+}
+
+static int cxgbit_send_abort_req(struct cxgbit_sock *csk)
+{
+ struct cpl_abort_req *req;
+ unsigned int len = roundup(sizeof(*req), 16);
+ struct sk_buff *skb;
+
+ pr_debug("%s: csk %p tid %u; state %d\n",
+ __func__, csk, csk->tid, csk->com.state);
+
+ __skb_queue_purge(&csk->txq);
+
+ if (!test_and_set_bit(CSK_TX_DATA_SENT, &csk->com.flags))
+ cxgbit_send_tx_flowc_wr(csk);
+
+ skb = __skb_dequeue(&csk->skbq);
+ req = (struct cpl_abort_req *)__skb_put(skb, len);
+ memset(req, 0, len);
+
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ t4_set_arp_err_handler(skb, csk->com.cdev, cxgbit_abort_arp_failure);
+ INIT_TP_WR(req, csk->tid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ,
+ csk->tid));
+ req->cmd = CPL_ABORT_SEND_RST;
+ return cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t);
+}
+
+void cxgbit_free_conn(struct iscsi_conn *conn)
+{
+ struct cxgbit_sock *csk = conn->context;
+ bool release = false;
+
+ pr_debug("%s: state %d\n",
+ __func__, csk->com.state);
+
+ spin_lock_bh(&csk->lock);
+ switch (csk->com.state) {
+ case CSK_STATE_ESTABLISHED:
+ if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) {
+ csk->com.state = CSK_STATE_CLOSING;
+ cxgbit_send_halfclose(csk);
+ } else {
+ csk->com.state = CSK_STATE_ABORTING;
+ cxgbit_send_abort_req(csk);
+ }
+ break;
+ case CSK_STATE_CLOSING:
+ csk->com.state = CSK_STATE_MORIBUND;
+ cxgbit_send_halfclose(csk);
+ break;
+ case CSK_STATE_DEAD:
+ release = true;
+ break;
+ default:
+ pr_err("%s: csk %p; state %d\n",
+ __func__, csk, csk->com.state);
+ }
+ spin_unlock_bh(&csk->lock);
+
+ if (release)
+ cxgbit_put_csk(csk);
+}
+
+static void cxgbit_set_emss(struct cxgbit_sock *csk, u16 opt)
+{
+ csk->emss = csk->com.cdev->lldi.mtus[TCPOPT_MSS_G(opt)] -
+ ((csk->com.remote_addr.ss_family == AF_INET) ?
+ sizeof(struct iphdr) : sizeof(struct ipv6hdr)) -
+ sizeof(struct tcphdr);
+ csk->mss = csk->emss;
+ if (TCPOPT_TSTAMP_G(opt))
+ csk->emss -= round_up(TCPOLEN_TIMESTAMP, 4);
+ if (csk->emss < 128)
+ csk->emss = 128;
+ if (csk->emss & 7)
+ pr_info("Warning: misaligned mtu idx %u mss %u emss=%u\n",
+ TCPOPT_MSS_G(opt), csk->mss, csk->emss);
+ pr_debug("%s mss_idx %u mss %u emss=%u\n", __func__, TCPOPT_MSS_G(opt),
+ csk->mss, csk->emss);
+}
+
+static void cxgbit_free_skb(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+
+ __skb_queue_purge(&csk->txq);
+ __skb_queue_purge(&csk->rxq);
+ __skb_queue_purge(&csk->backlogq);
+ __skb_queue_purge(&csk->ppodq);
+ __skb_queue_purge(&csk->skbq);
+
+ while ((skb = cxgbit_sock_dequeue_wr(csk)))
+ kfree_skb(skb);
+
+ __kfree_skb(csk->lro_hskb);
+}
+
+void _cxgbit_free_csk(struct kref *kref)
+{
+ struct cxgbit_sock *csk;
+ struct cxgbit_device *cdev;
+
+ csk = container_of(kref, struct cxgbit_sock, kref);
+
+ pr_debug("%s csk %p state %d\n", __func__, csk, csk->com.state);
+
+ if (csk->com.local_addr.ss_family == AF_INET6) {
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
+ &csk->com.local_addr;
+ cxgb4_clip_release(csk->com.cdev->lldi.ports[0],
+ (const u32 *)
+ &sin6->sin6_addr.s6_addr, 1);
+ }
+
+ cxgb4_remove_tid(csk->com.cdev->lldi.tids, 0, csk->tid);
+ dst_release(csk->dst);
+ cxgb4_l2t_release(csk->l2t);
+
+ cdev = csk->com.cdev;
+ spin_lock_bh(&cdev->cskq.lock);
+ list_del(&csk->list);
+ spin_unlock_bh(&cdev->cskq.lock);
+
+ cxgbit_free_skb(csk);
+ cxgbit_put_cdev(cdev);
+
+ kfree(csk);
+}
+
+static void
+cxgbit_get_tuple_info(struct cpl_pass_accept_req *req, int *iptype,
+ __u8 *local_ip, __u8 *peer_ip, __be16 *local_port,
+ __be16 *peer_port)
+{
+ u32 eth_len = ETH_HDR_LEN_G(be32_to_cpu(req->hdr_len));
+ u32 ip_len = IP_HDR_LEN_G(be32_to_cpu(req->hdr_len));
+ struct iphdr *ip = (struct iphdr *)((u8 *)(req + 1) + eth_len);
+ struct ipv6hdr *ip6 = (struct ipv6hdr *)((u8 *)(req + 1) + eth_len);
+ struct tcphdr *tcp = (struct tcphdr *)
+ ((u8 *)(req + 1) + eth_len + ip_len);
+
+ if (ip->version == 4) {
+ pr_debug("%s saddr 0x%x daddr 0x%x sport %u dport %u\n",
+ __func__,
+ ntohl(ip->saddr), ntohl(ip->daddr),
+ ntohs(tcp->source),
+ ntohs(tcp->dest));
+ *iptype = 4;
+ memcpy(peer_ip, &ip->saddr, 4);
+ memcpy(local_ip, &ip->daddr, 4);
+ } else {
+ pr_debug("%s saddr %pI6 daddr %pI6 sport %u dport %u\n",
+ __func__,
+ ip6->saddr.s6_addr, ip6->daddr.s6_addr,
+ ntohs(tcp->source),
+ ntohs(tcp->dest));
+ *iptype = 6;
+ memcpy(peer_ip, ip6->saddr.s6_addr, 16);
+ memcpy(local_ip, ip6->daddr.s6_addr, 16);
+ }
+
+ *peer_port = tcp->source;
+ *local_port = tcp->dest;
+}
+
+static int
+cxgbit_our_interface(struct cxgbit_device *cdev, struct net_device *egress_dev)
+{
+ u8 i;
+
+ egress_dev = cxgbit_get_real_dev(egress_dev);
+ for (i = 0; i < cdev->lldi.nports; i++)
+ if (cdev->lldi.ports[i] == egress_dev)
+ return 1;
+ return 0;
+}
+
+static struct dst_entry *
+cxgbit_find_route6(struct cxgbit_device *cdev, __u8 *local_ip, __u8 *peer_ip,
+ __be16 local_port, __be16 peer_port, u8 tos,
+ __u32 sin6_scope_id)
+{
+ struct dst_entry *dst = NULL;
+
+ if (IS_ENABLED(CONFIG_IPV6)) {
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ memcpy(&fl6.daddr, peer_ip, 16);
+ memcpy(&fl6.saddr, local_ip, 16);
+ if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
+ fl6.flowi6_oif = sin6_scope_id;
+ dst = ip6_route_output(&init_net, NULL, &fl6);
+ if (!dst)
+ goto out;
+ if (!cxgbit_our_interface(cdev, ip6_dst_idev(dst)->dev) &&
+ !(ip6_dst_idev(dst)->dev->flags & IFF_LOOPBACK)) {
+ dst_release(dst);
+ dst = NULL;
+ }
+ }
+out:
+ return dst;
+}
+
+static struct dst_entry *
+cxgbit_find_route(struct cxgbit_device *cdev, __be32 local_ip, __be32 peer_ip,
+ __be16 local_port, __be16 peer_port, u8 tos)
+{
+ struct rtable *rt;
+ struct flowi4 fl4;
+ struct neighbour *n;
+
+ rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip,
+ local_ip,
+ peer_port, local_port, IPPROTO_TCP,
+ tos, 0);
+ if (IS_ERR(rt))
+ return NULL;
+ n = dst_neigh_lookup(&rt->dst, &peer_ip);
+ if (!n)
+ return NULL;
+ if (!cxgbit_our_interface(cdev, n->dev) &&
+ !(n->dev->flags & IFF_LOOPBACK)) {
+ neigh_release(n);
+ dst_release(&rt->dst);
+ return NULL;
+ }
+ neigh_release(n);
+ return &rt->dst;
+}
+
+static void cxgbit_set_tcp_window(struct cxgbit_sock *csk, struct port_info *pi)
+{
+ unsigned int linkspeed;
+ u8 scale;
+
+ linkspeed = pi->link_cfg.speed;
+ scale = linkspeed / SPEED_10000;
+
+#define CXGBIT_10G_RCV_WIN (256 * 1024)
+ csk->rcv_win = CXGBIT_10G_RCV_WIN;
+ if (scale)
+ csk->rcv_win *= scale;
+
+#define CXGBIT_10G_SND_WIN (256 * 1024)
+ csk->snd_win = CXGBIT_10G_SND_WIN;
+ if (scale)
+ csk->snd_win *= scale;
+
+ pr_debug("%s snd_win %d rcv_win %d\n",
+ __func__, csk->snd_win, csk->rcv_win);
+}
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+static u8 cxgbit_get_iscsi_dcb_state(struct net_device *ndev)
+{
+ return ndev->dcbnl_ops->getstate(ndev);
+}
+
+static int cxgbit_select_priority(int pri_mask)
+{
+ if (!pri_mask)
+ return 0;
+
+ return (ffs(pri_mask) - 1);
+}
+
+static u8 cxgbit_get_iscsi_dcb_priority(struct net_device *ndev, u16 local_port)
+{
+ int ret;
+ u8 caps;
+
+ struct dcb_app iscsi_dcb_app = {
+ .protocol = local_port
+ };
+
+ ret = (int)ndev->dcbnl_ops->getcap(ndev, DCB_CAP_ATTR_DCBX, &caps);
+
+ if (ret)
+ return 0;
+
+ if (caps & DCB_CAP_DCBX_VER_IEEE) {
+ iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY;
+
+ ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app);
+
+ } else if (caps & DCB_CAP_DCBX_VER_CEE) {
+ iscsi_dcb_app.selector = DCB_APP_IDTYPE_PORTNUM;
+
+ ret = dcb_getapp(ndev, &iscsi_dcb_app);
+ }
+
+ pr_info("iSCSI priority is set to %u\n", cxgbit_select_priority(ret));
+
+ return cxgbit_select_priority(ret);
+}
+#endif
+
+static int
+cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip,
+ u16 local_port, struct dst_entry *dst,
+ struct cxgbit_device *cdev)
+{
+ struct neighbour *n;
+ int ret, step;
+ struct net_device *ndev;
+ u16 rxq_idx, port_id;
+#ifdef CONFIG_CHELSIO_T4_DCB
+ u8 priority = 0;
+#endif
+
+ n = dst_neigh_lookup(dst, peer_ip);
+ if (!n)
+ return -ENODEV;
+
+ rcu_read_lock();
+ ret = -ENOMEM;
+ if (n->dev->flags & IFF_LOOPBACK) {
+ if (iptype == 4)
+ ndev = cxgbit_ipv4_netdev(*(__be32 *)peer_ip);
+ else if (IS_ENABLED(CONFIG_IPV6))
+ ndev = cxgbit_ipv6_netdev((struct in6_addr *)peer_ip);
+ else
+ ndev = NULL;
+
+ if (!ndev) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ csk->l2t = cxgb4_l2t_get(cdev->lldi.l2t,
+ n, ndev, 0);
+ if (!csk->l2t)
+ goto out;
+ csk->mtu = ndev->mtu;
+ csk->tx_chan = cxgb4_port_chan(ndev);
+ csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1;
+ step = cdev->lldi.ntxq /
+ cdev->lldi.nchan;
+ csk->txq_idx = cxgb4_port_idx(ndev) * step;
+ step = cdev->lldi.nrxq /
+ cdev->lldi.nchan;
+ csk->ctrlq_idx = cxgb4_port_idx(ndev);
+ csk->rss_qid = cdev->lldi.rxq_ids[
+ cxgb4_port_idx(ndev) * step];
+ csk->port_id = cxgb4_port_idx(ndev);
+ cxgbit_set_tcp_window(csk,
+ (struct port_info *)netdev_priv(ndev));
+ } else {
+ ndev = cxgbit_get_real_dev(n->dev);
+ if (!ndev) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+ if (cxgbit_get_iscsi_dcb_state(ndev))
+ priority = cxgbit_get_iscsi_dcb_priority(ndev,
+ local_port);
+
+ csk->dcb_priority = priority;
+
+ csk->l2t = cxgb4_l2t_get(cdev->lldi.l2t, n, ndev, priority);
+#else
+ csk->l2t = cxgb4_l2t_get(cdev->lldi.l2t, n, ndev, 0);
+#endif
+ if (!csk->l2t)
+ goto out;
+ port_id = cxgb4_port_idx(ndev);
+ csk->mtu = dst_mtu(dst);
+ csk->tx_chan = cxgb4_port_chan(ndev);
+ csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1;
+ step = cdev->lldi.ntxq /
+ cdev->lldi.nports;
+ csk->txq_idx = (port_id * step) +
+ (cdev->selectq[port_id][0]++ % step);
+ csk->ctrlq_idx = cxgb4_port_idx(ndev);
+ step = cdev->lldi.nrxq /
+ cdev->lldi.nports;
+ rxq_idx = (port_id * step) +
+ (cdev->selectq[port_id][1]++ % step);
+ csk->rss_qid = cdev->lldi.rxq_ids[rxq_idx];
+ csk->port_id = port_id;
+ cxgbit_set_tcp_window(csk,
+ (struct port_info *)netdev_priv(ndev));
+ }
+ ret = 0;
+out:
+ rcu_read_unlock();
+ neigh_release(n);
+ return ret;
+}
+
+int cxgbit_ofld_send(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ int ret = 0;
+
+ if (!test_bit(CDEV_STATE_UP, &cdev->flags)) {
+ kfree_skb(skb);
+ pr_err("%s - device not up - dropping\n", __func__);
+ return -EIO;
+ }
+
+ ret = cxgb4_ofld_send(cdev->lldi.ports[0], skb);
+ if (ret < 0)
+ kfree_skb(skb);
+ return ret < 0 ? ret : 0;
+}
+
+static void cxgbit_release_tid(struct cxgbit_device *cdev, u32 tid)
+{
+ struct cpl_tid_release *req;
+ unsigned int len = roundup(sizeof(*req), 16);
+ struct sk_buff *skb;
+
+ skb = alloc_skb(len, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ req = (struct cpl_tid_release *)__skb_put(skb, len);
+ memset(req, 0, len);
+
+ INIT_TP_WR(req, tid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(
+ CPL_TID_RELEASE, tid));
+ set_wr_txq(skb, CPL_PRIORITY_SETUP, 0);
+ cxgbit_ofld_send(cdev, skb);
+}
+
+int
+cxgbit_l2t_send(struct cxgbit_device *cdev, struct sk_buff *skb,
+ struct l2t_entry *l2e)
+{
+ int ret = 0;
+
+ if (!test_bit(CDEV_STATE_UP, &cdev->flags)) {
+ kfree_skb(skb);
+ pr_err("%s - device not up - dropping\n", __func__);
+ return -EIO;
+ }
+
+ ret = cxgb4_l2t_send(cdev->lldi.ports[0], skb, l2e);
+ if (ret < 0)
+ kfree_skb(skb);
+ return ret < 0 ? ret : 0;
+}
+
+static void
+cxgbit_best_mtu(const unsigned short *mtus, unsigned short mtu,
+ unsigned int *idx, int use_ts, int ipv6)
+{
+ unsigned short hdr_size = (ipv6 ? sizeof(struct ipv6hdr) :
+ sizeof(struct iphdr)) +
+ sizeof(struct tcphdr) +
+ (use_ts ? round_up(TCPOLEN_TIMESTAMP,
+ 4) : 0);
+ unsigned short data_size = mtu - hdr_size;
+
+ cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx);
+}
+
+static void cxgbit_send_rx_credits(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ if (csk->com.state != CSK_STATE_ESTABLISHED) {
+ __kfree_skb(skb);
+ return;
+ }
+
+ cxgbit_ofld_send(csk->com.cdev, skb);
+}
+
+/*
+ * CPL connection rx data ack: host ->
+ * Send RX credits through an RX_DATA_ACK CPL message.
+ * Returns the number of credits sent.
+ */
+int cxgbit_rx_data_ack(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+ struct cpl_rx_data_ack *req;
+ unsigned int len = roundup(sizeof(*req), 16);
+
+ skb = alloc_skb(len, GFP_KERNEL);
+ if (!skb)
+ return -1;
+
+ req = (struct cpl_rx_data_ack *)__skb_put(skb, len);
+ memset(req, 0, len);
+
+ set_wr_txq(skb, CPL_PRIORITY_ACK, csk->ctrlq_idx);
+ INIT_TP_WR(req, csk->tid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK,
+ csk->tid));
+ req->credit_dack = cpu_to_be32(RX_DACK_CHANGE_F | RX_DACK_MODE_V(1) |
+ RX_CREDITS_V(csk->rx_credits));
+
+ csk->rx_credits = 0;
+
+ spin_lock_bh(&csk->lock);
+ if (csk->lock_owner) {
+ cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_send_rx_credits;
+ __skb_queue_tail(&csk->backlogq, skb);
+ spin_unlock_bh(&csk->lock);
+ return 0;
+ }
+
+ cxgbit_send_rx_credits(csk, skb);
+ spin_unlock_bh(&csk->lock);
+
+ return 0;
+}
+
+#define FLOWC_WR_NPARAMS_MIN 9
+#define FLOWC_WR_NPARAMS_MAX 11
+static int cxgbit_alloc_csk_skb(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+ u32 len, flowclen;
+ u8 i;
+
+ flowclen = offsetof(struct fw_flowc_wr,
+ mnemval[FLOWC_WR_NPARAMS_MAX]);
+
+ len = max_t(u32, sizeof(struct cpl_abort_req),
+ sizeof(struct cpl_abort_rpl));
+
+ len = max(len, flowclen);
+ len = roundup(len, 16);
+
+ for (i = 0; i < 3; i++) {
+ skb = alloc_skb(len, GFP_ATOMIC);
+ if (!skb)
+ goto out;
+ __skb_queue_tail(&csk->skbq, skb);
+ }
+
+ skb = alloc_skb(LRO_SKB_MIN_HEADROOM, GFP_ATOMIC);
+ if (!skb)
+ goto out;
+
+ memset(skb->data, 0, LRO_SKB_MIN_HEADROOM);
+ csk->lro_hskb = skb;
+
+ return 0;
+out:
+ __skb_queue_purge(&csk->skbq);
+ return -ENOMEM;
+}
+
+static u32 cxgbit_compute_wscale(u32 win)
+{
+ u32 wscale = 0;
+
+ while (wscale < 14 && (65535 << wscale) < win)
+ wscale++;
+ return wscale;
+}
+
+static void
+cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req)
+{
+ struct sk_buff *skb;
+ const struct tcphdr *tcph;
+ struct cpl_t5_pass_accept_rpl *rpl5;
+ unsigned int len = roundup(sizeof(*rpl5), 16);
+ unsigned int mtu_idx;
+ u64 opt0;
+ u32 opt2, hlen;
+ u32 wscale;
+ u32 win;
+
+ pr_debug("%s csk %p tid %u\n", __func__, csk, csk->tid);
+
+ skb = alloc_skb(len, GFP_ATOMIC);
+ if (!skb) {
+ cxgbit_put_csk(csk);
+ return;
+ }
+
+ rpl5 = (struct cpl_t5_pass_accept_rpl *)__skb_put(skb, len);
+ memset(rpl5, 0, len);
+
+ INIT_TP_WR(rpl5, csk->tid);
+ OPCODE_TID(rpl5) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
+ csk->tid));
+ cxgbit_best_mtu(csk->com.cdev->lldi.mtus, csk->mtu, &mtu_idx,
+ req->tcpopt.tstamp,
+ (csk->com.remote_addr.ss_family == AF_INET) ? 0 : 1);
+ wscale = cxgbit_compute_wscale(csk->rcv_win);
+ /*
+ * Specify the largest window that will fit in opt0. The
+ * remainder will be specified in the rx_data_ack.
+ */
+ win = csk->rcv_win >> 10;
+ if (win > RCV_BUFSIZ_M)
+ win = RCV_BUFSIZ_M;
+ opt0 = TCAM_BYPASS_F |
+ WND_SCALE_V(wscale) |
+ MSS_IDX_V(mtu_idx) |
+ L2T_IDX_V(csk->l2t->idx) |
+ TX_CHAN_V(csk->tx_chan) |
+ SMAC_SEL_V(csk->smac_idx) |
+ DSCP_V(csk->tos >> 2) |
+ ULP_MODE_V(ULP_MODE_ISCSI) |
+ RCV_BUFSIZ_V(win);
+
+ opt2 = RX_CHANNEL_V(0) |
+ RSS_QUEUE_VALID_F | RSS_QUEUE_V(csk->rss_qid);
+
+ if (req->tcpopt.tstamp)
+ opt2 |= TSTAMPS_EN_F;
+ if (req->tcpopt.sack)
+ opt2 |= SACK_EN_F;
+ if (wscale)
+ opt2 |= WND_SCALE_EN_F;
+
+ hlen = ntohl(req->hdr_len);
+ tcph = (const void *)(req + 1) + ETH_HDR_LEN_G(hlen) +
+ IP_HDR_LEN_G(hlen);
+
+ if (tcph->ece && tcph->cwr)
+ opt2 |= CCTRL_ECN_V(1);
+
+ opt2 |= RX_COALESCE_V(3);
+ opt2 |= CONG_CNTRL_V(CONG_ALG_NEWRENO);
+
+ opt2 |= T5_ISS_F;
+ rpl5->iss = cpu_to_be32((prandom_u32() & ~7UL) - 1);
+
+ opt2 |= T5_OPT_2_VALID_F;
+
+ rpl5->opt0 = cpu_to_be64(opt0);
+ rpl5->opt2 = cpu_to_be32(opt2);
+ set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->ctrlq_idx);
+ t4_set_arp_err_handler(skb, NULL, cxgbit_arp_failure_discard);
+ cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t);
+}
+
+static void
+cxgbit_pass_accept_req(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cxgbit_sock *csk = NULL;
+ struct cxgbit_np *cnp;
+ struct cpl_pass_accept_req *req = cplhdr(skb);
+ unsigned int stid = PASS_OPEN_TID_G(ntohl(req->tos_stid));
+ struct tid_info *t = cdev->lldi.tids;
+ unsigned int tid = GET_TID(req);
+ u16 peer_mss = ntohs(req->tcpopt.mss);
+ unsigned short hdrs;
+
+ struct dst_entry *dst;
+ __u8 local_ip[16], peer_ip[16];
+ __be16 local_port, peer_port;
+ int ret;
+ int iptype;
+
+ pr_debug("%s: cdev = %p; stid = %u; tid = %u\n",
+ __func__, cdev, stid, tid);
+
+ cnp = lookup_stid(t, stid);
+ if (!cnp) {
+ pr_err("%s connect request on invalid stid %d\n",
+ __func__, stid);
+ goto rel_skb;
+ }
+
+ if (cnp->com.state != CSK_STATE_LISTEN) {
+ pr_err("%s - listening parent not in CSK_STATE_LISTEN\n",
+ __func__);
+ goto reject;
+ }
+
+ csk = lookup_tid(t, tid);
+ if (csk) {
+ pr_err("%s csk not null tid %u\n",
+ __func__, tid);
+ goto rel_skb;
+ }
+
+ cxgbit_get_tuple_info(req, &iptype, local_ip, peer_ip,
+ &local_port, &peer_port);
+
+ /* Find output route */
+ if (iptype == 4) {
+ pr_debug("%s parent sock %p tid %u laddr %pI4 raddr %pI4 "
+ "lport %d rport %d peer_mss %d\n"
+ , __func__, cnp, tid,
+ local_ip, peer_ip, ntohs(local_port),
+ ntohs(peer_port), peer_mss);
+ dst = cxgbit_find_route(cdev, *(__be32 *)local_ip,
+ *(__be32 *)peer_ip,
+ local_port, peer_port,
+ PASS_OPEN_TOS_G(ntohl(req->tos_stid)));
+ } else {
+ pr_debug("%s parent sock %p tid %u laddr %pI6 raddr %pI6 "
+ "lport %d rport %d peer_mss %d\n"
+ , __func__, cnp, tid,
+ local_ip, peer_ip, ntohs(local_port),
+ ntohs(peer_port), peer_mss);
+ dst = cxgbit_find_route6(cdev, local_ip, peer_ip,
+ local_port, peer_port,
+ PASS_OPEN_TOS_G(ntohl(req->tos_stid)),
+ ((struct sockaddr_in6 *)
+ &cnp->com.local_addr)->sin6_scope_id);
+ }
+ if (!dst) {
+ pr_err("%s - failed to find dst entry!\n",
+ __func__);
+ goto reject;
+ }
+
+ csk = kzalloc(sizeof(*csk), GFP_ATOMIC);
+ if (!csk) {
+ dst_release(dst);
+ goto rel_skb;
+ }
+
+ ret = cxgbit_offload_init(csk, iptype, peer_ip, ntohs(local_port),
+ dst, cdev);
+ if (ret) {
+ pr_err("%s - failed to allocate l2t entry!\n",
+ __func__);
+ dst_release(dst);
+ kfree(csk);
+ goto reject;
+ }
+
+ kref_init(&csk->kref);
+ init_completion(&csk->com.wr_wait.completion);
+
+ INIT_LIST_HEAD(&csk->accept_node);
+
+ hdrs = (iptype == 4 ? sizeof(struct iphdr) : sizeof(struct ipv6hdr)) +
+ sizeof(struct tcphdr) + (req->tcpopt.tstamp ? 12 : 0);
+ if (peer_mss && csk->mtu > (peer_mss + hdrs))
+ csk->mtu = peer_mss + hdrs;
+
+ csk->com.state = CSK_STATE_CONNECTING;
+ csk->com.cdev = cdev;
+ csk->cnp = cnp;
+ csk->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid));
+ csk->dst = dst;
+ csk->tid = tid;
+ csk->wr_cred = cdev->lldi.wr_cred -
+ DIV_ROUND_UP(sizeof(struct cpl_abort_req), 16);
+ csk->wr_max_cred = csk->wr_cred;
+ csk->wr_una_cred = 0;
+
+ if (iptype == 4) {
+ struct sockaddr_in *sin = (struct sockaddr_in *)
+ &csk->com.local_addr;
+ sin->sin_family = AF_INET;
+ sin->sin_port = local_port;
+ sin->sin_addr.s_addr = *(__be32 *)local_ip;
+
+ sin = (struct sockaddr_in *)&csk->com.remote_addr;
+ sin->sin_family = AF_INET;
+ sin->sin_port = peer_port;
+ sin->sin_addr.s_addr = *(__be32 *)peer_ip;
+ } else {
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
+ &csk->com.local_addr;
+
+ sin6->sin6_family = PF_INET6;
+ sin6->sin6_port = local_port;
+ memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
+ cxgb4_clip_get(cdev->lldi.ports[0],
+ (const u32 *)&sin6->sin6_addr.s6_addr,
+ 1);
+
+ sin6 = (struct sockaddr_in6 *)&csk->com.remote_addr;
+ sin6->sin6_family = PF_INET6;
+ sin6->sin6_port = peer_port;
+ memcpy(sin6->sin6_addr.s6_addr, peer_ip, 16);
+ }
+
+ skb_queue_head_init(&csk->rxq);
+ skb_queue_head_init(&csk->txq);
+ skb_queue_head_init(&csk->ppodq);
+ skb_queue_head_init(&csk->backlogq);
+ skb_queue_head_init(&csk->skbq);
+ cxgbit_sock_reset_wr_list(csk);
+ spin_lock_init(&csk->lock);
+ init_waitqueue_head(&csk->waitq);
+ init_waitqueue_head(&csk->ack_waitq);
+ csk->lock_owner = false;
+
+ if (cxgbit_alloc_csk_skb(csk)) {
+ dst_release(dst);
+ kfree(csk);
+ goto rel_skb;
+ }
+
+ cxgbit_get_cdev(cdev);
+
+ spin_lock(&cdev->cskq.lock);
+ list_add_tail(&csk->list, &cdev->cskq.list);
+ spin_unlock(&cdev->cskq.lock);
+
+ cxgb4_insert_tid(t, csk, tid);
+ cxgbit_pass_accept_rpl(csk, req);
+ goto rel_skb;
+
+reject:
+ cxgbit_release_tid(cdev, tid);
+rel_skb:
+ __kfree_skb(skb);
+}
+
+static u32
+cxgbit_tx_flowc_wr_credits(struct cxgbit_sock *csk, u32 *nparamsp,
+ u32 *flowclenp)
+{
+ u32 nparams, flowclen16, flowclen;
+
+ nparams = FLOWC_WR_NPARAMS_MIN;
+
+ if (csk->snd_wscale)
+ nparams++;
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+ nparams++;
+#endif
+ flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]);
+ flowclen16 = DIV_ROUND_UP(flowclen, 16);
+ flowclen = flowclen16 * 16;
+ /*
+ * Return the number of 16-byte credits used by the flowc request.
+ * Pass back the nparams and actual flowc length if requested.
+ */
+ if (nparamsp)
+ *nparamsp = nparams;
+ if (flowclenp)
+ *flowclenp = flowclen;
+ return flowclen16;
+}
+
+u32 cxgbit_send_tx_flowc_wr(struct cxgbit_sock *csk)
+{
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct fw_flowc_wr *flowc;
+ u32 nparams, flowclen16, flowclen;
+ struct sk_buff *skb;
+ u8 index;
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+ u16 vlan = ((struct l2t_entry *)csk->l2t)->vlan;
+#endif
+
+ flowclen16 = cxgbit_tx_flowc_wr_credits(csk, &nparams, &flowclen);
+
+ skb = __skb_dequeue(&csk->skbq);
+ flowc = (struct fw_flowc_wr *)__skb_put(skb, flowclen);
+ memset(flowc, 0, flowclen);
+
+ flowc->op_to_nparams = cpu_to_be32(FW_WR_OP_V(FW_FLOWC_WR) |
+ FW_FLOWC_WR_NPARAMS_V(nparams));
+ flowc->flowid_len16 = cpu_to_be32(FW_WR_LEN16_V(flowclen16) |
+ FW_WR_FLOWID_V(csk->tid));
+ flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN;
+ flowc->mnemval[0].val = cpu_to_be32(FW_PFVF_CMD_PFN_V
+ (csk->com.cdev->lldi.pf));
+ flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH;
+ flowc->mnemval[1].val = cpu_to_be32(csk->tx_chan);
+ flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT;
+ flowc->mnemval[2].val = cpu_to_be32(csk->tx_chan);
+ flowc->mnemval[3].mnemonic = FW_FLOWC_MNEM_IQID;
+ flowc->mnemval[3].val = cpu_to_be32(csk->rss_qid);
+ flowc->mnemval[4].mnemonic = FW_FLOWC_MNEM_SNDNXT;
+ flowc->mnemval[4].val = cpu_to_be32(csk->snd_nxt);
+ flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT;
+ flowc->mnemval[5].val = cpu_to_be32(csk->rcv_nxt);
+ flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF;
+ flowc->mnemval[6].val = cpu_to_be32(csk->snd_win);
+ flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS;
+ flowc->mnemval[7].val = cpu_to_be32(csk->emss);
+
+ flowc->mnemval[8].mnemonic = FW_FLOWC_MNEM_TXDATAPLEN_MAX;
+ if (test_bit(CDEV_ISO_ENABLE, &cdev->flags))
+ flowc->mnemval[8].val = cpu_to_be32(CXGBIT_MAX_ISO_PAYLOAD);
+ else
+ flowc->mnemval[8].val = cpu_to_be32(16384);
+
+ index = 9;
+
+ if (csk->snd_wscale) {
+ flowc->mnemval[index].mnemonic = FW_FLOWC_MNEM_RCV_SCALE;
+ flowc->mnemval[index].val = cpu_to_be32(csk->snd_wscale);
+ index++;
+ }
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+ flowc->mnemval[index].mnemonic = FW_FLOWC_MNEM_DCBPRIO;
+ if (vlan == VLAN_NONE) {
+ pr_warn("csk %u without VLAN Tag on DCB Link\n", csk->tid);
+ flowc->mnemval[index].val = cpu_to_be32(0);
+ } else
+ flowc->mnemval[index].val = cpu_to_be32(
+ (vlan & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT);
+#endif
+
+ pr_debug("%s: csk %p; tx_chan = %u; rss_qid = %u; snd_seq = %u;"
+ " rcv_seq = %u; snd_win = %u; emss = %u\n",
+ __func__, csk, csk->tx_chan, csk->rss_qid, csk->snd_nxt,
+ csk->rcv_nxt, csk->snd_win, csk->emss);
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ cxgbit_ofld_send(csk->com.cdev, skb);
+ return flowclen16;
+}
+
+int cxgbit_setup_conn_digest(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+ struct cpl_set_tcb_field *req;
+ u8 hcrc = csk->submode & CXGBIT_SUBMODE_HCRC;
+ u8 dcrc = csk->submode & CXGBIT_SUBMODE_DCRC;
+ unsigned int len = roundup(sizeof(*req), 16);
+ int ret;
+
+ skb = alloc_skb(len, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ /* set up ulp submode */
+ req = (struct cpl_set_tcb_field *)__skb_put(skb, len);
+ memset(req, 0, len);
+
+ INIT_TP_WR(req, csk->tid);
+ OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->tid));
+ req->reply_ctrl = htons(NO_REPLY_V(0) | QUEUENO_V(csk->rss_qid));
+ req->word_cookie = htons(0);
+ req->mask = cpu_to_be64(0x3 << 4);
+ req->val = cpu_to_be64(((hcrc ? ULP_CRC_HEADER : 0) |
+ (dcrc ? ULP_CRC_DATA : 0)) << 4);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->ctrlq_idx);
+
+ cxgbit_get_csk(csk);
+ cxgbit_init_wr_wait(&csk->com.wr_wait);
+
+ cxgbit_ofld_send(csk->com.cdev, skb);
+
+ ret = cxgbit_wait_for_reply(csk->com.cdev,
+ &csk->com.wr_wait,
+ csk->tid, 5, __func__);
+ if (ret)
+ return -1;
+
+ return 0;
+}
+
+int cxgbit_setup_conn_pgidx(struct cxgbit_sock *csk, u32 pg_idx)
+{
+ struct sk_buff *skb;
+ struct cpl_set_tcb_field *req;
+ unsigned int len = roundup(sizeof(*req), 16);
+ int ret;
+
+ skb = alloc_skb(len, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ req = (struct cpl_set_tcb_field *)__skb_put(skb, len);
+ memset(req, 0, len);
+
+ INIT_TP_WR(req, csk->tid);
+ OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->tid));
+ req->reply_ctrl = htons(NO_REPLY_V(0) | QUEUENO_V(csk->rss_qid));
+ req->word_cookie = htons(0);
+ req->mask = cpu_to_be64(0x3 << 8);
+ req->val = cpu_to_be64(pg_idx << 8);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->ctrlq_idx);
+
+ cxgbit_get_csk(csk);
+ cxgbit_init_wr_wait(&csk->com.wr_wait);
+
+ cxgbit_ofld_send(csk->com.cdev, skb);
+
+ ret = cxgbit_wait_for_reply(csk->com.cdev,
+ &csk->com.wr_wait,
+ csk->tid, 5, __func__);
+ if (ret)
+ return -1;
+
+ return 0;
+}
+
+static void
+cxgbit_pass_open_rpl(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cpl_pass_open_rpl *rpl = cplhdr(skb);
+ struct tid_info *t = cdev->lldi.tids;
+ unsigned int stid = GET_TID(rpl);
+ struct cxgbit_np *cnp = lookup_stid(t, stid);
+
+ pr_debug("%s: cnp = %p; stid = %u; status = %d\n",
+ __func__, cnp, stid, rpl->status);
+
+ if (!cnp) {
+ pr_info("%s stid %d lookup failure\n", __func__, stid);
+ return;
+ }
+
+ cxgbit_wake_up(&cnp->com.wr_wait, __func__, rpl->status);
+ cxgbit_put_cnp(cnp);
+}
+
+static void
+cxgbit_close_listsrv_rpl(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cpl_close_listsvr_rpl *rpl = cplhdr(skb);
+ struct tid_info *t = cdev->lldi.tids;
+ unsigned int stid = GET_TID(rpl);
+ struct cxgbit_np *cnp = lookup_stid(t, stid);
+
+ pr_debug("%s: cnp = %p; stid = %u; status = %d\n",
+ __func__, cnp, stid, rpl->status);
+
+ if (!cnp) {
+ pr_info("%s stid %d lookup failure\n", __func__, stid);
+ return;
+ }
+
+ cxgbit_wake_up(&cnp->com.wr_wait, __func__, rpl->status);
+ cxgbit_put_cnp(cnp);
+}
+
+static void
+cxgbit_pass_establish(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cpl_pass_establish *req = cplhdr(skb);
+ struct tid_info *t = cdev->lldi.tids;
+ unsigned int tid = GET_TID(req);
+ struct cxgbit_sock *csk;
+ struct cxgbit_np *cnp;
+ u16 tcp_opt = be16_to_cpu(req->tcp_opt);
+ u32 snd_isn = be32_to_cpu(req->snd_isn);
+ u32 rcv_isn = be32_to_cpu(req->rcv_isn);
+
+ csk = lookup_tid(t, tid);
+ if (unlikely(!csk)) {
+ pr_err("can't find connection for tid %u.\n", tid);
+ goto rel_skb;
+ }
+ cnp = csk->cnp;
+
+ pr_debug("%s: csk %p; tid %u; cnp %p\n",
+ __func__, csk, tid, cnp);
+
+ csk->write_seq = snd_isn;
+ csk->snd_una = snd_isn;
+ csk->snd_nxt = snd_isn;
+
+ csk->rcv_nxt = rcv_isn;
+
+ if (csk->rcv_win > (RCV_BUFSIZ_M << 10))
+ csk->rx_credits = (csk->rcv_win - (RCV_BUFSIZ_M << 10));
+
+ csk->snd_wscale = TCPOPT_SND_WSCALE_G(tcp_opt);
+ cxgbit_set_emss(csk, tcp_opt);
+ dst_confirm(csk->dst);
+ csk->com.state = CSK_STATE_ESTABLISHED;
+ spin_lock_bh(&cnp->np_accept_lock);
+ list_add_tail(&csk->accept_node, &cnp->np_accept_list);
+ spin_unlock_bh(&cnp->np_accept_lock);
+ complete(&cnp->accept_comp);
+rel_skb:
+ __kfree_skb(skb);
+}
+
+static void cxgbit_queue_rx_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ cxgbit_skcb_flags(skb) = 0;
+ spin_lock_bh(&csk->rxq.lock);
+ __skb_queue_tail(&csk->rxq, skb);
+ spin_unlock_bh(&csk->rxq.lock);
+ wake_up(&csk->waitq);
+}
+
+static void cxgbit_peer_close(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ pr_debug("%s: csk %p; tid %u; state %d\n",
+ __func__, csk, csk->tid, csk->com.state);
+
+ switch (csk->com.state) {
+ case CSK_STATE_ESTABLISHED:
+ csk->com.state = CSK_STATE_CLOSING;
+ cxgbit_queue_rx_skb(csk, skb);
+ return;
+ case CSK_STATE_CLOSING:
+ /* simultaneous close */
+ csk->com.state = CSK_STATE_MORIBUND;
+ break;
+ case CSK_STATE_MORIBUND:
+ csk->com.state = CSK_STATE_DEAD;
+ cxgbit_put_csk(csk);
+ break;
+ case CSK_STATE_ABORTING:
+ break;
+ default:
+ pr_info("%s: cpl_peer_close in bad state %d\n",
+ __func__, csk->com.state);
+ }
+
+ __kfree_skb(skb);
+}
+
+static void cxgbit_close_con_rpl(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ pr_debug("%s: csk %p; tid %u; state %d\n",
+ __func__, csk, csk->tid, csk->com.state);
+
+ switch (csk->com.state) {
+ case CSK_STATE_CLOSING:
+ csk->com.state = CSK_STATE_MORIBUND;
+ break;
+ case CSK_STATE_MORIBUND:
+ csk->com.state = CSK_STATE_DEAD;
+ cxgbit_put_csk(csk);
+ break;
+ case CSK_STATE_ABORTING:
+ case CSK_STATE_DEAD:
+ break;
+ default:
+ pr_info("%s: cpl_close_con_rpl in bad state %d\n",
+ __func__, csk->com.state);
+ }
+
+ __kfree_skb(skb);
+}
+
+static void cxgbit_abort_req_rss(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ struct cpl_abort_req_rss *hdr = cplhdr(skb);
+ unsigned int tid = GET_TID(hdr);
+ struct cpl_abort_rpl *rpl;
+ struct sk_buff *rpl_skb;
+ bool release = false;
+ bool wakeup_thread = false;
+ unsigned int len = roundup(sizeof(*rpl), 16);
+
+ pr_debug("%s: csk %p; tid %u; state %d\n",
+ __func__, csk, tid, csk->com.state);
+
+ if (cxgbit_is_neg_adv(hdr->status)) {
+ pr_err("%s: got neg advise %d on tid %u\n",
+ __func__, hdr->status, tid);
+ goto rel_skb;
+ }
+
+ switch (csk->com.state) {
+ case CSK_STATE_CONNECTING:
+ case CSK_STATE_MORIBUND:
+ csk->com.state = CSK_STATE_DEAD;
+ release = true;
+ break;
+ case CSK_STATE_ESTABLISHED:
+ csk->com.state = CSK_STATE_DEAD;
+ wakeup_thread = true;
+ break;
+ case CSK_STATE_CLOSING:
+ csk->com.state = CSK_STATE_DEAD;
+ if (!csk->conn)
+ release = true;
+ break;
+ case CSK_STATE_ABORTING:
+ break;
+ default:
+ pr_info("%s: cpl_abort_req_rss in bad state %d\n",
+ __func__, csk->com.state);
+ csk->com.state = CSK_STATE_DEAD;
+ }
+
+ __skb_queue_purge(&csk->txq);
+
+ if (!test_and_set_bit(CSK_TX_DATA_SENT, &csk->com.flags))
+ cxgbit_send_tx_flowc_wr(csk);
+
+ rpl_skb = __skb_dequeue(&csk->skbq);
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+
+ rpl = (struct cpl_abort_rpl *)__skb_put(rpl_skb, len);
+ memset(rpl, 0, len);
+
+ INIT_TP_WR(rpl, csk->tid);
+ OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, tid));
+ rpl->cmd = CPL_ABORT_NO_RST;
+ cxgbit_ofld_send(csk->com.cdev, rpl_skb);
+
+ if (wakeup_thread) {
+ cxgbit_queue_rx_skb(csk, skb);
+ return;
+ }
+
+ if (release)
+ cxgbit_put_csk(csk);
+rel_skb:
+ __kfree_skb(skb);
+}
+
+static void cxgbit_abort_rpl_rss(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ pr_debug("%s: csk %p; tid %u; state %d\n",
+ __func__, csk, csk->tid, csk->com.state);
+
+ switch (csk->com.state) {
+ case CSK_STATE_ABORTING:
+ csk->com.state = CSK_STATE_DEAD;
+ cxgbit_put_csk(csk);
+ break;
+ default:
+ pr_info("%s: cpl_abort_rpl_rss in state %d\n",
+ __func__, csk->com.state);
+ }
+
+ __kfree_skb(skb);
+}
+
+static bool cxgbit_credit_err(const struct cxgbit_sock *csk)
+{
+ const struct sk_buff *skb = csk->wr_pending_head;
+ u32 credit = 0;
+
+ if (unlikely(csk->wr_cred > csk->wr_max_cred)) {
+ pr_err("csk 0x%p, tid %u, credit %u > %u\n",
+ csk, csk->tid, csk->wr_cred, csk->wr_max_cred);
+ return true;
+ }
+
+ while (skb) {
+ credit += skb->csum;
+ skb = cxgbit_skcb_tx_wr_next(skb);
+ }
+
+ if (unlikely((csk->wr_cred + credit) != csk->wr_max_cred)) {
+ pr_err("csk 0x%p, tid %u, credit %u + %u != %u.\n",
+ csk, csk->tid, csk->wr_cred,
+ credit, csk->wr_max_cred);
+
+ return true;
+ }
+
+ return false;
+}
+
+static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ struct cpl_fw4_ack *rpl = (struct cpl_fw4_ack *)cplhdr(skb);
+ u32 credits = rpl->credits;
+ u32 snd_una = ntohl(rpl->snd_una);
+
+ csk->wr_cred += credits;
+ if (csk->wr_una_cred > (csk->wr_max_cred - csk->wr_cred))
+ csk->wr_una_cred = csk->wr_max_cred - csk->wr_cred;
+
+ while (credits) {
+ struct sk_buff *p = cxgbit_sock_peek_wr(csk);
+
+ if (unlikely(!p)) {
+ pr_err("csk 0x%p,%u, cr %u,%u+%u, empty.\n",
+ csk, csk->tid, credits,
+ csk->wr_cred, csk->wr_una_cred);
+ break;
+ }
+
+ if (unlikely(credits < p->csum)) {
+ pr_warn("csk 0x%p,%u, cr %u,%u+%u, < %u.\n",
+ csk, csk->tid,
+ credits, csk->wr_cred, csk->wr_una_cred,
+ p->csum);
+ p->csum -= credits;
+ break;
+ }
+
+ cxgbit_sock_dequeue_wr(csk);
+ credits -= p->csum;
+ kfree_skb(p);
+ }
+
+ if (unlikely(cxgbit_credit_err(csk))) {
+ cxgbit_queue_rx_skb(csk, skb);
+ return;
+ }
+
+ if (rpl->seq_vld & CPL_FW4_ACK_FLAGS_SEQVAL) {
+ if (unlikely(before(snd_una, csk->snd_una))) {
+ pr_warn("csk 0x%p,%u, snd_una %u/%u.",
+ csk, csk->tid, snd_una,
+ csk->snd_una);
+ goto rel_skb;
+ }
+
+ if (csk->snd_una != snd_una) {
+ csk->snd_una = snd_una;
+ dst_confirm(csk->dst);
+ wake_up(&csk->ack_waitq);
+ }
+ }
+
+ if (skb_queue_len(&csk->txq))
+ cxgbit_push_tx_frames(csk);
+
+rel_skb:
+ __kfree_skb(skb);
+}
+
+static void cxgbit_set_tcb_rpl(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cxgbit_sock *csk;
+ struct cpl_set_tcb_rpl *rpl = (struct cpl_set_tcb_rpl *)skb->data;
+ unsigned int tid = GET_TID(rpl);
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+ struct tid_info *t = lldi->tids;
+
+ csk = lookup_tid(t, tid);
+ if (unlikely(!csk))
+ pr_err("can't find connection for tid %u.\n", tid);
+ else
+ cxgbit_wake_up(&csk->com.wr_wait, __func__, rpl->status);
+
+ cxgbit_put_csk(csk);
+}
+
+static void cxgbit_rx_data(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cxgbit_sock *csk;
+ struct cpl_rx_data *cpl = cplhdr(skb);
+ unsigned int tid = GET_TID(cpl);
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+ struct tid_info *t = lldi->tids;
+
+ csk = lookup_tid(t, tid);
+ if (unlikely(!csk)) {
+ pr_err("can't find conn. for tid %u.\n", tid);
+ goto rel_skb;
+ }
+
+ cxgbit_queue_rx_skb(csk, skb);
+ return;
+rel_skb:
+ __kfree_skb(skb);
+}
+
+static void
+__cxgbit_process_rx_cpl(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ spin_lock(&csk->lock);
+ if (csk->lock_owner) {
+ __skb_queue_tail(&csk->backlogq, skb);
+ spin_unlock(&csk->lock);
+ return;
+ }
+
+ cxgbit_skcb_rx_backlog_fn(skb)(csk, skb);
+ spin_unlock(&csk->lock);
+}
+
+static void cxgbit_process_rx_cpl(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ cxgbit_get_csk(csk);
+ __cxgbit_process_rx_cpl(csk, skb);
+ cxgbit_put_csk(csk);
+}
+
+static void cxgbit_rx_cpl(struct cxgbit_device *cdev, struct sk_buff *skb)
+{
+ struct cxgbit_sock *csk;
+ struct cpl_tx_data *cpl = cplhdr(skb);
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+ struct tid_info *t = lldi->tids;
+ unsigned int tid = GET_TID(cpl);
+ u8 opcode = cxgbit_skcb_rx_opcode(skb);
+ bool ref = true;
+
+ switch (opcode) {
+ case CPL_FW4_ACK:
+ cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_fw4_ack;
+ ref = false;
+ break;
+ case CPL_PEER_CLOSE:
+ cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_peer_close;
+ break;
+ case CPL_CLOSE_CON_RPL:
+ cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_close_con_rpl;
+ break;
+ case CPL_ABORT_REQ_RSS:
+ cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_abort_req_rss;
+ break;
+ case CPL_ABORT_RPL_RSS:
+ cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_abort_rpl_rss;
+ break;
+ default:
+ goto rel_skb;
+ }
+
+ csk = lookup_tid(t, tid);
+ if (unlikely(!csk)) {
+ pr_err("can't find conn. for tid %u.\n", tid);
+ goto rel_skb;
+ }
+
+ if (ref)
+ cxgbit_process_rx_cpl(csk, skb);
+ else
+ __cxgbit_process_rx_cpl(csk, skb);
+
+ return;
+rel_skb:
+ __kfree_skb(skb);
+}
+
+cxgbit_cplhandler_func cxgbit_cplhandlers[NUM_CPL_CMDS] = {
+ [CPL_PASS_OPEN_RPL] = cxgbit_pass_open_rpl,
+ [CPL_CLOSE_LISTSRV_RPL] = cxgbit_close_listsrv_rpl,
+ [CPL_PASS_ACCEPT_REQ] = cxgbit_pass_accept_req,
+ [CPL_PASS_ESTABLISH] = cxgbit_pass_establish,
+ [CPL_SET_TCB_RPL] = cxgbit_set_tcb_rpl,
+ [CPL_RX_DATA] = cxgbit_rx_data,
+ [CPL_FW4_ACK] = cxgbit_rx_cpl,
+ [CPL_PEER_CLOSE] = cxgbit_rx_cpl,
+ [CPL_CLOSE_CON_RPL] = cxgbit_rx_cpl,
+ [CPL_ABORT_REQ_RSS] = cxgbit_rx_cpl,
+ [CPL_ABORT_RPL_RSS] = cxgbit_rx_cpl,
+};
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c
new file mode 100644
index 000000000000..5d78bdb7fc64
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright (c) 2016 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "cxgbit.h"
+
+static void
+cxgbit_set_one_ppod(struct cxgbi_pagepod *ppod,
+ struct cxgbi_task_tag_info *ttinfo,
+ struct scatterlist **sg_pp, unsigned int *sg_off)
+{
+ struct scatterlist *sg = sg_pp ? *sg_pp : NULL;
+ unsigned int offset = sg_off ? *sg_off : 0;
+ dma_addr_t addr = 0UL;
+ unsigned int len = 0;
+ int i;
+
+ memcpy(ppod, &ttinfo->hdr, sizeof(struct cxgbi_pagepod_hdr));
+
+ if (sg) {
+ addr = sg_dma_address(sg);
+ len = sg_dma_len(sg);
+ }
+
+ for (i = 0; i < PPOD_PAGES_MAX; i++) {
+ if (sg) {
+ ppod->addr[i] = cpu_to_be64(addr + offset);
+ offset += PAGE_SIZE;
+ if (offset == (len + sg->offset)) {
+ offset = 0;
+ sg = sg_next(sg);
+ if (sg) {
+ addr = sg_dma_address(sg);
+ len = sg_dma_len(sg);
+ }
+ }
+ } else {
+ ppod->addr[i] = 0ULL;
+ }
+ }
+
+ /*
+ * the fifth address needs to be repeated in the next ppod, so do
+ * not move sg
+ */
+ if (sg_pp) {
+ *sg_pp = sg;
+ *sg_off = offset;
+ }
+
+ if (offset == len) {
+ offset = 0;
+ if (sg) {
+ sg = sg_next(sg);
+ if (sg)
+ addr = sg_dma_address(sg);
+ }
+ }
+ ppod->addr[i] = sg ? cpu_to_be64(addr + offset) : 0ULL;
+}
+
+static struct sk_buff *
+cxgbit_ppod_init_idata(struct cxgbit_device *cdev, struct cxgbi_ppm *ppm,
+ unsigned int idx, unsigned int npods, unsigned int tid)
+{
+ struct ulp_mem_io *req;
+ struct ulptx_idata *idata;
+ unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit;
+ unsigned int dlen = npods << PPOD_SIZE_SHIFT;
+ unsigned int wr_len = roundup(sizeof(struct ulp_mem_io) +
+ sizeof(struct ulptx_idata) + dlen, 16);
+ struct sk_buff *skb;
+
+ skb = alloc_skb(wr_len, GFP_KERNEL);
+ if (!skb)
+ return NULL;
+
+ req = (struct ulp_mem_io *)__skb_put(skb, wr_len);
+ INIT_ULPTX_WR(req, wr_len, 0, tid);
+ req->wr.wr_hi = htonl(FW_WR_OP_V(FW_ULPTX_WR) |
+ FW_WR_ATOMIC_V(0));
+ req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) |
+ ULP_MEMIO_ORDER_V(0) |
+ T5_ULP_MEMIO_IMM_V(1));
+ req->dlen = htonl(ULP_MEMIO_DATA_LEN_V(dlen >> 5));
+ req->lock_addr = htonl(ULP_MEMIO_ADDR_V(pm_addr >> 5));
+ req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16));
+
+ idata = (struct ulptx_idata *)(req + 1);
+ idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM));
+ idata->len = htonl(dlen);
+
+ return skb;
+}
+
+static int
+cxgbit_ppod_write_idata(struct cxgbi_ppm *ppm, struct cxgbit_sock *csk,
+ struct cxgbi_task_tag_info *ttinfo, unsigned int idx,
+ unsigned int npods, struct scatterlist **sg_pp,
+ unsigned int *sg_off)
+{
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct sk_buff *skb;
+ struct ulp_mem_io *req;
+ struct ulptx_idata *idata;
+ struct cxgbi_pagepod *ppod;
+ unsigned int i;
+
+ skb = cxgbit_ppod_init_idata(cdev, ppm, idx, npods, csk->tid);
+ if (!skb)
+ return -ENOMEM;
+
+ req = (struct ulp_mem_io *)skb->data;
+ idata = (struct ulptx_idata *)(req + 1);
+ ppod = (struct cxgbi_pagepod *)(idata + 1);
+
+ for (i = 0; i < npods; i++, ppod++)
+ cxgbit_set_one_ppod(ppod, ttinfo, sg_pp, sg_off);
+
+ __skb_queue_tail(&csk->ppodq, skb);
+
+ return 0;
+}
+
+static int
+cxgbit_ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbit_sock *csk,
+ struct cxgbi_task_tag_info *ttinfo)
+{
+ unsigned int pidx = ttinfo->idx;
+ unsigned int npods = ttinfo->npods;
+ unsigned int i, cnt;
+ struct scatterlist *sg = ttinfo->sgl;
+ unsigned int offset = 0;
+ int ret = 0;
+
+ for (i = 0; i < npods; i += cnt, pidx += cnt) {
+ cnt = npods - i;
+
+ if (cnt > ULPMEM_IDATA_MAX_NPPODS)
+ cnt = ULPMEM_IDATA_MAX_NPPODS;
+
+ ret = cxgbit_ppod_write_idata(ppm, csk, ttinfo, pidx, cnt,
+ &sg, &offset);
+ if (ret < 0)
+ break;
+ }
+
+ return ret;
+}
+
+static int cxgbit_ddp_sgl_check(struct scatterlist *sg,
+ unsigned int nents)
+{
+ unsigned int last_sgidx = nents - 1;
+ unsigned int i;
+
+ for (i = 0; i < nents; i++, sg = sg_next(sg)) {
+ unsigned int len = sg->length + sg->offset;
+
+ if ((sg->offset & 0x3) || (i && sg->offset) ||
+ ((i != last_sgidx) && (len != PAGE_SIZE))) {
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int
+cxgbit_ddp_reserve(struct cxgbit_sock *csk, struct cxgbi_task_tag_info *ttinfo,
+ unsigned int xferlen)
+{
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct cxgbi_ppm *ppm = cdev2ppm(cdev);
+ struct scatterlist *sgl = ttinfo->sgl;
+ unsigned int sgcnt = ttinfo->nents;
+ unsigned int sg_offset = sgl->offset;
+ int ret;
+
+ if ((xferlen < DDP_THRESHOLD) || (!sgcnt)) {
+ pr_debug("ppm 0x%p, pgidx %u, xfer %u, sgcnt %u, NO ddp.\n",
+ ppm, ppm->tformat.pgsz_idx_dflt,
+ xferlen, ttinfo->nents);
+ return -EINVAL;
+ }
+
+ if (cxgbit_ddp_sgl_check(sgl, sgcnt) < 0)
+ return -EINVAL;
+
+ ttinfo->nr_pages = (xferlen + sgl->offset +
+ (1 << PAGE_SHIFT) - 1) >> PAGE_SHIFT;
+
+ /*
+ * the ddp tag will be used for the ttt in the outgoing r2t pdu
+ */
+ ret = cxgbi_ppm_ppods_reserve(ppm, ttinfo->nr_pages, 0, &ttinfo->idx,
+ &ttinfo->tag, 0);
+ if (ret < 0)
+ return ret;
+ ttinfo->npods = ret;
+
+ sgl->offset = 0;
+ ret = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE);
+ sgl->offset = sg_offset;
+ if (!ret) {
+ pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n",
+ __func__, 0, xferlen, sgcnt);
+ goto rel_ppods;
+ }
+
+ cxgbi_ppm_make_ppod_hdr(ppm, ttinfo->tag, csk->tid, sgl->offset,
+ xferlen, &ttinfo->hdr);
+
+ ret = cxgbit_ddp_set_map(ppm, csk, ttinfo);
+ if (ret < 0) {
+ __skb_queue_purge(&csk->ppodq);
+ dma_unmap_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE);
+ goto rel_ppods;
+ }
+
+ return 0;
+
+rel_ppods:
+ cxgbi_ppm_ppod_release(ppm, ttinfo->idx);
+ return -EINVAL;
+}
+
+void
+cxgbit_get_r2t_ttt(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct iscsi_r2t *r2t)
+{
+ struct cxgbit_sock *csk = conn->context;
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd);
+ struct cxgbi_task_tag_info *ttinfo = &ccmd->ttinfo;
+ int ret = -EINVAL;
+
+ if ((!ccmd->setup_ddp) ||
+ (!test_bit(CSK_DDP_ENABLE, &csk->com.flags)))
+ goto out;
+
+ ccmd->setup_ddp = false;
+
+ ttinfo->sgl = cmd->se_cmd.t_data_sg;
+ ttinfo->nents = cmd->se_cmd.t_data_nents;
+
+ ret = cxgbit_ddp_reserve(csk, ttinfo, cmd->se_cmd.data_length);
+ if (ret < 0) {
+ pr_info("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n",
+ csk, cmd, cmd->se_cmd.data_length, ttinfo->nents);
+
+ ttinfo->sgl = NULL;
+ ttinfo->nents = 0;
+ } else {
+ ccmd->release = true;
+ }
+out:
+ pr_debug("cdev 0x%p, cmd 0x%p, tag 0x%x\n", cdev, cmd, ttinfo->tag);
+ r2t->targ_xfer_tag = ttinfo->tag;
+}
+
+void cxgbit_release_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
+{
+ struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd);
+
+ if (ccmd->release) {
+ struct cxgbi_task_tag_info *ttinfo = &ccmd->ttinfo;
+
+ if (ttinfo->sgl) {
+ struct cxgbit_sock *csk = conn->context;
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct cxgbi_ppm *ppm = cdev2ppm(cdev);
+
+ cxgbi_ppm_ppod_release(ppm, ttinfo->idx);
+
+ dma_unmap_sg(&ppm->pdev->dev, ttinfo->sgl,
+ ttinfo->nents, DMA_FROM_DEVICE);
+ } else {
+ put_page(sg_page(&ccmd->sg));
+ }
+
+ ccmd->release = false;
+ }
+}
+
+int cxgbit_ddp_init(struct cxgbit_device *cdev)
+{
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+ struct net_device *ndev = cdev->lldi.ports[0];
+ struct cxgbi_tag_format tformat;
+ unsigned int ppmax;
+ int ret, i;
+
+ if (!lldi->vr->iscsi.size) {
+ pr_warn("%s, iscsi NOT enabled, check config!\n", ndev->name);
+ return -EACCES;
+ }
+
+ ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT;
+
+ memset(&tformat, 0, sizeof(struct cxgbi_tag_format));
+ for (i = 0; i < 4; i++)
+ tformat.pgsz_order[i] = (lldi->iscsi_pgsz_order >> (i << 3))
+ & 0xF;
+ cxgbi_tagmask_check(lldi->iscsi_tagmask, &tformat);
+
+ ret = cxgbi_ppm_init(lldi->iscsi_ppm, cdev->lldi.ports[0],
+ cdev->lldi.pdev, &cdev->lldi, &tformat,
+ ppmax, lldi->iscsi_llimit,
+ lldi->vr->iscsi.start, 2);
+ if (ret >= 0) {
+ struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*lldi->iscsi_ppm);
+
+ if ((ppm->tformat.pgsz_idx_dflt < DDP_PGIDX_MAX) &&
+ (ppm->ppmax >= 1024))
+ set_bit(CDEV_DDP_ENABLE, &cdev->flags);
+ ret = 0;
+ }
+
+ return ret;
+}
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_lro.h b/drivers/target/iscsi/cxgbit/cxgbit_lro.h
new file mode 100644
index 000000000000..28c11bd1b930
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/cxgbit_lro.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (c) 2016 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ */
+
+#ifndef __CXGBIT_LRO_H__
+#define __CXGBIT_LRO_H__
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+
+#define LRO_FLUSH_LEN_MAX 65535
+
+struct cxgbit_lro_cb {
+ struct cxgbit_sock *csk;
+ u32 pdu_totallen;
+ u32 offset;
+ u8 pdu_idx;
+ bool complete;
+};
+
+enum cxgbit_pducb_flags {
+ PDUCBF_RX_HDR = (1 << 0), /* received pdu header */
+ PDUCBF_RX_DATA = (1 << 1), /* received pdu payload */
+ PDUCBF_RX_STATUS = (1 << 2), /* received ddp status */
+ PDUCBF_RX_DATA_DDPD = (1 << 3), /* pdu payload ddp'd */
+ PDUCBF_RX_HCRC_ERR = (1 << 4), /* header digest error */
+ PDUCBF_RX_DCRC_ERR = (1 << 5), /* data digest error */
+};
+
+struct cxgbit_lro_pdu_cb {
+ u8 flags;
+ u8 frags;
+ u8 hfrag_idx;
+ u8 nr_dfrags;
+ u8 dfrag_idx;
+ bool complete;
+ u32 seq;
+ u32 pdulen;
+ u32 hlen;
+ u32 dlen;
+ u32 doffset;
+ u32 ddigest;
+ void *hdr;
+};
+
+#define LRO_SKB_MAX_HEADROOM \
+ (sizeof(struct cxgbit_lro_cb) + \
+ (MAX_SKB_FRAGS * sizeof(struct cxgbit_lro_pdu_cb)))
+
+#define LRO_SKB_MIN_HEADROOM \
+ (sizeof(struct cxgbit_lro_cb) + \
+ sizeof(struct cxgbit_lro_pdu_cb))
+
+#define cxgbit_skb_lro_cb(skb) ((struct cxgbit_lro_cb *)skb->data)
+#define cxgbit_skb_lro_pdu_cb(skb, i) \
+ ((struct cxgbit_lro_pdu_cb *)(skb->data + sizeof(struct cxgbit_lro_cb) \
+ + (i * sizeof(struct cxgbit_lro_pdu_cb))))
+
+#define CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */
+#define CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT 19 /* pad error */
+#define CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */
+#define CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */
+
+#endif /*__CXGBIT_LRO_H_*/
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c
new file mode 100644
index 000000000000..60dccd02bd85
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c
@@ -0,0 +1,702 @@
+/*
+ * Copyright (c) 2016 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define DRV_NAME "cxgbit"
+#define DRV_VERSION "1.0.0-ko"
+#define pr_fmt(fmt) DRV_NAME ": " fmt
+
+#include "cxgbit.h"
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+#include <net/dcbevent.h>
+#include "cxgb4_dcb.h"
+#endif
+
+LIST_HEAD(cdev_list_head);
+/* cdev list lock */
+DEFINE_MUTEX(cdev_list_lock);
+
+void _cxgbit_free_cdev(struct kref *kref)
+{
+ struct cxgbit_device *cdev;
+
+ cdev = container_of(kref, struct cxgbit_device, kref);
+ kfree(cdev);
+}
+
+static void cxgbit_set_mdsl(struct cxgbit_device *cdev)
+{
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+ u32 mdsl;
+
+#define ULP2_MAX_PKT_LEN 16224
+#define ISCSI_PDU_NONPAYLOAD_LEN 312
+ mdsl = min_t(u32, lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN,
+ ULP2_MAX_PKT_LEN - ISCSI_PDU_NONPAYLOAD_LEN);
+ mdsl = min_t(u32, mdsl, 8192);
+ mdsl = min_t(u32, mdsl, (MAX_SKB_FRAGS - 1) * PAGE_SIZE);
+
+ cdev->mdsl = mdsl;
+}
+
+static void *cxgbit_uld_add(const struct cxgb4_lld_info *lldi)
+{
+ struct cxgbit_device *cdev;
+
+ if (is_t4(lldi->adapter_type))
+ return ERR_PTR(-ENODEV);
+
+ cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
+ if (!cdev)
+ return ERR_PTR(-ENOMEM);
+
+ kref_init(&cdev->kref);
+
+ cdev->lldi = *lldi;
+
+ cxgbit_set_mdsl(cdev);
+
+ if (cxgbit_ddp_init(cdev) < 0) {
+ kfree(cdev);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!test_bit(CDEV_DDP_ENABLE, &cdev->flags))
+ pr_info("cdev %s ddp init failed\n",
+ pci_name(lldi->pdev));
+
+ if (lldi->fw_vers >= 0x10d2b00)
+ set_bit(CDEV_ISO_ENABLE, &cdev->flags);
+
+ spin_lock_init(&cdev->cskq.lock);
+ INIT_LIST_HEAD(&cdev->cskq.list);
+
+ mutex_lock(&cdev_list_lock);
+ list_add_tail(&cdev->list, &cdev_list_head);
+ mutex_unlock(&cdev_list_lock);
+
+ pr_info("cdev %s added for iSCSI target transport\n",
+ pci_name(lldi->pdev));
+
+ return cdev;
+}
+
+static void cxgbit_close_conn(struct cxgbit_device *cdev)
+{
+ struct cxgbit_sock *csk;
+ struct sk_buff *skb;
+ bool wakeup_thread = false;
+
+ spin_lock_bh(&cdev->cskq.lock);
+ list_for_each_entry(csk, &cdev->cskq.list, list) {
+ skb = alloc_skb(0, GFP_ATOMIC);
+ if (!skb)
+ continue;
+
+ spin_lock_bh(&csk->rxq.lock);
+ __skb_queue_tail(&csk->rxq, skb);
+ if (skb_queue_len(&csk->rxq) == 1)
+ wakeup_thread = true;
+ spin_unlock_bh(&csk->rxq.lock);
+
+ if (wakeup_thread) {
+ wake_up(&csk->waitq);
+ wakeup_thread = false;
+ }
+ }
+ spin_unlock_bh(&cdev->cskq.lock);
+}
+
+static void cxgbit_detach_cdev(struct cxgbit_device *cdev)
+{
+ bool free_cdev = false;
+
+ spin_lock_bh(&cdev->cskq.lock);
+ if (list_empty(&cdev->cskq.list))
+ free_cdev = true;
+ spin_unlock_bh(&cdev->cskq.lock);
+
+ if (free_cdev) {
+ mutex_lock(&cdev_list_lock);
+ list_del(&cdev->list);
+ mutex_unlock(&cdev_list_lock);
+
+ cxgbit_put_cdev(cdev);
+ } else {
+ cxgbit_close_conn(cdev);
+ }
+}
+
+static int cxgbit_uld_state_change(void *handle, enum cxgb4_state state)
+{
+ struct cxgbit_device *cdev = handle;
+
+ switch (state) {
+ case CXGB4_STATE_UP:
+ set_bit(CDEV_STATE_UP, &cdev->flags);
+ pr_info("cdev %s state UP.\n", pci_name(cdev->lldi.pdev));
+ break;
+ case CXGB4_STATE_START_RECOVERY:
+ clear_bit(CDEV_STATE_UP, &cdev->flags);
+ cxgbit_close_conn(cdev);
+ pr_info("cdev %s state RECOVERY.\n", pci_name(cdev->lldi.pdev));
+ break;
+ case CXGB4_STATE_DOWN:
+ pr_info("cdev %s state DOWN.\n", pci_name(cdev->lldi.pdev));
+ break;
+ case CXGB4_STATE_DETACH:
+ clear_bit(CDEV_STATE_UP, &cdev->flags);
+ pr_info("cdev %s state DETACH.\n", pci_name(cdev->lldi.pdev));
+ cxgbit_detach_cdev(cdev);
+ break;
+ default:
+ pr_info("cdev %s unknown state %d.\n",
+ pci_name(cdev->lldi.pdev), state);
+ break;
+ }
+ return 0;
+}
+
+static void
+cxgbit_proc_ddp_status(unsigned int tid, struct cpl_rx_data_ddp *cpl,
+ struct cxgbit_lro_pdu_cb *pdu_cb)
+{
+ unsigned int status = ntohl(cpl->ddpvld);
+
+ pdu_cb->flags |= PDUCBF_RX_STATUS;
+ pdu_cb->ddigest = ntohl(cpl->ulp_crc);
+ pdu_cb->pdulen = ntohs(cpl->len);
+
+ if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) {
+ pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", tid, status);
+ pdu_cb->flags |= PDUCBF_RX_HCRC_ERR;
+ }
+
+ if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) {
+ pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", tid, status);
+ pdu_cb->flags |= PDUCBF_RX_DCRC_ERR;
+ }
+
+ if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT))
+ pr_info("tid 0x%x, status 0x%x, pad bad.\n", tid, status);
+
+ if ((status & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) &&
+ (!(pdu_cb->flags & PDUCBF_RX_DATA))) {
+ pdu_cb->flags |= PDUCBF_RX_DATA_DDPD;
+ }
+}
+
+static void
+cxgbit_lro_add_packet_rsp(struct sk_buff *skb, u8 op, const __be64 *rsp)
+{
+ struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb,
+ lro_cb->pdu_idx);
+ struct cpl_rx_iscsi_ddp *cpl = (struct cpl_rx_iscsi_ddp *)(rsp + 1);
+
+ cxgbit_proc_ddp_status(lro_cb->csk->tid, cpl, pdu_cb);
+
+ if (pdu_cb->flags & PDUCBF_RX_HDR)
+ pdu_cb->complete = true;
+
+ lro_cb->complete = true;
+ lro_cb->pdu_totallen += pdu_cb->pdulen;
+ lro_cb->pdu_idx++;
+}
+
+static void
+cxgbit_copy_frags(struct sk_buff *skb, const struct pkt_gl *gl,
+ unsigned int offset)
+{
+ u8 skb_frag_idx = skb_shinfo(skb)->nr_frags;
+ u8 i;
+
+ /* usually there's just one frag */
+ __skb_fill_page_desc(skb, skb_frag_idx, gl->frags[0].page,
+ gl->frags[0].offset + offset,
+ gl->frags[0].size - offset);
+ for (i = 1; i < gl->nfrags; i++)
+ __skb_fill_page_desc(skb, skb_frag_idx + i,
+ gl->frags[i].page,
+ gl->frags[i].offset,
+ gl->frags[i].size);
+
+ skb_shinfo(skb)->nr_frags += gl->nfrags;
+
+ /* get a reference to the last page, we don't own it */
+ get_page(gl->frags[gl->nfrags - 1].page);
+}
+
+static void
+cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl)
+{
+ struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb,
+ lro_cb->pdu_idx);
+ u32 len, offset;
+
+ if (op == CPL_ISCSI_HDR) {
+ struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)gl->va;
+
+ offset = sizeof(struct cpl_iscsi_hdr);
+ pdu_cb->flags |= PDUCBF_RX_HDR;
+ pdu_cb->seq = ntohl(cpl->seq);
+ len = ntohs(cpl->len);
+ pdu_cb->hdr = gl->va + offset;
+ pdu_cb->hlen = len;
+ pdu_cb->hfrag_idx = skb_shinfo(skb)->nr_frags;
+
+ if (unlikely(gl->nfrags > 1))
+ cxgbit_skcb_flags(skb) = 0;
+
+ lro_cb->complete = false;
+ } else {
+ struct cpl_iscsi_data *cpl = (struct cpl_iscsi_data *)gl->va;
+
+ offset = sizeof(struct cpl_iscsi_data);
+ pdu_cb->flags |= PDUCBF_RX_DATA;
+ len = ntohs(cpl->len);
+ pdu_cb->dlen = len;
+ pdu_cb->doffset = lro_cb->offset;
+ pdu_cb->nr_dfrags = gl->nfrags;
+ pdu_cb->dfrag_idx = skb_shinfo(skb)->nr_frags;
+ }
+
+ cxgbit_copy_frags(skb, gl, offset);
+
+ pdu_cb->frags += gl->nfrags;
+ lro_cb->offset += len;
+ skb->len += len;
+ skb->data_len += len;
+ skb->truesize += len;
+}
+
+static struct sk_buff *
+cxgbit_lro_init_skb(struct cxgbit_sock *csk, u8 op, const struct pkt_gl *gl,
+ const __be64 *rsp, struct napi_struct *napi)
+{
+ struct sk_buff *skb;
+ struct cxgbit_lro_cb *lro_cb;
+
+ skb = napi_alloc_skb(napi, LRO_SKB_MAX_HEADROOM);
+
+ if (unlikely(!skb))
+ return NULL;
+
+ memset(skb->data, 0, LRO_SKB_MAX_HEADROOM);
+
+ cxgbit_skcb_flags(skb) |= SKCBF_RX_LRO;
+
+ lro_cb = cxgbit_skb_lro_cb(skb);
+
+ cxgbit_get_csk(csk);
+
+ lro_cb->csk = csk;
+
+ return skb;
+}
+
+static void cxgbit_queue_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ bool wakeup_thread = false;
+
+ spin_lock(&csk->rxq.lock);
+ __skb_queue_tail(&csk->rxq, skb);
+ if (skb_queue_len(&csk->rxq) == 1)
+ wakeup_thread = true;
+ spin_unlock(&csk->rxq.lock);
+
+ if (wakeup_thread)
+ wake_up(&csk->waitq);
+}
+
+static void cxgbit_lro_flush(struct t4_lro_mgr *lro_mgr, struct sk_buff *skb)
+{
+ struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+ struct cxgbit_sock *csk = lro_cb->csk;
+
+ csk->lro_skb = NULL;
+
+ __skb_unlink(skb, &lro_mgr->lroq);
+ cxgbit_queue_lro_skb(csk, skb);
+
+ cxgbit_put_csk(csk);
+
+ lro_mgr->lro_pkts++;
+ lro_mgr->lro_session_cnt--;
+}
+
+static void cxgbit_uld_lro_flush(struct t4_lro_mgr *lro_mgr)
+{
+ struct sk_buff *skb;
+
+ while ((skb = skb_peek(&lro_mgr->lroq)))
+ cxgbit_lro_flush(lro_mgr, skb);
+}
+
+static int
+cxgbit_lro_receive(struct cxgbit_sock *csk, u8 op, const __be64 *rsp,
+ const struct pkt_gl *gl, struct t4_lro_mgr *lro_mgr,
+ struct napi_struct *napi)
+{
+ struct sk_buff *skb;
+ struct cxgbit_lro_cb *lro_cb;
+
+ if (!csk) {
+ pr_err("%s: csk NULL, op 0x%x.\n", __func__, op);
+ goto out;
+ }
+
+ if (csk->lro_skb)
+ goto add_packet;
+
+start_lro:
+ if (lro_mgr->lro_session_cnt >= MAX_LRO_SESSIONS) {
+ cxgbit_uld_lro_flush(lro_mgr);
+ goto start_lro;
+ }
+
+ skb = cxgbit_lro_init_skb(csk, op, gl, rsp, napi);
+ if (unlikely(!skb))
+ goto out;
+
+ csk->lro_skb = skb;
+
+ __skb_queue_tail(&lro_mgr->lroq, skb);
+ lro_mgr->lro_session_cnt++;
+
+add_packet:
+ skb = csk->lro_skb;
+ lro_cb = cxgbit_skb_lro_cb(skb);
+
+ if ((gl && (((skb_shinfo(skb)->nr_frags + gl->nfrags) >
+ MAX_SKB_FRAGS) || (lro_cb->pdu_totallen >= LRO_FLUSH_LEN_MAX))) ||
+ (lro_cb->pdu_idx >= MAX_SKB_FRAGS)) {
+ cxgbit_lro_flush(lro_mgr, skb);
+ goto start_lro;
+ }
+
+ if (gl)
+ cxgbit_lro_add_packet_gl(skb, op, gl);
+ else
+ cxgbit_lro_add_packet_rsp(skb, op, rsp);
+
+ lro_mgr->lro_merged++;
+
+ return 0;
+
+out:
+ return -1;
+}
+
+static int
+cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp,
+ const struct pkt_gl *gl, struct t4_lro_mgr *lro_mgr,
+ struct napi_struct *napi)
+{
+ struct cxgbit_device *cdev = hndl;
+ struct cxgb4_lld_info *lldi = &cdev->lldi;
+ struct cpl_tx_data *rpl = NULL;
+ struct cxgbit_sock *csk = NULL;
+ unsigned int tid = 0;
+ struct sk_buff *skb;
+ unsigned int op = *(u8 *)rsp;
+ bool lro_flush = true;
+
+ switch (op) {
+ case CPL_ISCSI_HDR:
+ case CPL_ISCSI_DATA:
+ case CPL_RX_ISCSI_DDP:
+ case CPL_FW4_ACK:
+ lro_flush = false;
+ case CPL_ABORT_RPL_RSS:
+ case CPL_PASS_ESTABLISH:
+ case CPL_PEER_CLOSE:
+ case CPL_CLOSE_CON_RPL:
+ case CPL_ABORT_REQ_RSS:
+ case CPL_SET_TCB_RPL:
+ case CPL_RX_DATA:
+ rpl = gl ? (struct cpl_tx_data *)gl->va :
+ (struct cpl_tx_data *)(rsp + 1);
+ tid = GET_TID(rpl);
+ csk = lookup_tid(lldi->tids, tid);
+ break;
+ default:
+ break;
+ }
+
+ if (csk && csk->lro_skb && lro_flush)
+ cxgbit_lro_flush(lro_mgr, csk->lro_skb);
+
+ if (!gl) {
+ unsigned int len;
+
+ if (op == CPL_RX_ISCSI_DDP) {
+ if (!cxgbit_lro_receive(csk, op, rsp, NULL, lro_mgr,
+ napi))
+ return 0;
+ }
+
+ len = 64 - sizeof(struct rsp_ctrl) - 8;
+ skb = napi_alloc_skb(napi, len);
+ if (!skb)
+ goto nomem;
+ __skb_put(skb, len);
+ skb_copy_to_linear_data(skb, &rsp[1], len);
+ } else {
+ if (unlikely(op != *(u8 *)gl->va)) {
+ pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n",
+ gl->va, be64_to_cpu(*rsp),
+ be64_to_cpu(*(u64 *)gl->va),
+ gl->tot_len);
+ return 0;
+ }
+
+ if (op == CPL_ISCSI_HDR || op == CPL_ISCSI_DATA) {
+ if (!cxgbit_lro_receive(csk, op, rsp, gl, lro_mgr,
+ napi))
+ return 0;
+ }
+
+#define RX_PULL_LEN 128
+ skb = cxgb4_pktgl_to_skb(gl, RX_PULL_LEN, RX_PULL_LEN);
+ if (unlikely(!skb))
+ goto nomem;
+ }
+
+ rpl = (struct cpl_tx_data *)skb->data;
+ op = rpl->ot.opcode;
+ cxgbit_skcb_rx_opcode(skb) = op;
+
+ pr_debug("cdev %p, opcode 0x%x(0x%x,0x%x), skb %p.\n",
+ cdev, op, rpl->ot.opcode_tid,
+ ntohl(rpl->ot.opcode_tid), skb);
+
+ if (op < NUM_CPL_CMDS && cxgbit_cplhandlers[op]) {
+ cxgbit_cplhandlers[op](cdev, skb);
+ } else {
+ pr_err("No handler for opcode 0x%x.\n", op);
+ __kfree_skb(skb);
+ }
+ return 0;
+nomem:
+ pr_err("%s OOM bailing out.\n", __func__);
+ return 1;
+}
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+struct cxgbit_dcb_work {
+ struct dcb_app_type dcb_app;
+ struct work_struct work;
+};
+
+static void
+cxgbit_update_dcb_priority(struct cxgbit_device *cdev, u8 port_id,
+ u8 dcb_priority, u16 port_num)
+{
+ struct cxgbit_sock *csk;
+ struct sk_buff *skb;
+ u16 local_port;
+ bool wakeup_thread = false;
+
+ spin_lock_bh(&cdev->cskq.lock);
+ list_for_each_entry(csk, &cdev->cskq.list, list) {
+ if (csk->port_id != port_id)
+ continue;
+
+ if (csk->com.local_addr.ss_family == AF_INET6) {
+ struct sockaddr_in6 *sock_in6;
+
+ sock_in6 = (struct sockaddr_in6 *)&csk->com.local_addr;
+ local_port = ntohs(sock_in6->sin6_port);
+ } else {
+ struct sockaddr_in *sock_in;
+
+ sock_in = (struct sockaddr_in *)&csk->com.local_addr;
+ local_port = ntohs(sock_in->sin_port);
+ }
+
+ if (local_port != port_num)
+ continue;
+
+ if (csk->dcb_priority == dcb_priority)
+ continue;
+
+ skb = alloc_skb(0, GFP_ATOMIC);
+ if (!skb)
+ continue;
+
+ spin_lock(&csk->rxq.lock);
+ __skb_queue_tail(&csk->rxq, skb);
+ if (skb_queue_len(&csk->rxq) == 1)
+ wakeup_thread = true;
+ spin_unlock(&csk->rxq.lock);
+
+ if (wakeup_thread) {
+ wake_up(&csk->waitq);
+ wakeup_thread = false;
+ }
+ }
+ spin_unlock_bh(&cdev->cskq.lock);
+}
+
+static void cxgbit_dcb_workfn(struct work_struct *work)
+{
+ struct cxgbit_dcb_work *dcb_work;
+ struct net_device *ndev;
+ struct cxgbit_device *cdev = NULL;
+ struct dcb_app_type *iscsi_app;
+ u8 priority, port_id = 0xff;
+
+ dcb_work = container_of(work, struct cxgbit_dcb_work, work);
+ iscsi_app = &dcb_work->dcb_app;
+
+ if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_IEEE) {
+ if (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY)
+ goto out;
+
+ priority = iscsi_app->app.priority;
+
+ } else if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_CEE) {
+ if (iscsi_app->app.selector != DCB_APP_IDTYPE_PORTNUM)
+ goto out;
+
+ if (!iscsi_app->app.priority)
+ goto out;
+
+ priority = ffs(iscsi_app->app.priority) - 1;
+ } else {
+ goto out;
+ }
+
+ pr_debug("priority for ifid %d is %u\n",
+ iscsi_app->ifindex, priority);
+
+ ndev = dev_get_by_index(&init_net, iscsi_app->ifindex);
+
+ if (!ndev)
+ goto out;
+
+ mutex_lock(&cdev_list_lock);
+ cdev = cxgbit_find_device(ndev, &port_id);
+
+ dev_put(ndev);
+
+ if (!cdev) {
+ mutex_unlock(&cdev_list_lock);
+ goto out;
+ }
+
+ cxgbit_update_dcb_priority(cdev, port_id, priority,
+ iscsi_app->app.protocol);
+ mutex_unlock(&cdev_list_lock);
+out:
+ kfree(dcb_work);
+}
+
+static int
+cxgbit_dcbevent_notify(struct notifier_block *nb, unsigned long action,
+ void *data)
+{
+ struct cxgbit_dcb_work *dcb_work;
+ struct dcb_app_type *dcb_app = data;
+
+ dcb_work = kzalloc(sizeof(*dcb_work), GFP_ATOMIC);
+ if (!dcb_work)
+ return NOTIFY_DONE;
+
+ dcb_work->dcb_app = *dcb_app;
+ INIT_WORK(&dcb_work->work, cxgbit_dcb_workfn);
+ schedule_work(&dcb_work->work);
+ return NOTIFY_OK;
+}
+#endif
+
+static enum target_prot_op cxgbit_get_sup_prot_ops(struct iscsi_conn *conn)
+{
+ return TARGET_PROT_NORMAL;
+}
+
+static struct iscsit_transport cxgbit_transport = {
+ .name = DRV_NAME,
+ .transport_type = ISCSI_CXGBIT,
+ .rdma_shutdown = false,
+ .priv_size = sizeof(struct cxgbit_cmd),
+ .owner = THIS_MODULE,
+ .iscsit_setup_np = cxgbit_setup_np,
+ .iscsit_accept_np = cxgbit_accept_np,
+ .iscsit_free_np = cxgbit_free_np,
+ .iscsit_free_conn = cxgbit_free_conn,
+ .iscsit_get_login_rx = cxgbit_get_login_rx,
+ .iscsit_put_login_tx = cxgbit_put_login_tx,
+ .iscsit_immediate_queue = iscsit_immediate_queue,
+ .iscsit_response_queue = iscsit_response_queue,
+ .iscsit_get_dataout = iscsit_build_r2ts_for_cmd,
+ .iscsit_queue_data_in = iscsit_queue_rsp,
+ .iscsit_queue_status = iscsit_queue_rsp,
+ .iscsit_xmit_pdu = cxgbit_xmit_pdu,
+ .iscsit_get_r2t_ttt = cxgbit_get_r2t_ttt,
+ .iscsit_get_rx_pdu = cxgbit_get_rx_pdu,
+ .iscsit_validate_params = cxgbit_validate_params,
+ .iscsit_release_cmd = cxgbit_release_cmd,
+ .iscsit_aborted_task = iscsit_aborted_task,
+ .iscsit_get_sup_prot_ops = cxgbit_get_sup_prot_ops,
+};
+
+static struct cxgb4_uld_info cxgbit_uld_info = {
+ .name = DRV_NAME,
+ .add = cxgbit_uld_add,
+ .state_change = cxgbit_uld_state_change,
+ .lro_rx_handler = cxgbit_uld_lro_rx_handler,
+ .lro_flush = cxgbit_uld_lro_flush,
+};
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+static struct notifier_block cxgbit_dcbevent_nb = {
+ .notifier_call = cxgbit_dcbevent_notify,
+};
+#endif
+
+static int __init cxgbit_init(void)
+{
+ cxgb4_register_uld(CXGB4_ULD_ISCSIT, &cxgbit_uld_info);
+ iscsit_register_transport(&cxgbit_transport);
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+ pr_info("%s dcb enabled.\n", DRV_NAME);
+ register_dcbevent_notifier(&cxgbit_dcbevent_nb);
+#endif
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) <
+ sizeof(union cxgbit_skb_cb));
+ return 0;
+}
+
+static void __exit cxgbit_exit(void)
+{
+ struct cxgbit_device *cdev, *tmp;
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+ unregister_dcbevent_notifier(&cxgbit_dcbevent_nb);
+#endif
+ mutex_lock(&cdev_list_lock);
+ list_for_each_entry_safe(cdev, tmp, &cdev_list_head, list) {
+ list_del(&cdev->list);
+ cxgbit_put_cdev(cdev);
+ }
+ mutex_unlock(&cdev_list_lock);
+ iscsit_unregister_transport(&cxgbit_transport);
+ cxgb4_unregister_uld(CXGB4_ULD_ISCSIT);
+}
+
+module_init(cxgbit_init);
+module_exit(cxgbit_exit);
+
+MODULE_DESCRIPTION("Chelsio iSCSI target offload driver");
+MODULE_AUTHOR("Chelsio Communications");
+MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
new file mode 100644
index 000000000000..d02bf58aea6d
--- /dev/null
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -0,0 +1,1561 @@
+/*
+ * Copyright (c) 2016 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <asm/unaligned.h>
+#include <target/target_core_base.h>
+#include <target/target_core_fabric.h>
+#include "cxgbit.h"
+
+struct sge_opaque_hdr {
+ void *dev;
+ dma_addr_t addr[MAX_SKB_FRAGS + 1];
+};
+
+static const u8 cxgbit_digest_len[] = {0, 4, 4, 8};
+
+#define TX_HDR_LEN (sizeof(struct sge_opaque_hdr) + \
+ sizeof(struct fw_ofld_tx_data_wr))
+
+static struct sk_buff *
+__cxgbit_alloc_skb(struct cxgbit_sock *csk, u32 len, bool iso)
+{
+ struct sk_buff *skb = NULL;
+ u8 submode = 0;
+ int errcode;
+ static const u32 hdr_len = TX_HDR_LEN + ISCSI_HDR_LEN;
+
+ if (len) {
+ skb = alloc_skb_with_frags(hdr_len, len,
+ 0, &errcode,
+ GFP_KERNEL);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, TX_HDR_LEN);
+ skb_reset_transport_header(skb);
+ __skb_put(skb, ISCSI_HDR_LEN);
+ skb->data_len = len;
+ skb->len += len;
+ submode |= (csk->submode & CXGBIT_SUBMODE_DCRC);
+
+ } else {
+ u32 iso_len = iso ? sizeof(struct cpl_tx_data_iso) : 0;
+
+ skb = alloc_skb(hdr_len + iso_len, GFP_KERNEL);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, TX_HDR_LEN + iso_len);
+ skb_reset_transport_header(skb);
+ __skb_put(skb, ISCSI_HDR_LEN);
+ }
+
+ submode |= (csk->submode & CXGBIT_SUBMODE_HCRC);
+ cxgbit_skcb_submode(skb) = submode;
+ cxgbit_skcb_tx_extralen(skb) = cxgbit_digest_len[submode];
+ cxgbit_skcb_flags(skb) |= SKCBF_TX_NEED_HDR;
+ return skb;
+}
+
+static struct sk_buff *cxgbit_alloc_skb(struct cxgbit_sock *csk, u32 len)
+{
+ return __cxgbit_alloc_skb(csk, len, false);
+}
+
+/*
+ * cxgbit_is_ofld_imm - check whether a packet can be sent as immediate data
+ * @skb: the packet
+ *
+ * Returns true if a packet can be sent as an offload WR with immediate
+ * data. We currently use the same limit as for Ethernet packets.
+ */
+static int cxgbit_is_ofld_imm(const struct sk_buff *skb)
+{
+ int length = skb->len;
+
+ if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_NEED_HDR))
+ length += sizeof(struct fw_ofld_tx_data_wr);
+
+ if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_ISO))
+ length += sizeof(struct cpl_tx_data_iso);
+
+#define MAX_IMM_TX_PKT_LEN 256
+ return length <= MAX_IMM_TX_PKT_LEN;
+}
+
+/*
+ * cxgbit_sgl_len - calculates the size of an SGL of the given capacity
+ * @n: the number of SGL entries
+ * Calculates the number of flits needed for a scatter/gather list that
+ * can hold the given number of entries.
+ */
+static inline unsigned int cxgbit_sgl_len(unsigned int n)
+{
+ n--;
+ return (3 * n) / 2 + (n & 1) + 2;
+}
+
+/*
+ * cxgbit_calc_tx_flits_ofld - calculate # of flits for an offload packet
+ * @skb: the packet
+ *
+ * Returns the number of flits needed for the given offload packet.
+ * These packets are already fully constructed and no additional headers
+ * will be added.
+ */
+static unsigned int cxgbit_calc_tx_flits_ofld(const struct sk_buff *skb)
+{
+ unsigned int flits, cnt;
+
+ if (cxgbit_is_ofld_imm(skb))
+ return DIV_ROUND_UP(skb->len, 8);
+ flits = skb_transport_offset(skb) / 8;
+ cnt = skb_shinfo(skb)->nr_frags;
+ if (skb_tail_pointer(skb) != skb_transport_header(skb))
+ cnt++;
+ return flits + cxgbit_sgl_len(cnt);
+}
+
+#define CXGBIT_ISO_FSLICE 0x1
+#define CXGBIT_ISO_LSLICE 0x2
+static void
+cxgbit_cpl_tx_data_iso(struct sk_buff *skb, struct cxgbit_iso_info *iso_info)
+{
+ struct cpl_tx_data_iso *cpl;
+ unsigned int submode = cxgbit_skcb_submode(skb);
+ unsigned int fslice = !!(iso_info->flags & CXGBIT_ISO_FSLICE);
+ unsigned int lslice = !!(iso_info->flags & CXGBIT_ISO_LSLICE);
+
+ cpl = (struct cpl_tx_data_iso *)__skb_push(skb, sizeof(*cpl));
+
+ cpl->op_to_scsi = htonl(CPL_TX_DATA_ISO_OP_V(CPL_TX_DATA_ISO) |
+ CPL_TX_DATA_ISO_FIRST_V(fslice) |
+ CPL_TX_DATA_ISO_LAST_V(lslice) |
+ CPL_TX_DATA_ISO_CPLHDRLEN_V(0) |
+ CPL_TX_DATA_ISO_HDRCRC_V(submode & 1) |
+ CPL_TX_DATA_ISO_PLDCRC_V(((submode >> 1) & 1)) |
+ CPL_TX_DATA_ISO_IMMEDIATE_V(0) |
+ CPL_TX_DATA_ISO_SCSI_V(2));
+
+ cpl->ahs_len = 0;
+ cpl->mpdu = htons(DIV_ROUND_UP(iso_info->mpdu, 4));
+ cpl->burst_size = htonl(DIV_ROUND_UP(iso_info->burst_len, 4));
+ cpl->len = htonl(iso_info->len);
+ cpl->reserved2_seglen_offset = htonl(0);
+ cpl->datasn_offset = htonl(0);
+ cpl->buffer_offset = htonl(0);
+ cpl->reserved3 = 0;
+
+ __skb_pull(skb, sizeof(*cpl));
+}
+
+static void
+cxgbit_tx_data_wr(struct cxgbit_sock *csk, struct sk_buff *skb, u32 dlen,
+ u32 len, u32 credits, u32 compl)
+{
+ struct fw_ofld_tx_data_wr *req;
+ u32 submode = cxgbit_skcb_submode(skb);
+ u32 wr_ulp_mode = 0;
+ u32 hdr_size = sizeof(*req);
+ u32 opcode = FW_OFLD_TX_DATA_WR;
+ u32 immlen = 0;
+ u32 force = TX_FORCE_V(!submode);
+
+ if (cxgbit_skcb_flags(skb) & SKCBF_TX_ISO) {
+ opcode = FW_ISCSI_TX_DATA_WR;
+ immlen += sizeof(struct cpl_tx_data_iso);
+ hdr_size += sizeof(struct cpl_tx_data_iso);
+ submode |= 8;
+ }
+
+ if (cxgbit_is_ofld_imm(skb))
+ immlen += dlen;
+
+ req = (struct fw_ofld_tx_data_wr *)__skb_push(skb,
+ hdr_size);
+ req->op_to_immdlen = cpu_to_be32(FW_WR_OP_V(opcode) |
+ FW_WR_COMPL_V(compl) |
+ FW_WR_IMMDLEN_V(immlen));
+ req->flowid_len16 = cpu_to_be32(FW_WR_FLOWID_V(csk->tid) |
+ FW_WR_LEN16_V(credits));
+ req->plen = htonl(len);
+ wr_ulp_mode = FW_OFLD_TX_DATA_WR_ULPMODE_V(ULP_MODE_ISCSI) |
+ FW_OFLD_TX_DATA_WR_ULPSUBMODE_V(submode);
+
+ req->tunnel_to_proxy = htonl((wr_ulp_mode) | force |
+ FW_OFLD_TX_DATA_WR_SHOVE_V(skb_peek(&csk->txq) ? 0 : 1));
+}
+
+static void cxgbit_arp_failure_skb_discard(void *handle, struct sk_buff *skb)
+{
+ kfree_skb(skb);
+}
+
+void cxgbit_push_tx_frames(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+
+ while (csk->wr_cred && ((skb = skb_peek(&csk->txq)) != NULL)) {
+ u32 dlen = skb->len;
+ u32 len = skb->len;
+ u32 credits_needed;
+ u32 compl = 0;
+ u32 flowclen16 = 0;
+ u32 iso_cpl_len = 0;
+
+ if (cxgbit_skcb_flags(skb) & SKCBF_TX_ISO)
+ iso_cpl_len = sizeof(struct cpl_tx_data_iso);
+
+ if (cxgbit_is_ofld_imm(skb))
+ credits_needed = DIV_ROUND_UP(dlen + iso_cpl_len, 16);
+ else
+ credits_needed = DIV_ROUND_UP((8 *
+ cxgbit_calc_tx_flits_ofld(skb)) +
+ iso_cpl_len, 16);
+
+ if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_NEED_HDR))
+ credits_needed += DIV_ROUND_UP(
+ sizeof(struct fw_ofld_tx_data_wr), 16);
+ /*
+ * Assumes the initial credits is large enough to support
+ * fw_flowc_wr plus largest possible first payload
+ */
+
+ if (!test_and_set_bit(CSK_TX_DATA_SENT, &csk->com.flags)) {
+ flowclen16 = cxgbit_send_tx_flowc_wr(csk);
+ csk->wr_cred -= flowclen16;
+ csk->wr_una_cred += flowclen16;
+ }
+
+ if (csk->wr_cred < credits_needed) {
+ pr_debug("csk 0x%p, skb %u/%u, wr %d < %u.\n",
+ csk, skb->len, skb->data_len,
+ credits_needed, csk->wr_cred);
+ break;
+ }
+ __skb_unlink(skb, &csk->txq);
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ skb->csum = credits_needed + flowclen16;
+ csk->wr_cred -= credits_needed;
+ csk->wr_una_cred += credits_needed;
+
+ pr_debug("csk 0x%p, skb %u/%u, wr %d, left %u, unack %u.\n",
+ csk, skb->len, skb->data_len, credits_needed,
+ csk->wr_cred, csk->wr_una_cred);
+
+ if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_NEED_HDR)) {
+ len += cxgbit_skcb_tx_extralen(skb);
+
+ if ((csk->wr_una_cred >= (csk->wr_max_cred / 2)) ||
+ (!before(csk->write_seq,
+ csk->snd_una + csk->snd_win))) {
+ compl = 1;
+ csk->wr_una_cred = 0;
+ }
+
+ cxgbit_tx_data_wr(csk, skb, dlen, len, credits_needed,
+ compl);
+ csk->snd_nxt += len;
+
+ } else if ((cxgbit_skcb_flags(skb) & SKCBF_TX_FLAG_COMPL) ||
+ (csk->wr_una_cred >= (csk->wr_max_cred / 2))) {
+ struct cpl_close_con_req *req =
+ (struct cpl_close_con_req *)skb->data;
+ req->wr.wr_hi |= htonl(FW_WR_COMPL_F);
+ csk->wr_una_cred = 0;
+ }
+
+ cxgbit_sock_enqueue_wr(csk, skb);
+ t4_set_arp_err_handler(skb, csk,
+ cxgbit_arp_failure_skb_discard);
+
+ pr_debug("csk 0x%p,%u, skb 0x%p, %u.\n",
+ csk, csk->tid, skb, len);
+
+ cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t);
+ }
+}
+
+static bool cxgbit_lock_sock(struct cxgbit_sock *csk)
+{
+ spin_lock_bh(&csk->lock);
+
+ if (before(csk->write_seq, csk->snd_una + csk->snd_win))
+ csk->lock_owner = true;
+
+ spin_unlock_bh(&csk->lock);
+
+ return csk->lock_owner;
+}
+
+static void cxgbit_unlock_sock(struct cxgbit_sock *csk)
+{
+ struct sk_buff_head backlogq;
+ struct sk_buff *skb;
+ void (*fn)(struct cxgbit_sock *, struct sk_buff *);
+
+ skb_queue_head_init(&backlogq);
+
+ spin_lock_bh(&csk->lock);
+ while (skb_queue_len(&csk->backlogq)) {
+ skb_queue_splice_init(&csk->backlogq, &backlogq);
+ spin_unlock_bh(&csk->lock);
+
+ while ((skb = __skb_dequeue(&backlogq))) {
+ fn = cxgbit_skcb_rx_backlog_fn(skb);
+ fn(csk, skb);
+ }
+
+ spin_lock_bh(&csk->lock);
+ }
+
+ csk->lock_owner = false;
+ spin_unlock_bh(&csk->lock);
+}
+
+static int cxgbit_queue_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ int ret = 0;
+
+ wait_event_interruptible(csk->ack_waitq, cxgbit_lock_sock(csk));
+
+ if (unlikely((csk->com.state != CSK_STATE_ESTABLISHED) ||
+ signal_pending(current))) {
+ __kfree_skb(skb);
+ __skb_queue_purge(&csk->ppodq);
+ ret = -1;
+ spin_lock_bh(&csk->lock);
+ if (csk->lock_owner) {
+ spin_unlock_bh(&csk->lock);
+ goto unlock;
+ }
+ spin_unlock_bh(&csk->lock);
+ return ret;
+ }
+
+ csk->write_seq += skb->len +
+ cxgbit_skcb_tx_extralen(skb);
+
+ skb_queue_splice_tail_init(&csk->ppodq, &csk->txq);
+ __skb_queue_tail(&csk->txq, skb);
+ cxgbit_push_tx_frames(csk);
+
+unlock:
+ cxgbit_unlock_sock(csk);
+ return ret;
+}
+
+static int
+cxgbit_map_skb(struct iscsi_cmd *cmd, struct sk_buff *skb, u32 data_offset,
+ u32 data_length)
+{
+ u32 i = 0, nr_frags = MAX_SKB_FRAGS;
+ u32 padding = ((-data_length) & 3);
+ struct scatterlist *sg;
+ struct page *page;
+ unsigned int page_off;
+
+ if (padding)
+ nr_frags--;
+
+ /*
+ * We know each entry in t_data_sg contains a page.
+ */
+ sg = &cmd->se_cmd.t_data_sg[data_offset / PAGE_SIZE];
+ page_off = (data_offset % PAGE_SIZE);
+
+ while (data_length && (i < nr_frags)) {
+ u32 cur_len = min_t(u32, data_length, sg->length - page_off);
+
+ page = sg_page(sg);
+
+ get_page(page);
+ skb_fill_page_desc(skb, i, page, sg->offset + page_off,
+ cur_len);
+ skb->data_len += cur_len;
+ skb->len += cur_len;
+ skb->truesize += cur_len;
+
+ data_length -= cur_len;
+ page_off = 0;
+ sg = sg_next(sg);
+ i++;
+ }
+
+ if (data_length)
+ return -1;
+
+ if (padding) {
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page)
+ return -1;
+ skb_fill_page_desc(skb, i, page, 0, padding);
+ skb->data_len += padding;
+ skb->len += padding;
+ skb->truesize += padding;
+ }
+
+ return 0;
+}
+
+static int
+cxgbit_tx_datain_iso(struct cxgbit_sock *csk, struct iscsi_cmd *cmd,
+ struct iscsi_datain_req *dr)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct sk_buff *skb;
+ struct iscsi_datain datain;
+ struct cxgbit_iso_info iso_info;
+ u32 data_length = cmd->se_cmd.data_length;
+ u32 mrdsl = conn->conn_ops->MaxRecvDataSegmentLength;
+ u32 num_pdu, plen, tx_data = 0;
+ bool task_sense = !!(cmd->se_cmd.se_cmd_flags &
+ SCF_TRANSPORT_TASK_SENSE);
+ bool set_statsn = false;
+ int ret = -1;
+
+ while (data_length) {
+ num_pdu = (data_length + mrdsl - 1) / mrdsl;
+ if (num_pdu > csk->max_iso_npdu)
+ num_pdu = csk->max_iso_npdu;
+
+ plen = num_pdu * mrdsl;
+ if (plen > data_length)
+ plen = data_length;
+
+ skb = __cxgbit_alloc_skb(csk, 0, true);
+ if (unlikely(!skb))
+ return -ENOMEM;
+
+ memset(skb->data, 0, ISCSI_HDR_LEN);
+ cxgbit_skcb_flags(skb) |= SKCBF_TX_ISO;
+ cxgbit_skcb_submode(skb) |= (csk->submode &
+ CXGBIT_SUBMODE_DCRC);
+ cxgbit_skcb_tx_extralen(skb) = (num_pdu *
+ cxgbit_digest_len[cxgbit_skcb_submode(skb)]) +
+ ((num_pdu - 1) * ISCSI_HDR_LEN);
+
+ memset(&datain, 0, sizeof(struct iscsi_datain));
+ memset(&iso_info, 0, sizeof(iso_info));
+
+ if (!tx_data)
+ iso_info.flags |= CXGBIT_ISO_FSLICE;
+
+ if (!(data_length - plen)) {
+ iso_info.flags |= CXGBIT_ISO_LSLICE;
+ if (!task_sense) {
+ datain.flags = ISCSI_FLAG_DATA_STATUS;
+ iscsit_increment_maxcmdsn(cmd, conn->sess);
+ cmd->stat_sn = conn->stat_sn++;
+ set_statsn = true;
+ }
+ }
+
+ iso_info.burst_len = num_pdu * mrdsl;
+ iso_info.mpdu = mrdsl;
+ iso_info.len = ISCSI_HDR_LEN + plen;
+
+ cxgbit_cpl_tx_data_iso(skb, &iso_info);
+
+ datain.offset = tx_data;
+ datain.data_sn = cmd->data_sn - 1;
+
+ iscsit_build_datain_pdu(cmd, conn, &datain,
+ (struct iscsi_data_rsp *)skb->data,
+ set_statsn);
+
+ ret = cxgbit_map_skb(cmd, skb, tx_data, plen);
+ if (unlikely(ret)) {
+ __kfree_skb(skb);
+ goto out;
+ }
+
+ ret = cxgbit_queue_skb(csk, skb);
+ if (unlikely(ret))
+ goto out;
+
+ tx_data += plen;
+ data_length -= plen;
+
+ cmd->read_data_done += plen;
+ cmd->data_sn += num_pdu;
+ }
+
+ dr->dr_complete = DATAIN_COMPLETE_NORMAL;
+
+ return 0;
+
+out:
+ return ret;
+}
+
+static int
+cxgbit_tx_datain(struct cxgbit_sock *csk, struct iscsi_cmd *cmd,
+ const struct iscsi_datain *datain)
+{
+ struct sk_buff *skb;
+ int ret = 0;
+
+ skb = cxgbit_alloc_skb(csk, 0);
+ if (unlikely(!skb))
+ return -ENOMEM;
+
+ memcpy(skb->data, cmd->pdu, ISCSI_HDR_LEN);
+
+ if (datain->length) {
+ cxgbit_skcb_submode(skb) |= (csk->submode &
+ CXGBIT_SUBMODE_DCRC);
+ cxgbit_skcb_tx_extralen(skb) =
+ cxgbit_digest_len[cxgbit_skcb_submode(skb)];
+ }
+
+ ret = cxgbit_map_skb(cmd, skb, datain->offset, datain->length);
+ if (ret < 0) {
+ __kfree_skb(skb);
+ return ret;
+ }
+
+ return cxgbit_queue_skb(csk, skb);
+}
+
+static int
+cxgbit_xmit_datain_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct iscsi_datain_req *dr,
+ const struct iscsi_datain *datain)
+{
+ struct cxgbit_sock *csk = conn->context;
+ u32 data_length = cmd->se_cmd.data_length;
+ u32 padding = ((-data_length) & 3);
+ u32 mrdsl = conn->conn_ops->MaxRecvDataSegmentLength;
+
+ if ((data_length > mrdsl) && (!dr->recovery) &&
+ (!padding) && (!datain->offset) && csk->max_iso_npdu) {
+ atomic_long_add(data_length - datain->length,
+ &conn->sess->tx_data_octets);
+ return cxgbit_tx_datain_iso(csk, cmd, dr);
+ }
+
+ return cxgbit_tx_datain(csk, cmd, datain);
+}
+
+static int
+cxgbit_xmit_nondatain_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ const void *data_buf, u32 data_buf_len)
+{
+ struct cxgbit_sock *csk = conn->context;
+ struct sk_buff *skb;
+ u32 padding = ((-data_buf_len) & 3);
+
+ skb = cxgbit_alloc_skb(csk, data_buf_len + padding);
+ if (unlikely(!skb))
+ return -ENOMEM;
+
+ memcpy(skb->data, cmd->pdu, ISCSI_HDR_LEN);
+
+ if (data_buf_len) {
+ u32 pad_bytes = 0;
+
+ skb_store_bits(skb, ISCSI_HDR_LEN, data_buf, data_buf_len);
+
+ if (padding)
+ skb_store_bits(skb, ISCSI_HDR_LEN + data_buf_len,
+ &pad_bytes, padding);
+ }
+
+ cxgbit_skcb_tx_extralen(skb) = cxgbit_digest_len[
+ cxgbit_skcb_submode(skb)];
+
+ return cxgbit_queue_skb(csk, skb);
+}
+
+int
+cxgbit_xmit_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct iscsi_datain_req *dr, const void *buf, u32 buf_len)
+{
+ if (dr)
+ return cxgbit_xmit_datain_pdu(conn, cmd, dr, buf);
+ else
+ return cxgbit_xmit_nondatain_pdu(conn, cmd, buf, buf_len);
+}
+
+int cxgbit_validate_params(struct iscsi_conn *conn)
+{
+ struct cxgbit_sock *csk = conn->context;
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct iscsi_param *param;
+ u32 max_xmitdsl;
+
+ param = iscsi_find_param_from_key(MAXXMITDATASEGMENTLENGTH,
+ conn->param_list);
+ if (!param)
+ return -1;
+
+ if (kstrtou32(param->value, 0, &max_xmitdsl) < 0)
+ return -1;
+
+ if (max_xmitdsl > cdev->mdsl) {
+ if (iscsi_change_param_sprintf(
+ conn, "MaxXmitDataSegmentLength=%u", cdev->mdsl))
+ return -1;
+ }
+
+ return 0;
+}
+
+static int cxgbit_set_digest(struct cxgbit_sock *csk)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct iscsi_param *param;
+
+ param = iscsi_find_param_from_key(HEADERDIGEST, conn->param_list);
+ if (!param) {
+ pr_err("param not found key %s\n", HEADERDIGEST);
+ return -1;
+ }
+
+ if (!strcmp(param->value, CRC32C))
+ csk->submode |= CXGBIT_SUBMODE_HCRC;
+
+ param = iscsi_find_param_from_key(DATADIGEST, conn->param_list);
+ if (!param) {
+ csk->submode = 0;
+ pr_err("param not found key %s\n", DATADIGEST);
+ return -1;
+ }
+
+ if (!strcmp(param->value, CRC32C))
+ csk->submode |= CXGBIT_SUBMODE_DCRC;
+
+ if (cxgbit_setup_conn_digest(csk)) {
+ csk->submode = 0;
+ return -1;
+ }
+
+ return 0;
+}
+
+static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct iscsi_conn_ops *conn_ops = conn->conn_ops;
+ struct iscsi_param *param;
+ u32 mrdsl, mbl;
+ u32 max_npdu, max_iso_npdu;
+
+ if (conn->login->leading_connection) {
+ param = iscsi_find_param_from_key(DATASEQUENCEINORDER,
+ conn->param_list);
+ if (!param) {
+ pr_err("param not found key %s\n", DATASEQUENCEINORDER);
+ return -1;
+ }
+
+ if (strcmp(param->value, YES))
+ return 0;
+
+ param = iscsi_find_param_from_key(DATAPDUINORDER,
+ conn->param_list);
+ if (!param) {
+ pr_err("param not found key %s\n", DATAPDUINORDER);
+ return -1;
+ }
+
+ if (strcmp(param->value, YES))
+ return 0;
+
+ param = iscsi_find_param_from_key(MAXBURSTLENGTH,
+ conn->param_list);
+ if (!param) {
+ pr_err("param not found key %s\n", MAXBURSTLENGTH);
+ return -1;
+ }
+
+ if (kstrtou32(param->value, 0, &mbl) < 0)
+ return -1;
+ } else {
+ if (!conn->sess->sess_ops->DataSequenceInOrder)
+ return 0;
+ if (!conn->sess->sess_ops->DataPDUInOrder)
+ return 0;
+
+ mbl = conn->sess->sess_ops->MaxBurstLength;
+ }
+
+ mrdsl = conn_ops->MaxRecvDataSegmentLength;
+ max_npdu = mbl / mrdsl;
+
+ max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD /
+ (ISCSI_HDR_LEN + mrdsl +
+ cxgbit_digest_len[csk->submode]);
+
+ csk->max_iso_npdu = min(max_npdu, max_iso_npdu);
+
+ if (csk->max_iso_npdu <= 1)
+ csk->max_iso_npdu = 0;
+
+ return 0;
+}
+
+static int cxgbit_set_params(struct iscsi_conn *conn)
+{
+ struct cxgbit_sock *csk = conn->context;
+ struct cxgbit_device *cdev = csk->com.cdev;
+ struct cxgbi_ppm *ppm = *csk->com.cdev->lldi.iscsi_ppm;
+ struct iscsi_conn_ops *conn_ops = conn->conn_ops;
+ struct iscsi_param *param;
+ u8 erl;
+
+ if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl)
+ conn_ops->MaxRecvDataSegmentLength = cdev->mdsl;
+
+ if (conn->login->leading_connection) {
+ param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL,
+ conn->param_list);
+ if (!param) {
+ pr_err("param not found key %s\n", ERRORRECOVERYLEVEL);
+ return -1;
+ }
+ if (kstrtou8(param->value, 0, &erl) < 0)
+ return -1;
+ } else {
+ erl = conn->sess->sess_ops->ErrorRecoveryLevel;
+ }
+
+ if (!erl) {
+ if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) {
+ if (cxgbit_set_iso_npdu(csk))
+ return -1;
+ }
+
+ if (test_bit(CDEV_DDP_ENABLE, &cdev->flags)) {
+ if (cxgbit_setup_conn_pgidx(csk,
+ ppm->tformat.pgsz_idx_dflt))
+ return -1;
+ set_bit(CSK_DDP_ENABLE, &csk->com.flags);
+ }
+ }
+
+ if (cxgbit_set_digest(csk))
+ return -1;
+
+ return 0;
+}
+
+int
+cxgbit_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
+ u32 length)
+{
+ struct cxgbit_sock *csk = conn->context;
+ struct sk_buff *skb;
+ u32 padding_buf = 0;
+ u8 padding = ((-length) & 3);
+
+ skb = cxgbit_alloc_skb(csk, length + padding);
+ if (!skb)
+ return -ENOMEM;
+ skb_store_bits(skb, 0, login->rsp, ISCSI_HDR_LEN);
+ skb_store_bits(skb, ISCSI_HDR_LEN, login->rsp_buf, length);
+
+ if (padding)
+ skb_store_bits(skb, ISCSI_HDR_LEN + length,
+ &padding_buf, padding);
+
+ if (login->login_complete) {
+ if (cxgbit_set_params(conn)) {
+ kfree_skb(skb);
+ return -1;
+ }
+
+ set_bit(CSK_LOGIN_DONE, &csk->com.flags);
+ }
+
+ if (cxgbit_queue_skb(csk, skb))
+ return -1;
+
+ if ((!login->login_complete) && (!login->login_failed))
+ schedule_delayed_work(&conn->login_work, 0);
+
+ return 0;
+}
+
+static void
+cxgbit_skb_copy_to_sg(struct sk_buff *skb, struct scatterlist *sg,
+ unsigned int nents)
+{
+ struct skb_seq_state st;
+ const u8 *buf;
+ unsigned int consumed = 0, buf_len;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(skb);
+
+ skb_prepare_seq_read(skb, pdu_cb->doffset,
+ pdu_cb->doffset + pdu_cb->dlen,
+ &st);
+
+ while (true) {
+ buf_len = skb_seq_read(consumed, &buf, &st);
+ if (!buf_len) {
+ skb_abort_seq_read(&st);
+ break;
+ }
+
+ consumed += sg_pcopy_from_buffer(sg, nents, (void *)buf,
+ buf_len, consumed);
+ }
+}
+
+static struct iscsi_cmd *cxgbit_allocate_cmd(struct cxgbit_sock *csk)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct cxgbi_ppm *ppm = cdev2ppm(csk->com.cdev);
+ struct cxgbit_cmd *ccmd;
+ struct iscsi_cmd *cmd;
+
+ cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
+ if (!cmd) {
+ pr_err("Unable to allocate iscsi_cmd + cxgbit_cmd\n");
+ return NULL;
+ }
+
+ ccmd = iscsit_priv_cmd(cmd);
+ ccmd->ttinfo.tag = ppm->tformat.no_ddp_mask;
+ ccmd->setup_ddp = true;
+
+ return cmd;
+}
+
+static int
+cxgbit_handle_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr,
+ u32 length)
+{
+ struct iscsi_conn *conn = cmd->conn;
+ struct cxgbit_sock *csk = conn->context;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+
+ if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) {
+ pr_err("ImmediateData CRC32C DataDigest error\n");
+ if (!conn->sess->sess_ops->ErrorRecoveryLevel) {
+ pr_err("Unable to recover from"
+ " Immediate Data digest failure while"
+ " in ERL=0.\n");
+ iscsit_reject_cmd(cmd, ISCSI_REASON_DATA_DIGEST_ERROR,
+ (unsigned char *)hdr);
+ return IMMEDIATE_DATA_CANNOT_RECOVER;
+ }
+
+ iscsit_reject_cmd(cmd, ISCSI_REASON_DATA_DIGEST_ERROR,
+ (unsigned char *)hdr);
+ return IMMEDIATE_DATA_ERL1_CRC_FAILURE;
+ }
+
+ if (cmd->se_cmd.se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) {
+ struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd);
+ struct skb_shared_info *ssi = skb_shinfo(csk->skb);
+ skb_frag_t *dfrag = &ssi->frags[pdu_cb->dfrag_idx];
+
+ sg_init_table(&ccmd->sg, 1);
+ sg_set_page(&ccmd->sg, dfrag->page.p, skb_frag_size(dfrag),
+ dfrag->page_offset);
+ get_page(dfrag->page.p);
+
+ cmd->se_cmd.t_data_sg = &ccmd->sg;
+ cmd->se_cmd.t_data_nents = 1;
+
+ ccmd->release = true;
+ } else {
+ struct scatterlist *sg = &cmd->se_cmd.t_data_sg[0];
+ u32 sg_nents = max(1UL, DIV_ROUND_UP(pdu_cb->dlen, PAGE_SIZE));
+
+ cxgbit_skb_copy_to_sg(csk->skb, sg, sg_nents);
+ }
+
+ cmd->write_data_done += pdu_cb->dlen;
+
+ if (cmd->write_data_done == cmd->se_cmd.data_length) {
+ spin_lock_bh(&cmd->istate_lock);
+ cmd->cmd_flags |= ICF_GOT_LAST_DATAOUT;
+ cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT;
+ spin_unlock_bh(&cmd->istate_lock);
+ }
+
+ return IMMEDIATE_DATA_NORMAL_OPERATION;
+}
+
+static int
+cxgbit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr,
+ bool dump_payload)
+{
+ struct iscsi_conn *conn = cmd->conn;
+ int cmdsn_ret = 0, immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION;
+ /*
+ * Special case for Unsupported SAM WRITE Opcodes and ImmediateData=Yes.
+ */
+ if (dump_payload)
+ goto after_immediate_data;
+
+ immed_ret = cxgbit_handle_immediate_data(cmd, hdr,
+ cmd->first_burst_len);
+after_immediate_data:
+ if (immed_ret == IMMEDIATE_DATA_NORMAL_OPERATION) {
+ /*
+ * A PDU/CmdSN carrying Immediate Data passed
+ * DataCRC, check against ExpCmdSN/MaxCmdSN if
+ * Immediate Bit is not set.
+ */
+ cmdsn_ret = iscsit_sequence_cmd(conn, cmd,
+ (unsigned char *)hdr,
+ hdr->cmdsn);
+ if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
+ return -1;
+
+ if (cmd->sense_reason || cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
+ target_put_sess_cmd(&cmd->se_cmd);
+ return 0;
+ } else if (cmd->unsolicited_data) {
+ iscsit_set_unsoliticed_dataout(cmd);
+ }
+
+ } else if (immed_ret == IMMEDIATE_DATA_ERL1_CRC_FAILURE) {
+ /*
+ * Immediate Data failed DataCRC and ERL>=1,
+ * silently drop this PDU and let the initiator
+ * plug the CmdSN gap.
+ *
+ * FIXME: Send Unsolicited NOPIN with reserved
+ * TTT here to help the initiator figure out
+ * the missing CmdSN, although they should be
+ * intelligent enough to determine the missing
+ * CmdSN and issue a retry to plug the sequence.
+ */
+ cmd->i_state = ISTATE_REMOVE;
+ iscsit_add_cmd_to_immediate_queue(cmd, conn, cmd->i_state);
+ } else /* immed_ret == IMMEDIATE_DATA_CANNOT_RECOVER */
+ return -1;
+
+ return 0;
+}
+
+static int
+cxgbit_handle_scsi_cmd(struct cxgbit_sock *csk, struct iscsi_cmd *cmd)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)pdu_cb->hdr;
+ int rc;
+ bool dump_payload = false;
+
+ rc = iscsit_setup_scsi_cmd(conn, cmd, (unsigned char *)hdr);
+ if (rc < 0)
+ return rc;
+
+ if (pdu_cb->dlen && (pdu_cb->dlen == cmd->se_cmd.data_length) &&
+ (pdu_cb->nr_dfrags == 1))
+ cmd->se_cmd.se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
+
+ rc = iscsit_process_scsi_cmd(conn, cmd, hdr);
+ if (rc < 0)
+ return 0;
+ else if (rc > 0)
+ dump_payload = true;
+
+ if (!pdu_cb->dlen)
+ return 0;
+
+ return cxgbit_get_immediate_data(cmd, hdr, dump_payload);
+}
+
+static int cxgbit_handle_iscsi_dataout(struct cxgbit_sock *csk)
+{
+ struct scatterlist *sg_start;
+ struct iscsi_conn *conn = csk->conn;
+ struct iscsi_cmd *cmd = NULL;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_data *hdr = (struct iscsi_data *)pdu_cb->hdr;
+ u32 data_offset = be32_to_cpu(hdr->offset);
+ u32 data_len = pdu_cb->dlen;
+ int rc, sg_nents, sg_off;
+ bool dcrc_err = false;
+
+ rc = iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, &cmd);
+ if (rc < 0)
+ return rc;
+ else if (!cmd)
+ return 0;
+
+ if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) {
+ pr_err("ITT: 0x%08x, Offset: %u, Length: %u,"
+ " DataSN: 0x%08x\n",
+ hdr->itt, hdr->offset, data_len,
+ hdr->datasn);
+
+ dcrc_err = true;
+ goto check_payload;
+ }
+
+ pr_debug("DataOut data_len: %u, "
+ "write_data_done: %u, data_length: %u\n",
+ data_len, cmd->write_data_done,
+ cmd->se_cmd.data_length);
+
+ if (!(pdu_cb->flags & PDUCBF_RX_DATA_DDPD)) {
+ sg_off = data_offset / PAGE_SIZE;
+ sg_start = &cmd->se_cmd.t_data_sg[sg_off];
+ sg_nents = max(1UL, DIV_ROUND_UP(data_len, PAGE_SIZE));
+
+ cxgbit_skb_copy_to_sg(csk->skb, sg_start, sg_nents);
+ }
+
+check_payload:
+
+ rc = iscsit_check_dataout_payload(cmd, hdr, dcrc_err);
+ if (rc < 0)
+ return rc;
+
+ return 0;
+}
+
+static int cxgbit_handle_nop_out(struct cxgbit_sock *csk, struct iscsi_cmd *cmd)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_nopout *hdr = (struct iscsi_nopout *)pdu_cb->hdr;
+ unsigned char *ping_data = NULL;
+ u32 payload_length = pdu_cb->dlen;
+ int ret;
+
+ ret = iscsit_setup_nop_out(conn, cmd, hdr);
+ if (ret < 0)
+ return 0;
+
+ if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) {
+ if (!conn->sess->sess_ops->ErrorRecoveryLevel) {
+ pr_err("Unable to recover from"
+ " NOPOUT Ping DataCRC failure while in"
+ " ERL=0.\n");
+ ret = -1;
+ goto out;
+ } else {
+ /*
+ * drop this PDU and let the
+ * initiator plug the CmdSN gap.
+ */
+ pr_info("Dropping NOPOUT"
+ " Command CmdSN: 0x%08x due to"
+ " DataCRC error.\n", hdr->cmdsn);
+ ret = 0;
+ goto out;
+ }
+ }
+
+ /*
+ * Handle NOP-OUT payload for traditional iSCSI sockets
+ */
+ if (payload_length && hdr->ttt == cpu_to_be32(0xFFFFFFFF)) {
+ ping_data = kzalloc(payload_length + 1, GFP_KERNEL);
+ if (!ping_data) {
+ pr_err("Unable to allocate memory for"
+ " NOPOUT ping data.\n");
+ ret = -1;
+ goto out;
+ }
+
+ skb_copy_bits(csk->skb, pdu_cb->doffset,
+ ping_data, payload_length);
+
+ ping_data[payload_length] = '\0';
+ /*
+ * Attach ping data to struct iscsi_cmd->buf_ptr.
+ */
+ cmd->buf_ptr = ping_data;
+ cmd->buf_ptr_size = payload_length;
+
+ pr_debug("Got %u bytes of NOPOUT ping"
+ " data.\n", payload_length);
+ pr_debug("Ping Data: \"%s\"\n", ping_data);
+ }
+
+ return iscsit_process_nop_out(conn, cmd, hdr);
+out:
+ if (cmd)
+ iscsit_free_cmd(cmd, false);
+ return ret;
+}
+
+static int
+cxgbit_handle_text_cmd(struct cxgbit_sock *csk, struct iscsi_cmd *cmd)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_text *hdr = (struct iscsi_text *)pdu_cb->hdr;
+ u32 payload_length = pdu_cb->dlen;
+ int rc;
+ unsigned char *text_in = NULL;
+
+ rc = iscsit_setup_text_cmd(conn, cmd, hdr);
+ if (rc < 0)
+ return rc;
+
+ if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) {
+ if (!conn->sess->sess_ops->ErrorRecoveryLevel) {
+ pr_err("Unable to recover from"
+ " Text Data digest failure while in"
+ " ERL=0.\n");
+ goto reject;
+ } else {
+ /*
+ * drop this PDU and let the
+ * initiator plug the CmdSN gap.
+ */
+ pr_info("Dropping Text"
+ " Command CmdSN: 0x%08x due to"
+ " DataCRC error.\n", hdr->cmdsn);
+ return 0;
+ }
+ }
+
+ if (payload_length) {
+ text_in = kzalloc(payload_length, GFP_KERNEL);
+ if (!text_in) {
+ pr_err("Unable to allocate text_in of payload_length: %u\n",
+ payload_length);
+ return -ENOMEM;
+ }
+ skb_copy_bits(csk->skb, pdu_cb->doffset,
+ text_in, payload_length);
+
+ text_in[payload_length - 1] = '\0';
+
+ cmd->text_in_ptr = text_in;
+ }
+
+ return iscsit_process_text_cmd(conn, cmd, hdr);
+
+reject:
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR,
+ pdu_cb->hdr);
+}
+
+static int cxgbit_target_rx_opcode(struct cxgbit_sock *csk)
+{
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_hdr *hdr = (struct iscsi_hdr *)pdu_cb->hdr;
+ struct iscsi_conn *conn = csk->conn;
+ struct iscsi_cmd *cmd = NULL;
+ u8 opcode = (hdr->opcode & ISCSI_OPCODE_MASK);
+ int ret = -EINVAL;
+
+ switch (opcode) {
+ case ISCSI_OP_SCSI_CMD:
+ cmd = cxgbit_allocate_cmd(csk);
+ if (!cmd)
+ goto reject;
+
+ ret = cxgbit_handle_scsi_cmd(csk, cmd);
+ break;
+ case ISCSI_OP_SCSI_DATA_OUT:
+ ret = cxgbit_handle_iscsi_dataout(csk);
+ break;
+ case ISCSI_OP_NOOP_OUT:
+ if (hdr->ttt == cpu_to_be32(0xFFFFFFFF)) {
+ cmd = cxgbit_allocate_cmd(csk);
+ if (!cmd)
+ goto reject;
+ }
+
+ ret = cxgbit_handle_nop_out(csk, cmd);
+ break;
+ case ISCSI_OP_SCSI_TMFUNC:
+ cmd = cxgbit_allocate_cmd(csk);
+ if (!cmd)
+ goto reject;
+
+ ret = iscsit_handle_task_mgt_cmd(conn, cmd,
+ (unsigned char *)hdr);
+ break;
+ case ISCSI_OP_TEXT:
+ if (hdr->ttt != cpu_to_be32(0xFFFFFFFF)) {
+ cmd = iscsit_find_cmd_from_itt(conn, hdr->itt);
+ if (!cmd)
+ goto reject;
+ } else {
+ cmd = cxgbit_allocate_cmd(csk);
+ if (!cmd)
+ goto reject;
+ }
+
+ ret = cxgbit_handle_text_cmd(csk, cmd);
+ break;
+ case ISCSI_OP_LOGOUT:
+ cmd = cxgbit_allocate_cmd(csk);
+ if (!cmd)
+ goto reject;
+
+ ret = iscsit_handle_logout_cmd(conn, cmd, (unsigned char *)hdr);
+ if (ret > 0)
+ wait_for_completion_timeout(&conn->conn_logout_comp,
+ SECONDS_FOR_LOGOUT_COMP
+ * HZ);
+ break;
+ case ISCSI_OP_SNACK:
+ ret = iscsit_handle_snack(conn, (unsigned char *)hdr);
+ break;
+ default:
+ pr_err("Got unknown iSCSI OpCode: 0x%02x\n", opcode);
+ dump_stack();
+ break;
+ }
+
+ return ret;
+
+reject:
+ return iscsit_add_reject(conn, ISCSI_REASON_BOOKMARK_NO_RESOURCES,
+ (unsigned char *)hdr);
+ return ret;
+}
+
+static int cxgbit_rx_opcode(struct cxgbit_sock *csk)
+{
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_conn *conn = csk->conn;
+ struct iscsi_hdr *hdr = pdu_cb->hdr;
+ u8 opcode;
+
+ if (pdu_cb->flags & PDUCBF_RX_HCRC_ERR) {
+ atomic_long_inc(&conn->sess->conn_digest_errors);
+ goto transport_err;
+ }
+
+ if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT)
+ goto transport_err;
+
+ opcode = hdr->opcode & ISCSI_OPCODE_MASK;
+
+ if (conn->sess->sess_ops->SessionType &&
+ ((!(opcode & ISCSI_OP_TEXT)) ||
+ (!(opcode & ISCSI_OP_LOGOUT)))) {
+ pr_err("Received illegal iSCSI Opcode: 0x%02x"
+ " while in Discovery Session, rejecting.\n", opcode);
+ iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ (unsigned char *)hdr);
+ goto transport_err;
+ }
+
+ if (cxgbit_target_rx_opcode(csk) < 0)
+ goto transport_err;
+
+ return 0;
+
+transport_err:
+ return -1;
+}
+
+static int cxgbit_rx_login_pdu(struct cxgbit_sock *csk)
+{
+ struct iscsi_conn *conn = csk->conn;
+ struct iscsi_login *login = conn->login;
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb);
+ struct iscsi_login_req *login_req;
+
+ login_req = (struct iscsi_login_req *)login->req;
+ memcpy(login_req, pdu_cb->hdr, sizeof(*login_req));
+
+ pr_debug("Got Login Command, Flags 0x%02x, ITT: 0x%08x,"
+ " CmdSN: 0x%08x, ExpStatSN: 0x%08x, CID: %hu, Length: %u\n",
+ login_req->flags, login_req->itt, login_req->cmdsn,
+ login_req->exp_statsn, login_req->cid, pdu_cb->dlen);
+ /*
+ * Setup the initial iscsi_login values from the leading
+ * login request PDU.
+ */
+ if (login->first_request) {
+ login_req = (struct iscsi_login_req *)login->req;
+ login->leading_connection = (!login_req->tsih) ? 1 : 0;
+ login->current_stage = ISCSI_LOGIN_CURRENT_STAGE(
+ login_req->flags);
+ login->version_min = login_req->min_version;
+ login->version_max = login_req->max_version;
+ memcpy(login->isid, login_req->isid, 6);
+ login->cmd_sn = be32_to_cpu(login_req->cmdsn);
+ login->init_task_tag = login_req->itt;
+ login->initial_exp_statsn = be32_to_cpu(login_req->exp_statsn);
+ login->cid = be16_to_cpu(login_req->cid);
+ login->tsih = be16_to_cpu(login_req->tsih);
+ }
+
+ if (iscsi_target_check_login_request(conn, login) < 0)
+ return -1;
+
+ memset(login->req_buf, 0, MAX_KEY_VALUE_PAIRS);
+ skb_copy_bits(csk->skb, pdu_cb->doffset, login->req_buf, pdu_cb->dlen);
+
+ return 0;
+}
+
+static int
+cxgbit_process_iscsi_pdu(struct cxgbit_sock *csk, struct sk_buff *skb, int idx)
+{
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, idx);
+ int ret;
+
+ cxgbit_rx_pdu_cb(skb) = pdu_cb;
+
+ csk->skb = skb;
+
+ if (!test_bit(CSK_LOGIN_DONE, &csk->com.flags)) {
+ ret = cxgbit_rx_login_pdu(csk);
+ set_bit(CSK_LOGIN_PDU_DONE, &csk->com.flags);
+ } else {
+ ret = cxgbit_rx_opcode(csk);
+ }
+
+ return ret;
+}
+
+static void cxgbit_lro_skb_dump(struct sk_buff *skb)
+{
+ struct skb_shared_info *ssi = skb_shinfo(skb);
+ struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, 0);
+ u8 i;
+
+ pr_info("skb 0x%p, head 0x%p, 0x%p, len %u,%u, frags %u.\n",
+ skb, skb->head, skb->data, skb->len, skb->data_len,
+ ssi->nr_frags);
+ pr_info("skb 0x%p, lro_cb, csk 0x%p, pdu %u, %u.\n",
+ skb, lro_cb->csk, lro_cb->pdu_idx, lro_cb->pdu_totallen);
+
+ for (i = 0; i < lro_cb->pdu_idx; i++, pdu_cb++)
+ pr_info("skb 0x%p, pdu %d, %u, f 0x%x, seq 0x%x, dcrc 0x%x, "
+ "frags %u.\n",
+ skb, i, pdu_cb->pdulen, pdu_cb->flags, pdu_cb->seq,
+ pdu_cb->ddigest, pdu_cb->frags);
+ for (i = 0; i < ssi->nr_frags; i++)
+ pr_info("skb 0x%p, frag %d, off %u, sz %u.\n",
+ skb, i, ssi->frags[i].page_offset, ssi->frags[i].size);
+}
+
+static void cxgbit_lro_hskb_reset(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb = csk->lro_hskb;
+ struct skb_shared_info *ssi = skb_shinfo(skb);
+ u8 i;
+
+ memset(skb->data, 0, LRO_SKB_MIN_HEADROOM);
+ for (i = 0; i < ssi->nr_frags; i++)
+ put_page(skb_frag_page(&ssi->frags[i]));
+ ssi->nr_frags = 0;
+}
+
+static void
+cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx)
+{
+ struct sk_buff *hskb = csk->lro_hskb;
+ struct cxgbit_lro_pdu_cb *hpdu_cb = cxgbit_skb_lro_pdu_cb(hskb, 0);
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, pdu_idx);
+ struct skb_shared_info *hssi = skb_shinfo(hskb);
+ struct skb_shared_info *ssi = skb_shinfo(skb);
+ unsigned int len = 0;
+
+ if (pdu_cb->flags & PDUCBF_RX_HDR) {
+ hpdu_cb->flags = pdu_cb->flags;
+ hpdu_cb->seq = pdu_cb->seq;
+ hpdu_cb->hdr = pdu_cb->hdr;
+ hpdu_cb->hlen = pdu_cb->hlen;
+
+ memcpy(&hssi->frags[0], &ssi->frags[pdu_cb->hfrag_idx],
+ sizeof(skb_frag_t));
+
+ get_page(skb_frag_page(&hssi->frags[0]));
+ hssi->nr_frags = 1;
+ hpdu_cb->frags = 1;
+ hpdu_cb->hfrag_idx = 0;
+
+ len = hssi->frags[0].size;
+ hskb->len = len;
+ hskb->data_len = len;
+ hskb->truesize = len;
+ }
+
+ if (pdu_cb->flags & PDUCBF_RX_DATA) {
+ u8 hfrag_idx = 1, i;
+
+ hpdu_cb->flags |= pdu_cb->flags;
+
+ len = 0;
+ for (i = 0; i < pdu_cb->nr_dfrags; hfrag_idx++, i++) {
+ memcpy(&hssi->frags[hfrag_idx],
+ &ssi->frags[pdu_cb->dfrag_idx + i],
+ sizeof(skb_frag_t));
+
+ get_page(skb_frag_page(&hssi->frags[hfrag_idx]));
+
+ len += hssi->frags[hfrag_idx].size;
+
+ hssi->nr_frags++;
+ hpdu_cb->frags++;
+ }
+
+ hpdu_cb->dlen = pdu_cb->dlen;
+ hpdu_cb->doffset = hpdu_cb->hlen;
+ hpdu_cb->nr_dfrags = pdu_cb->nr_dfrags;
+ hpdu_cb->dfrag_idx = 1;
+ hskb->len += len;
+ hskb->data_len += len;
+ hskb->truesize += len;
+ }
+
+ if (pdu_cb->flags & PDUCBF_RX_STATUS) {
+ hpdu_cb->flags |= pdu_cb->flags;
+
+ if (hpdu_cb->flags & PDUCBF_RX_DATA)
+ hpdu_cb->flags &= ~PDUCBF_RX_DATA_DDPD;
+
+ hpdu_cb->ddigest = pdu_cb->ddigest;
+ hpdu_cb->pdulen = pdu_cb->pdulen;
+ }
+}
+
+static int cxgbit_process_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, 0);
+ u8 pdu_idx = 0, last_idx = 0;
+ int ret = 0;
+
+ if (!pdu_cb->complete) {
+ cxgbit_lro_skb_merge(csk, skb, 0);
+
+ if (pdu_cb->flags & PDUCBF_RX_STATUS) {
+ struct sk_buff *hskb = csk->lro_hskb;
+
+ ret = cxgbit_process_iscsi_pdu(csk, hskb, 0);
+
+ cxgbit_lro_hskb_reset(csk);
+
+ if (ret < 0)
+ goto out;
+ }
+
+ pdu_idx = 1;
+ }
+
+ if (lro_cb->pdu_idx)
+ last_idx = lro_cb->pdu_idx - 1;
+
+ for (; pdu_idx <= last_idx; pdu_idx++) {
+ ret = cxgbit_process_iscsi_pdu(csk, skb, pdu_idx);
+ if (ret < 0)
+ goto out;
+ }
+
+ if ((!lro_cb->complete) && lro_cb->pdu_idx)
+ cxgbit_lro_skb_merge(csk, skb, lro_cb->pdu_idx);
+
+out:
+ return ret;
+}
+
+static int cxgbit_rx_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+ struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, 0);
+ int ret = -1;
+
+ if ((pdu_cb->flags & PDUCBF_RX_HDR) &&
+ (pdu_cb->seq != csk->rcv_nxt)) {
+ pr_info("csk 0x%p, tid 0x%x, seq 0x%x != 0x%x.\n",
+ csk, csk->tid, pdu_cb->seq, csk->rcv_nxt);
+ cxgbit_lro_skb_dump(skb);
+ return ret;
+ }
+
+ csk->rcv_nxt += lro_cb->pdu_totallen;
+
+ ret = cxgbit_process_lro_skb(csk, skb);
+
+ csk->rx_credits += lro_cb->pdu_totallen;
+
+ if (csk->rx_credits >= (csk->rcv_win / 4))
+ cxgbit_rx_data_ack(csk);
+
+ return ret;
+}
+
+static int cxgbit_rx_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+ int ret = -1;
+
+ if (likely(cxgbit_skcb_flags(skb) & SKCBF_RX_LRO))
+ ret = cxgbit_rx_lro_skb(csk, skb);
+
+ __kfree_skb(skb);
+ return ret;
+}
+
+static bool cxgbit_rxq_len(struct cxgbit_sock *csk, struct sk_buff_head *rxq)
+{
+ spin_lock_bh(&csk->rxq.lock);
+ if (skb_queue_len(&csk->rxq)) {
+ skb_queue_splice_init(&csk->rxq, rxq);
+ spin_unlock_bh(&csk->rxq.lock);
+ return true;
+ }
+ spin_unlock_bh(&csk->rxq.lock);
+ return false;
+}
+
+static int cxgbit_wait_rxq(struct cxgbit_sock *csk)
+{
+ struct sk_buff *skb;
+ struct sk_buff_head rxq;
+
+ skb_queue_head_init(&rxq);
+
+ wait_event_interruptible(csk->waitq, cxgbit_rxq_len(csk, &rxq));
+
+ if (signal_pending(current))
+ goto out;
+
+ while ((skb = __skb_dequeue(&rxq))) {
+ if (cxgbit_rx_skb(csk, skb))
+ goto out;
+ }
+
+ return 0;
+out:
+ __skb_queue_purge(&rxq);
+ return -1;
+}
+
+int cxgbit_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login)
+{
+ struct cxgbit_sock *csk = conn->context;
+ int ret = -1;
+
+ while (!test_and_clear_bit(CSK_LOGIN_PDU_DONE, &csk->com.flags)) {
+ ret = cxgbit_wait_rxq(csk);
+ if (ret) {
+ clear_bit(CSK_LOGIN_PDU_DONE, &csk->com.flags);
+ break;
+ }
+ }
+
+ return ret;
+}
+
+void cxgbit_get_rx_pdu(struct iscsi_conn *conn)
+{
+ struct cxgbit_sock *csk = conn->context;
+
+ while (!kthread_should_stop()) {
+ iscsit_thread_check_cpumask(conn, current, 0);
+ if (cxgbit_wait_rxq(csk))
+ return;
+ }
+}
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 961202f4e9aa..50f3d3a0dd7b 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -478,16 +478,16 @@ int iscsit_del_np(struct iscsi_np *np)
return 0;
}
-static int iscsit_immediate_queue(struct iscsi_conn *, struct iscsi_cmd *, int);
-static int iscsit_response_queue(struct iscsi_conn *, struct iscsi_cmd *, int);
+static void iscsit_get_rx_pdu(struct iscsi_conn *);
-static int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
+int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
return 0;
}
+EXPORT_SYMBOL(iscsit_queue_rsp);
-static void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
+void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
bool scsi_cmd = (cmd->iscsi_opcode == ISCSI_OP_SCSI_CMD);
@@ -498,6 +498,169 @@ static void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
__iscsit_free_cmd(cmd, scsi_cmd, true);
}
+EXPORT_SYMBOL(iscsit_aborted_task);
+
+static void iscsit_do_crypto_hash_buf(struct ahash_request *, const void *,
+ u32, u32, u8 *, u8 *);
+static void iscsit_tx_thread_wait_for_tcp(struct iscsi_conn *);
+
+static int
+iscsit_xmit_nondatain_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ const void *data_buf, u32 data_buf_len)
+{
+ struct iscsi_hdr *hdr = (struct iscsi_hdr *)cmd->pdu;
+ struct kvec *iov;
+ u32 niov = 0, tx_size = ISCSI_HDR_LEN;
+ int ret;
+
+ iov = &cmd->iov_misc[0];
+ iov[niov].iov_base = cmd->pdu;
+ iov[niov++].iov_len = ISCSI_HDR_LEN;
+
+ if (conn->conn_ops->HeaderDigest) {
+ u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
+
+ iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
+ ISCSI_HDR_LEN, 0, NULL,
+ (u8 *)header_digest);
+
+ iov[0].iov_len += ISCSI_CRC_LEN;
+ tx_size += ISCSI_CRC_LEN;
+ pr_debug("Attaching CRC32C HeaderDigest"
+ " to opcode 0x%x 0x%08x\n",
+ hdr->opcode, *header_digest);
+ }
+
+ if (data_buf_len) {
+ u32 padding = ((-data_buf_len) & 3);
+
+ iov[niov].iov_base = (void *)data_buf;
+ iov[niov++].iov_len = data_buf_len;
+ tx_size += data_buf_len;
+
+ if (padding != 0) {
+ iov[niov].iov_base = &cmd->pad_bytes;
+ iov[niov++].iov_len = padding;
+ tx_size += padding;
+ pr_debug("Attaching %u additional"
+ " padding bytes.\n", padding);
+ }
+
+ if (conn->conn_ops->DataDigest) {
+ iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
+ data_buf, data_buf_len,
+ padding,
+ (u8 *)&cmd->pad_bytes,
+ (u8 *)&cmd->data_crc);
+
+ iov[niov].iov_base = &cmd->data_crc;
+ iov[niov++].iov_len = ISCSI_CRC_LEN;
+ tx_size += ISCSI_CRC_LEN;
+ pr_debug("Attached DataDigest for %u"
+ " bytes opcode 0x%x, CRC 0x%08x\n",
+ data_buf_len, hdr->opcode, cmd->data_crc);
+ }
+ }
+
+ cmd->iov_misc_count = niov;
+ cmd->tx_size = tx_size;
+
+ ret = iscsit_send_tx_data(cmd, conn, 1);
+ if (ret < 0) {
+ iscsit_tx_thread_wait_for_tcp(conn);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int iscsit_map_iovec(struct iscsi_cmd *, struct kvec *, u32, u32);
+static void iscsit_unmap_iovec(struct iscsi_cmd *);
+static u32 iscsit_do_crypto_hash_sg(struct ahash_request *, struct iscsi_cmd *,
+ u32, u32, u32, u8 *);
+static int
+iscsit_xmit_datain_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ const struct iscsi_datain *datain)
+{
+ struct kvec *iov;
+ u32 iov_count = 0, tx_size = 0;
+ int ret, iov_ret;
+
+ iov = &cmd->iov_data[0];
+ iov[iov_count].iov_base = cmd->pdu;
+ iov[iov_count++].iov_len = ISCSI_HDR_LEN;
+ tx_size += ISCSI_HDR_LEN;
+
+ if (conn->conn_ops->HeaderDigest) {
+ u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
+
+ iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->pdu,
+ ISCSI_HDR_LEN, 0, NULL,
+ (u8 *)header_digest);
+
+ iov[0].iov_len += ISCSI_CRC_LEN;
+ tx_size += ISCSI_CRC_LEN;
+
+ pr_debug("Attaching CRC32 HeaderDigest for DataIN PDU 0x%08x\n",
+ *header_digest);
+ }
+
+ iov_ret = iscsit_map_iovec(cmd, &cmd->iov_data[1],
+ datain->offset, datain->length);
+ if (iov_ret < 0)
+ return -1;
+
+ iov_count += iov_ret;
+ tx_size += datain->length;
+
+ cmd->padding = ((-datain->length) & 3);
+ if (cmd->padding) {
+ iov[iov_count].iov_base = cmd->pad_bytes;
+ iov[iov_count++].iov_len = cmd->padding;
+ tx_size += cmd->padding;
+
+ pr_debug("Attaching %u padding bytes\n", cmd->padding);
+ }
+
+ if (conn->conn_ops->DataDigest) {
+ cmd->data_crc = iscsit_do_crypto_hash_sg(conn->conn_tx_hash,
+ cmd, datain->offset,
+ datain->length,
+ cmd->padding,
+ cmd->pad_bytes);
+
+ iov[iov_count].iov_base = &cmd->data_crc;
+ iov[iov_count++].iov_len = ISCSI_CRC_LEN;
+ tx_size += ISCSI_CRC_LEN;
+
+ pr_debug("Attached CRC32C DataDigest %d bytes, crc 0x%08x\n",
+ datain->length + cmd->padding, cmd->data_crc);
+ }
+
+ cmd->iov_data_count = iov_count;
+ cmd->tx_size = tx_size;
+
+ ret = iscsit_fe_sendpage_sg(cmd, conn);
+
+ iscsit_unmap_iovec(cmd);
+
+ if (ret < 0) {
+ iscsit_tx_thread_wait_for_tcp(conn);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int iscsit_xmit_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct iscsi_datain_req *dr, const void *buf,
+ u32 buf_len)
+{
+ if (dr)
+ return iscsit_xmit_datain_pdu(conn, cmd, buf);
+ else
+ return iscsit_xmit_nondatain_pdu(conn, cmd, buf, buf_len);
+}
static enum target_prot_op iscsit_get_sup_prot_ops(struct iscsi_conn *conn)
{
@@ -507,6 +670,7 @@ static enum target_prot_op iscsit_get_sup_prot_ops(struct iscsi_conn *conn)
static struct iscsit_transport iscsi_target_transport = {
.name = "iSCSI/TCP",
.transport_type = ISCSI_TCP,
+ .rdma_shutdown = false,
.owner = NULL,
.iscsit_setup_np = iscsit_setup_np,
.iscsit_accept_np = iscsit_accept_np,
@@ -519,6 +683,8 @@ static struct iscsit_transport iscsi_target_transport = {
.iscsit_queue_data_in = iscsit_queue_rsp,
.iscsit_queue_status = iscsit_queue_rsp,
.iscsit_aborted_task = iscsit_aborted_task,
+ .iscsit_xmit_pdu = iscsit_xmit_pdu,
+ .iscsit_get_rx_pdu = iscsit_get_rx_pdu,
.iscsit_get_sup_prot_ops = iscsit_get_sup_prot_ops,
};
@@ -634,7 +800,7 @@ static void __exit iscsi_target_cleanup_module(void)
kfree(iscsit_global);
}
-static int iscsit_add_reject(
+int iscsit_add_reject(
struct iscsi_conn *conn,
u8 reason,
unsigned char *buf)
@@ -664,6 +830,7 @@ static int iscsit_add_reject(
return -1;
}
+EXPORT_SYMBOL(iscsit_add_reject);
static int iscsit_add_reject_from_cmd(
struct iscsi_cmd *cmd,
@@ -719,6 +886,7 @@ int iscsit_reject_cmd(struct iscsi_cmd *cmd, u8 reason, unsigned char *buf)
{
return iscsit_add_reject_from_cmd(cmd, reason, false, buf);
}
+EXPORT_SYMBOL(iscsit_reject_cmd);
/*
* Map some portion of the allocated scatterlist to an iovec, suitable for
@@ -737,7 +905,14 @@ static int iscsit_map_iovec(
/*
* We know each entry in t_data_sg contains a page.
*/
- sg = &cmd->se_cmd.t_data_sg[data_offset / PAGE_SIZE];
+ u32 ent = data_offset / PAGE_SIZE;
+
+ if (ent >= cmd->se_cmd.t_data_nents) {
+ pr_err("Initial page entry out-of-bounds\n");
+ return -1;
+ }
+
+ sg = &cmd->se_cmd.t_data_sg[ent];
page_off = (data_offset % PAGE_SIZE);
cmd->first_data_sg = sg;
@@ -2335,7 +2510,7 @@ iscsit_handle_logout_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
}
EXPORT_SYMBOL(iscsit_handle_logout_cmd);
-static int iscsit_handle_snack(
+int iscsit_handle_snack(
struct iscsi_conn *conn,
unsigned char *buf)
{
@@ -2388,6 +2563,7 @@ static int iscsit_handle_snack(
return 0;
}
+EXPORT_SYMBOL(iscsit_handle_snack);
static void iscsit_rx_thread_wait_for_tcp(struct iscsi_conn *conn)
{
@@ -2534,7 +2710,6 @@ static int iscsit_send_conn_drop_async_message(
{
struct iscsi_async *hdr;
- cmd->tx_size = ISCSI_HDR_LEN;
cmd->iscsi_opcode = ISCSI_OP_ASYNC_EVENT;
hdr = (struct iscsi_async *) cmd->pdu;
@@ -2552,25 +2727,11 @@ static int iscsit_send_conn_drop_async_message(
hdr->param2 = cpu_to_be16(conn->sess->sess_ops->DefaultTime2Wait);
hdr->param3 = cpu_to_be16(conn->sess->sess_ops->DefaultTime2Retain);
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- cmd->tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32C HeaderDigest to"
- " Async Message 0x%08x\n", *header_digest);
- }
-
- cmd->iov_misc[0].iov_base = cmd->pdu;
- cmd->iov_misc[0].iov_len = cmd->tx_size;
- cmd->iov_misc_count = 1;
-
pr_debug("Sending Connection Dropped Async Message StatSN:"
" 0x%08x, for CID: %hu on CID: %hu\n", cmd->stat_sn,
cmd->logout_cid, conn->cid);
- return 0;
+
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL, NULL, 0);
}
static void iscsit_tx_thread_wait_for_tcp(struct iscsi_conn *conn)
@@ -2583,7 +2744,7 @@ static void iscsit_tx_thread_wait_for_tcp(struct iscsi_conn *conn)
}
}
-static void
+void
iscsit_build_datain_pdu(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
struct iscsi_datain *datain, struct iscsi_data_rsp *hdr,
bool set_statsn)
@@ -2627,15 +2788,14 @@ iscsit_build_datain_pdu(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
cmd->init_task_tag, ntohl(hdr->statsn), ntohl(hdr->datasn),
ntohl(hdr->offset), datain->length, conn->cid);
}
+EXPORT_SYMBOL(iscsit_build_datain_pdu);
static int iscsit_send_datain(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
struct iscsi_data_rsp *hdr = (struct iscsi_data_rsp *)&cmd->pdu[0];
struct iscsi_datain datain;
struct iscsi_datain_req *dr;
- struct kvec *iov;
- u32 iov_count = 0, tx_size = 0;
- int eodr = 0, ret, iov_ret;
+ int eodr = 0, ret;
bool set_statsn = false;
memset(&datain, 0, sizeof(struct iscsi_datain));
@@ -2677,64 +2837,9 @@ static int iscsit_send_datain(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
iscsit_build_datain_pdu(cmd, conn, &datain, hdr, set_statsn);
- iov = &cmd->iov_data[0];
- iov[iov_count].iov_base = cmd->pdu;
- iov[iov_count++].iov_len = ISCSI_HDR_LEN;
- tx_size += ISCSI_HDR_LEN;
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->pdu,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- iov[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
-
- pr_debug("Attaching CRC32 HeaderDigest"
- " for DataIN PDU 0x%08x\n", *header_digest);
- }
-
- iov_ret = iscsit_map_iovec(cmd, &cmd->iov_data[1],
- datain.offset, datain.length);
- if (iov_ret < 0)
- return -1;
-
- iov_count += iov_ret;
- tx_size += datain.length;
-
- cmd->padding = ((-datain.length) & 3);
- if (cmd->padding) {
- iov[iov_count].iov_base = cmd->pad_bytes;
- iov[iov_count++].iov_len = cmd->padding;
- tx_size += cmd->padding;
-
- pr_debug("Attaching %u padding bytes\n",
- cmd->padding);
- }
- if (conn->conn_ops->DataDigest) {
- cmd->data_crc = iscsit_do_crypto_hash_sg(conn->conn_tx_hash, cmd,
- datain.offset, datain.length, cmd->padding, cmd->pad_bytes);
-
- iov[iov_count].iov_base = &cmd->data_crc;
- iov[iov_count++].iov_len = ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
-
- pr_debug("Attached CRC32C DataDigest %d bytes, crc"
- " 0x%08x\n", datain.length+cmd->padding, cmd->data_crc);
- }
-
- cmd->iov_data_count = iov_count;
- cmd->tx_size = tx_size;
-
- ret = iscsit_fe_sendpage_sg(cmd, conn);
-
- iscsit_unmap_iovec(cmd);
-
- if (ret < 0) {
- iscsit_tx_thread_wait_for_tcp(conn);
+ ret = conn->conn_transport->iscsit_xmit_pdu(conn, cmd, dr, &datain, 0);
+ if (ret < 0)
return ret;
- }
if (dr->dr_complete) {
eodr = (cmd->se_cmd.se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) ?
@@ -2843,34 +2948,14 @@ EXPORT_SYMBOL(iscsit_build_logout_rsp);
static int
iscsit_send_logout(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
- struct kvec *iov;
- int niov = 0, tx_size, rc;
+ int rc;
rc = iscsit_build_logout_rsp(cmd, conn,
(struct iscsi_logout_rsp *)&cmd->pdu[0]);
if (rc < 0)
return rc;
- tx_size = ISCSI_HDR_LEN;
- iov = &cmd->iov_misc[0];
- iov[niov].iov_base = cmd->pdu;
- iov[niov++].iov_len = ISCSI_HDR_LEN;
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, &cmd->pdu[0],
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- iov[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32C HeaderDigest to"
- " Logout Response 0x%08x\n", *header_digest);
- }
- cmd->iov_misc_count = niov;
- cmd->tx_size = tx_size;
-
- return 0;
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL, NULL, 0);
}
void
@@ -2910,34 +2995,16 @@ static int iscsit_send_unsolicited_nopin(
int want_response)
{
struct iscsi_nopin *hdr = (struct iscsi_nopin *)&cmd->pdu[0];
- int tx_size = ISCSI_HDR_LEN, ret;
+ int ret;
iscsit_build_nopin_rsp(cmd, conn, hdr, false);
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32C HeaderDigest to"
- " NopIN 0x%08x\n", *header_digest);
- }
-
- cmd->iov_misc[0].iov_base = cmd->pdu;
- cmd->iov_misc[0].iov_len = tx_size;
- cmd->iov_misc_count = 1;
- cmd->tx_size = tx_size;
-
pr_debug("Sending Unsolicited NOPIN TTT: 0x%08x StatSN:"
" 0x%08x CID: %hu\n", hdr->ttt, cmd->stat_sn, conn->cid);
- ret = iscsit_send_tx_data(cmd, conn, 1);
- if (ret < 0) {
- iscsit_tx_thread_wait_for_tcp(conn);
+ ret = conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL, NULL, 0);
+ if (ret < 0)
return ret;
- }
spin_lock_bh(&cmd->istate_lock);
cmd->i_state = want_response ?
@@ -2951,75 +3018,24 @@ static int
iscsit_send_nopin(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
struct iscsi_nopin *hdr = (struct iscsi_nopin *)&cmd->pdu[0];
- struct kvec *iov;
- u32 padding = 0;
- int niov = 0, tx_size;
iscsit_build_nopin_rsp(cmd, conn, hdr, true);
- tx_size = ISCSI_HDR_LEN;
- iov = &cmd->iov_misc[0];
- iov[niov].iov_base = cmd->pdu;
- iov[niov++].iov_len = ISCSI_HDR_LEN;
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- iov[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32C HeaderDigest"
- " to NopIn 0x%08x\n", *header_digest);
- }
-
/*
* NOPOUT Ping Data is attached to struct iscsi_cmd->buf_ptr.
* NOPOUT DataSegmentLength is at struct iscsi_cmd->buf_ptr_size.
*/
- if (cmd->buf_ptr_size) {
- iov[niov].iov_base = cmd->buf_ptr;
- iov[niov++].iov_len = cmd->buf_ptr_size;
- tx_size += cmd->buf_ptr_size;
-
- pr_debug("Echoing back %u bytes of ping"
- " data.\n", cmd->buf_ptr_size);
-
- padding = ((-cmd->buf_ptr_size) & 3);
- if (padding != 0) {
- iov[niov].iov_base = &cmd->pad_bytes;
- iov[niov++].iov_len = padding;
- tx_size += padding;
- pr_debug("Attaching %u additional"
- " padding bytes.\n", padding);
- }
- if (conn->conn_ops->DataDigest) {
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
- cmd->buf_ptr, cmd->buf_ptr_size,
- padding, (u8 *)&cmd->pad_bytes,
- (u8 *)&cmd->data_crc);
-
- iov[niov].iov_base = &cmd->data_crc;
- iov[niov++].iov_len = ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attached DataDigest for %u"
- " bytes of ping data, CRC 0x%08x\n",
- cmd->buf_ptr_size, cmd->data_crc);
- }
- }
+ pr_debug("Echoing back %u bytes of ping data.\n", cmd->buf_ptr_size);
- cmd->iov_misc_count = niov;
- cmd->tx_size = tx_size;
-
- return 0;
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL,
+ cmd->buf_ptr,
+ cmd->buf_ptr_size);
}
static int iscsit_send_r2t(
struct iscsi_cmd *cmd,
struct iscsi_conn *conn)
{
- int tx_size = 0;
struct iscsi_r2t *r2t;
struct iscsi_r2t_rsp *hdr;
int ret;
@@ -3035,7 +3051,10 @@ static int iscsit_send_r2t(
int_to_scsilun(cmd->se_cmd.orig_fe_lun,
(struct scsi_lun *)&hdr->lun);
hdr->itt = cmd->init_task_tag;
- r2t->targ_xfer_tag = session_get_next_ttt(conn->sess);
+ if (conn->conn_transport->iscsit_get_r2t_ttt)
+ conn->conn_transport->iscsit_get_r2t_ttt(conn, cmd, r2t);
+ else
+ r2t->targ_xfer_tag = session_get_next_ttt(conn->sess);
hdr->ttt = cpu_to_be32(r2t->targ_xfer_tag);
hdr->statsn = cpu_to_be32(conn->stat_sn);
hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn);
@@ -3044,38 +3063,18 @@ static int iscsit_send_r2t(
hdr->data_offset = cpu_to_be32(r2t->offset);
hdr->data_length = cpu_to_be32(r2t->xfer_len);
- cmd->iov_misc[0].iov_base = cmd->pdu;
- cmd->iov_misc[0].iov_len = ISCSI_HDR_LEN;
- tx_size += ISCSI_HDR_LEN;
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- cmd->iov_misc[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32 HeaderDigest for R2T"
- " PDU 0x%08x\n", *header_digest);
- }
-
pr_debug("Built %sR2T, ITT: 0x%08x, TTT: 0x%08x, StatSN:"
" 0x%08x, R2TSN: 0x%08x, Offset: %u, DDTL: %u, CID: %hu\n",
(!r2t->recovery_r2t) ? "" : "Recovery ", cmd->init_task_tag,
r2t->targ_xfer_tag, ntohl(hdr->statsn), r2t->r2t_sn,
r2t->offset, r2t->xfer_len, conn->cid);
- cmd->iov_misc_count = 1;
- cmd->tx_size = tx_size;
-
spin_lock_bh(&cmd->r2t_lock);
r2t->sent_r2t = 1;
spin_unlock_bh(&cmd->r2t_lock);
- ret = iscsit_send_tx_data(cmd, conn, 1);
+ ret = conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL, NULL, 0);
if (ret < 0) {
- iscsit_tx_thread_wait_for_tcp(conn);
return ret;
}
@@ -3166,6 +3165,7 @@ int iscsit_build_r2ts_for_cmd(
return 0;
}
+EXPORT_SYMBOL(iscsit_build_r2ts_for_cmd);
void iscsit_build_rsp_pdu(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
bool inc_stat_sn, struct iscsi_scsi_rsp *hdr)
@@ -3204,18 +3204,12 @@ EXPORT_SYMBOL(iscsit_build_rsp_pdu);
static int iscsit_send_response(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
struct iscsi_scsi_rsp *hdr = (struct iscsi_scsi_rsp *)&cmd->pdu[0];
- struct kvec *iov;
- u32 padding = 0, tx_size = 0;
- int iov_count = 0;
bool inc_stat_sn = (cmd->i_state == ISTATE_SEND_STATUS);
+ void *data_buf = NULL;
+ u32 padding = 0, data_buf_len = 0;
iscsit_build_rsp_pdu(cmd, conn, inc_stat_sn, hdr);
- iov = &cmd->iov_misc[0];
- iov[iov_count].iov_base = cmd->pdu;
- iov[iov_count++].iov_len = ISCSI_HDR_LEN;
- tx_size += ISCSI_HDR_LEN;
-
/*
* Attach SENSE DATA payload to iSCSI Response PDU
*/
@@ -3227,56 +3221,23 @@ static int iscsit_send_response(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
padding = -(cmd->se_cmd.scsi_sense_length) & 3;
hton24(hdr->dlength, (u32)cmd->se_cmd.scsi_sense_length);
- iov[iov_count].iov_base = cmd->sense_buffer;
- iov[iov_count++].iov_len =
- (cmd->se_cmd.scsi_sense_length + padding);
- tx_size += cmd->se_cmd.scsi_sense_length;
+ data_buf = cmd->sense_buffer;
+ data_buf_len = cmd->se_cmd.scsi_sense_length + padding;
if (padding) {
memset(cmd->sense_buffer +
cmd->se_cmd.scsi_sense_length, 0, padding);
- tx_size += padding;
pr_debug("Adding %u bytes of padding to"
" SENSE.\n", padding);
}
- if (conn->conn_ops->DataDigest) {
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
- cmd->sense_buffer,
- (cmd->se_cmd.scsi_sense_length + padding),
- 0, NULL, (u8 *)&cmd->data_crc);
-
- iov[iov_count].iov_base = &cmd->data_crc;
- iov[iov_count++].iov_len = ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
-
- pr_debug("Attaching CRC32 DataDigest for"
- " SENSE, %u bytes CRC 0x%08x\n",
- (cmd->se_cmd.scsi_sense_length + padding),
- cmd->data_crc);
- }
-
pr_debug("Attaching SENSE DATA: %u bytes to iSCSI"
" Response PDU\n",
cmd->se_cmd.scsi_sense_length);
}
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->pdu,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- iov[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32 HeaderDigest for Response"
- " PDU 0x%08x\n", *header_digest);
- }
-
- cmd->iov_misc_count = iov_count;
- cmd->tx_size = tx_size;
-
- return 0;
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL, data_buf,
+ data_buf_len);
}
static u8 iscsit_convert_tcm_tmr_rsp(struct se_tmr_req *se_tmr)
@@ -3323,30 +3284,10 @@ static int
iscsit_send_task_mgt_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
struct iscsi_tm_rsp *hdr = (struct iscsi_tm_rsp *)&cmd->pdu[0];
- u32 tx_size = 0;
iscsit_build_task_mgt_rsp(cmd, conn, hdr);
- cmd->iov_misc[0].iov_base = cmd->pdu;
- cmd->iov_misc[0].iov_len = ISCSI_HDR_LEN;
- tx_size += ISCSI_HDR_LEN;
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- cmd->iov_misc[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32 HeaderDigest for Task"
- " Mgmt Response PDU 0x%08x\n", *header_digest);
- }
-
- cmd->iov_misc_count = 1;
- cmd->tx_size = tx_size;
-
- return 0;
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL, NULL, 0);
}
static bool iscsit_check_inaddr_any(struct iscsi_np *np)
@@ -3583,53 +3524,16 @@ static int iscsit_send_text_rsp(
struct iscsi_conn *conn)
{
struct iscsi_text_rsp *hdr = (struct iscsi_text_rsp *)cmd->pdu;
- struct kvec *iov;
- u32 tx_size = 0;
- int text_length, iov_count = 0, rc;
-
- rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_TCP);
- if (rc < 0)
- return rc;
-
- text_length = rc;
- iov = &cmd->iov_misc[0];
- iov[iov_count].iov_base = cmd->pdu;
- iov[iov_count++].iov_len = ISCSI_HDR_LEN;
- iov[iov_count].iov_base = cmd->buf_ptr;
- iov[iov_count++].iov_len = text_length;
-
- tx_size += (ISCSI_HDR_LEN + text_length);
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- iov[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32 HeaderDigest for"
- " Text Response PDU 0x%08x\n", *header_digest);
- }
-
- if (conn->conn_ops->DataDigest) {
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
- cmd->buf_ptr, text_length,
- 0, NULL, (u8 *)&cmd->data_crc);
-
- iov[iov_count].iov_base = &cmd->data_crc;
- iov[iov_count++].iov_len = ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
-
- pr_debug("Attaching DataDigest for %u bytes of text"
- " data, CRC 0x%08x\n", text_length,
- cmd->data_crc);
- }
+ int text_length;
- cmd->iov_misc_count = iov_count;
- cmd->tx_size = tx_size;
+ text_length = iscsit_build_text_rsp(cmd, conn, hdr,
+ conn->conn_transport->transport_type);
+ if (text_length < 0)
+ return text_length;
- return 0;
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL,
+ cmd->buf_ptr,
+ text_length);
}
void
@@ -3654,49 +3558,15 @@ static int iscsit_send_reject(
struct iscsi_conn *conn)
{
struct iscsi_reject *hdr = (struct iscsi_reject *)&cmd->pdu[0];
- struct kvec *iov;
- u32 iov_count = 0, tx_size;
iscsit_build_reject(cmd, conn, hdr);
- iov = &cmd->iov_misc[0];
- iov[iov_count].iov_base = cmd->pdu;
- iov[iov_count++].iov_len = ISCSI_HDR_LEN;
- iov[iov_count].iov_base = cmd->buf_ptr;
- iov[iov_count++].iov_len = ISCSI_HDR_LEN;
-
- tx_size = (ISCSI_HDR_LEN + ISCSI_HDR_LEN);
-
- if (conn->conn_ops->HeaderDigest) {
- u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
-
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
-
- iov[0].iov_len += ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32 HeaderDigest for"
- " REJECT PDU 0x%08x\n", *header_digest);
- }
-
- if (conn->conn_ops->DataDigest) {
- iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->buf_ptr,
- ISCSI_HDR_LEN, 0, NULL, (u8 *)&cmd->data_crc);
-
- iov[iov_count].iov_base = &cmd->data_crc;
- iov[iov_count++].iov_len = ISCSI_CRC_LEN;
- tx_size += ISCSI_CRC_LEN;
- pr_debug("Attaching CRC32 DataDigest for REJECT"
- " PDU 0x%08x\n", cmd->data_crc);
- }
-
- cmd->iov_misc_count = iov_count;
- cmd->tx_size = tx_size;
-
pr_debug("Built Reject PDU StatSN: 0x%08x, Reason: 0x%02x,"
" CID: %hu\n", ntohl(hdr->statsn), hdr->reason, conn->cid);
- return 0;
+ return conn->conn_transport->iscsit_xmit_pdu(conn, cmd, NULL,
+ cmd->buf_ptr,
+ ISCSI_HDR_LEN);
}
void iscsit_thread_get_cpumask(struct iscsi_conn *conn)
@@ -3724,33 +3594,7 @@ void iscsit_thread_get_cpumask(struct iscsi_conn *conn)
cpumask_setall(conn->conn_cpumask);
}
-static inline void iscsit_thread_check_cpumask(
- struct iscsi_conn *conn,
- struct task_struct *p,
- int mode)
-{
- /*
- * mode == 1 signals iscsi_target_tx_thread() usage.
- * mode == 0 signals iscsi_target_rx_thread() usage.
- */
- if (mode == 1) {
- if (!conn->conn_tx_reset_cpumask)
- return;
- conn->conn_tx_reset_cpumask = 0;
- } else {
- if (!conn->conn_rx_reset_cpumask)
- return;
- conn->conn_rx_reset_cpumask = 0;
- }
- /*
- * Update the CPU mask for this single kthread so that
- * both TX and RX kthreads are scheduled to run on the
- * same CPU.
- */
- set_cpus_allowed_ptr(p, conn->conn_cpumask);
-}
-
-static int
+int
iscsit_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
{
int ret;
@@ -3792,6 +3636,7 @@ iscsit_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state
err:
return -1;
}
+EXPORT_SYMBOL(iscsit_immediate_queue);
static int
iscsit_handle_immediate_queue(struct iscsi_conn *conn)
@@ -3816,7 +3661,7 @@ iscsit_handle_immediate_queue(struct iscsi_conn *conn)
return 0;
}
-static int
+int
iscsit_response_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
{
int ret;
@@ -3889,13 +3734,6 @@ check_rsp_state:
if (ret < 0)
goto err;
- if (iscsit_send_tx_data(cmd, conn, 1) < 0) {
- iscsit_tx_thread_wait_for_tcp(conn);
- iscsit_unmap_iovec(cmd);
- goto err;
- }
- iscsit_unmap_iovec(cmd);
-
switch (state) {
case ISTATE_SEND_LOGOUTRSP:
if (!iscsit_logout_post_handler(cmd, conn))
@@ -3928,6 +3766,7 @@ check_rsp_state:
err:
return -1;
}
+EXPORT_SYMBOL(iscsit_response_queue);
static int iscsit_handle_response_queue(struct iscsi_conn *conn)
{
@@ -4087,36 +3926,12 @@ static bool iscsi_target_check_conn_state(struct iscsi_conn *conn)
return ret;
}
-int iscsi_target_rx_thread(void *arg)
+static void iscsit_get_rx_pdu(struct iscsi_conn *conn)
{
- int ret, rc;
+ int ret;
u8 buffer[ISCSI_HDR_LEN], opcode;
u32 checksum = 0, digest = 0;
- struct iscsi_conn *conn = arg;
struct kvec iov;
- /*
- * Allow ourselves to be interrupted by SIGINT so that a
- * connection recovery / failure event can be triggered externally.
- */
- allow_signal(SIGINT);
- /*
- * Wait for iscsi_post_login_handler() to complete before allowing
- * incoming iscsi/tcp socket I/O, and/or failing the connection.
- */
- rc = wait_for_completion_interruptible(&conn->rx_login_comp);
- if (rc < 0 || iscsi_target_check_conn_state(conn))
- return 0;
-
- if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
- struct completion comp;
-
- init_completion(&comp);
- rc = wait_for_completion_interruptible(&comp);
- if (rc < 0)
- goto transport_err;
-
- goto transport_err;
- }
while (!kthread_should_stop()) {
/*
@@ -4134,7 +3949,7 @@ int iscsi_target_rx_thread(void *arg)
ret = rx_data(conn, &iov, 1, ISCSI_HDR_LEN);
if (ret != ISCSI_HDR_LEN) {
iscsit_rx_thread_wait_for_tcp(conn);
- goto transport_err;
+ return;
}
if (conn->conn_ops->HeaderDigest) {
@@ -4144,7 +3959,7 @@ int iscsi_target_rx_thread(void *arg)
ret = rx_data(conn, &iov, 1, ISCSI_CRC_LEN);
if (ret != ISCSI_CRC_LEN) {
iscsit_rx_thread_wait_for_tcp(conn);
- goto transport_err;
+ return;
}
iscsit_do_crypto_hash_buf(conn->conn_rx_hash,
@@ -4168,7 +3983,7 @@ int iscsi_target_rx_thread(void *arg)
}
if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT)
- goto transport_err;
+ return;
opcode = buffer[0] & ISCSI_OPCODE_MASK;
@@ -4179,15 +3994,38 @@ int iscsi_target_rx_thread(void *arg)
" while in Discovery Session, rejecting.\n", opcode);
iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
buffer);
- goto transport_err;
+ return;
}
ret = iscsi_target_rx_opcode(conn, buffer);
if (ret < 0)
- goto transport_err;
+ return;
}
+}
+
+int iscsi_target_rx_thread(void *arg)
+{
+ int rc;
+ struct iscsi_conn *conn = arg;
+
+ /*
+ * Allow ourselves to be interrupted by SIGINT so that a
+ * connection recovery / failure event can be triggered externally.
+ */
+ allow_signal(SIGINT);
+ /*
+ * Wait for iscsi_post_login_handler() to complete before allowing
+ * incoming iscsi/tcp socket I/O, and/or failing the connection.
+ */
+ rc = wait_for_completion_interruptible(&conn->rx_login_comp);
+ if (rc < 0 || iscsi_target_check_conn_state(conn))
+ return 0;
+
+ if (!conn->conn_transport->iscsit_get_rx_pdu)
+ return 0;
+
+ conn->conn_transport->iscsit_get_rx_pdu(conn);
-transport_err:
if (!signal_pending(current))
atomic_set(&conn->transport_failed, 1);
iscsit_take_action_for_connection_exit(conn);
@@ -4240,16 +4078,17 @@ int iscsit_close_connection(
pr_debug("Closing iSCSI connection CID %hu on SID:"
" %u\n", conn->cid, sess->sid);
/*
- * Always up conn_logout_comp for the traditional TCP case just in case
- * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout
- * response never got sent because the connection failed.
+ * Always up conn_logout_comp for the traditional TCP and HW_OFFLOAD
+ * case just in case the RX Thread in iscsi_target_rx_opcode() is
+ * sleeping and the logout response never got sent because the
+ * connection failed.
*
* However for iser-target, isert_wait4logout() is using conn_logout_comp
* to signal logout response TX interrupt completion. Go ahead and skip
* this for iser since isert_rx_opcode() does not wait on logout failure,
* and to avoid iscsi_conn pointer dereference in iser-target code.
*/
- if (conn->conn_transport->transport_type == ISCSI_TCP)
+ if (!conn->conn_transport->rdma_shutdown)
complete(&conn->conn_logout_comp);
if (!strcmp(current->comm, ISCSI_RX_THREAD_NAME)) {
@@ -4438,7 +4277,7 @@ int iscsit_close_connection(
if (!atomic_read(&sess->session_reinstatement) &&
atomic_read(&sess->session_fall_back_to_erl0)) {
spin_unlock_bh(&sess->conn_lock);
- target_put_session(sess->se_sess);
+ iscsit_close_session(sess);
return 0;
} else if (atomic_read(&sess->session_logout)) {
@@ -4467,6 +4306,10 @@ int iscsit_close_connection(
}
}
+/*
+ * If the iSCSI Session for the iSCSI Initiator Node exists,
+ * forcefully shutdown the iSCSI NEXUS.
+ */
int iscsit_close_session(struct iscsi_session *sess)
{
struct iscsi_portal_group *tpg = sess->tpg;
@@ -4556,7 +4399,7 @@ static void iscsit_logout_post_handler_closesession(
* always sleep waiting for RX/TX thread shutdown to complete
* within iscsit_close_connection().
*/
- if (conn->conn_transport->transport_type == ISCSI_TCP)
+ if (!conn->conn_transport->rdma_shutdown)
sleep = cmpxchg(&conn->tx_thread_active, true, false);
atomic_set(&conn->conn_logout_remove, 0);
@@ -4565,7 +4408,7 @@ static void iscsit_logout_post_handler_closesession(
iscsit_dec_conn_usage_count(conn);
iscsit_stop_session(sess, sleep, sleep);
iscsit_dec_session_usage_count(sess);
- target_put_session(sess->se_sess);
+ iscsit_close_session(sess);
}
static void iscsit_logout_post_handler_samecid(
@@ -4573,7 +4416,7 @@ static void iscsit_logout_post_handler_samecid(
{
int sleep = 1;
- if (conn->conn_transport->transport_type == ISCSI_TCP)
+ if (!conn->conn_transport->rdma_shutdown)
sleep = cmpxchg(&conn->tx_thread_active, true, false);
atomic_set(&conn->conn_logout_remove, 0);
@@ -4736,7 +4579,7 @@ int iscsit_free_session(struct iscsi_session *sess)
} else
spin_unlock_bh(&sess->conn_lock);
- target_put_session(sess->se_sess);
+ iscsit_close_session(sess);
return 0;
}
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 97e5b69e0668..923c032f0b95 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -43,14 +43,15 @@ static inline struct iscsi_tpg_np *to_iscsi_tpg_np(struct config_item *item)
return container_of(to_tpg_np(item), struct iscsi_tpg_np, se_tpg_np);
}
-static ssize_t lio_target_np_sctp_show(struct config_item *item, char *page)
+static ssize_t lio_target_np_driver_show(struct config_item *item, char *page,
+ enum iscsit_transport_type type)
{
struct iscsi_tpg_np *tpg_np = to_iscsi_tpg_np(item);
- struct iscsi_tpg_np *tpg_np_sctp;
+ struct iscsi_tpg_np *tpg_np_new;
ssize_t rb;
- tpg_np_sctp = iscsit_tpg_locate_child_np(tpg_np, ISCSI_SCTP_TCP);
- if (tpg_np_sctp)
+ tpg_np_new = iscsit_tpg_locate_child_np(tpg_np, type);
+ if (tpg_np_new)
rb = sprintf(page, "1\n");
else
rb = sprintf(page, "0\n");
@@ -58,19 +59,20 @@ static ssize_t lio_target_np_sctp_show(struct config_item *item, char *page)
return rb;
}
-static ssize_t lio_target_np_sctp_store(struct config_item *item,
- const char *page, size_t count)
+static ssize_t lio_target_np_driver_store(struct config_item *item,
+ const char *page, size_t count, enum iscsit_transport_type type,
+ const char *mod_name)
{
struct iscsi_tpg_np *tpg_np = to_iscsi_tpg_np(item);
struct iscsi_np *np;
struct iscsi_portal_group *tpg;
- struct iscsi_tpg_np *tpg_np_sctp = NULL;
+ struct iscsi_tpg_np *tpg_np_new = NULL;
u32 op;
- int ret;
+ int rc;
- ret = kstrtou32(page, 0, &op);
- if (ret)
- return ret;
+ rc = kstrtou32(page, 0, &op);
+ if (rc)
+ return rc;
if ((op != 1) && (op != 0)) {
pr_err("Illegal value for tpg_enable: %u\n", op);
return -EINVAL;
@@ -87,107 +89,64 @@ static ssize_t lio_target_np_sctp_store(struct config_item *item,
return -EINVAL;
if (op) {
- /*
- * Use existing np->np_sockaddr for SCTP network portal reference
- */
- tpg_np_sctp = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr,
- tpg_np, ISCSI_SCTP_TCP);
- if (!tpg_np_sctp || IS_ERR(tpg_np_sctp))
- goto out;
- } else {
- tpg_np_sctp = iscsit_tpg_locate_child_np(tpg_np, ISCSI_SCTP_TCP);
- if (!tpg_np_sctp)
- goto out;
+ if (strlen(mod_name)) {
+ rc = request_module(mod_name);
+ if (rc != 0) {
+ pr_warn("Unable to request_module for %s\n",
+ mod_name);
+ rc = 0;
+ }
+ }
- ret = iscsit_tpg_del_network_portal(tpg, tpg_np_sctp);
- if (ret < 0)
+ tpg_np_new = iscsit_tpg_add_network_portal(tpg,
+ &np->np_sockaddr, tpg_np, type);
+ if (IS_ERR(tpg_np_new))
goto out;
+ } else {
+ tpg_np_new = iscsit_tpg_locate_child_np(tpg_np, type);
+ if (tpg_np_new) {
+ rc = iscsit_tpg_del_network_portal(tpg, tpg_np_new);
+ if (rc < 0)
+ goto out;
+ }
}
iscsit_put_tpg(tpg);
return count;
out:
iscsit_put_tpg(tpg);
- return -EINVAL;
+ return rc;
}
static ssize_t lio_target_np_iser_show(struct config_item *item, char *page)
{
- struct iscsi_tpg_np *tpg_np = to_iscsi_tpg_np(item);
- struct iscsi_tpg_np *tpg_np_iser;
- ssize_t rb;
-
- tpg_np_iser = iscsit_tpg_locate_child_np(tpg_np, ISCSI_INFINIBAND);
- if (tpg_np_iser)
- rb = sprintf(page, "1\n");
- else
- rb = sprintf(page, "0\n");
-
- return rb;
+ return lio_target_np_driver_show(item, page, ISCSI_INFINIBAND);
}
static ssize_t lio_target_np_iser_store(struct config_item *item,
- const char *page, size_t count)
+ const char *page, size_t count)
{
- struct iscsi_tpg_np *tpg_np = to_iscsi_tpg_np(item);
- struct iscsi_np *np;
- struct iscsi_portal_group *tpg;
- struct iscsi_tpg_np *tpg_np_iser = NULL;
- char *endptr;
- u32 op;
- int rc = 0;
-
- op = simple_strtoul(page, &endptr, 0);
- if ((op != 1) && (op != 0)) {
- pr_err("Illegal value for tpg_enable: %u\n", op);
- return -EINVAL;
- }
- np = tpg_np->tpg_np;
- if (!np) {
- pr_err("Unable to locate struct iscsi_np from"
- " struct iscsi_tpg_np\n");
- return -EINVAL;
- }
-
- tpg = tpg_np->tpg;
- if (iscsit_get_tpg(tpg) < 0)
- return -EINVAL;
-
- if (op) {
- rc = request_module("ib_isert");
- if (rc != 0) {
- pr_warn("Unable to request_module for ib_isert\n");
- rc = 0;
- }
-
- tpg_np_iser = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr,
- tpg_np, ISCSI_INFINIBAND);
- if (IS_ERR(tpg_np_iser)) {
- rc = PTR_ERR(tpg_np_iser);
- goto out;
- }
- } else {
- tpg_np_iser = iscsit_tpg_locate_child_np(tpg_np, ISCSI_INFINIBAND);
- if (tpg_np_iser) {
- rc = iscsit_tpg_del_network_portal(tpg, tpg_np_iser);
- if (rc < 0)
- goto out;
- }
- }
+ return lio_target_np_driver_store(item, page, count,
+ ISCSI_INFINIBAND, "ib_isert");
+}
+CONFIGFS_ATTR(lio_target_np_, iser);
- iscsit_put_tpg(tpg);
- return count;
-out:
- iscsit_put_tpg(tpg);
- return rc;
+static ssize_t lio_target_np_cxgbit_show(struct config_item *item, char *page)
+{
+ return lio_target_np_driver_show(item, page, ISCSI_CXGBIT);
}
-CONFIGFS_ATTR(lio_target_np_, sctp);
-CONFIGFS_ATTR(lio_target_np_, iser);
+static ssize_t lio_target_np_cxgbit_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ return lio_target_np_driver_store(item, page, count,
+ ISCSI_CXGBIT, "cxgbit");
+}
+CONFIGFS_ATTR(lio_target_np_, cxgbit);
static struct configfs_attribute *lio_target_portal_attrs[] = {
- &lio_target_np_attr_sctp,
&lio_target_np_attr_iser,
+ &lio_target_np_attr_cxgbit,
NULL,
};
@@ -1554,7 +1513,7 @@ static int lio_tpg_check_prot_fabric_only(
* This function calls iscsit_inc_session_usage_count() on the
* struct iscsi_session in question.
*/
-static int lio_tpg_shutdown_session(struct se_session *se_sess)
+static void lio_tpg_close_session(struct se_session *se_sess)
{
struct iscsi_session *sess = se_sess->fabric_sess_ptr;
struct se_portal_group *se_tpg = &sess->tpg->tpg_se_tpg;
@@ -1566,7 +1525,7 @@ static int lio_tpg_shutdown_session(struct se_session *se_sess)
(sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) {
spin_unlock(&sess->conn_lock);
spin_unlock_bh(&se_tpg->session_lock);
- return 0;
+ return;
}
atomic_set(&sess->session_reinstatement, 1);
spin_unlock(&sess->conn_lock);
@@ -1575,20 +1534,6 @@ static int lio_tpg_shutdown_session(struct se_session *se_sess)
spin_unlock_bh(&se_tpg->session_lock);
iscsit_stop_session(sess, 1, 1);
- return 1;
-}
-
-/*
- * Calls iscsit_dec_session_usage_count() as inverse of
- * lio_tpg_shutdown_session()
- */
-static void lio_tpg_close_session(struct se_session *se_sess)
-{
- struct iscsi_session *sess = se_sess->fabric_sess_ptr;
- /*
- * If the iSCSI Session for the iSCSI Initiator Node exists,
- * forcefully shutdown the iSCSI NEXUS.
- */
iscsit_close_session(sess);
}
@@ -1640,7 +1585,6 @@ const struct target_core_fabric_ops iscsi_ops = {
.tpg_get_inst_index = lio_tpg_get_inst_index,
.check_stop_free = lio_check_stop_free,
.release_cmd = lio_release_cmd,
- .shutdown_session = lio_tpg_shutdown_session,
.close_session = lio_tpg_close_session,
.sess_get_index = lio_sess_get_index,
.sess_get_initiator_sid = lio_sess_get_initiator_sid,
diff --git a/drivers/target/iscsi/iscsi_target_datain_values.c b/drivers/target/iscsi/iscsi_target_datain_values.c
index fb3b52b124ac..647d4a5dca52 100644
--- a/drivers/target/iscsi/iscsi_target_datain_values.c
+++ b/drivers/target/iscsi/iscsi_target_datain_values.c
@@ -524,3 +524,4 @@ struct iscsi_datain_req *iscsit_get_datain_values(
return NULL;
}
+EXPORT_SYMBOL(iscsit_get_datain_values);
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 210f6e4830e3..b54e72c7ab0f 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -786,7 +786,7 @@ static void iscsit_handle_time2retain_timeout(unsigned long data)
}
spin_unlock_bh(&se_tpg->session_lock);
- target_put_session(sess->se_sess);
+ iscsit_close_session(sess);
}
void iscsit_start_time2retain_handler(struct iscsi_session *sess)
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 8436d56c5f0c..b5212f0f9571 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -228,7 +228,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
if (sess->session_state == TARG_SESS_STATE_FAILED) {
spin_unlock_bh(&sess->conn_lock);
iscsit_dec_session_usage_count(sess);
- target_put_session(sess->se_sess);
+ iscsit_close_session(sess);
return 0;
}
spin_unlock_bh(&sess->conn_lock);
@@ -236,7 +236,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
iscsit_stop_session(sess, 1, 1);
iscsit_dec_session_usage_count(sess);
- target_put_session(sess->se_sess);
+ iscsit_close_session(sess);
return 0;
}
@@ -258,7 +258,7 @@ static void iscsi_login_set_conn_values(
mutex_unlock(&auth_id_lock);
}
-static __printf(2, 3) int iscsi_change_param_sprintf(
+__printf(2, 3) int iscsi_change_param_sprintf(
struct iscsi_conn *conn,
const char *fmt, ...)
{
@@ -279,6 +279,7 @@ static __printf(2, 3) int iscsi_change_param_sprintf(
return 0;
}
+EXPORT_SYMBOL(iscsi_change_param_sprintf);
/*
* This is the leading connection of a new session,
@@ -1387,6 +1388,16 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
goto old_sess_out;
}
+ if (conn->conn_transport->iscsit_validate_params) {
+ ret = conn->conn_transport->iscsit_validate_params(conn);
+ if (ret < 0) {
+ if (zero_tsih)
+ goto new_sess_out;
+ else
+ goto old_sess_out;
+ }
+ }
+
ret = iscsi_target_start_negotiation(login, conn);
if (ret < 0)
goto new_sess_out;
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 9fc9117d0f22..89d34bd6d87f 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -269,6 +269,7 @@ int iscsi_target_check_login_request(
return 0;
}
+EXPORT_SYMBOL(iscsi_target_check_login_request);
static int iscsi_target_check_first_request(
struct iscsi_conn *conn,
@@ -1246,16 +1247,16 @@ int iscsi_target_start_negotiation(
{
int ret;
- ret = iscsi_target_do_login(conn, login);
- if (!ret) {
- if (conn->sock) {
- struct sock *sk = conn->sock->sk;
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
- write_lock_bh(&sk->sk_callback_lock);
- set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
- write_unlock_bh(&sk->sk_callback_lock);
- }
- } else if (ret < 0) {
+ write_lock_bh(&sk->sk_callback_lock);
+ set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
+ write_unlock_bh(&sk->sk_callback_lock);
+ }
+
+ ret = iscsi_target_do_login(conn, login);
+ if (ret < 0) {
cancel_delayed_work_sync(&conn->login_work);
cancel_delayed_work_sync(&conn->login_cleanup_work);
iscsi_target_restore_sock_callbacks(conn);
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 3a1f9a7e6bb6..0efa80bb8962 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -680,6 +680,7 @@ struct iscsi_param *iscsi_find_param_from_key(
pr_err("Unable to locate key \"%s\".\n", key);
return NULL;
}
+EXPORT_SYMBOL(iscsi_find_param_from_key);
int iscsi_extract_key_value(char *textbuf, char **key, char **value)
{
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 57720385a751..1f38177207e0 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -514,6 +514,7 @@ void iscsit_add_cmd_to_immediate_queue(
wake_up(&conn->queues_wq);
}
+EXPORT_SYMBOL(iscsit_add_cmd_to_immediate_queue);
struct iscsi_queue_req *iscsit_get_cmd_from_immediate_queue(struct iscsi_conn *conn)
{
@@ -725,6 +726,9 @@ void __iscsit_free_cmd(struct iscsi_cmd *cmd, bool scsi_cmd,
iscsit_remove_cmd_from_immediate_queue(cmd, conn);
iscsit_remove_cmd_from_response_queue(cmd, conn);
}
+
+ if (conn && conn->conn_transport->iscsit_release_cmd)
+ conn->conn_transport->iscsit_release_cmd(conn, cmd);
}
void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
@@ -773,6 +777,7 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
break;
}
}
+EXPORT_SYMBOL(iscsit_free_cmd);
int iscsit_check_session_usage_count(struct iscsi_session *sess)
{
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 0ad5ac541a7f..5091b31b3e56 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -601,16 +601,6 @@ static int tcm_loop_get_cmd_state(struct se_cmd *se_cmd)
return tl_cmd->sc_cmd_state;
}
-static int tcm_loop_shutdown_session(struct se_session *se_sess)
-{
- return 0;
-}
-
-static void tcm_loop_close_session(struct se_session *se_sess)
-{
- return;
-};
-
static int tcm_loop_write_pending(struct se_cmd *se_cmd)
{
/*
@@ -1243,8 +1233,6 @@ static const struct target_core_fabric_ops loop_ops = {
.tpg_get_inst_index = tcm_loop_get_inst_index,
.check_stop_free = tcm_loop_check_stop_free,
.release_cmd = tcm_loop_release_cmd,
- .shutdown_session = tcm_loop_shutdown_session,
- .close_session = tcm_loop_close_session,
.sess_get_index = tcm_loop_sess_get_index,
.write_pending = tcm_loop_write_pending,
.write_pending_status = tcm_loop_write_pending_status,
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index c57e7884973d..58bb6ed18185 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -1726,16 +1726,6 @@ static void sbp_release_cmd(struct se_cmd *se_cmd)
sbp_free_request(req);
}
-static int sbp_shutdown_session(struct se_session *se_sess)
-{
- return 0;
-}
-
-static void sbp_close_session(struct se_session *se_sess)
-{
- return;
-}
-
static u32 sbp_sess_get_index(struct se_session *se_sess)
{
return 0;
@@ -2349,8 +2339,6 @@ static const struct target_core_fabric_ops sbp_ops = {
.tpg_check_prod_mode_write_protect = sbp_check_false,
.tpg_get_inst_index = sbp_tpg_get_inst_index,
.release_cmd = sbp_release_cmd,
- .shutdown_session = sbp_shutdown_session,
- .close_session = sbp_close_session,
.sess_get_index = sbp_sess_get_index,
.write_pending = sbp_write_pending,
.write_pending_status = sbp_write_pending_status,
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 49aba4a31747..4c82bbe19003 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -932,7 +932,7 @@ static int core_alua_update_tpg_primary_metadata(
tg_pt_gp->tg_pt_gp_alua_access_status);
snprintf(path, ALUA_METADATA_PATH_LEN,
- "/var/target/alua/tpgs_%s/%s", &wwn->unit_serial[0],
+ "%s/alua/tpgs_%s/%s", db_root, &wwn->unit_serial[0],
config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item));
rc = core_alua_write_tpg_metadata(path, md_buf, len);
@@ -1275,8 +1275,8 @@ static int core_alua_update_tpg_secondary_metadata(struct se_lun *lun)
atomic_read(&lun->lun_tg_pt_secondary_offline),
lun->lun_tg_pt_secondary_stat);
- snprintf(path, ALUA_METADATA_PATH_LEN, "/var/target/alua/%s/%s/lun_%llu",
- se_tpg->se_tpg_tfo->get_fabric_name(), wwn,
+ snprintf(path, ALUA_METADATA_PATH_LEN, "%s/alua/%s/%s/lun_%llu",
+ db_root, se_tpg->se_tpg_tfo->get_fabric_name(), wwn,
lun->unpacked_lun);
rc = core_alua_write_tpg_metadata(path, md_buf, len);
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index d498533f09ee..2001005bef45 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -99,6 +99,67 @@ static ssize_t target_core_item_version_show(struct config_item *item,
CONFIGFS_ATTR_RO(target_core_item_, version);
+char db_root[DB_ROOT_LEN] = DB_ROOT_DEFAULT;
+static char db_root_stage[DB_ROOT_LEN];
+
+static ssize_t target_core_item_dbroot_show(struct config_item *item,
+ char *page)
+{
+ return sprintf(page, "%s\n", db_root);
+}
+
+static ssize_t target_core_item_dbroot_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ ssize_t read_bytes;
+ struct file *fp;
+
+ mutex_lock(&g_tf_lock);
+ if (!list_empty(&g_tf_list)) {
+ mutex_unlock(&g_tf_lock);
+ pr_err("db_root: cannot be changed: target drivers registered");
+ return -EINVAL;
+ }
+
+ if (count > (DB_ROOT_LEN - 1)) {
+ mutex_unlock(&g_tf_lock);
+ pr_err("db_root: count %d exceeds DB_ROOT_LEN-1: %u\n",
+ (int)count, DB_ROOT_LEN - 1);
+ return -EINVAL;
+ }
+
+ read_bytes = snprintf(db_root_stage, DB_ROOT_LEN, "%s", page);
+ if (!read_bytes) {
+ mutex_unlock(&g_tf_lock);
+ return -EINVAL;
+ }
+ if (db_root_stage[read_bytes - 1] == '\n')
+ db_root_stage[read_bytes - 1] = '\0';
+
+ /* validate new db root before accepting it */
+ fp = filp_open(db_root_stage, O_RDONLY, 0);
+ if (IS_ERR(fp)) {
+ mutex_unlock(&g_tf_lock);
+ pr_err("db_root: cannot open: %s\n", db_root_stage);
+ return -EINVAL;
+ }
+ if (!S_ISDIR(fp->f_inode->i_mode)) {
+ filp_close(fp, 0);
+ mutex_unlock(&g_tf_lock);
+ pr_err("db_root: not a directory: %s\n", db_root_stage);
+ return -EINVAL;
+ }
+ filp_close(fp, 0);
+
+ strncpy(db_root, db_root_stage, read_bytes);
+
+ mutex_unlock(&g_tf_lock);
+
+ return read_bytes;
+}
+
+CONFIGFS_ATTR(target_core_item_, dbroot);
+
static struct target_fabric_configfs *target_core_get_fabric(
const char *name)
{
@@ -239,6 +300,7 @@ static struct configfs_group_operations target_core_fabric_group_ops = {
*/
static struct configfs_attribute *target_core_fabric_item_attrs[] = {
&target_core_item_attr_version,
+ &target_core_item_attr_dbroot,
NULL,
};
@@ -323,14 +385,6 @@ static int target_fabric_tf_ops_check(const struct target_core_fabric_ops *tfo)
pr_err("Missing tfo->release_cmd()\n");
return -EINVAL;
}
- if (!tfo->shutdown_session) {
- pr_err("Missing tfo->shutdown_session()\n");
- return -EINVAL;
- }
- if (!tfo->close_session) {
- pr_err("Missing tfo->close_session()\n");
- return -EINVAL;
- }
if (!tfo->sess_get_index) {
pr_err("Missing tfo->sess_get_index()\n");
return -EINVAL;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 86b4a8375628..fc91e85f54ba 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -155,4 +155,10 @@ void target_stat_setup_mappedlun_default_groups(struct se_lun_acl *);
/* target_core_xcopy.c */
extern struct se_portal_group xcopy_pt_tpg;
+/* target_core_configfs.c */
+#define DB_ROOT_LEN 4096
+#define DB_ROOT_DEFAULT "/var/target"
+
+extern char db_root[];
+
#endif /* TARGET_CORE_INTERNAL_H */
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index b1795735eafc..47463c99c318 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1985,7 +1985,7 @@ static int __core_scsi3_write_aptpl_to_file(
return -EMSGSIZE;
}
- snprintf(path, 512, "/var/target/pr/aptpl_%s", &wwn->unit_serial[0]);
+ snprintf(path, 512, "%s/pr/aptpl_%s", db_root, &wwn->unit_serial[0]);
file = filp_open(path, flags, 0600);
if (IS_ERR(file)) {
pr_err("filp_open(%s) for APTPL metadata"
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 47a833f3a145..24b36fd785f1 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -403,7 +403,6 @@ static sense_reason_t rd_do_prot_rw(struct se_cmd *cmd, bool is_read)
struct se_device *se_dev = cmd->se_dev;
struct rd_dev *dev = RD_DEV(se_dev);
struct rd_dev_sg_table *prot_table;
- bool need_to_release = false;
struct scatterlist *prot_sg;
u32 sectors = cmd->data_length / se_dev->dev_attrib.block_size;
u32 prot_offset, prot_page;
@@ -432,9 +431,6 @@ static sense_reason_t rd_do_prot_rw(struct se_cmd *cmd, bool is_read)
if (!rc)
sbc_dif_copy_prot(cmd, sectors, is_read, prot_sg, prot_offset);
- if (need_to_release)
- kfree(prot_sg);
-
return rc;
}
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index ddf046080dc3..d99752c6cd60 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -336,44 +336,39 @@ struct se_node_acl *core_tpg_add_initiator_node_acl(
return acl;
}
-void core_tpg_del_initiator_node_acl(struct se_node_acl *acl)
+static void target_shutdown_sessions(struct se_node_acl *acl)
{
- struct se_portal_group *tpg = acl->se_tpg;
- LIST_HEAD(sess_list);
- struct se_session *sess, *sess_tmp;
+ struct se_session *sess;
unsigned long flags;
- int rc;
-
- mutex_lock(&tpg->acl_node_mutex);
- if (acl->dynamic_node_acl) {
- acl->dynamic_node_acl = 0;
- }
- list_del(&acl->acl_list);
- mutex_unlock(&tpg->acl_node_mutex);
+restart:
spin_lock_irqsave(&acl->nacl_sess_lock, flags);
- acl->acl_stop = 1;
-
- list_for_each_entry_safe(sess, sess_tmp, &acl->acl_sess_list,
- sess_acl_list) {
- if (sess->sess_tearing_down != 0)
+ list_for_each_entry(sess, &acl->acl_sess_list, sess_acl_list) {
+ if (sess->sess_tearing_down)
continue;
- if (!target_get_session(sess))
- continue;
- list_move(&sess->sess_acl_list, &sess_list);
+ list_del_init(&sess->sess_acl_list);
+ spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
+
+ if (acl->se_tpg->se_tpg_tfo->close_session)
+ acl->se_tpg->se_tpg_tfo->close_session(sess);
+ goto restart;
}
spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
+}
- list_for_each_entry_safe(sess, sess_tmp, &sess_list, sess_acl_list) {
- list_del(&sess->sess_acl_list);
+void core_tpg_del_initiator_node_acl(struct se_node_acl *acl)
+{
+ struct se_portal_group *tpg = acl->se_tpg;
+
+ mutex_lock(&tpg->acl_node_mutex);
+ if (acl->dynamic_node_acl)
+ acl->dynamic_node_acl = 0;
+ list_del(&acl->acl_list);
+ mutex_unlock(&tpg->acl_node_mutex);
+
+ target_shutdown_sessions(acl);
- rc = tpg->se_tpg_tfo->shutdown_session(sess);
- target_put_session(sess);
- if (!rc)
- continue;
- target_put_session(sess);
- }
target_put_nacl(acl);
/*
* Wait for last target_put_nacl() to complete in target_complete_nacl()
@@ -400,11 +395,7 @@ int core_tpg_set_initiator_node_queue_depth(
struct se_node_acl *acl,
u32 queue_depth)
{
- LIST_HEAD(sess_list);
struct se_portal_group *tpg = acl->se_tpg;
- struct se_session *sess, *sess_tmp;
- unsigned long flags;
- int rc;
/*
* User has requested to change the queue depth for a Initiator Node.
@@ -413,30 +404,10 @@ int core_tpg_set_initiator_node_queue_depth(
*/
target_set_nacl_queue_depth(tpg, acl, queue_depth);
- spin_lock_irqsave(&acl->nacl_sess_lock, flags);
- list_for_each_entry_safe(sess, sess_tmp, &acl->acl_sess_list,
- sess_acl_list) {
- if (sess->sess_tearing_down != 0)
- continue;
- if (!target_get_session(sess))
- continue;
- spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
-
- /*
- * Finally call tpg->se_tpg_tfo->close_session() to force session
- * reinstatement to occur if there is an active session for the
- * $FABRIC_MOD Initiator Node in question.
- */
- rc = tpg->se_tpg_tfo->shutdown_session(sess);
- target_put_session(sess);
- if (!rc) {
- spin_lock_irqsave(&acl->nacl_sess_lock, flags);
- continue;
- }
- target_put_session(sess);
- spin_lock_irqsave(&acl->nacl_sess_lock, flags);
- }
- spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
+ /*
+ * Shutdown all pending sessions to force session reinstatement.
+ */
+ target_shutdown_sessions(acl);
pr_debug("Successfully changed queue depth to: %d for Initiator"
" Node: %s on %s Target Portal Group: %u\n", acl->queue_depth,
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 590384a2bf8b..5ab3967dda43 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -239,7 +239,6 @@ struct se_session *transport_init_session(enum target_prot_op sup_prot_ops)
INIT_LIST_HEAD(&se_sess->sess_cmd_list);
INIT_LIST_HEAD(&se_sess->sess_wait_list);
spin_lock_init(&se_sess->sess_cmd_lock);
- kref_init(&se_sess->sess_kref);
se_sess->sup_prot_ops = sup_prot_ops;
return se_sess;
@@ -430,27 +429,6 @@ target_alloc_session(struct se_portal_group *tpg,
}
EXPORT_SYMBOL(target_alloc_session);
-static void target_release_session(struct kref *kref)
-{
- struct se_session *se_sess = container_of(kref,
- struct se_session, sess_kref);
- struct se_portal_group *se_tpg = se_sess->se_tpg;
-
- se_tpg->se_tpg_tfo->close_session(se_sess);
-}
-
-int target_get_session(struct se_session *se_sess)
-{
- return kref_get_unless_zero(&se_sess->sess_kref);
-}
-EXPORT_SYMBOL(target_get_session);
-
-void target_put_session(struct se_session *se_sess)
-{
- kref_put(&se_sess->sess_kref, target_release_session);
-}
-EXPORT_SYMBOL(target_put_session);
-
ssize_t target_show_dynamic_sessions(struct se_portal_group *se_tpg, char *page)
{
struct se_session *se_sess;
@@ -499,8 +477,8 @@ void transport_deregister_session_configfs(struct se_session *se_sess)
se_nacl = se_sess->se_node_acl;
if (se_nacl) {
spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
- if (se_nacl->acl_stop == 0)
- list_del(&se_sess->sess_acl_list);
+ if (!list_empty(&se_sess->sess_acl_list))
+ list_del_init(&se_sess->sess_acl_list);
/*
* If the session list is empty, then clear the pointer.
* Otherwise, set the struct se_session pointer from the tail
diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h
index c30003bd4ff0..e28209b99b59 100644
--- a/drivers/target/tcm_fc/tcm_fc.h
+++ b/drivers/target/tcm_fc/tcm_fc.h
@@ -139,7 +139,6 @@ extern unsigned int ft_debug_logging;
* Session ops.
*/
void ft_sess_put(struct ft_sess *);
-int ft_sess_shutdown(struct se_session *);
void ft_sess_close(struct se_session *);
u32 ft_sess_get_index(struct se_session *);
u32 ft_sess_get_port_name(struct se_session *, unsigned char *, u32);
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index 4d375e95841b..42ee91123dca 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -442,7 +442,6 @@ static const struct target_core_fabric_ops ft_fabric_ops = {
.tpg_get_inst_index = ft_tpg_get_inst_index,
.check_stop_free = ft_check_stop_free,
.release_cmd = ft_release_cmd,
- .shutdown_session = ft_sess_shutdown,
.close_session = ft_sess_close,
.sess_get_index = ft_sess_get_index,
.sess_get_initiator_sid = NULL,
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index d0c3e1894c61..f5186a744399 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -303,18 +303,6 @@ static void ft_sess_delete_all(struct ft_tport *tport)
*/
/*
- * Determine whether session is allowed to be shutdown in the current context.
- * Returns non-zero if the session should be shutdown.
- */
-int ft_sess_shutdown(struct se_session *se_sess)
-{
- struct ft_sess *sess = se_sess->fabric_sess_ptr;
-
- pr_debug("port_id %x\n", sess->port_id);
- return 1;
-}
-
-/*
* Remove session and send PRLO.
* This is called when the ACL is being deleted or queue depth is changing.
*/
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index d89d60c8b6cf..2d702ca6556f 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -260,16 +260,6 @@ config ARMADA_THERMAL
Enable this option if you want to have support for thermal management
controller present in Armada 370 and Armada XP SoC.
-config TEGRA_SOCTHERM
- tristate "Tegra SOCTHERM thermal management"
- depends on ARCH_TEGRA
- help
- Enable this option for integrated thermal management support on NVIDIA
- Tegra124 systems-on-chip. The driver supports four thermal zones
- (CPU, GPU, MEM, PLLX). Cooling devices can be bound to the thermal
- zones to manage temperatures. This option is also required for the
- emergency thermal reset (thermtrip) feature to function.
-
config DB8500_CPUFREQ_COOLING
tristate "DB8500 cpufreq cooling"
depends on ARCH_U8500 || COMPILE_TEST
@@ -377,6 +367,17 @@ depends on ARCH_STI && OF
source "drivers/thermal/st/Kconfig"
endmenu
+config TANGO_THERMAL
+ tristate "Tango thermal management"
+ depends on ARCH_TANGO || COMPILE_TEST
+ help
+ Enable the Tango thermal driver, which supports the primitive
+ temperature sensor embedded in Tango chips since the SMP8758.
+ This sensor only generates a 1-bit signal to indicate whether
+ the die temperature exceeds a programmable threshold.
+
+source "drivers/thermal/tegra/Kconfig"
+
config QCOM_SPMI_TEMP_ALARM
tristate "Qualcomm SPMI PMIC Temperature Alarm"
depends on OF && SPMI && IIO
@@ -388,4 +389,14 @@ config QCOM_SPMI_TEMP_ALARM
real time die temperature if an ADC is present or an estimate of the
temperature based upon the over temperature stage value.
+config GENERIC_ADC_THERMAL
+ tristate "Generic ADC based thermal sensor"
+ depends on IIO
+ help
+ This enabled a thermal sysfs driver for the temperature sensor
+ which is connected to the General Purpose ADC. The ADC channel
+ is read via IIO framework and the channel information is provided
+ to this driver. This driver reports the temperature by reading ADC
+ channel and converts it to temperature based on lookup table.
+
endif
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 8e9cbc3b5679..10b07c14f8a9 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -35,6 +35,7 @@ obj-y += samsung/
obj-$(CONFIG_DOVE_THERMAL) += dove_thermal.o
obj-$(CONFIG_DB8500_THERMAL) += db8500_thermal.o
obj-$(CONFIG_ARMADA_THERMAL) += armada_thermal.o
+obj-$(CONFIG_TANGO_THERMAL) += tango_thermal.o
obj-$(CONFIG_IMX_THERMAL) += imx_thermal.o
obj-$(CONFIG_DB8500_CPUFREQ_COOLING) += db8500_cpufreq_cooling.o
obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o
@@ -46,6 +47,7 @@ obj-$(CONFIG_TI_SOC_THERMAL) += ti-soc-thermal/
obj-$(CONFIG_INT340X_THERMAL) += int340x_thermal/
obj-$(CONFIG_INTEL_PCH_THERMAL) += intel_pch_thermal.o
obj-$(CONFIG_ST_THERMAL) += st/
-obj-$(CONFIG_TEGRA_SOCTHERM) += tegra_soctherm.o
+obj-$(CONFIG_TEGRA_SOCTHERM) += tegra/
obj-$(CONFIG_HISI_THERMAL) += hisi_thermal.o
obj-$(CONFIG_MTK_THERMAL) += mtk_thermal.o
+obj-$(CONFIG_GENERIC_ADC_THERMAL) += thermal-generic-adc.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6ceac4f2d4b2..5b4b47ed948b 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -857,14 +857,6 @@ __cpufreq_cooling_register(struct device_node *np,
goto free_power_table;
}
- snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
- cpufreq_dev->id);
-
- cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
- &cpufreq_cooling_ops);
- if (IS_ERR(cool_dev))
- goto remove_idr;
-
/* Fill freq-table in descending order of frequencies */
for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) {
freq = find_next_max(table, freq);
@@ -877,6 +869,14 @@ __cpufreq_cooling_register(struct device_node *np,
pr_debug("%s: freq:%u KHz\n", __func__, freq);
}
+ snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
+ cpufreq_dev->id);
+
+ cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
+ &cpufreq_cooling_ops);
+ if (IS_ERR(cool_dev))
+ goto remove_idr;
+
cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0];
cpufreq_dev->cool_dev = cool_dev;
diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
index 70836c5b89bc..fc52016d4e85 100644
--- a/drivers/thermal/gov_bang_bang.c
+++ b/drivers/thermal/gov_bang_bang.c
@@ -29,7 +29,13 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
struct thermal_instance *instance;
tz->ops->get_trip_temp(tz, trip, &trip_temp);
- tz->ops->get_trip_hyst(tz, trip, &trip_hyst);
+
+ if (!tz->ops->get_trip_hyst) {
+ pr_warn_once("Undefined get_trip_hyst for thermal zone %s - "
+ "running with default hysteresis zero\n", tz->type);
+ trip_hyst = 0;
+ } else
+ tz->ops->get_trip_hyst(tz, trip, &trip_hyst);
dev_dbg(&tz->device, "Trip%d[temp=%d]:temp=%d:hyst=%d\n",
trip, trip_temp, tz->temperature,
diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c
index 5e820b541506..97fad8f51e1c 100644
--- a/drivers/thermal/hisi_thermal.c
+++ b/drivers/thermal/hisi_thermal.c
@@ -160,7 +160,7 @@ static int hisi_thermal_get_temp(void *_sensor, int *temp)
struct hisi_thermal_sensor *sensor = _sensor;
struct hisi_thermal_data *data = sensor->thermal;
- int sensor_id = 0, i;
+ int sensor_id = -1, i;
long max_temp = 0;
*temp = hisi_thermal_get_sensor_temp(data, sensor);
@@ -168,12 +168,19 @@ static int hisi_thermal_get_temp(void *_sensor, int *temp)
sensor->sensor_temp = *temp;
for (i = 0; i < HISI_MAX_SENSORS; i++) {
+ if (!data->sensors[i].tzd)
+ continue;
+
if (data->sensors[i].sensor_temp >= max_temp) {
max_temp = data->sensors[i].sensor_temp;
sensor_id = i;
}
}
+ /* If no sensor has been enabled, then skip to enable irq */
+ if (sensor_id == -1)
+ return 0;
+
mutex_lock(&data->thermal_lock);
data->irq_bind_sensor = sensor_id;
mutex_unlock(&data->thermal_lock);
@@ -226,8 +233,12 @@ static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev)
sensor->thres_temp / 1000);
mutex_unlock(&data->thermal_lock);
- for (i = 0; i < HISI_MAX_SENSORS; i++)
+ for (i = 0; i < HISI_MAX_SENSORS; i++) {
+ if (!data->sensors[i].tzd)
+ continue;
+
thermal_zone_device_update(data->sensors[i].tzd);
+ }
return IRQ_HANDLED;
}
@@ -243,10 +254,11 @@ static int hisi_thermal_register_sensor(struct platform_device *pdev,
sensor->id = index;
sensor->thermal = data;
- sensor->tzd = thermal_zone_of_sensor_register(&pdev->dev, sensor->id,
- sensor, &hisi_of_thermal_ops);
+ sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
+ sensor->id, sensor, &hisi_of_thermal_ops);
if (IS_ERR(sensor->tzd)) {
ret = PTR_ERR(sensor->tzd);
+ sensor->tzd = NULL;
dev_err(&pdev->dev, "failed to register sensor id %d: %d\n",
sensor->id, ret);
return ret;
@@ -331,28 +343,21 @@ static int hisi_thermal_probe(struct platform_device *pdev)
return ret;
}
+ hisi_thermal_enable_bind_irq_sensor(data);
+ irq_get_irqchip_state(data->irq, IRQCHIP_STATE_MASKED,
+ &data->irq_enabled);
+
for (i = 0; i < HISI_MAX_SENSORS; ++i) {
ret = hisi_thermal_register_sensor(pdev, data,
&data->sensors[i], i);
- if (ret) {
+ if (ret)
dev_err(&pdev->dev,
"failed to register thermal sensor: %d\n", ret);
- goto err_get_sensor_data;
- }
+ else
+ hisi_thermal_toggle_sensor(&data->sensors[i], true);
}
- hisi_thermal_enable_bind_irq_sensor(data);
- data->irq_enabled = true;
-
- for (i = 0; i < HISI_MAX_SENSORS; i++)
- hisi_thermal_toggle_sensor(&data->sensors[i], true);
-
return 0;
-
-err_get_sensor_data:
- clk_disable_unprepare(data->clk);
-
- return ret;
}
static int hisi_thermal_remove(struct platform_device *pdev)
@@ -363,8 +368,10 @@ static int hisi_thermal_remove(struct platform_device *pdev)
for (i = 0; i < HISI_MAX_SENSORS; i++) {
struct hisi_thermal_sensor *sensor = &data->sensors[i];
+ if (!sensor->tzd)
+ continue;
+
hisi_thermal_toggle_sensor(sensor, false);
- thermal_zone_of_sensor_unregister(&pdev->dev, sensor->tzd);
}
hisi_thermal_disable_sensor(data);
diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c
index 13d431cbd29e..a578cd257db4 100644
--- a/drivers/thermal/int340x_thermal/int3406_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3406_thermal.c
@@ -177,7 +177,7 @@ static int int3406_thermal_probe(struct platform_device *pdev)
return -ENODEV;
d->raw_bd = bd;
- ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br);
+ ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br, NULL);
if (ret)
return ret;
diff --git a/drivers/thermal/int340x_thermal/processor_thermal_device.c b/drivers/thermal/int340x_thermal/processor_thermal_device.c
index 36fa724a36c8..42c1ac057bad 100644
--- a/drivers/thermal/int340x_thermal/processor_thermal_device.c
+++ b/drivers/thermal/int340x_thermal/processor_thermal_device.c
@@ -198,49 +198,33 @@ static struct thermal_zone_device_ops proc_thermal_local_ops = {
.get_temp = proc_thermal_get_zone_temp,
};
-static int proc_thermal_add(struct device *dev,
- struct proc_thermal_device **priv)
+static int proc_thermal_read_ppcc(struct proc_thermal_device *proc_priv)
{
- struct proc_thermal_device *proc_priv;
- struct acpi_device *adev;
+ int i;
acpi_status status;
struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *elements, *ppcc;
union acpi_object *p;
- unsigned long long tmp;
- struct thermal_zone_device_ops *ops = NULL;
- int i;
- int ret;
-
- adev = ACPI_COMPANION(dev);
- if (!adev)
- return -ENODEV;
+ int ret = 0;
- status = acpi_evaluate_object(adev->handle, "PPCC", NULL, &buf);
+ status = acpi_evaluate_object(proc_priv->adev->handle, "PPCC",
+ NULL, &buf);
if (ACPI_FAILURE(status))
return -ENODEV;
p = buf.pointer;
if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
- dev_err(dev, "Invalid PPCC data\n");
+ dev_err(proc_priv->dev, "Invalid PPCC data\n");
ret = -EFAULT;
goto free_buffer;
}
+
if (!p->package.count) {
- dev_err(dev, "Invalid PPCC package size\n");
+ dev_err(proc_priv->dev, "Invalid PPCC package size\n");
ret = -EFAULT;
goto free_buffer;
}
- proc_priv = devm_kzalloc(dev, sizeof(*proc_priv), GFP_KERNEL);
- if (!proc_priv) {
- ret = -ENOMEM;
- goto free_buffer;
- }
-
- proc_priv->dev = dev;
- proc_priv->adev = adev;
-
for (i = 0; i < min((int)p->package.count - 1, 2); ++i) {
elements = &(p->package.elements[i+1]);
if (elements->type != ACPI_TYPE_PACKAGE ||
@@ -257,12 +241,62 @@ static int proc_thermal_add(struct device *dev,
proc_priv->power_limits[i].step_uw = ppcc[5].integer.value;
}
+free_buffer:
+ kfree(buf.pointer);
+
+ return ret;
+}
+
+#define PROC_POWER_CAPABILITY_CHANGED 0x83
+static void proc_thermal_notify(acpi_handle handle, u32 event, void *data)
+{
+ struct proc_thermal_device *proc_priv = data;
+
+ if (!proc_priv)
+ return;
+
+ switch (event) {
+ case PROC_POWER_CAPABILITY_CHANGED:
+ proc_thermal_read_ppcc(proc_priv);
+ int340x_thermal_zone_device_update(proc_priv->int340x_zone);
+ break;
+ default:
+ dev_err(proc_priv->dev, "Unsupported event [0x%x]\n", event);
+ break;
+ }
+}
+
+
+static int proc_thermal_add(struct device *dev,
+ struct proc_thermal_device **priv)
+{
+ struct proc_thermal_device *proc_priv;
+ struct acpi_device *adev;
+ acpi_status status;
+ unsigned long long tmp;
+ struct thermal_zone_device_ops *ops = NULL;
+ int ret;
+
+ adev = ACPI_COMPANION(dev);
+ if (!adev)
+ return -ENODEV;
+
+ proc_priv = devm_kzalloc(dev, sizeof(*proc_priv), GFP_KERNEL);
+ if (!proc_priv)
+ return -ENOMEM;
+
+ proc_priv->dev = dev;
+ proc_priv->adev = adev;
*priv = proc_priv;
- ret = sysfs_create_group(&dev->kobj,
- &power_limit_attribute_group);
+ ret = proc_thermal_read_ppcc(proc_priv);
+ if (!ret) {
+ ret = sysfs_create_group(&dev->kobj,
+ &power_limit_attribute_group);
+
+ }
if (ret)
- goto free_buffer;
+ return ret;
status = acpi_evaluate_integer(adev->handle, "_TMP", NULL, &tmp);
if (ACPI_FAILURE(status)) {
@@ -274,20 +308,32 @@ static int proc_thermal_add(struct device *dev,
proc_priv->int340x_zone = int340x_thermal_zone_add(adev, ops);
if (IS_ERR(proc_priv->int340x_zone)) {
- sysfs_remove_group(&proc_priv->dev->kobj,
- &power_limit_attribute_group);
ret = PTR_ERR(proc_priv->int340x_zone);
+ goto remove_group;
} else
ret = 0;
-free_buffer:
- kfree(buf.pointer);
+ ret = acpi_install_notify_handler(adev->handle, ACPI_DEVICE_NOTIFY,
+ proc_thermal_notify,
+ (void *)proc_priv);
+ if (ret)
+ goto remove_zone;
+
+ return 0;
+
+remove_zone:
+ int340x_thermal_zone_remove(proc_priv->int340x_zone);
+remove_group:
+ sysfs_remove_group(&proc_priv->dev->kobj,
+ &power_limit_attribute_group);
return ret;
}
static void proc_thermal_remove(struct proc_thermal_device *proc_priv)
{
+ acpi_remove_notify_handler(proc_priv->adev->handle,
+ ACPI_DEVICE_NOTIFY, proc_thermal_notify);
int340x_thermal_zone_remove(proc_priv->int340x_zone);
sysfs_remove_group(&proc_priv->dev->kobj,
&power_limit_attribute_group);
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 6c79588251d5..015ce2eb6eb7 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -510,12 +510,6 @@ static int start_power_clamp(void)
unsigned long cpu;
struct task_struct *thread;
- /* check if pkg cstate counter is completely 0, abort in this case */
- if (!has_pkg_state_counter()) {
- pr_err("pkg cstate counter not functional, abort\n");
- return -EINVAL;
- }
-
set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1);
/* prevent cpu hotplug */
get_online_cpus();
@@ -672,35 +666,11 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
.set_cur_state = powerclamp_set_cur_state,
};
-/* runs on Nehalem and later */
static const struct x86_cpu_id intel_powerclamp_ids[] __initconst = {
- { X86_VENDOR_INTEL, 6, 0x1a},
- { X86_VENDOR_INTEL, 6, 0x1c},
- { X86_VENDOR_INTEL, 6, 0x1e},
- { X86_VENDOR_INTEL, 6, 0x1f},
- { X86_VENDOR_INTEL, 6, 0x25},
- { X86_VENDOR_INTEL, 6, 0x26},
- { X86_VENDOR_INTEL, 6, 0x2a},
- { X86_VENDOR_INTEL, 6, 0x2c},
- { X86_VENDOR_INTEL, 6, 0x2d},
- { X86_VENDOR_INTEL, 6, 0x2e},
- { X86_VENDOR_INTEL, 6, 0x2f},
- { X86_VENDOR_INTEL, 6, 0x37},
- { X86_VENDOR_INTEL, 6, 0x3a},
- { X86_VENDOR_INTEL, 6, 0x3c},
- { X86_VENDOR_INTEL, 6, 0x3d},
- { X86_VENDOR_INTEL, 6, 0x3e},
- { X86_VENDOR_INTEL, 6, 0x3f},
- { X86_VENDOR_INTEL, 6, 0x45},
- { X86_VENDOR_INTEL, 6, 0x46},
- { X86_VENDOR_INTEL, 6, 0x47},
- { X86_VENDOR_INTEL, 6, 0x4c},
- { X86_VENDOR_INTEL, 6, 0x4d},
- { X86_VENDOR_INTEL, 6, 0x4e},
- { X86_VENDOR_INTEL, 6, 0x4f},
- { X86_VENDOR_INTEL, 6, 0x56},
- { X86_VENDOR_INTEL, 6, 0x57},
- { X86_VENDOR_INTEL, 6, 0x5e},
+ { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
+ { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_ARAT },
+ { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_NONSTOP_TSC },
+ { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_CONSTANT_TSC},
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
@@ -712,11 +682,12 @@ static int __init powerclamp_probe(void)
boot_cpu_data.x86, boot_cpu_data.x86_model);
return -ENODEV;
}
- if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ||
- !boot_cpu_has(X86_FEATURE_CONSTANT_TSC) ||
- !boot_cpu_has(X86_FEATURE_MWAIT) ||
- !boot_cpu_has(X86_FEATURE_ARAT))
+
+ /* The goal for idle time alignment is to achieve package cstate. */
+ if (!has_pkg_state_counter()) {
+ pr_info("No package C-state available");
return -ENODEV;
+ }
/* find the deepest mwait value */
find_target_mwait();
diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
index 507632b9648e..262ab0a2266f 100644
--- a/drivers/thermal/mtk_thermal.c
+++ b/drivers/thermal/mtk_thermal.c
@@ -144,7 +144,6 @@ struct mtk_thermal {
s32 o_slope;
s32 vts[MT8173_NUM_SENSORS];
- struct thermal_zone_device *tzd;
};
struct mtk_thermal_bank_cfg {
@@ -572,16 +571,11 @@ static int mtk_thermal_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, mt);
- mt->tzd = thermal_zone_of_sensor_register(&pdev->dev, 0, mt,
- &mtk_thermal_ops);
- if (IS_ERR(mt->tzd))
- goto err_register;
+ devm_thermal_zone_of_sensor_register(&pdev->dev, 0, mt,
+ &mtk_thermal_ops);
return 0;
-err_register:
- clk_disable_unprepare(mt->clk_peri_therm);
-
err_disable_clk_auxadc:
clk_disable_unprepare(mt->clk_auxadc);
@@ -592,8 +586,6 @@ static int mtk_thermal_remove(struct platform_device *pdev)
{
struct mtk_thermal *mt = platform_get_drvdata(pdev);
- thermal_zone_of_sensor_unregister(&pdev->dev, mt->tzd);
-
clk_disable_unprepare(mt->clk_peri_therm);
clk_disable_unprepare(mt->clk_auxadc);
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index d8ec44b194d6..b8e509c60848 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -331,6 +331,14 @@ static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip,
if (trip >= data->ntrips || trip < 0)
return -EDOM;
+ if (data->ops->set_trip_temp) {
+ int ret;
+
+ ret = data->ops->set_trip_temp(data->sensor_data, trip, temp);
+ if (ret)
+ return ret;
+ }
+
/* thermal framework should take care of data->mask & (1 << trip) */
data->trips[trip].temperature = temp;
@@ -906,7 +914,7 @@ finish:
return tz;
free_tbps:
- for (i = 0; i < tz->num_tbps; i++)
+ for (i = i - 1; i >= 0; i--)
of_node_put(tz->tbps[i].cooling_device);
kfree(tz->tbps);
free_trips:
diff --git a/drivers/thermal/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom-spmi-temp-alarm.c
index b677aada5b52..f8a3c60bef94 100644
--- a/drivers/thermal/qcom-spmi-temp-alarm.c
+++ b/drivers/thermal/qcom-spmi-temp-alarm.c
@@ -260,7 +260,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
if (ret < 0)
goto fail;
- chip->tz_dev = thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
+ chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
&qpnp_tm_sensor_ops);
if (IS_ERR(chip->tz_dev)) {
dev_err(&pdev->dev, "failed to register sensor\n");
@@ -281,7 +281,6 @@ static int qpnp_tm_remove(struct platform_device *pdev)
{
struct qpnp_tm_chip *chip = dev_get_drvdata(&pdev->dev);
- thermal_zone_of_sensor_unregister(&pdev->dev, chip->tz_dev);
if (!IS_ERR(chip->adc))
iio_channel_release(chip->adc);
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 82daba09e150..71a339271fa5 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -492,7 +492,7 @@ static int rcar_thermal_probe(struct platform_device *pdev)
goto error_unregister;
if (of_data == USE_OF_THERMAL)
- priv->zone = thermal_zone_of_sensor_register(
+ priv->zone = devm_thermal_zone_of_sensor_register(
dev, i, priv,
&rcar_thermal_zone_of_ops);
else
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index 233a564442a0..5d491f16a866 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -1,7 +1,5 @@
/*
- * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
- *
- * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ * Copyright (c) 2014-2016, Fuzhou Rockchip Electronics Co., Ltd
* Caesar Wang <wxt@rock-chips.com>
*
* This program is free software; you can redistribute it and/or modify it
@@ -23,8 +21,10 @@
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/platform_device.h>
+#include <linux/regmap.h>
#include <linux/reset.h>
#include <linux/thermal.h>
+#include <linux/mfd/syscon.h>
#include <linux/pinctrl/consumer.h>
/**
@@ -73,7 +73,7 @@ enum adc_sort_mode {
#define SOC_MAX_SENSORS 2
/**
- * struct chip_tsadc_table: hold information about chip-specific differences
+ * struct chip_tsadc_table - hold information about chip-specific differences
* @id: conversion table
* @length: size of conversion table
* @data_mask: mask to apply on data inputs
@@ -86,6 +86,20 @@ struct chip_tsadc_table {
enum adc_sort_mode mode;
};
+/**
+ * struct rockchip_tsadc_chip - hold the private data of tsadc chip
+ * @chn_id[SOC_MAX_SENSORS]: the sensor id of chip correspond to the channel
+ * @chn_num: the channel number of tsadc chip
+ * @tshut_temp: the hardware-controlled shutdown temperature value
+ * @tshut_mode: the hardware-controlled shutdown mode (0:CRU 1:GPIO)
+ * @tshut_polarity: the hardware-controlled active polarity (0:LOW 1:HIGH)
+ * @initialize: SoC special initialize tsadc controller method
+ * @irq_ack: clear the interrupt
+ * @get_temp: get the temperature
+ * @set_tshut_temp: set the hardware-controlled shutdown temperature
+ * @set_tshut_mode: set the hardware-controlled shutdown mode
+ * @table: the chip-specific conversion table
+ */
struct rockchip_tsadc_chip {
/* The sensor id of chip correspond to the ADC channel */
int chn_id[SOC_MAX_SENSORS];
@@ -97,7 +111,8 @@ struct rockchip_tsadc_chip {
enum tshut_polarity tshut_polarity;
/* Chip-wide methods */
- void (*initialize)(void __iomem *reg, enum tshut_polarity p);
+ void (*initialize)(struct regmap *grf,
+ void __iomem *reg, enum tshut_polarity p);
void (*irq_ack)(void __iomem *reg);
void (*control)(void __iomem *reg, bool on);
@@ -112,12 +127,32 @@ struct rockchip_tsadc_chip {
struct chip_tsadc_table table;
};
+/**
+ * struct rockchip_thermal_sensor - hold the information of thermal sensor
+ * @thermal: pointer to the platform/configuration data
+ * @tzd: pointer to a thermal zone
+ * @id: identifier of the thermal sensor
+ */
struct rockchip_thermal_sensor {
struct rockchip_thermal_data *thermal;
struct thermal_zone_device *tzd;
int id;
};
+/**
+ * struct rockchip_thermal_data - hold the private data of thermal driver
+ * @chip: pointer to the platform/configuration data
+ * @pdev: platform device of thermal
+ * @reset: the reset controller of tsadc
+ * @sensors[SOC_MAX_SENSORS]: the thermal sensor
+ * @clk: the controller clock is divided by the exteral 24MHz
+ * @pclk: the advanced peripherals bus clock
+ * @grf: the general register file will be used to do static set by software
+ * @regs: the base address of tsadc controller
+ * @tshut_temp: the hardware-controlled shutdown temperature value
+ * @tshut_mode: the hardware-controlled shutdown mode (0:CRU 1:GPIO)
+ * @tshut_polarity: the hardware-controlled active polarity (0:LOW 1:HIGH)
+ */
struct rockchip_thermal_data {
const struct rockchip_tsadc_chip *chip;
struct platform_device *pdev;
@@ -128,6 +163,7 @@ struct rockchip_thermal_data {
struct clk *clk;
struct clk *pclk;
+ struct regmap *grf;
void __iomem *regs;
int tshut_temp;
@@ -142,6 +178,7 @@ struct rockchip_thermal_data {
* TSADCV3_* are used for newer SoCs than RK3288. (e.g: RK3228, RK3399)
*
*/
+#define TSADCV2_USER_CON 0x00
#define TSADCV2_AUTO_CON 0x04
#define TSADCV2_INT_EN 0x08
#define TSADCV2_INT_PD 0x0c
@@ -155,12 +192,7 @@ struct rockchip_thermal_data {
#define TSADCV2_AUTO_EN BIT(0)
#define TSADCV2_AUTO_SRC_EN(chn) BIT(4 + (chn))
#define TSADCV2_AUTO_TSHUT_POLARITY_HIGH BIT(8)
-/**
- * TSADCV1_AUTO_Q_SEL_EN:
- * whether select (1024 - tsadc_q) as output
- * 1'b0:use tsadc_q as output(temperature-code is rising sequence)
- * 1'b1:use(1024 - tsadc_q) as output (temperature-code is falling sequence)
- */
+
#define TSADCV3_AUTO_Q_SEL_EN BIT(1)
#define TSADCV2_INT_SRC_EN(chn) BIT(chn)
@@ -177,19 +209,32 @@ struct rockchip_thermal_data {
#define TSADCV2_HIGHT_TSHUT_DEBOUNCE_COUNT 4
#define TSADCV2_AUTO_PERIOD_TIME 250 /* msec */
#define TSADCV2_AUTO_PERIOD_HT_TIME 50 /* msec */
+#define TSADCV2_USER_INTER_PD_SOC 0x340 /* 13 clocks */
-struct tsadc_table {
- u32 code;
- int temp;
-};
+#define GRF_SARADC_TESTBIT 0x0e644
+#define GRF_TSADC_TESTBIT_L 0x0e648
+#define GRF_TSADC_TESTBIT_H 0x0e64c
+
+#define GRF_TSADC_TSEN_PD_ON (0x30003 << 0)
+#define GRF_TSADC_TSEN_PD_OFF (0x30000 << 0)
+#define GRF_SARADC_TESTBIT_ON (0x10001 << 2)
+#define GRF_TSADC_TESTBIT_H_ON (0x10001 << 2)
/**
+ * struct tsadc_table - code to temperature conversion table
+ * @code: the value of adc channel
+ * @temp: the temperature
* Note:
- * Code to Temperature mapping of the Temperature sensor is a piece wise linear
+ * code to temperature mapping of the temperature sensor is a piece wise linear
* curve.Any temperature, code faling between to 2 give temperatures can be
* linearly interpolated.
- * Code to Temperature mapping should be updated based on sillcon results.
+ * Code to Temperature mapping should be updated based on manufacturer results.
*/
+struct tsadc_table {
+ u32 code;
+ int temp;
+};
+
static const struct tsadc_table rk3228_code_table[] = {
{0, -40000},
{588, -40000},
@@ -308,40 +353,40 @@ static const struct tsadc_table rk3368_code_table[] = {
static const struct tsadc_table rk3399_code_table[] = {
{0, -40000},
- {593, -40000},
- {598, -35000},
- {603, -30000},
- {609, -25000},
- {614, -20000},
- {619, -15000},
- {625, -10000},
- {630, -5000},
- {635, 0},
- {641, 5000},
- {646, 10000},
- {651, 15000},
- {657, 20000},
- {662, 25000},
- {667, 30000},
- {673, 35000},
- {678, 40000},
- {684, 45000},
- {689, 50000},
- {694, 55000},
- {700, 60000},
- {705, 65000},
- {711, 70000},
- {716, 75000},
- {722, 80000},
- {727, 85000},
- {733, 90000},
- {738, 95000},
- {743, 100000},
- {749, 105000},
- {754, 110000},
- {760, 115000},
- {765, 120000},
- {771, 125000},
+ {402, -40000},
+ {410, -35000},
+ {419, -30000},
+ {427, -25000},
+ {436, -20000},
+ {444, -15000},
+ {453, -10000},
+ {461, -5000},
+ {470, 0},
+ {478, 5000},
+ {487, 10000},
+ {496, 15000},
+ {504, 20000},
+ {513, 25000},
+ {521, 30000},
+ {530, 35000},
+ {538, 40000},
+ {547, 45000},
+ {555, 50000},
+ {564, 55000},
+ {573, 60000},
+ {581, 65000},
+ {590, 70000},
+ {599, 75000},
+ {607, 80000},
+ {616, 85000},
+ {624, 90000},
+ {633, 95000},
+ {642, 100000},
+ {650, 105000},
+ {659, 110000},
+ {668, 115000},
+ {677, 120000},
+ {685, 125000},
{TSADCV3_DATA_MASK, 125000},
};
@@ -405,8 +450,8 @@ static int rk_tsadcv2_code_to_temp(struct chip_tsadc_table table, u32 code,
return -EAGAIN; /* Incorrect reading */
while (low <= high) {
- if (code >= table.id[mid - 1].code &&
- code < table.id[mid].code)
+ if (code <= table.id[mid].code &&
+ code > table.id[mid - 1].code)
break;
else if (code > table.id[mid].code)
low = mid + 1;
@@ -449,7 +494,7 @@ static int rk_tsadcv2_code_to_temp(struct chip_tsadc_table table, u32 code,
* If the temperature is higher than COMP_INT or COMP_SHUT for
* "debounce" times, TSADC controller will generate interrupt or TSHUT.
*/
-static void rk_tsadcv2_initialize(void __iomem *regs,
+static void rk_tsadcv2_initialize(struct regmap *grf, void __iomem *regs,
enum tshut_polarity tshut_polarity)
{
if (tshut_polarity == TSHUT_HIGH_ACTIVE)
@@ -466,6 +511,62 @@ static void rk_tsadcv2_initialize(void __iomem *regs,
regs + TSADCV2_AUTO_PERIOD_HT);
writel_relaxed(TSADCV2_HIGHT_TSHUT_DEBOUNCE_COUNT,
regs + TSADCV2_HIGHT_TSHUT_DEBOUNCE);
+
+ if (IS_ERR(grf)) {
+ pr_warn("%s: Missing rockchip,grf property\n", __func__);
+ return;
+ }
+}
+
+/**
+ * rk_tsadcv3_initialize - initialize TASDC Controller.
+ *
+ * (1) The tsadc control power sequence.
+ *
+ * (2) Set TSADC_V2_AUTO_PERIOD:
+ * Configure the interleave between every two accessing of
+ * TSADC in normal operation.
+ *
+ * (2) Set TSADCV2_AUTO_PERIOD_HT:
+ * Configure the interleave between every two accessing of
+ * TSADC after the temperature is higher than COM_SHUT or COM_INT.
+ *
+ * (3) Set TSADCV2_HIGH_INT_DEBOUNCE and TSADC_HIGHT_TSHUT_DEBOUNCE:
+ * If the temperature is higher than COMP_INT or COMP_SHUT for
+ * "debounce" times, TSADC controller will generate interrupt or TSHUT.
+ */
+static void rk_tsadcv3_initialize(struct regmap *grf, void __iomem *regs,
+ enum tshut_polarity tshut_polarity)
+{
+ /* The tsadc control power sequence */
+ if (IS_ERR(grf)) {
+ /* Set interleave value to workround ic time sync issue */
+ writel_relaxed(TSADCV2_USER_INTER_PD_SOC, regs +
+ TSADCV2_USER_CON);
+ } else {
+ regmap_write(grf, GRF_TSADC_TESTBIT_L, GRF_TSADC_TSEN_PD_ON);
+ mdelay(10);
+ regmap_write(grf, GRF_TSADC_TESTBIT_L, GRF_TSADC_TSEN_PD_OFF);
+ usleep_range(15, 100); /* The spec note says at least 15 us */
+ regmap_write(grf, GRF_SARADC_TESTBIT, GRF_SARADC_TESTBIT_ON);
+ regmap_write(grf, GRF_TSADC_TESTBIT_H, GRF_TSADC_TESTBIT_H_ON);
+ usleep_range(90, 200); /* The spec note says at least 90 us */
+ }
+
+ if (tshut_polarity == TSHUT_HIGH_ACTIVE)
+ writel_relaxed(0U | TSADCV2_AUTO_TSHUT_POLARITY_HIGH,
+ regs + TSADCV2_AUTO_CON);
+ else
+ writel_relaxed(0U & ~TSADCV2_AUTO_TSHUT_POLARITY_HIGH,
+ regs + TSADCV2_AUTO_CON);
+
+ writel_relaxed(TSADCV2_AUTO_PERIOD_TIME, regs + TSADCV2_AUTO_PERIOD);
+ writel_relaxed(TSADCV2_HIGHT_INT_DEBOUNCE_COUNT,
+ regs + TSADCV2_HIGHT_INT_DEBOUNCE);
+ writel_relaxed(TSADCV2_AUTO_PERIOD_HT_TIME,
+ regs + TSADCV2_AUTO_PERIOD_HT);
+ writel_relaxed(TSADCV2_HIGHT_TSHUT_DEBOUNCE_COUNT,
+ regs + TSADCV2_HIGHT_TSHUT_DEBOUNCE);
}
static void rk_tsadcv2_irq_ack(void __iomem *regs)
@@ -498,10 +599,11 @@ static void rk_tsadcv2_control(void __iomem *regs, bool enable)
}
/**
- * @rk_tsadcv3_control:
- * TSADC controller works at auto mode, and some SoCs need set the tsadc_q_sel
- * bit on TSADCV2_AUTO_CON[1]. The (1024 - tsadc_q) as output adc value if
- * setting this bit to enable.
+ * rk_tsadcv3_control - the tsadc controller is enabled or disabled.
+ *
+ * NOTE: TSADC controller works at auto mode, and some SoCs need set the
+ * tsadc_q_sel bit on TSADCV2_AUTO_CON[1]. The (1024 - tsadc_q) as output
+ * adc value if setting this bit to enable.
*/
static void rk_tsadcv3_control(void __iomem *regs, bool enable)
{
@@ -603,6 +705,30 @@ static const struct rockchip_tsadc_chip rk3288_tsadc_data = {
},
};
+static const struct rockchip_tsadc_chip rk3366_tsadc_data = {
+ .chn_id[SENSOR_CPU] = 0, /* cpu sensor is channel 0 */
+ .chn_id[SENSOR_GPU] = 1, /* gpu sensor is channel 1 */
+ .chn_num = 2, /* two channels for tsadc */
+
+ .tshut_mode = TSHUT_MODE_GPIO, /* default TSHUT via GPIO give PMIC */
+ .tshut_polarity = TSHUT_LOW_ACTIVE, /* default TSHUT LOW ACTIVE */
+ .tshut_temp = 95000,
+
+ .initialize = rk_tsadcv3_initialize,
+ .irq_ack = rk_tsadcv3_irq_ack,
+ .control = rk_tsadcv3_control,
+ .get_temp = rk_tsadcv2_get_temp,
+ .set_tshut_temp = rk_tsadcv2_tshut_temp,
+ .set_tshut_mode = rk_tsadcv2_tshut_mode,
+
+ .table = {
+ .id = rk3228_code_table,
+ .length = ARRAY_SIZE(rk3228_code_table),
+ .data_mask = TSADCV3_DATA_MASK,
+ .mode = ADC_INCREMENT,
+ },
+};
+
static const struct rockchip_tsadc_chip rk3368_tsadc_data = {
.chn_id[SENSOR_CPU] = 0, /* cpu sensor is channel 0 */
.chn_id[SENSOR_GPU] = 1, /* gpu sensor is channel 1 */
@@ -636,7 +762,7 @@ static const struct rockchip_tsadc_chip rk3399_tsadc_data = {
.tshut_polarity = TSHUT_LOW_ACTIVE, /* default TSHUT LOW ACTIVE */
.tshut_temp = 95000,
- .initialize = rk_tsadcv2_initialize,
+ .initialize = rk_tsadcv3_initialize,
.irq_ack = rk_tsadcv3_irq_ack,
.control = rk_tsadcv3_control,
.get_temp = rk_tsadcv2_get_temp,
@@ -661,6 +787,10 @@ static const struct of_device_id of_rockchip_thermal_match[] = {
.data = (void *)&rk3288_tsadc_data,
},
{
+ .compatible = "rockchip,rk3366-tsadc",
+ .data = (void *)&rk3366_tsadc_data,
+ },
+ {
.compatible = "rockchip,rk3368-tsadc",
.data = (void *)&rk3368_tsadc_data,
},
@@ -768,6 +898,11 @@ static int rockchip_configure_from_dt(struct device *dev,
return -EINVAL;
}
+ /* The tsadc wont to handle the error in here since some SoCs didn't
+ * need this property.
+ */
+ thermal->grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
+
return 0;
}
@@ -786,8 +921,8 @@ rockchip_thermal_register_sensor(struct platform_device *pdev,
sensor->thermal = thermal;
sensor->id = id;
- sensor->tzd = thermal_zone_of_sensor_register(&pdev->dev, id, sensor,
- &rockchip_of_thermal_ops);
+ sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev, id,
+ sensor, &rockchip_of_thermal_ops);
if (IS_ERR(sensor->tzd)) {
error = PTR_ERR(sensor->tzd);
dev_err(&pdev->dev, "failed to register sensor %d: %d\n",
@@ -815,7 +950,7 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
const struct of_device_id *match;
struct resource *res;
int irq;
- int i, j;
+ int i;
int error;
match = of_match_node(of_rockchip_thermal_match, np);
@@ -888,7 +1023,8 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
goto err_disable_pclk;
}
- thermal->chip->initialize(thermal->regs, thermal->tshut_polarity);
+ thermal->chip->initialize(thermal->grf, thermal->regs,
+ thermal->tshut_polarity);
for (i = 0; i < thermal->chip->chn_num; i++) {
error = rockchip_thermal_register_sensor(pdev, thermal,
@@ -898,9 +1034,6 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
dev_err(&pdev->dev,
"failed to register sensor[%d] : error = %d\n",
i, error);
- for (j = 0; j < i; j++)
- thermal_zone_of_sensor_unregister(&pdev->dev,
- thermal->sensors[j].tzd);
goto err_disable_pclk;
}
}
@@ -912,7 +1045,7 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
if (error) {
dev_err(&pdev->dev,
"failed to request tsadc irq: %d\n", error);
- goto err_unregister_sensor;
+ goto err_disable_pclk;
}
thermal->chip->control(thermal->regs, true);
@@ -924,11 +1057,6 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
return 0;
-err_unregister_sensor:
- while (i--)
- thermal_zone_of_sensor_unregister(&pdev->dev,
- thermal->sensors[i].tzd);
-
err_disable_pclk:
clk_disable_unprepare(thermal->pclk);
err_disable_clk:
@@ -946,7 +1074,6 @@ static int rockchip_thermal_remove(struct platform_device *pdev)
struct rockchip_thermal_sensor *sensor = &thermal->sensors[i];
rockchip_thermal_toggle_sensor(sensor, false);
- thermal_zone_of_sensor_unregister(&pdev->dev, sensor->tzd);
}
thermal->chip->control(thermal->regs, false);
@@ -988,12 +1115,15 @@ static int __maybe_unused rockchip_thermal_resume(struct device *dev)
return error;
error = clk_enable(thermal->pclk);
- if (error)
+ if (error) {
+ clk_disable(thermal->clk);
return error;
+ }
rockchip_thermal_reset_controller(thermal->reset);
- thermal->chip->initialize(thermal->regs, thermal->tshut_polarity);
+ thermal->chip->initialize(thermal->grf, thermal->regs,
+ thermal->tshut_polarity);
for (i = 0; i < thermal->chip->chn_num; i++) {
int id = thermal->sensors[i].id;
diff --git a/drivers/thermal/tango_thermal.c b/drivers/thermal/tango_thermal.c
new file mode 100644
index 000000000000..70e0d9f406e9
--- /dev/null
+++ b/drivers/thermal/tango_thermal.c
@@ -0,0 +1,109 @@
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/thermal.h>
+#include <linux/platform_device.h>
+
+/*
+ * According to a data sheet draft, "this temperature sensor uses a bandgap
+ * type of circuit to compare a voltage which has a negative temperature
+ * coefficient with a voltage that is proportional to absolute temperature.
+ * A resistor bank allows 41 different temperature thresholds to be selected
+ * and the logic output will then indicate whether the actual die temperature
+ * lies above or below the selected threshold."
+ */
+
+#define TEMPSI_CMD 0
+#define TEMPSI_RES 4
+#define TEMPSI_CFG 8
+
+#define CMD_OFF 0
+#define CMD_ON 1
+#define CMD_READ 2
+
+#define IDX_MIN 15
+#define IDX_MAX 40
+
+struct tango_thermal_priv {
+ void __iomem *base;
+ int thresh_idx;
+};
+
+static bool temp_above_thresh(void __iomem *base, int thresh_idx)
+{
+ writel(CMD_READ | thresh_idx << 8, base + TEMPSI_CMD);
+ usleep_range(10, 20);
+ writel(CMD_READ | thresh_idx << 8, base + TEMPSI_CMD);
+
+ return readl(base + TEMPSI_RES);
+}
+
+static int tango_get_temp(void *arg, int *res)
+{
+ struct tango_thermal_priv *priv = arg;
+ int idx = priv->thresh_idx;
+
+ if (temp_above_thresh(priv->base, idx)) {
+ /* Search upward by incrementing thresh_idx */
+ while (idx < IDX_MAX && temp_above_thresh(priv->base, ++idx))
+ cpu_relax();
+ idx = idx - 1; /* always return lower bound */
+ } else {
+ /* Search downward by decrementing thresh_idx */
+ while (idx > IDX_MIN && !temp_above_thresh(priv->base, --idx))
+ cpu_relax();
+ }
+
+ *res = (idx * 9 / 2 - 38) * 1000; /* millidegrees Celsius */
+ priv->thresh_idx = idx;
+
+ return 0;
+}
+
+static const struct thermal_zone_of_device_ops ops = {
+ .get_temp = tango_get_temp,
+};
+
+static int tango_thermal_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+ struct tango_thermal_priv *priv;
+ struct thermal_zone_device *tzdev;
+
+ priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ priv->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(priv->base))
+ return PTR_ERR(priv->base);
+
+ priv->thresh_idx = IDX_MIN;
+ writel(0, priv->base + TEMPSI_CFG);
+ writel(CMD_ON, priv->base + TEMPSI_CMD);
+
+ tzdev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, priv, &ops);
+ return PTR_ERR_OR_ZERO(tzdev);
+}
+
+static const struct of_device_id tango_sensor_ids[] = {
+ {
+ .compatible = "sigma,smp8758-thermal",
+ },
+ { /* sentinel */ }
+};
+
+static struct platform_driver tango_thermal_driver = {
+ .probe = tango_thermal_probe,
+ .driver = {
+ .name = "tango-thermal",
+ .of_match_table = tango_sensor_ids,
+ },
+};
+
+module_platform_driver(tango_thermal_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sigma Designs");
+MODULE_DESCRIPTION("Tango temperature sensor");
diff --git a/drivers/thermal/tegra/Kconfig b/drivers/thermal/tegra/Kconfig
new file mode 100644
index 000000000000..cec586ec7e4b
--- /dev/null
+++ b/drivers/thermal/tegra/Kconfig
@@ -0,0 +1,13 @@
+menu "NVIDIA Tegra thermal drivers"
+depends on ARCH_TEGRA
+
+config TEGRA_SOCTHERM
+ tristate "Tegra SOCTHERM thermal management"
+ help
+ Enable this option for integrated thermal management support on NVIDIA
+ Tegra systems-on-chip. The driver supports four thermal zones
+ (CPU, GPU, MEM, PLLX). Cooling devices can be bound to the thermal
+ zones to manage temperatures. This option is also required for the
+ emergency thermal reset (thermtrip) feature to function.
+
+endmenu
diff --git a/drivers/thermal/tegra/Makefile b/drivers/thermal/tegra/Makefile
new file mode 100644
index 000000000000..1ce1af2cf0f5
--- /dev/null
+++ b/drivers/thermal/tegra/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_TEGRA_SOCTHERM) += tegra-soctherm.o
+
+tegra-soctherm-y := soctherm.o soctherm-fuse.o
+tegra-soctherm-$(CONFIG_ARCH_TEGRA_124_SOC) += tegra124-soctherm.o
+tegra-soctherm-$(CONFIG_ARCH_TEGRA_132_SOC) += tegra132-soctherm.o
+tegra-soctherm-$(CONFIG_ARCH_TEGRA_210_SOC) += tegra210-soctherm.o
diff --git a/drivers/thermal/tegra/soctherm-fuse.c b/drivers/thermal/tegra/soctherm-fuse.c
new file mode 100644
index 000000000000..29963180c453
--- /dev/null
+++ b/drivers/thermal/tegra/soctherm-fuse.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <soc/tegra/fuse.h>
+
+#include "soctherm.h"
+
+#define NOMINAL_CALIB_FT 105
+#define NOMINAL_CALIB_CP 25
+
+#define FUSE_TSENSOR_CALIB_CP_TS_BASE_MASK 0x1fff
+#define FUSE_TSENSOR_CALIB_FT_TS_BASE_MASK (0x1fff << 13)
+#define FUSE_TSENSOR_CALIB_FT_TS_BASE_SHIFT 13
+
+#define FUSE_TSENSOR_COMMON 0x180
+
+/*
+ * Tegra210: Layout of bits in FUSE_TSENSOR_COMMON:
+ * 3 2 1 0
+ * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | BASE_FT | BASE_CP | SHFT_FT | SHIFT_CP |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Tegra12x, etc:
+ * In chips prior to Tegra210, this fuse was incorrectly sized as 26 bits,
+ * and didn't hold SHIFT_CP in [31:26]. Therefore these missing six bits
+ * were obtained via the FUSE_SPARE_REALIGNMENT_REG register [5:0].
+ *
+ * FUSE_TSENSOR_COMMON:
+ * 3 2 1 0
+ * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |-----------| SHFT_FT | BASE_FT | BASE_CP |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * FUSE_SPARE_REALIGNMENT_REG:
+ * 3 2 1 0
+ * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |---------------------------------------------------| SHIFT_CP |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+
+#define CALIB_COEFFICIENT 1000000LL
+
+/**
+ * div64_s64_precise() - wrapper for div64_s64()
+ * @a: the dividend
+ * @b: the divisor
+ *
+ * Implements division with fairly accurate rounding instead of truncation by
+ * shifting the dividend to the left by 16 so that the quotient has a
+ * much higher precision.
+ *
+ * Return: the quotient of a / b.
+ */
+static s64 div64_s64_precise(s64 a, s32 b)
+{
+ s64 r, al;
+
+ /* Scale up for increased precision division */
+ al = a << 16;
+
+ r = div64_s64(al * 2 + 1, 2 * b);
+ return r >> 16;
+}
+
+int tegra_calc_shared_calib(const struct tegra_soctherm_fuse *tfuse,
+ struct tsensor_shared_calib *shared)
+{
+ u32 val;
+ s32 shifted_cp, shifted_ft;
+ int err;
+
+ err = tegra_fuse_readl(FUSE_TSENSOR_COMMON, &val);
+ if (err)
+ return err;
+
+ shared->base_cp = (val & tfuse->fuse_base_cp_mask) >>
+ tfuse->fuse_base_cp_shift;
+ shared->base_ft = (val & tfuse->fuse_base_ft_mask) >>
+ tfuse->fuse_base_ft_shift;
+
+ shifted_ft = (val & tfuse->fuse_shift_ft_mask) >>
+ tfuse->fuse_shift_ft_shift;
+ shifted_ft = sign_extend32(shifted_ft, 4);
+
+ if (tfuse->fuse_spare_realignment) {
+ err = tegra_fuse_readl(tfuse->fuse_spare_realignment, &val);
+ if (err)
+ return err;
+ }
+
+ shifted_cp = sign_extend32(val, 5);
+
+ shared->actual_temp_cp = 2 * NOMINAL_CALIB_CP + shifted_cp;
+ shared->actual_temp_ft = 2 * NOMINAL_CALIB_FT + shifted_ft;
+
+ return 0;
+}
+
+int tegra_calc_tsensor_calib(const struct tegra_tsensor *sensor,
+ const struct tsensor_shared_calib *shared,
+ u32 *calibration)
+{
+ const struct tegra_tsensor_group *sensor_group;
+ u32 val, calib;
+ s32 actual_tsensor_ft, actual_tsensor_cp;
+ s32 delta_sens, delta_temp;
+ s32 mult, div;
+ s16 therma, thermb;
+ s64 temp;
+ int err;
+
+ sensor_group = sensor->group;
+
+ err = tegra_fuse_readl(sensor->calib_fuse_offset, &val);
+ if (err)
+ return err;
+
+ actual_tsensor_cp = (shared->base_cp * 64) + sign_extend32(val, 12);
+ val = (val & FUSE_TSENSOR_CALIB_FT_TS_BASE_MASK) >>
+ FUSE_TSENSOR_CALIB_FT_TS_BASE_SHIFT;
+ actual_tsensor_ft = (shared->base_ft * 32) + sign_extend32(val, 12);
+
+ delta_sens = actual_tsensor_ft - actual_tsensor_cp;
+ delta_temp = shared->actual_temp_ft - shared->actual_temp_cp;
+
+ mult = sensor_group->pdiv * sensor->config->tsample_ate;
+ div = sensor->config->tsample * sensor_group->pdiv_ate;
+
+ temp = (s64)delta_temp * (1LL << 13) * mult;
+ therma = div64_s64_precise(temp, (s64)delta_sens * div);
+
+ temp = ((s64)actual_tsensor_ft * shared->actual_temp_cp) -
+ ((s64)actual_tsensor_cp * shared->actual_temp_ft);
+ thermb = div64_s64_precise(temp, delta_sens);
+
+ temp = (s64)therma * sensor->fuse_corr_alpha;
+ therma = div64_s64_precise(temp, CALIB_COEFFICIENT);
+
+ temp = (s64)thermb * sensor->fuse_corr_alpha + sensor->fuse_corr_beta;
+ thermb = div64_s64_precise(temp, CALIB_COEFFICIENT);
+
+ calib = ((u16)therma << SENSOR_CONFIG2_THERMA_SHIFT) |
+ ((u16)thermb << SENSOR_CONFIG2_THERMB_SHIFT);
+
+ *calibration = calib;
+
+ return 0;
+}
+
+MODULE_AUTHOR("Wei Ni <wni@nvidia.com>");
+MODULE_DESCRIPTION("Tegra SOCTHERM fuse management");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c
new file mode 100644
index 000000000000..b8651726201e
--- /dev/null
+++ b/drivers/thermal/tegra/soctherm.c
@@ -0,0 +1,685 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Author:
+ * Mikko Perttunen <mperttunen@nvidia.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/thermal.h>
+
+#include <dt-bindings/thermal/tegra124-soctherm.h>
+
+#include "soctherm.h"
+
+#define SENSOR_CONFIG0 0
+#define SENSOR_CONFIG0_STOP BIT(0)
+#define SENSOR_CONFIG0_CPTR_OVER BIT(2)
+#define SENSOR_CONFIG0_OVER BIT(3)
+#define SENSOR_CONFIG0_TCALC_OVER BIT(4)
+#define SENSOR_CONFIG0_TALL_MASK (0xfffff << 8)
+#define SENSOR_CONFIG0_TALL_SHIFT 8
+
+#define SENSOR_CONFIG1 4
+#define SENSOR_CONFIG1_TSAMPLE_MASK 0x3ff
+#define SENSOR_CONFIG1_TSAMPLE_SHIFT 0
+#define SENSOR_CONFIG1_TIDDQ_EN_MASK (0x3f << 15)
+#define SENSOR_CONFIG1_TIDDQ_EN_SHIFT 15
+#define SENSOR_CONFIG1_TEN_COUNT_MASK (0x3f << 24)
+#define SENSOR_CONFIG1_TEN_COUNT_SHIFT 24
+#define SENSOR_CONFIG1_TEMP_ENABLE BIT(31)
+
+/*
+ * SENSOR_CONFIG2 is defined in soctherm.h
+ * because, it will be used by tegra_soctherm_fuse.c
+ */
+
+#define SENSOR_STATUS0 0xc
+#define SENSOR_STATUS0_VALID_MASK BIT(31)
+#define SENSOR_STATUS0_CAPTURE_MASK 0xffff
+
+#define SENSOR_STATUS1 0x10
+#define SENSOR_STATUS1_TEMP_VALID_MASK BIT(31)
+#define SENSOR_STATUS1_TEMP_MASK 0xffff
+
+#define READBACK_VALUE_MASK 0xff00
+#define READBACK_VALUE_SHIFT 8
+#define READBACK_ADD_HALF BIT(7)
+#define READBACK_NEGATE BIT(0)
+
+/* get val from register(r) mask bits(m) */
+#define REG_GET_MASK(r, m) (((r) & (m)) >> (ffs(m) - 1))
+/* set val(v) to mask bits(m) of register(r) */
+#define REG_SET_MASK(r, m, v) (((r) & ~(m)) | \
+ (((v) & (m >> (ffs(m) - 1))) << (ffs(m) - 1)))
+
+static const int min_low_temp = -127000;
+static const int max_high_temp = 127000;
+
+struct tegra_thermctl_zone {
+ void __iomem *reg;
+ struct device *dev;
+ struct thermal_zone_device *tz;
+ const struct tegra_tsensor_group *sg;
+};
+
+struct tegra_soctherm {
+ struct reset_control *reset;
+ struct clk *clock_tsensor;
+ struct clk *clock_soctherm;
+ void __iomem *regs;
+ struct thermal_zone_device **thermctl_tzs;
+
+ u32 *calib;
+ struct tegra_soctherm_soc *soc;
+
+ struct dentry *debugfs_dir;
+};
+
+static void enable_tsensor(struct tegra_soctherm *tegra, unsigned int i)
+{
+ const struct tegra_tsensor *sensor = &tegra->soc->tsensors[i];
+ void __iomem *base = tegra->regs + sensor->base;
+ unsigned int val;
+
+ val = sensor->config->tall << SENSOR_CONFIG0_TALL_SHIFT;
+ writel(val, base + SENSOR_CONFIG0);
+
+ val = (sensor->config->tsample - 1) << SENSOR_CONFIG1_TSAMPLE_SHIFT;
+ val |= sensor->config->tiddq_en << SENSOR_CONFIG1_TIDDQ_EN_SHIFT;
+ val |= sensor->config->ten_count << SENSOR_CONFIG1_TEN_COUNT_SHIFT;
+ val |= SENSOR_CONFIG1_TEMP_ENABLE;
+ writel(val, base + SENSOR_CONFIG1);
+
+ writel(tegra->calib[i], base + SENSOR_CONFIG2);
+}
+
+/*
+ * Translate from soctherm readback format to millicelsius.
+ * The soctherm readback format in bits is as follows:
+ * TTTTTTTT H______N
+ * where T's contain the temperature in Celsius,
+ * H denotes an addition of 0.5 Celsius and N denotes negation
+ * of the final value.
+ */
+static int translate_temp(u16 val)
+{
+ int t;
+
+ t = ((val & READBACK_VALUE_MASK) >> READBACK_VALUE_SHIFT) * 1000;
+ if (val & READBACK_ADD_HALF)
+ t += 500;
+ if (val & READBACK_NEGATE)
+ t *= -1;
+
+ return t;
+}
+
+static int tegra_thermctl_get_temp(void *data, int *out_temp)
+{
+ struct tegra_thermctl_zone *zone = data;
+ u32 val;
+
+ val = readl(zone->reg);
+ val = REG_GET_MASK(val, zone->sg->sensor_temp_mask);
+ *out_temp = translate_temp(val);
+
+ return 0;
+}
+
+static int
+thermtrip_program(struct device *dev, const struct tegra_tsensor_group *sg,
+ int trip_temp);
+
+static int tegra_thermctl_set_trip_temp(void *data, int trip, int temp)
+{
+ struct tegra_thermctl_zone *zone = data;
+ struct thermal_zone_device *tz = zone->tz;
+ const struct tegra_tsensor_group *sg = zone->sg;
+ struct device *dev = zone->dev;
+ enum thermal_trip_type type;
+ int ret;
+
+ if (!tz)
+ return -EINVAL;
+
+ ret = tz->ops->get_trip_type(tz, trip, &type);
+ if (ret)
+ return ret;
+
+ if (type != THERMAL_TRIP_CRITICAL)
+ return 0;
+
+ return thermtrip_program(dev, sg, temp);
+}
+
+static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = {
+ .get_temp = tegra_thermctl_get_temp,
+ .set_trip_temp = tegra_thermctl_set_trip_temp,
+};
+
+/**
+ * enforce_temp_range() - check and enforce temperature range [min, max]
+ * @trip_temp: the trip temperature to check
+ *
+ * Checks and enforces the permitted temperature range that SOC_THERM
+ * HW can support This is
+ * done while taking care of precision.
+ *
+ * Return: The precision adjusted capped temperature in millicelsius.
+ */
+static int enforce_temp_range(struct device *dev, int trip_temp)
+{
+ int temp;
+
+ temp = clamp_val(trip_temp, min_low_temp, max_high_temp);
+ if (temp != trip_temp)
+ dev_info(dev, "soctherm: trip temperature %d forced to %d\n",
+ trip_temp, temp);
+ return temp;
+}
+
+/**
+ * thermtrip_program() - Configures the hardware to shut down the
+ * system if a given sensor group reaches a given temperature
+ * @dev: ptr to the struct device for the SOC_THERM IP block
+ * @sg: pointer to the sensor group to set the thermtrip temperature for
+ * @trip_temp: the temperature in millicelsius to trigger the thermal trip at
+ *
+ * Sets the thermal trip threshold of the given sensor group to be the
+ * @trip_temp. If this threshold is crossed, the hardware will shut
+ * down.
+ *
+ * Note that, although @trip_temp is specified in millicelsius, the
+ * hardware is programmed in degrees Celsius.
+ *
+ * Return: 0 upon success, or %-EINVAL upon failure.
+ */
+static int thermtrip_program(struct device *dev,
+ const struct tegra_tsensor_group *sg,
+ int trip_temp)
+{
+ struct tegra_soctherm *ts = dev_get_drvdata(dev);
+ int temp;
+ u32 r;
+
+ if (!sg || !sg->thermtrip_threshold_mask)
+ return -EINVAL;
+
+ temp = enforce_temp_range(dev, trip_temp) / ts->soc->thresh_grain;
+
+ r = readl(ts->regs + THERMCTL_THERMTRIP_CTL);
+ r = REG_SET_MASK(r, sg->thermtrip_threshold_mask, temp);
+ r = REG_SET_MASK(r, sg->thermtrip_enable_mask, 1);
+ r = REG_SET_MASK(r, sg->thermtrip_any_en_mask, 0);
+ writel(r, ts->regs + THERMCTL_THERMTRIP_CTL);
+
+ return 0;
+}
+
+/**
+ * tegra_soctherm_set_hwtrips() - set HW trip point from DT data
+ * @dev: struct device * of the SOC_THERM instance
+ *
+ * Configure the SOC_THERM HW trip points, setting "THERMTRIP"
+ * trip points , using "critical" type trip_temp from thermal
+ * zone.
+ * After they have been configured, THERMTRIP will take action
+ * when the configured SoC thermal sensor group reaches a
+ * certain temperature.
+ *
+ * Return: 0 upon success, or a negative error code on failure.
+ * "Success" does not mean that trips was enabled; it could also
+ * mean that no node was found in DT.
+ * THERMTRIP has been enabled successfully when a message similar to
+ * this one appears on the serial console:
+ * "thermtrip: will shut down when sensor group XXX reaches YYYYYY mC"
+ */
+static int tegra_soctherm_set_hwtrips(struct device *dev,
+ const struct tegra_tsensor_group *sg,
+ struct thermal_zone_device *tz)
+{
+ int temperature;
+ int ret;
+
+ ret = tz->ops->get_crit_temp(tz, &temperature);
+ if (ret) {
+ dev_warn(dev, "thermtrip: %s: missing critical temperature\n",
+ sg->name);
+ return ret;
+ }
+
+ ret = thermtrip_program(dev, sg, temperature);
+ if (ret) {
+ dev_err(dev, "thermtrip: %s: error during enable\n",
+ sg->name);
+ return ret;
+ }
+
+ dev_info(dev,
+ "thermtrip: will shut down when %s reaches %d mC\n",
+ sg->name, temperature);
+
+ return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int regs_show(struct seq_file *s, void *data)
+{
+ struct platform_device *pdev = s->private;
+ struct tegra_soctherm *ts = platform_get_drvdata(pdev);
+ const struct tegra_tsensor *tsensors = ts->soc->tsensors;
+ const struct tegra_tsensor_group **ttgs = ts->soc->ttgs;
+ u32 r, state;
+ int i;
+
+ seq_puts(s, "-----TSENSE (convert HW)-----\n");
+
+ for (i = 0; i < ts->soc->num_tsensors; i++) {
+ r = readl(ts->regs + tsensors[i].base + SENSOR_CONFIG1);
+ state = REG_GET_MASK(r, SENSOR_CONFIG1_TEMP_ENABLE);
+
+ seq_printf(s, "%s: ", tsensors[i].name);
+ seq_printf(s, "En(%d) ", state);
+
+ if (!state) {
+ seq_puts(s, "\n");
+ continue;
+ }
+
+ state = REG_GET_MASK(r, SENSOR_CONFIG1_TIDDQ_EN_MASK);
+ seq_printf(s, "tiddq(%d) ", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG1_TEN_COUNT_MASK);
+ seq_printf(s, "ten_count(%d) ", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG1_TSAMPLE_MASK);
+ seq_printf(s, "tsample(%d) ", state + 1);
+
+ r = readl(ts->regs + tsensors[i].base + SENSOR_STATUS1);
+ state = REG_GET_MASK(r, SENSOR_STATUS1_TEMP_VALID_MASK);
+ seq_printf(s, "Temp(%d/", state);
+ state = REG_GET_MASK(r, SENSOR_STATUS1_TEMP_MASK);
+ seq_printf(s, "%d) ", translate_temp(state));
+
+ r = readl(ts->regs + tsensors[i].base + SENSOR_STATUS0);
+ state = REG_GET_MASK(r, SENSOR_STATUS0_VALID_MASK);
+ seq_printf(s, "Capture(%d/", state);
+ state = REG_GET_MASK(r, SENSOR_STATUS0_CAPTURE_MASK);
+ seq_printf(s, "%d) ", state);
+
+ r = readl(ts->regs + tsensors[i].base + SENSOR_CONFIG0);
+ state = REG_GET_MASK(r, SENSOR_CONFIG0_STOP);
+ seq_printf(s, "Stop(%d) ", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG0_TALL_MASK);
+ seq_printf(s, "Tall(%d) ", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG0_TCALC_OVER);
+ seq_printf(s, "Over(%d/", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG0_OVER);
+ seq_printf(s, "%d/", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG0_CPTR_OVER);
+ seq_printf(s, "%d) ", state);
+
+ r = readl(ts->regs + tsensors[i].base + SENSOR_CONFIG2);
+ state = REG_GET_MASK(r, SENSOR_CONFIG2_THERMA_MASK);
+ seq_printf(s, "Therm_A/B(%d/", state);
+ state = REG_GET_MASK(r, SENSOR_CONFIG2_THERMB_MASK);
+ seq_printf(s, "%d)\n", (s16)state);
+ }
+
+ r = readl(ts->regs + SENSOR_PDIV);
+ seq_printf(s, "PDIV: 0x%x\n", r);
+
+ r = readl(ts->regs + SENSOR_HOTSPOT_OFF);
+ seq_printf(s, "HOTSPOT: 0x%x\n", r);
+
+ seq_puts(s, "\n");
+ seq_puts(s, "-----SOC_THERM-----\n");
+
+ r = readl(ts->regs + SENSOR_TEMP1);
+ state = REG_GET_MASK(r, SENSOR_TEMP1_CPU_TEMP_MASK);
+ seq_printf(s, "Temperatures: CPU(%d) ", translate_temp(state));
+ state = REG_GET_MASK(r, SENSOR_TEMP1_GPU_TEMP_MASK);
+ seq_printf(s, " GPU(%d) ", translate_temp(state));
+ r = readl(ts->regs + SENSOR_TEMP2);
+ state = REG_GET_MASK(r, SENSOR_TEMP2_PLLX_TEMP_MASK);
+ seq_printf(s, " PLLX(%d) ", translate_temp(state));
+ state = REG_GET_MASK(r, SENSOR_TEMP2_MEM_TEMP_MASK);
+ seq_printf(s, " MEM(%d)\n", translate_temp(state));
+
+ r = readl(ts->regs + THERMCTL_THERMTRIP_CTL);
+ state = REG_GET_MASK(r, ttgs[0]->thermtrip_any_en_mask);
+ seq_printf(s, "Thermtrip Any En(%d)\n", state);
+ for (i = 0; i < ts->soc->num_ttgs; i++) {
+ state = REG_GET_MASK(r, ttgs[i]->thermtrip_enable_mask);
+ seq_printf(s, " %s En(%d) ", ttgs[i]->name, state);
+ state = REG_GET_MASK(r, ttgs[i]->thermtrip_threshold_mask);
+ state *= ts->soc->thresh_grain;
+ seq_printf(s, "Thresh(%d)\n", state);
+ }
+
+ return 0;
+}
+
+static int regs_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, regs_show, inode->i_private);
+}
+
+static const struct file_operations regs_fops = {
+ .open = regs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void soctherm_debug_init(struct platform_device *pdev)
+{
+ struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
+ struct dentry *root, *file;
+
+ root = debugfs_create_dir("soctherm", NULL);
+ if (!root) {
+ dev_err(&pdev->dev, "failed to create debugfs directory\n");
+ return;
+ }
+
+ tegra->debugfs_dir = root;
+
+ file = debugfs_create_file("reg_contents", 0644, root,
+ pdev, &regs_fops);
+ if (!file) {
+ dev_err(&pdev->dev, "failed to create debugfs file\n");
+ debugfs_remove_recursive(tegra->debugfs_dir);
+ tegra->debugfs_dir = NULL;
+ }
+}
+#else
+static inline void soctherm_debug_init(struct platform_device *pdev) {}
+#endif
+
+static int soctherm_clk_enable(struct platform_device *pdev, bool enable)
+{
+ struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
+ int err;
+
+ if (!tegra->clock_soctherm || !tegra->clock_tsensor)
+ return -EINVAL;
+
+ reset_control_assert(tegra->reset);
+
+ if (enable) {
+ err = clk_prepare_enable(tegra->clock_soctherm);
+ if (err) {
+ reset_control_deassert(tegra->reset);
+ return err;
+ }
+
+ err = clk_prepare_enable(tegra->clock_tsensor);
+ if (err) {
+ clk_disable_unprepare(tegra->clock_soctherm);
+ reset_control_deassert(tegra->reset);
+ return err;
+ }
+ } else {
+ clk_disable_unprepare(tegra->clock_tsensor);
+ clk_disable_unprepare(tegra->clock_soctherm);
+ }
+
+ reset_control_deassert(tegra->reset);
+
+ return 0;
+}
+
+static void soctherm_init(struct platform_device *pdev)
+{
+ struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
+ const struct tegra_tsensor_group **ttgs = tegra->soc->ttgs;
+ int i;
+ u32 pdiv, hotspot;
+
+ /* Initialize raw sensors */
+ for (i = 0; i < tegra->soc->num_tsensors; ++i)
+ enable_tsensor(tegra, i);
+
+ /* program pdiv and hotspot offsets per THERM */
+ pdiv = readl(tegra->regs + SENSOR_PDIV);
+ hotspot = readl(tegra->regs + SENSOR_HOTSPOT_OFF);
+ for (i = 0; i < tegra->soc->num_ttgs; ++i) {
+ pdiv = REG_SET_MASK(pdiv, ttgs[i]->pdiv_mask,
+ ttgs[i]->pdiv);
+ /* hotspot offset from PLLX, doesn't need to configure PLLX */
+ if (ttgs[i]->id == TEGRA124_SOCTHERM_SENSOR_PLLX)
+ continue;
+ hotspot = REG_SET_MASK(hotspot,
+ ttgs[i]->pllx_hotspot_mask,
+ ttgs[i]->pllx_hotspot_diff);
+ }
+ writel(pdiv, tegra->regs + SENSOR_PDIV);
+ writel(hotspot, tegra->regs + SENSOR_HOTSPOT_OFF);
+}
+
+static const struct of_device_id tegra_soctherm_of_match[] = {
+#ifdef CONFIG_ARCH_TEGRA_124_SOC
+ {
+ .compatible = "nvidia,tegra124-soctherm",
+ .data = &tegra124_soctherm,
+ },
+#endif
+#ifdef CONFIG_ARCH_TEGRA_132_SOC
+ {
+ .compatible = "nvidia,tegra132-soctherm",
+ .data = &tegra132_soctherm,
+ },
+#endif
+#ifdef CONFIG_ARCH_TEGRA_210_SOC
+ {
+ .compatible = "nvidia,tegra210-soctherm",
+ .data = &tegra210_soctherm,
+ },
+#endif
+ { },
+};
+MODULE_DEVICE_TABLE(of, tegra_soctherm_of_match);
+
+static int tegra_soctherm_probe(struct platform_device *pdev)
+{
+ const struct of_device_id *match;
+ struct tegra_soctherm *tegra;
+ struct thermal_zone_device *z;
+ struct tsensor_shared_calib shared_calib;
+ struct resource *res;
+ struct tegra_soctherm_soc *soc;
+ unsigned int i;
+ int err;
+
+ match = of_match_node(tegra_soctherm_of_match, pdev->dev.of_node);
+ if (!match)
+ return -ENODEV;
+
+ soc = (struct tegra_soctherm_soc *)match->data;
+ if (soc->num_ttgs > TEGRA124_SOCTHERM_SENSOR_NUM)
+ return -EINVAL;
+
+ tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
+ if (!tegra)
+ return -ENOMEM;
+
+ dev_set_drvdata(&pdev->dev, tegra);
+
+ tegra->soc = soc;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ tegra->regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(tegra->regs))
+ return PTR_ERR(tegra->regs);
+
+ tegra->reset = devm_reset_control_get(&pdev->dev, "soctherm");
+ if (IS_ERR(tegra->reset)) {
+ dev_err(&pdev->dev, "can't get soctherm reset\n");
+ return PTR_ERR(tegra->reset);
+ }
+
+ tegra->clock_tsensor = devm_clk_get(&pdev->dev, "tsensor");
+ if (IS_ERR(tegra->clock_tsensor)) {
+ dev_err(&pdev->dev, "can't get tsensor clock\n");
+ return PTR_ERR(tegra->clock_tsensor);
+ }
+
+ tegra->clock_soctherm = devm_clk_get(&pdev->dev, "soctherm");
+ if (IS_ERR(tegra->clock_soctherm)) {
+ dev_err(&pdev->dev, "can't get soctherm clock\n");
+ return PTR_ERR(tegra->clock_soctherm);
+ }
+
+ tegra->calib = devm_kzalloc(&pdev->dev,
+ sizeof(u32) * soc->num_tsensors,
+ GFP_KERNEL);
+ if (!tegra->calib)
+ return -ENOMEM;
+
+ /* calculate shared calibration data */
+ err = tegra_calc_shared_calib(soc->tfuse, &shared_calib);
+ if (err)
+ return err;
+
+ /* calculate tsensor calibaration data */
+ for (i = 0; i < soc->num_tsensors; ++i) {
+ err = tegra_calc_tsensor_calib(&soc->tsensors[i],
+ &shared_calib,
+ &tegra->calib[i]);
+ if (err)
+ return err;
+ }
+
+ tegra->thermctl_tzs = devm_kzalloc(&pdev->dev,
+ sizeof(*z) * soc->num_ttgs,
+ GFP_KERNEL);
+ if (!tegra->thermctl_tzs)
+ return -ENOMEM;
+
+ err = soctherm_clk_enable(pdev, true);
+ if (err)
+ return err;
+
+ soctherm_init(pdev);
+
+ for (i = 0; i < soc->num_ttgs; ++i) {
+ struct tegra_thermctl_zone *zone =
+ devm_kzalloc(&pdev->dev, sizeof(*zone), GFP_KERNEL);
+ if (!zone) {
+ err = -ENOMEM;
+ goto disable_clocks;
+ }
+
+ zone->reg = tegra->regs + soc->ttgs[i]->sensor_temp_offset;
+ zone->dev = &pdev->dev;
+ zone->sg = soc->ttgs[i];
+
+ z = devm_thermal_zone_of_sensor_register(&pdev->dev,
+ soc->ttgs[i]->id, zone,
+ &tegra_of_thermal_ops);
+ if (IS_ERR(z)) {
+ err = PTR_ERR(z);
+ dev_err(&pdev->dev, "failed to register sensor: %d\n",
+ err);
+ goto disable_clocks;
+ }
+
+ zone->tz = z;
+ tegra->thermctl_tzs[soc->ttgs[i]->id] = z;
+
+ /* Configure hw trip points */
+ tegra_soctherm_set_hwtrips(&pdev->dev, soc->ttgs[i], z);
+ }
+
+ soctherm_debug_init(pdev);
+
+ return 0;
+
+disable_clocks:
+ soctherm_clk_enable(pdev, false);
+
+ return err;
+}
+
+static int tegra_soctherm_remove(struct platform_device *pdev)
+{
+ struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
+
+ debugfs_remove_recursive(tegra->debugfs_dir);
+
+ soctherm_clk_enable(pdev, false);
+
+ return 0;
+}
+
+static int __maybe_unused soctherm_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+
+ soctherm_clk_enable(pdev, false);
+
+ return 0;
+}
+
+static int __maybe_unused soctherm_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
+ struct tegra_soctherm_soc *soc = tegra->soc;
+ int err, i;
+
+ err = soctherm_clk_enable(pdev, true);
+ if (err) {
+ dev_err(&pdev->dev,
+ "Resume failed: enable clocks failed\n");
+ return err;
+ }
+
+ soctherm_init(pdev);
+
+ for (i = 0; i < soc->num_ttgs; ++i) {
+ struct thermal_zone_device *tz;
+
+ tz = tegra->thermctl_tzs[soc->ttgs[i]->id];
+ tegra_soctherm_set_hwtrips(dev, soc->ttgs[i], tz);
+ }
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(tegra_soctherm_pm, soctherm_suspend, soctherm_resume);
+
+static struct platform_driver tegra_soctherm_driver = {
+ .probe = tegra_soctherm_probe,
+ .remove = tegra_soctherm_remove,
+ .driver = {
+ .name = "tegra_soctherm",
+ .pm = &tegra_soctherm_pm,
+ .of_match_table = tegra_soctherm_of_match,
+ },
+};
+module_platform_driver(tegra_soctherm_driver);
+
+MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra SOCTHERM thermal management driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/tegra/soctherm.h b/drivers/thermal/tegra/soctherm.h
new file mode 100644
index 000000000000..28e18ec4b4c3
--- /dev/null
+++ b/drivers/thermal/tegra/soctherm.h
@@ -0,0 +1,127 @@
+/*
+ * Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DRIVERS_THERMAL_TEGRA_SOCTHERM_H
+#define __DRIVERS_THERMAL_TEGRA_SOCTHERM_H
+
+#define SENSOR_CONFIG2 8
+#define SENSOR_CONFIG2_THERMA_MASK (0xffff << 16)
+#define SENSOR_CONFIG2_THERMA_SHIFT 16
+#define SENSOR_CONFIG2_THERMB_MASK 0xffff
+#define SENSOR_CONFIG2_THERMB_SHIFT 0
+
+#define THERMCTL_THERMTRIP_CTL 0x80
+/* BITs are defined in device file */
+
+#define SENSOR_PDIV 0x1c0
+#define SENSOR_PDIV_CPU_MASK (0xf << 12)
+#define SENSOR_PDIV_GPU_MASK (0xf << 8)
+#define SENSOR_PDIV_MEM_MASK (0xf << 4)
+#define SENSOR_PDIV_PLLX_MASK (0xf << 0)
+
+#define SENSOR_HOTSPOT_OFF 0x1c4
+#define SENSOR_HOTSPOT_CPU_MASK (0xff << 16)
+#define SENSOR_HOTSPOT_GPU_MASK (0xff << 8)
+#define SENSOR_HOTSPOT_MEM_MASK (0xff << 0)
+
+#define SENSOR_TEMP1 0x1c8
+#define SENSOR_TEMP1_CPU_TEMP_MASK (0xffff << 16)
+#define SENSOR_TEMP1_GPU_TEMP_MASK 0xffff
+#define SENSOR_TEMP2 0x1cc
+#define SENSOR_TEMP2_MEM_TEMP_MASK (0xffff << 16)
+#define SENSOR_TEMP2_PLLX_TEMP_MASK 0xffff
+
+/**
+ * struct tegra_tsensor_group - SOC_THERM sensor group data
+ * @name: short name of the temperature sensor group
+ * @id: numeric ID of the temperature sensor group
+ * @sensor_temp_offset: offset of the SENSOR_TEMP* register
+ * @sensor_temp_mask: bit mask for this sensor group in SENSOR_TEMP* register
+ * @pdiv: the sensor count post-divider to use during runtime
+ * @pdiv_ate: the sensor count post-divider used during automated test
+ * @pdiv_mask: register bitfield mask for the PDIV field for this sensor
+ * @pllx_hotspot_diff: hotspot offset from the PLLX sensor, must be 0 for
+ PLLX sensor group
+ * @pllx_hotspot_mask: register bitfield mask for the HOTSPOT field
+ */
+struct tegra_tsensor_group {
+ const char *name;
+ u8 id;
+ u16 sensor_temp_offset;
+ u32 sensor_temp_mask;
+ u32 pdiv, pdiv_ate, pdiv_mask;
+ u32 pllx_hotspot_diff, pllx_hotspot_mask;
+ u32 thermtrip_enable_mask;
+ u32 thermtrip_any_en_mask;
+ u32 thermtrip_threshold_mask;
+};
+
+struct tegra_tsensor_configuration {
+ u32 tall, tiddq_en, ten_count, pdiv, pdiv_ate, tsample, tsample_ate;
+};
+
+struct tegra_tsensor {
+ const char *name;
+ const u32 base;
+ const struct tegra_tsensor_configuration *config;
+ const u32 calib_fuse_offset;
+ /*
+ * Correction values used to modify values read from
+ * calibration fuses
+ */
+ const s32 fuse_corr_alpha, fuse_corr_beta;
+ const struct tegra_tsensor_group *group;
+};
+
+struct tegra_soctherm_fuse {
+ u32 fuse_base_cp_mask, fuse_base_cp_shift;
+ u32 fuse_base_ft_mask, fuse_base_ft_shift;
+ u32 fuse_shift_ft_mask, fuse_shift_ft_shift;
+ u32 fuse_spare_realignment;
+};
+
+struct tsensor_shared_calib {
+ u32 base_cp, base_ft;
+ u32 actual_temp_cp, actual_temp_ft;
+};
+
+struct tegra_soctherm_soc {
+ const struct tegra_tsensor *tsensors;
+ const unsigned int num_tsensors;
+ const struct tegra_tsensor_group **ttgs;
+ const unsigned int num_ttgs;
+ const struct tegra_soctherm_fuse *tfuse;
+ const int thresh_grain;
+};
+
+int tegra_calc_shared_calib(const struct tegra_soctherm_fuse *tfuse,
+ struct tsensor_shared_calib *shared);
+int tegra_calc_tsensor_calib(const struct tegra_tsensor *sensor,
+ const struct tsensor_shared_calib *shared,
+ u32 *calib);
+
+#ifdef CONFIG_ARCH_TEGRA_124_SOC
+extern const struct tegra_soctherm_soc tegra124_soctherm;
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_132_SOC
+extern const struct tegra_soctherm_soc tegra132_soctherm;
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_210_SOC
+extern const struct tegra_soctherm_soc tegra210_soctherm;
+#endif
+
+#endif
+
diff --git a/drivers/thermal/tegra/tegra124-soctherm.c b/drivers/thermal/tegra/tegra124-soctherm.c
new file mode 100644
index 000000000000..beb9d36b9c8a
--- /dev/null
+++ b/drivers/thermal/tegra/tegra124-soctherm.c
@@ -0,0 +1,196 @@
+/*
+ * Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <dt-bindings/thermal/tegra124-soctherm.h>
+
+#include "soctherm.h"
+
+#define TEGRA124_THERMTRIP_ANY_EN_MASK (0x1 << 28)
+#define TEGRA124_THERMTRIP_MEM_EN_MASK (0x1 << 27)
+#define TEGRA124_THERMTRIP_GPU_EN_MASK (0x1 << 26)
+#define TEGRA124_THERMTRIP_CPU_EN_MASK (0x1 << 25)
+#define TEGRA124_THERMTRIP_TSENSE_EN_MASK (0x1 << 24)
+#define TEGRA124_THERMTRIP_GPUMEM_THRESH_MASK (0xff << 16)
+#define TEGRA124_THERMTRIP_CPU_THRESH_MASK (0xff << 8)
+#define TEGRA124_THERMTRIP_TSENSE_THRESH_MASK 0xff
+
+#define TEGRA124_THRESH_GRAIN 1000
+
+static const struct tegra_tsensor_configuration tegra124_tsensor_config = {
+ .tall = 16300,
+ .tiddq_en = 1,
+ .ten_count = 1,
+ .tsample = 120,
+ .tsample_ate = 480,
+};
+
+static const struct tegra_tsensor_group tegra124_tsensor_group_cpu = {
+ .id = TEGRA124_SOCTHERM_SENSOR_CPU,
+ .name = "cpu",
+ .sensor_temp_offset = SENSOR_TEMP1,
+ .sensor_temp_mask = SENSOR_TEMP1_CPU_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_CPU_MASK,
+ .pllx_hotspot_diff = 10,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_CPU_MASK,
+ .thermtrip_any_en_mask = TEGRA124_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA124_THERMTRIP_CPU_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA124_THERMTRIP_CPU_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra124_tsensor_group_gpu = {
+ .id = TEGRA124_SOCTHERM_SENSOR_GPU,
+ .name = "gpu",
+ .sensor_temp_offset = SENSOR_TEMP1,
+ .sensor_temp_mask = SENSOR_TEMP1_GPU_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_GPU_MASK,
+ .pllx_hotspot_diff = 5,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_GPU_MASK,
+ .thermtrip_any_en_mask = TEGRA124_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA124_THERMTRIP_GPU_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA124_THERMTRIP_GPUMEM_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra124_tsensor_group_pll = {
+ .id = TEGRA124_SOCTHERM_SENSOR_PLLX,
+ .name = "pll",
+ .sensor_temp_offset = SENSOR_TEMP2,
+ .sensor_temp_mask = SENSOR_TEMP2_PLLX_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_PLLX_MASK,
+ .thermtrip_any_en_mask = TEGRA124_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA124_THERMTRIP_TSENSE_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA124_THERMTRIP_TSENSE_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra124_tsensor_group_mem = {
+ .id = TEGRA124_SOCTHERM_SENSOR_MEM,
+ .name = "mem",
+ .sensor_temp_offset = SENSOR_TEMP2,
+ .sensor_temp_mask = SENSOR_TEMP2_MEM_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_MEM_MASK,
+ .pllx_hotspot_diff = 0,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_MEM_MASK,
+ .thermtrip_any_en_mask = TEGRA124_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA124_THERMTRIP_MEM_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA124_THERMTRIP_GPUMEM_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group *tegra124_tsensor_groups[] = {
+ &tegra124_tsensor_group_cpu,
+ &tegra124_tsensor_group_gpu,
+ &tegra124_tsensor_group_pll,
+ &tegra124_tsensor_group_mem,
+};
+
+static const struct tegra_tsensor tegra124_tsensors[] = {
+ {
+ .name = "cpu0",
+ .base = 0xc0,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x098,
+ .fuse_corr_alpha = 1135400,
+ .fuse_corr_beta = -6266900,
+ .group = &tegra124_tsensor_group_cpu,
+ }, {
+ .name = "cpu1",
+ .base = 0xe0,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x084,
+ .fuse_corr_alpha = 1122220,
+ .fuse_corr_beta = -5700700,
+ .group = &tegra124_tsensor_group_cpu,
+ }, {
+ .name = "cpu2",
+ .base = 0x100,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x088,
+ .fuse_corr_alpha = 1127000,
+ .fuse_corr_beta = -6768200,
+ .group = &tegra124_tsensor_group_cpu,
+ }, {
+ .name = "cpu3",
+ .base = 0x120,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x12c,
+ .fuse_corr_alpha = 1110900,
+ .fuse_corr_beta = -6232000,
+ .group = &tegra124_tsensor_group_cpu,
+ }, {
+ .name = "mem0",
+ .base = 0x140,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x158,
+ .fuse_corr_alpha = 1122300,
+ .fuse_corr_beta = -5936400,
+ .group = &tegra124_tsensor_group_mem,
+ }, {
+ .name = "mem1",
+ .base = 0x160,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x15c,
+ .fuse_corr_alpha = 1145700,
+ .fuse_corr_beta = -7124600,
+ .group = &tegra124_tsensor_group_mem,
+ }, {
+ .name = "gpu",
+ .base = 0x180,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x154,
+ .fuse_corr_alpha = 1120100,
+ .fuse_corr_beta = -6000500,
+ .group = &tegra124_tsensor_group_gpu,
+ }, {
+ .name = "pllx",
+ .base = 0x1a0,
+ .config = &tegra124_tsensor_config,
+ .calib_fuse_offset = 0x160,
+ .fuse_corr_alpha = 1106500,
+ .fuse_corr_beta = -6729300,
+ .group = &tegra124_tsensor_group_pll,
+ },
+};
+
+/*
+ * Mask/shift bits in FUSE_TSENSOR_COMMON and
+ * FUSE_TSENSOR_COMMON, which are described in
+ * tegra_soctherm_fuse.c
+ */
+static const struct tegra_soctherm_fuse tegra124_soctherm_fuse = {
+ .fuse_base_cp_mask = 0x3ff,
+ .fuse_base_cp_shift = 0,
+ .fuse_base_ft_mask = 0x7ff << 10,
+ .fuse_base_ft_shift = 10,
+ .fuse_shift_ft_mask = 0x1f << 21,
+ .fuse_shift_ft_shift = 21,
+ .fuse_spare_realignment = 0x1fc,
+};
+
+const struct tegra_soctherm_soc tegra124_soctherm = {
+ .tsensors = tegra124_tsensors,
+ .num_tsensors = ARRAY_SIZE(tegra124_tsensors),
+ .ttgs = tegra124_tsensor_groups,
+ .num_ttgs = ARRAY_SIZE(tegra124_tsensor_groups),
+ .tfuse = &tegra124_soctherm_fuse,
+ .thresh_grain = TEGRA124_THRESH_GRAIN,
+};
diff --git a/drivers/thermal/tegra/tegra132-soctherm.c b/drivers/thermal/tegra/tegra132-soctherm.c
new file mode 100644
index 000000000000..e2aa84e1b307
--- /dev/null
+++ b/drivers/thermal/tegra/tegra132-soctherm.c
@@ -0,0 +1,196 @@
+/*
+ * Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <dt-bindings/thermal/tegra124-soctherm.h>
+
+#include "soctherm.h"
+
+#define TEGRA132_THERMTRIP_ANY_EN_MASK (0x1 << 28)
+#define TEGRA132_THERMTRIP_MEM_EN_MASK (0x1 << 27)
+#define TEGRA132_THERMTRIP_GPU_EN_MASK (0x1 << 26)
+#define TEGRA132_THERMTRIP_CPU_EN_MASK (0x1 << 25)
+#define TEGRA132_THERMTRIP_TSENSE_EN_MASK (0x1 << 24)
+#define TEGRA132_THERMTRIP_GPUMEM_THRESH_MASK (0xff << 16)
+#define TEGRA132_THERMTRIP_CPU_THRESH_MASK (0xff << 8)
+#define TEGRA132_THERMTRIP_TSENSE_THRESH_MASK 0xff
+
+#define TEGRA132_THRESH_GRAIN 1000
+
+static const struct tegra_tsensor_configuration tegra132_tsensor_config = {
+ .tall = 16300,
+ .tiddq_en = 1,
+ .ten_count = 1,
+ .tsample = 120,
+ .tsample_ate = 480,
+};
+
+static const struct tegra_tsensor_group tegra132_tsensor_group_cpu = {
+ .id = TEGRA124_SOCTHERM_SENSOR_CPU,
+ .name = "cpu",
+ .sensor_temp_offset = SENSOR_TEMP1,
+ .sensor_temp_mask = SENSOR_TEMP1_CPU_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_CPU_MASK,
+ .pllx_hotspot_diff = 10,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_CPU_MASK,
+ .thermtrip_any_en_mask = TEGRA132_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA132_THERMTRIP_CPU_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA132_THERMTRIP_CPU_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra132_tsensor_group_gpu = {
+ .id = TEGRA124_SOCTHERM_SENSOR_GPU,
+ .name = "gpu",
+ .sensor_temp_offset = SENSOR_TEMP1,
+ .sensor_temp_mask = SENSOR_TEMP1_GPU_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_GPU_MASK,
+ .pllx_hotspot_diff = 5,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_GPU_MASK,
+ .thermtrip_any_en_mask = TEGRA132_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA132_THERMTRIP_GPU_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA132_THERMTRIP_GPUMEM_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra132_tsensor_group_pll = {
+ .id = TEGRA124_SOCTHERM_SENSOR_PLLX,
+ .name = "pll",
+ .sensor_temp_offset = SENSOR_TEMP2,
+ .sensor_temp_mask = SENSOR_TEMP2_PLLX_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_PLLX_MASK,
+ .thermtrip_any_en_mask = TEGRA132_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA132_THERMTRIP_TSENSE_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA132_THERMTRIP_TSENSE_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra132_tsensor_group_mem = {
+ .id = TEGRA124_SOCTHERM_SENSOR_MEM,
+ .name = "mem",
+ .sensor_temp_offset = SENSOR_TEMP2,
+ .sensor_temp_mask = SENSOR_TEMP2_MEM_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_MEM_MASK,
+ .pllx_hotspot_diff = 0,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_MEM_MASK,
+ .thermtrip_any_en_mask = TEGRA132_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA132_THERMTRIP_MEM_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA132_THERMTRIP_GPUMEM_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group *tegra132_tsensor_groups[] = {
+ &tegra132_tsensor_group_cpu,
+ &tegra132_tsensor_group_gpu,
+ &tegra132_tsensor_group_pll,
+ &tegra132_tsensor_group_mem,
+};
+
+static struct tegra_tsensor tegra132_tsensors[] = {
+ {
+ .name = "cpu0",
+ .base = 0xc0,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x098,
+ .fuse_corr_alpha = 1126600,
+ .fuse_corr_beta = -9433500,
+ .group = &tegra132_tsensor_group_cpu,
+ }, {
+ .name = "cpu1",
+ .base = 0xe0,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x084,
+ .fuse_corr_alpha = 1110800,
+ .fuse_corr_beta = -7383000,
+ .group = &tegra132_tsensor_group_cpu,
+ }, {
+ .name = "cpu2",
+ .base = 0x100,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x088,
+ .fuse_corr_alpha = 1113800,
+ .fuse_corr_beta = -6215200,
+ .group = &tegra132_tsensor_group_cpu,
+ }, {
+ .name = "cpu3",
+ .base = 0x120,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x12c,
+ .fuse_corr_alpha = 1129600,
+ .fuse_corr_beta = -8196100,
+ .group = &tegra132_tsensor_group_cpu,
+ }, {
+ .name = "mem0",
+ .base = 0x140,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x158,
+ .fuse_corr_alpha = 1132900,
+ .fuse_corr_beta = -6755300,
+ .group = &tegra132_tsensor_group_mem,
+ }, {
+ .name = "mem1",
+ .base = 0x160,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x15c,
+ .fuse_corr_alpha = 1142300,
+ .fuse_corr_beta = -7374200,
+ .group = &tegra132_tsensor_group_mem,
+ }, {
+ .name = "gpu",
+ .base = 0x180,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x154,
+ .fuse_corr_alpha = 1125100,
+ .fuse_corr_beta = -6350400,
+ .group = &tegra132_tsensor_group_gpu,
+ }, {
+ .name = "pllx",
+ .base = 0x1a0,
+ .config = &tegra132_tsensor_config,
+ .calib_fuse_offset = 0x160,
+ .fuse_corr_alpha = 1118100,
+ .fuse_corr_beta = -8208800,
+ .group = &tegra132_tsensor_group_pll,
+ },
+};
+
+/*
+ * Mask/shift bits in FUSE_TSENSOR_COMMON and
+ * FUSE_TSENSOR_COMMON, which are described in
+ * tegra_soctherm_fuse.c
+ */
+static const struct tegra_soctherm_fuse tegra132_soctherm_fuse = {
+ .fuse_base_cp_mask = 0x3ff,
+ .fuse_base_cp_shift = 0,
+ .fuse_base_ft_mask = 0x7ff << 10,
+ .fuse_base_ft_shift = 10,
+ .fuse_shift_ft_mask = 0x1f << 21,
+ .fuse_shift_ft_shift = 21,
+ .fuse_spare_realignment = 0x1fc,
+};
+
+const struct tegra_soctherm_soc tegra132_soctherm = {
+ .tsensors = tegra132_tsensors,
+ .num_tsensors = ARRAY_SIZE(tegra132_tsensors),
+ .ttgs = tegra132_tsensor_groups,
+ .num_ttgs = ARRAY_SIZE(tegra132_tsensor_groups),
+ .tfuse = &tegra132_soctherm_fuse,
+ .thresh_grain = TEGRA132_THRESH_GRAIN,
+};
diff --git a/drivers/thermal/tegra/tegra210-soctherm.c b/drivers/thermal/tegra/tegra210-soctherm.c
new file mode 100644
index 000000000000..19cc0ab66f0e
--- /dev/null
+++ b/drivers/thermal/tegra/tegra210-soctherm.c
@@ -0,0 +1,197 @@
+/*
+ * Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <soc/tegra/fuse.h>
+
+#include <dt-bindings/thermal/tegra124-soctherm.h>
+
+#include "soctherm.h"
+
+#define TEGRA210_THERMTRIP_ANY_EN_MASK (0x1 << 31)
+#define TEGRA210_THERMTRIP_MEM_EN_MASK (0x1 << 30)
+#define TEGRA210_THERMTRIP_GPU_EN_MASK (0x1 << 29)
+#define TEGRA210_THERMTRIP_CPU_EN_MASK (0x1 << 28)
+#define TEGRA210_THERMTRIP_TSENSE_EN_MASK (0x1 << 27)
+#define TEGRA210_THERMTRIP_GPUMEM_THRESH_MASK (0x1ff << 18)
+#define TEGRA210_THERMTRIP_CPU_THRESH_MASK (0x1ff << 9)
+#define TEGRA210_THERMTRIP_TSENSE_THRESH_MASK 0x1ff
+
+#define TEGRA210_THRESH_GRAIN 500
+
+static const struct tegra_tsensor_configuration tegra210_tsensor_config = {
+ .tall = 16300,
+ .tiddq_en = 1,
+ .ten_count = 1,
+ .tsample = 120,
+ .tsample_ate = 480,
+};
+
+static const struct tegra_tsensor_group tegra210_tsensor_group_cpu = {
+ .id = TEGRA124_SOCTHERM_SENSOR_CPU,
+ .name = "cpu",
+ .sensor_temp_offset = SENSOR_TEMP1,
+ .sensor_temp_mask = SENSOR_TEMP1_CPU_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_CPU_MASK,
+ .pllx_hotspot_diff = 10,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_CPU_MASK,
+ .thermtrip_any_en_mask = TEGRA210_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA210_THERMTRIP_CPU_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA210_THERMTRIP_CPU_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra210_tsensor_group_gpu = {
+ .id = TEGRA124_SOCTHERM_SENSOR_GPU,
+ .name = "gpu",
+ .sensor_temp_offset = SENSOR_TEMP1,
+ .sensor_temp_mask = SENSOR_TEMP1_GPU_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_GPU_MASK,
+ .pllx_hotspot_diff = 5,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_GPU_MASK,
+ .thermtrip_any_en_mask = TEGRA210_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA210_THERMTRIP_GPU_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA210_THERMTRIP_GPUMEM_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra210_tsensor_group_pll = {
+ .id = TEGRA124_SOCTHERM_SENSOR_PLLX,
+ .name = "pll",
+ .sensor_temp_offset = SENSOR_TEMP2,
+ .sensor_temp_mask = SENSOR_TEMP2_PLLX_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_PLLX_MASK,
+ .thermtrip_any_en_mask = TEGRA210_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA210_THERMTRIP_TSENSE_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA210_THERMTRIP_TSENSE_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group tegra210_tsensor_group_mem = {
+ .id = TEGRA124_SOCTHERM_SENSOR_MEM,
+ .name = "mem",
+ .sensor_temp_offset = SENSOR_TEMP2,
+ .sensor_temp_mask = SENSOR_TEMP2_MEM_TEMP_MASK,
+ .pdiv = 8,
+ .pdiv_ate = 8,
+ .pdiv_mask = SENSOR_PDIV_MEM_MASK,
+ .pllx_hotspot_diff = 0,
+ .pllx_hotspot_mask = SENSOR_HOTSPOT_MEM_MASK,
+ .thermtrip_any_en_mask = TEGRA210_THERMTRIP_ANY_EN_MASK,
+ .thermtrip_enable_mask = TEGRA210_THERMTRIP_MEM_EN_MASK,
+ .thermtrip_threshold_mask = TEGRA210_THERMTRIP_GPUMEM_THRESH_MASK,
+};
+
+static const struct tegra_tsensor_group *tegra210_tsensor_groups[] = {
+ &tegra210_tsensor_group_cpu,
+ &tegra210_tsensor_group_gpu,
+ &tegra210_tsensor_group_pll,
+ &tegra210_tsensor_group_mem,
+};
+
+static const struct tegra_tsensor tegra210_tsensors[] = {
+ {
+ .name = "cpu0",
+ .base = 0xc0,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x098,
+ .fuse_corr_alpha = 1085000,
+ .fuse_corr_beta = 3244200,
+ .group = &tegra210_tsensor_group_cpu,
+ }, {
+ .name = "cpu1",
+ .base = 0xe0,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x084,
+ .fuse_corr_alpha = 1126200,
+ .fuse_corr_beta = -67500,
+ .group = &tegra210_tsensor_group_cpu,
+ }, {
+ .name = "cpu2",
+ .base = 0x100,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x088,
+ .fuse_corr_alpha = 1098400,
+ .fuse_corr_beta = 2251100,
+ .group = &tegra210_tsensor_group_cpu,
+ }, {
+ .name = "cpu3",
+ .base = 0x120,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x12c,
+ .fuse_corr_alpha = 1108000,
+ .fuse_corr_beta = 602700,
+ .group = &tegra210_tsensor_group_cpu,
+ }, {
+ .name = "mem0",
+ .base = 0x140,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x158,
+ .fuse_corr_alpha = 1069200,
+ .fuse_corr_beta = 3549900,
+ .group = &tegra210_tsensor_group_mem,
+ }, {
+ .name = "mem1",
+ .base = 0x160,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x15c,
+ .fuse_corr_alpha = 1173700,
+ .fuse_corr_beta = -6263600,
+ .group = &tegra210_tsensor_group_mem,
+ }, {
+ .name = "gpu",
+ .base = 0x180,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x154,
+ .fuse_corr_alpha = 1074300,
+ .fuse_corr_beta = 2734900,
+ .group = &tegra210_tsensor_group_gpu,
+ }, {
+ .name = "pllx",
+ .base = 0x1a0,
+ .config = &tegra210_tsensor_config,
+ .calib_fuse_offset = 0x160,
+ .fuse_corr_alpha = 1039700,
+ .fuse_corr_beta = 6829100,
+ .group = &tegra210_tsensor_group_pll,
+ },
+};
+
+/*
+ * Mask/shift bits in FUSE_TSENSOR_COMMON and
+ * FUSE_TSENSOR_COMMON, which are described in
+ * tegra_soctherm_fuse.c
+ */
+static const struct tegra_soctherm_fuse tegra210_soctherm_fuse = {
+ .fuse_base_cp_mask = 0x3ff << 11,
+ .fuse_base_cp_shift = 11,
+ .fuse_base_ft_mask = 0x7ff << 21,
+ .fuse_base_ft_shift = 21,
+ .fuse_shift_ft_mask = 0x1f << 6,
+ .fuse_shift_ft_shift = 6,
+ .fuse_spare_realignment = 0,
+};
+
+const struct tegra_soctherm_soc tegra210_soctherm = {
+ .tsensors = tegra210_tsensors,
+ .num_tsensors = ARRAY_SIZE(tegra210_tsensors),
+ .ttgs = tegra210_tsensor_groups,
+ .num_ttgs = ARRAY_SIZE(tegra210_tsensor_groups),
+ .tfuse = &tegra210_soctherm_fuse,
+ .thresh_grain = TEGRA210_THRESH_GRAIN,
+};
diff --git a/drivers/thermal/tegra_soctherm.c b/drivers/thermal/tegra_soctherm.c
deleted file mode 100644
index 136975220c92..000000000000
--- a/drivers/thermal/tegra_soctherm.c
+++ /dev/null
@@ -1,476 +0,0 @@
-/*
- * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
- *
- * Author:
- * Mikko Perttunen <mperttunen@nvidia.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/bitops.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/reset.h>
-#include <linux/thermal.h>
-
-#include <soc/tegra/fuse.h>
-
-#define SENSOR_CONFIG0 0
-#define SENSOR_CONFIG0_STOP BIT(0)
-#define SENSOR_CONFIG0_TALL_SHIFT 8
-#define SENSOR_CONFIG0_TCALC_OVER BIT(4)
-#define SENSOR_CONFIG0_OVER BIT(3)
-#define SENSOR_CONFIG0_CPTR_OVER BIT(2)
-
-#define SENSOR_CONFIG1 4
-#define SENSOR_CONFIG1_TSAMPLE_SHIFT 0
-#define SENSOR_CONFIG1_TIDDQ_EN_SHIFT 15
-#define SENSOR_CONFIG1_TEN_COUNT_SHIFT 24
-#define SENSOR_CONFIG1_TEMP_ENABLE BIT(31)
-
-#define SENSOR_CONFIG2 8
-#define SENSOR_CONFIG2_THERMA_SHIFT 16
-#define SENSOR_CONFIG2_THERMB_SHIFT 0
-
-#define SENSOR_PDIV 0x1c0
-#define SENSOR_PDIV_T124 0x8888
-#define SENSOR_HOTSPOT_OFF 0x1c4
-#define SENSOR_HOTSPOT_OFF_T124 0x00060600
-#define SENSOR_TEMP1 0x1c8
-#define SENSOR_TEMP2 0x1cc
-
-#define SENSOR_TEMP_MASK 0xffff
-#define READBACK_VALUE_MASK 0xff00
-#define READBACK_VALUE_SHIFT 8
-#define READBACK_ADD_HALF BIT(7)
-#define READBACK_NEGATE BIT(0)
-
-#define FUSE_TSENSOR8_CALIB 0x180
-#define FUSE_SPARE_REALIGNMENT_REG_0 0x1fc
-
-#define FUSE_TSENSOR_CALIB_CP_TS_BASE_MASK 0x1fff
-#define FUSE_TSENSOR_CALIB_FT_TS_BASE_MASK (0x1fff << 13)
-#define FUSE_TSENSOR_CALIB_FT_TS_BASE_SHIFT 13
-
-#define FUSE_TSENSOR8_CALIB_CP_TS_BASE_MASK 0x3ff
-#define FUSE_TSENSOR8_CALIB_FT_TS_BASE_MASK (0x7ff << 10)
-#define FUSE_TSENSOR8_CALIB_FT_TS_BASE_SHIFT 10
-
-#define FUSE_SPARE_REALIGNMENT_REG_SHIFT_CP_MASK 0x3f
-#define FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_MASK (0x1f << 21)
-#define FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_SHIFT 21
-
-#define NOMINAL_CALIB_FT_T124 105
-#define NOMINAL_CALIB_CP_T124 25
-
-struct tegra_tsensor_configuration {
- u32 tall, tsample, tiddq_en, ten_count, pdiv, tsample_ate, pdiv_ate;
-};
-
-struct tegra_tsensor {
- const struct tegra_tsensor_configuration *config;
- u32 base, calib_fuse_offset;
- /* Correction values used to modify values read from calibration fuses */
- s32 fuse_corr_alpha, fuse_corr_beta;
-};
-
-struct tegra_thermctl_zone {
- void __iomem *reg;
- unsigned int shift;
-};
-
-static const struct tegra_tsensor_configuration t124_tsensor_config = {
- .tall = 16300,
- .tsample = 120,
- .tiddq_en = 1,
- .ten_count = 1,
- .pdiv = 8,
- .tsample_ate = 480,
- .pdiv_ate = 8
-};
-
-static const struct tegra_tsensor t124_tsensors[] = {
- {
- .config = &t124_tsensor_config,
- .base = 0xc0,
- .calib_fuse_offset = 0x098,
- .fuse_corr_alpha = 1135400,
- .fuse_corr_beta = -6266900,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0xe0,
- .calib_fuse_offset = 0x084,
- .fuse_corr_alpha = 1122220,
- .fuse_corr_beta = -5700700,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0x100,
- .calib_fuse_offset = 0x088,
- .fuse_corr_alpha = 1127000,
- .fuse_corr_beta = -6768200,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0x120,
- .calib_fuse_offset = 0x12c,
- .fuse_corr_alpha = 1110900,
- .fuse_corr_beta = -6232000,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0x140,
- .calib_fuse_offset = 0x158,
- .fuse_corr_alpha = 1122300,
- .fuse_corr_beta = -5936400,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0x160,
- .calib_fuse_offset = 0x15c,
- .fuse_corr_alpha = 1145700,
- .fuse_corr_beta = -7124600,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0x180,
- .calib_fuse_offset = 0x154,
- .fuse_corr_alpha = 1120100,
- .fuse_corr_beta = -6000500,
- },
- {
- .config = &t124_tsensor_config,
- .base = 0x1a0,
- .calib_fuse_offset = 0x160,
- .fuse_corr_alpha = 1106500,
- .fuse_corr_beta = -6729300,
- },
-};
-
-struct tegra_soctherm {
- struct reset_control *reset;
- struct clk *clock_tsensor;
- struct clk *clock_soctherm;
- void __iomem *regs;
-
- struct thermal_zone_device *thermctl_tzs[4];
-};
-
-struct tsensor_shared_calibration {
- u32 base_cp, base_ft;
- u32 actual_temp_cp, actual_temp_ft;
-};
-
-static int calculate_shared_calibration(struct tsensor_shared_calibration *r)
-{
- u32 val, shifted_cp, shifted_ft;
- int err;
-
- err = tegra_fuse_readl(FUSE_TSENSOR8_CALIB, &val);
- if (err)
- return err;
- r->base_cp = val & FUSE_TSENSOR8_CALIB_CP_TS_BASE_MASK;
- r->base_ft = (val & FUSE_TSENSOR8_CALIB_FT_TS_BASE_MASK)
- >> FUSE_TSENSOR8_CALIB_FT_TS_BASE_SHIFT;
- val = ((val & FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_MASK)
- >> FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_SHIFT);
- shifted_ft = sign_extend32(val, 4);
-
- err = tegra_fuse_readl(FUSE_SPARE_REALIGNMENT_REG_0, &val);
- if (err)
- return err;
- shifted_cp = sign_extend32(val, 5);
-
- r->actual_temp_cp = 2 * NOMINAL_CALIB_CP_T124 + shifted_cp;
- r->actual_temp_ft = 2 * NOMINAL_CALIB_FT_T124 + shifted_ft;
-
- return 0;
-}
-
-static s64 div64_s64_precise(s64 a, s64 b)
-{
- s64 r, al;
-
- /* Scale up for increased precision division */
- al = a << 16;
-
- r = div64_s64(al * 2 + 1, 2 * b);
- return r >> 16;
-}
-
-static int
-calculate_tsensor_calibration(const struct tegra_tsensor *sensor,
- const struct tsensor_shared_calibration *shared,
- u32 *calib)
-{
- u32 val;
- s32 actual_tsensor_ft, actual_tsensor_cp, delta_sens, delta_temp,
- mult, div;
- s16 therma, thermb;
- s64 tmp;
- int err;
-
- err = tegra_fuse_readl(sensor->calib_fuse_offset, &val);
- if (err)
- return err;
-
- actual_tsensor_cp = (shared->base_cp * 64) + sign_extend32(val, 12);
- val = (val & FUSE_TSENSOR_CALIB_FT_TS_BASE_MASK)
- >> FUSE_TSENSOR_CALIB_FT_TS_BASE_SHIFT;
- actual_tsensor_ft = (shared->base_ft * 32) + sign_extend32(val, 12);
-
- delta_sens = actual_tsensor_ft - actual_tsensor_cp;
- delta_temp = shared->actual_temp_ft - shared->actual_temp_cp;
-
- mult = sensor->config->pdiv * sensor->config->tsample_ate;
- div = sensor->config->tsample * sensor->config->pdiv_ate;
-
- therma = div64_s64_precise((s64) delta_temp * (1LL << 13) * mult,
- (s64) delta_sens * div);
-
- tmp = (s64)actual_tsensor_ft * shared->actual_temp_cp -
- (s64)actual_tsensor_cp * shared->actual_temp_ft;
- thermb = div64_s64_precise(tmp, (s64)delta_sens);
-
- therma = div64_s64_precise((s64)therma * sensor->fuse_corr_alpha,
- (s64)1000000LL);
- thermb = div64_s64_precise((s64)thermb * sensor->fuse_corr_alpha +
- sensor->fuse_corr_beta, (s64)1000000LL);
-
- *calib = ((u16)therma << SENSOR_CONFIG2_THERMA_SHIFT) |
- ((u16)thermb << SENSOR_CONFIG2_THERMB_SHIFT);
-
- return 0;
-}
-
-static int enable_tsensor(struct tegra_soctherm *tegra,
- const struct tegra_tsensor *sensor,
- const struct tsensor_shared_calibration *shared)
-{
- void __iomem *base = tegra->regs + sensor->base;
- unsigned int val;
- u32 calib;
- int err;
-
- err = calculate_tsensor_calibration(sensor, shared, &calib);
- if (err)
- return err;
-
- val = sensor->config->tall << SENSOR_CONFIG0_TALL_SHIFT;
- writel(val, base + SENSOR_CONFIG0);
-
- val = (sensor->config->tsample - 1) << SENSOR_CONFIG1_TSAMPLE_SHIFT;
- val |= sensor->config->tiddq_en << SENSOR_CONFIG1_TIDDQ_EN_SHIFT;
- val |= sensor->config->ten_count << SENSOR_CONFIG1_TEN_COUNT_SHIFT;
- val |= SENSOR_CONFIG1_TEMP_ENABLE;
- writel(val, base + SENSOR_CONFIG1);
-
- writel(calib, base + SENSOR_CONFIG2);
-
- return 0;
-}
-
-/*
- * Translate from soctherm readback format to millicelsius.
- * The soctherm readback format in bits is as follows:
- * TTTTTTTT H______N
- * where T's contain the temperature in Celsius,
- * H denotes an addition of 0.5 Celsius and N denotes negation
- * of the final value.
- */
-static int translate_temp(u16 val)
-{
- long t;
-
- t = ((val & READBACK_VALUE_MASK) >> READBACK_VALUE_SHIFT) * 1000;
- if (val & READBACK_ADD_HALF)
- t += 500;
- if (val & READBACK_NEGATE)
- t *= -1;
-
- return t;
-}
-
-static int tegra_thermctl_get_temp(void *data, int *out_temp)
-{
- struct tegra_thermctl_zone *zone = data;
- u32 val;
-
- val = (readl(zone->reg) >> zone->shift) & SENSOR_TEMP_MASK;
- *out_temp = translate_temp(val);
-
- return 0;
-}
-
-static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = {
- .get_temp = tegra_thermctl_get_temp,
-};
-
-static const struct of_device_id tegra_soctherm_of_match[] = {
- { .compatible = "nvidia,tegra124-soctherm" },
- { },
-};
-MODULE_DEVICE_TABLE(of, tegra_soctherm_of_match);
-
-struct thermctl_zone_desc {
- unsigned int offset;
- unsigned int shift;
-};
-
-static const struct thermctl_zone_desc t124_thermctl_temp_zones[] = {
- { SENSOR_TEMP1, 16 },
- { SENSOR_TEMP2, 16 },
- { SENSOR_TEMP1, 0 },
- { SENSOR_TEMP2, 0 }
-};
-
-static int tegra_soctherm_probe(struct platform_device *pdev)
-{
- struct tegra_soctherm *tegra;
- struct thermal_zone_device *tz;
- struct tsensor_shared_calibration shared_calib;
- struct resource *res;
- unsigned int i;
- int err;
-
- const struct tegra_tsensor *tsensors = t124_tsensors;
-
- tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
- if (!tegra)
- return -ENOMEM;
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- tegra->regs = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(tegra->regs))
- return PTR_ERR(tegra->regs);
-
- tegra->reset = devm_reset_control_get(&pdev->dev, "soctherm");
- if (IS_ERR(tegra->reset)) {
- dev_err(&pdev->dev, "can't get soctherm reset\n");
- return PTR_ERR(tegra->reset);
- }
-
- tegra->clock_tsensor = devm_clk_get(&pdev->dev, "tsensor");
- if (IS_ERR(tegra->clock_tsensor)) {
- dev_err(&pdev->dev, "can't get tsensor clock\n");
- return PTR_ERR(tegra->clock_tsensor);
- }
-
- tegra->clock_soctherm = devm_clk_get(&pdev->dev, "soctherm");
- if (IS_ERR(tegra->clock_soctherm)) {
- dev_err(&pdev->dev, "can't get soctherm clock\n");
- return PTR_ERR(tegra->clock_soctherm);
- }
-
- reset_control_assert(tegra->reset);
-
- err = clk_prepare_enable(tegra->clock_soctherm);
- if (err)
- return err;
-
- err = clk_prepare_enable(tegra->clock_tsensor);
- if (err) {
- clk_disable_unprepare(tegra->clock_soctherm);
- return err;
- }
-
- reset_control_deassert(tegra->reset);
-
- /* Initialize raw sensors */
-
- err = calculate_shared_calibration(&shared_calib);
- if (err)
- goto disable_clocks;
-
- for (i = 0; i < ARRAY_SIZE(t124_tsensors); ++i) {
- err = enable_tsensor(tegra, tsensors + i, &shared_calib);
- if (err)
- goto disable_clocks;
- }
-
- writel(SENSOR_PDIV_T124, tegra->regs + SENSOR_PDIV);
- writel(SENSOR_HOTSPOT_OFF_T124, tegra->regs + SENSOR_HOTSPOT_OFF);
-
- /* Initialize thermctl sensors */
-
- for (i = 0; i < ARRAY_SIZE(tegra->thermctl_tzs); ++i) {
- struct tegra_thermctl_zone *zone =
- devm_kzalloc(&pdev->dev, sizeof(*zone), GFP_KERNEL);
- if (!zone) {
- err = -ENOMEM;
- goto unregister_tzs;
- }
-
- zone->reg = tegra->regs + t124_thermctl_temp_zones[i].offset;
- zone->shift = t124_thermctl_temp_zones[i].shift;
-
- tz = thermal_zone_of_sensor_register(&pdev->dev, i, zone,
- &tegra_of_thermal_ops);
- if (IS_ERR(tz)) {
- err = PTR_ERR(tz);
- dev_err(&pdev->dev, "failed to register sensor: %d\n",
- err);
- goto unregister_tzs;
- }
-
- tegra->thermctl_tzs[i] = tz;
- }
-
- return 0;
-
-unregister_tzs:
- while (i--)
- thermal_zone_of_sensor_unregister(&pdev->dev,
- tegra->thermctl_tzs[i]);
-
-disable_clocks:
- clk_disable_unprepare(tegra->clock_tsensor);
- clk_disable_unprepare(tegra->clock_soctherm);
-
- return err;
-}
-
-static int tegra_soctherm_remove(struct platform_device *pdev)
-{
- struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
- unsigned int i;
-
- for (i = 0; i < ARRAY_SIZE(tegra->thermctl_tzs); ++i) {
- thermal_zone_of_sensor_unregister(&pdev->dev,
- tegra->thermctl_tzs[i]);
- }
-
- clk_disable_unprepare(tegra->clock_tsensor);
- clk_disable_unprepare(tegra->clock_soctherm);
-
- return 0;
-}
-
-static struct platform_driver tegra_soctherm_driver = {
- .probe = tegra_soctherm_probe,
- .remove = tegra_soctherm_remove,
- .driver = {
- .name = "tegra-soctherm",
- .of_match_table = tegra_soctherm_of_match,
- },
-};
-module_platform_driver(tegra_soctherm_driver);
-
-MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
-MODULE_DESCRIPTION("NVIDIA Tegra SOCTHERM thermal management driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/thermal-generic-adc.c b/drivers/thermal/thermal-generic-adc.c
new file mode 100644
index 000000000000..73f55d6a1721
--- /dev/null
+++ b/drivers/thermal/thermal-generic-adc.c
@@ -0,0 +1,182 @@
+/*
+ * Generic ADC thermal driver
+ *
+ * Copyright (C) 2016 NVIDIA CORPORATION. All rights reserved.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/iio/consumer.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+struct gadc_thermal_info {
+ struct device *dev;
+ struct thermal_zone_device *tz_dev;
+ struct iio_channel *channel;
+ s32 *lookup_table;
+ int nlookup_table;
+};
+
+static int gadc_thermal_adc_to_temp(struct gadc_thermal_info *gti, int val)
+{
+ int temp, adc_hi, adc_lo;
+ int i;
+
+ for (i = 0; i < gti->nlookup_table; i++) {
+ if (val >= gti->lookup_table[2 * i + 1])
+ break;
+ }
+
+ if (i == 0) {
+ temp = gti->lookup_table[0];
+ } else if (i >= (gti->nlookup_table - 1)) {
+ temp = gti->lookup_table[2 * (gti->nlookup_table - 1)];
+ } else {
+ adc_hi = gti->lookup_table[2 * i - 1];
+ adc_lo = gti->lookup_table[2 * i + 1];
+ temp = gti->lookup_table[2 * i];
+ temp -= ((val - adc_lo) * 1000) / (adc_hi - adc_lo);
+ }
+
+ return temp;
+}
+
+static int gadc_thermal_get_temp(void *data, int *temp)
+{
+ struct gadc_thermal_info *gti = data;
+ int val;
+ int ret;
+
+ ret = iio_read_channel_processed(gti->channel, &val);
+ if (ret < 0) {
+ dev_err(gti->dev, "IIO channel read failed %d\n", ret);
+ return ret;
+ }
+ *temp = gadc_thermal_adc_to_temp(gti, val);
+
+ return 0;
+}
+
+static const struct thermal_zone_of_device_ops gadc_thermal_ops = {
+ .get_temp = gadc_thermal_get_temp,
+};
+
+static int gadc_thermal_read_linear_lookup_table(struct device *dev,
+ struct gadc_thermal_info *gti)
+{
+ struct device_node *np = dev->of_node;
+ int ntable;
+ int ret;
+
+ ntable = of_property_count_elems_of_size(np, "temperature-lookup-table",
+ sizeof(u32));
+ if (ntable < 0) {
+ dev_err(dev, "Lookup table is not provided\n");
+ return ntable;
+ }
+
+ if (ntable % 2) {
+ dev_err(dev, "Pair of temperature vs ADC read value missing\n");
+ return -EINVAL;
+ }
+
+ gti->lookup_table = devm_kzalloc(dev, sizeof(*gti->lookup_table) *
+ ntable, GFP_KERNEL);
+ if (!gti->lookup_table)
+ return -ENOMEM;
+
+ ret = of_property_read_u32_array(np, "temperature-lookup-table",
+ (u32 *)gti->lookup_table, ntable);
+ if (ret < 0) {
+ dev_err(dev, "Failed to read temperature lookup table: %d\n",
+ ret);
+ return ret;
+ }
+
+ gti->nlookup_table = ntable / 2;
+
+ return 0;
+}
+
+static int gadc_thermal_probe(struct platform_device *pdev)
+{
+ struct gadc_thermal_info *gti;
+ int ret;
+
+ if (!pdev->dev.of_node) {
+ dev_err(&pdev->dev, "Only DT based supported\n");
+ return -ENODEV;
+ }
+
+ gti = devm_kzalloc(&pdev->dev, sizeof(*gti), GFP_KERNEL);
+ if (!gti)
+ return -ENOMEM;
+
+ ret = gadc_thermal_read_linear_lookup_table(&pdev->dev, gti);
+ if (ret < 0)
+ return ret;
+
+ gti->dev = &pdev->dev;
+ platform_set_drvdata(pdev, gti);
+
+ gti->channel = iio_channel_get(&pdev->dev, "sensor-channel");
+ if (IS_ERR(gti->channel)) {
+ ret = PTR_ERR(gti->channel);
+ dev_err(&pdev->dev, "IIO channel not found: %d\n", ret);
+ return ret;
+ }
+
+ gti->tz_dev = thermal_zone_of_sensor_register(&pdev->dev, 0,
+ gti, &gadc_thermal_ops);
+ if (IS_ERR(gti->tz_dev)) {
+ ret = PTR_ERR(gti->tz_dev);
+ dev_err(&pdev->dev, "Thermal zone sensor register failed: %d\n",
+ ret);
+ goto sensor_fail;
+ }
+
+ return 0;
+
+sensor_fail:
+ iio_channel_release(gti->channel);
+
+ return ret;
+}
+
+static int gadc_thermal_remove(struct platform_device *pdev)
+{
+ struct gadc_thermal_info *gti = platform_get_drvdata(pdev);
+
+ thermal_zone_of_sensor_unregister(&pdev->dev, gti->tz_dev);
+ iio_channel_release(gti->channel);
+
+ return 0;
+}
+
+static const struct of_device_id of_adc_thermal_match[] = {
+ { .compatible = "generic-adc-thermal", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, of_adc_thermal_match);
+
+static struct platform_driver gadc_thermal_driver = {
+ .driver = {
+ .name = "generic-adc-thermal",
+ .of_match_table = of_adc_thermal_match,
+ },
+ .probe = gadc_thermal_probe,
+ .remove = gadc_thermal_remove,
+};
+
+module_platform_driver(gadc_thermal_driver);
+
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_DESCRIPTION("Generic ADC thermal driver using IIO framework with DT");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index b213a1222295..15c0a9ac2209 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -337,7 +337,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
return -EINVAL;
/* in case this is specified by DT */
- data->ti_thermal = thermal_zone_of_sensor_register(bgp->dev, id,
+ data->ti_thermal = devm_thermal_zone_of_sensor_register(bgp->dev, id,
data, &ti_of_thermal_ops);
if (IS_ERR(data->ti_thermal)) {
/* Create thermal zone */
@@ -368,9 +368,6 @@ int ti_thermal_remove_sensor(struct ti_bandgap *bgp, int id)
if (data && data->ti_thermal) {
if (data->our_zone)
thermal_zone_device_unregister(data->ti_thermal);
- else
- thermal_zone_of_sensor_unregister(bgp->dev,
- data->ti_thermal);
}
return 0;
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index 7fc919f7da4d..97f0a2bd93ed 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/x86_pkg_temp_thermal.c
@@ -555,7 +555,7 @@ static int pkg_temp_thermal_cpu_callback(struct notifier_block *nfb,
{
unsigned int cpu = (unsigned long) hcpu;
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
case CPU_DOWN_FAILED:
get_core_online(cpu);
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 82c4d2e45319..95103054c0e4 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -120,17 +120,6 @@ config UNIX98_PTYS
All modern Linux systems use the Unix98 ptys. Say Y unless
you're on an embedded system and want to conserve memory.
-config DEVPTS_MULTIPLE_INSTANCES
- bool "Support multiple instances of devpts"
- depends on UNIX98_PTYS
- default n
- ---help---
- Enable support for multiple instances of devpts filesystem.
- If you want to have isolated PTY namespaces (eg: in containers),
- say Y here. Otherwise, say N. If enabled, each mount of devpts
- filesystem with the '-o newinstance' option will create an
- independent PTY namespace.
-
config LEGACY_PTYS
bool "Legacy (BSD) PTY support"
default y
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index dd4b8417e7f4..51e0d32883ba 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -667,8 +667,11 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
fsi = tty->driver_data;
else
fsi = tty->link->driver_data;
- devpts_kill_index(fsi, tty->index);
- devpts_put_ref(fsi);
+
+ if (fsi) {
+ devpts_kill_index(fsi, tty->index);
+ devpts_release(fsi);
+ }
}
static const struct tty_operations ptm_unix98_ops = {
@@ -733,10 +736,11 @@ static int ptmx_open(struct inode *inode, struct file *filp)
if (retval)
return retval;
- fsi = devpts_get_ref(inode, filp);
- retval = -ENODEV;
- if (!fsi)
+ fsi = devpts_acquire(filp);
+ if (IS_ERR(fsi)) {
+ retval = PTR_ERR(fsi);
goto out_free_file;
+ }
/* find a device that is not in use. */
mutex_lock(&devpts_mutex);
@@ -745,7 +749,7 @@ static int ptmx_open(struct inode *inode, struct file *filp)
retval = index;
if (index < 0)
- goto out_put_ref;
+ goto out_put_fsi;
mutex_lock(&tty_mutex);
@@ -789,8 +793,8 @@ err_release:
return retval;
out:
devpts_kill_index(fsi, index);
-out_put_ref:
- devpts_put_ref(fsi);
+out_put_fsi:
+ devpts_release(fsi);
out_free_file:
tty_free_file(filp);
return retval;
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index a2aa655f56c4..1b7331e40d79 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2360,7 +2360,7 @@ static int pl011_probe_dt_alias(int index, struct device *dev)
return ret;
ret = of_alias_get_id(np, "serial");
- if (IS_ERR_VALUE(ret)) {
+ if (ret < 0) {
seen_dev_without_alias = true;
ret = index;
} else {
diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c
index 18971063f95f..699447aa8b43 100644
--- a/drivers/tty/serial/sprd_serial.c
+++ b/drivers/tty/serial/sprd_serial.c
@@ -654,7 +654,7 @@ static int sprd_probe_dt_alias(int index, struct device *dev)
return ret;
ret = of_alias_get_id(np, "serial");
- if (IS_ERR_VALUE(ret))
+ if (ret < 0)
ret = index;
else if (ret >= ARRAY_SIZE(sprd_port) || sprd_port[ret] != NULL) {
dev_warn(dev, "requested serial port %d not available.\n", ret);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index dc125322f48f..5b0fe97c46ca 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -750,6 +750,7 @@ static void visual_init(struct vc_data *vc, int num, int init)
vc->vc_complement_mask = 0;
vc->vc_can_do_color = 0;
vc->vc_panic_force_write = false;
+ vc->vc_cur_blink_ms = DEFAULT_CURSOR_BLINK_MS;
vc->vc_sw->con_init(vc, init);
if (!vc->vc_complement_mask)
vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800;
diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index 9059b7dc185e..2f537bbdda09 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -21,6 +21,7 @@
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/mutex.h>
@@ -450,3 +451,4 @@ int otg_statemachine(struct otg_fsm *fsm)
return fsm->state_changed;
}
EXPORT_SYMBOL_GPL(otg_statemachine);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 34b837ae1ed7..d2e3f655c26f 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2598,26 +2598,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd);
* Don't deallocate the bandwidth_mutex until the last shared usb_hcd is
* deallocated.
*
- * Make sure to only deallocate the bandwidth_mutex when the primary HCD is
- * freed. When hcd_release() is called for either hcd in a peer set
- * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to
- * block new peering attempts
+ * Make sure to deallocate the bandwidth_mutex only when the last HCD is
+ * freed. When hcd_release() is called for either hcd in a peer set,
+ * invalidate the peer's ->shared_hcd and ->primary_hcd pointers.
*/
static void hcd_release(struct kref *kref)
{
struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
mutex_lock(&usb_port_peer_mutex);
- if (usb_hcd_is_primary_hcd(hcd)) {
- kfree(hcd->address0_mutex);
- kfree(hcd->bandwidth_mutex);
- }
if (hcd->shared_hcd) {
struct usb_hcd *peer = hcd->shared_hcd;
peer->shared_hcd = NULL;
- if (peer->primary_hcd == hcd)
- peer->primary_hcd = NULL;
+ peer->primary_hcd = NULL;
+ } else {
+ kfree(hcd->address0_mutex);
+ kfree(hcd->bandwidth_mutex);
}
mutex_unlock(&usb_port_peer_mutex);
kfree(hcd);
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6dc810bce295..944a6dca0fcb 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Creative SB Audigy 2 NX */
{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* USB3503 */
+ { USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Microsoft Wireless Laser Mouse 6000 Receiver */
{ USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME },
@@ -173,6 +176,10 @@ static const struct usb_device_id usb_quirk_list[] = {
/* MAYA44USB sound device */
{ USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* ASUS Base Station(T100) */
+ { USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+ USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
/* Action Semiconductor flash disk */
{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
USB_QUIRK_STRING_FETCH_255 },
@@ -188,26 +195,22 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x1908, 0x1315), .driver_info =
USB_QUIRK_HONOR_BNUMINTERFACES },
- /* INTEL VALUE SSD */
- { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
-
- /* USB3503 */
- { USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
-
- /* ASUS Base Station(T100) */
- { USB_DEVICE(0x0b05, 0x17e0), .driver_info =
- USB_QUIRK_IGNORE_REMOTE_WAKEUP },
-
/* Protocol and OTG Electrical Test Device */
{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
+ /* Acer C120 LED Projector */
+ { USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM },
+
/* Blackmagic Design Intensity Shuttle */
{ USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM },
/* Blackmagic Design UltraStudio SDI */
{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
+ /* INTEL VALUE SSD */
+ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
+
{ } /* terminating entry must be last */
};
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index 3c58d633ce80..dec0b21fc626 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -64,6 +64,17 @@
DWC2_TRACE_SCHEDULER_VB(pr_fmt("%s: SCH: " fmt), \
dev_name(hsotg->dev), ##__VA_ARGS__)
+#ifdef CONFIG_MIPS
+/*
+ * There are some MIPS machines that can run in either big-endian
+ * or little-endian mode and that use the dwc2 register without
+ * a byteswap in both ways.
+ * Unlike other architectures, MIPS apparently does not require a
+ * barrier before the __raw_writel() to synchronize with DMA but does
+ * require the barrier after the __raw_writel() to serialize a set of
+ * writes. This set of operations was added specifically for MIPS and
+ * should only be used there.
+ */
static inline u32 dwc2_readl(const void __iomem *addr)
{
u32 value = __raw_readl(addr);
@@ -90,6 +101,22 @@ static inline void dwc2_writel(u32 value, void __iomem *addr)
pr_info("INFO:: wrote %08x to %p\n", value, addr);
#endif
}
+#else
+/* Normal architectures just use readl/write */
+static inline u32 dwc2_readl(const void __iomem *addr)
+{
+ return readl(addr);
+}
+
+static inline void dwc2_writel(u32 value, void __iomem *addr)
+{
+ writel(value, addr);
+
+#ifdef DWC2_LOG_WRITES
+ pr_info("info:: wrote %08x to %p\n", value, addr);
+#endif
+}
+#endif
/* Maximum number of Endpoints/HostChannels */
#define MAX_EPS_CHANNELS 16
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 4c5e3005e1dc..26cf09d0fe3c 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1018,7 +1018,7 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg,
return 1;
}
-static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value);
+static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now);
/**
* get_ep_head - return the first request on the endpoint
@@ -1094,7 +1094,7 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg,
case USB_ENDPOINT_HALT:
halted = ep->halted;
- dwc2_hsotg_ep_sethalt(&ep->ep, set);
+ dwc2_hsotg_ep_sethalt(&ep->ep, set, true);
ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
if (ret) {
@@ -2948,8 +2948,13 @@ static int dwc2_hsotg_ep_dequeue(struct usb_ep *ep, struct usb_request *req)
* dwc2_hsotg_ep_sethalt - set halt on a given endpoint
* @ep: The endpoint to set halt.
* @value: Set or unset the halt.
+ * @now: If true, stall the endpoint now. Otherwise return -EAGAIN if
+ * the endpoint is busy processing requests.
+ *
+ * We need to stall the endpoint immediately if request comes from set_feature
+ * protocol command handler.
*/
-static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value)
+static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now)
{
struct dwc2_hsotg_ep *hs_ep = our_ep(ep);
struct dwc2_hsotg *hs = hs_ep->parent;
@@ -2969,6 +2974,17 @@ static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value)
return 0;
}
+ if (hs_ep->isochronous) {
+ dev_err(hs->dev, "%s is Isochronous Endpoint\n", ep->name);
+ return -EINVAL;
+ }
+
+ if (!now && value && !list_empty(&hs_ep->queue)) {
+ dev_dbg(hs->dev, "%s request is pending, cannot halt\n",
+ ep->name);
+ return -EAGAIN;
+ }
+
if (hs_ep->dir_in) {
epreg = DIEPCTL(index);
epctl = dwc2_readl(hs->regs + epreg);
@@ -3020,7 +3036,7 @@ static int dwc2_hsotg_ep_sethalt_lock(struct usb_ep *ep, int value)
int ret = 0;
spin_lock_irqsave(&hs->lock, flags);
- ret = dwc2_hsotg_ep_sethalt(ep, value);
+ ret = dwc2_hsotg_ep_sethalt(ep, value, false);
spin_unlock_irqrestore(&hs->lock, flags);
return ret;
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 7ddf9449a063..654050684f4f 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -402,6 +402,7 @@
#define DWC3_DEPCMD_GET_RSC_IDX(x) (((x) >> DWC3_DEPCMD_PARAM_SHIFT) & 0x7f)
#define DWC3_DEPCMD_STATUS(x) (((x) >> 12) & 0x0F)
#define DWC3_DEPCMD_HIPRI_FORCERM (1 << 11)
+#define DWC3_DEPCMD_CLEARPENDIN (1 << 11)
#define DWC3_DEPCMD_CMDACT (1 << 10)
#define DWC3_DEPCMD_CMDIOC (1 << 8)
diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index dd5cb5577dca..2f1fb7e7aa54 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -128,12 +128,6 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, exynos);
- ret = dwc3_exynos_register_phys(exynos);
- if (ret) {
- dev_err(dev, "couldn't register PHYs\n");
- return ret;
- }
-
exynos->dev = dev;
exynos->clk = devm_clk_get(dev, "usbdrd30");
@@ -183,20 +177,29 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
goto err3;
}
+ ret = dwc3_exynos_register_phys(exynos);
+ if (ret) {
+ dev_err(dev, "couldn't register PHYs\n");
+ goto err4;
+ }
+
if (node) {
ret = of_platform_populate(node, NULL, NULL, dev);
if (ret) {
dev_err(dev, "failed to add dwc3 core\n");
- goto err4;
+ goto err5;
}
} else {
dev_err(dev, "no device node, failed to add dwc3 core\n");
ret = -ENODEV;
- goto err4;
+ goto err5;
}
return 0;
+err5:
+ platform_device_unregister(exynos->usb2_phy);
+ platform_device_unregister(exynos->usb3_phy);
err4:
regulator_disable(exynos->vdd10);
err3:
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 5c0adb9c6fb2..89a2f712fdfe 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -129,12 +129,18 @@ static int st_dwc3_drd_init(struct st_dwc3 *dwc3_data)
switch (dwc3_data->dr_mode) {
case USB_DR_MODE_PERIPHERAL:
- val &= ~(USB3_FORCE_VBUSVALID | USB3_DELAY_VBUSVALID
+ val &= ~(USB3_DELAY_VBUSVALID
| USB3_SEL_FORCE_OPMODE | USB3_FORCE_OPMODE(0x3)
| USB3_SEL_FORCE_DPPULLDOWN2 | USB3_FORCE_DPPULLDOWN2
| USB3_SEL_FORCE_DMPULLDOWN2 | USB3_FORCE_DMPULLDOWN2);
- val |= USB3_DEVICE_NOT_HOST;
+ /*
+ * USB3_PORT2_FORCE_VBUSVALID When '1' and when
+ * USB3_PORT2_DEVICE_NOT_HOST = 1, forces VBUSVLDEXT2 input
+ * of the pico PHY to 1.
+ */
+
+ val |= USB3_DEVICE_NOT_HOST | USB3_FORCE_VBUSVALID;
break;
case USB_DR_MODE_HOST:
@@ -227,7 +233,8 @@ static int st_dwc3_probe(struct platform_device *pdev)
dev_vdbg(&pdev->dev, "glue-logic addr 0x%p, syscfg-reg offset 0x%x\n",
dwc3_data->glue_base, dwc3_data->syscfg_reg_off);
- dwc3_data->rstc_pwrdn = devm_reset_control_get(dev, "powerdown");
+ dwc3_data->rstc_pwrdn =
+ devm_reset_control_get_exclusive(dev, "powerdown");
if (IS_ERR(dwc3_data->rstc_pwrdn)) {
dev_err(&pdev->dev, "could not get power controller\n");
ret = PTR_ERR(dwc3_data->rstc_pwrdn);
@@ -237,7 +244,8 @@ static int st_dwc3_probe(struct platform_device *pdev)
/* Manage PowerDown */
reset_control_deassert(dwc3_data->rstc_pwrdn);
- dwc3_data->rstc_rst = devm_reset_control_get(dev, "softreset");
+ dwc3_data->rstc_rst =
+ devm_reset_control_get_shared(dev, "softreset");
if (IS_ERR(dwc3_data->rstc_rst)) {
dev_err(&pdev->dev, "could not get reset controller\n");
ret = PTR_ERR(dwc3_data->rstc_rst);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 9a7d0bd15dc3..07248ff1be5c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -347,6 +347,28 @@ int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
return ret;
}
+static int dwc3_send_clear_stall_ep_cmd(struct dwc3_ep *dep)
+{
+ struct dwc3 *dwc = dep->dwc;
+ struct dwc3_gadget_ep_cmd_params params;
+ u32 cmd = DWC3_DEPCMD_CLEARSTALL;
+
+ /*
+ * As of core revision 2.60a the recommended programming model
+ * is to set the ClearPendIN bit when issuing a Clear Stall EP
+ * command for IN endpoints. This is to prevent an issue where
+ * some (non-compliant) hosts may not send ACK TPs for pending
+ * IN transfers due to a mishandled error condition. Synopsys
+ * STAR 9000614252.
+ */
+ if (dep->direction && (dwc->revision >= DWC3_REVISION_260A))
+ cmd |= DWC3_DEPCMD_CLEARPENDIN;
+
+ memset(&params, 0, sizeof(params));
+
+ return dwc3_send_gadget_ep_cmd(dwc, dep->number, cmd, &params);
+}
+
static dma_addr_t dwc3_trb_dma_offset(struct dwc3_ep *dep,
struct dwc3_trb *trb)
{
@@ -1314,8 +1336,7 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
else
dep->flags |= DWC3_EP_STALL;
} else {
- ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
- DWC3_DEPCMD_CLEARSTALL, &params);
+ ret = dwc3_send_clear_stall_ep_cmd(dep);
if (ret)
dev_err(dwc->dev, "failed to clear STALL on %s\n",
dep->name);
@@ -2247,7 +2268,6 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc)
for (epnum = 1; epnum < DWC3_ENDPOINTS_NUM; epnum++) {
struct dwc3_ep *dep;
- struct dwc3_gadget_ep_cmd_params params;
int ret;
dep = dwc->eps[epnum];
@@ -2259,9 +2279,7 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc)
dep->flags &= ~DWC3_EP_STALL;
- memset(&params, 0, sizeof(params));
- ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
- DWC3_DEPCMD_CLEARSTALL, &params);
+ ret = dwc3_send_clear_stall_ep_cmd(dep);
WARN_ON_ONCE(ret);
}
}
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index d67de0d22a2b..eb648485a58c 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1868,14 +1868,19 @@ unknown:
}
break;
}
- req->length = value;
- req->context = cdev;
- req->zero = value < w_length;
- value = composite_ep0_queue(cdev, req, GFP_ATOMIC);
- if (value < 0) {
- DBG(cdev, "ep_queue --> %d\n", value);
- req->status = 0;
- composite_setup_complete(gadget->ep0, req);
+
+ if (value >= 0) {
+ req->length = value;
+ req->context = cdev;
+ req->zero = value < w_length;
+ value = composite_ep0_queue(cdev, req,
+ GFP_ATOMIC);
+ if (value < 0) {
+ DBG(cdev, "ep_queue --> %d\n", value);
+ req->status = 0;
+ composite_setup_complete(gadget->ep0,
+ req);
+ }
}
return value;
}
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index b6f60ca8a035..70cf3477f951 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -1401,6 +1401,7 @@ static const struct usb_gadget_driver configfs_driver_template = {
.owner = THIS_MODULE,
.name = "configfs-gadget",
},
+ .match_existing_only = 1,
};
static struct config_group *gadgets_make(
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 73515d54e1cc..cc33d2667408 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2051,7 +2051,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
if (len < sizeof(*d) ||
d->bFirstInterfaceNumber >= ffs->interfaces_count ||
- d->Reserved1)
+ !d->Reserved1)
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i)
if (d->Reserved2[i])
@@ -2729,6 +2729,7 @@ static int _ffs_func_bind(struct usb_configuration *c,
func->ffs->ss_descs_count;
int fs_len, hs_len, ss_len, ret, i;
+ struct ffs_ep *eps_ptr;
/* Make it a single chunk, less management later on */
vla_group(d);
@@ -2777,12 +2778,9 @@ static int _ffs_func_bind(struct usb_configuration *c,
ffs->raw_descs_length);
memset(vla_ptr(vlabuf, d, inums), 0xff, d_inums__sz);
- for (ret = ffs->eps_count; ret; --ret) {
- struct ffs_ep *ptr;
-
- ptr = vla_ptr(vlabuf, d, eps);
- ptr[ret].num = -1;
- }
+ eps_ptr = vla_ptr(vlabuf, d, eps);
+ for (i = 0; i < ffs->eps_count; i++)
+ eps_ptr[i].num = -1;
/* Save pointers
* d_eps == vlabuf, func->eps used to kfree vlabuf later
@@ -2851,7 +2849,7 @@ static int _ffs_func_bind(struct usb_configuration *c,
goto error;
func->function.os_desc_table = vla_ptr(vlabuf, d, os_desc_table);
- if (c->cdev->use_os_string)
+ if (c->cdev->use_os_string) {
for (i = 0; i < ffs->interfaces_count; ++i) {
struct usb_os_desc *desc;
@@ -2862,13 +2860,15 @@ static int _ffs_func_bind(struct usb_configuration *c,
vla_ptr(vlabuf, d, ext_compat) + i * 16;
INIT_LIST_HEAD(&desc->ext_prop);
}
- ret = ffs_do_os_descs(ffs->ms_os_descs_count,
- vla_ptr(vlabuf, d, raw_descs) +
- fs_len + hs_len + ss_len,
- d_raw_descs__sz - fs_len - hs_len - ss_len,
- __ffs_func_bind_do_os_desc, func);
- if (unlikely(ret < 0))
- goto error;
+ ret = ffs_do_os_descs(ffs->ms_os_descs_count,
+ vla_ptr(vlabuf, d, raw_descs) +
+ fs_len + hs_len + ss_len,
+ d_raw_descs__sz - fs_len - hs_len -
+ ss_len,
+ __ffs_func_bind_do_os_desc, func);
+ if (unlikely(ret < 0))
+ goto error;
+ }
func->function.os_desc_n =
c->cdev->use_os_string ? ffs->interfaces_count : 0;
diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c
index c45104e3a64b..64706a789580 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -161,14 +161,6 @@ static struct usb_endpoint_descriptor hs_ep_out_desc = {
.wMaxPacketSize = cpu_to_le16(512)
};
-static struct usb_qualifier_descriptor dev_qualifier = {
- .bLength = sizeof(dev_qualifier),
- .bDescriptorType = USB_DT_DEVICE_QUALIFIER,
- .bcdUSB = cpu_to_le16(0x0200),
- .bDeviceClass = USB_CLASS_PRINTER,
- .bNumConfigurations = 1
-};
-
static struct usb_descriptor_header *hs_printer_function[] = {
(struct usb_descriptor_header *) &intf_desc,
(struct usb_descriptor_header *) &hs_ep_in_desc,
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 2ace0295408e..197f73386fac 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1290,15 +1290,6 @@ static void usbg_release_cmd(struct se_cmd *se_cmd)
percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
}
-static int usbg_shutdown_session(struct se_session *se_sess)
-{
- return 0;
-}
-
-static void usbg_close_session(struct se_session *se_sess)
-{
-}
-
static u32 usbg_sess_get_index(struct se_session *se_sess)
{
return 0;
@@ -1454,16 +1445,18 @@ static void usbg_drop_tpg(struct se_portal_group *se_tpg)
for (i = 0; i < TPG_INSTANCES; ++i)
if (tpg_instances[i].tpg == tpg)
break;
- if (i < TPG_INSTANCES)
+ if (i < TPG_INSTANCES) {
tpg_instances[i].tpg = NULL;
- opts = container_of(tpg_instances[i].func_inst,
- struct f_tcm_opts, func_inst);
- mutex_lock(&opts->dep_lock);
- if (opts->has_dep)
- module_put(opts->dependent);
- else
- configfs_undepend_item_unlocked(&opts->func_inst.group.cg_item);
- mutex_unlock(&opts->dep_lock);
+ opts = container_of(tpg_instances[i].func_inst,
+ struct f_tcm_opts, func_inst);
+ mutex_lock(&opts->dep_lock);
+ if (opts->has_dep)
+ module_put(opts->dependent);
+ else
+ configfs_undepend_item_unlocked(
+ &opts->func_inst.group.cg_item);
+ mutex_unlock(&opts->dep_lock);
+ }
mutex_unlock(&tpg_instances_lock);
kfree(tpg);
@@ -1735,8 +1728,6 @@ static const struct target_core_fabric_ops usbg_ops = {
.tpg_check_prod_mode_write_protect = usbg_check_false,
.tpg_get_inst_index = usbg_tpg_get_inst_index,
.release_cmd = usbg_release_cmd,
- .shutdown_session = usbg_shutdown_session,
- .close_session = usbg_close_session,
.sess_get_index = usbg_sess_get_index,
.sess_get_initiator_sid = NULL,
.write_pending = usbg_send_write_request,
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 186d4b162524..cd214ec8a601 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -598,18 +598,6 @@ static struct usb_gadget_strings *fn_strings[] = {
NULL,
};
-static struct usb_qualifier_descriptor devqual_desc = {
- .bLength = sizeof devqual_desc,
- .bDescriptorType = USB_DT_DEVICE_QUALIFIER,
-
- .bcdUSB = cpu_to_le16(0x200),
- .bDeviceClass = USB_CLASS_MISC,
- .bDeviceSubClass = 0x02,
- .bDeviceProtocol = 0x01,
- .bNumConfigurations = 1,
- .bRESERVED = 0,
-};
-
static struct usb_interface_assoc_descriptor iad_desc = {
.bLength = sizeof iad_desc,
.bDescriptorType = USB_DT_INTERFACE_ASSOCIATION,
@@ -1292,6 +1280,7 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr)
if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
struct cntrl_cur_lay3 c;
+ memset(&c, 0, sizeof(struct cntrl_cur_lay3));
if (entity_id == USB_IN_CLK_ID)
c.dCUR = p_srate;
diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c
index d62683017cf3..990df221c629 100644
--- a/drivers/usb/gadget/function/storage_common.c
+++ b/drivers/usb/gadget/function/storage_common.c
@@ -83,9 +83,7 @@ EXPORT_SYMBOL_GPL(fsg_fs_function);
* USB 2.0 devices need to expose both high speed and full speed
* descriptors, unless they only run at full speed.
*
- * That means alternate endpoint descriptors (bigger packets)
- * and a "device qualifier" ... plus more construction options
- * for the configuration descriptor.
+ * That means alternate endpoint descriptors (bigger packets).
*/
struct usb_endpoint_descriptor fsg_hs_bulk_in_desc = {
.bLength = USB_DT_ENDPOINT_SIZE,
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index e64479f882a5..aa3707bdebb4 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -938,8 +938,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr)
struct usb_ep *ep = dev->gadget->ep0;
struct usb_request *req = dev->req;
- if ((retval = setup_req (ep, req, 0)) == 0)
- retval = usb_ep_queue (ep, req, GFP_ATOMIC);
+ if ((retval = setup_req (ep, req, 0)) == 0) {
+ spin_unlock_irq (&dev->lock);
+ retval = usb_ep_queue (ep, req, GFP_KERNEL);
+ spin_lock_irq (&dev->lock);
+ }
dev->state = STATE_DEV_CONNECTED;
/* assume that was SET_CONFIGURATION */
@@ -1457,8 +1460,11 @@ delegate:
w_length);
if (value < 0)
break;
+
+ spin_unlock (&dev->lock);
value = usb_ep_queue (gadget->ep0, dev->req,
- GFP_ATOMIC);
+ GFP_KERNEL);
+ spin_lock (&dev->lock);
if (value < 0) {
clean_req (gadget->ep0, dev->req);
break;
@@ -1481,11 +1487,14 @@ delegate:
if (value >= 0 && dev->state != STATE_DEV_SETUP) {
req->length = value;
req->zero = value < w_length;
- value = usb_ep_queue (gadget->ep0, req, GFP_ATOMIC);
+
+ spin_unlock (&dev->lock);
+ value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL);
if (value < 0) {
DBG (dev, "ep_queue --> %d\n", value);
req->status = 0;
}
+ return value;
}
/* device stalls when value < 0 */
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index 6e8300d6a737..e1b2dcebdc2e 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -603,11 +603,15 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver)
}
}
- list_add_tail(&driver->pending, &gadget_driver_pending_list);
- pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n",
- driver->function);
+ if (!driver->match_existing_only) {
+ list_add_tail(&driver->pending, &gadget_driver_pending_list);
+ pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n",
+ driver->function);
+ ret = 0;
+ }
+
mutex_unlock(&udc_lock);
- return 0;
+ return ret;
found:
ret = udc_bind_to_driver(udc, driver);
mutex_unlock(&udc_lock);
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index ae1b6e69eb96..a962b89b65a6 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -368,6 +368,15 @@ static void ehci_shutdown(struct usb_hcd *hcd)
{
struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+ /**
+ * Protect the system from crashing at system shutdown in cases where
+ * usb host is not added yet from OTG controller driver.
+ * As ehci_setup() not done yet, so stop accessing registers or
+ * variables initialized in ehci_setup()
+ */
+ if (!ehci->sbrn)
+ return;
+
spin_lock_irq(&ehci->lock);
ehci->shutdown = true;
ehci->rh_state = EHCI_RH_STOPPING;
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index ffc90295a95f..74f62d68f013 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -872,15 +872,23 @@ int ehci_hub_control(
) {
struct ehci_hcd *ehci = hcd_to_ehci (hcd);
int ports = HCS_N_PORTS (ehci->hcs_params);
- u32 __iomem *status_reg = &ehci->regs->port_status[
- (wIndex & 0xff) - 1];
- u32 __iomem *hostpc_reg = &ehci->regs->hostpc[(wIndex & 0xff) - 1];
+ u32 __iomem *status_reg, *hostpc_reg;
u32 temp, temp1, status;
unsigned long flags;
int retval = 0;
unsigned selector;
/*
+ * Avoid underflow while calculating (wIndex & 0xff) - 1.
+ * The compiler might deduce that wIndex can never be 0 and then
+ * optimize away the tests for !wIndex below.
+ */
+ temp = wIndex & 0xff;
+ temp -= (temp > 0);
+ status_reg = &ehci->regs->port_status[temp];
+ hostpc_reg = &ehci->regs->hostpc[temp];
+
+ /*
* FIXME: support SetPortFeatures USB_PORT_FEAT_INDICATOR.
* HCS_INDICATOR may say we can change LEDs to off/amber/green.
* (track current state ourselves) ... blink for diagnostics,
diff --git a/drivers/usb/host/ehci-msm.c b/drivers/usb/host/ehci-msm.c
index d3afc89d00f5..2f8d3af811ce 100644
--- a/drivers/usb/host/ehci-msm.c
+++ b/drivers/usb/host/ehci-msm.c
@@ -179,22 +179,32 @@ static int ehci_msm_remove(struct platform_device *pdev)
static int ehci_msm_pm_suspend(struct device *dev)
{
struct usb_hcd *hcd = dev_get_drvdata(dev);
+ struct ehci_hcd *ehci = hcd_to_ehci(hcd);
bool do_wakeup = device_may_wakeup(dev);
dev_dbg(dev, "ehci-msm PM suspend\n");
- return ehci_suspend(hcd, do_wakeup);
+ /* Only call ehci_suspend if ehci_setup has been done */
+ if (ehci->sbrn)
+ return ehci_suspend(hcd, do_wakeup);
+
+ return 0;
}
static int ehci_msm_pm_resume(struct device *dev)
{
struct usb_hcd *hcd = dev_get_drvdata(dev);
+ struct ehci_hcd *ehci = hcd_to_ehci(hcd);
dev_dbg(dev, "ehci-msm PM resume\n");
- ehci_resume(hcd, false);
+
+ /* Only call ehci_resume if ehci_setup has been done */
+ if (ehci->sbrn)
+ ehci_resume(hcd, false);
return 0;
}
+
#else
#define ehci_msm_pm_suspend NULL
#define ehci_msm_pm_resume NULL
diff --git a/drivers/usb/host/ehci-st.c b/drivers/usb/host/ehci-st.c
index a94ed677d937..be4a2788fc58 100644
--- a/drivers/usb/host/ehci-st.c
+++ b/drivers/usb/host/ehci-st.c
@@ -206,7 +206,8 @@ static int st_ehci_platform_probe(struct platform_device *dev)
priv->clk48 = NULL;
}
- priv->pwr = devm_reset_control_get_optional(&dev->dev, "power");
+ priv->pwr =
+ devm_reset_control_get_optional_shared(&dev->dev, "power");
if (IS_ERR(priv->pwr)) {
err = PTR_ERR(priv->pwr);
if (err == -EPROBE_DEFER)
@@ -214,7 +215,8 @@ static int st_ehci_platform_probe(struct platform_device *dev)
priv->pwr = NULL;
}
- priv->rst = devm_reset_control_get_optional(&dev->dev, "softreset");
+ priv->rst =
+ devm_reset_control_get_optional_shared(&dev->dev, "softreset");
if (IS_ERR(priv->rst)) {
err = PTR_ERR(priv->rst);
if (err == -EPROBE_DEFER)
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index 4031b372008e..9a3d7db5be57 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -81,15 +81,23 @@ static int tegra_reset_usb_controller(struct platform_device *pdev)
struct usb_hcd *hcd = platform_get_drvdata(pdev);
struct tegra_ehci_hcd *tegra =
(struct tegra_ehci_hcd *)hcd_to_ehci(hcd)->priv;
+ bool has_utmi_pad_registers = false;
phy_np = of_parse_phandle(pdev->dev.of_node, "nvidia,phy", 0);
if (!phy_np)
return -ENOENT;
+ if (of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers"))
+ has_utmi_pad_registers = true;
+
if (!usb1_reset_attempted) {
struct reset_control *usb1_reset;
- usb1_reset = of_reset_control_get(phy_np, "usb");
+ if (!has_utmi_pad_registers)
+ usb1_reset = of_reset_control_get(phy_np, "utmi-pads");
+ else
+ usb1_reset = tegra->rst;
+
if (IS_ERR(usb1_reset)) {
dev_warn(&pdev->dev,
"can't get utmi-pads reset from the PHY\n");
@@ -99,13 +107,15 @@ static int tegra_reset_usb_controller(struct platform_device *pdev)
reset_control_assert(usb1_reset);
udelay(1);
reset_control_deassert(usb1_reset);
+
+ if (!has_utmi_pad_registers)
+ reset_control_put(usb1_reset);
}
- reset_control_put(usb1_reset);
usb1_reset_attempted = true;
}
- if (!of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers")) {
+ if (!has_utmi_pad_registers) {
reset_control_assert(tegra->rst);
udelay(1);
reset_control_deassert(tegra->rst);
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index d029bbe9eb36..641fed609911 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -183,7 +183,6 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed)
{
int branch;
- ed->state = ED_OPER;
ed->ed_prev = NULL;
ed->ed_next = NULL;
ed->hwNextED = 0;
@@ -259,6 +258,8 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed)
/* the HC may not see the schedule updates yet, but if it does
* then they'll be properly ordered.
*/
+
+ ed->state = ED_OPER;
return 0;
}
diff --git a/drivers/usb/host/ohci-st.c b/drivers/usb/host/ohci-st.c
index acf2eb2a5676..02816a1515a1 100644
--- a/drivers/usb/host/ohci-st.c
+++ b/drivers/usb/host/ohci-st.c
@@ -188,13 +188,15 @@ static int st_ohci_platform_probe(struct platform_device *dev)
priv->clk48 = NULL;
}
- priv->pwr = devm_reset_control_get_optional(&dev->dev, "power");
+ priv->pwr =
+ devm_reset_control_get_optional_shared(&dev->dev, "power");
if (IS_ERR(priv->pwr)) {
err = PTR_ERR(priv->pwr);
goto err_put_clks;
}
- priv->rst = devm_reset_control_get_optional(&dev->dev, "softreset");
+ priv->rst =
+ devm_reset_control_get_optional_shared(&dev->dev, "softreset");
if (IS_ERR(priv->rst)) {
err = PTR_ERR(priv->rst);
goto err_put_clks;
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 48672fac7ff3..c10972fcc8e4 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -37,6 +37,7 @@
/* Device for a quirk */
#define PCI_VENDOR_ID_FRESCO_LOGIC 0x1b73
#define PCI_DEVICE_ID_FRESCO_LOGIC_PDK 0x1000
+#define PCI_DEVICE_ID_FRESCO_LOGIC_FL1009 0x1009
#define PCI_DEVICE_ID_FRESCO_LOGIC_FL1400 0x1400
#define PCI_VENDOR_ID_ETRON 0x1b6f
@@ -114,6 +115,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
}
+ if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+ pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
+ xhci->quirks |= XHCI_BROKEN_STREAMS;
+
if (pdev->vendor == PCI_VENDOR_ID_NEC)
xhci->quirks |= XHCI_NEC_HOST;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 676ea458148b..1f3f981fe7f8 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -196,6 +196,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
ret = clk_prepare_enable(clk);
if (ret)
goto put_hcd;
+ } else if (PTR_ERR(clk) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto put_hcd;
}
xhci = hcd_to_xhci(hcd);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 52deae4b7eac..d7d502578d79 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -290,6 +290,14 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
+
+ /*
+ * Writing the CMD_RING_ABORT bit should cause a cmd completion event,
+ * however on some host hw the CMD_RING_RUNNING bit is correctly cleared
+ * but the completion event in never sent. Use the cmd timeout timer to
+ * handle those cases. Use twice the time to cover the bit polling retry
+ */
+ mod_timer(&xhci->cmd_timer, jiffies + (2 * XHCI_CMD_DEFAULT_TIMEOUT));
xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
&xhci->op_regs->cmd_ring);
@@ -314,6 +322,7 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
xhci_err(xhci, "Stopped the command ring failed, "
"maybe the host is dead\n");
+ del_timer(&xhci->cmd_timer);
xhci->xhc_state |= XHCI_STATE_DYING;
xhci_quiesce(xhci);
xhci_halt(xhci);
@@ -1246,22 +1255,21 @@ void xhci_handle_command_timeout(unsigned long data)
int ret;
unsigned long flags;
u64 hw_ring_state;
- struct xhci_command *cur_cmd = NULL;
+ bool second_timeout = false;
xhci = (struct xhci_hcd *) data;
/* mark this command to be cancelled */
spin_lock_irqsave(&xhci->lock, flags);
if (xhci->current_cmd) {
- cur_cmd = xhci->current_cmd;
- cur_cmd->status = COMP_CMD_ABORT;
+ if (xhci->current_cmd->status == COMP_CMD_ABORT)
+ second_timeout = true;
+ xhci->current_cmd->status = COMP_CMD_ABORT;
}
-
/* Make sure command ring is running before aborting it */
hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) &&
(hw_ring_state & CMD_RING_RUNNING)) {
-
spin_unlock_irqrestore(&xhci->lock, flags);
xhci_dbg(xhci, "Command timeout\n");
ret = xhci_abort_cmd_ring(xhci);
@@ -1273,6 +1281,15 @@ void xhci_handle_command_timeout(unsigned long data)
}
return;
}
+
+ /* command ring failed to restart, or host removed. Bail out */
+ if (second_timeout || xhci->xhc_state & XHCI_STATE_REMOVING) {
+ spin_unlock_irqrestore(&xhci->lock, flags);
+ xhci_dbg(xhci, "command timed out twice, ring start fail?\n");
+ xhci_cleanup_command_queue(xhci);
+ return;
+ }
+
/* command timeout on stopped ring, ring can't be aborted */
xhci_dbg(xhci, "Command timeout on stopped ring\n");
xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd);
@@ -2721,7 +2738,8 @@ hw_died:
writel(irq_pending, &xhci->ir_set->irq_pending);
}
- if (xhci->xhc_state & XHCI_STATE_DYING) {
+ if (xhci->xhc_state & XHCI_STATE_DYING ||
+ xhci->xhc_state & XHCI_STATE_HALTED) {
xhci_dbg(xhci, "xHCI dying, ignoring interrupt. "
"Shouldn't IRQs be disabled?\n");
/* Clear the event handler busy flag (RW1C);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index fa7e1ef36cd9..f2f9518c53ab 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -685,20 +685,23 @@ void xhci_stop(struct usb_hcd *hcd)
u32 temp;
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
- if (xhci->xhc_state & XHCI_STATE_HALTED)
- return;
-
mutex_lock(&xhci->mutex);
- spin_lock_irq(&xhci->lock);
- xhci->xhc_state |= XHCI_STATE_HALTED;
- xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
- /* Make sure the xHC is halted for a USB3 roothub
- * (xhci_stop() could be called as part of failed init).
- */
- xhci_halt(xhci);
- xhci_reset(xhci);
- spin_unlock_irq(&xhci->lock);
+ if (!(xhci->xhc_state & XHCI_STATE_HALTED)) {
+ spin_lock_irq(&xhci->lock);
+
+ xhci->xhc_state |= XHCI_STATE_HALTED;
+ xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+ xhci_halt(xhci);
+ xhci_reset(xhci);
+
+ spin_unlock_irq(&xhci->lock);
+ }
+
+ if (!usb_hcd_is_primary_hcd(hcd)) {
+ mutex_unlock(&xhci->mutex);
+ return;
+ }
xhci_cleanup_msix(xhci);
@@ -4886,7 +4889,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
xhci->hcc_params2 = readl(&xhci->cap_regs->hcc_params2);
xhci_print_registers(xhci);
- xhci->quirks = quirks;
+ xhci->quirks |= quirks;
get_quirks(dev, xhci);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 39fd95833eb8..f824336def5c 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1090,29 +1090,6 @@ void musb_stop(struct musb *musb)
musb_platform_try_idle(musb, 0);
}
-static void musb_shutdown(struct platform_device *pdev)
-{
- struct musb *musb = dev_to_musb(&pdev->dev);
- unsigned long flags;
-
- pm_runtime_get_sync(musb->controller);
-
- musb_host_cleanup(musb);
- musb_gadget_cleanup(musb);
-
- spin_lock_irqsave(&musb->lock, flags);
- musb_platform_disable(musb);
- musb_generic_disable(musb);
- spin_unlock_irqrestore(&musb->lock, flags);
-
- musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
- musb_platform_exit(musb);
-
- pm_runtime_put(musb->controller);
- /* FIXME power down */
-}
-
-
/*-------------------------------------------------------------------------*/
/*
@@ -1702,7 +1679,7 @@ EXPORT_SYMBOL_GPL(musb_dma_completion);
#define use_dma 0
#endif
-static void (*musb_phy_callback)(enum musb_vbus_id_status status);
+static int (*musb_phy_callback)(enum musb_vbus_id_status status);
/*
* musb_mailbox - optional phy notifier function
@@ -1711,11 +1688,12 @@ static void (*musb_phy_callback)(enum musb_vbus_id_status status);
* Optionally gets called from the USB PHY. Note that the USB PHY must be
* disabled at the point the phy_callback is registered or unregistered.
*/
-void musb_mailbox(enum musb_vbus_id_status status)
+int musb_mailbox(enum musb_vbus_id_status status)
{
if (musb_phy_callback)
- musb_phy_callback(status);
+ return musb_phy_callback(status);
+ return -ENODEV;
};
EXPORT_SYMBOL_GPL(musb_mailbox);
@@ -2028,11 +2006,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
musb_readl = musb_default_readl;
musb_writel = musb_default_writel;
- /* We need musb_read/write functions initialized for PM */
- pm_runtime_use_autosuspend(musb->controller);
- pm_runtime_set_autosuspend_delay(musb->controller, 200);
- pm_runtime_enable(musb->controller);
-
/* The musb_platform_init() call:
* - adjusts musb->mregs
* - sets the musb->isr
@@ -2134,6 +2107,16 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
if (musb->ops->phy_callback)
musb_phy_callback = musb->ops->phy_callback;
+ /*
+ * We need musb_read/write functions initialized for PM.
+ * Note that at least 2430 glue needs autosuspend delay
+ * somewhere above 300 ms for the hardware to idle properly
+ * after disconnecting the cable in host mode. Let's use
+ * 500 ms for some margin.
+ */
+ pm_runtime_use_autosuspend(musb->controller);
+ pm_runtime_set_autosuspend_delay(musb->controller, 500);
+ pm_runtime_enable(musb->controller);
pm_runtime_get_sync(musb->controller);
status = usb_phy_init(musb->xceiv);
@@ -2237,13 +2220,8 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
if (status)
goto fail5;
- pm_runtime_put(musb->controller);
-
- /*
- * For why this is currently needed, see commit 3e43a0725637
- * ("usb: musb: core: add pm_runtime_irq_safe()")
- */
- pm_runtime_irq_safe(musb->controller);
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
return 0;
@@ -2265,7 +2243,9 @@ fail2_5:
usb_phy_shutdown(musb->xceiv);
err_usb_phy_init:
+ pm_runtime_dont_use_autosuspend(musb->controller);
pm_runtime_put_sync(musb->controller);
+ pm_runtime_disable(musb->controller);
fail2:
if (musb->irq_wake)
@@ -2273,7 +2253,6 @@ fail2:
musb_platform_exit(musb);
fail1:
- pm_runtime_disable(musb->controller);
dev_err(musb->controller,
"musb_init_controller failed with status %d\n", status);
@@ -2312,6 +2291,7 @@ static int musb_remove(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct musb *musb = dev_to_musb(dev);
+ unsigned long flags;
/* this gets called on rmmod.
* - Host mode: host may still be active
@@ -2319,17 +2299,26 @@ static int musb_remove(struct platform_device *pdev)
* - OTG mode: both roles are deactivated (or never-activated)
*/
musb_exit_debugfs(musb);
- musb_shutdown(pdev);
- musb_phy_callback = NULL;
-
- if (musb->dma_controller)
- musb_dma_controller_destroy(musb->dma_controller);
-
- usb_phy_shutdown(musb->xceiv);
cancel_work_sync(&musb->irq_work);
cancel_delayed_work_sync(&musb->finish_resume_work);
cancel_delayed_work_sync(&musb->deassert_reset_work);
+ pm_runtime_get_sync(musb->controller);
+ musb_host_cleanup(musb);
+ musb_gadget_cleanup(musb);
+ spin_lock_irqsave(&musb->lock, flags);
+ musb_platform_disable(musb);
+ musb_generic_disable(musb);
+ spin_unlock_irqrestore(&musb->lock, flags);
+ musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
+ pm_runtime_dont_use_autosuspend(musb->controller);
+ pm_runtime_put_sync(musb->controller);
+ pm_runtime_disable(musb->controller);
+ musb_platform_exit(musb);
+ musb_phy_callback = NULL;
+ if (musb->dma_controller)
+ musb_dma_controller_destroy(musb->dma_controller);
+ usb_phy_shutdown(musb->xceiv);
musb_free(musb);
device_init_wakeup(dev, 0);
return 0;
@@ -2429,7 +2418,8 @@ static void musb_restore_context(struct musb *musb)
musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe);
musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe);
musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe);
- musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl);
+ if (musb->context.devctl & MUSB_DEVCTL_SESSION)
+ musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl);
for (i = 0; i < musb->config->num_eps; ++i) {
struct musb_hw_ep *hw_ep;
@@ -2612,7 +2602,6 @@ static struct platform_driver musb_driver = {
},
.probe = musb_probe,
.remove = musb_remove,
- .shutdown = musb_shutdown,
};
module_platform_driver(musb_driver);
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index b6afe9e43305..b55a776b03eb 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -215,7 +215,7 @@ struct musb_platform_ops {
dma_addr_t *dma_addr, u32 *len);
void (*pre_root_reset_end)(struct musb *musb);
void (*post_root_reset_end)(struct musb *musb);
- void (*phy_callback)(enum musb_vbus_id_status status);
+ int (*phy_callback)(enum musb_vbus_id_status status);
};
/*
@@ -312,6 +312,7 @@ struct musb {
struct work_struct irq_work;
struct delayed_work deassert_reset_work;
struct delayed_work finish_resume_work;
+ struct delayed_work gadget_work;
u16 hwvers;
u16 intrrxe;
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index 152865b36522..af2a3a7addf9 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1656,6 +1656,20 @@ static int musb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA)
return usb_phy_set_power(musb->xceiv, mA);
}
+static void musb_gadget_work(struct work_struct *work)
+{
+ struct musb *musb;
+ unsigned long flags;
+
+ musb = container_of(work, struct musb, gadget_work.work);
+ pm_runtime_get_sync(musb->controller);
+ spin_lock_irqsave(&musb->lock, flags);
+ musb_pullup(musb, musb->softconnect);
+ spin_unlock_irqrestore(&musb->lock, flags);
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
+}
+
static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on)
{
struct musb *musb = gadget_to_musb(gadget);
@@ -1663,20 +1677,16 @@ static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on)
is_on = !!is_on;
- pm_runtime_get_sync(musb->controller);
-
/* NOTE: this assumes we are sensing vbus; we'd rather
* not pullup unless the B-session is active.
*/
spin_lock_irqsave(&musb->lock, flags);
if (is_on != musb->softconnect) {
musb->softconnect = is_on;
- musb_pullup(musb, is_on);
+ schedule_delayed_work(&musb->gadget_work, 0);
}
spin_unlock_irqrestore(&musb->lock, flags);
- pm_runtime_put(musb->controller);
-
return 0;
}
@@ -1845,7 +1855,7 @@ int musb_gadget_setup(struct musb *musb)
#elif IS_ENABLED(CONFIG_USB_MUSB_GADGET)
musb->g.is_otg = 0;
#endif
-
+ INIT_DELAYED_WORK(&musb->gadget_work, musb_gadget_work);
musb_g_init_endpoints(musb);
musb->is_active = 0;
@@ -1866,6 +1876,8 @@ void musb_gadget_cleanup(struct musb *musb)
{
if (musb->port_mode == MUSB_PORT_MODE_HOST)
return;
+
+ cancel_delayed_work_sync(&musb->gadget_work);
usb_del_gadget_udc(&musb->g);
}
@@ -1914,8 +1926,8 @@ static int musb_gadget_start(struct usb_gadget *g,
if (musb->xceiv->last_event == USB_EVENT_ID)
musb_platform_set_vbus(musb, 1);
- if (musb->xceiv->last_event == USB_EVENT_NONE)
- pm_runtime_put(musb->controller);
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
return 0;
@@ -1934,8 +1946,7 @@ static int musb_gadget_stop(struct usb_gadget *g)
struct musb *musb = gadget_to_musb(g);
unsigned long flags;
- if (musb->xceiv->last_event == USB_EVENT_NONE)
- pm_runtime_get_sync(musb->controller);
+ pm_runtime_get_sync(musb->controller);
/*
* REVISIT always use otg_set_peripheral() here too;
@@ -1963,7 +1974,8 @@ static int musb_gadget_stop(struct usb_gadget *g)
* that currently misbehaves.
*/
- pm_runtime_put(musb->controller);
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
return 0;
}
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 2f8ad7f1f482..d227a71d85e1 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -434,7 +434,13 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb,
}
}
- if (qh != NULL && qh->is_ready) {
+ /*
+ * The pipe must be broken if current urb->status is set, so don't
+ * start next urb.
+ * TODO: to minimize the risk of regression, only check urb->status
+ * for RX, until we have a test case to understand the behavior of TX.
+ */
+ if ((!status || !is_in) && qh && qh->is_ready) {
dev_dbg(musb->controller, "... next ep%d %cX urb %p\n",
hw_ep->epnum, is_in ? 'R' : 'T', next_urb(qh));
musb_start_urb(musb, is_in, qh);
@@ -594,14 +600,13 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum)
musb_writew(ep->regs, MUSB_TXCSR, 0);
/* scrub all previous state, clearing toggle */
- } else {
- csr = musb_readw(ep->regs, MUSB_RXCSR);
- if (csr & MUSB_RXCSR_RXPKTRDY)
- WARNING("rx%d, packet/%d ready?\n", ep->epnum,
- musb_readw(ep->regs, MUSB_RXCOUNT));
-
- musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
}
+ csr = musb_readw(ep->regs, MUSB_RXCSR);
+ if (csr & MUSB_RXCSR_RXPKTRDY)
+ WARNING("rx%d, packet/%d ready?\n", ep->epnum,
+ musb_readw(ep->regs, MUSB_RXCOUNT));
+
+ musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
/* target addr and (for multipoint) hub addr/port */
if (musb->is_multipoint) {
@@ -627,7 +632,7 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum)
ep->rx_reinit = 0;
}
-static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
+static void musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
struct musb_hw_ep *hw_ep, struct musb_qh *qh,
struct urb *urb, u32 offset,
u32 *length, u8 *mode)
@@ -664,23 +669,18 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
}
channel->desired_mode = *mode;
musb_writew(epio, MUSB_TXCSR, csr);
-
- return 0;
}
-static int musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma,
- struct musb_hw_ep *hw_ep,
- struct musb_qh *qh,
- struct urb *urb,
- u32 offset,
- u32 *length,
- u8 *mode)
+static void musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma,
+ struct musb_hw_ep *hw_ep,
+ struct musb_qh *qh,
+ struct urb *urb,
+ u32 offset,
+ u32 *length,
+ u8 *mode)
{
struct dma_channel *channel = hw_ep->tx_channel;
- if (!is_cppi_enabled(hw_ep->musb) && !tusb_dma_omap(hw_ep->musb))
- return -ENODEV;
-
channel->actual_len = 0;
/*
@@ -688,8 +688,6 @@ static int musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma,
* to identify the zero-length-final-packet case.
*/
*mode = (urb->transfer_flags & URB_ZERO_PACKET) ? 1 : 0;
-
- return 0;
}
static bool musb_tx_dma_program(struct dma_controller *dma,
@@ -699,15 +697,14 @@ static bool musb_tx_dma_program(struct dma_controller *dma,
struct dma_channel *channel = hw_ep->tx_channel;
u16 pkt_size = qh->maxpacket;
u8 mode;
- int res;
if (musb_dma_inventra(hw_ep->musb) || musb_dma_ux500(hw_ep->musb))
- res = musb_tx_dma_set_mode_mentor(dma, hw_ep, qh, urb,
- offset, &length, &mode);
+ musb_tx_dma_set_mode_mentor(dma, hw_ep, qh, urb, offset,
+ &length, &mode);
+ else if (is_cppi_enabled(hw_ep->musb) || tusb_dma_omap(hw_ep->musb))
+ musb_tx_dma_set_mode_cppi_tusb(dma, hw_ep, qh, urb, offset,
+ &length, &mode);
else
- res = musb_tx_dma_set_mode_cppi_tusb(dma, hw_ep, qh, urb,
- offset, &length, &mode);
- if (res)
return false;
qh->segsize = length;
@@ -995,9 +992,15 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep,
if (is_in) {
dma = is_dma_capable() ? ep->rx_channel : NULL;
- /* clear nak timeout bit */
+ /*
+ * Need to stop the transaction by clearing REQPKT first
+ * then the NAK Timeout bit ref MUSBMHDRC USB 2.0 HIGH-SPEED
+ * DUAL-ROLE CONTROLLER Programmer's Guide, section 9.2.2
+ */
rx_csr = musb_readw(epio, MUSB_RXCSR);
rx_csr |= MUSB_RXCSR_H_WZC_BITS;
+ rx_csr &= ~MUSB_RXCSR_H_REQPKT;
+ musb_writew(epio, MUSB_RXCSR, rx_csr);
rx_csr &= ~MUSB_RXCSR_DATAERROR;
musb_writew(epio, MUSB_RXCSR, rx_csr);
@@ -1551,7 +1554,7 @@ static int musb_rx_dma_iso_cppi41(struct dma_controller *dma,
struct urb *urb,
size_t len)
{
- struct dma_channel *channel = hw_ep->tx_channel;
+ struct dma_channel *channel = hw_ep->rx_channel;
void __iomem *epio = hw_ep->regs;
dma_addr_t *buf;
u32 length, res;
@@ -1870,6 +1873,9 @@ void musb_host_rx(struct musb *musb, u8 epnum)
status = -EPROTO;
musb_writeb(epio, MUSB_RXINTERVAL, 0);
+ rx_csr &= ~MUSB_RXCSR_H_ERROR;
+ musb_writew(epio, MUSB_RXCSR, rx_csr);
+
} else if (rx_csr & MUSB_RXCSR_DATAERROR) {
if (USB_ENDPOINT_XFER_ISOC != qh->type) {
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index c84e0322c108..0b4cec940386 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -49,97 +49,14 @@ struct omap2430_glue {
enum musb_vbus_id_status status;
struct work_struct omap_musb_mailbox_work;
struct device *control_otghs;
+ bool cable_connected;
+ bool enabled;
+ bool powered;
};
#define glue_to_musb(g) platform_get_drvdata(g->musb)
static struct omap2430_glue *_glue;
-static struct timer_list musb_idle_timer;
-
-static void musb_do_idle(unsigned long _musb)
-{
- struct musb *musb = (void *)_musb;
- unsigned long flags;
- u8 power;
- u8 devctl;
-
- spin_lock_irqsave(&musb->lock, flags);
-
- switch (musb->xceiv->otg->state) {
- case OTG_STATE_A_WAIT_BCON:
-
- devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
- if (devctl & MUSB_DEVCTL_BDEVICE) {
- musb->xceiv->otg->state = OTG_STATE_B_IDLE;
- MUSB_DEV_MODE(musb);
- } else {
- musb->xceiv->otg->state = OTG_STATE_A_IDLE;
- MUSB_HST_MODE(musb);
- }
- break;
- case OTG_STATE_A_SUSPEND:
- /* finish RESUME signaling? */
- if (musb->port1_status & MUSB_PORT_STAT_RESUME) {
- power = musb_readb(musb->mregs, MUSB_POWER);
- power &= ~MUSB_POWER_RESUME;
- dev_dbg(musb->controller, "root port resume stopped, power %02x\n", power);
- musb_writeb(musb->mregs, MUSB_POWER, power);
- musb->is_active = 1;
- musb->port1_status &= ~(USB_PORT_STAT_SUSPEND
- | MUSB_PORT_STAT_RESUME);
- musb->port1_status |= USB_PORT_STAT_C_SUSPEND << 16;
- usb_hcd_poll_rh_status(musb->hcd);
- /* NOTE: it might really be A_WAIT_BCON ... */
- musb->xceiv->otg->state = OTG_STATE_A_HOST;
- }
- break;
- case OTG_STATE_A_HOST:
- devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
- if (devctl & MUSB_DEVCTL_BDEVICE)
- musb->xceiv->otg->state = OTG_STATE_B_IDLE;
- else
- musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
- default:
- break;
- }
- spin_unlock_irqrestore(&musb->lock, flags);
-}
-
-
-static void omap2430_musb_try_idle(struct musb *musb, unsigned long timeout)
-{
- unsigned long default_timeout = jiffies + msecs_to_jiffies(3);
- static unsigned long last_timer;
-
- if (timeout == 0)
- timeout = default_timeout;
-
- /* Never idle if active, or when VBUS timeout is not set as host */
- if (musb->is_active || ((musb->a_wait_bcon == 0)
- && (musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON))) {
- dev_dbg(musb->controller, "%s active, deleting timer\n",
- usb_otg_state_string(musb->xceiv->otg->state));
- del_timer(&musb_idle_timer);
- last_timer = jiffies;
- return;
- }
-
- if (time_after(last_timer, timeout)) {
- if (!timer_pending(&musb_idle_timer))
- last_timer = timeout;
- else {
- dev_dbg(musb->controller, "Longer idle timer already pending, ignoring\n");
- return;
- }
- }
- last_timer = timeout;
-
- dev_dbg(musb->controller, "%s inactive, for idle timer for %lu ms\n",
- usb_otg_state_string(musb->xceiv->otg->state),
- (unsigned long)jiffies_to_msecs(timeout - jiffies));
- mod_timer(&musb_idle_timer, timeout);
-}
-
static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
{
struct usb_otg *otg = musb->xceiv->otg;
@@ -205,16 +122,6 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
musb_readb(musb->mregs, MUSB_DEVCTL));
}
-static int omap2430_musb_set_mode(struct musb *musb, u8 musb_mode)
-{
- u8 devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
-
- devctl |= MUSB_DEVCTL_SESSION;
- musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
-
- return 0;
-}
-
static inline void omap2430_low_level_exit(struct musb *musb)
{
u32 l;
@@ -234,22 +141,63 @@ static inline void omap2430_low_level_init(struct musb *musb)
musb_writel(musb->mregs, OTG_FORCESTDBY, l);
}
-static void omap2430_musb_mailbox(enum musb_vbus_id_status status)
+/*
+ * We can get multiple cable events so we need to keep track
+ * of the power state. Only keep power enabled if USB cable is
+ * connected and a gadget is started.
+ */
+static void omap2430_set_power(struct musb *musb, bool enabled, bool cable)
+{
+ struct device *dev = musb->controller;
+ struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
+ bool power_up;
+ int res;
+
+ if (glue->enabled != enabled)
+ glue->enabled = enabled;
+
+ if (glue->cable_connected != cable)
+ glue->cable_connected = cable;
+
+ power_up = glue->enabled && glue->cable_connected;
+ if (power_up == glue->powered) {
+ dev_warn(musb->controller, "power state already %i\n",
+ power_up);
+ return;
+ }
+
+ glue->powered = power_up;
+
+ if (power_up) {
+ res = pm_runtime_get_sync(musb->controller);
+ if (res < 0) {
+ dev_err(musb->controller, "could not enable: %i", res);
+ glue->powered = false;
+ }
+ } else {
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
+ }
+}
+
+static int omap2430_musb_mailbox(enum musb_vbus_id_status status)
{
struct omap2430_glue *glue = _glue;
if (!glue) {
pr_err("%s: musb core is not yet initialized\n", __func__);
- return;
+ return -EPROBE_DEFER;
}
glue->status = status;
if (!glue_to_musb(glue)) {
pr_err("%s: musb core is not yet ready\n", __func__);
- return;
+ return -EPROBE_DEFER;
}
schedule_work(&glue->omap_musb_mailbox_work);
+
+ return 0;
}
static void omap_musb_set_mailbox(struct omap2430_glue *glue)
@@ -259,6 +207,13 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev);
struct omap_musb_board_data *data = pdata->board_data;
struct usb_otg *otg = musb->xceiv->otg;
+ bool cable_connected;
+
+ cable_connected = ((glue->status == MUSB_ID_GROUND) ||
+ (glue->status == MUSB_VBUS_VALID));
+
+ if (cable_connected)
+ omap2430_set_power(musb, glue->enabled, cable_connected);
switch (glue->status) {
case MUSB_ID_GROUND:
@@ -268,7 +223,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
musb->xceiv->otg->state = OTG_STATE_A_IDLE;
musb->xceiv->last_event = USB_EVENT_ID;
if (musb->gadget_driver) {
- pm_runtime_get_sync(dev);
omap_control_usb_set_mode(glue->control_otghs,
USB_MODE_HOST);
omap2430_musb_set_vbus(musb, 1);
@@ -281,8 +235,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
otg->default_a = false;
musb->xceiv->otg->state = OTG_STATE_B_IDLE;
musb->xceiv->last_event = USB_EVENT_VBUS;
- if (musb->gadget_driver)
- pm_runtime_get_sync(dev);
omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DEVICE);
break;
@@ -291,11 +243,8 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
dev_dbg(dev, "VBUS Disconnect\n");
musb->xceiv->last_event = USB_EVENT_NONE;
- if (musb->gadget_driver) {
+ if (musb->gadget_driver)
omap2430_musb_set_vbus(musb, 0);
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
- }
if (data->interface_type == MUSB_INTERFACE_UTMI)
otg_set_vbus(musb->xceiv->otg, 0);
@@ -307,6 +256,9 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
dev_dbg(dev, "ID float\n");
}
+ if (!cable_connected)
+ omap2430_set_power(musb, glue->enabled, cable_connected);
+
atomic_notifier_call_chain(&musb->xceiv->notifier,
musb->xceiv->last_event, NULL);
}
@@ -316,13 +268,8 @@ static void omap_musb_mailbox_work(struct work_struct *mailbox_work)
{
struct omap2430_glue *glue = container_of(mailbox_work,
struct omap2430_glue, omap_musb_mailbox_work);
- struct musb *musb = glue_to_musb(glue);
- struct device *dev = musb->controller;
- pm_runtime_get_sync(dev);
omap_musb_set_mailbox(glue);
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
}
static irqreturn_t omap2430_musb_interrupt(int irq, void *__hci)
@@ -389,23 +336,7 @@ static int omap2430_musb_init(struct musb *musb)
return PTR_ERR(musb->phy);
}
musb->isr = omap2430_musb_interrupt;
-
- /*
- * Enable runtime PM for musb parent (this driver). We can't
- * do it earlier as struct musb is not yet allocated and we
- * need to touch the musb registers for runtime PM.
- */
- pm_runtime_enable(glue->dev);
- status = pm_runtime_get_sync(glue->dev);
- if (status < 0)
- goto err1;
-
- status = pm_runtime_get_sync(dev);
- if (status < 0) {
- dev_err(dev, "pm_runtime_get_sync FAILED %d\n", status);
- pm_runtime_put_sync(glue->dev);
- goto err1;
- }
+ phy_init(musb->phy);
l = musb_readl(musb->mregs, OTG_INTERFSEL);
@@ -427,20 +358,10 @@ static int omap2430_musb_init(struct musb *musb)
musb_readl(musb->mregs, OTG_INTERFSEL),
musb_readl(musb->mregs, OTG_SIMENABLE));
- setup_timer(&musb_idle_timer, musb_do_idle, (unsigned long) musb);
-
if (glue->status != MUSB_UNKNOWN)
omap_musb_set_mailbox(glue);
- phy_init(musb->phy);
- phy_power_on(musb->phy);
-
- pm_runtime_put_noidle(musb->controller);
- pm_runtime_put_noidle(glue->dev);
return 0;
-
-err1:
- return status;
}
static void omap2430_musb_enable(struct musb *musb)
@@ -452,6 +373,11 @@ static void omap2430_musb_enable(struct musb *musb)
struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev);
struct omap_musb_board_data *data = pdata->board_data;
+ if (!WARN_ON(!musb->phy))
+ phy_power_on(musb->phy);
+
+ omap2430_set_power(musb, true, glue->cable_connected);
+
switch (glue->status) {
case MUSB_ID_GROUND:
@@ -487,18 +413,25 @@ static void omap2430_musb_disable(struct musb *musb)
struct device *dev = musb->controller;
struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
+ if (!WARN_ON(!musb->phy))
+ phy_power_off(musb->phy);
+
if (glue->status != MUSB_UNKNOWN)
omap_control_usb_set_mode(glue->control_otghs,
USB_MODE_DISCONNECT);
+
+ omap2430_set_power(musb, false, glue->cable_connected);
}
static int omap2430_musb_exit(struct musb *musb)
{
- del_timer_sync(&musb_idle_timer);
+ struct device *dev = musb->controller;
+ struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
omap2430_low_level_exit(musb);
- phy_power_off(musb->phy);
phy_exit(musb->phy);
+ musb->phy = NULL;
+ cancel_work_sync(&glue->omap_musb_mailbox_work);
return 0;
}
@@ -512,9 +445,6 @@ static const struct musb_platform_ops omap2430_ops = {
.init = omap2430_musb_init,
.exit = omap2430_musb_exit,
- .set_mode = omap2430_musb_set_mode,
- .try_idle = omap2430_musb_try_idle,
-
.set_vbus = omap2430_musb_set_vbus,
.enable = omap2430_musb_enable,
@@ -639,11 +569,9 @@ static int omap2430_probe(struct platform_device *pdev)
goto err2;
}
- /*
- * Note that we cannot enable PM runtime yet for this
- * driver as we need struct musb initialized first.
- * See omap2430_musb_init above.
- */
+ pm_runtime_enable(glue->dev);
+ pm_runtime_use_autosuspend(glue->dev);
+ pm_runtime_set_autosuspend_delay(glue->dev, 500);
ret = platform_device_add(musb);
if (ret) {
@@ -662,12 +590,14 @@ err0:
static int omap2430_remove(struct platform_device *pdev)
{
- struct omap2430_glue *glue = platform_get_drvdata(pdev);
+ struct omap2430_glue *glue = platform_get_drvdata(pdev);
+ struct musb *musb = glue_to_musb(glue);
pm_runtime_get_sync(glue->dev);
- cancel_work_sync(&glue->omap_musb_mailbox_work);
platform_device_unregister(glue->musb);
+ omap2430_set_power(musb, false, false);
pm_runtime_put_sync(glue->dev);
+ pm_runtime_dont_use_autosuspend(glue->dev);
pm_runtime_disable(glue->dev);
return 0;
@@ -680,12 +610,13 @@ static int omap2430_runtime_suspend(struct device *dev)
struct omap2430_glue *glue = dev_get_drvdata(dev);
struct musb *musb = glue_to_musb(glue);
- if (musb) {
- musb->context.otg_interfsel = musb_readl(musb->mregs,
- OTG_INTERFSEL);
+ if (!musb)
+ return 0;
- omap2430_low_level_exit(musb);
- }
+ musb->context.otg_interfsel = musb_readl(musb->mregs,
+ OTG_INTERFSEL);
+
+ omap2430_low_level_exit(musb);
return 0;
}
@@ -696,7 +627,7 @@ static int omap2430_runtime_resume(struct device *dev)
struct musb *musb = glue_to_musb(glue);
if (!musb)
- return -EPROBE_DEFER;
+ return 0;
omap2430_low_level_init(musb);
musb_writel(musb->mregs, OTG_INTERFSEL,
@@ -738,18 +669,8 @@ static struct platform_driver omap2430_driver = {
},
};
+module_platform_driver(omap2430_driver);
+
MODULE_DESCRIPTION("OMAP2PLUS MUSB Glue Layer");
MODULE_AUTHOR("Felipe Balbi <balbi@ti.com>");
MODULE_LICENSE("GPL v2");
-
-static int __init omap2430_init(void)
-{
- return platform_driver_register(&omap2430_driver);
-}
-subsys_initcall(omap2430_init);
-
-static void __exit omap2430_exit(void)
-{
- platform_driver_unregister(&omap2430_driver);
-}
-module_exit(omap2430_exit);
diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c
index fdab4232cfbf..76500515dd8b 100644
--- a/drivers/usb/musb/sunxi.c
+++ b/drivers/usb/musb/sunxi.c
@@ -80,7 +80,8 @@ static struct musb *sunxi_musb;
struct sunxi_glue {
struct device *dev;
- struct platform_device *musb;
+ struct musb *musb;
+ struct platform_device *musb_pdev;
struct clk *clk;
struct reset_control *rst;
struct phy *phy;
@@ -102,7 +103,7 @@ static void sunxi_musb_work(struct work_struct *work)
return;
if (test_and_clear_bit(SUNXI_MUSB_FL_HOSTMODE_PEND, &glue->flags)) {
- struct musb *musb = platform_get_drvdata(glue->musb);
+ struct musb *musb = glue->musb;
unsigned long flags;
u8 devctl;
@@ -112,7 +113,7 @@ static void sunxi_musb_work(struct work_struct *work)
if (test_bit(SUNXI_MUSB_FL_HOSTMODE, &glue->flags)) {
set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
musb->xceiv->otg->default_a = 1;
- musb->xceiv->otg->state = OTG_STATE_A_IDLE;
+ musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
MUSB_HST_MODE(musb);
devctl |= MUSB_DEVCTL_SESSION;
} else {
@@ -145,10 +146,12 @@ static void sunxi_musb_set_vbus(struct musb *musb, int is_on)
{
struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent);
- if (is_on)
+ if (is_on) {
set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
- else
+ musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
+ } else {
clear_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
+ }
schedule_work(&glue->work);
}
@@ -264,15 +267,6 @@ static int sunxi_musb_init(struct musb *musb)
if (ret)
goto error_unregister_notifier;
- if (musb->port_mode == MUSB_PORT_MODE_HOST) {
- ret = phy_power_on(glue->phy);
- if (ret)
- goto error_phy_exit;
- set_bit(SUNXI_MUSB_FL_PHY_ON, &glue->flags);
- /* Stop musb work from turning vbus off again */
- set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
- }
-
musb->isr = sunxi_musb_interrupt;
/* Stop the musb-core from doing runtime pm (not supported on sunxi) */
@@ -280,8 +274,6 @@ static int sunxi_musb_init(struct musb *musb)
return 0;
-error_phy_exit:
- phy_exit(glue->phy);
error_unregister_notifier:
if (musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
extcon_unregister_notifier(glue->extcon, EXTCON_USB_HOST,
@@ -323,10 +315,31 @@ static int sunxi_musb_exit(struct musb *musb)
return 0;
}
+static int sunxi_set_mode(struct musb *musb, u8 mode)
+{
+ struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent);
+ int ret;
+
+ if (mode == MUSB_HOST) {
+ ret = phy_power_on(glue->phy);
+ if (ret)
+ return ret;
+
+ set_bit(SUNXI_MUSB_FL_PHY_ON, &glue->flags);
+ /* Stop musb work from turning vbus off again */
+ set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
+ musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
+ }
+
+ return 0;
+}
+
static void sunxi_musb_enable(struct musb *musb)
{
struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent);
+ glue->musb = musb;
+
/* musb_core does not call us in a balanced manner */
if (test_and_set_bit(SUNXI_MUSB_FL_ENABLED, &glue->flags))
return;
@@ -569,6 +582,7 @@ static const struct musb_platform_ops sunxi_musb_ops = {
.exit = sunxi_musb_exit,
.enable = sunxi_musb_enable,
.disable = sunxi_musb_disable,
+ .set_mode = sunxi_set_mode,
.fifo_offset = sunxi_musb_fifo_offset,
.ep_offset = sunxi_musb_ep_offset,
.busctl_offset = sunxi_musb_busctl_offset,
@@ -721,9 +735,9 @@ static int sunxi_musb_probe(struct platform_device *pdev)
pinfo.data = &pdata;
pinfo.size_data = sizeof(pdata);
- glue->musb = platform_device_register_full(&pinfo);
- if (IS_ERR(glue->musb)) {
- ret = PTR_ERR(glue->musb);
+ glue->musb_pdev = platform_device_register_full(&pinfo);
+ if (IS_ERR(glue->musb_pdev)) {
+ ret = PTR_ERR(glue->musb_pdev);
dev_err(&pdev->dev, "Error registering musb dev: %d\n", ret);
goto err_unregister_usb_phy;
}
@@ -740,7 +754,7 @@ static int sunxi_musb_remove(struct platform_device *pdev)
struct sunxi_glue *glue = platform_get_drvdata(pdev);
struct platform_device *usb_phy = glue->usb_phy;
- platform_device_unregister(glue->musb); /* Frees glue ! */
+ platform_device_unregister(glue->musb_pdev);
usb_phy_generic_unregister(usb_phy);
return 0;
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index 24e2b3cf1867..a72e8d670adc 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -97,6 +97,9 @@ struct twl6030_usb {
struct regulator *usb3v3;
+ /* used to check initial cable status after probe */
+ struct delayed_work get_status_work;
+
/* used to set vbus, in atomic path */
struct work_struct set_vbus_work;
@@ -227,12 +230,16 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl)
twl->asleep = 1;
status = MUSB_VBUS_VALID;
twl->linkstat = status;
- musb_mailbox(status);
+ ret = musb_mailbox(status);
+ if (ret)
+ twl->linkstat = MUSB_UNKNOWN;
} else {
if (twl->linkstat != MUSB_UNKNOWN) {
status = MUSB_VBUS_OFF;
twl->linkstat = status;
- musb_mailbox(status);
+ ret = musb_mailbox(status);
+ if (ret)
+ twl->linkstat = MUSB_UNKNOWN;
if (twl->asleep) {
regulator_disable(twl->usb3v3);
twl->asleep = 0;
@@ -264,7 +271,9 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl)
twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_SET);
status = MUSB_ID_GROUND;
twl->linkstat = status;
- musb_mailbox(status);
+ ret = musb_mailbox(status);
+ if (ret)
+ twl->linkstat = MUSB_UNKNOWN;
} else {
twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_CLR);
twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET);
@@ -274,6 +283,15 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl)
return IRQ_HANDLED;
}
+static void twl6030_status_work(struct work_struct *work)
+{
+ struct twl6030_usb *twl = container_of(work, struct twl6030_usb,
+ get_status_work.work);
+
+ twl6030_usb_irq(twl->irq2, twl);
+ twl6030_usbotg_irq(twl->irq1, twl);
+}
+
static int twl6030_enable_irq(struct twl6030_usb *twl)
{
twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET);
@@ -284,8 +302,6 @@ static int twl6030_enable_irq(struct twl6030_usb *twl)
REG_INT_MSK_LINE_C);
twl6030_interrupt_unmask(TWL6030_CHARGER_CTRL_INT_MASK,
REG_INT_MSK_STS_C);
- twl6030_usb_irq(twl->irq2, twl);
- twl6030_usbotg_irq(twl->irq1, twl);
return 0;
}
@@ -371,6 +387,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
dev_warn(&pdev->dev, "could not create sysfs file\n");
INIT_WORK(&twl->set_vbus_work, otg_set_vbus_work);
+ INIT_DELAYED_WORK(&twl->get_status_work, twl6030_status_work);
status = request_threaded_irq(twl->irq1, NULL, twl6030_usbotg_irq,
IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | IRQF_ONESHOT,
@@ -395,6 +412,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
twl->asleep = 0;
twl6030_enable_irq(twl);
+ schedule_delayed_work(&twl->get_status_work, HZ);
dev_info(&pdev->dev, "Initialized TWL6030 USB module\n");
return 0;
@@ -404,6 +422,7 @@ static int twl6030_usb_remove(struct platform_device *pdev)
{
struct twl6030_usb *twl = platform_get_drvdata(pdev);
+ cancel_delayed_work(&twl->get_status_work);
twl6030_interrupt_mask(TWL6030_USBOTG_INT_MASK,
REG_INT_MSK_LINE_C);
twl6030_interrupt_mask(TWL6030_USBOTG_INT_MASK,
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 2eddbe538cda..5608af4a369d 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -2007,6 +2007,7 @@ static void mos7720_release(struct usb_serial *serial)
urblist_entry)
usb_unlink_urb(urbtrack->urb);
spin_unlock_irqrestore(&mos_parport->listlock, flags);
+ parport_del_port(mos_parport->pp);
kref_put(&mos_parport->ref_count, destroy_mos_parport);
}
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 4d49fce406e1..5ef014ba6ae8 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -836,6 +836,7 @@ static int uas_slave_configure(struct scsi_device *sdev)
if (devinfo->flags & US_FL_BROKEN_FUA)
sdev->broken_fua = 1;
+ scsi_change_queue_depth(sdev, devinfo->qdepth - 2);
return 0;
}
@@ -848,7 +849,6 @@ static struct scsi_host_template uas_host_template = {
.slave_configure = uas_slave_configure,
.eh_abort_handler = uas_eh_abort_handler,
.eh_bus_reset_handler = uas_eh_bus_reset_handler,
- .can_queue = MAX_CMNDS,
.this_id = -1,
.sg_tablesize = SG_NONE,
.skip_settle_delay = 1,
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index fca51105974e..2e0450bec1b1 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -941,7 +941,7 @@ static void vhci_stop(struct usb_hcd *hcd)
static int vhci_get_frame_number(struct usb_hcd *hcd)
{
- pr_err("Not yet implemented\n");
+ dev_err_ratelimited(&hcd->self.root_hub->dev, "Not yet implemented\n");
return 0;
}
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 712a84978e97..188b1ff03f5f 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -113,6 +113,35 @@ static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
static void vfio_pci_disable(struct vfio_pci_device *vdev);
+/*
+ * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND
+ * _and_ the ability detect when the device is asserting INTx via PCI_STATUS.
+ * If a device implements the former but not the latter we would typically
+ * expect broken_intx_masking be set and require an exclusive interrupt.
+ * However since we do have control of the device's ability to assert INTx,
+ * we can instead pretend that the device does not implement INTx, virtualizing
+ * the pin register to report zero and maintaining DisINTx set on the host.
+ */
+static bool vfio_pci_nointx(struct pci_dev *pdev)
+{
+ switch (pdev->vendor) {
+ case PCI_VENDOR_ID_INTEL:
+ switch (pdev->device) {
+ /* All i40e (XL710/X710) 10/20/40GbE NICs */
+ case 0x1572:
+ case 0x1574:
+ case 0x1580 ... 0x1581:
+ case 0x1583 ... 0x1589:
+ case 0x37d0 ... 0x37d2:
+ return true;
+ default:
+ return false;
+ }
+ }
+
+ return false;
+}
+
static int vfio_pci_enable(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
@@ -136,23 +165,29 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
pr_debug("%s: Couldn't store %s saved state\n",
__func__, dev_name(&pdev->dev));
- ret = vfio_config_init(vdev);
- if (ret) {
- kfree(vdev->pci_saved_state);
- vdev->pci_saved_state = NULL;
- pci_disable_device(pdev);
- return ret;
+ if (likely(!nointxmask)) {
+ if (vfio_pci_nointx(pdev)) {
+ dev_info(&pdev->dev, "Masking broken INTx support\n");
+ vdev->nointx = true;
+ pci_intx(pdev, 0);
+ } else
+ vdev->pci_2_3 = pci_intx_mask_supported(pdev);
}
- if (likely(!nointxmask))
- vdev->pci_2_3 = pci_intx_mask_supported(pdev);
-
pci_read_config_word(pdev, PCI_COMMAND, &cmd);
if (vdev->pci_2_3 && (cmd & PCI_COMMAND_INTX_DISABLE)) {
cmd &= ~PCI_COMMAND_INTX_DISABLE;
pci_write_config_word(pdev, PCI_COMMAND, cmd);
}
+ ret = vfio_config_init(vdev);
+ if (ret) {
+ kfree(vdev->pci_saved_state);
+ vdev->pci_saved_state = NULL;
+ pci_disable_device(pdev);
+ return ret;
+ }
+
msix_pos = pdev->msix_cap;
if (msix_pos) {
u16 flags;
@@ -304,7 +339,7 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
u8 pin;
pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
- if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && pin)
+ if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && !vdev->nointx && pin)
return 1;
} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 142c533efec7..688691d9058d 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -408,6 +408,7 @@ static void vfio_bar_restore(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
u32 *rbar = vdev->rbar;
+ u16 cmd;
int i;
if (pdev->is_virtfn)
@@ -420,6 +421,12 @@ static void vfio_bar_restore(struct vfio_pci_device *vdev)
pci_user_write_config_dword(pdev, i, *rbar);
pci_user_write_config_dword(pdev, PCI_ROM_ADDRESS, *rbar);
+
+ if (vdev->nointx) {
+ pci_user_read_config_word(pdev, PCI_COMMAND, &cmd);
+ cmd |= PCI_COMMAND_INTX_DISABLE;
+ pci_user_write_config_word(pdev, PCI_COMMAND, cmd);
+ }
}
static __le32 vfio_generate_bar_flags(struct pci_dev *pdev, int bar)
@@ -515,6 +522,23 @@ static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos,
return count;
}
+/* Test whether BARs match the value we think they should contain */
+static bool vfio_need_bar_restore(struct vfio_pci_device *vdev)
+{
+ int i = 0, pos = PCI_BASE_ADDRESS_0, ret;
+ u32 bar;
+
+ for (; pos <= PCI_BASE_ADDRESS_5; i++, pos += 4) {
+ if (vdev->rbar[i]) {
+ ret = pci_user_read_config_dword(vdev->pdev, pos, &bar);
+ if (ret || vdev->rbar[i] != bar)
+ return true;
+ }
+ }
+
+ return false;
+}
+
static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
int count, struct perm_bits *perm,
int offset, __le32 val)
@@ -553,7 +577,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
* SR-IOV devices will trigger this, but we catch them later
*/
if ((new_mem && virt_mem && !phys_mem) ||
- (new_io && virt_io && !phys_io))
+ (new_io && virt_io && !phys_io) ||
+ vfio_need_bar_restore(vdev))
vfio_bar_restore(vdev);
}
@@ -724,7 +749,8 @@ static int vfio_vpd_config_write(struct vfio_pci_device *vdev, int pos,
if (pci_write_vpd(pdev, addr & ~PCI_VPD_ADDR_F, 4, &data) != 4)
return count;
} else {
- if (pci_read_vpd(pdev, addr, 4, &data) != 4)
+ data = 0;
+ if (pci_read_vpd(pdev, addr, 4, &data) < 0)
return count;
*pdata = cpu_to_le32(data);
}
@@ -1124,9 +1150,12 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
return pcibios_err_to_errno(ret);
if (PCI_X_CMD_VERSION(word)) {
- /* Test for extended capabilities */
- pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
- vdev->extended_caps = (dword != 0);
+ if (pdev->cfg_size > PCI_CFG_SPACE_SIZE) {
+ /* Test for extended capabilities */
+ pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE,
+ &dword);
+ vdev->extended_caps = (dword != 0);
+ }
return PCI_CAP_PCIX_SIZEOF_V2;
} else
return PCI_CAP_PCIX_SIZEOF_V0;
@@ -1138,9 +1167,11 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
return byte;
case PCI_CAP_ID_EXP:
- /* Test for extended capabilities */
- pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
- vdev->extended_caps = (dword != 0);
+ if (pdev->cfg_size > PCI_CFG_SPACE_SIZE) {
+ /* Test for extended capabilities */
+ pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+ vdev->extended_caps = (dword != 0);
+ }
/* length based on version */
if ((pcie_caps_reg(pdev) & PCI_EXP_FLAGS_VERS) == 1)
@@ -1545,7 +1576,7 @@ int vfio_config_init(struct vfio_pci_device *vdev)
*(__le16 *)&vconfig[PCI_DEVICE_ID] = cpu_to_le16(pdev->device);
}
- if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX))
+ if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
vconfig[PCI_INTERRUPT_PIN] = 0;
ret = vfio_cap_init(vdev);
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index e9ea3fef144a..15ecfc9c5f6c 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -228,9 +228,9 @@ static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd)
static void vfio_intx_disable(struct vfio_pci_device *vdev)
{
- vfio_intx_set_signal(vdev, -1);
vfio_virqfd_disable(&vdev->ctx[0].unmask);
vfio_virqfd_disable(&vdev->ctx[0].mask);
+ vfio_intx_set_signal(vdev, -1);
vdev->irq_type = VFIO_PCI_NUM_IRQS;
vdev->num_ctx = 0;
kfree(vdev->ctx);
@@ -401,13 +401,13 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
struct pci_dev *pdev = vdev->pdev;
int i;
- vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
-
for (i = 0; i < vdev->num_ctx; i++) {
vfio_virqfd_disable(&vdev->ctx[i].unmask);
vfio_virqfd_disable(&vdev->ctx[i].mask);
}
+ vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
+
if (msix) {
pci_disable_msix(vdev->pdev);
kfree(vdev->msix);
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 8a7d546d18a0..016c14a1b454 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -83,6 +83,7 @@ struct vfio_pci_device {
bool bardirty;
bool has_vga;
bool needs_reset;
+ bool nointx;
struct pci_saved_state *pci_saved_state;
int refcnt;
struct eventfd_ctx *err_trigger;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 3054e3fa63ac..80378ddadc5c 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -331,14 +331,12 @@ static void tce_iommu_free_table(struct iommu_table *tbl);
static void tce_iommu_release(void *iommu_data)
{
struct tce_container *container = iommu_data;
- struct iommu_table_group *table_group;
struct tce_iommu_group *tcegrp;
long i;
while (tce_groups_attached(container)) {
tcegrp = list_first_entry(&container->group_list,
struct tce_iommu_group, next);
- table_group = iommu_group_get_iommudata(tcegrp->grp);
tce_iommu_detach_group(iommu_data, tcegrp->grp);
}
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 15a65823aad9..2ba19424e4a1 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -515,7 +515,7 @@ static int map_try_harder(struct vfio_domain *domain, dma_addr_t iova,
unsigned long pfn, long npage, int prot)
{
long i;
- int ret;
+ int ret = 0;
for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
ret = iommu_map(domain->domain, iova,
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 0e6fd556c982..9d6320e8ff3e 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -333,16 +333,6 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
}
-static int vhost_scsi_shutdown_session(struct se_session *se_sess)
-{
- return 0;
-}
-
-static void vhost_scsi_close_session(struct se_session *se_sess)
-{
- return;
-}
-
static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
{
return 0;
@@ -2114,8 +2104,6 @@ static struct target_core_fabric_ops vhost_scsi_ops = {
.tpg_get_inst_index = vhost_scsi_tpg_get_inst_index,
.release_cmd = vhost_scsi_release_cmd,
.check_stop_free = vhost_scsi_check_stop_free,
- .shutdown_session = vhost_scsi_shutdown_session,
- .close_session = vhost_scsi_close_session,
.sess_get_index = vhost_scsi_sess_get_index,
.sess_get_initiator_sid = NULL,
.write_pending = vhost_scsi_write_pending,
diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c
index 35fe4825a454..60d6c2ac87aa 100644
--- a/drivers/video/backlight/lm3630a_bl.c
+++ b/drivers/video/backlight/lm3630a_bl.c
@@ -162,7 +162,7 @@ static int lm3630a_intr_config(struct lm3630a_chip *pchip)
static void lm3630a_pwm_ctrl(struct lm3630a_chip *pchip, int br, int br_max)
{
- unsigned int period = pwm_get_period(pchip->pwmd);
+ unsigned int period = pchip->pdata->pwm_period;
unsigned int duty = br * period / br_max;
pwm_config(pchip->pwmd, duty, period);
@@ -424,8 +424,13 @@ static int lm3630a_probe(struct i2c_client *client,
dev_err(&client->dev, "fail : get pwm device\n");
return PTR_ERR(pchip->pwmd);
}
+
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(pchip->pwmd);
}
- pchip->pwmd->period = pdata->pwm_period;
/* interrupt enable : irq 0 is not allowed */
pchip->irq = client->irq;
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index daca9e6a2bb3..e5b14f52628f 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -246,6 +246,12 @@ static void lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
return;
lp->pwm = pwm;
+
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(pwm);
}
pwm_config(lp->pwm, duty, period);
diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c
index 5d583d7a517b..cf869ec90cce 100644
--- a/drivers/video/backlight/lp8788_bl.c
+++ b/drivers/video/backlight/lp8788_bl.c
@@ -145,6 +145,12 @@ static void lp8788_pwm_ctrl(struct lp8788_bl *bl, int br, int max_br)
}
bl->pwm = pwm;
+
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(pwm);
}
pwm_config(bl->pwm, duty, period);
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index 64f9e1b8655f..b2b366bb0f97 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -201,6 +201,7 @@ static int pwm_backlight_probe(struct platform_device *pdev)
struct device_node *node = pdev->dev.of_node;
struct pwm_bl_data *pb;
int initial_blank = FB_BLANK_UNBLANK;
+ struct pwm_args pargs;
int ret;
if (!data) {
@@ -307,16 +308,21 @@ static int pwm_backlight_probe(struct platform_device *pdev)
dev_dbg(&pdev->dev, "got pwm for backlight\n");
/*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(pb->pwm);
+
+ /*
* The DT case will set the pwm_period_ns field to 0 and store the
* period, parsed from the DT, in the PWM device. For the non-DT case,
* set the period from platform data if it has not already been set
* via the PWM lookup table.
*/
- pb->period = pwm_get_period(pb->pwm);
- if (!pb->period && (data->pwm_period_ns > 0)) {
+ pwm_get_args(pb->pwm, &pargs);
+ pb->period = pargs.period;
+ if (!pb->period && (data->pwm_period_ns > 0))
pb->period = data->pwm_period_ns;
- pwm_set_period(pb->pwm, data->pwm_period_ns);
- }
pb->lth_brightness = data->lth_brightness * (pb->period / pb->scale);
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index d8d583d32a37..c229b1a0d13b 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -713,7 +713,7 @@ static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par,
if (par->lcdc_clk_rate != lcdc_clk_rate) {
ret = clk_set_rate(par->lcdc_clk, lcdc_clk_rate);
- if (IS_ERR_VALUE(ret)) {
+ if (ret) {
dev_err(par->dev,
"unable to set clock rate at %u\n",
lcdc_clk_rate);
@@ -784,7 +784,7 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
int ret = 0;
ret = da8xx_fb_calc_config_clk_divider(par, panel);
- if (IS_ERR_VALUE(ret)) {
+ if (ret) {
dev_err(par->dev, "unable to configure clock\n");
return ret;
}
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
index 8ea531d2652c..bbfe7e2d4332 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
@@ -51,8 +51,8 @@ static void hdmi_core_ddc_init(struct hdmi_core_data *core)
{
void __iomem *base = core->base;
const unsigned long long iclk = 266000000; /* DSS L3 ICLK */
- const unsigned ss_scl_high = 4000; /* ns */
- const unsigned ss_scl_low = 4700; /* ns */
+ const unsigned ss_scl_high = 4600; /* ns */
+ const unsigned ss_scl_low = 5400; /* ns */
const unsigned fs_scl_high = 600; /* ns */
const unsigned fs_scl_low = 1300; /* ns */
const unsigned sda_hold = 1000; /* ns */
@@ -442,7 +442,7 @@ static void hdmi_core_write_avi_infoframe(struct hdmi_core_data *core,
c = (ptr[1] >> 6) & 0x3;
m = (ptr[1] >> 4) & 0x3;
- r = (ptr[1] >> 0) & 0x3;
+ r = (ptr[1] >> 0) & 0xf;
itc = (ptr[2] >> 7) & 0x1;
ec = (ptr[2] >> 4) & 0x7;
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index 21dafe53ca49..a9c45c89b15e 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -286,6 +286,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
{
int ret;
u32 precharge, dclk, com_invdir, compins;
+ struct pwm_args pargs;
if (par->device_info->need_pwm) {
par->pwm = pwm_get(&par->client->dev, NULL);
@@ -294,7 +295,15 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
return PTR_ERR(par->pwm);
}
- par->pwm_period = pwm_get_period(par->pwm);
+ /*
+ * FIXME: pwm_apply_args() should be removed when switching to
+ * the atomic PWM API.
+ */
+ pwm_apply_args(par->pwm);
+
+ pwm_get_args(par->pwm, &pargs);
+
+ par->pwm_period = pargs.period;
/* Enable the PWM */
pwm_config(par->pwm, par->pwm_period / 2, par->pwm_period);
pwm_enable(par->pwm);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 7b6d74f0c72f..476c0e3a7150 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -75,7 +75,7 @@ struct virtio_balloon {
/* The array of pfns we tell the Host about. */
unsigned int num_pfns;
- u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
+ __virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
/* Memory statistics */
struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
@@ -127,14 +127,16 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
}
-static void set_page_pfns(u32 pfns[], struct page *page)
+static void set_page_pfns(struct virtio_balloon *vb,
+ __virtio32 pfns[], struct page *page)
{
unsigned int i;
/* Set balloon pfns pointing at this page.
* Note that the first pfn points at start of the page. */
for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
- pfns[i] = page_to_balloon_pfn(page) + i;
+ pfns[i] = cpu_to_virtio32(vb->vdev,
+ page_to_balloon_pfn(page) + i);
}
static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
@@ -158,7 +160,7 @@ static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
msleep(200);
break;
}
- set_page_pfns(vb->pfns + vb->num_pfns, page);
+ set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
if (!virtio_has_feature(vb->vdev,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
@@ -177,10 +179,12 @@ static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
static void release_pages_balloon(struct virtio_balloon *vb)
{
unsigned int i;
+ struct page *page;
/* Find pfns pointing at start of each page, get pages and free them. */
for (i = 0; i < vb->num_pfns; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
- struct page *page = balloon_pfn_to_page(vb->pfns[i]);
+ page = balloon_pfn_to_page(virtio32_to_cpu(vb->vdev,
+ vb->pfns[i]));
if (!virtio_has_feature(vb->vdev,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
adjust_managed_page_count(page, 1);
@@ -203,7 +207,7 @@ static unsigned leak_balloon(struct virtio_balloon *vb, size_t num)
page = balloon_page_dequeue(vb_dev_info);
if (!page)
break;
- set_page_pfns(vb->pfns + vb->num_pfns, page);
+ set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
}
@@ -471,13 +475,13 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
__count_vm_event(BALLOON_MIGRATE);
spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
- set_page_pfns(vb->pfns, newpage);
+ set_page_pfns(vb, vb->pfns, newpage);
tell_host(vb, vb->inflate_vq);
/* balloon's page migration 2nd step -- deflate "page" */
balloon_page_delete(page);
vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
- set_page_pfns(vb->pfns, page);
+ set_page_pfns(vb, vb->pfns, page);
tell_host(vb, vb->deflate_vq);
mutex_unlock(&vb->balloon_lock);
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 5b45e277697b..b4b3e256491b 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -661,6 +661,14 @@ config ATLAS7_WATCHDOG
To compile this driver as a module, choose M here: the
module will be called atlas7_wdt.
+config RENESAS_WDT
+ tristate "Renesas WDT Watchdog"
+ depends on ARCH_RENESAS || COMPILE_TEST
+ select WATCHDOG_CORE
+ help
+ This driver adds watchdog support for the integrated watchdogs in the
+ Renesas R-Car and other SH-Mobile SoCs (usually named RWDT or SWDT).
+
# AVR32 Architecture
config AT32AP700X_WDT
@@ -738,7 +746,7 @@ config ALIM7101_WDT
config EBC_C384_WDT
tristate "WinSystems EBC-C384 Watchdog Timer"
- depends on X86 && ISA
+ depends on X86 && ISA_BUS_API
select WATCHDOG_CORE
help
Enables watchdog timer support for the watchdog timer on the
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 9bde095ff691..a46e7c1380ac 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -73,6 +73,7 @@ obj-$(CONFIG_DIGICOLOR_WATCHDOG) += digicolor_wdt.o
obj-$(CONFIG_LPC18XX_WATCHDOG) += lpc18xx_wdt.o
obj-$(CONFIG_BCM7038_WDT) += bcm7038_wdt.o
obj-$(CONFIG_ATLAS7_WATCHDOG) += atlas7_wdt.o
+obj-$(CONFIG_RENESAS_WDT) += renesas_wdt.o
# AVR32 Architecture
obj-$(CONFIG_AT32AP700X_WDT) += at32ap700x_wdt.o
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 02007689e9ca..71ee07950e63 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -611,9 +611,7 @@ static int cpwd_probe(struct platform_device *op)
}
if (p->broken) {
- init_timer(&cpwd_timer);
- cpwd_timer.function = cpwd_brokentimer;
- cpwd_timer.data = (unsigned long) p;
+ setup_timer(&cpwd_timer, cpwd_brokentimer, (unsigned long)p);
cpwd_timer.expires = WD_BTIMEOUT;
pr_info("PLD defect workaround enabled for model %s\n",
diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index 016bd9355190..d4ba262da7ba 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -38,7 +38,7 @@
#define SIO_F71808FG_LD_WDT 0x07 /* Watchdog timer logical device */
#define SIO_UNLOCK_KEY 0x87 /* Key to enable Super-I/O */
-#define SIO_LOCK_KEY 0xAA /* Key to diasble Super-I/O */
+#define SIO_LOCK_KEY 0xAA /* Key to disable Super-I/O */
#define SIO_REG_LDSEL 0x07 /* Logical device select */
#define SIO_REG_DEVID 0x20 /* Device ID (2 bytes) */
@@ -59,6 +59,7 @@
#define SIO_F71869A_ID 0x1007 /* Chipset ID */
#define SIO_F71882_ID 0x0541 /* Chipset ID */
#define SIO_F71889_ID 0x0723 /* Chipset ID */
+#define SIO_F81865_ID 0x0704 /* Chipset ID */
#define F71808FG_REG_WDO_CONF 0xf0
#define F71808FG_REG_WDT_CONF 0xf5
@@ -66,11 +67,14 @@
#define F71808FG_FLAG_WDOUT_EN 7
-#define F71808FG_FLAG_WDTMOUT_STS 5
+#define F71808FG_FLAG_WDTMOUT_STS 6
#define F71808FG_FLAG_WD_EN 5
#define F71808FG_FLAG_WD_PULSE 4
#define F71808FG_FLAG_WD_UNIT 3
+#define F81865_REG_WDO_CONF 0xfa
+#define F81865_FLAG_WDOUT_EN 0
+
/* Default values */
#define WATCHDOG_TIMEOUT 60 /* 1 minute default timeout */
#define WATCHDOG_MAX_TIMEOUT (60 * 255)
@@ -112,7 +116,7 @@ module_param(start_withtimeout, uint, 0);
MODULE_PARM_DESC(start_withtimeout, "Start watchdog timer on module load with"
" given initial timeout. Zero (default) disables this feature.");
-enum chips { f71808fg, f71858fg, f71862fg, f71869, f71882fg, f71889fg };
+enum chips { f71808fg, f71858fg, f71862fg, f71869, f71882fg, f71889fg, f81865 };
static const char *f71808e_names[] = {
"f71808fg",
@@ -121,6 +125,7 @@ static const char *f71808e_names[] = {
"f71869",
"f71882fg",
"f71889fg",
+ "f81865",
};
/* Super-I/O Function prototypes */
@@ -360,6 +365,11 @@ static int watchdog_start(void)
superio_inb(watchdog.sioaddr, SIO_REG_MFUNCT3) & 0xcf);
break;
+ case f81865:
+ /* Set pin 70 to WDTRST# */
+ superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 5);
+ break;
+
default:
/*
* 'default' label to shut up the compiler and catch
@@ -371,8 +381,13 @@ static int watchdog_start(void)
superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT);
superio_set_bit(watchdog.sioaddr, SIO_REG_ENABLE, 0);
- superio_set_bit(watchdog.sioaddr, F71808FG_REG_WDO_CONF,
- F71808FG_FLAG_WDOUT_EN);
+
+ if (watchdog.type == f81865)
+ superio_set_bit(watchdog.sioaddr, F81865_REG_WDO_CONF,
+ F81865_FLAG_WDOUT_EN);
+ else
+ superio_set_bit(watchdog.sioaddr, F71808FG_REG_WDO_CONF,
+ F71808FG_FLAG_WDOUT_EN);
superio_set_bit(watchdog.sioaddr, F71808FG_REG_WDT_CONF,
F71808FG_FLAG_WD_EN);
@@ -655,7 +670,7 @@ static int __init watchdog_init(int sioaddr)
superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT);
wdt_conf = superio_inb(sioaddr, F71808FG_REG_WDT_CONF);
- watchdog.caused_reboot = wdt_conf & F71808FG_FLAG_WDTMOUT_STS;
+ watchdog.caused_reboot = wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS);
superio_exit(sioaddr);
@@ -770,6 +785,9 @@ static int __init f71808e_find(int sioaddr)
/* Confirmed (by datasheet) not to have a watchdog. */
err = -ENODEV;
goto exit;
+ case SIO_F81865_ID:
+ watchdog.type = f81865;
+ break;
default:
pr_info("Unrecognized Fintek device: %04x\n",
(unsigned int)devid);
diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index 331aed831dac..62f346bb4348 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -37,6 +37,8 @@
#define IMX2_WDT_WCR 0x00 /* Control Register */
#define IMX2_WDT_WCR_WT (0xFF << 8) /* -> Watchdog Timeout Field */
+#define IMX2_WDT_WCR_WDA (1 << 5) /* -> External Reset WDOG_B */
+#define IMX2_WDT_WCR_SRS (1 << 4) /* -> Software Reset Signal */
#define IMX2_WDT_WCR_WRE (1 << 3) /* -> WDOG Reset Enable */
#define IMX2_WDT_WCR_WDE (1 << 2) /* -> Watchdog Enable */
#define IMX2_WDT_WCR_WDZST (1 << 0) /* -> Watchdog timer Suspend */
@@ -59,6 +61,7 @@ struct imx2_wdt_device {
struct clk *clk;
struct regmap *regmap;
struct watchdog_device wdog;
+ bool ext_reset;
};
static bool nowayout = WATCHDOG_NOWAYOUT;
@@ -83,6 +86,12 @@ static int imx2_wdt_restart(struct watchdog_device *wdog, unsigned long action,
struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
unsigned int wcr_enable = IMX2_WDT_WCR_WDE;
+ /* Use internal reset or external - not both */
+ if (wdev->ext_reset)
+ wcr_enable |= IMX2_WDT_WCR_SRS; /* do not assert int reset */
+ else
+ wcr_enable |= IMX2_WDT_WCR_WDA; /* do not assert ext-reset */
+
/* Assert SRS signal */
regmap_write(wdev->regmap, IMX2_WDT_WCR, wcr_enable);
/*
@@ -112,8 +121,12 @@ static inline void imx2_wdt_setup(struct watchdog_device *wdog)
val |= IMX2_WDT_WCR_WDZST;
/* Strip the old watchdog Time-Out value */
val &= ~IMX2_WDT_WCR_WT;
- /* Generate reset if WDOG times out */
- val &= ~IMX2_WDT_WCR_WRE;
+ /* Generate internal chip-level reset if WDOG times out */
+ if (!wdev->ext_reset)
+ val &= ~IMX2_WDT_WCR_WRE;
+ /* Or if external-reset assert WDOG_B reset only on time-out */
+ else
+ val |= IMX2_WDT_WCR_WRE;
/* Keep Watchdog Disabled */
val &= ~IMX2_WDT_WCR_WDE;
/* Set the watchdog's Time-Out value */
@@ -230,6 +243,8 @@ static int __init imx2_wdt_probe(struct platform_device *pdev)
regmap_read(wdev->regmap, IMX2_WDT_WRSR, &val);
wdog->bootstatus = val & IMX2_WDT_WRSR_TOUT ? WDIOF_CARDRESET : 0;
+ wdev->ext_reset = of_property_read_bool(pdev->dev.of_node,
+ "fsl,ext-reset-output");
wdog->timeout = clamp_t(unsigned, timeout, 1, IMX2_WDT_MAX_TIME);
if (wdog->timeout != timeout)
dev_warn(&pdev->dev, "Initial timeout out of range! Clamped from %u to %u\n",
diff --git a/drivers/watchdog/jz4740_wdt.c b/drivers/watchdog/jz4740_wdt.c
index 6a7d5c365438..c8d51ddb26d5 100644
--- a/drivers/watchdog/jz4740_wdt.c
+++ b/drivers/watchdog/jz4740_wdt.c
@@ -160,10 +160,8 @@ static int jz4740_wdt_probe(struct platform_device *pdev)
drvdata = devm_kzalloc(&pdev->dev, sizeof(struct jz4740_wdt_drvdata),
GFP_KERNEL);
- if (!drvdata) {
- dev_err(&pdev->dev, "Unable to alloacate watchdog device\n");
+ if (!drvdata)
return -ENOMEM;
- }
if (heartbeat < 1 || heartbeat > MAX_HEARTBEAT)
heartbeat = DEFAULT_HEARTBEAT;
diff --git a/drivers/watchdog/octeon-wdt-main.c b/drivers/watchdog/octeon-wdt-main.c
index 14521c8b3d5a..b55981f88a08 100644
--- a/drivers/watchdog/octeon-wdt-main.c
+++ b/drivers/watchdog/octeon-wdt-main.c
@@ -431,7 +431,7 @@ static int octeon_wdt_cpu_callback(struct notifier_block *nfb,
{
unsigned int cpu = (unsigned long)hcpu;
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
octeon_wdt_disable_interrupt(cpu);
break;
diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c
index 20563ccb7be0..a043fa4f60e5 100644
--- a/drivers/watchdog/qcom-wdt.c
+++ b/drivers/watchdog/qcom-wdt.c
@@ -21,6 +21,7 @@
#define WDT_RST 0x38
#define WDT_EN 0x40
+#define WDT_STS 0x44
#define WDT_BITE_TIME 0x5C
struct qcom_wdt {
@@ -108,7 +109,8 @@ static const struct watchdog_ops qcom_wdt_ops = {
static const struct watchdog_info qcom_wdt_info = {
.options = WDIOF_KEEPALIVEPING
| WDIOF_MAGICCLOSE
- | WDIOF_SETTIMEOUT,
+ | WDIOF_SETTIMEOUT
+ | WDIOF_CARDRESET,
.identity = KBUILD_MODNAME,
};
@@ -171,6 +173,9 @@ static int qcom_wdt_probe(struct platform_device *pdev)
wdt->wdd.max_timeout = 0x10000000U / wdt->rate;
wdt->wdd.parent = &pdev->dev;
+ if (readl(wdt->base + WDT_STS) & 1)
+ wdt->wdd.bootstatus = WDIOF_CARDRESET;
+
/*
* If 'timeout-sec' unspecified in devicetree, assume a 30 second
* default, unless the max timeout is less than 30 seconds, then use
diff --git a/drivers/watchdog/renesas_wdt.c b/drivers/watchdog/renesas_wdt.c
new file mode 100644
index 000000000000..cf61c92f7ecd
--- /dev/null
+++ b/drivers/watchdog/renesas_wdt.c
@@ -0,0 +1,213 @@
+/*
+ * Watchdog driver for Renesas WDT watchdog
+ *
+ * Copyright (C) 2015-16 Wolfram Sang, Sang Engineering <wsa@sang-engineering.com>
+ * Copyright (C) 2015-16 Renesas Electronics Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/watchdog.h>
+
+#define RWTCNT 0
+#define RWTCSRA 4
+#define RWTCSRA_WOVF BIT(4)
+#define RWTCSRA_WRFLG BIT(5)
+#define RWTCSRA_TME BIT(7)
+
+#define RWDT_DEFAULT_TIMEOUT 60U
+
+static const unsigned int clk_divs[] = { 1, 4, 16, 32, 64, 128, 1024 };
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
+ __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
+struct rwdt_priv {
+ void __iomem *base;
+ struct watchdog_device wdev;
+ struct clk *clk;
+ unsigned int clks_per_sec;
+ u8 cks;
+};
+
+static void rwdt_write(struct rwdt_priv *priv, u32 val, unsigned int reg)
+{
+ if (reg == RWTCNT)
+ val |= 0x5a5a0000;
+ else
+ val |= 0xa5a5a500;
+
+ writel_relaxed(val, priv->base + reg);
+}
+
+static int rwdt_init_timeout(struct watchdog_device *wdev)
+{
+ struct rwdt_priv *priv = watchdog_get_drvdata(wdev);
+
+ rwdt_write(priv, 65536 - wdev->timeout * priv->clks_per_sec, RWTCNT);
+
+ return 0;
+}
+
+static int rwdt_start(struct watchdog_device *wdev)
+{
+ struct rwdt_priv *priv = watchdog_get_drvdata(wdev);
+
+ clk_prepare_enable(priv->clk);
+
+ rwdt_write(priv, priv->cks, RWTCSRA);
+ rwdt_init_timeout(wdev);
+
+ while (readb_relaxed(priv->base + RWTCSRA) & RWTCSRA_WRFLG)
+ cpu_relax();
+
+ rwdt_write(priv, priv->cks | RWTCSRA_TME, RWTCSRA);
+
+ return 0;
+}
+
+static int rwdt_stop(struct watchdog_device *wdev)
+{
+ struct rwdt_priv *priv = watchdog_get_drvdata(wdev);
+
+ rwdt_write(priv, priv->cks, RWTCSRA);
+ clk_disable_unprepare(priv->clk);
+
+ return 0;
+}
+
+static unsigned int rwdt_get_timeleft(struct watchdog_device *wdev)
+{
+ struct rwdt_priv *priv = watchdog_get_drvdata(wdev);
+ u16 val = readw_relaxed(priv->base + RWTCNT);
+
+ return DIV_ROUND_CLOSEST(65536 - val, priv->clks_per_sec);
+}
+
+static const struct watchdog_info rwdt_ident = {
+ .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT,
+ .identity = "Renesas WDT Watchdog",
+};
+
+static const struct watchdog_ops rwdt_ops = {
+ .owner = THIS_MODULE,
+ .start = rwdt_start,
+ .stop = rwdt_stop,
+ .ping = rwdt_init_timeout,
+ .get_timeleft = rwdt_get_timeleft,
+};
+
+static int rwdt_probe(struct platform_device *pdev)
+{
+ struct rwdt_priv *priv;
+ struct resource *res;
+ unsigned long rate;
+ unsigned int clks_per_sec;
+ int ret, i;
+
+ priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ priv->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(priv->base))
+ return PTR_ERR(priv->base);
+
+ priv->clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(priv->clk))
+ return PTR_ERR(priv->clk);
+
+ rate = clk_get_rate(priv->clk);
+ if (!rate)
+ return -ENOENT;
+
+ for (i = ARRAY_SIZE(clk_divs) - 1; i >= 0; i--) {
+ clks_per_sec = DIV_ROUND_UP(rate, clk_divs[i]);
+ if (clks_per_sec) {
+ priv->clks_per_sec = clks_per_sec;
+ priv->cks = i;
+ break;
+ }
+ }
+
+ if (!clks_per_sec) {
+ dev_err(&pdev->dev, "Can't find suitable clock divider\n");
+ return -ERANGE;
+ }
+
+ pm_runtime_enable(&pdev->dev);
+ pm_runtime_get_sync(&pdev->dev);
+
+ priv->wdev.info = &rwdt_ident,
+ priv->wdev.ops = &rwdt_ops,
+ priv->wdev.parent = &pdev->dev;
+ priv->wdev.min_timeout = 1;
+ priv->wdev.max_timeout = 65536 / clks_per_sec;
+ priv->wdev.timeout = min(priv->wdev.max_timeout, RWDT_DEFAULT_TIMEOUT);
+
+ platform_set_drvdata(pdev, priv);
+ watchdog_set_drvdata(&priv->wdev, priv);
+ watchdog_set_nowayout(&priv->wdev, nowayout);
+
+ /* This overrides the default timeout only if DT configuration was found */
+ ret = watchdog_init_timeout(&priv->wdev, 0, &pdev->dev);
+ if (ret)
+ dev_warn(&pdev->dev, "Specified timeout value invalid, using default\n");
+
+ ret = watchdog_register_device(&priv->wdev);
+ if (ret < 0) {
+ pm_runtime_put(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int rwdt_remove(struct platform_device *pdev)
+{
+ struct rwdt_priv *priv = platform_get_drvdata(pdev);
+
+ watchdog_unregister_device(&priv->wdev);
+ pm_runtime_put(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+
+ return 0;
+}
+
+/*
+ * This driver does also fit for R-Car Gen2 (r8a779[0-4]) WDT. However, for SMP
+ * to work there, one also needs a RESET (RST) driver which does not exist yet
+ * due to HW issues. This needs to be solved before adding compatibles here.
+ */
+static const struct of_device_id rwdt_ids[] = {
+ { .compatible = "renesas,rcar-gen3-wdt", },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, rwdt_ids);
+
+static struct platform_driver rwdt_driver = {
+ .driver = {
+ .name = "renesas_wdt",
+ .of_match_table = rwdt_ids,
+ },
+ .probe = rwdt_probe,
+ .remove = rwdt_remove,
+};
+module_platform_driver(rwdt_driver);
+
+MODULE_DESCRIPTION("Renesas WDT Watchdog Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Wolfram Sang <wsa@sang-engineering.com>");
diff --git a/drivers/watchdog/shwdt.c b/drivers/watchdog/shwdt.c
index f90812170657..517a733175ef 100644
--- a/drivers/watchdog/shwdt.c
+++ b/drivers/watchdog/shwdt.c
@@ -275,9 +275,7 @@ static int sh_wdt_probe(struct platform_device *pdev)
return rc;
}
- init_timer(&wdt->timer);
- wdt->timer.function = sh_wdt_ping;
- wdt->timer.data = (unsigned long)wdt;
+ setup_timer(&wdt->timer, sh_wdt_ping, (unsigned long)wdt);
wdt->timer.expires = next_ping_period(clock_division_ratio);
dev_info(&pdev->dev, "initialized.\n");
diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c
index 6467b91f2245..028618c5eeba 100644
--- a/drivers/watchdog/sp5100_tco.c
+++ b/drivers/watchdog/sp5100_tco.c
@@ -73,6 +73,13 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started."
/*
* Some TCO specific functions
*/
+
+static bool tco_has_sp5100_reg_layout(struct pci_dev *dev)
+{
+ return dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS &&
+ dev->revision < 0x40;
+}
+
static void tco_timer_start(void)
{
u32 val;
@@ -129,7 +136,7 @@ static void tco_timer_enable(void)
{
int val;
- if (sp5100_tco_pci->revision >= 0x40) {
+ if (!tco_has_sp5100_reg_layout(sp5100_tco_pci)) {
/* For SB800 or later */
/* Set the Watchdog timer resolution to 1 sec */
outb(SB800_PM_WATCHDOG_CONFIG, SB800_IO_PM_INDEX_REG);
@@ -342,8 +349,7 @@ static unsigned char sp5100_tco_setupdevice(void)
/*
* Determine type of southbridge chipset.
*/
- if (sp5100_tco_pci->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS &&
- sp5100_tco_pci->revision < 0x40) {
+ if (tco_has_sp5100_reg_layout(sp5100_tco_pci)) {
dev_name = SP5100_DEVNAME;
index_reg = SP5100_IO_PM_INDEX_REG;
data_reg = SP5100_IO_PM_DATA_REG;
@@ -388,8 +394,7 @@ static unsigned char sp5100_tco_setupdevice(void)
* Secondly, Find the watchdog timer MMIO address
* from SBResource_MMIO register.
*/
- if (sp5100_tco_pci->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS &&
- sp5100_tco_pci->revision < 0x40) {
+ if (tco_has_sp5100_reg_layout(sp5100_tco_pci)) {
/* Read SBResource_MMIO from PCI config(PCI_Reg: 9Ch) */
pci_read_config_dword(sp5100_tco_pci,
SP5100_SB_RESOURCE_MMIO_BASE, &val);
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index 981a668b17e3..7c3ba58ae1be 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -104,7 +104,7 @@ static void watchdog_check_min_max_timeout(struct watchdog_device *wdd)
* timeout module parameter (if it is valid value) or the timeout-sec property
* (only if it is a valid value and the timeout_parm is out of bounds).
* If none of them are valid then we keep the old value (which should normally
- * be the default timeout value.
+ * be the default timeout value).
*
* A zero is returned on success and -EINVAL for failure.
*/
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index e2c5abbb45ff..3595cffa24ea 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -736,7 +736,6 @@ static int watchdog_release(struct inode *inode, struct file *file)
watchdog_ping(wdd);
}
- cancel_delayed_work_sync(&wd_data->work);
watchdog_update_worker(wdd);
/* make sure that /dev/watchdog can be re-opened */
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 9b7a35c9e51d..030e91b38e32 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -8,6 +8,7 @@ nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_features.o := $(nostackp)
CFLAGS_efi.o += -fshort-wchar
+LDFLAGS += $(call ld-option, --no-wchar-size-warning)
dom0-$(CONFIG_PCI) += pci.o
dom0-$(CONFIG_USB_SUPPORT) += dbgp.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index d46839f51e73..e4db19e88ab1 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -151,8 +151,6 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq);
static void balloon_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
-static void release_memory_resource(struct resource *resource);
-
/* When ballooning out (allocating memory to return to Xen) we don't really
want the kernel to try too hard since that can trigger the oom killer. */
#define GFP_BALLOON \
@@ -248,6 +246,19 @@ static enum bp_state update_schedule(enum bp_state state)
}
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+static void release_memory_resource(struct resource *resource)
+{
+ if (!resource)
+ return;
+
+ /*
+ * No need to reset region to identity mapped since we now
+ * know that no I/O can be in this region
+ */
+ release_resource(resource);
+ kfree(resource);
+}
+
static struct resource *additional_memory_resource(phys_addr_t size)
{
struct resource *res;
@@ -286,19 +297,6 @@ static struct resource *additional_memory_resource(phys_addr_t size)
return res;
}
-static void release_memory_resource(struct resource *resource)
-{
- if (!resource)
- return;
-
- /*
- * No need to reset region to identity mapped since we now
- * know that no I/O can be in this region
- */
- release_resource(resource);
- kfree(resource);
-}
-
static enum bp_state reserve_additional_memory(void)
{
long credit;
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index cb7138c97c69..71d49a95f8c0 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -487,7 +487,8 @@ static void eoi_pirq(struct irq_data *data)
if (!VALID_EVTCHN(evtchn))
return;
- if (unlikely(irqd_is_setaffinity_pending(data))) {
+ if (unlikely(irqd_is_setaffinity_pending(data)) &&
+ likely(!irqd_irq_disabled(data))) {
int masked = test_and_set_mask(evtchn);
clear_evtchn(evtchn);
@@ -1370,7 +1371,8 @@ static void ack_dynirq(struct irq_data *data)
if (!VALID_EVTCHN(evtchn))
return;
- if (unlikely(irqd_is_setaffinity_pending(data))) {
+ if (unlikely(irqd_is_setaffinity_pending(data)) &&
+ likely(!irqd_irq_disabled(data))) {
int masked = test_and_set_mask(evtchn);
clear_evtchn(evtchn);
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index dc495383ad73..67939578cd6d 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -748,7 +748,7 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
return rc;
}
-#define GNTDEV_COPY_BATCH 24
+#define GNTDEV_COPY_BATCH 16
struct gntdev_copy_batch {
struct gnttab_copy ops[GNTDEV_COPY_BATCH];
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 8e67336f8ddd..6a25533da237 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
field_start = OFFSET(cfg_entry);
field_end = OFFSET(cfg_entry) + field->size;
- if ((req_start >= field_start && req_start < field_end)
- || (req_end > field_start && req_end <= field_end)) {
+ if (req_end > field_start && field_end > req_start) {
err = conf_space_read(dev, cfg_entry, field_start,
&tmp_val);
if (err)
@@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
field_start = OFFSET(cfg_entry);
field_end = OFFSET(cfg_entry) + field->size;
- if ((req_start >= field_start && req_start < field_end)
- || (req_end > field_start && req_end <= field_end)) {
+ if (req_end > field_start && field_end > req_start) {
tmp_val = 0;
err = xen_pcibk_config_read(dev, field_start,
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index ad3d17d29c81..9ead1c2ff1dd 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -145,7 +145,7 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data)
/* A write to obtain the length must happen as a 32-bit write.
* This does not (yet) support writing individual bytes
*/
- if (value == ~PCI_ROM_ADDRESS_ENABLE)
+ if ((value | ~PCI_ROM_ADDRESS_MASK) == ~0U)
bar->which = 1;
else {
u32 tmpval;
@@ -225,38 +225,42 @@ static inline void read_dev_bar(struct pci_dev *dev,
(PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_TYPE_64))) {
bar_info->val = res[pos - 1].start >> 32;
- bar_info->len_val = res[pos - 1].end >> 32;
+ bar_info->len_val = -resource_size(&res[pos - 1]) >> 32;
return;
}
}
+ if (!res[pos].flags ||
+ (res[pos].flags & (IORESOURCE_DISABLED | IORESOURCE_UNSET |
+ IORESOURCE_BUSY)))
+ return;
+
bar_info->val = res[pos].start |
(res[pos].flags & PCI_REGION_FLAG_MASK);
- bar_info->len_val = resource_size(&res[pos]);
+ bar_info->len_val = -resource_size(&res[pos]) |
+ (res[pos].flags & PCI_REGION_FLAG_MASK);
}
static void *bar_init(struct pci_dev *dev, int offset)
{
- struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+ struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL);
if (!bar)
return ERR_PTR(-ENOMEM);
read_dev_bar(dev, bar, offset, ~0);
- bar->which = 0;
return bar;
}
static void *rom_init(struct pci_dev *dev, int offset)
{
- struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+ struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL);
if (!bar)
return ERR_PTR(-ENOMEM);
read_dev_bar(dev, bar, offset, ~PCI_ROM_ADDRESS_ENABLE);
- bar->which = 0;
return bar;
}
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index ff932624eaad..d6950e0802b7 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1399,15 +1399,6 @@ static void scsiback_release_cmd(struct se_cmd *se_cmd)
percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
}
-static int scsiback_shutdown_session(struct se_session *se_sess)
-{
- return 0;
-}
-
-static void scsiback_close_session(struct se_session *se_sess)
-{
-}
-
static u32 scsiback_sess_get_index(struct se_session *se_sess)
{
return 0;
@@ -1841,8 +1832,6 @@ static const struct target_core_fabric_ops scsiback_ops = {
.tpg_get_inst_index = scsiback_tpg_get_inst_index,
.check_stop_free = scsiback_check_stop_free,
.release_cmd = scsiback_release_cmd,
- .shutdown_session = scsiback_shutdown_session,
- .close_session = scsiback_close_session,
.sess_get_index = scsiback_sess_get_index,
.sess_get_initiator_sid = NULL,
.write_pending = scsiback_write_pending,
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index eb3589edf485..0576eaeb60b9 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -239,13 +239,13 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
}
static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
int retval;
struct posix_acl *acl;
struct v9fs_session_info *v9ses;
- struct inode *inode = d_inode(dentry);
v9ses = v9fs_dentry2v9ses(dentry);
/*
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index b84c291ba1eb..d7b78d531e63 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -74,7 +74,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
v9fs_proto_dotu(v9ses));
fid = file->private_data;
if (!fid) {
- fid = v9fs_fid_clone(file->f_path.dentry);
+ fid = v9fs_fid_clone(file_dentry(file));
if (IS_ERR(fid))
return PTR_ERR(fid);
@@ -100,7 +100,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
* because we want write after unlink usecase
* to work.
*/
- fid = v9fs_writeback_fid(file->f_path.dentry);
+ fid = v9fs_writeback_fid(file_dentry(file));
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
mutex_unlock(&v9inode->v_mutex);
@@ -516,7 +516,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
* because we want write after unlink usecase
* to work.
*/
- fid = v9fs_writeback_fid(filp->f_path.dentry);
+ fid = v9fs_writeback_fid(file_dentry(filp));
if (IS_ERR(fid)) {
retval = PTR_ERR(fid);
mutex_unlock(&v9inode->v_mutex);
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 18c62bae9591..a6bd349bab23 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -147,8 +147,9 @@ static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
}
static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
const char *full_name = xattr_full_name(handler, name);
diff --git a/fs/Kconfig b/fs/Kconfig
index 6725f59c18e6..b8fcb416be72 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -52,6 +52,7 @@ config FS_DAX_PMD
depends on FS_DAX
depends on ZONE_DEVICE
depends on TRANSPARENT_HUGEPAGE
+ depends on BROKEN
endif # BLOCK
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 2a6713b6b9f4..d6384863192c 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -528,7 +528,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
char *prefix = NULL;
new_opts = kstrdup(data, GFP_KERNEL);
- if (!new_opts)
+ if (data && !new_opts)
return -ENOMEM;
pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
@@ -546,7 +546,8 @@ affs_remount(struct super_block *sb, int *flags, char *data)
}
flush_delayed_work(&sbi->sb_work);
- replace_mount_options(sb, new_opts);
+ if (new_opts)
+ replace_mount_options(sb, new_opts);
sbi->s_flags = mount_flags;
sbi->s_mode = mode;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 65de439bdc4f..14d506efd1aa 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -643,10 +643,6 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
return 0;
result = generic_file_write_iter(iocb, from);
- if (IS_ERR_VALUE(result)) {
- _leave(" = %zd", result);
- return result;
- }
_leave(" = %zd", result);
return result;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index f0d268b97d19..a439548de785 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -70,9 +70,13 @@ struct autofs_info {
};
#define AUTOFS_INF_EXPIRING (1<<0) /* dentry in the process of expiring */
-#define AUTOFS_INF_NO_RCU (1<<1) /* the dentry is being considered
+#define AUTOFS_INF_WANT_EXPIRE (1<<1) /* the dentry is being considered
* for expiry, so RCU_walk is
- * not permitted
+ * not permitted. If it progresses to
+ * actual expiry attempt, the flag is
+ * not cleared when EXPIRING is set -
+ * in that case it gets cleared only
+ * when it comes to clearing EXPIRING.
*/
#define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 9510d8d2e9cd..b493909e7492 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -316,19 +316,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
if (ino->flags & AUTOFS_INF_PENDING)
goto out;
if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
- ino->flags |= AUTOFS_INF_NO_RCU;
+ ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
spin_lock(&sbi->fs_lock);
if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
ino->flags |= AUTOFS_INF_EXPIRING;
- smp_mb();
- ino->flags &= ~AUTOFS_INF_NO_RCU;
init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
return root;
}
- ino->flags &= ~AUTOFS_INF_NO_RCU;
+ ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
}
out:
spin_unlock(&sbi->fs_lock);
@@ -446,7 +444,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
while ((dentry = get_next_positive_subdir(dentry, root))) {
spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(dentry);
- if (ino->flags & AUTOFS_INF_NO_RCU)
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
expired = NULL;
else
expired = should_expire(dentry, mnt, timeout, how);
@@ -455,7 +453,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
continue;
}
ino = autofs4_dentry_ino(expired);
- ino->flags |= AUTOFS_INF_NO_RCU;
+ ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
spin_lock(&sbi->fs_lock);
@@ -465,7 +463,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
goto found;
}
- ino->flags &= ~AUTOFS_INF_NO_RCU;
+ ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
if (expired != dentry)
dput(expired);
spin_unlock(&sbi->fs_lock);
@@ -475,17 +473,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
found:
pr_debug("returning %p %pd\n", expired, expired);
ino->flags |= AUTOFS_INF_EXPIRING;
- smp_mb();
- ino->flags &= ~AUTOFS_INF_NO_RCU;
init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
- spin_lock(&sbi->lookup_lock);
- spin_lock(&expired->d_parent->d_lock);
- spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&expired->d_parent->d_subdirs, &expired->d_child);
- spin_unlock(&expired->d_lock);
- spin_unlock(&expired->d_parent->d_lock);
- spin_unlock(&sbi->lookup_lock);
return expired;
}
@@ -496,7 +485,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
int status;
/* Block on any pending expire */
- if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)))
+ if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
return 0;
if (rcu_walk)
return -ECHILD;
@@ -554,7 +543,7 @@ int autofs4_expire_run(struct super_block *sb,
ino = autofs4_dentry_ino(dentry);
/* avoid rapid-fire expire attempts if expiry fails */
ino->last_used = now;
- ino->flags &= ~AUTOFS_INF_EXPIRING;
+ ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
@@ -583,7 +572,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
spin_lock(&sbi->fs_lock);
/* avoid rapid-fire expire attempts if expiry fails */
ino->last_used = now;
- ino->flags &= ~AUTOFS_INF_EXPIRING;
+ ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
dput(dentry);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 78bd80298528..3767f6641af1 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -458,7 +458,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
*/
struct inode *inode;
- if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
return 0;
if (d_mountpoint(dentry))
return 0;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 0146d911f468..631f1554c87b 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -66,11 +66,12 @@ static int autofs4_write(struct autofs_sb_info *sbi,
set_fs(KERNEL_DS);
mutex_lock(&sbi->pipe_mutex);
- wr = __vfs_write(file, data, bytes, &file->f_pos);
- while (bytes && wr) {
+ while (bytes) {
+ wr = __vfs_write(file, data, bytes, &file->f_pos);
+ if (wr <= 0)
+ break;
data += wr;
bytes -= wr;
- wr = __vfs_write(file, data, bytes, &file->f_pos);
}
mutex_unlock(&sbi->pipe_mutex);
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 72e35b721608..3ba385eaa26e 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -100,8 +100,8 @@ static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs)
return -EIO;
}
-static int bad_inode_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+static int bad_inode_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value, size_t size, int flags)
{
return -EIO;
}
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 2fab9f130e51..ae1b5404fced 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -127,12 +127,8 @@ static int set_brk(unsigned long start, unsigned long end)
{
start = PAGE_ALIGN(start);
end = PAGE_ALIGN(end);
- if (end > start) {
- unsigned long addr;
- addr = vm_brk(start, end - start);
- if (BAD_ADDR(addr))
- return addr;
- }
+ if (end > start)
+ return vm_brk(start, end - start);
return 0;
}
@@ -275,7 +271,7 @@ static int load_aout_binary(struct linux_binprm * bprm)
map_size = ex.a_text+ex.a_data;
#endif
error = vm_brk(text_addr & PAGE_MASK, map_size);
- if (error != (text_addr & PAGE_MASK))
+ if (error)
return error;
error = read_code(bprm->file, text_addr, pos,
@@ -298,7 +294,7 @@ static int load_aout_binary(struct linux_binprm * bprm)
if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
- if (IS_ERR_VALUE(error))
+ if (error)
return error;
read_code(bprm->file, N_TXTADDR(ex), fd_offset,
@@ -382,7 +378,7 @@ static int load_aout_library(struct file *file)
file);
}
retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
- if (IS_ERR_VALUE(retval))
+ if (retval)
goto out;
read_code(file, start_addr, N_TXTOFF(ex),
@@ -402,9 +398,8 @@ static int load_aout_library(struct file *file)
len = PAGE_ALIGN(ex.a_text + ex.a_data);
bss = ex.a_text + ex.a_data + ex.a_bss;
if (bss > len) {
- error = vm_brk(start_addr + len, bss - len);
- retval = error;
- if (error != start_addr + len)
+ retval = vm_brk(start_addr + len, bss - len);
+ if (retval)
goto out;
}
retval = 0;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 938fc4ede764..a7a28110dc80 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -96,10 +96,9 @@ static int set_brk(unsigned long start, unsigned long end)
start = ELF_PAGEALIGN(start);
end = ELF_PAGEALIGN(end);
if (end > start) {
- unsigned long addr;
- addr = vm_brk(start, end - start);
- if (BAD_ADDR(addr))
- return addr;
+ int error = vm_brk(start, end - start);
+ if (error)
+ return error;
}
current->mm->start_brk = current->mm->brk = end;
return 0;
@@ -629,7 +628,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
/* Map the last of the bss segment */
error = vm_brk(elf_bss, last_bss - elf_bss);
- if (BAD_ADDR(error))
+ if (error)
goto out;
}
@@ -1178,7 +1177,7 @@ static int load_elf_library(struct file *file)
bss = eppnt->p_memsz + eppnt->p_vaddr;
if (bss > len) {
error = vm_brk(len, bss - len);
- if (BAD_ADDR(error))
+ if (error)
goto out_free_ph;
}
error = 0;
@@ -2276,7 +2275,7 @@ static int elf_core_dump(struct coredump_params *cprm)
goto end_coredump;
/* Align to page */
- if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
+ if (!dump_skip(cprm, dataoff - cprm->pos))
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 71ade0e556b7..203589311bf8 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1787,7 +1787,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
goto end_coredump;
}
- if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
+ if (!dump_skip(cprm, dataoff - cprm->pos))
goto end_coredump;
if (!elf_fdpic_dump_segments(cprm))
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index f723cd3a455c..caf9e39bb82b 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -337,7 +337,7 @@ calc_reloc(unsigned long r, struct lib_info *p, int curid, int internalp)
"(%d != %d)", (unsigned) r, curid, id);
goto failed;
} else if ( ! p->lib_list[id].loaded &&
- IS_ERR_VALUE(load_flat_shared_library(id, p))) {
+ load_flat_shared_library(id, p) < 0) {
printk("BINFMT_FLAT: failed to load library %d", id);
goto failed;
}
@@ -837,7 +837,7 @@ static int load_flat_shared_library(int id, struct lib_info *libs)
res = prepare_binprm(&bprm);
- if (!IS_ERR_VALUE(res))
+ if (!res)
res = load_flat_file(&bprm, libs, id, NULL);
abort_creds(bprm.cred);
@@ -883,7 +883,7 @@ static int load_flat_binary(struct linux_binprm * bprm)
stack_len += FLAT_STACK_ALIGN - 1; /* reserve for upcoming alignment */
res = load_flat_file(bprm, &libinfo, 0, &stack_len);
- if (IS_ERR_VALUE(res))
+ if (res < 0)
return res;
/* Update data segment pointers for all libraries */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1089dbf25925..71ccab1d22c6 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -51,6 +51,18 @@ struct block_device *I_BDEV(struct inode *inode)
}
EXPORT_SYMBOL(I_BDEV);
+void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
+{
+ struct va_format vaf;
+ va_list args;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk_ratelimited("%sVFS (%s): %pV\n", prefix, sb->s_id, &vaf);
+ va_end(args);
+}
+
static void bdev_write_inode(struct block_device *bdev)
{
struct inode *inode = bdev->bd_inode;
@@ -489,7 +501,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
sector += get_start_sect(bdev);
if (sector % (PAGE_SIZE / 512))
return -EINVAL;
- avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn);
+ avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size);
if (!avail)
return -ERANGE;
if (avail > 0 && avail & ~PAGE_MASK)
@@ -498,6 +510,75 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
}
EXPORT_SYMBOL_GPL(bdev_direct_access);
+/**
+ * bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @sb: The superblock of the device
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: negative errno if unsupported, 0 if supported.
+ */
+int bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+ struct blk_dax_ctl dax = {
+ .sector = 0,
+ .size = PAGE_SIZE,
+ };
+ int err;
+
+ if (blocksize != PAGE_SIZE) {
+ vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
+ return -EINVAL;
+ }
+
+ err = bdev_direct_access(sb->s_bdev, &dax);
+ if (err < 0) {
+ switch (err) {
+ case -EOPNOTSUPP:
+ vfs_msg(sb, KERN_ERR,
+ "error: device does not support dax");
+ break;
+ case -EINVAL:
+ vfs_msg(sb, KERN_ERR,
+ "error: unaligned partition for dax");
+ break;
+ default:
+ vfs_msg(sb, KERN_ERR,
+ "error: dax access failed (%d)", err);
+ }
+ return err;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_dax_supported);
+
+/**
+ * bdev_dax_capable() - Return if the raw device is capable for dax
+ * @bdev: The device for raw block device access
+ */
+bool bdev_dax_capable(struct block_device *bdev)
+{
+ struct blk_dax_ctl dax = {
+ .size = PAGE_SIZE,
+ };
+
+ if (!IS_ENABLED(CONFIG_FS_DAX))
+ return false;
+
+ dax.sector = 0;
+ if (bdev_direct_access(bdev, &dax) < 0)
+ return false;
+
+ dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512);
+ if (bdev_direct_access(bdev, &dax) < 0)
+ return false;
+
+ return true;
+}
+
/*
* pseudo-fs
*/
@@ -1160,33 +1241,6 @@ void bd_set_size(struct block_device *bdev, loff_t size)
}
EXPORT_SYMBOL(bd_set_size);
-static bool blkdev_dax_capable(struct block_device *bdev)
-{
- struct gendisk *disk = bdev->bd_disk;
-
- if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX))
- return false;
-
- /*
- * If the partition is not aligned on a page boundary, we can't
- * do dax I/O to it.
- */
- if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
- || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
- return false;
-
- /*
- * If the device has known bad blocks, force all I/O through the
- * driver / page cache.
- *
- * TODO: support finer grained dax error handling
- */
- if (disk->bb && disk->bb->count)
- return false;
-
- return true;
-}
-
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
/*
@@ -1266,7 +1320,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
if (!ret) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
- if (!blkdev_dax_capable(bdev))
+ if (!bdev_dax_capable(bdev))
bdev->bd_inode->i_flags &= ~S_DAX;
}
@@ -1303,7 +1357,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
goto out_clear;
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
- if (!blkdev_dax_capable(bdev))
+ if (!bdev_dax_capable(bdev))
bdev->bd_inode->i_flags &= ~S_DAX;
}
} else {
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index d3090187fd76..8bb3509099e8 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1939,7 +1939,7 @@ static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off,
* from ipath->fspath->val[i].
* when it returns, there are ipath->fspath->elem_cnt number of paths available
* in ipath->fspath->val[]. when the allocated space wasn't sufficient, the
- * number of missed paths in recored in ipath->fspath->elem_missed, otherwise,
+ * number of missed paths is recorded in ipath->fspath->elem_missed, otherwise,
* it's zero. ipath->fspath->bytes_missing holds the number of bytes that would
* have been needed to return all paths.
*/
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 1da5753d886d..4919aedb5fc1 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -313,7 +313,7 @@ struct btrfs_dio_private {
struct bio *dio_bio;
/*
- * The original bio may be splited to several sub-bios, this is
+ * The original bio may be split to several sub-bios, this is
* done during endio of sub-bios
*/
int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 516e19d1d202..7706c8dc5fa6 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1939,7 +1939,7 @@ again:
/*
* Clear all references of this block. Do not free
* the block itself even if is not referenced anymore
- * because it still carries valueable information
+ * because it still carries valuable information
* like whether it was ever written and IO completed.
*/
list_for_each_entry_safe(l, tmp, &block->ref_to_list,
@@ -2645,7 +2645,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
* This algorithm is recursive because the amount of used stack space
* is very small and the max recursion depth is limited.
*/
- indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)",
+ indent_add = sprintf(buf, "%c-%llu(%s/%llu/%u)",
btrfsic_get_block_type(state, block),
block->logical_bytenr, block->dev_state->name,
block->dev_bytenr, block->mirror_num);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index decd0a3f5d61..a85cf7d23309 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -156,7 +156,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
/*
* RCU really hurts here, we could free up the root node because
- * it was cow'ed but we may not get the new root node yet so do
+ * it was COWed but we may not get the new root node yet so do
* the inc_not_zero dance and if it doesn't work then
* synchronize_rcu and try again.
*/
@@ -955,7 +955,7 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
struct extent_buffer *buf)
{
/*
- * Tree blocks not in refernece counted trees and tree roots
+ * Tree blocks not in reference counted trees and tree roots
* are never shared. If a block was allocated after the last
* snapshot and the block was not allocated by tree relocation,
* we know the block is not shared.
@@ -1270,7 +1270,7 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
/*
* tm is a pointer to the first operation to rewind within eb. then, all
- * previous operations will be rewinded (until we reach something older than
+ * previous operations will be rewound (until we reach something older than
* time_seq).
*/
static void
@@ -1345,7 +1345,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
}
/*
- * Called with eb read locked. If the buffer cannot be rewinded, the same buffer
+ * Called with eb read locked. If the buffer cannot be rewound, the same buffer
* is returned. If rewind operations happen, a fresh buffer is returned. The
* returned buffer is always read-locked. If the returned buffer is not the
* input buffer, the lock on the input buffer is released and the input buffer
@@ -1373,7 +1373,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
BUG_ON(tm->slot != 0);
- eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
+ eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start,
+ eb->len);
if (!eb_rewin) {
btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
@@ -1454,7 +1455,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
} else if (old_root) {
btrfs_tree_read_unlock(eb_root);
free_extent_buffer(eb_root);
- eb = alloc_dummy_extent_buffer(root->fs_info, logical);
+ eb = alloc_dummy_extent_buffer(root->fs_info, logical,
+ root->nodesize);
} else {
btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK);
eb = btrfs_clone_extent_buffer(eb_root);
@@ -1516,7 +1518,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
* 3) the root is not forced COW.
*
* What is forced COW:
- * when we create snapshot during commiting the transaction,
+ * when we create snapshot during committing the transaction,
* after we've finished coping src root, we must COW the shared
* block to ensure the metadata consistency.
*/
@@ -1531,7 +1533,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
/*
* cows a single block, see __btrfs_cow_block for the real work.
- * This version of it has extra checks so that a block isn't cow'd more than
+ * This version of it has extra checks so that a block isn't COWed more than
* once per transaction, as long as it hasn't been written yet
*/
noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
@@ -1552,6 +1554,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
trans->transid, root->fs_info->generation);
if (!should_cow_block(trans, root, buf)) {
+ trans->dirty = true;
*cow_ret = buf;
return 0;
}
@@ -1783,10 +1786,12 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
if (!err) {
tmp = (struct btrfs_disk_key *)(kaddr + offset -
map_start);
- } else {
+ } else if (err == 1) {
read_extent_buffer(eb, &unaligned,
offset, sizeof(unaligned));
tmp = &unaligned;
+ } else {
+ return err;
}
} else {
@@ -2510,6 +2515,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
if (!btrfs_buffer_uptodate(tmp, 0, 0))
ret = -EIO;
free_extent_buffer(tmp);
+ } else {
+ ret = PTR_ERR(tmp);
}
return ret;
}
@@ -2773,8 +2780,10 @@ again:
* then we don't want to set the path blocking,
* so we test it here
*/
- if (!should_cow_block(trans, root, b))
+ if (!should_cow_block(trans, root, b)) {
+ trans->dirty = true;
goto cow_done;
+ }
/*
* must have write locks on this node and the
@@ -2823,6 +2832,8 @@ cow_done:
}
ret = key_search(b, key, level, &prev_cmp, &slot);
+ if (ret < 0)
+ goto done;
if (level != 0) {
int dec = 0;
@@ -2986,7 +2997,7 @@ again:
btrfs_unlock_up_safe(p, level + 1);
/*
- * Since we can unwind eb's we want to do a real search every
+ * Since we can unwind ebs we want to do a real search every
* time.
*/
prev_cmp = -1;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ddcc58f03c79..4274a7bfdaed 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -89,7 +89,7 @@ static const int btrfs_csum_sizes[] = { 4 };
/* four bytes for CRC32 */
#define BTRFS_EMPTY_DIR_SIZE 0
-/* spefic to btrfs_map_block(), therefore not in include/linux/blk_types.h */
+/* specific to btrfs_map_block(), therefore not in include/linux/blk_types.h */
#define REQ_GET_READ_MIRRORS (1 << 30)
/* ioprio of readahead is set to idle */
@@ -431,7 +431,7 @@ struct btrfs_space_info {
* bytes_pinned does not reflect the bytes that will be pinned once the
* delayed refs are flushed, so this counter is inc'ed every time we
* call btrfs_free_extent so it is a realtime count of what will be
- * freed once the transaction is committed. It will be zero'ed every
+ * freed once the transaction is committed. It will be zeroed every
* time the transaction commits.
*/
struct percpu_counter total_bytes_pinned;
@@ -1401,7 +1401,7 @@ static inline void btrfs_init_map_token (struct btrfs_map_token *token)
token->kaddr = NULL;
}
-/* some macros to generate set/get funcs for the struct fields. This
+/* some macros to generate set/get functions for the struct fields. This
* assumes there is a lefoo_to_cpu for every type, so lets make a simple
* one for u8:
*/
@@ -2518,7 +2518,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
int btrfs_async_run_delayed_refs(struct btrfs_root *root,
- unsigned long count, int wait);
+ unsigned long count, u64 transid, int wait);
int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 61561c2a3f96..d3aaabbfada0 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1606,15 +1606,23 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode)
return 0;
}
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
- struct list_head *del_list)
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list)
{
struct btrfs_delayed_node *delayed_node;
struct btrfs_delayed_item *item;
delayed_node = btrfs_get_delayed_node(inode);
if (!delayed_node)
- return;
+ return false;
+
+ /*
+ * We can only do one readdir with delayed items at a time because of
+ * item->readdir_list.
+ */
+ inode_unlock_shared(inode);
+ inode_lock(inode);
mutex_lock(&delayed_node->mutex);
item = __btrfs_first_delayed_insertion_item(delayed_node);
@@ -1641,10 +1649,13 @@ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
* requeue or dequeue this delayed node.
*/
atomic_dec(&delayed_node->refs);
+
+ return true;
}
-void btrfs_put_delayed_items(struct list_head *ins_list,
- struct list_head *del_list)
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list)
{
struct btrfs_delayed_item *curr, *next;
@@ -1659,6 +1670,12 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
if (atomic_dec_and_test(&curr->refs))
kfree(curr);
}
+
+ /*
+ * The VFS is going to do up_read(), so we need to downgrade back to a
+ * read lock.
+ */
+ downgrade_write(&inode->i_rwsem);
}
int btrfs_should_delete_dir_index(struct list_head *del_list,
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 0167853c84ae..2495b3d4075f 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -137,10 +137,12 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
void btrfs_destroy_delayed_inodes(struct btrfs_root *root);
/* Used for readdir() */
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
- struct list_head *del_list);
-void btrfs_put_delayed_items(struct list_head *ins_list,
- struct list_head *del_list);
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list);
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list);
int btrfs_should_delete_dir_index(struct list_head *del_list,
u64 index);
int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index c24b653c7343..5fca9534a271 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -188,7 +188,7 @@ struct btrfs_delayed_ref_root {
/*
* To make qgroup to skip given root.
- * This is for snapshot, as btrfs_qgroup_inherit() will manully
+ * This is for snapshot, as btrfs_qgroup_inherit() will manually
* modify counters for snapshot and its source, so we should skip
* the snapshot in new_root/old_roots or it will get calculated twice
*/
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 85f12e6e28d2..63ef9cdf0144 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -450,7 +450,7 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
}
/*
- * blocked until all flighting bios are finished.
+ * blocked until all in-flight bios operations are finished.
*/
static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info)
{
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 91d123938cef..60ce1190307b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -384,7 +384,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
/*
* Things reading via commit roots that don't have normal protection,
* like send, can have a really old block in cache that may point at a
- * block that has been free'd and re-allocated. So don't clear uptodate
+ * block that has been freed and re-allocated. So don't clear uptodate
* if we find an eb that is under IO (dirty/writeback) because we could
* end up reading in the stale data and then writing it back out and
* making everybody very sad.
@@ -418,7 +418,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
/*
* The super_block structure does not span the whole
* BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
- * is filled with zeros and is included in the checkum.
+ * is filled with zeros and is included in the checksum.
*/
crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
@@ -600,7 +600,7 @@ static noinline int check_leaf(struct btrfs_root *root,
/*
* Check to make sure that we don't point outside of the leaf,
- * just incase all the items are consistent to eachother, but
+ * just in case all the items are consistent to each other, but
* all point outside of the leaf.
*/
if (btrfs_item_end_nr(leaf, slot) >
@@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
struct inode *btree_inode = root->fs_info->btree_inode;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
+ if (IS_ERR(buf))
return;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
buf, 0, WAIT_NONE, btree_get_extent, 0);
@@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
int ret;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
+ if (IS_ERR(buf))
return 0;
set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
@@ -1147,7 +1147,8 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 bytenr)
{
if (btrfs_test_is_dummy_root(root))
- return alloc_test_extent_buffer(root->fs_info, bytenr);
+ return alloc_test_extent_buffer(root->fs_info, bytenr,
+ root->nodesize);
return alloc_extent_buffer(root->fs_info, bytenr);
}
@@ -1171,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
int ret;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(buf))
+ return buf;
ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
if (ret) {
@@ -1314,14 +1315,16 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* Should only be used by the testing infrastructure */
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize)
{
struct btrfs_root *root;
root = btrfs_alloc_root(NULL, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
- __setup_root(4096, 4096, 4096, root, NULL, 1);
+ /* We don't use the stripesize in selftest, set it as sectorsize */
+ __setup_root(nodesize, sectorsize, sectorsize, root, NULL,
+ BTRFS_ROOT_TREE_OBJECTID);
set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
root->alloc_bytenr = 0;
@@ -1803,6 +1806,13 @@ static int cleaner_kthread(void *arg)
if (btrfs_need_cleaner_sleep(root))
goto sleep;
+ /*
+ * Do not do anything if we might cause open_ctree() to block
+ * before we have finished mounting the filesystem.
+ */
+ if (!root->fs_info->open)
+ goto sleep;
+
if (!mutex_trylock(&root->fs_info->cleaner_mutex))
goto sleep;
@@ -2517,7 +2527,6 @@ int open_ctree(struct super_block *sb,
int num_backups_tried = 0;
int backup_index = 0;
int max_active;
- bool cleaner_mutex_locked = false;
tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2797,7 +2806,7 @@ int open_ctree(struct super_block *sb,
nodesize = btrfs_super_nodesize(disk_super);
sectorsize = btrfs_super_sectorsize(disk_super);
- stripesize = btrfs_super_stripesize(disk_super);
+ stripesize = sectorsize;
fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
@@ -2996,13 +3005,6 @@ retry_root_backup:
goto fail_sysfs;
}
- /*
- * Hold the cleaner_mutex thread here so that we don't block
- * for a long time on btrfs_recover_relocation. cleaner_kthread
- * will wait for us to finish mounting the filesystem.
- */
- mutex_lock(&fs_info->cleaner_mutex);
- cleaner_mutex_locked = true;
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
"btrfs-cleaner");
if (IS_ERR(fs_info->cleaner_kthread))
@@ -3022,7 +3024,7 @@ retry_root_backup:
}
/*
- * Mount does not set all options immediatelly, we can do it now and do
+ * Mount does not set all options immediately, we can do it now and do
* not have to wait for transaction commit
*/
btrfs_apply_pending_changes(fs_info);
@@ -3062,8 +3064,10 @@ retry_root_backup:
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto fail_qgroup;
- /* We locked cleaner_mutex before creating cleaner_kthread. */
+
+ mutex_lock(&fs_info->cleaner_mutex);
ret = btrfs_recover_relocation(tree_root);
+ mutex_unlock(&fs_info->cleaner_mutex);
if (ret < 0) {
btrfs_warn(fs_info, "failed to recover relocation: %d",
ret);
@@ -3071,8 +3075,6 @@ retry_root_backup:
goto fail_qgroup;
}
}
- mutex_unlock(&fs_info->cleaner_mutex);
- cleaner_mutex_locked = false;
location.objectid = BTRFS_FS_TREE_OBJECTID;
location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3186,10 +3188,6 @@ fail_cleaner:
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
fail_sysfs:
- if (cleaner_mutex_locked) {
- mutex_unlock(&fs_info->cleaner_mutex);
- cleaner_mutex_locked = false;
- }
btrfs_sysfs_remove_mounted(fs_info);
fail_fsdev_sysfs:
@@ -3255,7 +3253,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
btrfs_warn_rl_in_rcu(device->dev_root->fs_info,
"lost page write due to IO error on %s",
rcu_str_deref(device->name));
- /* note, we dont' set_buffer_write_io_error because we have
+ /* note, we don't set_buffer_write_io_error because we have
* our own ways of dealing with the IO errors
*/
clear_buffer_uptodate(bh);
@@ -4130,6 +4128,16 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
* Hint to catch really bogus numbers, bitflips or so, more exact checks are
* done later
*/
+ if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+ btrfs_err(fs_info, "bytes_used is too small %llu",
+ btrfs_super_bytes_used(sb));
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+ btrfs_err(fs_info, "invalid stripesize %u",
+ btrfs_super_stripesize(sb));
+ ret = -EINVAL;
+ }
if (btrfs_super_num_devices(sb) > (1UL << 31))
printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
btrfs_super_num_devices(sb));
@@ -4367,7 +4375,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
if (ret)
break;
- clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+ clear_extent_bits(dirty_pages, start, end, mark);
while (start <= end) {
eb = btrfs_find_tree_block(root->fs_info, start);
start += root->nodesize;
@@ -4402,7 +4410,7 @@ again:
if (ret)
break;
- clear_extent_dirty(unpin, start, end, GFP_NOFS);
+ clear_extent_dirty(unpin, start, end);
btrfs_error_unpin_extent_range(root, start, end);
cond_resched();
}
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8e79d0070bcf..acba821499a9 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -90,7 +90,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
void btrfs_free_fs_root(struct btrfs_root *root);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-struct btrfs_root *btrfs_alloc_dummy_root(void);
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize);
#endif
/*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9424864fd01a..82b912a293ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -231,9 +231,9 @@ static int add_excluded_extent(struct btrfs_root *root,
{
u64 end = start + num_bytes - 1;
set_extent_bits(&root->fs_info->freed_extents[0],
- start, end, EXTENT_UPTODATE, GFP_NOFS);
+ start, end, EXTENT_UPTODATE);
set_extent_bits(&root->fs_info->freed_extents[1],
- start, end, EXTENT_UPTODATE, GFP_NOFS);
+ start, end, EXTENT_UPTODATE);
return 0;
}
@@ -246,9 +246,9 @@ static void free_excluded_extents(struct btrfs_root *root,
end = start + cache->key.offset - 1;
clear_extent_bits(&root->fs_info->freed_extents[0],
- start, end, EXTENT_UPTODATE, GFP_NOFS);
+ start, end, EXTENT_UPTODATE);
clear_extent_bits(&root->fs_info->freed_extents[1],
- start, end, EXTENT_UPTODATE, GFP_NOFS);
+ start, end, EXTENT_UPTODATE);
}
static int exclude_super_stripes(struct btrfs_root *root,
@@ -980,7 +980,7 @@ out_free:
* event that tree block loses its owner tree's reference and do the
* back refs conversion.
*
- * When a tree block is COW'd through a tree, there are four cases:
+ * When a tree block is COWed through a tree, there are four cases:
*
* The reference count of the block is one and the tree is the block's
* owner tree. Nothing to do in this case.
@@ -2042,6 +2042,11 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
struct btrfs_bio *bbio = NULL;
+ /*
+ * Avoid races with device replace and make sure our bbio has devices
+ * associated to its stripes that don't go away while we are discarding.
+ */
+ btrfs_bio_counter_inc_blocked(root->fs_info);
/* Tell the block device(s) that the sectors can be discarded */
ret = btrfs_map_block(root->fs_info, REQ_DISCARD,
bytenr, &num_bytes, &bbio, 0);
@@ -2074,6 +2079,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
}
btrfs_put_bbio(bbio);
}
+ btrfs_bio_counter_dec(root->fs_info);
if (actual_bytes)
*actual_bytes = discarded_bytes;
@@ -2595,7 +2601,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
}
/*
- * Need to drop our head ref lock and re-aqcuire the
+ * Need to drop our head ref lock and re-acquire the
* delayed ref lock and then re-check to make sure
* nobody got added.
*/
@@ -2747,7 +2753,7 @@ static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads)
/*
* We don't ever fill up leaves all the way so multiply by 2 just to be
- * closer to what we're really going to want to ouse.
+ * closer to what we're really going to want to use.
*/
return div_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(root));
}
@@ -2829,6 +2835,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
struct async_delayed_refs {
struct btrfs_root *root;
+ u64 transid;
int count;
int error;
int sync;
@@ -2844,6 +2851,10 @@ static void delayed_ref_async_start(struct btrfs_work *work)
async = container_of(work, struct async_delayed_refs, work);
+ /* if the commit is already started, we don't need to wait here */
+ if (btrfs_transaction_blocked(async->root->fs_info))
+ goto done;
+
trans = btrfs_join_transaction(async->root);
if (IS_ERR(trans)) {
async->error = PTR_ERR(trans);
@@ -2851,14 +2862,19 @@ static void delayed_ref_async_start(struct btrfs_work *work)
}
/*
- * trans->sync means that when we call end_transaciton, we won't
+ * trans->sync means that when we call end_transaction, we won't
* wait on delayed refs
*/
trans->sync = true;
+
+ /* Don't bother flushing if we got into a different transaction */
+ if (trans->transid > async->transid)
+ goto end;
+
ret = btrfs_run_delayed_refs(trans, async->root, async->count);
if (ret)
async->error = ret;
-
+end:
ret = btrfs_end_transaction(trans, async->root);
if (ret && !async->error)
async->error = ret;
@@ -2870,7 +2886,7 @@ done:
}
int btrfs_async_run_delayed_refs(struct btrfs_root *root,
- unsigned long count, int wait)
+ unsigned long count, u64 transid, int wait)
{
struct async_delayed_refs *async;
int ret;
@@ -2882,6 +2898,7 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
async->root = root->fs_info->tree_root;
async->count = count;
async->error = 0;
+ async->transid = transid;
if (wait)
async->sync = 1;
else
@@ -4296,7 +4313,7 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
* Called if we need to clear a data reservation for this inode
* Normally in a error case.
*
- * This one will handle the per-indoe data rsv map for accurate reserved
+ * This one will handle the per-inode data rsv map for accurate reserved
* space framework.
*/
void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
@@ -4967,7 +4984,7 @@ void btrfs_init_async_reclaim_work(struct work_struct *work)
* @orig_bytes - the number of bytes we want
* @flush - whether or not we can flush to make our reservation
*
- * This will reserve orgi_bytes number of bytes from the space info associated
+ * This will reserve orig_bytes number of bytes from the space info associated
* with the block_rsv. If there is not enough space it will make an attempt to
* flush out space to make room. It will do this by flushing delalloc if
* possible or committing the transaction. If flush is 0 then no attempts to
@@ -5572,7 +5589,7 @@ void btrfs_orphan_release_metadata(struct inode *inode)
* common file/directory operations, they change two fs/file trees
* and root tree, the number of items that the qgroup reserves is
* different with the free space reservation. So we can not use
- * the space reseravtion mechanism in start_transaction().
+ * the space reservation mechanism in start_transaction().
*/
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
@@ -5621,7 +5638,7 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
/**
* drop_outstanding_extent - drop an outstanding extent
* @inode: the inode we're dropping the extent for
- * @num_bytes: the number of bytes we're relaseing.
+ * @num_bytes: the number of bytes we're releasing.
*
* This is called when we are freeing up an outstanding extent, either called
* after an error or after an extent is written. This will return the number of
@@ -5647,7 +5664,7 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
drop_inode_space = 1;
/*
- * If we have more or the same amount of outsanding extents than we have
+ * If we have more or the same amount of outstanding extents than we have
* reserved then we need to leave the reserved extents count alone.
*/
if (BTRFS_I(inode)->outstanding_extents >=
@@ -5661,8 +5678,8 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
}
/**
- * calc_csum_metadata_size - return the amount of metada space that must be
- * reserved/free'd for the given bytes.
+ * calc_csum_metadata_size - return the amount of metadata space that must be
+ * reserved/freed for the given bytes.
* @inode: the inode we're manipulating
* @num_bytes: the number of bytes in question
* @reserve: 1 if we are reserving space, 0 if we are freeing space
@@ -5814,7 +5831,7 @@ out_fail:
/*
* This is tricky, but first we need to figure out how much we
- * free'd from any free-ers that occurred during this
+ * freed from any free-ers that occurred during this
* reservation, so we reset ->csum_bytes to the csum_bytes
* before we dropped our lock, and then call the free for the
* number of bytes that were freed while we were trying our
@@ -5836,7 +5853,7 @@ out_fail:
/*
* Now reset ->csum_bytes to what it should be. If bytes is
- * more than to_free then we would have free'd more space had we
+ * more than to_free then we would have freed more space had we
* not had an artificially high ->csum_bytes, so we need to free
* the remainder. If bytes is the same or less then we don't
* need to do anything, the other free-ers did the correct
@@ -6515,7 +6532,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
ret = btrfs_discard_extent(root, start,
end + 1 - start, NULL);
- clear_extent_dirty(unpin, start, end, GFP_NOFS);
+ clear_extent_dirty(unpin, start, end);
unpin_extent_range(root, start, end, true);
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
cond_resched();
@@ -7578,7 +7595,7 @@ loop:
if (loop == LOOP_CACHING_NOWAIT) {
/*
* We want to skip the LOOP_CACHING_WAIT step if we
- * don't have any unached bgs and we've alrelady done a
+ * don't have any uncached bgs and we've already done a
* full search through.
*/
if (orig_have_caching_bg || !full_search)
@@ -7982,7 +7999,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
/*
* Mixed block groups will exclude before processing the log so we only
- * need to do the exlude dance if this fs isn't mixed.
+ * need to do the exclude dance if this fs isn't mixed.
*/
if (!btrfs_fs_incompat(root->fs_info, MIXED_GROUPS)) {
ret = __exclude_logged_extent(root, ins->objectid, ins->offset);
@@ -8010,8 +8027,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(buf))
+ return buf;
+
btrfs_set_header_generation(buf, trans->transid);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
@@ -8032,13 +8050,13 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
buf->start + buf->len - 1, GFP_NOFS);
else
set_extent_new(&root->dirty_log_pages, buf->start,
- buf->start + buf->len - 1, GFP_NOFS);
+ buf->start + buf->len - 1);
} else {
buf->log_index = -1;
set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
buf->start + buf->len - 1, GFP_NOFS);
}
- trans->blocks_used++;
+ trans->dirty = true;
/* this returns a buffer locked for blocking */
return buf;
}
@@ -8653,8 +8671,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
next = btrfs_find_tree_block(root->fs_info, bytenr);
if (!next) {
next = btrfs_find_create_tree_block(root, bytenr);
- if (!next)
- return -ENOMEM;
+ if (IS_ERR(next))
+ return PTR_ERR(next);
+
btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
level - 1);
reada = 1;
@@ -9426,7 +9445,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
u64 free_bytes = 0;
int factor;
- /* It's df, we don't care if it's racey */
+ /* It's df, we don't care if it's racy */
if (list_empty(&sinfo->ro_bgs))
return 0;
@@ -10635,14 +10654,14 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
*/
mutex_lock(&fs_info->unused_bg_unpin_mutex);
ret = clear_extent_bits(&fs_info->freed_extents[0], start, end,
- EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_DIRTY);
if (ret) {
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
btrfs_dec_block_group_ro(root, block_group);
goto end_trans;
}
ret = clear_extent_bits(&fs_info->freed_extents[1], start, end,
- EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_DIRTY);
if (ret) {
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
btrfs_dec_block_group_ro(root, block_group);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2f83448d34fe..75533adef998 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -726,14 +726,6 @@ next:
start = last_end + 1;
if (start <= end && state && !need_resched())
goto hit_next;
- goto search_again;
-
-out:
- spin_unlock(&tree->lock);
- if (prealloc)
- free_extent_state(prealloc);
-
- return 0;
search_again:
if (start > end)
@@ -742,6 +734,14 @@ search_again:
if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
+
+out:
+ spin_unlock(&tree->lock);
+ if (prealloc)
+ free_extent_state(prealloc);
+
+ return 0;
+
}
static void wait_on_state(struct extent_io_tree *tree,
@@ -873,8 +873,14 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
bits |= EXTENT_FIRST_DELALLOC;
again:
if (!prealloc && gfpflags_allow_blocking(mask)) {
+ /*
+ * Don't care for allocation failure here because we might end
+ * up not needing the pre-allocated extent state at all, which
+ * is the case if we only have in the tree extent states that
+ * cover our input range and don't cover too any other range.
+ * If we end up needing a new extent state we allocate it later.
+ */
prealloc = alloc_extent_state(mask);
- BUG_ON(!prealloc);
}
spin_lock(&tree->lock);
@@ -1037,7 +1043,13 @@ hit_next:
goto out;
}
- goto search_again;
+search_again:
+ if (start > end)
+ goto out;
+ spin_unlock(&tree->lock);
+ if (gfpflags_allow_blocking(mask))
+ cond_resched();
+ goto again;
out:
spin_unlock(&tree->lock);
@@ -1046,13 +1058,6 @@ out:
return err;
-search_again:
- if (start > end)
- goto out;
- spin_unlock(&tree->lock);
- if (gfpflags_allow_blocking(mask))
- cond_resched();
- goto again;
}
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1073,17 +1078,18 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
* @bits: the bits to set in this range
* @clear_bits: the bits to clear in this range
* @cached_state: state that we're going to cache
- * @mask: the allocation mask
*
* This will go through and set bits for the given range. If any states exist
* already in this range they are set with the given bit and cleared of the
* clear_bits. This is only meant to be used by things that are mergeable, ie
* converting from say DELALLOC to DIRTY. This is not meant to be used with
* boundary bits like LOCK.
+ *
+ * All allocations are done with GFP_NOFS.
*/
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned clear_bits,
- struct extent_state **cached_state, gfp_t mask)
+ struct extent_state **cached_state)
{
struct extent_state *state;
struct extent_state *prealloc = NULL;
@@ -1098,7 +1104,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
btrfs_debug_check_extent_io_range(tree, start, end);
again:
- if (!prealloc && gfpflags_allow_blocking(mask)) {
+ if (!prealloc) {
/*
* Best effort, don't worry if extent state allocation fails
* here for the first iteration. We might have a cached state
@@ -1106,7 +1112,7 @@ again:
* extent state allocations are needed. We'll only know this
* after locking the tree.
*/
- prealloc = alloc_extent_state(mask);
+ prealloc = alloc_extent_state(GFP_NOFS);
if (!prealloc && !first_iteration)
return -ENOMEM;
}
@@ -1263,7 +1269,13 @@ hit_next:
goto out;
}
- goto search_again;
+search_again:
+ if (start > end)
+ goto out;
+ spin_unlock(&tree->lock);
+ cond_resched();
+ first_iteration = false;
+ goto again;
out:
spin_unlock(&tree->lock);
@@ -1271,21 +1283,11 @@ out:
free_extent_state(prealloc);
return err;
-
-search_again:
- if (start > end)
- goto out;
- spin_unlock(&tree->lock);
- if (gfpflags_allow_blocking(mask))
- cond_resched();
- first_iteration = false;
- goto again;
}
/* wrappers around set/clear extent bit */
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, gfp_t mask,
- struct extent_changeset *changeset)
+ unsigned bits, struct extent_changeset *changeset)
{
/*
* We don't support EXTENT_LOCKED yet, as current changeset will
@@ -1295,7 +1297,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
*/
BUG_ON(bits & EXTENT_LOCKED);
- return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask,
+ return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS,
changeset);
}
@@ -1308,8 +1310,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
}
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, gfp_t mask,
- struct extent_changeset *changeset)
+ unsigned bits, struct extent_changeset *changeset)
{
/*
* Don't support EXTENT_LOCKED case, same reason as
@@ -1317,7 +1318,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
*/
BUG_ON(bits & EXTENT_LOCKED);
- return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask,
+ return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, GFP_NOFS,
changeset);
}
@@ -1975,13 +1976,13 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
set_state_failrec(failure_tree, rec->start, NULL);
ret = clear_extent_bits(failure_tree, rec->start,
rec->start + rec->len - 1,
- EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_LOCKED | EXTENT_DIRTY);
if (ret)
err = ret;
ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
rec->start + rec->len - 1,
- EXTENT_DAMAGED, GFP_NOFS);
+ EXTENT_DAMAGED);
if (ret && !err)
err = ret;
@@ -2024,9 +2025,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
bio->bi_iter.bi_size = 0;
map_length = length;
+ /*
+ * Avoid races with device replace and make sure our bbio has devices
+ * associated to its stripes that don't go away while we are doing the
+ * read repair operation.
+ */
+ btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_block(fs_info, WRITE, logical,
&map_length, &bbio, mirror_num);
if (ret) {
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
return -EIO;
}
@@ -2036,6 +2044,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
dev = bbio->stripes[mirror_num-1].dev;
btrfs_put_bbio(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
return -EIO;
}
@@ -2044,6 +2053,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
/* try to remap that extent elsewhere? */
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
return -EIO;
@@ -2053,6 +2063,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
"read error corrected: ino %llu off %llu (dev %s sector %llu)",
btrfs_ino(inode), start,
rcu_str_deref(dev->name), sector);
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
return 0;
}
@@ -2232,13 +2243,12 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
/* set the bits in the private failure tree */
ret = set_extent_bits(failure_tree, start, end,
- EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_LOCKED | EXTENT_DIRTY);
if (ret >= 0)
ret = set_state_failrec(failure_tree, start, failrec);
/* set the bits in the inode's tree */
if (ret >= 0)
- ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED,
- GFP_NOFS);
+ ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED);
if (ret < 0) {
kfree(failrec);
return ret;
@@ -4389,8 +4399,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (ret < 0) {
btrfs_free_path(path);
return ret;
+ } else {
+ WARN_ON(!ret);
+ if (ret == 1)
+ ret = 0;
}
- WARN_ON(!ret);
+
path->slots[0]--;
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = found_key.type;
@@ -4601,7 +4615,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
if (mapped)
spin_unlock(&page->mapping->private_lock);
- /* One for when we alloced the page */
+ /* One for when we allocated the page */
put_page(page);
} while (index != 0);
}
@@ -4714,16 +4728,16 @@ err:
}
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
- u64 start)
+ u64 start, u32 nodesize)
{
unsigned long len;
if (!fs_info) {
/*
* Called only from tests that don't always have a fs_info
- * available, but we know that nodesize is 4096
+ * available
*/
- len = 4096;
+ len = nodesize;
} else {
len = fs_info->tree_root->nodesize;
}
@@ -4819,7 +4833,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
- u64 start)
+ u64 start, u32 nodesize)
{
struct extent_buffer *eb, *exists = NULL;
int ret;
@@ -4827,7 +4841,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
- eb = alloc_dummy_extent_buffer(fs_info, start);
+ eb = alloc_dummy_extent_buffer(fs_info, start, nodesize);
if (!eb)
return NULL;
eb->fs_info = fs_info;
@@ -4878,18 +4892,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
int uptodate = 1;
int ret;
+ if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) {
+ btrfs_err(fs_info, "bad tree block start %llu", start);
+ return ERR_PTR(-EINVAL);
+ }
+
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
- return NULL;
+ return ERR_PTR(-ENOMEM);
for (i = 0; i < num_pages; i++, index++) {
p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
- if (!p)
+ if (!p) {
+ exists = ERR_PTR(-ENOMEM);
goto free_eb;
+ }
spin_lock(&mapping->private_lock);
if (PagePrivate(p)) {
@@ -4934,8 +4955,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
again:
ret = radix_tree_preload(GFP_NOFS);
- if (ret)
+ if (ret) {
+ exists = ERR_PTR(ret);
goto free_eb;
+ }
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
@@ -5319,6 +5342,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
return ret;
}
+/*
+ * return 0 if the item is found within a page.
+ * return 1 if the item spans two pages.
+ * return -EINVAL otherwise.
+ */
int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
unsigned long min_len, char **map,
unsigned long *map_start,
@@ -5333,7 +5361,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
PAGE_SHIFT;
if (i != end_i)
- return -EINVAL;
+ return 1;
if (i == 0) {
offset = start_offset;
@@ -5761,7 +5789,7 @@ int try_release_extent_buffer(struct page *page)
struct extent_buffer *eb;
/*
- * We need to make sure noboody is attaching this page to an eb right
+ * We need to make sure nobody is attaching this page to an eb right
* now.
*/
spin_lock(&page->mapping->private_lock);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 981f402bf754..c0c1c4fef6ce 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -220,8 +220,7 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int filled,
struct extent_state *cached_state);
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, gfp_t mask,
- struct extent_changeset *changeset);
+ unsigned bits, struct extent_changeset *changeset);
int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int wake, int delete,
struct extent_state **cached, gfp_t mask);
@@ -240,27 +239,27 @@ static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
}
static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
- u64 end, unsigned bits, gfp_t mask)
+ u64 end, unsigned bits)
{
int wake = 0;
if (bits & EXTENT_LOCKED)
wake = 1;
- return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
+ return clear_extent_bit(tree, start, end, bits, wake, 0, NULL,
+ GFP_NOFS);
}
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, gfp_t mask,
- struct extent_changeset *changeset);
+ unsigned bits, struct extent_changeset *changeset);
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, u64 *failed_start,
struct extent_state **cached_state, gfp_t mask);
static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
- u64 end, unsigned bits, gfp_t mask)
+ u64 end, unsigned bits)
{
- return set_extent_bit(tree, start, end, bits, NULL, NULL, mask);
+ return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
}
static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -278,37 +277,38 @@ static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
}
static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
- u64 end, gfp_t mask)
+ u64 end)
{
return clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING, 0, 0, NULL, mask);
+ EXTENT_DO_ACCOUNTING, 0, 0, NULL, GFP_NOFS);
}
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned clear_bits,
- struct extent_state **cached_state, gfp_t mask);
+ struct extent_state **cached_state);
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state, gfp_t mask)
+ u64 end, struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE,
- NULL, cached_state, mask);
+ NULL, cached_state, GFP_NOFS);
}
static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state, gfp_t mask)
+ u64 end, struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
- NULL, cached_state, mask);
+ NULL, cached_state, GFP_NOFS);
}
static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
- u64 end, gfp_t mask)
+ u64 end)
{
- return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL, mask);
+ return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+ GFP_NOFS);
}
static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -348,7 +348,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len);
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
- u64 start);
+ u64 start, u32 nodesize);
struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
@@ -468,5 +468,5 @@ noinline u64 find_lock_delalloc_range(struct inode *inode,
u64 *end, u64 max_bytes);
#endif
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
- u64 start);
+ u64 start, u32 nodesize);
#endif
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 318b048eb254..e0715fcfb11e 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -62,7 +62,7 @@ struct extent_map *alloc_extent_map(void)
/**
* free_extent_map - drop reference count of an extent_map
- * @em: extent map being releasead
+ * @em: extent map being released
*
* Drops the reference out on @em by one and free the structure
* if the reference count hits zero.
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 7a7d6e253cfc..62a81ee13a5f 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -248,7 +248,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
BTRFS_DATA_RELOC_TREE_OBJECTID) {
set_extent_bits(io_tree, offset,
offset + root->sectorsize - 1,
- EXTENT_NODATASUM, GFP_NOFS);
+ EXTENT_NODATASUM);
} else {
btrfs_info(BTRFS_I(inode)->root->fs_info,
"no csum found for inode %llu start %llu",
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index c98805c35bab..2234e88cf674 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1534,30 +1534,30 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
reserve_bytes = round_up(write_bytes + sector_offset,
root->sectorsize);
- if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
- BTRFS_INODE_PREALLOC)) &&
- check_can_nocow(inode, pos, &write_bytes) > 0) {
- /*
- * For nodata cow case, no need to reserve
- * data space.
- */
- only_release_metadata = true;
- /*
- * our prealloc extent may be smaller than
- * write_bytes, so scale down.
- */
- num_pages = DIV_ROUND_UP(write_bytes + offset,
- PAGE_SIZE);
- reserve_bytes = round_up(write_bytes + sector_offset,
- root->sectorsize);
- goto reserve_metadata;
- }
-
ret = btrfs_check_data_free_space(inode, pos, write_bytes);
- if (ret < 0)
- break;
+ if (ret < 0) {
+ if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) &&
+ check_can_nocow(inode, pos, &write_bytes) > 0) {
+ /*
+ * For nodata cow case, no need to reserve
+ * data space.
+ */
+ only_release_metadata = true;
+ /*
+ * our prealloc extent may be smaller than
+ * write_bytes, so scale down.
+ */
+ num_pages = DIV_ROUND_UP(write_bytes + offset,
+ PAGE_SIZE);
+ reserve_bytes = round_up(write_bytes +
+ sector_offset,
+ root->sectorsize);
+ } else {
+ break;
+ }
+ }
-reserve_metadata:
ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
if (ret) {
if (!only_release_metadata)
@@ -1596,6 +1596,13 @@ again:
copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
+ num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ reserve_bytes);
+ dirty_sectors = round_up(copied + sector_offset,
+ root->sectorsize);
+ dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ dirty_sectors);
+
/*
* if we have trouble faulting in the pages, fall
* back to one page at a time
@@ -1605,6 +1612,7 @@ again:
if (copied == 0) {
force_page_uptodate = true;
+ dirty_sectors = 0;
dirty_pages = 0;
} else {
force_page_uptodate = false;
@@ -1615,20 +1623,19 @@ again:
/*
* If we had a short copy we need to release the excess delaloc
* bytes we reserved. We need to increment outstanding_extents
- * because btrfs_delalloc_release_space will decrement it, but
+ * because btrfs_delalloc_release_space and
+ * btrfs_delalloc_release_metadata will decrement it, but
* we still have an outstanding extent for the chunk we actually
* managed to copy.
*/
- num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
- reserve_bytes);
- dirty_sectors = round_up(copied + sector_offset,
- root->sectorsize);
- dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
- dirty_sectors);
-
if (num_sectors > dirty_sectors) {
- release_bytes = (write_bytes - copied)
- & ~((u64)root->sectorsize - 1);
+ /*
+ * we round down because we don't want to count
+ * any partial blocks actually sent through the
+ * IO machines
+ */
+ release_bytes = round_down(release_bytes - copied,
+ root->sectorsize);
if (copied > 0) {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
@@ -2022,7 +2029,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
BTRFS_I(inode)->last_trans
<= root->fs_info->last_trans_committed)) {
/*
- * We'v had everything committed since the last time we were
+ * We've had everything committed since the last time we were
* modified so clear this flag in case it was set for whatever
* reason, it's no longer relevant.
*/
@@ -2370,7 +2377,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
/* Check the aligned pages after the first unaligned page,
* if offset != orig_start, which means the first unaligned page
- * including serveral following pages are already in holes,
+ * including several following pages are already in holes,
* the extra check can be skipped */
if (offset == orig_start) {
/* after truncate page, check hole again */
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 5e6062c26129..69d270f6602c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -29,7 +29,7 @@
#include "inode-map.h"
#include "volumes.h"
-#define BITS_PER_BITMAP (PAGE_SIZE * 8)
+#define BITS_PER_BITMAP (PAGE_SIZE * 8UL)
#define MAX_CACHE_BYTES_PER_GIG SZ_32K
struct btrfs_trim_range {
@@ -1415,11 +1415,11 @@ static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl,
u64 offset)
{
u64 bitmap_start;
- u32 bytes_per_bitmap;
+ u64 bytes_per_bitmap;
bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit;
bitmap_start = offset - ctl->start;
- bitmap_start = div_u64(bitmap_start, bytes_per_bitmap);
+ bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap);
bitmap_start *= bytes_per_bitmap;
bitmap_start += ctl->start;
@@ -1638,10 +1638,10 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
u64 bitmap_bytes;
u64 extent_bytes;
u64 size = block_group->key.offset;
- u32 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
- u32 max_bitmaps = div_u64(size + bytes_per_bg - 1, bytes_per_bg);
+ u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
+ u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
- max_bitmaps = max_t(u32, max_bitmaps, 1);
+ max_bitmaps = max_t(u64, max_bitmaps, 1);
ASSERT(ctl->total_bitmaps <= max_bitmaps);
@@ -1660,7 +1660,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
* sure we don't go over our overall goal of MAX_CACHE_BYTES_PER_GIG as
* we add more bitmaps.
*/
- bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_SIZE;
+ bitmap_bytes = (ctl->total_bitmaps + 1) * ctl->unit;
if (bitmap_bytes >= max_bytes) {
ctl->extents_thresh = 0;
@@ -1983,7 +1983,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
/*
* If this block group has some small extents we don't want to
* use up all of our free slots in the cache with them, we want
- * to reserve them to larger extents, however if we have plent
+ * to reserve them to larger extents, however if we have plenty
* of cache left then go ahead an dadd them, no sense in adding
* the overhead of a bitmap if we don't have to.
*/
@@ -3662,7 +3662,7 @@ have_info:
if (tmp->offset + tmp->bytes < offset)
break;
if (offset + bytes < tmp->offset) {
- n = rb_prev(&info->offset_index);
+ n = rb_prev(&tmp->offset_index);
continue;
}
info = tmp;
@@ -3676,7 +3676,7 @@ have_info:
if (offset + bytes < tmp->offset)
break;
if (tmp->offset + tmp->bytes < offset) {
- n = rb_next(&info->offset_index);
+ n = rb_next(&tmp->offset_index);
continue;
}
info = tmp;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 33178c490ace..3af651c2bbc7 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -123,7 +123,7 @@ int btrfs_return_cluster_to_free_space(
int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen);
-/* Support functions for runnint our sanity tests */
+/* Support functions for running our sanity tests */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
u64 offset, u64 bytes, bool bitmap);
diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c
index aae520b2aee5..a97fdc156a03 100644
--- a/fs/btrfs/hash.c
+++ b/fs/btrfs/hash.c
@@ -24,6 +24,11 @@ int __init btrfs_hash_init(void)
return PTR_ERR_OR_ZERO(tfm);
}
+const char* btrfs_crc32c_impl(void)
+{
+ return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm));
+}
+
void btrfs_hash_exit(void)
{
crypto_free_shash(tfm);
diff --git a/fs/btrfs/hash.h b/fs/btrfs/hash.h
index 118a2316e5d3..c3a2ec554361 100644
--- a/fs/btrfs/hash.h
+++ b/fs/btrfs/hash.h
@@ -22,6 +22,7 @@
int __init btrfs_hash_init(void);
void btrfs_hash_exit(void);
+const char* btrfs_crc32c_impl(void);
u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 91419ef79b00..4421954720b8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -455,7 +455,7 @@ again:
/*
* skip compression for a small file range(<=blocksize) that
- * isn't an inline extent, since it dosen't save disk space at all.
+ * isn't an inline extent, since it doesn't save disk space at all.
*/
if (total_compressed <= blocksize &&
(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
@@ -1978,7 +1978,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
{
WARN_ON((end & (PAGE_SIZE - 1)) == 0);
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
- cached_state, GFP_NOFS);
+ cached_state);
}
/* see btrfs_writepage_start_hook for details on why this is required */
@@ -3119,8 +3119,7 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
- clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM,
- GFP_NOFS);
+ clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);
return 0;
}
@@ -3272,7 +3271,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
/* grab metadata reservation from transaction handle */
if (reserve) {
ret = btrfs_orphan_reserve_metadata(trans, inode);
- BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
+ ASSERT(!ret);
+ if (ret) {
+ atomic_dec(&root->orphan_inodes);
+ clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+ &BTRFS_I(inode)->runtime_flags);
+ if (insert)
+ clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+ &BTRFS_I(inode)->runtime_flags);
+ return ret;
+ }
}
/* insert an orphan item to track this unlinked/truncated file */
@@ -3722,7 +3730,7 @@ cache_index:
* and doesn't have an inode ref with the name "bar" anymore.
*
* Setting last_unlink_trans to last_trans is a pessimistic approach,
- * but it guarantees correctness at the expense of ocassional full
+ * but it guarantees correctness at the expense of occasional full
* transaction commits on fsync if our inode is a directory, or if our
* inode is not a directory, logging its parent unnecessarily.
*/
@@ -4550,6 +4558,7 @@ delete:
BUG_ON(ret);
if (btrfs_should_throttle_delayed_refs(trans, root))
btrfs_async_run_delayed_refs(root,
+ trans->transid,
trans->delayed_ref_updates * 2, 0);
if (be_nice) {
if (truncate_space_check(trans, root,
@@ -4978,7 +4987,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
* be instantly completed which will give us extents that need
* to be truncated. If we fail to get an orphan inode down we
* could have left over extents that were never meant to live,
- * so we need to garuntee from this point on that everything
+ * so we need to guarantee from this point on that everything
* will be consistent.
*/
ret = btrfs_orphan_add(trans, inode);
@@ -5248,7 +5257,7 @@ void btrfs_evict_inode(struct inode *inode)
}
/*
- * We can't just steal from the global reserve, we need tomake
+ * We can't just steal from the global reserve, we need to make
* sure there is room to do it, if not we need to commit and try
* again.
*/
@@ -5749,6 +5758,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
int name_len;
int is_curr = 0; /* ctx->pos points to the current index? */
bool emitted;
+ bool put = false;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
@@ -5766,7 +5776,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
if (key_type == BTRFS_DIR_INDEX_KEY) {
INIT_LIST_HEAD(&ins_list);
INIT_LIST_HEAD(&del_list);
- btrfs_get_delayed_items(inode, &ins_list, &del_list);
+ put = btrfs_readdir_get_delayed_items(inode, &ins_list,
+ &del_list);
}
key.type = key_type;
@@ -5913,8 +5924,8 @@ next:
nopos:
ret = 0;
err:
- if (key_type == BTRFS_DIR_INDEX_KEY)
- btrfs_put_delayed_items(&ins_list, &del_list);
+ if (put)
+ btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
btrfs_free_path(path);
return ret;
}
@@ -6980,7 +6991,18 @@ insert:
* existing will always be non-NULL, since there must be
* extent causing the -EEXIST.
*/
- if (start >= extent_map_end(existing) ||
+ if (existing->start == em->start &&
+ extent_map_end(existing) == extent_map_end(em) &&
+ em->block_start == existing->block_start) {
+ /*
+ * these two extents are the same, it happens
+ * with inlines especially
+ */
+ free_extent_map(em);
+ em = existing;
+ err = 0;
+
+ } else if (start >= extent_map_end(existing) ||
start <= existing->start) {
/*
* The existing extent map is the one nearest to
@@ -7433,7 +7455,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
cached_state);
/*
* We're concerned with the entire range that we're going to be
- * doing DIO to, so we need to make sure theres no ordered
+ * doing DIO to, so we need to make sure there's no ordered
* extents in this range.
*/
ordered = btrfs_lookup_ordered_range(inode, lockstart,
@@ -7595,7 +7617,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
if (current->journal_info) {
/*
* Need to pull our outstanding extents and set journal_info to NULL so
- * that anything that needs to check if there's a transction doesn't get
+ * that anything that needs to check if there's a transaction doesn't get
* confused.
*/
dio_data = current->journal_info;
@@ -7628,7 +7650,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
* decompress it, so there will be buffering required no matter what we
* do, so go ahead and fallback to buffered.
*
- * We return -ENOTBLK because thats what makes DIO go ahead and go back
+ * We return -ENOTBLK because that's what makes DIO go ahead and go back
* to buffered IO. Don't blame me, this is the price we pay for using
* the generic code.
*/
@@ -9041,7 +9063,7 @@ static int btrfs_truncate(struct inode *inode)
return ret;
/*
- * Yes ladies and gentelment, this is indeed ugly. The fact is we have
+ * Yes ladies and gentlemen, this is indeed ugly. The fact is we have
* 3 things going on here
*
* 1) We need to reserve space for our orphan item and the space to
@@ -9055,15 +9077,15 @@ static int btrfs_truncate(struct inode *inode)
* space reserved in case it uses space during the truncate (thank you
* very much snapshotting).
*
- * And we need these to all be seperate. The fact is we can use alot of
+ * And we need these to all be separate. The fact is we can use a lot of
* space doing the truncate, and we have no earthly idea how much space
- * we will use, so we need the truncate reservation to be seperate so it
+ * we will use, so we need the truncate reservation to be separate so it
* doesn't end up using space reserved for updating the inode or
* removing the orphan item. We also need to be able to stop the
* transaction and start a new one, which means we need to be able to
* update the inode several times, and we have no idea of knowing how
* many times that will be, so we can't just reserve 1 item for the
- * entirety of the opration, so that has to be done seperately as well.
+ * entirety of the operation, so that has to be done separately as well.
* Then there is the orphan item, which does indeed need to be held on
* to for the whole operation, and we need nobody to touch this reserved
* space except the orphan code.
@@ -10515,7 +10537,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = {
static const struct file_operations btrfs_dir_file_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = btrfs_real_readdir,
+ .iterate_shared = btrfs_real_readdir,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_compat_ioctl,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4e700694b741..05173563e4a6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -296,7 +296,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
}
} else {
/*
- * Revert back under same assuptions as above
+ * Revert back under same assumptions as above
*/
if (S_ISREG(mode)) {
if (inode->i_size == 0)
@@ -465,7 +465,7 @@ static noinline int create_subvol(struct inode *dir,
/*
* Don't create subvolume whose level is not zero. Or qgroup will be
- * screwed up since it assume subvolme qgroup's level to be 0.
+ * screwed up since it assumes subvolume qgroup's level to be 0.
*/
if (btrfs_qgroup_level(objectid)) {
ret = -ENOSPC;
@@ -780,7 +780,7 @@ free_pending:
* a. be owner of dir, or
* b. be owner of victim, or
* c. have CAP_FOWNER capability
- * 6. If the victim is append-only or immutable we can't do antyhing with
+ * 6. If the victim is append-only or immutable we can't do anything with
* links pointing to it.
* 7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
* 8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
@@ -846,11 +846,9 @@ static noinline int btrfs_mksubvol(struct path *parent,
struct dentry *dentry;
int error;
- inode_lock_nested(dir, I_MUTEX_PARENT);
- // XXX: should've been
- // mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- // if (error == -EINTR)
- // return error;
+ error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
+ if (error == -EINTR)
+ return error;
dentry = lookup_one_len(name, parent->dentry, namelen);
error = PTR_ERR(dentry);
@@ -1239,7 +1237,7 @@ again:
set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
- &cached_state, GFP_NOFS);
+ &cached_state);
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
page_start, page_end - 1, &cached_state,
@@ -2377,11 +2375,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
goto out;
- inode_lock_nested(dir, I_MUTEX_PARENT);
- // XXX: should've been
- // err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- // if (err == -EINTR)
- // goto out_drop_write;
+ err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
+ if (err == -EINTR)
+ goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -2571,7 +2567,7 @@ out_dput:
dput(dentry);
out_unlock_dir:
inode_unlock(dir);
-//out_drop_write:
+out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
@@ -4654,7 +4650,7 @@ again:
}
/*
- * mut. excl. ops lock is locked. Three possibilites:
+ * mut. excl. ops lock is locked. Three possibilities:
* (1) some other op is running
* (2) balance is running
* (3) balance is paused -- special case (think resume)
@@ -5571,7 +5567,7 @@ long btrfs_ioctl(struct file *file, unsigned int
ret = btrfs_sync_fs(file_inode(file)->i_sb, 1);
/*
* The transaction thread may want to do more work,
- * namely it pokes the cleaner ktread that will start
+ * namely it pokes the cleaner kthread that will start
* processing uncleaned subvols.
*/
wake_up_process(root->fs_info->transaction_kthread);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 559170464d7c..aca8264f4a49 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -718,12 +718,13 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
return count;
}
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
const u64 range_start, const u64 range_len)
{
struct btrfs_root *root;
struct list_head splice;
int done;
+ int total_done = 0;
INIT_LIST_HEAD(&splice);
@@ -742,6 +743,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
done = btrfs_wait_ordered_extents(root, nr,
range_start, range_len);
btrfs_put_fs_root(root);
+ total_done += done;
spin_lock(&fs_info->ordered_root_lock);
if (nr != -1) {
@@ -752,6 +754,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
list_splice_tail(&splice, &fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
mutex_unlock(&fs_info->ordered_operations_mutex);
+
+ return total_done;
}
/*
@@ -964,6 +968,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
struct rb_node *prev = NULL;
struct btrfs_ordered_extent *test;
int ret = 1;
+ u64 orig_offset = offset;
spin_lock_irq(&tree->lock);
if (ordered) {
@@ -979,7 +984,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
/* truncate file */
if (disk_i_size > i_size) {
- BTRFS_I(inode)->disk_i_size = i_size;
+ BTRFS_I(inode)->disk_i_size = orig_offset;
ret = 0;
goto out;
}
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 8ef12623d65c..451507776ff5 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -58,7 +58,7 @@ struct btrfs_ordered_sum {
#define BTRFS_ORDERED_COMPRESSED 3 /* writing a zlib compressed extent */
-#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
+#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to preallocated extent */
#define BTRFS_ORDERED_DIRECT 5 /* set when we're doing DIO with this extent */
@@ -199,7 +199,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
u32 *sum, int len);
int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
const u64 range_start, const u64 range_len);
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
const u64 range_start, const u64 range_len);
void btrfs_get_logged_extents(struct inode *inode,
struct list_head *logged_list,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 9e119552ed32..9d4c05b14f6e 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -85,7 +85,7 @@ struct btrfs_qgroup {
/*
* temp variables for accounting operations
- * Refer to qgroup_shared_accouting() for details.
+ * Refer to qgroup_shared_accounting() for details.
*/
u64 old_refcnt;
u64 new_refcnt;
@@ -499,7 +499,7 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
}
/*
* we call btrfs_free_qgroup_config() when umounting
- * filesystem and disabling quota, so we set qgroup_ulit
+ * filesystem and disabling quota, so we set qgroup_ulist
* to be null here to avoid double free.
*/
ulist_free(fs_info->qgroup_ulist);
@@ -1036,7 +1036,7 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info,
/*
* The easy accounting, if we are adding/removing the only ref for an extent
- * then this qgroup and all of the parent qgroups get their refrence and
+ * then this qgroup and all of the parent qgroups get their reference and
* exclusive counts adjusted.
*
* Caller should hold fs_info->qgroup_lock.
@@ -1436,7 +1436,7 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
/*
* No need to do lock, since this function will only be called in
- * btrfs_commmit_transaction().
+ * btrfs_commit_transaction().
*/
node = rb_first(&delayed_refs->dirty_extent_root);
while (node) {
@@ -1557,7 +1557,7 @@ static int qgroup_update_refcnt(struct btrfs_fs_info *fs_info,
* A: cur_old_roots < nr_old_roots (not exclusive before)
* !A: cur_old_roots == nr_old_roots (possible exclusive before)
* B: cur_new_roots < nr_new_roots (not exclusive now)
- * !B: cur_new_roots == nr_new_roots (possible exclsuive now)
+ * !B: cur_new_roots == nr_new_roots (possible exclusive now)
*
* Results:
* +: Possible sharing -> exclusive -: Possible exclusive -> sharing
@@ -1851,7 +1851,7 @@ out:
}
/*
- * Copy the acounting information between qgroups. This is necessary
+ * Copy the accounting information between qgroups. This is necessary
* when a snapshot or a subvolume is created. Throwing an error will
* cause a transaction abort so we take extra care here to only error
* when a readonly fs is a reasonable outcome.
@@ -2340,7 +2340,7 @@ out:
mutex_unlock(&fs_info->qgroup_rescan_lock);
/*
- * only update status, since the previous part has alreay updated the
+ * only update status, since the previous part has already updated the
* qgroup info.
*/
trans = btrfs_start_transaction(fs_info->quota_root, 1);
@@ -2542,8 +2542,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len)
changeset.bytes_changed = 0;
changeset.range_changed = ulist_alloc(GFP_NOFS);
ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
- start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
- &changeset);
+ start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
trace_btrfs_qgroup_reserve_data(inode, start, len,
changeset.bytes_changed,
QGROUP_RESERVE);
@@ -2580,8 +2579,7 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
return -ENOMEM;
ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
- start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
- &changeset);
+ start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
if (ret < 0)
goto out;
@@ -2672,7 +2670,7 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
}
/*
- * Check qgroup reserved space leaking, normally at destory inode
+ * Check qgroup reserved space leaking, normally at destroy inode
* time
*/
void btrfs_qgroup_check_reserved_leak(struct inode *inode)
@@ -2688,7 +2686,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode)
return;
ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
- EXTENT_QGROUP_RESERVED, GFP_NOFS, &changeset);
+ EXTENT_QGROUP_RESERVED, &changeset);
WARN_ON(ret < 0);
if (WARN_ON(changeset.bytes_changed)) {
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0b7792e02dd5..f8b6d411a034 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -576,7 +576,7 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
* we can't merge with cached rbios, since the
* idea is that when we merge the destination
* rbio is going to run our IO for us. We can
- * steal from cached rbio's though, other functions
+ * steal from cached rbios though, other functions
* handle that.
*/
if (test_bit(RBIO_CACHE_BIT, &last->flags) ||
@@ -2368,7 +2368,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
}
- /* Check scrubbing pairty and repair it */
+ /* Check scrubbing parity and repair it */
p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
parity = kmap(p);
if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
@@ -2493,7 +2493,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
/*
* Here means we got one corrupted data stripe and one
* corrupted parity on RAID6, if the corrupted parity
- * is scrubbing parity, luckly, use the other one to repair
+ * is scrubbing parity, luckily, use the other one to repair
* the data, or we can not repair the data stripe.
*/
if (failp != rbio->scrubp)
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 298631eaee78..8428db7cd88f 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -761,12 +761,14 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info)
do {
enqueued = 0;
+ mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (atomic_read(&device->reada_in_flight) <
MAX_IN_FLIGHT)
enqueued += reada_start_machine_dev(fs_info,
device);
}
+ mutex_unlock(&fs_devices->device_list_mutex);
total += enqueued;
} while (enqueued && total < 10000);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 1cfd35cfac76..0477dca154ed 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -668,8 +668,8 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
* roots of b-trees that reference the tree block.
*
* the basic idea of this function is check backrefs of a given block
- * to find upper level blocks that refernece the block, and then check
- * bakcrefs of these upper level blocks recursively. the recursion stop
+ * to find upper level blocks that reference the block, and then check
+ * backrefs of these upper level blocks recursively. the recursion stop
* when tree root is reached or backrefs for the block is cached.
*
* NOTE: if we find backrefs for a block are cached, we know backrefs
@@ -1160,7 +1160,7 @@ out:
if (!RB_EMPTY_NODE(&upper->rb_node))
continue;
- /* Add this guy's upper edges to the list to proces */
+ /* Add this guy's upper edges to the list to process */
list_for_each_entry(edge, &upper->upper, list[LOWER])
list_add_tail(&edge->list[UPPER], &list);
if (list_empty(&upper->upper))
@@ -2396,7 +2396,7 @@ again:
}
/*
- * we keep the old last snapshod transid in rtranid when we
+ * we keep the old last snapshot transid in rtranid when we
* created the relocation tree.
*/
last_snap = btrfs_root_rtransid(&reloc_root->root_item);
@@ -2616,7 +2616,7 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
* only one thread can access block_rsv at this point,
* so we don't need hold lock to protect block_rsv.
* we expand more reservation size here to allow enough
- * space for relocation and we will return eailer in
+ * space for relocation and we will return earlier in
* enospc case.
*/
rc->block_rsv->size = tmp + rc->extent_root->nodesize *
@@ -2814,7 +2814,7 @@ static void mark_block_processed(struct reloc_control *rc,
u64 bytenr, u32 blocksize)
{
set_extent_bits(&rc->processed_blocks, bytenr, bytenr + blocksize - 1,
- EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_DIRTY);
}
static void __mark_block_processed(struct reloc_control *rc,
@@ -3182,7 +3182,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
page_start + offset == cluster->boundary[nr]) {
set_extent_bits(&BTRFS_I(inode)->io_tree,
page_start, page_end,
- EXTENT_BOUNDARY, GFP_NOFS);
+ EXTENT_BOUNDARY);
nr++;
}
@@ -4059,8 +4059,7 @@ restart:
}
btrfs_release_path(path);
- clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY,
- GFP_NOFS);
+ clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY);
if (trans) {
btrfs_end_transaction_throttle(trans, rc->extent_root);
@@ -4591,7 +4590,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
/*
* called before creating snapshot. it calculates metadata reservation
- * requried for relocating tree blocks in the snapshot
+ * required for relocating tree blocks in the snapshot
*/
void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
u64 *bytes_to_reserve)
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index b2b14e7115f1..f1c30861d062 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -71,9 +71,9 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
* search_key: the key to search
* path: the path we search
* root_item: the root item of the tree we look for
- * root_key: the reak key of the tree we look for
+ * root_key: the root key of the tree we look for
*
- * If ->offset of 'seach_key' is -1ULL, it means we are not sure the offset
+ * If ->offset of 'search_key' is -1ULL, it means we are not sure the offset
* of the search key, just lookup the root with the highest offset for a
* given objectid.
*
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fa35cdc46494..70427ef66b04 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -745,7 +745,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
* sure we read the bad mirror.
*/
ret = set_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
- EXTENT_DAMAGED, GFP_NOFS);
+ EXTENT_DAMAGED);
if (ret) {
/* set_extent_bits should give proper error */
WARN_ON(ret > 0);
@@ -763,7 +763,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
end, EXTENT_DAMAGED, 0, NULL);
if (!corrected)
clear_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
- EXTENT_DAMAGED, GFP_NOFS);
+ EXTENT_DAMAGED);
}
out:
@@ -1044,7 +1044,7 @@ nodatasum_case:
/*
* !is_metadata and !have_csum, this means that the data
- * might not be COW'ed, that it might be modified
+ * might not be COWed, that it might be modified
* concurrently. The general strategy to work on the
* commit root does not help in the case when COW is not
* used.
@@ -1125,7 +1125,7 @@ nodatasum_case:
* the 2nd page of mirror #1 faces I/O errors, and the 2nd page
* of mirror #2 is readable but the final checksum test fails,
* then the 2nd page of mirror #3 could be tried, whether now
- * the final checksum succeedes. But this would be a rare
+ * the final checksum succeeds. But this would be a rare
* exception and is therefore not implemented. At least it is
* avoided that the good copy is overwritten.
* A more useful improvement would be to pick the sectors
@@ -2181,7 +2181,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
u64 length = sblock->page_count * PAGE_SIZE;
u64 logical = sblock->pagev[0]->logical;
- struct btrfs_bio *bbio;
+ struct btrfs_bio *bbio = NULL;
struct bio *bio;
struct btrfs_raid_bio *rbio;
int ret;
@@ -2982,6 +2982,7 @@ again:
extent_len);
mapped_length = extent_len;
+ bbio = NULL;
ret = btrfs_map_block(fs_info, READ, extent_logical,
&mapped_length, &bbio, 0);
if (!ret) {
@@ -3581,6 +3582,46 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
*/
scrub_pause_on(fs_info);
ret = btrfs_inc_block_group_ro(root, cache);
+ if (!ret && is_dev_replace) {
+ /*
+ * If we are doing a device replace wait for any tasks
+ * that started dellaloc right before we set the block
+ * group to RO mode, as they might have just allocated
+ * an extent from it or decided they could do a nocow
+ * write. And if any such tasks did that, wait for their
+ * ordered extents to complete and then commit the
+ * current transaction, so that we can later see the new
+ * extent items in the extent tree - the ordered extents
+ * create delayed data references (for cow writes) when
+ * they complete, which will be run and insert the
+ * corresponding extent items into the extent tree when
+ * we commit the transaction they used when running
+ * inode.c:btrfs_finish_ordered_io(). We later use
+ * the commit root of the extent tree to find extents
+ * to copy from the srcdev into the tgtdev, and we don't
+ * want to miss any new extents.
+ */
+ btrfs_wait_block_group_reservations(cache);
+ btrfs_wait_nocow_writers(cache);
+ ret = btrfs_wait_ordered_roots(fs_info, -1,
+ cache->key.objectid,
+ cache->key.offset);
+ if (ret > 0) {
+ struct btrfs_trans_handle *trans;
+
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans))
+ ret = PTR_ERR(trans);
+ else
+ ret = btrfs_commit_transaction(trans,
+ root);
+ if (ret) {
+ scrub_pause_off(fs_info);
+ btrfs_put_block_group(cache);
+ break;
+ }
+ }
+ }
scrub_pause_off(fs_info);
if (ret == 0) {
@@ -3601,9 +3642,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
break;
}
+ btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
dev_replace->cursor_right = found_key.offset + length;
dev_replace->cursor_left = found_key.offset;
dev_replace->item_needs_writeback = 1;
+ btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
found_key.offset, cache, is_dev_replace);
@@ -3639,6 +3682,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
scrub_pause_off(fs_info);
+ btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
+ dev_replace->cursor_left = dev_replace->cursor_right;
+ dev_replace->item_needs_writeback = 1;
+ btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
+
if (ro_set)
btrfs_dec_block_group_ro(root, cache);
@@ -3676,9 +3724,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
ret = -ENOMEM;
break;
}
-
- dev_replace->cursor_left = dev_replace->cursor_right;
- dev_replace->item_needs_writeback = 1;
skip:
key.offset = found_key.offset + length;
btrfs_release_path(path);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 6a8c86074aa4..b71dd298385c 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1831,7 +1831,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
/*
* If we have a parent root we need to verify that the parent dir was
- * not delted and then re-created, if it was then we have no overwrite
+ * not deleted and then re-created, if it was then we have no overwrite
* and we can just unlink this entry.
*/
if (sctx->parent_root) {
@@ -4192,9 +4192,9 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key,
return -ENOMEM;
/*
- * This hack is needed because empty acl's are stored as zero byte
+ * This hack is needed because empty acls are stored as zero byte
* data in xattrs. Problem with that is, that receiving these zero byte
- * acl's will fail later. To fix this, we send a dummy acl list that
+ * acls will fail later. To fix this, we send a dummy acl list that
* only contains the version number and no entries.
*/
if (!strncmp(name, XATTR_NAME_POSIX_ACL_ACCESS, name_len) ||
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index e05619f241be..875c757e73e2 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -36,7 +36,7 @@ static inline void put_unaligned_le8(u8 val, void *p)
*
* The end result is that anyone who #includes ctree.h gets a
* declaration for the btrfs_set_foo functions and btrfs_foo functions,
- * which are wappers of btrfs_set_token_#bits functions and
+ * which are wrappers of btrfs_set_token_#bits functions and
* btrfs_get_token_#bits functions, which are defined in this file.
*
* These setget functions do all the extent_buffer related mapping
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index bf71071ab6f6..60e7179ed4b7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -112,7 +112,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
* Note that a running device replace operation is not
* canceled here although there is no way to update
* the progress. It would add the risk of a deadlock,
- * therefore the canceling is ommited. The only penalty
+ * therefore the canceling is omitted. The only penalty
* is that some I/O remains active until the procedure
* completes. The next time when the filesystem is
* mounted writeable again, the device replace
@@ -235,7 +235,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
trans->aborted = errno;
/* Nothing used. The other threads that have joined this
* transaction may be able to continue. */
- if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
+ if (!trans->dirty && list_empty(&trans->new_bgs)) {
const char *errstr;
errstr = btrfs_decode_error(errno);
@@ -1807,6 +1807,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
}
}
sb->s_flags &= ~MS_RDONLY;
+
+ fs_info->open = 1;
}
out:
wake_up_process(fs_info->transaction_kthread);
@@ -1877,7 +1879,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
int ret;
/*
- * We aren't under the device list lock, so this is racey-ish, but good
+ * We aren't under the device list lock, so this is racy-ish, but good
* enough for our purposes.
*/
nr_devices = fs_info->fs_devices->open_devices;
@@ -1896,7 +1898,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
if (!devices_info)
return -ENOMEM;
- /* calc min stripe number for data space alloction */
+ /* calc min stripe number for data space allocation */
type = btrfs_get_alloc_profile(root, 1);
if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
@@ -1932,7 +1934,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
avail_space *= BTRFS_STRIPE_LEN;
/*
- * In order to avoid overwritting the superblock on the drive,
+ * In order to avoid overwriting the superblock on the drive,
* btrfs starts at an offset of at least 1MB when doing chunk
* allocation.
*/
@@ -2303,7 +2305,7 @@ static void btrfs_interface_exit(void)
static void btrfs_print_mod_info(void)
{
- printk(KERN_INFO "Btrfs loaded"
+ printk(KERN_INFO "Btrfs loaded, crc32c=%s"
#ifdef CONFIG_BTRFS_DEBUG
", debug=on"
#endif
@@ -2313,33 +2315,48 @@ static void btrfs_print_mod_info(void)
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
", integrity-checker=on"
#endif
- "\n");
+ "\n",
+ btrfs_crc32c_impl());
}
static int btrfs_run_sanity_tests(void)
{
- int ret;
-
+ int ret, i;
+ u32 sectorsize, nodesize;
+ u32 test_sectorsize[] = {
+ PAGE_SIZE,
+ };
ret = btrfs_init_test_fs();
if (ret)
return ret;
-
- ret = btrfs_test_free_space_cache();
- if (ret)
- goto out;
- ret = btrfs_test_extent_buffer_operations();
- if (ret)
- goto out;
- ret = btrfs_test_extent_io();
- if (ret)
- goto out;
- ret = btrfs_test_inodes();
- if (ret)
- goto out;
- ret = btrfs_test_qgroups();
- if (ret)
- goto out;
- ret = btrfs_test_free_space_tree();
+ for (i = 0; i < ARRAY_SIZE(test_sectorsize); i++) {
+ sectorsize = test_sectorsize[i];
+ for (nodesize = sectorsize;
+ nodesize <= BTRFS_MAX_METADATA_BLOCKSIZE;
+ nodesize <<= 1) {
+ pr_info("BTRFS: selftest: sectorsize: %u nodesize: %u\n",
+ sectorsize, nodesize);
+ ret = btrfs_test_free_space_cache(sectorsize, nodesize);
+ if (ret)
+ goto out;
+ ret = btrfs_test_extent_buffer_operations(sectorsize,
+ nodesize);
+ if (ret)
+ goto out;
+ ret = btrfs_test_extent_io(sectorsize, nodesize);
+ if (ret)
+ goto out;
+ ret = btrfs_test_inodes(sectorsize, nodesize);
+ if (ret)
+ goto out;
+ ret = btrfs_test_qgroups(sectorsize, nodesize);
+ if (ret)
+ goto out;
+ ret = btrfs_test_free_space_tree(sectorsize, nodesize);
+ if (ret)
+ goto out;
+ }
+ }
out:
btrfs_destroy_test_fs();
return ret;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index f54bf450bad3..02223f3f78f4 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -68,7 +68,7 @@ int btrfs_init_test_fs(void)
if (IS_ERR(test_mnt)) {
printk(KERN_ERR "btrfs: cannot mount test file system\n");
unregister_filesystem(&test_type);
- return ret;
+ return PTR_ERR(test_mnt);
}
return 0;
}
@@ -175,7 +175,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
}
struct btrfs_block_group_cache *
-btrfs_alloc_dummy_block_group(unsigned long length)
+btrfs_alloc_dummy_block_group(unsigned long length, u32 sectorsize)
{
struct btrfs_block_group_cache *cache;
@@ -192,8 +192,8 @@ btrfs_alloc_dummy_block_group(unsigned long length)
cache->key.objectid = 0;
cache->key.offset = length;
cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
- cache->sectorsize = 4096;
- cache->full_stripe_len = 4096;
+ cache->sectorsize = sectorsize;
+ cache->full_stripe_len = sectorsize;
INIT_LIST_HEAD(&cache->list);
INIT_LIST_HEAD(&cache->cluster_list);
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 054b8c73c951..66fb6b701eb7 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -26,27 +26,28 @@
struct btrfs_root;
struct btrfs_trans_handle;
-int btrfs_test_free_space_cache(void);
-int btrfs_test_extent_buffer_operations(void);
-int btrfs_test_extent_io(void);
-int btrfs_test_inodes(void);
-int btrfs_test_qgroups(void);
-int btrfs_test_free_space_tree(void);
+int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize);
+int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize);
+int btrfs_test_extent_io(u32 sectorsize, u32 nodesize);
+int btrfs_test_inodes(u32 sectorsize, u32 nodesize);
+int btrfs_test_qgroups(u32 sectorsize, u32 nodesize);
+int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize);
int btrfs_init_test_fs(void);
void btrfs_destroy_test_fs(void);
struct inode *btrfs_new_test_inode(void);
struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void);
void btrfs_free_dummy_root(struct btrfs_root *root);
struct btrfs_block_group_cache *
-btrfs_alloc_dummy_block_group(unsigned long length);
+btrfs_alloc_dummy_block_group(unsigned long length, u32 sectorsize);
void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans);
#else
-static inline int btrfs_test_free_space_cache(void)
+static inline int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
{
return 0;
}
-static inline int btrfs_test_extent_buffer_operations(void)
+static inline int btrfs_test_extent_buffer_operations(u32 sectorsize,
+ u32 nodesize)
{
return 0;
}
@@ -57,19 +58,19 @@ static inline int btrfs_init_test_fs(void)
static inline void btrfs_destroy_test_fs(void)
{
}
-static inline int btrfs_test_extent_io(void)
+static inline int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
{
return 0;
}
-static inline int btrfs_test_inodes(void)
+static inline int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
{
return 0;
}
-static inline int btrfs_test_qgroups(void)
+static inline int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
{
return 0;
}
-static inline int btrfs_test_free_space_tree(void)
+static inline int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
{
return 0;
}
diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c
index f51963a8f929..4f8cbd1ec5ee 100644
--- a/fs/btrfs/tests/extent-buffer-tests.c
+++ b/fs/btrfs/tests/extent-buffer-tests.c
@@ -22,7 +22,7 @@
#include "../extent_io.h"
#include "../disk-io.h"
-static int test_btrfs_split_item(void)
+static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
{
struct btrfs_path *path;
struct btrfs_root *root;
@@ -40,7 +40,7 @@ static int test_btrfs_split_item(void)
test_msg("Running btrfs_split_item tests\n");
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
test_msg("Could not allocate root\n");
return PTR_ERR(root);
@@ -53,7 +53,8 @@ static int test_btrfs_split_item(void)
return -ENOMEM;
}
- path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, 4096);
+ path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, nodesize,
+ nodesize);
if (!eb) {
test_msg("Could not allocate dummy buffer\n");
ret = -ENOMEM;
@@ -222,8 +223,8 @@ out:
return ret;
}
-int btrfs_test_extent_buffer_operations(void)
+int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize)
{
- test_msg("Running extent buffer operation tests");
- return test_btrfs_split_item();
+ test_msg("Running extent buffer operation tests\n");
+ return test_btrfs_split_item(sectorsize, nodesize);
}
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 70948b13bc81..d19ab0317283 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -21,6 +21,7 @@
#include <linux/slab.h>
#include <linux/sizes.h>
#include "btrfs-tests.h"
+#include "../ctree.h"
#include "../extent_io.h"
#define PROCESS_UNLOCK (1 << 0)
@@ -65,7 +66,7 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
return count;
}
-static int test_find_delalloc(void)
+static int test_find_delalloc(u32 sectorsize)
{
struct inode *inode;
struct extent_io_tree tmp;
@@ -113,7 +114,7 @@ static int test_find_delalloc(void)
* |--- delalloc ---|
* |--- search ---|
*/
- set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL);
+ set_extent_delalloc(&tmp, 0, sectorsize - 1, NULL);
start = 0;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -122,9 +123,9 @@ static int test_find_delalloc(void)
test_msg("Should have found at least one delalloc\n");
goto out_bits;
}
- if (start != 0 || end != 4095) {
- test_msg("Expected start 0 end 4095, got start %Lu end %Lu\n",
- start, end);
+ if (start != 0 || end != (sectorsize - 1)) {
+ test_msg("Expected start 0 end %u, got start %llu end %llu\n",
+ sectorsize - 1, start, end);
goto out_bits;
}
unlock_extent(&tmp, start, end);
@@ -144,7 +145,7 @@ static int test_find_delalloc(void)
test_msg("Couldn't find the locked page\n");
goto out_bits;
}
- set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL);
+ set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, NULL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -172,11 +173,11 @@ static int test_find_delalloc(void)
* |--- delalloc ---|
* |--- search ---|
*/
- test_start = max_bytes + 4096;
+ test_start = max_bytes + sectorsize;
locked_page = find_lock_page(inode->i_mapping, test_start >>
PAGE_SHIFT);
if (!locked_page) {
- test_msg("Could'nt find the locked page\n");
+ test_msg("Couldn't find the locked page\n");
goto out_bits;
}
start = test_start;
@@ -199,7 +200,7 @@ static int test_find_delalloc(void)
*
* We are re-using our test_start from above since it works out well.
*/
- set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL);
+ set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -262,7 +263,7 @@ static int test_find_delalloc(void)
}
ret = 0;
out_bits:
- clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL);
+ clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1);
out:
if (locked_page)
put_page(locked_page);
@@ -272,6 +273,16 @@ out:
return ret;
}
+/**
+ * test_bit_in_byte - Determine whether a bit is set in a byte
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit_in_byte(int nr, const u8 *addr)
+{
+ return 1UL & (addr[nr / BITS_PER_BYTE] >> (nr & (BITS_PER_BYTE - 1)));
+}
+
static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
unsigned long len)
{
@@ -298,25 +309,29 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
return -EINVAL;
}
- bitmap_set(bitmap, (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
- sizeof(long) * BITS_PER_BYTE);
- extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
- sizeof(long) * BITS_PER_BYTE);
- if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
- test_msg("Setting straddling pages failed\n");
- return -EINVAL;
- }
+ /* Straddling pages test */
+ if (len > PAGE_SIZE) {
+ bitmap_set(bitmap,
+ (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+ sizeof(long) * BITS_PER_BYTE);
+ extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+ sizeof(long) * BITS_PER_BYTE);
+ if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+ test_msg("Setting straddling pages failed\n");
+ return -EINVAL;
+ }
- bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
- bitmap_clear(bitmap,
- (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
- sizeof(long) * BITS_PER_BYTE);
- extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
- extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
- sizeof(long) * BITS_PER_BYTE);
- if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
- test_msg("Clearing straddling pages failed\n");
- return -EINVAL;
+ bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
+ bitmap_clear(bitmap,
+ (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+ sizeof(long) * BITS_PER_BYTE);
+ extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
+ extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+ sizeof(long) * BITS_PER_BYTE);
+ if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+ test_msg("Clearing straddling pages failed\n");
+ return -EINVAL;
+ }
}
/*
@@ -333,7 +348,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
for (i = 0; i < len * BITS_PER_BYTE; i++) {
int bit, bit1;
- bit = !!test_bit(i, bitmap);
+ bit = !!test_bit_in_byte(i, (u8 *)bitmap);
bit1 = !!extent_buffer_test_bit(eb, 0, i);
if (bit1 != bit) {
test_msg("Testing bit pattern failed\n");
@@ -351,15 +366,22 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
return 0;
}
-static int test_eb_bitmaps(void)
+static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
{
- unsigned long len = PAGE_SIZE * 4;
+ unsigned long len;
unsigned long *bitmap;
struct extent_buffer *eb;
int ret;
test_msg("Running extent buffer bitmap tests\n");
+ /*
+ * In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than
+ * BTRFS_MAX_METADATA_BLOCKSIZE.
+ */
+ len = (sectorsize < BTRFS_MAX_METADATA_BLOCKSIZE)
+ ? sectorsize * 4 : sectorsize;
+
bitmap = kmalloc(len, GFP_KERNEL);
if (!bitmap) {
test_msg("Couldn't allocate test bitmap\n");
@@ -379,7 +401,7 @@ static int test_eb_bitmaps(void)
/* Do it over again with an extent buffer which isn't page-aligned. */
free_extent_buffer(eb);
- eb = __alloc_dummy_extent_buffer(NULL, PAGE_SIZE / 2, len);
+ eb = __alloc_dummy_extent_buffer(NULL, nodesize / 2, len);
if (!eb) {
test_msg("Couldn't allocate test extent buffer\n");
kfree(bitmap);
@@ -393,17 +415,17 @@ out:
return ret;
}
-int btrfs_test_extent_io(void)
+int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
{
int ret;
test_msg("Running extent I/O tests\n");
- ret = test_find_delalloc();
+ ret = test_find_delalloc(sectorsize);
if (ret)
goto out;
- ret = test_eb_bitmaps();
+ ret = test_eb_bitmaps(sectorsize, nodesize);
out:
test_msg("Extent I/O tests finished\n");
return ret;
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index 514247515312..3956bb2ff84c 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -22,10 +22,10 @@
#include "../disk-io.h"
#include "../free-space-cache.h"
-#define BITS_PER_BITMAP (PAGE_SIZE * 8)
+#define BITS_PER_BITMAP (PAGE_SIZE * 8UL)
/*
- * This test just does basic sanity checking, making sure we can add an exten
+ * This test just does basic sanity checking, making sure we can add an extent
* entry and remove space from either end and the middle, and make sure we can
* remove space that covers adjacent extent entries.
*/
@@ -99,7 +99,8 @@ static int test_extents(struct btrfs_block_group_cache *cache)
return 0;
}
-static int test_bitmaps(struct btrfs_block_group_cache *cache)
+static int test_bitmaps(struct btrfs_block_group_cache *cache,
+ u32 sectorsize)
{
u64 next_bitmap_offset;
int ret;
@@ -139,7 +140,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
* The first bitmap we have starts at offset 0 so the next one is just
* at the end of the first bitmap.
*/
- next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+ next_bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
/* Test a bit straddling two bitmaps */
ret = test_add_free_space_entry(cache, next_bitmap_offset - SZ_2M,
@@ -167,9 +168,10 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
}
/* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
+static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
+ u32 sectorsize)
{
- u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+ u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
int ret;
test_msg("Running bitmap and extent tests\n");
@@ -396,11 +398,13 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
* wasn't optimal as they could be spread all over the block group while under
* concurrency (extra overhead and fragmentation).
*
- * This stealing approach is benefical, since we always prefer to allocate from
- * extent entries, both for clustered and non-clustered allocation requests.
+ * This stealing approach is beneficial, since we always prefer to allocate
+ * from extent entries, both for clustered and non-clustered allocation
+ * requests.
*/
static int
-test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
+ u32 sectorsize)
{
int ret;
u64 offset;
@@ -538,7 +542,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
* The goal is to test that the bitmap entry space stealing doesn't
* steal this space region.
*/
- ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, 4096);
+ ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, sectorsize);
if (ret) {
test_msg("Error adding free space: %d\n", ret);
return ret;
@@ -596,8 +600,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
return -ENOENT;
}
- if (cache->free_space_ctl->free_space != (SZ_1M + 4096)) {
- test_msg("Cache free space is not 1Mb + 4Kb\n");
+ if (cache->free_space_ctl->free_space != (SZ_1M + sectorsize)) {
+ test_msg("Cache free space is not 1Mb + %u\n", sectorsize);
return -EINVAL;
}
@@ -610,22 +614,25 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
return -EINVAL;
}
- /* All that remains is a 4Kb free space region in a bitmap. Confirm. */
+ /*
+ * All that remains is a sectorsize free space region in a bitmap.
+ * Confirm.
+ */
ret = check_num_extents_and_bitmaps(cache, 1, 1);
if (ret)
return ret;
- if (cache->free_space_ctl->free_space != 4096) {
- test_msg("Cache free space is not 4Kb\n");
+ if (cache->free_space_ctl->free_space != sectorsize) {
+ test_msg("Cache free space is not %u\n", sectorsize);
return -EINVAL;
}
offset = btrfs_find_space_for_alloc(cache,
- 0, 4096, 0,
+ 0, sectorsize, 0,
&max_extent_size);
if (offset != (SZ_128M + SZ_16M)) {
- test_msg("Failed to allocate 4Kb from space cache, returned offset is: %llu\n",
- offset);
+ test_msg("Failed to allocate %u, returned offset : %llu\n",
+ sectorsize, offset);
return -EINVAL;
}
@@ -732,7 +739,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
* The goal is to test that the bitmap entry space stealing doesn't
* steal this space region.
*/
- ret = btrfs_add_free_space(cache, SZ_32M, 8192);
+ ret = btrfs_add_free_space(cache, SZ_32M, 2 * sectorsize);
if (ret) {
test_msg("Error adding free space: %d\n", ret);
return ret;
@@ -756,7 +763,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
/*
* Confirm that our extent entry didn't stole all free space from the
- * bitmap, because of the small 8Kb free space region.
+ * bitmap, because of the small 2 * sectorsize free space region.
*/
ret = check_num_extents_and_bitmaps(cache, 2, 1);
if (ret)
@@ -782,8 +789,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
return -ENOENT;
}
- if (cache->free_space_ctl->free_space != (SZ_1M + 8192)) {
- test_msg("Cache free space is not 1Mb + 8Kb\n");
+ if (cache->free_space_ctl->free_space != (SZ_1M + 2 * sectorsize)) {
+ test_msg("Cache free space is not 1Mb + %u\n", 2 * sectorsize);
return -EINVAL;
}
@@ -795,21 +802,25 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
return -EINVAL;
}
- /* All that remains is a 8Kb free space region in a bitmap. Confirm. */
+ /*
+ * All that remains is 2 * sectorsize free space region
+ * in a bitmap. Confirm.
+ */
ret = check_num_extents_and_bitmaps(cache, 1, 1);
if (ret)
return ret;
- if (cache->free_space_ctl->free_space != 8192) {
- test_msg("Cache free space is not 8Kb\n");
+ if (cache->free_space_ctl->free_space != 2 * sectorsize) {
+ test_msg("Cache free space is not %u\n", 2 * sectorsize);
return -EINVAL;
}
offset = btrfs_find_space_for_alloc(cache,
- 0, 8192, 0,
+ 0, 2 * sectorsize, 0,
&max_extent_size);
if (offset != SZ_32M) {
- test_msg("Failed to allocate 8Kb from space cache, returned offset is: %llu\n",
+ test_msg("Failed to allocate %u, offset: %llu\n",
+ 2 * sectorsize,
offset);
return -EINVAL;
}
@@ -824,7 +835,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
return 0;
}
-int btrfs_test_free_space_cache(void)
+int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
{
struct btrfs_block_group_cache *cache;
struct btrfs_root *root = NULL;
@@ -832,13 +843,19 @@ int btrfs_test_free_space_cache(void)
test_msg("Running btrfs free space cache tests\n");
- cache = btrfs_alloc_dummy_block_group(1024 * 1024 * 1024);
+ /*
+ * For ppc64 (with 64k page size), bytes per bitmap might be
+ * larger than 1G. To make bitmap test available in ppc64,
+ * alloc dummy block group whose size cross bitmaps.
+ */
+ cache = btrfs_alloc_dummy_block_group(BITS_PER_BITMAP * sectorsize
+ + PAGE_SIZE, sectorsize);
if (!cache) {
test_msg("Couldn't run the tests\n");
return 0;
}
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
@@ -854,14 +871,14 @@ int btrfs_test_free_space_cache(void)
ret = test_extents(cache);
if (ret)
goto out;
- ret = test_bitmaps(cache);
+ ret = test_bitmaps(cache, sectorsize);
if (ret)
goto out;
- ret = test_bitmaps_and_extents(cache);
+ ret = test_bitmaps_and_extents(cache, sectorsize);
if (ret)
goto out;
- ret = test_steal_space_from_bitmap_to_extent(cache);
+ ret = test_steal_space_from_bitmap_to_extent(cache, sectorsize);
out:
btrfs_free_dummy_block_group(cache);
btrfs_free_dummy_root(root);
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index 7cea4462acd5..aac507085ab0 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -16,6 +16,7 @@
* Boston, MA 021110-1307, USA.
*/
+#include <linux/types.h>
#include "btrfs-tests.h"
#include "../ctree.h"
#include "../disk-io.h"
@@ -30,7 +31,7 @@ struct free_space_extent {
* The test cases align their operations to this in order to hit some of the
* edge cases in the bitmap code.
*/
-#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * 4096)
+#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE)
static int __check_free_space_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
@@ -439,7 +440,8 @@ typedef int (*test_func_t)(struct btrfs_trans_handle *,
struct btrfs_block_group_cache *,
struct btrfs_path *);
-static int run_test(test_func_t test_func, int bitmaps)
+static int run_test(test_func_t test_func, int bitmaps,
+ u32 sectorsize, u32 nodesize)
{
struct btrfs_root *root = NULL;
struct btrfs_block_group_cache *cache = NULL;
@@ -447,7 +449,7 @@ static int run_test(test_func_t test_func, int bitmaps)
struct btrfs_path *path = NULL;
int ret;
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
test_msg("Couldn't allocate dummy root\n");
ret = PTR_ERR(root);
@@ -466,7 +468,8 @@ static int run_test(test_func_t test_func, int bitmaps)
root->fs_info->free_space_root = root;
root->fs_info->tree_root = root;
- root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+ root->node = alloc_test_extent_buffer(root->fs_info,
+ nodesize, nodesize);
if (!root->node) {
test_msg("Couldn't allocate dummy buffer\n");
ret = -ENOMEM;
@@ -474,9 +477,9 @@ static int run_test(test_func_t test_func, int bitmaps)
}
btrfs_set_header_level(root->node, 0);
btrfs_set_header_nritems(root->node, 0);
- root->alloc_bytenr += 8192;
+ root->alloc_bytenr += 2 * nodesize;
- cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE);
+ cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE, sectorsize);
if (!cache) {
test_msg("Couldn't allocate dummy block group cache\n");
ret = -ENOMEM;
@@ -534,17 +537,18 @@ out:
return ret;
}
-static int run_test_both_formats(test_func_t test_func)
+static int run_test_both_formats(test_func_t test_func,
+ u32 sectorsize, u32 nodesize)
{
int ret;
- ret = run_test(test_func, 0);
+ ret = run_test(test_func, 0, sectorsize, nodesize);
if (ret)
return ret;
- return run_test(test_func, 1);
+ return run_test(test_func, 1, sectorsize, nodesize);
}
-int btrfs_test_free_space_tree(void)
+int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
{
test_func_t tests[] = {
test_empty_block_group,
@@ -561,9 +565,11 @@ int btrfs_test_free_space_tree(void)
test_msg("Running free space tree tests\n");
for (i = 0; i < ARRAY_SIZE(tests); i++) {
- int ret = run_test_both_formats(tests[i]);
+ int ret = run_test_both_formats(tests[i], sectorsize,
+ nodesize);
if (ret) {
- test_msg("%pf failed\n", tests[i]);
+ test_msg("%pf : sectorsize %u failed\n",
+ tests[i], sectorsize);
return ret;
}
}
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 863a6a3af1f8..29648c0a39f1 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -16,6 +16,7 @@
* Boston, MA 021110-1307, USA.
*/
+#include <linux/types.h>
#include "btrfs-tests.h"
#include "../ctree.h"
#include "../btrfs_inode.h"
@@ -86,19 +87,19 @@ static void insert_inode_item_key(struct btrfs_root *root)
* diagram of how the extents will look though this may not be possible we still
* want to make sure everything acts normally (the last number is not inclusive)
*
- * [0 - 5][5 - 6][6 - 10][10 - 4096][ 4096 - 8192 ][8192 - 12288]
- * [hole ][inline][ hole ][ regular ][regular1 split][ hole ]
+ * [0 - 5][5 - 6][ 6 - 4096 ][ 4096 - 4100][4100 - 8195][8195 - 12291]
+ * [hole ][inline][hole but no extent][ hole ][ regular ][regular1 split]
*
- * [ 12288 - 20480][20480 - 24576][ 24576 - 28672 ][28672 - 36864][36864 - 45056]
- * [regular1 split][ prealloc1 ][prealloc1 written][ prealloc1 ][ compressed ]
+ * [12291 - 16387][16387 - 24579][24579 - 28675][ 28675 - 32771][32771 - 36867 ]
+ * [ hole ][regular1 split][ prealloc ][ prealloc1 ][prealloc1 written]
*
- * [45056 - 49152][49152-53248][53248-61440][61440-65536][ 65536+81920 ]
- * [ compressed1 ][ regular ][compressed1][ regular ][ hole but no extent]
+ * [36867 - 45059][45059 - 53251][53251 - 57347][57347 - 61443][61443- 69635]
+ * [ prealloc1 ][ compressed ][ compressed1 ][ regular ][ compressed1]
*
- * [81920-86016]
- * [ regular ]
+ * [69635-73731][ 73731 - 86019 ][86019-90115]
+ * [ regular ][ hole but no extent][ regular ]
*/
-static void setup_file_extents(struct btrfs_root *root)
+static void setup_file_extents(struct btrfs_root *root, u32 sectorsize)
{
int slot = 0;
u64 disk_bytenr = SZ_1M;
@@ -119,7 +120,7 @@ static void setup_file_extents(struct btrfs_root *root)
insert_extent(root, offset, 1, 1, 0, 0, 0, BTRFS_FILE_EXTENT_INLINE, 0,
slot);
slot++;
- offset = 4096;
+ offset = sectorsize;
/* Now another hole */
insert_extent(root, offset, 4, 4, 0, 0, 0, BTRFS_FILE_EXTENT_REG, 0,
@@ -128,99 +129,106 @@ static void setup_file_extents(struct btrfs_root *root)
offset += 4;
/* Now for a regular extent */
- insert_extent(root, offset, 4095, 4095, 0, disk_bytenr, 4096,
- BTRFS_FILE_EXTENT_REG, 0, slot);
+ insert_extent(root, offset, sectorsize - 1, sectorsize - 1, 0,
+ disk_bytenr, sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
slot++;
- disk_bytenr += 4096;
- offset += 4095;
+ disk_bytenr += sectorsize;
+ offset += sectorsize - 1;
/*
* Now for 3 extents that were split from a hole punch so we test
* offsets properly.
*/
- insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 16384,
- BTRFS_FILE_EXTENT_REG, 0, slot);
+ insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+ 4 * sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
slot++;
- offset += 4096;
- insert_extent(root, offset, 4096, 4096, 0, 0, 0, BTRFS_FILE_EXTENT_REG,
- 0, slot);
+ offset += sectorsize;
+ insert_extent(root, offset, sectorsize, sectorsize, 0, 0, 0,
+ BTRFS_FILE_EXTENT_REG, 0, slot);
slot++;
- offset += 4096;
- insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 16384,
+ offset += sectorsize;
+ insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+ 2 * sectorsize, disk_bytenr, 4 * sectorsize,
BTRFS_FILE_EXTENT_REG, 0, slot);
slot++;
- offset += 8192;
- disk_bytenr += 16384;
+ offset += 2 * sectorsize;
+ disk_bytenr += 4 * sectorsize;
/* Now for a unwritten prealloc extent */
- insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
- BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
+ insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+ sectorsize, BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
slot++;
- offset += 4096;
+ offset += sectorsize;
/*
* We want to jack up disk_bytenr a little more so the em stuff doesn't
* merge our records.
*/
- disk_bytenr += 8192;
+ disk_bytenr += 2 * sectorsize;
/*
* Now for a partially written prealloc extent, basically the same as
* the hole punch example above. Ram_bytes never changes when you mark
* extents written btw.
*/
- insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 16384,
- BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
+ insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+ 4 * sectorsize, BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
slot++;
- offset += 4096;
- insert_extent(root, offset, 4096, 16384, 4096, disk_bytenr, 16384,
- BTRFS_FILE_EXTENT_REG, 0, slot);
+ offset += sectorsize;
+ insert_extent(root, offset, sectorsize, 4 * sectorsize, sectorsize,
+ disk_bytenr, 4 * sectorsize, BTRFS_FILE_EXTENT_REG, 0,
+ slot);
slot++;
- offset += 4096;
- insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 16384,
+ offset += sectorsize;
+ insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+ 2 * sectorsize, disk_bytenr, 4 * sectorsize,
BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
slot++;
- offset += 8192;
- disk_bytenr += 16384;
+ offset += 2 * sectorsize;
+ disk_bytenr += 4 * sectorsize;
/* Now a normal compressed extent */
- insert_extent(root, offset, 8192, 8192, 0, disk_bytenr, 4096,
- BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
+ insert_extent(root, offset, 2 * sectorsize, 2 * sectorsize, 0,
+ disk_bytenr, sectorsize, BTRFS_FILE_EXTENT_REG,
+ BTRFS_COMPRESS_ZLIB, slot);
slot++;
- offset += 8192;
+ offset += 2 * sectorsize;
/* No merges */
- disk_bytenr += 8192;
+ disk_bytenr += 2 * sectorsize;
/* Now a split compressed extent */
- insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 4096,
- BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
+ insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+ sectorsize, BTRFS_FILE_EXTENT_REG,
+ BTRFS_COMPRESS_ZLIB, slot);
slot++;
- offset += 4096;
- insert_extent(root, offset, 4096, 4096, 0, disk_bytenr + 4096, 4096,
+ offset += sectorsize;
+ insert_extent(root, offset, sectorsize, sectorsize, 0,
+ disk_bytenr + sectorsize, sectorsize,
BTRFS_FILE_EXTENT_REG, 0, slot);
slot++;
- offset += 4096;
- insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 4096,
+ offset += sectorsize;
+ insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+ 2 * sectorsize, disk_bytenr, sectorsize,
BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
slot++;
- offset += 8192;
- disk_bytenr += 8192;
+ offset += 2 * sectorsize;
+ disk_bytenr += 2 * sectorsize;
/* Now extents that have a hole but no hole extent */
- insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
- BTRFS_FILE_EXTENT_REG, 0, slot);
+ insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+ sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
slot++;
- offset += 16384;
- disk_bytenr += 4096;
- insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
- BTRFS_FILE_EXTENT_REG, 0, slot);
+ offset += 4 * sectorsize;
+ disk_bytenr += sectorsize;
+ insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+ sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
}
static unsigned long prealloc_only = 0;
static unsigned long compressed_only = 0;
static unsigned long vacancy_only = 0;
-static noinline int test_btrfs_get_extent(void)
+static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
{
struct inode *inode = NULL;
struct btrfs_root *root = NULL;
@@ -240,7 +248,7 @@ static noinline int test_btrfs_get_extent(void)
BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
BTRFS_I(inode)->location.offset = 0;
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
test_msg("Couldn't allocate root\n");
goto out;
@@ -256,7 +264,7 @@ static noinline int test_btrfs_get_extent(void)
goto out;
}
- root->node = alloc_dummy_extent_buffer(NULL, 4096);
+ root->node = alloc_dummy_extent_buffer(NULL, nodesize, nodesize);
if (!root->node) {
test_msg("Couldn't allocate dummy buffer\n");
goto out;
@@ -264,7 +272,7 @@ static noinline int test_btrfs_get_extent(void)
/*
* We will just free a dummy node if it's ref count is 2 so we need an
- * extra ref so our searches don't accidently release our page.
+ * extra ref so our searches don't accidentally release our page.
*/
extent_buffer_get(root->node);
btrfs_set_header_nritems(root->node, 0);
@@ -273,7 +281,7 @@ static noinline int test_btrfs_get_extent(void)
/* First with no extents */
BTRFS_I(inode)->root = root;
- em = btrfs_get_extent(inode, NULL, 0, 0, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, 0, sectorsize, 0);
if (IS_ERR(em)) {
em = NULL;
test_msg("Got an error when we shouldn't have\n");
@@ -295,7 +303,7 @@ static noinline int test_btrfs_get_extent(void)
* setup_file_extents, so if you change anything there you need to
* update the comment and update the expected values below.
*/
- setup_file_extents(root);
+ setup_file_extents(root, sectorsize);
em = btrfs_get_extent(inode, NULL, 0, 0, (u64)-1, 0);
if (IS_ERR(em)) {
@@ -318,7 +326,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -327,7 +335,8 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected an inline, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4091) {
+
+ if (em->start != offset || em->len != (sectorsize - 5)) {
test_msg("Unexpected extent wanted start %llu len 1, got start "
"%llu len %llu\n", offset, em->start, em->len);
goto out;
@@ -344,7 +353,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -366,7 +375,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* Regular extent */
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -375,7 +384,7 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4095) {
+ if (em->start != offset || em->len != sectorsize - 1) {
test_msg("Unexpected extent wanted start %llu len 4095, got "
"start %llu len %llu\n", offset, em->start, em->len);
goto out;
@@ -393,7 +402,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* The next 3 are split extents */
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -402,9 +411,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -421,7 +431,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -430,9 +440,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a hole, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -442,7 +453,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -451,9 +462,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 8192) {
- test_msg("Unexpected extent wanted start %llu len 8192, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != 2 * sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -475,7 +487,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* Prealloc extent */
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -484,9 +496,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != prealloc_only) {
@@ -503,7 +516,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* The next 3 are a half written prealloc extent */
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -512,9 +525,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != prealloc_only) {
@@ -532,7 +546,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -541,9 +555,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -564,7 +579,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -573,9 +588,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 8192) {
- test_msg("Unexpected extent wanted start %llu len 8192, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != 2 * sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != prealloc_only) {
@@ -598,7 +614,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* Now for the compressed extent */
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -607,9 +623,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 8192) {
- test_msg("Unexpected extent wanted start %llu len 8192, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != 2 * sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u,"
+ "got start %llu len %llu\n",
+ offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != compressed_only) {
@@ -631,7 +648,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* Split compressed extent */
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -640,9 +657,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u,"
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != compressed_only) {
@@ -665,7 +683,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -674,9 +692,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -691,7 +710,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -701,9 +720,10 @@ static noinline int test_btrfs_get_extent(void)
disk_bytenr, em->block_start);
goto out;
}
- if (em->start != offset || em->len != 8192) {
- test_msg("Unexpected extent wanted start %llu len 8192, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != 2 * sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != compressed_only) {
@@ -725,7 +745,7 @@ static noinline int test_btrfs_get_extent(void)
free_extent_map(em);
/* A hole between regular extents but no hole extent */
- em = btrfs_get_extent(inode, NULL, 0, offset + 6, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset + 6, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -734,9 +754,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -765,9 +786,10 @@ static noinline int test_btrfs_get_extent(void)
* length of the actual hole, if this changes we'll have to change this
* test.
*/
- if (em->start != offset || em->len != 12288) {
- test_msg("Unexpected extent wanted start %llu len 12288, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != 3 * sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u, "
+ "got start %llu len %llu\n",
+ offset, 3 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != vacancy_only) {
@@ -783,7 +805,7 @@ static noinline int test_btrfs_get_extent(void)
offset = em->start + em->len;
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+ em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -792,9 +814,10 @@ static noinline int test_btrfs_get_extent(void)
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != offset || em->len != 4096) {
- test_msg("Unexpected extent wanted start %llu len 4096, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ if (em->start != offset || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %llu len %u,"
+ "got start %llu len %llu\n",
+ offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -815,7 +838,7 @@ out:
return ret;
}
-static int test_hole_first(void)
+static int test_hole_first(u32 sectorsize, u32 nodesize)
{
struct inode *inode = NULL;
struct btrfs_root *root = NULL;
@@ -832,7 +855,7 @@ static int test_hole_first(void)
BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
BTRFS_I(inode)->location.offset = 0;
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
test_msg("Couldn't allocate root\n");
goto out;
@@ -844,7 +867,7 @@ static int test_hole_first(void)
goto out;
}
- root->node = alloc_dummy_extent_buffer(NULL, 4096);
+ root->node = alloc_dummy_extent_buffer(NULL, nodesize, nodesize);
if (!root->node) {
test_msg("Couldn't allocate dummy buffer\n");
goto out;
@@ -861,9 +884,9 @@ static int test_hole_first(void)
* btrfs_get_extent.
*/
insert_inode_item_key(root);
- insert_extent(root, 4096, 4096, 4096, 0, 4096, 4096,
- BTRFS_FILE_EXTENT_REG, 0, 1);
- em = btrfs_get_extent(inode, NULL, 0, 0, 8192, 0);
+ insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
+ sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
+ em = btrfs_get_extent(inode, NULL, 0, 0, 2 * sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
@@ -872,9 +895,10 @@ static int test_hole_first(void)
test_msg("Expected a hole, got %llu\n", em->block_start);
goto out;
}
- if (em->start != 0 || em->len != 4096) {
- test_msg("Unexpected extent wanted start 0 len 4096, got start "
- "%llu len %llu\n", em->start, em->len);
+ if (em->start != 0 || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start 0 len %u, "
+ "got start %llu len %llu\n",
+ sectorsize, em->start, em->len);
goto out;
}
if (em->flags != vacancy_only) {
@@ -884,18 +908,19 @@ static int test_hole_first(void)
}
free_extent_map(em);
- em = btrfs_get_extent(inode, NULL, 0, 4096, 8192, 0);
+ em = btrfs_get_extent(inode, NULL, 0, sectorsize, 2 * sectorsize, 0);
if (IS_ERR(em)) {
test_msg("Got an error when we shouldn't have\n");
goto out;
}
- if (em->block_start != 4096) {
+ if (em->block_start != sectorsize) {
test_msg("Expected a real extent, got %llu\n", em->block_start);
goto out;
}
- if (em->start != 4096 || em->len != 4096) {
- test_msg("Unexpected extent wanted start 4096 len 4096, got "
- "start %llu len %llu\n", em->start, em->len);
+ if (em->start != sectorsize || em->len != sectorsize) {
+ test_msg("Unexpected extent wanted start %u len %u, "
+ "got start %llu len %llu\n",
+ sectorsize, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
@@ -912,7 +937,7 @@ out:
return ret;
}
-static int test_extent_accounting(void)
+static int test_extent_accounting(u32 sectorsize, u32 nodesize)
{
struct inode *inode = NULL;
struct btrfs_root *root = NULL;
@@ -924,7 +949,7 @@ static int test_extent_accounting(void)
return ret;
}
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
test_msg("Couldn't allocate root\n");
goto out;
@@ -954,10 +979,11 @@ static int test_extent_accounting(void)
goto out;
}
- /* [BTRFS_MAX_EXTENT_SIZE][4k] */
+ /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
BTRFS_I(inode)->outstanding_extents++;
ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
- BTRFS_MAX_EXTENT_SIZE + 4095, NULL);
+ BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
+ NULL);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -969,10 +995,10 @@ static int test_extent_accounting(void)
goto out;
}
- /* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */
+ /* [BTRFS_MAX_EXTENT_SIZE/2][sectorsize HOLE][the rest] */
ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
BTRFS_MAX_EXTENT_SIZE >> 1,
- (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+ (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1,
EXTENT_DELALLOC | EXTENT_DIRTY |
EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
NULL, GFP_KERNEL);
@@ -987,10 +1013,11 @@ static int test_extent_accounting(void)
goto out;
}
- /* [BTRFS_MAX_EXTENT_SIZE][4K] */
+ /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
BTRFS_I(inode)->outstanding_extents++;
ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
- (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+ (BTRFS_MAX_EXTENT_SIZE >> 1)
+ + sectorsize - 1,
NULL);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
@@ -1004,16 +1031,17 @@ static int test_extent_accounting(void)
}
/*
- * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K]
+ * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize HOLE][BTRFS_MAX_EXTENT_SIZE+sectorsize]
*
* I'm artificially adding 2 to outstanding_extents because in the
* buffered IO case we'd add things up as we go, but I don't feel like
* doing that here, this isn't the interesting case we want to test.
*/
BTRFS_I(inode)->outstanding_extents += 2;
- ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192,
- (BTRFS_MAX_EXTENT_SIZE << 1) + 12287,
- NULL);
+ ret = btrfs_set_extent_delalloc(inode,
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize,
+ (BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
+ NULL);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1025,10 +1053,13 @@ static int test_extent_accounting(void)
goto out;
}
- /* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */
+ /*
+ * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize][BTRFS_MAX_EXTENT_SIZE+sectorsize]
+ */
BTRFS_I(inode)->outstanding_extents++;
- ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
- BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+ ret = btrfs_set_extent_delalloc(inode,
+ BTRFS_MAX_EXTENT_SIZE + sectorsize,
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1042,8 +1073,8 @@ static int test_extent_accounting(void)
/* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */
ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
- BTRFS_MAX_EXTENT_SIZE+4096,
- BTRFS_MAX_EXTENT_SIZE+8191,
+ BTRFS_MAX_EXTENT_SIZE + sectorsize,
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
NULL, GFP_KERNEL);
@@ -1063,8 +1094,9 @@ static int test_extent_accounting(void)
* might fail and I'd rather satisfy my paranoia at this point.
*/
BTRFS_I(inode)->outstanding_extents++;
- ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
- BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+ ret = btrfs_set_extent_delalloc(inode,
+ BTRFS_MAX_EXTENT_SIZE + sectorsize,
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1103,7 +1135,7 @@ out:
return ret;
}
-int btrfs_test_inodes(void)
+int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
{
int ret;
@@ -1112,13 +1144,13 @@ int btrfs_test_inodes(void)
set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
test_msg("Running btrfs_get_extent tests\n");
- ret = test_btrfs_get_extent();
+ ret = test_btrfs_get_extent(sectorsize, nodesize);
if (ret)
return ret;
test_msg("Running hole first btrfs_get_extent test\n");
- ret = test_hole_first();
+ ret = test_hole_first(sectorsize, nodesize);
if (ret)
return ret;
test_msg("Running outstanding_extents tests\n");
- return test_extent_accounting();
+ return test_extent_accounting(sectorsize, nodesize);
}
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 8ea5d34bc5a2..57a12c0d680b 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -16,6 +16,7 @@
* Boston, MA 021110-1307, USA.
*/
+#include <linux/types.h>
#include "btrfs-tests.h"
#include "../ctree.h"
#include "../transaction.h"
@@ -216,7 +217,8 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
return ret;
}
-static int test_no_shared_qgroup(struct btrfs_root *root)
+static int test_no_shared_qgroup(struct btrfs_root *root,
+ u32 sectorsize, u32 nodesize)
{
struct btrfs_trans_handle trans;
struct btrfs_fs_info *fs_info = root->fs_info;
@@ -227,29 +229,30 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
btrfs_init_dummy_trans(&trans);
test_msg("Qgroup basic add\n");
- ret = btrfs_create_qgroup(NULL, fs_info, 5);
+ ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
if (ret) {
test_msg("Couldn't create a qgroup %d\n", ret);
return ret;
}
/*
- * Since the test trans doesn't havee the complicated delayed refs,
+ * Since the test trans doesn't have the complicated delayed refs,
* we can only call btrfs_qgroup_account_extent() directly to test
* quota.
*/
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
if (ret) {
ulist_free(old_roots);
test_msg("Couldn't find old roots: %d\n", ret);
return ret;
}
- ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+ ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
+ BTRFS_FS_TREE_OBJECTID);
if (ret)
return ret;
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -257,32 +260,33 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
return ret;
}
- ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
- old_roots, new_roots);
+ ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+ nodesize, old_roots, new_roots);
if (ret) {
test_msg("Couldn't account space for a qgroup %d\n", ret);
return ret;
}
- if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+ nodesize, nodesize)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
old_roots = NULL;
new_roots = NULL;
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
if (ret) {
ulist_free(old_roots);
test_msg("Couldn't find old roots: %d\n", ret);
return ret;
}
- ret = remove_extent_item(root, 4096, 4096);
+ ret = remove_extent_item(root, nodesize, nodesize);
if (ret)
return -EINVAL;
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -290,14 +294,14 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
return ret;
}
- ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
- old_roots, new_roots);
+ ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+ nodesize, old_roots, new_roots);
if (ret) {
test_msg("Couldn't account space for a qgroup %d\n", ret);
return -EINVAL;
}
- if (btrfs_verify_qgroup_counts(fs_info, 5, 0, 0)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, 0, 0)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
@@ -310,7 +314,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
* right, also remove one of the roots and make sure the exclusive count is
* adjusted properly.
*/
-static int test_multiple_refs(struct btrfs_root *root)
+static int test_multiple_refs(struct btrfs_root *root,
+ u32 sectorsize, u32 nodesize)
{
struct btrfs_trans_handle trans;
struct btrfs_fs_info *fs_info = root->fs_info;
@@ -322,25 +327,29 @@ static int test_multiple_refs(struct btrfs_root *root)
test_msg("Qgroup multiple refs test\n");
- /* We have 5 created already from the previous test */
- ret = btrfs_create_qgroup(NULL, fs_info, 256);
+ /*
+ * We have BTRFS_FS_TREE_OBJECTID created already from the
+ * previous test.
+ */
+ ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
if (ret) {
test_msg("Couldn't create a qgroup %d\n", ret);
return ret;
}
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
if (ret) {
ulist_free(old_roots);
test_msg("Couldn't find old roots: %d\n", ret);
return ret;
}
- ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+ ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
+ BTRFS_FS_TREE_OBJECTID);
if (ret)
return ret;
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -348,30 +357,32 @@ static int test_multiple_refs(struct btrfs_root *root)
return ret;
}
- ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
- old_roots, new_roots);
+ ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+ nodesize, old_roots, new_roots);
if (ret) {
test_msg("Couldn't account space for a qgroup %d\n", ret);
return ret;
}
- if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+ nodesize, nodesize)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
if (ret) {
ulist_free(old_roots);
test_msg("Couldn't find old roots: %d\n", ret);
return ret;
}
- ret = add_tree_ref(root, 4096, 4096, 0, 256);
+ ret = add_tree_ref(root, nodesize, nodesize, 0,
+ BTRFS_FIRST_FREE_OBJECTID);
if (ret)
return ret;
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -379,35 +390,38 @@ static int test_multiple_refs(struct btrfs_root *root)
return ret;
}
- ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
- old_roots, new_roots);
+ ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+ nodesize, old_roots, new_roots);
if (ret) {
test_msg("Couldn't account space for a qgroup %d\n", ret);
return ret;
}
- if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 0)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+ nodesize, 0)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
- if (btrfs_verify_qgroup_counts(fs_info, 256, 4096, 0)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
+ nodesize, 0)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
if (ret) {
ulist_free(old_roots);
test_msg("Couldn't find old roots: %d\n", ret);
return ret;
}
- ret = remove_extent_ref(root, 4096, 4096, 0, 256);
+ ret = remove_extent_ref(root, nodesize, nodesize, 0,
+ BTRFS_FIRST_FREE_OBJECTID);
if (ret)
return ret;
- ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -415,19 +429,21 @@ static int test_multiple_refs(struct btrfs_root *root)
return ret;
}
- ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
- old_roots, new_roots);
+ ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+ nodesize, old_roots, new_roots);
if (ret) {
test_msg("Couldn't account space for a qgroup %d\n", ret);
return ret;
}
- if (btrfs_verify_qgroup_counts(fs_info, 256, 0, 0)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
+ 0, 0)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
- if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+ if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+ nodesize, nodesize)) {
test_msg("Qgroup counts didn't match expected values\n");
return -EINVAL;
}
@@ -435,13 +451,13 @@ static int test_multiple_refs(struct btrfs_root *root)
return 0;
}
-int btrfs_test_qgroups(void)
+int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
{
struct btrfs_root *root;
struct btrfs_root *tmp_root;
int ret = 0;
- root = btrfs_alloc_dummy_root();
+ root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(root)) {
test_msg("Couldn't allocate root\n");
return PTR_ERR(root);
@@ -468,7 +484,8 @@ int btrfs_test_qgroups(void)
* Can't use bytenr 0, some things freak out
* *cough*backref walking code*cough*
*/
- root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+ root->node = alloc_test_extent_buffer(root->fs_info, nodesize,
+ nodesize);
if (!root->node) {
test_msg("Couldn't allocate dummy buffer\n");
ret = -ENOMEM;
@@ -476,16 +493,16 @@ int btrfs_test_qgroups(void)
}
btrfs_set_header_level(root->node, 0);
btrfs_set_header_nritems(root->node, 0);
- root->alloc_bytenr += 8192;
+ root->alloc_bytenr += 2 * nodesize;
- tmp_root = btrfs_alloc_dummy_root();
+ tmp_root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(tmp_root)) {
test_msg("Couldn't allocate a fs root\n");
ret = PTR_ERR(tmp_root);
goto out;
}
- tmp_root->root_key.objectid = 5;
+ tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID;
root->fs_info->fs_root = tmp_root;
ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
if (ret) {
@@ -493,14 +510,14 @@ int btrfs_test_qgroups(void)
goto out;
}
- tmp_root = btrfs_alloc_dummy_root();
+ tmp_root = btrfs_alloc_dummy_root(sectorsize, nodesize);
if (IS_ERR(tmp_root)) {
test_msg("Couldn't allocate a fs root\n");
ret = PTR_ERR(tmp_root);
goto out;
}
- tmp_root->root_key.objectid = 256;
+ tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID;
ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
if (ret) {
test_msg("Couldn't insert fs root %d\n", ret);
@@ -508,10 +525,10 @@ int btrfs_test_qgroups(void)
}
test_msg("Running qgroup tests\n");
- ret = test_no_shared_qgroup(root);
+ ret = test_no_shared_qgroup(root, sectorsize, nodesize);
if (ret)
goto out;
- ret = test_multiple_refs(root);
+ ret = test_multiple_refs(root, sectorsize, nodesize);
out:
btrfs_free_dummy_root(root);
return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5b0b758a3f79..948aa186b353 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -818,6 +818,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
{
struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *info = root->fs_info;
+ u64 transid = trans->transid;
unsigned long cur = trans->delayed_ref_updates;
int lock = (trans->type != TRANS_JOIN_NOLOCK);
int err = 0;
@@ -905,7 +906,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
kmem_cache_free(btrfs_trans_handle_cachep, trans);
if (must_run_delayed_refs) {
- btrfs_async_run_delayed_refs(root, cur,
+ btrfs_async_run_delayed_refs(root, cur, transid,
must_run_delayed_refs == 1);
}
return err;
@@ -944,7 +945,7 @@ int btrfs_write_marked_extents(struct btrfs_root *root,
err = convert_extent_bit(dirty_pages, start, end,
EXTENT_NEED_WAIT,
- mark, &cached_state, GFP_NOFS);
+ mark, &cached_state);
/*
* convert_extent_bit can return -ENOMEM, which is most of the
* time a temporary error. So when it happens, ignore the error
@@ -1311,11 +1312,6 @@ int btrfs_defrag_root(struct btrfs_root *root)
return ret;
}
-/* Bisesctability fixup, remove in 4.8 */
-#ifndef btrfs_std_error
-#define btrfs_std_error btrfs_handle_fs_error
-#endif
-
/*
* Do all special snapshot related qgroup dirty hack.
*
@@ -1385,7 +1381,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
switch_commit_roots(trans->transaction, fs_info);
ret = btrfs_write_and_wait_transaction(trans, src);
if (ret)
- btrfs_std_error(fs_info, ret,
+ btrfs_handle_fs_error(fs_info, ret,
"Error while writing out transaction for qgroup");
out:
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 72be51f7ca2f..c5abee4f01ad 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -110,7 +110,6 @@ struct btrfs_trans_handle {
u64 chunk_bytes_reserved;
unsigned long use_count;
unsigned long blocks_reserved;
- unsigned long blocks_used;
unsigned long delayed_ref_updates;
struct btrfs_transaction *transaction;
struct btrfs_block_rsv *block_rsv;
@@ -121,6 +120,7 @@ struct btrfs_trans_handle {
bool can_flush_pending_bgs;
bool reloc_reserved;
bool sync;
+ bool dirty;
unsigned int type;
/*
* this root is only needed to validate that the root passed to
@@ -144,7 +144,7 @@ struct btrfs_pending_snapshot {
/* block reservation for the operation */
struct btrfs_block_rsv block_rsv;
u64 qgroup_reserved;
- /* extra metadata reseration for relocation */
+ /* extra metadata reservation for relocation */
int error;
bool readonly;
struct list_head list;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8aaca5c6af94..c05f69a8ec42 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2330,7 +2330,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
break;
/* for regular files, make sure corresponding
- * orhpan item exist. extents past the new EOF
+ * orphan item exist. extents past the new EOF
* will be truncated later by orphan cleanup.
*/
if (S_ISREG(mode)) {
@@ -2422,8 +2422,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
root_owner = btrfs_header_owner(parent);
next = btrfs_find_create_tree_block(root, bytenr);
- if (!next)
- return -ENOMEM;
+ if (IS_ERR(next))
+ return PTR_ERR(next);
if (*level == 1) {
ret = wc->process_func(root, next, wc, ptr_gen);
@@ -3001,7 +3001,7 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
break;
clear_extent_bits(&log->dirty_log_pages, start, end,
- EXTENT_DIRTY | EXTENT_NEW, GFP_NOFS);
+ EXTENT_DIRTY | EXTENT_NEW);
}
/*
@@ -4914,7 +4914,7 @@ out_unlock:
* the actual unlink operation, so if we do this check before a concurrent task
* sets last_unlink_trans it means we've logged a consistent version/state of
* all the inode items, otherwise we are not sure and must do a transaction
- * commit (the concurrent task migth have only updated last_unlink_trans before
+ * commit (the concurrent task might have only updated last_unlink_trans before
* we logged the inode or it might have also done the unlink).
*/
static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
@@ -4973,7 +4973,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
while (1) {
/*
* If we are logging a directory then we start with our inode,
- * not our parents inode, so we need to skipp setting the
+ * not our parent's inode, so we need to skip setting the
* logged_trans so that further down in the log code we don't
* think this inode has already been logged.
*/
@@ -5357,7 +5357,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
log_dentries = true;
/*
- * On unlink we must make sure all our current and old parent directores
+ * On unlink we must make sure all our current and old parent directory
* inodes are fully logged. This is to prevent leaving dangling
* directory index entries in directories that were our parents but are
* not anymore. Not doing this results in old parent directory being
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index 91feb2bdefee..b1434bb57e36 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -28,7 +28,7 @@
* }
* ulist_free(ulist);
*
- * This assumes the graph nodes are adressable by u64. This stems from the
+ * This assumes the graph nodes are addressable by u64. This stems from the
* usage for tree enumeration in btrfs, where the logical addresses are
* 64 bit.
*
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2b88127bba5b..589f128173b1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2190,7 +2190,7 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
}
/*
- * strore the expected generation for seed devices in device items.
+ * Store the expected generation for seed devices in device items.
*/
static int btrfs_finish_sprout(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
@@ -2761,6 +2761,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
u64 dev_extent_len = 0;
u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
int i, ret = 0;
+ struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
/* Just in case */
root = root->fs_info->chunk_root;
@@ -2787,12 +2788,19 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
check_system_chunk(trans, extent_root, map->type);
unlock_chunks(root->fs_info->chunk_root);
+ /*
+ * Take the device list mutex to prevent races with the final phase of
+ * a device replace operation that replaces the device object associated
+ * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()).
+ */
+ mutex_lock(&fs_devices->device_list_mutex);
for (i = 0; i < map->num_stripes; i++) {
struct btrfs_device *device = map->stripes[i].dev;
ret = btrfs_free_dev_extent(trans, device,
map->stripes[i].physical,
&dev_extent_len);
if (ret) {
+ mutex_unlock(&fs_devices->device_list_mutex);
btrfs_abort_transaction(trans, root, ret);
goto out;
}
@@ -2811,11 +2819,14 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
if (map->stripes[i].dev) {
ret = btrfs_update_device(trans, map->stripes[i].dev);
if (ret) {
+ mutex_unlock(&fs_devices->device_list_mutex);
btrfs_abort_transaction(trans, root, ret);
goto out;
}
}
}
+ mutex_unlock(&fs_devices->device_list_mutex);
+
ret = btrfs_free_chunk(trans, root, chunk_objectid, chunk_offset);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
@@ -3387,7 +3398,7 @@ static int should_balance_chunk(struct btrfs_root *root,
} else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) {
/*
* Same logic as the 'limit' filter; the minimum cannot be
- * determined here because we do not have the global informatoin
+ * determined here because we do not have the global information
* about the count of all chunks that satisfy the filters.
*/
if (bargs->limit_max == 0)
@@ -4230,6 +4241,7 @@ int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info)
if (IS_ERR(uuid_root)) {
ret = PTR_ERR(uuid_root);
btrfs_abort_transaction(trans, tree_root, ret);
+ btrfs_end_transaction(trans, tree_root);
return ret;
}
@@ -4682,12 +4694,12 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
if (type & BTRFS_BLOCK_GROUP_RAID5) {
raid_stripe_len = find_raid56_stripe_len(ndevs - 1,
- btrfs_super_stripesize(info->super_copy));
+ extent_root->stripesize);
data_stripes = num_stripes - 1;
}
if (type & BTRFS_BLOCK_GROUP_RAID6) {
raid_stripe_len = find_raid56_stripe_len(ndevs - 2,
- btrfs_super_stripesize(info->super_copy));
+ extent_root->stripesize);
data_stripes = num_stripes - 2;
}
@@ -5762,20 +5774,17 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
}
}
if (found) {
- if (physical_of_found + map->stripe_len <=
- dev_replace->cursor_left) {
- struct btrfs_bio_stripe *tgtdev_stripe =
- bbio->stripes + num_stripes;
+ struct btrfs_bio_stripe *tgtdev_stripe =
+ bbio->stripes + num_stripes;
- tgtdev_stripe->physical = physical_of_found;
- tgtdev_stripe->length =
- bbio->stripes[index_srcdev].length;
- tgtdev_stripe->dev = dev_replace->tgtdev;
- bbio->tgtdev_map[index_srcdev] = num_stripes;
+ tgtdev_stripe->physical = physical_of_found;
+ tgtdev_stripe->length =
+ bbio->stripes[index_srcdev].length;
+ tgtdev_stripe->dev = dev_replace->tgtdev;
+ bbio->tgtdev_map[index_srcdev] = num_stripes;
- tgtdev_indexes++;
- num_stripes++;
- }
+ tgtdev_indexes++;
+ num_stripes++;
}
}
@@ -6076,7 +6085,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
{
atomic_inc(&bbio->error);
if (atomic_dec_and_test(&bbio->stripes_pending)) {
- /* Shoud be the original bio. */
+ /* Should be the original bio. */
WARN_ON(bio != bbio->orig_bio);
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
@@ -6250,27 +6259,23 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
return dev;
}
-static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
- struct extent_buffer *leaf,
- struct btrfs_chunk *chunk)
+/* Return -EIO if any error, otherwise return 0. */
+static int btrfs_check_chunk_valid(struct btrfs_root *root,
+ struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk, u64 logical)
{
- struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
- struct map_lookup *map;
- struct extent_map *em;
- u64 logical;
u64 length;
u64 stripe_len;
- u64 devid;
- u8 uuid[BTRFS_UUID_SIZE];
- int num_stripes;
- int ret;
- int i;
+ u16 num_stripes;
+ u16 sub_stripes;
+ u64 type;
- logical = key->offset;
length = btrfs_chunk_length(leaf, chunk);
stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
- /* Validation check */
+ sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+ type = btrfs_chunk_type(leaf, chunk);
+
if (!num_stripes) {
btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
num_stripes);
@@ -6281,6 +6286,11 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
"invalid chunk logical %llu", logical);
return -EIO;
}
+ if (btrfs_chunk_sector_size(leaf, chunk) != root->sectorsize) {
+ btrfs_err(root->fs_info, "invalid chunk sectorsize %u",
+ btrfs_chunk_sector_size(leaf, chunk));
+ return -EIO;
+ }
if (!length || !IS_ALIGNED(length, root->sectorsize)) {
btrfs_err(root->fs_info,
"invalid chunk length %llu", length);
@@ -6292,13 +6302,54 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
return -EIO;
}
if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
- btrfs_chunk_type(leaf, chunk)) {
+ type) {
btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
~(BTRFS_BLOCK_GROUP_TYPE_MASK |
BTRFS_BLOCK_GROUP_PROFILE_MASK) &
btrfs_chunk_type(leaf, chunk));
return -EIO;
}
+ if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
+ (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
+ (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
+ (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) ||
+ (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) ||
+ ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
+ num_stripes != 1)) {
+ btrfs_err(root->fs_info,
+ "invalid num_stripes:sub_stripes %u:%u for profile %llu",
+ num_stripes, sub_stripes,
+ type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
+ struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk)
+{
+ struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
+ struct map_lookup *map;
+ struct extent_map *em;
+ u64 logical;
+ u64 length;
+ u64 stripe_len;
+ u64 devid;
+ u8 uuid[BTRFS_UUID_SIZE];
+ int num_stripes;
+ int ret;
+ int i;
+
+ logical = key->offset;
+ length = btrfs_chunk_length(leaf, chunk);
+ stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+ num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+
+ ret = btrfs_check_chunk_valid(root, leaf, chunk, logical);
+ if (ret)
+ return ret;
read_lock(&map_tree->map_tree.lock);
em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6546,6 +6597,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
u32 array_size;
u32 len = 0;
u32 cur_offset;
+ u64 type;
struct btrfs_key key;
ASSERT(BTRFS_SUPER_INFO_SIZE <= root->nodesize);
@@ -6555,12 +6607,12 @@ int btrfs_read_sys_array(struct btrfs_root *root)
* overallocate but we can keep it as-is, only the first page is used.
*/
sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
- if (!sb)
- return -ENOMEM;
+ if (IS_ERR(sb))
+ return PTR_ERR(sb);
set_extent_buffer_uptodate(sb);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
/*
- * The sb extent buffer is artifical and just used to read the system array.
+ * The sb extent buffer is artificial and just used to read the system array.
* set_extent_buffer_uptodate() call does not properly mark all it's
* pages up-to-date when the page is larger: extent does not cover the
* whole page and consequently check_page_uptodate does not find all
@@ -6612,6 +6664,15 @@ int btrfs_read_sys_array(struct btrfs_root *root)
break;
}
+ type = btrfs_chunk_type(sb, chunk);
+ if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
+ btrfs_err(root->fs_info,
+ "invalid chunk type %llu in sys_array at offset %u",
+ type, cur_offset);
+ ret = -EIO;
+ break;
+ }
+
len = btrfs_chunk_item_size(num_stripes);
if (cur_offset + len > array_size)
goto out_short_read;
@@ -6630,13 +6691,15 @@ int btrfs_read_sys_array(struct btrfs_root *root)
sb_array_offset += len;
cur_offset += len;
}
- free_extent_buffer(sb);
+ clear_extent_buffer_uptodate(sb);
+ free_extent_buffer_stale(sb);
return ret;
out_short_read:
printk(KERN_ERR "BTRFS: sys_array too short to read %u bytes at offset %u\n",
len, cur_offset);
- free_extent_buffer(sb);
+ clear_extent_buffer_uptodate(sb);
+ free_extent_buffer_stale(sb);
return -EIO;
}
@@ -6648,6 +6711,7 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
struct btrfs_key found_key;
int ret;
int slot;
+ u64 total_dev = 0;
root = root->fs_info->chunk_root;
@@ -6689,6 +6753,7 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
ret = read_one_dev(root, leaf, dev_item);
if (ret)
goto error;
+ total_dev++;
} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
struct btrfs_chunk *chunk;
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
@@ -6698,6 +6763,28 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
}
path->slots[0]++;
}
+
+ /*
+ * After loading chunk tree, we've got all device information,
+ * do another round of validation checks.
+ */
+ if (total_dev != root->fs_info->fs_devices->total_devices) {
+ btrfs_err(root->fs_info,
+ "super_num_devices %llu mismatch with num_devices %llu found here",
+ btrfs_super_num_devices(root->fs_info->super_copy),
+ total_dev);
+ ret = -EINVAL;
+ goto error;
+ }
+ if (btrfs_super_total_bytes(root->fs_info->super_copy) <
+ root->fs_info->fs_devices->total_rw_bytes) {
+ btrfs_err(root->fs_info,
+ "super_total_bytes %llu mismatch with fs_devices total_rw_bytes %llu",
+ btrfs_super_total_bytes(root->fs_info->super_copy),
+ root->fs_info->fs_devices->total_rw_bytes);
+ ret = -EINVAL;
+ goto error;
+ }
ret = 0;
error:
unlock_chunks(root);
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 3bfb252206c7..d1a177a3dbe8 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -380,23 +380,21 @@ static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
}
static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size,
- int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
name = xattr_full_name(handler, name);
return __btrfs_setxattr(NULL, inode, name, buffer, size, flags);
}
static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
- struct dentry *dentry,
+ struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
name = xattr_full_name(handler, name);
- return btrfs_set_prop(d_inode(dentry), name, value, size, flags);
+ return btrfs_set_prop(inode, name, value, size, flags);
}
static const struct xattr_handler btrfs_security_xattr_handler = {
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 861d611b8c05..ce5f345d70f5 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -380,7 +380,7 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache)
* check if the backing cache is updated to FS-Cache
* - called by FS-Cache when evaluates if need to invalidate the cache
*/
-static bool cachefiles_check_consistency(struct fscache_operation *op)
+static int cachefiles_check_consistency(struct fscache_operation *op)
{
struct cachefiles_object *object;
struct cachefiles_cache *cache;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 43098cd9602b..26a9d10d75e9 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -257,12 +257,12 @@ static int ceph_readpage(struct file *filp, struct page *page)
/*
* Finish an async read(ahead) op.
*/
-static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
+static void finish_read(struct ceph_osd_request *req)
{
struct inode *inode = req->r_inode;
struct ceph_osd_data *osd_data;
- int rc = req->r_result;
- int bytes = le32_to_cpu(msg->hdr.data_len);
+ int rc = req->r_result <= 0 ? req->r_result : 0;
+ int bytes = req->r_result >= 0 ? req->r_result : 0;
int num_pages;
int i;
@@ -276,8 +276,10 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
for (i = 0; i < num_pages; i++) {
struct page *page = osd_data->pages[i];
- if (rc < 0 && rc != -ENOENT)
+ if (rc < 0 && rc != -ENOENT) {
+ ceph_fscache_readpage_cancel(inode, page);
goto unlock;
+ }
if (bytes < (int)PAGE_SIZE) {
/* zero (remainder of) page */
int s = bytes < 0 ? 0 : bytes;
@@ -376,8 +378,6 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
req->r_callback = finish_read;
req->r_inode = inode;
- ceph_osdc_build_request(req, off, NULL, vino.snap, NULL);
-
dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len);
ret = ceph_osdc_start_request(osdc, req, false);
if (ret < 0)
@@ -537,8 +537,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
- ceph_readpage_to_fscache(inode, page);
-
set_page_writeback(page);
err = ceph_osdc_writepages(osdc, ceph_vino(inode),
&ci->i_layout, snapc,
@@ -546,11 +544,21 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
truncate_seq, truncate_size,
&inode->i_mtime, &page, 1);
if (err < 0) {
- dout("writepage setting page/mapping error %d %p\n", err, page);
+ struct writeback_control tmp_wbc;
+ if (!wbc)
+ wbc = &tmp_wbc;
+ if (err == -ERESTARTSYS) {
+ /* killed by SIGKILL */
+ dout("writepage interrupted page %p\n", page);
+ redirty_page_for_writepage(wbc, page);
+ end_page_writeback(page);
+ goto out;
+ }
+ dout("writepage setting page/mapping error %d %p\n",
+ err, page);
SetPageError(page);
mapping_set_error(&inode->i_data, err);
- if (wbc)
- wbc->pages_skipped++;
+ wbc->pages_skipped++;
} else {
dout("writepage cleaned page %p\n", page);
err = 0; /* vfs expects us to return 0 */
@@ -571,12 +579,16 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
BUG_ON(!inode);
ihold(inode);
err = writepage_nounlock(page, wbc);
+ if (err == -ERESTARTSYS) {
+ /* direct memory reclaimer was killed by SIGKILL. return 0
+ * to prevent caller from setting mapping/page error */
+ err = 0;
+ }
unlock_page(page);
iput(inode);
return err;
}
-
/*
* lame release_pages helper. release_pages() isn't exported to
* modules.
@@ -600,8 +612,7 @@ static void ceph_release_pages(struct page **pages, int num)
* If we get an error, set the mapping error bit, but not the individual
* page error bits.
*/
-static void writepages_finish(struct ceph_osd_request *req,
- struct ceph_msg *msg)
+static void writepages_finish(struct ceph_osd_request *req)
{
struct inode *inode = req->r_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -615,7 +626,6 @@ static void writepages_finish(struct ceph_osd_request *req,
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
bool remove_page;
-
dout("writepages_finish %p rc %d\n", inode, rc);
if (rc < 0)
mapping_set_error(mapping, rc);
@@ -650,6 +660,9 @@ static void writepages_finish(struct ceph_osd_request *req,
clear_bdi_congested(&fsc->backing_dev_info,
BLK_RW_ASYNC);
+ if (rc < 0)
+ SetPageError(page);
+
ceph_put_snap_context(page_snap_context(page));
page->private = 0;
ClearPagePrivate(page);
@@ -718,8 +731,11 @@ static int ceph_writepages_start(struct address_space *mapping,
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
- pr_warn("writepage_start %p on forced umount\n", inode);
- truncate_pagecache(inode, 0);
+ if (ci->i_wrbuffer_ref > 0) {
+ pr_warn_ratelimited(
+ "writepage_start %p %lld forced umount\n",
+ inode, ceph_ino(inode));
+ }
mapping_set_error(mapping, -EIO);
return -EIO; /* we're in a forced umount, don't write! */
}
@@ -1063,10 +1079,7 @@ new_request:
pages = NULL;
}
- vino = ceph_vino(inode);
- ceph_osdc_build_request(req, offset, snapc, vino.snap,
- &inode->i_mtime);
-
+ req->r_mtime = inode->i_mtime;
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
BUG_ON(rc);
req = NULL;
@@ -1099,8 +1112,7 @@ release_pvec_pages:
mapping->writeback_index = index;
out:
- if (req)
- ceph_osdc_put_request(req);
+ ceph_osdc_put_request(req);
ceph_put_snap_context(snapc);
dout("writepages done, rc = %d\n", rc);
return rc;
@@ -1134,6 +1146,7 @@ static int ceph_update_writeable_page(struct file *file,
struct page *page)
{
struct inode *inode = file_inode(file);
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
loff_t page_off = pos & PAGE_MASK;
int pos_in_page = pos & ~PAGE_MASK;
@@ -1142,6 +1155,12 @@ static int ceph_update_writeable_page(struct file *file,
int r;
struct ceph_snap_context *snapc, *oldest;
+ if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+ dout(" page %p forced umount\n", page);
+ unlock_page(page);
+ return -EIO;
+ }
+
retry_locked:
/* writepages currently holds page lock, but if we change that later, */
wait_on_page_writeback(page);
@@ -1165,7 +1184,7 @@ retry_locked:
snapc = ceph_get_snap_context(snapc);
unlock_page(page);
ceph_queue_writeback(inode);
- r = wait_event_interruptible(ci->i_cap_wq,
+ r = wait_event_killable(ci->i_cap_wq,
context_is_writeable_or_written(inode, snapc));
ceph_put_snap_context(snapc);
if (r == -ERESTARTSYS)
@@ -1311,6 +1330,17 @@ const struct address_space_operations ceph_aops = {
.direct_IO = ceph_direct_io,
};
+static void ceph_block_sigs(sigset_t *oldset)
+{
+ sigset_t mask;
+ siginitsetinv(&mask, sigmask(SIGKILL));
+ sigprocmask(SIG_BLOCK, &mask, oldset);
+}
+
+static void ceph_restore_sigs(sigset_t *oldset)
+{
+ sigprocmask(SIG_SETMASK, oldset, NULL);
+}
/*
* vm ops
@@ -1323,6 +1353,9 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
struct page *pinned_page = NULL;
loff_t off = vmf->pgoff << PAGE_SHIFT;
int want, got, ret;
+ sigset_t oldset;
+
+ ceph_block_sigs(&oldset);
dout("filemap_fault %p %llx.%llx %llu~%zd trying to get caps\n",
inode, ceph_vinop(inode), off, (size_t)PAGE_SIZE);
@@ -1330,17 +1363,12 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_CACHE;
- while (1) {
- got = 0;
- ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want,
- -1, &got, &pinned_page);
- if (ret == 0)
- break;
- if (ret != -ERESTARTSYS) {
- WARN_ON(1);
- return VM_FAULT_SIGBUS;
- }
- }
+
+ got = 0;
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, -1, &got, &pinned_page);
+ if (ret < 0)
+ goto out_restore;
+
dout("filemap_fault %p %llu~%zd got cap refs on %s\n",
inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got));
@@ -1357,7 +1385,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
ceph_put_cap_refs(ci, got);
if (ret != -EAGAIN)
- return ret;
+ goto out_restore;
/* read inline data */
if (off >= PAGE_SIZE) {
@@ -1371,15 +1399,18 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
~__GFP_FS));
if (!page) {
ret = VM_FAULT_OOM;
- goto out;
+ goto out_inline;
}
ret1 = __ceph_do_getattr(inode, page,
CEPH_STAT_CAP_INLINE_DATA, true);
if (ret1 < 0 || off >= i_size_read(inode)) {
unlock_page(page);
put_page(page);
- ret = VM_FAULT_SIGBUS;
- goto out;
+ if (ret1 < 0)
+ ret = ret1;
+ else
+ ret = VM_FAULT_SIGBUS;
+ goto out_inline;
}
if (ret1 < PAGE_SIZE)
zero_user_segment(page, ret1, PAGE_SIZE);
@@ -1388,10 +1419,15 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
SetPageUptodate(page);
vmf->page = page;
ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
+out_inline:
+ dout("filemap_fault %p %llu~%zd read inline data ret %d\n",
+ inode, off, (size_t)PAGE_SIZE, ret);
}
-out:
- dout("filemap_fault %p %llu~%zd read inline data ret %d\n",
- inode, off, (size_t)PAGE_SIZE, ret);
+out_restore:
+ ceph_restore_sigs(&oldset);
+ if (ret < 0)
+ ret = (ret == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+
return ret;
}
@@ -1409,10 +1445,13 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
loff_t size = i_size_read(inode);
size_t len;
int want, got, ret;
+ sigset_t oldset;
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
- return VM_FAULT_SIGBUS;
+ return VM_FAULT_OOM;
+
+ ceph_block_sigs(&oldset);
if (ci->i_inline_version != CEPH_INLINE_NONE) {
struct page *locked_page = NULL;
@@ -1423,10 +1462,8 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
ret = ceph_uninline_data(vma->vm_file, locked_page);
if (locked_page)
unlock_page(locked_page);
- if (ret < 0) {
- ret = VM_FAULT_SIGBUS;
+ if (ret < 0)
goto out_free;
- }
}
if (off + PAGE_SIZE <= size)
@@ -1440,45 +1477,36 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_BUFFER;
- while (1) {
- got = 0;
- ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, off + len,
- &got, NULL);
- if (ret == 0)
- break;
- if (ret != -ERESTARTSYS) {
- WARN_ON(1);
- ret = VM_FAULT_SIGBUS;
- goto out_free;
- }
- }
+
+ got = 0;
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, off + len,
+ &got, NULL);
+ if (ret < 0)
+ goto out_free;
+
dout("page_mkwrite %p %llu~%zd got cap refs on %s\n",
inode, off, len, ceph_cap_string(got));
/* Update time before taking page lock */
file_update_time(vma->vm_file);
- lock_page(page);
+ do {
+ lock_page(page);
- ret = VM_FAULT_NOPAGE;
- if ((off > size) ||
- (page->mapping != inode->i_mapping)) {
- unlock_page(page);
- goto out;
- }
+ if ((off > size) || (page->mapping != inode->i_mapping)) {
+ unlock_page(page);
+ ret = VM_FAULT_NOPAGE;
+ break;
+ }
+
+ ret = ceph_update_writeable_page(vma->vm_file, off, len, page);
+ if (ret >= 0) {
+ /* success. we'll keep the page locked. */
+ set_page_dirty(page);
+ ret = VM_FAULT_LOCKED;
+ }
+ } while (ret == -EAGAIN);
- ret = ceph_update_writeable_page(vma->vm_file, off, len, page);
- if (ret >= 0) {
- /* success. we'll keep the page locked. */
- set_page_dirty(page);
- ret = VM_FAULT_LOCKED;
- } else {
- if (ret == -ENOMEM)
- ret = VM_FAULT_OOM;
- else
- ret = VM_FAULT_SIGBUS;
- }
-out:
if (ret == VM_FAULT_LOCKED ||
ci->i_inline_version != CEPH_INLINE_NONE) {
int dirty;
@@ -1495,8 +1523,10 @@ out:
inode, off, len, ceph_cap_string(got), ret);
ceph_put_cap_refs(ci, got);
out_free:
+ ceph_restore_sigs(&oldset);
ceph_free_cap_flush(prealloc_cf);
-
+ if (ret < 0)
+ ret = (ret == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
return ret;
}
@@ -1614,7 +1644,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
goto out;
}
- ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
+ req->r_mtime = inode->i_mtime;
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
@@ -1657,7 +1687,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
goto out_put;
}
- ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
+ req->r_mtime = inode->i_mtime;
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
@@ -1758,9 +1788,11 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
rd_req->r_flags = CEPH_OSD_FLAG_READ;
osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);
rd_req->r_base_oloc.pool = pool;
- snprintf(rd_req->r_base_oid.name, sizeof(rd_req->r_base_oid.name),
- "%llx.00000000", ci->i_vino.ino);
- rd_req->r_base_oid.name_len = strlen(rd_req->r_base_oid.name);
+ ceph_oid_printf(&rd_req->r_base_oid, "%llx.00000000", ci->i_vino.ino);
+
+ err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS);
+ if (err)
+ goto out_unlock;
wr_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
1, false, GFP_NOFS);
@@ -1769,11 +1801,14 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
goto out_unlock;
}
- wr_req->r_flags = CEPH_OSD_FLAG_WRITE |
- CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK;
+ wr_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ACK;
osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);
- wr_req->r_base_oloc.pool = pool;
- wr_req->r_base_oid = rd_req->r_base_oid;
+ ceph_oloc_copy(&wr_req->r_base_oloc, &rd_req->r_base_oloc);
+ ceph_oid_copy(&wr_req->r_base_oid, &rd_req->r_base_oid);
+
+ err = ceph_osdc_alloc_messages(wr_req, GFP_NOFS);
+ if (err)
+ goto out_unlock;
/* one page should be large enough for STAT data */
pages = ceph_alloc_page_vector(1, GFP_KERNEL);
@@ -1784,12 +1819,9 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
0, false, true);
- ceph_osdc_build_request(rd_req, 0, NULL, CEPH_NOSNAP,
- &ci->vfs_inode.i_mtime);
err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
- ceph_osdc_build_request(wr_req, 0, NULL, CEPH_NOSNAP,
- &ci->vfs_inode.i_mtime);
+ wr_req->r_mtime = ci->vfs_inode.i_mtime;
err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
if (!err)
@@ -1823,10 +1855,8 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
out_unlock:
up_write(&mdsc->pool_perm_rwsem);
- if (rd_req)
- ceph_osdc_put_request(rd_req);
- if (wr_req)
- ceph_osdc_put_request(wr_req);
+ ceph_osdc_put_request(rd_req);
+ ceph_osdc_put_request(wr_req);
out:
if (!err)
err = have;
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index a351480dbabc..238c55b01723 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -25,6 +25,7 @@
#include "cache.h"
struct ceph_aux_inode {
+ u64 version;
struct timespec mtime;
loff_t size;
};
@@ -69,15 +70,8 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
&ceph_fscache_fsid_object_def,
fsc, true);
-
- if (fsc->fscache == NULL) {
+ if (!fsc->fscache)
pr_err("Unable to resgister fsid: %p fscache cookie", fsc);
- return 0;
- }
-
- fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
- if (fsc->revalidate_wq == NULL)
- return -ENOMEM;
return 0;
}
@@ -105,6 +99,7 @@ static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
const struct inode* inode = &ci->vfs_inode;
memset(&aux, 0, sizeof(aux));
+ aux.version = ci->i_version;
aux.mtime = inode->i_mtime;
aux.size = i_size_read(inode);
@@ -131,6 +126,7 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux(
return FSCACHE_CHECKAUX_OBSOLETE;
memset(&aux, 0, sizeof(aux));
+ aux.version = ci->i_version;
aux.mtime = inode->i_mtime;
aux.size = i_size_read(inode);
@@ -181,32 +177,26 @@ static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
.now_uncached = ceph_fscache_inode_now_uncached,
};
-void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
- struct ceph_inode_info* ci)
+void ceph_fscache_register_inode_cookie(struct inode *inode)
{
- struct inode* inode = &ci->vfs_inode;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
/* No caching for filesystem */
if (fsc->fscache == NULL)
return;
/* Only cache for regular files that are read only */
- if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
+ if (!S_ISREG(inode->i_mode))
return;
- /* Avoid multiple racing open requests */
- inode_lock(inode);
-
- if (ci->fscache)
- goto done;
-
- ci->fscache = fscache_acquire_cookie(fsc->fscache,
- &ceph_fscache_inode_object_def,
- ci, true);
- fscache_check_consistency(ci->fscache);
-done:
+ inode_lock_nested(inode, I_MUTEX_CHILD);
+ if (!ci->fscache) {
+ ci->fscache = fscache_acquire_cookie(fsc->fscache,
+ &ceph_fscache_inode_object_def,
+ ci, false);
+ }
inode_unlock(inode);
-
}
void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
@@ -222,6 +212,34 @@ void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
fscache_relinquish_cookie(cookie, 0);
}
+static bool ceph_fscache_can_enable(void *data)
+{
+ struct inode *inode = data;
+ return !inode_is_open_for_write(inode);
+}
+
+void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+
+ if (!fscache_cookie_valid(ci->fscache))
+ return;
+
+ if (inode_is_open_for_write(inode)) {
+ dout("fscache_file_set_cookie %p %p disabling cache\n",
+ inode, filp);
+ fscache_disable_cookie(ci->fscache, false);
+ fscache_uncache_all_inode_pages(ci->fscache, inode);
+ } else {
+ fscache_enable_cookie(ci->fscache, ceph_fscache_can_enable,
+ inode);
+ if (fscache_cookie_enabled(ci->fscache)) {
+ dout("fscache_file_set_cookie %p %p enabing cache\n",
+ inode, filp);
+ }
+ }
+}
+
static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
{
if (!error)
@@ -236,10 +254,9 @@ static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int
unlock_page(page);
}
-static inline int cache_valid(struct ceph_inode_info *ci)
+static inline bool cache_valid(struct ceph_inode_info *ci)
{
- return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
- (ci->i_fscache_gen == ci->i_rdcache_gen));
+ return ci->i_fscache_gen == ci->i_rdcache_gen;
}
@@ -332,69 +349,27 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
{
- if (fsc->revalidate_wq)
- destroy_workqueue(fsc->revalidate_wq);
-
fscache_relinquish_cookie(fsc->fscache, 0);
fsc->fscache = NULL;
}
-static void ceph_revalidate_work(struct work_struct *work)
-{
- int issued;
- u32 orig_gen;
- struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
- i_revalidate_work);
- struct inode *inode = &ci->vfs_inode;
-
- spin_lock(&ci->i_ceph_lock);
- issued = __ceph_caps_issued(ci, NULL);
- orig_gen = ci->i_rdcache_gen;
- spin_unlock(&ci->i_ceph_lock);
-
- if (!(issued & CEPH_CAP_FILE_CACHE)) {
- dout("revalidate_work lost cache before validation %p\n",
- inode);
- goto out;
- }
-
- if (!fscache_check_consistency(ci->fscache))
- fscache_invalidate(ci->fscache);
-
- spin_lock(&ci->i_ceph_lock);
- /* Update the new valid generation (backwards sanity check too) */
- if (orig_gen > ci->i_fscache_gen) {
- ci->i_fscache_gen = orig_gen;
- }
- spin_unlock(&ci->i_ceph_lock);
-
-out:
- iput(&ci->vfs_inode);
-}
-
-void ceph_queue_revalidate(struct inode *inode)
+/*
+ * caller should hold CEPH_CAP_FILE_{RD,CACHE}
+ */
+void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
- struct ceph_inode_info *ci = ceph_inode(inode);
-
- if (fsc->revalidate_wq == NULL || ci->fscache == NULL)
+ if (cache_valid(ci))
return;
- ihold(inode);
-
- if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
- &ci->i_revalidate_work)) {
- dout("ceph_queue_revalidate %p\n", inode);
- } else {
- dout("ceph_queue_revalidate %p failed\n)", inode);
- iput(inode);
+ /* resue i_truncate_mutex. There should be no pending
+ * truncate while the caller holds CEPH_CAP_FILE_RD */
+ mutex_lock(&ci->i_truncate_mutex);
+ if (!cache_valid(ci)) {
+ if (fscache_check_consistency(ci->fscache))
+ fscache_invalidate(ci->fscache);
+ spin_lock(&ci->i_ceph_lock);
+ ci->i_fscache_gen = ci->i_rdcache_gen;
+ spin_unlock(&ci->i_ceph_lock);
}
-}
-
-void ceph_fscache_inode_init(struct ceph_inode_info *ci)
-{
- ci->fscache = NULL;
- /* The first load is verifed cookie open time */
- ci->i_fscache_gen = 1;
- INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
+ mutex_unlock(&ci->i_truncate_mutex);
}
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 5ac591bd012b..7e72c7594f0c 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -34,10 +34,10 @@ void ceph_fscache_unregister(void);
int ceph_fscache_register_fs(struct ceph_fs_client* fsc);
void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
-void ceph_fscache_inode_init(struct ceph_inode_info *ci);
-void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
- struct ceph_inode_info* ci);
+void ceph_fscache_register_inode_cookie(struct inode *inode);
void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci);
+void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp);
+void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci);
int ceph_readpage_from_fscache(struct inode *inode, struct page *page);
int ceph_readpages_from_fscache(struct inode *inode,
@@ -46,12 +46,11 @@ int ceph_readpages_from_fscache(struct inode *inode,
unsigned *nr_pages);
void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
-void ceph_queue_revalidate(struct inode *inode);
-static inline void ceph_fscache_update_objectsize(struct inode *inode)
+static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
- fscache_attr_changed(ci->fscache);
+ ci->fscache = NULL;
+ ci->i_fscache_gen = 0;
}
static inline void ceph_fscache_invalidate(struct inode *inode)
@@ -88,6 +87,11 @@ static inline void ceph_fscache_readpages_cancel(struct inode *inode,
return fscache_readpages_cancel(ci->fscache, pages);
}
+static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
+{
+ ci->i_fscache_gen = ci->i_rdcache_gen - 1;
+}
+
#else
static inline int ceph_fscache_register(void)
@@ -112,8 +116,20 @@ static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
{
}
-static inline void ceph_fscache_register_inode_cookie(struct ceph_fs_client* parent_fsc,
- struct ceph_inode_info* ci)
+static inline void ceph_fscache_register_inode_cookie(struct inode *inode)
+{
+}
+
+static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
+{
+}
+
+static inline void ceph_fscache_file_set_cookie(struct inode *inode,
+ struct file *filp)
+{
+}
+
+static inline void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
{
}
@@ -141,10 +157,6 @@ static inline void ceph_readpage_to_fscache(struct inode *inode,
{
}
-static inline void ceph_fscache_update_objectsize(struct inode *inode)
-{
-}
-
static inline void ceph_fscache_invalidate(struct inode *inode)
{
}
@@ -154,10 +166,6 @@ static inline void ceph_invalidate_fscache_page(struct inode *inode,
{
}
-static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
-{
-}
-
static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
{
return 1;
@@ -173,7 +181,7 @@ static inline void ceph_fscache_readpages_cancel(struct inode *inode,
{
}
-static inline void ceph_queue_revalidate(struct inode *inode)
+static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
{
}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index cfaeef18cbca..6f60d0a3d0f9 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1656,7 +1656,7 @@ retry_locked:
*/
if ((!is_delayed || mdsc->stopping) &&
!S_ISDIR(inode->i_mode) && /* ignore readdir cache */
- ci->i_wrbuffer_ref == 0 && /* no dirty pages... */
+ !(ci->i_wb_ref || ci->i_wrbuffer_ref) && /* no dirty pages... */
inode->i_data.nrpages && /* have cached pages */
(revoking & (CEPH_CAP_FILE_CACHE|
CEPH_CAP_FILE_LAZYIO)) && /* or revoking cache */
@@ -1698,8 +1698,8 @@ retry_locked:
revoking = cap->implemented & ~cap->issued;
dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
- cap->mds, cap, ceph_cap_string(cap->issued),
- ceph_cap_string(cap_used),
+ cap->mds, cap, ceph_cap_string(cap_used),
+ ceph_cap_string(cap->issued),
ceph_cap_string(cap->implemented),
ceph_cap_string(revoking));
@@ -2317,7 +2317,7 @@ again:
/* make sure file is actually open */
file_wanted = __ceph_caps_file_wanted(ci);
- if ((file_wanted & need) == 0) {
+ if ((file_wanted & need) != need) {
dout("try_get_cap_refs need %s file_wanted %s, EBADF\n",
ceph_cap_string(need), ceph_cap_string(file_wanted));
*err = -EBADF;
@@ -2393,6 +2393,9 @@ again:
snap_rwsem_locked = true;
}
*got = need | (have & want);
+ if ((need & CEPH_CAP_FILE_RD) &&
+ !(*got & CEPH_CAP_FILE_CACHE))
+ ceph_disable_fscache_readpage(ci);
__take_cap_refs(ci, *got, true);
ret = 1;
}
@@ -2412,12 +2415,26 @@ again:
goto out_unlock;
}
- if (!__ceph_is_any_caps(ci) &&
- ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
- dout("get_cap_refs %p forced umount\n", inode);
- *err = -EIO;
- ret = 1;
- goto out_unlock;
+ if (ci->i_ceph_flags & CEPH_I_CAP_DROPPED) {
+ int mds_wanted;
+ if (ACCESS_ONCE(mdsc->fsc->mount_state) ==
+ CEPH_MOUNT_SHUTDOWN) {
+ dout("get_cap_refs %p forced umount\n", inode);
+ *err = -EIO;
+ ret = 1;
+ goto out_unlock;
+ }
+ mds_wanted = __ceph_caps_mds_wanted(ci);
+ if ((mds_wanted & need) != need) {
+ dout("get_cap_refs %p caps were dropped"
+ " (session killed?)\n", inode);
+ *err = -ESTALE;
+ ret = 1;
+ goto out_unlock;
+ }
+ if ((mds_wanted & file_wanted) ==
+ (file_wanted & (CEPH_CAP_FILE_RD|CEPH_CAP_FILE_WR)))
+ ci->i_ceph_flags &= ~CEPH_I_CAP_DROPPED;
}
dout("get_cap_refs %p have %s needed %s\n", inode,
@@ -2487,7 +2504,7 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
if (err == -EAGAIN)
continue;
if (err < 0)
- return err;
+ ret = err;
} else {
ret = wait_event_interruptible(ci->i_cap_wq,
try_get_cap_refs(ci, need, want, endoff,
@@ -2496,8 +2513,15 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
continue;
if (err < 0)
ret = err;
- if (ret < 0)
- return ret;
+ }
+ if (ret < 0) {
+ if (err == -ESTALE) {
+ /* session was killed, try renew caps */
+ ret = ceph_renew_caps(&ci->vfs_inode);
+ if (ret == 0)
+ continue;
+ }
+ return ret;
}
if (ci->i_inline_version != CEPH_INLINE_NONE &&
@@ -2533,6 +2557,9 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
break;
}
+ if ((_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE))
+ ceph_fscache_revalidate_cookie(ci);
+
*got = _got;
return 0;
}
@@ -2774,7 +2801,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
bool writeback = false;
bool queue_trunc = false;
bool queue_invalidate = false;
- bool queue_revalidate = false;
bool deleted_inode = false;
bool fill_inline = false;
@@ -2807,7 +2833,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
if (!S_ISDIR(inode->i_mode) && /* don't invalidate readdir cache */
((cap->issued & ~newcaps) & CEPH_CAP_FILE_CACHE) &&
(newcaps & CEPH_CAP_FILE_LAZYIO) == 0 &&
- !ci->i_wrbuffer_ref) {
+ !(ci->i_wrbuffer_ref || ci->i_wb_ref)) {
if (try_nonblocking_invalidate(inode)) {
/* there were locked pages.. invalidate later
in a separate thread. */
@@ -2816,8 +2842,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
ci->i_rdcache_revoking = ci->i_rdcache_gen;
}
}
-
- ceph_fscache_invalidate(inode);
}
/* side effects now are allowed */
@@ -2859,11 +2883,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
}
}
- /* Do we need to revalidate our fscache cookie. Don't bother on the
- * first cache cap as we already validate at cookie creation time. */
- if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
- queue_revalidate = true;
-
if (newcaps & CEPH_CAP_ANY_RD) {
/* ctime/mtime/atime? */
ceph_decode_timespec(&mtime, &grant->mtime);
@@ -2972,11 +2991,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
if (fill_inline)
ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
- if (queue_trunc) {
+ if (queue_trunc)
ceph_queue_vmtruncate(inode);
- ceph_queue_revalidate(inode);
- } else if (queue_revalidate)
- ceph_queue_revalidate(inode);
if (writeback)
/*
@@ -3178,10 +3194,8 @@ static void handle_cap_trunc(struct inode *inode,
truncate_seq, truncate_size, size);
spin_unlock(&ci->i_ceph_lock);
- if (queue_trunc) {
+ if (queue_trunc)
ceph_queue_vmtruncate(inode);
- ceph_fscache_invalidate(inode);
- }
}
/*
@@ -3226,6 +3240,8 @@ retry:
if (target < 0) {
__ceph_remove_cap(cap, false);
+ if (!ci->i_auth_cap)
+ ci->i_ceph_flags |= CEPH_I_CAP_DROPPED;
goto out_unlock;
}
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 31f831471ed2..39ff678e567f 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -109,7 +109,7 @@ static int mdsc_show(struct seq_file *s, void *p)
path ? path : "");
spin_unlock(&req->r_old_dentry->d_lock);
kfree(path);
- } else if (req->r_path2) {
+ } else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) {
if (req->r_ino2.ino)
seq_printf(s, " #%llx/%s", req->r_ino2.ino,
req->r_path2);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 3ab1192d2029..6e0fedf6713b 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -70,16 +70,42 @@ out_unlock:
}
/*
- * for readdir, we encode the directory frag and offset within that
- * frag into f_pos.
+ * for f_pos for readdir:
+ * - hash order:
+ * (0xff << 52) | ((24 bits hash) << 28) |
+ * (the nth entry has hash collision);
+ * - frag+name order;
+ * ((frag value) << 28) | (the nth entry in frag);
*/
+#define OFFSET_BITS 28
+#define OFFSET_MASK ((1 << OFFSET_BITS) - 1)
+#define HASH_ORDER (0xffull << (OFFSET_BITS + 24))
+loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order)
+{
+ loff_t fpos = ((loff_t)high << 28) | (loff_t)off;
+ if (hash_order)
+ fpos |= HASH_ORDER;
+ return fpos;
+}
+
+static bool is_hash_order(loff_t p)
+{
+ return (p & HASH_ORDER) == HASH_ORDER;
+}
+
static unsigned fpos_frag(loff_t p)
{
- return p >> 32;
+ return p >> OFFSET_BITS;
}
+
+static unsigned fpos_hash(loff_t p)
+{
+ return ceph_frag_value(fpos_frag(p));
+}
+
static unsigned fpos_off(loff_t p)
{
- return p & 0xffffffff;
+ return p & OFFSET_MASK;
}
static int fpos_cmp(loff_t l, loff_t r)
@@ -111,6 +137,50 @@ static int note_last_dentry(struct ceph_file_info *fi, const char *name,
return 0;
}
+
+static struct dentry *
+__dcache_find_get_entry(struct dentry *parent, u64 idx,
+ struct ceph_readdir_cache_control *cache_ctl)
+{
+ struct inode *dir = d_inode(parent);
+ struct dentry *dentry;
+ unsigned idx_mask = (PAGE_SIZE / sizeof(struct dentry *)) - 1;
+ loff_t ptr_pos = idx * sizeof(struct dentry *);
+ pgoff_t ptr_pgoff = ptr_pos >> PAGE_SHIFT;
+
+ if (ptr_pos >= i_size_read(dir))
+ return NULL;
+
+ if (!cache_ctl->page || ptr_pgoff != page_index(cache_ctl->page)) {
+ ceph_readdir_cache_release(cache_ctl);
+ cache_ctl->page = find_lock_page(&dir->i_data, ptr_pgoff);
+ if (!cache_ctl->page) {
+ dout(" page %lu not found\n", ptr_pgoff);
+ return ERR_PTR(-EAGAIN);
+ }
+ /* reading/filling the cache are serialized by
+ i_mutex, no need to use page lock */
+ unlock_page(cache_ctl->page);
+ cache_ctl->dentries = kmap(cache_ctl->page);
+ }
+
+ cache_ctl->index = idx & idx_mask;
+
+ rcu_read_lock();
+ spin_lock(&parent->d_lock);
+ /* check i_size again here, because empty directory can be
+ * marked as complete while not holding the i_mutex. */
+ if (ceph_dir_is_complete_ordered(dir) && ptr_pos < i_size_read(dir))
+ dentry = cache_ctl->dentries[cache_ctl->index];
+ else
+ dentry = NULL;
+ spin_unlock(&parent->d_lock);
+ if (dentry && !lockref_get_not_dead(&dentry->d_lockref))
+ dentry = NULL;
+ rcu_read_unlock();
+ return dentry ? : ERR_PTR(-EAGAIN);
+}
+
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
@@ -130,75 +200,68 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
struct inode *dir = d_inode(parent);
struct dentry *dentry, *last = NULL;
struct ceph_dentry_info *di;
- unsigned nsize = PAGE_SIZE / sizeof(struct dentry *);
- int err = 0;
- loff_t ptr_pos = 0;
struct ceph_readdir_cache_control cache_ctl = {};
+ u64 idx = 0;
+ int err = 0;
- dout("__dcache_readdir %p v%u at %llu\n", dir, shared_gen, ctx->pos);
+ dout("__dcache_readdir %p v%u at %llx\n", dir, shared_gen, ctx->pos);
+
+ /* search start position */
+ if (ctx->pos > 2) {
+ u64 count = div_u64(i_size_read(dir), sizeof(struct dentry *));
+ while (count > 0) {
+ u64 step = count >> 1;
+ dentry = __dcache_find_get_entry(parent, idx + step,
+ &cache_ctl);
+ if (!dentry) {
+ /* use linar search */
+ idx = 0;
+ break;
+ }
+ if (IS_ERR(dentry)) {
+ err = PTR_ERR(dentry);
+ goto out;
+ }
+ di = ceph_dentry(dentry);
+ spin_lock(&dentry->d_lock);
+ if (fpos_cmp(di->offset, ctx->pos) < 0) {
+ idx += step + 1;
+ count -= step + 1;
+ } else {
+ count = step;
+ }
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ }
- /* we can calculate cache index for the first dirfrag */
- if (ceph_frag_is_leftmost(fpos_frag(ctx->pos))) {
- cache_ctl.index = fpos_off(ctx->pos) - 2;
- BUG_ON(cache_ctl.index < 0);
- ptr_pos = cache_ctl.index * sizeof(struct dentry *);
+ dout("__dcache_readdir %p cache idx %llu\n", dir, idx);
}
- while (true) {
- pgoff_t pgoff;
- bool emit_dentry;
- if (ptr_pos >= i_size_read(dir)) {
+ for (;;) {
+ bool emit_dentry = false;
+ dentry = __dcache_find_get_entry(parent, idx++, &cache_ctl);
+ if (!dentry) {
fi->flags |= CEPH_F_ATEND;
err = 0;
break;
}
-
- err = -EAGAIN;
- pgoff = ptr_pos >> PAGE_SHIFT;
- if (!cache_ctl.page || pgoff != page_index(cache_ctl.page)) {
- ceph_readdir_cache_release(&cache_ctl);
- cache_ctl.page = find_lock_page(&dir->i_data, pgoff);
- if (!cache_ctl.page) {
- dout(" page %lu not found\n", pgoff);
- break;
- }
- /* reading/filling the cache are serialized by
- * i_mutex, no need to use page lock */
- unlock_page(cache_ctl.page);
- cache_ctl.dentries = kmap(cache_ctl.page);
+ if (IS_ERR(dentry)) {
+ err = PTR_ERR(dentry);
+ goto out;
}
- rcu_read_lock();
- spin_lock(&parent->d_lock);
- /* check i_size again here, because empty directory can be
- * marked as complete while not holding the i_mutex. */
- if (ceph_dir_is_complete_ordered(dir) &&
- ptr_pos < i_size_read(dir))
- dentry = cache_ctl.dentries[cache_ctl.index % nsize];
- else
- dentry = NULL;
- spin_unlock(&parent->d_lock);
- if (dentry && !lockref_get_not_dead(&dentry->d_lockref))
- dentry = NULL;
- rcu_read_unlock();
- if (!dentry)
- break;
-
- emit_dentry = false;
di = ceph_dentry(dentry);
spin_lock(&dentry->d_lock);
if (di->lease_shared_gen == shared_gen &&
d_really_is_positive(dentry) &&
- ceph_snap(d_inode(dentry)) != CEPH_SNAPDIR &&
- ceph_ino(d_inode(dentry)) != CEPH_INO_CEPH &&
fpos_cmp(ctx->pos, di->offset) <= 0) {
emit_dentry = true;
}
spin_unlock(&dentry->d_lock);
if (emit_dentry) {
- dout(" %llu (%llu) dentry %p %pd %p\n", di->offset, ctx->pos,
+ dout(" %llx dentry %p %pd %p\n", di->offset,
dentry, dentry, d_inode(dentry));
ctx->pos = di->offset;
if (!dir_emit(ctx, dentry->d_name.name,
@@ -218,10 +281,8 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
} else {
dput(dentry);
}
-
- cache_ctl.index++;
- ptr_pos += sizeof(struct dentry *);
}
+out:
ceph_readdir_cache_release(&cache_ctl);
if (last) {
int ret;
@@ -235,6 +296,16 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
return err;
}
+static bool need_send_readdir(struct ceph_file_info *fi, loff_t pos)
+{
+ if (!fi->last_readdir)
+ return true;
+ if (is_hash_order(pos))
+ return !ceph_frag_contains_value(fi->frag, fpos_hash(pos));
+ else
+ return fi->frag != fpos_frag(pos);
+}
+
static int ceph_readdir(struct file *file, struct dir_context *ctx)
{
struct ceph_file_info *fi = file->private_data;
@@ -242,13 +313,12 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
- unsigned frag = fpos_frag(ctx->pos);
- int off = fpos_off(ctx->pos);
+ int i;
int err;
u32 ftype;
struct ceph_mds_reply_info_parsed *rinfo;
- dout("readdir %p file %p frag %u off %u\n", inode, file, frag, off);
+ dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
if (fi->flags & CEPH_F_ATEND)
return 0;
@@ -260,7 +330,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
inode->i_mode >> 12))
return 0;
ctx->pos = 1;
- off = 1;
}
if (ctx->pos == 1) {
ino_t ino = parent_ino(file->f_path.dentry);
@@ -270,7 +339,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
inode->i_mode >> 12))
return 0;
ctx->pos = 2;
- off = 2;
}
/* can we use the dcache? */
@@ -285,8 +353,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
err = __dcache_readdir(file, ctx, shared_gen);
if (err != -EAGAIN)
return err;
- frag = fpos_frag(ctx->pos);
- off = fpos_off(ctx->pos);
} else {
spin_unlock(&ci->i_ceph_lock);
}
@@ -294,8 +360,9 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
/* proceed with a normal readdir */
more:
/* do we have the correct frag content buffered? */
- if (fi->frag != frag || fi->last_readdir == NULL) {
+ if (need_send_readdir(fi, ctx->pos)) {
struct ceph_mds_request *req;
+ unsigned frag;
int op = ceph_snap(inode) == CEPH_SNAPDIR ?
CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
@@ -305,6 +372,13 @@ more:
fi->last_readdir = NULL;
}
+ if (is_hash_order(ctx->pos)) {
+ frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
+ NULL, NULL);
+ } else {
+ frag = fpos_frag(ctx->pos);
+ }
+
dout("readdir fetching %llx.%llx frag %x offset '%s'\n",
ceph_vinop(inode), frag, fi->last_name);
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
@@ -331,6 +405,8 @@ more:
req->r_readdir_cache_idx = fi->readdir_cache_idx;
req->r_readdir_offset = fi->next_offset;
req->r_args.readdir.frag = cpu_to_le32(frag);
+ req->r_args.readdir.flags =
+ cpu_to_le16(CEPH_READDIR_REPLY_BITFLAGS);
req->r_inode = inode;
ihold(inode);
@@ -340,22 +416,26 @@ more:
ceph_mdsc_put_request(req);
return err;
}
- dout("readdir got and parsed readdir result=%d"
- " on frag %x, end=%d, complete=%d\n", err, frag,
+ dout("readdir got and parsed readdir result=%d on "
+ "frag %x, end=%d, complete=%d, hash_order=%d\n",
+ err, frag,
(int)req->r_reply_info.dir_end,
- (int)req->r_reply_info.dir_complete);
-
+ (int)req->r_reply_info.dir_complete,
+ (int)req->r_reply_info.hash_order);
- /* note next offset and last dentry name */
rinfo = &req->r_reply_info;
if (le32_to_cpu(rinfo->dir_dir->frag) != frag) {
frag = le32_to_cpu(rinfo->dir_dir->frag);
- off = req->r_readdir_offset;
- fi->next_offset = off;
+ if (!rinfo->hash_order) {
+ fi->next_offset = req->r_readdir_offset;
+ /* adjust ctx->pos to beginning of frag */
+ ctx->pos = ceph_make_fpos(frag,
+ fi->next_offset,
+ false);
+ }
}
fi->frag = frag;
- fi->offset = fi->next_offset;
fi->last_readdir = req;
if (req->r_did_prepopulate) {
@@ -363,7 +443,8 @@ more:
if (fi->readdir_cache_idx < 0) {
/* preclude from marking dir ordered */
fi->dir_ordered_count = 0;
- } else if (ceph_frag_is_leftmost(frag) && off == 2) {
+ } else if (ceph_frag_is_leftmost(frag) &&
+ fi->next_offset == 2) {
/* note dir version at start of readdir so
* we can tell if any dentries get dropped */
fi->dir_release_count = req->r_dir_release_cnt;
@@ -377,65 +458,87 @@ more:
fi->dir_release_count = 0;
}
- if (req->r_reply_info.dir_end) {
- kfree(fi->last_name);
- fi->last_name = NULL;
- if (ceph_frag_is_rightmost(frag))
- fi->next_offset = 2;
- else
- fi->next_offset = 0;
- } else {
- err = note_last_dentry(fi,
- rinfo->dir_dname[rinfo->dir_nr-1],
- rinfo->dir_dname_len[rinfo->dir_nr-1],
- fi->next_offset + rinfo->dir_nr);
+ /* note next offset and last dentry name */
+ if (rinfo->dir_nr > 0) {
+ struct ceph_mds_reply_dir_entry *rde =
+ rinfo->dir_entries + (rinfo->dir_nr-1);
+ unsigned next_offset = req->r_reply_info.dir_end ?
+ 2 : (fpos_off(rde->offset) + 1);
+ err = note_last_dentry(fi, rde->name, rde->name_len,
+ next_offset);
if (err)
return err;
+ } else if (req->r_reply_info.dir_end) {
+ fi->next_offset = 2;
+ /* keep last name */
}
}
rinfo = &fi->last_readdir->r_reply_info;
- dout("readdir frag %x num %d off %d chunkoff %d\n", frag,
- rinfo->dir_nr, off, fi->offset);
-
- ctx->pos = ceph_make_fpos(frag, off);
- while (off >= fi->offset && off - fi->offset < rinfo->dir_nr) {
- struct ceph_mds_reply_inode *in =
- rinfo->dir_in[off - fi->offset].in;
+ dout("readdir frag %x num %d pos %llx chunk first %llx\n",
+ fi->frag, rinfo->dir_nr, ctx->pos,
+ rinfo->dir_nr ? rinfo->dir_entries[0].offset : 0LL);
+
+ i = 0;
+ /* search start position */
+ if (rinfo->dir_nr > 0) {
+ int step, nr = rinfo->dir_nr;
+ while (nr > 0) {
+ step = nr >> 1;
+ if (rinfo->dir_entries[i + step].offset < ctx->pos) {
+ i += step + 1;
+ nr -= step + 1;
+ } else {
+ nr = step;
+ }
+ }
+ }
+ for (; i < rinfo->dir_nr; i++) {
+ struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
struct ceph_vino vino;
ino_t ino;
- dout("readdir off %d (%d/%d) -> %lld '%.*s' %p\n",
- off, off - fi->offset, rinfo->dir_nr, ctx->pos,
- rinfo->dir_dname_len[off - fi->offset],
- rinfo->dir_dname[off - fi->offset], in);
- BUG_ON(!in);
- ftype = le32_to_cpu(in->mode) >> 12;
- vino.ino = le64_to_cpu(in->ino);
- vino.snap = le64_to_cpu(in->snapid);
+ BUG_ON(rde->offset < ctx->pos);
+
+ ctx->pos = rde->offset;
+ dout("readdir (%d/%d) -> %llx '%.*s' %p\n",
+ i, rinfo->dir_nr, ctx->pos,
+ rde->name_len, rde->name, &rde->inode.in);
+
+ BUG_ON(!rde->inode.in);
+ ftype = le32_to_cpu(rde->inode.in->mode) >> 12;
+ vino.ino = le64_to_cpu(rde->inode.in->ino);
+ vino.snap = le64_to_cpu(rde->inode.in->snapid);
ino = ceph_vino_to_ino(vino);
- if (!dir_emit(ctx,
- rinfo->dir_dname[off - fi->offset],
- rinfo->dir_dname_len[off - fi->offset],
- ceph_translate_ino(inode->i_sb, ino), ftype)) {
+
+ if (!dir_emit(ctx, rde->name, rde->name_len,
+ ceph_translate_ino(inode->i_sb, ino), ftype)) {
dout("filldir stopping us...\n");
return 0;
}
- off++;
ctx->pos++;
}
- if (fi->last_name) {
+ if (fi->next_offset > 2) {
ceph_mdsc_put_request(fi->last_readdir);
fi->last_readdir = NULL;
goto more;
}
/* more frags? */
- if (!ceph_frag_is_rightmost(frag)) {
- frag = ceph_frag_next(frag);
- off = 0;
- ctx->pos = ceph_make_fpos(frag, off);
+ if (!ceph_frag_is_rightmost(fi->frag)) {
+ unsigned frag = ceph_frag_next(fi->frag);
+ if (is_hash_order(ctx->pos)) {
+ loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
+ fi->next_offset, true);
+ if (new_pos > ctx->pos)
+ ctx->pos = new_pos;
+ /* keep last_name */
+ } else {
+ ctx->pos = ceph_make_fpos(frag, fi->next_offset, false);
+ kfree(fi->last_name);
+ fi->last_name = NULL;
+ }
dout("readdir next frag is %x\n", frag);
goto more;
}
@@ -467,7 +570,7 @@ more:
return 0;
}
-static void reset_readdir(struct ceph_file_info *fi, unsigned frag)
+static void reset_readdir(struct ceph_file_info *fi)
{
if (fi->last_readdir) {
ceph_mdsc_put_request(fi->last_readdir);
@@ -477,18 +580,38 @@ static void reset_readdir(struct ceph_file_info *fi, unsigned frag)
fi->last_name = NULL;
fi->dir_release_count = 0;
fi->readdir_cache_idx = -1;
- if (ceph_frag_is_leftmost(frag))
- fi->next_offset = 2; /* compensate for . and .. */
- else
- fi->next_offset = 0;
+ fi->next_offset = 2; /* compensate for . and .. */
fi->flags &= ~CEPH_F_ATEND;
}
+/*
+ * discard buffered readdir content on seekdir(0), or seek to new frag,
+ * or seek prior to current chunk
+ */
+static bool need_reset_readdir(struct ceph_file_info *fi, loff_t new_pos)
+{
+ struct ceph_mds_reply_info_parsed *rinfo;
+ loff_t chunk_offset;
+ if (new_pos == 0)
+ return true;
+ if (is_hash_order(new_pos)) {
+ /* no need to reset last_name for a forward seek when
+ * dentries are sotred in hash order */
+ } else if (fi->frag |= fpos_frag(new_pos)) {
+ return true;
+ }
+ rinfo = fi->last_readdir ? &fi->last_readdir->r_reply_info : NULL;
+ if (!rinfo || !rinfo->dir_nr)
+ return true;
+ chunk_offset = rinfo->dir_entries[0].offset;
+ return new_pos < chunk_offset ||
+ is_hash_order(new_pos) != is_hash_order(chunk_offset);
+}
+
static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
{
struct ceph_file_info *fi = file->private_data;
struct inode *inode = file->f_mapping->host;
- loff_t old_offset = ceph_make_fpos(fi->frag, fi->next_offset);
loff_t retval;
inode_lock(inode);
@@ -505,25 +628,22 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
}
if (offset >= 0) {
+ if (need_reset_readdir(fi, offset)) {
+ dout("dir_llseek dropping %p content\n", file);
+ reset_readdir(fi);
+ } else if (is_hash_order(offset) && offset > file->f_pos) {
+ /* for hash offset, we don't know if a forward seek
+ * is within same frag */
+ fi->dir_release_count = 0;
+ fi->readdir_cache_idx = -1;
+ }
+
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
fi->flags &= ~CEPH_F_ATEND;
}
retval = offset;
-
- if (offset == 0 ||
- fpos_frag(offset) != fi->frag ||
- fpos_off(offset) < fi->offset) {
- /* discard buffered readdir content on seekdir(0), or
- * seek to new frag, or seek prior to current chunk */
- dout("dir_llseek dropping %p content\n", file);
- reset_readdir(fi, fpos_frag(offset));
- } else if (fpos_cmp(offset, old_offset) > 0) {
- /* reset dir_release_count if we did a forward seek */
- fi->dir_release_count = 0;
- fi->readdir_cache_idx = -1;
- }
}
out:
inode_unlock(inode);
@@ -591,7 +711,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
return dentry;
}
-static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
+static bool is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
{
return ceph_ino(inode) == CEPH_INO_ROOT &&
strncmp(dentry->d_name.name, ".ceph", 5) == 0;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 6e72c98162d5..1780218a48f0 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -95,10 +95,8 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
}
dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- iput(inode);
+ if (IS_ERR(dentry))
return dentry;
- }
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
@@ -167,10 +165,8 @@ static struct dentry *__get_parent(struct super_block *sb,
return ERR_PTR(-ENOENT);
dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- iput(inode);
+ if (IS_ERR(dentry))
return dentry;
- }
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
@@ -210,7 +206,7 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
dout("fh_to_parent %llx\n", cfh->parent_ino);
dentry = __get_parent(sb, NULL, cfh->ino);
- if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT)
+ if (unlikely(dentry == ERR_PTR(-ENOENT)))
dentry = __fh_to_dentry(sb, cfh->parent_ino);
return dentry;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 4f1dc7120916..ce2f5795e44b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -137,23 +137,11 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
struct ceph_file_info *cf;
int ret = 0;
- struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
- struct ceph_mds_client *mdsc = fsc->mdsc;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
- /* First file open request creates the cookie, we want to keep
- * this cookie around for the filetime of the inode as not to
- * have to worry about fscache register / revoke / operation
- * races.
- *
- * Also, if we know the operation is going to invalidate data
- * (non readonly) just nuke the cache right away.
- */
- ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
- if ((fmode & CEPH_FILE_MODE_WR))
- ceph_fscache_invalidate(inode);
+ ceph_fscache_register_inode_cookie(inode);
+ ceph_fscache_file_set_cookie(inode, file);
case S_IFDIR:
dout("init_file %p %p 0%o (regular)\n", inode, file,
inode->i_mode);
@@ -192,6 +180,59 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
}
/*
+ * try renew caps after session gets killed.
+ */
+int ceph_renew_caps(struct inode *inode)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_mds_request *req;
+ int err, flags, wanted;
+
+ spin_lock(&ci->i_ceph_lock);
+ wanted = __ceph_caps_file_wanted(ci);
+ if (__ceph_is_any_real_caps(ci) &&
+ (!(wanted & CEPH_CAP_ANY_WR) == 0 || ci->i_auth_cap)) {
+ int issued = __ceph_caps_issued(ci, NULL);
+ spin_unlock(&ci->i_ceph_lock);
+ dout("renew caps %p want %s issued %s updating mds_wanted\n",
+ inode, ceph_cap_string(wanted), ceph_cap_string(issued));
+ ceph_check_caps(ci, 0, NULL);
+ return 0;
+ }
+ spin_unlock(&ci->i_ceph_lock);
+
+ flags = 0;
+ if ((wanted & CEPH_CAP_FILE_RD) && (wanted & CEPH_CAP_FILE_WR))
+ flags = O_RDWR;
+ else if (wanted & CEPH_CAP_FILE_RD)
+ flags = O_RDONLY;
+ else if (wanted & CEPH_CAP_FILE_WR)
+ flags = O_WRONLY;
+#ifdef O_LAZY
+ if (wanted & CEPH_CAP_FILE_LAZYIO)
+ flags |= O_LAZY;
+#endif
+
+ req = prepare_open_request(inode->i_sb, flags, 0);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ goto out;
+ }
+
+ req->r_inode = inode;
+ ihold(inode);
+ req->r_num_caps = 1;
+ req->r_fmode = -1;
+
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
+ ceph_mdsc_put_request(req);
+out:
+ dout("renew caps %p open result=%d\n", inode, err);
+ return err < 0 ? err : 0;
+}
+
+/*
* If we already have the requisite capabilities, we can satisfy
* the open request locally (no need to request new caps from the
* MDS). We do, however, need to inform the MDS (asynchronously)
@@ -616,8 +657,7 @@ static void ceph_aio_complete(struct inode *inode,
kfree(aio_req);
}
-static void ceph_aio_complete_req(struct ceph_osd_request *req,
- struct ceph_msg *msg)
+static void ceph_aio_complete_req(struct ceph_osd_request *req)
{
int rc = req->r_result;
struct inode *inode = req->r_inode;
@@ -714,14 +754,21 @@ static void ceph_aio_retry_work(struct work_struct *work)
req->r_flags = CEPH_OSD_FLAG_ORDERSNAP |
CEPH_OSD_FLAG_ONDISK |
CEPH_OSD_FLAG_WRITE;
- req->r_base_oloc = orig_req->r_base_oloc;
- req->r_base_oid = orig_req->r_base_oid;
+ ceph_oloc_copy(&req->r_base_oloc, &orig_req->r_base_oloc);
+ ceph_oid_copy(&req->r_base_oid, &orig_req->r_base_oid);
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOFS);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ req = orig_req;
+ goto out;
+ }
req->r_ops[0] = orig_req->r_ops[0];
osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0);
- ceph_osdc_build_request(req, req->r_ops[0].extent.offset,
- snapc, CEPH_NOSNAP, &aio_req->mtime);
+ req->r_mtime = aio_req->mtime;
+ req->r_data_offset = req->r_ops[0].extent.offset;
ceph_osdc_put_request(orig_req);
@@ -733,7 +780,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
out:
if (ret < 0) {
req->r_result = ret;
- ceph_aio_complete_req(req, NULL);
+ ceph_aio_complete_req(req);
}
ceph_put_snap_context(snapc);
@@ -764,6 +811,8 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
list_add_tail(&req->r_unsafe_item,
&ci->i_unsafe_writes);
spin_unlock(&ci->i_unsafe_lock);
+
+ complete_all(&req->r_completion);
} else {
spin_lock(&ci->i_unsafe_lock);
list_del_init(&req->r_unsafe_item);
@@ -875,14 +924,12 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
(pos+len) | (PAGE_SIZE - 1));
osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0);
+ req->r_mtime = mtime;
}
-
osd_req_op_extent_osd_data_pages(req, 0, pages, len, start,
false, false);
- ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);
-
if (aio_req) {
aio_req->total_len += len;
aio_req->num_reqs++;
@@ -956,7 +1003,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
req, false);
if (ret < 0) {
req->r_result = ret;
- ceph_aio_complete_req(req, NULL);
+ ceph_aio_complete_req(req);
}
}
return -EIOCBQUEUED;
@@ -1067,9 +1114,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
false, true);
- /* BUG_ON(vino.snap != CEPH_NOSNAP); */
- ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);
-
+ req->r_mtime = mtime;
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!ret)
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
@@ -1292,7 +1337,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
}
retry_snap:
- if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
+ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
err = -ENOSPC;
goto out;
}
@@ -1350,7 +1395,6 @@ retry_snap:
iov_iter_advance(from, written);
ceph_put_snap_context(snapc);
} else {
- loff_t old_size = i_size_read(inode);
/*
* No need to acquire the i_truncate_mutex. Because
* the MDS revokes Fwb caps before sending truncate
@@ -1361,8 +1405,6 @@ retry_snap:
written = generic_perform_write(file, from, pos);
if (likely(written >= 0))
iocb->ki_pos = pos + written;
- if (i_size_read(inode) > old_size)
- ceph_fscache_update_objectsize(inode);
inode_unlock(inode);
}
@@ -1383,7 +1425,7 @@ retry_snap:
ceph_put_cap_refs(ci, got);
if (written >= 0) {
- if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))
+ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_NEARFULL))
iocb->ki_flags |= IOCB_DSYNC;
written = generic_write_sync(iocb, written);
@@ -1524,9 +1566,7 @@ static int ceph_zero_partial_object(struct inode *inode,
goto out;
}
- ceph_osdc_build_request(req, offset, NULL, ceph_vino(inode).snap,
- &inode->i_mtime);
-
+ req->r_mtime = inode->i_mtime;
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!ret) {
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
@@ -1617,8 +1657,8 @@ static long ceph_fallocate(struct file *file, int mode,
goto unlock;
}
- if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) &&
- !(mode & FALLOC_FL_PUNCH_HOLE)) {
+ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) &&
+ !(mode & FALLOC_FL_PUNCH_HOLE)) {
ret = -ENOSPC;
goto unlock;
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e669cfa9d793..f059b5997072 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -11,6 +11,7 @@
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/random.h>
+#include <linux/sort.h>
#include "super.h"
#include "mds_client.h"
@@ -254,6 +255,9 @@ static int ceph_fill_dirfrag(struct inode *inode,
diri_auth = ci->i_auth_cap->mds;
spin_unlock(&ci->i_ceph_lock);
+ if (mds == -1) /* CDIR_AUTH_PARENT */
+ mds = diri_auth;
+
mutex_lock(&ci->i_fragtree_mutex);
if (ndist == 0 && mds == diri_auth) {
/* no delegation info needed. */
@@ -300,20 +304,38 @@ out:
return err;
}
+static int frag_tree_split_cmp(const void *l, const void *r)
+{
+ struct ceph_frag_tree_split *ls = (struct ceph_frag_tree_split*)l;
+ struct ceph_frag_tree_split *rs = (struct ceph_frag_tree_split*)r;
+ return ceph_frag_compare(ls->frag, rs->frag);
+}
+
+static bool is_frag_child(u32 f, struct ceph_inode_frag *frag)
+{
+ if (!frag)
+ return f == ceph_frag_make(0, 0);
+ if (ceph_frag_bits(f) != ceph_frag_bits(frag->frag) + frag->split_by)
+ return false;
+ return ceph_frag_contains_value(frag->frag, ceph_frag_value(f));
+}
+
static int ceph_fill_fragtree(struct inode *inode,
struct ceph_frag_tree_head *fragtree,
struct ceph_mds_reply_dirfrag *dirinfo)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_inode_frag *frag;
+ struct ceph_inode_frag *frag, *prev_frag = NULL;
struct rb_node *rb_node;
- int i;
- u32 id, nsplits;
+ unsigned i, split_by, nsplits;
+ u32 id;
bool update = false;
mutex_lock(&ci->i_fragtree_mutex);
nsplits = le32_to_cpu(fragtree->nsplits);
- if (nsplits) {
+ if (nsplits != ci->i_fragtree_nsplits) {
+ update = true;
+ } else if (nsplits) {
i = prandom_u32() % nsplits;
id = le32_to_cpu(fragtree->splits[i].frag);
if (!__ceph_find_frag(ci, id))
@@ -332,10 +354,22 @@ static int ceph_fill_fragtree(struct inode *inode,
if (!update)
goto out_unlock;
+ if (nsplits > 1) {
+ sort(fragtree->splits, nsplits, sizeof(fragtree->splits[0]),
+ frag_tree_split_cmp, NULL);
+ }
+
dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
rb_node = rb_first(&ci->i_fragtree);
for (i = 0; i < nsplits; i++) {
id = le32_to_cpu(fragtree->splits[i].frag);
+ split_by = le32_to_cpu(fragtree->splits[i].by);
+ if (split_by == 0 || ceph_frag_bits(id) + split_by > 24) {
+ pr_err("fill_fragtree %llx.%llx invalid split %d/%u, "
+ "frag %x split by %d\n", ceph_vinop(inode),
+ i, nsplits, id, split_by);
+ continue;
+ }
frag = NULL;
while (rb_node) {
frag = rb_entry(rb_node, struct ceph_inode_frag, node);
@@ -347,8 +381,14 @@ static int ceph_fill_fragtree(struct inode *inode,
break;
}
rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
+ /* delete stale split/leaf node */
+ if (frag->split_by > 0 ||
+ !is_frag_child(frag->frag, prev_frag)) {
+ rb_erase(&frag->node, &ci->i_fragtree);
+ if (frag->split_by > 0)
+ ci->i_fragtree_nsplits--;
+ kfree(frag);
+ }
frag = NULL;
}
if (!frag) {
@@ -356,14 +396,23 @@ static int ceph_fill_fragtree(struct inode *inode,
if (IS_ERR(frag))
continue;
}
- frag->split_by = le32_to_cpu(fragtree->splits[i].by);
+ if (frag->split_by == 0)
+ ci->i_fragtree_nsplits++;
+ frag->split_by = split_by;
dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+ prev_frag = frag;
}
while (rb_node) {
frag = rb_entry(rb_node, struct ceph_inode_frag, node);
rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
+ /* delete stale split/leaf node */
+ if (frag->split_by > 0 ||
+ !is_frag_child(frag->frag, prev_frag)) {
+ rb_erase(&frag->node, &ci->i_fragtree);
+ if (frag->split_by > 0)
+ ci->i_fragtree_nsplits--;
+ kfree(frag);
+ }
}
out_unlock:
mutex_unlock(&ci->i_fragtree_mutex);
@@ -513,6 +562,7 @@ void ceph_destroy_inode(struct inode *inode)
rb_erase(n, &ci->i_fragtree);
kfree(frag);
}
+ ci->i_fragtree_nsplits = 0;
__ceph_destroy_xattrs(ci);
if (ci->i_xattrs.blob)
@@ -533,6 +583,11 @@ int ceph_drop_inode(struct inode *inode)
return 1;
}
+static inline blkcnt_t calc_inode_blocks(u64 size)
+{
+ return (size + (1<<9) - 1) >> 9;
+}
+
/*
* Helpers to fill in size, ctime, mtime, and atime. We have to be
* careful because either the client or MDS may have more up to date
@@ -555,7 +610,7 @@ int ceph_fill_file_size(struct inode *inode, int issued,
size = 0;
}
i_size_write(inode, size);
- inode->i_blocks = (size + (1<<9) - 1) >> 9;
+ inode->i_blocks = calc_inode_blocks(size);
ci->i_reported_size = size;
if (truncate_seq != ci->i_truncate_seq) {
dout("truncate_seq %u -> %u\n",
@@ -814,9 +869,13 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
spin_unlock(&ci->i_ceph_lock);
- err = -EINVAL;
- if (WARN_ON(symlen != i_size_read(inode)))
- goto out;
+ if (symlen != i_size_read(inode)) {
+ pr_err("fill_inode %llx.%llx BAD symlink "
+ "size %lld\n", ceph_vinop(inode),
+ i_size_read(inode));
+ i_size_write(inode, symlen);
+ inode->i_blocks = calc_inode_blocks(symlen);
+ }
err = -ENOMEM;
sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
@@ -1309,12 +1368,13 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
int i, err = 0;
for (i = 0; i < rinfo->dir_nr; i++) {
+ struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
struct ceph_vino vino;
struct inode *in;
int rc;
- vino.ino = le64_to_cpu(rinfo->dir_in[i].in->ino);
- vino.snap = le64_to_cpu(rinfo->dir_in[i].in->snapid);
+ vino.ino = le64_to_cpu(rde->inode.in->ino);
+ vino.snap = le64_to_cpu(rde->inode.in->snapid);
in = ceph_get_inode(req->r_dentry->d_sb, vino);
if (IS_ERR(in)) {
@@ -1322,14 +1382,14 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
dout("new_inode badness got %d\n", err);
continue;
}
- rc = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
+ rc = fill_inode(in, NULL, &rde->inode, NULL, session,
req->r_request_started, -1,
&req->r_caps_reservation);
if (rc < 0) {
pr_err("fill_inode badness on %p got %d\n", in, rc);
err = rc;
- continue;
}
+ iput(in);
}
return err;
@@ -1387,6 +1447,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
struct ceph_mds_session *session)
{
struct dentry *parent = req->r_dentry;
+ struct ceph_inode_info *ci = ceph_inode(d_inode(parent));
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
struct qstr dname;
struct dentry *dn;
@@ -1394,22 +1455,27 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
int err = 0, skipped = 0, ret, i;
struct inode *snapdir = NULL;
struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
- struct ceph_dentry_info *di;
u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+ u32 last_hash = 0;
+ u32 fpos_offset;
struct ceph_readdir_cache_control cache_ctl = {};
if (req->r_aborted)
return readdir_prepopulate_inodes_only(req, session);
+ if (rinfo->hash_order && req->r_path2) {
+ last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+ req->r_path2, strlen(req->r_path2));
+ last_hash = ceph_frag_value(last_hash);
+ }
+
if (rinfo->dir_dir &&
le32_to_cpu(rinfo->dir_dir->frag) != frag) {
dout("readdir_prepopulate got new frag %x -> %x\n",
frag, le32_to_cpu(rinfo->dir_dir->frag));
frag = le32_to_cpu(rinfo->dir_dir->frag);
- if (ceph_frag_is_leftmost(frag))
+ if (!rinfo->hash_order)
req->r_readdir_offset = 2;
- else
- req->r_readdir_offset = 0;
}
if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
@@ -1427,24 +1493,37 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
- struct ceph_inode_info *ci = ceph_inode(d_inode(parent));
req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
req->r_dir_ordered_cnt = atomic64_read(&ci->i_ordered_count);
req->r_readdir_cache_idx = 0;
}
cache_ctl.index = req->r_readdir_cache_idx;
+ fpos_offset = req->r_readdir_offset;
/* FIXME: release caps/leases if error occurs */
for (i = 0; i < rinfo->dir_nr; i++) {
+ struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
struct ceph_vino vino;
- dname.name = rinfo->dir_dname[i];
- dname.len = rinfo->dir_dname_len[i];
+ dname.name = rde->name;
+ dname.len = rde->name_len;
dname.hash = full_name_hash(dname.name, dname.len);
- vino.ino = le64_to_cpu(rinfo->dir_in[i].in->ino);
- vino.snap = le64_to_cpu(rinfo->dir_in[i].in->snapid);
+ vino.ino = le64_to_cpu(rde->inode.in->ino);
+ vino.snap = le64_to_cpu(rde->inode.in->snapid);
+
+ if (rinfo->hash_order) {
+ u32 hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+ rde->name, rde->name_len);
+ hash = ceph_frag_value(hash);
+ if (hash != last_hash)
+ fpos_offset = 2;
+ last_hash = hash;
+ rde->offset = ceph_make_fpos(hash, fpos_offset++, true);
+ } else {
+ rde->offset = ceph_make_fpos(frag, fpos_offset++, false);
+ }
retry_lookup:
dn = d_lookup(parent, &dname);
@@ -1490,7 +1569,7 @@ retry_lookup:
}
}
- ret = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
+ ret = fill_inode(in, NULL, &rde->inode, NULL, session,
req->r_request_started, -1,
&req->r_caps_reservation);
if (ret < 0) {
@@ -1523,11 +1602,9 @@ retry_lookup:
dn = realdn;
}
- di = dn->d_fsdata;
- di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset);
+ ceph_dentry(dn)->offset = rde->offset;
- update_dentry_lease(dn, rinfo->dir_dlease[i],
- req->r_session,
+ update_dentry_lease(dn, rde->lease, req->r_session,
req->r_request_started);
if (err == 0 && skipped == 0 && cache_ctl.index >= 0) {
@@ -1562,7 +1639,7 @@ int ceph_inode_set_size(struct inode *inode, loff_t size)
spin_lock(&ci->i_ceph_lock);
dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
i_size_write(inode, size);
- inode->i_blocks = (size + (1 << 9) - 1) >> 9;
+ inode->i_blocks = calc_inode_blocks(size);
/* tell the MDS if we are approaching max_size */
if ((size << 1) >= ci->i_max_size &&
@@ -1624,10 +1701,21 @@ static void ceph_invalidate_work(struct work_struct *work)
struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
i_pg_inv_work);
struct inode *inode = &ci->vfs_inode;
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
u32 orig_gen;
int check = 0;
mutex_lock(&ci->i_truncate_mutex);
+
+ if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+ pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n",
+ inode, ceph_ino(inode));
+ mapping_set_error(inode->i_mapping, -EIO);
+ truncate_pagecache(inode, 0);
+ mutex_unlock(&ci->i_truncate_mutex);
+ goto out;
+ }
+
spin_lock(&ci->i_ceph_lock);
dout("invalidate_pages %p gen %d revoking %d\n", inode,
ci->i_rdcache_gen, ci->i_rdcache_revoking);
@@ -1641,7 +1729,9 @@ static void ceph_invalidate_work(struct work_struct *work)
orig_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
- truncate_pagecache(inode, 0);
+ if (invalidate_inode_pages2(inode->i_mapping) < 0) {
+ pr_err("invalidate_pages %p fails\n", inode);
+ }
spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
@@ -1920,8 +2010,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
if ((issued & CEPH_CAP_FILE_EXCL) &&
attr->ia_size > inode->i_size) {
i_size_write(inode, attr->ia_size);
- inode->i_blocks =
- (attr->ia_size + (1 << 9) - 1) >> 9;
+ inode->i_blocks = calc_inode_blocks(attr->ia_size);
inode->i_ctime = attr->ia_ctime;
ci->i_reported_size = attr->ia_size;
dirtied |= CEPH_CAP_FILE_EXCL;
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index f851d8d70158..be6b1657b1af 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -193,12 +193,12 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
if (copy_from_user(&dl, arg, sizeof(dl)))
return -EFAULT;
- down_read(&osdc->map_sem);
+ down_read(&osdc->lock);
r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
&dl.object_no, &dl.object_offset,
&olen);
if (r < 0) {
- up_read(&osdc->map_sem);
+ up_read(&osdc->lock);
return -EIO;
}
dl.file_offset -= dl.object_offset;
@@ -213,15 +213,15 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
ceph_ino(inode), dl.object_no);
oloc.pool = ceph_file_layout_pg_pool(ci->i_layout);
- ceph_oid_set_name(&oid, dl.object_name);
+ ceph_oid_printf(&oid, "%s", dl.object_name);
- r = ceph_oloc_oid_to_pg(osdc->osdmap, &oloc, &oid, &pgid);
+ r = ceph_object_locator_to_pg(osdc->osdmap, &oid, &oloc, &pgid);
if (r < 0) {
- up_read(&osdc->map_sem);
+ up_read(&osdc->lock);
return r;
}
- dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
+ dl.osd = ceph_pg_to_acting_primary(osdc->osdmap, &pgid);
if (dl.osd >= 0) {
struct ceph_entity_addr *a =
ceph_osd_addr(osdc->osdmap, dl.osd);
@@ -230,7 +230,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
} else {
memset(&dl.osd_addr, 0, sizeof(dl.osd_addr));
}
- up_read(&osdc->map_sem);
+ up_read(&osdc->lock);
/* send result back to user */
if (copy_to_user(arg, &dl, sizeof(dl)))
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 85b8517f17a0..2103b823bec0 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -181,17 +181,18 @@ static int parse_reply_info_dir(void **p, void *end,
ceph_decode_need(p, end, sizeof(num) + 2, bad);
num = ceph_decode_32(p);
- info->dir_end = ceph_decode_8(p);
- info->dir_complete = ceph_decode_8(p);
+ {
+ u16 flags = ceph_decode_16(p);
+ info->dir_end = !!(flags & CEPH_READDIR_FRAG_END);
+ info->dir_complete = !!(flags & CEPH_READDIR_FRAG_COMPLETE);
+ info->hash_order = !!(flags & CEPH_READDIR_HASH_ORDER);
+ }
if (num == 0)
goto done;
- BUG_ON(!info->dir_in);
- info->dir_dname = (void *)(info->dir_in + num);
- info->dir_dname_len = (void *)(info->dir_dname + num);
- info->dir_dlease = (void *)(info->dir_dname_len + num);
- if ((unsigned long)(info->dir_dlease + num) >
- (unsigned long)info->dir_in + info->dir_buf_size) {
+ BUG_ON(!info->dir_entries);
+ if ((unsigned long)(info->dir_entries + num) >
+ (unsigned long)info->dir_entries + info->dir_buf_size) {
pr_err("dir contents are larger than expected\n");
WARN_ON(1);
goto bad;
@@ -199,21 +200,23 @@ static int parse_reply_info_dir(void **p, void *end,
info->dir_nr = num;
while (num) {
+ struct ceph_mds_reply_dir_entry *rde = info->dir_entries + i;
/* dentry */
ceph_decode_need(p, end, sizeof(u32)*2, bad);
- info->dir_dname_len[i] = ceph_decode_32(p);
- ceph_decode_need(p, end, info->dir_dname_len[i], bad);
- info->dir_dname[i] = *p;
- *p += info->dir_dname_len[i];
- dout("parsed dir dname '%.*s'\n", info->dir_dname_len[i],
- info->dir_dname[i]);
- info->dir_dlease[i] = *p;
+ rde->name_len = ceph_decode_32(p);
+ ceph_decode_need(p, end, rde->name_len, bad);
+ rde->name = *p;
+ *p += rde->name_len;
+ dout("parsed dir dname '%.*s'\n", rde->name_len, rde->name);
+ rde->lease = *p;
*p += sizeof(struct ceph_mds_reply_lease);
/* inode */
- err = parse_reply_info_in(p, end, &info->dir_in[i], features);
+ err = parse_reply_info_in(p, end, &rde->inode, features);
if (err < 0)
goto out_bad;
+ /* ceph_readdir_prepopulate() will update it */
+ rde->offset = 0;
i++;
num--;
}
@@ -345,9 +348,9 @@ out_bad:
static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
{
- if (!info->dir_in)
+ if (!info->dir_entries)
return;
- free_pages((unsigned long)info->dir_in, get_order(info->dir_buf_size));
+ free_pages((unsigned long)info->dir_entries, get_order(info->dir_buf_size));
}
@@ -567,51 +570,23 @@ void ceph_mdsc_release_request(struct kref *kref)
kfree(req);
}
+DEFINE_RB_FUNCS(request, struct ceph_mds_request, r_tid, r_node)
+
/*
* lookup session, bump ref if found.
*
* called under mdsc->mutex.
*/
-static struct ceph_mds_request *__lookup_request(struct ceph_mds_client *mdsc,
- u64 tid)
+static struct ceph_mds_request *
+lookup_get_request(struct ceph_mds_client *mdsc, u64 tid)
{
struct ceph_mds_request *req;
- struct rb_node *n = mdsc->request_tree.rb_node;
-
- while (n) {
- req = rb_entry(n, struct ceph_mds_request, r_node);
- if (tid < req->r_tid)
- n = n->rb_left;
- else if (tid > req->r_tid)
- n = n->rb_right;
- else {
- ceph_mdsc_get_request(req);
- return req;
- }
- }
- return NULL;
-}
-static void __insert_request(struct ceph_mds_client *mdsc,
- struct ceph_mds_request *new)
-{
- struct rb_node **p = &mdsc->request_tree.rb_node;
- struct rb_node *parent = NULL;
- struct ceph_mds_request *req = NULL;
+ req = lookup_request(&mdsc->request_tree, tid);
+ if (req)
+ ceph_mdsc_get_request(req);
- while (*p) {
- parent = *p;
- req = rb_entry(parent, struct ceph_mds_request, r_node);
- if (new->r_tid < req->r_tid)
- p = &(*p)->rb_left;
- else if (new->r_tid > req->r_tid)
- p = &(*p)->rb_right;
- else
- BUG();
- }
-
- rb_link_node(&new->r_node, parent, p);
- rb_insert_color(&new->r_node, &mdsc->request_tree);
+ return req;
}
/*
@@ -630,7 +605,7 @@ static void __register_request(struct ceph_mds_client *mdsc,
req->r_num_caps);
dout("__register_request %p tid %lld\n", req, req->r_tid);
ceph_mdsc_get_request(req);
- __insert_request(mdsc, req);
+ insert_request(&mdsc->request_tree, req);
req->r_uid = current_fsuid();
req->r_gid = current_fsgid();
@@ -663,8 +638,7 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
}
}
- rb_erase(&req->r_node, &mdsc->request_tree);
- RB_CLEAR_NODE(&req->r_node);
+ erase_request(&mdsc->request_tree, req);
if (req->r_unsafe_dir && req->r_got_unsafe) {
struct ceph_inode_info *ci = ceph_inode(req->r_unsafe_dir);
@@ -868,12 +842,14 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
int metadata_bytes = 0;
int metadata_key_count = 0;
struct ceph_options *opt = mdsc->fsc->client->options;
+ struct ceph_mount_options *fsopt = mdsc->fsc->mount_options;
void *p;
const char* metadata[][2] = {
{"hostname", utsname()->nodename},
{"kernel_version", utsname()->release},
- {"entity_id", opt->name ? opt->name : ""},
+ {"entity_id", opt->name ? : ""},
+ {"root", fsopt->server_path ? : "/"},
{NULL, NULL}
};
@@ -1149,9 +1125,11 @@ out:
static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
void *arg)
{
+ struct ceph_fs_client *fsc = (struct ceph_fs_client *)arg;
struct ceph_inode_info *ci = ceph_inode(inode);
LIST_HEAD(to_remove);
- int drop = 0;
+ bool drop = false;
+ bool invalidate = false;
dout("removing cap %p, ci is %p, inode is %p\n",
cap, ci, &ci->vfs_inode);
@@ -1159,8 +1137,13 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
__ceph_remove_cap(cap, false);
if (!ci->i_auth_cap) {
struct ceph_cap_flush *cf;
- struct ceph_mds_client *mdsc =
- ceph_sb_to_client(inode->i_sb)->mdsc;
+ struct ceph_mds_client *mdsc = fsc->mdsc;
+
+ ci->i_ceph_flags |= CEPH_I_CAP_DROPPED;
+
+ if (ci->i_wrbuffer_ref > 0 &&
+ ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
+ invalidate = true;
while (true) {
struct rb_node *n = rb_first(&ci->i_cap_flush_tree);
@@ -1183,7 +1166,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
inode, ceph_ino(inode));
ci->i_dirty_caps = 0;
list_del_init(&ci->i_dirty_item);
- drop = 1;
+ drop = true;
}
if (!list_empty(&ci->i_flushing_item)) {
pr_warn_ratelimited(
@@ -1193,7 +1176,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
ci->i_flushing_caps = 0;
list_del_init(&ci->i_flushing_item);
mdsc->num_cap_flushing--;
- drop = 1;
+ drop = true;
}
spin_unlock(&mdsc->cap_dirty_lock);
@@ -1210,7 +1193,11 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
list_del(&cf->list);
ceph_free_cap_flush(cf);
}
- while (drop--)
+
+ wake_up_all(&ci->i_cap_wq);
+ if (invalidate)
+ ceph_queue_invalidate(inode);
+ if (drop)
iput(inode);
return 0;
}
@@ -1220,12 +1207,13 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
*/
static void remove_session_caps(struct ceph_mds_session *session)
{
+ struct ceph_fs_client *fsc = session->s_mdsc->fsc;
+ struct super_block *sb = fsc->sb;
dout("remove_session_caps on %p\n", session);
- iterate_session_caps(session, remove_session_caps_cb, NULL);
+ iterate_session_caps(session, remove_session_caps_cb, fsc);
spin_lock(&session->s_cap_lock);
if (session->s_nr_caps > 0) {
- struct super_block *sb = session->s_mdsc->fsc->sb;
struct inode *inode;
struct ceph_cap *cap, *prev = NULL;
struct ceph_vino vino;
@@ -1270,13 +1258,13 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap,
{
struct ceph_inode_info *ci = ceph_inode(inode);
- wake_up_all(&ci->i_cap_wq);
if (arg) {
spin_lock(&ci->i_ceph_lock);
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
spin_unlock(&ci->i_ceph_lock);
}
+ wake_up_all(&ci->i_cap_wq);
return 0;
}
@@ -1671,8 +1659,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options;
- size_t size = sizeof(*rinfo->dir_in) + sizeof(*rinfo->dir_dname_len) +
- sizeof(*rinfo->dir_dname) + sizeof(*rinfo->dir_dlease);
+ size_t size = sizeof(struct ceph_mds_reply_dir_entry);
int order, num_entries;
spin_lock(&ci->i_ceph_lock);
@@ -1683,14 +1670,14 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
order = get_order(size * num_entries);
while (order >= 0) {
- rinfo->dir_in = (void*)__get_free_pages(GFP_KERNEL |
- __GFP_NOWARN,
- order);
- if (rinfo->dir_in)
+ rinfo->dir_entries = (void*)__get_free_pages(GFP_KERNEL |
+ __GFP_NOWARN,
+ order);
+ if (rinfo->dir_entries)
break;
order--;
}
- if (!rinfo->dir_in)
+ if (!rinfo->dir_entries)
return -ENOMEM;
num_entries = (PAGE_SIZE << order) / size;
@@ -1722,6 +1709,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
INIT_LIST_HEAD(&req->r_unsafe_target_item);
req->r_fmode = -1;
kref_init(&req->r_kref);
+ RB_CLEAR_NODE(&req->r_node);
INIT_LIST_HEAD(&req->r_wait);
init_completion(&req->r_completion);
init_completion(&req->r_safe_completion);
@@ -2414,7 +2402,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
/* get request, session */
tid = le64_to_cpu(msg->hdr.tid);
mutex_lock(&mdsc->mutex);
- req = __lookup_request(mdsc, tid);
+ req = lookup_get_request(mdsc, tid);
if (!req) {
dout("handle_reply on unknown tid %llu\n", tid);
mutex_unlock(&mdsc->mutex);
@@ -2604,7 +2592,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
fwd_seq = ceph_decode_32(&p);
mutex_lock(&mdsc->mutex);
- req = __lookup_request(mdsc, tid);
+ req = lookup_get_request(mdsc, tid);
if (!req) {
dout("forward tid %llu to mds%d - req dne\n", tid, next_mds);
goto out; /* dup reply? */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index ee69a537dba5..e7d38aac7109 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -47,6 +47,14 @@ struct ceph_mds_reply_info_in {
u32 pool_ns_len;
};
+struct ceph_mds_reply_dir_entry {
+ char *name;
+ u32 name_len;
+ struct ceph_mds_reply_lease *lease;
+ struct ceph_mds_reply_info_in inode;
+ loff_t offset;
+};
+
/*
* parsed info about an mds reply, including information about
* either: 1) the target inode and/or its parent directory and dentry,
@@ -73,11 +81,10 @@ struct ceph_mds_reply_info_parsed {
struct ceph_mds_reply_dirfrag *dir_dir;
size_t dir_buf_size;
int dir_nr;
- char **dir_dname;
- u32 *dir_dname_len;
- struct ceph_mds_reply_lease **dir_dlease;
- struct ceph_mds_reply_info_in *dir_in;
- u8 dir_complete, dir_end;
+ bool dir_complete;
+ bool dir_end;
+ bool hash_order;
+ struct ceph_mds_reply_dir_entry *dir_entries;
};
/* for create results */
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 261531e55e9d..8c3591a7fbae 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -54,16 +54,21 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
const void *start = *p;
int i, j, n;
int err = -EINVAL;
- u16 version;
+ u8 mdsmap_v, mdsmap_cv;
m = kzalloc(sizeof(*m), GFP_NOFS);
if (m == NULL)
return ERR_PTR(-ENOMEM);
- ceph_decode_16_safe(p, end, version, bad);
- if (version > 3) {
- pr_warn("got mdsmap version %d > 3, failing", version);
- goto bad;
+ ceph_decode_need(p, end, 1 + 1, bad);
+ mdsmap_v = ceph_decode_8(p);
+ mdsmap_cv = ceph_decode_8(p);
+ if (mdsmap_v >= 4) {
+ u32 mdsmap_len;
+ ceph_decode_32_safe(p, end, mdsmap_len, bad);
+ if (end < *p + mdsmap_len)
+ goto bad;
+ end = *p + mdsmap_len;
}
ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad);
@@ -87,16 +92,29 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
u32 namelen;
s32 mds, inc, state;
u64 state_seq;
- u8 infoversion;
+ u8 info_v;
+ void *info_end = NULL;
struct ceph_entity_addr addr;
u32 num_export_targets;
void *pexport_targets = NULL;
struct ceph_timespec laggy_since;
struct ceph_mds_info *info;
- ceph_decode_need(p, end, sizeof(u64)*2 + 1 + sizeof(u32), bad);
+ ceph_decode_need(p, end, sizeof(u64) + 1, bad);
global_id = ceph_decode_64(p);
- infoversion = ceph_decode_8(p);
+ info_v= ceph_decode_8(p);
+ if (info_v >= 4) {
+ u32 info_len;
+ u8 info_cv;
+ ceph_decode_need(p, end, 1 + sizeof(u32), bad);
+ info_cv = ceph_decode_8(p);
+ info_len = ceph_decode_32(p);
+ info_end = *p + info_len;
+ if (info_end > end)
+ goto bad;
+ }
+
+ ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
*p += sizeof(u64);
namelen = ceph_decode_32(p); /* skip mds name */
*p += namelen;
@@ -115,7 +133,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
*p += sizeof(u32);
ceph_decode_32_safe(p, end, namelen, bad);
*p += namelen;
- if (infoversion >= 2) {
+ if (info_v >= 2) {
ceph_decode_32_safe(p, end, num_export_targets, bad);
pexport_targets = *p;
*p += num_export_targets * sizeof(u32);
@@ -123,6 +141,12 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
num_export_targets = 0;
}
+ if (info_end && *p != info_end) {
+ if (*p > info_end)
+ goto bad;
+ *p = info_end;
+ }
+
dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n",
i+1, n, global_id, mds, inc,
ceph_pr_addr(&addr.in_addr),
@@ -163,6 +187,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
m->m_cas_pg_pool = ceph_decode_64(p);
/* ok, we don't care about the rest. */
+ *p = end;
dout("mdsmap_decode success epoch %u\n", m->m_epoch);
return m;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index f12d5e2955c2..91e02481ce06 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -108,6 +108,7 @@ static int ceph_sync_fs(struct super_block *sb, int wait)
* mount options
*/
enum {
+ Opt_mds_namespace,
Opt_wsize,
Opt_rsize,
Opt_rasize,
@@ -143,6 +144,7 @@ enum {
};
static match_table_t fsopt_tokens = {
+ {Opt_mds_namespace, "mds_namespace=%d"},
{Opt_wsize, "wsize=%d"},
{Opt_rsize, "rsize=%d"},
{Opt_rasize, "rasize=%d"},
@@ -212,6 +214,9 @@ static int parse_fsopt_token(char *c, void *private)
break;
/* misc */
+ case Opt_mds_namespace:
+ fsopt->mds_namespace = intval;
+ break;
case Opt_wsize:
fsopt->wsize = intval;
break;
@@ -297,6 +302,7 @@ static void destroy_mount_options(struct ceph_mount_options *args)
{
dout("destroy_mount_options %p\n", args);
kfree(args->snapdir_name);
+ kfree(args->server_path);
kfree(args);
}
@@ -328,14 +334,17 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
if (ret)
return ret;
+ ret = strcmp_null(fsopt1->server_path, fsopt2->server_path);
+ if (ret)
+ return ret;
+
return ceph_compare_options(new_opt, fsc->client);
}
static int parse_mount_options(struct ceph_mount_options **pfsopt,
struct ceph_options **popt,
int flags, char *options,
- const char *dev_name,
- const char **path)
+ const char *dev_name)
{
struct ceph_mount_options *fsopt;
const char *dev_name_end;
@@ -367,6 +376,7 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
fsopt->congestion_kb = default_congestion_kb();
+ fsopt->mds_namespace = CEPH_FS_CLUSTER_ID_NONE;
/*
* Distinguish the server list from the path in "dev_name".
@@ -380,12 +390,13 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
*/
dev_name_end = strchr(dev_name, '/');
if (dev_name_end) {
- /* skip over leading '/' for path */
- *path = dev_name_end + 1;
+ fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
+ if (!fsopt->server_path) {
+ err = -ENOMEM;
+ goto out;
+ }
} else {
- /* path is empty */
dev_name_end = dev_name + strlen(dev_name);
- *path = dev_name_end;
}
err = -EINVAL;
dev_name_end--; /* back up to ':' separator */
@@ -395,7 +406,8 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
goto out;
}
dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
- dout("server path '%s'\n", *path);
+ if (fsopt->server_path)
+ dout("server path '%s'\n", fsopt->server_path);
*popt = ceph_parse_options(options, dev_name, dev_name_end,
parse_fsopt_token, (void *)fsopt);
@@ -457,6 +469,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",noacl");
#endif
+ if (fsopt->mds_namespace != CEPH_FS_CLUSTER_ID_NONE)
+ seq_printf(m, ",mds_namespace=%d", fsopt->mds_namespace);
if (fsopt->wsize)
seq_printf(m, ",wsize=%d", fsopt->wsize);
if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -511,9 +525,8 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
{
struct ceph_fs_client *fsc;
const u64 supported_features =
- CEPH_FEATURE_FLOCK |
- CEPH_FEATURE_DIRLAYOUTHASH |
- CEPH_FEATURE_MDS_INLINE_DATA;
+ CEPH_FEATURE_FLOCK | CEPH_FEATURE_DIRLAYOUTHASH |
+ CEPH_FEATURE_MDSENC | CEPH_FEATURE_MDS_INLINE_DATA;
const u64 required_features = 0;
int page_count;
size_t size;
@@ -530,6 +543,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
goto fail;
}
fsc->client->extra_mon_dispatch = extra_mon_dispatch;
+ fsc->client->monc.fs_cluster_id = fsopt->mds_namespace;
ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true);
fsc->mount_options = fsopt;
@@ -785,8 +799,7 @@ out:
/*
* mount: join the ceph cluster, and open root directory.
*/
-static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
- const char *path)
+static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
{
int err;
unsigned long started = jiffies; /* note the start time */
@@ -815,11 +828,12 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
goto fail;
}
- if (path[0] == 0) {
+ if (!fsc->mount_options->server_path) {
root = fsc->sb->s_root;
dget(root);
} else {
- dout("mount opening base mountpoint\n");
+ const char *path = fsc->mount_options->server_path + 1;
+ dout("mount opening path %s\n", path);
root = open_root_dentry(fsc, path, started);
if (IS_ERR(root)) {
err = PTR_ERR(root);
@@ -935,7 +949,6 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
struct dentry *res;
int err;
int (*compare_super)(struct super_block *, void *) = ceph_compare_super;
- const char *path = NULL;
struct ceph_mount_options *fsopt = NULL;
struct ceph_options *opt = NULL;
@@ -944,7 +957,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
#ifdef CONFIG_CEPH_FS_POSIX_ACL
flags |= MS_POSIXACL;
#endif
- err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
+ err = parse_mount_options(&fsopt, &opt, flags, data, dev_name);
if (err < 0) {
res = ERR_PTR(err);
goto out_final;
@@ -987,7 +1000,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
}
}
- res = ceph_real_mount(fsc, path);
+ res = ceph_real_mount(fsc);
if (IS_ERR(res))
goto out_splat;
dout("root %p inode %p ino %llx.%llx\n", res,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 7b99eb756477..0168b49fb6ad 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -62,6 +62,7 @@ struct ceph_mount_options {
int cap_release_safety;
int max_readdir; /* max readdir result (entires) */
int max_readdir_bytes; /* max readdir result (bytes) */
+ int mds_namespace;
/*
* everything above this point can be memcmp'd; everything below
@@ -69,6 +70,7 @@ struct ceph_mount_options {
*/
char *snapdir_name; /* default ".snap" */
+ char *server_path; /* default "/" */
};
struct ceph_fs_client {
@@ -101,7 +103,6 @@ struct ceph_fs_client {
#ifdef CONFIG_CEPH_FSCACHE
struct fscache_cookie *fscache;
- struct workqueue_struct *revalidate_wq;
#endif
};
@@ -295,6 +296,7 @@ struct ceph_inode_info {
u64 i_files, i_subdirs;
struct rb_root i_fragtree;
+ int i_fragtree_nsplits;
struct mutex i_fragtree_mutex;
struct ceph_inode_xattrs_info i_xattrs;
@@ -357,8 +359,7 @@ struct ceph_inode_info {
#ifdef CONFIG_CEPH_FSCACHE
struct fscache_cookie *fscache;
- u32 i_fscache_gen; /* sequence, for delayed fscache validate */
- struct work_struct i_revalidate_work;
+ u32 i_fscache_gen;
#endif
struct inode vfs_inode; /* at end */
};
@@ -469,6 +470,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
#define CEPH_I_POOL_RD (1 << 5) /* can read from pool */
#define CEPH_I_POOL_WR (1 << 6) /* can write to pool */
#define CEPH_I_SEC_INITED (1 << 7) /* security initialized */
+#define CEPH_I_CAP_DROPPED (1 << 8) /* caps were forcibly dropped */
static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
long long release_count,
@@ -537,11 +539,6 @@ static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry)
return (struct ceph_dentry_info *)dentry->d_fsdata;
}
-static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
-{
- return ((loff_t)frag << 32) | (loff_t)off;
-}
-
/*
* caps helpers
*/
@@ -632,7 +629,6 @@ struct ceph_file_info {
struct ceph_mds_request *last_readdir;
/* readdir: position within a frag */
- unsigned offset; /* offset of last chunk, adjusted for . and .. */
unsigned next_offset; /* offset of next chunk (last_name's + 1) */
char *last_name; /* last entry in previous chunk */
long long dir_release_count;
@@ -927,6 +923,7 @@ extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
/* file.c */
extern const struct file_operations ceph_file_fops;
+extern int ceph_renew_caps(struct inode *inode);
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode,
@@ -942,6 +939,7 @@ extern const struct inode_operations ceph_snapdir_iops;
extern const struct dentry_operations ceph_dentry_ops, ceph_snap_dentry_ops,
ceph_snapdir_dentry_ops;
+extern loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order);
extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
extern int ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *dentry, int err);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 0d66722c6a52..4870b29df224 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -77,7 +77,7 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
char buf[128];
dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
- down_read(&osdc->map_sem);
+ down_read(&osdc->lock);
pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
if (pool_name) {
size_t len = strlen(pool_name);
@@ -109,7 +109,7 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
ret = -ERANGE;
}
}
- up_read(&osdc->map_sem);
+ up_read(&osdc->lock);
return ret;
}
@@ -143,13 +143,13 @@ static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
const char *pool_name;
- down_read(&osdc->map_sem);
+ down_read(&osdc->lock);
pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
if (pool_name)
ret = snprintf(val, size, "%s", pool_name);
else
ret = snprintf(val, size, "%lld", (unsigned long long)pool);
- up_read(&osdc->map_sem);
+ up_read(&osdc->lock);
return ret;
}
@@ -862,6 +862,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_pagelist *pagelist = NULL;
+ int op = CEPH_MDS_OP_SETXATTR;
int err;
if (size > 0) {
@@ -875,20 +876,21 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
if (err)
goto out;
} else if (!value) {
- flags |= CEPH_XATTR_REMOVE;
+ if (flags & CEPH_XATTR_REPLACE)
+ op = CEPH_MDS_OP_RMXATTR;
+ else
+ flags |= CEPH_XATTR_REMOVE;
}
dout("setxattr value=%.*s\n", (int)size, value);
/* do request */
- req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
- USE_AUTH_MDS);
+ req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
- req->r_args.setxattr.flags = cpu_to_le32(flags);
req->r_path2 = kstrdup(name, GFP_NOFS);
if (!req->r_path2) {
ceph_mdsc_put_request(req);
@@ -896,8 +898,11 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
goto out;
}
- req->r_pagelist = pagelist;
- pagelist = NULL;
+ if (op == CEPH_MDS_OP_SETXATTR) {
+ req->r_args.setxattr.flags = cpu_to_le32(flags);
+ req->r_pagelist = pagelist;
+ pagelist = NULL;
+ }
req->r_inode = inode;
ihold(inode);
@@ -1051,12 +1056,13 @@ static int ceph_get_xattr_handler(const struct xattr_handler *handler,
}
static int ceph_set_xattr_handler(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
- return __ceph_setxattr(d_inode(dentry), name, value, size, flags);
+ return __ceph_setxattr(inode, name, value, size, flags);
}
const struct xattr_handler ceph_other_xattr_handler = {
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 5a53ac6b1e02..02b071bf3732 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -101,6 +101,12 @@ convert_sfm_char(const __u16 src_char, char *target)
case SFM_SLASH:
*target = '\\';
break;
+ case SFM_SPACE:
+ *target = ' ';
+ break;
+ case SFM_PERIOD:
+ *target = '.';
+ break;
default:
return false;
}
@@ -404,7 +410,7 @@ static __le16 convert_to_sfu_char(char src_char)
return dest_char;
}
-static __le16 convert_to_sfm_char(char src_char)
+static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
{
__le16 dest_char;
@@ -427,6 +433,18 @@ static __le16 convert_to_sfm_char(char src_char)
case '|':
dest_char = cpu_to_le16(SFM_PIPE);
break;
+ case '.':
+ if (end_of_string)
+ dest_char = cpu_to_le16(SFM_PERIOD);
+ else
+ dest_char = 0;
+ break;
+ case ' ':
+ if (end_of_string)
+ dest_char = cpu_to_le16(SFM_SPACE);
+ else
+ dest_char = 0;
+ break;
default:
dest_char = 0;
}
@@ -469,9 +487,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
/* see if we must remap this char */
if (map_chars == SFU_MAP_UNI_RSVD)
dst_char = convert_to_sfu_char(src_char);
- else if (map_chars == SFM_MAP_UNI_RSVD)
- dst_char = convert_to_sfm_char(src_char);
- else
+ else if (map_chars == SFM_MAP_UNI_RSVD) {
+ bool end_of_string;
+
+ if (i == srclen - 1)
+ end_of_string = true;
+ else
+ end_of_string = false;
+
+ dst_char = convert_to_sfm_char(src_char, end_of_string);
+ } else
dst_char = 0;
/*
* FIXME: We can not handle remapping backslash (UNI_SLASH)
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index bdc52cb9a676..479bc0a941f3 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -64,6 +64,8 @@
#define SFM_LESSTHAN ((__u16) 0xF023)
#define SFM_PIPE ((__u16) 0xF027)
#define SFM_SLASH ((__u16) 0xF026)
+#define SFM_PERIOD ((__u16) 0xF028)
+#define SFM_SPACE ((__u16) 0xF029)
/*
* Mapping mechanism to use when one of the seven reserved characters is
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5d8b7edf8a8f..5d841f39c4b7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -87,6 +87,7 @@ extern mempool_t *cifs_req_poolp;
extern mempool_t *cifs_mid_poolp;
struct workqueue_struct *cifsiod_wq;
+__u32 cifs_lock_secret;
/*
* Bumps refcount for cifs super block.
@@ -1266,6 +1267,8 @@ init_cifs(void)
spin_lock_init(&cifs_file_list_lock);
spin_lock_init(&GlobalMid_Lock);
+ get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret));
+
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index bba106cdc43c..8f1d8c1e72be 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1619,6 +1619,7 @@ void cifs_oplock_break(struct work_struct *work);
extern const struct slow_work_ops cifs_oplock_break_ops;
extern struct workqueue_struct *cifsiod_wq;
+extern __u32 cifs_lock_secret;
extern mempool_t *cifs_mid_poolp;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 66736f57b5ab..7d2b15c06090 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -428,7 +428,9 @@ cifs_echo_request(struct work_struct *work)
* server->ops->need_neg() == true. Also, no need to ping if
* we got a response recently.
*/
- if (!server->ops->need_neg || server->ops->need_neg(server) ||
+
+ if (server->tcpStatus == CifsNeedReconnect ||
+ server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
(server->ops->can_echo && !server->ops->can_echo(server)) ||
time_before(jiffies, server->lstrp + echo_interval - HZ))
goto requeue_echo;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9793ae0bcaa2..d4890b6dc22d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1112,6 +1112,12 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
return rc;
}
+static __u32
+hash_lockowner(fl_owner_t owner)
+{
+ return cifs_lock_secret ^ hash32_ptr((const void *)owner);
+}
+
struct lock_to_push {
struct list_head llist;
__u64 offset;
@@ -1178,7 +1184,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
else
type = CIFS_WRLCK;
lck = list_entry(el, struct lock_to_push, llist);
- lck->pid = flock->fl_pid;
+ lck->pid = hash_lockowner(flock->fl_owner);
lck->netfid = cfile->fid.netfid;
lck->length = length;
lck->type = type;
@@ -1305,7 +1311,8 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
posix_lock_type = CIFS_RDLCK;
else
posix_lock_type = CIFS_WRLCK;
- rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid,
+ rc = CIFSSMBPosixLock(xid, tcon, netfid,
+ hash_lockowner(flock->fl_owner),
flock->fl_start, length, flock,
posix_lock_type, wait_flag);
return rc;
@@ -1505,7 +1512,8 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
posix_lock_type = CIFS_UNLCK;
rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid,
- current->tgid, flock->fl_start, length,
+ hash_lockowner(flock->fl_owner),
+ flock->fl_start, length,
NULL, posix_lock_type, wait_flag);
goto out;
}
diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h
index 848249fa120f..3079b38f0afb 100644
--- a/fs/cifs/ntlmssp.h
+++ b/fs/cifs/ntlmssp.h
@@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE {
int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses);
void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses);
-int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen,
+int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
struct cifs_ses *ses,
const struct nls_table *nls_cp);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index af0ec2d5ad0e..538d9b55699a 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
sec_blob->DomainName.MaximumLength = 0;
}
-/* We do not malloc the blob, it is passed in pbuffer, because its
- maximum possible size is fixed and small, making this approach cleaner.
- This function returns the length of the data in the blob */
-int build_ntlmssp_auth_blob(unsigned char *pbuffer,
+static int size_of_ntlmssp_blob(struct cifs_ses *ses)
+{
+ int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len
+ - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
+
+ if (ses->domainName)
+ sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ else
+ sz += 2;
+
+ if (ses->user_name)
+ sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+ else
+ sz += 2;
+
+ return sz;
+}
+
+int build_ntlmssp_auth_blob(unsigned char **pbuffer,
u16 *buflen,
struct cifs_ses *ses,
const struct nls_table *nls_cp)
{
int rc;
- AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer;
+ AUTHENTICATE_MESSAGE *sec_blob;
__u32 flags;
unsigned char *tmp;
+ rc = setup_ntlmv2_rsp(ses, nls_cp);
+ if (rc) {
+ cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
+ *buflen = 0;
+ goto setup_ntlmv2_ret;
+ }
+ *pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL);
+ sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer;
+
memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
sec_blob->MessageType = NtLmAuthenticate;
@@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
}
- tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
+ tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
sec_blob->NegotiateFlags = cpu_to_le32(flags);
sec_blob->LmChallengeResponse.BufferOffset =
@@ -399,13 +423,9 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
sec_blob->LmChallengeResponse.Length = 0;
sec_blob->LmChallengeResponse.MaximumLength = 0;
- sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->NtChallengeResponse.BufferOffset =
+ cpu_to_le32(tmp - *pbuffer);
if (ses->user_name != NULL) {
- rc = setup_ntlmv2_rsp(ses, nls_cp);
- if (rc) {
- cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
- goto setup_ntlmv2_ret;
- }
memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
ses->auth_key.len - CIFS_SESS_KEY_SIZE);
tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
@@ -423,23 +443,23 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
}
if (ses->domainName == NULL) {
- sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->DomainName.Length = 0;
sec_blob->DomainName.MaximumLength = 0;
tmp += 2;
} else {
int len;
len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
- CIFS_MAX_USERNAME_LEN, nls_cp);
+ CIFS_MAX_DOMAINNAME_LEN, nls_cp);
len *= 2; /* unicode is 2 bytes each */
- sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->DomainName.Length = cpu_to_le16(len);
sec_blob->DomainName.MaximumLength = cpu_to_le16(len);
tmp += len;
}
if (ses->user_name == NULL) {
- sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->UserName.Length = 0;
sec_blob->UserName.MaximumLength = 0;
tmp += 2;
@@ -448,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
CIFS_MAX_USERNAME_LEN, nls_cp);
len *= 2; /* unicode is 2 bytes each */
- sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->UserName.Length = cpu_to_le16(len);
sec_blob->UserName.MaximumLength = cpu_to_le16(len);
tmp += len;
}
- sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->WorkstationName.Length = 0;
sec_blob->WorkstationName.MaximumLength = 0;
tmp += 2;
@@ -463,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
(ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
&& !calc_seckey(ses)) {
memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
- sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
sec_blob->SessionKey.MaximumLength =
cpu_to_le16(CIFS_CPHTXT_SIZE);
tmp += CIFS_CPHTXT_SIZE;
} else {
- sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->SessionKey.Length = 0;
sec_blob->SessionKey.MaximumLength = 0;
}
+ *buflen = tmp - *pbuffer;
setup_ntlmv2_ret:
- *buflen = tmp - pbuffer;
return rc;
}
@@ -690,6 +710,8 @@ sess_auth_lanman(struct sess_data *sess_data)
rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
true : false, lnm_session_key);
+ if (rc)
+ goto out;
memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
bcc_ptr += CIFS_AUTH_RESP_SIZE;
@@ -1266,7 +1288,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
struct cifs_ses *ses = sess_data->ses;
__u16 bytes_remaining;
char *bcc_ptr;
- char *ntlmsspblob = NULL;
+ unsigned char *ntlmsspblob = NULL;
u16 blob_len;
cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n");
@@ -1279,19 +1301,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
/* Build security blob before we assemble the request */
pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
smb_buf = (struct smb_hdr *)pSMB;
- /*
- * 5 is an empirical value, large enough to hold
- * authenticate message plus max 10 of av paris,
- * domain, user, workstation names, flags, etc.
- */
- ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE),
- GFP_KERNEL);
- if (!ntlmsspblob) {
- rc = -ENOMEM;
- goto out;
- }
-
- rc = build_ntlmssp_auth_blob(ntlmsspblob,
+ rc = build_ntlmssp_auth_blob(&ntlmsspblob,
&blob_len, ses, sess_data->nls_cp);
if (rc)
goto out_free_ntlmsspblob;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 8f38e33d365b..29e06db5f187 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -588,7 +588,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
u16 blob_length = 0;
struct key *spnego_key = NULL;
char *security_blob = NULL;
- char *ntlmssp_blob = NULL;
+ unsigned char *ntlmssp_blob = NULL;
bool use_spnego = false; /* else use raw ntlmssp */
cifs_dbg(FYI, "Session Setup\n");
@@ -713,13 +713,7 @@ ssetup_ntlmssp_authenticate:
iov[1].iov_len = blob_length;
} else if (phase == NtLmAuthenticate) {
req->hdr.SessionId = ses->Suid;
- ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
- GFP_KERNEL);
- if (ntlmssp_blob == NULL) {
- rc = -ENOMEM;
- goto ssetup_exit;
- }
- rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses,
+ rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
nls_cp);
if (rc) {
cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n",
@@ -1818,6 +1812,33 @@ SMB2_echo(struct TCP_Server_Info *server)
cifs_dbg(FYI, "In echo request\n");
+ if (server->tcpStatus == CifsNeedNegotiate) {
+ struct list_head *tmp, *tmp2;
+ struct cifs_ses *ses;
+ struct cifs_tcon *tcon;
+
+ cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+ spin_lock(&cifs_tcp_ses_lock);
+ list_for_each(tmp, &server->smb_ses_list) {
+ ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+ list_for_each(tmp2, &ses->tcon_list) {
+ tcon = list_entry(tmp2, struct cifs_tcon,
+ tcon_list);
+ /* add check for persistent handle reconnect */
+ if (tcon && tcon->need_reconnect) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ rc = smb2_reconnect(SMB2_ECHO, tcon);
+ spin_lock(&cifs_tcp_ses_lock);
+ }
+ }
+ }
+ spin_unlock(&cifs_tcp_ses_lock);
+ }
+
+ /* if no session, renegotiate failed above */
+ if (server->tcpStatus == CifsNeedNegotiate)
+ return -EIO;
+
rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
if (rc)
return rc;
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index c8b77aa24a1d..5e23f64c0804 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -39,8 +39,9 @@
enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
static int cifs_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
int rc = -EOPNOTSUPP;
unsigned int xid;
@@ -99,12 +100,12 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
if (value &&
pTcon->ses->server->ops->set_acl)
rc = pTcon->ses->server->ops->set_acl(pacl,
- size, d_inode(dentry),
+ size, inode,
full_path, CIFS_ACL_DACL);
else
rc = -EOPNOTSUPP;
if (rc == 0) /* force revalidate of the inode */
- CIFS_I(d_inode(dentry))->time = 0;
+ CIFS_I(inode)->time = 0;
kfree(pacl);
}
#endif /* CONFIG_CIFS_ACL */
diff --git a/fs/compat.c b/fs/compat.c
index 8754e9aa14ad..be6e48b0a46c 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -936,6 +936,8 @@ static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
}
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
@@ -1020,6 +1022,8 @@ static int compat_filldir64(struct dir_context *ctx, const char *name,
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user_unaligned(offset, &dirent->d_off))
goto efault;
}
diff --git a/fs/coredump.c b/fs/coredump.c
index 38a7ab87e10a..281b768000e6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -794,6 +794,7 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
return 0;
file->f_pos = pos;
cprm->written += n;
+ cprm->pos += n;
nr -= n;
}
return 1;
@@ -808,6 +809,7 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
if (dump_interrupted() ||
file->f_op->llseek(file, nr, SEEK_CUR) < 0)
return 0;
+ cprm->pos += nr;
return 1;
} else {
while (nr > PAGE_SIZE) {
@@ -822,7 +824,7 @@ EXPORT_SYMBOL(dump_skip);
int dump_align(struct coredump_params *cprm, int align)
{
- unsigned mod = cprm->file->f_pos & (align - 1);
+ unsigned mod = cprm->pos & (align - 1);
if (align & (align - 1))
return 0;
return mod ? dump_skip(cprm, align - mod) : 1;
diff --git a/fs/dax.c b/fs/dax.c
index a345c168acaa..e207f8f9b700 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -32,14 +32,43 @@
#include <linux/pfn_t.h>
#include <linux/sizes.h>
-#define RADIX_DAX_MASK 0xf
-#define RADIX_DAX_SHIFT 4
-#define RADIX_DAX_PTE (0x4 | RADIX_TREE_EXCEPTIONAL_ENTRY)
-#define RADIX_DAX_PMD (0x8 | RADIX_TREE_EXCEPTIONAL_ENTRY)
-#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_MASK)
+/*
+ * We use lowest available bit in exceptional entry for locking, other two
+ * bits to determine entry type. In total 3 special bits.
+ */
+#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)
+#define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
+#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
+#define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD)
+#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_MASK)
#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT))
#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \
- RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE)))
+ RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE) | \
+ RADIX_TREE_EXCEPTIONAL_ENTRY))
+
+/* We choose 4096 entries - same as per-zone page wait tables */
+#define DAX_WAIT_TABLE_BITS 12
+#define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
+
+wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
+
+static int __init init_dax_wait_table(void)
+{
+ int i;
+
+ for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
+ init_waitqueue_head(wait_table + i);
+ return 0;
+}
+fs_initcall(init_dax_wait_table);
+
+static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
+ pgoff_t index)
+{
+ unsigned long hash = hash_long((unsigned long)mapping ^ index,
+ DAX_WAIT_TABLE_BITS);
+ return wait_table + hash;
+}
static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
{
@@ -87,50 +116,6 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
return page;
}
-/*
- * dax_clear_sectors() is called from within transaction context from XFS,
- * and hence this means the stack from this point must follow GFP_NOFS
- * semantics for all operations.
- */
-int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
-{
- struct blk_dax_ctl dax = {
- .sector = _sector,
- .size = _size,
- };
-
- might_sleep();
- do {
- long count, sz;
-
- count = dax_map_atomic(bdev, &dax);
- if (count < 0)
- return count;
- sz = min_t(long, count, SZ_128K);
- clear_pmem(dax.addr, sz);
- dax.size -= sz;
- dax.sector += sz / 512;
- dax_unmap_atomic(bdev, &dax);
- cond_resched();
- } while (dax.size);
-
- wmb_pmem();
- return 0;
-}
-EXPORT_SYMBOL_GPL(dax_clear_sectors);
-
-/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
-static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
- loff_t pos, loff_t end)
-{
- loff_t final = end - pos + first; /* The final byte of the buffer */
-
- if (first > 0)
- clear_pmem(addr, first);
- if (final < size)
- clear_pmem(addr + final, size - final);
-}
-
static bool buffer_written(struct buffer_head *bh)
{
return buffer_mapped(bh) && !buffer_unwritten(bh);
@@ -169,6 +154,9 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
struct blk_dax_ctl dax = {
.addr = (void __pmem *) ERR_PTR(-EIO),
};
+ unsigned blkbits = inode->i_blkbits;
+ sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
+ >> blkbits;
if (rw == READ)
end = min(end, i_size_read(inode));
@@ -176,7 +164,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
while (pos < end) {
size_t len;
if (pos == max) {
- unsigned blkbits = inode->i_blkbits;
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
@@ -192,6 +179,13 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
bh->b_size = 1 << blkbits;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
+ /*
+ * We allow uninitialized buffers for writes
+ * beyond EOF as those cannot race with faults
+ */
+ WARN_ON_ONCE(
+ (buffer_new(bh) && block < file_blks) ||
+ (rw == WRITE && buffer_unwritten(bh)));
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
@@ -211,15 +205,15 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
rc = map_len;
break;
}
- if (buffer_unwritten(bh) || buffer_new(bh)) {
- dax_new_buf(dax.addr, map_len, first,
- pos, end);
- need_wmb = true;
- }
dax.addr += first;
size = map_len - first;
}
- max = min(pos + size, end);
+ /*
+ * pos + size is one past the last offset for IO,
+ * so pos + size can overflow loff_t at extreme offsets.
+ * Cast to u64 to catch this and get the true minimum.
+ */
+ max = min_t(u64, pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
@@ -276,15 +270,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
- if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
- struct address_space *mapping = inode->i_mapping;
+ if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_lock(inode);
- retval = filemap_write_and_wait_range(mapping, pos, end - 1);
- if (retval) {
- inode_unlock(inode);
- goto out;
- }
- }
/* Protects against truncate */
if (!(flags & DIO_SKIP_DIO_COUNT))
@@ -305,12 +292,268 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
- out:
return retval;
}
EXPORT_SYMBOL_GPL(dax_do_io);
/*
+ * DAX radix tree locking
+ */
+struct exceptional_entry_key {
+ struct address_space *mapping;
+ unsigned long index;
+};
+
+struct wait_exceptional_entry_queue {
+ wait_queue_t wait;
+ struct exceptional_entry_key key;
+};
+
+static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
+ int sync, void *keyp)
+{
+ struct exceptional_entry_key *key = keyp;
+ struct wait_exceptional_entry_queue *ewait =
+ container_of(wait, struct wait_exceptional_entry_queue, wait);
+
+ if (key->mapping != ewait->key.mapping ||
+ key->index != ewait->key.index)
+ return 0;
+ return autoremove_wake_function(wait, mode, sync, NULL);
+}
+
+/*
+ * Check whether the given slot is locked. The function must be called with
+ * mapping->tree_lock held
+ */
+static inline int slot_locked(struct address_space *mapping, void **slot)
+{
+ unsigned long entry = (unsigned long)
+ radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ return entry & RADIX_DAX_ENTRY_LOCK;
+}
+
+/*
+ * Mark the given slot is locked. The function must be called with
+ * mapping->tree_lock held
+ */
+static inline void *lock_slot(struct address_space *mapping, void **slot)
+{
+ unsigned long entry = (unsigned long)
+ radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+
+ entry |= RADIX_DAX_ENTRY_LOCK;
+ radix_tree_replace_slot(slot, (void *)entry);
+ return (void *)entry;
+}
+
+/*
+ * Mark the given slot is unlocked. The function must be called with
+ * mapping->tree_lock held
+ */
+static inline void *unlock_slot(struct address_space *mapping, void **slot)
+{
+ unsigned long entry = (unsigned long)
+ radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+
+ entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
+ radix_tree_replace_slot(slot, (void *)entry);
+ return (void *)entry;
+}
+
+/*
+ * Lookup entry in radix tree, wait for it to become unlocked if it is
+ * exceptional entry and return it. The caller must call
+ * put_unlocked_mapping_entry() when he decided not to lock the entry or
+ * put_locked_mapping_entry() when he locked the entry and now wants to
+ * unlock it.
+ *
+ * The function must be called with mapping->tree_lock held.
+ */
+static void *get_unlocked_mapping_entry(struct address_space *mapping,
+ pgoff_t index, void ***slotp)
+{
+ void *ret, **slot;
+ struct wait_exceptional_entry_queue ewait;
+ wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
+
+ init_wait(&ewait.wait);
+ ewait.wait.func = wake_exceptional_entry_func;
+ ewait.key.mapping = mapping;
+ ewait.key.index = index;
+
+ for (;;) {
+ ret = __radix_tree_lookup(&mapping->page_tree, index, NULL,
+ &slot);
+ if (!ret || !radix_tree_exceptional_entry(ret) ||
+ !slot_locked(mapping, slot)) {
+ if (slotp)
+ *slotp = slot;
+ return ret;
+ }
+ prepare_to_wait_exclusive(wq, &ewait.wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock_irq(&mapping->tree_lock);
+ schedule();
+ finish_wait(wq, &ewait.wait);
+ spin_lock_irq(&mapping->tree_lock);
+ }
+}
+
+/*
+ * Find radix tree entry at given index. If it points to a page, return with
+ * the page locked. If it points to the exceptional entry, return with the
+ * radix tree entry locked. If the radix tree doesn't contain given index,
+ * create empty exceptional entry for the index and return with it locked.
+ *
+ * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
+ * persistent memory the benefit is doubtful. We can add that later if we can
+ * show it helps.
+ */
+static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+ void *ret, **slot;
+
+restart:
+ spin_lock_irq(&mapping->tree_lock);
+ ret = get_unlocked_mapping_entry(mapping, index, &slot);
+ /* No entry for given index? Make sure radix tree is big enough. */
+ if (!ret) {
+ int err;
+
+ spin_unlock_irq(&mapping->tree_lock);
+ err = radix_tree_preload(
+ mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
+ if (err)
+ return ERR_PTR(err);
+ ret = (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+ RADIX_DAX_ENTRY_LOCK);
+ spin_lock_irq(&mapping->tree_lock);
+ err = radix_tree_insert(&mapping->page_tree, index, ret);
+ radix_tree_preload_end();
+ if (err) {
+ spin_unlock_irq(&mapping->tree_lock);
+ /* Someone already created the entry? */
+ if (err == -EEXIST)
+ goto restart;
+ return ERR_PTR(err);
+ }
+ /* Good, we have inserted empty locked entry into the tree. */
+ mapping->nrexceptional++;
+ spin_unlock_irq(&mapping->tree_lock);
+ return ret;
+ }
+ /* Normal page in radix tree? */
+ if (!radix_tree_exceptional_entry(ret)) {
+ struct page *page = ret;
+
+ get_page(page);
+ spin_unlock_irq(&mapping->tree_lock);
+ lock_page(page);
+ /* Page got truncated? Retry... */
+ if (unlikely(page->mapping != mapping)) {
+ unlock_page(page);
+ put_page(page);
+ goto restart;
+ }
+ return page;
+ }
+ ret = lock_slot(mapping, slot);
+ spin_unlock_irq(&mapping->tree_lock);
+ return ret;
+}
+
+void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+ pgoff_t index, bool wake_all)
+{
+ wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
+
+ /*
+ * Checking for locked entry and prepare_to_wait_exclusive() happens
+ * under mapping->tree_lock, ditto for entry handling in our callers.
+ * So at this point all tasks that could have seen our entry locked
+ * must be in the waitqueue and the following check will see them.
+ */
+ if (waitqueue_active(wq)) {
+ struct exceptional_entry_key key;
+
+ key.mapping = mapping;
+ key.index = index;
+ __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
+ }
+}
+
+void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+ void *ret, **slot;
+
+ spin_lock_irq(&mapping->tree_lock);
+ ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
+ if (WARN_ON_ONCE(!ret || !radix_tree_exceptional_entry(ret) ||
+ !slot_locked(mapping, slot))) {
+ spin_unlock_irq(&mapping->tree_lock);
+ return;
+ }
+ unlock_slot(mapping, slot);
+ spin_unlock_irq(&mapping->tree_lock);
+ dax_wake_mapping_entry_waiter(mapping, index, false);
+}
+
+static void put_locked_mapping_entry(struct address_space *mapping,
+ pgoff_t index, void *entry)
+{
+ if (!radix_tree_exceptional_entry(entry)) {
+ unlock_page(entry);
+ put_page(entry);
+ } else {
+ dax_unlock_mapping_entry(mapping, index);
+ }
+}
+
+/*
+ * Called when we are done with radix tree entry we looked up via
+ * get_unlocked_mapping_entry() and which we didn't lock in the end.
+ */
+static void put_unlocked_mapping_entry(struct address_space *mapping,
+ pgoff_t index, void *entry)
+{
+ if (!radix_tree_exceptional_entry(entry))
+ return;
+
+ /* We have to wake up next waiter for the radix tree entry lock */
+ dax_wake_mapping_entry_waiter(mapping, index, false);
+}
+
+/*
+ * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
+ * entry to get unlocked before deleting it.
+ */
+int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+ void *entry;
+
+ spin_lock_irq(&mapping->tree_lock);
+ entry = get_unlocked_mapping_entry(mapping, index, NULL);
+ /*
+ * This gets called from truncate / punch_hole path. As such, the caller
+ * must hold locks protecting against concurrent modifications of the
+ * radix tree (usually fs-private i_mmap_sem for writing). Since the
+ * caller has seen exceptional entry for this index, we better find it
+ * at that index as well...
+ */
+ if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
+ spin_unlock_irq(&mapping->tree_lock);
+ return 0;
+ }
+ radix_tree_delete(&mapping->page_tree, index);
+ mapping->nrexceptional--;
+ spin_unlock_irq(&mapping->tree_lock);
+ dax_wake_mapping_entry_waiter(mapping, index, true);
+
+ return 1;
+}
+
+/*
* The user has performed a load from a hole in the file. Allocating
* a new page in the file would cause excessive storage usage for
* workloads with sparse files. We allocate a page cache page instead.
@@ -318,24 +561,24 @@ EXPORT_SYMBOL_GPL(dax_do_io);
* otherwise it will simply fall out of the page cache under memory
* pressure without ever having been dirtied.
*/
-static int dax_load_hole(struct address_space *mapping, struct page *page,
- struct vm_fault *vmf)
+static int dax_load_hole(struct address_space *mapping, void *entry,
+ struct vm_fault *vmf)
{
- unsigned long size;
- struct inode *inode = mapping->host;
- if (!page)
- page = find_or_create_page(mapping, vmf->pgoff,
- GFP_KERNEL | __GFP_ZERO);
- if (!page)
- return VM_FAULT_OOM;
- /* Recheck i_size under page lock to avoid truncate race */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (vmf->pgoff >= size) {
- unlock_page(page);
- put_page(page);
- return VM_FAULT_SIGBUS;
+ struct page *page;
+
+ /* Hole page already exists? Return it... */
+ if (!radix_tree_exceptional_entry(entry)) {
+ vmf->page = entry;
+ return VM_FAULT_LOCKED;
}
+ /* This will replace locked radix tree entry with a hole page */
+ page = find_or_create_page(mapping, vmf->pgoff,
+ vmf->gfp_mask | __GFP_ZERO);
+ if (!page) {
+ put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+ return VM_FAULT_OOM;
+ }
vmf->page = page;
return VM_FAULT_LOCKED;
}
@@ -359,77 +602,72 @@ static int copy_user_bh(struct page *to, struct inode *inode,
return 0;
}
-#define NO_SECTOR -1
#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
-static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
- sector_t sector, bool pmd_entry, bool dirty)
+static void *dax_insert_mapping_entry(struct address_space *mapping,
+ struct vm_fault *vmf,
+ void *entry, sector_t sector)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
- pgoff_t pmd_index = DAX_PMD_INDEX(index);
- int type, error = 0;
- void *entry;
+ int error = 0;
+ bool hole_fill = false;
+ void *new_entry;
+ pgoff_t index = vmf->pgoff;
- WARN_ON_ONCE(pmd_entry && !dirty);
- if (dirty)
+ if (vmf->flags & FAULT_FLAG_WRITE)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- spin_lock_irq(&mapping->tree_lock);
-
- entry = radix_tree_lookup(page_tree, pmd_index);
- if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) {
- index = pmd_index;
- goto dirty;
+ /* Replacing hole page with block mapping? */
+ if (!radix_tree_exceptional_entry(entry)) {
+ hole_fill = true;
+ /*
+ * Unmap the page now before we remove it from page cache below.
+ * The page is locked so it cannot be faulted in again.
+ */
+ unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
+ PAGE_SIZE, 0);
+ error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM);
+ if (error)
+ return ERR_PTR(error);
}
- entry = radix_tree_lookup(page_tree, index);
- if (entry) {
- type = RADIX_DAX_TYPE(entry);
- if (WARN_ON_ONCE(type != RADIX_DAX_PTE &&
- type != RADIX_DAX_PMD)) {
- error = -EIO;
+ spin_lock_irq(&mapping->tree_lock);
+ new_entry = (void *)((unsigned long)RADIX_DAX_ENTRY(sector, false) |
+ RADIX_DAX_ENTRY_LOCK);
+ if (hole_fill) {
+ __delete_from_page_cache(entry, NULL);
+ /* Drop pagecache reference */
+ put_page(entry);
+ error = radix_tree_insert(page_tree, index, new_entry);
+ if (error) {
+ new_entry = ERR_PTR(error);
goto unlock;
}
+ mapping->nrexceptional++;
+ } else {
+ void **slot;
+ void *ret;
- if (!pmd_entry || type == RADIX_DAX_PMD)
- goto dirty;
-
- /*
- * We only insert dirty PMD entries into the radix tree. This
- * means we don't need to worry about removing a dirty PTE
- * entry and inserting a clean PMD entry, thus reducing the
- * range we would flush with a follow-up fsync/msync call.
- */
- radix_tree_delete(&mapping->page_tree, index);
- mapping->nrexceptional--;
- }
-
- if (sector == NO_SECTOR) {
- /*
- * This can happen during correct operation if our pfn_mkwrite
- * fault raced against a hole punch operation. If this
- * happens the pte that was hole punched will have been
- * unmapped and the radix tree entry will have been removed by
- * the time we are called, but the call will still happen. We
- * will return all the way up to wp_pfn_shared(), where the
- * pte_same() check will fail, eventually causing page fault
- * to be retried by the CPU.
- */
- goto unlock;
+ ret = __radix_tree_lookup(page_tree, index, NULL, &slot);
+ WARN_ON_ONCE(ret != entry);
+ radix_tree_replace_slot(slot, new_entry);
}
-
- error = radix_tree_insert(page_tree, index,
- RADIX_DAX_ENTRY(sector, pmd_entry));
- if (error)
- goto unlock;
-
- mapping->nrexceptional++;
- dirty:
- if (dirty)
+ if (vmf->flags & FAULT_FLAG_WRITE)
radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
unlock:
spin_unlock_irq(&mapping->tree_lock);
- return error;
+ if (hole_fill) {
+ radix_tree_preload_end();
+ /*
+ * We don't need hole page anymore, it has been replaced with
+ * locked radix tree entry now.
+ */
+ if (mapping->a_ops->freepage)
+ mapping->a_ops->freepage(entry);
+ unlock_page(entry);
+ put_page(entry);
+ }
+ return new_entry;
}
static int dax_writeback_one(struct block_device *bdev,
@@ -555,56 +793,29 @@ int dax_writeback_mapping_range(struct address_space *mapping,
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
-static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
+static int dax_insert_mapping(struct address_space *mapping,
+ struct buffer_head *bh, void **entryp,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
unsigned long vaddr = (unsigned long)vmf->virtual_address;
- struct address_space *mapping = inode->i_mapping;
struct block_device *bdev = bh->b_bdev;
struct blk_dax_ctl dax = {
- .sector = to_sector(bh, inode),
+ .sector = to_sector(bh, mapping->host),
.size = bh->b_size,
};
- pgoff_t size;
- int error;
-
- i_mmap_lock_read(mapping);
+ void *ret;
+ void *entry = *entryp;
- /*
- * Check truncate didn't happen while we were allocating a block.
- * If it did, this block may or may not be still allocated to the
- * file. We can't tell the filesystem to free it because we can't
- * take i_mutex here. In the worst case, the file still has blocks
- * allocated past the end of the file.
- */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (unlikely(vmf->pgoff >= size)) {
- error = -EIO;
- goto out;
- }
-
- if (dax_map_atomic(bdev, &dax) < 0) {
- error = PTR_ERR(dax.addr);
- goto out;
- }
-
- if (buffer_unwritten(bh) || buffer_new(bh)) {
- clear_pmem(dax.addr, PAGE_SIZE);
- wmb_pmem();
- }
+ if (dax_map_atomic(bdev, &dax) < 0)
+ return PTR_ERR(dax.addr);
dax_unmap_atomic(bdev, &dax);
- error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
- vmf->flags & FAULT_FLAG_WRITE);
- if (error)
- goto out;
+ ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector);
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
+ *entryp = ret;
- error = vm_insert_mixed(vma, vaddr, dax.pfn);
-
- out:
- i_mmap_unlock_read(mapping);
-
- return error;
+ return vm_insert_mixed(vma, vaddr, dax.pfn);
}
/**
@@ -612,24 +823,18 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
- * @complete_unwritten: The filesystem method used to convert unwritten blocks
- * to written so the data written to them is exposed. This is required for
- * required by write faults for filesystems that will return unwritten
- * extent mappings from @get_block, but it is optional for reads as
- * dax_insert_mapping() will always zero unwritten blocks. If the fs does
- * not support unwritten extents, the it should pass NULL.
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files. __dax_fault() assumes the caller has done all
* the necessary locking for the page fault to proceed successfully.
*/
int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block, dax_iodone_t complete_unwritten)
+ get_block_t get_block)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
- struct page *page;
+ void *entry;
struct buffer_head bh;
unsigned long vaddr = (unsigned long)vmf->virtual_address;
unsigned blkbits = inode->i_blkbits;
@@ -638,6 +843,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
int error;
int major = 0;
+ /*
+ * Check whether offset isn't beyond end of file now. Caller is supposed
+ * to hold locks serializing us with truncate / punch hole so this is
+ * a reliable test.
+ */
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
@@ -647,49 +857,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
- repeat:
- page = find_get_page(mapping, vmf->pgoff);
- if (page) {
- if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
- put_page(page);
- return VM_FAULT_RETRY;
- }
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- put_page(page);
- goto repeat;
- }
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (unlikely(vmf->pgoff >= size)) {
- /*
- * We have a struct page covering a hole in the file
- * from a read fault and we've raced with a truncate
- */
- error = -EIO;
- goto unlock_page;
- }
+ entry = grab_mapping_entry(mapping, vmf->pgoff);
+ if (IS_ERR(entry)) {
+ error = PTR_ERR(entry);
+ goto out;
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
- goto unlock_page;
-
- if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
- if (vmf->flags & FAULT_FLAG_WRITE) {
- error = get_block(inode, block, &bh, 1);
- count_vm_event(PGMAJFAULT);
- mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
- major = VM_FAULT_MAJOR;
- if (!error && (bh.b_size < PAGE_SIZE))
- error = -EIO;
- if (error)
- goto unlock_page;
- } else {
- return dax_load_hole(mapping, page, vmf);
- }
- }
+ goto unlock_entry;
if (vmf->cow_page) {
struct page *new_page = vmf->cow_page;
@@ -698,53 +876,35 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
else
clear_user_highpage(new_page, vaddr);
if (error)
- goto unlock_page;
- vmf->page = page;
- if (!page) {
- i_mmap_lock_read(mapping);
- /* Check we didn't race with truncate */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >>
- PAGE_SHIFT;
- if (vmf->pgoff >= size) {
- i_mmap_unlock_read(mapping);
- error = -EIO;
- goto out;
- }
+ goto unlock_entry;
+ if (!radix_tree_exceptional_entry(entry)) {
+ vmf->page = entry;
+ return VM_FAULT_LOCKED;
}
- return VM_FAULT_LOCKED;
+ vmf->entry = entry;
+ return VM_FAULT_DAX_LOCKED;
}
- /* Check we didn't race with a read fault installing a new page */
- if (!page && major)
- page = find_lock_page(mapping, vmf->pgoff);
-
- if (page) {
- unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
- PAGE_SIZE, 0);
- delete_from_page_cache(page);
- unlock_page(page);
- put_page(page);
- page = NULL;
- }
-
- /*
- * If we successfully insert the new mapping over an unwritten extent,
- * we need to ensure we convert the unwritten extent. If there is an
- * error inserting the mapping, the filesystem needs to leave it as
- * unwritten to prevent exposure of the stale underlying data to
- * userspace, but we still need to call the completion function so
- * the private resources on the mapping buffer can be released. We
- * indicate what the callback should do via the uptodate variable, same
- * as for normal BH based IO completions.
- */
- error = dax_insert_mapping(inode, &bh, vma, vmf);
- if (buffer_unwritten(&bh)) {
- if (complete_unwritten)
- complete_unwritten(&bh, !error);
- else
- WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
+ if (!buffer_mapped(&bh)) {
+ if (vmf->flags & FAULT_FLAG_WRITE) {
+ error = get_block(inode, block, &bh, 1);
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ major = VM_FAULT_MAJOR;
+ if (!error && (bh.b_size < PAGE_SIZE))
+ error = -EIO;
+ if (error)
+ goto unlock_entry;
+ } else {
+ return dax_load_hole(mapping, entry, vmf);
+ }
}
+ /* Filesystem should not return unwritten buffers to us! */
+ WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
+ error = dax_insert_mapping(mapping, &bh, &entry, vma, vmf);
+ unlock_entry:
+ put_locked_mapping_entry(mapping, vmf->pgoff, entry);
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
@@ -752,13 +912,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
if ((error < 0) && (error != -EBUSY))
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
-
- unlock_page:
- if (page) {
- unlock_page(page);
- put_page(page);
- }
- goto out;
}
EXPORT_SYMBOL(__dax_fault);
@@ -772,7 +925,7 @@ EXPORT_SYMBOL(__dax_fault);
* fault handler for DAX files.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block, dax_iodone_t complete_unwritten)
+ get_block_t get_block)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
@@ -781,7 +934,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
- result = __dax_fault(vma, vmf, get_block, complete_unwritten);
+ result = __dax_fault(vma, vmf, get_block);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
@@ -789,7 +942,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
EXPORT_SYMBOL_GPL(dax_fault);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
/*
* The 'colour' (ie low bits) within a PMD of a page offset. This comes up
* more often than one might expect in the below function.
@@ -815,8 +968,7 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd")
int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
- pmd_t *pmd, unsigned int flags, get_block_t get_block,
- dax_iodone_t complete_unwritten)
+ pmd_t *pmd, unsigned int flags, get_block_t get_block)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
@@ -828,7 +980,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
struct block_device *bdev;
pgoff_t size, pgoff;
sector_t block;
- int error, result = 0;
+ int result = 0;
bool alloc = false;
/* dax pmd mappings require pfn_t_devmap() */
@@ -875,6 +1027,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
if (get_block(inode, block, &bh, 1) != 0)
return VM_FAULT_SIGBUS;
alloc = true;
+ WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
}
bdev = bh.b_bdev;
@@ -900,26 +1053,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
truncate_pagecache_range(inode, lstart, lend);
}
- i_mmap_lock_read(mapping);
-
- /*
- * If a truncate happened while we were allocating blocks, we may
- * leave blocks allocated to the file that are beyond EOF. We can't
- * take i_mutex here, so just leave them hanging; they'll be freed
- * when the file is deleted.
- */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (pgoff >= size) {
- result = VM_FAULT_SIGBUS;
- goto out;
- }
- if ((pgoff | PG_PMD_COLOUR) >= size) {
- dax_pmd_dbg(&bh, address,
- "offset + huge page size > file size");
- goto fallback;
- }
-
- if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+ if (!write && !buffer_mapped(&bh)) {
spinlock_t *ptl;
pmd_t entry;
struct page *zero_page = get_huge_zero_page();
@@ -954,8 +1088,8 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
long length = dax_map_atomic(bdev, &dax);
if (length < 0) {
- result = VM_FAULT_SIGBUS;
- goto out;
+ dax_pmd_dbg(&bh, address, "dax-error fallback");
+ goto fallback;
}
if (length < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "dax-length too small");
@@ -973,14 +1107,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
dax_pmd_dbg(&bh, address, "pfn not in memmap");
goto fallback;
}
-
- if (buffer_unwritten(&bh) || buffer_new(&bh)) {
- clear_pmem(dax.addr, PMD_SIZE);
- wmb_pmem();
- count_vm_event(PGMAJFAULT);
- mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
- result |= VM_FAULT_MAJOR;
- }
dax_unmap_atomic(bdev, &dax);
/*
@@ -999,13 +1125,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
* the write to insert a dirty entry.
*/
if (write) {
- error = dax_radix_entry(mapping, pgoff, dax.sector,
- true, true);
- if (error) {
- dax_pmd_dbg(&bh, address,
- "PMD radix insertion failed");
- goto fallback;
- }
+ /*
+ * We should insert radix-tree entry and dirty it here.
+ * For now this is broken...
+ */
}
dev_dbg(part_to_dev(bdev->bd_part),
@@ -1018,11 +1141,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
}
out:
- i_mmap_unlock_read(mapping);
-
- if (buffer_unwritten(&bh))
- complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
-
return result;
fallback:
@@ -1042,8 +1160,7 @@ EXPORT_SYMBOL_GPL(__dax_pmd_fault);
* pmd_fault handler for DAX files.
*/
int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
- pmd_t *pmd, unsigned int flags, get_block_t get_block,
- dax_iodone_t complete_unwritten)
+ pmd_t *pmd, unsigned int flags, get_block_t get_block)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
@@ -1052,8 +1169,7 @@ int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
- result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
- complete_unwritten);
+ result = __dax_pmd_fault(vma, address, pmd, flags, get_block);
if (flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
@@ -1070,27 +1186,59 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct file *file = vma->vm_file;
- int error;
-
- /*
- * We pass NO_SECTOR to dax_radix_entry() because we expect that a
- * RADIX_DAX_PTE entry already exists in the radix tree from a
- * previous call to __dax_fault(). We just want to look up that PTE
- * entry using vmf->pgoff and make sure the dirty tag is set. This
- * saves us from having to make a call to get_block() here to look
- * up the sector.
- */
- error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false,
- true);
+ struct address_space *mapping = file->f_mapping;
+ void *entry;
+ pgoff_t index = vmf->pgoff;
- if (error == -ENOMEM)
- return VM_FAULT_OOM;
- if (error)
- return VM_FAULT_SIGBUS;
+ spin_lock_irq(&mapping->tree_lock);
+ entry = get_unlocked_mapping_entry(mapping, index, NULL);
+ if (!entry || !radix_tree_exceptional_entry(entry))
+ goto out;
+ radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
+ put_unlocked_mapping_entry(mapping, index, entry);
+out:
+ spin_unlock_irq(&mapping->tree_lock);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
+static bool dax_range_is_aligned(struct block_device *bdev,
+ unsigned int offset, unsigned int length)
+{
+ unsigned short sector_size = bdev_logical_block_size(bdev);
+
+ if (!IS_ALIGNED(offset, sector_size))
+ return false;
+ if (!IS_ALIGNED(length, sector_size))
+ return false;
+
+ return true;
+}
+
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+ unsigned int offset, unsigned int length)
+{
+ struct blk_dax_ctl dax = {
+ .sector = sector,
+ .size = PAGE_SIZE,
+ };
+
+ if (dax_range_is_aligned(bdev, offset, length)) {
+ sector_t start_sector = dax.sector + (offset >> 9);
+
+ return blkdev_issue_zeroout(bdev, start_sector,
+ length >> 9, GFP_NOFS, true);
+ } else {
+ if (dax_map_atomic(bdev, &dax) < 0)
+ return PTR_ERR(dax.addr);
+ clear_pmem(dax.addr + offset, length);
+ wmb_pmem();
+ dax_unmap_atomic(bdev, &dax);
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__dax_zero_page_range);
+
/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
@@ -1102,12 +1250,6 @@ EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
* page in a DAX file. This is intended for hole-punch operations. If
* you are truncating a file, the helper function dax_truncate_page() may be
* more convenient.
- *
- * We work in terms of PAGE_SIZE here for commonality with
- * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
- * took care of disposing of the unnecessary blocks. Even if the filesystem
- * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
- * since the file might be mmapped.
*/
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
get_block_t get_block)
@@ -1126,23 +1268,11 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
err = get_block(inode, index, &bh, 0);
- if (err < 0)
+ if (err < 0 || !buffer_written(&bh))
return err;
- if (buffer_written(&bh)) {
- struct block_device *bdev = bh.b_bdev;
- struct blk_dax_ctl dax = {
- .sector = to_sector(&bh, inode),
- .size = PAGE_SIZE,
- };
- if (dax_map_atomic(bdev, &dax) < 0)
- return PTR_ERR(dax.addr);
- clear_pmem(dax.addr + offset, length);
- wmb_pmem();
- dax_unmap_atomic(bdev, &dax);
- }
-
- return 0;
+ return __dax_zero_page_range(bh.b_bdev, to_sector(&bh, inode),
+ offset, length);
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);
@@ -1154,12 +1284,6 @@ EXPORT_SYMBOL_GPL(dax_zero_page_range);
*
* Similar to block_truncate_page(), this function can be called by a
* filesystem when it is truncating a DAX file to handle the partial page.
- *
- * We work in terms of PAGE_SIZE here for commonality with
- * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
- * took care of disposing of the unnecessary blocks. Even if the filesystem
- * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
- * since the file might be mmapped.
*/
int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
{
diff --git a/fs/dcache.c b/fs/dcache.c
index c622872c12c5..d6847d7b123d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -507,6 +507,44 @@ void d_drop(struct dentry *dentry)
}
EXPORT_SYMBOL(d_drop);
+static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
+{
+ struct dentry *next;
+ /*
+ * Inform d_walk() and shrink_dentry_list() that we are no longer
+ * attached to the dentry tree
+ */
+ dentry->d_flags |= DCACHE_DENTRY_KILLED;
+ if (unlikely(list_empty(&dentry->d_child)))
+ return;
+ __list_del_entry(&dentry->d_child);
+ /*
+ * Cursors can move around the list of children. While we'd been
+ * a normal list member, it didn't matter - ->d_child.next would've
+ * been updated. However, from now on it won't be and for the
+ * things like d_walk() it might end up with a nasty surprise.
+ * Normally d_walk() doesn't care about cursors moving around -
+ * ->d_lock on parent prevents that and since a cursor has no children
+ * of its own, we get through it without ever unlocking the parent.
+ * There is one exception, though - if we ascend from a child that
+ * gets killed as soon as we unlock it, the next sibling is found
+ * using the value left in its ->d_child.next. And if _that_
+ * pointed to a cursor, and cursor got moved (e.g. by lseek())
+ * before d_walk() regains parent->d_lock, we'll end up skipping
+ * everything the cursor had been moved past.
+ *
+ * Solution: make sure that the pointer left behind in ->d_child.next
+ * points to something that won't be moving around. I.e. skip the
+ * cursors.
+ */
+ while (dentry->d_child.next != &parent->d_subdirs) {
+ next = list_entry(dentry->d_child.next, struct dentry, d_child);
+ if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
+ break;
+ dentry->d_child.next = next->d_child.next;
+ }
+}
+
static void __dentry_kill(struct dentry *dentry)
{
struct dentry *parent = NULL;
@@ -532,12 +570,7 @@ static void __dentry_kill(struct dentry *dentry)
}
/* if it was on the hash then remove it */
__d_drop(dentry);
- __list_del_entry(&dentry->d_child);
- /*
- * Inform d_walk() that we are no longer attached to the
- * dentry tree
- */
- dentry->d_flags |= DCACHE_DENTRY_KILLED;
+ dentry_unlist(dentry, parent);
if (parent)
spin_unlock(&parent->d_lock);
dentry_iput(dentry);
@@ -1203,6 +1236,9 @@ resume:
struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
+ if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
+ continue;
+
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
ret = enter(data, dentry);
@@ -1636,7 +1672,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
struct dentry *dentry = __d_alloc(parent->d_sb, name);
if (!dentry)
return NULL;
-
+ dentry->d_flags |= DCACHE_RCUACCESS;
spin_lock(&parent->d_lock);
/*
* don't need child lock because it is not subject
@@ -1651,6 +1687,16 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
}
EXPORT_SYMBOL(d_alloc);
+struct dentry *d_alloc_cursor(struct dentry * parent)
+{
+ struct dentry *dentry = __d_alloc(parent->d_sb, NULL);
+ if (dentry) {
+ dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR;
+ dentry->d_parent = dget(parent);
+ }
+ return dentry;
+}
+
/**
* d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
* @sb: the superblock
@@ -1670,8 +1716,7 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name)
struct qstr q;
q.name = name;
- q.len = strlen(name);
- q.hash = full_name_hash(q.name, q.len);
+ q.hash_len = hashlen_string(name);
return d_alloc(parent, &q);
}
EXPORT_SYMBOL(d_alloc_name);
@@ -2359,7 +2404,6 @@ static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b)
{
BUG_ON(!d_unhashed(entry));
hlist_bl_lock(b);
- entry->d_flags |= DCACHE_RCUACCESS;
hlist_bl_add_head_rcu(&entry->d_hash, b);
hlist_bl_unlock(b);
}
@@ -2459,7 +2503,6 @@ retry:
rcu_read_unlock();
goto retry;
}
- rcu_read_unlock();
/*
* No changes for the parent since the beginning of d_lookup().
* Since all removals from the chain happen with hlist_bl_lock(),
@@ -2472,8 +2515,6 @@ retry:
continue;
if (dentry->d_parent != parent)
continue;
- if (d_unhashed(dentry))
- continue;
if (parent->d_flags & DCACHE_OP_COMPARE) {
int tlen = dentry->d_name.len;
const char *tname = dentry->d_name.name;
@@ -2485,9 +2526,18 @@ retry:
if (dentry_cmp(dentry, str, len))
continue;
}
- dget(dentry);
hlist_bl_unlock(b);
- /* somebody is doing lookup for it right now; wait for it */
+ /* now we can try to grab a reference */
+ if (!lockref_get_not_dead(&dentry->d_lockref)) {
+ rcu_read_unlock();
+ goto retry;
+ }
+
+ rcu_read_unlock();
+ /*
+ * somebody is likely to be still doing lookup for it;
+ * wait for them to finish
+ */
spin_lock(&dentry->d_lock);
d_wait_lookup(dentry);
/*
@@ -2518,6 +2568,7 @@ retry:
dput(new);
return dentry;
}
+ rcu_read_unlock();
/* we can't take ->d_lock here; it's OK, though. */
new->d_flags |= DCACHE_PAR_LOOKUP;
new->d_wait = wq;
@@ -2844,6 +2895,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
/* ... and switch them in the tree */
if (IS_ROOT(dentry)) {
/* splicing a tree */
+ dentry->d_flags |= DCACHE_RCUACCESS;
dentry->d_parent = target->d_parent;
target->d_parent = target;
list_del_init(&target->d_child);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 9c1c9a01b7e5..592059f88e04 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -127,7 +127,6 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
r = real_fops->open(inode, filp);
out:
- fops_put(real_fops);
debugfs_use_file_finish(srcu_idx);
return r;
}
@@ -262,8 +261,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
if (real_fops->open) {
r = real_fops->open(inode, filp);
-
- if (filp->f_op != proxy_fops) {
+ if (r) {
+ replace_fops(filp, d_inode(dentry)->i_fop);
+ goto free_proxy;
+ } else if (filp->f_op != proxy_fops) {
/* No protection against file removal anymore. */
WARN(1, "debugfs file owner replaced proxy fops: %pd",
dentry);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 0b2954d7172d..37c134a132c7 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -95,8 +95,6 @@ static struct ctl_table pty_root_table[] = {
static DEFINE_MUTEX(allocated_ptys_lock);
-static struct vfsmount *devpts_mnt;
-
struct pts_mount_opts {
int setuid;
int setgid;
@@ -104,7 +102,7 @@ struct pts_mount_opts {
kgid_t gid;
umode_t mode;
umode_t ptmxmode;
- int newinstance;
+ int reserve;
int max;
};
@@ -117,11 +115,9 @@ static const match_table_t tokens = {
{Opt_uid, "uid=%u"},
{Opt_gid, "gid=%u"},
{Opt_mode, "mode=%o"},
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
{Opt_ptmxmode, "ptmxmode=%o"},
{Opt_newinstance, "newinstance"},
{Opt_max, "max=%d"},
-#endif
{Opt_err, NULL}
};
@@ -137,15 +133,48 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
return sb->s_fs_info;
}
-static inline struct super_block *pts_sb_from_inode(struct inode *inode)
+struct pts_fs_info *devpts_acquire(struct file *filp)
{
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
- if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
- return inode->i_sb;
-#endif
- if (!devpts_mnt)
- return NULL;
- return devpts_mnt->mnt_sb;
+ struct pts_fs_info *result;
+ struct path path;
+ struct super_block *sb;
+ int err;
+
+ path = filp->f_path;
+ path_get(&path);
+
+ /* Has the devpts filesystem already been found? */
+ sb = path.mnt->mnt_sb;
+ if (sb->s_magic != DEVPTS_SUPER_MAGIC) {
+ /* Is a devpts filesystem at "pts" in the same directory? */
+ err = path_pts(&path);
+ if (err) {
+ result = ERR_PTR(err);
+ goto out;
+ }
+
+ /* Is the path the root of a devpts filesystem? */
+ result = ERR_PTR(-ENODEV);
+ sb = path.mnt->mnt_sb;
+ if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+ (path.mnt->mnt_root != sb->s_root))
+ goto out;
+ }
+
+ /*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+ atomic_inc(&sb->s_active);
+ result = DEVPTS_SB(sb);
+
+out:
+ path_put(&path);
+ return result;
+}
+
+void devpts_release(struct pts_fs_info *fsi)
+{
+ deactivate_super(fsi->sb);
}
#define PARSE_MOUNT 0
@@ -154,9 +183,7 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode)
/*
* parse_mount_options():
* Set @opts to mount options specified in @data. If an option is not
- * specified in @data, set it to its default value. The exception is
- * 'newinstance' option which can only be set/cleared on a mount (i.e.
- * cannot be changed during remount).
+ * specified in @data, set it to its default value.
*
* Note: @data may be NULL (in which case all options are set to default).
*/
@@ -174,9 +201,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
opts->max = NR_UNIX98_PTY_MAX;
- /* newinstance makes sense only on initial mount */
+ /* Only allow instances mounted from the initial mount
+ * namespace to tap the reserve pool of ptys.
+ */
if (op == PARSE_MOUNT)
- opts->newinstance = 0;
+ opts->reserve =
+ (current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns);
while ((p = strsep(&data, ",")) != NULL) {
substring_t args[MAX_OPT_ARGS];
@@ -211,16 +241,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
return -EINVAL;
opts->mode = option & S_IALLUGO;
break;
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
case Opt_ptmxmode:
if (match_octal(&args[0], &option))
return -EINVAL;
opts->ptmxmode = option & S_IALLUGO;
break;
case Opt_newinstance:
- /* newinstance makes sense only on initial mount */
- if (op == PARSE_MOUNT)
- opts->newinstance = 1;
break;
case Opt_max:
if (match_int(&args[0], &option) ||
@@ -228,7 +254,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
return -EINVAL;
opts->max = option;
break;
-#endif
default:
pr_err("called with bogus options\n");
return -EINVAL;
@@ -238,7 +263,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
return 0;
}
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
static int mknod_ptmx(struct super_block *sb)
{
int mode;
@@ -305,12 +329,6 @@ static void update_ptmx_mode(struct pts_fs_info *fsi)
inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode;
}
}
-#else
-static inline void update_ptmx_mode(struct pts_fs_info *fsi)
-{
- return;
-}
-#endif
static int devpts_remount(struct super_block *sb, int *flags, char *data)
{
@@ -344,11 +362,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root)
seq_printf(seq, ",gid=%u",
from_kgid_munged(&init_user_ns, opts->gid));
seq_printf(seq, ",mode=%03o", opts->mode);
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
if (opts->max < NR_UNIX98_PTY_MAX)
seq_printf(seq, ",max=%d", opts->max);
-#endif
return 0;
}
@@ -410,40 +426,11 @@ fail:
return -ENOMEM;
}
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-static int compare_init_pts_sb(struct super_block *s, void *p)
-{
- if (devpts_mnt)
- return devpts_mnt->mnt_sb == s;
- return 0;
-}
-
/*
* devpts_mount()
*
- * If the '-o newinstance' mount option was specified, mount a new
- * (private) instance of devpts. PTYs created in this instance are
- * independent of the PTYs in other devpts instances.
- *
- * If the '-o newinstance' option was not specified, mount/remount the
- * initial kernel mount of devpts. This type of mount gives the
- * legacy, single-instance semantics.
- *
- * The 'newinstance' option is needed to support multiple namespace
- * semantics in devpts while preserving backward compatibility of the
- * current 'single-namespace' semantics. i.e all mounts of devpts
- * without the 'newinstance' mount option should bind to the initial
- * kernel mount, like mount_single().
- *
- * Mounts with 'newinstance' option create a new, private namespace.
- *
- * NOTE:
- *
- * For single-mount semantics, devpts cannot use mount_single(),
- * because mount_single()/sget() find and use the super-block from
- * the most recent mount of devpts. But that recent mount may be a
- * 'newinstance' mount and mount_single() would pick the newinstance
- * super-block instead of the initial super-block.
+ * Mount a new (private) instance of devpts. PTYs created in this
+ * instance are independent of the PTYs in other devpts instances.
*/
static struct dentry *devpts_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
@@ -456,18 +443,7 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type,
if (error)
return ERR_PTR(error);
- /* Require newinstance for all user namespace mounts to ensure
- * the mount options are not changed.
- */
- if ((current_user_ns() != &init_user_ns) && !opts.newinstance)
- return ERR_PTR(-EINVAL);
-
- if (opts.newinstance)
- s = sget(fs_type, NULL, set_anon_super, flags, NULL);
- else
- s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags,
- NULL);
-
+ s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
@@ -491,18 +467,6 @@ out_undo_sget:
return ERR_PTR(error);
}
-#else
-/*
- * This supports only the legacy single-instance semantics (no
- * multiple-instance semantics)
- */
-static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data)
-{
- return mount_single(fs_type, flags, data, devpts_fill_super);
-}
-#endif
-
static void devpts_kill_sb(struct super_block *sb)
{
struct pts_fs_info *fsi = DEVPTS_SB(sb);
@@ -516,9 +480,7 @@ static struct file_system_type devpts_fs_type = {
.name = "devpts",
.mount = devpts_mount,
.kill_sb = devpts_kill_sb,
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
.fs_flags = FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT,
-#endif
};
/*
@@ -531,16 +493,13 @@ int devpts_new_index(struct pts_fs_info *fsi)
int index;
int ida_ret;
- if (!fsi)
- return -ENODEV;
-
retry:
if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
return -ENOMEM;
mutex_lock(&allocated_ptys_lock);
- if (pty_count >= pty_limit -
- (fsi->mount_opts.newinstance ? pty_reserve : 0)) {
+ if (pty_count >= (pty_limit -
+ (fsi->mount_opts.reserve ? 0 : pty_reserve))) {
mutex_unlock(&allocated_ptys_lock);
return -ENOSPC;
}
@@ -571,30 +530,6 @@ void devpts_kill_index(struct pts_fs_info *fsi, int idx)
mutex_unlock(&allocated_ptys_lock);
}
-/*
- * pty code needs to hold extra references in case of last /dev/tty close
- */
-struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
-{
- struct super_block *sb;
- struct pts_fs_info *fsi;
-
- sb = pts_sb_from_inode(ptmx_inode);
- if (!sb)
- return NULL;
- fsi = DEVPTS_SB(sb);
- if (!fsi)
- return NULL;
-
- atomic_inc(&sb->s_active);
- return fsi;
-}
-
-void devpts_put_ref(struct pts_fs_info *fsi)
-{
- deactivate_super(fsi->sb);
-}
-
/**
* devpts_pty_new -- create a new inode in /dev/pts/
* @ptmx_inode: inode of the master
@@ -607,16 +542,12 @@ void devpts_put_ref(struct pts_fs_info *fsi)
struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
{
struct dentry *dentry;
- struct super_block *sb;
+ struct super_block *sb = fsi->sb;
struct inode *inode;
struct dentry *root;
struct pts_mount_opts *opts;
char s[12];
- if (!fsi)
- return ERR_PTR(-ENODEV);
-
- sb = fsi->sb;
root = sb->s_root;
opts = &fsi->mount_opts;
@@ -676,20 +607,8 @@ void devpts_pty_kill(struct dentry *dentry)
static int __init init_devpts_fs(void)
{
int err = register_filesystem(&devpts_fs_type);
- struct ctl_table_header *table;
-
if (!err) {
- struct vfsmount *mnt;
-
- table = register_sysctl_table(pty_root_table);
- mnt = kern_mount(&devpts_fs_type);
- if (IS_ERR(mnt)) {
- err = PTR_ERR(mnt);
- unregister_filesystem(&devpts_fs_type);
- unregister_sysctl_table(table);
- } else {
- devpts_mnt = mnt;
- }
+ register_sysctl_table(pty_root_table);
}
return err;
}
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 3bf3f20f8ecc..f3b4408be590 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -628,11 +628,11 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
map_bh->b_size = fs_count << i_blkbits;
/*
- * For writes inside i_size on a DIO_SKIP_HOLES filesystem we
- * forbid block creations: only overwrites are permitted.
- * We will return early to the caller once we see an
- * unmapped buffer head returned, and the caller will fall
- * back to buffered I/O.
+ * For writes that could fill holes inside i_size on a
+ * DIO_SKIP_HOLES filesystem we forbid block creations: only
+ * overwrites are permitted. We will return early to the caller
+ * once we see an unmapped buffer head returned, and the caller
+ * will fall back to buffered I/O.
*
* Otherwise the decision is left to the get_blocks method,
* which may decide to handle it or also return an unmapped
@@ -640,8 +640,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
*/
create = dio->rw & WRITE;
if (dio->flags & DIO_SKIP_HOLES) {
- if (sdio->block_in_file < (i_size_read(dio->inode) >>
- sdio->blkbits))
+ if (fs_startblk <= ((i_size_read(dio->inode) - 1) >>
+ i_blkbits))
create = 0;
}
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index ebd40f46ed4c..0d8eb3455b34 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1141,12 +1141,13 @@ ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode,
static int
ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry,
+ struct inode *ecryptfs_inode,
char *page_virt, size_t size)
{
int rc;
- rc = ecryptfs_setxattr(ecryptfs_dentry, ECRYPTFS_XATTR_NAME, page_virt,
- size, 0);
+ rc = ecryptfs_setxattr(ecryptfs_dentry, ecryptfs_inode,
+ ECRYPTFS_XATTR_NAME, page_virt, size, 0);
return rc;
}
@@ -1215,8 +1216,8 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
goto out_free;
}
if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
- rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
- size);
+ rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, ecryptfs_inode,
+ virt, size);
else
rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt,
virt_len);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 3ec495db7e82..4ba1547bb9ad 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -609,8 +609,8 @@ ssize_t
ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
const char *name, void *value, size_t size);
int
-ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags);
+ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name,
+ const void *value, size_t size, int flags);
int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode);
#ifdef CONFIG_ECRYPT_FS_MESSAGING
int ecryptfs_process_response(struct ecryptfs_daemon *daemon,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 318b04689d76..9d153b6a1d72 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1001,7 +1001,8 @@ static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
}
int
-ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
+ecryptfs_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
size_t size, int flags)
{
int rc = 0;
@@ -1014,8 +1015,8 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
}
rc = vfs_setxattr(lower_dentry, name, value, size, flags);
- if (!rc && d_really_is_positive(dentry))
- fsstack_copy_attr_all(d_inode(dentry), d_inode(lower_dentry));
+ if (!rc && inode)
+ fsstack_copy_attr_all(inode, d_inode(lower_dentry));
out:
return rc;
}
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index 866bb18efefe..e818f5ac7a26 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/mount.h>
+#include <linux/file.h>
#include "ecryptfs_kernel.h"
struct ecryptfs_open_req {
@@ -147,7 +148,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
(*lower_file) = dentry_open(&req.path, flags, cred);
if (!IS_ERR(*lower_file))
- goto out;
+ goto have_file;
if ((flags & O_ACCMODE) == O_RDONLY) {
rc = PTR_ERR((*lower_file));
goto out;
@@ -165,8 +166,16 @@ int ecryptfs_privileged_open(struct file **lower_file,
mutex_unlock(&ecryptfs_kthread_ctl.mux);
wake_up(&ecryptfs_kthread_ctl.wait);
wait_for_completion(&req.done);
- if (IS_ERR(*lower_file))
+ if (IS_ERR(*lower_file)) {
rc = PTR_ERR(*lower_file);
+ goto out;
+ }
+have_file:
+ if ((*lower_file)->f_op->mmap == NULL) {
+ fput(*lower_file);
+ *lower_file = NULL;
+ rc = -EMEDIUMTYPE;
+ }
out:
return rc;
}
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 148d11b514fb..9c3437c8a5b1 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -442,7 +442,8 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
if (size < 0)
size = 8;
put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt);
- rc = lower_inode->i_op->setxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
+ rc = lower_inode->i_op->setxattr(lower_dentry, lower_inode,
+ ECRYPTFS_XATTR_NAME,
xattr_virt, size, 0);
inode_unlock(lower_inode);
if (rc)
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index c1400b109805..868c02317b05 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
}
down_read(&ei->dax_sem);
- ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+ ret = __dax_fault(vma, vmf, ext2_get_block);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
@@ -72,7 +72,7 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
}
down_read(&ei->dax_sem);
- ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+ ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
up_read(&ei->dax_sem);
if (flags & FAULT_FLAG_WRITE)
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index b675610391b8..fcbe58641e40 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -26,6 +26,7 @@
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
+#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
@@ -737,19 +738,18 @@ static int ext2_get_blocks(struct inode *inode,
* so that it's not found by another thread before it's
* initialised
*/
- err = dax_clear_sectors(inode->i_sb->s_bdev,
- le32_to_cpu(chain[depth-1].key) <<
- (inode->i_blkbits - 9),
- 1 << inode->i_blkbits);
+ err = sb_issue_zeroout(inode->i_sb,
+ le32_to_cpu(chain[depth-1].key), count,
+ GFP_NOFS);
if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
- }
+ } else
+ set_buffer_new(bh_result);
ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
- set_buffer_new(bh_result);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index b78caf25f746..1d9379568aa8 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -922,16 +922,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
- if (blocksize != PAGE_SIZE) {
- ext2_msg(sb, KERN_ERR,
- "error: unsupported blocksize for dax");
+ err = bdev_dax_supported(sb, blocksize);
+ if (err)
goto failed_mount;
- }
- if (!sb->s_bdev->bd_disk->fops->direct_access) {
- ext2_msg(sb, KERN_ERR,
- "error: device does not support dax");
- goto failed_mount;
- }
}
/* If the blocksize doesn't match, re-read the thing.. */
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index 7fd3b867ce65..7b9e9c1842d5 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -18,10 +18,11 @@ ext2_xattr_security_get(const struct xattr_handler *handler,
static int
ext2_xattr_security_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 0f85705ff519..65049b71af13 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -25,10 +25,11 @@ ext2_xattr_trusted_get(const struct xattr_handler *handler,
static int
ext2_xattr_trusted_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_set(inode, EXT2_XATTR_INDEX_TRUSTED, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index 1fafd27037cc..fb2f992ae763 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -29,13 +29,14 @@ ext2_xattr_user_get(const struct xattr_handler *handler,
static int
ext2_xattr_user_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- if (!test_opt(dentry->d_sb, XATTR_USER))
+ if (!test_opt(inode->i_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_USER,
+ return ext2_xattr_set(inode, EXT2_XATTR_INDEX_USER,
name, value, size, flags);
}
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index fe1f50fe764f..3020fd70c392 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -610,7 +610,8 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
- return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+ jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+ return 1;
}
/*
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 5d00bf060254..68323e3da3fa 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -150,6 +150,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
while (ctx->pos < inode->i_size) {
struct ext4_map_blocks map;
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto errout;
+ }
+ cond_resched();
map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
map.m_len = 1;
err = ext4_map_blocks(NULL, inode, &map, 0);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 72f4c9e00e97..b84aa1ca480a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -33,6 +33,7 @@
#include <linux/ratelimit.h>
#include <crypto/hash.h>
#include <linux/falloc.h>
+#include <linux/percpu-rwsem.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
@@ -581,6 +582,9 @@ enum {
#define EXT4_GET_BLOCKS_ZERO 0x0200
#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\
EXT4_GET_BLOCKS_ZERO)
+ /* Caller will submit data before dropping transaction handle. This
+ * allows jbd2 to avoid submitting data before commit. */
+#define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400
/*
* The bit position of these flags must not overlap with any of the
@@ -1505,6 +1509,9 @@ struct ext4_sb_info {
struct ratelimit_state s_err_ratelimit_state;
struct ratelimit_state s_warning_ratelimit_state;
struct ratelimit_state s_msg_ratelimit_state;
+
+ /* Barrier between changing inodes' journal flags and writepages ops. */
+ struct percpu_rw_semaphore s_journal_flag_rwsem;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1549,7 +1556,6 @@ enum {
EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read
nolocking */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
- EXT4_STATE_ORDERED_MODE, /* data=ordered mode */
EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
};
@@ -2521,8 +2527,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create);
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_dio_get_block(struct inode *inode, sector_t iblock,
@@ -2581,7 +2587,6 @@ extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
-extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
@@ -3329,6 +3334,13 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
}
}
+static inline bool ext4_aligned_io(struct inode *inode, loff_t off, loff_t len)
+{
+ int blksize = 1 << inode->i_blkbits;
+
+ return IS_ALIGNED(off, blksize) && IS_ALIGNED(len, blksize);
+}
+
#endif /* __KERNEL__ */
#define EFSBADCRC EBADMSG /* Bad CRC detected */
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5f5846211095..09c1ef38cbe6 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -359,10 +359,21 @@ static inline int ext4_journal_force_commit(journal_t *journal)
return 0;
}
-static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
+static inline int ext4_jbd2_inode_add_write(handle_t *handle,
+ struct inode *inode)
{
if (ext4_handle_valid(handle))
- return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
+ return jbd2_journal_inode_add_write(handle,
+ EXT4_I(inode)->jinode);
+ return 0;
+}
+
+static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
+ struct inode *inode)
+{
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_inode_add_wait(handle,
+ EXT4_I(inode)->jinode);
return 0;
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 95bf4679ac54..2a2eef9c14e4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -120,9 +120,14 @@ static int ext4_ext_truncate_extend_restart(handle_t *handle,
if (!ext4_handle_valid(handle))
return 0;
- if (handle->h_buffer_credits > needed)
+ if (handle->h_buffer_credits >= needed)
return 0;
- err = ext4_journal_extend(handle, needed);
+ /*
+ * If we need to extend the journal get a few extra blocks
+ * while we're at it for efficiency's sake.
+ */
+ needed += 3;
+ err = ext4_journal_extend(handle, needed - handle->h_buffer_credits);
if (err <= 0)
return err;
err = ext4_truncate_restart_trans(handle, inode, needed);
@@ -907,13 +912,6 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
eh = ext_block_hdr(bh);
ppos++;
- if (unlikely(ppos > depth)) {
- put_bh(bh);
- EXT4_ERROR_INODE(inode,
- "ppos %d > depth %d", ppos, depth);
- ret = -EFSCORRUPTED;
- goto err;
- }
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
}
@@ -2583,7 +2581,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
}
} else
ext4_error(sbi->s_sb, "strange request: removal(2) "
- "%u-%u from %u:%u\n",
+ "%u-%u from %u:%u",
from, to, le32_to_cpu(ex->ee_block), ee_len);
return 0;
}
@@ -3738,7 +3736,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
if (ee_block != map->m_lblk || ee_len > map->m_len) {
#ifdef EXT4_DEBUG
ext4_warning("Inode (%ld) finished: extent logical block %llu,"
- " len %u; IO logical block %llu, len %u\n",
+ " len %u; IO logical block %llu, len %u",
inode->i_ino, (unsigned long long)ee_block, ee_len,
(unsigned long long)map->m_lblk, map->m_len);
#endif
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index e38b987ac7f5..37e059202cd2 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -707,7 +707,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
(status & EXTENT_STATUS_WRITTEN)) {
ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as "
" delayed and written which can potentially "
- " cause data loss.\n", lblk, len);
+ " cause data loss.", lblk, len);
WARN_ON(1);
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 00ff6912adb3..df44c877892a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,7 +202,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else
- result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
+ result = __dax_fault(vma, vmf, ext4_dax_get_block);
if (write) {
if (!IS_ERR(handle))
@@ -238,7 +238,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
result = VM_FAULT_SIGBUS;
else
result = __dax_pmd_fault(vma, addr, pmd, flags,
- ext4_dax_mmap_get_block, NULL);
+ ext4_dax_get_block);
if (write) {
if (!IS_ERR(handle))
@@ -373,7 +373,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
if (ext4_encrypted_inode(d_inode(dir)) &&
!ext4_is_child_context_consistent_with_parent(d_inode(dir), inode)) {
ext4_warning(inode->i_sb,
- "Inconsistent encryption contexts: %lu/%lu\n",
+ "Inconsistent encryption contexts: %lu/%lu",
(unsigned long) d_inode(dir)->i_ino,
(unsigned long) inode->i_ino);
dput(dir);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 237b877d316d..3da4cf8d18b6 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1150,25 +1150,20 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
ext4_group_t block_group;
int bit;
- struct buffer_head *bitmap_bh;
+ struct buffer_head *bitmap_bh = NULL;
struct inode *inode = NULL;
- long err = -EIO;
+ int err = -EFSCORRUPTED;
- /* Error cases - e2fsck has already cleaned up for us */
- if (ino > max_ino) {
- ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino);
- err = -EFSCORRUPTED;
- goto error;
- }
+ if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+ goto bad_orphan;
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- ext4_warning(sb, "inode bitmap error %ld for orphan %lu",
- ino, err);
- goto error;
+ ext4_error(sb, "inode bitmap error %ld for orphan %lu",
+ ino, PTR_ERR(bitmap_bh));
+ return (struct inode *) bitmap_bh;
}
/* Having the inode bit set should be a 100% indicator that this
@@ -1179,15 +1174,21 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
goto bad_orphan;
inode = ext4_iget(sb, ino);
- if (IS_ERR(inode))
- goto iget_failed;
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
+ ino, err);
+ return inode;
+ }
/*
- * If the orphans has i_nlinks > 0 then it should be able to be
- * truncated, otherwise it won't be removed from the orphan list
- * during processing and an infinite loop will result.
+ * If the orphans has i_nlinks > 0 then it should be able to
+ * be truncated, otherwise it won't be removed from the orphan
+ * list during processing and an infinite loop will result.
+ * Similarly, it must not be a bad inode.
*/
- if (inode->i_nlink && !ext4_can_truncate(inode))
+ if ((inode->i_nlink && !ext4_can_truncate(inode)) ||
+ is_bad_inode(inode))
goto bad_orphan;
if (NEXT_ORPHAN(inode) > max_ino)
@@ -1195,29 +1196,25 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
brelse(bitmap_bh);
return inode;
-iget_failed:
- err = PTR_ERR(inode);
- inode = NULL;
bad_orphan:
- ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino);
- printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n",
- bit, (unsigned long long)bitmap_bh->b_blocknr,
- ext4_test_bit(bit, bitmap_bh->b_data));
- printk(KERN_WARNING "inode=%p\n", inode);
+ ext4_error(sb, "bad orphan inode %lu", ino);
+ if (bitmap_bh)
+ printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+ bit, (unsigned long long)bitmap_bh->b_blocknr,
+ ext4_test_bit(bit, bitmap_bh->b_data));
if (inode) {
- printk(KERN_WARNING "is_bad_inode(inode)=%d\n",
+ printk(KERN_ERR "is_bad_inode(inode)=%d\n",
is_bad_inode(inode));
- printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n",
+ printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n",
NEXT_ORPHAN(inode));
- printk(KERN_WARNING "max_ino=%lu\n", max_ino);
- printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink);
+ printk(KERN_ERR "max_ino=%lu\n", max_ino);
+ printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink);
/* Avoid freeing blocks if we got a bad deleted inode */
if (inode->i_nlink == 0)
inode->i_blocks = 0;
iput(inode);
}
brelse(bitmap_bh);
-error:
return ERR_PTR(err);
}
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 627b7e8f9ef3..bc15c2c17633 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -649,133 +649,6 @@ out:
}
/*
- * O_DIRECT for ext3 (or indirect map) based files
- *
- * If the O_DIRECT write will extend the file then add this inode to the
- * orphan list. So recovery will truncate it back to the original size
- * if the machine crashes during the write.
- *
- * If the O_DIRECT write is intantiating holes inside i_size and the machine
- * crashes then stale disk data _may_ be exposed inside the file. But current
- * VFS code falls back into buffered path in that case so we are safe.
- */
-ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- loff_t offset = iocb->ki_pos;
- handle_t *handle;
- ssize_t ret;
- int orphan = 0;
- size_t count = iov_iter_count(iter);
- int retries = 0;
-
- if (iov_iter_rw(iter) == WRITE) {
- loff_t final_size = offset + count;
-
- if (final_size > inode->i_size) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ei->i_disksize = inode->i_size;
- ext4_journal_stop(handle);
- }
- }
-
-retry:
- if (iov_iter_rw(iter) == READ && ext4_should_dioread_nolock(inode)) {
- /*
- * Nolock dioread optimization may be dynamically disabled
- * via ext4_inode_block_unlocked_dio(). Check inode's state
- * while holding extra i_dio_count ref.
- */
- inode_dio_begin(inode);
- smp_mb();
- if (unlikely(ext4_test_inode_state(inode,
- EXT4_STATE_DIOREAD_LOCK))) {
- inode_dio_end(inode);
- goto locked;
- }
- if (IS_DAX(inode))
- ret = dax_do_io(iocb, inode, iter,
- ext4_dio_get_block, NULL, 0);
- else
- ret = __blockdev_direct_IO(iocb, inode,
- inode->i_sb->s_bdev, iter,
- ext4_dio_get_block,
- NULL, NULL, 0);
- inode_dio_end(inode);
- } else {
-locked:
- if (IS_DAX(inode))
- ret = dax_do_io(iocb, inode, iter,
- ext4_dio_get_block, NULL, DIO_LOCKING);
- else
- ret = blockdev_direct_IO(iocb, inode, iter,
- ext4_dio_get_block);
-
- if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
- loff_t isize = i_size_read(inode);
- loff_t end = offset + count;
-
- if (end > isize)
- ext4_truncate_failed_write(inode);
- }
- }
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-
- if (orphan) {
- int err;
-
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- /* This is really bad luck. We've written the data
- * but cannot extend i_size. Bail out and pretend
- * the write failed... */
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
-
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size) {
- ei->i_disksize = end;
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
- }
-out:
- return ret;
-}
-
-/*
* Calculate the number of metadata blocks need to reserve
* to allocate a new block at @lblocks for non extent file based file
*/
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 7bc6c855cc18..ff7538c26992 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1780,7 +1780,7 @@ int empty_inline_dir(struct inode *dir, int *has_inline_data)
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - "
"inode %u, rec_len %u, name_len %d"
- "inline size %d\n",
+ "inline size %d",
dir->i_ino, le32_to_cpu(de->inode),
le16_to_cpu(de->rec_len), de->name_len,
inline_size);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 79b298d397b4..f7140ca66e3b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -684,6 +684,24 @@ out_sem:
ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
+
+ /*
+ * Inodes with freshly allocated blocks where contents will be
+ * visible after transaction commit must be on transaction's
+ * ordered data list.
+ */
+ if (map->m_flags & EXT4_MAP_NEW &&
+ !(map->m_flags & EXT4_MAP_UNWRITTEN) &&
+ !(flags & EXT4_GET_BLOCKS_ZERO) &&
+ !IS_NOQUOTA(inode) &&
+ ext4_should_order_data(inode)) {
+ if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
+ ret = ext4_jbd2_inode_add_wait(handle, inode);
+ else
+ ret = ext4_jbd2_inode_add_write(handle, inode);
+ if (ret)
+ return ret;
+ }
}
return retval;
}
@@ -1289,15 +1307,6 @@ static int ext4_write_end(struct file *file,
int i_size_changed = 0;
trace_ext4_write_end(inode, pos, len, copied);
- if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) {
- ret = ext4_jbd2_file_inode(handle, inode);
- if (ret) {
- unlock_page(page);
- put_page(page);
- goto errout;
- }
- }
-
if (ext4_has_inline_data(inode)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
@@ -2313,7 +2322,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
* the data was copied into the page cache.
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
- EXT4_GET_BLOCKS_METADATA_NOFAIL;
+ EXT4_GET_BLOCKS_METADATA_NOFAIL |
+ EXT4_GET_BLOCKS_IO_SUBMIT;
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
@@ -2602,11 +2612,14 @@ static int ext4_writepages(struct address_space *mapping,
struct blk_plug plug;
bool give_up_on_write = false;
+ percpu_down_read(&sbi->s_journal_flag_rwsem);
trace_ext4_writepages(inode, wbc);
- if (dax_mapping(mapping))
- return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
- wbc);
+ if (dax_mapping(mapping)) {
+ ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+ wbc);
+ goto out_writepages;
+ }
/*
* No pages to write? This is mainly a kludge to avoid starting
@@ -2776,6 +2789,7 @@ retry:
out_writepages:
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
+ percpu_up_read(&sbi->s_journal_flag_rwsem);
return ret;
}
@@ -3215,75 +3229,52 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
}
#ifdef CONFIG_FS_DAX
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+/*
+ * Get block function for DAX IO and mmap faults. It takes care of converting
+ * unwritten extents to written ones and initializes new / converted blocks
+ * to zeros.
+ */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
- int ret, err;
- int credits;
- struct ext4_map_blocks map;
- handle_t *handle = NULL;
- int flags = 0;
-
- ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n",
- inode->i_ino, create);
- map.m_lblk = iblock;
- map.m_len = bh_result->b_size >> inode->i_blkbits;
- credits = ext4_chunk_trans_blocks(inode, map.m_len);
- if (create) {
- flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO;
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- return ret;
- }
- }
+ int ret;
- ret = ext4_map_blocks(handle, inode, &map, flags);
- if (create) {
- err = ext4_journal_stop(handle);
- if (ret >= 0 && err < 0)
- ret = err;
- }
- if (ret <= 0)
- goto out;
- if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- int err2;
+ ext4_debug("inode %lu, create flag %d\n", inode->i_ino, create);
+ if (!create)
+ return _ext4_get_block(inode, iblock, bh_result, 0);
- /*
- * We are protected by i_mmap_sem so we know block cannot go
- * away from under us even though we dropped i_data_sem.
- * Convert extent to written and write zeros there.
- *
- * Note: We may get here even when create == 0.
- */
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
+ ret = ext4_get_block_trans(inode, iblock, bh_result,
+ EXT4_GET_BLOCKS_PRE_IO |
+ EXT4_GET_BLOCKS_CREATE_ZERO);
+ if (ret < 0)
+ return ret;
- err = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO);
- if (err < 0)
- ret = err;
- err2 = ext4_journal_stop(handle);
- if (err2 < 0 && ret > 0)
- ret = err2;
- }
-out:
- WARN_ON_ONCE(ret == 0 && create);
- if (ret > 0) {
- map_bh(bh_result, inode->i_sb, map.m_pblk);
+ if (buffer_unwritten(bh_result)) {
/*
- * At least for now we have to clear BH_New so that DAX code
- * doesn't attempt to zero blocks again in a racy way.
+ * We are protected by i_mmap_sem or i_mutex so we know block
+ * cannot go away from under us even though we dropped
+ * i_data_sem. Convert extent to written and write zeros there.
*/
- map.m_flags &= ~EXT4_MAP_NEW;
- ext4_update_bh_state(bh_result, map.m_flags);
- bh_result->b_size = map.m_len << inode->i_blkbits;
- ret = 0;
+ ret = ext4_get_block_trans(inode, iblock, bh_result,
+ EXT4_GET_BLOCKS_CONVERT |
+ EXT4_GET_BLOCKS_CREATE_ZERO);
+ if (ret < 0)
+ return ret;
}
- return ret;
+ /*
+ * At least for now we have to clear BH_New so that DAX code
+ * doesn't attempt to zero blocks again in a racy way.
+ */
+ clear_buffer_new(bh_result);
+ return 0;
+}
+#else
+/* Just define empty function, it will never get called. */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ BUG();
+ return 0;
}
#endif
@@ -3316,7 +3307,9 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
}
/*
- * For ext4 extent files, ext4 will do direct-io write to holes,
+ * Handling of direct IO writes.
+ *
+ * For ext4 extent files, ext4 will do direct-io write even to holes,
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
@@ -3334,10 +3327,11 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
* if the machine crashes during the write.
*
*/
-static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ struct ext4_inode_info *ei = EXT4_I(inode);
ssize_t ret;
loff_t offset = iocb->ki_pos;
size_t count = iov_iter_count(iter);
@@ -3345,10 +3339,25 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
get_block_t *get_block_func = NULL;
int dio_flags = 0;
loff_t final_size = offset + count;
+ int orphan = 0;
+ handle_t *handle;
- /* Use the old path for reads and writes beyond i_size. */
- if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
- return ext4_ind_direct_IO(iocb, iter);
+ if (final_size > inode->i_size) {
+ /* Credits for sb + inode write */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ ret = ext4_orphan_add(handle, inode);
+ if (ret) {
+ ext4_journal_stop(handle);
+ goto out;
+ }
+ orphan = 1;
+ ei->i_disksize = inode->i_size;
+ ext4_journal_stop(handle);
+ }
BUG_ON(iocb->private == NULL);
@@ -3357,8 +3366,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
* conversion. This also disallows race between truncate() and
* overwrite DIO as i_dio_count needs to be incremented under i_mutex.
*/
- if (iov_iter_rw(iter) == WRITE)
- inode_dio_begin(inode);
+ inode_dio_begin(inode);
/* If we do a overwrite dio, i_mutex locking can be released */
overwrite = *((int *)iocb->private);
@@ -3367,7 +3375,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
inode_unlock(inode);
/*
- * We could direct write to holes and fallocate.
+ * For extent mapped files we could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as unwritten to prevent
* parallel buffered read to expose the stale data before DIO complete
@@ -3389,7 +3397,23 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
iocb->private = NULL;
if (overwrite)
get_block_func = ext4_dio_get_block_overwrite;
- else if (is_sync_kiocb(iocb)) {
+ else if (IS_DAX(inode)) {
+ /*
+ * We can avoid zeroing for aligned DAX writes beyond EOF. Other
+ * writes need zeroing either because they can race with page
+ * faults or because they use partial blocks.
+ */
+ if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
+ ext4_aligned_io(inode, offset, count))
+ get_block_func = ext4_dio_get_block;
+ else
+ get_block_func = ext4_dax_get_block;
+ dio_flags = DIO_LOCKING;
+ } else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+ round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+ get_block_func = ext4_dio_get_block;
+ dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
+ } else if (is_sync_kiocb(iocb)) {
get_block_func = ext4_dio_get_block_unwritten_sync;
dio_flags = DIO_LOCKING;
} else {
@@ -3399,10 +3423,10 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
#ifdef CONFIG_EXT4_FS_ENCRYPTION
BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
#endif
- if (IS_DAX(inode))
+ if (IS_DAX(inode)) {
ret = dax_do_io(iocb, inode, iter, get_block_func,
ext4_end_io_dio, dio_flags);
- else
+ } else
ret = __blockdev_direct_IO(iocb, inode,
inode->i_sb->s_bdev, iter,
get_block_func,
@@ -3422,12 +3446,86 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
}
- if (iov_iter_rw(iter) == WRITE)
- inode_dio_end(inode);
+ inode_dio_end(inode);
/* take i_mutex locking again if we do a ovewrite dio */
if (overwrite)
inode_lock(inode);
+ if (ret < 0 && final_size > inode->i_size)
+ ext4_truncate_failed_write(inode);
+
+ /* Handle extending of i_size after direct IO write */
+ if (orphan) {
+ int err;
+
+ /* Credits for sb + inode write */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ /* This is really bad luck. We've written the data
+ * but cannot extend i_size. Bail out and pretend
+ * the write failed... */
+ ret = PTR_ERR(handle);
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+
+ goto out;
+ }
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+ if (ret > 0) {
+ loff_t end = offset + ret;
+ if (end > inode->i_size) {
+ ei->i_disksize = end;
+ i_size_write(inode, end);
+ /*
+ * We're going to return a positive `ret'
+ * here due to non-zero-length I/O, so there's
+ * no way of reporting error returns from
+ * ext4_mark_inode_dirty() to userspace. So
+ * ignore it.
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+ }
+ err = ext4_journal_stop(handle);
+ if (ret == 0)
+ ret = err;
+ }
+out:
+ return ret;
+}
+
+static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
+{
+ int unlocked = 0;
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ ssize_t ret;
+
+ if (ext4_should_dioread_nolock(inode)) {
+ /*
+ * Nolock dioread optimization may be dynamically disabled
+ * via ext4_inode_block_unlocked_dio(). Check inode's state
+ * while holding extra i_dio_count ref.
+ */
+ inode_dio_begin(inode);
+ smp_mb();
+ if (unlikely(ext4_test_inode_state(inode,
+ EXT4_STATE_DIOREAD_LOCK)))
+ inode_dio_end(inode);
+ else
+ unlocked = 1;
+ }
+ if (IS_DAX(inode)) {
+ ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block,
+ NULL, unlocked ? 0 : DIO_LOCKING);
+ } else {
+ ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+ iter, ext4_dio_get_block,
+ NULL, NULL,
+ unlocked ? 0 : DIO_LOCKING);
+ }
+ if (unlocked)
+ inode_dio_end(inode);
return ret;
}
@@ -3455,10 +3553,10 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
return 0;
trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ret = ext4_ext_direct_IO(iocb, iter);
+ if (iov_iter_rw(iter) == READ)
+ ret = ext4_direct_IO_read(iocb, iter);
else
- ret = ext4_ind_direct_IO(iocb, iter);
+ ret = ext4_direct_IO_write(iocb, iter);
trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
return ret;
}
@@ -3534,10 +3632,7 @@ void ext4_set_aops(struct inode *inode)
{
switch (ext4_inode_journal_mode(inode)) {
case EXT4_INODE_ORDERED_DATA_MODE:
- ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE);
- break;
case EXT4_INODE_WRITEBACK_DATA_MODE:
- ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE);
break;
case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
@@ -3630,8 +3725,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
} else {
err = 0;
mark_buffer_dirty(bh);
- if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE))
- err = ext4_jbd2_file_inode(handle, inode);
+ if (ext4_should_order_data(inode))
+ err = ext4_jbd2_inode_add_write(handle, inode);
}
unlock:
@@ -5429,6 +5524,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
journal_t *journal;
handle_t *handle;
int err;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
/*
* We have to be very careful here: changing a data block's
@@ -5445,22 +5541,30 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
return 0;
if (is_journal_aborted(journal))
return -EROFS;
- /* We have to allocate physical blocks for delalloc blocks
- * before flushing journal. otherwise delalloc blocks can not
- * be allocated any more. even more truncate on delalloc blocks
- * could trigger BUG by flushing delalloc blocks in journal.
- * There is no delalloc block in non-journal data mode.
- */
- if (val && test_opt(inode->i_sb, DELALLOC)) {
- err = ext4_alloc_da_blocks(inode);
- if (err < 0)
- return err;
- }
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(inode);
inode_dio_wait(inode);
+ /*
+ * Before flushing the journal and switching inode's aops, we have
+ * to flush all dirty data the inode has. There can be outstanding
+ * delayed allocations, there can be unwritten extents created by
+ * fallocate or buffered writes in dioread_nolock mode covered by
+ * dirty data which can be converted only after flushing the dirty
+ * data (and journalled aops don't know how to handle these cases).
+ */
+ if (val) {
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ err = filemap_write_and_wait(inode->i_mapping);
+ if (err < 0) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ ext4_inode_resume_unlocked_dio(inode);
+ return err;
+ }
+ }
+
+ percpu_down_write(&sbi->s_journal_flag_rwsem);
jbd2_journal_lock_updates(journal);
/*
@@ -5477,6 +5581,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
err = jbd2_journal_flush(journal);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
+ percpu_up_write(&sbi->s_journal_flag_rwsem);
ext4_inode_resume_unlocked_dio(inode);
return err;
}
@@ -5485,6 +5590,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
+ percpu_up_write(&sbi->s_journal_flag_rwsem);
+
+ if (val)
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
/* Finally we can mark the inode as dirty. */
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 7497f50cb293..28cc412852af 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -365,7 +365,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
struct dquot *transfer_to[MAXQUOTAS] = { };
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
- if (transfer_to[PRJQUOTA]) {
+ if (!IS_ERR(transfer_to[PRJQUOTA])) {
err = __dquot_transfer(inode, transfer_to);
dqput(transfer_to[PRJQUOTA]);
if (err)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index eeeade76012e..c1ab3ec30423 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1266,6 +1266,7 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
{
int order = 1;
+ int bb_incr = 1 << (e4b->bd_blkbits - 1);
void *bb;
BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
@@ -1278,7 +1279,8 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
/* this block is part of buddy of order 'order' */
return order;
}
- bb += 1 << (e4b->bd_blkbits - order);
+ bb += bb_incr;
+ bb_incr >>= 1;
order++;
}
return 0;
@@ -2583,7 +2585,7 @@ int ext4_mb_init(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned i, j;
- unsigned offset;
+ unsigned offset, offset_incr;
unsigned max;
int ret;
@@ -2612,11 +2614,13 @@ int ext4_mb_init(struct super_block *sb)
i = 1;
offset = 0;
+ offset_incr = 1 << (sb->s_blocksize_bits - 1);
max = sb->s_blocksize << 2;
do {
sbi->s_mb_offsets[i] = offset;
sbi->s_mb_maxs[i] = max;
- offset += 1 << (sb->s_blocksize_bits - i);
+ offset += offset_incr;
+ offset_incr = offset_incr >> 1;
max = max >> 1;
i++;
} while (i <= sb->s_blocksize_bits + 1);
@@ -4935,7 +4939,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
* boundary.
*/
if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
- ext4_warning(sb, "too much blocks added to group %u\n",
+ ext4_warning(sb, "too much blocks added to group %u",
block_group);
err = -EINVAL;
goto error_return;
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 24445275d330..23d436d6f8b8 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -121,7 +121,7 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
__ext4_warning(sb, function, line, "%s", msg);
__ext4_warning(sb, function, line,
"MMP failure info: last update time: %llu, last update "
- "node: %s, last update device: %s\n",
+ "node: %s, last update device: %s",
(long long unsigned int) le64_to_cpu(mmp->mmp_time),
mmp->mmp_nodename, mmp->mmp_bdevname);
}
@@ -353,7 +353,7 @@ skip:
* wait for MMP interval and check mmp_seq.
*/
if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
- ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+ ext4_warning(sb, "MMP startup interrupted, failing mount");
goto failed;
}
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 325cef48b39a..a920c5d29fac 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -400,7 +400,7 @@ data_copy:
/* Even in case of data=writeback it is reasonable to pin
* inode to transaction, to prevent unexpected data loss */
- *err = ext4_jbd2_file_inode(handle, orig_inode);
+ *err = ext4_jbd2_inode_add_write(handle, orig_inode);
unlock_pages:
unlock_page(pagep[0]);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5611ec9348d7..ec4c39952e84 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1107,6 +1107,11 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
}
while (1) {
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto errout;
+ }
+ cond_resched();
block = dx_get_block(frame->at);
ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo,
start_hash, start_minor_hash);
@@ -1613,7 +1618,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
if (nokey)
return ERR_PTR(-ENOKEY);
ext4_warning(inode->i_sb,
- "Inconsistent encryption contexts: %lu/%lu\n",
+ "Inconsistent encryption contexts: %lu/%lu",
(unsigned long) dir->i_ino,
(unsigned long) inode->i_ino);
return ERR_PTR(-EPERM);
@@ -2828,7 +2833,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
* list entries can cause panics at unmount time.
*/
mutex_lock(&sbi->s_orphan_lock);
- list_del(&EXT4_I(inode)->i_orphan);
+ list_del_init(&EXT4_I(inode)->i_orphan);
mutex_unlock(&sbi->s_orphan_lock);
}
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index e4fc8ea45d78..2a01df9cc1c3 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -342,9 +342,7 @@ void ext4_io_submit(struct ext4_io_submit *io)
if (bio) {
int io_op = io->io_wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC : WRITE;
- bio_get(io->io_bio);
submit_bio(io_op, io->io_bio);
- bio_put(io->io_bio);
}
io->io_bio = NULL;
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 34038e3598d5..cf681004b196 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -41,7 +41,7 @@ int ext4_resize_begin(struct super_block *sb)
*/
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
ext4_warning(sb, "There are errors in the filesystem, "
- "so online resizing is not allowed\n");
+ "so online resizing is not allowed");
return -EPERM;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 304c712dbe12..3822a5aedc61 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -859,6 +859,7 @@ static void ext4_put_super(struct super_block *sb)
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
@@ -3416,16 +3417,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
- if (blocksize != PAGE_SIZE) {
- ext4_msg(sb, KERN_ERR,
- "error: unsupported blocksize for dax");
- goto failed_mount;
- }
- if (!sb->s_bdev->bd_disk->fops->direct_access) {
- ext4_msg(sb, KERN_ERR,
- "error: device does not support dax");
+ err = bdev_dax_supported(sb, blocksize);
+ if (err)
goto failed_mount;
- }
}
if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) {
@@ -3930,6 +3924,9 @@ no_journal:
if (!err)
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
+ if (!err)
+ err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
+
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount6;
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 123a7d010efe..a8921112030d 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -22,10 +22,11 @@ ext4_xattr_security_get(const struct xattr_handler *handler,
static int
ext4_xattr_security_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY,
name, value, size, flags);
}
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index 60652fa24cbc..c7765c735714 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -29,10 +29,11 @@ ext4_xattr_trusted_get(const struct xattr_handler *handler,
static int
ext4_xattr_trusted_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED,
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED,
name, value, size, flags);
}
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index 17a446ffecd3..ca20e423034b 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -30,12 +30,13 @@ ext4_xattr_user_get(const struct xattr_handler *handler,
static int
ext4_xattr_user_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- if (!test_opt(dentry->d_sb, XATTR_USER))
+ if (!test_opt(inode->i_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_USER,
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER,
name, value, size, flags);
}
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 00ea56797258..e3decae3acfb 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -50,10 +50,11 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
}
static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, const void *value,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
size_t size, int flags)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
switch (handler->flags) {
case F2FS_XATTR_INDEX_USER:
@@ -69,7 +70,7 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
default:
return -EINVAL;
}
- return f2fs_setxattr(d_inode(dentry), handler->flags, name,
+ return f2fs_setxattr(inode, handler->flags, name,
value, size, NULL, flags);
}
@@ -95,11 +96,10 @@ static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
}
static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, const void *value,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value == NULL)
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3078b679fcd1..c8c4f79c7ce1 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -887,6 +887,8 @@ void fscache_invalidate_writes(struct fscache_cookie *cookie)
put_page(results[i]);
}
+ wake_up_bit(&cookie->flags, 0);
+
_leave("");
}
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b9419058108f..264f07c7754e 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -341,8 +341,10 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
struct dentry *newent;
bool outarg_valid = true;
+ fuse_lock_inode(dir);
err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
&outarg, &inode);
+ fuse_unlock_inode(dir);
if (err == -ENOENT) {
outarg_valid = false;
err = 0;
@@ -1341,7 +1343,9 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx)
fuse_read_fill(req, file, ctx->pos, PAGE_SIZE,
FUSE_READDIR);
}
+ fuse_lock_inode(inode);
fuse_request_send(fc, req);
+ fuse_unlock_inode(inode);
nbytes = req->out.args[0].size;
err = req->out.h.error;
fuse_put_request(fc, req);
@@ -1719,10 +1723,10 @@ static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
return fuse_update_attributes(inode, stat, NULL, NULL);
}
-static int fuse_setxattr(struct dentry *entry, const char *name,
- const void *value, size_t size, int flags)
+static int fuse_setxattr(struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
FUSE_ARGS(args);
struct fuse_setxattr_in inarg;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index eddbe02c4028..929c383432b0 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -110,6 +110,9 @@ struct fuse_inode {
/** Miscellaneous bits describing inode state */
unsigned long state;
+
+ /** Lock for serializing lookup and readdir for back compatibility*/
+ struct mutex mutex;
};
/** FUSE inode state bits */
@@ -540,6 +543,9 @@ struct fuse_conn {
/** write-back cache policy (default is write-through) */
unsigned writeback_cache:1;
+ /** allow parallel lookups and readdir (default is serialized) */
+ unsigned parallel_dirops:1;
+
/*
* The following bitfields are only for optimization purposes
* and hence races in setting them will not cause malfunction
@@ -956,4 +962,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
void fuse_set_initialized(struct fuse_conn *fc);
+void fuse_unlock_inode(struct inode *inode);
+void fuse_lock_inode(struct inode *inode);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1ce67668a8e1..9961d8432ce3 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -97,6 +97,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&fi->queued_writes);
INIT_LIST_HEAD(&fi->writepages);
init_waitqueue_head(&fi->page_waitq);
+ mutex_init(&fi->mutex);
fi->forget = fuse_alloc_forget();
if (!fi->forget) {
kmem_cache_free(fuse_inode_cachep, inode);
@@ -117,6 +118,7 @@ static void fuse_destroy_inode(struct inode *inode)
struct fuse_inode *fi = get_fuse_inode(inode);
BUG_ON(!list_empty(&fi->write_files));
BUG_ON(!list_empty(&fi->queued_writes));
+ mutex_destroy(&fi->mutex);
kfree(fi->forget);
call_rcu(&inode->i_rcu, fuse_i_callback);
}
@@ -351,6 +353,18 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
return 0;
}
+void fuse_lock_inode(struct inode *inode)
+{
+ if (!get_fuse_conn(inode)->parallel_dirops)
+ mutex_lock(&get_fuse_inode(inode)->mutex);
+}
+
+void fuse_unlock_inode(struct inode *inode)
+{
+ if (!get_fuse_conn(inode)->parallel_dirops)
+ mutex_unlock(&get_fuse_inode(inode)->mutex);
+}
+
static void fuse_umount_begin(struct super_block *sb)
{
fuse_abort_conn(get_fuse_conn_super(sb));
@@ -898,6 +912,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->async_dio = 1;
if (arg->flags & FUSE_WRITEBACK_CACHE)
fc->writeback_cache = 1;
+ if (arg->flags & FUSE_PARALLEL_DIROPS)
+ fc->parallel_dirops = 1;
if (arg->time_gran && arg->time_gran <= 1000000000)
fc->sb->s_time_gran = arg->time_gran;
} else {
@@ -928,7 +944,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
- FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
+ FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
+ FUSE_PARALLEL_DIROPS;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 4a01f30e9995..271d93905bac 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -783,12 +783,15 @@ static int get_leaf_nr(struct gfs2_inode *dip, u32 index,
u64 *leaf_out)
{
__be64 *hash;
+ int error;
hash = gfs2_dir_get_hash_table(dip);
- if (IS_ERR(hash))
- return PTR_ERR(hash);
- *leaf_out = be64_to_cpu(*(hash + index));
- return 0;
+ error = PTR_ERR_OR_ZERO(hash);
+
+ if (!error)
+ *leaf_out = be64_to_cpu(*(hash + index));
+
+ return error;
}
static int get_first_leaf(struct gfs2_inode *dip, u32 index,
@@ -798,7 +801,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index,
int error;
error = get_leaf_nr(dip, index, &leaf_no);
- if (!IS_ERR_VALUE(error))
+ if (!error)
error = get_leaf(dip, leaf_no, bh_out);
return error;
@@ -1014,7 +1017,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
index = name->hash >> (32 - dip->i_depth);
error = get_leaf_nr(dip, index, &leaf_no);
- if (IS_ERR_VALUE(error))
+ if (error)
return error;
/* Get the old leaf block */
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index f42ab53bd30d..3a2853504084 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1251,10 +1251,10 @@ int __gfs2_xattr_set(struct inode *inode, const char *name,
}
static int gfs2_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int ret;
diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c
index 064f92f17efc..d9a86919fdf6 100644
--- a/fs/hfs/attr.c
+++ b/fs/hfs/attr.c
@@ -13,10 +13,10 @@
#include "hfs_fs.h"
#include "btree.h"
-int hfs_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+int hfs_setxattr(struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
struct hfs_find_data fd;
hfs_cat_rec rec;
struct hfs_cat_file *file;
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index fa3eed86837c..ee2f385811c8 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -212,7 +212,7 @@ extern void hfs_evict_inode(struct inode *);
extern void hfs_delete_inode(struct inode *);
/* attr.c */
-extern int hfs_setxattr(struct dentry *dentry, const char *name,
+extern int hfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name,
const void *value, size_t size, int flags);
extern ssize_t hfs_getxattr(struct dentry *dentry, struct inode *inode,
const char *name, void *value, size_t size);
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index 4f118d282a7a..d37bb88dc746 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -424,7 +424,7 @@ static int copy_name(char *buffer, const char *xattr_name, int name_len)
return len;
}
-int hfsplus_setxattr(struct dentry *dentry, const char *name,
+int hfsplus_setxattr(struct inode *inode, const char *name,
const void *value, size_t size, int flags,
const char *prefix, size_t prefixlen)
{
@@ -437,8 +437,7 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name,
return -ENOMEM;
strcpy(xattr_name, prefix);
strcpy(xattr_name + prefixlen, name);
- res = __hfsplus_setxattr(d_inode(dentry), xattr_name, value, size,
- flags);
+ res = __hfsplus_setxattr(inode, xattr_name, value, size, flags);
kfree(xattr_name);
return res;
}
@@ -864,8 +863,9 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler,
}
static int hfsplus_osx_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
/*
* Don't allow setting properly prefixed attributes
@@ -880,7 +880,7 @@ static int hfsplus_osx_setxattr(const struct xattr_handler *handler,
* creates), so we pass the name through unmodified (after
* ensuring it doesn't conflict with another namespace).
*/
- return __hfsplus_setxattr(d_inode(dentry), name, buffer, size, flags);
+ return __hfsplus_setxattr(inode, name, buffer, size, flags);
}
const struct xattr_handler hfsplus_xattr_osx_handler = {
diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h
index d04ba6f58df2..68f6b539371f 100644
--- a/fs/hfsplus/xattr.h
+++ b/fs/hfsplus/xattr.h
@@ -21,7 +21,7 @@ extern const struct xattr_handler *hfsplus_xattr_handlers[];
int __hfsplus_setxattr(struct inode *inode, const char *name,
const void *value, size_t size, int flags);
-int hfsplus_setxattr(struct dentry *dentry, const char *name,
+int hfsplus_setxattr(struct inode *inode, const char *name,
const void *value, size_t size, int flags,
const char *prefix, size_t prefixlen);
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
index ae2ca8c2e335..37b3efa733ef 100644
--- a/fs/hfsplus/xattr_security.c
+++ b/fs/hfsplus/xattr_security.c
@@ -23,10 +23,11 @@ static int hfsplus_security_getxattr(const struct xattr_handler *handler,
}
static int hfsplus_security_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- return hfsplus_setxattr(dentry, name, buffer, size, flags,
+ return hfsplus_setxattr(inode, name, buffer, size, flags,
XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
}
diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c
index eae2947060aa..94519d6c627d 100644
--- a/fs/hfsplus/xattr_trusted.c
+++ b/fs/hfsplus/xattr_trusted.c
@@ -21,10 +21,11 @@ static int hfsplus_trusted_getxattr(const struct xattr_handler *handler,
}
static int hfsplus_trusted_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- return hfsplus_setxattr(dentry, name, buffer, size, flags,
+ return hfsplus_setxattr(inode, name, buffer, size, flags,
XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c
index 3c9eec3e4c7b..fae6c0ea0030 100644
--- a/fs/hfsplus/xattr_user.c
+++ b/fs/hfsplus/xattr_user.c
@@ -21,10 +21,11 @@ static int hfsplus_user_getxattr(const struct xattr_handler *handler,
}
static int hfsplus_user_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- return hfsplus_setxattr(dentry, name, buffer, size, flags,
+ return hfsplus_setxattr(inode, name, buffer, size, flags,
XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
}
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 458cf463047b..82067ca22f2b 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -15,6 +15,7 @@
#include <linux/sched.h>
#include <linux/bitmap.h>
#include <linux/slab.h>
+#include <linux/seq_file.h>
/* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */
@@ -453,10 +454,6 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
int lowercase, eas, chk, errs, chkdsk, timeshift;
int o;
struct hpfs_sb_info *sbi = hpfs_sb(s);
- char *new_opts = kstrdup(data, GFP_KERNEL);
-
- if (!new_opts)
- return -ENOMEM;
sync_filesystem(s);
@@ -493,17 +490,44 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
if (!(*flags & MS_RDONLY)) mark_dirty(s, 1);
- replace_mount_options(s, new_opts);
-
hpfs_unlock(s);
return 0;
out_err:
hpfs_unlock(s);
- kfree(new_opts);
return -EINVAL;
}
+static int hpfs_show_options(struct seq_file *seq, struct dentry *root)
+{
+ struct hpfs_sb_info *sbi = hpfs_sb(root->d_sb);
+
+ seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbi->sb_uid));
+ seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbi->sb_gid));
+ seq_printf(seq, ",umask=%03o", (~sbi->sb_mode & 0777));
+ if (sbi->sb_lowercase)
+ seq_printf(seq, ",case=lower");
+ if (!sbi->sb_chk)
+ seq_printf(seq, ",check=none");
+ if (sbi->sb_chk == 2)
+ seq_printf(seq, ",check=strict");
+ if (!sbi->sb_err)
+ seq_printf(seq, ",errors=continue");
+ if (sbi->sb_err == 2)
+ seq_printf(seq, ",errors=panic");
+ if (!sbi->sb_chkdsk)
+ seq_printf(seq, ",chkdsk=no");
+ if (sbi->sb_chkdsk == 2)
+ seq_printf(seq, ",chkdsk=always");
+ if (!sbi->sb_eas)
+ seq_printf(seq, ",eas=no");
+ if (sbi->sb_eas == 1)
+ seq_printf(seq, ",eas=ro");
+ if (sbi->sb_timeshift)
+ seq_printf(seq, ",timeshift=%d", sbi->sb_timeshift);
+ return 0;
+}
+
/* Super operations */
static const struct super_operations hpfs_sops =
@@ -514,7 +538,7 @@ static const struct super_operations hpfs_sops =
.put_super = hpfs_put_super,
.statfs = hpfs_statfs,
.remount_fs = hpfs_remount_fs,
- .show_options = generic_show_options,
+ .show_options = hpfs_show_options,
};
static int hpfs_fill_super(struct super_block *s, void *options, int silent)
@@ -537,8 +561,6 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
int o;
- save_mount_options(s, options);
-
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi) {
return -ENOMEM;
diff --git a/fs/internal.h b/fs/internal.h
index b71deeecea17..f57ced528cde 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -130,6 +130,7 @@ extern int invalidate_inodes(struct super_block *, bool);
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern int d_set_mounted(struct dentry *dentry);
extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
+extern struct dentry *d_alloc_cursor(struct dentry *);
/*
* read_write.c
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2ad98d6e19f4..70078096117d 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -219,6 +219,8 @@ static int journal_submit_data_buffers(journal_t *journal,
spin_lock(&journal->j_list_lock);
list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+ if (!(jinode->i_flags & JI_WRITE_DATA))
+ continue;
mapping = jinode->i_vfs_inode->i_mapping;
jinode->i_flags |= JI_COMMIT_RUNNING;
spin_unlock(&journal->j_list_lock);
@@ -256,6 +258,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
/* For locking, see the comment in journal_submit_data_buffers() */
spin_lock(&journal->j_list_lock);
list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+ if (!(jinode->i_flags & JI_WAIT_DATA))
+ continue;
jinode->i_flags |= JI_COMMIT_RUNNING;
spin_unlock(&journal->j_list_lock);
err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 435f0b26ac20..e3ca4b4cac84 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -94,7 +94,8 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
EXPORT_SYMBOL(jbd2_journal_invalidatepage);
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
EXPORT_SYMBOL(jbd2_journal_force_commit);
-EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_inode_add_write);
+EXPORT_SYMBOL(jbd2_journal_inode_add_wait);
EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
@@ -2328,18 +2329,10 @@ void *jbd2_alloc(size_t size, gfp_t flags)
BUG_ON(size & (size-1)); /* Must be a power of 2 */
- flags |= __GFP_REPEAT;
- if (size == PAGE_SIZE)
- ptr = (void *)__get_free_pages(flags, 0);
- else if (size > PAGE_SIZE) {
- int order = get_order(size);
-
- if (order < 3)
- ptr = (void *)__get_free_pages(flags, order);
- else
- ptr = vmalloc(size);
- } else
+ if (size < PAGE_SIZE)
ptr = kmem_cache_alloc(get_slab(size), flags);
+ else
+ ptr = (void *)__get_free_pages(flags, get_order(size));
/* Check alignment; SLUB has gotten this wrong in the past,
* and this can lead to user data corruption! */
@@ -2350,20 +2343,10 @@ void *jbd2_alloc(size_t size, gfp_t flags)
void jbd2_free(void *ptr, size_t size)
{
- if (size == PAGE_SIZE) {
- free_pages((unsigned long)ptr, 0);
- return;
- }
- if (size > PAGE_SIZE) {
- int order = get_order(size);
-
- if (order < 3)
- free_pages((unsigned long)ptr, order);
- else
- vfree(ptr);
- return;
- }
- kmem_cache_free(get_slab(size), ptr);
+ if (size < PAGE_SIZE)
+ kmem_cache_free(get_slab(size), ptr);
+ else
+ free_pages((unsigned long)ptr, get_order(size));
};
/*
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 2c56c3e32194..1749519b362f 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2462,7 +2462,8 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
/*
* File inode in the inode list of the handle's transaction
*/
-int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
+static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
+ unsigned long flags)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal;
@@ -2487,12 +2488,14 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
* and if jinode->i_next_transaction == transaction, commit code
* will only file the inode where we want it.
*/
- if (jinode->i_transaction == transaction ||
- jinode->i_next_transaction == transaction)
+ if ((jinode->i_transaction == transaction ||
+ jinode->i_next_transaction == transaction) &&
+ (jinode->i_flags & flags) == flags)
return 0;
spin_lock(&journal->j_list_lock);
-
+ jinode->i_flags |= flags;
+ /* Is inode already attached where we need it? */
if (jinode->i_transaction == transaction ||
jinode->i_next_transaction == transaction)
goto done;
@@ -2523,6 +2526,17 @@ done:
return 0;
}
+int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode)
+{
+ return jbd2_journal_file_inode(handle, jinode,
+ JI_WRITE_DATA | JI_WAIT_DATA);
+}
+
+int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode)
+{
+ return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA);
+}
+
/*
* File truncate and transaction commit interact with each other in a
* non-trivial way. If a transaction writing data block A is
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index 3ed9a4b49778..c2332e30f218 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -57,10 +57,11 @@ static int jffs2_security_getxattr(const struct xattr_handler *handler,
}
static int jffs2_security_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY,
+ return do_jffs2_setxattr(inode, JFFS2_XPREFIX_SECURITY,
name, buffer, size, flags);
}
diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c
index 4ebecff1d922..5d6030826c52 100644
--- a/fs/jffs2/xattr_trusted.c
+++ b/fs/jffs2/xattr_trusted.c
@@ -25,10 +25,11 @@ static int jffs2_trusted_getxattr(const struct xattr_handler *handler,
}
static int jffs2_trusted_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED,
+ return do_jffs2_setxattr(inode, JFFS2_XPREFIX_TRUSTED,
name, buffer, size, flags);
}
diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c
index bce249e1b277..9d027b4abcf9 100644
--- a/fs/jffs2/xattr_user.c
+++ b/fs/jffs2/xattr_user.c
@@ -25,10 +25,11 @@ static int jffs2_user_getxattr(const struct xattr_handler *handler,
}
static int jffs2_user_setxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *buffer, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *buffer,
+ size_t size, int flags)
{
- return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_USER,
+ return do_jffs2_setxattr(inode, JFFS2_XPREFIX_USER,
name, buffer, size, flags);
}
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index beb182b503b3..0bf3c33aedff 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -943,11 +943,10 @@ static int jfs_xattr_get(const struct xattr_handler *handler,
}
static int jfs_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
name = xattr_full_name(handler, name);
return __jfs_xattr_set(inode, name, value, size, flags);
}
@@ -962,11 +961,10 @@ static int jfs_xattr_get_os2(const struct xattr_handler *handler,
}
static int jfs_xattr_set_os2(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
if (is_known_namespace(name))
return -EOPNOTSUPP;
return __jfs_xattr_set(inode, name, value, size, flags);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 1719649d7ad7..63b925d5ba1e 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -160,10 +160,11 @@ static int kernfs_node_setsecdata(struct kernfs_node *kn, void **secdata,
return 0;
}
-int kernfs_iop_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+int kernfs_iop_setxattr(struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_node *kn = inode->i_private;
struct kernfs_iattrs *attrs;
void *secdata;
int error;
@@ -175,11 +176,11 @@ int kernfs_iop_setxattr(struct dentry *dentry, const char *name,
if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
- error = security_inode_setsecurity(d_inode(dentry), suffix,
+ error = security_inode_setsecurity(inode, suffix,
value, size, flags);
if (error)
return error;
- error = security_inode_getsecctx(d_inode(dentry),
+ error = security_inode_getsecctx(inode,
&secdata, &secdata_len);
if (error)
return error;
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 45c9192c276e..37159235ac10 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -81,7 +81,8 @@ int kernfs_iop_permission(struct inode *inode, int mask);
int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
-int kernfs_iop_setxattr(struct dentry *dentry, const char *name, const void *value,
+int kernfs_iop_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
size_t size, int flags);
int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
ssize_t kernfs_iop_getxattr(struct dentry *dentry, struct inode *inode,
diff --git a/fs/libfs.c b/fs/libfs.c
index 8765ff1adc07..74dc8b9e7f53 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -71,9 +71,7 @@ EXPORT_SYMBOL(simple_lookup);
int dcache_dir_open(struct inode *inode, struct file *file)
{
- static struct qstr cursor_name = QSTR_INIT(".", 1);
-
- file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
+ file->private_data = d_alloc_cursor(file->f_path.dentry);
return file->private_data ? 0 : -ENOMEM;
}
@@ -86,6 +84,61 @@ int dcache_dir_close(struct inode *inode, struct file *file)
}
EXPORT_SYMBOL(dcache_dir_close);
+/* parent is locked at least shared */
+static struct dentry *next_positive(struct dentry *parent,
+ struct list_head *from,
+ int count)
+{
+ unsigned *seq = &parent->d_inode->i_dir_seq, n;
+ struct dentry *res;
+ struct list_head *p;
+ bool skipped;
+ int i;
+
+retry:
+ i = count;
+ skipped = false;
+ n = smp_load_acquire(seq) & ~1;
+ res = NULL;
+ rcu_read_lock();
+ for (p = from->next; p != &parent->d_subdirs; p = p->next) {
+ struct dentry *d = list_entry(p, struct dentry, d_child);
+ if (!simple_positive(d)) {
+ skipped = true;
+ } else if (!--i) {
+ res = d;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ if (skipped) {
+ smp_rmb();
+ if (unlikely(*seq != n))
+ goto retry;
+ }
+ return res;
+}
+
+static void move_cursor(struct dentry *cursor, struct list_head *after)
+{
+ struct dentry *parent = cursor->d_parent;
+ unsigned n, *seq = &parent->d_inode->i_dir_seq;
+ spin_lock(&parent->d_lock);
+ for (;;) {
+ n = *seq;
+ if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
+ break;
+ cpu_relax();
+ }
+ __list_del(cursor->d_child.prev, cursor->d_child.next);
+ if (after)
+ list_add(&cursor->d_child, after);
+ else
+ list_add_tail(&cursor->d_child, &parent->d_subdirs);
+ smp_store_release(seq, n + 2);
+ spin_unlock(&parent->d_lock);
+}
+
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry *dentry = file->f_path.dentry;
@@ -101,25 +154,14 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
if (offset != file->f_pos) {
file->f_pos = offset;
if (file->f_pos >= 2) {
- struct list_head *p;
struct dentry *cursor = file->private_data;
+ struct dentry *to;
loff_t n = file->f_pos - 2;
- spin_lock(&dentry->d_lock);
- /* d_lock not required for cursor */
- list_del(&cursor->d_child);
- p = dentry->d_subdirs.next;
- while (n && p != &dentry->d_subdirs) {
- struct dentry *next;
- next = list_entry(p, struct dentry, d_child);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- if (simple_positive(next))
- n--;
- spin_unlock(&next->d_lock);
- p = p->next;
- }
- list_add_tail(&cursor->d_child, p);
- spin_unlock(&dentry->d_lock);
+ inode_lock_shared(dentry->d_inode);
+ to = next_positive(dentry, &dentry->d_subdirs, n);
+ move_cursor(cursor, to ? &to->d_child : NULL);
+ inode_unlock_shared(dentry->d_inode);
}
}
return offset;
@@ -142,36 +184,25 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dentry = file->f_path.dentry;
struct dentry *cursor = file->private_data;
- struct list_head *p, *q = &cursor->d_child;
+ struct list_head *p = &cursor->d_child;
+ struct dentry *next;
+ bool moved = false;
if (!dir_emit_dots(file, ctx))
return 0;
- spin_lock(&dentry->d_lock);
- if (ctx->pos == 2)
- list_move(q, &dentry->d_subdirs);
- for (p = q->next; p != &dentry->d_subdirs; p = p->next) {
- struct dentry *next = list_entry(p, struct dentry, d_child);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- if (!simple_positive(next)) {
- spin_unlock(&next->d_lock);
- continue;
- }
-
- spin_unlock(&next->d_lock);
- spin_unlock(&dentry->d_lock);
+ if (ctx->pos == 2)
+ p = &dentry->d_subdirs;
+ while ((next = next_positive(dentry, p, 1)) != NULL) {
if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
d_inode(next)->i_ino, dt_type(d_inode(next))))
- return 0;
- spin_lock(&dentry->d_lock);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- /* next is still alive */
- list_move(q, p);
- spin_unlock(&next->d_lock);
- p = q;
+ break;
+ moved = true;
+ p = &next->d_child;
ctx->pos++;
}
- spin_unlock(&dentry->d_lock);
+ if (moved)
+ move_cursor(cursor, p);
return 0;
}
EXPORT_SYMBOL(dcache_readdir);
@@ -1118,8 +1149,9 @@ static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr)
return -EPERM;
}
-static int empty_dir_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+static int empty_dir_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
return -EOPNOTSUPP;
}
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 154a107cd376..fc4084ef4736 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -335,12 +335,17 @@ static struct notifier_block lockd_inet6addr_notifier = {
};
#endif
-static void lockd_svc_exit_thread(void)
+static void lockd_unregister_notifiers(void)
{
unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
#if IS_ENABLED(CONFIG_IPV6)
unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
#endif
+}
+
+static void lockd_svc_exit_thread(void)
+{
+ lockd_unregister_notifiers();
svc_exit_thread(nlmsvc_rqst);
}
@@ -462,7 +467,7 @@ int lockd_up(struct net *net)
* Note: svc_serv structures have an initial use count of 1,
* so we exit through here on both success and failure.
*/
-err_net:
+err_put:
svc_destroy(serv);
err_create:
mutex_unlock(&nlmsvc_mutex);
@@ -470,7 +475,9 @@ err_create:
err_start:
lockd_down_net(serv, net);
- goto err_net;
+err_net:
+ lockd_unregister_notifiers();
+ goto err_put;
}
EXPORT_SYMBOL_GPL(lockd_up);
diff --git a/fs/locks.c b/fs/locks.c
index 7c5f91be9b65..ee1b15f6fc13 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1628,7 +1628,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
{
struct file_lock *fl, *my_fl = NULL, *lease;
struct dentry *dentry = filp->f_path.dentry;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct file_lock_context *ctx;
bool is_deleg = (*flp)->fl_flags & FL_DELEG;
int error;
diff --git a/fs/namei.c b/fs/namei.c
index 5375571cf6e1..70580ab1445c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -35,6 +35,7 @@
#include <linux/fs_struct.h>
#include <linux/posix_acl.h>
#include <linux/hash.h>
+#include <linux/bitops.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -1415,21 +1416,28 @@ static void follow_mount(struct path *path)
}
}
+static int path_parent_directory(struct path *path)
+{
+ struct dentry *old = path->dentry;
+ /* rare case of legitimate dget_parent()... */
+ path->dentry = dget_parent(path->dentry);
+ dput(old);
+ if (unlikely(!path_connected(path)))
+ return -ENOENT;
+ return 0;
+}
+
static int follow_dotdot(struct nameidata *nd)
{
while(1) {
- struct dentry *old = nd->path.dentry;
-
if (nd->path.dentry == nd->root.dentry &&
nd->path.mnt == nd->root.mnt) {
break;
}
if (nd->path.dentry != nd->path.mnt->mnt_root) {
- /* rare case of legitimate dget_parent()... */
- nd->path.dentry = dget_parent(nd->path.dentry);
- dput(old);
- if (unlikely(!path_connected(&nd->path)))
- return -ENOENT;
+ int ret = path_parent_directory(&nd->path);
+ if (ret)
+ return ret;
break;
}
if (!follow_up(&nd->path))
@@ -1797,74 +1805,144 @@ static int walk_component(struct nameidata *nd, int flags)
#include <asm/word-at-a-time.h>
-#ifdef CONFIG_64BIT
+#ifdef HASH_MIX
-static inline unsigned int fold_hash(unsigned long hash)
-{
- return hash_64(hash, 32);
-}
+/* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */
+
+#elif defined(CONFIG_64BIT)
+/*
+ * Register pressure in the mixing function is an issue, particularly
+ * on 32-bit x86, but almost any function requires one state value and
+ * one temporary. Instead, use a function designed for two state values
+ * and no temporaries.
+ *
+ * This function cannot create a collision in only two iterations, so
+ * we have two iterations to achieve avalanche. In those two iterations,
+ * we have six layers of mixing, which is enough to spread one bit's
+ * influence out to 2^6 = 64 state bits.
+ *
+ * Rotate constants are scored by considering either 64 one-bit input
+ * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the
+ * probability of that delta causing a change to each of the 128 output
+ * bits, using a sample of random initial states.
+ *
+ * The Shannon entropy of the computed probabilities is then summed
+ * to produce a score. Ideally, any input change has a 50% chance of
+ * toggling any given output bit.
+ *
+ * Mixing scores (in bits) for (12,45):
+ * Input delta: 1-bit 2-bit
+ * 1 round: 713.3 42542.6
+ * 2 rounds: 2753.7 140389.8
+ * 3 rounds: 5954.1 233458.2
+ * 4 rounds: 7862.6 256672.2
+ * Perfect: 8192 258048
+ * (64*128) (64*63/2 * 128)
+ */
+#define HASH_MIX(x, y, a) \
+ ( x ^= (a), \
+ y ^= x, x = rol64(x,12),\
+ x += y, y = rol64(y,45),\
+ y *= 9 )
/*
- * This is George Marsaglia's XORSHIFT generator.
- * It implements a maximum-period LFSR in only a few
- * instructions. It also has the property (required
- * by hash_name()) that mix_hash(0) = 0.
+ * Fold two longs into one 32-bit hash value. This must be fast, but
+ * latency isn't quite as critical, as there is a fair bit of additional
+ * work done before the hash value is used.
*/
-static inline unsigned long mix_hash(unsigned long hash)
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
- hash ^= hash << 13;
- hash ^= hash >> 7;
- hash ^= hash << 17;
- return hash;
+ y ^= x * GOLDEN_RATIO_64;
+ y *= GOLDEN_RATIO_64;
+ return y >> 32;
}
#else /* 32-bit case */
-#define fold_hash(x) (x)
+/*
+ * Mixing scores (in bits) for (7,20):
+ * Input delta: 1-bit 2-bit
+ * 1 round: 330.3 9201.6
+ * 2 rounds: 1246.4 25475.4
+ * 3 rounds: 1907.1 31295.1
+ * 4 rounds: 2042.3 31718.6
+ * Perfect: 2048 31744
+ * (32*64) (32*31/2 * 64)
+ */
+#define HASH_MIX(x, y, a) \
+ ( x ^= (a), \
+ y ^= x, x = rol32(x, 7),\
+ x += y, y = rol32(y,20),\
+ y *= 9 )
-static inline unsigned long mix_hash(unsigned long hash)
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
- hash ^= hash << 13;
- hash ^= hash >> 17;
- hash ^= hash << 5;
- return hash;
+ /* Use arch-optimized multiply if one exists */
+ return __hash_32(y ^ __hash_32(x));
}
#endif
-unsigned int full_name_hash(const unsigned char *name, unsigned int len)
+/*
+ * Return the hash of a string of known length. This is carfully
+ * designed to match hash_name(), which is the more critical function.
+ * In particular, we must end by hashing a final word containing 0..7
+ * payload bytes, to match the way that hash_name() iterates until it
+ * finds the delimiter after the name.
+ */
+unsigned int full_name_hash(const char *name, unsigned int len)
{
- unsigned long a, hash = 0;
+ unsigned long a, x = 0, y = 0;
for (;;) {
+ if (!len)
+ goto done;
a = load_unaligned_zeropad(name);
if (len < sizeof(unsigned long))
break;
- hash = mix_hash(hash + a);
+ HASH_MIX(x, y, a);
name += sizeof(unsigned long);
len -= sizeof(unsigned long);
- if (!len)
- goto done;
}
- hash += a & bytemask_from_count(len);
+ x ^= a & bytemask_from_count(len);
done:
- return fold_hash(hash);
+ return fold_hash(x, y);
}
EXPORT_SYMBOL(full_name_hash);
+/* Return the "hash_len" (hash and length) of a null-terminated string */
+u64 hashlen_string(const char *name)
+{
+ unsigned long a = 0, x = 0, y = 0, adata, mask, len;
+ const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+
+ len = -sizeof(unsigned long);
+ do {
+ HASH_MIX(x, y, a);
+ len += sizeof(unsigned long);
+ a = load_unaligned_zeropad(name+len);
+ } while (!has_zero(a, &adata, &constants));
+
+ adata = prep_zero_mask(a, adata, &constants);
+ mask = create_zero_mask(adata);
+ x ^= a & zero_bytemask(mask);
+
+ return hashlen_create(fold_hash(x, y), len + find_zero(mask));
+}
+EXPORT_SYMBOL(hashlen_string);
+
/*
* Calculate the length and hash of the path component, and
* return the "hash_len" as the result.
*/
static inline u64 hash_name(const char *name)
{
- unsigned long a, b, adata, bdata, mask, hash, len;
+ unsigned long a = 0, b, x = 0, y = 0, adata, bdata, mask, len;
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
- hash = a = 0;
len = -sizeof(unsigned long);
do {
- hash = mix_hash(hash + a);
+ HASH_MIX(x, y, a);
len += sizeof(unsigned long);
a = load_unaligned_zeropad(name+len);
b = a ^ REPEAT_BYTE('/');
@@ -1872,25 +1950,40 @@ static inline u64 hash_name(const char *name)
adata = prep_zero_mask(a, adata, &constants);
bdata = prep_zero_mask(b, bdata, &constants);
-
mask = create_zero_mask(adata | bdata);
+ x ^= a & zero_bytemask(mask);
- hash += a & zero_bytemask(mask);
- len += find_zero(mask);
- return hashlen_create(fold_hash(hash), len);
+ return hashlen_create(fold_hash(x, y), len + find_zero(mask));
}
-#else
+#else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */
-unsigned int full_name_hash(const unsigned char *name, unsigned int len)
+/* Return the hash of a string of known length */
+unsigned int full_name_hash(const char *name, unsigned int len)
{
unsigned long hash = init_name_hash();
while (len--)
- hash = partial_name_hash(*name++, hash);
+ hash = partial_name_hash((unsigned char)*name++, hash);
return end_name_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);
+/* Return the "hash_len" (hash and length) of a null-terminated string */
+u64 hashlen_string(const char *name)
+{
+ unsigned long hash = init_name_hash();
+ unsigned long len = 0, c;
+
+ c = (unsigned char)*name;
+ while (c) {
+ len++;
+ hash = partial_name_hash(c, hash);
+ c = (unsigned char)name[len];
+ }
+ return hashlen_create(end_name_hash(hash), len);
+}
+EXPORT_SYMBOL(hashlen_string);
+
/*
* We know there's a real path component here of at least
* one character.
@@ -1934,7 +2027,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
int type;
err = may_lookup(nd);
- if (err)
+ if (err)
return err;
hash_len = hash_name(name);
@@ -2428,6 +2521,34 @@ struct dentry *lookup_one_len_unlocked(const char *name,
}
EXPORT_SYMBOL(lookup_one_len_unlocked);
+#ifdef CONFIG_UNIX98_PTYS
+int path_pts(struct path *path)
+{
+ /* Find something mounted on "pts" in the same directory as
+ * the input path.
+ */
+ struct dentry *child, *parent;
+ struct qstr this;
+ int ret;
+
+ ret = path_parent_directory(path);
+ if (ret)
+ return ret;
+
+ parent = path->dentry;
+ this.name = "pts";
+ this.len = 3;
+ child = d_hash_and_lookup(parent, &this);
+ if (!child)
+ return -ENOENT;
+
+ path->dentry = child;
+ dput(parent);
+ follow_mount(path);
+ return 0;
+}
+#endif
+
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
struct path *path, int *empty)
{
@@ -2909,9 +3030,13 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
}
if (*opened & FILE_CREATED)
fsnotify_create(dir, dentry);
- path->dentry = dentry;
- path->mnt = nd->path.mnt;
- return 1;
+ if (unlikely(d_is_negative(dentry))) {
+ error = -ENOENT;
+ } else {
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
+ return 1;
+ }
}
}
dput(dentry);
@@ -3080,9 +3205,7 @@ static int do_last(struct nameidata *nd,
int acc_mode = op->acc_mode;
unsigned seq;
struct inode *inode;
- struct path save_parent = { .dentry = NULL, .mnt = NULL };
struct path path;
- bool retried = false;
int error;
nd->flags &= ~LOOKUP_PARENT;
@@ -3125,7 +3248,6 @@ static int do_last(struct nameidata *nd,
return -EISDIR;
}
-retry_lookup:
if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
error = mnt_want_write(nd->path.mnt);
if (!error)
@@ -3177,6 +3299,10 @@ retry_lookup:
got_write = false;
}
+ error = follow_managed(&path, nd);
+ if (unlikely(error < 0))
+ return error;
+
if (unlikely(d_is_negative(path.dentry))) {
path_to_nameidata(&path, nd);
return -ENOENT;
@@ -3192,10 +3318,6 @@ retry_lookup:
return -EEXIST;
}
- error = follow_managed(&path, nd);
- if (unlikely(error < 0))
- return error;
-
seq = 0; /* out of RCU mode, so the value doesn't matter */
inode = d_backing_inode(path.dentry);
finish_lookup:
@@ -3206,23 +3328,14 @@ finish_lookup:
if (unlikely(error))
return error;
- if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
- path_to_nameidata(&path, nd);
- } else {
- save_parent.dentry = nd->path.dentry;
- save_parent.mnt = mntget(path.mnt);
- nd->path.dentry = path.dentry;
-
- }
+ path_to_nameidata(&path, nd);
nd->inode = inode;
nd->seq = seq;
/* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */
finish_open:
error = complete_walk(nd);
- if (error) {
- path_put(&save_parent);
+ if (error)
return error;
- }
audit_inode(nd->name, nd->path.dentry, 0);
error = -EISDIR;
if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
@@ -3245,13 +3358,9 @@ finish_open_created:
goto out;
BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
error = vfs_open(&nd->path, file, current_cred());
- if (!error) {
- *opened |= FILE_OPENED;
- } else {
- if (error == -EOPENSTALE)
- goto stale_open;
+ if (error)
goto out;
- }
+ *opened |= FILE_OPENED;
opened:
error = open_check_o_direct(file);
if (!error)
@@ -3267,26 +3376,7 @@ out:
}
if (got_write)
mnt_drop_write(nd->path.mnt);
- path_put(&save_parent);
return error;
-
-stale_open:
- /* If no saved parent or already retried then can't retry */
- if (!save_parent.dentry || retried)
- goto out;
-
- BUG_ON(save_parent.dentry != dir);
- path_put(&nd->path);
- nd->path = save_parent;
- nd->inode = dir->d_inode;
- save_parent.mnt = NULL;
- save_parent.dentry = NULL;
- if (got_write) {
- mnt_drop_write(nd->path.mnt);
- got_write = false;
- }
- retried = true;
- goto retry_lookup;
}
static int do_tmpfile(struct nameidata *nd, unsigned flags,
@@ -4542,7 +4632,6 @@ int readlink_copy(char __user *buffer, int buflen, const char *link)
out:
return len;
}
-EXPORT_SYMBOL(readlink_copy);
/*
* A helper for ->readlink(). This should be used *ONLY* for symlinks that
diff --git a/fs/namespace.c b/fs/namespace.c
index 4fb1691b4355..419f746d851d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1562,6 +1562,7 @@ void __detach_mounts(struct dentry *dentry)
goto out_unlock;
lock_mount_hash();
+ event++;
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
@@ -2409,8 +2410,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
}
if (type->fs_flags & FS_USERNS_VISIBLE) {
- if (!fs_fully_visible(type, &mnt_flags))
+ if (!fs_fully_visible(type, &mnt_flags)) {
+ put_filesystem(type);
return -EPERM;
+ }
}
}
@@ -3245,6 +3248,10 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC)
mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC);
+ /* Don't miss readonly hidden in the superblock flags */
+ if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY)
+ mnt_flags |= MNT_LOCK_READONLY;
+
/* Verify the mount flags are equal to or more permissive
* than the proposed new mount.
*/
@@ -3271,7 +3278,7 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
struct inode *inode = child->mnt_mountpoint->d_inode;
/* Only worry about locked mounts */
- if (!(mnt_flags & MNT_LOCKED))
+ if (!(child->mnt.mnt_flags & MNT_LOCKED))
continue;
/* Is the directory permanetly empty? */
if (!is_empty_dir_inode(inode))
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 618ced381a14..aaa2e8d3df6f 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -217,7 +217,8 @@ static u32 initiate_file_draining(struct nfs_client *clp,
}
if (pnfs_mark_matching_lsegs_return(lo, &free_me_list,
- &args->cbl_range)) {
+ &args->cbl_range,
+ be32_to_cpu(args->cbl_stateid.seqid))) {
rv = NFS4_OK;
goto unlock;
}
@@ -500,8 +501,10 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
cps->slot = slot;
/* The ca_maxresponsesize_cached is 0 with no DRC */
- if (args->csa_cachethis != 0)
- return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
+ if (args->csa_cachethis != 0) {
+ status = htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
+ goto out_unlock;
+ }
/*
* Check for pending referring calls. If a match is found, a
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 976c90608e56..d81f96aacd51 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -146,10 +146,16 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
p = read_buf(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
- memcpy(stateid, p, NFS4_STATEID_SIZE);
+ memcpy(stateid->data, p, NFS4_STATEID_SIZE);
return 0;
}
+static __be32 decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_DELEGATION_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound_hdr_arg *hdr)
{
__be32 *p;
@@ -211,7 +217,7 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr,
__be32 *p;
__be32 status;
- status = decode_stateid(xdr, &args->stateid);
+ status = decode_delegation_stateid(xdr, &args->stateid);
if (unlikely(status != 0))
goto out;
p = read_buf(xdr, 4);
@@ -227,6 +233,11 @@ out:
}
#if defined(CONFIG_NFS_V4_1)
+static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_LAYOUT_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
struct xdr_stream *xdr,
@@ -263,7 +274,7 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
}
p = xdr_decode_hyper(p, &args->cbl_range.offset);
p = xdr_decode_hyper(p, &args->cbl_range.length);
- status = decode_stateid(xdr, &args->cbl_stateid);
+ status = decode_layout_stateid(xdr, &args->cbl_stateid);
if (unlikely(status != 0))
goto out;
} else if (args->cbl_recall_type == RETURN_FSID) {
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5166adcfc0fb..322c2585bc34 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -875,15 +875,16 @@ int nfs_delegations_present(struct nfs_client *clp)
/**
* nfs4_copy_delegation_stateid - Copy inode's state ID information
- * @dst: stateid data structure to fill in
* @inode: inode to check
* @flags: delegation type requirement
+ * @dst: stateid data structure to fill in
+ * @cred: optional argument to retrieve credential
*
* Returns "true" and fills in "dst->data" * if inode had a delegation,
* otherwise "false" is returned.
*/
-bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
- fmode_t flags)
+bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags,
+ nfs4_stateid *dst, struct rpc_cred **cred)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_delegation *delegation;
@@ -896,6 +897,8 @@ bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
if (ret) {
nfs4_stateid_copy(dst, &delegation->stateid);
nfs_mark_delegation_referenced(delegation);
+ if (cred)
+ *cred = get_rpccred(delegation->cred);
}
rcu_read_unlock();
return ret;
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 333063e032f0..64724d252a79 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -56,7 +56,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
-bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
+bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
int nfs4_have_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index aaf7bd0cbae2..d8015a03db4c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -424,12 +424,17 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
static
int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
{
+ struct inode *inode;
struct nfs_inode *nfsi;
if (d_really_is_negative(dentry))
return 0;
- nfsi = NFS_I(d_inode(dentry));
+ inode = d_inode(dentry);
+ if (is_bad_inode(inode) || NFS_STALE(inode))
+ return 0;
+
+ nfsi = NFS_I(inode);
if (entry->fattr->fileid == nfsi->fileid)
return 1;
if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
@@ -1363,7 +1368,6 @@ EXPORT_SYMBOL_GPL(nfs_dentry_operations);
struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *res;
- struct dentry *parent;
struct inode *inode = NULL;
struct nfs_fh *fhandle = NULL;
struct nfs_fattr *fattr = NULL;
@@ -1393,7 +1397,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
if (IS_ERR(label))
goto out;
- parent = dentry->d_parent;
/* Protect against concurrent sillydeletes */
trace_nfs_lookup_enter(dir, dentry, flags);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
@@ -1536,9 +1539,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
err = PTR_ERR(inode);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
put_nfs_open_context(ctx);
+ d_drop(dentry);
switch (err) {
case -ENOENT:
- d_drop(dentry);
d_add(dentry, NULL);
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
break;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 741a92c470bb..c7326c2af2c3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -87,6 +87,7 @@ struct nfs_direct_req {
int mirror_count;
ssize_t count, /* bytes actually processed */
+ max_count, /* max expected count */
bytes_left, /* bytes left to be sent */
io_start, /* start of IO */
error; /* any reported error */
@@ -123,6 +124,8 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
int i;
ssize_t count;
+ WARN_ON_ONCE(dreq->count >= dreq->max_count);
+
if (dreq->mirror_count == 1) {
dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
dreq->count += hdr->good_bytes;
@@ -275,7 +278,7 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
struct nfs_direct_req *dreq)
{
- cinfo->lock = &dreq->inode->i_lock;
+ cinfo->inode = dreq->inode;
cinfo->mds = &dreq->mds_cinfo;
cinfo->ds = &dreq->ds_cinfo;
cinfo->dreq = dreq;
@@ -350,10 +353,12 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq)
result = wait_for_completion_killable(&dreq->completion);
+ if (!result) {
+ result = dreq->count;
+ WARN_ON_ONCE(dreq->count < 0);
+ }
if (!result)
result = dreq->error;
- if (!result)
- result = dreq->count;
out:
return (ssize_t) result;
@@ -383,8 +388,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
if (dreq->iocb) {
long res = (long) dreq->error;
- if (!res)
+ if (dreq->count != 0) {
res = (long) dreq->count;
+ WARN_ON_ONCE(dreq->count < 0);
+ }
dreq->iocb->ki_complete(dreq->iocb, res, 0);
}
@@ -591,7 +598,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
goto out_unlock;
dreq->inode = inode;
- dreq->bytes_left = count;
+ dreq->bytes_left = dreq->max_count = count;
dreq->io_start = iocb->ki_pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
@@ -630,13 +637,13 @@ nfs_direct_write_scan_commit_list(struct inode *inode,
struct list_head *list,
struct nfs_commit_info *cinfo)
{
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
#ifdef CONFIG_NFS_V4_1
if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
#endif
nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
}
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
@@ -671,13 +678,13 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
if (!nfs_pageio_add_request(&desc, req)) {
nfs_list_remove_request(req);
nfs_list_add_request(req, &failed);
- spin_lock(cinfo.lock);
+ spin_lock(&cinfo.inode->i_lock);
dreq->flags = 0;
if (desc.pg_error < 0)
dreq->error = desc.pg_error;
else
dreq->error = -EIO;
- spin_unlock(cinfo.lock);
+ spin_unlock(&cinfo.inode->i_lock);
}
nfs_release_request(req);
}
@@ -1023,7 +1030,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
goto out_unlock;
dreq->inode = inode;
- dreq->bytes_left = iov_iter_count(iter);
+ dreq->bytes_left = dreq->max_count = iov_iter_count(iter);
dreq->io_start = pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 3384dc8e6683..aa59757389dc 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -795,7 +795,7 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW;
}
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
if (cinfo->ds->nbuckets >= size)
goto out;
for (i = 0; i < cinfo->ds->nbuckets; i++) {
@@ -811,7 +811,7 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
swap(cinfo->ds->buckets, buckets);
cinfo->ds->nbuckets = size;
out:
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
kfree(buckets);
return 0;
}
@@ -890,6 +890,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_READ,
+ false,
GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -915,6 +916,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 0cb1abd535e3..0e8018bc9880 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -26,6 +26,8 @@
#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ)
+static struct group_info *ff_zero_group;
+
static struct pnfs_layout_hdr *
ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
{
@@ -53,14 +55,15 @@ ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
kfree(FF_LAYOUT_FROM_HDR(lo));
}
-static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+static int decode_pnfs_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
{
__be32 *p;
p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return -ENOBUFS;
- memcpy(stateid, p, NFS4_STATEID_SIZE);
+ stateid->type = NFS4_PNFS_DS_STATEID_TYPE;
+ memcpy(stateid->data, p, NFS4_STATEID_SIZE);
dprintk("%s: stateid id= [%x%x%x%x]\n", __func__,
p[0], p[1], p[2], p[3]);
return 0;
@@ -211,10 +214,16 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
+ struct rpc_cred *cred;
+
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
- if (mirror->cred)
- put_rpccred(mirror->cred);
+ cred = rcu_access_pointer(mirror->ro_cred);
+ if (cred)
+ put_rpccred(cred);
+ cred = rcu_access_pointer(mirror->rw_cred);
+ if (cred)
+ put_rpccred(cred);
nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
kfree(mirror);
}
@@ -290,6 +299,8 @@ ff_lseg_merge(struct pnfs_layout_segment *new,
{
u64 new_end, old_end;
+ if (test_bit(NFS_LSEG_LAYOUTRETURN, &old->pls_flags))
+ return false;
if (new->pls_range.iomode != old->pls_range.iomode)
return false;
old_end = pnfs_calc_offset_end(old->pls_range.offset,
@@ -310,8 +321,6 @@ ff_lseg_merge(struct pnfs_layout_segment *new,
new_end);
if (test_bit(NFS_LSEG_ROC, &old->pls_flags))
set_bit(NFS_LSEG_ROC, &new->pls_flags);
- if (test_bit(NFS_LSEG_LAYOUTRETURN, &old->pls_flags))
- set_bit(NFS_LSEG_LAYOUTRETURN, &new->pls_flags);
return true;
}
@@ -407,8 +416,9 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_deviceid devid;
struct nfs4_deviceid_node *idnode;
- u32 ds_count;
- u32 fh_count;
+ struct auth_cred acred = { .group_info = ff_zero_group };
+ struct rpc_cred __rcu *cred;
+ u32 ds_count, fh_count, id;
int j;
rc = -EIO;
@@ -456,7 +466,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
fls->mirror_array[i]->efficiency = be32_to_cpup(p);
/* stateid */
- rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid);
+ rc = decode_pnfs_stateid(&stream, &fls->mirror_array[i]->stateid);
if (rc)
goto out_err_free;
@@ -484,24 +494,49 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
fls->mirror_array[i]->fh_versions_cnt = fh_count;
/* user */
- rc = decode_name(&stream, &fls->mirror_array[i]->uid);
+ rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
+ acred.uid = make_kuid(&init_user_ns, id);
+
/* group */
- rc = decode_name(&stream, &fls->mirror_array[i]->gid);
+ rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
+ acred.gid = make_kgid(&init_user_ns, id);
+
+ /* find the cred for it */
+ rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags));
+ if (IS_ERR(cred)) {
+ rc = PTR_ERR(cred);
+ goto out_err_free;
+ }
+
+ if (lgr->range.iomode == IOMODE_READ)
+ rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
+ else
+ rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
+
mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
if (mirror != fls->mirror_array[i]) {
+ /* swap cred ptrs so free_mirror will clean up old */
+ if (lgr->range.iomode == IOMODE_READ) {
+ cred = xchg(&mirror->ro_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
+ } else {
+ cred = xchg(&mirror->rw_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
+ }
ff_layout_free_mirror(fls->mirror_array[i]);
fls->mirror_array[i] = mirror;
}
- dprintk("%s: uid %d gid %d\n", __func__,
- fls->mirror_array[i]->uid,
- fls->mirror_array[i]->gid);
+ dprintk("%s: iomode %s uid %u gid %u\n", __func__,
+ lgr->range.iomode == IOMODE_READ ? "READ" : "RW",
+ from_kuid(&init_user_ns, acred.uid),
+ from_kgid(&init_user_ns, acred.gid));
}
p = xdr_inline_decode(&stream, 4);
@@ -745,7 +780,7 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
else {
int i;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
if (cinfo->ds->nbuckets != 0)
kfree(buckets);
else {
@@ -759,7 +794,7 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
NFS_INVALID_STABLE_HOW;
}
}
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
return 0;
}
}
@@ -786,6 +821,36 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
}
static void
+ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
+ struct nfs_page *req,
+ bool strict_iomode)
+{
+retry_strict:
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+ req->wb_context,
+ 0,
+ NFS4_MAX_UINT64,
+ IOMODE_READ,
+ strict_iomode,
+ GFP_KERNEL);
+ if (IS_ERR(pgio->pg_lseg)) {
+ pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ }
+
+ /* If we don't have checking, do get a IOMODE_RW
+ * segment, and the server wants to avoid READs
+ * there, then retry!
+ */
+ if (pgio->pg_lseg && !strict_iomode &&
+ ff_layout_avoid_read_on_rw(pgio->pg_lseg)) {
+ strict_iomode = true;
+ goto retry_strict;
+ }
+}
+
+static void
ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
@@ -795,26 +860,23 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
int ds_idx;
/* Use full layout for now */
- if (!pgio->pg_lseg) {
- pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
- IOMODE_READ,
- GFP_KERNEL);
- if (IS_ERR(pgio->pg_lseg)) {
- pgio->pg_error = PTR_ERR(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
- return;
- }
- }
+ if (!pgio->pg_lseg)
+ ff_layout_pg_get_read(pgio, req, false);
+ else if (ff_layout_avoid_read_on_rw(pgio->pg_lseg))
+ ff_layout_pg_get_read(pgio, req, true);
+
/* If no lseg, fall back to read through mds */
if (pgio->pg_lseg == NULL)
goto out_mds;
ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
- if (!ds)
- goto out_mds;
+ if (!ds) {
+ if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
+ goto out_pnfs;
+ else
+ goto out_mds;
+ }
+
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
pgio->pg_mirror_idx = ds_idx;
@@ -828,6 +890,12 @@ out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_read_mds(pgio);
+ return;
+
+out_pnfs:
+ pnfs_set_lo_fail(pgio->pg_lseg);
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
}
static void
@@ -847,6 +915,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -870,8 +939,12 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
for (i = 0; i < pgio->pg_mirror_count; i++) {
ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
- if (!ds)
- goto out_mds;
+ if (!ds) {
+ if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
+ goto out_pnfs;
+ else
+ goto out_mds;
+ }
pgm = &pgio->pg_mirrors[i];
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
@@ -883,6 +956,12 @@ out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_write_mds(pgio);
+ return;
+
+out_pnfs:
+ pnfs_set_lo_fail(pgio->pg_lseg);
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
}
static unsigned int
@@ -895,6 +974,7 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -1067,8 +1147,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
rpc_wake_up(&tbl->slot_tbl_waitq);
/* fall through */
default:
- if (ff_layout_no_fallback_to_mds(lseg) ||
- ff_layout_has_available_ds(lseg))
+ if (ff_layout_avoid_mds_available_ds(lseg))
return -NFS4ERR_RESET_TO_PNFS;
reset:
dprintk("%s Retry through MDS. Error %d\n", __func__,
@@ -1215,8 +1294,6 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
hdr->pgio_mirror_idx + 1,
&hdr->pgio_mirror_idx))
goto out_eagain;
- set_bit(NFS_LAYOUT_RETURN_REQUESTED,
- &hdr->lseg->pls_layout->plh_flags);
pnfs_read_resend_pnfs(hdr);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
@@ -1260,7 +1337,7 @@ ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
}
static bool
-ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_device_unavailable(struct pnfs_layout_segment *lseg, int idx)
{
/* No mirroring for now */
struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx);
@@ -1297,16 +1374,10 @@ static int ff_layout_read_prepare_common(struct rpc_task *task,
rpc_exit(task, -EIO);
return -EIO;
}
- if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) {
- dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
- if (ff_layout_has_available_ds(hdr->lseg))
- pnfs_read_resend_pnfs(hdr);
- else
- ff_layout_reset_read(hdr);
- rpc_exit(task, 0);
+ if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
+ rpc_exit(task, -EHOSTDOWN);
return -EAGAIN;
}
- hdr->pgio_done_cb = ff_layout_read_done_cb;
ff_layout_read_record_layoutstats_start(task, hdr);
return 0;
@@ -1496,14 +1567,8 @@ static int ff_layout_write_prepare_common(struct rpc_task *task,
return -EIO;
}
- if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) {
- bool retry_pnfs;
-
- retry_pnfs = ff_layout_has_available_ds(hdr->lseg);
- dprintk("%s task %u reset io to %s\n", __func__,
- task->tk_pid, retry_pnfs ? "pNFS" : "MDS");
- ff_layout_reset_write(hdr, retry_pnfs);
- rpc_exit(task, 0);
+ if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
+ rpc_exit(task, -EHOSTDOWN);
return -EAGAIN;
}
@@ -1712,7 +1777,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
goto out_failed;
ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
- if (IS_ERR(ds_cred))
+ if (!ds_cred)
goto out_failed;
vers = nfs4_ff_layout_ds_version(lseg, idx);
@@ -1720,6 +1785,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers);
+ hdr->pgio_done_cb = ff_layout_read_done_cb;
atomic_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
@@ -1737,11 +1803,11 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
0, RPC_TASK_SOFTCONN);
-
+ put_rpccred(ds_cred);
return PNFS_ATTEMPTED;
out_failed:
- if (ff_layout_has_available_ds(lseg))
+ if (ff_layout_avoid_mds_available_ds(lseg))
return PNFS_TRY_AGAIN;
return PNFS_NOT_ATTEMPTED;
}
@@ -1769,7 +1835,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
return PNFS_NOT_ATTEMPTED;
ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
- if (IS_ERR(ds_cred))
+ if (!ds_cred)
return PNFS_NOT_ATTEMPTED;
vers = nfs4_ff_layout_ds_version(lseg, idx);
@@ -1798,6 +1864,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
sync, RPC_TASK_SOFTCONN);
+ put_rpccred(ds_cred);
return PNFS_ATTEMPTED;
}
@@ -1824,7 +1891,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
struct rpc_clnt *ds_clnt;
struct rpc_cred *ds_cred;
u32 idx;
- int vers;
+ int vers, ret;
struct nfs_fh *fh;
idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
@@ -1838,7 +1905,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
goto out_err;
ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred);
- if (IS_ERR(ds_cred))
+ if (!ds_cred)
goto out_err;
vers = nfs4_ff_layout_ds_version(lseg, idx);
@@ -1854,10 +1921,12 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
if (fh)
data->args.fh = fh;
- return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
+ ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
how, RPC_TASK_SOFTCONN);
+ put_rpccred(ds_cred);
+ return ret;
out_err:
pnfs_generic_prepare_to_resend_writes(data);
pnfs_generic_commit_release(data);
@@ -2223,6 +2292,11 @@ static int __init nfs4flexfilelayout_init(void)
{
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n",
__func__);
+ if (!ff_zero_group) {
+ ff_zero_group = groups_alloc(0);
+ if (!ff_zero_group)
+ return -ENOMEM;
+ }
return pnfs_register_layoutdriver(&flexfilelayout_type);
}
@@ -2231,6 +2305,10 @@ static void __exit nfs4flexfilelayout_exit(void)
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n",
__func__);
pnfs_unregister_layoutdriver(&flexfilelayout_type);
+ if (ff_zero_group) {
+ put_group_info(ff_zero_group);
+ ff_zero_group = NULL;
+ }
}
MODULE_ALIAS("nfs-layouttype4-4");
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index dd353bb7dc0a..1bcdb15d0c41 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -10,7 +10,8 @@
#define FS_NFS_NFS4FLEXFILELAYOUT_H
#define FF_FLAGS_NO_LAYOUTCOMMIT 1
-#define FF_FLAGS_NO_IO_THRU_MDS 2
+#define FF_FLAGS_NO_IO_THRU_MDS 2
+#define FF_FLAGS_NO_READ_IO 4
#include "../pnfs.h"
@@ -76,9 +77,8 @@ struct nfs4_ff_layout_mirror {
u32 fh_versions_cnt;
struct nfs_fh *fh_versions;
nfs4_stateid stateid;
- u32 uid;
- u32 gid;
- struct rpc_cred *cred;
+ struct rpc_cred __rcu *ro_cred;
+ struct rpc_cred __rcu *rw_cred;
atomic_t ref;
spinlock_t lock;
struct nfs4_ff_layoutstat read_stat;
@@ -154,6 +154,12 @@ ff_layout_no_fallback_to_mds(struct pnfs_layout_segment *lseg)
}
static inline bool
+ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg)
+{
+ return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_READ_IO;
+}
+
+static inline bool
ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
{
return nfs4_test_deviceid_unavailable(node);
@@ -192,4 +198,7 @@ nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
u32 ds_idx, struct rpc_cred *mdscred);
bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
+bool ff_layout_avoid_mds_available_ds(struct pnfs_layout_segment *lseg);
+bool ff_layout_avoid_read_on_rw(struct pnfs_layout_segment *lseg);
+
#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index add0e5a70bd6..0aa36be71fce 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -228,7 +228,8 @@ ff_ds_error_match(const struct nfs4_ff_layout_ds_err *e1,
return e1->opnum < e2->opnum ? -1 : 1;
if (e1->status != e2->status)
return e1->status < e2->status ? -1 : 1;
- ret = memcmp(&e1->stateid, &e2->stateid, sizeof(e1->stateid));
+ ret = memcmp(e1->stateid.data, e2->stateid.data,
+ sizeof(e1->stateid.data));
if (ret != 0)
return ret;
ret = memcmp(&e1->deviceid, &e2->deviceid, sizeof(e1->deviceid));
@@ -302,40 +303,26 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
return 0;
}
-/* currently we only support AUTH_NONE and AUTH_SYS */
-static rpc_authflavor_t
-nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror)
+static struct rpc_cred *
+ff_layout_get_mirror_cred(struct nfs4_ff_layout_mirror *mirror, u32 iomode)
{
- if (mirror->uid == (u32)-1)
- return RPC_AUTH_NULL;
- return RPC_AUTH_UNIX;
-}
+ struct rpc_cred *cred, __rcu **pcred;
-/* fetch cred for NFSv3 DS */
-static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror,
- struct nfs4_pnfs_ds *ds)
-{
- if (ds->ds_clp && !mirror->cred &&
- mirror->mirror_ds->ds_versions[0].version == 3) {
- struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth;
- struct rpc_cred *cred;
- struct auth_cred acred = {
- .uid = make_kuid(&init_user_ns, mirror->uid),
- .gid = make_kgid(&init_user_ns, mirror->gid),
- };
-
- /* AUTH_NULL ignores acred */
- cred = auth->au_ops->lookup_cred(auth, &acred, 0);
- if (IS_ERR(cred)) {
- dprintk("%s: lookup_cred failed with %ld\n",
- __func__, PTR_ERR(cred));
- return PTR_ERR(cred);
- } else {
- if (cmpxchg(&mirror->cred, NULL, cred))
- put_rpccred(cred);
- }
- }
- return 0;
+ if (iomode == IOMODE_READ)
+ pcred = &mirror->ro_cred;
+ else
+ pcred = &mirror->rw_cred;
+
+ rcu_read_lock();
+ do {
+ cred = rcu_dereference(*pcred);
+ if (!cred)
+ break;
+
+ cred = get_rpccred_rcu(cred);
+ } while(!cred);
+ rcu_read_unlock();
+ return cred;
}
struct nfs_fh *
@@ -356,7 +343,23 @@ out:
return fh;
}
-/* Upon return, either ds is connected, or ds is NULL */
+/**
+ * nfs4_ff_layout_prepare_ds - prepare a DS connection for an RPC call
+ * @lseg: the layout segment we're operating on
+ * @ds_idx: index of the DS to use
+ * @fail_return: return layout on connect failure?
+ *
+ * Try to prepare a DS connection to accept an RPC call. This involves
+ * selecting a mirror to use and connecting the client to it if it's not
+ * already connected.
+ *
+ * Since we only need a single functioning mirror to satisfy a read, we don't
+ * want to return the layout if there is one. For writes though, any down
+ * mirror should result in a LAYOUTRETURN. @fail_return is how we distinguish
+ * between the two cases.
+ *
+ * Returns a pointer to a connected DS object on success or NULL on failure.
+ */
struct nfs4_pnfs_ds *
nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
bool fail_return)
@@ -367,7 +370,6 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct inode *ino = lseg->pls_layout->plh_inode;
struct nfs_server *s = NFS_SERVER(ino);
unsigned int max_payload;
- rpc_authflavor_t flavor;
if (!ff_layout_mirror_valid(lseg, mirror)) {
pr_err_ratelimited("NFS: %s: No data server for offset index %d\n",
@@ -383,9 +385,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
smp_rmb();
if (ds->ds_clp)
- goto out_update_creds;
-
- flavor = nfs4_ff_layout_choose_authflavor(mirror);
+ goto out;
/* FIXME: For now we assume the server sent only one version of NFS
* to use for the DS.
@@ -394,7 +394,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
dataserver_retrans,
mirror->mirror_ds->ds_versions[0].version,
mirror->mirror_ds->ds_versions[0].minor_version,
- flavor);
+ RPC_AUTH_UNIX);
/* connect success, check rsize/wsize limit */
if (ds->ds_clp) {
@@ -410,20 +410,10 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
mirror, lseg->pls_range.offset,
lseg->pls_range.length, NFS4ERR_NXIO,
OP_ILLEGAL, GFP_NOIO);
- if (!fail_return) {
- if (ff_layout_has_available_ds(lseg))
- set_bit(NFS_LAYOUT_RETURN_REQUESTED,
- &lseg->pls_layout->plh_flags);
- else
- pnfs_error_mark_layout_for_return(ino, lseg);
- } else
+ if (fail_return || !ff_layout_has_available_ds(lseg))
pnfs_error_mark_layout_for_return(ino, lseg);
ds = NULL;
- goto out;
}
-out_update_creds:
- if (ff_layout_update_mirror_cred(mirror, ds))
- ds = NULL;
out:
return ds;
}
@@ -433,16 +423,15 @@ ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct rpc_cred *mdscred)
{
struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
- struct rpc_cred *cred = ERR_PTR(-EINVAL);
-
- if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true))
- goto out;
+ struct rpc_cred *cred;
- if (mirror && mirror->cred)
- cred = mirror->cred;
- else
- cred = mdscred;
-out:
+ if (mirror) {
+ cred = ff_layout_get_mirror_cred(mirror, lseg->pls_range.iomode);
+ if (!cred)
+ cred = get_rpccred(mdscred);
+ } else {
+ cred = get_rpccred(mdscred);
+ }
return cred;
}
@@ -562,6 +551,18 @@ bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg)
return ff_rw_layout_has_available_ds(lseg);
}
+bool ff_layout_avoid_mds_available_ds(struct pnfs_layout_segment *lseg)
+{
+ return ff_layout_no_fallback_to_mds(lseg) ||
+ ff_layout_has_available_ds(lseg);
+}
+
+bool ff_layout_avoid_read_on_rw(struct pnfs_layout_segment *lseg)
+{
+ return lseg->pls_range.iomode == IOMODE_RW &&
+ ff_layout_no_read_on_rw(lseg);
+}
+
module_param(dataserver_retrans, uint, 0644);
MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client "
"retries a request before it attempts further "
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 52e7d6869e3b..dda689d7a8a7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -282,6 +282,7 @@ nfs_init_locked(struct inode *inode, void *opaque)
struct nfs_fattr *fattr = desc->fattr;
set_nfs_fileid(inode, fattr->fileid);
+ inode->i_mode = fattr->mode;
nfs_copy_fh(NFS_FH(inode), desc->fh);
return 0;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index f1d1d2c472e9..5154fa65a2f2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -477,6 +477,7 @@ void nfs_mark_request_commit(struct nfs_page *req,
u32 ds_commit_idx);
int nfs_write_need_commit(struct nfs_pgio_header *);
void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
+int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf);
int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
int how, struct nfs_commit_info *cinfo);
void nfs_retry_commit(struct list_head *page_list,
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index b587ccd31083..b6cd15314bab 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -13,6 +13,7 @@
/* nfs4.2proc.c */
int nfs42_proc_allocate(struct file *, loff_t, loff_t);
+ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
loff_t nfs42_proc_llseek(struct file *, loff_t, int);
int nfs42_proc_layoutstats_generic(struct nfs_server *,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index dff83460e5a6..aa03ed09ba06 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -126,6 +126,111 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
return err;
}
+static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
+ struct nfs_lock_context *src_lock,
+ struct file *dst, loff_t pos_dst,
+ struct nfs_lock_context *dst_lock,
+ size_t count)
+{
+ struct nfs42_copy_args args = {
+ .src_fh = NFS_FH(file_inode(src)),
+ .src_pos = pos_src,
+ .dst_fh = NFS_FH(file_inode(dst)),
+ .dst_pos = pos_dst,
+ .count = count,
+ };
+ struct nfs42_copy_res res;
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
+ .rpc_argp = &args,
+ .rpc_resp = &res,
+ };
+ struct inode *dst_inode = file_inode(dst);
+ struct nfs_server *server = NFS_SERVER(dst_inode);
+ int status;
+
+ status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+ src_lock, FMODE_READ);
+ if (status)
+ return status;
+
+ status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+ dst_lock, FMODE_WRITE);
+ if (status)
+ return status;
+
+ status = nfs4_call_sync(server->client, server, &msg,
+ &args.seq_args, &res.seq_res, 0);
+ if (status == -ENOTSUPP)
+ server->caps &= ~NFS_CAP_COPY;
+ if (status)
+ return status;
+
+ if (res.write_res.verifier.committed != NFS_FILE_SYNC) {
+ status = nfs_commit_file(dst, &res.write_res.verifier.verifier);
+ if (status)
+ return status;
+ }
+
+ truncate_pagecache_range(dst_inode, pos_dst,
+ pos_dst + res.write_res.count);
+
+ return res.write_res.count;
+}
+
+ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
+ struct file *dst, loff_t pos_dst,
+ size_t count)
+{
+ struct nfs_server *server = NFS_SERVER(file_inode(dst));
+ struct nfs_lock_context *src_lock;
+ struct nfs_lock_context *dst_lock;
+ struct nfs4_exception src_exception = { };
+ struct nfs4_exception dst_exception = { };
+ ssize_t err, err2;
+
+ if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
+ return -EOPNOTSUPP;
+
+ src_lock = nfs_get_lock_context(nfs_file_open_context(src));
+ if (IS_ERR(src_lock))
+ return PTR_ERR(src_lock);
+
+ src_exception.inode = file_inode(src);
+ src_exception.state = src_lock->open_context->state;
+
+ dst_lock = nfs_get_lock_context(nfs_file_open_context(dst));
+ if (IS_ERR(dst_lock)) {
+ err = PTR_ERR(dst_lock);
+ goto out_put_src_lock;
+ }
+
+ dst_exception.inode = file_inode(dst);
+ dst_exception.state = dst_lock->open_context->state;
+
+ do {
+ inode_lock(file_inode(dst));
+ err = _nfs42_proc_copy(src, pos_src, src_lock,
+ dst, pos_dst, dst_lock, count);
+ inode_unlock(file_inode(dst));
+
+ if (err == -ENOTSUPP) {
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ err2 = nfs4_handle_exception(server, err, &src_exception);
+ err = nfs4_handle_exception(server, err, &dst_exception);
+ if (!err)
+ err = err2;
+ } while (src_exception.retry || dst_exception.retry);
+
+ nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+ nfs_put_lock_context(src_lock);
+ return err;
+}
+
static loff_t _nfs42_proc_llseek(struct file *filep,
struct nfs_lock_context *lock, loff_t offset, int whence)
{
@@ -232,7 +337,7 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
* with the current stateid.
*/
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
} else
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 0ca482a51e53..6dc6f2aea0d6 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -9,9 +9,22 @@
#define encode_fallocate_maxsz (encode_stateid_maxsz + \
2 /* offset */ + \
2 /* length */)
+#define NFS42_WRITE_RES_SIZE (1 /* wr_callback_id size */ +\
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ 2 /* wr_count */ + \
+ 1 /* wr_committed */ + \
+ XDR_QUADLEN(NFS4_VERIFIER_SIZE))
#define encode_allocate_maxsz (op_encode_hdr_maxsz + \
encode_fallocate_maxsz)
#define decode_allocate_maxsz (op_decode_hdr_maxsz)
+#define encode_copy_maxsz (op_encode_hdr_maxsz + \
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ 2 + 2 + 2 + 1 + 1 + 1)
+#define decode_copy_maxsz (op_decode_hdr_maxsz + \
+ NFS42_WRITE_RES_SIZE + \
+ 1 /* cr_consecutive */ + \
+ 1 /* cr_synchronous */)
#define encode_deallocate_maxsz (op_encode_hdr_maxsz + \
encode_fallocate_maxsz)
#define decode_deallocate_maxsz (op_decode_hdr_maxsz)
@@ -49,6 +62,16 @@
decode_putfh_maxsz + \
decode_allocate_maxsz + \
decode_getattr_maxsz)
+#define NFS4_enc_copy_sz (compound_encode_hdr_maxsz + \
+ encode_putfh_maxsz + \
+ encode_savefh_maxsz + \
+ encode_putfh_maxsz + \
+ encode_copy_maxsz)
+#define NFS4_dec_copy_sz (compound_decode_hdr_maxsz + \
+ decode_putfh_maxsz + \
+ decode_savefh_maxsz + \
+ decode_putfh_maxsz + \
+ decode_copy_maxsz)
#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \
encode_putfh_maxsz + \
encode_deallocate_maxsz + \
@@ -102,6 +125,23 @@ static void encode_allocate(struct xdr_stream *xdr,
encode_fallocate(xdr, args);
}
+static void encode_copy(struct xdr_stream *xdr,
+ struct nfs42_copy_args *args,
+ struct compound_hdr *hdr)
+{
+ encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr);
+ encode_nfs4_stateid(xdr, &args->src_stateid);
+ encode_nfs4_stateid(xdr, &args->dst_stateid);
+
+ encode_uint64(xdr, args->src_pos);
+ encode_uint64(xdr, args->dst_pos);
+ encode_uint64(xdr, args->count);
+
+ encode_uint32(xdr, 1); /* consecutive = true */
+ encode_uint32(xdr, 1); /* synchronous = true */
+ encode_uint32(xdr, 0); /* src server list */
+}
+
static void encode_deallocate(struct xdr_stream *xdr,
struct nfs42_falloc_args *args,
struct compound_hdr *hdr)
@@ -182,6 +222,26 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
}
/*
+ * Encode COPY request
+ */
+static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ struct nfs42_copy_args *args)
+{
+ struct compound_hdr hdr = {
+ .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+ };
+
+ encode_compound_hdr(xdr, req, &hdr);
+ encode_sequence(xdr, &args->seq_args, &hdr);
+ encode_putfh(xdr, args->src_fh, &hdr);
+ encode_savefh(xdr, &hdr);
+ encode_putfh(xdr, args->dst_fh, &hdr);
+ encode_copy(xdr, args, &hdr);
+ encode_nops(&hdr);
+}
+
+/*
* Encode DEALLOCATE request
*/
static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -266,6 +326,62 @@ static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
return decode_op_hdr(xdr, OP_ALLOCATE);
}
+static int decode_write_response(struct xdr_stream *xdr,
+ struct nfs42_write_res *res)
+{
+ __be32 *p;
+ int stateids;
+
+ p = xdr_inline_decode(xdr, 4 + 8 + 4);
+ if (unlikely(!p))
+ goto out_overflow;
+
+ stateids = be32_to_cpup(p++);
+ p = xdr_decode_hyper(p, &res->count);
+ res->verifier.committed = be32_to_cpup(p);
+ return decode_verifier(xdr, &res->verifier.verifier);
+
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
+static int decode_copy_requirements(struct xdr_stream *xdr,
+ struct nfs42_copy_res *res) {
+ __be32 *p;
+
+ p = xdr_inline_decode(xdr, 4 + 4);
+ if (unlikely(!p))
+ goto out_overflow;
+
+ res->consecutive = be32_to_cpup(p++);
+ res->synchronous = be32_to_cpup(p++);
+ return 0;
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
+static int decode_copy(struct xdr_stream *xdr, struct nfs42_copy_res *res)
+{
+ int status;
+
+ status = decode_op_hdr(xdr, OP_COPY);
+ if (status == NFS4ERR_OFFLOAD_NO_REQS) {
+ status = decode_copy_requirements(xdr, res);
+ if (status)
+ return status;
+ return NFS4ERR_OFFLOAD_NO_REQS;
+ } else if (status)
+ return status;
+
+ status = decode_write_response(xdr, &res->write_res);
+ if (status)
+ return status;
+
+ return decode_copy_requirements(xdr, res);
+}
+
static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
{
return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -331,6 +447,36 @@ out:
}
/*
+ * Decode COPY response
+ */
+static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ struct nfs42_copy_res *res)
+{
+ struct compound_hdr hdr;
+ int status;
+
+ status = decode_compound_hdr(xdr, &hdr);
+ if (status)
+ goto out;
+ status = decode_sequence(xdr, &res->seq_res, rqstp);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_savefh(xdr);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_copy(xdr, res);
+out:
+ return status;
+}
+
+/*
* Decode DEALLOCATE request
*/
static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4afdee420d25..768456fa1b17 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -438,8 +438,9 @@ extern void nfs41_handle_server_scope(struct nfs_client *,
struct nfs41_server_scope **);
extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern int nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
- fmode_t, const struct nfs_lockowner *);
+extern int nfs4_select_rw_stateid(struct nfs4_state *, fmode_t,
+ const struct nfs_lockowner *, nfs4_stateid *,
+ struct rpc_cred **);
extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -496,12 +497,15 @@ extern struct svc_version nfs4_callback_version4;
static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
{
- memcpy(dst, src, sizeof(*dst));
+ memcpy(dst->data, src->data, sizeof(dst->data));
+ dst->type = src->type;
}
static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src)
{
- return memcmp(dst, src, sizeof(*dst)) == 0;
+ if (dst->type != src->type)
+ return false;
+ return memcmp(dst->data, src->data, sizeof(dst->data)) == 0;
}
static inline bool nfs4_stateid_match_other(const nfs4_stateid *dst, const nfs4_stateid *src)
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index d0390516467c..014b0e41ace5 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -129,6 +129,28 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
}
#ifdef CONFIG_NFS_V4_2
+static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ size_t count, unsigned int flags)
+{
+ struct inode *in_inode = file_inode(file_in);
+ struct inode *out_inode = file_inode(file_out);
+ int ret;
+
+ if (in_inode == out_inode)
+ return -EINVAL;
+
+ /* flush any pending writes */
+ ret = nfs_sync_inode(in_inode);
+ if (ret)
+ return ret;
+ ret = nfs_sync_inode(out_inode);
+ if (ret)
+ return ret;
+
+ return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+}
+
static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
{
loff_t ret;
@@ -243,6 +265,7 @@ const struct file_operations nfs4_file_operations = {
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
#ifdef CONFIG_NFS_V4_2
+ .copy_file_range = nfs4_copy_file_range,
.llseek = nfs4_file_llseek,
.fallocate = nfs42_fallocate,
.clone_file_range = nfs42_clone_file_range,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 084e8570da18..ff416d0e24bc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -74,6 +74,17 @@
#define NFS4_POLL_RETRY_MIN (HZ/10)
#define NFS4_POLL_RETRY_MAX (15*HZ)
+/* file attributes which can be mapped to nfs attributes */
+#define NFS4_VALID_ATTRS (ATTR_MODE \
+ | ATTR_UID \
+ | ATTR_GID \
+ | ATTR_SIZE \
+ | ATTR_ATIME \
+ | ATTR_MTIME \
+ | ATTR_CTIME \
+ | ATTR_ATIME_SET \
+ | ATTR_MTIME_SET)
+
struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
@@ -416,6 +427,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
case -NFS4ERR_GRACE:
+ case -NFS4ERR_RECALLCONFLICT:
exception->delay = 1;
return 0;
@@ -2558,15 +2570,20 @@ static int _nfs4_do_open(struct inode *dir,
if ((opendata->o_arg.open_flags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL) &&
(opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) {
nfs4_exclusive_attrset(opendata, sattr, &label);
-
- nfs_fattr_init(opendata->o_res.f_attr);
- status = nfs4_do_setattr(state->inode, cred,
- opendata->o_res.f_attr, sattr,
- state, label, olabel);
- if (status == 0) {
- nfs_setattr_update_inode(state->inode, sattr,
- opendata->o_res.f_attr);
- nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
+ /*
+ * send create attributes which was not set by open
+ * with an extra setattr.
+ */
+ if (sattr->ia_valid & NFS4_VALID_ATTRS) {
+ nfs_fattr_init(opendata->o_res.f_attr);
+ status = nfs4_do_setattr(state->inode, cred,
+ opendata->o_res.f_attr, sattr,
+ state, label, olabel);
+ if (status == 0) {
+ nfs_setattr_update_inode(state->inode, sattr,
+ opendata->o_res.f_attr);
+ nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
+ }
}
}
if (opened && opendata->file_created)
@@ -2676,6 +2693,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
.rpc_resp = &res,
.rpc_cred = cred,
};
+ struct rpc_cred *delegation_cred = NULL;
unsigned long timestamp = jiffies;
fmode_t fmode;
bool truncate;
@@ -2691,7 +2709,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false;
fmode = truncate ? FMODE_WRITE : FMODE_READ;
- if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
+ if (nfs4_copy_delegation_stateid(inode, fmode, &arg.stateid, &delegation_cred)) {
/* Use that stateid */
} else if (truncate && state != NULL) {
struct nfs_lockowner lockowner = {
@@ -2700,13 +2718,17 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
};
if (!nfs4_valid_open_stateid(state))
return -EBADF;
- if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
- &lockowner) == -EIO)
+ if (nfs4_select_rw_stateid(state, FMODE_WRITE, &lockowner,
+ &arg.stateid, &delegation_cred) == -EIO)
return -EBADF;
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
+ if (delegation_cred)
+ msg.rpc_cred = delegation_cred;
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
+
+ put_rpccred(delegation_cred);
if (status == 0 && state != NULL)
renew_lease(server, timestamp);
trace_nfs4_setattr(inode, &arg.stateid, status);
@@ -2860,12 +2882,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
call_close |= is_wronly;
else if (is_wronly)
calldata->arg.fmode |= FMODE_WRITE;
+ if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE))
+ call_close |= is_rdwr;
} else if (is_rdwr)
calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
- if (calldata->arg.fmode == 0)
- call_close |= is_rdwr;
-
if (!nfs4_valid_open_stateid(state))
call_close = 0;
spin_unlock(&state->owner->so_lock);
@@ -4285,7 +4306,7 @@ int nfs4_set_rw_stateid(nfs4_stateid *stateid,
if (l_ctx != NULL)
lockowner = &l_ctx->lockowner;
- return nfs4_select_rw_stateid(stateid, ctx->state, fmode, lockowner);
+ return nfs4_select_rw_stateid(ctx->state, fmode, lockowner, stateid, NULL);
}
EXPORT_SYMBOL_GPL(nfs4_set_rw_stateid);
@@ -4993,12 +5014,11 @@ static int nfs4_do_set_security_label(struct inode *inode,
}
static int
-nfs4_set_security_label(struct dentry *dentry, const void *buf, size_t buflen)
+nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen)
{
struct nfs4_label ilabel, *olabel = NULL;
struct nfs_fattr fattr;
struct rpc_cred *cred;
- struct inode *inode = d_inode(dentry);
int status;
if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL))
@@ -6054,6 +6074,7 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
struct nfs_inode *nfsi = NFS_I(state->inode);
+ struct nfs4_state_owner *sp = state->owner;
unsigned char fl_flags = request->fl_flags;
int status = -ENOLCK;
@@ -6068,6 +6089,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
status = do_vfs_lock(state->inode, request);
if (status < 0)
goto out;
+ mutex_lock(&sp->so_delegreturn_mutex);
down_read(&nfsi->rwsem);
if (test_bit(NFS_DELEGATED_STATE, &state->flags)) {
/* Yes: cache locks! */
@@ -6075,9 +6097,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
request->fl_flags = fl_flags & ~FL_SLEEP;
status = do_vfs_lock(state->inode, request);
up_read(&nfsi->rwsem);
+ mutex_unlock(&sp->so_delegreturn_mutex);
goto out;
}
up_read(&nfsi->rwsem);
+ mutex_unlock(&sp->so_delegreturn_mutex);
status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
out:
request->fl_flags = fl_flags;
@@ -6255,11 +6279,11 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp)
#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- const void *buf, size_t buflen,
- int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *key, const void *buf,
+ size_t buflen, int flags)
{
- return nfs4_proc_set_acl(d_inode(dentry), buf, buflen);
+ return nfs4_proc_set_acl(inode, buf, buflen);
}
static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
@@ -6277,12 +6301,12 @@ static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- const void *buf, size_t buflen,
- int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *key, const void *buf,
+ size_t buflen, int flags)
{
if (security_ismaclabel(key))
- return nfs4_set_security_label(dentry, buf, buflen);
+ return nfs4_set_security_label(inode, buf, buflen);
return -EOPNOTSUPP;
}
@@ -7351,9 +7375,11 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
* always set csa_cachethis to FALSE because the current implementation
* of the back channel DRC only supports caching the CB_SEQUENCE operation.
*/
-static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
+static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args,
+ struct rpc_clnt *clnt)
{
unsigned int max_rqst_sz, max_resp_sz;
+ unsigned int max_bc_payload = rpc_max_bc_payload(clnt);
max_rqst_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxwrite_overhead;
max_resp_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxread_overhead;
@@ -7371,8 +7397,8 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
args->fc_attrs.max_ops, args->fc_attrs.max_reqs);
/* Back channel attributes */
- args->bc_attrs.max_rqst_sz = PAGE_SIZE;
- args->bc_attrs.max_resp_sz = PAGE_SIZE;
+ args->bc_attrs.max_rqst_sz = max_bc_payload;
+ args->bc_attrs.max_resp_sz = max_bc_payload;
args->bc_attrs.max_resp_sz_cached = 0;
args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
@@ -7476,7 +7502,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
};
int status;
- nfs4_init_channel_attrs(&args);
+ nfs4_init_channel_attrs(&args, clp->cl_rpcclient);
args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN);
status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
@@ -7820,40 +7846,34 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
struct nfs4_layoutget *lgp = calldata;
struct nfs_server *server = NFS_SERVER(lgp->args.inode);
struct nfs4_session *session = nfs4_get_session(server);
- int ret;
dprintk("--> %s\n", __func__);
- /* Note the is a race here, where a CB_LAYOUTRECALL can come in
- * right now covering the LAYOUTGET we are about to send.
- * However, that is not so catastrophic, and there seems
- * to be no way to prevent it completely.
- */
- if (nfs41_setup_sequence(session, &lgp->args.seq_args,
- &lgp->res.seq_res, task))
- return;
- ret = pnfs_choose_layoutget_stateid(&lgp->args.stateid,
- NFS_I(lgp->args.inode)->layout,
- &lgp->args.range,
- lgp->args.ctx->state);
- if (ret < 0)
- rpc_exit(task, ret);
+ nfs41_setup_sequence(session, &lgp->args.seq_args,
+ &lgp->res.seq_res, task);
+ dprintk("<-- %s\n", __func__);
}
static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
{
struct nfs4_layoutget *lgp = calldata;
+
+ dprintk("--> %s\n", __func__);
+ nfs41_sequence_done(task, &lgp->res.seq_res);
+ dprintk("<-- %s\n", __func__);
+}
+
+static int
+nfs4_layoutget_handle_exception(struct rpc_task *task,
+ struct nfs4_layoutget *lgp, struct nfs4_exception *exception)
+{
struct inode *inode = lgp->args.inode;
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
- struct nfs4_state *state = NULL;
- unsigned long timeo, now, giveup;
+ int status = task->tk_status;
dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
- if (!nfs41_sequence_done(task, &lgp->res.seq_res))
- goto out;
-
- switch (task->tk_status) {
+ switch (status) {
case 0:
goto out;
@@ -7863,62 +7883,48 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
* retry go inband.
*/
case -NFS4ERR_LAYOUTUNAVAILABLE:
- task->tk_status = -ENODATA;
+ status = -ENODATA;
goto out;
/*
* NFS4ERR_BADLAYOUT means the MDS cannot return a layout of
* length lgp->args.minlength != 0 (see RFC5661 section 18.43.3).
*/
case -NFS4ERR_BADLAYOUT:
- goto out_overflow;
+ status = -EOVERFLOW;
+ goto out;
/*
* NFS4ERR_LAYOUTTRYLATER is a conflict with another client
* (or clients) writing to the same RAID stripe except when
* the minlength argument is 0 (see RFC5661 section 18.43.3).
+ *
+ * Treat it like we would RECALLCONFLICT -- we retry for a little
+ * while, and then eventually give up.
*/
case -NFS4ERR_LAYOUTTRYLATER:
- if (lgp->args.minlength == 0)
- goto out_overflow;
- /*
- * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
- * existing layout before getting a new one).
- */
- case -NFS4ERR_RECALLCONFLICT:
- timeo = rpc_get_timeout(task->tk_client);
- giveup = lgp->args.timestamp + timeo;
- now = jiffies;
- if (time_after(giveup, now)) {
- unsigned long delay;
-
- /* Delay for:
- * - Not less then NFS4_POLL_RETRY_MIN.
- * - One last time a jiffie before we give up
- * - exponential backoff (time_now minus start_attempt)
- */
- delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
- min((giveup - now - 1),
- now - lgp->args.timestamp));
-
- dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
- __func__, delay);
- rpc_delay(task, delay);
- /* Do not call nfs4_async_handle_error() */
- goto out_restart;
+ if (lgp->args.minlength == 0) {
+ status = -EOVERFLOW;
+ goto out;
}
- break;
+ /* Fallthrough */
+ case -NFS4ERR_RECALLCONFLICT:
+ nfs4_handle_exception(server, -NFS4ERR_RECALLCONFLICT,
+ exception);
+ status = -ERECALLCONFLICT;
+ goto out;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
+ exception->timeout = 0;
spin_lock(&inode->i_lock);
if (nfs4_stateid_match(&lgp->args.stateid,
&lgp->args.ctx->state->stateid)) {
spin_unlock(&inode->i_lock);
/* If the open stateid was bad, then recover it. */
- state = lgp->args.ctx->state;
+ exception->state = lgp->args.ctx->state;
break;
}
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match(&lgp->args.stateid,
- &lo->plh_stateid)) {
+ if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) &&
+ nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
LIST_HEAD(head);
/*
@@ -7926,25 +7932,21 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
* with the current stateid.
*/
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
+ status = -EAGAIN;
+ goto out;
} else
spin_unlock(&inode->i_lock);
- goto out_restart;
}
- if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
- goto out_restart;
+
+ status = nfs4_handle_exception(server, status, exception);
+ if (exception->retry)
+ status = -EAGAIN;
out:
dprintk("<-- %s\n", __func__);
- return;
-out_restart:
- task->tk_status = 0;
- rpc_restart_call_prepare(task);
- return;
-out_overflow:
- task->tk_status = -EOVERFLOW;
- goto out;
+ return status;
}
static size_t max_response_pages(struct nfs_server *server)
@@ -8013,7 +8015,7 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
};
struct pnfs_layout_segment *
-nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
{
struct inode *inode = lgp->args.inode;
struct nfs_server *server = NFS_SERVER(inode);
@@ -8033,6 +8035,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
.flags = RPC_TASK_ASYNC,
};
struct pnfs_layout_segment *lseg = NULL;
+ struct nfs4_exception exception = {
+ .inode = inode,
+ .timeout = *timeout,
+ };
int status = 0;
dprintk("--> %s\n", __func__);
@@ -8046,7 +8052,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
return ERR_PTR(-ENOMEM);
}
lgp->args.layout.pglen = max_pages * PAGE_SIZE;
- lgp->args.timestamp = jiffies;
lgp->res.layoutp = &lgp->args.layout;
lgp->res.seq_res.sr_slot = NULL;
@@ -8056,13 +8061,17 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
if (IS_ERR(task))
return ERR_CAST(task);
status = nfs4_wait_for_completion_rpc_task(task);
- if (status == 0)
- status = task->tk_status;
+ if (status == 0) {
+ status = nfs4_layoutget_handle_exception(task, lgp, &exception);
+ *timeout = exception.timeout;
+ }
+
trace_nfs4_layoutget(lgp->args.ctx,
&lgp->args.range,
&lgp->res.range,
&lgp->res.stateid,
status);
+
/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
if (status == 0 && lgp->res.layoutp->len)
lseg = pnfs_layout_process(lgp);
@@ -8118,7 +8127,8 @@ static void nfs4_layoutreturn_release(void *calldata)
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
- pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
+ be32_to_cpu(lrp->args.stateid.seqid));
pnfs_mark_layout_returned_if_empty(lo);
if (lrp->res.lrs_present)
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
@@ -8653,6 +8663,9 @@ nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
static bool nfs41_match_stateid(const nfs4_stateid *s1,
const nfs4_stateid *s2)
{
+ if (s1->type != s2->type)
+ return false;
+
if (memcmp(s1->other, s2->other, sizeof(s1->other)) != 0)
return false;
@@ -8793,6 +8806,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_STATEID_NFSV41
| NFS_CAP_ATOMIC_OPEN_V1
| NFS_CAP_ALLOCATE
+ | NFS_CAP_COPY
| NFS_CAP_DEALLOCATE
| NFS_CAP_SEEK
| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d854693a15b0..834b875900d6 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -65,7 +65,10 @@
#define OPENOWNER_POOL_SIZE 8
-const nfs4_stateid zero_stateid;
+const nfs4_stateid zero_stateid = {
+ { .data = { 0 } },
+ .type = NFS4_SPECIAL_STATEID_TYPE,
+};
static DEFINE_MUTEX(nfs_clid_init_mutex);
int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
@@ -985,15 +988,20 @@ static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
* Byte-range lock aware utility to initialize the stateid of read/write
* requests.
*/
-int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
- fmode_t fmode, const struct nfs_lockowner *lockowner)
+int nfs4_select_rw_stateid(struct nfs4_state *state,
+ fmode_t fmode, const struct nfs_lockowner *lockowner,
+ nfs4_stateid *dst, struct rpc_cred **cred)
{
- int ret = nfs4_copy_lock_stateid(dst, state, lockowner);
+ int ret;
+
+ if (cred != NULL)
+ *cred = NULL;
+ ret = nfs4_copy_lock_stateid(dst, state, lockowner);
if (ret == -EIO)
/* A lost lock - don't even consider delegations */
goto out;
/* returns true if delegation stateid found and copied */
- if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+ if (nfs4_copy_delegation_stateid(state->inode, fmode, dst, cred)) {
ret = 0;
goto out;
}
@@ -1480,9 +1488,9 @@ restart:
}
spin_unlock(&state->state_lock);
}
- nfs4_put_open_state(state);
clear_bit(NFS_STATE_RECLAIM_NOGRACE,
&state->flags);
+ nfs4_put_open_state(state);
spin_lock(&sp->so_lock);
goto restart;
}
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 2c8d05dae5b1..9c150b153782 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -1520,6 +1520,8 @@ DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
{ PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" }, \
{ PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" }, \
{ PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \
+ { PNFS_UPDATE_LAYOUT_INVALID_OPEN, "invalid open" }, \
+ { PNFS_UPDATE_LAYOUT_RETRY, "retrying" }, \
{ PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" })
TRACE_EVENT(pnfs_update_layout,
@@ -1528,9 +1530,10 @@ TRACE_EVENT(pnfs_update_layout,
u64 count,
enum pnfs_iomode iomode,
struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_segment *lseg,
enum pnfs_update_layout_reason reason
),
- TP_ARGS(inode, pos, count, iomode, lo, reason),
+ TP_ARGS(inode, pos, count, iomode, lo, lseg, reason),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(u64, fileid)
@@ -1540,6 +1543,7 @@ TRACE_EVENT(pnfs_update_layout,
__field(enum pnfs_iomode, iomode)
__field(int, layoutstateid_seq)
__field(u32, layoutstateid_hash)
+ __field(long, lseg)
__field(enum pnfs_update_layout_reason, reason)
),
TP_fast_assign(
@@ -1559,11 +1563,12 @@ TRACE_EVENT(pnfs_update_layout,
__entry->layoutstateid_seq = 0;
__entry->layoutstateid_hash = 0;
}
+ __entry->lseg = (long)lseg;
),
TP_printk(
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"iomode=%s pos=%llu count=%llu "
- "layoutstateid=%d:0x%08x (%s)",
+ "layoutstateid=%d:0x%08x lseg=0x%lx (%s)",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1571,6 +1576,7 @@ TRACE_EVENT(pnfs_update_layout,
(unsigned long long)__entry->pos,
(unsigned long long)__entry->count,
__entry->layoutstateid_seq, __entry->layoutstateid_hash,
+ __entry->lseg,
show_pnfs_update_layout_reason(__entry->reason)
)
);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 88474a4fc669..661e753fe1c9 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4270,6 +4270,24 @@ static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
}
+static int decode_open_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_OPEN_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
+static int decode_lock_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_LOCK_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
+static int decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_DELEGATION_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
{
int status;
@@ -4278,7 +4296,7 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
if (status != -EIO)
nfs_increment_open_seqid(status, res->seqid);
if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
return status;
}
@@ -4937,7 +4955,7 @@ static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res)
if (status == -EIO)
goto out;
if (status == 0) {
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_lock_stateid(xdr, &res->stateid);
if (unlikely(status))
goto out;
} else if (status == -NFS4ERR_DENIED)
@@ -4966,7 +4984,7 @@ static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res)
if (status != -EIO)
nfs_increment_lock_seqid(status, res->seqid);
if (status == 0)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_lock_stateid(xdr, &res->stateid);
return status;
}
@@ -5016,7 +5034,7 @@ static int decode_rw_delegation(struct xdr_stream *xdr,
__be32 *p;
int status;
- status = decode_stateid(xdr, &res->delegation);
+ status = decode_delegation_stateid(xdr, &res->delegation);
if (unlikely(status))
return status;
p = xdr_inline_decode(xdr, 4);
@@ -5096,7 +5114,7 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
nfs_increment_open_seqid(status, res->seqid);
if (status)
return status;
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
if (unlikely(status))
return status;
@@ -5136,7 +5154,7 @@ static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmre
if (status != -EIO)
nfs_increment_open_seqid(status, res->seqid);
if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
return status;
}
@@ -5148,7 +5166,7 @@ static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *re
if (status != -EIO)
nfs_increment_open_seqid(status, res->seqid);
if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
return status;
}
@@ -5838,6 +5856,12 @@ out_overflow:
}
#if defined(CONFIG_NFS_V4_1)
+static int decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_LAYOUT_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
static int decode_getdeviceinfo(struct xdr_stream *xdr,
struct nfs4_getdeviceinfo_res *res)
{
@@ -5919,7 +5943,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
if (unlikely(!p))
goto out_overflow;
res->return_on_close = be32_to_cpup(p);
- decode_stateid(xdr, &res->stateid);
+ decode_layout_stateid(xdr, &res->stateid);
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
@@ -5985,7 +6009,7 @@ static int decode_layoutreturn(struct xdr_stream *xdr,
goto out_overflow;
res->lrs_present = be32_to_cpup(p);
if (res->lrs_present)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_layout_stateid(xdr, &res->stateid);
return status;
out_overflow:
print_overflow_msg(__func__, xdr);
@@ -7515,6 +7539,7 @@ struct rpc_procinfo nfs4_procedures[] = {
PROC(DEALLOCATE, enc_deallocate, dec_deallocate),
PROC(LAYOUTSTATS, enc_layoutstats, dec_layoutstats),
PROC(CLONE, enc_clone, dec_clone),
+ PROC(COPY, enc_copy, dec_copy),
#endif /* CONFIG_NFS_V4_2 */
};
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 1f6db4231057..174dd4cf5747 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -341,8 +341,10 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page,
* long write-back delay. This will be adjusted in
* update_nfs_request below if the region is not locked. */
req->wb_page = page;
- req->wb_index = page_file_index(page);
- get_page(page);
+ if (page) {
+ req->wb_index = page_file_index(page);
+ get_page(page);
+ }
req->wb_offset = offset;
req->wb_pgbase = offset;
req->wb_bytes = count;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 89a5ef4df08a..0fbe734cc38c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -270,7 +270,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
};
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range);
+ return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range, 0);
}
static int
@@ -308,7 +308,7 @@ pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
spin_lock(&inode->i_lock);
pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
- pnfs_mark_matching_lsegs_invalid(lo, &head, &range);
+ pnfs_mark_matching_lsegs_invalid(lo, &head, &range, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
@@ -361,8 +361,10 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
list_del_init(&lseg->pls_list);
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
- if (list_empty(&lo->plh_segs))
+ if (list_empty(&lo->plh_segs)) {
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+ }
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
}
@@ -522,13 +524,35 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
return rv;
}
-/* Returns count of number of matching invalid lsegs remaining in list
- * after call.
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+ return (s32)(s1 - s2) > 0;
+}
+
+/**
+ * pnfs_mark_matching_lsegs_invalid - tear down lsegs or mark them for later
+ * @lo: layout header containing the lsegs
+ * @tmp_list: list head where doomed lsegs should go
+ * @recall_range: optional recall range argument to match (may be NULL)
+ * @seq: only invalidate lsegs obtained prior to this sequence (may be 0)
+ *
+ * Walk the list of lsegs in the layout header, and tear down any that should
+ * be destroyed. If "recall_range" is specified then the segment must match
+ * that range. If "seq" is non-zero, then only match segments that were handed
+ * out at or before that sequence.
+ *
+ * Returns number of matching invalid lsegs remaining in list after scanning
+ * it and purging them.
*/
int
pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *recall_range)
+ const struct pnfs_layout_range *recall_range,
+ u32 seq)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
@@ -540,10 +564,12 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (!recall_range ||
should_free_lseg(&lseg->pls_range, recall_range)) {
- dprintk("%s: freeing lseg %p iomode %d "
+ if (seq && pnfs_seqid_is_newer(lseg->pls_seq, seq))
+ continue;
+ dprintk("%s: freeing lseg %p iomode %d seq %u"
"offset %llu length %llu\n", __func__,
- lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
- lseg->pls_range.length);
+ lseg, lseg->pls_range.iomode, lseg->pls_seq,
+ lseg->pls_range.offset, lseg->pls_range.length);
if (!mark_lseg_invalid(lseg, tmp_list))
remaining++;
}
@@ -730,15 +756,6 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
pnfs_destroy_layouts_byclid(clp, false);
}
-/*
- * Compare 2 layout stateid sequence ids, to see which is newer,
- * taking into account wraparound issues.
- */
-static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
-{
- return (s32)(s1 - s2) > 0;
-}
-
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
@@ -781,50 +798,22 @@ pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo)
test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
-int
-pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
- const struct pnfs_layout_range *range,
- struct nfs4_state *open_state)
-{
- int status = 0;
-
- dprintk("--> %s\n", __func__);
- spin_lock(&lo->plh_inode->i_lock);
- if (pnfs_layoutgets_blocked(lo)) {
- status = -EAGAIN;
- } else if (!nfs4_valid_open_stateid(open_state)) {
- status = -EBADF;
- } else if (list_empty(&lo->plh_segs) ||
- test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
- int seq;
-
- do {
- seq = read_seqbegin(&open_state->seqlock);
- nfs4_stateid_copy(dst, &open_state->stateid);
- } while (read_seqretry(&open_state->seqlock, seq));
- } else
- nfs4_stateid_copy(dst, &lo->plh_stateid);
- spin_unlock(&lo->plh_inode->i_lock);
- dprintk("<-- %s\n", __func__);
- return status;
-}
-
/*
-* Get layout from server.
-* for now, assume that whole file layouts are requested.
-* arg->offset: 0
-* arg->length: all ones
-*/
+ * Get layout from server.
+ * for now, assume that whole file layouts are requested.
+ * arg->offset: 0
+ * arg->length: all ones
+ */
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
struct nfs_open_context *ctx,
+ nfs4_stateid *stateid,
const struct pnfs_layout_range *range,
- gfp_t gfp_flags)
+ long *timeout, gfp_t gfp_flags)
{
struct inode *ino = lo->plh_inode;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs4_layoutget *lgp;
- struct pnfs_layout_segment *lseg;
loff_t i_size;
dprintk("--> %s\n", __func__);
@@ -834,40 +823,31 @@ send_layoutget(struct pnfs_layout_hdr *lo,
* store in lseg. If we race with a concurrent seqid morphing
* op, then re-send the LAYOUTGET.
*/
- do {
- lgp = kzalloc(sizeof(*lgp), gfp_flags);
- if (lgp == NULL)
- return NULL;
-
- i_size = i_size_read(ino);
-
- lgp->args.minlength = PAGE_SIZE;
- if (lgp->args.minlength > range->length)
- lgp->args.minlength = range->length;
- if (range->iomode == IOMODE_READ) {
- if (range->offset >= i_size)
- lgp->args.minlength = 0;
- else if (i_size - range->offset < lgp->args.minlength)
- lgp->args.minlength = i_size - range->offset;
- }
- lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
- pnfs_copy_range(&lgp->args.range, range);
- lgp->args.type = server->pnfs_curr_ld->id;
- lgp->args.inode = ino;
- lgp->args.ctx = get_nfs_open_context(ctx);
- lgp->gfp_flags = gfp_flags;
- lgp->cred = lo->plh_lc_cred;
-
- lseg = nfs4_proc_layoutget(lgp, gfp_flags);
- } while (lseg == ERR_PTR(-EAGAIN));
-
- if (IS_ERR(lseg) && !nfs_error_is_fatal(PTR_ERR(lseg)))
- lseg = NULL;
- else
- pnfs_layout_clear_fail_bit(lo,
- pnfs_iomode_to_fail_bit(range->iomode));
+ lgp = kzalloc(sizeof(*lgp), gfp_flags);
+ if (lgp == NULL)
+ return ERR_PTR(-ENOMEM);
- return lseg;
+ i_size = i_size_read(ino);
+
+ lgp->args.minlength = PAGE_SIZE;
+ if (lgp->args.minlength > range->length)
+ lgp->args.minlength = range->length;
+ if (range->iomode == IOMODE_READ) {
+ if (range->offset >= i_size)
+ lgp->args.minlength = 0;
+ else if (i_size - range->offset < lgp->args.minlength)
+ lgp->args.minlength = i_size - range->offset;
+ }
+ lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+ pnfs_copy_range(&lgp->args.range, range);
+ lgp->args.type = server->pnfs_curr_ld->id;
+ lgp->args.inode = ino;
+ lgp->args.ctx = get_nfs_open_context(ctx);
+ nfs4_stateid_copy(&lgp->args.stateid, stateid);
+ lgp->gfp_flags = gfp_flags;
+ lgp->cred = lo->plh_lc_cred;
+
+ return nfs4_proc_layoutget(lgp, timeout, gfp_flags);
}
static void pnfs_clear_layoutcommit(struct inode *inode,
@@ -899,6 +879,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
lo->plh_return_iomode = 0;
+ lo->plh_return_seq = 0;
pnfs_get_layout_hdr(lo);
clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
return true;
@@ -969,6 +950,7 @@ static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
bool send;
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
+ stateid.seqid = cpu_to_be32(lo->plh_return_seq);
iomode = lo->plh_return_iomode;
send = pnfs_prepare_layoutreturn(lo);
spin_unlock(&inode->i_lock);
@@ -1012,7 +994,7 @@ _pnfs_return_layout(struct inode *ino)
pnfs_get_layout_hdr(lo);
empty = list_empty(&lo->plh_segs);
pnfs_clear_layoutcommit(ino, &tmp_list);
- pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL, 0);
if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
struct pnfs_layout_range range = {
@@ -1310,6 +1292,7 @@ alloc_init_layout_hdr(struct inode *ino,
INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
lo->plh_lc_cred = get_rpccred(ctx->cred);
+ lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID;
return lo;
}
@@ -1317,6 +1300,8 @@ static struct pnfs_layout_hdr *
pnfs_find_alloc_layout(struct inode *ino,
struct nfs_open_context *ctx,
gfp_t gfp_flags)
+ __releases(&ino->i_lock)
+ __acquires(&ino->i_lock)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct pnfs_layout_hdr *new = NULL;
@@ -1341,23 +1326,28 @@ out_existing:
/*
* iomode matching rules:
- * iomode lseg match
- * ----- ----- -----
- * ANY READ true
- * ANY RW true
- * RW READ false
- * RW RW true
- * READ READ true
- * READ RW true
+ * iomode lseg strict match
+ * iomode
+ * ----- ----- ------ -----
+ * ANY READ N/A true
+ * ANY RW N/A true
+ * RW READ N/A false
+ * RW RW N/A true
+ * READ READ N/A true
+ * READ RW true false
+ * READ RW false true
*/
static bool
pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range,
- const struct pnfs_layout_range *range)
+ const struct pnfs_layout_range *range,
+ bool strict_iomode)
{
struct pnfs_layout_range range1;
if ((range->iomode == IOMODE_RW &&
ls_range->iomode != IOMODE_RW) ||
+ (range->iomode != ls_range->iomode &&
+ strict_iomode == true) ||
!pnfs_lseg_range_intersecting(ls_range, range))
return 0;
@@ -1372,7 +1362,8 @@ pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range,
*/
static struct pnfs_layout_segment *
pnfs_find_lseg(struct pnfs_layout_hdr *lo,
- struct pnfs_layout_range *range)
+ struct pnfs_layout_range *range,
+ bool strict_iomode)
{
struct pnfs_layout_segment *lseg, *ret = NULL;
@@ -1381,7 +1372,8 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
- pnfs_lseg_range_match(&lseg->pls_range, range)) {
+ pnfs_lseg_range_match(&lseg->pls_range, range,
+ strict_iomode)) {
ret = pnfs_get_lseg(lseg);
break;
}
@@ -1498,6 +1490,7 @@ pnfs_update_layout(struct inode *ino,
loff_t pos,
u64 count,
enum pnfs_iomode iomode,
+ bool strict_iomode,
gfp_t gfp_flags)
{
struct pnfs_layout_range arg = {
@@ -1505,27 +1498,30 @@ pnfs_update_layout(struct inode *ino,
.offset = pos,
.length = count,
};
- unsigned pg_offset;
+ unsigned pg_offset, seq;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs_client *clp = server->nfs_client;
- struct pnfs_layout_hdr *lo;
+ struct pnfs_layout_hdr *lo = NULL;
struct pnfs_layout_segment *lseg = NULL;
+ nfs4_stateid stateid;
+ long timeout = 0;
+ unsigned long giveup = jiffies + rpc_get_timeout(server->client);
bool first;
if (!pnfs_enabled_sb(NFS_SERVER(ino))) {
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_NO_PNFS);
goto out;
}
if (iomode == IOMODE_READ && i_size_read(ino) == 0) {
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_RD_ZEROLEN);
goto out;
}
if (pnfs_within_mdsthreshold(ctx, ino, iomode)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_MDSTHRESH);
goto out;
}
@@ -1536,14 +1532,14 @@ lookup_again:
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) {
spin_unlock(&ino->i_lock);
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_NOMEM);
goto out;
}
/* Do we even need to bother with this? */
if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BULK_RECALL);
dprintk("%s matches recall, use MDS\n", __func__);
goto out_unlock;
@@ -1551,14 +1547,33 @@ lookup_again:
/* if LAYOUTGET already failed once we don't try again */
if (pnfs_layout_io_test_failed(lo, iomode)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_IO_TEST_FAIL);
goto out_unlock;
}
- first = list_empty(&lo->plh_segs);
- if (first) {
- /* The first layoutget for the file. Need to serialize per
+ lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
+ if (lseg) {
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_FOUND_CACHED);
+ goto out_unlock;
+ }
+
+ if (!nfs4_valid_open_stateid(ctx->state)) {
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_INVALID_OPEN);
+ goto out_unlock;
+ }
+
+ /*
+ * Choose a stateid for the LAYOUTGET. If we don't have a layout
+ * stateid, or it has been invalidated, then we must use the open
+ * stateid.
+ */
+ if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+
+ /*
+ * The first layoutget for the file. Need to serialize per
* RFC 5661 Errata 3208.
*/
if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
@@ -1567,18 +1582,17 @@ lookup_again:
wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
TASK_UNINTERRUPTIBLE);
pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
goto lookup_again;
}
+
+ first = true;
+ do {
+ seq = read_seqbegin(&ctx->state->seqlock);
+ nfs4_stateid_copy(&stateid, &ctx->state->stateid);
+ } while (read_seqretry(&ctx->state->seqlock, seq));
} else {
- /* Check to see if the layout for the given range
- * already exists
- */
- lseg = pnfs_find_lseg(lo, &arg);
- if (lseg) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
- PNFS_UPDATE_LAYOUT_FOUND_CACHED);
- goto out_unlock;
- }
+ nfs4_stateid_copy(&stateid, &lo->plh_stateid);
}
/*
@@ -1593,15 +1607,17 @@ lookup_again:
pnfs_clear_first_layoutget(lo);
pnfs_put_layout_hdr(lo);
dprintk("%s retrying\n", __func__);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg, PNFS_UPDATE_LAYOUT_RETRY);
goto lookup_again;
}
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_RETURN);
goto out_put_layout_hdr;
}
if (pnfs_layoutgets_blocked(lo)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BLOCKED);
goto out_unlock;
}
@@ -1626,10 +1642,36 @@ lookup_again:
if (arg.length != NFS4_MAX_UINT64)
arg.length = PAGE_ALIGN(arg.length);
- lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
- atomic_dec(&lo->plh_outstanding);
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg = send_layoutget(lo, ctx, &stateid, &arg, &timeout, gfp_flags);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
+ if (IS_ERR(lseg)) {
+ switch(PTR_ERR(lseg)) {
+ case -ERECALLCONFLICT:
+ if (time_after(jiffies, giveup))
+ lseg = NULL;
+ /* Fallthrough */
+ case -EAGAIN:
+ pnfs_put_layout_hdr(lo);
+ if (first)
+ pnfs_clear_first_layoutget(lo);
+ if (lseg) {
+ trace_pnfs_update_layout(ino, pos, count,
+ iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY);
+ goto lookup_again;
+ }
+ /* Fallthrough */
+ default:
+ if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
+ pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+ lseg = NULL;
+ }
+ }
+ } else {
+ pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+ }
+
+ atomic_dec(&lo->plh_outstanding);
out_put_layout_hdr:
if (first)
pnfs_clear_first_layoutget(lo);
@@ -1678,38 +1720,36 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
struct pnfs_layout_segment *lseg;
struct inode *ino = lo->plh_inode;
LIST_HEAD(free_me);
- int status = -EINVAL;
if (!pnfs_sanity_check_layout_range(&res->range))
- goto out;
+ return ERR_PTR(-EINVAL);
/* Inject layout blob into I/O device driver */
lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags);
- if (!lseg || IS_ERR(lseg)) {
+ if (IS_ERR_OR_NULL(lseg)) {
if (!lseg)
- status = -ENOMEM;
- else
- status = PTR_ERR(lseg);
- dprintk("%s: Could not allocate layout: error %d\n",
- __func__, status);
- goto out;
+ lseg = ERR_PTR(-ENOMEM);
+
+ dprintk("%s: Could not allocate layout: error %ld\n",
+ __func__, PTR_ERR(lseg));
+ return lseg;
}
init_lseg(lo, lseg);
lseg->pls_range = res->range;
+ lseg->pls_seq = be32_to_cpu(res->stateid.seqid);
spin_lock(&ino->i_lock);
if (pnfs_layoutgets_blocked(lo)) {
dprintk("%s forget reply due to state\n", __func__);
- goto out_forget_reply;
+ goto out_forget;
}
if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
dprintk("%s forget reply due to sequence\n", __func__);
- status = -EAGAIN;
- goto out_forget_reply;
+ goto out_forget;
}
pnfs_set_layout_stateid(lo, &res->stateid, false);
} else {
@@ -1718,7 +1758,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
* inode invalid, and don't bother validating the stateid
* sequence number.
*/
- pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL, 0);
nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
@@ -1735,18 +1775,17 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&free_me);
return lseg;
-out:
- return ERR_PTR(status);
-out_forget_reply:
+out_forget:
spin_unlock(&ino->i_lock);
lseg->pls_layout = lo;
NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
- goto out;
+ return ERR_PTR(-EAGAIN);
}
static void
-pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
+pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
+ u32 seq)
{
if (lo->plh_return_iomode == iomode)
return;
@@ -1754,6 +1793,8 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
iomode = IOMODE_ANY;
lo->plh_return_iomode = iomode;
set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+ if (!lo->plh_return_seq || pnfs_seqid_is_newer(seq, lo->plh_return_seq))
+ lo->plh_return_seq = seq;
}
/**
@@ -1769,7 +1810,8 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
int
pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *return_range)
+ const struct pnfs_layout_range *return_range,
+ u32 seq)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
@@ -1792,8 +1834,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
continue;
remaining++;
set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
- pnfs_set_plh_return_iomode(lo, return_range->iomode);
}
+
+ if (remaining)
+ pnfs_set_plh_return_info(lo, return_range->iomode, seq);
+
return remaining;
}
@@ -1810,13 +1855,14 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
bool return_now = false;
spin_lock(&inode->i_lock);
- pnfs_set_plh_return_iomode(lo, range.iomode);
+ pnfs_set_plh_return_info(lo, range.iomode, lseg->pls_seq);
/*
* mark all matching lsegs so that we are sure to have no live
* segments at hand when sending layoutreturn. See pnfs_put_lseg()
* for how it works.
*/
- if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range)) {
+ if (!pnfs_mark_matching_lsegs_return(lo, &free_me,
+ &range, lseg->pls_seq)) {
nfs4_stateid stateid;
enum pnfs_iomode iomode = lo->plh_return_iomode;
@@ -1849,6 +1895,7 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
req_offset(req),
rd_size,
IOMODE_READ,
+ false,
GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -1873,6 +1920,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
req_offset(req),
wb_size,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -2143,12 +2191,15 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
}
/* Resend all requests through pnfs. */
-int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
{
struct nfs_pageio_descriptor pgio;
- nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops);
- return nfs_pageio_resend(&pgio, hdr);
+ if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ nfs_pageio_init_read(&pgio, hdr->inode, false,
+ hdr->completion_ops);
+ hdr->task.tk_status = nfs_pageio_resend(&pgio, hdr);
+ }
}
EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs);
@@ -2158,12 +2209,11 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
enum pnfs_try_status trypnfs;
- int err = 0;
trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
if (trypnfs == PNFS_TRY_AGAIN)
- err = pnfs_read_resend_pnfs(hdr);
- if (trypnfs == PNFS_NOT_ATTEMPTED || err)
+ pnfs_read_resend_pnfs(hdr);
+ if (trypnfs == PNFS_NOT_ATTEMPTED || hdr->task.tk_status)
pnfs_read_through_mds(desc, hdr);
}
@@ -2405,7 +2455,7 @@ pnfs_report_layoutstat(struct inode *inode, gfp_t gfp_flags)
spin_lock(&inode->i_lock);
if (!NFS_I(inode)->layout) {
spin_unlock(&inode->i_lock);
- goto out;
+ goto out_clear_layoutstats;
}
hdr = NFS_I(inode)->layout;
pnfs_get_layout_hdr(hdr);
@@ -2434,6 +2484,7 @@ out_free:
kfree(data);
out_put:
pnfs_put_layout_hdr(hdr);
+out_clear_layoutstats:
smp_mb__before_atomic();
clear_bit(NFS_INO_LAYOUTSTATS, &nfsi->flags);
smp_mb__after_atomic();
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1ac1db5f6dad..b21bd0bee784 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -64,6 +64,7 @@ struct pnfs_layout_segment {
struct list_head pls_lc_list;
struct pnfs_layout_range pls_range;
atomic_t pls_refcount;
+ u32 pls_seq;
unsigned long pls_flags;
struct pnfs_layout_hdr *pls_layout;
struct work_struct pls_work;
@@ -194,6 +195,7 @@ struct pnfs_layout_hdr {
unsigned long plh_flags;
nfs4_stateid plh_stateid;
u32 plh_barrier; /* ignore lower seqids */
+ u32 plh_return_seq;
enum pnfs_iomode plh_return_iomode;
loff_t plh_lwb; /* last write byte for layoutcommit */
struct rpc_cred *plh_lc_cred; /* layoutcommit cred */
@@ -226,7 +228,7 @@ extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *dev,
struct rpc_cred *cred);
-extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
+extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags);
extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
/* pnfs.c */
@@ -258,16 +260,14 @@ void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
const nfs4_stateid *new,
bool update_barrier);
-int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
- struct pnfs_layout_hdr *lo,
- const struct pnfs_layout_range *range,
- struct nfs4_state *open_state);
int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *recall_range);
+ const struct pnfs_layout_range *recall_range,
+ u32 seq);
int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *recall_range);
+ const struct pnfs_layout_range *recall_range,
+ u32 seq);
bool pnfs_roc(struct inode *ino);
void pnfs_roc_release(struct inode *ino);
void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
@@ -282,12 +282,13 @@ int _pnfs_return_layout(struct inode *);
int pnfs_commit_and_return_layout(struct inode *);
void pnfs_ld_write_done(struct nfs_pgio_header *);
void pnfs_ld_read_done(struct nfs_pgio_header *);
-int pnfs_read_resend_pnfs(struct nfs_pgio_header *);
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *);
struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
struct nfs_open_context *ctx,
loff_t pos,
u64 count,
enum pnfs_iomode iomode,
+ bool strict_iomode,
gfp_t gfp_flags);
void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 4aaed890048f..b38e3c0dc790 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -61,7 +61,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_release);
/* The generic layer is about to remove the req from the commit list.
* If this will make the bucket empty, it will need to put the lseg reference.
- * Note this must be called holding the inode (/cinfo) lock
+ * Note this must be called holding i_lock
*/
void
pnfs_generic_clear_request_commit(struct nfs_page *req,
@@ -98,7 +98,7 @@ pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst,
if (!nfs_lock_request(req))
continue;
kref_get(&req->wb_kref);
- if (cond_resched_lock(cinfo->lock))
+ if (cond_resched_lock(&cinfo->inode->i_lock))
list_safe_reset_next(req, tmp, wb_list);
nfs_request_remove_commit_list(req, cinfo);
clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
@@ -119,7 +119,7 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
struct list_head *dst = &bucket->committing;
int ret;
- lockdep_assert_held(cinfo->lock);
+ lockdep_assert_held(&cinfo->inode->i_lock);
ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max);
if (ret) {
cinfo->ds->nwritten -= ret;
@@ -142,7 +142,7 @@ int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
{
int i, rv = 0, cnt;
- lockdep_assert_held(cinfo->lock);
+ lockdep_assert_held(&cinfo->inode->i_lock);
for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i],
cinfo, max);
@@ -161,16 +161,16 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst,
struct pnfs_layout_segment *freeme;
int i;
- lockdep_assert_held(cinfo->lock);
+ lockdep_assert_held(&cinfo->inode->i_lock);
restart:
for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
if (pnfs_generic_transfer_commit_list(&b->written, dst,
cinfo, 0)) {
freeme = b->wlseg;
b->wlseg = NULL;
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
pnfs_put_lseg(freeme);
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
goto restart;
}
}
@@ -186,7 +186,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
LIST_HEAD(pages);
int i;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
for (i = idx; i < fl_cinfo->nbuckets; i++) {
bucket = &fl_cinfo->buckets[i];
if (list_empty(&bucket->committing))
@@ -194,12 +194,12 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
freeme = bucket->clseg;
bucket->clseg = NULL;
list_splice_init(&bucket->committing, &pages);
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
nfs_retry_commit(&pages, freeme, cinfo, i);
pnfs_put_lseg(freeme);
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
}
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
}
static unsigned int
@@ -238,14 +238,39 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
struct pnfs_commit_bucket *bucket;
bucket = &cinfo->ds->buckets[data->ds_commit_index];
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
list_splice_init(&bucket->committing, pages);
data->lseg = bucket->clseg;
bucket->clseg = NULL;
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
}
+/* Helper function for pnfs_generic_commit_pagelist to catch an empty
+ * page list. This can happen when two commits race.
+ *
+ * This must be called instead of nfs_init_commit - call one or the other, but
+ * not both!
+ */
+static bool
+pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
+ struct nfs_commit_data *data,
+ struct nfs_commit_info *cinfo)
+{
+ if (list_empty(pages)) {
+ if (atomic_dec_and_test(&cinfo->mds->rpcs_out))
+ wake_up_atomic_t(&cinfo->mds->rpcs_out);
+ /* don't call nfs_commitdata_release - it tries to put
+ * the open_context which is not acquired until nfs_init_commit
+ * which has not been called on @data */
+ WARN_ON_ONCE(data->context);
+ nfs_commit_free(data);
+ return true;
+ }
+
+ return false;
+}
+
/* This follows nfs_commit_list pretty closely */
int
pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
@@ -280,6 +305,11 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
list_for_each_entry_safe(data, tmp, &list, pages) {
list_del_init(&data->pages);
if (data->ds_commit_index < 0) {
+ /* another commit raced with us */
+ if (pnfs_generic_commit_cancel_empty_pagelist(mds_pages,
+ data, cinfo))
+ continue;
+
nfs_init_commit(data, mds_pages, NULL, cinfo);
nfs_initiate_commit(NFS_CLIENT(inode), data,
NFS_PROTO(data->inode),
@@ -288,6 +318,12 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
LIST_HEAD(pages);
pnfs_fetch_commit_bucket_list(&pages, data, cinfo);
+
+ /* another commit raced with us */
+ if (pnfs_generic_commit_cancel_empty_pagelist(&pages,
+ data, cinfo))
+ continue;
+
nfs_init_commit(data, &pages, data->lseg, cinfo);
initiate_commit(data, how);
}
@@ -874,12 +910,12 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
struct list_head *list;
struct pnfs_commit_bucket *buckets;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
buckets = cinfo->ds->buckets;
list = &buckets[ds_commit_idx].written;
if (list_empty(list)) {
if (!pnfs_is_valid_lseg(lseg)) {
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
cinfo->completion_ops->resched_write(cinfo, req);
return;
}
@@ -896,7 +932,7 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
cinfo->ds->nwritten++;
nfs_request_add_commit_list_locked(req, list, cinfo);
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
nfs_mark_page_unstable(req->wb_page, cinfo);
}
EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 6776d7a7839e..572e5b3b06f1 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -367,13 +367,13 @@ readpage_async_filler(void *data, struct page *page)
nfs_list_remove_request(new);
nfs_readpage_release(new);
error = desc->pgio->pg_error;
- goto out_unlock;
+ goto out;
}
return 0;
out_error:
error = PTR_ERR(new);
-out_unlock:
unlock_page(page);
+out:
return error;
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f1268280244e..2137e0202f25 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -191,6 +191,7 @@ static const match_table_t nfs_mount_option_tokens = {
enum {
Opt_xprt_udp, Opt_xprt_udp6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_rdma,
+ Opt_xprt_rdma6,
Opt_xprt_err
};
@@ -201,6 +202,7 @@ static const match_table_t nfs_xprt_protocol_tokens = {
{ Opt_xprt_tcp, "tcp" },
{ Opt_xprt_tcp6, "tcp6" },
{ Opt_xprt_rdma, "rdma" },
+ { Opt_xprt_rdma6, "rdma6" },
{ Opt_xprt_err, NULL }
};
@@ -1456,6 +1458,8 @@ static int nfs_parse_mount_options(char *raw,
mnt->flags |= NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
break;
+ case Opt_xprt_rdma6:
+ protofamily = AF_INET6;
case Opt_xprt_rdma:
/* vector side protocols to TCP */
mnt->flags |= NFS_MOUNT_TCP;
@@ -2408,6 +2412,11 @@ static int nfs_compare_super_address(struct nfs_server *server1,
struct nfs_server *server2)
{
struct sockaddr *sap1, *sap2;
+ struct rpc_xprt *xprt1 = server1->client->cl_xprt;
+ struct rpc_xprt *xprt2 = server2->client->cl_xprt;
+
+ if (!net_eq(xprt1->xprt_net, xprt2->xprt_net))
+ return 0;
sap1 = (struct sockaddr *)&server1->nfs_client->cl_addr;
sap2 = (struct sockaddr *)&server2->nfs_client->cl_addr;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5f4fd53e5764..e1c74d3db64d 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -245,8 +245,7 @@ static void nfs_mark_uptodate(struct nfs_page *req)
static int wb_priority(struct writeback_control *wbc)
{
int ret = 0;
- if (wbc->for_reclaim)
- return FLUSH_HIGHPRI | FLUSH_COND_STABLE;
+
if (wbc->sync_mode == WB_SYNC_ALL)
ret = FLUSH_COND_STABLE;
return ret;
@@ -737,7 +736,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
head = req->wb_head;
spin_lock(&inode->i_lock);
- if (likely(!PageSwapCache(head->wb_page))) {
+ if (likely(head->wb_page && !PageSwapCache(head->wb_page))) {
set_page_private(head->wb_page, 0);
ClearPagePrivate(head->wb_page);
smp_mb__after_atomic();
@@ -759,7 +758,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
static void
nfs_mark_request_dirty(struct nfs_page *req)
{
- __set_page_dirty_nobuffers(req->wb_page);
+ if (req->wb_page)
+ __set_page_dirty_nobuffers(req->wb_page);
}
/*
@@ -804,7 +804,7 @@ nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
* number of outstanding requests requiring a commit as well as
* the MM page stats.
*
- * The caller must hold the cinfo->lock, and the nfs_page lock.
+ * The caller must hold cinfo->inode->i_lock, and the nfs_page lock.
*/
void
nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst,
@@ -832,10 +832,11 @@ EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked);
void
nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo)
{
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo);
- spin_unlock(cinfo->lock);
- nfs_mark_page_unstable(req->wb_page, cinfo);
+ spin_unlock(&cinfo->inode->i_lock);
+ if (req->wb_page)
+ nfs_mark_page_unstable(req->wb_page, cinfo);
}
EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
@@ -864,7 +865,7 @@ EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
struct inode *inode)
{
- cinfo->lock = &inode->i_lock;
+ cinfo->inode = inode;
cinfo->mds = &NFS_I(inode)->commit_info;
cinfo->ds = pnfs_get_ds_info(inode);
cinfo->dreq = NULL;
@@ -967,7 +968,7 @@ nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
return cinfo->mds->ncommit;
}
-/* cinfo->lock held by caller */
+/* cinfo->inode->i_lock held by caller */
int
nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_commit_info *cinfo, int max)
@@ -979,7 +980,7 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
if (!nfs_lock_request(req))
continue;
kref_get(&req->wb_kref);
- if (cond_resched_lock(cinfo->lock))
+ if (cond_resched_lock(&cinfo->inode->i_lock))
list_safe_reset_next(req, tmp, wb_list);
nfs_request_remove_commit_list(req, cinfo);
nfs_list_add_request(req, dst);
@@ -1005,7 +1006,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
{
int ret = 0;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
if (cinfo->mds->ncommit > 0) {
const int max = INT_MAX;
@@ -1013,7 +1014,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
cinfo, max);
ret += pnfs_scan_commit_lists(inode, cinfo, max - ret);
}
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
return ret;
}
@@ -1709,6 +1710,10 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
{
struct nfs_commit_data *data;
+ /* another commit raced with us */
+ if (list_empty(head))
+ return 0;
+
data = nfs_commitdata_alloc();
if (!data)
@@ -1724,6 +1729,36 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
return -ENOMEM;
}
+int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf)
+{
+ struct inode *inode = file_inode(file);
+ struct nfs_open_context *open;
+ struct nfs_commit_info cinfo;
+ struct nfs_page *req;
+ int ret;
+
+ open = get_nfs_open_context(nfs_file_open_context(file));
+ req = nfs_create_request(open, NULL, NULL, 0, i_size_read(inode));
+ if (IS_ERR(req)) {
+ ret = PTR_ERR(req);
+ goto out_put;
+ }
+
+ nfs_init_cinfo_from_inode(&cinfo, inode);
+
+ memcpy(&req->wb_verf, verf, sizeof(struct nfs_write_verifier));
+ nfs_request_add_commit_list(req, &cinfo);
+ ret = nfs_commit_inode(inode, FLUSH_SYNC);
+ if (ret > 0)
+ ret = 0;
+
+ nfs_free_request(req);
+out_put:
+ put_nfs_open_context(open);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_commit_file);
+
/*
* COMMIT call returned
*/
@@ -1748,7 +1783,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
- nfs_clear_page_commit(req->wb_page);
+ if (req->wb_page)
+ nfs_clear_page_commit(req->wb_page);
dprintk("NFS: commit (%s/%llu %d@%lld)",
req->wb_context->dentry->d_sb->s_id,
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index e55b5242614d..31f3df193bdb 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -290,7 +290,7 @@ out_free_buf:
return error;
}
-#define NFSD_MDS_PR_KEY 0x0100000000000000
+#define NFSD_MDS_PR_KEY 0x0100000000000000ULL
/*
* We use the client ID as a unique key for the reservations.
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 1580ea6fd64d..d08cd88155c7 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -104,22 +104,21 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
goto out;
inode = d_inode(fh->fh_dentry);
- if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
- error = -EOPNOTSUPP;
- goto out_errno;
- }
error = fh_want_write(fh);
if (error)
goto out_errno;
- error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+ fh_lock(fh);
+
+ error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
if (error)
- goto out_drop_write;
- error = inode->i_op->set_acl(inode, argp->acl_default,
- ACL_TYPE_DEFAULT);
+ goto out_drop_lock;
+ error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
if (error)
- goto out_drop_write;
+ goto out_drop_lock;
+
+ fh_unlock(fh);
fh_drop_write(fh);
@@ -131,7 +130,8 @@ out:
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
return nfserr;
-out_drop_write:
+out_drop_lock:
+ fh_unlock(fh);
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 01df4cd7c753..0c890347cde3 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -95,22 +95,20 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
goto out;
inode = d_inode(fh->fh_dentry);
- if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
- error = -EOPNOTSUPP;
- goto out_errno;
- }
error = fh_want_write(fh);
if (error)
goto out_errno;
- error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+ fh_lock(fh);
+
+ error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
if (error)
- goto out_drop_write;
- error = inode->i_op->set_acl(inode, argp->acl_default,
- ACL_TYPE_DEFAULT);
+ goto out_drop_lock;
+ error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
-out_drop_write:
+out_drop_lock:
+ fh_unlock(fh);
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 93d5853f8c99..dba2ff8eaa68 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -379,7 +379,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
*/
hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
- - hdr;
+ + rqstp->rq_arg.tail[0].iov_len - hdr;
/*
* Round the length of the data which was specified up to
* the next multiple of XDR units and then compare that
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 6adabd6049b7..71292a0d6f09 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -770,9 +770,6 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
dentry = fhp->fh_dentry;
inode = d_inode(dentry);
- if (!inode->i_op->set_acl || !IS_POSIXACL(inode))
- return nfserr_attrnotsupp;
-
if (S_ISDIR(inode->i_mode))
flags = NFS4_ACL_DIR;
@@ -782,16 +779,19 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (host_error < 0)
goto out_nfserr;
- host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS);
+ fh_lock(fhp);
+
+ host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl);
if (host_error < 0)
- goto out_release;
+ goto out_drop_lock;
if (S_ISDIR(inode->i_mode)) {
- host_error = inode->i_op->set_acl(inode, dpacl,
- ACL_TYPE_DEFAULT);
+ host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl);
}
-out_release:
+out_drop_lock:
+ fh_unlock(fhp);
+
posix_acl_release(pacl);
posix_acl_release(dpacl);
out_nfserr:
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7389cb1d7409..04c68d900324 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
}
}
-static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
-{
- struct rpc_xprt *xprt;
-
- if (args->protocol != XPRT_TRANSPORT_BC_TCP)
- return rpc_create(args);
-
- xprt = args->bc_xprt->xpt_bc_xprt;
- if (xprt) {
- xprt_get(xprt);
- return rpc_create_xprt(args, xprt);
- }
-
- return rpc_create(args);
-}
-
static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
{
int maxtime = max_cb_time(clp->net);
@@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
args.authflavor = ses->se_cb_sec.flavor;
}
/* Create RPC client */
- client = create_backchannel_client(&args);
+ client = rpc_create(&args);
if (IS_ERR(client)) {
dprintk("NFSD: couldn't create callback client: %ld\n",
PTR_ERR(client));
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 825c7bc8d789..953c0755cb37 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -289,7 +289,7 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
status = nfserr_bad_stateid;
mutex_lock(&ls->ls_mutex);
- if (stateid->si_generation > stid->sc_stateid.si_generation)
+ if (nfsd4_stateid_generation_after(stateid, &stid->sc_stateid))
goto out_unlock_stid;
if (layout_type != ls->ls_layout_type)
goto out_unlock_stid;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0462eeddfff9..70d0b9b33031 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3480,12 +3480,17 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
}
static struct nfs4_ol_stateid *
-init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
- struct nfsd4_open *open)
+init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
{
struct nfs4_openowner *oo = open->op_openowner;
struct nfs4_ol_stateid *retstp = NULL;
+ struct nfs4_ol_stateid *stp;
+
+ stp = open->op_stp;
+ /* We are moving these outside of the spinlocks to avoid the warnings */
+ mutex_init(&stp->st_mutex);
+ mutex_lock(&stp->st_mutex);
spin_lock(&oo->oo_owner.so_client->cl_lock);
spin_lock(&fp->fi_lock);
@@ -3493,6 +3498,8 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
retstp = nfsd4_find_existing_open(fp, open);
if (retstp)
goto out_unlock;
+
+ open->op_stp = NULL;
atomic_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
@@ -3502,14 +3509,19 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
stp->st_access_bmap = 0;
stp->st_deny_bmap = 0;
stp->st_openstp = NULL;
- init_rwsem(&stp->st_rwsem);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
out_unlock:
spin_unlock(&fp->fi_lock);
spin_unlock(&oo->oo_owner.so_client->cl_lock);
- return retstp;
+ if (retstp) {
+ mutex_lock(&retstp->st_mutex);
+ /* To keep mutex tracking happy */
+ mutex_unlock(&stp->st_mutex);
+ stp = retstp;
+ }
+ return stp;
}
/*
@@ -4305,7 +4317,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
struct nfs4_file *fp = NULL;
struct nfs4_ol_stateid *stp = NULL;
- struct nfs4_ol_stateid *swapstp = NULL;
struct nfs4_delegation *dp = NULL;
__be32 status;
@@ -4335,32 +4346,28 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
*/
if (stp) {
/* Stateid was found, this is an OPEN upgrade */
- down_read(&stp->st_rwsem);
+ mutex_lock(&stp->st_mutex);
status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
if (status) {
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
goto out;
}
} else {
- stp = open->op_stp;
- open->op_stp = NULL;
- swapstp = init_open_stateid(stp, fp, open);
- if (swapstp) {
- nfs4_put_stid(&stp->st_stid);
- stp = swapstp;
- down_read(&stp->st_rwsem);
+ /* stp is returned locked. */
+ stp = init_open_stateid(fp, open);
+ /* See if we lost the race to some other thread */
+ if (stp->st_access_bmap != 0) {
status = nfs4_upgrade_open(rqstp, fp, current_fh,
stp, open);
if (status) {
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
goto out;
}
goto upgrade_out;
}
- down_read(&stp->st_rwsem);
status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
if (status) {
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
release_open_stateid(stp);
goto out;
}
@@ -4372,7 +4379,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
}
upgrade_out:
nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
if (nfsd4_has_session(&resp->cstate)) {
if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4651,12 +4658,6 @@ grace_disallows_io(struct net *net, struct inode *inode)
return opens_in_grace(net) && mandatory_lock(inode);
}
-/* Returns true iff a is later than b: */
-static bool stateid_generation_after(stateid_t *a, stateid_t *b)
-{
- return (s32)(a->si_generation - b->si_generation) > 0;
-}
-
static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session)
{
/*
@@ -4670,7 +4671,7 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s
return nfs_ok;
/* If the client sends us a stateid from the future, it's buggy: */
- if (stateid_generation_after(in, ref))
+ if (nfsd4_stateid_generation_after(in, ref))
return nfserr_bad_stateid;
/*
* However, we could see a stateid from the past, even from a
@@ -4983,12 +4984,12 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
* revoked delegations are kept only for free_stateid.
*/
return nfserr_bad_stateid;
- down_write(&stp->st_rwsem);
+ mutex_lock(&stp->st_mutex);
status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
if (status == nfs_ok)
status = nfs4_check_fh(current_fh, &stp->st_stid);
if (status != nfs_ok)
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
return status;
}
@@ -5036,7 +5037,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
return status;
oo = openowner(stp->st_stateowner);
if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfs4_put_stid(&stp->st_stid);
return nfserr_bad_stateid;
}
@@ -5068,12 +5069,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
oo = openowner(stp->st_stateowner);
status = nfserr_bad_stateid;
if (oo->oo_flags & NFS4_OO_CONFIRMED) {
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
goto put_stateid;
}
oo->oo_flags |= NFS4_OO_CONFIRMED;
nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
@@ -5149,7 +5150,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
status = nfs_ok;
put_stateid:
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfs4_put_stid(&stp->st_stid);
out:
nfsd4_bump_seqid(cstate, status);
@@ -5202,7 +5203,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfsd4_close_open_stateid(stp);
@@ -5428,7 +5429,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
- init_rwsem(&stp->st_rwsem);
+ mutex_init(&stp->st_mutex);
list_add(&stp->st_locks, &open_stp->st_locks);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
spin_lock(&fp->fi_lock);
@@ -5597,7 +5598,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&open_stp, nn);
if (status)
goto out;
- up_write(&open_stp->st_rwsem);
+ mutex_unlock(&open_stp->st_mutex);
open_sop = openowner(open_stp->st_stateowner);
status = nfserr_bad_stateid;
if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5606,7 +5607,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = lookup_or_create_lock_state(cstate, open_stp, lock,
&lock_stp, &new);
if (status == nfs_ok)
- down_write(&lock_stp->st_rwsem);
+ mutex_lock(&lock_stp->st_mutex);
} else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
@@ -5710,7 +5711,7 @@ out:
seqid_mutating_err(ntohl(status)))
lock_sop->lo_owner.so_seqid++;
- up_write(&lock_stp->st_rwsem);
+ mutex_unlock(&lock_stp->st_mutex);
/*
* If this is a new, never-before-used stateid, and we are
@@ -5880,7 +5881,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fput:
fput(filp);
put_stateid:
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfs4_put_stid(&stp->st_stid);
out:
nfsd4_bump_seqid(cstate, status);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index c050c53036a6..64053eadeb81 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -535,7 +535,7 @@ struct nfs4_ol_stateid {
unsigned char st_access_bmap;
unsigned char st_deny_bmap;
struct nfs4_ol_stateid *st_openstp;
- struct rw_semaphore st_rwsem;
+ struct mutex st_mutex;
};
static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
@@ -573,6 +573,11 @@ enum nfsd4_cb_op {
NFSPROC4_CLNT_CB_SEQUENCE,
};
+/* Returns true iff a is later than b: */
+static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b)
+{
+ return (s32)(a->si_generation - b->si_generation) > 0;
+}
struct nfsd4_compound_state;
struct nfsd_net;
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 809bd2de7ad0..e9fd241b9a0a 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -439,7 +439,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp)
if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC)
return 0;
bytes = le16_to_cpu(sbp->s_bytes);
- if (bytes > BLOCK_SIZE)
+ if (bytes < sumoff + 4 || bytes > BLOCK_SIZE)
return 0;
crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp,
sumoff);
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index e27e6527912b..4342c7ee7d20 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -1,7 +1,5 @@
ccflags-y := -Ifs/ocfs2
-ccflags-y += -DCATCH_BH_JBD_RACES
-
obj-$(CONFIG_OCFS2_FS) += \
ocfs2.o \
ocfs2_stackglue.o
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index fe50ded1b4ce..498641eed2db 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -139,11 +139,16 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
lock_buffer(bh);
if (buffer_jbd(bh)) {
+#ifdef CATCH_BH_JBD_RACES
mlog(ML_ERROR,
"block %llu had the JBD bit set "
"while I was in lock_buffer!",
(unsigned long long)bh->b_blocknr);
BUG();
+#else
+ unlock_buffer(bh);
+ continue;
+#endif
}
clear_buffer_uptodate(bh);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index a8d15beee5cb..6aaf3e351391 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -272,10 +272,21 @@ struct o2hb_region {
struct delayed_work hr_write_timeout_work;
unsigned long hr_last_timeout_start;
+ /* negotiate timer, used to negotiate extending hb timeout. */
+ struct delayed_work hr_nego_timeout_work;
+ unsigned long hr_nego_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+
/* Used during o2hb_check_slot to hold a copy of the block
* being checked because we temporarily have to zero out the
* crc field. */
struct o2hb_disk_heartbeat_block *hr_tmp_block;
+
+ /* Message key for negotiate timeout message. */
+ unsigned int hr_key;
+ struct list_head hr_handler_list;
+
+ /* last hb status, 0 for success, other value for error. */
+ int hr_last_hb_status;
};
struct o2hb_bio_wait_ctxt {
@@ -284,6 +295,17 @@ struct o2hb_bio_wait_ctxt {
int wc_error;
};
+#define O2HB_NEGO_TIMEOUT_MS (O2HB_MAX_WRITE_TIMEOUT_MS/2)
+
+enum {
+ O2HB_NEGO_TIMEOUT_MSG = 1,
+ O2HB_NEGO_APPROVE_MSG = 2,
+};
+
+struct o2hb_nego_msg {
+ u8 node_num;
+};
+
static void o2hb_write_timeout(struct work_struct *work)
{
int failed, quorum;
@@ -319,7 +341,7 @@ static void o2hb_write_timeout(struct work_struct *work)
o2quo_disk_timeout();
}
-static void o2hb_arm_write_timeout(struct o2hb_region *reg)
+static void o2hb_arm_timeout(struct o2hb_region *reg)
{
/* Arm writeout only after thread reaches steady state */
if (atomic_read(&reg->hr_steady_iterations) != 0)
@@ -334,14 +356,132 @@ static void o2hb_arm_write_timeout(struct o2hb_region *reg)
spin_unlock(&o2hb_live_lock);
}
cancel_delayed_work(&reg->hr_write_timeout_work);
- reg->hr_last_timeout_start = jiffies;
schedule_delayed_work(&reg->hr_write_timeout_work,
msecs_to_jiffies(O2HB_MAX_WRITE_TIMEOUT_MS));
+
+ cancel_delayed_work(&reg->hr_nego_timeout_work);
+ /* negotiate timeout must be less than write timeout. */
+ schedule_delayed_work(&reg->hr_nego_timeout_work,
+ msecs_to_jiffies(O2HB_NEGO_TIMEOUT_MS));
+ memset(reg->hr_nego_node_bitmap, 0, sizeof(reg->hr_nego_node_bitmap));
}
-static void o2hb_disarm_write_timeout(struct o2hb_region *reg)
+static void o2hb_disarm_timeout(struct o2hb_region *reg)
{
cancel_delayed_work_sync(&reg->hr_write_timeout_work);
+ cancel_delayed_work_sync(&reg->hr_nego_timeout_work);
+}
+
+static int o2hb_send_nego_msg(int key, int type, u8 target)
+{
+ struct o2hb_nego_msg msg;
+ int status, ret;
+
+ msg.node_num = o2nm_this_node();
+again:
+ ret = o2net_send_message(type, key, &msg, sizeof(msg),
+ target, &status);
+
+ if (ret == -EAGAIN || ret == -ENOMEM) {
+ msleep(100);
+ goto again;
+ }
+
+ return ret;
+}
+
+static void o2hb_nego_timeout(struct work_struct *work)
+{
+ unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+ int master_node, i, ret;
+ struct o2hb_region *reg;
+
+ reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.work);
+ /* don't negotiate timeout if last hb failed since it is very
+ * possible io failed. Should let write timeout fence self.
+ */
+ if (reg->hr_last_hb_status)
+ return;
+
+ o2hb_fill_node_map(live_node_bitmap, sizeof(live_node_bitmap));
+ /* lowest node as master node to make negotiate decision. */
+ master_node = find_next_bit(live_node_bitmap, O2NM_MAX_NODES, 0);
+
+ if (master_node == o2nm_this_node()) {
+ if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
+ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s).\n",
+ o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
+ config_item_name(&reg->hr_item), reg->hr_dev_name);
+ set_bit(master_node, reg->hr_nego_node_bitmap);
+ }
+ if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
+ sizeof(reg->hr_nego_node_bitmap))) {
+ /* check negotiate bitmap every second to do timeout
+ * approve decision.
+ */
+ schedule_delayed_work(&reg->hr_nego_timeout_work,
+ msecs_to_jiffies(1000));
+
+ return;
+ }
+
+ printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
+ config_item_name(&reg->hr_item), reg->hr_dev_name);
+ /* approve negotiate timeout request. */
+ o2hb_arm_timeout(reg);
+
+ i = -1;
+ while ((i = find_next_bit(live_node_bitmap,
+ O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
+ if (i == master_node)
+ continue;
+
+ mlog(ML_HEARTBEAT, "send NEGO_APPROVE msg to node %d\n", i);
+ ret = o2hb_send_nego_msg(reg->hr_key,
+ O2HB_NEGO_APPROVE_MSG, i);
+ if (ret)
+ mlog(ML_ERROR, "send NEGO_APPROVE msg to node %d fail %d\n",
+ i, ret);
+ }
+ } else {
+ /* negotiate timeout with master node. */
+ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
+ o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->hr_item),
+ reg->hr_dev_name, master_node);
+ ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
+ master_node);
+ if (ret)
+ mlog(ML_ERROR, "send NEGO_TIMEOUT msg to node %d fail %d\n",
+ master_node, ret);
+ }
+}
+
+static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
+ void **ret_data)
+{
+ struct o2hb_region *reg = data;
+ struct o2hb_nego_msg *nego_msg;
+
+ nego_msg = (struct o2hb_nego_msg *)msg->buf;
+ printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%s).\n",
+ nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_dev_name);
+ if (nego_msg->node_num < O2NM_MAX_NODES)
+ set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
+ else
+ mlog(ML_ERROR, "got nego timeout message from bad node.\n");
+
+ return 0;
+}
+
+static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
+ void **ret_data)
+{
+ struct o2hb_region *reg = data;
+
+ printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
+ config_item_name(&reg->hr_item), reg->hr_dev_name);
+ o2hb_arm_timeout(reg);
+ return 0;
}
static inline void o2hb_bio_wait_init(struct o2hb_bio_wait_ctxt *wc)
@@ -1032,7 +1172,8 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
/* Skip disarming the timeout if own slot has stale/bad data */
if (own_slot_ok) {
o2hb_set_quorum_device(reg);
- o2hb_arm_write_timeout(reg);
+ o2hb_arm_timeout(reg);
+ reg->hr_last_timeout_start = jiffies;
}
bail:
@@ -1096,6 +1237,7 @@ static int o2hb_thread(void *data)
before_hb = ktime_get_real();
ret = o2hb_do_disk_heartbeat(reg);
+ reg->hr_last_hb_status = ret;
after_hb = ktime_get_real();
@@ -1114,7 +1256,7 @@ static int o2hb_thread(void *data)
}
}
- o2hb_disarm_write_timeout(reg);
+ o2hb_disarm_timeout(reg);
/* unclean stop is only used in very bad situation */
for(i = 0; !reg->hr_unclean_stop && i < reg->hr_blocks; i++)
@@ -1451,6 +1593,7 @@ static void o2hb_region_release(struct config_item *item)
list_del(&reg->hr_all_item);
spin_unlock(&o2hb_live_lock);
+ o2net_unregister_handler_list(&reg->hr_handler_list);
kfree(reg);
}
@@ -1762,6 +1905,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
}
INIT_DELAYED_WORK(&reg->hr_write_timeout_work, o2hb_write_timeout);
+ INIT_DELAYED_WORK(&reg->hr_nego_timeout_work, o2hb_nego_timeout);
/*
* A node is considered live after it has beat LIVE_THRESHOLD
@@ -1995,13 +2139,37 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g
config_item_init_type_name(&reg->hr_item, name, &o2hb_region_type);
+ /* this is the same way to generate msg key as dlm, for local heartbeat,
+ * name is also the same, so make initial crc value different to avoid
+ * message key conflict.
+ */
+ reg->hr_key = crc32_le(reg->hr_region_num + O2NM_MAX_REGIONS,
+ name, strlen(name));
+ INIT_LIST_HEAD(&reg->hr_handler_list);
+ ret = o2net_register_handler(O2HB_NEGO_TIMEOUT_MSG, reg->hr_key,
+ sizeof(struct o2hb_nego_msg),
+ o2hb_nego_timeout_handler,
+ reg, NULL, &reg->hr_handler_list);
+ if (ret)
+ goto free;
+
+ ret = o2net_register_handler(O2HB_NEGO_APPROVE_MSG, reg->hr_key,
+ sizeof(struct o2hb_nego_msg),
+ o2hb_nego_approve_handler,
+ reg, NULL, &reg->hr_handler_list);
+ if (ret)
+ goto unregister_handler;
+
ret = o2hb_debug_region_init(reg, o2hb_debug_dir);
if (ret) {
config_item_put(&reg->hr_item);
- goto free;
+ goto unregister_handler;
}
return &reg->hr_item;
+
+unregister_handler:
+ o2net_unregister_handler_list(&reg->hr_handler_list);
free:
kfree(reg);
return ERR_PTR(ret);
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index b95e7df5b76a..94b18369b1cc 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -44,6 +44,9 @@
* version here in tcp_internal.h should not need to be bumped for
* filesystem locking changes.
*
+ * New in version 12
+ * - Negotiate hb timeout when storage is down.
+ *
* New in version 11
* - Negotiation of filesystem locking in the dlm join.
*
@@ -75,7 +78,7 @@
* - full 64 bit i_size in the metadata lock lvbs
* - introduction of "rw" lock and pushing meta/data locking down
*/
-#define O2NET_PROTOCOL_VERSION 11ULL
+#define O2NET_PROTOCOL_VERSION 12ULL
struct o2net_handshake {
__be64 protocol_version;
__be64 connector_id;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 0748777f2e2a..c56a7679df93 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -176,12 +176,7 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
}
if (is_bad_inode(inode)) {
iput(inode);
- if ((flags & OCFS2_FI_FLAG_FILECHECK_CHK) ||
- (flags & OCFS2_FI_FLAG_FILECHECK_FIX))
- /* Return OCFS2_FILECHECK_ERR_XXX related errno */
- inode = ERR_PTR(rc);
- else
- inode = ERR_PTR(-ESTALE);
+ inode = ERR_PTR(rc);
goto bail;
}
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index f4cd3c3e9fb7..497a4171ef61 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -619,7 +619,7 @@ static inline int ocfs2_calc_tree_trunc_credits(struct super_block *sb,
static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
- return jbd2_journal_file_inode(handle, &OCFS2_I(inode)->ip_jinode);
+ return jbd2_journal_inode_add_write(handle, &OCFS2_I(inode)->ip_jinode);
}
static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index ad16995c9e7a..d2053853951e 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7254,10 +7254,11 @@ static int ocfs2_xattr_security_get(const struct xattr_handler *handler,
}
static int ocfs2_xattr_security_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY,
+ return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY,
name, value, size, flags);
}
@@ -7325,10 +7326,11 @@ static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler,
}
static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED,
+ return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_TRUSTED,
name, value, size, flags);
}
@@ -7354,15 +7356,16 @@ static int ocfs2_xattr_user_get(const struct xattr_handler *handler,
}
static int ocfs2_xattr_user_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
return -EOPNOTSUPP;
- return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_USER,
+ return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_USER,
name, value, size, flags);
}
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
index 99c19545752c..5893ddde0e4b 100644
--- a/fs/orangefs/xattr.c
+++ b/fs/orangefs/xattr.c
@@ -448,13 +448,14 @@ out_unlock:
}
static int orangefs_xattr_set_default(const struct xattr_handler *handler,
- struct dentry *dentry,
+ struct dentry *unused,
+ struct inode *inode,
const char *name,
const void *buffer,
size_t size,
int flags)
{
- return orangefs_inode_setxattr(dentry->d_inode,
+ return orangefs_inode_setxattr(inode,
ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
name,
buffer,
@@ -478,13 +479,14 @@ static int orangefs_xattr_get_default(const struct xattr_handler *handler,
}
static int orangefs_xattr_set_trusted(const struct xattr_handler *handler,
- struct dentry *dentry,
+ struct dentry *unused,
+ struct inode *inode,
const char *name,
const void *buffer,
size_t size,
int flags)
{
- return orangefs_inode_setxattr(dentry->d_inode,
+ return orangefs_inode_setxattr(inode,
ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
name,
buffer,
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index cc514da6f3e7..80aa6f1eb336 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -336,7 +336,6 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
struct dentry *upperdir;
struct dentry *upperdentry;
const struct cred *old_cred;
- struct cred *override_cred;
char *link = NULL;
if (WARN_ON(!workdir))
@@ -357,28 +356,7 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
return PTR_ERR(link);
}
- err = -ENOMEM;
- override_cred = prepare_creds();
- if (!override_cred)
- goto out_free_link;
-
- override_cred->fsuid = stat->uid;
- override_cred->fsgid = stat->gid;
- /*
- * CAP_SYS_ADMIN for copying up extended attributes
- * CAP_DAC_OVERRIDE for create
- * CAP_FOWNER for chmod, timestamp update
- * CAP_FSETID for chmod
- * CAP_CHOWN for chown
- * CAP_MKNOD for mknod
- */
- cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
- cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
- cap_raise(override_cred->cap_effective, CAP_FOWNER);
- cap_raise(override_cred->cap_effective, CAP_FSETID);
- cap_raise(override_cred->cap_effective, CAP_CHOWN);
- cap_raise(override_cred->cap_effective, CAP_MKNOD);
- old_cred = override_creds(override_cred);
+ old_cred = ovl_override_creds(dentry->d_sb);
err = -EIO;
if (lock_rename(workdir, upperdir) != NULL) {
@@ -401,9 +379,7 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
out_unlock:
unlock_rename(workdir, upperdir);
revert_creds(old_cred);
- put_cred(override_cred);
-out_free_link:
if (link)
free_page((unsigned long) link);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index b3fc0a35bf62..c2a6b0894022 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -407,26 +407,20 @@ static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev,
const struct cred *old_cred;
struct cred *override_cred;
+ old_cred = ovl_override_creds(dentry->d_sb);
+
err = -ENOMEM;
override_cred = prepare_creds();
- if (!override_cred)
- goto out_iput;
-
- /*
- * CAP_SYS_ADMIN for setting opaque xattr
- * CAP_DAC_OVERRIDE for create in workdir, rename
- * CAP_FOWNER for removing whiteout from sticky dir
- */
- cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
- cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
- cap_raise(override_cred->cap_effective, CAP_FOWNER);
- old_cred = override_creds(override_cred);
-
- err = ovl_create_over_whiteout(dentry, inode, &stat, link,
- hardlink);
-
+ if (override_cred) {
+ override_cred->fsuid = old_cred->fsuid;
+ override_cred->fsgid = old_cred->fsgid;
+ put_cred(override_creds(override_cred));
+ put_cred(override_cred);
+
+ err = ovl_create_over_whiteout(dentry, inode, &stat,
+ link, hardlink);
+ }
revert_creds(old_cred);
- put_cred(override_cred);
}
if (!err)
@@ -662,32 +656,11 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
if (OVL_TYPE_PURE_UPPER(type)) {
err = ovl_remove_upper(dentry, is_dir);
} else {
- const struct cred *old_cred;
- struct cred *override_cred;
-
- err = -ENOMEM;
- override_cred = prepare_creds();
- if (!override_cred)
- goto out_drop_write;
-
- /*
- * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir
- * CAP_DAC_OVERRIDE for create in workdir, rename
- * CAP_FOWNER for removing whiteout from sticky dir
- * CAP_FSETID for chmod of opaque dir
- * CAP_CHOWN for chown of opaque dir
- */
- cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
- cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
- cap_raise(override_cred->cap_effective, CAP_FOWNER);
- cap_raise(override_cred->cap_effective, CAP_FSETID);
- cap_raise(override_cred->cap_effective, CAP_CHOWN);
- old_cred = override_creds(override_cred);
+ const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
err = ovl_remove_and_whiteout(dentry, is_dir);
revert_creds(old_cred);
- put_cred(override_cred);
}
out_drop_write:
ovl_drop_write(dentry);
@@ -725,7 +698,6 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
bool new_is_dir = false;
struct dentry *opaquedir = NULL;
const struct cred *old_cred = NULL;
- struct cred *override_cred = NULL;
err = -EINVAL;
if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
@@ -794,26 +766,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
old_opaque = !OVL_TYPE_PURE_UPPER(old_type);
new_opaque = !OVL_TYPE_PURE_UPPER(new_type);
- if (old_opaque || new_opaque) {
- err = -ENOMEM;
- override_cred = prepare_creds();
- if (!override_cred)
- goto out_drop_write;
-
- /*
- * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir
- * CAP_DAC_OVERRIDE for create in workdir
- * CAP_FOWNER for removing whiteout from sticky dir
- * CAP_FSETID for chmod of opaque dir
- * CAP_CHOWN for chown of opaque dir
- */
- cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
- cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
- cap_raise(override_cred->cap_effective, CAP_FOWNER);
- cap_raise(override_cred->cap_effective, CAP_FSETID);
- cap_raise(override_cred->cap_effective, CAP_CHOWN);
- old_cred = override_creds(override_cred);
- }
+ if (old_opaque || new_opaque)
+ old_cred = ovl_override_creds(old->d_sb);
if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) {
opaquedir = ovl_check_empty_and_clear(new);
@@ -943,10 +897,8 @@ out_dput_old:
out_unlock:
unlock_rename(new_upperdir, old_upperdir);
out_revert_creds:
- if (old_opaque || new_opaque) {
+ if (old_opaque || new_opaque)
revert_creds(old_cred);
- put_cred(override_cred);
- }
out_drop_write:
ovl_drop_write(old);
out:
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index c7b31a03dc9c..c831c2e5f803 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -59,16 +59,37 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
if (err)
goto out;
+ if (attr->ia_valid & ATTR_SIZE) {
+ struct inode *realinode = d_inode(ovl_dentry_real(dentry));
+
+ err = -ETXTBSY;
+ if (atomic_read(&realinode->i_writecount) < 0)
+ goto out_drop_write;
+ }
+
err = ovl_copy_up(dentry);
if (!err) {
+ struct inode *winode = NULL;
+
upperdentry = ovl_dentry_upper(dentry);
+ if (attr->ia_valid & ATTR_SIZE) {
+ winode = d_inode(upperdentry);
+ err = get_write_access(winode);
+ if (err)
+ goto out_drop_write;
+ }
+
inode_lock(upperdentry->d_inode);
err = notify_change(upperdentry, attr, NULL);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
+
+ if (winode)
+ put_write_access(winode);
}
+out_drop_write:
ovl_drop_write(dentry);
out:
return err;
@@ -121,16 +142,18 @@ int ovl_permission(struct inode *inode, int mask)
err = vfs_getattr(&realpath, &stat);
if (err)
- return err;
+ goto out_dput;
+ err = -ESTALE;
if ((stat.mode ^ inode->i_mode) & S_IFMT)
- return -ESTALE;
+ goto out_dput;
inode->i_mode = stat.mode;
inode->i_uid = stat.uid;
inode->i_gid = stat.gid;
- return generic_permission(inode, mask);
+ err = generic_permission(inode, mask);
+ goto out_dput;
}
/* Careful in RCU walk mode */
@@ -210,8 +233,9 @@ static bool ovl_is_private_xattr(const char *name)
return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0;
}
-int ovl_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+int ovl_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
int err;
struct dentry *upperdentry;
@@ -237,41 +261,27 @@ out:
return err;
}
-static bool ovl_need_xattr_filter(struct dentry *dentry,
- enum ovl_path_type type)
-{
- if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER)
- return S_ISDIR(dentry->d_inode->i_mode);
- else
- return false;
-}
-
ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
const char *name, void *value, size_t size)
{
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+ struct dentry *realdentry = ovl_dentry_real(dentry);
- if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+ if (ovl_is_private_xattr(name))
return -ENODATA;
- return vfs_getxattr(realpath.dentry, name, value, size);
+ return vfs_getxattr(realdentry, name, value, size);
}
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+ struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
int off;
- res = vfs_listxattr(realpath.dentry, list, size);
+ res = vfs_listxattr(realdentry, list, size);
if (res <= 0 || size == 0)
return res;
- if (!ovl_need_xattr_filter(dentry, type))
- return res;
-
/* filter out private xattrs */
for (off = 0; off < res;) {
char *s = list + off;
@@ -301,7 +311,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name)
goto out;
err = -ENODATA;
- if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+ if (ovl_is_private_xattr(name))
goto out_drop_write;
if (!OVL_TYPE_UPPER(type)) {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 99ec4b035237..4bd9b5ba8f42 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -153,6 +153,7 @@ void ovl_drop_write(struct dentry *dentry);
bool ovl_dentry_is_opaque(struct dentry *dentry);
void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque);
bool ovl_is_whiteout(struct dentry *dentry);
+const struct cred *ovl_override_creds(struct super_block *sb);
void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags);
@@ -171,8 +172,9 @@ int ovl_check_d_type_supported(struct path *realpath);
/* inode.c */
int ovl_setattr(struct dentry *dentry, struct iattr *attr);
int ovl_permission(struct inode *inode, int mask);
-int ovl_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
+int ovl_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags);
ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
const char *name, void *value, size_t size);
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index da186ee4f846..cf37fc76fc9f 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -36,6 +36,7 @@ struct ovl_dir_cache {
struct ovl_readdir_data {
struct dir_context ctx;
+ struct dentry *dentry;
bool is_lowest;
struct rb_root root;
struct list_head *list;
@@ -206,21 +207,10 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
struct ovl_cache_entry *p;
struct dentry *dentry;
const struct cred *old_cred;
- struct cred *override_cred;
-
- override_cred = prepare_creds();
- if (!override_cred)
- return -ENOMEM;
- /*
- * CAP_DAC_OVERRIDE for lookup
- */
- cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
- old_cred = override_creds(override_cred);
+ old_cred = ovl_override_creds(rdd->dentry->d_sb);
- inode_lock(dir->d_inode);
- err = 0;
- // XXX: err = mutex_lock_killable(&dir->d_inode->i_mutex);
+ err = down_write_killable(&dir->d_inode->i_rwsem);
if (!err) {
while (rdd->first_maybe_whiteout) {
p = rdd->first_maybe_whiteout;
@@ -234,7 +224,6 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
inode_unlock(dir->d_inode);
}
revert_creds(old_cred);
- put_cred(override_cred);
return err;
}
@@ -290,6 +279,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
struct path realpath;
struct ovl_readdir_data rdd = {
.ctx.actor = ovl_fill_merge,
+ .dentry = dentry,
.list = list,
.root = RB_ROOT,
.is_lowest = false,
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index ed53ae0fe868..9a7693d5f8ff 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -42,6 +42,8 @@ struct ovl_fs {
long lower_namelen;
/* pathnames of lower and upper dirs, for show_options */
struct ovl_config config;
+ /* creds of process who forced instantiation of super block */
+ const struct cred *creator_cred;
};
struct ovl_dir_cache;
@@ -265,6 +267,13 @@ bool ovl_is_whiteout(struct dentry *dentry)
return inode && IS_WHITEOUT(inode);
}
+const struct cred *ovl_override_creds(struct super_block *sb)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ return override_creds(ofs->creator_cred);
+}
+
static bool ovl_is_opaquedir(struct dentry *dentry)
{
int res;
@@ -603,6 +612,7 @@ static void ovl_put_super(struct super_block *sb)
kfree(ufs->config.lowerdir);
kfree(ufs->config.upperdir);
kfree(ufs->config.workdir);
+ put_cred(ufs->creator_cred);
kfree(ufs);
}
@@ -1064,16 +1074,21 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
/*
* Upper should support d_type, else whiteouts are visible.
* Given workdir and upper are on same fs, we can do
- * iterate_dir() on workdir.
+ * iterate_dir() on workdir. This check requires successful
+ * creation of workdir in previous step.
*/
- err = ovl_check_d_type_supported(&workpath);
- if (err < 0)
- goto out_put_workdir;
+ if (ufs->workdir) {
+ err = ovl_check_d_type_supported(&workpath);
+ if (err < 0)
+ goto out_put_workdir;
- if (!err) {
- pr_err("overlayfs: upper fs needs to support d_type.\n");
- err = -EINVAL;
- goto out_put_workdir;
+ /*
+ * We allowed this configuration and don't want to
+ * break users over kernel upgrade. So warn instead
+ * of erroring out.
+ */
+ if (!err)
+ pr_warn("overlayfs: upper fs needs to support d_type.\n");
}
}
@@ -1108,10 +1123,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
else
sb->s_d_op = &ovl_dentry_operations;
+ ufs->creator_cred = prepare_creds();
+ if (!ufs->creator_cred)
+ goto out_put_lower_mnt;
+
err = -ENOMEM;
oe = ovl_alloc_entry(numlower);
if (!oe)
- goto out_put_lower_mnt;
+ goto out_put_cred;
root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe));
if (!root_dentry)
@@ -1144,6 +1163,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
out_free_oe:
kfree(oe);
+out_put_cred:
+ put_cred(ufs->creator_cred);
out_put_lower_mnt:
for (i = 0; i < ufs->numlower; i++)
mntput(ufs->lower_mnt[i]);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 2c60f17e7d92..edc452c2a563 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -820,39 +820,43 @@ posix_acl_xattr_get(const struct xattr_handler *handler,
return error;
}
-static int
-posix_acl_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+int
+set_posix_acl(struct inode *inode, int type, struct posix_acl *acl)
{
- struct inode *inode = d_backing_inode(dentry);
- struct posix_acl *acl = NULL;
- int ret;
-
if (!IS_POSIXACL(inode))
return -EOPNOTSUPP;
if (!inode->i_op->set_acl)
return -EOPNOTSUPP;
- if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
- return value ? -EACCES : 0;
+ if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+ return acl ? -EACCES : 0;
if (!inode_owner_or_capable(inode))
return -EPERM;
+ if (acl) {
+ int ret = posix_acl_valid(acl);
+ if (ret)
+ return ret;
+ }
+ return inode->i_op->set_acl(inode, acl, type);
+}
+EXPORT_SYMBOL(set_posix_acl);
+
+static int
+posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ struct posix_acl *acl = NULL;
+ int ret;
+
if (value) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
-
- if (acl) {
- ret = posix_acl_valid(acl);
- if (ret)
- goto out;
- }
}
-
- ret = inode->i_op->set_acl(inode, acl, handler->flags);
-out:
+ ret = set_posix_acl(inode, handler->flags, acl);
posix_acl_release(acl);
return ret;
}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 55bc7d6c8aac..06702783bf40 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -121,6 +121,13 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
if (IS_ERR(sb))
return ERR_CAST(sb);
+ /*
+ * procfs isn't actually a stacking filesystem; however, there is
+ * too much magic going on inside it to permit stacking things on
+ * top of it
+ */
+ sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+
if (!proc_parse_options(options, ns)) {
deactivate_locked_super(sb);
return ERR_PTR(-EINVAL);
diff --git a/fs/readdir.c b/fs/readdir.c
index a86c6c04b9bc..9d0212c374d6 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -35,13 +35,13 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
if (res)
goto out;
- if (shared)
+ if (shared) {
inode_lock_shared(inode);
- else
- inode_lock(inode);
- // res = mutex_lock_killable(&inode->i_mutex);
- // if (res)
- // goto out;
+ } else {
+ res = down_write_killable(&inode->i_rwsem);
+ if (res)
+ goto out;
+ }
res = -ENOENT;
if (!IS_DEADDIR(inode)) {
@@ -182,6 +182,8 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen,
}
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
@@ -261,6 +263,8 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
return -EINVAL;
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b8f2d1e8c645..c72c16c5a60f 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1393,7 +1393,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
unsigned long safe_mask = 0;
unsigned int commit_max_age = (unsigned int)-1;
struct reiserfs_journal *journal = SB_JOURNAL(s);
- char *new_opts = kstrdup(arg, GFP_KERNEL);
+ char *new_opts;
int err;
char *qf_names[REISERFS_MAXQUOTAS];
unsigned int qfmt = 0;
@@ -1401,6 +1401,10 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
int i;
#endif
+ new_opts = kstrdup(arg, GFP_KERNEL);
+ if (arg && !new_opts)
+ return -ENOMEM;
+
sync_filesystem(s);
reiserfs_write_lock(s);
@@ -1546,7 +1550,8 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
}
out_ok_unlocked:
- replace_mount_options(s, new_opts);
+ if (new_opts)
+ replace_mount_options(s, new_opts);
return 0;
out_err_unlock:
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index 86aeb9dd805a..e4cbb7719906 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -20,13 +20,14 @@ security_get(const struct xattr_handler *handler, struct dentry *unused,
}
static int
-security_set(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, const void *buffer, size_t size, int flags)
+security_set(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, const void *buffer,
+ size_t size, int flags)
{
- if (IS_PRIVATE(d_inode(dentry)))
+ if (IS_PRIVATE(inode))
return -EPERM;
- return reiserfs_xattr_set(d_inode(dentry),
+ return reiserfs_xattr_set(inode,
xattr_full_name(handler, name),
buffer, size, flags);
}
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index 31837f031f59..f15a5f9e84ce 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -19,13 +19,14 @@ trusted_get(const struct xattr_handler *handler, struct dentry *unused,
}
static int
-trusted_set(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, const void *buffer, size_t size, int flags)
+trusted_set(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, const void *buffer,
+ size_t size, int flags)
{
- if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
+ if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
return -EPERM;
- return reiserfs_xattr_set(d_inode(dentry),
+ return reiserfs_xattr_set(inode,
xattr_full_name(handler, name),
buffer, size, flags);
}
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index f7c39731684b..dc59df43b2db 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -17,12 +17,13 @@ user_get(const struct xattr_handler *handler, struct dentry *unused,
}
static int
-user_set(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, const void *buffer, size_t size, int flags)
+user_set(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, const void *buffer,
+ size_t size, int flags)
{
- if (!reiserfs_xattrs_user(dentry->d_sb))
+ if (!reiserfs_xattrs_user(inode->i_sb))
return -EOPNOTSUPP;
- return reiserfs_xattr_set(d_inode(dentry),
+ return reiserfs_xattr_set(inode,
xattr_full_name(handler, name),
buffer, size, flags);
}
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 595ca0debe11..69e287e20732 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -260,7 +260,7 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode)
pr_err("\txattr_names %u\n", ui->xattr_names);
pr_err("\tdirty %u\n", ui->dirty);
pr_err("\txattr %u\n", ui->xattr);
- pr_err("\tbulk_read %u\n", ui->xattr);
+ pr_err("\tbulk_read %u\n", ui->bulk_read);
pr_err("\tsynced_i_size %llu\n",
(unsigned long long)ui->synced_i_size);
pr_err("\tui_size %llu\n",
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 08316972ff93..7bbf420d1289 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -52,6 +52,7 @@
#include "ubifs.h"
#include <linux/mount.h>
#include <linux/slab.h>
+#include <linux/migrate.h>
static int read_block(struct inode *inode, void *addr, unsigned int block,
struct ubifs_data_node *dn)
@@ -1452,6 +1453,26 @@ static int ubifs_set_page_dirty(struct page *page)
return ret;
}
+#ifdef CONFIG_MIGRATION
+static int ubifs_migrate_page(struct address_space *mapping,
+ struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+ int rc;
+
+ rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+ if (rc != MIGRATEPAGE_SUCCESS)
+ return rc;
+
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ SetPagePrivate(newpage);
+ }
+
+ migrate_page_copy(newpage, page);
+ return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
{
/*
@@ -1591,6 +1612,9 @@ const struct address_space_operations ubifs_file_address_operations = {
.write_end = ubifs_write_end,
.invalidatepage = ubifs_invalidatepage,
.set_page_dirty = ubifs_set_page_dirty,
+#ifdef CONFIG_MIGRATION
+ .migratepage = ubifs_migrate_page,
+#endif
.releasepage = ubifs_releasepage,
};
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 6c277eb6aef9..b5fc27969e9d 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -579,11 +579,10 @@ static int ubifs_xattr_get(const struct xattr_handler *handler,
}
static int ubifs_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
name, inode->i_ino, dentry, size);
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index 5f861ed287c3..888c364b2fe9 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -295,7 +295,8 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block,
map = &UDF_SB(sb)->s_partmaps[partition];
/* map to sparable/physical partition desc */
phyblock = udf_get_pblock(sb, eloc.logicalBlockNum,
- map->s_partition_num, ext_offset + offset);
+ map->s_type_specific.s_metadata.s_phys_partition_ref,
+ ext_offset + offset);
}
brelse(epos.bh);
@@ -317,14 +318,18 @@ uint32_t udf_get_pblock_meta25(struct super_block *sb, uint32_t block,
mdata = &map->s_type_specific.s_metadata;
inode = mdata->s_metadata_fe ? : mdata->s_mirror_fe;
- /* We shouldn't mount such media... */
- BUG_ON(!inode);
+ if (!inode)
+ return 0xFFFFFFFF;
+
retblk = udf_try_read_meta(inode, block, partition, offset);
if (retblk == 0xFFFFFFFF && mdata->s_metadata_fe) {
udf_warn(sb, "error reading from METADATA, trying to read from MIRROR\n");
if (!(mdata->s_flags & MF_MIRROR_FE_LOADED)) {
mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb,
- mdata->s_mirror_file_loc, map->s_partition_num);
+ mdata->s_mirror_file_loc,
+ mdata->s_phys_partition_ref);
+ if (IS_ERR(mdata->s_mirror_fe))
+ mdata->s_mirror_fe = NULL;
mdata->s_flags |= MF_MIRROR_FE_LOADED;
}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5e2c8c814e1b..4942549e7dc8 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -951,13 +951,13 @@ out2:
}
struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
- u32 meta_file_loc, u32 partition_num)
+ u32 meta_file_loc, u32 partition_ref)
{
struct kernel_lb_addr addr;
struct inode *metadata_fe;
addr.logicalBlockNum = meta_file_loc;
- addr.partitionReferenceNum = partition_num;
+ addr.partitionReferenceNum = partition_ref;
metadata_fe = udf_iget_special(sb, &addr);
@@ -974,7 +974,8 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
return metadata_fe;
}
-static int udf_load_metadata_files(struct super_block *sb, int partition)
+static int udf_load_metadata_files(struct super_block *sb, int partition,
+ int type1_index)
{
struct udf_sb_info *sbi = UDF_SB(sb);
struct udf_part_map *map;
@@ -984,20 +985,21 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
map = &sbi->s_partmaps[partition];
mdata = &map->s_type_specific.s_metadata;
+ mdata->s_phys_partition_ref = type1_index;
/* metadata address */
udf_debug("Metadata file location: block = %d part = %d\n",
- mdata->s_meta_file_loc, map->s_partition_num);
+ mdata->s_meta_file_loc, mdata->s_phys_partition_ref);
fe = udf_find_metadata_inode_efe(sb, mdata->s_meta_file_loc,
- map->s_partition_num);
+ mdata->s_phys_partition_ref);
if (IS_ERR(fe)) {
/* mirror file entry */
udf_debug("Mirror metadata file location: block = %d part = %d\n",
- mdata->s_mirror_file_loc, map->s_partition_num);
+ mdata->s_mirror_file_loc, mdata->s_phys_partition_ref);
fe = udf_find_metadata_inode_efe(sb, mdata->s_mirror_file_loc,
- map->s_partition_num);
+ mdata->s_phys_partition_ref);
if (IS_ERR(fe)) {
udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n");
@@ -1015,7 +1017,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
*/
if (mdata->s_bitmap_file_loc != 0xFFFFFFFF) {
addr.logicalBlockNum = mdata->s_bitmap_file_loc;
- addr.partitionReferenceNum = map->s_partition_num;
+ addr.partitionReferenceNum = mdata->s_phys_partition_ref;
udf_debug("Bitmap file location: block = %d part = %d\n",
addr.logicalBlockNum, addr.partitionReferenceNum);
@@ -1283,7 +1285,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
p = (struct partitionDesc *)bh->b_data;
partitionNumber = le16_to_cpu(p->partitionNumber);
- /* First scan for TYPE1, SPARABLE and METADATA partitions */
+ /* First scan for TYPE1 and SPARABLE partitions */
for (i = 0; i < sbi->s_partitions; i++) {
map = &sbi->s_partmaps[i];
udf_debug("Searching map: (%d == %d)\n",
@@ -1333,7 +1335,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
goto out_bh;
if (map->s_partition_type == UDF_METADATA_MAP25) {
- ret = udf_load_metadata_files(sb, i);
+ ret = udf_load_metadata_files(sb, i, type1_idx);
if (ret < 0) {
udf_err(sb, "error loading MetaData partition map %d\n",
i);
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 27b5335730c9..c13875d669c0 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -61,6 +61,11 @@ struct udf_meta_data {
__u32 s_bitmap_file_loc;
__u32 s_alloc_unit_size;
__u16 s_align_unit_size;
+ /*
+ * Partition Reference Number of the associated physical / sparable
+ * partition
+ */
+ __u16 s_phys_partition_ref;
int s_flags;
struct inode *s_metadata_fe;
struct inode *s_mirror_fe;
diff --git a/fs/xattr.c b/fs/xattr.c
index b11945e15fde..4beafc43daa5 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -100,7 +100,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
if (issec)
inode->i_flags &= ~S_NOSEC;
if (inode->i_op->setxattr) {
- error = inode->i_op->setxattr(dentry, name, value, size, flags);
+ error = inode->i_op->setxattr(dentry, inode, name, value, size, flags);
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_setxattr(dentry, name, value,
@@ -655,6 +655,7 @@ strcmp_prefix(const char *a, const char *a_prefix)
* operations to the correct xattr_handler.
*/
#define for_each_xattr_handler(handlers, handler) \
+ if (handlers) \
for ((handler) = *(handlers)++; \
(handler) != NULL; \
(handler) = *(handlers)++)
@@ -668,7 +669,7 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name)
const struct xattr_handler *handler;
if (!*name)
- return NULL;
+ return ERR_PTR(-EINVAL);
for_each_xattr_handler(handlers, handler) {
const char *n;
@@ -744,7 +745,8 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
* Find the handler for the prefix and dispatch its set() operation.
*/
int
-generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags)
+generic_setxattr(struct dentry *dentry, struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
{
const struct xattr_handler *handler;
@@ -753,7 +755,7 @@ generic_setxattr(struct dentry *dentry, const char *name, const void *value, siz
handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
- return handler->set(handler, dentry, name, value, size, flags);
+ return handler->set(handler, dentry, inode, name, value, size, flags);
}
/*
@@ -768,7 +770,8 @@ generic_removexattr(struct dentry *dentry, const char *name)
handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
- return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
+ return handler->set(handler, dentry, d_inode(dentry), name, NULL,
+ 0, XATTR_REPLACE);
}
EXPORT_SYMBOL(generic_getxattr);
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 686ba6fb20dd..339c696bbc01 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -93,19 +93,23 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
}
void *
-kmem_realloc(const void *ptr, size_t newsize, size_t oldsize,
- xfs_km_flags_t flags)
+kmem_realloc(const void *old, size_t newsize, xfs_km_flags_t flags)
{
- void *new;
+ int retries = 0;
+ gfp_t lflags = kmem_flags_convert(flags);
+ void *ptr;
- new = kmem_alloc(newsize, flags);
- if (ptr) {
- if (new)
- memcpy(new, ptr,
- ((oldsize < newsize) ? oldsize : newsize));
- kmem_free(ptr);
- }
- return new;
+ do {
+ ptr = krealloc(old, newsize, lflags);
+ if (ptr || (flags & (KM_MAYFAIL|KM_NOSLEEP)))
+ return ptr;
+ if (!(++retries % 100))
+ xfs_err(NULL,
+ "%s(%u) possible memory allocation deadlock size %zu in %s (mode:0x%x)",
+ current->comm, current->pid,
+ newsize, __func__, lflags);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ } while (1);
}
void *
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index d1c66e465ca5..689f746224e7 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -62,7 +62,7 @@ kmem_flags_convert(xfs_km_flags_t flags)
extern void *kmem_alloc(size_t, xfs_km_flags_t);
extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t);
-extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t);
+extern void *kmem_realloc(const void *, size_t, xfs_km_flags_t);
static inline void kmem_free(const void *ptr)
{
kvfree(ptr);
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index fa3b948ef9c2..4e126f41a0aa 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -242,37 +242,21 @@ xfs_attr_set(
return error;
}
- /*
- * Start our first transaction of the day.
- *
- * All future transactions during this code must be "chained" off
- * this one via the trans_dup() call. All transactions will contain
- * the inode, and the inode will always be marked with trans_ihold().
- * Since the inode will be locked in all transactions, we must log
- * the inode in every transaction to let it float upward through
- * the log.
- */
- args.trans = xfs_trans_alloc(mp, XFS_TRANS_ATTR_SET);
+ tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
+ M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
+ tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
+ tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
-
- if (rsvd)
- args.trans->t_flags |= XFS_TRANS_RESERVE;
-
- tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
- M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
- tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
- tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
- error = xfs_trans_reserve(args.trans, &tres, args.total, 0);
- if (error) {
- xfs_trans_cancel(args.trans);
+ error = xfs_trans_alloc(mp, &tres, args.total, 0,
+ rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
+ if (error)
return error;
- }
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
@@ -429,31 +413,15 @@ xfs_attr_remove(
return error;
/*
- * Start our first transaction of the day.
- *
- * All future transactions during this code must be "chained" off
- * this one via the trans_dup() call. All transactions will contain
- * the inode, and the inode will always be marked with trans_ihold().
- * Since the inode will be locked in all transactions, we must log
- * the inode in every transaction to let it float upward through
- * the log.
- */
- args.trans = xfs_trans_alloc(mp, XFS_TRANS_ATTR_RM);
-
- /*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
-
- if (flags & ATTR_ROOT)
- args.trans->t_flags |= XFS_TRANS_RESERVE;
-
- error = xfs_trans_reserve(args.trans, &M_RES(mp)->tr_attrrm,
- XFS_ATTRRM_SPACE_RES(mp), 0);
- if (error) {
- xfs_trans_cancel(args.trans);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrrm,
+ XFS_ATTRRM_SPACE_RES(mp), 0,
+ (flags & ATTR_ROOT) ? XFS_TRANS_RESERVE : 0,
+ &args.trans);
+ if (error)
return error;
- }
xfs_ilock(dp, XFS_ILOCK_EXCL);
/*
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index ce41d7fe753c..932381caef1b 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1121,15 +1121,14 @@ xfs_bmap_add_attrfork(
mp = ip->i_mount;
ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
- tp = xfs_trans_alloc(mp, XFS_TRANS_ADDAFORK);
+
blks = XFS_ADDAFORK_SPACE_RES(mp);
- if (rsvd)
- tp->t_flags |= XFS_TRANS_RESERVE;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_addafork, blks, 0);
- if (error) {
- xfs_trans_cancel(tp);
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_addafork, blks, 0,
+ rsvd ? XFS_TRANS_RESERVE : 0, &tp);
+ if (error)
return error;
- }
+
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
@@ -6026,13 +6025,10 @@ xfs_bmap_split_extent(
xfs_fsblock_t firstfsb;
int error;
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
- XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
+ XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
+ if (error)
return error;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 974d62e677f4..e5bb9cc3b243 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -257,15 +257,12 @@ xfs_dir2_block_to_sf(
*
* Convert the inode to local format and copy the data in.
*/
- dp->i_df.if_flags &= ~XFS_IFEXTENTS;
- dp->i_df.if_flags |= XFS_IFINLINE;
- dp->i_d.di_format = XFS_DINODE_FMT_LOCAL;
ASSERT(dp->i_df.if_bytes == 0);
- xfs_idata_realloc(dp, size, XFS_DATA_FORK);
+ xfs_init_local_fork(dp, XFS_DATA_FORK, dst, size);
+ dp->i_d.di_format = XFS_DINODE_FMT_LOCAL;
+ dp->i_d.di_size = size;
logflags |= XFS_ILOG_DDATA;
- memcpy(dp->i_df.if_u1.if_data, dst, size);
- dp->i_d.di_size = size;
xfs_dir2_sf_check(args);
out:
xfs_trans_log_inode(args->trans, dp, logflags);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 11faf7df14c8..bbcc8c7a44b3 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -231,6 +231,48 @@ xfs_iformat_fork(
return error;
}
+void
+xfs_init_local_fork(
+ struct xfs_inode *ip,
+ int whichfork,
+ const void *data,
+ int size)
+{
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ int mem_size = size, real_size = 0;
+ bool zero_terminate;
+
+ /*
+ * If we are using the local fork to store a symlink body we need to
+ * zero-terminate it so that we can pass it back to the VFS directly.
+ * Overallocate the in-memory fork by one for that and add a zero
+ * to terminate it below.
+ */
+ zero_terminate = S_ISLNK(VFS_I(ip)->i_mode);
+ if (zero_terminate)
+ mem_size++;
+
+ if (size == 0)
+ ifp->if_u1.if_data = NULL;
+ else if (mem_size <= sizeof(ifp->if_u2.if_inline_data))
+ ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
+ else {
+ real_size = roundup(mem_size, 4);
+ ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP | KM_NOFS);
+ }
+
+ if (size) {
+ memcpy(ifp->if_u1.if_data, data, size);
+ if (zero_terminate)
+ ifp->if_u1.if_data[size] = '\0';
+ }
+
+ ifp->if_bytes = size;
+ ifp->if_real_bytes = real_size;
+ ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
+ ifp->if_flags |= XFS_IFINLINE;
+}
+
/*
* The file is in-lined in the on-disk inode.
* If it fits into if_inline_data, then copy
@@ -248,8 +290,6 @@ xfs_iformat_local(
int whichfork,
int size)
{
- xfs_ifork_t *ifp;
- int real_size;
/*
* If the size is unreasonable, then something
@@ -265,22 +305,8 @@ xfs_iformat_local(
ip->i_mount, dip);
return -EFSCORRUPTED;
}
- ifp = XFS_IFORK_PTR(ip, whichfork);
- real_size = 0;
- if (size == 0)
- ifp->if_u1.if_data = NULL;
- else if (size <= sizeof(ifp->if_u2.if_inline_data))
- ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
- else {
- real_size = roundup(size, 4);
- ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP | KM_NOFS);
- }
- ifp->if_bytes = size;
- ifp->if_real_bytes = real_size;
- if (size)
- memcpy(ifp->if_u1.if_data, XFS_DFORK_PTR(dip, whichfork), size);
- ifp->if_flags &= ~XFS_IFEXTENTS;
- ifp->if_flags |= XFS_IFINLINE;
+
+ xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
return 0;
}
@@ -516,7 +542,6 @@ xfs_iroot_realloc(
new_max = cur_max + rec_diff;
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
ifp->if_broot = kmem_realloc(ifp->if_broot, new_size,
- XFS_BMAP_BROOT_SPACE_CALC(mp, cur_max),
KM_SLEEP | KM_NOFS);
op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
ifp->if_broot_bytes);
@@ -660,7 +685,6 @@ xfs_idata_realloc(
ifp->if_u1.if_data =
kmem_realloc(ifp->if_u1.if_data,
real_size,
- ifp->if_real_bytes,
KM_SLEEP | KM_NOFS);
}
} else {
@@ -1376,8 +1400,7 @@ xfs_iext_realloc_direct(
if (rnew_size != ifp->if_real_bytes) {
ifp->if_u1.if_extents =
kmem_realloc(ifp->if_u1.if_extents,
- rnew_size,
- ifp->if_real_bytes, KM_NOFS);
+ rnew_size, KM_NOFS);
}
if (rnew_size > ifp->if_real_bytes) {
memset(&ifp->if_u1.if_extents[ifp->if_bytes /
@@ -1461,9 +1484,8 @@ xfs_iext_realloc_indirect(
if (new_size == 0) {
xfs_iext_destroy(ifp);
} else {
- ifp->if_u1.if_ext_irec = (xfs_ext_irec_t *)
- kmem_realloc(ifp->if_u1.if_ext_irec,
- new_size, size, KM_NOFS);
+ ifp->if_u1.if_ext_irec =
+ kmem_realloc(ifp->if_u1.if_ext_irec, new_size, KM_NOFS);
}
}
@@ -1497,6 +1519,24 @@ xfs_iext_indirect_to_direct(
}
/*
+ * Remove all records from the indirection array.
+ */
+STATIC void
+xfs_iext_irec_remove_all(
+ struct xfs_ifork *ifp)
+{
+ int nlists;
+ int i;
+
+ ASSERT(ifp->if_flags & XFS_IFEXTIREC);
+ nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
+ for (i = 0; i < nlists; i++)
+ kmem_free(ifp->if_u1.if_ext_irec[i].er_extbuf);
+ kmem_free(ifp->if_u1.if_ext_irec);
+ ifp->if_flags &= ~XFS_IFEXTIREC;
+}
+
+/*
* Free incore file extents.
*/
void
@@ -1504,14 +1544,7 @@ xfs_iext_destroy(
xfs_ifork_t *ifp) /* inode fork pointer */
{
if (ifp->if_flags & XFS_IFEXTIREC) {
- int erp_idx;
- int nlists;
-
- nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
- for (erp_idx = nlists - 1; erp_idx >= 0 ; erp_idx--) {
- xfs_iext_irec_remove(ifp, erp_idx);
- }
- ifp->if_flags &= ~XFS_IFEXTIREC;
+ xfs_iext_irec_remove_all(ifp);
} else if (ifp->if_real_bytes) {
kmem_free(ifp->if_u1.if_extents);
} else if (ifp->if_bytes) {
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 7d3b1ed6dcbe..f95e072ae646 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -134,6 +134,7 @@ void xfs_iroot_realloc(struct xfs_inode *, int, int);
int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *,
int);
+void xfs_init_local_fork(struct xfs_inode *, int, const void *, int);
struct xfs_bmbt_rec_host *
xfs_iext_get_ext(struct xfs_ifork *, xfs_extnum_t);
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index d54a8018b079..e8f49c029ff0 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -212,6 +212,11 @@ typedef struct xfs_trans_header {
#define XFS_TRANS_HEADER_MAGIC 0x5452414e /* TRAN */
/*
+ * The only type valid for th_type in CIL-enabled file system logs:
+ */
+#define XFS_TRANS_CHECKPOINT 40
+
+/*
* Log item types.
*/
#define XFS_LI_EFI 0x1236
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 8a53eaa349f4..12ca86778e02 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -838,12 +838,10 @@ xfs_sync_sb(
struct xfs_trans *tp;
int error;
- tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_CHANGE, KM_SLEEP);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0,
+ XFS_TRANS_NO_WRITECOUNT, &tp);
+ if (error)
return error;
- }
xfs_log_sb(tp);
if (wait)
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 81ac870834da..16002b5ec4eb 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -56,103 +56,6 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
extern const struct xfs_buf_ops xfs_rtbuf_ops;
/*
- * Transaction types. Used to distinguish types of buffers. These never reach
- * the log.
- */
-#define XFS_TRANS_SETATTR_NOT_SIZE 1
-#define XFS_TRANS_SETATTR_SIZE 2
-#define XFS_TRANS_INACTIVE 3
-#define XFS_TRANS_CREATE 4
-#define XFS_TRANS_CREATE_TRUNC 5
-#define XFS_TRANS_TRUNCATE_FILE 6
-#define XFS_TRANS_REMOVE 7
-#define XFS_TRANS_LINK 8
-#define XFS_TRANS_RENAME 9
-#define XFS_TRANS_MKDIR 10
-#define XFS_TRANS_RMDIR 11
-#define XFS_TRANS_SYMLINK 12
-#define XFS_TRANS_SET_DMATTRS 13
-#define XFS_TRANS_GROWFS 14
-#define XFS_TRANS_STRAT_WRITE 15
-#define XFS_TRANS_DIOSTRAT 16
-/* 17 was XFS_TRANS_WRITE_SYNC */
-#define XFS_TRANS_WRITEID 18
-#define XFS_TRANS_ADDAFORK 19
-#define XFS_TRANS_ATTRINVAL 20
-#define XFS_TRANS_ATRUNCATE 21
-#define XFS_TRANS_ATTR_SET 22
-#define XFS_TRANS_ATTR_RM 23
-#define XFS_TRANS_ATTR_FLAG 24
-#define XFS_TRANS_CLEAR_AGI_BUCKET 25
-#define XFS_TRANS_SB_CHANGE 26
-/*
- * Dummy entries since we use the transaction type to index into the
- * trans_type[] in xlog_recover_print_trans_head()
- */
-#define XFS_TRANS_DUMMY1 27
-#define XFS_TRANS_DUMMY2 28
-#define XFS_TRANS_QM_QUOTAOFF 29
-#define XFS_TRANS_QM_DQALLOC 30
-#define XFS_TRANS_QM_SETQLIM 31
-#define XFS_TRANS_QM_DQCLUSTER 32
-#define XFS_TRANS_QM_QINOCREATE 33
-#define XFS_TRANS_QM_QUOTAOFF_END 34
-#define XFS_TRANS_FSYNC_TS 35
-#define XFS_TRANS_GROWFSRT_ALLOC 36
-#define XFS_TRANS_GROWFSRT_ZERO 37
-#define XFS_TRANS_GROWFSRT_FREE 38
-#define XFS_TRANS_SWAPEXT 39
-#define XFS_TRANS_CHECKPOINT 40
-#define XFS_TRANS_ICREATE 41
-#define XFS_TRANS_CREATE_TMPFILE 42
-#define XFS_TRANS_TYPE_MAX 43
-/* new transaction types need to be reflected in xfs_logprint(8) */
-
-#define XFS_TRANS_TYPES \
- { XFS_TRANS_SETATTR_NOT_SIZE, "SETATTR_NOT_SIZE" }, \
- { XFS_TRANS_SETATTR_SIZE, "SETATTR_SIZE" }, \
- { XFS_TRANS_INACTIVE, "INACTIVE" }, \
- { XFS_TRANS_CREATE, "CREATE" }, \
- { XFS_TRANS_CREATE_TRUNC, "CREATE_TRUNC" }, \
- { XFS_TRANS_TRUNCATE_FILE, "TRUNCATE_FILE" }, \
- { XFS_TRANS_REMOVE, "REMOVE" }, \
- { XFS_TRANS_LINK, "LINK" }, \
- { XFS_TRANS_RENAME, "RENAME" }, \
- { XFS_TRANS_MKDIR, "MKDIR" }, \
- { XFS_TRANS_RMDIR, "RMDIR" }, \
- { XFS_TRANS_SYMLINK, "SYMLINK" }, \
- { XFS_TRANS_SET_DMATTRS, "SET_DMATTRS" }, \
- { XFS_TRANS_GROWFS, "GROWFS" }, \
- { XFS_TRANS_STRAT_WRITE, "STRAT_WRITE" }, \
- { XFS_TRANS_DIOSTRAT, "DIOSTRAT" }, \
- { XFS_TRANS_WRITEID, "WRITEID" }, \
- { XFS_TRANS_ADDAFORK, "ADDAFORK" }, \
- { XFS_TRANS_ATTRINVAL, "ATTRINVAL" }, \
- { XFS_TRANS_ATRUNCATE, "ATRUNCATE" }, \
- { XFS_TRANS_ATTR_SET, "ATTR_SET" }, \
- { XFS_TRANS_ATTR_RM, "ATTR_RM" }, \
- { XFS_TRANS_ATTR_FLAG, "ATTR_FLAG" }, \
- { XFS_TRANS_CLEAR_AGI_BUCKET, "CLEAR_AGI_BUCKET" }, \
- { XFS_TRANS_SB_CHANGE, "SBCHANGE" }, \
- { XFS_TRANS_DUMMY1, "DUMMY1" }, \
- { XFS_TRANS_DUMMY2, "DUMMY2" }, \
- { XFS_TRANS_QM_QUOTAOFF, "QM_QUOTAOFF" }, \
- { XFS_TRANS_QM_DQALLOC, "QM_DQALLOC" }, \
- { XFS_TRANS_QM_SETQLIM, "QM_SETQLIM" }, \
- { XFS_TRANS_QM_DQCLUSTER, "QM_DQCLUSTER" }, \
- { XFS_TRANS_QM_QINOCREATE, "QM_QINOCREATE" }, \
- { XFS_TRANS_QM_QUOTAOFF_END, "QM_QOFF_END" }, \
- { XFS_TRANS_FSYNC_TS, "FSYNC_TS" }, \
- { XFS_TRANS_GROWFSRT_ALLOC, "GROWFSRT_ALLOC" }, \
- { XFS_TRANS_GROWFSRT_ZERO, "GROWFSRT_ZERO" }, \
- { XFS_TRANS_GROWFSRT_FREE, "GROWFSRT_FREE" }, \
- { XFS_TRANS_SWAPEXT, "SWAPEXT" }, \
- { XFS_TRANS_CHECKPOINT, "CHECKPOINT" }, \
- { XFS_TRANS_ICREATE, "ICREATE" }, \
- { XFS_TRANS_CREATE_TMPFILE, "CREATE_TMPFILE" }, \
- { XLOG_UNMOUNT_REC_TYPE, "UNMOUNT" }
-
-/*
* This structure is used to track log items associated with
* a transaction. It points to the log item and keeps some
* flags to track the state of the log item. It also tracks
@@ -181,8 +84,9 @@ int xfs_log_calc_minimum_size(struct xfs_mount *);
#define XFS_TRANS_SYNC 0x08 /* make commit synchronous */
#define XFS_TRANS_DQ_DIRTY 0x10 /* at least one dquot in trx dirty */
#define XFS_TRANS_RESERVE 0x20 /* OK to use reserved data blocks */
-#define XFS_TRANS_FREEZE_PROT 0x40 /* Transaction has elevated writer
- count in superblock */
+#define XFS_TRANS_NO_WRITECOUNT 0x40 /* do not elevate SB writecount */
+#define XFS_TRANS_NOFS 0x80 /* pass KM_NOFS to kmem_alloc */
+
/*
* Field values for xfs_trans_mod_sb.
*/
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index c535887c60a8..4c463b99fe57 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -84,23 +84,71 @@ xfs_find_bdev_for_inode(
}
/*
- * We're now finished for good with this ioend structure.
- * Update the page state via the associated buffer_heads,
- * release holds on the inode and bio, and finally free
- * up memory. Do not use the ioend after this.
+ * We're now finished for good with this page. Update the page state via the
+ * associated buffer_heads, paying attention to the start and end offsets that
+ * we need to process on the page.
+ */
+static void
+xfs_finish_page_writeback(
+ struct inode *inode,
+ struct bio_vec *bvec,
+ int error)
+{
+ unsigned int end = bvec->bv_offset + bvec->bv_len - 1;
+ struct buffer_head *head, *bh;
+ unsigned int off = 0;
+
+ ASSERT(bvec->bv_offset < PAGE_SIZE);
+ ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
+ ASSERT(end < PAGE_SIZE);
+ ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0);
+
+ bh = head = page_buffers(bvec->bv_page);
+
+ do {
+ if (off < bvec->bv_offset)
+ goto next_bh;
+ if (off > end)
+ break;
+ bh->b_end_io(bh, !error);
+next_bh:
+ off += bh->b_size;
+ } while ((bh = bh->b_this_page) != head);
+}
+
+/*
+ * We're now finished for good with this ioend structure. Update the page
+ * state, release holds on bios, and finally free up memory. Do not use the
+ * ioend after this.
*/
STATIC void
xfs_destroy_ioend(
- xfs_ioend_t *ioend)
+ struct xfs_ioend *ioend,
+ int error)
{
- struct buffer_head *bh, *next;
+ struct inode *inode = ioend->io_inode;
+ struct bio *last = ioend->io_bio;
+ struct bio *bio, *next;
- for (bh = ioend->io_buffer_head; bh; bh = next) {
- next = bh->b_private;
- bh->b_end_io(bh, !ioend->io_error);
- }
+ for (bio = &ioend->io_inline_bio; bio; bio = next) {
+ struct bio_vec *bvec;
+ int i;
+
+ /*
+ * For the last bio, bi_private points to the ioend, so we
+ * need to explicitly end the iteration here.
+ */
+ if (bio == last)
+ next = NULL;
+ else
+ next = bio->bi_private;
- mempool_free(ioend, xfs_ioend_pool);
+ /* walk each page on bio, ending page IO on them */
+ bio_for_each_segment_all(bvec, bio, i)
+ xfs_finish_page_writeback(inode, bvec, error);
+
+ bio_put(bio);
+ }
}
/*
@@ -120,13 +168,9 @@ xfs_setfilesize_trans_alloc(
struct xfs_trans *tp;
int error;
- tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
-
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
+ if (error)
return error;
- }
ioend->io_append_trans = tp;
@@ -174,7 +218,8 @@ xfs_setfilesize(
STATIC int
xfs_setfilesize_ioend(
- struct xfs_ioend *ioend)
+ struct xfs_ioend *ioend,
+ int error)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
struct xfs_trans *tp = ioend->io_append_trans;
@@ -188,53 +233,32 @@ xfs_setfilesize_ioend(
__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
/* we abort the update if there was an IO error */
- if (ioend->io_error) {
+ if (error) {
xfs_trans_cancel(tp);
- return ioend->io_error;
+ return error;
}
return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
}
/*
- * Schedule IO completion handling on the final put of an ioend.
- *
- * If there is no work to do we might as well call it a day and free the
- * ioend right now.
- */
-STATIC void
-xfs_finish_ioend(
- struct xfs_ioend *ioend)
-{
- if (atomic_dec_and_test(&ioend->io_remaining)) {
- struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount;
-
- if (ioend->io_type == XFS_IO_UNWRITTEN)
- queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
- else if (ioend->io_append_trans)
- queue_work(mp->m_data_workqueue, &ioend->io_work);
- else
- xfs_destroy_ioend(ioend);
- }
-}
-
-/*
* IO write completion.
*/
STATIC void
xfs_end_io(
struct work_struct *work)
{
- xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work);
- struct xfs_inode *ip = XFS_I(ioend->io_inode);
- int error = 0;
+ struct xfs_ioend *ioend =
+ container_of(work, struct xfs_ioend, io_work);
+ struct xfs_inode *ip = XFS_I(ioend->io_inode);
+ int error = ioend->io_bio->bi_error;
/*
* Set an error if the mount has shut down and proceed with end I/O
* processing so it can perform whatever cleanups are necessary.
*/
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- ioend->io_error = -EIO;
+ error = -EIO;
/*
* For unwritten extents we need to issue transactions to convert a
@@ -244,55 +268,33 @@ xfs_end_io(
* on error.
*/
if (ioend->io_type == XFS_IO_UNWRITTEN) {
- if (ioend->io_error)
+ if (error)
goto done;
error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
ioend->io_size);
} else if (ioend->io_append_trans) {
- error = xfs_setfilesize_ioend(ioend);
+ error = xfs_setfilesize_ioend(ioend, error);
} else {
ASSERT(!xfs_ioend_is_append(ioend));
}
done:
- if (error)
- ioend->io_error = error;
- xfs_destroy_ioend(ioend);
+ xfs_destroy_ioend(ioend, error);
}
-/*
- * Allocate and initialise an IO completion structure.
- * We need to track unwritten extent write completion here initially.
- * We'll need to extend this for updating the ondisk inode size later
- * (vs. incore size).
- */
-STATIC xfs_ioend_t *
-xfs_alloc_ioend(
- struct inode *inode,
- unsigned int type)
+STATIC void
+xfs_end_bio(
+ struct bio *bio)
{
- xfs_ioend_t *ioend;
-
- ioend = mempool_alloc(xfs_ioend_pool, GFP_NOFS);
-
- /*
- * Set the count to 1 initially, which will prevent an I/O
- * completion callback from happening before we have started
- * all the I/O from calling the completion routine too early.
- */
- atomic_set(&ioend->io_remaining, 1);
- ioend->io_error = 0;
- INIT_LIST_HEAD(&ioend->io_list);
- ioend->io_type = type;
- ioend->io_inode = inode;
- ioend->io_buffer_head = NULL;
- ioend->io_buffer_tail = NULL;
- ioend->io_offset = 0;
- ioend->io_size = 0;
- ioend->io_append_trans = NULL;
+ struct xfs_ioend *ioend = bio->bi_private;
+ struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount;
- INIT_WORK(&ioend->io_work, xfs_end_io);
- return ioend;
+ if (ioend->io_type == XFS_IO_UNWRITTEN)
+ queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
+ else if (ioend->io_append_trans)
+ queue_work(mp->m_data_workqueue, &ioend->io_work);
+ else
+ xfs_destroy_ioend(ioend, bio->bi_error);
}
STATIC int
@@ -364,50 +366,6 @@ xfs_imap_valid(
offset < imap->br_startoff + imap->br_blockcount;
}
-/*
- * BIO completion handler for buffered IO.
- */
-STATIC void
-xfs_end_bio(
- struct bio *bio)
-{
- xfs_ioend_t *ioend = bio->bi_private;
-
- if (!ioend->io_error)
- ioend->io_error = bio->bi_error;
-
- /* Toss bio and pass work off to an xfsdatad thread */
- bio->bi_private = NULL;
- bio->bi_end_io = NULL;
- bio_put(bio);
-
- xfs_finish_ioend(ioend);
-}
-
-STATIC void
-xfs_submit_ioend_bio(
- struct writeback_control *wbc,
- xfs_ioend_t *ioend,
- struct bio *bio)
-{
- atomic_inc(&ioend->io_remaining);
- bio->bi_private = ioend;
- bio->bi_end_io = xfs_end_bio;
- submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE, bio);
-}
-
-STATIC struct bio *
-xfs_alloc_ioend_bio(
- struct buffer_head *bh)
-{
- struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
-
- ASSERT(bio->bi_private == NULL);
- bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
- return bio;
-}
-
STATIC void
xfs_start_buffer_writeback(
struct buffer_head *bh)
@@ -452,28 +410,35 @@ static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
}
/*
- * Submit all of the bios for an ioend. We are only passed a single ioend at a
- * time; the caller is responsible for chaining prior to submission.
+ * Submit the bio for an ioend. We are passed an ioend with a bio attached to
+ * it, and we submit that bio. The ioend may be used for multiple bio
+ * submissions, so we only want to allocate an append transaction for the ioend
+ * once. In the case of multiple bio submission, each bio will take an IO
+ * reference to the ioend to ensure that the ioend completion is only done once
+ * all bios have been submitted and the ioend is really done.
*
* If @fail is non-zero, it means that we have a situation where some part of
* the submission process has failed after we have marked paged for writeback
- * and unlocked them. In this situation, we need to fail the ioend chain rather
- * than submit it to IO. This typically only happens on a filesystem shutdown.
+ * and unlocked them. In this situation, we need to fail the bio and ioend
+ * rather than submit it to IO. This typically only happens on a filesystem
+ * shutdown.
*/
STATIC int
xfs_submit_ioend(
struct writeback_control *wbc,
- xfs_ioend_t *ioend,
+ struct xfs_ioend *ioend,
int status)
{
- struct buffer_head *bh;
- struct bio *bio;
- sector_t lastblock = 0;
-
/* Reserve log space if we might write beyond the on-disk inode size. */
if (!status &&
- ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
+ ioend->io_type != XFS_IO_UNWRITTEN &&
+ xfs_ioend_is_append(ioend) &&
+ !ioend->io_append_trans)
status = xfs_setfilesize_trans_alloc(ioend);
+
+ ioend->io_bio->bi_private = ioend;
+ ioend->io_bio->bi_end_io = xfs_end_bio;
+
/*
* If we are failing the IO now, just mark the ioend with an
* error and finish it. This will run IO completion immediately
@@ -481,33 +446,73 @@ xfs_submit_ioend(
* time.
*/
if (status) {
- ioend->io_error = status;
- xfs_finish_ioend(ioend);
+ ioend->io_bio->bi_error = status;
+ bio_endio(ioend->io_bio);
return status;
}
- bio = NULL;
- for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
+ submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
+ ioend->io_bio);
+ return 0;
+}
- if (!bio) {
-retry:
- bio = xfs_alloc_ioend_bio(bh);
- } else if (bh->b_blocknr != lastblock + 1) {
- xfs_submit_ioend_bio(wbc, ioend, bio);
- goto retry;
- }
+static void
+xfs_init_bio_from_bh(
+ struct bio *bio,
+ struct buffer_head *bh)
+{
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_bdev = bh->b_bdev;
+}
- if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
- xfs_submit_ioend_bio(wbc, ioend, bio);
- goto retry;
- }
+static struct xfs_ioend *
+xfs_alloc_ioend(
+ struct inode *inode,
+ unsigned int type,
+ xfs_off_t offset,
+ struct buffer_head *bh)
+{
+ struct xfs_ioend *ioend;
+ struct bio *bio;
- lastblock = bh->b_blocknr;
- }
- if (bio)
- xfs_submit_ioend_bio(wbc, ioend, bio);
- xfs_finish_ioend(ioend);
- return 0;
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, xfs_ioend_bioset);
+ xfs_init_bio_from_bh(bio, bh);
+
+ ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
+ INIT_LIST_HEAD(&ioend->io_list);
+ ioend->io_type = type;
+ ioend->io_inode = inode;
+ ioend->io_size = 0;
+ ioend->io_offset = offset;
+ INIT_WORK(&ioend->io_work, xfs_end_io);
+ ioend->io_append_trans = NULL;
+ ioend->io_bio = bio;
+ return ioend;
+}
+
+/*
+ * Allocate a new bio, and chain the old bio to the new one.
+ *
+ * Note that we have to do perform the chaining in this unintuitive order
+ * so that the bi_private linkage is set up in the right direction for the
+ * traversal in xfs_destroy_ioend().
+ */
+static void
+xfs_chain_bio(
+ struct xfs_ioend *ioend,
+ struct writeback_control *wbc,
+ struct buffer_head *bh)
+{
+ struct bio *new;
+
+ new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+ xfs_init_bio_from_bh(new, bh);
+
+ bio_chain(ioend->io_bio, new);
+ bio_get(ioend->io_bio); /* for xfs_destroy_ioend */
+ submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
+ ioend->io_bio);
+ ioend->io_bio = new;
}
/*
@@ -523,27 +528,24 @@ xfs_add_to_ioend(
struct buffer_head *bh,
xfs_off_t offset,
struct xfs_writepage_ctx *wpc,
+ struct writeback_control *wbc,
struct list_head *iolist)
{
if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
bh->b_blocknr != wpc->last_block + 1 ||
offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
- struct xfs_ioend *new;
-
if (wpc->ioend)
list_add(&wpc->ioend->io_list, iolist);
-
- new = xfs_alloc_ioend(inode, wpc->io_type);
- new->io_offset = offset;
- new->io_buffer_head = bh;
- new->io_buffer_tail = bh;
- wpc->ioend = new;
- } else {
- wpc->ioend->io_buffer_tail->b_private = bh;
- wpc->ioend->io_buffer_tail = bh;
+ wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset, bh);
}
- bh->b_private = NULL;
+ /*
+ * If the buffer doesn't fit into the bio we need to allocate a new
+ * one. This shouldn't happen more than once for a given buffer.
+ */
+ while (xfs_bio_add_buffer(wpc->ioend->io_bio, bh) != bh->b_size)
+ xfs_chain_bio(wpc->ioend, wbc, bh);
+
wpc->ioend->io_size += bh->b_size;
wpc->last_block = bh->b_blocknr;
xfs_start_buffer_writeback(bh);
@@ -803,7 +805,7 @@ xfs_writepage_map(
lock_buffer(bh);
if (wpc->io_type != XFS_IO_OVERWRITE)
xfs_map_at_offset(inode, bh, &wpc->imap, offset);
- xfs_add_to_ioend(inode, bh, offset, wpc, &submit_list);
+ xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
count++;
}
@@ -1391,13 +1393,10 @@ xfs_end_io_direct_write(
trace_xfs_end_io_direct_write_append(ip, offset, size);
- tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
- return error;
- }
- error = xfs_setfilesize(ip, tp, offset, size);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0,
+ &tp);
+ if (!error)
+ error = xfs_setfilesize(ip, tp, offset, size);
}
return error;
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index b4421177b68d..814aab790713 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -18,7 +18,7 @@
#ifndef __XFS_AOPS_H__
#define __XFS_AOPS_H__
-extern mempool_t *xfs_ioend_pool;
+extern struct bio_set *xfs_ioend_bioset;
/*
* Types of I/O for bmap clustering and I/O completion tracking.
@@ -37,22 +37,19 @@ enum {
{ XFS_IO_OVERWRITE, "overwrite" }
/*
- * xfs_ioend struct manages large extent writes for XFS.
- * It can manage several multi-page bio's at once.
+ * Structure for buffered I/O completions.
*/
-typedef struct xfs_ioend {
+struct xfs_ioend {
struct list_head io_list; /* next ioend in chain */
unsigned int io_type; /* delalloc / unwritten */
- int io_error; /* I/O error code */
- atomic_t io_remaining; /* hold count */
struct inode *io_inode; /* file being written to */
- struct buffer_head *io_buffer_head;/* buffer linked list head */
- struct buffer_head *io_buffer_tail;/* buffer linked list tail */
size_t io_size; /* size of the extent */
xfs_off_t io_offset; /* offset in the file */
struct work_struct io_work; /* xfsdatad work queue */
struct xfs_trans *io_append_trans;/* xact. for size update */
-} xfs_ioend_t;
+ struct bio *io_bio; /* bio being built */
+ struct bio io_inline_bio; /* MUST BE LAST! */
+};
extern const struct address_space_operations xfs_address_space_operations;
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index dd4824589470..e3da5d448bcf 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -112,8 +112,9 @@ typedef struct attrlist_cursor_kern {
*========================================================================*/
+/* Return 0 on success, or -errno; other state communicated via *context */
typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, int,
- unsigned char *, int, int, unsigned char *);
+ unsigned char *, int, int);
typedef struct xfs_attr_list_context {
struct xfs_inode *dp; /* inode */
@@ -126,7 +127,6 @@ typedef struct xfs_attr_list_context {
int firstu; /* first used byte in buffer */
int flags; /* from VOP call */
int resynch; /* T/F: resynch with cursor */
- int put_value; /* T/F: need value for listent */
put_listent_func_t put_listent; /* list output fmt function */
int index; /* index into output buffer */
} xfs_attr_list_context_t;
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 2bb959ada45b..55d214981ed2 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -405,21 +405,11 @@ xfs_attr_inactive(
goto out_destroy_fork;
xfs_iunlock(dp, lock_mode);
- /*
- * Start our first transaction of the day.
- *
- * All future transactions during this code must be "chained" off
- * this one via the trans_dup() call. All transactions will contain
- * the inode, and the inode will always be marked with trans_ihold().
- * Since the inode will be locked in all transactions, we must log
- * the inode in every transaction to let it float upward through
- * the log.
- */
lock_mode = 0;
- trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
- error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrinval, 0, 0, 0, &trans);
if (error)
- goto out_cancel;
+ goto out_destroy_fork;
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(dp, lock_mode);
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 4fa14820e2e2..d25f26b22ac9 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -106,18 +106,15 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
sfe->flags,
sfe->nameval,
(int)sfe->namelen,
- (int)sfe->valuelen,
- &sfe->nameval[sfe->namelen]);
-
+ (int)sfe->valuelen);
+ if (error)
+ return error;
/*
* Either search callback finished early or
* didn't fit it all in the buffer after all.
*/
if (context->seen_enough)
break;
-
- if (error)
- return error;
sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
}
trace_xfs_attr_list_sf_all(context);
@@ -200,8 +197,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
sbp->flags,
sbp->name,
sbp->namelen,
- sbp->valuelen,
- &sbp->name[sbp->namelen]);
+ sbp->valuelen);
if (error) {
kmem_free(sbuf);
return error;
@@ -416,6 +412,9 @@ xfs_attr3_leaf_list_int(
*/
retval = 0;
for (; i < ichdr.count; entry++, i++) {
+ char *name;
+ int namelen, valuelen;
+
if (be32_to_cpu(entry->hashval) != cursor->hashval) {
cursor->hashval = be32_to_cpu(entry->hashval);
cursor->offset = 0;
@@ -425,56 +424,25 @@ xfs_attr3_leaf_list_int(
continue; /* skip incomplete entries */
if (entry->flags & XFS_ATTR_LOCAL) {
- xfs_attr_leaf_name_local_t *name_loc =
- xfs_attr3_leaf_name_local(leaf, i);
-
- retval = context->put_listent(context,
- entry->flags,
- name_loc->nameval,
- (int)name_loc->namelen,
- be16_to_cpu(name_loc->valuelen),
- &name_loc->nameval[name_loc->namelen]);
- if (retval)
- return retval;
+ xfs_attr_leaf_name_local_t *name_loc;
+
+ name_loc = xfs_attr3_leaf_name_local(leaf, i);
+ name = name_loc->nameval;
+ namelen = name_loc->namelen;
+ valuelen = be16_to_cpu(name_loc->valuelen);
} else {
- xfs_attr_leaf_name_remote_t *name_rmt =
- xfs_attr3_leaf_name_remote(leaf, i);
-
- int valuelen = be32_to_cpu(name_rmt->valuelen);
-
- if (context->put_value) {
- xfs_da_args_t args;
-
- memset((char *)&args, 0, sizeof(args));
- args.geo = context->dp->i_mount->m_attr_geo;
- args.dp = context->dp;
- args.whichfork = XFS_ATTR_FORK;
- args.valuelen = valuelen;
- args.rmtvaluelen = valuelen;
- args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS);
- args.rmtblkno = be32_to_cpu(name_rmt->valueblk);
- args.rmtblkcnt = xfs_attr3_rmt_blocks(
- args.dp->i_mount, valuelen);
- retval = xfs_attr_rmtval_get(&args);
- if (!retval)
- retval = context->put_listent(context,
- entry->flags,
- name_rmt->name,
- (int)name_rmt->namelen,
- valuelen,
- args.value);
- kmem_free(args.value);
- } else {
- retval = context->put_listent(context,
- entry->flags,
- name_rmt->name,
- (int)name_rmt->namelen,
- valuelen,
- NULL);
- }
- if (retval)
- return retval;
+ xfs_attr_leaf_name_remote_t *name_rmt;
+
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+ name = name_rmt->name;
+ namelen = name_rmt->namelen;
+ valuelen = be32_to_cpu(name_rmt->valuelen);
}
+
+ retval = context->put_listent(context, entry->flags,
+ name, namelen, valuelen);
+ if (retval)
+ break;
if (context->seen_enough)
break;
cursor->offset++;
@@ -551,8 +519,7 @@ xfs_attr_put_listent(
int flags,
unsigned char *name,
int namelen,
- int valuelen,
- unsigned char *value)
+ int valuelen)
{
struct attrlist *alist = (struct attrlist *)context->alist;
attrlist_ent_t *aep;
@@ -581,7 +548,7 @@ xfs_attr_put_listent(
trace_xfs_attr_list_full(context);
alist->al_more = 1;
context->seen_enough = 1;
- return 1;
+ return 0;
}
aep = (attrlist_ent_t *)&context->alist[context->firstu];
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 3b6309865c65..586bb64e674b 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -72,18 +72,11 @@ xfs_zero_extent(
struct xfs_mount *mp = ip->i_mount;
xfs_daddr_t sector = xfs_fsb_to_db(ip, start_fsb);
sector_t block = XFS_BB_TO_FSBT(mp, sector);
- ssize_t size = XFS_FSB_TO_B(mp, count_fsb);
-
- if (IS_DAX(VFS_I(ip)))
- return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
- sector, size);
-
- /*
- * let the block layer decide on the fastest method of
- * implementing the zeroing.
- */
- return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS);
+ return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
+ block << (mp->m_super->s_blocksize_bits - 9),
+ count_fsb << (mp->m_super->s_blocksize_bits - 9),
+ GFP_NOFS, true);
}
/*
@@ -900,19 +893,15 @@ xfs_free_eofblocks(
* Free them up now by truncating the file to
* its current size.
*/
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-
if (need_iolock) {
- if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
- xfs_trans_cancel(tp);
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
return -EAGAIN;
- }
}
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0,
+ &tp);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
@@ -1037,9 +1026,9 @@ xfs_alloc_file_space(
/*
* Allocate and setup the transaction.
*/
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
- resblks, resrtextents);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks,
+ resrtextents, 0, &tp);
+
/*
* Check for running out of space
*/
@@ -1048,7 +1037,6 @@ xfs_alloc_file_space(
* Free the transaction structure.
*/
ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
@@ -1311,18 +1299,10 @@ xfs_free_file_space(
* transaction to dip into the reserve blocks to ensure
* the freeing of the space succeeds at ENOSPC.
*/
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
-
- /*
- * check for running out of space
- */
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
+ &tp);
if (error) {
- /*
- * Free the transaction structure.
- */
ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
@@ -1482,19 +1462,16 @@ xfs_shift_file_space(
}
while (!error && !done) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
/*
* We would need to reserve permanent block for transaction.
* This will come into picture when after shifting extent into
* hole we found that adjacent extents can be merged which
* may lead to freeing of a block during record update.
*/
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
- XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
+ XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
+ if (error)
break;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
@@ -1747,12 +1724,9 @@ xfs_swap_extents(
if (error)
goto out_unlock;
- tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
+ if (error)
goto out_unlock;
- }
/*
* Lock and join the inodes to the tansaction so that transaction commit
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 9a2191b91137..e71cfbd5acb3 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1100,22 +1100,18 @@ xfs_bwrite(
return error;
}
-STATIC void
+static void
xfs_buf_bio_end_io(
struct bio *bio)
{
- xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private;
+ struct xfs_buf *bp = (struct xfs_buf *)bio->bi_private;
/*
* don't overwrite existing errors - otherwise we can lose errors on
* buffers that require multiple bios to complete.
*/
- if (bio->bi_error) {
- spin_lock(&bp->b_lock);
- if (!bp->b_io_error)
- bp->b_io_error = bio->bi_error;
- spin_unlock(&bp->b_lock);
- }
+ if (bio->bi_error)
+ cmpxchg(&bp->b_io_error, 0, bio->bi_error);
if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 4eb89bd4ee73..8bfb974f0772 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -183,6 +183,26 @@ typedef struct xfs_buf {
unsigned int b_page_count; /* size of page array */
unsigned int b_offset; /* page offset in first page */
int b_error; /* error code on I/O */
+
+ /*
+ * async write failure retry count. Initialised to zero on the first
+ * failure, then when it exceeds the maximum configured without a
+ * success the write is considered to be failed permanently and the
+ * iodone handler will take appropriate action.
+ *
+ * For retry timeouts, we record the jiffie of the first failure. This
+ * means that we can change the retry timeout for buffers already under
+ * I/O and thus avoid getting stuck in a retry loop with a long timeout.
+ *
+ * last_error is used to ensure that we are getting repeated errors, not
+ * different errors. e.g. a block device might change ENOSPC to EIO when
+ * a failure timeout occurs, so we want to re-initialise the error
+ * retry behaviour appropriately when that happens.
+ */
+ int b_retries;
+ unsigned long b_first_retry_time; /* in jiffies */
+ int b_last_error;
+
const struct xfs_buf_ops *b_ops;
#ifdef XFS_BUF_LOCK_TRACKING
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 99e91a0e554e..34257992934c 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -1042,35 +1042,22 @@ xfs_buf_do_callbacks(
}
}
-/*
- * This is the iodone() function for buffers which have had callbacks
- * attached to them by xfs_buf_attach_iodone(). It should remove each
- * log item from the buffer's list and call the callback of each in turn.
- * When done, the buffer's fsprivate field is set to NULL and the buffer
- * is unlocked with a call to iodone().
- */
-void
-xfs_buf_iodone_callbacks(
+static bool
+xfs_buf_iodone_callback_error(
struct xfs_buf *bp)
{
struct xfs_log_item *lip = bp->b_fspriv;
struct xfs_mount *mp = lip->li_mountp;
static ulong lasttime;
static xfs_buftarg_t *lasttarg;
-
- if (likely(!bp->b_error))
- goto do_callbacks;
+ struct xfs_error_cfg *cfg;
/*
* If we've already decided to shutdown the filesystem because of
* I/O errors, there's no point in giving this a retry.
*/
- if (XFS_FORCED_SHUTDOWN(mp)) {
- xfs_buf_stale(bp);
- bp->b_flags |= XBF_DONE;
- trace_xfs_buf_item_iodone(bp, _RET_IP_);
- goto do_callbacks;
- }
+ if (XFS_FORCED_SHUTDOWN(mp))
+ goto out_stale;
if (bp->b_target != lasttarg ||
time_after(jiffies, (lasttime + 5*HZ))) {
@@ -1079,45 +1066,93 @@ xfs_buf_iodone_callbacks(
}
lasttarg = bp->b_target;
+ /* synchronous writes will have callers process the error */
+ if (!(bp->b_flags & XBF_ASYNC))
+ goto out_stale;
+
+ trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+ ASSERT(bp->b_iodone != NULL);
+
/*
* If the write was asynchronous then no one will be looking for the
- * error. Clear the error state and write the buffer out again.
- *
- * XXX: This helps against transient write errors, but we need to find
- * a way to shut the filesystem down if the writes keep failing.
- *
- * In practice we'll shut the filesystem down soon as non-transient
- * errors tend to affect the whole device and a failing log write
- * will make us give up. But we really ought to do better here.
+ * error. If this is the first failure of this type, clear the error
+ * state and write the buffer out again. This means we always retry an
+ * async write failure at least once, but we also need to set the buffer
+ * up to behave correctly now for repeated failures.
*/
- if (bp->b_flags & XBF_ASYNC) {
- ASSERT(bp->b_iodone != NULL);
+ if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL)) ||
+ bp->b_last_error != bp->b_error) {
+ bp->b_flags |= (XBF_WRITE | XBF_ASYNC |
+ XBF_DONE | XBF_WRITE_FAIL);
+ bp->b_last_error = bp->b_error;
+ bp->b_retries = 0;
+ bp->b_first_retry_time = jiffies;
+
+ xfs_buf_ioerror(bp, 0);
+ xfs_buf_submit(bp);
+ return true;
+ }
- trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+ /*
+ * Repeated failure on an async write. Take action according to the
+ * error configuration we have been set up to use.
+ */
+ cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error);
- xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
+ if (cfg->max_retries != XFS_ERR_RETRY_FOREVER &&
+ ++bp->b_retries > cfg->max_retries)
+ goto permanent_error;
+ if (cfg->retry_timeout &&
+ time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time))
+ goto permanent_error;
- if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
- bp->b_flags |= XBF_WRITE | XBF_ASYNC |
- XBF_DONE | XBF_WRITE_FAIL;
- xfs_buf_submit(bp);
- } else {
- xfs_buf_relse(bp);
- }
+ /* At unmount we may treat errors differently */
+ if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
+ goto permanent_error;
- return;
- }
+ /* still a transient error, higher layers will retry */
+ xfs_buf_ioerror(bp, 0);
+ xfs_buf_relse(bp);
+ return true;
/*
- * If the write of the buffer was synchronous, we want to make
- * sure to return the error to the caller of xfs_bwrite().
+ * Permanent error - we need to trigger a shutdown if we haven't already
+ * to indicate that inconsistency will result from this action.
*/
+permanent_error:
+ xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+out_stale:
xfs_buf_stale(bp);
bp->b_flags |= XBF_DONE;
-
trace_xfs_buf_error_relse(bp, _RET_IP_);
+ return false;
+}
+
+/*
+ * This is the iodone() function for buffers which have had callbacks attached
+ * to them by xfs_buf_attach_iodone(). We need to iterate the items on the
+ * callback list, mark the buffer as having no more callbacks and then push the
+ * buffer through IO completion processing.
+ */
+void
+xfs_buf_iodone_callbacks(
+ struct xfs_buf *bp)
+{
+ /*
+ * If there is an error, process it. Some errors require us
+ * to run callbacks after failure processing is done so we
+ * detect that and take appropriate action.
+ */
+ if (bp->b_error && xfs_buf_iodone_callback_error(bp))
+ return;
+
+ /*
+ * Successful IO or permanent error. Either way, we can clear the
+ * retry state here in preparation for the next error that may occur.
+ */
+ bp->b_last_error = 0;
+ bp->b_retries = 0;
-do_callbacks:
xfs_buf_do_callbacks(bp);
bp->b_fspriv = NULL;
bp->b_iodone = NULL;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 316b2a1bdba5..e0646659ce16 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -614,11 +614,10 @@ xfs_qm_dqread(
trace_xfs_dqread(dqp);
if (flags & XFS_QMOPT_DQALLOC) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_QM_DQALLOC);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_dqalloc,
- XFS_QM_DQALLOC_SPACE_RES(mp), 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
+ XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
if (error)
- goto error1;
+ goto error0;
}
/*
@@ -692,7 +691,7 @@ error0:
* end of the chunk, skip ahead to first id in next allocated chunk
* using the SEEK_DATA interface.
*/
-int
+static int
xfs_dq_get_next_id(
xfs_mount_t *mp,
uint type,
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 85ce3032f815..47fc63295422 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -145,12 +145,10 @@ xfs_update_prealloc_flags(
struct xfs_trans *tp;
int error;
- tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
- error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
+ 0, 0, 0, &tp);
+ if (error)
return error;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -1553,7 +1551,7 @@ xfs_filemap_page_mkwrite(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+ ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
} else {
ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
ret = block_page_mkwrite_return(ret);
@@ -1587,7 +1585,7 @@ xfs_filemap_fault(
* changes to xfs_get_blocks_direct() to map unwritten extent
* ioend for conversion on read-only mappings.
*/
- ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+ ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
} else
ret = filemap_fault(vma, vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1624,8 +1622,7 @@ xfs_filemap_pmd_fault(
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
- NULL);
+ ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (flags & FAULT_FLAG_WRITE)
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index ee3aaa0a5317..b4d75825ae37 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -198,14 +198,10 @@ xfs_growfs_data_private(
return error;
}
- tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFS);
- tp->t_flags |= XFS_TRANS_RESERVE;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growdata,
- XFS_GROWFS_SPACE_RES(mp), 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
+ XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+ if (error)
return error;
- }
/*
* Write new AG headers to disk. Non-transactional, but written
@@ -243,8 +239,8 @@ xfs_growfs_data_private(
agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
- agf->agf_flfirst = 0;
- agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
+ agf->agf_flfirst = cpu_to_be32(1);
+ agf->agf_fllast = 0;
agf->agf_flcount = 0;
tmpsize = agsize - XFS_PREALLOC_BLOCKS(mp);
agf->agf_freeblks = cpu_to_be32(tmpsize);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index bf2d60749278..99ee6eee5e0b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -37,9 +37,6 @@
#include <linux/kthread.h>
#include <linux/freezer.h>
-STATIC void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp,
- struct xfs_perag *pag, struct xfs_inode *ip);
-
/*
* Allocate and initialise an xfs_inode.
*/
@@ -94,13 +91,6 @@ xfs_inode_free_callback(
struct inode *inode = container_of(head, struct inode, i_rcu);
struct xfs_inode *ip = XFS_I(inode);
- kmem_zone_free(xfs_inode_zone, ip);
-}
-
-void
-xfs_inode_free(
- struct xfs_inode *ip)
-{
switch (VFS_I(ip)->i_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
@@ -118,6 +108,25 @@ xfs_inode_free(
ip->i_itemp = NULL;
}
+ kmem_zone_free(xfs_inode_zone, ip);
+}
+
+static void
+__xfs_inode_free(
+ struct xfs_inode *ip)
+{
+ /* asserts to verify all state is correct here */
+ ASSERT(atomic_read(&ip->i_pincount) == 0);
+ ASSERT(!xfs_isiflocked(ip));
+ XFS_STATS_DEC(ip->i_mount, vn_active);
+
+ call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
+}
+
+void
+xfs_inode_free(
+ struct xfs_inode *ip)
+{
/*
* Because we use RCU freeing we need to ensure the inode always
* appears to be reclaimed with an invalid inode number when in the
@@ -129,12 +138,123 @@ xfs_inode_free(
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
- /* asserts to verify all state is correct here */
- ASSERT(atomic_read(&ip->i_pincount) == 0);
- ASSERT(!xfs_isiflocked(ip));
- XFS_STATS_DEC(ip->i_mount, vn_active);
+ __xfs_inode_free(ip);
+}
- call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
+/*
+ * Queue a new inode reclaim pass if there are reclaimable inodes and there
+ * isn't a reclaim pass already in progress. By default it runs every 5s based
+ * on the xfs periodic sync default of 30s. Perhaps this should have it's own
+ * tunable, but that can be done if this method proves to be ineffective or too
+ * aggressive.
+ */
+static void
+xfs_reclaim_work_queue(
+ struct xfs_mount *mp)
+{
+
+ rcu_read_lock();
+ if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
+ queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
+ msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
+ }
+ rcu_read_unlock();
+}
+
+/*
+ * This is a fast pass over the inode cache to try to get reclaim moving on as
+ * many inodes as possible in a short period of time. It kicks itself every few
+ * seconds, as well as being kicked by the inode cache shrinker when memory
+ * goes low. It scans as quickly as possible avoiding locked inodes or those
+ * already being flushed, and once done schedules a future pass.
+ */
+void
+xfs_reclaim_worker(
+ struct work_struct *work)
+{
+ struct xfs_mount *mp = container_of(to_delayed_work(work),
+ struct xfs_mount, m_reclaim_work);
+
+ xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
+ xfs_reclaim_work_queue(mp);
+}
+
+static void
+xfs_perag_set_reclaim_tag(
+ struct xfs_perag *pag)
+{
+ struct xfs_mount *mp = pag->pag_mount;
+
+ ASSERT(spin_is_locked(&pag->pag_ici_lock));
+ if (pag->pag_ici_reclaimable++)
+ return;
+
+ /* propagate the reclaim tag up into the perag radix tree */
+ spin_lock(&mp->m_perag_lock);
+ radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno,
+ XFS_ICI_RECLAIM_TAG);
+ spin_unlock(&mp->m_perag_lock);
+
+ /* schedule periodic background inode reclaim */
+ xfs_reclaim_work_queue(mp);
+
+ trace_xfs_perag_set_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
+}
+
+static void
+xfs_perag_clear_reclaim_tag(
+ struct xfs_perag *pag)
+{
+ struct xfs_mount *mp = pag->pag_mount;
+
+ ASSERT(spin_is_locked(&pag->pag_ici_lock));
+ if (--pag->pag_ici_reclaimable)
+ return;
+
+ /* clear the reclaim tag from the perag radix tree */
+ spin_lock(&mp->m_perag_lock);
+ radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno,
+ XFS_ICI_RECLAIM_TAG);
+ spin_unlock(&mp->m_perag_lock);
+ trace_xfs_perag_clear_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
+}
+
+
+/*
+ * We set the inode flag atomically with the radix tree tag.
+ * Once we get tag lookups on the radix tree, this inode flag
+ * can go away.
+ */
+void
+xfs_inode_set_reclaim_tag(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_perag *pag;
+
+ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+ spin_lock(&pag->pag_ici_lock);
+ spin_lock(&ip->i_flags_lock);
+
+ radix_tree_tag_set(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino),
+ XFS_ICI_RECLAIM_TAG);
+ xfs_perag_set_reclaim_tag(pag);
+ __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
+
+ spin_unlock(&ip->i_flags_lock);
+ spin_unlock(&pag->pag_ici_lock);
+ xfs_perag_put(pag);
+}
+
+STATIC void
+xfs_inode_clear_reclaim_tag(
+ struct xfs_perag *pag,
+ xfs_ino_t ino)
+{
+ radix_tree_tag_clear(&pag->pag_ici_root,
+ XFS_INO_TO_AGINO(pag->pag_mount, ino),
+ XFS_ICI_RECLAIM_TAG);
+ xfs_perag_clear_reclaim_tag(pag);
}
/*
@@ -264,7 +384,7 @@ xfs_iget_cache_hit(
*/
ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
ip->i_flags |= XFS_INEW;
- __xfs_inode_clear_reclaim_tag(mp, pag, ip);
+ xfs_inode_clear_reclaim_tag(pag, ip->i_ino);
inode->i_state = I_NEW;
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
@@ -723,121 +843,6 @@ xfs_inode_ag_iterator_tag(
}
/*
- * Queue a new inode reclaim pass if there are reclaimable inodes and there
- * isn't a reclaim pass already in progress. By default it runs every 5s based
- * on the xfs periodic sync default of 30s. Perhaps this should have it's own
- * tunable, but that can be done if this method proves to be ineffective or too
- * aggressive.
- */
-static void
-xfs_reclaim_work_queue(
- struct xfs_mount *mp)
-{
-
- rcu_read_lock();
- if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
- queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
- msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
- }
- rcu_read_unlock();
-}
-
-/*
- * This is a fast pass over the inode cache to try to get reclaim moving on as
- * many inodes as possible in a short period of time. It kicks itself every few
- * seconds, as well as being kicked by the inode cache shrinker when memory
- * goes low. It scans as quickly as possible avoiding locked inodes or those
- * already being flushed, and once done schedules a future pass.
- */
-void
-xfs_reclaim_worker(
- struct work_struct *work)
-{
- struct xfs_mount *mp = container_of(to_delayed_work(work),
- struct xfs_mount, m_reclaim_work);
-
- xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
- xfs_reclaim_work_queue(mp);
-}
-
-static void
-__xfs_inode_set_reclaim_tag(
- struct xfs_perag *pag,
- struct xfs_inode *ip)
-{
- radix_tree_tag_set(&pag->pag_ici_root,
- XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
- XFS_ICI_RECLAIM_TAG);
-
- if (!pag->pag_ici_reclaimable) {
- /* propagate the reclaim tag up into the perag radix tree */
- spin_lock(&ip->i_mount->m_perag_lock);
- radix_tree_tag_set(&ip->i_mount->m_perag_tree,
- XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
- XFS_ICI_RECLAIM_TAG);
- spin_unlock(&ip->i_mount->m_perag_lock);
-
- /* schedule periodic background inode reclaim */
- xfs_reclaim_work_queue(ip->i_mount);
-
- trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
- -1, _RET_IP_);
- }
- pag->pag_ici_reclaimable++;
-}
-
-/*
- * We set the inode flag atomically with the radix tree tag.
- * Once we get tag lookups on the radix tree, this inode flag
- * can go away.
- */
-void
-xfs_inode_set_reclaim_tag(
- xfs_inode_t *ip)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_perag *pag;
-
- pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
- spin_lock(&pag->pag_ici_lock);
- spin_lock(&ip->i_flags_lock);
- __xfs_inode_set_reclaim_tag(pag, ip);
- __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
- spin_unlock(&ip->i_flags_lock);
- spin_unlock(&pag->pag_ici_lock);
- xfs_perag_put(pag);
-}
-
-STATIC void
-__xfs_inode_clear_reclaim(
- xfs_perag_t *pag,
- xfs_inode_t *ip)
-{
- pag->pag_ici_reclaimable--;
- if (!pag->pag_ici_reclaimable) {
- /* clear the reclaim tag from the perag radix tree */
- spin_lock(&ip->i_mount->m_perag_lock);
- radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
- XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
- XFS_ICI_RECLAIM_TAG);
- spin_unlock(&ip->i_mount->m_perag_lock);
- trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno,
- -1, _RET_IP_);
- }
-}
-
-STATIC void
-__xfs_inode_clear_reclaim_tag(
- xfs_mount_t *mp,
- xfs_perag_t *pag,
- xfs_inode_t *ip)
-{
- radix_tree_tag_clear(&pag->pag_ici_root,
- XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
- __xfs_inode_clear_reclaim(pag, ip);
-}
-
-/*
* Grab the inode for reclaim exclusively.
* Return 0 if we grabbed it, non-zero otherwise.
*/
@@ -929,6 +934,7 @@ xfs_reclaim_inode(
int sync_mode)
{
struct xfs_buf *bp = NULL;
+ xfs_ino_t ino = ip->i_ino; /* for radix_tree_delete */
int error;
restart:
@@ -993,6 +999,22 @@ restart:
xfs_iflock(ip);
reclaim:
+ /*
+ * Because we use RCU freeing we need to ensure the inode always appears
+ * to be reclaimed with an invalid inode number when in the free state.
+ * We do this as early as possible under the ILOCK and flush lock so
+ * that xfs_iflush_cluster() can be guaranteed to detect races with us
+ * here. By doing this, we guarantee that once xfs_iflush_cluster has
+ * locked both the XFS_ILOCK and the flush lock that it will see either
+ * a valid, flushable inode that will serialise correctly against the
+ * locks below, or it will see a clean (and invalid) inode that it can
+ * skip.
+ */
+ spin_lock(&ip->i_flags_lock);
+ ip->i_flags = XFS_IRECLAIM;
+ ip->i_ino = 0;
+ spin_unlock(&ip->i_flags_lock);
+
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1006,9 +1028,9 @@ reclaim:
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
- XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
+ XFS_INO_TO_AGINO(ip->i_mount, ino)))
ASSERT(0);
- __xfs_inode_clear_reclaim(pag, ip);
+ xfs_perag_clear_reclaim_tag(pag);
spin_unlock(&pag->pag_ici_lock);
/*
@@ -1023,7 +1045,7 @@ reclaim:
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_inode_free(ip);
+ __xfs_inode_free(ip);
return error;
out_ifunlock:
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 96f606deee31..ee6799e0476f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1030,7 +1030,7 @@ xfs_dir_ialloc(
tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY);
}
- code = xfs_trans_roll(&tp, 0);
+ code = xfs_trans_roll(&tp, NULL);
if (committed != NULL)
*committed = 1;
@@ -1161,11 +1161,9 @@ xfs_create(
rdev = 0;
resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
tres = &M_RES(mp)->tr_mkdir;
- tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
} else {
resblks = XFS_CREATE_SPACE_RES(mp, name->len);
tres = &M_RES(mp)->tr_create;
- tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
}
/*
@@ -1174,20 +1172,19 @@ xfs_create(
* the case we'll drop the one we have and get a more
* appropriate transaction later.
*/
- error = xfs_trans_reserve(tp, tres, resblks, 0);
+ error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
if (error == -ENOSPC) {
/* flush outstanding delalloc blocks and retry */
xfs_flush_inodes(mp);
- error = xfs_trans_reserve(tp, tres, resblks, 0);
+ error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
}
if (error == -ENOSPC) {
/* No space at all so try a "no-allocation" reservation */
resblks = 0;
- error = xfs_trans_reserve(tp, tres, 0, 0);
+ error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp);
}
if (error)
- goto out_trans_cancel;
-
+ goto out_release_inode;
xfs_ilock(dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL |
XFS_IOLOCK_PARENT | XFS_ILOCK_PARENT);
@@ -1337,17 +1334,16 @@ xfs_create_tmpfile(
return error;
resblks = XFS_IALLOC_SPACE_RES(mp);
- tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE_TMPFILE);
-
tres = &M_RES(mp)->tr_create_tmpfile;
- error = xfs_trans_reserve(tp, tres, resblks, 0);
+
+ error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
if (error == -ENOSPC) {
/* No space at all so try a "no-allocation" reservation */
resblks = 0;
- error = xfs_trans_reserve(tp, tres, 0, 0);
+ error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp);
}
if (error)
- goto out_trans_cancel;
+ goto out_release_inode;
error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
pdqp, resblks, 1, 0);
@@ -1432,15 +1428,14 @@ xfs_link(
if (error)
goto std_return;
- tp = xfs_trans_alloc(mp, XFS_TRANS_LINK);
resblks = XFS_LINK_SPACE_RES(mp, target_name->len);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_link, resblks, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, resblks, 0, 0, &tp);
if (error == -ENOSPC) {
resblks = 0;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_link, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &tp);
}
if (error)
- goto error_return;
+ goto std_return;
xfs_ilock(tdp, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT);
xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL);
@@ -1710,11 +1705,9 @@ xfs_inactive_truncate(
struct xfs_trans *tp;
int error;
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp);
return error;
}
@@ -1764,8 +1757,6 @@ xfs_inactive_ifree(
struct xfs_trans *tp;
int error;
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-
/*
* The ifree transaction might need to allocate blocks for record
* insertion to the finobt. We don't want to fail here at ENOSPC, so
@@ -1781,9 +1772,8 @@ xfs_inactive_ifree(
* now remains allocated and sits on the unlinked list until the fs is
* repaired.
*/
- tp->t_flags |= XFS_TRANS_RESERVE;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree,
- XFS_IFREE_SPACE_RES(mp), 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
+ XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
if (error) {
if (error == -ENOSPC) {
xfs_warn_ratelimited(mp,
@@ -1792,7 +1782,6 @@ xfs_inactive_ifree(
} else {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
}
- xfs_trans_cancel(tp);
return error;
}
@@ -2525,11 +2514,6 @@ xfs_remove(
if (error)
goto std_return;
- if (is_dir)
- tp = xfs_trans_alloc(mp, XFS_TRANS_RMDIR);
- else
- tp = xfs_trans_alloc(mp, XFS_TRANS_REMOVE);
-
/*
* We try to get the real space reservation first,
* allowing for directory btree deletion(s) implying
@@ -2540,14 +2524,15 @@ xfs_remove(
* block from the directory.
*/
resblks = XFS_REMOVE_SPACE_RES(mp);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_remove, resblks, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, resblks, 0, 0, &tp);
if (error == -ENOSPC) {
resblks = 0;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_remove, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, 0, 0, 0,
+ &tp);
}
if (error) {
ASSERT(error != -ENOSPC);
- goto out_trans_cancel;
+ goto std_return;
}
xfs_ilock(dp, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT);
@@ -2855,6 +2840,7 @@ xfs_rename_alloc_whiteout(
* and flag it as linkable.
*/
drop_nlink(VFS_I(tmpfile));
+ xfs_setup_iops(tmpfile);
xfs_finish_inode_setup(tmpfile);
VFS_I(tmpfile)->i_state |= I_LINKABLE;
@@ -2910,15 +2896,15 @@ xfs_rename(
xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, wip,
inodes, &num_inodes);
- tp = xfs_trans_alloc(mp, XFS_TRANS_RENAME);
spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_rename, spaceres, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, spaceres, 0, 0, &tp);
if (error == -ENOSPC) {
spaceres = 0;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_rename, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, 0, 0, 0,
+ &tp);
}
if (error)
- goto out_trans_cancel;
+ goto out_release_wip;
/*
* Attach the dquots to the inodes
@@ -3155,6 +3141,7 @@ out_bmap_cancel:
xfs_bmap_cancel(&free_list);
out_trans_cancel:
xfs_trans_cancel(tp);
+out_release_wip:
if (wip)
IRELE(wip);
return error;
@@ -3162,16 +3149,16 @@ out_trans_cancel:
STATIC int
xfs_iflush_cluster(
- xfs_inode_t *ip,
- xfs_buf_t *bp)
+ struct xfs_inode *ip,
+ struct xfs_buf *bp)
{
- xfs_mount_t *mp = ip->i_mount;
+ struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
unsigned long first_index, mask;
unsigned long inodes_per_cluster;
- int ilist_size;
- xfs_inode_t **ilist;
- xfs_inode_t *iq;
+ int cilist_size;
+ struct xfs_inode **cilist;
+ struct xfs_inode *cip;
int nr_found;
int clcount = 0;
int bufwasdelwri;
@@ -3180,23 +3167,23 @@ xfs_iflush_cluster(
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
inodes_per_cluster = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
- ilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
- ilist = kmem_alloc(ilist_size, KM_MAYFAIL|KM_NOFS);
- if (!ilist)
+ cilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
+ cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
+ if (!cilist)
goto out_put;
mask = ~(((mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog)) - 1);
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
rcu_read_lock();
/* really need a gang lookup range call here */
- nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
+ nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
first_index, inodes_per_cluster);
if (nr_found == 0)
goto out_free;
for (i = 0; i < nr_found; i++) {
- iq = ilist[i];
- if (iq == ip)
+ cip = cilist[i];
+ if (cip == ip)
continue;
/*
@@ -3205,20 +3192,30 @@ xfs_iflush_cluster(
* We need to check under the i_flags_lock for a valid inode
* here. Skip it if it is not valid or the wrong inode.
*/
- spin_lock(&ip->i_flags_lock);
- if (!ip->i_ino ||
- (XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index) {
- spin_unlock(&ip->i_flags_lock);
+ spin_lock(&cip->i_flags_lock);
+ if (!cip->i_ino ||
+ __xfs_iflags_test(cip, XFS_ISTALE)) {
+ spin_unlock(&cip->i_flags_lock);
continue;
}
- spin_unlock(&ip->i_flags_lock);
+
+ /*
+ * Once we fall off the end of the cluster, no point checking
+ * any more inodes in the list because they will also all be
+ * outside the cluster.
+ */
+ if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) {
+ spin_unlock(&cip->i_flags_lock);
+ break;
+ }
+ spin_unlock(&cip->i_flags_lock);
/*
* Do an un-protected check to see if the inode is dirty and
* is a candidate for flushing. These checks will be repeated
* later after the appropriate locks are acquired.
*/
- if (xfs_inode_clean(iq) && xfs_ipincount(iq) == 0)
+ if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0)
continue;
/*
@@ -3226,15 +3223,28 @@ xfs_iflush_cluster(
* then this inode cannot be flushed and is skipped.
*/
- if (!xfs_ilock_nowait(iq, XFS_ILOCK_SHARED))
+ if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED))
+ continue;
+ if (!xfs_iflock_nowait(cip)) {
+ xfs_iunlock(cip, XFS_ILOCK_SHARED);
continue;
- if (!xfs_iflock_nowait(iq)) {
- xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ }
+ if (xfs_ipincount(cip)) {
+ xfs_ifunlock(cip);
+ xfs_iunlock(cip, XFS_ILOCK_SHARED);
continue;
}
- if (xfs_ipincount(iq)) {
- xfs_ifunlock(iq);
- xfs_iunlock(iq, XFS_ILOCK_SHARED);
+
+
+ /*
+ * Check the inode number again, just to be certain we are not
+ * racing with freeing in xfs_reclaim_inode(). See the comments
+ * in that function for more information as to why the initial
+ * check is not sufficient.
+ */
+ if (!cip->i_ino) {
+ xfs_ifunlock(cip);
+ xfs_iunlock(cip, XFS_ILOCK_SHARED);
continue;
}
@@ -3242,18 +3252,18 @@ xfs_iflush_cluster(
* arriving here means that this inode can be flushed. First
* re-check that it's dirty before flushing.
*/
- if (!xfs_inode_clean(iq)) {
+ if (!xfs_inode_clean(cip)) {
int error;
- error = xfs_iflush_int(iq, bp);
+ error = xfs_iflush_int(cip, bp);
if (error) {
- xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ xfs_iunlock(cip, XFS_ILOCK_SHARED);
goto cluster_corrupt_out;
}
clcount++;
} else {
- xfs_ifunlock(iq);
+ xfs_ifunlock(cip);
}
- xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ xfs_iunlock(cip, XFS_ILOCK_SHARED);
}
if (clcount) {
@@ -3263,7 +3273,7 @@ xfs_iflush_cluster(
out_free:
rcu_read_unlock();
- kmem_free(ilist);
+ kmem_free(cilist);
out_put:
xfs_perag_put(pag);
return 0;
@@ -3306,8 +3316,8 @@ cluster_corrupt_out:
/*
* Unlocks the flush lock
*/
- xfs_iflush_abort(iq, false);
- kmem_free(ilist);
+ xfs_iflush_abort(cip, false);
+ kmem_free(cilist);
xfs_perag_put(pag);
return -EFSCORRUPTED;
}
@@ -3327,7 +3337,7 @@ xfs_iflush(
struct xfs_buf **bpp)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_buf *bp;
+ struct xfs_buf *bp = NULL;
struct xfs_dinode *dip;
int error;
@@ -3369,14 +3379,22 @@ xfs_iflush(
}
/*
- * Get the buffer containing the on-disk inode.
+ * Get the buffer containing the on-disk inode. We are doing a try-lock
+ * operation here, so we may get an EAGAIN error. In that case, we
+ * simply want to return with the inode still dirty.
+ *
+ * If we get any other error, we effectively have a corruption situation
+ * and we cannot flush the inode, so we treat it the same as failing
+ * xfs_iflush_int().
*/
error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
0);
- if (error || !bp) {
+ if (error == -EAGAIN) {
xfs_ifunlock(ip);
return error;
}
+ if (error)
+ goto corrupt_out;
/*
* First flush out the inode that xfs_iflush was called with.
@@ -3404,7 +3422,8 @@ xfs_iflush(
return 0;
corrupt_out:
- xfs_buf_relse(bp);
+ if (bp)
+ xfs_buf_relse(bp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
cluster_corrupt_out:
error = -EFSCORRUPTED;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 43e1d51b15eb..e52d7c7aeb5b 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -440,6 +440,9 @@ loff_t __xfs_seek_hole_data(struct inode *inode, loff_t start,
/* from xfs_iops.c */
+extern void xfs_setup_inode(struct xfs_inode *ip);
+extern void xfs_setup_iops(struct xfs_inode *ip);
+
/*
* When setting up a newly allocated inode, we need to call
* xfs_finish_inode_setup() once the inode is fully instantiated at
@@ -447,7 +450,6 @@ loff_t __xfs_seek_hole_data(struct inode *inode, loff_t start,
* before we've completed instantiation. Otherwise we can do it
* the moment the inode lookup is complete.
*/
-extern void xfs_setup_inode(struct xfs_inode *ip);
static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
{
xfs_iflags_clear(ip, XFS_INEW);
@@ -458,6 +460,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
{
xfs_setup_inode(ip);
+ xfs_setup_iops(ip);
xfs_finish_inode_setup(ip);
}
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index c48b5b18d771..a1b07612224c 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -210,7 +210,7 @@ xfs_inode_item_format_data_fork(
*/
data_bytes = roundup(ip->i_df.if_bytes, 4);
ASSERT(ip->i_df.if_real_bytes == 0 ||
- ip->i_df.if_real_bytes == data_bytes);
+ ip->i_df.if_real_bytes >= data_bytes);
ASSERT(ip->i_df.if_u1.if_data != NULL);
ASSERT(ip->i_d.di_size > 0);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
@@ -305,7 +305,7 @@ xfs_inode_item_format_attr_fork(
*/
data_bytes = roundup(ip->i_afp->if_bytes, 4);
ASSERT(ip->i_afp->if_real_bytes == 0 ||
- ip->i_afp->if_real_bytes == data_bytes);
+ ip->i_afp->if_real_bytes >= data_bytes);
ASSERT(ip->i_afp->if_u1.if_data != NULL);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
ip->i_afp->if_u1.if_data,
@@ -479,6 +479,8 @@ STATIC uint
xfs_inode_item_push(
struct xfs_log_item *lip,
struct list_head *buffer_list)
+ __releases(&lip->li_ailp->xa_lock)
+ __acquires(&lip->li_ailp->xa_lock)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bcb6c19ce3ea..dbca7375deef 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -277,7 +277,6 @@ xfs_readlink_by_handle(
{
struct dentry *dentry;
__u32 olen;
- void *link;
int error;
if (!capable(CAP_SYS_ADMIN))
@@ -288,7 +287,7 @@ xfs_readlink_by_handle(
return PTR_ERR(dentry);
/* Restrict this handle operation to symlinks only. */
- if (!d_is_symlink(dentry)) {
+ if (!d_inode(dentry)->i_op->readlink) {
error = -EINVAL;
goto out_dput;
}
@@ -298,21 +297,8 @@ xfs_readlink_by_handle(
goto out_dput;
}
- link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
- if (!link) {
- error = -ENOMEM;
- goto out_dput;
- }
-
- error = xfs_readlink(XFS_I(d_inode(dentry)), link);
- if (error)
- goto out_kfree;
- error = readlink_copy(hreq->ohandle, olen, link);
- if (error)
- goto out_kfree;
+ error = d_inode(dentry)->i_op->readlink(dentry, hreq->ohandle, olen);
- out_kfree:
- kfree(link);
out_dput:
dput(dentry);
return error;
@@ -334,12 +320,10 @@ xfs_set_dmattrs(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- tp = xfs_trans_alloc(mp, XFS_TRANS_SET_DMATTRS);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
+ if (error)
return error;
- }
+
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -1141,10 +1125,9 @@ xfs_ioctl_setattr_get_trans(
if (XFS_FORCED_SHUTDOWN(mp))
goto out_unlock;
- tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
if (error)
- goto out_cancel;
+ return ERR_PTR(error);
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d81bdc080370..58391355a44d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -132,6 +132,7 @@ xfs_iomap_write_direct(
int error;
int lockmode;
int bmapi_flags = XFS_BMAPI_PREALLOC;
+ uint tflags = 0;
rt = XFS_IS_REALTIME_INODE(ip);
extsz = xfs_get_extsz_hint(ip);
@@ -192,11 +193,6 @@ xfs_iomap_write_direct(
return error;
/*
- * Allocate and setup the transaction
- */
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
-
- /*
* For DAX, we do not allocate unwritten extents, but instead we zero
* the block before we commit the transaction. Ideally we'd like to do
* this outside the transaction context, but if we commit and then crash
@@ -209,23 +205,17 @@ xfs_iomap_write_direct(
* the reserve block pool for bmbt block allocation if there is no space
* left but we need to do unwritten extent conversion.
*/
-
if (IS_DAX(VFS_I(ip))) {
bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
if (ISUNWRITTEN(imap)) {
- tp->t_flags |= XFS_TRANS_RESERVE;
+ tflags |= XFS_TRANS_RESERVE;
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
}
}
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
- resblks, resrtextents);
- /*
- * Check for running out of space, note: need lock to return
- */
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, resrtextents,
+ tflags, &tp);
+ if (error)
return error;
- }
lockmode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lockmode);
@@ -726,15 +716,13 @@ xfs_iomap_write_allocate(
nimaps = 0;
while (nimaps == 0) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
- tp->t_flags |= XFS_TRANS_RESERVE;
nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
- nres, 0);
- if (error) {
- xfs_trans_cancel(tp);
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, nres,
+ 0, XFS_TRANS_RESERVE, &tp);
+ if (error)
return error;
- }
+
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
@@ -878,25 +866,18 @@ xfs_iomap_write_unwritten(
do {
/*
- * set up a transaction to convert the range of extents
+ * Set up a transaction to convert the range of extents
* from unwritten to real. Do allocations in a loop until
* we have covered the range passed in.
*
- * Note that we open code the transaction allocation here
- * to pass KM_NOFS--we can't risk to recursing back into
- * the filesystem here as we might be asked to write out
- * the same inode that we complete here and might deadlock
- * on the iolock.
+ * Note that we can't risk to recursing back into the filesystem
+ * here as we might be asked to write out the same inode that we
+ * complete here and might deadlock on the iolock.
*/
- sb_start_intwrite(mp->m_super);
- tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
- tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
- resblks, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
+ XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp);
+ if (error)
return error;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index fb7dc61f4a29..c5d4eba6972e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -181,6 +181,8 @@ xfs_generic_create(
}
#endif
+ xfs_setup_iops(ip);
+
if (tmpfile)
d_tmpfile(dentry, inode);
else
@@ -368,6 +370,8 @@ xfs_vn_symlink(
if (unlikely(error))
goto out_cleanup_inode;
+ xfs_setup_iops(cip);
+
d_instantiate(dentry, inode);
xfs_finish_inode_setup(cip);
return 0;
@@ -442,6 +446,16 @@ xfs_vn_get_link(
return ERR_PTR(error);
}
+STATIC const char *
+xfs_vn_get_link_inline(
+ struct dentry *dentry,
+ struct inode *inode,
+ struct delayed_call *done)
+{
+ ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE);
+ return XFS_I(inode)->i_df.if_u1.if_data;
+}
+
STATIC int
xfs_vn_getattr(
struct vfsmount *mnt,
@@ -599,12 +613,12 @@ xfs_setattr_nonsize(
return error;
}
- tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
if (error)
- goto out_trans_cancel;
+ goto out_dqrele;
xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
/*
* Change file ownership. Must be the owner or privileged.
@@ -633,12 +647,10 @@ xfs_setattr_nonsize(
NULL, capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (error) /* out of quota */
- goto out_unlock;
+ goto out_cancel;
}
}
- xfs_trans_ijoin(tp, ip, 0);
-
/*
* Change file ownership. Must be the owner or privileged.
*/
@@ -722,10 +734,9 @@ xfs_setattr_nonsize(
return 0;
-out_unlock:
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-out_trans_cancel:
+out_cancel:
xfs_trans_cancel(tp);
+out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return error;
@@ -834,7 +845,7 @@ xfs_setattr_size(
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
- * Hence a truncate can fail with ENOMEM from xfs_trans_reserve(), but
+ * Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but
* having already truncated the in-memory version of the file (i.e. made
* user visible changes). There's not much we can do about this, except
* to hope that the caller sees ENOMEM and retries the truncate
@@ -849,10 +860,9 @@ xfs_setattr_size(
return error;
truncate_setsize(inode, newsize);
- tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
- goto out_trans_cancel;
+ return error;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
@@ -971,12 +981,9 @@ xfs_vn_update_time(
trace_xfs_update_time(ip);
- tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
+ if (error)
return error;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (flags & S_CTIME)
@@ -1167,6 +1174,18 @@ static const struct inode_operations xfs_symlink_inode_operations = {
.update_time = xfs_vn_update_time,
};
+static const struct inode_operations xfs_inline_symlink_inode_operations = {
+ .readlink = generic_readlink,
+ .get_link = xfs_vn_get_link_inline,
+ .getattr = xfs_vn_getattr,
+ .setattr = xfs_vn_setattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .removexattr = generic_removexattr,
+ .listxattr = xfs_vn_listxattr,
+ .update_time = xfs_vn_update_time,
+};
+
STATIC void
xfs_diflags_to_iflags(
struct inode *inode,
@@ -1193,7 +1212,7 @@ xfs_diflags_to_iflags(
}
/*
- * Initialize the Linux inode and set up the operation vectors.
+ * Initialize the Linux inode.
*
* When reading existing inodes from disk this is called directly from xfs_iget,
* when creating a new inode it is called from xfs_ialloc after setting up the
@@ -1232,32 +1251,12 @@ xfs_setup_inode(
i_size_write(inode, ip->i_d.di_size);
xfs_diflags_to_iflags(inode, ip);
- ip->d_ops = ip->i_mount->m_nondir_inode_ops;
- lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
- switch (inode->i_mode & S_IFMT) {
- case S_IFREG:
- inode->i_op = &xfs_inode_operations;
- inode->i_fop = &xfs_file_operations;
- inode->i_mapping->a_ops = &xfs_address_space_operations;
- break;
- case S_IFDIR:
+ if (S_ISDIR(inode->i_mode)) {
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
- if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
- inode->i_op = &xfs_dir_ci_inode_operations;
- else
- inode->i_op = &xfs_dir_inode_operations;
- inode->i_fop = &xfs_dir_file_operations;
ip->d_ops = ip->i_mount->m_dir_inode_ops;
- break;
- case S_IFLNK:
- inode->i_op = &xfs_symlink_inode_operations;
- if (!(ip->i_df.if_flags & XFS_IFINLINE))
- inode->i_mapping->a_ops = &xfs_address_space_operations;
- break;
- default:
- inode->i_op = &xfs_inode_operations;
- init_special_inode(inode, inode->i_mode, inode->i_rdev);
- break;
+ } else {
+ ip->d_ops = ip->i_mount->m_nondir_inode_ops;
+ lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
}
/*
@@ -1277,3 +1276,35 @@ xfs_setup_inode(
cache_no_acl(inode);
}
}
+
+void
+xfs_setup_iops(
+ struct xfs_inode *ip)
+{
+ struct inode *inode = &ip->i_vnode;
+
+ switch (inode->i_mode & S_IFMT) {
+ case S_IFREG:
+ inode->i_op = &xfs_inode_operations;
+ inode->i_fop = &xfs_file_operations;
+ inode->i_mapping->a_ops = &xfs_address_space_operations;
+ break;
+ case S_IFDIR:
+ if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
+ inode->i_op = &xfs_dir_ci_inode_operations;
+ else
+ inode->i_op = &xfs_dir_inode_operations;
+ inode->i_fop = &xfs_dir_file_operations;
+ break;
+ case S_IFLNK:
+ if (ip->i_df.if_flags & XFS_IFINLINE)
+ inode->i_op = &xfs_inline_symlink_inode_operations;
+ else
+ inode->i_op = &xfs_symlink_inode_operations;
+ break;
+ default:
+ inode->i_op = &xfs_inode_operations;
+ init_special_inode(inode, inode->i_mode, inode->i_rdev);
+ break;
+ }
+}
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index b49ccf5c1d75..bde02f1fba73 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -435,8 +435,7 @@ xfs_log_reserve(
int cnt,
struct xlog_ticket **ticp,
__uint8_t client,
- bool permanent,
- uint t_type)
+ bool permanent)
{
struct xlog *log = mp->m_log;
struct xlog_ticket *tic;
@@ -456,7 +455,6 @@ xfs_log_reserve(
if (!tic)
return -ENOMEM;
- tic->t_trans_type = t_type;
*ticp = tic;
xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt
@@ -823,8 +821,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
} while (iclog != first_iclog);
#endif
if (! (XLOG_FORCED_SHUTDOWN(log))) {
- error = xfs_log_reserve(mp, 600, 1, &tic,
- XFS_LOG, 0, XLOG_UNMOUNT_REC_TYPE);
+ error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
if (!error) {
/* the data section must be 32 bit size aligned */
struct {
@@ -2032,58 +2029,8 @@ xlog_print_tic_res(
REG_TYPE_STR(ICREATE, "inode create")
};
#undef REG_TYPE_STR
-#define TRANS_TYPE_STR(type) [XFS_TRANS_##type] = #type
- static char *trans_type_str[XFS_TRANS_TYPE_MAX] = {
- TRANS_TYPE_STR(SETATTR_NOT_SIZE),
- TRANS_TYPE_STR(SETATTR_SIZE),
- TRANS_TYPE_STR(INACTIVE),
- TRANS_TYPE_STR(CREATE),
- TRANS_TYPE_STR(CREATE_TRUNC),
- TRANS_TYPE_STR(TRUNCATE_FILE),
- TRANS_TYPE_STR(REMOVE),
- TRANS_TYPE_STR(LINK),
- TRANS_TYPE_STR(RENAME),
- TRANS_TYPE_STR(MKDIR),
- TRANS_TYPE_STR(RMDIR),
- TRANS_TYPE_STR(SYMLINK),
- TRANS_TYPE_STR(SET_DMATTRS),
- TRANS_TYPE_STR(GROWFS),
- TRANS_TYPE_STR(STRAT_WRITE),
- TRANS_TYPE_STR(DIOSTRAT),
- TRANS_TYPE_STR(WRITEID),
- TRANS_TYPE_STR(ADDAFORK),
- TRANS_TYPE_STR(ATTRINVAL),
- TRANS_TYPE_STR(ATRUNCATE),
- TRANS_TYPE_STR(ATTR_SET),
- TRANS_TYPE_STR(ATTR_RM),
- TRANS_TYPE_STR(ATTR_FLAG),
- TRANS_TYPE_STR(CLEAR_AGI_BUCKET),
- TRANS_TYPE_STR(SB_CHANGE),
- TRANS_TYPE_STR(DUMMY1),
- TRANS_TYPE_STR(DUMMY2),
- TRANS_TYPE_STR(QM_QUOTAOFF),
- TRANS_TYPE_STR(QM_DQALLOC),
- TRANS_TYPE_STR(QM_SETQLIM),
- TRANS_TYPE_STR(QM_DQCLUSTER),
- TRANS_TYPE_STR(QM_QINOCREATE),
- TRANS_TYPE_STR(QM_QUOTAOFF_END),
- TRANS_TYPE_STR(FSYNC_TS),
- TRANS_TYPE_STR(GROWFSRT_ALLOC),
- TRANS_TYPE_STR(GROWFSRT_ZERO),
- TRANS_TYPE_STR(GROWFSRT_FREE),
- TRANS_TYPE_STR(SWAPEXT),
- TRANS_TYPE_STR(CHECKPOINT),
- TRANS_TYPE_STR(ICREATE),
- TRANS_TYPE_STR(CREATE_TMPFILE)
- };
-#undef TRANS_TYPE_STR
xfs_warn(mp, "xlog_write: reservation summary:");
- xfs_warn(mp, " trans type = %s (%u)",
- ((ticket->t_trans_type <= 0 ||
- ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
- "bad-trans-type" : trans_type_str[ticket->t_trans_type]),
- ticket->t_trans_type);
xfs_warn(mp, " unit res = %d bytes",
ticket->t_unit_res);
xfs_warn(mp, " current res = %d bytes",
@@ -3378,7 +3325,7 @@ xfs_log_force(
{
int error;
- trace_xfs_log_force(mp, 0);
+ trace_xfs_log_force(mp, 0, _RET_IP_);
error = _xfs_log_force(mp, flags, NULL);
if (error)
xfs_warn(mp, "%s: error %d returned.", __func__, error);
@@ -3527,7 +3474,7 @@ xfs_log_force_lsn(
{
int error;
- trace_xfs_log_force(mp, lsn);
+ trace_xfs_log_force(mp, lsn, _RET_IP_);
error = _xfs_log_force_lsn(mp, lsn, flags, NULL);
if (error)
xfs_warn(mp, "%s: error %d returned.", __func__, error);
@@ -3709,7 +3656,6 @@ xlog_ticket_alloc(
tic->t_tid = prandom_u32();
tic->t_clientid = client;
tic->t_flags = XLOG_TIC_INITED;
- tic->t_trans_type = 0;
if (permanent)
tic->t_flags |= XLOG_TIC_PERM_RESERV;
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index aa533a7d50f2..80ba0c047090 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -161,8 +161,7 @@ int xfs_log_reserve(struct xfs_mount *mp,
int count,
struct xlog_ticket **ticket,
__uint8_t clientid,
- bool permanent,
- uint t_type);
+ bool permanent);
int xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
int xfs_log_unmount_write(struct xfs_mount *mp);
void xfs_log_unmount(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 4e7649351f5a..5e54e7955ea6 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -51,7 +51,6 @@ xlog_cil_ticket_alloc(
tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0,
KM_SLEEP|KM_NOFS);
- tic->t_trans_type = XFS_TRANS_CHECKPOINT;
/*
* set the current reservation to zero so we know to steal the basic
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ed8896310c00..765f084759b5 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -175,7 +175,6 @@ typedef struct xlog_ticket {
char t_cnt; /* current count : 1 */
char t_clientid; /* who does this belong to; : 1 */
char t_flags; /* properties of reservation : 1 */
- uint t_trans_type; /* transaction type : 4 */
/* reservation array fields */
uint t_res_num; /* num in array : 4 */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 396565f43247..835997843846 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3843,7 +3843,7 @@ xlog_recover_add_to_cont_trans(
old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
old_len = item->ri_buf[item->ri_cnt-1].i_len;
- ptr = kmem_realloc(old_ptr, len+old_len, old_len, KM_SLEEP);
+ ptr = kmem_realloc(old_ptr, len + old_len, KM_SLEEP);
memcpy(&ptr[old_len], dp, len);
item->ri_buf[item->ri_cnt-1].i_len += len;
item->ri_buf[item->ri_cnt-1].i_addr = ptr;
@@ -4205,10 +4205,9 @@ xlog_recover_process_efi(
}
}
- tp = xfs_trans_alloc(mp, 0);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
- goto abort_error;
+ return error;
efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
@@ -4355,10 +4354,9 @@ xlog_recover_clear_agi_bucket(
int offset;
int error;
- tp = xfs_trans_alloc(mp, XFS_TRANS_CLEAR_AGI_BUCKET);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_clearagi, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_clearagi, 0, 0, 0, &tp);
if (error)
- goto out_abort;
+ goto out_error;
error = xfs_read_agi(mp, tp, agno, &agibp);
if (error)
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index cfd4210dd015..e39b02351b4a 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -89,7 +89,6 @@ xfs_uuid_mount(
if (hole < 0) {
xfs_uuid_table = kmem_realloc(xfs_uuid_table,
(xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
- xfs_uuid_table_size * sizeof(*xfs_uuid_table),
KM_SLEEP);
hole = xfs_uuid_table_size++;
}
@@ -681,6 +680,9 @@ xfs_mountfs(
xfs_set_maxicount(mp);
+ /* enable fail_at_unmount as default */
+ mp->m_fail_unmount = 1;
+
error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname);
if (error)
goto out;
@@ -690,10 +692,15 @@ xfs_mountfs(
if (error)
goto out_remove_sysfs;
- error = xfs_uuid_mount(mp);
+ error = xfs_error_sysfs_init(mp);
if (error)
goto out_del_stats;
+
+ error = xfs_uuid_mount(mp);
+ if (error)
+ goto out_remove_error_sysfs;
+
/*
* Set the minimum read and write sizes
*/
@@ -957,6 +964,7 @@ xfs_mountfs(
cancel_delayed_work_sync(&mp->m_reclaim_work);
xfs_reclaim_inodes(mp, SYNC_WAIT);
out_log_dealloc:
+ mp->m_flags |= XFS_MOUNT_UNMOUNTING;
xfs_log_mount_cancel(mp);
out_fail_wait:
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
@@ -968,6 +976,8 @@ xfs_mountfs(
xfs_da_unmount(mp);
out_remove_uuid:
xfs_uuid_unmount(mp);
+ out_remove_error_sysfs:
+ xfs_error_sysfs_del(mp);
out_del_stats:
xfs_sysfs_del(&mp->m_stats.xs_kobj);
out_remove_sysfs:
@@ -1006,6 +1016,14 @@ xfs_unmountfs(
xfs_log_force(mp, XFS_LOG_SYNC);
/*
+ * We now need to tell the world we are unmounting. This will allow
+ * us to detect that the filesystem is going away and we should error
+ * out anything that we have been retrying in the background. This will
+ * prevent neverending retries in AIL pushing from hanging the unmount.
+ */
+ mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
+ /*
* Flush all pending changes from the AIL.
*/
xfs_ail_push_all_sync(mp->m_ail);
@@ -1056,6 +1074,7 @@ xfs_unmountfs(
#endif
xfs_free_perag(mp);
+ xfs_error_sysfs_del(mp);
xfs_sysfs_del(&mp->m_stats.xs_kobj);
xfs_sysfs_del(&mp->m_kobj);
}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index eafe257b357a..c1b798c72126 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -37,6 +37,32 @@ enum {
XFS_LOWSP_MAX,
};
+/*
+ * Error Configuration
+ *
+ * Error classes define the subsystem the configuration belongs to.
+ * Error numbers define the errors that are configurable.
+ */
+enum {
+ XFS_ERR_METADATA,
+ XFS_ERR_CLASS_MAX,
+};
+enum {
+ XFS_ERR_DEFAULT,
+ XFS_ERR_EIO,
+ XFS_ERR_ENOSPC,
+ XFS_ERR_ENODEV,
+ XFS_ERR_ERRNO_MAX,
+};
+
+#define XFS_ERR_RETRY_FOREVER -1
+
+struct xfs_error_cfg {
+ struct xfs_kobj kobj;
+ int max_retries;
+ unsigned long retry_timeout; /* in jiffies, 0 = no timeout */
+};
+
typedef struct xfs_mount {
struct super_block *m_super;
xfs_tid_t m_tid; /* next unused tid for fs */
@@ -127,6 +153,9 @@ typedef struct xfs_mount {
int64_t m_low_space[XFS_LOWSP_MAX];
/* low free space thresholds */
struct xfs_kobj m_kobj;
+ struct xfs_kobj m_error_kobj;
+ struct xfs_kobj m_error_meta_kobj;
+ struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX];
struct xstats m_stats; /* per-fs stats */
struct workqueue_struct *m_buf_workqueue;
@@ -148,6 +177,7 @@ typedef struct xfs_mount {
*/
__uint32_t m_generation;
+ bool m_fail_unmount;
#ifdef DEBUG
/*
* DEBUG mode instrumentation to test and/or trigger delayed allocation
@@ -166,6 +196,7 @@ typedef struct xfs_mount {
#define XFS_MOUNT_WSYNC (1ULL << 0) /* for nfs - all metadata ops
must be synchronous except
for space allocations */
+#define XFS_MOUNT_UNMOUNTING (1ULL << 1) /* filesystem is unmounting */
#define XFS_MOUNT_WAS_CLEAN (1ULL << 3)
#define XFS_MOUNT_FS_SHUTDOWN (1ULL << 4) /* atomic stop of all filesystem
operations, typically for
@@ -364,4 +395,7 @@ extern void xfs_set_low_space_thresholds(struct xfs_mount *);
int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
xfs_off_t count_fsb);
+struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
+ int error_class, int error);
+
#endif /* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 51ddaf2c2b8c..d5b756669fb5 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -308,12 +308,9 @@ xfs_fs_commit_blocks(
goto out_drop_iolock;
}
- tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
+ if (error)
goto out_drop_iolock;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index be125e1758c1..a60d9e2739d1 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -783,13 +783,10 @@ xfs_qm_qino_alloc(
}
}
- tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QINOCREATE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_create,
- XFS_QM_QINOCREATE_SPACE_RES(mp), 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_create,
+ XFS_QM_QINOCREATE_SPACE_RES(mp), 0, 0, &tp);
+ if (error)
return error;
- }
if (need_alloc) {
error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index f4d0e0a8f517..475a3882a81f 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -236,10 +236,8 @@ xfs_qm_scall_trunc_qfile(
xfs_ilock(ip, XFS_IOLOCK_EXCL);
- tp = xfs_trans_alloc(mp, XFS_TRANS_TRUNCATE_FILE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error) {
- xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
goto out_put;
}
@@ -436,12 +434,9 @@ xfs_qm_scall_setqlim(
defq = xfs_get_defquota(dqp, q);
xfs_dqunlock(dqp);
- tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_setqlim, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_setqlim, 0, 0, 0, &tp);
+ if (error)
goto out_rele;
- }
xfs_dqlock(dqp);
xfs_trans_dqjoin(tp, dqp);
@@ -569,13 +564,9 @@ xfs_qm_log_quotaoff_end(
int error;
xfs_qoff_logitem_t *qoffi;
- tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QUOTAOFF_END);
-
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_equotaoff, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_equotaoff, 0, 0, 0, &tp);
+ if (error)
return error;
- }
qoffi = xfs_trans_get_qoff_item(tp, startqoff,
flags & XFS_ALL_QUOTA_ACCT);
@@ -603,12 +594,9 @@ xfs_qm_log_quotaoff(
*qoffstartp = NULL;
- tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QUOTAOFF);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_quotaoff, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_quotaoff, 0, 0, 0, &tp);
+ if (error)
goto out;
- }
qoffi = xfs_trans_get_qoff_item(tp, NULL, flags & XFS_ALL_QUOTA_ACCT);
xfs_trans_log_quotaoff_item(tp, qoffi);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index abf44435d04a..3938b37d1043 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -780,15 +780,14 @@ xfs_growfs_rt_alloc(
* Allocate space to the file, as necessary.
*/
while (oblocks < nblocks) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ALLOC);
resblks = XFS_GROWFSRT_SPACE_RES(mp, nblocks - oblocks);
/*
* Reserve space & log for one extent added to the file.
*/
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtalloc,
- resblks, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtalloc, resblks,
+ 0, 0, &tp);
if (error)
- goto out_trans_cancel;
+ return error;
/*
* Lock the inode.
*/
@@ -823,14 +822,13 @@ xfs_growfs_rt_alloc(
for (bno = map.br_startoff, fsbno = map.br_startblock;
bno < map.br_startoff + map.br_blockcount;
bno++, fsbno++) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ZERO);
/*
* Reserve log for one block zeroing.
*/
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtzero,
- 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtzero,
+ 0, 0, 0, &tp);
if (error)
- goto out_trans_cancel;
+ return error;
/*
* Lock the bitmap inode.
*/
@@ -994,11 +992,10 @@ xfs_growfs_rt(
/*
* Start a transaction, get the log reservation.
*/
- tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_FREE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtfree,
- 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtfree, 0, 0, 0,
+ &tp);
if (error)
- goto error_cancel;
+ break;
/*
* Lock out other callers by grabbing the bitmap inode lock.
*/
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 187e14b696c2..11ea5d51db56 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -58,8 +58,7 @@
#include <linux/parser.h>
static const struct super_operations xfs_super_operations;
-static kmem_zone_t *xfs_ioend_zone;
-mempool_t *xfs_ioend_pool;
+struct bio_set *xfs_ioend_bioset;
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
@@ -350,6 +349,7 @@ xfs_parseargs(
case Opt_pqnoenforce:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_PQUOTA_ENFD;
+ break;
case Opt_gquota:
case Opt_grpquota:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
@@ -928,7 +928,7 @@ xfs_fs_alloc_inode(
/*
* Now that the generic code is guaranteed not to be accessing
- * the linux inode, we can reclaim the inode.
+ * the linux inode, we can inactivate and reclaim the inode.
*/
STATIC void
xfs_fs_destroy_inode(
@@ -938,9 +938,14 @@ xfs_fs_destroy_inode(
trace_xfs_destroy_inode(ip);
- XFS_STATS_INC(ip->i_mount, vn_reclaim);
+ ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+ XFS_STATS_INC(ip->i_mount, vn_rele);
+ XFS_STATS_INC(ip->i_mount, vn_remove);
+
+ xfs_inactive(ip);
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
+ XFS_STATS_INC(ip->i_mount, vn_reclaim);
/*
* We should never get here with one of the reclaim flags already set.
@@ -987,24 +992,6 @@ xfs_fs_inode_init_once(
"xfsino", ip->i_ino);
}
-STATIC void
-xfs_fs_evict_inode(
- struct inode *inode)
-{
- xfs_inode_t *ip = XFS_I(inode);
-
- ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
-
- trace_xfs_evict_inode(ip);
-
- truncate_inode_pages_final(&inode->i_data);
- clear_inode(inode);
- XFS_STATS_INC(ip->i_mount, vn_rele);
- XFS_STATS_INC(ip->i_mount, vn_remove);
-
- xfs_inactive(ip);
-}
-
/*
* We do an unlocked check for XFS_IDONTCACHE here because we are already
* serialised against cache hits here via the inode->i_lock and igrab() in
@@ -1276,6 +1263,16 @@ xfs_fs_remount(
return -EINVAL;
}
+ if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+ xfs_sb_has_ro_compat_feature(sbp,
+ XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+ xfs_warn(mp,
+"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
+ (sbp->sb_features_ro_compat &
+ XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+ return -EINVAL;
+ }
+
mp->m_flags &= ~XFS_MOUNT_RDONLY;
/*
@@ -1558,14 +1555,12 @@ xfs_fs_fill_super(
if (mp->m_flags & XFS_MOUNT_DAX) {
xfs_warn(mp,
- "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
- if (sb->s_blocksize != PAGE_SIZE) {
- xfs_alert(mp,
- "Filesystem block size invalid for DAX Turning DAX off.");
- mp->m_flags &= ~XFS_MOUNT_DAX;
- } else if (!sb->s_bdev->bd_disk->fops->direct_access) {
+ "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+
+ error = bdev_dax_supported(sb, sb->s_blocksize);
+ if (error) {
xfs_alert(mp,
- "Block device does not support DAX Turning DAX off.");
+ "DAX unsupported by block device. Turning off DAX.");
mp->m_flags &= ~XFS_MOUNT_DAX;
}
}
@@ -1663,7 +1658,6 @@ xfs_fs_free_cached_objects(
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
- .evict_inode = xfs_fs_evict_inode,
.drop_inode = xfs_fs_drop_inode,
.put_super = xfs_fs_put_super,
.sync_fs = xfs_fs_sync_fs,
@@ -1688,20 +1682,15 @@ MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_zones(void)
{
-
- xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
- if (!xfs_ioend_zone)
+ xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
+ offsetof(struct xfs_ioend, io_inline_bio));
+ if (!xfs_ioend_bioset)
goto out;
- xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
- xfs_ioend_zone);
- if (!xfs_ioend_pool)
- goto out_destroy_ioend_zone;
-
xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
"xfs_log_ticket");
if (!xfs_log_ticket_zone)
- goto out_destroy_ioend_pool;
+ goto out_free_ioend_bioset;
xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
"xfs_bmap_free_item");
@@ -1797,10 +1786,8 @@ xfs_init_zones(void)
kmem_zone_destroy(xfs_bmap_free_item_zone);
out_destroy_log_ticket_zone:
kmem_zone_destroy(xfs_log_ticket_zone);
- out_destroy_ioend_pool:
- mempool_destroy(xfs_ioend_pool);
- out_destroy_ioend_zone:
- kmem_zone_destroy(xfs_ioend_zone);
+ out_free_ioend_bioset:
+ bioset_free(xfs_ioend_bioset);
out:
return -ENOMEM;
}
@@ -1826,9 +1813,7 @@ xfs_destroy_zones(void)
kmem_zone_destroy(xfs_btree_cur_zone);
kmem_zone_destroy(xfs_bmap_free_item_zone);
kmem_zone_destroy(xfs_log_ticket_zone);
- mempool_destroy(xfs_ioend_pool);
- kmem_zone_destroy(xfs_ioend_zone);
-
+ bioset_free(xfs_ioend_bioset);
}
STATIC int __init
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index b44284c1adda..08a46c6181fd 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -131,6 +131,8 @@ xfs_readlink(
trace_xfs_readlink(ip);
+ ASSERT(!(ip->i_df.if_flags & XFS_IFINLINE));
+
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
@@ -150,12 +152,7 @@ xfs_readlink(
}
- if (ip->i_df.if_flags & XFS_IFINLINE) {
- memcpy(link, ip->i_df.if_u1.if_data, pathlen);
- link[pathlen] = '\0';
- } else {
- error = xfs_readlink_bmap(ip, link);
- }
+ error = xfs_readlink_bmap(ip, link);
out:
xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -221,7 +218,6 @@ xfs_symlink(
if (error)
return error;
- tp = xfs_trans_alloc(mp, XFS_TRANS_SYMLINK);
/*
* The symlink will fit into the inode data fork?
* There can't be any attributes so we get the whole variable part.
@@ -231,13 +227,15 @@ xfs_symlink(
else
fs_blocks = xfs_symlink_blocks(mp, pathlen);
resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_symlink, resblks, 0);
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp);
if (error == -ENOSPC && fs_blocks == 0) {
resblks = 0;
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_symlink, 0, 0);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, 0, 0, 0,
+ &tp);
}
if (error)
- goto out_trans_cancel;
+ goto out_release_inode;
xfs_ilock(dp, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL |
XFS_IOLOCK_PARENT | XFS_ILOCK_PARENT);
@@ -302,19 +300,11 @@ xfs_symlink(
* If the symlink will fit into the inode, write it inline.
*/
if (pathlen <= XFS_IFORK_DSIZE(ip)) {
- xfs_idata_realloc(ip, pathlen, XFS_DATA_FORK);
- memcpy(ip->i_df.if_u1.if_data, target_path, pathlen);
- ip->i_d.di_size = pathlen;
-
- /*
- * The inode was initially created in extent format.
- */
- ip->i_df.if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
- ip->i_df.if_flags |= XFS_IFINLINE;
+ xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
+ ip->i_d.di_size = pathlen;
ip->i_d.di_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
-
} else {
int offset;
@@ -455,12 +445,9 @@ xfs_inactive_symlink_rmt(
*/
ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
- if (error) {
- xfs_trans_cancel(tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+ if (error)
return error;
- }
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 6ced4f143494..4c2c55086208 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -17,10 +17,11 @@
*/
#include "xfs.h"
-#include "xfs_sysfs.h"
+#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
+#include "xfs_sysfs.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_stats.h"
@@ -362,3 +363,291 @@ struct kobj_type xfs_log_ktype = {
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_log_attrs,
};
+
+/*
+ * Metadata IO error configuration
+ *
+ * The sysfs structure here is:
+ * ...xfs/<dev>/error/<class>/<errno>/<error_attrs>
+ *
+ * where <class> allows us to discriminate between data IO and metadata IO,
+ * and any other future type of IO (e.g. special inode or directory error
+ * handling) we care to support.
+ */
+static inline struct xfs_error_cfg *
+to_error_cfg(struct kobject *kobject)
+{
+ struct xfs_kobj *kobj = to_kobj(kobject);
+ return container_of(kobj, struct xfs_error_cfg, kobj);
+}
+
+static inline struct xfs_mount *
+err_to_mp(struct kobject *kobject)
+{
+ struct xfs_kobj *kobj = to_kobj(kobject);
+ return container_of(kobj, struct xfs_mount, m_error_kobj);
+}
+
+static ssize_t
+max_retries_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ struct xfs_error_cfg *cfg = to_error_cfg(kobject);
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", cfg->max_retries);
+}
+
+static ssize_t
+max_retries_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ struct xfs_error_cfg *cfg = to_error_cfg(kobject);
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ if (val < -1)
+ return -EINVAL;
+
+ cfg->max_retries = val;
+ return count;
+}
+XFS_SYSFS_ATTR_RW(max_retries);
+
+static ssize_t
+retry_timeout_seconds_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ struct xfs_error_cfg *cfg = to_error_cfg(kobject);
+
+ return snprintf(buf, PAGE_SIZE, "%ld\n",
+ jiffies_to_msecs(cfg->retry_timeout) / MSEC_PER_SEC);
+}
+
+static ssize_t
+retry_timeout_seconds_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ struct xfs_error_cfg *cfg = to_error_cfg(kobject);
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ /* 1 day timeout maximum */
+ if (val < 0 || val > 86400)
+ return -EINVAL;
+
+ cfg->retry_timeout = msecs_to_jiffies(val * MSEC_PER_SEC);
+ return count;
+}
+XFS_SYSFS_ATTR_RW(retry_timeout_seconds);
+
+static ssize_t
+fail_at_unmount_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ struct xfs_mount *mp = err_to_mp(kobject);
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_unmount);
+}
+
+static ssize_t
+fail_at_unmount_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ struct xfs_mount *mp = err_to_mp(kobject);
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ if (val < 0 || val > 1)
+ return -EINVAL;
+
+ mp->m_fail_unmount = val;
+ return count;
+}
+XFS_SYSFS_ATTR_RW(fail_at_unmount);
+
+static struct attribute *xfs_error_attrs[] = {
+ ATTR_LIST(max_retries),
+ ATTR_LIST(retry_timeout_seconds),
+ NULL,
+};
+
+
+struct kobj_type xfs_error_cfg_ktype = {
+ .release = xfs_sysfs_release,
+ .sysfs_ops = &xfs_sysfs_ops,
+ .default_attrs = xfs_error_attrs,
+};
+
+struct kobj_type xfs_error_ktype = {
+ .release = xfs_sysfs_release,
+ .sysfs_ops = &xfs_sysfs_ops,
+};
+
+/*
+ * Error initialization tables. These need to be ordered in the same
+ * order as the enums used to index the array. All class init tables need to
+ * define a "default" behaviour as the first entry, all other entries can be
+ * empty.
+ */
+struct xfs_error_init {
+ char *name;
+ int max_retries;
+ int retry_timeout; /* in seconds */
+};
+
+static const struct xfs_error_init xfs_error_meta_init[XFS_ERR_ERRNO_MAX] = {
+ { .name = "default",
+ .max_retries = XFS_ERR_RETRY_FOREVER,
+ .retry_timeout = 0,
+ },
+ { .name = "EIO",
+ .max_retries = XFS_ERR_RETRY_FOREVER,
+ .retry_timeout = 0,
+ },
+ { .name = "ENOSPC",
+ .max_retries = XFS_ERR_RETRY_FOREVER,
+ .retry_timeout = 0,
+ },
+ { .name = "ENODEV",
+ .max_retries = 0,
+ },
+};
+
+static int
+xfs_error_sysfs_init_class(
+ struct xfs_mount *mp,
+ int class,
+ const char *parent_name,
+ struct xfs_kobj *parent_kobj,
+ const struct xfs_error_init init[])
+{
+ struct xfs_error_cfg *cfg;
+ int error;
+ int i;
+
+ ASSERT(class < XFS_ERR_CLASS_MAX);
+
+ error = xfs_sysfs_init(parent_kobj, &xfs_error_ktype,
+ &mp->m_error_kobj, parent_name);
+ if (error)
+ return error;
+
+ for (i = 0; i < XFS_ERR_ERRNO_MAX; i++) {
+ cfg = &mp->m_error_cfg[class][i];
+ error = xfs_sysfs_init(&cfg->kobj, &xfs_error_cfg_ktype,
+ parent_kobj, init[i].name);
+ if (error)
+ goto out_error;
+
+ cfg->max_retries = init[i].max_retries;
+ cfg->retry_timeout = msecs_to_jiffies(
+ init[i].retry_timeout * MSEC_PER_SEC);
+ }
+ return 0;
+
+out_error:
+ /* unwind the entries that succeeded */
+ for (i--; i >= 0; i--) {
+ cfg = &mp->m_error_cfg[class][i];
+ xfs_sysfs_del(&cfg->kobj);
+ }
+ xfs_sysfs_del(parent_kobj);
+ return error;
+}
+
+int
+xfs_error_sysfs_init(
+ struct xfs_mount *mp)
+{
+ int error;
+
+ /* .../xfs/<dev>/error/ */
+ error = xfs_sysfs_init(&mp->m_error_kobj, &xfs_error_ktype,
+ &mp->m_kobj, "error");
+ if (error)
+ return error;
+
+ error = sysfs_create_file(&mp->m_error_kobj.kobject,
+ ATTR_LIST(fail_at_unmount));
+
+ if (error)
+ goto out_error;
+
+ /* .../xfs/<dev>/error/metadata/ */
+ error = xfs_error_sysfs_init_class(mp, XFS_ERR_METADATA,
+ "metadata", &mp->m_error_meta_kobj,
+ xfs_error_meta_init);
+ if (error)
+ goto out_error;
+
+ return 0;
+
+out_error:
+ xfs_sysfs_del(&mp->m_error_kobj);
+ return error;
+}
+
+void
+xfs_error_sysfs_del(
+ struct xfs_mount *mp)
+{
+ struct xfs_error_cfg *cfg;
+ int i, j;
+
+ for (i = 0; i < XFS_ERR_CLASS_MAX; i++) {
+ for (j = 0; j < XFS_ERR_ERRNO_MAX; j++) {
+ cfg = &mp->m_error_cfg[i][j];
+
+ xfs_sysfs_del(&cfg->kobj);
+ }
+ }
+ xfs_sysfs_del(&mp->m_error_meta_kobj);
+ xfs_sysfs_del(&mp->m_error_kobj);
+}
+
+struct xfs_error_cfg *
+xfs_error_get_cfg(
+ struct xfs_mount *mp,
+ int error_class,
+ int error)
+{
+ struct xfs_error_cfg *cfg;
+
+ switch (error) {
+ case EIO:
+ cfg = &mp->m_error_cfg[error_class][XFS_ERR_EIO];
+ break;
+ case ENOSPC:
+ cfg = &mp->m_error_cfg[error_class][XFS_ERR_ENOSPC];
+ break;
+ case ENODEV:
+ cfg = &mp->m_error_cfg[error_class][XFS_ERR_ENODEV];
+ break;
+ default:
+ cfg = &mp->m_error_cfg[error_class][XFS_ERR_DEFAULT];
+ break;
+ }
+
+ return cfg;
+}
diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h
index be692e59938d..d04637181ef2 100644
--- a/fs/xfs/xfs_sysfs.h
+++ b/fs/xfs/xfs_sysfs.h
@@ -58,4 +58,7 @@ xfs_sysfs_del(
wait_for_completion(&kobj->complete);
}
+int xfs_error_sysfs_init(struct xfs_mount *mp);
+void xfs_error_sysfs_del(struct xfs_mount *mp);
+
#endif /* __XFS_SYSFS_H__ */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index c8d58426008e..ea94ee0fe5ea 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -364,7 +364,6 @@ DEFINE_BUF_EVENT(xfs_buf_delwri_split);
DEFINE_BUF_EVENT(xfs_buf_get_uncached);
DEFINE_BUF_EVENT(xfs_bdstrat_shut);
DEFINE_BUF_EVENT(xfs_buf_item_relse);
-DEFINE_BUF_EVENT(xfs_buf_item_iodone);
DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);
DEFINE_BUF_EVENT(xfs_buf_error_relse);
DEFINE_BUF_EVENT(xfs_buf_wait_buftarg);
@@ -944,7 +943,6 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class,
TP_ARGS(log, tic),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(unsigned, trans_type)
__field(char, ocnt)
__field(char, cnt)
__field(int, curr_res)
@@ -962,7 +960,6 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class,
),
TP_fast_assign(
__entry->dev = log->l_mp->m_super->s_dev;
- __entry->trans_type = tic->t_trans_type;
__entry->ocnt = tic->t_ocnt;
__entry->cnt = tic->t_cnt;
__entry->curr_res = tic->t_curr_res;
@@ -980,14 +977,13 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class,
__entry->curr_block = log->l_curr_block;
__entry->tail_lsn = atomic64_read(&log->l_tail_lsn);
),
- TP_printk("dev %d:%d type %s t_ocnt %u t_cnt %u t_curr_res %u "
+ TP_printk("dev %d:%d t_ocnt %u t_cnt %u t_curr_res %u "
"t_unit_res %u t_flags %s reserveq %s "
"writeq %s grant_reserve_cycle %d "
"grant_reserve_bytes %d grant_write_cycle %d "
"grant_write_bytes %d curr_cycle %d curr_block %d "
"tail_cycle %d tail_block %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __print_symbolic(__entry->trans_type, XFS_TRANS_TYPES),
__entry->ocnt,
__entry->cnt,
__entry->curr_res,
@@ -1053,19 +1049,21 @@ DECLARE_EVENT_CLASS(xfs_log_item_class,
)
TRACE_EVENT(xfs_log_force,
- TP_PROTO(struct xfs_mount *mp, xfs_lsn_t lsn),
- TP_ARGS(mp, lsn),
+ TP_PROTO(struct xfs_mount *mp, xfs_lsn_t lsn, unsigned long caller_ip),
+ TP_ARGS(mp, lsn, caller_ip),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_lsn_t, lsn)
+ __field(unsigned long, caller_ip)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->lsn = lsn;
+ __entry->caller_ip = caller_ip;
),
- TP_printk("dev %d:%d lsn 0x%llx",
+ TP_printk("dev %d:%d lsn 0x%llx caller %ps",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->lsn)
+ __entry->lsn, (void *)__entry->caller_ip)
)
#define DEFINE_LOG_ITEM_EVENT(name) \
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 20c53666cb4b..5f3d33d16e67 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -47,47 +47,6 @@ xfs_trans_init(
}
/*
- * This routine is called to allocate a transaction structure.
- * The type parameter indicates the type of the transaction. These
- * are enumerated in xfs_trans.h.
- *
- * Dynamically allocate the transaction structure from the transaction
- * zone, initialize it, and return it to the caller.
- */
-xfs_trans_t *
-xfs_trans_alloc(
- xfs_mount_t *mp,
- uint type)
-{
- xfs_trans_t *tp;
-
- sb_start_intwrite(mp->m_super);
- tp = _xfs_trans_alloc(mp, type, KM_SLEEP);
- tp->t_flags |= XFS_TRANS_FREEZE_PROT;
- return tp;
-}
-
-xfs_trans_t *
-_xfs_trans_alloc(
- xfs_mount_t *mp,
- uint type,
- xfs_km_flags_t memflags)
-{
- xfs_trans_t *tp;
-
- WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
- atomic_inc(&mp->m_active_trans);
-
- tp = kmem_zone_zalloc(xfs_trans_zone, memflags);
- tp->t_magic = XFS_TRANS_HEADER_MAGIC;
- tp->t_type = type;
- tp->t_mountp = mp;
- INIT_LIST_HEAD(&tp->t_items);
- INIT_LIST_HEAD(&tp->t_busy);
- return tp;
-}
-
-/*
* Free the transaction structure. If there is more clean up
* to do when the structure is freed, add it here.
*/
@@ -99,7 +58,7 @@ xfs_trans_free(
xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
atomic_dec(&tp->t_mountp->m_active_trans);
- if (tp->t_flags & XFS_TRANS_FREEZE_PROT)
+ if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
sb_end_intwrite(tp->t_mountp->m_super);
xfs_trans_free_dqinfo(tp);
kmem_zone_free(xfs_trans_zone, tp);
@@ -125,7 +84,6 @@ xfs_trans_dup(
* Initialize the new transaction structure.
*/
ntp->t_magic = XFS_TRANS_HEADER_MAGIC;
- ntp->t_type = tp->t_type;
ntp->t_mountp = tp->t_mountp;
INIT_LIST_HEAD(&ntp->t_items);
INIT_LIST_HEAD(&ntp->t_busy);
@@ -135,9 +93,9 @@ xfs_trans_dup(
ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
(tp->t_flags & XFS_TRANS_RESERVE) |
- (tp->t_flags & XFS_TRANS_FREEZE_PROT);
+ (tp->t_flags & XFS_TRANS_NO_WRITECOUNT);
/* We gave our writer reference to the new transaction */
- tp->t_flags &= ~XFS_TRANS_FREEZE_PROT;
+ tp->t_flags |= XFS_TRANS_NO_WRITECOUNT;
ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
tp->t_blk_res = tp->t_blk_res_used;
@@ -165,7 +123,7 @@ xfs_trans_dup(
* This does not do quota reservations. That typically is done by the
* caller afterwards.
*/
-int
+static int
xfs_trans_reserve(
struct xfs_trans *tp,
struct xfs_trans_res *resp,
@@ -219,7 +177,7 @@ xfs_trans_reserve(
resp->tr_logres,
resp->tr_logcount,
&tp->t_ticket, XFS_TRANSACTION,
- permanent, tp->t_type);
+ permanent);
}
if (error)
@@ -268,6 +226,42 @@ undo_blocks:
return error;
}
+int
+xfs_trans_alloc(
+ struct xfs_mount *mp,
+ struct xfs_trans_res *resp,
+ uint blocks,
+ uint rtextents,
+ uint flags,
+ struct xfs_trans **tpp)
+{
+ struct xfs_trans *tp;
+ int error;
+
+ if (!(flags & XFS_TRANS_NO_WRITECOUNT))
+ sb_start_intwrite(mp->m_super);
+
+ WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+ atomic_inc(&mp->m_active_trans);
+
+ tp = kmem_zone_zalloc(xfs_trans_zone,
+ (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP);
+ tp->t_magic = XFS_TRANS_HEADER_MAGIC;
+ tp->t_flags = flags;
+ tp->t_mountp = mp;
+ INIT_LIST_HEAD(&tp->t_items);
+ INIT_LIST_HEAD(&tp->t_busy);
+
+ error = xfs_trans_reserve(tp, resp, blocks, rtextents);
+ if (error) {
+ xfs_trans_cancel(tp);
+ return error;
+ }
+
+ *tpp = tp;
+ return 0;
+}
+
/*
* Record the indicated change to the given field for application
* to the file system's superblock when the transaction commits.
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index e7c49cf43fbc..9a462e892e4f 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -90,7 +90,6 @@ void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
*/
typedef struct xfs_trans {
unsigned int t_magic; /* magic number */
- unsigned int t_type; /* transaction type */
unsigned int t_log_res; /* amt of log space resvd */
unsigned int t_log_count; /* count for perm log res */
unsigned int t_blk_res; /* # of blocks resvd */
@@ -148,10 +147,9 @@ typedef struct xfs_trans {
/*
* XFS transaction mechanism exported interfaces.
*/
-xfs_trans_t *xfs_trans_alloc(struct xfs_mount *, uint);
-xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint, xfs_km_flags_t);
-int xfs_trans_reserve(struct xfs_trans *, struct xfs_trans_res *,
- uint, uint);
+int xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
+ uint blocks, uint rtextents, uint flags,
+ struct xfs_trans **tpp);
void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
struct xfs_buf *xfs_trans_get_buf_map(struct xfs_trans *tp,
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index d111f691f313..ea62245fee26 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -74,11 +74,12 @@ xfs_forget_acl(
}
static int
-xfs_xattr_set(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, const void *value, size_t size, int flags)
+xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, const void *value,
+ size_t size, int flags)
{
int xflags = handler->flags;
- struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ struct xfs_inode *ip = XFS_I(inode);
int error;
/* Convert Linux syscall to XFS internal ATTR flags */
@@ -92,7 +93,7 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *dentry,
error = xfs_attr_set(ip, (unsigned char *)name,
(void *)value, size, xflags);
if (!error)
- xfs_forget_acl(d_inode(dentry), name, xflags);
+ xfs_forget_acl(inode, name, xflags);
return error;
}
@@ -146,7 +147,7 @@ __xfs_xattr_put_listent(
arraytop = context->count + prefix_len + namelen + 1;
if (arraytop > context->firstu) {
context->count = -1; /* insufficient space */
- return 1;
+ return 0;
}
offset = (char *)context->alist + context->count;
strncpy(offset, prefix, prefix_len);
@@ -166,8 +167,7 @@ xfs_xattr_put_listent(
int flags,
unsigned char *name,
int namelen,
- int valuelen,
- unsigned char *value)
+ int valuelen)
{
char *prefix;
int prefix_len;
@@ -221,11 +221,15 @@ xfs_xattr_put_listent(
}
ssize_t
-xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
+xfs_vn_listxattr(
+ struct dentry *dentry,
+ char *data,
+ size_t size)
{
struct xfs_attr_list_context context;
struct attrlist_cursor_kern cursor = { 0 };
- struct inode *inode = d_inode(dentry);
+ struct inode *inode = d_inode(dentry);
+ int error;
/*
* First read the regular on-disk attributes.
@@ -239,7 +243,9 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
context.firstu = context.bufsize;
context.put_listent = xfs_xattr_put_listent;
- xfs_attr_list_int(&context);
+ error = xfs_attr_list_int(&context);
+ if (error)
+ return error;
if (context.count < 0)
return -ERANGE;
diff --git a/include/acpi/video.h b/include/acpi/video.h
index 70a41f742037..5731ccb42585 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -51,7 +51,8 @@ extern void acpi_video_set_dmi_backlight_type(enum acpi_backlight_type type);
*/
extern bool acpi_video_handles_brightness_key_presses(void);
extern int acpi_video_get_levels(struct acpi_device *device,
- struct acpi_video_device_brightness **dev_br);
+ struct acpi_video_device_brightness **dev_br,
+ int *pmax_level);
#else
static inline int acpi_video_register(void) { return 0; }
static inline void acpi_video_unregister(void) { return; }
@@ -72,7 +73,8 @@ static inline bool acpi_video_handles_brightness_key_presses(void)
return false;
}
static inline int acpi_video_get_levels(struct acpi_device *device,
- struct acpi_video_device_brightness **dev_br)
+ struct acpi_video_device_brightness **dev_br,
+ int *pmax_level)
{
return -ENODEV;
}
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 5d8ffa3e6f8c..c1cde3577551 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -7,10 +7,10 @@
static __always_inline int preempt_count(void)
{
- return current_thread_info()->preempt_count;
+ return READ_ONCE(current_thread_info()->preempt_count);
}
-static __always_inline int *preempt_count_ptr(void)
+static __always_inline volatile int *preempt_count_ptr(void)
{
return &current_thread_info()->preempt_count;
}
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 6bd05700d8c9..05f05f17a7c2 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -22,37 +22,33 @@
#include <asm-generic/qspinlock_types.h>
/**
+ * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+#ifndef queued_spin_unlock_wait
+extern void queued_spin_unlock_wait(struct qspinlock *lock);
+#endif
+
+/**
* queued_spin_is_locked - is the spinlock locked?
* @lock: Pointer to queued spinlock structure
* Return: 1 if it is locked, 0 otherwise
*/
+#ifndef queued_spin_is_locked
static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
{
/*
- * queued_spin_lock_slowpath() can ACQUIRE the lock before
- * issuing the unordered store that sets _Q_LOCKED_VAL.
- *
- * See both smp_cond_acquire() sites for more detail.
- *
- * This however means that in code like:
- *
- * spin_lock(A) spin_lock(B)
- * spin_unlock_wait(B) spin_is_locked(A)
- * do_something() do_something()
- *
- * Both CPUs can end up running do_something() because the store
- * setting _Q_LOCKED_VAL will pass through the loads in
- * spin_unlock_wait() and/or spin_is_locked().
+ * See queued_spin_unlock_wait().
*
- * Avoid this by issuing a full memory barrier between the spin_lock()
- * and the loads in spin_unlock_wait() and spin_is_locked().
- *
- * Note that regular mutual exclusion doesn't care about this
- * delayed store.
+ * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
+ * isn't immediately observable.
*/
- smp_mb();
- return atomic_read(&lock->val) & _Q_LOCKED_MASK;
+ return atomic_read(&lock->val);
}
+#endif
/**
* queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -122,21 +118,6 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
}
#endif
-/**
- * queued_spin_unlock_wait - wait until current lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-static inline void queued_spin_unlock_wait(struct qspinlock *lock)
-{
- /* See queued_spin_is_locked() */
- smp_mb();
- while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
- cpu_relax();
-}
-
#ifndef virt_spin_lock
static __always_inline bool virt_spin_lock(struct qspinlock *lock)
{
diff --git a/include/drm/drm_dp_dual_mode_helper.h b/include/drm/drm_dp_dual_mode_helper.h
new file mode 100644
index 000000000000..e8a9dfd0e055
--- /dev/null
+++ b/include/drm/drm_dp_dual_mode_helper.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef DRM_DP_DUAL_MODE_HELPER_H
+#define DRM_DP_DUAL_MODE_HELPER_H
+
+#include <linux/types.h>
+
+/*
+ * Optional for type 1 DVI adaptors
+ * Mandatory for type 1 HDMI and type 2 adaptors
+ */
+#define DP_DUAL_MODE_HDMI_ID 0x00 /* 00-0f */
+#define DP_DUAL_MODE_HDMI_ID_LEN 16
+/*
+ * Optional for type 1 adaptors
+ * Mandatory for type 2 adaptors
+ */
+#define DP_DUAL_MODE_ADAPTOR_ID 0x10
+#define DP_DUAL_MODE_REV_MASK 0x07
+#define DP_DUAL_MODE_REV_TYPE2 0x00
+#define DP_DUAL_MODE_TYPE_MASK 0xf0
+#define DP_DUAL_MODE_TYPE_TYPE2 0xa0
+#define DP_DUAL_MODE_IEEE_OUI 0x11 /* 11-13*/
+#define DP_DUAL_IEEE_OUI_LEN 3
+#define DP_DUAL_DEVICE_ID 0x14 /* 14-19 */
+#define DP_DUAL_DEVICE_ID_LEN 6
+#define DP_DUAL_MODE_HARDWARE_REV 0x1a
+#define DP_DUAL_MODE_FIRMWARE_MAJOR_REV 0x1b
+#define DP_DUAL_MODE_FIRMWARE_MINOR_REV 0x1c
+#define DP_DUAL_MODE_MAX_TMDS_CLOCK 0x1d
+#define DP_DUAL_MODE_I2C_SPEED_CAP 0x1e
+#define DP_DUAL_MODE_TMDS_OEN 0x20
+#define DP_DUAL_MODE_TMDS_DISABLE 0x01
+#define DP_DUAL_MODE_HDMI_PIN_CTRL 0x21
+#define DP_DUAL_MODE_CEC_ENABLE 0x01
+#define DP_DUAL_MODE_I2C_SPEED_CTRL 0x22
+
+struct i2c_adapter;
+
+ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter,
+ u8 offset, void *buffer, size_t size);
+ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter,
+ u8 offset, const void *buffer, size_t size);
+
+/**
+ * enum drm_dp_dual_mode_type - Type of the DP dual mode adaptor
+ * @DRM_DP_DUAL_MODE_NONE: No DP dual mode adaptor
+ * @DRM_DP_DUAL_MODE_UNKNOWN: Could be either none or type 1 DVI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE1_DVI: Type 1 DVI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE1_HDMI: Type 1 HDMI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE2_DVI: Type 2 DVI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE2_HDMI: Type 2 HDMI adaptor
+ */
+enum drm_dp_dual_mode_type {
+ DRM_DP_DUAL_MODE_NONE,
+ DRM_DP_DUAL_MODE_UNKNOWN,
+ DRM_DP_DUAL_MODE_TYPE1_DVI,
+ DRM_DP_DUAL_MODE_TYPE1_HDMI,
+ DRM_DP_DUAL_MODE_TYPE2_DVI,
+ DRM_DP_DUAL_MODE_TYPE2_HDMI,
+};
+
+enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(struct i2c_adapter *adapter);
+int drm_dp_dual_mode_max_tmds_clock(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter);
+int drm_dp_dual_mode_get_tmds_output(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter, bool *enabled);
+int drm_dp_dual_mode_set_tmds_output(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter, bool enable);
+const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type);
+
+#endif
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 9094599a1150..33466bfc6440 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -309,6 +309,7 @@
INTEL_VGA_DEVICE(0x5906, info), /* ULT GT1 */ \
INTEL_VGA_DEVICE(0x590E, info), /* ULX GT1 */ \
INTEL_VGA_DEVICE(0x5902, info), /* DT GT1 */ \
+ INTEL_VGA_DEVICE(0x5908, info), /* Halo GT1 */ \
INTEL_VGA_DEVICE(0x590B, info), /* Halo GT1 */ \
INTEL_VGA_DEVICE(0x590A, info) /* SRV GT1 */
@@ -322,15 +323,12 @@
INTEL_VGA_DEVICE(0x591D, info) /* WKS GT2 */
#define INTEL_KBL_GT3_IDS(info) \
+ INTEL_VGA_DEVICE(0x5923, info), /* ULT GT3 */ \
INTEL_VGA_DEVICE(0x5926, info), /* ULT GT3 */ \
- INTEL_VGA_DEVICE(0x592B, info), /* Halo GT3 */ \
- INTEL_VGA_DEVICE(0x592A, info) /* SRV GT3 */
+ INTEL_VGA_DEVICE(0x5927, info) /* ULT GT3 */
#define INTEL_KBL_GT4_IDS(info) \
- INTEL_VGA_DEVICE(0x5932, info), /* DT GT4 */ \
- INTEL_VGA_DEVICE(0x593B, info), /* Halo GT4 */ \
- INTEL_VGA_DEVICE(0x593A, info), /* SRV GT4 */ \
- INTEL_VGA_DEVICE(0x593D, info) /* WKS GT4 */
+ INTEL_VGA_DEVICE(0x593B, info) /* Halo GT4 */
#define INTEL_KBL_IDS(info) \
INTEL_KBL_GT1_IDS(info), \
diff --git a/include/dt-bindings/thermal/tegra124-soctherm.h b/include/dt-bindings/thermal/tegra124-soctherm.h
index 85aaf66690f9..729ab9fc325e 100644
--- a/include/dt-bindings/thermal/tegra124-soctherm.h
+++ b/include/dt-bindings/thermal/tegra124-soctherm.h
@@ -9,5 +9,6 @@
#define TEGRA124_SOCTHERM_SENSOR_MEM 1
#define TEGRA124_SOCTHERM_SENSOR_GPU 2
#define TEGRA124_SOCTHERM_SENSOR_PLLX 3
+#define TEGRA124_SOCTHERM_SENSOR_NUM 4
#endif
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index b651aed9dc6b..dda39d8fa189 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -24,9 +24,6 @@
#include <linux/workqueue.h>
struct arch_timer_kvm {
- /* Is the timer enabled */
- bool enabled;
-
/* Virtual offset */
cycle_t cntvoff;
};
@@ -53,15 +50,15 @@ struct arch_timer_cpu {
/* Timer IRQ */
struct kvm_irq_level irq;
- /* VGIC mapping */
- struct irq_phys_map *map;
-
/* Active IRQ state caching */
bool active_cleared_last;
+
+ /* Is the timer enabled */
+ bool enabled;
};
int kvm_timer_hyp_init(void);
-void kvm_timer_enable(struct kvm *kvm);
+int kvm_timer_enable(struct kvm_vcpu *vcpu);
void kvm_timer_init(struct kvm *kvm);
int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
const struct kvm_irq_level *irq);
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index fe389ac31489..92e7e97ca8ff 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -18,13 +18,13 @@
#ifndef __ASM_ARM_KVM_PMU_H
#define __ASM_ARM_KVM_PMU_H
-#ifdef CONFIG_KVM_ARM_PMU
-
#include <linux/perf_event.h>
#include <asm/perf_event.h>
#define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1)
+#ifdef CONFIG_KVM_ARM_PMU
+
struct kvm_pmc {
u8 idx; /* index into the pmu->pmc array */
struct perf_event *perf_event;
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index be6037aa703d..da0a524802cb 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -19,6 +19,10 @@
#ifndef __ASM_ARM_KVM_VGIC_H
#define __ASM_ARM_KVM_VGIC_H
+#ifdef CONFIG_KVM_NEW_VGIC
+#include <kvm/vgic/vgic.h>
+#else
+
#include <linux/kernel.h>
#include <linux/kvm.h>
#include <linux/irqreturn.h>
@@ -158,7 +162,6 @@ struct vgic_io_device {
struct irq_phys_map {
u32 virt_irq;
u32 phys_irq;
- u32 irq;
};
struct irq_phys_map_entry {
@@ -305,9 +308,6 @@ struct vgic_cpu {
unsigned long *active_shared;
unsigned long *pend_act_shared;
- /* Number of list registers on this CPU */
- int nr_lr;
-
/* CPU vif control registers for world switch */
union {
struct vgic_v2_cpu_if vgic_v2;
@@ -342,17 +342,18 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
bool level);
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
- struct irq_phys_map *map, bool level);
+ unsigned int virt_irq, bool level);
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
- int virt_irq, int irq);
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq);
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus))
#define vgic_ready(k) ((k)->arch.vgic.ready)
+#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
+ ((i) < (k)->arch.vgic.nr_irqs))
int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
@@ -370,4 +371,5 @@ static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
}
#endif
+#endif /* old VGIC include */
#endif
diff --git a/include/kvm/vgic/vgic.h b/include/kvm/vgic/vgic.h
new file mode 100644
index 000000000000..3fbd175265ae
--- /dev/null
+++ b/include/kvm/vgic/vgic.h
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_ARM_KVM_VGIC_VGIC_H
+#define __ASM_ARM_KVM_VGIC_VGIC_H
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/irqreturn.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <kvm/iodev.h>
+
+#define VGIC_V3_MAX_CPUS 255
+#define VGIC_V2_MAX_CPUS 8
+#define VGIC_NR_IRQS_LEGACY 256
+#define VGIC_NR_SGIS 16
+#define VGIC_NR_PPIS 16
+#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
+#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1)
+#define VGIC_MAX_SPI 1019
+#define VGIC_MAX_RESERVED 1023
+#define VGIC_MIN_LPI 8192
+
+enum vgic_type {
+ VGIC_V2, /* Good ol' GICv2 */
+ VGIC_V3, /* New fancy GICv3 */
+};
+
+/* same for all guests, as depending only on the _host's_ GIC model */
+struct vgic_global {
+ /* type of the host GIC */
+ enum vgic_type type;
+
+ /* Physical address of vgic virtual cpu interface */
+ phys_addr_t vcpu_base;
+
+ /* virtual control interface mapping */
+ void __iomem *vctrl_base;
+
+ /* Number of implemented list registers */
+ int nr_lr;
+
+ /* Maintenance IRQ number */
+ unsigned int maint_irq;
+
+ /* maximum number of VCPUs allowed (GICv2 limits us to 8) */
+ int max_gic_vcpus;
+
+ /* Only needed for the legacy KVM_CREATE_IRQCHIP */
+ bool can_emulate_gicv2;
+};
+
+extern struct vgic_global kvm_vgic_global_state;
+
+#define VGIC_V2_MAX_LRS (1 << 6)
+#define VGIC_V3_MAX_LRS 16
+#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
+
+enum vgic_irq_config {
+ VGIC_CONFIG_EDGE = 0,
+ VGIC_CONFIG_LEVEL
+};
+
+struct vgic_irq {
+ spinlock_t irq_lock; /* Protects the content of the struct */
+ struct list_head ap_list;
+
+ struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU
+ * SPIs and LPIs: The VCPU whose ap_list
+ * this is queued on.
+ */
+
+ struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should
+ * be sent to, as a result of the
+ * targets reg (v2) or the
+ * affinity reg (v3).
+ */
+
+ u32 intid; /* Guest visible INTID */
+ bool pending;
+ bool line_level; /* Level only */
+ bool soft_pending; /* Level only */
+ bool active; /* not used for LPIs */
+ bool enabled;
+ bool hw; /* Tied to HW IRQ */
+ u32 hwintid; /* HW INTID number */
+ union {
+ u8 targets; /* GICv2 target VCPUs mask */
+ u32 mpidr; /* GICv3 target VCPU */
+ };
+ u8 source; /* GICv2 SGIs only */
+ u8 priority;
+ enum vgic_irq_config config; /* Level or edge */
+};
+
+struct vgic_register_region;
+
+struct vgic_io_device {
+ gpa_t base_addr;
+ struct kvm_vcpu *redist_vcpu;
+ const struct vgic_register_region *regions;
+ int nr_regions;
+ struct kvm_io_device dev;
+};
+
+struct vgic_dist {
+ bool in_kernel;
+ bool ready;
+ bool initialized;
+
+ /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
+ u32 vgic_model;
+
+ int nr_spis;
+
+ /* TODO: Consider moving to global state */
+ /* Virtual control interface mapping */
+ void __iomem *vctrl_base;
+
+ /* base addresses in guest physical address space: */
+ gpa_t vgic_dist_base; /* distributor */
+ union {
+ /* either a GICv2 CPU interface */
+ gpa_t vgic_cpu_base;
+ /* or a number of GICv3 redistributor regions */
+ gpa_t vgic_redist_base;
+ };
+
+ /* distributor enabled */
+ bool enabled;
+
+ struct vgic_irq *spis;
+
+ struct vgic_io_device dist_iodev;
+ struct vgic_io_device *redist_iodevs;
+};
+
+struct vgic_v2_cpu_if {
+ u32 vgic_hcr;
+ u32 vgic_vmcr;
+ u32 vgic_misr; /* Saved only */
+ u64 vgic_eisr; /* Saved only */
+ u64 vgic_elrsr; /* Saved only */
+ u32 vgic_apr;
+ u32 vgic_lr[VGIC_V2_MAX_LRS];
+};
+
+struct vgic_v3_cpu_if {
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+ u32 vgic_hcr;
+ u32 vgic_vmcr;
+ u32 vgic_sre; /* Restored only, change ignored */
+ u32 vgic_misr; /* Saved only */
+ u32 vgic_eisr; /* Saved only */
+ u32 vgic_elrsr; /* Saved only */
+ u32 vgic_ap0r[4];
+ u32 vgic_ap1r[4];
+ u64 vgic_lr[VGIC_V3_MAX_LRS];
+#endif
+};
+
+struct vgic_cpu {
+ /* CPU vif control registers for world switch */
+ union {
+ struct vgic_v2_cpu_if vgic_v2;
+ struct vgic_v3_cpu_if vgic_v3;
+ };
+
+ unsigned int used_lrs;
+ struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
+
+ spinlock_t ap_list_lock; /* Protects the ap_list */
+
+ /*
+ * List of IRQs that this VCPU should consider because they are either
+ * Active or Pending (hence the name; AP list), or because they recently
+ * were one of the two and need to be migrated off this list to another
+ * VCPU.
+ */
+ struct list_head ap_list_head;
+
+ u64 live_lrs;
+};
+
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
+void kvm_vgic_early_init(struct kvm *kvm);
+int kvm_vgic_create(struct kvm *kvm, u32 type);
+void kvm_vgic_destroy(struct kvm *kvm);
+void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
+int kvm_vgic_map_resources(struct kvm *kvm);
+int kvm_vgic_hyp_init(void);
+
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+ bool level);
+int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+ bool level);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
+
+#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
+#define vgic_initialized(k) ((k)->arch.vgic.initialized)
+#define vgic_ready(k) ((k)->arch.vgic.ready)
+#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
+ ((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
+
+bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
+#else
+static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
+{
+}
+#endif
+
+/**
+ * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
+ *
+ * The host's GIC naturally limits the maximum amount of VCPUs a guest
+ * can use.
+ */
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+ return kvm_vgic_global_state.max_gic_vcpus;
+}
+
+#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 961a417d641e..e38e3fc13ea8 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -26,7 +26,6 @@
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <uapi/linux/audit.h>
-#include <linux/tty.h>
#define AUDIT_INO_UNSET ((unsigned long)-1)
#define AUDIT_DEV_UNSET ((dev_t)-1)
@@ -348,23 +347,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
return tsk->sessionid;
}
-static inline struct tty_struct *audit_get_tty(struct task_struct *tsk)
-{
- struct tty_struct *tty = NULL;
- unsigned long flags;
-
- spin_lock_irqsave(&tsk->sighand->siglock, flags);
- if (tsk->signal)
- tty = tty_kref_get(tsk->signal->tty);
- spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
- return tty;
-}
-
-static inline void audit_put_tty(struct tty_struct *tty)
-{
- tty_kref_put(tty);
-}
-
extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode);
extern void __audit_bprm(struct linux_binprm *bprm);
@@ -522,12 +504,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
{
return -1;
}
-static inline struct tty_struct *audit_get_tty(struct task_struct *tsk)
-{
- return NULL;
-}
-static inline void audit_put_tty(struct tty_struct *tty)
-{ }
static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
{ }
static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid,
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 846513c73606..a5ac2cad5cb7 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -587,7 +587,6 @@ struct mtd_info;
struct bcma_sflash {
bool present;
- u32 window;
u32 blocksize;
u16 numblocks;
u32 size;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 576e4639ca60..314b3caa701c 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -65,6 +65,7 @@ struct coredump_params {
unsigned long limit;
unsigned long mm_flags;
loff_t written;
+ loff_t pos;
};
/*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1fd8fdff2f81..3d9cf326574f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -768,6 +768,17 @@ static inline void rq_flush_dcache_pages(struct request *rq)
}
#endif
+#ifdef CONFIG_PRINTK
+#define vfs_msg(sb, level, fmt, ...) \
+ __vfs_msg(sb, level, fmt, ##__VA_ARGS__)
+#else
+#define vfs_msg(sb, level, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __vfs_msg(sb, "", " "); \
+} while (0)
+#endif
+
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
extern blk_qc_t generic_make_request(struct bio *bio);
@@ -1660,7 +1671,7 @@ struct block_device_operations {
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
long (*direct_access)(struct block_device *, sector_t, void __pmem **,
- pfn_t *);
+ pfn_t *, long);
unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing);
/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1680,6 +1691,8 @@ extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *);
extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *);
+extern int bdev_dax_supported(struct super_block *, int);
+extern bool bdev_dax_capable(struct block_device *);
#else /* CONFIG_BLOCK */
struct block_device;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8ee27b8afe81..0de4de6dd43e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -111,6 +111,31 @@ enum bpf_access_type {
BPF_WRITE = 2
};
+/* types of values stored in eBPF registers */
+enum bpf_reg_type {
+ NOT_INIT = 0, /* nothing was written into register */
+ UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */
+ PTR_TO_CTX, /* reg points to bpf_context */
+ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
+ PTR_TO_MAP_VALUE, /* reg points to map element value */
+ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
+ FRAME_PTR, /* reg == frame_pointer */
+ PTR_TO_STACK, /* reg == frame_pointer + imm */
+ CONST_IMM, /* constant integer value */
+
+ /* PTR_TO_PACKET represents:
+ * skb->data
+ * skb->data + imm
+ * skb->data + (u16) var
+ * skb->data + (u16) var + imm
+ * if (range > 0) then [ptr, ptr + range - off) is safe to access
+ * if (id > 0) means that some 'var' was added
+ * if (off > 0) menas that 'imm' was added
+ */
+ PTR_TO_PACKET,
+ PTR_TO_PACKET_END, /* skb->data + headlen */
+};
+
struct bpf_prog;
struct bpf_verifier_ops {
@@ -120,7 +145,8 @@ struct bpf_verifier_ops {
/* return true if 'size' wide access at offset 'off' within bpf_context
* with 'type' (read or write) is allowed
*/
- bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
+ bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type);
u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
@@ -238,6 +264,10 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd)
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
+
+static inline void bpf_prog_put_rcu(struct bpf_prog *prog)
+{
+}
#endif /* CONFIG_BPF_SYSCALL */
/* verifier prototypes for helper functions called from eBPF programs */
diff --git a/include/linux/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
index b827e066e55a..146507df8650 100644
--- a/include/linux/ceph/ceph_frag.h
+++ b/include/linux/ceph/ceph_frag.h
@@ -51,11 +51,11 @@ static inline __u32 ceph_frag_make_child(__u32 f, int by, int i)
return ceph_frag_make(newbits,
ceph_frag_value(f) | (i << (24 - newbits)));
}
-static inline int ceph_frag_is_leftmost(__u32 f)
+static inline bool ceph_frag_is_leftmost(__u32 f)
{
return ceph_frag_value(f) == 0;
}
-static inline int ceph_frag_is_rightmost(__u32 f)
+static inline bool ceph_frag_is_rightmost(__u32 f)
{
return ceph_frag_value(f) == ceph_frag_mask(f);
}
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 37f28bf55ce4..dfce616002ad 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -153,8 +153,9 @@ struct ceph_dir_layout {
/* watch-notify operations */
enum {
- WATCH_NOTIFY = 1, /* notifying watcher */
- WATCH_NOTIFY_COMPLETE = 2, /* notifier notified when done */
+ CEPH_WATCH_EVENT_NOTIFY = 1, /* notifying watcher */
+ CEPH_WATCH_EVENT_NOTIFY_COMPLETE = 2, /* notifier notified when done */
+ CEPH_WATCH_EVENT_DISCONNECT = 3, /* we were disconnected */
};
@@ -207,6 +208,8 @@ struct ceph_mon_subscribe_ack {
struct ceph_fsid fsid;
} __attribute__ ((packed));
+#define CEPH_FS_CLUSTER_ID_NONE -1
+
/*
* mdsmap flags
*/
@@ -344,6 +347,18 @@ extern const char *ceph_mds_op_name(int op);
#define CEPH_XATTR_REPLACE (1 << 1)
#define CEPH_XATTR_REMOVE (1 << 31)
+/*
+ * readdir request flags;
+ */
+#define CEPH_READDIR_REPLY_BITFLAGS (1<<0)
+
+/*
+ * readdir reply flags.
+ */
+#define CEPH_READDIR_FRAG_END (1<<0)
+#define CEPH_READDIR_FRAG_COMPLETE (1<<8)
+#define CEPH_READDIR_HASH_ORDER (1<<9)
+
union ceph_mds_request_args {
struct {
__le32 mask; /* CEPH_CAP_* */
@@ -361,6 +376,7 @@ union ceph_mds_request_args {
__le32 frag; /* which dir fragment */
__le32 max_entries; /* how many dentries to grab */
__le32 max_bytes;
+ __le16 flags;
} __attribute__ ((packed)) readdir;
struct {
__le32 mode;
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index a6ef9cc267ec..19e9932f3e77 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -47,7 +47,7 @@ static inline void ceph_decode_copy(void **p, void *pv, size_t n)
/*
* bounds check input.
*/
-static inline int ceph_has_room(void **p, void *end, size_t n)
+static inline bool ceph_has_room(void **p, void *end, size_t n)
{
return end >= *p && n <= end - *p;
}
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index db92a8d4926e..690985daad1c 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -180,6 +180,63 @@ static inline int calc_pages_for(u64 off, u64 len)
(off >> PAGE_SHIFT);
}
+/*
+ * These are not meant to be generic - an integer key is assumed.
+ */
+#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \
+static void insert_##name(struct rb_root *root, type *t) \
+{ \
+ struct rb_node **n = &root->rb_node; \
+ struct rb_node *parent = NULL; \
+ \
+ BUG_ON(!RB_EMPTY_NODE(&t->nodefld)); \
+ \
+ while (*n) { \
+ type *cur = rb_entry(*n, type, nodefld); \
+ \
+ parent = *n; \
+ if (t->keyfld < cur->keyfld) \
+ n = &(*n)->rb_left; \
+ else if (t->keyfld > cur->keyfld) \
+ n = &(*n)->rb_right; \
+ else \
+ BUG(); \
+ } \
+ \
+ rb_link_node(&t->nodefld, parent, n); \
+ rb_insert_color(&t->nodefld, root); \
+} \
+static void erase_##name(struct rb_root *root, type *t) \
+{ \
+ BUG_ON(RB_EMPTY_NODE(&t->nodefld)); \
+ rb_erase(&t->nodefld, root); \
+ RB_CLEAR_NODE(&t->nodefld); \
+}
+
+#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \
+static type *lookup_##name(struct rb_root *root, \
+ typeof(((type *)0)->keyfld) key) \
+{ \
+ struct rb_node *n = root->rb_node; \
+ \
+ while (n) { \
+ type *cur = rb_entry(n, type, nodefld); \
+ \
+ if (key < cur->keyfld) \
+ n = n->rb_left; \
+ else if (key > cur->keyfld) \
+ n = n->rb_right; \
+ else \
+ return cur; \
+ } \
+ \
+ return NULL; \
+}
+
+#define DEFINE_RB_FUNCS(name, type, keyfld, nodefld) \
+DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \
+DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)
+
extern struct kmem_cache *ceph_inode_cachep;
extern struct kmem_cache *ceph_cap_cachep;
extern struct kmem_cache *ceph_cap_flush_cachep;
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index e230e7ed60d3..e2a92df08b47 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -39,20 +39,31 @@ struct ceph_mon_request {
ceph_monc_request_func_t do_request;
};
+typedef void (*ceph_monc_callback_t)(struct ceph_mon_generic_request *);
+
/*
* ceph_mon_generic_request is being used for the statfs and
* mon_get_version requests which are being done a bit differently
* because we need to get data back to the caller
*/
struct ceph_mon_generic_request {
+ struct ceph_mon_client *monc;
struct kref kref;
u64 tid;
struct rb_node node;
int result;
- void *buf;
+
struct completion completion;
+ ceph_monc_callback_t complete_cb;
+ u64 private_data; /* r_tid/linger_id */
+
struct ceph_msg *request; /* original request */
struct ceph_msg *reply; /* and reply */
+
+ union {
+ struct ceph_statfs *st;
+ u64 newest;
+ } u;
};
struct ceph_mon_client {
@@ -77,7 +88,6 @@ struct ceph_mon_client {
/* pending generic requests */
struct rb_root generic_request_tree;
- int num_generic_requests;
u64 last_tid;
/* subs, indexed with CEPH_SUB_* */
@@ -86,6 +96,7 @@ struct ceph_mon_client {
bool want;
u32 have; /* epoch */
} subs[3];
+ int fs_cluster_id; /* "mdsmap.<id>" sub */
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_file;
@@ -116,16 +127,18 @@ extern const char *ceph_sub_str[];
bool ceph_monc_want_map(struct ceph_mon_client *monc, int sub, u32 epoch,
bool continuous);
void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch);
+void ceph_monc_renew_subs(struct ceph_mon_client *monc);
-extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
unsigned long timeout);
extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
struct ceph_statfs *buf);
-extern int ceph_monc_do_get_version(struct ceph_mon_client *monc,
- const char *what, u64 *newest);
+int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
+ u64 *newest);
+int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what,
+ ceph_monc_callback_t cb, u64 private_data);
extern int ceph_monc_open_session(struct ceph_mon_client *monc);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index cbf460927c42..1b3b6e155392 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -20,10 +20,11 @@ struct ceph_osd_client;
/*
* completion callback for async writepages
*/
-typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *,
- struct ceph_msg *);
+typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool);
+#define CEPH_HOMELESS_OSD -1
+
/* a given osd we're communicating with */
struct ceph_osd {
atomic_t o_ref;
@@ -32,16 +33,15 @@ struct ceph_osd {
int o_incarnation;
struct rb_node o_node;
struct ceph_connection o_con;
- struct list_head o_requests;
- struct list_head o_linger_requests;
+ struct rb_root o_requests;
+ struct rb_root o_linger_requests;
struct list_head o_osd_lru;
struct ceph_auth_handshake o_auth;
unsigned long lru_ttl;
- int o_marked_for_keepalive;
struct list_head o_keepalive_item;
+ struct mutex lock;
};
-
#define CEPH_OSD_SLAB_OPS 2
#define CEPH_OSD_MAX_OPS 16
@@ -104,76 +104,95 @@ struct ceph_osd_req_op {
struct ceph_osd_data response_data;
__u8 class_len;
__u8 method_len;
- __u8 argc;
+ u32 indata_len;
} cls;
struct {
u64 cookie;
- u64 ver;
- u32 prot_ver;
- u32 timeout;
- __u8 flag;
+ __u8 op; /* CEPH_OSD_WATCH_OP_ */
+ u32 gen;
} watch;
struct {
+ struct ceph_osd_data request_data;
+ } notify_ack;
+ struct {
+ u64 cookie;
+ struct ceph_osd_data request_data;
+ struct ceph_osd_data response_data;
+ } notify;
+ struct {
u64 expected_object_size;
u64 expected_write_size;
} alloc_hint;
};
};
+struct ceph_osd_request_target {
+ struct ceph_object_id base_oid;
+ struct ceph_object_locator base_oloc;
+ struct ceph_object_id target_oid;
+ struct ceph_object_locator target_oloc;
+
+ struct ceph_pg pgid;
+ u32 pg_num;
+ u32 pg_num_mask;
+ struct ceph_osds acting;
+ struct ceph_osds up;
+ int size;
+ int min_size;
+ bool sort_bitwise;
+
+ unsigned int flags; /* CEPH_OSD_FLAG_* */
+ bool paused;
+
+ int osd;
+};
+
/* an in-flight request */
struct ceph_osd_request {
u64 r_tid; /* unique for this client */
struct rb_node r_node;
- struct list_head r_req_lru_item;
- struct list_head r_osd_item;
- struct list_head r_linger_item;
- struct list_head r_linger_osd_item;
+ struct rb_node r_mc_node; /* map check */
struct ceph_osd *r_osd;
- struct ceph_pg r_pgid;
- int r_pg_osds[CEPH_PG_MAX_SIZE];
- int r_num_pg_osds;
+
+ struct ceph_osd_request_target r_t;
+#define r_base_oid r_t.base_oid
+#define r_base_oloc r_t.base_oloc
+#define r_flags r_t.flags
struct ceph_msg *r_request, *r_reply;
- int r_flags; /* any additional flags for the osd */
u32 r_sent; /* >0 if r_request is sending/sent */
/* request osd ops array */
unsigned int r_num_ops;
- /* these are updated on each send */
- __le32 *r_request_osdmap_epoch;
- __le32 *r_request_flags;
- __le64 *r_request_pool;
- void *r_request_pgid;
- __le32 *r_request_attempts;
- bool r_paused;
- struct ceph_eversion *r_request_reassert_version;
-
int r_result;
- int r_got_reply;
- int r_linger;
+ bool r_got_reply;
struct ceph_osd_client *r_osdc;
struct kref r_kref;
bool r_mempool;
- struct completion r_completion, r_safe_completion;
+ struct completion r_completion;
+ struct completion r_safe_completion; /* fsync waiter */
ceph_osdc_callback_t r_callback;
ceph_osdc_unsafe_callback_t r_unsafe_callback;
- struct ceph_eversion r_reassert_version;
struct list_head r_unsafe_item;
struct inode *r_inode; /* for use by callbacks */
void *r_priv; /* ditto */
- struct ceph_object_locator r_base_oloc;
- struct ceph_object_id r_base_oid;
- struct ceph_object_locator r_target_oloc;
- struct ceph_object_id r_target_oid;
-
- u64 r_snapid;
- unsigned long r_stamp; /* send OR check time */
+ /* set by submitter */
+ u64 r_snapid; /* for reads, CEPH_NOSNAP o/w */
+ struct ceph_snap_context *r_snapc; /* for writes */
+ struct timespec r_mtime; /* ditto */
+ u64 r_data_offset; /* ditto */
+ bool r_linger; /* don't resend on failure */
- struct ceph_snap_context *r_snapc; /* snap context for writes */
+ /* internal */
+ unsigned long r_stamp; /* jiffies, send or check time */
+ int r_attempts;
+ struct ceph_eversion r_replay_version; /* aka reassert_version */
+ u32 r_last_force_resend;
+ u32 r_map_dne_bound;
struct ceph_osd_req_op r_ops[];
};
@@ -182,44 +201,70 @@ struct ceph_request_redirect {
struct ceph_object_locator oloc;
};
-struct ceph_osd_event {
- u64 cookie;
- int one_shot;
+typedef void (*rados_watchcb2_t)(void *arg, u64 notify_id, u64 cookie,
+ u64 notifier_id, void *data, size_t data_len);
+typedef void (*rados_watcherrcb_t)(void *arg, u64 cookie, int err);
+
+struct ceph_osd_linger_request {
struct ceph_osd_client *osdc;
- void (*cb)(u64, u64, u8, void *);
- void *data;
- struct rb_node node;
- struct list_head osd_node;
+ u64 linger_id;
+ bool committed;
+ bool is_watch; /* watch or notify */
+
+ struct ceph_osd *osd;
+ struct ceph_osd_request *reg_req;
+ struct ceph_osd_request *ping_req;
+ unsigned long ping_sent;
+ unsigned long watch_valid_thru;
+ struct list_head pending_lworks;
+
+ struct ceph_osd_request_target t;
+ u32 last_force_resend;
+ u32 map_dne_bound;
+
+ struct timespec mtime;
+
struct kref kref;
-};
+ struct mutex lock;
+ struct rb_node node; /* osd */
+ struct rb_node osdc_node; /* osdc */
+ struct rb_node mc_node; /* map check */
+ struct list_head scan_item;
+
+ struct completion reg_commit_wait;
+ struct completion notify_finish_wait;
+ int reg_commit_error;
+ int notify_finish_error;
+ int last_error;
+
+ u32 register_gen;
+ u64 notify_id;
+
+ rados_watchcb2_t wcb;
+ rados_watcherrcb_t errcb;
+ void *data;
-struct ceph_osd_event_work {
- struct work_struct work;
- struct ceph_osd_event *event;
- u64 ver;
- u64 notify_id;
- u8 opcode;
+ struct page ***preply_pages;
+ size_t *preply_len;
};
struct ceph_osd_client {
struct ceph_client *client;
struct ceph_osdmap *osdmap; /* current map */
- struct rw_semaphore map_sem;
- struct completion map_waiters;
- u64 last_requested_map;
+ struct rw_semaphore lock;
- struct mutex request_mutex;
struct rb_root osds; /* osds */
struct list_head osd_lru; /* idle osds */
- u64 timeout_tid; /* tid of timeout triggering rq */
- u64 last_tid; /* tid of last request */
- struct rb_root requests; /* pending requests */
- struct list_head req_lru; /* in-flight lru */
- struct list_head req_unsent; /* unsent/need-resend queue */
- struct list_head req_notarget; /* map to no osd */
- struct list_head req_linger; /* lingering requests */
- int num_requests;
+ spinlock_t osd_lru_lock;
+ struct ceph_osd homeless_osd;
+ atomic64_t last_tid; /* tid of last request */
+ u64 last_linger_id;
+ struct rb_root linger_requests; /* lingering requests */
+ struct rb_root map_checks;
+ struct rb_root linger_map_checks;
+ atomic_t num_requests;
+ atomic_t num_homeless;
struct delayed_work timeout_work;
struct delayed_work osds_timeout_work;
#ifdef CONFIG_DEBUG_FS
@@ -231,13 +276,14 @@ struct ceph_osd_client {
struct ceph_msgpool msgpool_op;
struct ceph_msgpool msgpool_op_reply;
- spinlock_t event_lock;
- struct rb_root event_tree;
- u64 event_count;
-
struct workqueue_struct *notify_wq;
};
+static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag)
+{
+ return osdc->osdmap->flags & flag;
+}
+
extern int ceph_osdc_setup(void);
extern void ceph_osdc_cleanup(void);
@@ -271,9 +317,6 @@ extern void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
extern struct ceph_osd_data *osd_req_op_extent_osd_data(
struct ceph_osd_request *osd_req,
unsigned int which);
-extern struct ceph_osd_data *osd_req_op_cls_response_data(
- struct ceph_osd_request *osd_req,
- unsigned int which);
extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
unsigned int which,
@@ -309,9 +352,6 @@ extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
u16 opcode, const char *name, const void *value,
size_t size, u8 cmp_op, u8 cmp_mode);
-extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
- unsigned int which, u16 opcode,
- u64 cookie, u64 version, int flag);
extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
unsigned int which,
u64 expected_object_size,
@@ -322,11 +362,7 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *
unsigned int num_ops,
bool use_mempool,
gfp_t gfp_flags);
-
-extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off,
- struct ceph_snap_context *snapc,
- u64 snap_id,
- struct timespec *mtime);
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp);
extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
struct ceph_file_layout *layout,
@@ -338,9 +374,6 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
u32 truncate_seq, u64 truncate_size,
bool use_mempool);
-extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req);
-
extern void ceph_osdc_get_request(struct ceph_osd_request *req);
extern void ceph_osdc_put_request(struct ceph_osd_request *req);
@@ -353,6 +386,7 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc);
+void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc);
extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
struct ceph_vino vino,
@@ -371,11 +405,33 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
struct timespec *mtime,
struct page **pages, int nr_pages);
-/* watch/notify events */
-extern int ceph_osdc_create_event(struct ceph_osd_client *osdc,
- void (*event_cb)(u64, u64, u8, void *),
- void *data, struct ceph_osd_event **pevent);
-extern void ceph_osdc_cancel_event(struct ceph_osd_event *event);
-extern void ceph_osdc_put_event(struct ceph_osd_event *event);
+/* watch/notify */
+struct ceph_osd_linger_request *
+ceph_osdc_watch(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ rados_watchcb2_t wcb,
+ rados_watcherrcb_t errcb,
+ void *data);
+int ceph_osdc_unwatch(struct ceph_osd_client *osdc,
+ struct ceph_osd_linger_request *lreq);
+
+int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ u64 notify_id,
+ u64 cookie,
+ void *payload,
+ size_t payload_len);
+int ceph_osdc_notify(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ void *payload,
+ size_t payload_len,
+ u32 timeout,
+ struct page ***preply_pages,
+ size_t *preply_len);
+int ceph_osdc_watch_check(struct ceph_osd_client *osdc,
+ struct ceph_osd_linger_request *lreq);
#endif
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index e55c08bc3a96..9ccf4dbe55f8 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -24,21 +24,29 @@ struct ceph_pg {
uint32_t seed;
};
-#define CEPH_POOL_FLAG_HASHPSPOOL 1
+int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs);
+
+#define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id
+ together */
+#define CEPH_POOL_FLAG_FULL (1ULL << 1) /* pool is full */
struct ceph_pg_pool_info {
struct rb_node node;
s64 id;
- u8 type;
+ u8 type; /* CEPH_POOL_TYPE_* */
u8 size;
+ u8 min_size;
u8 crush_ruleset;
u8 object_hash;
+ u32 last_force_request_resend;
u32 pg_num, pgp_num;
int pg_num_mask, pgp_num_mask;
s64 read_tier;
s64 write_tier; /* wins for read+write ops */
- u64 flags;
+ u64 flags; /* CEPH_POOL_FLAG_* */
char *name;
+
+ bool was_full; /* for handle_one_map() */
};
static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
@@ -57,6 +65,22 @@ struct ceph_object_locator {
s64 pool;
};
+static inline void ceph_oloc_init(struct ceph_object_locator *oloc)
+{
+ oloc->pool = -1;
+}
+
+static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
+{
+ return oloc->pool == -1;
+}
+
+static inline void ceph_oloc_copy(struct ceph_object_locator *dest,
+ const struct ceph_object_locator *src)
+{
+ dest->pool = src->pool;
+}
+
/*
* Maximum supported by kernel client object name length
*
@@ -64,11 +88,47 @@ struct ceph_object_locator {
*/
#define CEPH_MAX_OID_NAME_LEN 100
+/*
+ * 51-char inline_name is long enough for all cephfs and all but one
+ * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be
+ * arbitrarily long (~PAGE_SIZE). It's done once during rbd map; all
+ * other rbd requests fit into inline_name.
+ *
+ * Makes ceph_object_id 64 bytes on 64-bit.
+ */
+#define CEPH_OID_INLINE_LEN 52
+
+/*
+ * Both inline and external buffers have space for a NUL-terminator,
+ * which is carried around. It's not required though - RADOS object
+ * names don't have to be NUL-terminated and may contain NULs.
+ */
struct ceph_object_id {
- char name[CEPH_MAX_OID_NAME_LEN];
+ char *name;
+ char inline_name[CEPH_OID_INLINE_LEN];
int name_len;
};
+static inline void ceph_oid_init(struct ceph_object_id *oid)
+{
+ oid->name = oid->inline_name;
+ oid->name_len = 0;
+}
+
+static inline bool ceph_oid_empty(const struct ceph_object_id *oid)
+{
+ return oid->name == oid->inline_name && !oid->name_len;
+}
+
+void ceph_oid_copy(struct ceph_object_id *dest,
+ const struct ceph_object_id *src);
+__printf(2, 3)
+void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...);
+__printf(3, 4)
+int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
+ const char *fmt, ...);
+void ceph_oid_destroy(struct ceph_object_id *oid);
+
struct ceph_pg_mapping {
struct rb_node node;
struct ceph_pg pgid;
@@ -87,7 +147,6 @@ struct ceph_pg_mapping {
struct ceph_osdmap {
struct ceph_fsid fsid;
u32 epoch;
- u32 mkfs_epoch;
struct ceph_timespec created, modified;
u32 flags; /* CEPH_OSDMAP_* */
@@ -113,52 +172,23 @@ struct ceph_osdmap {
int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3];
};
-static inline void ceph_oid_set_name(struct ceph_object_id *oid,
- const char *name)
-{
- int len;
-
- len = strlen(name);
- if (len > sizeof(oid->name)) {
- WARN(1, "ceph_oid_set_name '%s' len %d vs %zu, truncating\n",
- name, len, sizeof(oid->name));
- len = sizeof(oid->name);
- }
-
- memcpy(oid->name, name, len);
- oid->name_len = len;
-}
-
-static inline void ceph_oid_copy(struct ceph_object_id *dest,
- struct ceph_object_id *src)
-{
- BUG_ON(src->name_len > sizeof(dest->name));
- memcpy(dest->name, src->name, src->name_len);
- dest->name_len = src->name_len;
-}
-
-static inline int ceph_osd_exists(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd)
{
return osd >= 0 && osd < map->max_osd &&
(map->osd_state[osd] & CEPH_OSD_EXISTS);
}
-static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_is_up(struct ceph_osdmap *map, int osd)
{
return ceph_osd_exists(map, osd) &&
(map->osd_state[osd] & CEPH_OSD_UP);
}
-static inline int ceph_osd_is_down(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd)
{
return !ceph_osd_is_up(map, osd);
}
-static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
-{
- return map && (map->flags & flag);
-}
-
extern char *ceph_osdmap_state_str(char *str, int len, int state);
extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);
@@ -192,28 +222,59 @@ static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
return 0;
}
+struct ceph_osdmap *ceph_osdmap_alloc(void);
extern struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end);
-extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
- struct ceph_osdmap *map,
- struct ceph_messenger *msgr);
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+ struct ceph_osdmap *map);
extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
+struct ceph_osds {
+ int osds[CEPH_PG_MAX_SIZE];
+ int size;
+ int primary; /* id, NOT index */
+};
+
+static inline void ceph_osds_init(struct ceph_osds *set)
+{
+ set->size = 0;
+ set->primary = -1;
+}
+
+void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src);
+
+bool ceph_is_new_interval(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting,
+ const struct ceph_osds *old_up,
+ const struct ceph_osds *new_up,
+ int old_size,
+ int new_size,
+ int old_min_size,
+ int new_min_size,
+ u32 old_pg_num,
+ u32 new_pg_num,
+ bool old_sort_bitwise,
+ bool new_sort_bitwise,
+ const struct ceph_pg *pgid);
+bool ceph_osds_changed(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting,
+ bool any_change);
+
/* calculate mapping of a file extent to an object */
extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u64 off, u64 len,
u64 *bno, u64 *oxoff, u64 *oxlen);
-/* calculate mapping of object to a placement group */
-extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
- struct ceph_object_locator *oloc,
- struct ceph_object_id *oid,
- struct ceph_pg *pg_out);
-
-extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
- struct ceph_pg pgid,
- int *osds, int *primary);
-extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
- struct ceph_pg pgid);
+int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ struct ceph_pg *raw_pgid);
+
+void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *raw_pgid,
+ struct ceph_osds *up,
+ struct ceph_osds *acting);
+int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *raw_pgid);
extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map,
u64 id);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 2f822dca1046..5c0da61cb763 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -114,8 +114,8 @@ struct ceph_object_layout {
* compound epoch+version, used by storage layer to serialize mutations
*/
struct ceph_eversion {
- __le32 epoch;
__le64 version;
+ __le32 epoch;
} __attribute__ ((packed));
/*
@@ -153,6 +153,11 @@ extern const char *ceph_osd_state_name(int s);
#define CEPH_OSDMAP_NOIN (1<<8) /* block osd auto mark-in */
#define CEPH_OSDMAP_NOBACKFILL (1<<9) /* block osd backfill */
#define CEPH_OSDMAP_NORECOVER (1<<10) /* block osd recovery and backfill */
+#define CEPH_OSDMAP_NOSCRUB (1<<11) /* block periodic scrub */
+#define CEPH_OSDMAP_NODEEP_SCRUB (1<<12) /* block periodic deep-scrub */
+#define CEPH_OSDMAP_NOTIERAGENT (1<<13) /* disable tiering agent */
+#define CEPH_OSDMAP_NOREBALANCE (1<<14) /* block osd backfill unless pg is degraded */
+#define CEPH_OSDMAP_SORTBITWISE (1<<15) /* use bitwise hobject_t sort */
/*
* The error code to return when an OSD can't handle a write
@@ -389,6 +394,13 @@ enum {
CEPH_OSD_FLAG_SKIPRWLOCKS = 0x10000, /* skip rw locks */
CEPH_OSD_FLAG_IGNORE_OVERLAY = 0x20000, /* ignore pool overlay */
CEPH_OSD_FLAG_FLUSH = 0x40000, /* this is part of flush */
+ CEPH_OSD_FLAG_MAP_SNAP_CLONE = 0x80000, /* map snap direct to clone id */
+ CEPH_OSD_FLAG_ENFORCE_SNAPC = 0x100000, /* use snapc provided even if
+ pool uses pool snaps */
+ CEPH_OSD_FLAG_REDIRECTED = 0x200000, /* op has been redirected */
+ CEPH_OSD_FLAG_KNOWN_REDIR = 0x400000, /* redirect bit is authoritative */
+ CEPH_OSD_FLAG_FULL_TRY = 0x800000, /* try op despite full flag */
+ CEPH_OSD_FLAG_FULL_FORCE = 0x1000000, /* force op despite full flag */
};
enum {
@@ -415,7 +427,17 @@ enum {
CEPH_OSD_CMPXATTR_MODE_U64 = 2
};
-#define RADOS_NOTIFY_VER 1
+enum {
+ CEPH_OSD_WATCH_OP_UNWATCH = 0,
+ CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1,
+ /* note: use only ODD ids to prevent pre-giant code from
+ interpreting the op as UNWATCH */
+ CEPH_OSD_WATCH_OP_WATCH = 3,
+ CEPH_OSD_WATCH_OP_RECONNECT = 5,
+ CEPH_OSD_WATCH_OP_PING = 7,
+};
+
+const char *ceph_osd_watch_op_name(int o);
/*
* an individual object operation. each may be accompanied by some data
@@ -450,10 +472,14 @@ struct ceph_osd_op {
} __attribute__ ((packed)) snap;
struct {
__le64 cookie;
- __le64 ver;
- __u8 flag; /* 0 = unwatch, 1 = watch */
+ __le64 ver; /* no longer used */
+ __u8 op; /* CEPH_OSD_WATCH_OP_* */
+ __le32 gen; /* registration generation */
} __attribute__ ((packed)) watch;
struct {
+ __le64 cookie;
+ } __attribute__ ((packed)) notify;
+ struct {
__le64 offset, length;
__le64 src_offset;
} __attribute__ ((packed)) clonerange;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 0c72204c75fc..fb39d5add173 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -25,7 +25,7 @@
#define CLK_SET_PARENT_GATE BIT(1) /* must be gated across re-parent */
#define CLK_SET_RATE_PARENT BIT(2) /* propagate rate change up one level */
#define CLK_IGNORE_UNUSED BIT(3) /* do not gate even if unused */
-#define CLK_IS_ROOT BIT(4) /* Deprecated: Don't use */
+ /* unused */
#define CLK_IS_BASIC BIT(5) /* Basic clk, can't do a to_clk_foo() */
#define CLK_GET_RATE_NOCACHE BIT(6) /* do not use the cached clk rate */
#define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 786ad32631a6..07b83d32f66c 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -152,6 +152,8 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev);
extern int cpuidle_play_dead(void);
extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
+static inline struct cpuidle_device *cpuidle_get_device(void)
+{return __this_cpu_read(cpuidle_devices); }
#else
static inline void disable_cpuidle(void) { }
static inline bool cpuidle_not_available(struct cpuidle_driver *drv,
@@ -187,6 +189,7 @@ static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
static inline int cpuidle_play_dead(void) {return -ENODEV; }
static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
struct cpuidle_device *dev) {return NULL; }
+static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
#endif
#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND)
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 982a6c4a62f3..43d5f0b799c7 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -3,45 +3,62 @@
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/radix-tree.h>
#include <asm/pgtable.h>
+/* We use lowest available exceptional entry bit for locking */
+#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+
ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
get_block_t, dio_iodone_t, int flags);
-int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+ pgoff_t index, bool wake_all);
#ifdef CONFIG_FS_DAX
struct page *read_dax_sector(struct block_device *bdev, sector_t n);
+void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index);
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+ unsigned int offset, unsigned int length);
#else
static inline struct page *read_dax_sector(struct block_device *bdev,
sector_t n)
{
return ERR_PTR(-ENXIO);
}
+/* Shouldn't ever be called when dax is disabled. */
+static inline void dax_unlock_mapping_entry(struct address_space *mapping,
+ pgoff_t index)
+{
+ BUG();
+}
+static inline int __dax_zero_page_range(struct block_device *bdev,
+ sector_t sector, unsigned int offset, unsigned int length)
+{
+ return -ENXIO;
+}
#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
+ unsigned int flags, get_block_t);
int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
+ unsigned int flags, get_block_t);
#else
static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags, get_block_t gb,
- dax_iodone_t di)
+ pmd_t *pmd, unsigned int flags, get_block_t gb)
{
return VM_FAULT_FALLBACK;
}
#define __dax_pmd_fault dax_pmd_fault
#endif
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod)
+#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb)
+#define __dax_mkwrite(vma, vmf, gb) __dax_fault(vma, vmf, gb)
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index f8506e8dd4d4..f53fa055021a 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -10,6 +10,7 @@
#include <linux/cache.h>
#include <linux/rcupdate.h>
#include <linux/lockref.h>
+#include <linux/stringhash.h>
struct path;
struct vfsmount;
@@ -52,9 +53,6 @@ struct qstr {
};
#define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
-#define hashlen_hash(hashlen) ((u32) (hashlen))
-#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
-#define hashlen_create(hash,len) (((u64)(len)<<32)|(u32)(hash))
struct dentry_stat_t {
long nr_dentry;
@@ -65,29 +63,6 @@ struct dentry_stat_t {
};
extern struct dentry_stat_t dentry_stat;
-/* Name hashing routines. Initial hash value */
-/* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
-#define init_name_hash() 0
-
-/* partial hash update function. Assume roughly 4 bits per character */
-static inline unsigned long
-partial_name_hash(unsigned long c, unsigned long prevhash)
-{
- return (prevhash + (c << 4) + (c >> 4)) * 11;
-}
-
-/*
- * Finally: cut down the number of bits to a int value (and try to avoid
- * losing bits)
- */
-static inline unsigned long end_name_hash(unsigned long hash)
-{
- return (unsigned int) hash;
-}
-
-/* Compute the hash for a name string. */
-extern unsigned int full_name_hash(const unsigned char *, unsigned int);
-
/*
* Try to keep struct dentry aligned on 64 byte cachelines (this will
* give reasonable cacheline footprint with larger lines without the
@@ -237,6 +212,7 @@ struct dentry_operations {
#define DCACHE_OP_REAL 0x08000000
#define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */
+#define DCACHE_DENTRY_CURSOR 0x20000000
extern seqlock_t rename_lock;
@@ -600,5 +576,17 @@ static inline struct inode *vfs_select_inode(struct dentry *dentry,
return inode;
}
+/**
+ * d_real_inode - Return the real inode
+ * @dentry: The dentry to query
+ *
+ * If dentry is on an union/overlay, then return the underlying, real inode.
+ * Otherwise return d_inode().
+ */
+static inline struct inode *d_real_inode(struct dentry *dentry)
+{
+ return d_backing_inode(d_real(dentry));
+}
+
#endif /* __LINUX_DCACHE_H */
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 5871f292b596..277ab9af9ac2 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,13 +15,12 @@
#include <linux/errno.h>
-struct pts_fs_info;
-
#ifdef CONFIG_UNIX98_PTYS
-/* Look up a pts fs info and get a ref to it */
-struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
-void devpts_put_ref(struct pts_fs_info *);
+struct pts_fs_info;
+
+struct pts_fs_info *devpts_acquire(struct file *);
+void devpts_release(struct pts_fs_info *);
int devpts_new_index(struct pts_fs_info *);
void devpts_kill_index(struct pts_fs_info *, int);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 3fe90d494edb..4551c6f2a6c4 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -112,19 +112,24 @@ struct dma_buf_ops {
* @file: file pointer used for sharing buffers across, and for refcounting.
* @attachments: list of dma_buf_attachment that denotes all devices attached.
* @ops: dma_buf_ops associated with this buffer object.
+ * @lock: used internally to serialize list manipulation, attach/detach and vmap/unmap
+ * @vmapping_counter: used internally to refcnt the vmaps
+ * @vmap_ptr: the current vmap ptr if vmapping_counter > 0
* @exp_name: name of the exporter; useful for debugging.
* @owner: pointer to exporter module; used for refcounting when exporter is a
* kernel module.
* @list_node: node for dma_buf accounting and debugging.
* @priv: exporter specific private data for this buffer object.
* @resv: reservation object linked to this dma-buf
+ * @poll: for userspace poll support
+ * @cb_excl: for userspace poll support
+ * @cb_shared: for userspace poll support
*/
struct dma_buf {
size_t size;
struct file *file;
struct list_head attachments;
const struct dma_buf_ops *ops;
- /* mutex to serialize list manipulation, attach/detach and vmap/unmap */
struct mutex lock;
unsigned vmapping_counter;
void *vmap_ptr;
@@ -188,9 +193,11 @@ struct dma_buf_export_info {
/**
* helper macro for exporters; zeros and fills in most common values
+ *
+ * @name: export-info name
*/
-#define DEFINE_DMA_BUF_EXPORT_INFO(a) \
- struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \
+#define DEFINE_DMA_BUF_EXPORT_INFO(name) \
+ struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \
.owner = THIS_MODULE }
/**
diff --git a/include/linux/efi.h b/include/linux/efi.h
index c2db3ca22217..f196dd0b0f2f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1005,7 +1005,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm,
/* Iterate through an efi_memory_map */
#define for_each_efi_memory_desc_in_map(m, md) \
for ((md) = (m)->map; \
- (md) <= (efi_memory_desc_t *)((m)->map_end - (m)->desc_size); \
+ ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
(md) = (void *)(md) + (m)->desc_size)
/**
diff --git a/include/linux/err.h b/include/linux/err.h
index 56762ab41713..1e3558845e4c 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -18,7 +18,7 @@
#ifndef __ASSEMBLY__
-#define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO)
+#define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO)
static inline void * __must_check ERR_PTR(long error)
{
diff --git a/include/linux/errno.h b/include/linux/errno.h
index 89627b9187f9..7ce9fb1b7d28 100644
--- a/include/linux/errno.h
+++ b/include/linux/errno.h
@@ -28,5 +28,6 @@
#define EBADTYPE 527 /* Type not supported by server */
#define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */
#define EIOCBQUEUED 529 /* iocb queued, will get completion event */
+#define ERECALLCONFLICT 530 /* conflict with recalled state */
#endif
diff --git a/include/linux/export.h b/include/linux/export.h
index 96e45ea463e7..2f9ccbe6a639 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -38,7 +38,7 @@ extern struct module __this_module;
#ifdef CONFIG_MODULES
-#ifndef __GENKSYMS__
+#if defined(__KERNEL__) && !defined(__GENKSYMS__)
#ifdef CONFIG_MODVERSIONS
/* Mark the CRC weak since genksyms apparently decides not to
* generate a checksums for some symbols */
@@ -53,7 +53,7 @@ extern struct module __this_module;
#endif
/* For every exported symbol, place a struct in the __ksymtab section */
-#define __EXPORT_SYMBOL(sym, sec) \
+#define ___EXPORT_SYMBOL(sym, sec) \
extern typeof(sym) sym; \
__CRC_SYMBOL(sym, sec) \
static const char __kstrtab_##sym[] \
@@ -65,6 +65,35 @@ extern struct module __this_module;
__attribute__((section("___ksymtab" sec "+" #sym), unused)) \
= { (unsigned long)&sym, __kstrtab_##sym }
+#if defined(__KSYM_DEPS__)
+
+/*
+ * For fine grained build dependencies, we want to tell the build system
+ * about each possible exported symbol even if they're not actually exported.
+ * We use a string pattern that is unlikely to be valid code that the build
+ * system filters out from the preprocessor output (see ksym_dep_filter
+ * in scripts/Kbuild.include).
+ */
+#define __EXPORT_SYMBOL(sym, sec) === __KSYM_##sym ===
+
+#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+
+#include <linux/kconfig.h>
+#include <generated/autoksyms.h>
+
+#define __EXPORT_SYMBOL(sym, sec) \
+ __cond_export_sym(sym, sec, config_enabled(__KSYM_##sym))
+#define __cond_export_sym(sym, sec, conf) \
+ ___cond_export_sym(sym, sec, conf)
+#define ___cond_export_sym(sym, sec, enabled) \
+ __cond_export_sym_##enabled(sym, sec)
+#define __cond_export_sym_1(sym, sec) ___EXPORT_SYMBOL(sym, sec)
+#define __cond_export_sym_0(sym, sec) /* nothing */
+
+#else
+#define __EXPORT_SYMBOL ___EXPORT_SYMBOL
+#endif
+
#define EXPORT_SYMBOL(sym) \
__EXPORT_SYMBOL(sym, "")
diff --git a/include/linux/fence.h b/include/linux/fence.h
index 2b17698b60b8..2056e9fd0138 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -49,6 +49,8 @@ struct fence_cb;
* @timestamp: Timestamp when the fence was signaled.
* @status: Optional, only valid if < 0, must be set before calling
* fence_signal, indicates that the fence has completed with an error.
+ * @child_list: list of children fences
+ * @active_list: list of active fences
*
* the flags member must be manipulated and read using the appropriate
* atomic ops (bit_*), so taking the spinlock will not be needed most
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5f61431d8673..dd288148a6b1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -74,7 +74,6 @@ typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
-typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
@@ -1730,7 +1729,8 @@ struct inode_operations {
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
- int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
+ int (*setxattr) (struct dentry *, struct inode *,
+ const char *, const void *, size_t, int);
ssize_t (*getxattr) (struct dentry *, struct inode *,
const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 604e1526cd00..13ba552e6c09 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -241,7 +241,7 @@ struct fscache_cache_ops {
/* check the consistency between the backing cache and the FS-Cache
* cookie */
- bool (*check_consistency)(struct fscache_operation *op);
+ int (*check_consistency)(struct fscache_operation *op);
/* store the updated auxiliary data on an object */
void (*update_object)(struct fscache_object *object);
diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
index 0023088b253b..3f9778cbc79d 100644
--- a/include/linux/fsl_ifc.h
+++ b/include/linux/fsl_ifc.h
@@ -39,6 +39,10 @@
#define FSL_IFC_VERSION_MASK 0x0F0F0000
#define FSL_IFC_VERSION_1_0_0 0x01000000
#define FSL_IFC_VERSION_1_1_0 0x01010000
+#define FSL_IFC_VERSION_2_0_0 0x02000000
+
+#define PGOFFSET_64K (64*1024)
+#define PGOFFSET_4K (4*1024)
/*
* CSPR - Chip Select Property Register
@@ -723,20 +727,26 @@ struct fsl_ifc_nand {
__be32 nand_evter_en;
u32 res17[0x2];
__be32 nand_evter_intr_en;
- u32 res18[0x2];
+ __be32 nand_vol_addr_stat;
+ u32 res18;
__be32 nand_erattr0;
__be32 nand_erattr1;
u32 res19[0x10];
__be32 nand_fsr;
- u32 res20;
- __be32 nand_eccstat[4];
- u32 res21[0x20];
+ u32 res20[0x3];
+ __be32 nand_eccstat[6];
+ u32 res21[0x1c];
__be32 nanndcr;
u32 res22[0x2];
__be32 nand_autoboot_trgr;
u32 res23;
__be32 nand_mdr;
- u32 res24[0x5C];
+ u32 res24[0x1C];
+ __be32 nand_dll_lowcfg0;
+ __be32 nand_dll_lowcfg1;
+ u32 res25;
+ __be32 nand_dll_lowstat;
+ u32 res26[0x3c];
};
/*
@@ -771,13 +781,12 @@ struct fsl_ifc_gpcm {
__be32 gpcm_erattr1;
__be32 gpcm_erattr2;
__be32 gpcm_stat;
- u32 res4[0x1F3];
};
/*
* IFC Controller Registers
*/
-struct fsl_ifc_regs {
+struct fsl_ifc_global {
__be32 ifc_rev;
u32 res1[0x2];
struct {
@@ -803,21 +812,26 @@ struct fsl_ifc_regs {
} ftim_cs[FSL_IFC_BANK_COUNT];
u32 res9[0x30];
__be32 rb_stat;
- u32 res10[0x2];
+ __be32 rb_map;
+ __be32 wb_map;
__be32 ifc_gcr;
- u32 res11[0x2];
+ u32 res10[0x2];
__be32 cm_evter_stat;
- u32 res12[0x2];
+ u32 res11[0x2];
__be32 cm_evter_en;
- u32 res13[0x2];
+ u32 res12[0x2];
__be32 cm_evter_intr_en;
- u32 res14[0x2];
+ u32 res13[0x2];
__be32 cm_erattr0;
__be32 cm_erattr1;
- u32 res15[0x2];
+ u32 res14[0x2];
__be32 ifc_ccr;
__be32 ifc_csr;
- u32 res16[0x2EB];
+ __be32 ddr_ccr_low;
+};
+
+
+struct fsl_ifc_runtime {
struct fsl_ifc_nand ifc_nand;
struct fsl_ifc_nor ifc_nor;
struct fsl_ifc_gpcm ifc_gpcm;
@@ -831,7 +845,8 @@ extern int fsl_ifc_find(phys_addr_t addr_base);
struct fsl_ifc_ctrl {
/* device info */
struct device *dev;
- struct fsl_ifc_regs __iomem *regs;
+ struct fsl_ifc_global __iomem *gregs;
+ struct fsl_ifc_runtime __iomem *rregs;
int irq;
int nand_irq;
spinlock_t lock;
diff --git a/include/linux/hash.h b/include/linux/hash.h
index 79c52fa81cac..ad6fa21d977b 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -3,92 +3,94 @@
/* Fast hashing routine for ints, longs and pointers.
(C) 2002 Nadia Yvette Chambers, IBM */
-/*
- * Knuth recommends primes in approximately golden ratio to the maximum
- * integer representable by a machine word for multiplicative hashing.
- * Chuck Lever verified the effectiveness of this technique:
- * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
- *
- * These primes are chosen to be bit-sparse, that is operations on
- * them can use shifts and additions instead of multiplications for
- * machines where multiplications are slow.
- */
-
#include <asm/types.h>
#include <linux/compiler.h>
-/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
-#define GOLDEN_RATIO_PRIME_32 0x9e370001UL
-/* 2^63 + 2^61 - 2^57 + 2^54 - 2^51 - 2^18 + 1 */
-#define GOLDEN_RATIO_PRIME_64 0x9e37fffffffc0001UL
-
+/*
+ * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and
+ * fs/inode.c. It's not actually prime any more (the previous primes
+ * were actively bad for hashing), but the name remains.
+ */
#if BITS_PER_LONG == 32
-#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_PRIME_32
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32
#define hash_long(val, bits) hash_32(val, bits)
#elif BITS_PER_LONG == 64
#define hash_long(val, bits) hash_64(val, bits)
-#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_PRIME_64
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64
#else
#error Wordsize not 32 or 64
#endif
/*
- * The above primes are actively bad for hashing, since they are
- * too sparse. The 32-bit one is mostly ok, the 64-bit one causes
- * real problems. Besides, the "prime" part is pointless for the
- * multiplicative hash.
+ * This hash multiplies the input by a large odd number and takes the
+ * high bits. Since multiplication propagates changes to the most
+ * significant end only, it is essential that the high bits of the
+ * product be used for the hash value.
+ *
+ * Chuck Lever verified the effectiveness of this technique:
+ * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
*
* Although a random odd number will do, it turns out that the golden
* ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice
- * properties.
+ * properties. (See Knuth vol 3, section 6.4, exercise 9.)
*
- * These are the negative, (1 - phi) = (phi^2) = (3 - sqrt(5))/2.
- * (See Knuth vol 3, section 6.4, exercise 9.)
+ * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2,
+ * which is very slightly easier to multiply by and makes no
+ * difference to the hash distribution.
*/
#define GOLDEN_RATIO_32 0x61C88647
#define GOLDEN_RATIO_64 0x61C8864680B583EBull
-static __always_inline u64 hash_64(u64 val, unsigned int bits)
-{
- u64 hash = val;
+#ifdef CONFIG_HAVE_ARCH_HASH
+/* This header may use the GOLDEN_RATIO_xx constants */
+#include <asm/hash.h>
+#endif
-#if BITS_PER_LONG == 64
- hash = hash * GOLDEN_RATIO_64;
-#else
- /* Sigh, gcc can't optimise this alone like it does for 32 bits. */
- u64 n = hash;
- n <<= 18;
- hash -= n;
- n <<= 33;
- hash -= n;
- n <<= 3;
- hash += n;
- n <<= 3;
- hash -= n;
- n <<= 4;
- hash += n;
- n <<= 2;
- hash += n;
+/*
+ * The _generic versions exist only so lib/test_hash.c can compare
+ * the arch-optimized versions with the generic.
+ *
+ * Note that if you change these, any <asm/hash.h> that aren't updated
+ * to match need to have their HAVE_ARCH_* define values updated so the
+ * self-test will not false-positive.
+ */
+#ifndef HAVE_ARCH__HASH_32
+#define __hash_32 __hash_32_generic
#endif
+static inline u32 __hash_32_generic(u32 val)
+{
+ return val * GOLDEN_RATIO_32;
+}
+#ifndef HAVE_ARCH_HASH_32
+#define hash_32 hash_32_generic
+#endif
+static inline u32 hash_32_generic(u32 val, unsigned int bits)
+{
/* High bits are more random, so use them. */
- return hash >> (64 - bits);
+ return __hash_32(val) >> (32 - bits);
}
-static inline u32 hash_32(u32 val, unsigned int bits)
+#ifndef HAVE_ARCH_HASH_64
+#define hash_64 hash_64_generic
+#endif
+static __always_inline u32 hash_64_generic(u64 val, unsigned int bits)
{
- /* On some cpus multiply is faster, on others gcc will do shifts */
- u32 hash = val * GOLDEN_RATIO_PRIME_32;
-
- /* High bits are more random, so use them. */
- return hash >> (32 - bits);
+#if BITS_PER_LONG == 64
+ /* 64x64-bit multiply is efficient on all 64-bit processors */
+ return val * GOLDEN_RATIO_64 >> (64 - bits);
+#else
+ /* Hash 64 bits using only 32x32-bit multiply. */
+ return hash_32((u32)val ^ __hash_32(val >> 32), bits);
+#endif
}
-static inline unsigned long hash_ptr(const void *ptr, unsigned int bits)
+static inline u32 hash_ptr(const void *ptr, unsigned int bits)
{
return hash_long((unsigned long)ptr, bits);
}
+/* This really should be called fold32_ptr; it does no hashing to speak of. */
static inline u32 hash32_ptr(const void *ptr)
{
unsigned long val = (unsigned long)ptr;
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index d029ffac0d69..99403b19092f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -223,6 +223,8 @@ struct st_sensor_settings {
* @get_irq_data_ready: Function to get the IRQ used for data ready signal.
* @tf: Transfer function structure used by I/O operations.
* @tb: Transfer buffers and mutex used by I/O operations.
+ * @hw_irq_trigger: if we're using the hardware interrupt on the sensor.
+ * @hw_timestamp: Latest timestamp from the interrupt handler, when in use.
*/
struct st_sensor_data {
struct device *dev;
@@ -247,6 +249,9 @@ struct st_sensor_data {
const struct st_sensor_transfer_function *tf;
struct st_sensor_transfer_buffer tb;
+
+ bool hw_irq_trigger;
+ s64 hw_timestamp;
};
#ifdef CONFIG_IIO_BUFFER
@@ -260,7 +265,8 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
const struct iio_trigger_ops *trigger_ops);
void st_sensors_deallocate_trigger(struct iio_dev *indio_dev);
-
+int st_sensors_validate_device(struct iio_trigger *trig,
+ struct iio_dev *indio_dev);
#else
static inline int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
const struct iio_trigger_ops *trigger_ops)
@@ -271,6 +277,7 @@ static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev)
{
return;
}
+#define st_sensors_validate_device NULL
#endif
int st_sensors_init_sensor(struct iio_dev *indio_dev,
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 7c27fa1030e8..feb04ea20f11 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -52,6 +52,12 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
+void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);
+
+int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
+ struct inet_diag_msg *r, int ext,
+ struct user_namespace *user_ns);
+
extern int inet_diag_register(const struct inet_diag_handler *handler);
extern void inet_diag_unregister(const struct inet_diag_handler *handler);
#endif /* _INET_DIAG_H_ */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f2cb8d45513d..f8834f820ec2 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -190,7 +190,7 @@ extern struct task_group root_task_group;
#define INIT_TASK(tsk) \
{ \
.state = 0, \
- .stack = &init_thread_info, \
+ .stack = init_stack, \
.usage = ATOMIC_INIT(2), \
.flags = PF_KTHREAD, \
.prio = MAX_PRIO-20, \
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 92f7177db2ce..f27bb2c62fca 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -19,8 +19,21 @@
/* iova structure */
struct iova {
struct rb_node node;
- unsigned long pfn_hi; /* IOMMU dish out addr hi */
- unsigned long pfn_lo; /* IOMMU dish out addr lo */
+ unsigned long pfn_hi; /* Highest allocated pfn */
+ unsigned long pfn_lo; /* Lowest allocated pfn */
+};
+
+struct iova_magazine;
+struct iova_cpu_rcache;
+
+#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */
+#define MAX_GLOBAL_MAGS 32 /* magazines per bin */
+
+struct iova_rcache {
+ spinlock_t lock;
+ unsigned long depot_size;
+ struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+ struct iova_cpu_rcache __percpu *cpu_rcaches;
};
/* holds all the iova translations for a domain */
@@ -31,6 +44,7 @@ struct iova_domain {
unsigned long granule; /* pfn granularity for this domain */
unsigned long start_pfn; /* Lower limit for this domain */
unsigned long dma_32bit_pfn;
+ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */
};
static inline unsigned long iova_size(struct iova *iova)
@@ -78,6 +92,10 @@ void __free_iova(struct iova_domain *iovad, struct iova *iova);
struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
unsigned long limit_pfn,
bool size_aligned);
+void free_iova_fast(struct iova_domain *iovad, unsigned long pfn,
+ unsigned long size);
+unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
+ unsigned long limit_pfn);
struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
unsigned long pfn_hi);
void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
@@ -87,5 +105,6 @@ struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
void put_iova_domain(struct iova_domain *iovad);
struct iova *split_and_remove_iova(struct iova_domain *iovad,
struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi);
+void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
#endif
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 9e6fdd33bdb2..dc493e0f0ff7 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -273,6 +273,12 @@
#define ICH_LR_ACTIVE_BIT (1ULL << 63)
#define ICH_LR_PHYS_ID_SHIFT 32
#define ICH_LR_PHYS_ID_MASK (0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PRIORITY_SHIFT 48
+
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID (0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT (10)
+#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT)
#define ICH_MISR_EOI (1 << 0)
#define ICH_MISR_U (1 << 1)
@@ -299,12 +305,12 @@
#define ICC_SGI1R_AFFINITY_1_SHIFT 16
#define ICC_SGI1R_AFFINITY_1_MASK (0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
#define ICC_SGI1R_SGI_ID_SHIFT 24
-#define ICC_SGI1R_SGI_ID_MASK (0xff << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_SGI_ID_MASK (0xfULL << ICC_SGI1R_SGI_ID_SHIFT)
#define ICC_SGI1R_AFFINITY_2_SHIFT 32
-#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT)
#define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40
#define ICC_SGI1R_AFFINITY_3_SHIFT 48
-#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT)
#include <asm/arch_gicv3.h>
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 9c940263ca23..fd051855539b 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -33,6 +33,7 @@
#define GIC_DIST_CTRL 0x000
#define GIC_DIST_CTR 0x004
+#define GIC_DIST_IIDR 0x008
#define GIC_DIST_IGROUP 0x080
#define GIC_DIST_ENABLE_SET 0x100
#define GIC_DIST_ENABLE_CLEAR 0x180
@@ -76,6 +77,7 @@
#define GICH_LR_VIRTUALID (0x3ff << 0)
#define GICH_LR_PHYSID_CPUID_SHIFT (10)
#define GICH_LR_PHYSID_CPUID (0x3ff << GICH_LR_PHYSID_CPUID_SHIFT)
+#define GICH_LR_PRIORITY_SHIFT 23
#define GICH_LR_STATE (3 << 28)
#define GICH_LR_PENDING_BIT (1 << 28)
#define GICH_LR_ACTIVE_BIT (1 << 29)
diff --git a/include/linux/isa.h b/include/linux/isa.h
index 5ab85281230b..f2d0258414cf 100644
--- a/include/linux/isa.h
+++ b/include/linux/isa.h
@@ -6,6 +6,7 @@
#define __LINUX_ISA_H
#include <linux/device.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
struct isa_driver {
@@ -22,13 +23,13 @@ struct isa_driver {
#define to_isa_driver(x) container_of((x), struct isa_driver, driver)
-#ifdef CONFIG_ISA
+#ifdef CONFIG_ISA_BUS_API
int isa_register_driver(struct isa_driver *, unsigned int);
void isa_unregister_driver(struct isa_driver *);
#else
static inline int isa_register_driver(struct isa_driver *d, unsigned int i)
{
- return 0;
+ return -ENODEV;
}
static inline void isa_unregister_driver(struct isa_driver *d)
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index fd1083c46c61..efb232c5f668 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -403,11 +403,19 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
/* Flags in jbd_inode->i_flags */
#define __JI_COMMIT_RUNNING 0
-/* Commit of the inode data in progress. We use this flag to protect us from
+#define __JI_WRITE_DATA 1
+#define __JI_WAIT_DATA 2
+
+/*
+ * Commit of the inode data in progress. We use this flag to protect us from
* concurrent deletion of inode. We cannot use reference to inode for this
* since we cannot afford doing last iput() on behalf of kjournald
*/
#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+/* Write allocated dirty buffers in this inode before commit */
+#define JI_WRITE_DATA (1 << __JI_WRITE_DATA)
+/* Wait for outstanding data writes for this inode before commit */
+#define JI_WAIT_DATA (1 << __JI_WAIT_DATA)
/**
* struct jbd_inode is the structure linking inodes in ordered mode
@@ -781,9 +789,6 @@ jbd2_time_diff(unsigned long start, unsigned long end)
* @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the
* number that will fit in j_blocksize
* @j_last_sync_writer: most recent pid which did a synchronous write
- * @j_history: Buffer storing the transactions statistics history
- * @j_history_max: Maximum number of transactions in the statistics history
- * @j_history_cur: Current number of transactions in the statistics history
* @j_history_lock: Protect the transactions statistics history
* @j_proc_entry: procfs entry for the jbd statistics directory
* @j_stats: Overall statistics
@@ -1270,7 +1275,8 @@ extern int jbd2_journal_clear_err (journal_t *);
extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
extern int jbd2_journal_force_commit(journal_t *);
extern int jbd2_journal_force_commit_nested(journal_t *);
-extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode);
+extern int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode);
extern int jbd2_journal_begin_ordered_truncate(journal_t *journal,
struct jbd2_inode *inode, loff_t new_size);
extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 0536524bb9eb..68904469fba1 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -117,13 +117,18 @@ struct module;
#include <linux/atomic.h>
+#ifdef HAVE_JUMP_LABEL
+
static inline int static_key_count(struct static_key *key)
{
- return atomic_read(&key->enabled);
+ /*
+ * -1 means the first static_key_slow_inc() is in progress.
+ * static_key_enabled() must return true, so return 1 here.
+ */
+ int n = atomic_read(&key->enabled);
+ return n >= 0 ? n : 1;
}
-#ifdef HAVE_JUMP_LABEL
-
#define JUMP_TYPE_FALSE 0UL
#define JUMP_TYPE_TRUE 1UL
#define JUMP_TYPE_MASK 1UL
@@ -162,6 +167,11 @@ extern void jump_label_apply_nops(struct module *mod);
#else /* !HAVE_JUMP_LABEL */
+static inline int static_key_count(struct static_key *key)
+{
+ return atomic_read(&key->enabled);
+}
+
static __always_inline void jump_label_init(void)
{
static_key_initialized = true;
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 611927f5870d..ac4b3c46a84d 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -59,14 +59,13 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object);
void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags);
void kasan_kfree_large(const void *ptr);
-void kasan_kfree(void *ptr);
+void kasan_poison_kfree(void *ptr);
void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size,
gfp_t flags);
void kasan_krealloc(const void *object, size_t new_size, gfp_t flags);
void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags);
bool kasan_slab_free(struct kmem_cache *s, void *object);
-void kasan_poison_slab_free(struct kmem_cache *s, void *object);
struct kasan_cache {
int alloc_meta_offset;
@@ -76,6 +75,9 @@ struct kasan_cache {
int kasan_module_alloc(void *addr, size_t size);
void kasan_free_shadow(const struct vm_struct *vm);
+size_t ksize(const void *);
+static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
+
#else /* CONFIG_KASAN */
static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
@@ -102,7 +104,7 @@ static inline void kasan_poison_object_data(struct kmem_cache *cache,
static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {}
static inline void kasan_kfree_large(const void *ptr) {}
-static inline void kasan_kfree(void *ptr) {}
+static inline void kasan_poison_kfree(void *ptr) {}
static inline void kasan_kmalloc(struct kmem_cache *s, const void *object,
size_t size, gfp_t flags) {}
static inline void kasan_krealloc(const void *object, size_t new_size,
@@ -114,11 +116,12 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object)
{
return false;
}
-static inline void kasan_poison_slab_free(struct kmem_cache *s, void *object) {}
static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
static inline void kasan_free_shadow(const struct vm_struct *vm) {}
+static inline void kasan_unpoison_slab(const void *ptr) { }
+
#endif /* CONFIG_KASAN */
#endif /* LINUX_KASAN_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b1fa8f11c95b..1c9c973a7dd9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -412,6 +412,8 @@ struct kvm {
#endif
long tlbs_dirty;
struct list_head devices;
+ struct dentry *debugfs_dentry;
+ struct kvm_stat_data **debugfs_stat_data;
};
#define kvm_err(fmt, ...) \
@@ -991,6 +993,11 @@ enum kvm_stat_kind {
KVM_STAT_VCPU,
};
+struct kvm_stat_data {
+ int offset;
+ struct kvm *kvm;
+};
+
struct kvm_stats_debugfs_item {
const char *name;
int offset;
diff --git a/include/linux/leds.h b/include/linux/leds.h
index d2b13066e781..e5e7f2e80a54 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -42,15 +42,16 @@ struct led_classdev {
#define LED_UNREGISTERING (1 << 1)
/* Upper 16 bits reflect control information */
#define LED_CORE_SUSPENDRESUME (1 << 16)
-#define LED_BLINK_ONESHOT (1 << 17)
-#define LED_BLINK_ONESHOT_STOP (1 << 18)
-#define LED_BLINK_INVERT (1 << 19)
-#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 20)
-#define LED_BLINK_DISABLE (1 << 21)
-#define LED_SYSFS_DISABLE (1 << 22)
-#define LED_DEV_CAP_FLASH (1 << 23)
-#define LED_HW_PLUGGABLE (1 << 24)
-#define LED_PANIC_INDICATOR (1 << 25)
+#define LED_BLINK_SW (1 << 17)
+#define LED_BLINK_ONESHOT (1 << 18)
+#define LED_BLINK_ONESHOT_STOP (1 << 19)
+#define LED_BLINK_INVERT (1 << 20)
+#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 21)
+#define LED_BLINK_DISABLE (1 << 22)
+#define LED_SYSFS_DISABLE (1 << 23)
+#define LED_DEV_CAP_FLASH (1 << 24)
+#define LED_HW_PLUGGABLE (1 << 25)
+#define LED_PANIC_INDICATOR (1 << 26)
/* Set LED brightness level
* Must not sleep. Use brightness_set_blocking for drivers
@@ -72,8 +73,8 @@ struct led_classdev {
* and if both are zero then a sensible default should be chosen.
* The call should adjust the timings in that case and if it can't
* match the values specified exactly.
- * Deactivate blinking again when the brightness is set to a fixed
- * value via the brightness_set() callback.
+ * Deactivate blinking again when the brightness is set to LED_OFF
+ * via the brightness_set() callback.
*/
int (*blink_set)(struct led_classdev *led_cdev,
unsigned long *delay_on,
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 20d8a5d4d133..5145620ba48a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -182,7 +182,7 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
+extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
#else
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index a677c2bd485c..64184d27e3cd 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -50,9 +50,11 @@ enum {
EC_MSG_TX_TRAILER_BYTES,
EC_MSG_RX_PROTO_BYTES = 3,
- /* Max length of messages */
- EC_MSG_BYTES = EC_PROTO2_MAX_PARAM_SIZE +
+ /* Max length of messages for proto 2*/
+ EC_PROTO2_MSG_BYTES = EC_PROTO2_MAX_PARAM_SIZE +
EC_MSG_TX_PROTO_BYTES,
+
+ EC_MAX_MSG_BYTES = 64 * 1024,
};
/*
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index c18a4c19d6fc..ce9230af09c2 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -171,7 +171,7 @@ static inline int da9052_group_read(struct da9052 *da9052, unsigned char reg,
static inline int da9052_group_write(struct da9052 *da9052, unsigned char reg,
unsigned reg_cnt, unsigned char *val)
{
- int ret;
+ int ret = 0;
int i;
for (i = 0; i < reg_cnt; i++) {
diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h
index 8f9fc3d26e6d..8e95cd87cd74 100644
--- a/include/linux/mfd/twl6040.h
+++ b/include/linux/mfd/twl6040.h
@@ -134,6 +134,7 @@
#define TWL6040_HFDACENA (1 << 0)
#define TWL6040_HFPGAENA (1 << 1)
#define TWL6040_HFDRVENA (1 << 4)
+#define TWL6040_HFSWENA (1 << 6)
/* VIBCTLL/R (0x18/0x1A) fields */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 80dec87a94f8..d46a0e7f144d 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -466,6 +466,7 @@ enum {
enum {
MLX4_INTERFACE_STATE_UP = 1 << 0,
MLX4_INTERFACE_STATE_DELETION = 1 << 1,
+ MLX4_INTERFACE_STATE_SHUTDOWN = 1 << 2,
};
#define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 035abdf62cfe..73a48479892d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1240,8 +1240,6 @@ struct mlx5_destroy_psv_out {
u8 rsvd[8];
};
-#define MLX5_CMD_OP_MAX 0x920
-
enum {
VPORT_STATE_DOWN = 0x0,
VPORT_STATE_UP = 0x1,
@@ -1369,6 +1367,12 @@ enum mlx5_cap_type {
#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap)
+#define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
+ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
+
+#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \
+ MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap)
+
#define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
MLX5_GET(flow_table_eswitch_cap, \
mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9a05cd7e5890..e955a2859009 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -205,7 +205,8 @@ enum {
MLX5_CMD_OP_ALLOC_FLOW_COUNTER = 0x939,
MLX5_CMD_OP_DEALLOC_FLOW_COUNTER = 0x93a,
MLX5_CMD_OP_QUERY_FLOW_COUNTER = 0x93b,
- MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c
+ MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c,
+ MLX5_CMD_OP_MAX
};
struct mlx5_ifc_flow_table_fields_supported_bits {
@@ -500,7 +501,9 @@ struct mlx5_ifc_e_switch_cap_bits {
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert_if_not_exist[0x1];
u8 vport_cvlan_insert_overwrite[0x1];
- u8 reserved_at_5[0x1b];
+ u8 reserved_at_5[0x19];
+ u8 nic_vport_node_guid_modify[0x1];
+ u8 nic_vport_port_guid_modify[0x1];
u8 reserved_at_20[0x7e0];
};
@@ -4583,7 +4586,10 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
};
struct mlx5_ifc_modify_nic_vport_field_select_bits {
- u8 reserved_at_0[0x19];
+ u8 reserved_at_0[0x16];
+ u8 node_guid[0x1];
+ u8 port_guid[0x1];
+ u8 reserved_at_18[0x1];
u8 mtu[0x1];
u8 change_event[0x1];
u8 promisc[0x1];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 64221027bf1f..ab310819ac36 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -172,6 +172,7 @@ enum {
enum {
MLX5_FENCE_MODE_NONE = 0 << 5,
MLX5_FENCE_MODE_INITIATOR_SMALL = 1 << 5,
+ MLX5_FENCE_MODE_FENCE = 2 << 5,
MLX5_FENCE_MODE_STRONG_ORDERING = 3 << 5,
MLX5_FENCE_MODE_SMALL_AND_FENCE = 4 << 5,
};
@@ -460,10 +461,9 @@ struct mlx5_core_qp {
};
struct mlx5_qp_path {
- u8 fl;
+ u8 fl_free_ar;
u8 rsvd3;
- u8 free_ar;
- u8 pkey_index;
+ __be16 pkey_index;
u8 rsvd0;
u8 grh_mlid;
__be16 rlid;
@@ -560,6 +560,7 @@ struct mlx5_modify_qp_mbox_in {
__be32 optparam;
u8 rsvd0[4];
struct mlx5_qp_context ctx;
+ u8 rsvd2[16];
};
struct mlx5_modify_qp_mbox_out {
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 301da4a5e6bf..6c16c198f680 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -50,6 +50,8 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
u64 *system_image_guid);
int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
+int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+ u32 vport, u64 node_guid);
int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
u16 *qkey_viol_cntr);
int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2835d598d258..ece042dfe23c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -303,6 +303,12 @@ struct vm_fault {
* is set (which is also implied by
* VM_FAULT_ERROR).
*/
+ void *entry; /* ->fault handler can alternatively
+ * return locked DAX entry. In that
+ * case handler should return
+ * VM_FAULT_DAX_LOCKED and fill in
+ * entry here.
+ */
/* for ->map_pages() only */
pgoff_t max_pgoff; /* map pages for offset from pgoff till
* max_pgoff inclusive */
@@ -596,7 +602,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
}
void do_set_pte(struct vm_area_struct *vma, unsigned long address,
- struct page *page, pte_t *pte, bool write, bool anon, bool old);
+ struct page *page, pte_t *pte, bool write, bool anon);
#endif
/*
@@ -1076,6 +1082,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */
+#define VM_FAULT_DAX_LOCKED 0x1000 /* ->fault has locked DAX entry */
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
@@ -2011,7 +2018,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {}
#endif
/* These take the mm semaphore themselves */
-extern unsigned long __must_check vm_brk(unsigned long, unsigned long);
+extern int __must_check vm_brk(unsigned long, unsigned long);
extern int vm_munmap(unsigned long, size_t);
extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
unsigned long, unsigned long,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d553855503e6..ca3e517980a0 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -514,7 +514,9 @@ struct mm_struct {
#ifdef CONFIG_HUGETLB_PAGE
atomic_long_t hugetlb_usage;
#endif
+#ifdef CONFIG_MMU
struct work_struct async_put_work;
+#endif
};
static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 85800b48241f..45cde8cd39f2 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -329,6 +329,7 @@ struct mmc_host {
unsigned int can_retune:1; /* re-tuning can be used */
unsigned int doing_retune:1; /* re-tuning in progress */
unsigned int retune_now:1; /* do re-tuning at next req */
+ unsigned int retune_paused:1; /* re-tuning is temporarily disabled */
int rescan_disable; /* disable card detection */
int rescan_entered; /* used with nonremovable devices */
@@ -526,4 +527,7 @@ static inline void mmc_retune_recheck(struct mmc_host *host)
host->retune_now = 1;
}
+void mmc_retune_pause(struct mmc_host *host);
+void mmc_retune_unpause(struct mmc_host *host);
+
#endif /* LINUX_MMC_HOST_H */
diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h
index c8be32e9fc49..ad3c3488073c 100644
--- a/include/linux/mtd/fsmc.h
+++ b/include/linux/mtd/fsmc.h
@@ -103,24 +103,6 @@
#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ)
-/*
- * There are 13 bytes of ecc for every 512 byte block in FSMC version 8
- * and it has to be read consecutively and immediately after the 512
- * byte data block for hardware to generate the error bit offsets
- * Managing the ecc bytes in the following way is easier. This way is
- * similar to oobfree structure maintained already in u-boot nand driver
- */
-#define MAX_ECCPLACE_ENTRIES 32
-
-struct fsmc_nand_eccplace {
- uint8_t offset;
- uint8_t length;
-};
-
-struct fsmc_eccplace {
- struct fsmc_nand_eccplace eccplace[MAX_ECCPLACE_ENTRIES];
-};
-
struct fsmc_nand_timings {
uint8_t tclr;
uint8_t tar;
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 5e0eb7ccabd4..3aa56e3104bb 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -122,18 +122,13 @@
#endif
#ifdef CONFIG_MTD_MAP_BANK_WIDTH_32
-# ifdef map_bankwidth
-# undef map_bankwidth
-# define map_bankwidth(map) ((map)->bankwidth)
-# undef map_bankwidth_is_large
-# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8)
-# undef map_words
-# define map_words(map) map_calc_words(map)
-# else
-# define map_bankwidth(map) 32
-# define map_bankwidth_is_large(map) (1)
-# define map_words(map) map_calc_words(map)
-# endif
+/* always use indirect access for 256-bit to preserve kernel stack */
+# undef map_bankwidth
+# define map_bankwidth(map) ((map)->bankwidth)
+# undef map_bankwidth_is_large
+# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8)
+# undef map_words
+# define map_words(map) map_calc_words(map)
#define map_bankwidth_is_32(map) (map_bankwidth(map) == 32)
#undef MAX_MAP_BANKWIDTH
#define MAX_MAP_BANKWIDTH 32
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index ef9fea4fc400..29a170612203 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -96,16 +96,35 @@ struct mtd_oob_ops {
#define MTD_MAX_OOBFREE_ENTRIES_LARGE 32
#define MTD_MAX_ECCPOS_ENTRIES_LARGE 640
+/**
+ * struct mtd_oob_region - oob region definition
+ * @offset: region offset
+ * @length: region length
+ *
+ * This structure describes a region of the OOB area, and is used
+ * to retrieve ECC or free bytes sections.
+ * Each section is defined by an offset within the OOB area and a
+ * length.
+ */
+struct mtd_oob_region {
+ u32 offset;
+ u32 length;
+};
+
/*
- * Internal ECC layout control structure. For historical reasons, there is a
- * similar, smaller struct nand_ecclayout_user (in mtd-abi.h) that is retained
- * for export to user-space via the ECCGETLAYOUT ioctl.
- * nand_ecclayout should be expandable in the future simply by the above macros.
+ * struct mtd_ooblayout_ops - NAND OOB layout operations
+ * @ecc: function returning an ECC region in the OOB area.
+ * Should return -ERANGE if %section exceeds the total number of
+ * ECC sections.
+ * @free: function returning a free region in the OOB area.
+ * Should return -ERANGE if %section exceeds the total number of
+ * free sections.
*/
-struct nand_ecclayout {
- __u32 eccbytes;
- __u32 eccpos[MTD_MAX_ECCPOS_ENTRIES_LARGE];
- struct nand_oobfree oobfree[MTD_MAX_OOBFREE_ENTRIES_LARGE];
+struct mtd_ooblayout_ops {
+ int (*ecc)(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobecc);
+ int (*free)(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobfree);
};
struct module; /* only needed for owner field in mtd_info */
@@ -166,8 +185,8 @@ struct mtd_info {
const char *name;
int index;
- /* ECC layout structure pointer - read only! */
- struct nand_ecclayout *ecclayout;
+ /* OOB layout description */
+ const struct mtd_ooblayout_ops *ooblayout;
/* the ecc step size. */
unsigned int ecc_step_size;
@@ -253,6 +272,30 @@ struct mtd_info {
int usecount;
};
+int mtd_ooblayout_ecc(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobecc);
+int mtd_ooblayout_find_eccregion(struct mtd_info *mtd, int eccbyte,
+ int *section,
+ struct mtd_oob_region *oobregion);
+int mtd_ooblayout_get_eccbytes(struct mtd_info *mtd, u8 *eccbuf,
+ const u8 *oobbuf, int start, int nbytes);
+int mtd_ooblayout_set_eccbytes(struct mtd_info *mtd, const u8 *eccbuf,
+ u8 *oobbuf, int start, int nbytes);
+int mtd_ooblayout_free(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobfree);
+int mtd_ooblayout_get_databytes(struct mtd_info *mtd, u8 *databuf,
+ const u8 *oobbuf, int start, int nbytes);
+int mtd_ooblayout_set_databytes(struct mtd_info *mtd, const u8 *databuf,
+ u8 *oobbuf, int start, int nbytes);
+int mtd_ooblayout_count_freebytes(struct mtd_info *mtd);
+int mtd_ooblayout_count_eccbytes(struct mtd_info *mtd);
+
+static inline void mtd_set_ooblayout(struct mtd_info *mtd,
+ const struct mtd_ooblayout_ops *ooblayout)
+{
+ mtd->ooblayout = ooblayout;
+}
+
static inline void mtd_set_of_node(struct mtd_info *mtd,
struct device_node *np)
{
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 56574ba36555..fbe8e164a4ee 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -116,9 +116,14 @@ typedef enum {
NAND_ECC_HW,
NAND_ECC_HW_SYNDROME,
NAND_ECC_HW_OOB_FIRST,
- NAND_ECC_SOFT_BCH,
} nand_ecc_modes_t;
+enum nand_ecc_algo {
+ NAND_ECC_UNKNOWN,
+ NAND_ECC_HAMMING,
+ NAND_ECC_BCH,
+};
+
/*
* Constants for Hardware ECC
*/
@@ -458,6 +463,7 @@ struct nand_hw_control {
/**
* struct nand_ecc_ctrl - Control structure for ECC
* @mode: ECC mode
+ * @algo: ECC algorithm
* @steps: number of ECC steps per page
* @size: data bytes per ECC step
* @bytes: ECC bytes per step
@@ -466,7 +472,6 @@ struct nand_hw_control {
* @prepad: padding information for syndrome based ECC generators
* @postpad: padding information for syndrome based ECC generators
* @options: ECC specific options (see NAND_ECC_XXX flags defined above)
- * @layout: ECC layout control struct pointer
* @priv: pointer to private ECC control data
* @hwctl: function to control hardware ECC generator. Must only
* be provided if an hardware ECC is available
@@ -508,6 +513,7 @@ struct nand_hw_control {
*/
struct nand_ecc_ctrl {
nand_ecc_modes_t mode;
+ enum nand_ecc_algo algo;
int steps;
int size;
int bytes;
@@ -516,7 +522,6 @@ struct nand_ecc_ctrl {
int prepad;
int postpad;
unsigned int options;
- struct nand_ecclayout *layout;
void *priv;
void (*hwctl)(struct mtd_info *mtd, int mode);
int (*calculate)(struct mtd_info *mtd, const uint8_t *dat,
@@ -740,6 +745,9 @@ struct nand_chip {
void *priv;
};
+extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops;
+extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops;
+
static inline void nand_set_flash_node(struct nand_chip *chip,
struct device_node *np)
{
@@ -1070,4 +1078,18 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
void *ecc, int ecclen,
void *extraoob, int extraooblen,
int threshold);
+
+/* Default write_oob implementation */
+int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
+
+/* Default write_oob syndrome implementation */
+int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
+ int page);
+
+/* Default read_oob implementation */
+int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
+
+/* Default read_oob syndrome implementation */
+int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
+ int page);
#endif /* __LINUX_MTD_NAND_H */
diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h
index 4596503c9da9..0aaa98b219a4 100644
--- a/include/linux/mtd/onenand.h
+++ b/include/linux/mtd/onenand.h
@@ -80,7 +80,6 @@ struct onenand_bufferram {
* @page_buf: [INTERN] page main data buffer
* @oob_buf: [INTERN] page oob data buffer
* @subpagesize: [INTERN] holds the subpagesize
- * @ecclayout: [REPLACEABLE] the default ecc placement scheme
* @bbm: [REPLACEABLE] pointer to Bad Block Management
* @priv: [OPTIONAL] pointer to private chip date
*/
@@ -134,7 +133,6 @@ struct onenand_chip {
#endif
int subpagesize;
- struct nand_ecclayout *ecclayout;
void *bbm;
diff --git a/include/linux/mtd/sharpsl.h b/include/linux/mtd/sharpsl.h
index 25f4d2a845c1..65e91d0fa981 100644
--- a/include/linux/mtd/sharpsl.h
+++ b/include/linux/mtd/sharpsl.h
@@ -14,7 +14,7 @@
struct sharpsl_nand_platform_data {
struct nand_bbt_descr *badblock_pattern;
- struct nand_ecclayout *ecc_layout;
+ const struct mtd_ooblayout_ops *ecc_layout;
struct mtd_partition *partitions;
unsigned int nr_partitions;
};
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 3c36113a88e1..7f041bd88b82 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -21,6 +21,7 @@
* Sometimes these are the same as CFI IDs, but sometimes they aren't.
*/
#define SNOR_MFR_ATMEL CFI_MFR_ATMEL
+#define SNOR_MFR_GIGADEVICE 0xc8
#define SNOR_MFR_INTEL CFI_MFR_INTEL
#define SNOR_MFR_MICRON CFI_MFR_ST /* ST Micro <--> Micron */
#define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX
diff --git a/include/linux/namei.h b/include/linux/namei.h
index ec5ec2818a28..d3d0398f2a1b 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -45,6 +45,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
#define LOOKUP_ROOT 0x2000
#define LOOKUP_EMPTY 0x4000
+extern int path_pts(struct path *path);
+
extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
diff --git a/include/linux/net.h b/include/linux/net.h
index 9aa49a05fe38..25aa03b51c4e 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -251,7 +251,8 @@ do { \
DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \
net_ratelimit()) \
- __dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__); \
+ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \
+ ##__VA_ARGS__); \
} while (0)
#elif defined(DEBUG)
#define net_dbg_ratelimited(fmt, ...) \
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 011433478a14..bfed6b367350 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -50,12 +50,27 @@ struct nfs4_label {
typedef struct { char data[NFS4_VERIFIER_SIZE]; } nfs4_verifier;
-struct nfs_stateid4 {
- __be32 seqid;
- char other[NFS4_STATEID_OTHER_SIZE];
-} __attribute__ ((packed));
+struct nfs4_stateid_struct {
+ union {
+ char data[NFS4_STATEID_SIZE];
+ struct {
+ __be32 seqid;
+ char other[NFS4_STATEID_OTHER_SIZE];
+ } __attribute__ ((packed));
+ };
+
+ enum {
+ NFS4_INVALID_STATEID_TYPE = 0,
+ NFS4_SPECIAL_STATEID_TYPE,
+ NFS4_OPEN_STATEID_TYPE,
+ NFS4_LOCK_STATEID_TYPE,
+ NFS4_DELEGATION_STATEID_TYPE,
+ NFS4_LAYOUT_STATEID_TYPE,
+ NFS4_PNFS_DS_STATEID_TYPE,
+ } type;
+};
-typedef struct nfs_stateid4 nfs4_stateid;
+typedef struct nfs4_stateid_struct nfs4_stateid;
enum nfs_opnum4 {
OP_ACCESS = 3,
@@ -504,6 +519,7 @@ enum {
NFSPROC4_CLNT_DEALLOCATE,
NFSPROC4_CLNT_LAYOUTSTATS,
NFSPROC4_CLNT_CLONE,
+ NFSPROC4_CLNT_COPY,
};
/* nfs41 types */
@@ -621,7 +637,9 @@ enum pnfs_update_layout_reason {
PNFS_UPDATE_LAYOUT_IO_TEST_FAIL,
PNFS_UPDATE_LAYOUT_FOUND_CACHED,
PNFS_UPDATE_LAYOUT_RETURN,
+ PNFS_UPDATE_LAYOUT_RETRY,
PNFS_UPDATE_LAYOUT_BLOCKED,
+ PNFS_UPDATE_LAYOUT_INVALID_OPEN,
PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET,
};
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7fcc13c8cf1f..14a762d2734d 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -246,5 +246,6 @@ struct nfs_server {
#define NFS_CAP_DEALLOCATE (1U << 21)
#define NFS_CAP_LAYOUTSTATS (1U << 22)
#define NFS_CAP_CLONE (1U << 23)
+#define NFS_CAP_COPY (1U << 24)
#endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index ee8491dadbf3..c304a11b5b1a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -233,7 +233,6 @@ struct nfs4_layoutget_args {
struct inode *inode;
struct nfs_open_context *ctx;
nfs4_stateid stateid;
- unsigned long timestamp;
struct nfs4_layoutdriver_data layout;
};
@@ -251,7 +250,6 @@ struct nfs4_layoutget {
struct nfs4_layoutget_res res;
struct rpc_cred *cred;
gfp_t gfp_flags;
- long timeout;
};
struct nfs4_getdeviceinfo_args {
@@ -1343,6 +1341,32 @@ struct nfs42_falloc_res {
const struct nfs_server *falloc_server;
};
+struct nfs42_copy_args {
+ struct nfs4_sequence_args seq_args;
+
+ struct nfs_fh *src_fh;
+ nfs4_stateid src_stateid;
+ u64 src_pos;
+
+ struct nfs_fh *dst_fh;
+ nfs4_stateid dst_stateid;
+ u64 dst_pos;
+
+ u64 count;
+};
+
+struct nfs42_write_res {
+ u64 count;
+ struct nfs_writeverf verifier;
+};
+
+struct nfs42_copy_res {
+ struct nfs4_sequence_res seq_res;
+ struct nfs42_write_res write_res;
+ bool consecutive;
+ bool synchronous;
+};
+
struct nfs42_seek_args {
struct nfs4_sequence_args seq_args;
@@ -1431,7 +1455,7 @@ struct nfs_commit_completion_ops {
};
struct nfs_commit_info {
- spinlock_t *lock; /* inode->i_lock */
+ struct inode *inode; /* Needed for inode->i_lock */
struct nfs_mds_commit_info *mds;
struct pnfs_ds_commit_info *ds;
struct nfs_direct_req *dreq; /* O_DIRECT request */
diff --git a/include/linux/of.h b/include/linux/of.h
index c7292e8ea080..74eb28cadbef 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -614,7 +614,7 @@ static inline struct device_node *of_parse_phandle(const struct device_node *np,
return NULL;
}
-static inline int of_parse_phandle_with_args(struct device_node *np,
+static inline int of_parse_phandle_with_args(const struct device_node *np,
const char *list_name,
const char *cells_name,
int index,
diff --git a/include/linux/of_mtd.h b/include/linux/of_mtd.h
deleted file mode 100644
index e266caa36402..000000000000
--- a/include/linux/of_mtd.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
- *
- * OF helpers for mtd.
- *
- * This file is released under the GPLv2
- */
-
-#ifndef __LINUX_OF_MTD_H
-#define __LINUX_OF_MTD_H
-
-#ifdef CONFIG_OF_MTD
-
-#include <linux/of.h>
-int of_get_nand_ecc_mode(struct device_node *np);
-int of_get_nand_ecc_step_size(struct device_node *np);
-int of_get_nand_ecc_strength(struct device_node *np);
-int of_get_nand_bus_width(struct device_node *np);
-bool of_get_nand_on_flash_bbt(struct device_node *np);
-
-#else /* CONFIG_OF_MTD */
-
-static inline int of_get_nand_ecc_mode(struct device_node *np)
-{
- return -ENOSYS;
-}
-
-static inline int of_get_nand_ecc_step_size(struct device_node *np)
-{
- return -ENOSYS;
-}
-
-static inline int of_get_nand_ecc_strength(struct device_node *np)
-{
- return -ENOSYS;
-}
-
-static inline int of_get_nand_bus_width(struct device_node *np)
-{
- return -ENOSYS;
-}
-
-static inline bool of_get_nand_on_flash_bbt(struct device_node *np)
-{
- return false;
-}
-
-#endif /* CONFIG_OF_MTD */
-
-#endif /* __LINUX_OF_MTD_H */
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index f6e9e85164e8..b969e9443962 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -8,7 +8,7 @@ struct pci_dev;
struct of_phandle_args;
struct device_node;
-#ifdef CONFIG_OF
+#ifdef CONFIG_OF_PCI
int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq);
struct device_node *of_pci_find_child_device(struct device_node *parent,
unsigned int devfn);
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index ad2f67054372..c201060e0c6d 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -31,6 +31,13 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem);
int of_reserved_mem_device_init(struct device *dev);
void of_reserved_mem_device_release(struct device *dev);
+int early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+ phys_addr_t align,
+ phys_addr_t start,
+ phys_addr_t end,
+ bool nomap,
+ phys_addr_t *res_base);
+
void fdt_init_reserved_mem(void);
void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
phys_addr_t base, phys_addr_t size);
diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h
index d833eb4dd446..9e9d79e8efa5 100644
--- a/include/linux/omap-gpmc.h
+++ b/include/linux/omap-gpmc.h
@@ -7,161 +7,53 @@
* option) any later version.
*/
-/* Maximum Number of Chip Selects */
-#define GPMC_CS_NUM 8
+#include <linux/platform_data/gpmc-omap.h>
#define GPMC_CONFIG_WP 0x00000005
-#define GPMC_IRQ_FIFOEVENTENABLE 0x01
-#define GPMC_IRQ_COUNT_EVENT 0x02
-
-#define GPMC_BURST_4 4 /* 4 word burst */
-#define GPMC_BURST_8 8 /* 8 word burst */
-#define GPMC_BURST_16 16 /* 16 word burst */
-#define GPMC_DEVWIDTH_8BIT 1 /* 8-bit device width */
-#define GPMC_DEVWIDTH_16BIT 2 /* 16-bit device width */
-#define GPMC_MUX_AAD 1 /* Addr-Addr-Data multiplex */
-#define GPMC_MUX_AD 2 /* Addr-Data multiplex */
-
-/* bool type time settings */
-struct gpmc_bool_timings {
- bool cycle2cyclediffcsen;
- bool cycle2cyclesamecsen;
- bool we_extra_delay;
- bool oe_extra_delay;
- bool adv_extra_delay;
- bool cs_extra_delay;
- bool time_para_granularity;
-};
+/* IRQ numbers in GPMC IRQ domain for legacy boot use */
+#define GPMC_IRQ_FIFOEVENTENABLE 0
+#define GPMC_IRQ_COUNT_EVENT 1
-/*
- * Note that all values in this struct are in nanoseconds except sync_clk
- * (which is in picoseconds), while the register values are in gpmc_fck cycles.
+/**
+ * gpmc_nand_ops - Interface between NAND and GPMC
+ * @nand_write_buffer_empty: get the NAND write buffer empty status.
*/
-struct gpmc_timings {
- /* Minimum clock period for synchronous mode (in picoseconds) */
- u32 sync_clk;
-
- /* Chip-select signal timings corresponding to GPMC_CS_CONFIG2 */
- u32 cs_on; /* Assertion time */
- u32 cs_rd_off; /* Read deassertion time */
- u32 cs_wr_off; /* Write deassertion time */
-
- /* ADV signal timings corresponding to GPMC_CONFIG3 */
- u32 adv_on; /* Assertion time */
- u32 adv_rd_off; /* Read deassertion time */
- u32 adv_wr_off; /* Write deassertion time */
- u32 adv_aad_mux_on; /* ADV assertion time for AAD */
- u32 adv_aad_mux_rd_off; /* ADV read deassertion time for AAD */
- u32 adv_aad_mux_wr_off; /* ADV write deassertion time for AAD */
-
- /* WE signals timings corresponding to GPMC_CONFIG4 */
- u32 we_on; /* WE assertion time */
- u32 we_off; /* WE deassertion time */
-
- /* OE signals timings corresponding to GPMC_CONFIG4 */
- u32 oe_on; /* OE assertion time */
- u32 oe_off; /* OE deassertion time */
- u32 oe_aad_mux_on; /* OE assertion time for AAD */
- u32 oe_aad_mux_off; /* OE deassertion time for AAD */
-
- /* Access time and cycle time timings corresponding to GPMC_CONFIG5 */
- u32 page_burst_access; /* Multiple access word delay */
- u32 access; /* Start-cycle to first data valid delay */
- u32 rd_cycle; /* Total read cycle time */
- u32 wr_cycle; /* Total write cycle time */
-
- u32 bus_turnaround;
- u32 cycle2cycle_delay;
-
- u32 wait_monitoring;
- u32 clk_activation;
-
- /* The following are only on OMAP3430 */
- u32 wr_access; /* WRACCESSTIME */
- u32 wr_data_mux_bus; /* WRDATAONADMUXBUS */
-
- struct gpmc_bool_timings bool_timings;
+struct gpmc_nand_ops {
+ bool (*nand_writebuffer_empty)(void);
};
-/* Device timings in picoseconds */
-struct gpmc_device_timings {
- u32 t_ceasu; /* address setup to CS valid */
- u32 t_avdasu; /* address setup to ADV valid */
- /* XXX: try to combine t_avdp_r & t_avdp_w. Issue is
- * of tusb using these timings even for sync whilst
- * ideally for adv_rd/(wr)_off it should have considered
- * t_avdh instead. This indirectly necessitates r/w
- * variations of t_avdp as it is possible to have one
- * sync & other async
- */
- u32 t_avdp_r; /* ADV low time (what about t_cer ?) */
- u32 t_avdp_w;
- u32 t_aavdh; /* address hold time */
- u32 t_oeasu; /* address setup to OE valid */
- u32 t_aa; /* access time from ADV assertion */
- u32 t_iaa; /* initial access time */
- u32 t_oe; /* access time from OE assertion */
- u32 t_ce; /* access time from CS asertion */
- u32 t_rd_cycle; /* read cycle time */
- u32 t_cez_r; /* read CS deassertion to high Z */
- u32 t_cez_w; /* write CS deassertion to high Z */
- u32 t_oez; /* OE deassertion to high Z */
- u32 t_weasu; /* address setup to WE valid */
- u32 t_wpl; /* write assertion time */
- u32 t_wph; /* write deassertion time */
- u32 t_wr_cycle; /* write cycle time */
-
- u32 clk;
- u32 t_bacc; /* burst access valid clock to output delay */
- u32 t_ces; /* CS setup time to clk */
- u32 t_avds; /* ADV setup time to clk */
- u32 t_avdh; /* ADV hold time from clk */
- u32 t_ach; /* address hold time from clk */
- u32 t_rdyo; /* clk to ready valid */
-
- u32 t_ce_rdyz; /* XXX: description ?, or use t_cez instead */
- u32 t_ce_avd; /* CS on to ADV on delay */
-
- /* XXX: check the possibility of combining
- * cyc_aavhd_oe & cyc_aavdh_we
- */
- u8 cyc_aavdh_oe;/* read address hold time in cycles */
- u8 cyc_aavdh_we;/* write address hold time in cycles */
- u8 cyc_oe; /* access time from OE assertion in cycles */
- u8 cyc_wpl; /* write deassertion time in cycles */
- u32 cyc_iaa; /* initial access time in cycles */
-
- /* extra delays */
- bool ce_xdelay;
- bool avd_xdelay;
- bool oe_xdelay;
- bool we_xdelay;
-};
+struct gpmc_nand_regs;
-struct gpmc_settings {
- bool burst_wrap; /* enables wrap bursting */
- bool burst_read; /* enables read page/burst mode */
- bool burst_write; /* enables write page/burst mode */
- bool device_nand; /* device is NAND */
- bool sync_read; /* enables synchronous reads */
- bool sync_write; /* enables synchronous writes */
- bool wait_on_read; /* monitor wait on reads */
- bool wait_on_write; /* monitor wait on writes */
- u32 burst_len; /* page/burst length */
- u32 device_width; /* device bus width (8 or 16 bit) */
- u32 mux_add_data; /* multiplex address & data */
- u32 wait_pin; /* wait-pin to be used */
-};
+#if IS_ENABLED(CONFIG_OMAP_GPMC)
+struct gpmc_nand_ops *gpmc_omap_get_nand_ops(struct gpmc_nand_regs *regs,
+ int cs);
+#else
+static inline gpmc_nand_ops *gpmc_omap_get_nand_ops(struct gpmc_nand_regs *regs,
+ int cs)
+{
+ return NULL;
+}
+#endif /* CONFIG_OMAP_GPMC */
+
+/*--------------------------------*/
+
+/* deprecated APIs */
+#if IS_ENABLED(CONFIG_OMAP_GPMC)
+void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs);
+#else
+static inline void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs)
+{
+}
+#endif /* CONFIG_OMAP_GPMC */
+/*--------------------------------*/
extern int gpmc_calc_timings(struct gpmc_timings *gpmc_t,
struct gpmc_settings *gpmc_s,
struct gpmc_device_timings *dev_t);
-struct gpmc_nand_regs;
struct device_node;
-extern void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs);
extern int gpmc_get_client_irq(unsigned irq_config);
extern unsigned int gpmc_ticks_to_ns(unsigned int ticks);
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index bf268fa92c5b..fec40271339f 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -46,33 +46,62 @@ extern struct page_ext_operations page_idle_ops;
static inline bool page_is_young(struct page *page)
{
- return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+ struct page_ext *page_ext = lookup_page_ext(page);
+
+ if (unlikely(!page_ext))
+ return false;
+
+ return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
static inline void set_page_young(struct page *page)
{
- set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+ struct page_ext *page_ext = lookup_page_ext(page);
+
+ if (unlikely(!page_ext))
+ return;
+
+ set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
static inline bool test_and_clear_page_young(struct page *page)
{
- return test_and_clear_bit(PAGE_EXT_YOUNG,
- &lookup_page_ext(page)->flags);
+ struct page_ext *page_ext = lookup_page_ext(page);
+
+ if (unlikely(!page_ext))
+ return false;
+
+ return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
static inline bool page_is_idle(struct page *page)
{
- return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+ struct page_ext *page_ext = lookup_page_ext(page);
+
+ if (unlikely(!page_ext))
+ return false;
+
+ return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
static inline void set_page_idle(struct page *page)
{
- set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+ struct page_ext *page_ext = lookup_page_ext(page);
+
+ if (unlikely(!page_ext))
+ return;
+
+ set_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
static inline void clear_page_idle(struct page *page)
{
- clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+ struct page_ext *page_ext = lookup_page_ext(page);
+
+ if (unlikely(!page_ext))
+ return;
+
+ clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
#endif /* CONFIG_64BIT */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 44f33834ad78..1a827cecd62f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -61,6 +61,14 @@ struct perf_callchain_entry {
__u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
};
+struct perf_callchain_entry_ctx {
+ struct perf_callchain_entry *entry;
+ u32 max_stack;
+ u32 nr;
+ short contexts;
+ bool contexts_maxed;
+};
+
struct perf_raw_record {
u32 size;
void *data;
@@ -1061,20 +1069,36 @@ extern void perf_event_fork(struct task_struct *tsk);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
-extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
-extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
- bool crosstask, bool add_mark);
+ u32 max_stack, bool crosstask, bool add_mark);
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
+
+static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
+{
+ if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) {
+ struct perf_callchain_entry *entry = ctx->entry;
+ entry->ip[entry->nr++] = ip;
+ ++ctx->contexts;
+ return 0;
+ } else {
+ ctx->contexts_maxed = true;
+ return -1; /* no more room, stop walking the stack */
+ }
+}
-static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
- if (entry->nr < sysctl_perf_event_max_stack) {
+ if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) {
+ struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
+ ++ctx->nr;
return 0;
} else {
return -1; /* no more room, stop walking the stack */
diff --git a/include/linux/platform_data/at24.h b/include/linux/platform_data/at24.h
index dc9a13e5acda..be830b141d83 100644
--- a/include/linux/platform_data/at24.h
+++ b/include/linux/platform_data/at24.h
@@ -26,7 +26,7 @@
*
* An example in pseudo code for a setup() callback:
*
- * void get_mac_addr(struct mvmem_device *nvmem, void *context)
+ * void get_mac_addr(struct nvmem_device *nvmem, void *context)
* {
* u8 *mac_addr = ethernet_pdata->mac_addr;
* off_t offset = context;
diff --git a/include/linux/platform_data/gpmc-omap.h b/include/linux/platform_data/gpmc-omap.h
new file mode 100644
index 000000000000..67ccdb0e1606
--- /dev/null
+++ b/include/linux/platform_data/gpmc-omap.h
@@ -0,0 +1,172 @@
+/*
+ * OMAP GPMC Platform data
+ *
+ * Copyright (C) 2014 Texas Instruments, Inc. - http://www.ti.com
+ * Roger Quadros <rogerq@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#ifndef _GPMC_OMAP_H_
+#define _GPMC_OMAP_H_
+
+/* Maximum Number of Chip Selects */
+#define GPMC_CS_NUM 8
+
+/* bool type time settings */
+struct gpmc_bool_timings {
+ bool cycle2cyclediffcsen;
+ bool cycle2cyclesamecsen;
+ bool we_extra_delay;
+ bool oe_extra_delay;
+ bool adv_extra_delay;
+ bool cs_extra_delay;
+ bool time_para_granularity;
+};
+
+/*
+ * Note that all values in this struct are in nanoseconds except sync_clk
+ * (which is in picoseconds), while the register values are in gpmc_fck cycles.
+ */
+struct gpmc_timings {
+ /* Minimum clock period for synchronous mode (in picoseconds) */
+ u32 sync_clk;
+
+ /* Chip-select signal timings corresponding to GPMC_CS_CONFIG2 */
+ u32 cs_on; /* Assertion time */
+ u32 cs_rd_off; /* Read deassertion time */
+ u32 cs_wr_off; /* Write deassertion time */
+
+ /* ADV signal timings corresponding to GPMC_CONFIG3 */
+ u32 adv_on; /* Assertion time */
+ u32 adv_rd_off; /* Read deassertion time */
+ u32 adv_wr_off; /* Write deassertion time */
+ u32 adv_aad_mux_on; /* ADV assertion time for AAD */
+ u32 adv_aad_mux_rd_off; /* ADV read deassertion time for AAD */
+ u32 adv_aad_mux_wr_off; /* ADV write deassertion time for AAD */
+
+ /* WE signals timings corresponding to GPMC_CONFIG4 */
+ u32 we_on; /* WE assertion time */
+ u32 we_off; /* WE deassertion time */
+
+ /* OE signals timings corresponding to GPMC_CONFIG4 */
+ u32 oe_on; /* OE assertion time */
+ u32 oe_off; /* OE deassertion time */
+ u32 oe_aad_mux_on; /* OE assertion time for AAD */
+ u32 oe_aad_mux_off; /* OE deassertion time for AAD */
+
+ /* Access time and cycle time timings corresponding to GPMC_CONFIG5 */
+ u32 page_burst_access; /* Multiple access word delay */
+ u32 access; /* Start-cycle to first data valid delay */
+ u32 rd_cycle; /* Total read cycle time */
+ u32 wr_cycle; /* Total write cycle time */
+
+ u32 bus_turnaround;
+ u32 cycle2cycle_delay;
+
+ u32 wait_monitoring;
+ u32 clk_activation;
+
+ /* The following are only on OMAP3430 */
+ u32 wr_access; /* WRACCESSTIME */
+ u32 wr_data_mux_bus; /* WRDATAONADMUXBUS */
+
+ struct gpmc_bool_timings bool_timings;
+};
+
+/* Device timings in picoseconds */
+struct gpmc_device_timings {
+ u32 t_ceasu; /* address setup to CS valid */
+ u32 t_avdasu; /* address setup to ADV valid */
+ /* XXX: try to combine t_avdp_r & t_avdp_w. Issue is
+ * of tusb using these timings even for sync whilst
+ * ideally for adv_rd/(wr)_off it should have considered
+ * t_avdh instead. This indirectly necessitates r/w
+ * variations of t_avdp as it is possible to have one
+ * sync & other async
+ */
+ u32 t_avdp_r; /* ADV low time (what about t_cer ?) */
+ u32 t_avdp_w;
+ u32 t_aavdh; /* address hold time */
+ u32 t_oeasu; /* address setup to OE valid */
+ u32 t_aa; /* access time from ADV assertion */
+ u32 t_iaa; /* initial access time */
+ u32 t_oe; /* access time from OE assertion */
+ u32 t_ce; /* access time from CS asertion */
+ u32 t_rd_cycle; /* read cycle time */
+ u32 t_cez_r; /* read CS deassertion to high Z */
+ u32 t_cez_w; /* write CS deassertion to high Z */
+ u32 t_oez; /* OE deassertion to high Z */
+ u32 t_weasu; /* address setup to WE valid */
+ u32 t_wpl; /* write assertion time */
+ u32 t_wph; /* write deassertion time */
+ u32 t_wr_cycle; /* write cycle time */
+
+ u32 clk;
+ u32 t_bacc; /* burst access valid clock to output delay */
+ u32 t_ces; /* CS setup time to clk */
+ u32 t_avds; /* ADV setup time to clk */
+ u32 t_avdh; /* ADV hold time from clk */
+ u32 t_ach; /* address hold time from clk */
+ u32 t_rdyo; /* clk to ready valid */
+
+ u32 t_ce_rdyz; /* XXX: description ?, or use t_cez instead */
+ u32 t_ce_avd; /* CS on to ADV on delay */
+
+ /* XXX: check the possibility of combining
+ * cyc_aavhd_oe & cyc_aavdh_we
+ */
+ u8 cyc_aavdh_oe;/* read address hold time in cycles */
+ u8 cyc_aavdh_we;/* write address hold time in cycles */
+ u8 cyc_oe; /* access time from OE assertion in cycles */
+ u8 cyc_wpl; /* write deassertion time in cycles */
+ u32 cyc_iaa; /* initial access time in cycles */
+
+ /* extra delays */
+ bool ce_xdelay;
+ bool avd_xdelay;
+ bool oe_xdelay;
+ bool we_xdelay;
+};
+
+#define GPMC_BURST_4 4 /* 4 word burst */
+#define GPMC_BURST_8 8 /* 8 word burst */
+#define GPMC_BURST_16 16 /* 16 word burst */
+#define GPMC_DEVWIDTH_8BIT 1 /* 8-bit device width */
+#define GPMC_DEVWIDTH_16BIT 2 /* 16-bit device width */
+#define GPMC_MUX_AAD 1 /* Addr-Addr-Data multiplex */
+#define GPMC_MUX_AD 2 /* Addr-Data multiplex */
+
+struct gpmc_settings {
+ bool burst_wrap; /* enables wrap bursting */
+ bool burst_read; /* enables read page/burst mode */
+ bool burst_write; /* enables write page/burst mode */
+ bool device_nand; /* device is NAND */
+ bool sync_read; /* enables synchronous reads */
+ bool sync_write; /* enables synchronous writes */
+ bool wait_on_read; /* monitor wait on reads */
+ bool wait_on_write; /* monitor wait on writes */
+ u32 burst_len; /* page/burst length */
+ u32 device_width; /* device bus width (8 or 16 bit) */
+ u32 mux_add_data; /* multiplex address & data */
+ u32 wait_pin; /* wait-pin to be used */
+};
+
+/* Data for each chip select */
+struct gpmc_omap_cs_data {
+ bool valid; /* data is valid */
+ bool is_nand; /* device within this CS is NAND */
+ struct gpmc_settings *settings;
+ struct gpmc_device_timings *device_timings;
+ struct gpmc_timings *gpmc_timings;
+ struct platform_device *pdev; /* device within this CS region */
+ unsigned int pdata_size;
+};
+
+struct gpmc_omap_platform_data {
+ struct gpmc_omap_cs_data cs[GPMC_CS_NUM];
+};
+
+#endif /* _GPMC_OMAP_H */
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 090bbab0130a..17d57a18bac5 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -45,7 +45,6 @@ enum omap_ecc {
};
struct gpmc_nand_regs {
- void __iomem *gpmc_status;
void __iomem *gpmc_nand_command;
void __iomem *gpmc_nand_address;
void __iomem *gpmc_nand_data;
@@ -64,21 +63,24 @@ struct gpmc_nand_regs {
void __iomem *gpmc_bch_result4[GPMC_BCH_NUM_REMAINDER];
void __iomem *gpmc_bch_result5[GPMC_BCH_NUM_REMAINDER];
void __iomem *gpmc_bch_result6[GPMC_BCH_NUM_REMAINDER];
+ /* Deprecated. Do not use */
+ void __iomem *gpmc_status;
};
struct omap_nand_platform_data {
int cs;
struct mtd_partition *parts;
int nr_parts;
- bool dev_ready;
bool flash_bbt;
enum nand_io xfer_type;
int devsize;
enum omap_ecc ecc_opt;
- struct gpmc_nand_regs reg;
- /* for passing the partitions */
- struct device_node *of_node;
struct device_node *elm_of_node;
+
+ /* deprecated */
+ struct gpmc_nand_regs reg;
+ struct device_node *of_node;
+ bool dev_ready;
};
#endif
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index b78d27c42629..c038ae36b10e 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -5,59 +5,7 @@
#include <linux/mutex.h>
#include <linux/of.h>
-struct pwm_device;
struct seq_file;
-
-#if IS_ENABLED(CONFIG_PWM)
-/*
- * pwm_request - request a PWM device
- */
-struct pwm_device *pwm_request(int pwm_id, const char *label);
-
-/*
- * pwm_free - free a PWM device
- */
-void pwm_free(struct pwm_device *pwm);
-
-/*
- * pwm_config - change a PWM device configuration
- */
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns);
-
-/*
- * pwm_enable - start a PWM output toggling
- */
-int pwm_enable(struct pwm_device *pwm);
-
-/*
- * pwm_disable - stop a PWM output toggling
- */
-void pwm_disable(struct pwm_device *pwm);
-#else
-static inline struct pwm_device *pwm_request(int pwm_id, const char *label)
-{
- return ERR_PTR(-ENODEV);
-}
-
-static inline void pwm_free(struct pwm_device *pwm)
-{
-}
-
-static inline int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
-{
- return -EINVAL;
-}
-
-static inline int pwm_enable(struct pwm_device *pwm)
-{
- return -EINVAL;
-}
-
-static inline void pwm_disable(struct pwm_device *pwm)
-{
-}
-#endif
-
struct pwm_chip;
/**
@@ -94,8 +42,21 @@ struct pwm_args {
enum {
PWMF_REQUESTED = 1 << 0,
- PWMF_ENABLED = 1 << 1,
- PWMF_EXPORTED = 1 << 2,
+ PWMF_EXPORTED = 1 << 1,
+};
+
+/*
+ * struct pwm_state - state of a PWM channel
+ * @period: PWM period (in nanoseconds)
+ * @duty_cycle: PWM duty cycle (in nanoseconds)
+ * @polarity: PWM polarity
+ * @enabled: PWM enabled status
+ */
+struct pwm_state {
+ unsigned int period;
+ unsigned int duty_cycle;
+ enum pwm_polarity polarity;
+ bool enabled;
};
/**
@@ -106,11 +67,8 @@ enum {
* @pwm: global index of the PWM device
* @chip: PWM chip providing this PWM device
* @chip_data: chip-private data associated with the PWM device
- * @lock: used to serialize accesses to the PWM device where necessary
- * @period: period of the PWM signal (in nanoseconds)
- * @duty_cycle: duty cycle of the PWM signal (in nanoseconds)
- * @polarity: polarity of the PWM signal
* @args: PWM arguments
+ * @state: curent PWM channel state
*/
struct pwm_device {
const char *label;
@@ -119,50 +77,68 @@ struct pwm_device {
unsigned int pwm;
struct pwm_chip *chip;
void *chip_data;
- struct mutex lock;
-
- unsigned int period;
- unsigned int duty_cycle;
- enum pwm_polarity polarity;
struct pwm_args args;
+ struct pwm_state state;
};
+/**
+ * pwm_get_state() - retrieve the current PWM state
+ * @pwm: PWM device
+ * @state: state to fill with the current PWM state
+ */
+static inline void pwm_get_state(const struct pwm_device *pwm,
+ struct pwm_state *state)
+{
+ *state = pwm->state;
+}
+
static inline bool pwm_is_enabled(const struct pwm_device *pwm)
{
- return test_bit(PWMF_ENABLED, &pwm->flags);
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
+
+ return state.enabled;
}
static inline void pwm_set_period(struct pwm_device *pwm, unsigned int period)
{
if (pwm)
- pwm->period = period;
+ pwm->state.period = period;
}
static inline unsigned int pwm_get_period(const struct pwm_device *pwm)
{
- return pwm ? pwm->period : 0;
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
+
+ return state.period;
}
static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty)
{
if (pwm)
- pwm->duty_cycle = duty;
+ pwm->state.duty_cycle = duty;
}
static inline unsigned int pwm_get_duty_cycle(const struct pwm_device *pwm)
{
- return pwm ? pwm->duty_cycle : 0;
-}
+ struct pwm_state state;
-/*
- * pwm_set_polarity - configure the polarity of a PWM signal
- */
-int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity);
+ pwm_get_state(pwm, &state);
+
+ return state.duty_cycle;
+}
static inline enum pwm_polarity pwm_get_polarity(const struct pwm_device *pwm)
{
- return pwm ? pwm->polarity : PWM_POLARITY_NORMAL;
+ struct pwm_state state;
+
+ pwm_get_state(pwm, &state);
+
+ return state.polarity;
}
static inline void pwm_get_args(const struct pwm_device *pwm,
@@ -171,12 +147,6 @@ static inline void pwm_get_args(const struct pwm_device *pwm,
*args = pwm->args;
}
-static inline void pwm_apply_args(struct pwm_device *pwm)
-{
- pwm_set_period(pwm, pwm->args.period);
- pwm_set_polarity(pwm, pwm->args.polarity);
-}
-
/**
* struct pwm_ops - PWM controller operations
* @request: optional hook for requesting a PWM
@@ -185,6 +155,13 @@ static inline void pwm_apply_args(struct pwm_device *pwm)
* @set_polarity: configure the polarity of this PWM
* @enable: enable PWM output toggling
* @disable: disable PWM output toggling
+ * @apply: atomically apply a new PWM config. The state argument
+ * should be adjusted with the real hardware config (if the
+ * approximate the period or duty_cycle value, state should
+ * reflect it)
+ * @get_state: get the current PWM state. This function is only
+ * called once per PWM device when the PWM chip is
+ * registered.
* @dbg_show: optional routine to show contents in debugfs
* @owner: helps prevent removal of modules exporting active PWMs
*/
@@ -197,6 +174,10 @@ struct pwm_ops {
enum pwm_polarity polarity);
int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm);
void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm);
+ int (*apply)(struct pwm_chip *chip, struct pwm_device *pwm,
+ struct pwm_state *state);
+ void (*get_state)(struct pwm_chip *chip, struct pwm_device *pwm,
+ struct pwm_state *state);
#ifdef CONFIG_DEBUG_FS
void (*dbg_show)(struct pwm_chip *chip, struct seq_file *s);
#endif
@@ -232,6 +213,118 @@ struct pwm_chip {
};
#if IS_ENABLED(CONFIG_PWM)
+/* PWM user APIs */
+struct pwm_device *pwm_request(int pwm_id, const char *label);
+void pwm_free(struct pwm_device *pwm);
+int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state);
+int pwm_adjust_config(struct pwm_device *pwm);
+
+/**
+ * pwm_config() - change a PWM device configuration
+ * @pwm: PWM device
+ * @duty_ns: "on" time (in nanoseconds)
+ * @period_ns: duration (in nanoseconds) of one cycle
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
+ int period_ns)
+{
+ struct pwm_state state;
+
+ if (!pwm)
+ return -EINVAL;
+
+ if (duty_ns < 0 || period_ns < 0)
+ return -EINVAL;
+
+ pwm_get_state(pwm, &state);
+ if (state.duty_cycle == duty_ns && state.period == period_ns)
+ return 0;
+
+ state.duty_cycle = duty_ns;
+ state.period = period_ns;
+ return pwm_apply_state(pwm, &state);
+}
+
+/**
+ * pwm_set_polarity() - configure the polarity of a PWM signal
+ * @pwm: PWM device
+ * @polarity: new polarity of the PWM signal
+ *
+ * Note that the polarity cannot be configured while the PWM device is
+ * enabled.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static inline int pwm_set_polarity(struct pwm_device *pwm,
+ enum pwm_polarity polarity)
+{
+ struct pwm_state state;
+
+ if (!pwm)
+ return -EINVAL;
+
+ pwm_get_state(pwm, &state);
+ if (state.polarity == polarity)
+ return 0;
+
+ /*
+ * Changing the polarity of a running PWM without adjusting the
+ * dutycycle/period value is a bit risky (can introduce glitches).
+ * Return -EBUSY in this case.
+ * Note that this is allowed when using pwm_apply_state() because
+ * the user specifies all the parameters.
+ */
+ if (state.enabled)
+ return -EBUSY;
+
+ state.polarity = polarity;
+ return pwm_apply_state(pwm, &state);
+}
+
+/**
+ * pwm_enable() - start a PWM output toggling
+ * @pwm: PWM device
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static inline int pwm_enable(struct pwm_device *pwm)
+{
+ struct pwm_state state;
+
+ if (!pwm)
+ return -EINVAL;
+
+ pwm_get_state(pwm, &state);
+ if (state.enabled)
+ return 0;
+
+ state.enabled = true;
+ return pwm_apply_state(pwm, &state);
+}
+
+/**
+ * pwm_disable() - stop a PWM output toggling
+ * @pwm: PWM device
+ */
+static inline void pwm_disable(struct pwm_device *pwm)
+{
+ struct pwm_state state;
+
+ if (!pwm)
+ return;
+
+ pwm_get_state(pwm, &state);
+ if (!state.enabled)
+ return;
+
+ state.enabled = false;
+ pwm_apply_state(pwm, &state);
+}
+
+
+/* PWM provider APIs */
int pwm_set_chip_data(struct pwm_device *pwm, void *data);
void *pwm_get_chip_data(struct pwm_device *pwm);
@@ -257,6 +350,47 @@ void devm_pwm_put(struct device *dev, struct pwm_device *pwm);
bool pwm_can_sleep(struct pwm_device *pwm);
#else
+static inline struct pwm_device *pwm_request(int pwm_id, const char *label)
+{
+ return ERR_PTR(-ENODEV);
+}
+
+static inline void pwm_free(struct pwm_device *pwm)
+{
+}
+
+static inline int pwm_apply_state(struct pwm_device *pwm,
+ const struct pwm_state *state)
+{
+ return -ENOTSUPP;
+}
+
+static inline int pwm_adjust_config(struct pwm_device *pwm)
+{
+ return -ENOTSUPP;
+}
+
+static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
+ int period_ns)
+{
+ return -EINVAL;
+}
+
+static inline int pwm_set_polarity(struct pwm_device *pwm,
+ enum pwm_polarity polarity)
+{
+ return -ENOTSUPP;
+}
+
+static inline int pwm_enable(struct pwm_device *pwm)
+{
+ return -EINVAL;
+}
+
+static inline void pwm_disable(struct pwm_device *pwm)
+{
+}
+
static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data)
{
return -EINVAL;
@@ -328,6 +462,38 @@ static inline bool pwm_can_sleep(struct pwm_device *pwm)
}
#endif
+static inline void pwm_apply_args(struct pwm_device *pwm)
+{
+ struct pwm_state state = { };
+
+ /*
+ * PWM users calling pwm_apply_args() expect to have a fresh config
+ * where the polarity and period are set according to pwm_args info.
+ * The problem is, polarity can only be changed when the PWM is
+ * disabled.
+ *
+ * PWM drivers supporting hardware readout may declare the PWM device
+ * as enabled, and prevent polarity setting, which changes from the
+ * existing behavior, where all PWM devices are declared as disabled
+ * at startup (even if they are actually enabled), thus authorizing
+ * polarity setting.
+ *
+ * To fulfill this requirement, we apply a new state which disables
+ * the PWM device and set the reference period and polarity config.
+ *
+ * Note that PWM users requiring a smooth handover between the
+ * bootloader and the kernel (like critical regulators controlled by
+ * PWM devices) will have to switch to the atomic API and avoid calling
+ * pwm_apply_args().
+ */
+
+ state.enabled = false;
+ state.polarity = pwm->args.polarity;
+ state.period = pwm->args.period;
+
+ pwm_apply_state(pwm, &state);
+}
+
struct pwm_lookup {
struct list_head list;
const char *provider;
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 6ae8cb4a61d3..6c876a63558d 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -49,6 +49,7 @@ struct qed_start_vport_params {
bool drop_ttl0;
u8 vport_id;
u16 mtu;
+ bool clear_stats;
};
struct qed_stop_rxq_params {
diff --git a/include/linux/reservation.h b/include/linux/reservation.h
index 49d057655d62..b0f305e77b7f 100644
--- a/include/linux/reservation.h
+++ b/include/linux/reservation.h
@@ -49,12 +49,27 @@ extern struct ww_class reservation_ww_class;
extern struct lock_class_key reservation_seqcount_class;
extern const char reservation_seqcount_string[];
+/**
+ * struct reservation_object_list - a list of shared fences
+ * @rcu: for internal use
+ * @shared_count: table of shared fences
+ * @shared_max: for growing shared fence table
+ * @shared: shared fence table
+ */
struct reservation_object_list {
struct rcu_head rcu;
u32 shared_count, shared_max;
struct fence __rcu *shared[];
};
+/**
+ * struct reservation_object - a reservation object manages fences for a buffer
+ * @lock: update side lock
+ * @seq: sequence count for managing RCU read-side synchronization
+ * @fence_excl: the exclusive fence, if there is one currently
+ * @fence: list of current shared fences
+ * @staged: staged copy of shared fences for RCU updates
+ */
struct reservation_object {
struct ww_mutex lock;
seqcount_t seq;
@@ -68,6 +83,10 @@ struct reservation_object {
#define reservation_object_assert_held(obj) \
lockdep_assert_held(&(obj)->lock.base)
+/**
+ * reservation_object_init - initialize a reservation object
+ * @obj: the reservation object
+ */
static inline void
reservation_object_init(struct reservation_object *obj)
{
@@ -79,6 +98,10 @@ reservation_object_init(struct reservation_object *obj)
obj->staged = NULL;
}
+/**
+ * reservation_object_fini - destroys a reservation object
+ * @obj: the reservation object
+ */
static inline void
reservation_object_fini(struct reservation_object *obj)
{
@@ -106,6 +129,14 @@ reservation_object_fini(struct reservation_object *obj)
ww_mutex_destroy(&obj->lock);
}
+/**
+ * reservation_object_get_list - get the reservation object's
+ * shared fence list, with update-side lock held
+ * @obj: the reservation object
+ *
+ * Returns the shared fence list. Does NOT take references to
+ * the fence. The obj->lock must be held.
+ */
static inline struct reservation_object_list *
reservation_object_get_list(struct reservation_object *obj)
{
@@ -113,6 +144,17 @@ reservation_object_get_list(struct reservation_object *obj)
reservation_object_held(obj));
}
+/**
+ * reservation_object_get_excl - get the reservation object's
+ * exclusive fence, with update-side lock held
+ * @obj: the reservation object
+ *
+ * Returns the exclusive fence (if any). Does NOT take a
+ * reference. The obj->lock must be held.
+ *
+ * RETURNS
+ * The exclusive fence or NULL
+ */
static inline struct fence *
reservation_object_get_excl(struct reservation_object *obj)
{
@@ -120,6 +162,17 @@ reservation_object_get_excl(struct reservation_object *obj)
reservation_object_held(obj));
}
+/**
+ * reservation_object_get_excl_rcu - get the reservation object's
+ * exclusive fence, without lock held.
+ * @obj: the reservation object
+ *
+ * If there is an exclusive fence, this atomically increments it's
+ * reference count and returns it.
+ *
+ * RETURNS
+ * The exclusive fence or NULL if none
+ */
static inline struct fence *
reservation_object_get_excl_rcu(struct reservation_object *obj)
{
diff --git a/include/linux/reset.h b/include/linux/reset.h
index ec0306ce7b92..45a4abeb6acb 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -84,8 +84,8 @@ static inline struct reset_control *__devm_reset_control_get(
#endif /* CONFIG_RESET_CONTROLLER */
/**
- * reset_control_get - Lookup and obtain an exclusive reference to a
- * reset controller.
+ * reset_control_get_exclusive - Lookup and obtain an exclusive reference
+ * to a reset controller.
* @dev: device to be reset by the controller
* @id: reset line name
*
@@ -98,8 +98,8 @@ static inline struct reset_control *__devm_reset_control_get(
*
* Use of id names is optional.
*/
-static inline struct reset_control *__must_check reset_control_get(
- struct device *dev, const char *id)
+static inline struct reset_control *
+__must_check reset_control_get_exclusive(struct device *dev, const char *id)
{
#ifndef CONFIG_RESET_CONTROLLER
WARN_ON(1);
@@ -107,12 +107,6 @@ static inline struct reset_control *__must_check reset_control_get(
return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0);
}
-static inline struct reset_control *reset_control_get_optional(
- struct device *dev, const char *id)
-{
- return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0);
-}
-
/**
* reset_control_get_shared - Lookup and obtain a shared reference to a
* reset controller.
@@ -141,9 +135,21 @@ static inline struct reset_control *reset_control_get_shared(
return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 1);
}
+static inline struct reset_control *reset_control_get_optional_exclusive(
+ struct device *dev, const char *id)
+{
+ return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0);
+}
+
+static inline struct reset_control *reset_control_get_optional_shared(
+ struct device *dev, const char *id)
+{
+ return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 1);
+}
+
/**
- * of_reset_control_get - Lookup and obtain an exclusive reference to a
- * reset controller.
+ * of_reset_control_get_exclusive - Lookup and obtain an exclusive reference
+ * to a reset controller.
* @node: device to be reset by the controller
* @id: reset line name
*
@@ -151,15 +157,41 @@ static inline struct reset_control *reset_control_get_shared(
*
* Use of id names is optional.
*/
-static inline struct reset_control *of_reset_control_get(
+static inline struct reset_control *of_reset_control_get_exclusive(
struct device_node *node, const char *id)
{
return __of_reset_control_get(node, id, 0, 0);
}
/**
- * of_reset_control_get_by_index - Lookup and obtain an exclusive reference to
- * a reset controller by index.
+ * of_reset_control_get_shared - Lookup and obtain an shared reference
+ * to a reset controller.
+ * @node: device to be reset by the controller
+ * @id: reset line name
+ *
+ * When a reset-control is shared, the behavior of reset_control_assert /
+ * deassert is changed, the reset-core will keep track of a deassert_count
+ * and only (re-)assert the reset after reset_control_assert has been called
+ * as many times as reset_control_deassert was called. Also see the remark
+ * about shared reset-controls in the reset_control_assert docs.
+ *
+ * Calling reset_control_assert without first calling reset_control_deassert
+ * is not allowed on a shared reset control. Calling reset_control_reset is
+ * also not allowed on a shared reset control.
+ * Returns a struct reset_control or IS_ERR() condition containing errno.
+ *
+ * Use of id names is optional.
+ */
+static inline struct reset_control *of_reset_control_get_shared(
+ struct device_node *node, const char *id)
+{
+ return __of_reset_control_get(node, id, 0, 1);
+}
+
+/**
+ * of_reset_control_get_exclusive_by_index - Lookup and obtain an exclusive
+ * reference to a reset controller
+ * by index.
* @node: device to be reset by the controller
* @index: index of the reset controller
*
@@ -167,49 +199,60 @@ static inline struct reset_control *of_reset_control_get(
* in whatever order. Returns a struct reset_control or IS_ERR() condition
* containing errno.
*/
-static inline struct reset_control *of_reset_control_get_by_index(
+static inline struct reset_control *of_reset_control_get_exclusive_by_index(
struct device_node *node, int index)
{
return __of_reset_control_get(node, NULL, index, 0);
}
/**
- * devm_reset_control_get - resource managed reset_control_get()
- * @dev: device to be reset by the controller
- * @id: reset line name
+ * of_reset_control_get_shared_by_index - Lookup and obtain an shared
+ * reference to a reset controller
+ * by index.
+ * @node: device to be reset by the controller
+ * @index: index of the reset controller
+ *
+ * When a reset-control is shared, the behavior of reset_control_assert /
+ * deassert is changed, the reset-core will keep track of a deassert_count
+ * and only (re-)assert the reset after reset_control_assert has been called
+ * as many times as reset_control_deassert was called. Also see the remark
+ * about shared reset-controls in the reset_control_assert docs.
+ *
+ * Calling reset_control_assert without first calling reset_control_deassert
+ * is not allowed on a shared reset control. Calling reset_control_reset is
+ * also not allowed on a shared reset control.
+ * Returns a struct reset_control or IS_ERR() condition containing errno.
*
- * Managed reset_control_get(). For reset controllers returned from this
- * function, reset_control_put() is called automatically on driver detach.
- * See reset_control_get() for more information.
+ * This is to be used to perform a list of resets for a device or power domain
+ * in whatever order. Returns a struct reset_control or IS_ERR() condition
+ * containing errno.
*/
-static inline struct reset_control *__must_check devm_reset_control_get(
- struct device *dev, const char *id)
-{
-#ifndef CONFIG_RESET_CONTROLLER
- WARN_ON(1);
-#endif
- return __devm_reset_control_get(dev, id, 0, 0);
-}
-
-static inline struct reset_control *devm_reset_control_get_optional(
- struct device *dev, const char *id)
+static inline struct reset_control *of_reset_control_get_shared_by_index(
+ struct device_node *node, int index)
{
- return __devm_reset_control_get(dev, id, 0, 0);
+ return __of_reset_control_get(node, NULL, index, 1);
}
/**
- * devm_reset_control_get_by_index - resource managed reset_control_get
+ * devm_reset_control_get_exclusive - resource managed
+ * reset_control_get_exclusive()
* @dev: device to be reset by the controller
- * @index: index of the reset controller
+ * @id: reset line name
*
- * Managed reset_control_get(). For reset controllers returned from this
- * function, reset_control_put() is called automatically on driver detach.
- * See reset_control_get() for more information.
+ * Managed reset_control_get_exclusive(). For reset controllers returned
+ * from this function, reset_control_put() is called automatically on driver
+ * detach.
+ *
+ * See reset_control_get_exclusive() for more information.
*/
-static inline struct reset_control *devm_reset_control_get_by_index(
- struct device *dev, int index)
+static inline struct reset_control *
+__must_check devm_reset_control_get_exclusive(struct device *dev,
+ const char *id)
{
- return __devm_reset_control_get(dev, NULL, index, 0);
+#ifndef CONFIG_RESET_CONTROLLER
+ WARN_ON(1);
+#endif
+ return __devm_reset_control_get(dev, id, 0, 0);
}
/**
@@ -227,6 +270,36 @@ static inline struct reset_control *devm_reset_control_get_shared(
return __devm_reset_control_get(dev, id, 0, 1);
}
+static inline struct reset_control *devm_reset_control_get_optional_exclusive(
+ struct device *dev, const char *id)
+{
+ return __devm_reset_control_get(dev, id, 0, 0);
+}
+
+static inline struct reset_control *devm_reset_control_get_optional_shared(
+ struct device *dev, const char *id)
+{
+ return __devm_reset_control_get(dev, id, 0, 1);
+}
+
+/**
+ * devm_reset_control_get_exclusive_by_index - resource managed
+ * reset_control_get_exclusive()
+ * @dev: device to be reset by the controller
+ * @index: index of the reset controller
+ *
+ * Managed reset_control_get_exclusive(). For reset controllers returned from
+ * this function, reset_control_put() is called automatically on driver
+ * detach.
+ *
+ * See reset_control_get_exclusive() for more information.
+ */
+static inline struct reset_control *
+devm_reset_control_get_exclusive_by_index(struct device *dev, int index)
+{
+ return __devm_reset_control_get(dev, NULL, index, 0);
+}
+
/**
* devm_reset_control_get_shared_by_index - resource managed
* reset_control_get_shared
@@ -237,10 +310,60 @@ static inline struct reset_control *devm_reset_control_get_shared(
* this function, reset_control_put() is called automatically on driver detach.
* See reset_control_get_shared() for more information.
*/
-static inline struct reset_control *devm_reset_control_get_shared_by_index(
- struct device *dev, int index)
+static inline struct reset_control *
+devm_reset_control_get_shared_by_index(struct device *dev, int index)
{
return __devm_reset_control_get(dev, NULL, index, 1);
}
+/*
+ * TEMPORARY calls to use during transition:
+ *
+ * of_reset_control_get() => of_reset_control_get_exclusive()
+ *
+ * These inline function calls will be removed once all consumers
+ * have been moved over to the new explicit API.
+ */
+static inline struct reset_control *reset_control_get(
+ struct device *dev, const char *id)
+{
+ return reset_control_get_exclusive(dev, id);
+}
+
+static inline struct reset_control *reset_control_get_optional(
+ struct device *dev, const char *id)
+{
+ return reset_control_get_optional_exclusive(dev, id);
+}
+
+static inline struct reset_control *of_reset_control_get(
+ struct device_node *node, const char *id)
+{
+ return of_reset_control_get_exclusive(node, id);
+}
+
+static inline struct reset_control *of_reset_control_get_by_index(
+ struct device_node *node, int index)
+{
+ return of_reset_control_get_exclusive_by_index(node, index);
+}
+
+static inline struct reset_control *devm_reset_control_get(
+ struct device *dev, const char *id)
+{
+ return devm_reset_control_get_exclusive(dev, id);
+}
+
+static inline struct reset_control *devm_reset_control_get_optional(
+ struct device *dev, const char *id)
+{
+ return devm_reset_control_get_optional_exclusive(dev, id);
+
+}
+
+static inline struct reset_control *devm_reset_control_get_by_index(
+ struct device *dev, int index)
+{
+ return devm_reset_control_get_exclusive_by_index(dev, index);
+}
#endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index d1c12d160ace..d37fbb34d06f 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -156,6 +156,7 @@ extern void downgrade_write(struct rw_semaphore *sem);
*/
extern void down_read_nested(struct rw_semaphore *sem, int subclass);
extern void down_write_nested(struct rw_semaphore *sem, int subclass);
+extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass);
extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
# define down_write_nest_lock(sem, nest_lock) \
@@ -176,6 +177,7 @@ extern void up_read_non_owner(struct rw_semaphore *sem);
# define down_read_nested(sem, subclass) down_read(sem)
# define down_write_nest_lock(sem, nest_lock) down_write(sem)
# define down_write_nested(sem, subclass) down_write(sem)
+# define down_write_killable_nested(sem, subclass) down_write_killable(sem)
# define down_read_non_owner(sem) down_read(sem)
# define up_read_non_owner(sem) up_read(sem)
#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 21c26e78aec5..253538f29ade 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1539,6 +1539,7 @@ struct task_struct {
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
+ unsigned sched_remote_wakeup:1;
unsigned :0; /* force alignment to the next boundary */
/* unserialized, strictly 'current' */
@@ -2744,10 +2745,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm)
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
-/* same as above but performs the slow path from the async kontext. Can
+#ifdef CONFIG_MMU
+/* same as above but performs the slow path from the async context. Can
* be called from the atomic context as well
*/
extern void mmput_async(struct mm_struct *);
+#endif
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
@@ -3004,7 +3007,7 @@ static inline int object_is_on_stack(void *obj)
return (obj >= stack) && (obj < (stack + THREAD_SIZE));
}
-extern void thread_info_cache_init(void);
+extern void thread_stack_cache_init(void);
#ifdef CONFIG_DEBUG_STACK_USAGE
static inline unsigned long stack_not_used(struct task_struct *p)
diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index dacb5e711994..de1f64318fc4 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -765,6 +765,8 @@ struct sctp_info {
__u8 sctpi_s_disable_fragments;
__u8 sctpi_s_v4mapped;
__u8 sctpi_s_frag_interleave;
+ __u32 sctpi_s_type;
+ __u32 __reserved3;
};
struct sctp_infox {
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e0582106ef4f..ead97654c4e9 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -277,7 +277,10 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
static inline int raw_read_seqcount_latch(seqcount_t *s)
{
- return lockless_dereference(s->sequence);
+ int seq = READ_ONCE(s->sequence);
+ /* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
+ smp_read_barrier_depends();
+ return seq;
}
/**
@@ -331,7 +334,7 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
* unsigned seq, idx;
*
* do {
- * seq = lockless_dereference(latch->seq);
+ * seq = raw_read_seqcount_latch(&latch->seq);
*
* idx = seq & 0x01;
* entry = data_query(latch->data[idx], ...);
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 665cd0cd18b8..d1faa019c02a 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -111,22 +111,6 @@ static inline void sysfs_slab_remove(struct kmem_cache *s)
}
#endif
-
-/**
- * virt_to_obj - returns address of the beginning of object.
- * @s: object's kmem_cache
- * @slab_page: address of slab page
- * @x: address within object memory range
- *
- * Returns address of the beginning of object
- */
-static inline void *virt_to_obj(struct kmem_cache *s,
- const void *slab_page,
- const void *x)
-{
- return (void *)x - ((x - slab_page) % s->size);
-}
-
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 4018b48f2b3b..a0596ca0e80a 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -36,6 +36,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
{
switch (sk->sk_family) {
case AF_INET:
+ if (sk->sk_type == SOCK_RAW)
+ return SKNLGRP_NONE;
+
switch (sk->sk_protocol) {
case IPPROTO_TCP:
return SKNLGRP_INET_TCP_DESTROY;
@@ -45,6 +48,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
return SKNLGRP_NONE;
}
case AF_INET6:
+ if (sk->sk_type == SOCK_RAW)
+ return SKNLGRP_NONE;
+
switch (sk->sk_protocol) {
case IPPROTO_TCP:
return SKNLGRP_INET6_TCP_DESTROY;
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 857a9a1d82b5..1f03483f61e5 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -372,6 +372,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
* @unprepare_message: undo any work done by prepare_message().
* @spi_flash_read: to support spi-controller hardwares that provide
* accelerated interface to read from flash devices.
+ * @flash_read_supported: spi device supports flash read
* @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
* number. Any individual value may be -ENOENT for CS lines that
* are not GPIOs (driven by the SPI controller itself).
@@ -529,6 +530,7 @@ struct spi_master {
struct spi_message *message);
int (*spi_flash_read)(struct spi_device *spi,
struct spi_flash_read_message *msg);
+ bool (*flash_read_supported)(struct spi_device *spi);
/*
* These hooks are for drivers that use a generic implementation
@@ -1158,7 +1160,9 @@ struct spi_flash_read_message {
/* SPI core interface for flash read support */
static inline bool spi_flash_read_supported(struct spi_device *spi)
{
- return spi->master->spi_flash_read ? true : false;
+ return spi->master->spi_flash_read &&
+ (!spi->master->flash_read_supported ||
+ spi->master->flash_read_supported(spi));
}
int spi_flash_read(struct spi_device *spi,
diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h
new file mode 100644
index 000000000000..451771d9b9c0
--- /dev/null
+++ b/include/linux/stringhash.h
@@ -0,0 +1,76 @@
+#ifndef __LINUX_STRINGHASH_H
+#define __LINUX_STRINGHASH_H
+
+#include <linux/compiler.h> /* For __pure */
+#include <linux/types.h> /* For u32, u64 */
+
+/*
+ * Routines for hashing strings of bytes to a 32-bit hash value.
+ *
+ * These hash functions are NOT GUARANTEED STABLE between kernel
+ * versions, architectures, or even repeated boots of the same kernel.
+ * (E.g. they may depend on boot-time hardware detection or be
+ * deliberately randomized.)
+ *
+ * They are also not intended to be secure against collisions caused by
+ * malicious inputs; much slower hash functions are required for that.
+ *
+ * They are optimized for pathname components, meaning short strings.
+ * Even if a majority of files have longer names, the dynamic profile of
+ * pathname components skews short due to short directory names.
+ * (E.g. /usr/lib/libsesquipedalianism.so.3.141.)
+ */
+
+/*
+ * Version 1: one byte at a time. Example of use:
+ *
+ * unsigned long hash = init_name_hash;
+ * while (*p)
+ * hash = partial_name_hash(tolower(*p++), hash);
+ * hash = end_name_hash(hash);
+ *
+ * Although this is designed for bytes, fs/hfsplus/unicode.c
+ * abuses it to hash 16-bit values.
+ */
+
+/* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
+#define init_name_hash() 0
+
+/* partial hash update function. Assume roughly 4 bits per character */
+static inline unsigned long
+partial_name_hash(unsigned long c, unsigned long prevhash)
+{
+ return (prevhash + (c << 4) + (c >> 4)) * 11;
+}
+
+/*
+ * Finally: cut down the number of bits to a int value (and try to avoid
+ * losing bits)
+ */
+static inline unsigned long end_name_hash(unsigned long hash)
+{
+ return (unsigned int)hash;
+}
+
+/*
+ * Version 2: One word (32 or 64 bits) at a time.
+ * If CONFIG_DCACHE_WORD_ACCESS is defined (meaning <asm/word-at-a-time.h>
+ * exists, which describes major Linux platforms like x86 and ARM), then
+ * this computes a different hash function much faster.
+ *
+ * If not set, this falls back to a wrapper around the preceding.
+ */
+extern unsigned int __pure full_name_hash(const char *, unsigned int);
+
+/*
+ * A hash_len is a u64 with the hash of a string in the low
+ * half and the length in the high half.
+ */
+#define hashlen_hash(hashlen) ((u32)(hashlen))
+#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
+#define hashlen_create(hash, len) ((u64)(len)<<32 | (u32)(hash))
+
+/* Return the "hash_len" (hash and length) of a null-terminated string */
+extern u64 __pure hashlen_string(const char *name);
+
+#endif /* __LINUX_STRINGHASH_H */
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 6a241a277249..899791573a40 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -127,7 +127,7 @@ struct rpc_authops {
void (*destroy)(struct rpc_auth *);
struct rpc_cred * (*lookup_cred)(struct rpc_auth *, struct auth_cred *, int);
- struct rpc_cred * (*crcreate)(struct rpc_auth*, struct auth_cred *, int);
+ struct rpc_cred * (*crcreate)(struct rpc_auth*, struct auth_cred *, int, gfp_t);
int (*list_pseudoflavors)(rpc_authflavor_t *, int);
rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *);
int (*flavor2info)(rpc_authflavor_t,
@@ -167,6 +167,7 @@ void rpc_destroy_authunix(void);
struct rpc_cred * rpc_lookup_cred(void);
struct rpc_cred * rpc_lookup_cred_nonblock(void);
+struct rpc_cred * rpc_lookup_generic_cred(struct auth_cred *, int, gfp_t);
struct rpc_cred * rpc_lookup_machine_cred(const char *service_name);
int rpcauth_register(const struct rpc_authops *);
int rpcauth_unregister(const struct rpc_authops *);
@@ -178,7 +179,7 @@ rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t,
int rpcauth_get_gssinfo(rpc_authflavor_t,
struct rpcsec_gss_info *);
int rpcauth_list_flavors(rpc_authflavor_t *, int);
-struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int);
+struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int, gfp_t);
void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *);
struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *, int);
struct rpc_cred * rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int);
@@ -201,9 +202,28 @@ char * rpcauth_stringify_acceptor(struct rpc_cred *);
static inline
struct rpc_cred * get_rpccred(struct rpc_cred *cred)
{
- atomic_inc(&cred->cr_count);
+ if (cred != NULL)
+ atomic_inc(&cred->cr_count);
return cred;
}
+/**
+ * get_rpccred_rcu - get a reference to a cred using rcu-protected pointer
+ * @cred: cred of which to take a reference
+ *
+ * In some cases, we may have a pointer to a credential to which we
+ * want to take a reference, but don't already have one. Because these
+ * objects are freed using RCU, we can access the cr_count while its
+ * on its way to destruction and only take a reference if it's not already
+ * zero.
+ */
+static inline struct rpc_cred *
+get_rpccred_rcu(struct rpc_cred *cred)
+{
+ if (atomic_inc_not_zero(&cred->cr_count))
+ return cred;
+ return NULL;
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_SUNRPC_AUTH_H */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 9a7ddbaf116e..b6810c92b8bb 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -137,8 +137,6 @@ struct rpc_create_args {
#define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9)
struct rpc_clnt *rpc_create(struct rpc_create_args *args);
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
- struct rpc_xprt *xprt);
struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *,
const struct rpc_program *, u32);
struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
@@ -176,6 +174,7 @@ void rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
int rpc_protocol(struct rpc_clnt *);
struct net * rpc_net_ns(struct rpc_clnt *);
size_t rpc_max_payload(struct rpc_clnt *);
+size_t rpc_max_bc_payload(struct rpc_clnt *);
unsigned long rpc_get_timeout(struct rpc_clnt *clnt);
void rpc_force_rebind(struct rpc_clnt *);
size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index 807371357160..59cbf16eaeb5 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -158,9 +158,9 @@ typedef __be32 rpc_fraghdr;
/*
* Note that RFC 1833 does not put any size restrictions on the
- * netid string, but all currently defined netid's fit in 4 bytes.
+ * netid string, but all currently defined netid's fit in 5 bytes.
*/
-#define RPCBIND_MAXNETIDLEN (4u)
+#define RPCBIND_MAXNETIDLEN (5u)
/*
* Universal addresses are introduced in RFC 1833 and further spelled
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 3081339968c3..d6917b896d3a 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -199,7 +199,7 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
struct xdr_buf *rcvbuf);
/* svc_rdma_marshal.c */
-extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg *, struct svc_rqst *);
+extern int svc_rdma_xdr_decode_req(struct xdr_buf *);
extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
struct rpcrdma_msg *,
enum rpcrdma_errcode, __be32 *);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b7dabc4baafd..79ba50856707 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -84,6 +84,7 @@ struct svc_xprt {
struct net *xpt_net;
struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */
+ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */
};
static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index c00f53a4ccdd..91d5a5d6f52b 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -16,6 +16,7 @@
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/hash.h>
+#include <linux/stringhash.h>
#include <linux/cred.h>
struct svc_cred {
@@ -165,41 +166,18 @@ extern int svcauth_unix_set_client(struct svc_rqst *rqstp);
extern int unix_gid_cache_create(struct net *net);
extern void unix_gid_cache_destroy(struct net *net);
-static inline unsigned long hash_str(char *name, int bits)
+/*
+ * The <stringhash.h> functions are good enough that we don't need to
+ * use hash_32() on them; just extracting the high bits is enough.
+ */
+static inline unsigned long hash_str(char const *name, int bits)
{
- unsigned long hash = 0;
- unsigned long l = 0;
- int len = 0;
- unsigned char c;
- do {
- if (unlikely(!(c = *name++))) {
- c = (char)len; len = -1;
- }
- l = (l << 8) | c;
- len++;
- if ((len & (BITS_PER_LONG/8-1))==0)
- hash = hash_long(hash^l, BITS_PER_LONG);
- } while (len);
- return hash >> (BITS_PER_LONG - bits);
+ return hashlen_hash(hashlen_string(name)) >> (32 - bits);
}
-static inline unsigned long hash_mem(char *buf, int length, int bits)
+static inline unsigned long hash_mem(char const *buf, int length, int bits)
{
- unsigned long hash = 0;
- unsigned long l = 0;
- int len = 0;
- unsigned char c;
- do {
- if (len == length) {
- c = (char)len; len = -1;
- } else
- c = *buf++;
- l = (l << 8) | c;
- len++;
- if ((len & (BITS_PER_LONG/8-1))==0)
- hash = hash_long(hash^l, BITS_PER_LONG);
- } while (len);
- return hash >> (BITS_PER_LONG - bits);
+ return full_name_hash(buf, length) >> (32 - bits);
}
#endif /* __KERNEL__ */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index fb0d212e0d3a..5e3e1b63dbb3 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -142,6 +142,7 @@ struct rpc_xprt_ops {
int (*bc_setup)(struct rpc_xprt *xprt,
unsigned int min_reqs);
int (*bc_up)(struct svc_serv *serv, struct net *net);
+ size_t (*bc_maxpayload)(struct rpc_xprt *xprt);
void (*bc_free_rqst)(struct rpc_rqst *rqst);
void (*bc_destroy)(struct rpc_xprt *xprt,
unsigned int max_reqs);
@@ -296,6 +297,7 @@ struct xprt_create {
size_t addrlen;
const char *servername;
struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */
+ struct rpc_xprt_switch *bc_xps;
unsigned int flags;
};
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index 767190b01363..39267dc3486a 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -52,7 +52,9 @@
#define RPCRDMA_DEF_SLOT_TABLE (128U)
#define RPCRDMA_MAX_SLOT_TABLE (256U)
-#define RPCRDMA_DEF_INLINE (1024) /* default inline max */
+#define RPCRDMA_MIN_INLINE (1024) /* min inline thresh */
+#define RPCRDMA_DEF_INLINE (1024) /* default inline thresh */
+#define RPCRDMA_MAX_INLINE (3068) /* max inline thresh */
/* Memory registration strategies, by number.
* This is part of a kernel / user space API. Do not remove. */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 1b8a5a7876ce..ee517bef0db0 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -335,11 +335,14 @@ struct thermal_genl_event {
* @get_trend: a pointer to a function that reads the sensor temperature trend.
* @set_emul_temp: a pointer to a function that sets sensor emulated
* temperature.
+ * @set_trip_temp: a pointer to a function that sets the trip temperature on
+ * hardware.
*/
struct thermal_zone_of_device_ops {
int (*get_temp)(void *, int *);
int (*get_trend)(void *, long *);
int (*set_emul_temp)(void *, int);
+ int (*set_trip_temp)(void *, int, int);
};
/**
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 37dbacf84849..816b7543f81b 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -21,6 +21,9 @@ static inline int do_sys_settimeofday(const struct timespec *tv,
struct timespec64 ts64;
if (!tv)
+ return do_sys_settimeofday64(NULL, tz);
+
+ if (!timespec_valid(tv))
return -EINVAL;
ts64 = timespec_to_timespec64(*tv);
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index 966889a20ea3..e479033bd782 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -180,11 +180,11 @@ struct ehci_regs {
* PORTSCx
*/
/* HOSTPC: offset 0x84 */
- u32 hostpc[1]; /* HOSTPC extension */
+ u32 hostpc[0]; /* HOSTPC extension */
#define HOSTPC_PHCD (1<<22) /* Phy clock disable */
#define HOSTPC_PSPD (3<<25) /* Port speed detection */
- u32 reserved5[16];
+ u32 reserved5[17];
/* USBMODE_EX: offset 0xc8 */
u32 usbmode_ex; /* USB Device mode extension */
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 457651bf45b0..fefe8b06a63d 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -1034,6 +1034,8 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget)
* @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL,
* this driver will be bound to any available UDC.
* @pending: UDC core private data used for deferred probe of this driver.
+ * @match_existing_only: If udc is not found, return an error and don't add this
+ * gadget driver to list of pending driver
*
* Devices are disabled till a gadget driver successfully bind()s, which
* means the driver will handle setup() requests needed to enumerate (and
@@ -1097,6 +1099,7 @@ struct usb_gadget_driver {
char *udc_name;
struct list_head pending;
+ unsigned match_existing_only:1;
};
diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h
index 0b3da40a525e..d315c8907869 100644
--- a/include/linux/usb/musb.h
+++ b/include/linux/usb/musb.h
@@ -142,10 +142,11 @@ enum musb_vbus_id_status {
};
#if IS_ENABLED(CONFIG_USB_MUSB_HDRC)
-void musb_mailbox(enum musb_vbus_id_status status);
+int musb_mailbox(enum musb_vbus_id_status status);
#else
-static inline void musb_mailbox(enum musb_vbus_id_status status)
+static inline int musb_mailbox(enum musb_vbus_id_status status)
{
+ return 0;
}
#endif
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 1cc4c578deb9..94079bab9243 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -33,8 +33,8 @@ struct xattr_handler {
struct inode *inode, const char *name, void *buffer,
size_t size);
int (*set)(const struct xattr_handler *, struct dentry *dentry,
- const char *name, const void *buffer, size_t size,
- int flags);
+ struct inode *inode, const char *name, const void *buffer,
+ size_t size, int flags);
};
const char *xattr_full_name(const struct xattr_handler *, const char *);
@@ -54,7 +54,8 @@ int vfs_removexattr(struct dentry *, const char *);
ssize_t generic_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size);
ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
-int generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags);
+int generic_setxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value, size_t size, int flags);
int generic_removexattr(struct dentry *dentry, const char *name);
ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name,
char **xattr_value, size_t size, gfp_t flags);
diff --git a/include/media/v4l2-mc.h b/include/media/v4l2-mc.h
index 98a938aabdfb..7a8d6037a4bb 100644
--- a/include/media/v4l2-mc.h
+++ b/include/media/v4l2-mc.h
@@ -1,7 +1,7 @@
/*
* v4l2-mc.h - Media Controller V4L2 types and prototypes
*
- * Copyright (C) 2016 Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+ * Copyright (C) 2016 Mauro Carvalho Chehab <mchehab@kernel.org>
* Copyright (C) 2006-2010 Nokia Corporation
* Copyright (c) 2016 Intel Corporation.
*
diff --git a/include/net/compat.h b/include/net/compat.h
index 48103cf94e97..13de0ccaa059 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -42,6 +42,7 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
struct sockaddr __user **, struct iovec **);
+struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *,
unsigned int);
asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
diff --git a/include/net/gre.h b/include/net/gre.h
index 5dce30a6abe3..7a54a31d1d4c 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -26,7 +26,7 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version);
struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
u8 name_assign_type);
int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
- bool *csum_err, __be16 proto);
+ bool *csum_err, __be16 proto, int nhs);
static inline int gre_calc_hlen(__be16 o_flags)
{
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index d325c81332e3..43a5a0e4524c 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -63,6 +63,8 @@ struct ip6_tnl_encap_ops {
u8 *protocol, struct flowi6 *fl6);
};
+#ifdef CONFIG_INET
+
extern const struct ip6_tnl_encap_ops __rcu *
ip6tun_encaps[MAX_IPTUN_ENCAP_OPS];
@@ -138,7 +140,6 @@ struct net *ip6_tnl_get_link_net(const struct net_device *dev);
int ip6_tnl_get_iflink(const struct net_device *dev);
int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu);
-#ifdef CONFIG_INET
static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
struct net_device *dev)
{
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index af4c10ebb241..cd6018a9ee24 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1232,7 +1232,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
const char *ip_vs_state_name(__u16 proto, int state);
void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
-int ip_vs_check_template(struct ip_vs_conn *ct);
+int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest);
void ip_vs_random_dropentry(struct netns_ipvs *ipvs);
int ip_vs_conn_init(void);
void ip_vs_conn_cleanup(void);
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 9c5638ad872e..0dbce55437f2 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -28,8 +28,8 @@ struct nf_queue_handler {
struct nf_hook_ops *ops);
};
-void nf_register_queue_handler(const struct nf_queue_handler *qh);
-void nf_unregister_queue_handler(void);
+void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh);
+void nf_unregister_queue_handler(struct net *net);
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
void nf_queue_entry_get_refs(struct nf_queue_entry *entry);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 092235458691..f7c291ff4074 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -167,6 +167,7 @@ struct nft_set_elem {
struct nft_set;
struct nft_set_iter {
+ u8 genmask;
unsigned int count;
unsigned int skip;
int err;
diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h
index 38aa4983e2a9..36d723579af2 100644
--- a/include/net/netns/netfilter.h
+++ b/include/net/netns/netfilter.h
@@ -5,11 +5,13 @@
struct proc_dir_entry;
struct nf_logger;
+struct nf_queue_handler;
struct netns_nf {
#if defined CONFIG_PROC_FS
struct proc_dir_entry *proc_netfilter;
#endif
+ const struct nf_queue_handler __rcu *queue_handler;
const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO];
#ifdef CONFIG_SYSCTL
struct ctl_table_header *nf_log_dir_header;
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 0f7efa88f210..3722dda0199d 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -392,16 +392,20 @@ struct tc_cls_u32_offload {
};
};
-static inline bool tc_should_offload(struct net_device *dev, u32 flags)
+static inline bool tc_should_offload(const struct net_device *dev,
+ const struct tcf_proto *tp, u32 flags)
{
+ const struct Qdisc *sch = tp->q;
+ const struct Qdisc_class_ops *cops = sch->ops->cl_ops;
+
if (!(dev->features & NETIF_F_HW_TC))
return false;
-
if (flags & TCA_CLS_FLAGS_SKIP_HW)
return false;
-
if (!dev->netdev_ops->ndo_setup_tc)
return false;
+ if (cops && cops->tcf_cl_offload)
+ return cops->tcf_cl_offload(tp->classid);
return true;
}
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 401038d2f9b8..fea53f4d92ca 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -61,6 +61,7 @@ psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound)
}
struct qdisc_watchdog {
+ u64 last_expires;
struct hrtimer timer;
struct Qdisc *qdisc;
};
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a1fd76c22a59..62d553184e91 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -168,6 +168,7 @@ struct Qdisc_class_ops {
/* Filter manipulation */
struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long);
+ bool (*tcf_cl_offload)(u32 classid);
unsigned long (*bind_tcf)(struct Qdisc *, unsigned long,
u32 classid);
void (*unbind_tcf)(struct Qdisc *, unsigned long);
@@ -691,9 +692,11 @@ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch)
/* we can reuse ->gso_skb because peek isn't called for root qdiscs */
if (!sch->gso_skb) {
sch->gso_skb = sch->dequeue(sch);
- if (sch->gso_skb)
+ if (sch->gso_skb) {
/* it's still part of the queue */
+ qdisc_qstats_backlog_inc(sch, sch->gso_skb);
sch->q.qlen++;
+ }
}
return sch->gso_skb;
@@ -706,6 +709,7 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
if (skb) {
sch->gso_skb = NULL;
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
} else {
skb = sch->dequeue(sch);
diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index dc9a09aefb33..c55facd17b7e 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -36,7 +36,7 @@ struct tcf_meta_ops {
int (*encode)(struct sk_buff *, void *, struct tcf_meta_info *);
int (*decode)(struct sk_buff *, void *, u16 len);
int (*get)(struct sk_buff *skb, struct tcf_meta_info *mi);
- int (*alloc)(struct tcf_meta_info *, void *);
+ int (*alloc)(struct tcf_meta_info *, void *, gfp_t);
void (*release)(struct tcf_meta_info *);
int (*validate)(void *val, int len);
struct module *owner;
@@ -48,8 +48,8 @@ int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi);
int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
const void *dval);
-int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval);
-int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval);
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp);
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp);
int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi);
int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi);
int ife_validate_meta_u32(void *val, int len);
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 37dd534cbeab..c8a773ffe23b 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -239,12 +239,15 @@ struct ib_vendor_mad {
#define IB_MGMT_CLASSPORTINFO_ATTR_ID cpu_to_be16(0x0001)
+#define IB_CLASS_PORT_INFO_RESP_TIME_MASK 0x1F
+#define IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE 5
+
struct ib_class_port_info {
u8 base_version;
u8 class_version;
__be16 capability_mask;
- u8 reserved[3];
- u8 resp_time_value;
+ /* 27 bits for cap_mask2, 5 bits for resp_time */
+ __be32 cap_mask2_resp_time;
u8 redirect_gid[16];
__be32 redirect_tcslfl;
__be16 redirect_lid;
@@ -259,6 +262,59 @@ struct ib_class_port_info {
__be32 trap_qkey;
};
+/**
+ * ib_get_cpi_resp_time - Returns the resp_time value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u8 ib_get_cpi_resp_time(struct ib_class_port_info *cpi)
+{
+ return (u8)(be32_to_cpu(cpi->cap_mask2_resp_time) &
+ IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_set_cpi_resptime - Sets the response time in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @rtime: The response time to set.
+ */
+static inline void ib_set_cpi_resp_time(struct ib_class_port_info *cpi,
+ u8 rtime)
+{
+ cpi->cap_mask2_resp_time =
+ (cpi->cap_mask2_resp_time &
+ cpu_to_be32(~IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+ cpu_to_be32(rtime & IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_get_cpi_capmask2 - Returns the capmask2 value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u32 ib_get_cpi_capmask2(struct ib_class_port_info *cpi)
+{
+ return (be32_to_cpu(cpi->cap_mask2_resp_time) >>
+ IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
+/**
+ * ib_set_cpi_capmask2 - Sets the capmask2 in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @capmask2: The capmask2 to set.
+ */
+static inline void ib_set_cpi_capmask2(struct ib_class_port_info *cpi,
+ u32 capmask2)
+{
+ cpi->cap_mask2_resp_time =
+ (cpi->cap_mask2_resp_time &
+ cpu_to_be32(IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+ cpu_to_be32(capmask2 <<
+ IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
struct ib_mad_notice_attr {
u8 generic_type;
u8 prod_type_msb;
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index 0f3daae44bf9..b13419ce99ff 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -103,6 +103,9 @@ enum {
IB_OPCODE_ATOMIC_ACKNOWLEDGE = 0x12,
IB_OPCODE_COMPARE_SWAP = 0x13,
IB_OPCODE_FETCH_ADD = 0x14,
+ /* opcode 0x15 is reserved */
+ IB_OPCODE_SEND_LAST_WITH_INVALIDATE = 0x16,
+ IB_OPCODE_SEND_ONLY_WITH_INVALIDATE = 0x17,
/* real constants follow -- see comment about above IB_OPCODE()
macro for more details */
@@ -129,6 +132,8 @@ enum {
IB_OPCODE(RC, ATOMIC_ACKNOWLEDGE),
IB_OPCODE(RC, COMPARE_SWAP),
IB_OPCODE(RC, FETCH_ADD),
+ IB_OPCODE(RC, SEND_LAST_WITH_INVALIDATE),
+ IB_OPCODE(RC, SEND_ONLY_WITH_INVALIDATE),
/* UC */
IB_OPCODE(UC, SEND_FIRST),
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index cdc1c81aa275..384041669489 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -94,6 +94,8 @@ enum ib_sa_selector {
IB_SA_BEST = 3
};
+#define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT BIT(12)
+
/*
* Structures for SA records are named "struct ib_sa_xxx_rec." No
* attempt is made to pack structures to match the physical layout of
@@ -439,4 +441,14 @@ int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
void *context,
struct ib_sa_query **sa_query);
+/* Support get SA ClassPortInfo */
+int ib_sa_classport_info_rec_query(struct ib_sa_client *client,
+ struct ib_device *device, u8 port_num,
+ int timeout_ms, gfp_t gfp_mask,
+ void (*callback)(int status,
+ struct ib_class_port_info *resp,
+ void *context),
+ void *context,
+ struct ib_sa_query **sa_query);
+
#endif /* IB_SA_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fc0320c004a3..7e440d41487a 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -217,10 +217,10 @@ enum ib_device_cap_flags {
IB_DEVICE_CROSS_CHANNEL = (1 << 27),
IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29),
IB_DEVICE_SIGNATURE_HANDOVER = (1 << 30),
- IB_DEVICE_ON_DEMAND_PAGING = (1 << 31),
+ IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31),
IB_DEVICE_SG_GAPS_REG = (1ULL << 32),
- IB_DEVICE_VIRTUAL_FUNCTION = ((u64)1 << 33),
- IB_DEVICE_RAW_SCATTER_FCS = ((u64)1 << 34),
+ IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33),
+ IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34),
};
enum ib_signature_prot_cap {
@@ -403,56 +403,55 @@ enum ib_port_speed {
IB_SPEED_EDR = 32
};
-struct ib_protocol_stats {
- /* TBD... */
-};
-
-struct iw_protocol_stats {
- u64 ipInReceives;
- u64 ipInHdrErrors;
- u64 ipInTooBigErrors;
- u64 ipInNoRoutes;
- u64 ipInAddrErrors;
- u64 ipInUnknownProtos;
- u64 ipInTruncatedPkts;
- u64 ipInDiscards;
- u64 ipInDelivers;
- u64 ipOutForwDatagrams;
- u64 ipOutRequests;
- u64 ipOutDiscards;
- u64 ipOutNoRoutes;
- u64 ipReasmTimeout;
- u64 ipReasmReqds;
- u64 ipReasmOKs;
- u64 ipReasmFails;
- u64 ipFragOKs;
- u64 ipFragFails;
- u64 ipFragCreates;
- u64 ipInMcastPkts;
- u64 ipOutMcastPkts;
- u64 ipInBcastPkts;
- u64 ipOutBcastPkts;
-
- u64 tcpRtoAlgorithm;
- u64 tcpRtoMin;
- u64 tcpRtoMax;
- u64 tcpMaxConn;
- u64 tcpActiveOpens;
- u64 tcpPassiveOpens;
- u64 tcpAttemptFails;
- u64 tcpEstabResets;
- u64 tcpCurrEstab;
- u64 tcpInSegs;
- u64 tcpOutSegs;
- u64 tcpRetransSegs;
- u64 tcpInErrs;
- u64 tcpOutRsts;
-};
-
-union rdma_protocol_stats {
- struct ib_protocol_stats ib;
- struct iw_protocol_stats iw;
-};
+/**
+ * struct rdma_hw_stats
+ * @timestamp - Used by the core code to track when the last update was
+ * @lifespan - Used by the core code to determine how old the counters
+ * should be before being updated again. Stored in jiffies, defaults
+ * to 10 milliseconds, drivers can override the default be specifying
+ * their own value during their allocation routine.
+ * @name - Array of pointers to static names used for the counters in
+ * directory.
+ * @num_counters - How many hardware counters there are. If name is
+ * shorter than this number, a kernel oops will result. Driver authors
+ * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters)
+ * in their code to prevent this.
+ * @value - Array of u64 counters that are accessed by the sysfs code and
+ * filled in by the drivers get_stats routine
+ */
+struct rdma_hw_stats {
+ unsigned long timestamp;
+ unsigned long lifespan;
+ const char * const *names;
+ int num_counters;
+ u64 value[];
+};
+
+#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10
+/**
+ * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct
+ * for drivers.
+ * @names - Array of static const char *
+ * @num_counters - How many elements in array
+ * @lifespan - How many milliseconds between updates
+ */
+static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
+ const char * const *names, int num_counters,
+ unsigned long lifespan)
+{
+ struct rdma_hw_stats *stats;
+
+ stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64),
+ GFP_KERNEL);
+ if (!stats)
+ return NULL;
+ stats->names = names;
+ stats->num_counters = num_counters;
+ stats->lifespan = msecs_to_jiffies(lifespan);
+
+ return stats;
+}
+
/* Define bits for the various functionality this port needs to be supported by
* the core.
@@ -1707,8 +1706,29 @@ struct ib_device {
struct iw_cm_verbs *iwcm;
- int (*get_protocol_stats)(struct ib_device *device,
- union rdma_protocol_stats *stats);
+ /**
+ * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the
+ * driver initialized data. The struct is kfree()'ed by the sysfs
+ * core when the device is removed. A lifespan of -1 in the return
+ * struct tells the core to set a default lifespan.
+ */
+ struct rdma_hw_stats *(*alloc_hw_stats)(struct ib_device *device,
+ u8 port_num);
+ /**
+ * get_hw_stats - Fill in the counter value(s) in the stats struct.
+ * @index - The index in the value array we wish to have updated, or
+ * num_counters if we want all stats updated
+ * Return codes -
+ * < 0 - Error, no counters updated
+ * index - Updated the single counter pointed to by index
+ * num_counters - Updated all counters (will reset the timestamp
+ * and prevent further calls for lifespan milliseconds)
+ * Drivers are allowed to update all counters in leiu of just the
+ * one given in index at their option
+ */
+ int (*get_hw_stats)(struct ib_device *device,
+ struct rdma_hw_stats *stats,
+ u8 port, int index);
int (*query_device)(struct ib_device *device,
struct ib_device_attr *device_attr,
struct ib_udata *udata);
@@ -1926,6 +1946,8 @@ struct ib_device {
u8 node_type;
u8 phys_port_cnt;
struct ib_device_attr attrs;
+ struct attribute_group *hw_stats_ag;
+ struct rdma_hw_stats *hw_stats;
/**
* The following mandatory functions are used only at device
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index d57ceee90d26..9c9a27d42aaa 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -149,15 +149,15 @@ struct rvt_driver_params {
int qpn_res_end;
int nports;
int npkeys;
- u8 qos_shift;
char cq_name[RVT_CQN_MAX];
int node;
- int max_rdma_atomic;
int psn_mask;
int psn_shift;
int psn_modify_mask;
u32 core_cap_flags;
u32 max_mad_size;
+ u8 qos_shift;
+ u8 max_rdma_atomic;
};
/* Protection domain */
@@ -203,7 +203,9 @@ struct rvt_driver_provided {
/*
* Allocate a private queue pair data structure for driver specific
- * information which is opaque to rdmavt.
+ * information which is opaque to rdmavt. Errors are returned via
+ * ERR_PTR(err). The driver is free to return NULL or a valid
+ * pointer.
*/
void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
gfp_t gfp);
@@ -426,6 +428,15 @@ static inline unsigned rvt_get_npkeys(struct rvt_dev_info *rdi)
}
/*
+ * Return the max atomic suitable for determining
+ * the size of the ack ring buffer in a QP.
+ */
+static inline unsigned int rvt_max_atomic(struct rvt_dev_info *rdi)
+{
+ return rdi->dparms.max_rdma_atomic + 1;
+}
+
+/*
* Return the indexed PKEY from the port PKEY table.
*/
static inline u16 rvt_get_pkey(struct rvt_dev_info *rdi,
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 0e1ff2abfe92..6d23b879416a 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -211,8 +211,6 @@ struct rvt_mmap_info {
unsigned size;
};
-#define RVT_MAX_RDMA_ATOMIC 16
-
/*
* This structure holds the information that the send tasklet needs
* to send a RDMA read response or atomic operation.
@@ -282,8 +280,7 @@ struct rvt_qp {
atomic_t refcount ____cacheline_aligned_in_smp;
wait_queue_head_t wait;
- struct rvt_ack_entry s_ack_queue[RVT_MAX_RDMA_ATOMIC + 1]
- ____cacheline_aligned_in_smp;
+ struct rvt_ack_entry *s_ack_queue;
struct rvt_sge_state s_rdma_read_sge;
spinlock_t r_lock ____cacheline_aligned_in_smp; /* used for APM */
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index c3371fa548cb..4ac24f5a3308 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -74,6 +74,7 @@ enum iscsit_transport_type {
ISCSI_IWARP_TCP = 3,
ISCSI_IWARP_SCTP = 4,
ISCSI_INFINIBAND = 5,
+ ISCSI_CXGBIT = 6,
};
/* RFC-3720 7.1.4 Standard Connection State Diagram for a Target */
@@ -890,4 +891,30 @@ static inline u32 session_get_next_ttt(struct iscsi_session *session)
}
extern struct iscsi_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t);
+
+static inline void iscsit_thread_check_cpumask(
+ struct iscsi_conn *conn,
+ struct task_struct *p,
+ int mode)
+{
+ /*
+ * mode == 1 signals iscsi_target_tx_thread() usage.
+ * mode == 0 signals iscsi_target_rx_thread() usage.
+ */
+ if (mode == 1) {
+ if (!conn->conn_tx_reset_cpumask)
+ return;
+ conn->conn_tx_reset_cpumask = 0;
+ } else {
+ if (!conn->conn_rx_reset_cpumask)
+ return;
+ conn->conn_rx_reset_cpumask = 0;
+ }
+ /*
+ * Update the CPU mask for this single kthread so that
+ * both TX and RX kthreads are scheduled to run on the
+ * same CPU.
+ */
+ set_cpus_allowed_ptr(p, conn->conn_cpumask);
+}
#endif /* ISCSI_TARGET_CORE_H */
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 90e37faa2ede..40ac7cd80150 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -6,6 +6,7 @@ struct iscsit_transport {
#define ISCSIT_TRANSPORT_NAME 16
char name[ISCSIT_TRANSPORT_NAME];
int transport_type;
+ bool rdma_shutdown;
int priv_size;
struct module *owner;
struct list_head t_node;
@@ -22,6 +23,13 @@ struct iscsit_transport {
int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsi_cmd *);
int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsi_cmd *);
void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsi_cmd *);
+ int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsi_cmd *,
+ struct iscsi_datain_req *, const void *, u32);
+ void (*iscsit_release_cmd)(struct iscsi_conn *, struct iscsi_cmd *);
+ void (*iscsit_get_rx_pdu)(struct iscsi_conn *);
+ int (*iscsit_validate_params)(struct iscsi_conn *);
+ void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsi_cmd *,
+ struct iscsi_r2t *);
enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsi_conn *);
};
@@ -77,6 +85,18 @@ extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *,
extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *,
struct iscsi_logout_rsp *);
extern int iscsit_logout_post_handler(struct iscsi_cmd *, struct iscsi_conn *);
+extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsi_cmd *);
+extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsi_cmd *);
+extern int iscsit_add_reject(struct iscsi_conn *, u8, unsigned char *);
+extern int iscsit_reject_cmd(struct iscsi_cmd *, u8, unsigned char *);
+extern int iscsit_handle_snack(struct iscsi_conn *, unsigned char *);
+extern void iscsit_build_datain_pdu(struct iscsi_cmd *, struct iscsi_conn *,
+ struct iscsi_datain *,
+ struct iscsi_data_rsp *, bool);
+extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsi_cmd *,
+ bool);
+extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsi_cmd *, int);
+extern int iscsit_response_queue(struct iscsi_conn *, struct iscsi_cmd *, int);
/*
* From iscsi_target_device.c
*/
@@ -102,3 +122,24 @@ extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int);
extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *,
unsigned char *, __be32);
extern void iscsit_release_cmd(struct iscsi_cmd *);
+extern void iscsit_free_cmd(struct iscsi_cmd *, bool);
+extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *,
+ struct iscsi_conn *, u8);
+
+/*
+ * From iscsi_target_nego.c
+ */
+extern int iscsi_target_check_login_request(struct iscsi_conn *,
+ struct iscsi_login *);
+
+/*
+ * From iscsi_target_login.c
+ */
+extern __printf(2, 3) int iscsi_change_param_sprintf(
+ struct iscsi_conn *, const char *, ...);
+
+/*
+ * From iscsi_target_parameters.c
+ */
+extern struct iscsi_param *iscsi_find_param_from_key(
+ char *, struct iscsi_param_list *);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 3e0dd86360a2..b316b44d03f3 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -536,7 +536,6 @@ struct se_node_acl {
char initiatorname[TRANSPORT_IQN_LEN];
/* Used to signal demo mode created ACL, disabled by default */
bool dynamic_node_acl;
- bool acl_stop:1;
u32 queue_depth;
u32 acl_index;
enum target_prot_type saved_prot_type;
@@ -603,7 +602,6 @@ struct se_session {
struct list_head sess_cmd_list;
struct list_head sess_wait_list;
spinlock_t sess_cmd_lock;
- struct kref sess_kref;
void *sess_cmd_map;
struct percpu_ida sess_tag_pool;
};
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 78d88f03b296..de44462a7680 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -50,10 +50,6 @@ struct target_core_fabric_ops {
*/
int (*check_stop_free)(struct se_cmd *);
void (*release_cmd)(struct se_cmd *);
- /*
- * Called with spin_lock_bh(struct se_portal_group->session_lock held.
- */
- int (*shutdown_session)(struct se_session *);
void (*close_session)(struct se_session *);
u32 (*sess_get_index)(struct se_session *);
/*
@@ -123,8 +119,6 @@ void __transport_register_session(struct se_portal_group *,
struct se_node_acl *, struct se_session *, void *);
void transport_register_session(struct se_portal_group *,
struct se_node_acl *, struct se_session *, void *);
-int target_get_session(struct se_session *);
-void target_put_session(struct se_session *);
ssize_t target_show_dynamic_sessions(struct se_portal_group *, char *);
void transport_free_session(struct se_session *);
void target_put_nacl(struct se_node_acl *);
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 526fb3d2e43a..f28292d73ddb 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -108,7 +108,7 @@ TRACE_EVENT(kvm_ioapic_set_irq,
__entry->coalesced = coalesced;
),
- TP_printk("pin %u dst %x vec=%u (%s|%s|%s%s)%s",
+ TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s",
__entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e,
__print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
(__entry->e & (1<<11)) ? "logical" : "physical",
@@ -129,7 +129,7 @@ TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
__entry->e = e;
),
- TP_printk("dst %x vec=%u (%s|%s|%s%s)",
+ TP_printk("dst %x vec %u (%s|%s|%s%s)",
(u8)(__entry->e >> 56), (u8)__entry->e,
__print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
(__entry->e & (1<<11)) ? "logical" : "physical",
@@ -151,7 +151,7 @@ TRACE_EVENT(kvm_msi_set_irq,
__entry->data = data;
),
- TP_printk("dst %u vec %x (%s|%s|%s%s)",
+ TP_printk("dst %u vec %u (%s|%s|%s%s)",
(u8)(__entry->address >> 12), (u8)__entry->data,
__print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
(__entry->address & (1<<2)) ? "logical" : "physical",
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index c51afb71bfab..a26415b5151c 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -127,8 +127,11 @@ __SYSCALL(__NR_unlinkat, sys_unlinkat)
__SYSCALL(__NR_symlinkat, sys_symlinkat)
#define __NR_linkat 37
__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
#define __NR_renameat 38
__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
/* fs/namespace.c */
#define __NR_umount2 39
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 23c6960e94a4..2bdd1e3e7007 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -118,7 +118,7 @@ struct btrfs_ioctl_vol_args_v2 {
};
union {
char name[BTRFS_SUBVOL_NAME_MAX + 1];
- u64 devid;
+ __u64 devid;
};
};
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 9222db8ccccc..5f030b46cff4 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1353,6 +1353,15 @@ enum ethtool_link_mode_bit_indices {
ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28,
ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29,
ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30,
+ ETHTOOL_LINK_MODE_25000baseCR_Full_BIT = 31,
+ ETHTOOL_LINK_MODE_25000baseKR_Full_BIT = 32,
+ ETHTOOL_LINK_MODE_25000baseSR_Full_BIT = 33,
+ ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT = 34,
+ ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT = 35,
+ ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT = 36,
+ ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT = 37,
+ ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT = 38,
+ ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39,
/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
* 31. Please do NOT define any SUPPORTED_* or ADVERTISED_*
@@ -1361,7 +1370,7 @@ enum ethtool_link_mode_bit_indices {
*/
__ETHTOOL_LINK_MODE_LAST
- = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT,
+ = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
};
#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 5974fae54e12..27e17363263a 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -105,6 +105,9 @@
*
* 7.24
* - add FUSE_LSEEK for SEEK_HOLE and SEEK_DATA support
+ *
+ * 7.25
+ * - add FUSE_PARALLEL_DIROPS
*/
#ifndef _LINUX_FUSE_H
@@ -140,7 +143,7 @@
#define FUSE_KERNEL_VERSION 7
/** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 24
+#define FUSE_KERNEL_MINOR_VERSION 25
/** The node ID of the root inode */
#define FUSE_ROOT_ID 1
@@ -234,6 +237,7 @@ struct fuse_file_lock {
* FUSE_ASYNC_DIO: asynchronous direct I/O submission
* FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes
* FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens
+ * FUSE_PARALLEL_DIROPS: allow parallel lookups and readdir
*/
#define FUSE_ASYNC_READ (1 << 0)
#define FUSE_POSIX_LOCKS (1 << 1)
@@ -253,6 +257,7 @@ struct fuse_file_lock {
#define FUSE_ASYNC_DIO (1 << 15)
#define FUSE_WRITEBACK_CACHE (1 << 16)
#define FUSE_NO_OPEN_SUPPORT (1 << 17)
+#define FUSE_PARALLEL_DIROPS (1 << 18)
/**
* CUSE INIT request/reply flags
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index ca1054dd8249..72a04a0e8cce 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -1,5 +1,5 @@
#ifndef _UAPI_LINUX_GTP_H_
-#define _UAPI_LINUX_GTP_H__
+#define _UAPI_LINUX_GTP_H_
enum gtp_genl_cmds {
GTP_CMD_NEWPDP,
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 87cf351bab03..737fa32faad4 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -611,6 +611,37 @@
#define KEY_KBDINPUTASSIST_ACCEPT 0x264
#define KEY_KBDINPUTASSIST_CANCEL 0x265
+/* Diagonal movement keys */
+#define KEY_RIGHT_UP 0x266
+#define KEY_RIGHT_DOWN 0x267
+#define KEY_LEFT_UP 0x268
+#define KEY_LEFT_DOWN 0x269
+
+#define KEY_ROOT_MENU 0x26a /* Show Device's Root Menu */
+/* Show Top Menu of the Media (e.g. DVD) */
+#define KEY_MEDIA_TOP_MENU 0x26b
+#define KEY_NUMERIC_11 0x26c
+#define KEY_NUMERIC_12 0x26d
+/*
+ * Toggle Audio Description: refers to an audio service that helps blind and
+ * visually impaired consumers understand the action in a program. Note: in
+ * some countries this is referred to as "Video Description".
+ */
+#define KEY_AUDIO_DESC 0x26e
+#define KEY_3D_MODE 0x26f
+#define KEY_NEXT_FAVORITE 0x270
+#define KEY_STOP_RECORD 0x271
+#define KEY_PAUSE_RECORD 0x272
+#define KEY_VOD 0x273 /* Video on Demand */
+#define KEY_UNMUTE 0x274
+#define KEY_FASTREVERSE 0x275
+#define KEY_SLOWREVERSE 0x276
+/*
+ * Control a data application associated with the currently viewed channel,
+ * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.)
+ */
+#define KEY_DATA 0x275
+
#define BTN_TRIGGER_HAPPY 0x2c0
#define BTN_TRIGGER_HAPPY1 0x2c0
#define BTN_TRIGGER_HAPPY2 0x2c1
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index 01113841190d..c51494119817 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -247,6 +247,7 @@ struct input_mask {
#define BUS_ATARI 0x1B
#define BUS_SPI 0x1C
#define BUS_RMI 0x1D
+#define BUS_CEC 0x1E
/*
* MT_TOOL types
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 1d973d2ba417..cd26d7a0fd07 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -33,6 +33,7 @@ header-y += xt_NFLOG.h
header-y += xt_NFQUEUE.h
header-y += xt_RATEEST.h
header-y += xt_SECMARK.h
+header-y += xt_SYNPROXY.h
header-y += xt_TCPMSS.h
header-y += xt_TCPOPTSTRIP.h
header-y += xt_TEE.h
diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h
index 2d59fbaa93c6..ca67e61d2a61 100644
--- a/include/uapi/linux/netfilter/xt_SYNPROXY.h
+++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h
@@ -1,6 +1,8 @@
#ifndef _XT_SYNPROXY_H
#define _XT_SYNPROXY_H
+#include <linux/types.h>
+
#define XT_SYNPROXY_OPT_MSS 0x01
#define XT_SYNPROXY_OPT_WSCALE 0x02
#define XT_SYNPROXY_OPT_SACK_PERM 0x04
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index c4b2a3f90829..50ff21f748b6 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -61,5 +61,6 @@ struct nvme_passthru_cmd {
#define NVME_IOCTL_IO_CMD _IOWR('N', 0x43, struct nvme_passthru_cmd)
#define NVME_IOCTL_RESET _IO('N', 0x44)
#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45)
+#define NVME_IOCTL_RESCAN _IO('N', 0x46)
#endif /* _UAPI_LINUX_NVME_IOCTL_H */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 43fc8d213472..36ce552cf6a9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -862,6 +862,7 @@ enum perf_event_type {
};
#define PERF_MAX_STACK_DEPTH 127
+#define PERF_MAX_CONTEXTS_PER_STACK 8
enum perf_callchain_context {
PERF_CONTEXT_HV = (__u64)-32,
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index eba5914ba5d1..f4297c8a42fe 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -145,6 +145,8 @@ enum {
TCA_POLICE_PEAKRATE,
TCA_POLICE_AVRATE,
TCA_POLICE_RESULT,
+ TCA_POLICE_TM,
+ TCA_POLICE_PAD,
__TCA_POLICE_MAX
#define TCA_POLICE_RESULT TCA_POLICE_RESULT
};
@@ -173,7 +175,7 @@ enum {
TCA_U32_DIVISOR,
TCA_U32_SEL,
TCA_U32_POLICE,
- TCA_U32_ACT,
+ TCA_U32_ACT,
TCA_U32_INDEV,
TCA_U32_PCNT,
TCA_U32_MARK,
diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h
index 763bb6950402..0ec1da2ef652 100644
--- a/include/uapi/mtd/mtd-abi.h
+++ b/include/uapi/mtd/mtd-abi.h
@@ -228,7 +228,7 @@ struct nand_oobfree {
* complete set of ECC information. The ioctl truncates the larger internal
* structure to retain binary compatibility with the static declaration of the
* ioctl. Note that the "MTD_MAX_..._ENTRIES" macros represent the max size of
- * the user struct, not the MAX size of the internal struct nand_ecclayout.
+ * the user struct, not the MAX size of the internal OOB layout representation.
*/
struct nand_ecclayout_user {
__u32 eccbytes;
diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h
index a533cecab14f..98bebf8bef55 100644
--- a/include/uapi/rdma/hfi/hfi1_user.h
+++ b/include/uapi/rdma/hfi/hfi1_user.h
@@ -66,7 +66,7 @@
* The major version changes when data structures change in an incompatible
* way. The driver must be the same for initialization to succeed.
*/
-#define HFI1_USER_SWMAJOR 5
+#define HFI1_USER_SWMAJOR 6
/*
* Minor version differences are always compatible
@@ -75,7 +75,12 @@
* may not be implemented; the user code must deal with this if it
* cares, or it must abort after initialization reports the difference.
*/
-#define HFI1_USER_SWMINOR 0
+#define HFI1_USER_SWMINOR 1
+
+/*
+ * We will encode the major/minor inside a single 32bit version number.
+ */
+#define HFI1_SWMAJOR_SHIFT 16
/*
* Set of HW and driver capability/feature bits.
@@ -107,19 +112,6 @@
#define HFI1_RCVHDR_ENTSIZE_16 (1UL << 1)
#define HFI1_RCVDHR_ENTSIZE_32 (1UL << 2)
-/*
- * If the unit is specified via open, HFI choice is fixed. If port is
- * specified, it's also fixed. Otherwise we try to spread contexts
- * across ports and HFIs, using different algorithms. WITHIN is
- * the old default, prior to this mechanism.
- */
-#define HFI1_ALG_ACROSS 0 /* round robin contexts across HFIs, then
- * ports; this is the default */
-#define HFI1_ALG_WITHIN 1 /* use all contexts on an HFI (round robin
- * active ports within), then next HFI */
-#define HFI1_ALG_COUNT 2 /* number of algorithm choices */
-
-
/* User commands. */
#define HFI1_CMD_ASSIGN_CTXT 1 /* allocate HFI and context */
#define HFI1_CMD_CTXT_INFO 2 /* find out what resources we got */
@@ -127,7 +119,6 @@
#define HFI1_CMD_TID_UPDATE 4 /* update expected TID entries */
#define HFI1_CMD_TID_FREE 5 /* free expected TID entries */
#define HFI1_CMD_CREDIT_UPD 6 /* force an update of PIO credit */
-#define HFI1_CMD_SDMA_STATUS_UPD 7 /* force update of SDMA status ring */
#define HFI1_CMD_RECV_CTRL 8 /* control receipt of packets */
#define HFI1_CMD_POLL_TYPE 9 /* set the kind of polling we want */
@@ -135,13 +126,46 @@
#define HFI1_CMD_SET_PKEY 11 /* set context's pkey */
#define HFI1_CMD_CTXT_RESET 12 /* reset context's HW send context */
#define HFI1_CMD_TID_INVAL_READ 13 /* read TID cache invalidations */
-/* separate EPROM commands from normal PSM commands */
-#define HFI1_CMD_EP_INFO 64 /* read EPROM device ID */
-#define HFI1_CMD_EP_ERASE_CHIP 65 /* erase whole EPROM */
-/* range 66-74 no longer used */
-#define HFI1_CMD_EP_ERASE_RANGE 75 /* erase EPROM range */
-#define HFI1_CMD_EP_READ_RANGE 76 /* read EPROM range */
-#define HFI1_CMD_EP_WRITE_RANGE 77 /* write EPROM range */
+#define HFI1_CMD_GET_VERS 14 /* get the version of the user cdev */
+
+/*
+ * User IOCTLs can not go above 128 if they do then see common.h and change the
+ * base for the snoop ioctl
+ */
+#define IB_IOCTL_MAGIC 0x1b /* See Documentation/ioctl/ioctl-number.txt */
+
+/*
+ * Make the ioctls occupy the last 0xf0-0xff portion of the IB range
+ */
+#define __NUM(cmd) (HFI1_CMD_##cmd + 0xe0)
+
+struct hfi1_cmd;
+#define HFI1_IOCTL_ASSIGN_CTXT \
+ _IOWR(IB_IOCTL_MAGIC, __NUM(ASSIGN_CTXT), struct hfi1_user_info)
+#define HFI1_IOCTL_CTXT_INFO \
+ _IOW(IB_IOCTL_MAGIC, __NUM(CTXT_INFO), struct hfi1_ctxt_info)
+#define HFI1_IOCTL_USER_INFO \
+ _IOW(IB_IOCTL_MAGIC, __NUM(USER_INFO), struct hfi1_base_info)
+#define HFI1_IOCTL_TID_UPDATE \
+ _IOWR(IB_IOCTL_MAGIC, __NUM(TID_UPDATE), struct hfi1_tid_info)
+#define HFI1_IOCTL_TID_FREE \
+ _IOWR(IB_IOCTL_MAGIC, __NUM(TID_FREE), struct hfi1_tid_info)
+#define HFI1_IOCTL_CREDIT_UPD \
+ _IO(IB_IOCTL_MAGIC, __NUM(CREDIT_UPD))
+#define HFI1_IOCTL_RECV_CTRL \
+ _IOW(IB_IOCTL_MAGIC, __NUM(RECV_CTRL), int)
+#define HFI1_IOCTL_POLL_TYPE \
+ _IOW(IB_IOCTL_MAGIC, __NUM(POLL_TYPE), int)
+#define HFI1_IOCTL_ACK_EVENT \
+ _IOW(IB_IOCTL_MAGIC, __NUM(ACK_EVENT), unsigned long)
+#define HFI1_IOCTL_SET_PKEY \
+ _IOW(IB_IOCTL_MAGIC, __NUM(SET_PKEY), __u16)
+#define HFI1_IOCTL_CTXT_RESET \
+ _IO(IB_IOCTL_MAGIC, __NUM(CTXT_RESET))
+#define HFI1_IOCTL_TID_INVAL_READ \
+ _IOWR(IB_IOCTL_MAGIC, __NUM(TID_INVAL_READ), struct hfi1_tid_info)
+#define HFI1_IOCTL_GET_VERS \
+ _IOR(IB_IOCTL_MAGIC, __NUM(GET_VERS), int)
#define _HFI1_EVENT_FROZEN_BIT 0
#define _HFI1_EVENT_LINKDOWN_BIT 1
@@ -199,9 +223,7 @@ struct hfi1_user_info {
* Should be set to HFI1_USER_SWVERSION.
*/
__u32 userversion;
- __u16 pad;
- /* HFI selection algorithm, if unit has not selected */
- __u16 hfi1_alg;
+ __u32 pad;
/*
* If two or more processes wish to share a context, each process
* must set the subcontext_cnt and subcontext_id to the same
@@ -243,12 +265,6 @@ struct hfi1_tid_info {
__u32 length;
};
-struct hfi1_cmd {
- __u32 type; /* command type */
- __u32 len; /* length of struct pointed to by add */
- __u64 addr; /* pointer to user structure */
-};
-
enum hfi1_sdma_comp_state {
FREE = 0,
QUEUED,
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 6e373d151cad..02fe8390c18f 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -135,10 +135,12 @@ enum {
* Local service operations:
* RESOLVE - The client requests the local service to resolve a path.
* SET_TIMEOUT - The local service requests the client to set the timeout.
+ * IP_RESOLVE - The client requests the local service to resolve an IP to GID.
*/
enum {
RDMA_NL_LS_OP_RESOLVE = 0,
RDMA_NL_LS_OP_SET_TIMEOUT,
+ RDMA_NL_LS_OP_IP_RESOLVE,
RDMA_NL_LS_NUM_OPS
};
@@ -176,6 +178,10 @@ struct rdma_ls_resolve_header {
__u8 path_use;
};
+struct rdma_ls_ip_resolve_header {
+ __u32 ifindex;
+};
+
/* Local service attribute type */
#define RDMA_NLA_F_MANDATORY (1 << 13)
#define RDMA_NLA_TYPE_MASK (~(NLA_F_NESTED | NLA_F_NET_BYTEORDER | \
@@ -193,6 +199,8 @@ struct rdma_ls_resolve_header {
* TCLASS u8
* PKEY u16 cpu
* QOS_CLASS u16 cpu
+ * IPV4 u32 BE
+ * IPV6 u8[16] BE
*/
enum {
LS_NLA_TYPE_UNSPEC = 0,
@@ -204,6 +212,8 @@ enum {
LS_NLA_TYPE_TCLASS,
LS_NLA_TYPE_PKEY,
LS_NLA_TYPE_QOS_CLASS,
+ LS_NLA_TYPE_IPV4,
+ LS_NLA_TYPE_IPV6,
LS_NLA_TYPE_MAX
};
diff --git a/include/uapi/sound/Kbuild b/include/uapi/sound/Kbuild
index a7f27704f980..691984cb0b91 100644
--- a/include/uapi/sound/Kbuild
+++ b/include/uapi/sound/Kbuild
@@ -1,5 +1,6 @@
# UAPI Header export list
header-y += asequencer.h
+header-y += asoc.h
header-y += asound.h
header-y += asound_fm.h
header-y += compress_offload.h
@@ -10,3 +11,5 @@ header-y += hdsp.h
header-y += hdspm.h
header-y += sb16_csp.h
header-y += sfnt_info.h
+header-y += tlv.h
+header-y += usb_stream.h
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index c4cc1e40b35c..e4701a3c6331 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -116,6 +116,14 @@
#define SND_SOC_TPLG_STREAM_PLAYBACK 0
#define SND_SOC_TPLG_STREAM_CAPTURE 1
+/* vendor tuple types */
+#define SND_SOC_TPLG_TUPLE_TYPE_UUID 0
+#define SND_SOC_TPLG_TUPLE_TYPE_STRING 1
+#define SND_SOC_TPLG_TUPLE_TYPE_BOOL 2
+#define SND_SOC_TPLG_TUPLE_TYPE_BYTE 3
+#define SND_SOC_TPLG_TUPLE_TYPE_WORD 4
+#define SND_SOC_TPLG_TUPLE_TYPE_SHORT 5
+
/*
* Block Header.
* This header precedes all object and object arrays below.
@@ -132,6 +140,35 @@ struct snd_soc_tplg_hdr {
__le32 count; /* number of elements in block */
} __attribute__((packed));
+/* vendor tuple for uuid */
+struct snd_soc_tplg_vendor_uuid_elem {
+ __le32 token;
+ char uuid[16];
+} __attribute__((packed));
+
+/* vendor tuple for a bool/byte/short/word value */
+struct snd_soc_tplg_vendor_value_elem {
+ __le32 token;
+ __le32 value;
+} __attribute__((packed));
+
+/* vendor tuple for string */
+struct snd_soc_tplg_vendor_string_elem {
+ __le32 token;
+ char string[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+} __attribute__((packed));
+
+struct snd_soc_tplg_vendor_array {
+ __le32 size; /* size in bytes of the array, including all elements */
+ __le32 type; /* SND_SOC_TPLG_TUPLE_TYPE_ */
+ __le32 num_elems; /* number of elements in array */
+ union {
+ struct snd_soc_tplg_vendor_uuid_elem uuid[0];
+ struct snd_soc_tplg_vendor_value_elem value[0];
+ struct snd_soc_tplg_vendor_string_elem string[0];
+ };
+} __attribute__((packed));
+
/*
* Private data.
* All topology objects may have private data that can be used by the driver or
@@ -139,7 +176,10 @@ struct snd_soc_tplg_hdr {
*/
struct snd_soc_tplg_private {
__le32 size; /* in bytes of private data */
- char data[0];
+ union {
+ char data[0];
+ struct snd_soc_tplg_vendor_array array[0];
+ };
} __attribute__((packed));
/*
@@ -383,7 +423,7 @@ struct snd_soc_tplg_pcm {
__le32 size; /* in bytes of this structure */
char pcm_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
char dai_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
- __le32 pcm_id; /* unique ID - used to match */
+ __le32 pcm_id; /* unique ID - used to match with DAI link */
__le32 dai_id; /* unique ID - used to match */
__le32 playback; /* supports playback mode */
__le32 capture; /* supports capture mode */
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index ad66589f2ae6..3a2a79401789 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -16,6 +16,7 @@
#include <linux/videodev2.h>
#include <linux/bitmap.h>
#include <linux/fb.h>
+#include <linux/of.h>
#include <media/v4l2-mediabus.h>
#include <video/videomode.h>
@@ -345,6 +346,7 @@ struct ipu_client_platformdata {
int dc;
int dp;
int dma[2];
+ struct device_node *of_node;
};
#endif /* __DRM_IPU_H__ */
diff --git a/init/Kconfig b/init/Kconfig
index a9c4aefd5436..f755a602d4a1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1306,6 +1306,17 @@ source "usr/Kconfig"
endif
+choice
+ prompt "Compiler optimization level"
+ default CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
+
+config CC_OPTIMIZE_FOR_PERFORMANCE
+ bool "Optimize for performance"
+ help
+ This is the default optimization level for the kernel, building
+ with the "-O2" compiler flag for best performance and most
+ helpful compile-time warnings.
+
config CC_OPTIMIZE_FOR_SIZE
bool "Optimize for size"
help
@@ -1314,6 +1325,8 @@ config CC_OPTIMIZE_FOR_SIZE
If unsure, say N.
+endchoice
+
config SYSCTL
bool
@@ -2049,6 +2062,22 @@ config MODULE_COMPRESS_XZ
endchoice
+config TRIM_UNUSED_KSYMS
+ bool "Trim unused exported kernel symbols"
+ depends on MODULES && !UNUSED_SYMBOLS
+ help
+ The kernel and some modules make many symbols available for
+ other modules to use via EXPORT_SYMBOL() and variants. Depending
+ on the set of modules being selected in your kernel configuration,
+ many of those exported symbols might never be used.
+
+ This option allows for unused exported symbols to be dropped from
+ the build. In turn, this provides the compiler more opportunities
+ (especially when using LTO) for optimizing the code and reducing
+ binary size. This might have some security advantages as well.
+
+ If unsure say N.
+
endif # MODULES
config MODULES_TREE_LOOKUP
diff --git a/init/main.c b/init/main.c
index bc0f9e0bcf22..eae02aa03c9e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -453,7 +453,7 @@ void __init __weak smp_setup_processor_id(void)
}
# if THREAD_SIZE >= PAGE_SIZE
-void __init __weak thread_info_cache_init(void)
+void __init __weak thread_stack_cache_init(void)
{
}
#endif
@@ -607,6 +607,7 @@ asmlinkage __visible void __init start_kernel(void)
initrd_start = 0;
}
#endif
+ page_ext_init();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
@@ -626,7 +627,7 @@ asmlinkage __visible void __init start_kernel(void)
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
#endif
- thread_info_cache_init();
+ thread_stack_cache_init();
cred_init();
fork_init();
proc_caches_init();
@@ -707,11 +708,13 @@ static bool __init_or_module initcall_blacklisted(initcall_t fn)
{
struct blacklist_entry *entry;
char fn_name[KSYM_SYMBOL_LEN];
+ unsigned long addr;
if (list_empty(&blacklisted_initcalls))
return false;
- sprint_symbol_no_offset(fn_name, (unsigned long)fn);
+ addr = (unsigned long) dereference_function_descriptor(fn);
+ sprint_symbol_no_offset(fn_name, addr);
list_for_each_entry(entry, &blacklisted_initcalls, next) {
if (!strcmp(fn_name, entry->buf)) {
@@ -1003,8 +1006,6 @@ static noinline void __init kernel_init_freeable(void)
sched_init_smp();
page_alloc_init_late();
- /* Initialize page ext after all struct pages are initializaed */
- page_ext_init();
do_basic_setup();
diff --git a/kernel/audit.c b/kernel/audit.c
index 22bb4f24f071..8d528f9930da 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1883,6 +1883,23 @@ out_null:
audit_log_format(ab, " exe=(null)");
}
+struct tty_struct *audit_get_tty(struct task_struct *tsk)
+{
+ struct tty_struct *tty = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tsk->sighand->siglock, flags);
+ if (tsk->signal)
+ tty = tty_kref_get(tsk->signal->tty);
+ spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+ return tty;
+}
+
+void audit_put_tty(struct tty_struct *tty)
+{
+ tty_kref_put(tty);
+}
+
void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
const struct cred *cred;
diff --git a/kernel/audit.h b/kernel/audit.h
index cbbe6bb6496e..a492f4c4e710 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -23,6 +23,7 @@
#include <linux/audit.h>
#include <linux/skbuff.h>
#include <uapi/linux/mqueue.h>
+#include <linux/tty.h>
/* AUDIT_NAMES is the number of slots we reserve in the audit_context
* for saving names from getname(). If we get more names we will allocate
@@ -262,6 +263,9 @@ extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);
extern void audit_log_d_path_exe(struct audit_buffer *ab,
struct mm_struct *mm);
+extern struct tty_struct *audit_get_tty(struct task_struct *tsk);
+extern void audit_put_tty(struct tty_struct *tty);
+
/* audit watch functions */
#ifdef CONFIG_AUDIT_WATCH
extern void audit_put_watch(struct audit_watch *watch);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 62ab53d7619c..2672d105cffc 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -63,7 +63,6 @@
#include <asm/unistd.h>
#include <linux/security.h>
#include <linux/list.h>
-#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
@@ -1985,14 +1984,15 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
if (!audit_enabled)
return;
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+ if (!ab)
+ return;
+
uid = from_kuid(&init_user_ns, task_uid(current));
oldloginuid = from_kuid(&init_user_ns, koldloginuid);
loginuid = from_kuid(&init_user_ns, kloginuid),
tty = audit_get_tty(current);
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
- if (!ab)
- return;
audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid);
audit_log_task_context(ab);
audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d",
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 04be7021f848..318858edb1cd 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -365,7 +365,6 @@ static struct file_system_type bpf_fs_type = {
.name = "bpf",
.mount = bpf_mount,
.kill_sb = kill_litter_super,
- .fs_flags = FS_USERNS_MOUNT,
};
MODULE_ALIAS_FS("bpf");
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index c8ee35287bfe..080a2dfb5800 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -136,7 +136,8 @@ u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
return -EINVAL;
- trace = get_perf_callchain(regs, init_nr, kernel, user, false, false);
+ trace = get_perf_callchain(regs, init_nr, kernel, user,
+ sysctl_perf_event_max_stack, false, false);
if (unlikely(!trace))
/* couldn't fetch the stack trace */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 668e07903c8f..eec9f90ba030 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -126,31 +126,6 @@
* are set to NOT_INIT to indicate that they are no longer readable.
*/
-/* types of values stored in eBPF registers */
-enum bpf_reg_type {
- NOT_INIT = 0, /* nothing was written into register */
- UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */
- PTR_TO_CTX, /* reg points to bpf_context */
- CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
- PTR_TO_MAP_VALUE, /* reg points to map element value */
- PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
- FRAME_PTR, /* reg == frame_pointer */
- PTR_TO_STACK, /* reg == frame_pointer + imm */
- CONST_IMM, /* constant integer value */
-
- /* PTR_TO_PACKET represents:
- * skb->data
- * skb->data + imm
- * skb->data + (u16) var
- * skb->data + (u16) var + imm
- * if (range > 0) then [ptr, ptr + range - off) is safe to access
- * if (id > 0) means that some 'var' was added
- * if (off > 0) menas that 'imm' was added
- */
- PTR_TO_PACKET,
- PTR_TO_PACKET_END, /* skb->data + headlen */
-};
-
struct reg_state {
enum bpf_reg_type type;
union {
@@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off,
/* check access to 'struct bpf_context' fields */
static int check_ctx_access(struct verifier_env *env, int off, int size,
- enum bpf_access_type t)
+ enum bpf_access_type t, enum bpf_reg_type *reg_type)
{
if (env->prog->aux->ops->is_valid_access &&
- env->prog->aux->ops->is_valid_access(off, size, t)) {
+ env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
@@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
mark_reg_unknown_value(state->regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
+ enum bpf_reg_type reg_type = UNKNOWN_VALUE;
+
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose("R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
- err = check_ctx_access(env, off, size, t);
+ err = check_ctx_access(env, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
mark_reg_unknown_value(state->regs, value_regno);
- if (off == offsetof(struct __sk_buff, data) &&
- env->allow_ptr_leaks)
+ if (env->allow_ptr_leaks)
/* note that reg.[id|off|range] == 0 */
- state->regs[value_regno].type = PTR_TO_PACKET;
- else if (off == offsetof(struct __sk_buff, data_end) &&
- env->allow_ptr_leaks)
- state->regs[value_regno].type = PTR_TO_PACKET_END;
+ state->regs[value_regno].type = reg_type;
}
} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 86cb5c6e8932..75c0ff00aca6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -837,6 +837,8 @@ static void put_css_set_locked(struct css_set *cset)
static void put_css_set(struct css_set *cset)
{
+ unsigned long flags;
+
/*
* Ensure that the refcount doesn't hit zero while any readers
* can see it. Similar to atomic_dec_and_lock(), but for an
@@ -845,9 +847,9 @@ static void put_css_set(struct css_set *cset)
if (atomic_add_unless(&cset->refcount, -1, 1))
return;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irqsave(&css_set_lock, flags);
put_css_set_locked(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irqrestore(&css_set_lock, flags);
}
/*
@@ -1070,11 +1072,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
/* First see if we already have a cgroup group that matches
* the desired set */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = find_existing_css_set(old_cset, cgrp, template);
if (cset)
get_css_set(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (cset)
return cset;
@@ -1102,7 +1104,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
* find_existing_css_set() */
memcpy(cset->subsys, template, sizeof(cset->subsys));
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
/* Add reference counts and links from the new css_set. */
list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
@@ -1128,7 +1130,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
css_get(css);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return cset;
}
@@ -1192,7 +1194,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
* Release all the links from cset_links to this hierarchy's
* root cgroup
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
list_del(&link->cset_link);
@@ -1200,7 +1202,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
kfree(link);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (!list_empty(&root->root_list)) {
list_del(&root->root_list);
@@ -1600,11 +1602,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
ss->root = dst_root;
css->cgroup = dcgrp;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist)
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* default hierarchy doesn't enable controllers by default */
dst_root->subsys_mask |= 1 << ssid;
@@ -1640,10 +1642,10 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
if (!buf)
return -ENOMEM;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot);
len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (len >= PATH_MAX)
len = -ERANGE;
@@ -1897,7 +1899,7 @@ static void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
if (use_task_css_set_links)
goto out_unlock;
@@ -1922,8 +1924,12 @@ static void cgroup_enable_task_cg_lists(void)
* entry won't be deleted though the process has exited.
* Do it while holding siglock so that we don't end up
* racing against cgroup_exit().
+ *
+ * Interrupts were already disabled while acquiring
+ * the css_set_lock, so we do not need to disable it
+ * again when acquiring the sighand->siglock here.
*/
- spin_lock_irq(&p->sighand->siglock);
+ spin_lock(&p->sighand->siglock);
if (!(p->flags & PF_EXITING)) {
struct css_set *cset = task_css_set(p);
@@ -1932,11 +1938,11 @@ static void cgroup_enable_task_cg_lists(void)
list_add_tail(&p->cg_list, &cset->tasks);
get_css_set(cset);
}
- spin_unlock_irq(&p->sighand->siglock);
+ spin_unlock(&p->sighand->siglock);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
out_unlock:
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -2043,13 +2049,13 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
* Link the root cgroup in this hierarchy into all the css_set
* objects.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist) {
link_css_set(&tmp_links, cset, root_cgrp);
if (css_set_populated(cset))
cgroup_update_populated(root_cgrp, true);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
BUG_ON(!list_empty(&root_cgrp->self.children));
BUG_ON(atomic_read(&root->nr_cgrps) != 1);
@@ -2256,11 +2262,11 @@ out_mount:
struct cgroup *cgrp;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgrp = cset_cgroup_from_root(ns->root_cset, root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
@@ -2337,11 +2343,11 @@ char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
char *ret;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
return ret;
@@ -2369,7 +2375,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
char *path = NULL;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
@@ -2382,7 +2388,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
path = buf;
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
return path;
}
@@ -2557,7 +2563,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
* the new cgroup. There are no failure cases after here, so this
* is the commit point.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(cset, &tset->src_csets, mg_node) {
list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
struct css_set *from_cset = task_css_set(task);
@@ -2568,7 +2574,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
put_css_set_locked(from_cset);
}
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/*
* Migration is committed, all target tasks are now on dst_csets.
@@ -2597,13 +2603,13 @@ out_cancel_attach:
}
} while_each_subsys_mask();
out_release_tset:
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_splice_init(&tset->dst_csets, &tset->src_csets);
list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
list_del_init(&cset->mg_node);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return ret;
}
@@ -2634,7 +2640,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
lockdep_assert_held(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
@@ -2642,7 +2648,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
list_del_init(&cset->mg_preload_node);
put_css_set_locked(cset);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/**
@@ -2783,7 +2789,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
* already PF_EXITING could be freed from underneath us unless we
* take an rcu_read_lock.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
@@ -2792,7 +2798,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return cgroup_taskset_migrate(&tset, root);
}
@@ -2816,7 +2822,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
return -EBUSY;
/* look up all src csets */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
@@ -2826,7 +2832,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* prepare dst csets and commit */
ret = cgroup_migrate_prepare_dst(&preloaded_csets);
@@ -2859,9 +2865,9 @@ static int cgroup_procs_write_permission(struct task_struct *task,
struct cgroup *cgrp;
struct inode *inode;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
while (!cgroup_is_descendant(dst_cgrp, cgrp))
cgrp = cgroup_parent(cgrp);
@@ -2962,9 +2968,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
if (root == &cgrp_dfl_root)
continue;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
from_cgrp = task_cgroup_from_root(from, root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
retval = cgroup_attach_task(from_cgrp, tsk, false);
if (retval)
@@ -3080,7 +3086,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
percpu_down_write(&cgroup_threadgroup_rwsem);
/* look up all csses currently attached to @cgrp's subtree */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
struct cgrp_cset_link *link;
@@ -3088,14 +3094,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
cgroup_migrate_add_src(link->cset, dsct,
&preloaded_csets);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* NULL dst indicates self on default hierarchy */
ret = cgroup_migrate_prepare_dst(&preloaded_csets);
if (ret)
goto out_finish;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
struct task_struct *task, *ntask;
@@ -3107,7 +3113,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
cgroup_taskset_add(task, &tset);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
ret = cgroup_taskset_migrate(&tset, cgrp->root);
out_finish:
@@ -3908,10 +3914,10 @@ static int cgroup_task_count(const struct cgroup *cgrp)
int count = 0;
struct cgrp_cset_link *link;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
count += atomic_read(&link->cset->refcount);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return count;
}
@@ -4249,7 +4255,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
memset(it, 0, sizeof(*it));
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
it->ss = css->ss;
@@ -4262,7 +4268,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
css_task_iter_advance_css_set(it);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/**
@@ -4280,7 +4286,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
it->cur_task = NULL;
}
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
if (it->task_pos) {
it->cur_task = list_entry(it->task_pos, struct task_struct,
@@ -4289,7 +4295,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
css_task_iter_advance(it);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return it->cur_task;
}
@@ -4303,10 +4309,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
void css_task_iter_end(struct css_task_iter *it)
{
if (it->cur_cset) {
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_del(&it->iters_node);
put_css_set_locked(it->cur_cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
if (it->cur_task)
@@ -4338,10 +4344,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
mutex_lock(&cgroup_mutex);
/* all tasks in @from are being moved, all csets are source */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &from->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_prepare_dst(&preloaded_csets);
if (ret)
@@ -5063,6 +5069,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
memset(css, 0, sizeof(*css));
css->cgroup = cgrp;
css->ss = ss;
+ css->id = -1;
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
css->serial_nr = css_serial_nr_next++;
@@ -5150,7 +5157,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
if (err < 0)
- goto err_free_percpu_ref;
+ goto err_free_css;
css->id = err;
/* @css is ready to be brought online now, make it visible */
@@ -5174,9 +5181,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
err_list_del:
list_del_rcu(&css->sibling);
- cgroup_idr_remove(&ss->css_idr, css->id);
-err_free_percpu_ref:
- percpu_ref_exit(&css->refcnt);
err_free_css:
call_rcu(&css->rcu_head, css_free_rcu_fn);
return ERR_PTR(err);
@@ -5451,10 +5455,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
*/
cgrp->self.flags &= ~CSS_ONLINE;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
link->cset->dead = true;
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* initiate massacre of all css's */
for_each_css(css, ssid, cgrp)
@@ -5725,7 +5729,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
goto out;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
for_each_root(root) {
struct cgroup_subsys *ss;
@@ -5778,7 +5782,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
retval = 0;
out_unlock:
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
kfree(buf);
out:
@@ -5923,13 +5927,13 @@ void cgroup_post_fork(struct task_struct *child)
if (use_task_css_set_links) {
struct css_set *cset;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
if (list_empty(&child->cg_list)) {
get_css_set(cset);
css_set_move_task(child, NULL, cset, false);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/*
@@ -5974,9 +5978,9 @@ void cgroup_exit(struct task_struct *tsk)
cset = task_css_set(tsk);
if (!list_empty(&tsk->cg_list)) {
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
css_set_move_task(tsk, cset, NULL, false);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
} else {
get_css_set(cset);
}
@@ -6044,9 +6048,9 @@ static void cgroup_release_agent(struct work_struct *work)
if (!pathbuf || !agentbuf)
goto out;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (!path)
goto out;
@@ -6306,12 +6310,12 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
return ERR_PTR(-EPERM);
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
get_css_set(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
new_ns = alloc_cgroup_ns();
@@ -6435,7 +6439,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
if (!name_buf)
return -ENOMEM;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
@@ -6446,7 +6450,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
c->root->hierarchy_id, name_buf);
}
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
kfree(name_buf);
return 0;
}
@@ -6457,7 +6461,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
struct css_set *cset = link->cset;
struct task_struct *task;
@@ -6480,7 +6484,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
overflow:
seq_puts(seq, " ...\n");
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return 0;
}
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index b9325e7dcba1..179ef4640964 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -19,11 +19,13 @@ struct callchain_cpus_entries {
};
int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;
static inline size_t perf_callchain_entry__sizeof(void)
{
return (sizeof(struct perf_callchain_entry) +
- sizeof(__u64) * sysctl_perf_event_max_stack);
+ sizeof(__u64) * (sysctl_perf_event_max_stack +
+ sysctl_perf_event_max_contexts_per_stack));
}
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
@@ -32,12 +34,12 @@ static DEFINE_MUTEX(callchain_mutex);
static struct callchain_cpus_entries *callchain_cpus_entries;
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+__weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+__weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
@@ -176,14 +178,15 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
if (!kernel && !user)
return NULL;
- return get_perf_callchain(regs, 0, kernel, user, crosstask, true);
+ return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
}
struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
- bool crosstask, bool add_mark)
+ u32 max_stack, bool crosstask, bool add_mark)
{
struct perf_callchain_entry *entry;
+ struct perf_callchain_entry_ctx ctx;
int rctx;
entry = get_callchain_entry(&rctx);
@@ -193,12 +196,16 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
if (!entry)
goto exit_put;
- entry->nr = init_nr;
+ ctx.entry = entry;
+ ctx.max_stack = max_stack;
+ ctx.nr = entry->nr = init_nr;
+ ctx.contexts = 0;
+ ctx.contexts_maxed = false;
if (kernel && !user_mode(regs)) {
if (add_mark)
- perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
- perf_callchain_kernel(entry, regs);
+ perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL);
+ perf_callchain_kernel(&ctx, regs);
}
if (user) {
@@ -214,8 +221,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
goto exit_put;
if (add_mark)
- perf_callchain_store(entry, PERF_CONTEXT_USER);
- perf_callchain_user(entry, regs);
+ perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+ perf_callchain_user(&ctx, regs);
}
}
@@ -225,10 +232,15 @@ exit_put:
return entry;
}
+/*
+ * Used for sysctl_perf_event_max_stack and
+ * sysctl_perf_event_max_contexts_per_stack.
+ */
int perf_event_max_stack_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- int new_value = sysctl_perf_event_max_stack, ret;
+ int *value = table->data;
+ int new_value = *value, ret;
struct ctl_table new_table = *table;
new_table.data = &new_value;
@@ -240,7 +252,7 @@ int perf_event_max_stack_handler(struct ctl_table *table, int write,
if (atomic_read(&nr_callchain_events))
ret = -EBUSY;
else
- sysctl_perf_event_max_stack = new_value;
+ *value = new_value;
mutex_unlock(&callchain_mutex);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 274450efea90..85cd41878a74 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3862,10 +3862,8 @@ static void _free_event(struct perf_event *event)
if (event->ctx)
put_ctx(event->ctx);
- if (event->pmu) {
- exclusive_event_destroy(event);
- module_put(event->pmu->module);
- }
+ exclusive_event_destroy(event);
+ module_put(event->pmu->module);
call_rcu(&event->rcu_head, free_event_rcu);
}
@@ -7531,7 +7529,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
prog = event->tp_event->prog;
if (prog) {
event->tp_event->prog = NULL;
- bpf_prog_put(prog);
+ bpf_prog_put_rcu(prog);
}
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 47887bba944f..4a7ec0c6c88c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk)
}
#endif
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
{
}
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
# if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
@@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
return page ? page_address(page) : NULL;
}
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
{
- struct page *page = virt_to_page(ti);
+ struct page *page = virt_to_page(stack);
memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-(1 << THREAD_SIZE_ORDER));
__free_kmem_pages(page, THREAD_SIZE_ORDER);
}
# else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+ return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
{
- kmem_cache_free(thread_info_cache, ti);
+ kmem_cache_free(thread_stack_cache, stack);
}
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
{
- thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
THREAD_SIZE, 0, NULL);
- BUG_ON(thread_info_cache == NULL);
+ BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif
@@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
{
- struct zone *zone = page_zone(virt_to_page(ti));
+ struct zone *zone = page_zone(virt_to_page(stack));
mod_zone_page_state(zone, NR_KERNEL_STACK, account);
}
@@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account)
void free_task(struct task_struct *tsk)
{
account_kernel_stack(tsk->stack, -1);
- arch_release_thread_info(tsk->stack);
- free_thread_info(tsk->stack);
+ arch_release_thread_stack(tsk->stack);
+ free_thread_stack(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
@@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk)
static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
- struct thread_info *ti;
+ unsigned long *stack;
int err;
if (node == NUMA_NO_NODE)
@@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
if (!tsk)
return NULL;
- ti = alloc_thread_info_node(tsk, node);
- if (!ti)
+ stack = alloc_thread_stack_node(tsk, node);
+ if (!stack)
goto free_tsk;
err = arch_dup_task_struct(tsk, orig);
if (err)
- goto free_ti;
+ goto free_stack;
- tsk->stack = ti;
+ tsk->stack = stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
@@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- account_kernel_stack(ti, 1);
+ account_kernel_stack(stack, 1);
kcov_task_init(tsk);
return tsk;
-free_ti:
- free_thread_info(ti);
+free_stack:
+ free_thread_stack(stack);
free_tsk:
free_task_struct(tsk);
return NULL;
@@ -736,6 +736,7 @@ void mmput(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mmput);
+#ifdef CONFIG_MMU
static void mmput_async_fn(struct work_struct *work)
{
struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
@@ -749,6 +750,7 @@ void mmput_async(struct mm_struct *mm)
schedule_work(&mm->async_put_work);
}
}
+#endif
/**
* set_mm_exe_file - change a reference to the mm's executable file
diff --git a/kernel/futex.c b/kernel/futex.c
index ee25f5ba4aca..33664f70e2d2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
{
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
- struct page *page;
+ struct page *page, *tail;
struct address_space *mapping;
int err, ro = 0;
@@ -530,7 +530,15 @@ again:
* considered here and page lock forces unnecessarily serialization
* From this point on, mapping will be re-verified if necessary and
* page lock will be acquired only if it is unavoidable
- */
+ *
+ * Mapping checks require the head page for any compound page so the
+ * head page and mapping is looked up now. For anonymous pages, it
+ * does not matter if the page splits in the future as the key is
+ * based on the address. For filesystem-backed pages, the tail is
+ * required as the index of the page determines the key. For
+ * base pages, there is no tail page and tail == page.
+ */
+ tail = page;
page = compound_head(page);
mapping = READ_ONCE(page->mapping);
@@ -654,7 +662,7 @@ again:
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.inode = inode;
- key->shared.pgoff = basepage_index(page);
+ key->shared.pgoff = basepage_index(tail);
rcu_read_unlock();
}
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index c92e44855ddd..1276aabaab55 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -37,6 +37,7 @@ config ARCH_HAS_GCOV_PROFILE_ALL
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
+ depends on !COMPILE_TEST
depends on GCOV_KERNEL
depends on ARCH_HAS_GCOV_PROFILE_ALL
default n
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index c42742208e5e..89b49f6773f0 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -125,7 +125,7 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest)
domain = data->domain;
if (WARN_ON(domain == NULL))
- return;
+ return -EINVAL;
if (!irq_domain_is_ipi(domain)) {
pr_warn("Trying to destroy a non IPI domain!\n");
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 05254eeb4b4e..4b353e0be121 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key);
void static_key_slow_inc(struct static_key *key)
{
+ int v, v1;
+
STATIC_KEY_CHECK_USE();
- if (atomic_inc_not_zero(&key->enabled))
- return;
+
+ /*
+ * Careful if we get concurrent static_key_slow_inc() calls;
+ * later calls must wait for the first one to _finish_ the
+ * jump_label_update() process. At the same time, however,
+ * the jump_label_update() call below wants to see
+ * static_key_enabled(&key) for jumps to be updated properly.
+ *
+ * So give a special meaning to negative key->enabled: it sends
+ * static_key_slow_inc() down the slow path, and it is non-zero
+ * so it counts as "enabled" in jump_label_update(). Note that
+ * atomic_inc_unless_negative() checks >= 0, so roll our own.
+ */
+ for (v = atomic_read(&key->enabled); v > 0; v = v1) {
+ v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
+ if (likely(v1 == v))
+ return;
+ }
jump_label_lock();
- if (atomic_inc_return(&key->enabled) == 1)
+ if (atomic_read(&key->enabled) == 0) {
+ atomic_set(&key->enabled, -1);
jump_label_update(key);
+ atomic_set(&key->enabled, 1);
+ } else {
+ atomic_inc(&key->enabled);
+ }
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_slow_inc);
@@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
static void __static_key_slow_dec(struct static_key *key,
unsigned long rate_limit, struct delayed_work *work)
{
+ /*
+ * The negative count check is valid even when a negative
+ * key->enabled is in use by static_key_slow_inc(); a
+ * __static_key_slow_dec() before the first static_key_slow_inc()
+ * returns is unbalanced, because all other static_key_slow_inc()
+ * instances block while the update is in progress.
+ */
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
WARN(atomic_read(&key->enabled) < 0,
"jump label: negative count!\n");
diff --git a/kernel/kcov.c b/kernel/kcov.c
index a02f2dddd1d7..8d44b3fea9d0 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -264,7 +264,12 @@ static const struct file_operations kcov_fops = {
static int __init kcov_init(void)
{
- if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) {
+ /*
+ * The kcov debugfs file won't ever get removed and thus,
+ * there is no need to protect it against removal races. The
+ * use of debugfs_create_file_unsafe() is actually safe here.
+ */
+ if (!debugfs_create_file_unsafe("kcov", 0600, NULL, NULL, &kcov_fops)) {
pr_err("failed to create kcov in debugfs\n");
return -ENOMEM;
}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 3ef3736002d8..9c951fade415 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
}
void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti)
+ struct task_struct *task)
{
SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
/* Mark the current thread as blocked on the lock: */
- ti->task->blocked_on = waiter;
+ task->blocked_on = waiter;
}
void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti)
+ struct task_struct *task)
{
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
- DEBUG_LOCKS_WARN_ON(waiter->task != ti->task);
- DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter);
- ti->task->blocked_on = NULL;
+ DEBUG_LOCKS_WARN_ON(waiter->task != task);
+ DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
+ task->blocked_on = NULL;
list_del_init(&waiter->list);
waiter->task = NULL;
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cfa..d06ae3bb46c5 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock,
extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
extern void debug_mutex_add_waiter(struct mutex *lock,
struct mutex_waiter *waiter,
- struct thread_info *ti);
+ struct task_struct *task);
extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti);
+ struct task_struct *task);
extern void debug_mutex_unlock(struct mutex *lock);
extern void debug_mutex_init(struct mutex *lock, const char *name,
struct lock_class_key *key);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index e364b424b019..a70b90db3909 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
if (!hold_ctx)
return 0;
- if (unlikely(ctx == hold_ctx))
- return -EALREADY;
-
if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
(ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
#ifdef CONFIG_DEBUG_MUTEXES
@@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
unsigned long flags;
int ret;
+ if (use_ww_ctx) {
+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+ if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+ return -EALREADY;
+ }
+
preempt_disable();
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
@@ -534,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto skip_wait;
debug_mutex_lock_common(lock, &waiter);
- debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
+ debug_mutex_add_waiter(lock, &waiter, task);
/* add waiting tasks to the end of the waitqueue (FIFO): */
list_add_tail(&waiter.list, &lock->wait_list);
@@ -581,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
}
__set_task_state(task, TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, current_thread_info());
+ mutex_remove_waiter(lock, &waiter, task);
/* set it to 0 if there are no waiters left: */
if (likely(list_empty(&lock->wait_list)))
atomic_set(&lock->count, 0);
@@ -602,7 +605,7 @@ skip_wait:
return 0;
err:
- mutex_remove_waiter(lock, &waiter, task_thread_info(task));
+ mutex_remove_waiter(lock, &waiter, task);
spin_unlock_mutex(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, 1, ip);
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 5cda397607f2..a68bae5e852a 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -13,7 +13,7 @@
do { spin_lock(lock); (void)(flags); } while (0)
#define spin_unlock_mutex(lock, flags) \
do { spin_unlock(lock); (void)(flags); } while (0)
-#define mutex_remove_waiter(lock, waiter, ti) \
+#define mutex_remove_waiter(lock, waiter, task) \
__list_del((waiter)->list.prev, (waiter)->list.next)
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index f231e0bb311c..bec0b647f9cc 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -37,6 +37,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
free_percpu(brw->fast_read_ctr);
brw->fast_read_ctr = NULL; /* catch use after free bugs */
}
+EXPORT_SYMBOL_GPL(percpu_free_rwsem);
/*
* This is the fast-path for down_read/up_read. If it succeeds we rely
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ce2f75e32ae1..5fc8c311b8fe 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -267,6 +267,66 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
#endif
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ * (1) clear_pending_set_locked(): *,1,0 -> *,0,1
+ *
+ * (2) set_locked(): t,0,0 -> t,0,1 ; t != 0
+ * atomic_cmpxchg_relaxed(): t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+ u32 val;
+
+ for (;;) {
+ val = atomic_read(&lock->val);
+
+ if (!val) /* not locked, we're done */
+ goto done;
+
+ if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+ break;
+
+ /* not locked, but pending, wait until we observe the lock */
+ cpu_relax();
+ }
+
+ /* any unlock is good */
+ while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+ cpu_relax();
+
+done:
+ smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
#endif /* _GEN_PV_LOCK_SLOWPATH */
/**
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index c817216c1615..2e853ad93a3a 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -173,6 +173,22 @@ void down_write_nested(struct rw_semaphore *sem, int subclass)
EXPORT_SYMBOL(down_write_nested);
+int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
+{
+ might_sleep();
+ rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
+
+ if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+ rwsem_release(&sem->dep_map, 1, _RET_IP_);
+ return -EINTR;
+ }
+
+ rwsem_set_owner(sem);
+ return 0;
+}
+
+EXPORT_SYMBOL(down_write_killable_nested);
+
void up_read_non_owner(struct rw_semaphore *sem)
{
__up_read(sem);
diff --git a/kernel/pid.c b/kernel/pid.c
index 4d73a834c7e6..f66162f2359b 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -311,7 +311,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
nr = alloc_pidmap(tmp);
- if (IS_ERR_VALUE(nr)) {
+ if (nr < 0) {
retval = nr;
goto out_free;
}
diff --git a/kernel/power/process.c b/kernel/power/process.c
index df058bed53ce..0c2ee9761d57 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -146,6 +146,18 @@ int freeze_processes(void)
if (!error && !oom_killer_disable())
error = -EBUSY;
+ /*
+ * There is a hard to fix race between oom_reaper kernel thread
+ * and oom_killer_disable. oom_reaper calls exit_oom_victim
+ * before the victim reaches exit_mm so try to freeze all the tasks
+ * again and catch such a left over task.
+ */
+ if (!error) {
+ pr_info("Double checking all user space processes after OOM killer disable... ");
+ error = try_to_freeze_tasks(true);
+ pr_cont("\n");
+ }
+
if (error)
thaw_processes();
return error;
diff --git a/kernel/relay.c b/kernel/relay.c
index 074994bcfa9b..04d7cf3ef8cf 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -614,6 +614,7 @@ free_bufs:
kref_put(&chan->kref, relay_destroy_channel);
mutex_unlock(&relay_channels_mutex);
+ kfree(chan);
return NULL;
}
EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 404c0784b1fc..51d7105f529a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
for (;;) {
/* Any allowed, online CPU? */
for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
- if (!cpu_active(dest_cpu))
+ if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
+ continue;
+ if (!cpu_online(dest_cpu))
continue;
goto out;
}
@@ -1768,13 +1770,15 @@ void sched_ttwu_pending(void)
cookie = lockdep_pin_lock(&rq->lock);
while (llist) {
+ int wake_flags = 0;
+
p = llist_entry(llist, struct task_struct, wake_entry);
llist = llist_next(llist);
- /*
- * See ttwu_queue(); we only call ttwu_queue_remote() when
- * its a x-cpu wakeup.
- */
- ttwu_do_activate(rq, p, WF_MIGRATED, cookie);
+
+ if (p->sched_remote_wakeup)
+ wake_flags = WF_MIGRATED;
+
+ ttwu_do_activate(rq, p, wake_flags, cookie);
}
lockdep_unpin_lock(&rq->lock, cookie);
@@ -1819,10 +1823,12 @@ void scheduler_ipi(void)
irq_exit();
}
-static void ttwu_queue_remote(struct task_struct *p, int cpu)
+static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
+ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
+
if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
if (!set_nr_if_polling(rq->idle))
smp_send_reschedule(cpu);
@@ -1869,7 +1875,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
#if defined(CONFIG_SMP)
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
sched_clock_cpu(cpu); /* sync clocks x-cpu */
- ttwu_queue_remote(p, cpu);
+ ttwu_queue_remote(p, cpu, wake_flags);
return;
}
#endif
@@ -2249,9 +2255,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
#endif
#endif
+#ifdef CONFIG_SCHEDSTATS
+
DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+static bool __initdata __sched_schedstats = false;
-#ifdef CONFIG_SCHEDSTATS
static void set_schedstats(bool enabled)
{
if (enabled)
@@ -2274,11 +2282,16 @@ static int __init setup_schedstats(char *str)
if (!str)
goto out;
+ /*
+ * This code is called before jump labels have been set up, so we can't
+ * change the static branch directly just yet. Instead set a temporary
+ * variable so init_schedstats() can do it later.
+ */
if (!strcmp(str, "enable")) {
- set_schedstats(true);
+ __sched_schedstats = true;
ret = 1;
} else if (!strcmp(str, "disable")) {
- set_schedstats(false);
+ __sched_schedstats = false;
ret = 1;
}
out:
@@ -2289,6 +2302,11 @@ out:
}
__setup("schedstats=", setup_schedstats);
+static void __init init_schedstats(void)
+{
+ set_schedstats(__sched_schedstats);
+}
+
#ifdef CONFIG_PROC_SYSCTL
int sysctl_schedstats(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -2309,8 +2327,10 @@ int sysctl_schedstats(struct ctl_table *table, int write,
set_schedstats(state);
return err;
}
-#endif
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
+#else /* !CONFIG_SCHEDSTATS */
+static inline void init_schedstats(void) {}
+#endif /* CONFIG_SCHEDSTATS */
/*
* fork()/clone()-time setup:
@@ -2517,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p)
*/
set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
- /* Post initialize new task's util average when its cfs_rq is set */
+ rq = __task_rq_lock(p, &rf);
post_init_entity_util_avg(&p->se);
- rq = __task_rq_lock(p, &rf);
activate_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
@@ -3152,7 +3171,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
static inline void schedule_debug(struct task_struct *prev)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
- BUG_ON(task_stack_end_corrupted(prev));
+ if (task_stack_end_corrupted(prev))
+ panic("corrupted stack end detected inside scheduler\n");
#endif
if (unlikely(in_atomic_preempt_off())) {
@@ -5129,14 +5149,16 @@ void show_state_filter(unsigned long state_filter)
/*
* reset the NMI-timeout, listing all files on a slow
* console might take a lot of time:
+ * Also, reset softlockup watchdogs on all CPUs, because
+ * another CPU might be blocked waiting for us to process
+ * an IPI.
*/
touch_nmi_watchdog();
+ touch_all_softlockup_watchdogs();
if (!state_filter || (p->state & state_filter))
sched_show_task(p);
}
- touch_all_softlockup_watchdogs();
-
#ifdef CONFIG_SCHED_DEBUG
if (!state_filter)
sysrq_sched_debug_show();
@@ -7483,6 +7505,8 @@ void __init sched_init(void)
#endif
init_sched_fair_class();
+ init_schedstats();
+
scheduler_running = 1;
}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 154ae3a51e86..14c4aa25cc45 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -9,6 +9,8 @@
* published by the Free Software Foundation.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/cpufreq.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -388,7 +390,7 @@ static int sugov_init(struct cpufreq_policy *policy)
mutex_unlock(&global_tunables_lock);
sugov_policy_free(sg_policy);
- pr_err("cpufreq: schedutil governor initialization failed (error %d)\n", ret);
+ pr_err("initialization failed (error %d)\n", ret);
return ret;
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index cf905f655ba1..0368c393a336 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -427,19 +427,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
SPLIT_NS(p->se.vruntime),
(long long)(p->nvcsw + p->nivcsw),
p->prio);
-#ifdef CONFIG_SCHEDSTATS
- if (schedstat_enabled()) {
- SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- SPLIT_NS(p->se.statistics.wait_sum),
- SPLIT_NS(p->se.sum_exec_runtime),
- SPLIT_NS(p->se.statistics.sum_sleep_runtime));
- }
-#else
+
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- 0LL, 0L,
+ SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)),
SPLIT_NS(p->se.sum_exec_runtime),
- 0LL, 0L);
-#endif
+ SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime)));
+
#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e83db73..bdcbeea90c95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2904,6 +2904,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
}
}
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ typeof(*ptr) val = (_val); \
+ typeof(*ptr) res, var = READ_ONCE(*ptr); \
+ res = var - val; \
+ if (res > var) \
+ res = 0; \
+ WRITE_ONCE(*ptr, res); \
+} while (0)
+
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
@@ -2913,15 +2930,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
- sa->load_avg = max_t(long, sa->load_avg - r, 0);
- sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->load_avg, r);
+ sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
removed_load = 1;
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
- sa->util_avg = max_t(long, sa->util_avg - r, 0);
- sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->util_avg, r);
+ sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
removed_util = 1;
}
@@ -2994,10 +3011,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
&se->avg, se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
- cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
- cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
- cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
- cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+ sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+ sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+ sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+ sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
cfs_rq_util_change(cfs_rq);
}
@@ -3246,7 +3263,7 @@ static inline void check_schedstat_required(void)
trace_sched_stat_iowait_enabled() ||
trace_sched_stat_blocked_enabled() ||
trace_sched_stat_runtime_enabled()) {
- pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+ printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
"stat_blocked and stat_runtime require the "
"kernel parameter schedstats=enabled or "
"kernel.sched_schedstats=1\n");
@@ -4185,6 +4202,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
if (!cfs_bandwidth_used())
return;
+ /* Synchronize hierarchical throttle counter: */
+ if (unlikely(!cfs_rq->throttle_uptodate)) {
+ struct rq *rq = rq_of(cfs_rq);
+ struct cfs_rq *pcfs_rq;
+ struct task_group *tg;
+
+ cfs_rq->throttle_uptodate = 1;
+
+ /* Get closest up-to-date node, because leaves go first: */
+ for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+ pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+ if (pcfs_rq->throttle_uptodate)
+ break;
+ }
+ if (tg) {
+ cfs_rq->throttle_count = pcfs_rq->throttle_count;
+ cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ }
+ }
+
/* an active group must be handled by the update_curr()->put() path */
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
return;
@@ -4500,15 +4537,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
+ /* Avoid re-evaluating load for this entity: */
+ se = parent_entity(se);
/*
* Bias pick_next to pick a task from this cfs_rq, as
* p is sleeping when it is within its sched_slice.
*/
- if (task_sleep && parent_entity(se))
- set_next_buddy(parent_entity(se));
-
- /* avoid re-evaluating load for this entity */
- se = parent_entity(se);
+ if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+ set_next_buddy(se);
break;
}
flags |= DEQUEUE_SLEEP;
@@ -8496,8 +8532,9 @@ void free_fair_sched_group(struct task_group *tg)
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
- struct cfs_rq *cfs_rq;
struct sched_entity *se;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
int i;
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8512,6 +8549,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
@@ -8525,7 +8564,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
init_entity_runnable_average(se);
+
+ raw_spin_lock_irq(&rq->lock);
post_init_entity_util_avg(se);
+ raw_spin_unlock_irq(&rq->lock);
}
return 1;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bd12c6c714ec..c5aeedf4e93a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
*/
static void cpuidle_idle_call(void)
{
- struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 72f1f3087b04..7cbeb92a1cb9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -437,7 +437,7 @@ struct cfs_rq {
u64 throttled_clock, throttled_clock_task;
u64 throttled_clock_task_time;
- int throttled, throttle_count;
+ int throttled, throttle_count, throttle_uptodate;
struct list_head throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 70b3b6a20fb0..78955cbea31c 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -33,6 +33,8 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
# define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
# define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
# define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0)
+# define schedstat_val(rq, field) ((schedstat_enabled()) ? (rq)->field : 0)
+
#else /* !CONFIG_SCHEDSTATS */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -47,6 +49,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
# define schedstat_inc(rq, field) do { } while (0)
# define schedstat_add(rq, field, amt) do { } while (0)
# define schedstat_set(var, val) do { } while (0)
+# define schedstat_val(rq, field) 0
#endif
#ifdef CONFIG_SCHED_INFO
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2effd84d83e3..87b2fc38398b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1149,13 +1149,22 @@ static struct ctl_table kern_table[] = {
},
{
.procname = "perf_event_max_stack",
- .data = NULL, /* filled in by handler */
+ .data = &sysctl_perf_event_max_stack,
.maxlen = sizeof(sysctl_perf_event_max_stack),
.mode = 0644,
.proc_handler = perf_event_max_stack_handler,
.extra1 = &zero,
.extra2 = &six_hundred_forty_kb,
},
+ {
+ .procname = "perf_event_max_contexts_per_stack",
+ .data = &sysctl_perf_event_max_contexts_per_stack,
+ .maxlen = sizeof(sysctl_perf_event_max_contexts_per_stack),
+ .mode = 0644,
+ .proc_handler = perf_event_max_stack_handler,
+ .extra1 = &zero,
+ .extra2 = &one_thousand,
+ },
#endif
#ifdef CONFIG_KMEMCHECK
{
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8c7392c4fdbd..e99df0ff1d42 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -425,6 +425,7 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
debug_object_free(timer, &hrtimer_debug_descr);
}
+EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 780bcbe1d4de..26f603da7e26 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -198,7 +198,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- file = (struct file *)array->ptrs[index];
+ file = READ_ONCE(array->ptrs[index]);
if (unlikely(!file))
return -ENOENT;
@@ -209,6 +209,10 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
event->pmu->count)
return -EINVAL;
+ if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
+ event->attr.type != PERF_TYPE_RAW))
+ return -EINVAL;
+
/*
* we don't know if the function is run successfully by the
* return value. It can be judged in other places, such as
@@ -247,7 +251,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- file = (struct file *)array->ptrs[index];
+ file = READ_ONCE(array->ptrs[index]);
if (unlikely(!file))
return -ENOENT;
@@ -349,7 +353,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
}
/* bpf+kprobe programs can access fields of 'struct pt_regs' */
-static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
/* check bounds */
if (off < 0 || off >= sizeof(struct pt_regs))
@@ -427,7 +432,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
}
}
-static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
return false;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index f96f0383f6c6..ad1d6164e946 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
{
struct trace_bprintk_fmt *pos;
+
+ if (!fmt)
+ return ERR_PTR(-EINVAL);
+
list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
if (!strcmp(pos->fmt, fmt))
return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
for (iter = start; iter < end; iter++) {
struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
if (tb_fmt) {
- *iter = tb_fmt->fmt;
+ if (!IS_ERR(tb_fmt))
+ *iter = tb_fmt->fmt;
continue;
}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e707ab3e1991..b9cfdbfae9aa 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1841,6 +1841,9 @@ config TEST_BITMAP
If unsure, say N.
+config TEST_UUID
+ tristate "Test functions located in the uuid module at runtime"
+
config TEST_RHASHTABLE
tristate "Perform selftest on resizable hash table"
default n
@@ -1849,6 +1852,17 @@ config TEST_RHASHTABLE
If unsure, say N.
+config TEST_HASH
+ tristate "Perform selftest on hash functions"
+ default n
+ help
+ Enable this option to test the kernel's integer (<linux/hash,h>)
+ and string (<linux/stringhash.h>) hash functions on boot
+ (or module load).
+
+ This is intended to help people writing architecture-specific
+ optimized versions. If unsure, say N.
+
endmenu # runtime tests
config PROVIDE_OHCI1394_DMA_INIT
diff --git a/lib/Makefile b/lib/Makefile
index 42b69185f963..ff6a7a6c6395 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
obj-y += kstrtox.o
obj-$(CONFIG_TEST_BPF) += test_bpf.o
obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
+obj-$(CONFIG_TEST_HASH) += test_hash.o
obj-$(CONFIG_TEST_KASAN) += test_kasan.o
obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
obj-$(CONFIG_TEST_LKM) += test_module.o
@@ -57,6 +58,7 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
obj-$(CONFIG_TEST_PRINTF) += test_printf.o
obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
+obj-$(CONFIG_TEST_UUID) += test_uuid.o
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
CFLAGS_kobject.o += -DDEBUG
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 4a1515f4b452..51a76af25c66 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -657,9 +657,9 @@ static struct dma_debug_entry *dma_entry_alloc(void)
spin_lock_irqsave(&free_entries_lock, flags);
if (list_empty(&free_entries)) {
- pr_err("DMA-API: debugging out of memory - disabling\n");
global_disable = true;
spin_unlock_irqrestore(&free_entries_lock, flags);
+ pr_err("DMA-API: debugging out of memory - disabling\n");
return NULL;
}
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 28cb4315fe57..0cd522753ff5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -101,7 +101,7 @@
#define iterate_and_advance(i, n, v, I, B, K) { \
if (unlikely(i->count < n)) \
n = i->count; \
- if (n) { \
+ if (i->count) { \
size_t skip = i->iov_offset; \
if (unlikely(i->type & ITER_BVEC)) { \
const struct bio_vec *bvec; \
diff --git a/lib/test_hash.c b/lib/test_hash.c
new file mode 100644
index 000000000000..c9549c8b4909
--- /dev/null
+++ b/lib/test_hash.c
@@ -0,0 +1,250 @@
+/*
+ * Test cases for <linux/hash.h> and <linux/stringhash.h>
+ * This just verifies that various ways of computing a hash
+ * produce the same thing and, for cases where a k-bit hash
+ * value is requested, is of the requested size.
+ *
+ * We fill a buffer with a 255-byte null-terminated string,
+ * and use both full_name_hash() and hashlen_string() to hash the
+ * substrings from i to j, where 0 <= i < j < 256.
+ *
+ * The returned values are used to check that __hash_32() and
+ * __hash_32_generic() compute the same thing. Likewise hash_32()
+ * and hash_64().
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt "\n"
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/hash.h>
+#include <linux/stringhash.h>
+#include <linux/printk.h>
+
+/* 32-bit XORSHIFT generator. Seed must not be zero. */
+static u32 __init __attribute_const__
+xorshift(u32 seed)
+{
+ seed ^= seed << 13;
+ seed ^= seed >> 17;
+ seed ^= seed << 5;
+ return seed;
+}
+
+/* Given a non-zero x, returns a non-zero byte. */
+static u8 __init __attribute_const__
+mod255(u32 x)
+{
+ x = (x & 0xffff) + (x >> 16); /* 1 <= x <= 0x1fffe */
+ x = (x & 0xff) + (x >> 8); /* 1 <= x <= 0x2fd */
+ x = (x & 0xff) + (x >> 8); /* 1 <= x <= 0x100 */
+ x = (x & 0xff) + (x >> 8); /* 1 <= x <= 0xff */
+ return x;
+}
+
+/* Fill the buffer with non-zero bytes. */
+static void __init
+fill_buf(char *buf, size_t len, u32 seed)
+{
+ size_t i;
+
+ for (i = 0; i < len; i++) {
+ seed = xorshift(seed);
+ buf[i] = mod255(seed);
+ }
+}
+
+/*
+ * Test the various integer hash functions. h64 (or its low-order bits)
+ * is the integer to hash. hash_or accumulates the OR of the hash values,
+ * which are later checked to see that they cover all the requested bits.
+ *
+ * Because these functions (as opposed to the string hashes) are all
+ * inline, the code being tested is actually in the module, and you can
+ * recompile and re-test the module without rebooting.
+ */
+static bool __init
+test_int_hash(unsigned long long h64, u32 hash_or[2][33])
+{
+ int k;
+ u32 h0 = (u32)h64, h1, h2;
+
+ /* Test __hash32 */
+ hash_or[0][0] |= h1 = __hash_32(h0);
+#ifdef HAVE_ARCH__HASH_32
+ hash_or[1][0] |= h2 = __hash_32_generic(h0);
+#if HAVE_ARCH__HASH_32 == 1
+ if (h1 != h2) {
+ pr_err("__hash_32(%#x) = %#x != __hash_32_generic() = %#x",
+ h0, h1, h2);
+ return false;
+ }
+#endif
+#endif
+
+ /* Test k = 1..32 bits */
+ for (k = 1; k <= 32; k++) {
+ u32 const m = ((u32)2 << (k-1)) - 1; /* Low k bits set */
+
+ /* Test hash_32 */
+ hash_or[0][k] |= h1 = hash_32(h0, k);
+ if (h1 > m) {
+ pr_err("hash_32(%#x, %d) = %#x > %#x", h0, k, h1, m);
+ return false;
+ }
+#ifdef HAVE_ARCH_HASH_32
+ h2 = hash_32_generic(h0, k);
+#if HAVE_ARCH_HASH_32 == 1
+ if (h1 != h2) {
+ pr_err("hash_32(%#x, %d) = %#x != hash_32_generic() "
+ " = %#x", h0, k, h1, h2);
+ return false;
+ }
+#else
+ if (h2 > m) {
+ pr_err("hash_32_generic(%#x, %d) = %#x > %#x",
+ h0, k, h1, m);
+ return false;
+ }
+#endif
+#endif
+ /* Test hash_64 */
+ hash_or[1][k] |= h1 = hash_64(h64, k);
+ if (h1 > m) {
+ pr_err("hash_64(%#llx, %d) = %#x > %#x", h64, k, h1, m);
+ return false;
+ }
+#ifdef HAVE_ARCH_HASH_64
+ h2 = hash_64_generic(h64, k);
+#if HAVE_ARCH_HASH_64 == 1
+ if (h1 != h2) {
+ pr_err("hash_64(%#llx, %d) = %#x != hash_64_generic() "
+ "= %#x", h64, k, h1, h2);
+ return false;
+ }
+#else
+ if (h2 > m) {
+ pr_err("hash_64_generic(%#llx, %d) = %#x > %#x",
+ h64, k, h1, m);
+ return false;
+ }
+#endif
+#endif
+ }
+
+ (void)h2; /* Suppress unused variable warning */
+ return true;
+}
+
+#define SIZE 256 /* Run time is cubic in SIZE */
+
+static int __init
+test_hash_init(void)
+{
+ char buf[SIZE+1];
+ u32 string_or = 0, hash_or[2][33] = { 0 };
+ unsigned tests = 0;
+ unsigned long long h64 = 0;
+ int i, j;
+
+ fill_buf(buf, SIZE, 1);
+
+ /* Test every possible non-empty substring in the buffer. */
+ for (j = SIZE; j > 0; --j) {
+ buf[j] = '\0';
+
+ for (i = 0; i <= j; i++) {
+ u64 hashlen = hashlen_string(buf+i);
+ u32 h0 = full_name_hash(buf+i, j-i);
+
+ /* Check that hashlen_string gets the length right */
+ if (hashlen_len(hashlen) != j-i) {
+ pr_err("hashlen_string(%d..%d) returned length"
+ " %u, expected %d",
+ i, j, hashlen_len(hashlen), j-i);
+ return -EINVAL;
+ }
+ /* Check that the hashes match */
+ if (hashlen_hash(hashlen) != h0) {
+ pr_err("hashlen_string(%d..%d) = %08x != "
+ "full_name_hash() = %08x",
+ i, j, hashlen_hash(hashlen), h0);
+ return -EINVAL;
+ }
+
+ string_or |= h0;
+ h64 = h64 << 32 | h0; /* For use with hash_64 */
+ if (!test_int_hash(h64, hash_or))
+ return -EINVAL;
+ tests++;
+ } /* i */
+ } /* j */
+
+ /* The OR of all the hash values should cover all the bits */
+ if (~string_or) {
+ pr_err("OR of all string hash results = %#x != %#x",
+ string_or, -1u);
+ return -EINVAL;
+ }
+ if (~hash_or[0][0]) {
+ pr_err("OR of all __hash_32 results = %#x != %#x",
+ hash_or[0][0], -1u);
+ return -EINVAL;
+ }
+#ifdef HAVE_ARCH__HASH_32
+#if HAVE_ARCH__HASH_32 != 1 /* Test is pointless if results match */
+ if (~hash_or[1][0]) {
+ pr_err("OR of all __hash_32_generic results = %#x != %#x",
+ hash_or[1][0], -1u);
+ return -EINVAL;
+ }
+#endif
+#endif
+
+ /* Likewise for all the i-bit hash values */
+ for (i = 1; i <= 32; i++) {
+ u32 const m = ((u32)2 << (i-1)) - 1; /* Low i bits set */
+
+ if (hash_or[0][i] != m) {
+ pr_err("OR of all hash_32(%d) results = %#x "
+ "(%#x expected)", i, hash_or[0][i], m);
+ return -EINVAL;
+ }
+ if (hash_or[1][i] != m) {
+ pr_err("OR of all hash_64(%d) results = %#x "
+ "(%#x expected)", i, hash_or[1][i], m);
+ return -EINVAL;
+ }
+ }
+
+ /* Issue notices about skipped tests. */
+#ifndef HAVE_ARCH__HASH_32
+ pr_info("__hash_32() has no arch implementation to test.");
+#elif HAVE_ARCH__HASH_32 != 1
+ pr_info("__hash_32() is arch-specific; not compared to generic.");
+#endif
+#ifndef HAVE_ARCH_HASH_32
+ pr_info("hash_32() has no arch implementation to test.");
+#elif HAVE_ARCH_HASH_32 != 1
+ pr_info("hash_32() is arch-specific; not compared to generic.");
+#endif
+#ifndef HAVE_ARCH_HASH_64
+ pr_info("hash_64() has no arch implementation to test.");
+#elif HAVE_ARCH_HASH_64 != 1
+ pr_info("hash_64() is arch-specific; not compared to generic.");
+#endif
+
+ pr_notice("%u tests passed.", tests);
+
+ return 0;
+}
+
+static void __exit test_hash_exit(void)
+{
+}
+
+module_init(test_hash_init); /* Does everything */
+module_exit(test_hash_exit); /* Does nothing */
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_uuid.c b/lib/test_uuid.c
new file mode 100644
index 000000000000..547d3127a3cf
--- /dev/null
+++ b/lib/test_uuid.c
@@ -0,0 +1,133 @@
+/*
+ * Test cases for lib/uuid.c module.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/uuid.h>
+
+struct test_uuid_data {
+ const char *uuid;
+ uuid_le le;
+ uuid_be be;
+};
+
+static const struct test_uuid_data test_uuid_test_data[] = {
+ {
+ .uuid = "c33f4995-3701-450e-9fbf-206a2e98e576",
+ .le = UUID_LE(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76),
+ .be = UUID_BE(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76),
+ },
+ {
+ .uuid = "64b4371c-77c1-48f9-8221-29f054fc023b",
+ .le = UUID_LE(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b),
+ .be = UUID_BE(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b),
+ },
+ {
+ .uuid = "0cb4ddff-a545-4401-9d06-688af53e7f84",
+ .le = UUID_LE(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84),
+ .be = UUID_BE(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84),
+ },
+};
+
+static const char * const test_uuid_wrong_data[] = {
+ "c33f4995-3701-450e-9fbf206a2e98e576 ", /* no hyphen(s) */
+ "64b4371c-77c1-48f9-8221-29f054XX023b", /* invalid character(s) */
+ "0cb4ddff-a545-4401-9d06-688af53e", /* not enough data */
+};
+
+static unsigned total_tests __initdata;
+static unsigned failed_tests __initdata;
+
+static void __init test_uuid_failed(const char *prefix, bool wrong, bool be,
+ const char *data, const char *actual)
+{
+ pr_err("%s test #%u %s %s data: '%s'\n",
+ prefix,
+ total_tests,
+ wrong ? "passed on wrong" : "failed on",
+ be ? "BE" : "LE",
+ data);
+ if (actual && *actual)
+ pr_err("%s test #%u actual data: '%s'\n",
+ prefix,
+ total_tests,
+ actual);
+ failed_tests++;
+}
+
+static void __init test_uuid_test(const struct test_uuid_data *data)
+{
+ uuid_le le;
+ uuid_be be;
+ char buf[48];
+
+ /* LE */
+ total_tests++;
+ if (uuid_le_to_bin(data->uuid, &le))
+ test_uuid_failed("conversion", false, false, data->uuid, NULL);
+
+ total_tests++;
+ if (uuid_le_cmp(data->le, le)) {
+ sprintf(buf, "%pUl", &le);
+ test_uuid_failed("cmp", false, false, data->uuid, buf);
+ }
+
+ /* BE */
+ total_tests++;
+ if (uuid_be_to_bin(data->uuid, &be))
+ test_uuid_failed("conversion", false, true, data->uuid, NULL);
+
+ total_tests++;
+ if (uuid_be_cmp(data->be, be)) {
+ sprintf(buf, "%pUb", &be);
+ test_uuid_failed("cmp", false, true, data->uuid, buf);
+ }
+}
+
+static void __init test_uuid_wrong(const char *data)
+{
+ uuid_le le;
+ uuid_be be;
+
+ /* LE */
+ total_tests++;
+ if (!uuid_le_to_bin(data, &le))
+ test_uuid_failed("negative", true, false, data, NULL);
+
+ /* BE */
+ total_tests++;
+ if (!uuid_be_to_bin(data, &be))
+ test_uuid_failed("negative", true, true, data, NULL);
+}
+
+static int __init test_uuid_init(void)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(test_uuid_test_data); i++)
+ test_uuid_test(&test_uuid_test_data[i]);
+
+ for (i = 0; i < ARRAY_SIZE(test_uuid_wrong_data); i++)
+ test_uuid_wrong(test_uuid_wrong_data[i]);
+
+ if (failed_tests == 0)
+ pr_info("all %u tests passed\n", total_tests);
+ else
+ pr_err("failed %u out of %u tests\n", failed_tests, total_tests);
+
+ return failed_tests ? -EINVAL : 0;
+}
+module_init(test_uuid_init);
+
+static void __exit test_uuid_exit(void)
+{
+ /* do nothing */
+}
+module_exit(test_uuid_exit);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/uuid.c b/lib/uuid.c
index e116ae5fa00f..37687af77ff8 100644
--- a/lib/uuid.c
+++ b/lib/uuid.c
@@ -106,8 +106,8 @@ static int __uuid_to_bin(const char *uuid, __u8 b[16], const u8 ei[16])
return -EINVAL;
for (i = 0; i < 16; i++) {
- int hi = hex_to_bin(uuid[si[i]] + 0);
- int lo = hex_to_bin(uuid[si[i]] + 1);
+ int hi = hex_to_bin(uuid[si[i] + 0]);
+ int lo = hex_to_bin(uuid[si[i] + 1]);
b[ei[i]] = (hi << 4) | lo;
}
diff --git a/mm/Kconfig b/mm/Kconfig
index 2664c118b5d2..3e2daef3c946 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -648,7 +648,8 @@ config DEFERRED_STRUCT_PAGE_INIT
bool "Defer initialisation of struct pages to kthreads"
default n
depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
- depends on MEMORY_HOTPLUG
+ depends on NO_BOOTMEM && MEMORY_HOTPLUG
+ depends on !FLATMEM
help
Ordinarily all struct pages are initialised during early boot in a
single thread. On very large machines this can take a considerable
diff --git a/mm/cma.c b/mm/cma.c
index ea506eb18cd6..bd0e1412475e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -183,7 +183,8 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
return -EINVAL;
/* ensure minimal alignment required by mm core */
- alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+ alignment = PAGE_SIZE <<
+ max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
/* alignment should be aligned with order_per_bit */
if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
@@ -266,8 +267,8 @@ int __init cma_declare_contiguous(phys_addr_t base,
* migratetype page by page allocator's buddy algorithm. In the case,
* you couldn't get a contiguous memory, which is not what we want.
*/
- alignment = max(alignment,
- (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+ alignment = max(alignment, (phys_addr_t)PAGE_SIZE <<
+ max_t(unsigned long, MAX_ORDER - 1, pageblock_order));
base = ALIGN(base, alignment);
size = ALIGN(size, alignment);
limit &= ~(alignment - 1);
diff --git a/mm/compaction.c b/mm/compaction.c
index 1427366ad673..79bfe0e06907 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -441,25 +441,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
/* Found a free page, break it into order-0 pages */
isolated = split_free_page(page);
+ if (!isolated)
+ break;
+
total_isolated += isolated;
+ cc->nr_freepages += isolated;
for (i = 0; i < isolated; i++) {
list_add(&page->lru, freelist);
page++;
}
-
- /* If a page was split, advance to the end of it */
- if (isolated) {
- cc->nr_freepages += isolated;
- if (!strict &&
- cc->nr_migratepages <= cc->nr_freepages) {
- blockpfn += isolated;
- break;
- }
-
- blockpfn += isolated - 1;
- cursor += isolated - 1;
- continue;
+ if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
+ blockpfn += isolated;
+ break;
}
+ /* Advance to the end of split page */
+ blockpfn += isolated - 1;
+ cursor += isolated - 1;
+ continue;
isolate_fail:
if (strict)
@@ -469,6 +467,9 @@ isolate_fail:
}
+ if (locked)
+ spin_unlock_irqrestore(&cc->zone->lock, flags);
+
/*
* There is a tiny chance that we have read bogus compound_order(),
* so be careful to not go outside of the pageblock.
@@ -490,9 +491,6 @@ isolate_fail:
if (strict && blockpfn < end_pfn)
total_isolated = 0;
- if (locked)
- spin_unlock_irqrestore(&cc->zone->lock, flags);
-
/* Update the pageblock-skip if the whole pageblock was scanned */
if (blockpfn == end_pfn)
update_pageblock_skip(cc, valid_page, total_isolated, false);
@@ -1011,6 +1009,7 @@ static void isolate_freepages(struct compact_control *cc)
block_end_pfn = block_start_pfn,
block_start_pfn -= pageblock_nr_pages,
isolate_start_pfn = block_start_pfn) {
+ unsigned long isolated;
/*
* This can iterate a massively long zone without finding any
@@ -1035,8 +1034,12 @@ static void isolate_freepages(struct compact_control *cc)
continue;
/* Found a block suitable for isolating free pages from. */
- isolate_freepages_block(cc, &isolate_start_pfn,
- block_end_pfn, freelist, false);
+ isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+ block_end_pfn, freelist, false);
+ /* If isolation failed early, do not continue needlessly */
+ if (!isolated && isolate_start_pfn < block_end_pfn &&
+ cc->nr_migratepages > cc->nr_freepages)
+ break;
/*
* If we isolated enough freepages, or aborted due to async
diff --git a/mm/fadvise.c b/mm/fadvise.c
index b8024fa7101d..6c707bfe02fd 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -126,6 +126,17 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
*/
start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT;
end_index = (endbyte >> PAGE_SHIFT);
+ if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK) {
+ /* First page is tricky as 0 - 1 = -1, but pgoff_t
+ * is unsigned, so the end_index >= start_index
+ * check below would be true and we'll discard the whole
+ * file cache which is not what was asked.
+ */
+ if (end_index == 0)
+ break;
+
+ end_index--;
+ }
if (end_index >= start_index) {
unsigned long count = invalidate_mapping_pages(mapping,
diff --git a/mm/filemap.c b/mm/filemap.c
index 9665b1d4f318..20f3b1f33f0e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -143,13 +143,15 @@ static void page_cache_tree_delete(struct address_space *mapping,
return;
/*
- * Track node that only contains shadow entries.
+ * Track node that only contains shadow entries. DAX mappings contain
+ * no shadow entries and may contain other exceptional entries so skip
+ * those.
*
* Avoid acquiring the list_lru lock if already tracked. The
* list_empty() test is safe as node->private_list is
* protected by mapping->tree_lock.
*/
- if (!workingset_node_pages(node) &&
+ if (!dax_mapping(mapping) && !workingset_node_pages(node) &&
list_empty(&node->private_list)) {
node->private_data = mapping;
list_lru_add(&workingset_shadow_nodes, &node->private_list);
@@ -580,14 +582,24 @@ static int page_cache_tree_insert(struct address_space *mapping,
if (!radix_tree_exceptional_entry(p))
return -EEXIST;
- if (WARN_ON(dax_mapping(mapping)))
- return -EINVAL;
-
- if (shadowp)
- *shadowp = p;
mapping->nrexceptional--;
- if (node)
- workingset_node_shadows_dec(node);
+ if (!dax_mapping(mapping)) {
+ if (shadowp)
+ *shadowp = p;
+ if (node)
+ workingset_node_shadows_dec(node);
+ } else {
+ /* DAX can replace empty locked entry with a hole */
+ WARN_ON_ONCE(p !=
+ (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+ RADIX_DAX_ENTRY_LOCK));
+ /* DAX accounts exceptional entries as normal pages */
+ if (node)
+ workingset_node_pages_dec(node);
+ /* Wakeup waiters for exceptional entry lock */
+ dax_wake_mapping_entry_waiter(mapping, page->index,
+ false);
+ }
}
radix_tree_replace_slot(slot, page);
mapping->nrpages++;
@@ -2174,7 +2186,7 @@ repeat:
if (file->f_ra.mmap_miss > 0)
file->f_ra.mmap_miss--;
addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
- do_set_pte(vma, addr, page, pte, false, false, true);
+ do_set_pte(vma, addr, page, pte, false, false);
unlock_page(page);
goto next;
unlock:
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d26162e81fea..c1f3c0be150a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -832,8 +832,27 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
* Only the process that called mmap() has reserves for
* private mappings.
*/
- if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
- return true;
+ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+ /*
+ * Like the shared case above, a hole punch or truncate
+ * could have been performed on the private mapping.
+ * Examine the value of chg to determine if reserves
+ * actually exist or were previously consumed.
+ * Very Subtle - The value of chg comes from a previous
+ * call to vma_needs_reserves(). The reserve map for
+ * private mappings has different (opposite) semantics
+ * than that of shared mappings. vma_needs_reserves()
+ * has already taken this difference in semantics into
+ * account. Therefore, the meaning of chg is the same
+ * as in the shared case above. Code could easily be
+ * combined, but keeping it separate draws attention to
+ * subtle differences.
+ */
+ if (chg)
+ return false;
+ else
+ return true;
+ }
return false;
}
@@ -1011,6 +1030,7 @@ static void destroy_compound_gigantic_page(struct page *page,
int nr_pages = 1 << order;
struct page *p = page + 1;
+ atomic_set(compound_mapcount_ptr(page), 0);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
clear_compound_head(p);
set_page_refcounted(p);
@@ -1816,6 +1836,25 @@ static long __vma_reservation_common(struct hstate *h,
if (vma->vm_flags & VM_MAYSHARE)
return ret;
+ else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) {
+ /*
+ * In most cases, reserves always exist for private mappings.
+ * However, a file associated with mapping could have been
+ * hole punched or truncated after reserves were consumed.
+ * As subsequent fault on such a range will not use reserves.
+ * Subtle - The reserve map for private mappings has the
+ * opposite meaning than that of shared mappings. If NO
+ * entry is in the reserve map, it means a reservation exists.
+ * If an entry exists in the reserve map, it means the
+ * reservation has already been consumed. As a result, the
+ * return value of this routine is the opposite of the
+ * value returned from reserve map manipulation routines above.
+ */
+ if (ret)
+ return 0;
+ else
+ return 1;
+ }
else
return ret < 0 ? ret : 0;
}
@@ -4190,7 +4229,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
if (saddr) {
spte = huge_pte_offset(svma->vm_mm, saddr);
if (spte) {
- mm_inc_nr_pmds(mm);
get_page(virt_to_page(spte));
break;
}
@@ -4205,9 +4243,9 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
if (pud_none(*pud)) {
pud_populate(mm, pud,
(pmd_t *)((unsigned long)spte & PAGE_MASK));
+ mm_inc_nr_pmds(mm);
} else {
put_page(virt_to_page(spte));
- mm_inc_nr_pmds(mm);
}
spin_unlock(ptl);
out:
diff --git a/mm/internal.h b/mm/internal.h
index a37e5b6f9d25..2524ec880e24 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -24,7 +24,8 @@
*/
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
- __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
+ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
+ __GFP_ATOMIC)
/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 18b6a2b8d183..6845f9294696 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -508,7 +508,7 @@ void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
kasan_kmalloc(cache, object, cache->object_size, flags);
}
-void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
+static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
{
unsigned long size = cache->object_size;
unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
@@ -626,7 +626,7 @@ void kasan_krealloc(const void *object, size_t size, gfp_t flags)
kasan_kmalloc(page->slab_cache, object, size, flags);
}
-void kasan_kfree(void *ptr)
+void kasan_poison_kfree(void *ptr)
{
struct page *page;
@@ -636,7 +636,7 @@ void kasan_kfree(void *ptr)
kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page),
KASAN_FREE_PAGE);
else
- kasan_slab_free(page->slab_cache, ptr);
+ kasan_poison_slab_free(page->slab_cache, ptr);
}
void kasan_kfree_large(const void *ptr)
@@ -763,8 +763,8 @@ static int kasan_mem_notifier(struct notifier_block *nb,
static int __init kasan_memhotplug_init(void)
{
- pr_err("WARNING: KASAN doesn't support memory hot-add\n");
- pr_err("Memory hot-add will be disabled\n");
+ pr_info("WARNING: KASAN doesn't support memory hot-add\n");
+ pr_info("Memory hot-add will be disabled\n");
hotplug_memory_notifier(kasan_mem_notifier, 0);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 7f7ac51d7faf..fb87923552ef 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -77,7 +77,6 @@ struct kasan_alloc_meta {
struct kasan_track track;
u32 state : 2; /* enum kasan_state */
u32 alloc_size : 30;
- u32 reserved;
};
struct qlist_node {
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e6429926e957..04320d3adbef 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -307,8 +307,10 @@ static void hex_dump_object(struct seq_file *seq,
len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE);
seq_printf(seq, " hex dump (first %zu bytes):\n", len);
+ kasan_disable_current();
seq_hex_dump(seq, " ", DUMP_PREFIX_NONE, HEX_ROW_SIZE,
HEX_GROUP_SIZE, ptr, len, HEX_ASCII);
+ kasan_enable_current();
}
/*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cf428d7b9a03..ac8664db3823 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1108,6 +1108,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
limit = READ_ONCE(memcg->memsw.limit);
if (count <= limit)
margin = min(margin, limit - count);
+ else
+ margin = 0;
}
return margin;
@@ -1302,6 +1304,8 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
mem_cgroup_iter_break(memcg, iter);
if (chosen)
put_task_struct(chosen);
+ /* Set a dummy value to return "true". */
+ chosen = (void *) 1;
goto unlock;
case OOM_SCAN_OK:
break;
@@ -1604,7 +1608,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
- if (!current->memcg_may_oom || current->memcg_in_oom)
+ if (!current->memcg_may_oom)
return;
/*
* We are in the middle of the charge context here, so we
@@ -2892,6 +2896,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
* ordering is imposed by list_lru_node->lock taken by
* memcg_drain_all_list_lrus().
*/
+ rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
css_for_each_descendant_pre(css, &memcg->css) {
child = mem_cgroup_from_css(css);
BUG_ON(child->kmemcg_id != kmemcg_id);
@@ -2899,6 +2904,8 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
if (!memcg->use_hierarchy)
break;
}
+ rcu_read_unlock();
+
memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
memcg_free_cache_id(kmemcg_id);
@@ -4196,7 +4203,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
return &memcg->css;
fail:
mem_cgroup_free(memcg);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
static int
@@ -4305,24 +4312,6 @@ static int mem_cgroup_do_precharge(unsigned long count)
return 0;
}
-/**
- * get_mctgt_type - get target type of moving charge
- * @vma: the vma the pte to be checked belongs
- * @addr: the address corresponding to the pte to be checked
- * @ptent: the pte to be checked
- * @target: the pointer the target page or swap ent will be stored(can be NULL)
- *
- * Returns
- * 0(MC_TARGET_NONE): if the pte is not a target for move charge.
- * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
- * move charge. if @target is not NULL, the page is stored in target->page
- * with extra refcnt got(Callers should handle it).
- * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
- * target for charge migration. if @target is not NULL, the entry is stored
- * in target->ent.
- *
- * Called with pte lock held.
- */
union mc_target {
struct page *page;
swp_entry_t ent;
@@ -4511,6 +4500,25 @@ out:
return ret;
}
+/**
+ * get_mctgt_type - get target type of moving charge
+ * @vma: the vma the pte to be checked belongs
+ * @addr: the address corresponding to the pte to be checked
+ * @ptent: the pte to be checked
+ * @target: the pointer the target page or swap ent will be stored(can be NULL)
+ *
+ * Returns
+ * 0(MC_TARGET_NONE): if the pte is not a target for move charge.
+ * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
+ * move charge. if @target is not NULL, the page is stored in target->page
+ * with extra refcnt got(Callers should handle it).
+ * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
+ * target for charge migration. if @target is not NULL, the entry is stored
+ * in target->ent.
+ *
+ * Called with pte lock held.
+ */
+
static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
unsigned long addr, pte_t ptent, union mc_target *target)
{
@@ -5536,6 +5544,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
struct mem_cgroup *memcg;
unsigned int nr_pages;
bool compound;
+ unsigned long flags;
VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
@@ -5566,10 +5575,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
commit_charge(newpage, memcg, false);
- local_irq_disable();
+ local_irq_save(flags);
mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
memcg_check_events(memcg, newpage);
- local_irq_enable();
+ local_irq_restore(flags);
}
DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
diff --git a/mm/memory.c b/mm/memory.c
index a1b93d9e4449..cd1f29e4897e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -63,6 +63,7 @@
#include <linux/dma-debug.h>
#include <linux/debugfs.h>
#include <linux/userfaultfd_k.h>
+#include <linux/dax.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
@@ -2492,8 +2493,6 @@ void unmap_mapping_range(struct address_space *mapping,
if (details.last_index < details.first_index)
details.last_index = ULONG_MAX;
-
- /* DAX uses i_mmap_lock to serialise file truncate vs page fault */
i_mmap_lock_write(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
@@ -2825,7 +2824,8 @@ oom:
*/
static int __do_fault(struct vm_area_struct *vma, unsigned long address,
pgoff_t pgoff, unsigned int flags,
- struct page *cow_page, struct page **page)
+ struct page *cow_page, struct page **page,
+ void **entry)
{
struct vm_fault vmf;
int ret;
@@ -2840,8 +2840,10 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
ret = vma->vm_ops->fault(vma, &vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
- if (!vmf.page)
- goto out;
+ if (ret & VM_FAULT_DAX_LOCKED) {
+ *entry = vmf.entry;
+ return ret;
+ }
if (unlikely(PageHWPoison(vmf.page))) {
if (ret & VM_FAULT_LOCKED)
@@ -2855,7 +2857,6 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
else
VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
- out:
*page = vmf.page;
return ret;
}
@@ -2876,7 +2877,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
* vm_ops->map_pages.
*/
void do_set_pte(struct vm_area_struct *vma, unsigned long address,
- struct page *page, pte_t *pte, bool write, bool anon, bool old)
+ struct page *page, pte_t *pte, bool write, bool anon)
{
pte_t entry;
@@ -2884,8 +2885,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
entry = mk_pte(page, vma->vm_page_prot);
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- if (old)
- entry = pte_mkold(entry);
if (anon) {
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address, false);
@@ -2899,16 +2898,8 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
update_mmu_cache(vma, address, pte);
}
-/*
- * If architecture emulates "accessed" or "young" bit without HW support,
- * there is no much gain with fault_around.
- */
static unsigned long fault_around_bytes __read_mostly =
-#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
- PAGE_SIZE;
-#else
rounddown_pow_of_two(65536);
-#endif
#ifdef CONFIG_DEBUG_FS
static int fault_around_bytes_get(void *data, u64 *val)
@@ -3031,24 +3022,13 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
*/
if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
- if (!pte_same(*pte, orig_pte))
- goto unlock_out;
do_fault_around(vma, address, pte, pgoff, flags);
- /* Check if the fault is handled by faultaround */
- if (!pte_same(*pte, orig_pte)) {
- /*
- * Faultaround produce old pte, but the pte we've
- * handler fault for should be young.
- */
- pte_t entry = pte_mkyoung(*pte);
- if (ptep_set_access_flags(vma, address, pte, entry, 0))
- update_mmu_cache(vma, address, pte);
+ if (!pte_same(*pte, orig_pte))
goto unlock_out;
- }
pte_unmap_unlock(pte, ptl);
}
- ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
+ ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
@@ -3059,7 +3039,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
put_page(fault_page);
return ret;
}
- do_set_pte(vma, address, fault_page, pte, false, false, false);
+ do_set_pte(vma, address, fault_page, pte, false, false);
unlock_page(fault_page);
unlock_out:
pte_unmap_unlock(pte, ptl);
@@ -3071,6 +3051,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
struct page *fault_page, *new_page;
+ void *fault_entry;
struct mem_cgroup *memcg;
spinlock_t *ptl;
pte_t *pte;
@@ -3088,42 +3069,36 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
return VM_FAULT_OOM;
}
- ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page);
+ ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page,
+ &fault_entry);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
goto uncharge_out;
- if (fault_page)
+ if (!(ret & VM_FAULT_DAX_LOCKED))
copy_user_highpage(new_page, fault_page, address, vma);
__SetPageUptodate(new_page);
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
if (unlikely(!pte_same(*pte, orig_pte))) {
pte_unmap_unlock(pte, ptl);
- if (fault_page) {
+ if (!(ret & VM_FAULT_DAX_LOCKED)) {
unlock_page(fault_page);
put_page(fault_page);
} else {
- /*
- * The fault handler has no page to lock, so it holds
- * i_mmap_lock for read to protect against truncate.
- */
- i_mmap_unlock_read(vma->vm_file->f_mapping);
+ dax_unlock_mapping_entry(vma->vm_file->f_mapping,
+ pgoff);
}
goto uncharge_out;
}
- do_set_pte(vma, address, new_page, pte, true, true, false);
+ do_set_pte(vma, address, new_page, pte, true, true);
mem_cgroup_commit_charge(new_page, memcg, false, false);
lru_cache_add_active_or_unevictable(new_page, vma);
pte_unmap_unlock(pte, ptl);
- if (fault_page) {
+ if (!(ret & VM_FAULT_DAX_LOCKED)) {
unlock_page(fault_page);
put_page(fault_page);
} else {
- /*
- * The fault handler has no page to lock, so it holds
- * i_mmap_lock for read to protect against truncate.
- */
- i_mmap_unlock_read(vma->vm_file->f_mapping);
+ dax_unlock_mapping_entry(vma->vm_file->f_mapping, pgoff);
}
return ret;
uncharge_out:
@@ -3143,7 +3118,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
int dirtied = 0;
int ret, tmp;
- ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
+ ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
@@ -3168,7 +3143,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
put_page(fault_page);
return ret;
}
- do_set_pte(vma, address, fault_page, pte, true, false, false);
+ do_set_pte(vma, address, fault_page, pte, true, false);
pte_unmap_unlock(pte, ptl);
if (set_page_dirty(fault_page))
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index caf2a14c37ad..e3cbdcaff2a5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -263,7 +263,7 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
-void register_page_bootmem_info_node(struct pglist_data *pgdat)
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
{
unsigned long i, pfn, end_pfn, nr_pages;
int node = pgdat->node_id;
@@ -300,7 +300,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
* multiple nodes we check that this pfn does not already
* reside in some other nodes.
*/
- if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+ if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
register_page_bootmem_info_section(pfn);
}
}
diff --git a/mm/mempool.c b/mm/mempool.c
index 9e075f829d0d..8f65464da5de 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -104,20 +104,16 @@ static inline void poison_element(mempool_t *pool, void *element)
static void kasan_poison_element(mempool_t *pool, void *element)
{
- if (pool->alloc == mempool_alloc_slab)
- kasan_poison_slab_free(pool->pool_data, element);
- if (pool->alloc == mempool_kmalloc)
- kasan_kfree(element);
+ if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
+ kasan_poison_kfree(element);
if (pool->alloc == mempool_alloc_pages)
kasan_free_pages(element, (unsigned long)pool->pool_data);
}
static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags)
{
- if (pool->alloc == mempool_alloc_slab)
- kasan_slab_alloc(pool->pool_data, element, flags);
- if (pool->alloc == mempool_kmalloc)
- kasan_krealloc(element, (size_t)pool->pool_data, flags);
+ if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
+ kasan_unpoison_slab(element);
if (pool->alloc == mempool_alloc_pages)
kasan_alloc_pages(element, (unsigned long)pool->pool_data);
}
diff --git a/mm/migrate.c b/mm/migrate.c
index 9baf41c877ff..bd3fdc202e8b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -431,6 +431,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
return MIGRATEPAGE_SUCCESS;
}
+EXPORT_SYMBOL(migrate_page_move_mapping);
/*
* The expected number of remaining references is the same as that
@@ -586,6 +587,7 @@ void migrate_page_copy(struct page *newpage, struct page *page)
mem_cgroup_migrate(page, newpage);
}
+EXPORT_SYMBOL(migrate_page_copy);
/************************************************************
* Migration functions
diff --git a/mm/mmap.c b/mm/mmap.c
index d3d9a94ca031..de2c1769cc68 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -168,7 +168,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
return next;
}
-static unsigned long do_brk(unsigned long addr, unsigned long len);
+static int do_brk(unsigned long addr, unsigned long len);
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
@@ -224,7 +224,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
goto out;
/* Ok, looks good - let it rip. */
- if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
+ if (do_brk(oldbrk, newbrk-oldbrk) < 0)
goto out;
set_brk:
@@ -2625,7 +2625,7 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
* anonymous maps. eventually we may be able to do some
* brk-specific accounting here.
*/
-static unsigned long do_brk(unsigned long addr, unsigned long len)
+static int do_brk(unsigned long addr, unsigned long len)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
@@ -2636,7 +2636,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
len = PAGE_ALIGN(len);
if (!len)
- return addr;
+ return 0;
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
@@ -2703,13 +2703,13 @@ out:
if (flags & VM_LOCKED)
mm->locked_vm += (len >> PAGE_SHIFT);
vma->vm_flags |= VM_SOFTDIRTY;
- return addr;
+ return 0;
}
-unsigned long vm_brk(unsigned long addr, unsigned long len)
+int vm_brk(unsigned long addr, unsigned long len)
{
struct mm_struct *mm = current->mm;
- unsigned long ret;
+ int ret;
bool populate;
if (down_write_killable(&mm->mmap_sem))
@@ -2718,7 +2718,7 @@ unsigned long vm_brk(unsigned long addr, unsigned long len)
ret = do_brk(addr, len);
populate = ((mm->def_flags & VM_LOCKED) != 0);
up_write(&mm->mmap_sem);
- if (populate)
+ if (populate && !ret)
mm_populate(addr, len);
return ret;
}
diff --git a/mm/nommu.c b/mm/nommu.c
index c8bd59a03c71..c2e58880207f 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1682,7 +1682,7 @@ void exit_mmap(struct mm_struct *mm)
}
}
-unsigned long vm_brk(unsigned long addr, unsigned long len)
+int vm_brk(unsigned long addr, unsigned long len)
{
return -ENOMEM;
}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5bb2f7698ad7..ddf74487f848 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -443,13 +443,29 @@ static bool __oom_reap_task(struct task_struct *tsk)
{
struct mmu_gather tlb;
struct vm_area_struct *vma;
- struct mm_struct *mm;
+ struct mm_struct *mm = NULL;
struct task_struct *p;
struct zap_details details = {.check_swap_entries = true,
.ignore_dirty = true};
bool ret = true;
/*
+ * We have to make sure to not race with the victim exit path
+ * and cause premature new oom victim selection:
+ * __oom_reap_task exit_mm
+ * atomic_inc_not_zero
+ * mmput
+ * atomic_dec_and_test
+ * exit_oom_victim
+ * [...]
+ * out_of_memory
+ * select_bad_process
+ * # no TIF_MEMDIE task selects new victim
+ * unmap_page_range # frees some memory
+ */
+ mutex_lock(&oom_lock);
+
+ /*
* Make sure we find the associated mm_struct even when the particular
* thread has already terminated and cleared its mm.
* We might have race with exit path so consider our work done if there
@@ -457,19 +473,14 @@ static bool __oom_reap_task(struct task_struct *tsk)
*/
p = find_lock_task_mm(tsk);
if (!p)
- return true;
-
+ goto unlock_oom;
mm = p->mm;
- if (!atomic_inc_not_zero(&mm->mm_users)) {
- task_unlock(p);
- return true;
- }
-
+ atomic_inc(&mm->mm_users);
task_unlock(p);
if (!down_read_trylock(&mm->mmap_sem)) {
ret = false;
- goto out;
+ goto unlock_oom;
}
tlb_gather_mmu(&tlb, mm, 0, -1);
@@ -511,13 +522,15 @@ static bool __oom_reap_task(struct task_struct *tsk)
* to release its memory.
*/
set_bit(MMF_OOM_REAPED, &mm->flags);
-out:
+unlock_oom:
+ mutex_unlock(&oom_lock);
/*
* Drop our reference but make sure the mmput slow path is called from a
* different context because we shouldn't risk we get stuck there and
* put the oom_reaper out of the way.
*/
- mmput_async(mm);
+ if (mm)
+ mmput_async(mm);
return ret;
}
@@ -607,12 +620,8 @@ void try_oom_reaper(struct task_struct *tsk)
if (atomic_read(&mm->mm_users) > 1) {
rcu_read_lock();
for_each_process(p) {
- bool exiting;
-
if (!process_shares_mm(p, mm))
continue;
- if (same_thread_group(p, tsk))
- continue;
if (fatal_signal_pending(p))
continue;
@@ -620,10 +629,7 @@ void try_oom_reaper(struct task_struct *tsk)
* If the task is exiting make sure the whole thread group
* is exiting and cannot acces mm anymore.
*/
- spin_lock_irq(&p->sighand->siglock);
- exiting = signal_group_exit(p->signal);
- spin_unlock_irq(&p->sighand->siglock);
- if (exiting)
+ if (signal_group_exit(p->signal))
continue;
/* Give up */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b9956fdee8f5..e2481949494c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -373,8 +373,9 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc);
unsigned long bytes = vm_dirty_bytes;
unsigned long bg_bytes = dirty_background_bytes;
- unsigned long ratio = vm_dirty_ratio;
- unsigned long bg_ratio = dirty_background_ratio;
+ /* convert ratios to per-PAGE_SIZE for higher precision */
+ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100;
+ unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100;
unsigned long thresh;
unsigned long bg_thresh;
struct task_struct *tsk;
@@ -386,26 +387,28 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
/*
* The byte settings can't be applied directly to memcg
* domains. Convert them to ratios by scaling against
- * globally available memory.
+ * globally available memory. As the ratios are in
+ * per-PAGE_SIZE, they can be obtained by dividing bytes by
+ * number of pages.
*/
if (bytes)
- ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 /
- global_avail, 100UL);
+ ratio = min(DIV_ROUND_UP(bytes, global_avail),
+ PAGE_SIZE);
if (bg_bytes)
- bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 /
- global_avail, 100UL);
+ bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail),
+ PAGE_SIZE);
bytes = bg_bytes = 0;
}
if (bytes)
thresh = DIV_ROUND_UP(bytes, PAGE_SIZE);
else
- thresh = (ratio * available_memory) / 100;
+ thresh = (ratio * available_memory) / PAGE_SIZE;
if (bg_bytes)
bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE);
else
- bg_thresh = (bg_ratio * available_memory) / 100;
+ bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
if (bg_thresh >= thresh)
bg_thresh = thresh / 2;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f8f3bfc435ee..6903b695ebae 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -656,6 +656,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
return;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
+
__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
INIT_LIST_HEAD(&page->lru);
@@ -673,6 +676,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
return;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
+
__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
set_page_private(page, 0);
@@ -2609,11 +2615,12 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
page = list_last_entry(list, struct page, lru);
else
page = list_first_entry(list, struct page, lru);
- } while (page && check_new_pcp(page));
- __dec_zone_state(zone, NR_ALLOC_BATCH);
- list_del(&page->lru);
- pcp->count--;
+ __dec_zone_state(zone, NR_ALLOC_BATCH);
+ list_del(&page->lru);
+ pcp->count--;
+
+ } while (check_new_pcp(page));
} else {
/*
* We most definitely don't want callers attempting to
@@ -3023,6 +3030,7 @@ reset_fair:
apply_fair = false;
fair_skipped = false;
reset_alloc_batches(ac->preferred_zoneref->zone);
+ z = ac->preferred_zoneref;
goto zonelist_scan;
}
@@ -3596,6 +3604,17 @@ retry:
*/
alloc_flags = gfp_to_alloc_flags(gfp_mask);
+ /*
+ * Reset the zonelist iterators if memory policies can be ignored.
+ * These allocations are high priority and system rather than user
+ * orientated.
+ */
+ if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+ ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
+ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+ ac->high_zoneidx, ac->nodemask);
+ }
+
/* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, order,
alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3604,12 +3623,6 @@ retry:
/* Allocate without watermarks if the context allows */
if (alloc_flags & ALLOC_NO_WATERMARKS) {
- /*
- * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
- * the allocation is high priority and these type of
- * allocations are system rather than user orientated
- */
- ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
page = get_page_from_freelist(gfp_mask, order,
ALLOC_NO_WATERMARKS, ac);
if (page)
@@ -3808,7 +3821,11 @@ retry_cpuset:
/* Dirty zone balancing only done in the fast path */
ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
- /* The preferred zone is used for statistics later */
+ /*
+ * The preferred zone is used for statistics but crucially it is
+ * also used as the starting point for the zonelist iterator. It
+ * may get reset for allocations that ignore memory policies.
+ */
ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
ac.high_zoneidx, ac.nodemask);
if (!ac.preferred_zoneref) {
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 2d864e64f7fe..44a4c029c8e7 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -390,8 +390,10 @@ void __init page_ext_init(void)
* We know some arch can have a nodes layout such as
* -------------pfn-------------->
* N0 | N1 | N2 | N0 | N1 | N2|....
+ *
+ * Take into account DEFERRED_STRUCT_PAGE_INIT.
*/
- if (pfn_to_nid(pfn) != nid)
+ if (early_pfn_to_nid(pfn) != nid)
continue;
if (init_section_page_ext(pfn, nid))
goto oom;
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 792b56da13d8..fedeba88c9cb 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -55,6 +55,8 @@ void __reset_page_owner(struct page *page, unsigned int order)
for (i = 0; i < (1 << order); i++) {
page_ext = lookup_page_ext(page + i);
+ if (unlikely(!page_ext))
+ continue;
__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
}
}
@@ -62,6 +64,7 @@ void __reset_page_owner(struct page *page, unsigned int order)
void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
{
struct page_ext *page_ext = lookup_page_ext(page);
+
struct stack_trace trace = {
.nr_entries = 0,
.max_entries = ARRAY_SIZE(page_ext->trace_entries),
@@ -69,6 +72,9 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
.skip = 3,
};
+ if (unlikely(!page_ext))
+ return;
+
save_stack_trace(&trace);
page_ext->order = order;
@@ -82,6 +88,8 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
void __set_page_owner_migrate_reason(struct page *page, int reason)
{
struct page_ext *page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
page_ext->last_migrate_reason = reason;
}
@@ -89,6 +97,12 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
gfp_t __get_page_owner_gfp(struct page *page)
{
struct page_ext *page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ /*
+ * The caller just returns 0 if no valid gfp
+ * So return 0 here too.
+ */
+ return 0;
return page_ext->gfp_mask;
}
@@ -99,6 +113,9 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
struct page_ext *new_ext = lookup_page_ext(newpage);
int i;
+ if (unlikely(!old_ext || !new_ext))
+ return;
+
new_ext->order = old_ext->order;
new_ext->gfp_mask = old_ext->gfp_mask;
new_ext->nr_entries = old_ext->nr_entries;
@@ -190,8 +207,15 @@ void __dump_page_owner(struct page *page)
.nr_entries = page_ext->nr_entries,
.entries = &page_ext->trace_entries[0],
};
- gfp_t gfp_mask = page_ext->gfp_mask;
- int mt = gfpflags_to_migratetype(gfp_mask);
+ gfp_t gfp_mask;
+ int mt;
+
+ if (unlikely(!page_ext)) {
+ pr_alert("There is not page extension available.\n");
+ return;
+ }
+ gfp_mask = page_ext->gfp_mask;
+ mt = gfpflags_to_migratetype(gfp_mask);
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
pr_alert("page_owner info is not active (free page?)\n");
@@ -251,6 +275,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
}
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ continue;
/*
* Some pages could be missed by concurrent allocation or free,
@@ -317,6 +343,8 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
continue;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ continue;
/* Maybe overraping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
diff --git a/mm/page_poison.c b/mm/page_poison.c
index 1eae5fad2446..2e647c65916b 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -54,6 +54,9 @@ static inline void set_page_poison(struct page *page)
struct page_ext *page_ext;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
+
__set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
}
@@ -62,6 +65,9 @@ static inline void clear_page_poison(struct page *page)
struct page_ext *page_ext;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
+
__clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
}
@@ -70,7 +76,7 @@ bool page_is_poisoned(struct page *page)
struct page_ext *page_ext;
page_ext = lookup_page_ext(page);
- if (!page_ext)
+ if (unlikely(!page_ext))
return false;
return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
diff --git a/mm/percpu.c b/mm/percpu.c
index 0c59684f1ff2..9903830aaebb 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -112,7 +112,7 @@ struct pcpu_chunk {
int map_used; /* # of map entries used before the sentry */
int map_alloc; /* # of map entries allocated */
int *map; /* allocation map */
- struct work_struct map_extend_work;/* async ->map[] extension */
+ struct list_head map_extend_list;/* on pcpu_map_extend_chunks */
void *data; /* chunk data */
int first_free; /* no free below this */
@@ -162,10 +162,13 @@ static struct pcpu_chunk *pcpu_reserved_chunk;
static int pcpu_reserved_chunk_limit;
static DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */
-static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop */
+static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */
static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
+/* chunks which need their map areas extended, protected by pcpu_lock */
+static LIST_HEAD(pcpu_map_extend_chunks);
+
/*
* The number of empty populated pages, protected by pcpu_lock. The
* reserved chunk doesn't contribute to the count.
@@ -395,13 +398,19 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
{
int margin, new_alloc;
+ lockdep_assert_held(&pcpu_lock);
+
if (is_atomic) {
margin = 3;
if (chunk->map_alloc <
- chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW &&
- pcpu_async_enabled)
- schedule_work(&chunk->map_extend_work);
+ chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) {
+ if (list_empty(&chunk->map_extend_list)) {
+ list_add_tail(&chunk->map_extend_list,
+ &pcpu_map_extend_chunks);
+ pcpu_schedule_balance_work();
+ }
+ }
} else {
margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
}
@@ -435,6 +444,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
unsigned long flags;
+ lockdep_assert_held(&pcpu_alloc_mutex);
+
new = pcpu_mem_zalloc(new_size);
if (!new)
return -ENOMEM;
@@ -467,20 +478,6 @@ out_unlock:
return 0;
}
-static void pcpu_map_extend_workfn(struct work_struct *work)
-{
- struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk,
- map_extend_work);
- int new_alloc;
-
- spin_lock_irq(&pcpu_lock);
- new_alloc = pcpu_need_to_extend(chunk, false);
- spin_unlock_irq(&pcpu_lock);
-
- if (new_alloc)
- pcpu_extend_area_map(chunk, new_alloc);
-}
-
/**
* pcpu_fit_in_area - try to fit the requested allocation in a candidate area
* @chunk: chunk the candidate area belongs to
@@ -740,7 +737,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
chunk->map_used = 1;
INIT_LIST_HEAD(&chunk->list);
- INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn);
+ INIT_LIST_HEAD(&chunk->map_extend_list);
chunk->free_size = pcpu_unit_size;
chunk->contig_hint = pcpu_unit_size;
@@ -895,6 +892,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
return NULL;
}
+ if (!is_atomic)
+ mutex_lock(&pcpu_alloc_mutex);
+
spin_lock_irqsave(&pcpu_lock, flags);
/* serve reserved allocations from the reserved chunk if available */
@@ -967,12 +967,9 @@ restart:
if (is_atomic)
goto fail;
- mutex_lock(&pcpu_alloc_mutex);
-
if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
chunk = pcpu_create_chunk();
if (!chunk) {
- mutex_unlock(&pcpu_alloc_mutex);
err = "failed to allocate new chunk";
goto fail;
}
@@ -983,7 +980,6 @@ restart:
spin_lock_irqsave(&pcpu_lock, flags);
}
- mutex_unlock(&pcpu_alloc_mutex);
goto restart;
area_found:
@@ -993,8 +989,6 @@ area_found:
if (!is_atomic) {
int page_start, page_end, rs, re;
- mutex_lock(&pcpu_alloc_mutex);
-
page_start = PFN_DOWN(off);
page_end = PFN_UP(off + size);
@@ -1005,7 +999,6 @@ area_found:
spin_lock_irqsave(&pcpu_lock, flags);
if (ret) {
- mutex_unlock(&pcpu_alloc_mutex);
pcpu_free_area(chunk, off, &occ_pages);
err = "failed to populate";
goto fail_unlock;
@@ -1045,6 +1038,8 @@ fail:
/* see the flag handling in pcpu_blance_workfn() */
pcpu_atomic_alloc_failed = true;
pcpu_schedule_balance_work();
+ } else {
+ mutex_unlock(&pcpu_alloc_mutex);
}
return NULL;
}
@@ -1129,6 +1124,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
continue;
+ list_del_init(&chunk->map_extend_list);
list_move(&chunk->list, &to_free);
}
@@ -1146,6 +1142,25 @@ static void pcpu_balance_workfn(struct work_struct *work)
pcpu_destroy_chunk(chunk);
}
+ /* service chunks which requested async area map extension */
+ do {
+ int new_alloc = 0;
+
+ spin_lock_irq(&pcpu_lock);
+
+ chunk = list_first_entry_or_null(&pcpu_map_extend_chunks,
+ struct pcpu_chunk, map_extend_list);
+ if (chunk) {
+ list_del_init(&chunk->map_extend_list);
+ new_alloc = pcpu_need_to_extend(chunk, false);
+ }
+
+ spin_unlock_irq(&pcpu_lock);
+
+ if (new_alloc)
+ pcpu_extend_area_map(chunk, new_alloc);
+ } while (chunk);
+
/*
* Ensure there are certain number of free populated pages for
* atomic allocs. Fill up from the most packed so that atomic
@@ -1644,7 +1659,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
*/
schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
INIT_LIST_HEAD(&schunk->list);
- INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn);
+ INIT_LIST_HEAD(&schunk->map_extend_list);
schunk->base_addr = base_addr;
schunk->map = smap;
schunk->map_alloc = ARRAY_SIZE(smap);
@@ -1673,7 +1688,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
if (dyn_size) {
dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
INIT_LIST_HEAD(&dchunk->list);
- INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn);
+ INIT_LIST_HEAD(&dchunk->map_extend_list);
dchunk->base_addr = base_addr;
dchunk->map = dmap;
dchunk->map_alloc = ARRAY_SIZE(dmap);
diff --git a/mm/rmap.c b/mm/rmap.c
index 8a839935b18c..0ea5d9071b32 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1098,6 +1098,8 @@ void page_move_anon_rmap(struct page *page,
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_VMA(!anon_vma, vma);
+ if (IS_ENABLED(CONFIG_DEBUG_VM) && PageTransHuge(page))
+ address &= HPAGE_PMD_MASK;
VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page);
anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
diff --git a/mm/shmem.c b/mm/shmem.c
index e418a995427d..24463b67b6ef 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2227,7 +2227,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
/* Remove the !PageUptodate pages we added */
shmem_undo_range(inode,
(loff_t)start << PAGE_SHIFT,
- (loff_t)index << PAGE_SHIFT, true);
+ ((loff_t)index << PAGE_SHIFT) - 1, true);
goto undone;
}
@@ -2645,10 +2645,11 @@ static int shmem_xattr_handler_get(const struct xattr_handler *handler,
}
static int shmem_xattr_handler_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
+ struct shmem_inode_info *info = SHMEM_I(inode);
name = xattr_full_name(handler, name);
return simple_xattr_set(&info->xattrs, name, value, size, flags);
diff --git a/mm/swap.c b/mm/swap.c
index 95916142fc46..90530ff8ed16 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -242,7 +242,7 @@ void rotate_reclaimable_page(struct page *page)
get_page(page);
local_irq_save(flags);
pvec = this_cpu_ptr(&lru_rotate_pvecs);
- if (!pagevec_add(pvec, page))
+ if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_move_tail(pvec);
local_irq_restore(flags);
}
@@ -296,7 +296,7 @@ void activate_page(struct page *page)
struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
get_page(page);
- if (!pagevec_add(pvec, page))
+ if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, __activate_page, NULL);
put_cpu_var(activate_page_pvecs);
}
@@ -391,9 +391,8 @@ static void __lru_cache_add(struct page *page)
struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
get_page(page);
- if (!pagevec_space(pvec))
+ if (!pagevec_add(pvec, page) || PageCompound(page))
__pagevec_lru_add(pvec);
- pagevec_add(pvec, page);
put_cpu_var(lru_add_pvec);
}
@@ -628,7 +627,7 @@ void deactivate_file_page(struct page *page)
if (likely(get_page_unless_zero(page))) {
struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
- if (!pagevec_add(pvec, page))
+ if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
put_cpu_var(lru_deactivate_file_pvecs);
}
@@ -648,7 +647,7 @@ void deactivate_page(struct page *page)
struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
get_page(page);
- if (!pagevec_add(pvec, page))
+ if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
put_cpu_var(lru_deactivate_pvecs);
}
@@ -667,6 +666,24 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
+/*
+ * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
+ * workqueue, aiding in getting memory freed.
+ */
+static struct workqueue_struct *lru_add_drain_wq;
+
+static int __init lru_init(void)
+{
+ lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
+
+ if (WARN(!lru_add_drain_wq,
+ "Failed to create workqueue lru_add_drain_wq"))
+ return -ENOMEM;
+
+ return 0;
+}
+early_initcall(lru_init);
+
void lru_add_drain_all(void)
{
static DEFINE_MUTEX(lock);
@@ -686,7 +703,7 @@ void lru_add_drain_all(void)
pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
- schedule_work_on(cpu, work);
+ queue_work_on(cpu, lru_add_drain_wq, work);
cpumask_set_cpu(cpu, &has_work);
}
}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 0d457e7db8d6..c99463ac02fb 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -252,7 +252,10 @@ static inline void free_swap_cache(struct page *page)
void free_page_and_swap_cache(struct page *page)
{
free_swap_cache(page);
- put_page(page);
+ if (is_huge_zero_page(page))
+ put_huge_zero_page();
+ else
+ put_page(page);
}
/*
diff --git a/mm/truncate.c b/mm/truncate.c
index b00272810871..4064f8f53daa 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -34,40 +34,38 @@ static void clear_exceptional_entry(struct address_space *mapping,
if (shmem_mapping(mapping))
return;
- spin_lock_irq(&mapping->tree_lock);
-
if (dax_mapping(mapping)) {
- if (radix_tree_delete_item(&mapping->page_tree, index, entry))
- mapping->nrexceptional--;
- } else {
- /*
- * Regular page slots are stabilized by the page lock even
- * without the tree itself locked. These unlocked entries
- * need verification under the tree lock.
- */
- if (!__radix_tree_lookup(&mapping->page_tree, index, &node,
- &slot))
- goto unlock;
- if (*slot != entry)
- goto unlock;
- radix_tree_replace_slot(slot, NULL);
- mapping->nrexceptional--;
- if (!node)
- goto unlock;
- workingset_node_shadows_dec(node);
- /*
- * Don't track node without shadow entries.
- *
- * Avoid acquiring the list_lru lock if already untracked.
- * The list_empty() test is safe as node->private_list is
- * protected by mapping->tree_lock.
- */
- if (!workingset_node_shadows(node) &&
- !list_empty(&node->private_list))
- list_lru_del(&workingset_shadow_nodes,
- &node->private_list);
- __radix_tree_delete_node(&mapping->page_tree, node);
+ dax_delete_mapping_entry(mapping, index);
+ return;
}
+ spin_lock_irq(&mapping->tree_lock);
+ /*
+ * Regular page slots are stabilized by the page lock even
+ * without the tree itself locked. These unlocked entries
+ * need verification under the tree lock.
+ */
+ if (!__radix_tree_lookup(&mapping->page_tree, index, &node,
+ &slot))
+ goto unlock;
+ if (*slot != entry)
+ goto unlock;
+ radix_tree_replace_slot(slot, NULL);
+ mapping->nrexceptional--;
+ if (!node)
+ goto unlock;
+ workingset_node_shadows_dec(node);
+ /*
+ * Don't track node without shadow entries.
+ *
+ * Avoid acquiring the list_lru lock if already untracked.
+ * The list_empty() test is safe as node->private_list is
+ * protected by mapping->tree_lock.
+ */
+ if (!workingset_node_shadows(node) &&
+ !list_empty(&node->private_list))
+ list_lru_del(&workingset_shadow_nodes,
+ &node->private_list);
+ __radix_tree_delete_node(&mapping->page_tree, node);
unlock:
spin_unlock_irq(&mapping->tree_lock);
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cf7ad1a53be0..e11475cdeb7a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1105,7 +1105,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases);
*/
void vm_unmap_ram(const void *mem, unsigned int count)
{
- unsigned long size = count << PAGE_SHIFT;
+ unsigned long size = (unsigned long)count << PAGE_SHIFT;
unsigned long addr = (unsigned long)mem;
BUG_ON(!addr);
@@ -1140,7 +1140,7 @@ EXPORT_SYMBOL(vm_unmap_ram);
*/
void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
{
- unsigned long size = count << PAGE_SHIFT;
+ unsigned long size = (unsigned long)count << PAGE_SHIFT;
unsigned long addr;
void *mem;
@@ -1574,14 +1574,15 @@ void *vmap(struct page **pages, unsigned int count,
unsigned long flags, pgprot_t prot)
{
struct vm_struct *area;
+ unsigned long size; /* In bytes */
might_sleep();
if (count > totalram_pages)
return NULL;
- area = get_vm_area_caller((count << PAGE_SHIFT), flags,
- __builtin_return_address(0));
+ size = (unsigned long)count << PAGE_SHIFT;
+ area = get_vm_area_caller(size, flags, __builtin_return_address(0));
if (!area)
return NULL;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 77e42ef388c2..cb2a67bb4158 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1061,6 +1061,8 @@ static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
continue;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ continue;
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 34917d55d311..8f9e89ca1d31 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -412,7 +412,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
/* HEADLESS page stored */
bud = HEADLESS;
} else {
- bud = (handle - zhdr->first_num) & BUDDY_MASK;
+ bud = handle_to_buddy(handle);
switch (bud) {
case FIRST:
@@ -572,15 +572,19 @@ next:
pool->pages_nr--;
spin_unlock(&pool->lock);
return 0;
- } else if (zhdr->first_chunks != 0 &&
- zhdr->last_chunks != 0 && zhdr->middle_chunks != 0) {
- /* Full, add to buddied list */
- list_add(&zhdr->buddy, &pool->buddied);
- } else if (!test_bit(PAGE_HEADLESS, &page->private)) {
- z3fold_compact_page(zhdr);
- /* add to unbuddied list */
- freechunks = num_free_chunks(zhdr);
- list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+ } else if (!test_bit(PAGE_HEADLESS, &page->private)) {
+ if (zhdr->first_chunks != 0 &&
+ zhdr->last_chunks != 0 &&
+ zhdr->middle_chunks != 0) {
+ /* Full, add to buddied list */
+ list_add(&zhdr->buddy, &pool->buddied);
+ } else {
+ z3fold_compact_page(zhdr);
+ /* add to unbuddied list */
+ freechunks = num_free_chunks(zhdr);
+ list_add(&zhdr->buddy,
+ &pool->unbuddied[freechunks]);
+ }
}
/* add to beginning of LRU */
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 72698db958e7..b6d4f258cb53 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -45,6 +45,8 @@
*
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
@@ -483,16 +485,16 @@ static inline unsigned long zs_stat_get(struct size_class *class,
#ifdef CONFIG_ZSMALLOC_STAT
-static int __init zs_stat_init(void)
+static void __init zs_stat_init(void)
{
- if (!debugfs_initialized())
- return -ENODEV;
+ if (!debugfs_initialized()) {
+ pr_warn("debugfs not available, stat dir not created\n");
+ return;
+ }
zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
if (!zs_stat_root)
- return -ENOMEM;
-
- return 0;
+ pr_warn("debugfs 'zsmalloc' stat dir creation failed\n");
}
static void __exit zs_stat_exit(void)
@@ -577,8 +579,10 @@ static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
struct dentry *entry;
- if (!zs_stat_root)
+ if (!zs_stat_root) {
+ pr_warn("no root stat dir, not creating <%s> stat dir\n", name);
return;
+ }
entry = debugfs_create_dir(name, zs_stat_root);
if (!entry) {
@@ -592,7 +596,8 @@ static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
if (!entry) {
pr_warn("%s: debugfs file entry <%s> creation failed\n",
name, "classes");
- return;
+ debugfs_remove_recursive(pool->stat_dentry);
+ pool->stat_dentry = NULL;
}
}
@@ -602,9 +607,8 @@ static void zs_pool_stat_destroy(struct zs_pool *pool)
}
#else /* CONFIG_ZSMALLOC_STAT */
-static int __init zs_stat_init(void)
+static void __init zs_stat_init(void)
{
- return 0;
}
static void __exit zs_stat_exit(void)
@@ -2011,17 +2015,10 @@ static int __init zs_init(void)
zpool_register_driver(&zs_zpool_driver);
#endif
- ret = zs_stat_init();
- if (ret) {
- pr_err("zs stat initialization failed\n");
- goto stat_fail;
- }
+ zs_stat_init();
+
return 0;
-stat_fail:
-#ifdef CONFIG_ZPOOL
- zpool_unregister_driver(&zs_zpool_driver);
-#endif
notifier_fail:
zs_unregister_cpu_notifier();
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index a1e273af6fc8..82a116ba590e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -290,6 +290,10 @@ static void vlan_sync_address(struct net_device *dev,
if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr))
return;
+ /* vlan continues to inherit address of lower device */
+ if (vlan_dev_inherit_address(vlandev, dev))
+ goto out;
+
/* vlan address was different from the old address and is equal to
* the new address */
if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
@@ -302,6 +306,7 @@ static void vlan_sync_address(struct net_device *dev,
!ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
dev_uc_add(dev, vlandev->dev_addr);
+out:
ether_addr_copy(vlan->real_dev_addr, dev->dev_addr);
}
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 9d010a09ab98..cc1557978066 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -109,6 +109,8 @@ int vlan_check_real_dev(struct net_device *real_dev,
void vlan_setup(struct net_device *dev);
int register_vlan_dev(struct net_device *dev);
void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+bool vlan_dev_inherit_address(struct net_device *dev,
+ struct net_device *real_dev);
static inline u32 vlan_get_ingress_priority(struct net_device *dev,
u16 vlan_tci)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e7e62570bdb8..86ae75b77390 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -245,6 +245,17 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
}
+bool vlan_dev_inherit_address(struct net_device *dev,
+ struct net_device *real_dev)
+{
+ if (dev->addr_assign_type != NET_ADDR_STOLEN)
+ return false;
+
+ ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return true;
+}
+
static int vlan_dev_open(struct net_device *dev)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
@@ -255,7 +266,8 @@ static int vlan_dev_open(struct net_device *dev)
!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
return -ENETDOWN;
- if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) {
+ if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) &&
+ !vlan_dev_inherit_address(dev, real_dev)) {
err = dev_uc_add(real_dev, dev->dev_addr);
if (err < 0)
goto out;
@@ -560,8 +572,10 @@ static int vlan_dev_init(struct net_device *dev)
/* ipv6 shared card related stuff */
dev->dev_id = real_dev->dev_id;
- if (is_zero_ether_addr(dev->dev_addr))
- eth_hw_addr_inherit(dev, real_dev);
+ if (is_zero_ether_addr(dev->dev_addr)) {
+ ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
+ dev->addr_assign_type = NET_ADDR_STOLEN;
+ }
if (is_zero_ether_addr(dev->broadcast))
memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
diff --git a/net/9p/client.c b/net/9p/client.c
index ea79ee9a7348..3fc94a49ccd5 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -518,10 +518,10 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
if (err)
goto out_err;
- if (p9_is_proto_dotu(c))
+ if (p9_is_proto_dotu(c) && ecode < 512)
err = -ecode;
- if (!err || !IS_ERR_VALUE(err)) {
+ if (!err) {
err = p9_errstr2errno(ename, strlen(ename));
p9_debug(P9_DEBUG_9P, "<<< RERROR (%d) %s\n",
@@ -605,10 +605,10 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
if (err)
goto out_err;
- if (p9_is_proto_dotu(c))
+ if (p9_is_proto_dotu(c) && ecode < 512)
err = -ecode;
- if (!err || !IS_ERR_VALUE(err)) {
+ if (!err) {
err = p9_errstr2errno(ename, strlen(ename));
p9_debug(P9_DEBUG_9P, "<<< RERROR (%d) %s\n",
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 4fd6af47383a..adb6e3d21b1e 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -124,7 +124,7 @@ as_indicate_complete:
break;
case as_addparty:
case as_dropparty:
- sk->sk_err_soft = msg->reply;
+ sk->sk_err_soft = -msg->reply;
/* < 0 failure, otherwise ep_ref */
clear_bit(ATM_VF_WAITING, &vcc->flags);
break;
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 3fa0a9ee98d1..878563a8354d 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -546,7 +546,7 @@ static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr,
schedule();
}
finish_wait(sk_sleep(sk), &wait);
- error = xchg(&sk->sk_err_soft, 0);
+ error = -xchg(&sk->sk_err_soft, 0);
out:
release_sock(sk);
return error;
@@ -573,7 +573,7 @@ static int svc_dropparty(struct socket *sock, int ep_ref)
error = -EUNATCH;
goto out;
}
- error = xchg(&sk->sk_err_soft, 0);
+ error = -xchg(&sk->sk_err_soft, 0);
out:
release_sock(sk);
return error;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fbd0acf80b13..2fdebabbfacd 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -976,7 +976,8 @@ static int ax25_release(struct socket *sock)
release_sock(sk);
ax25_disconnect(ax25, 0);
lock_sock(sk);
- ax25_destroy_socket(ax25);
+ if (!sock_flag(ax25->sk, SOCK_DESTROY))
+ ax25_destroy_socket(ax25);
break;
case AX25_STATE_3:
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 951cd57bb07d..5237dff6941d 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -102,6 +102,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
switch (ax25->state) {
case AX25_STATE_0:
+ case AX25_STATE_2:
/* Magic here: If we listen() and a new link dies before it
is accepted() it isn't 'dead' so doesn't get removed. */
if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -111,6 +112,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
sock_hold(sk);
ax25_destroy_socket(ax25);
bh_unlock_sock(sk);
+ /* Ungrab socket and destroy it */
sock_put(sk);
} else
ax25_destroy_socket(ax25);
@@ -213,7 +215,8 @@ void ax25_ds_t1_timeout(ax25_cb *ax25)
case AX25_STATE_2:
if (ax25->n2count == ax25->n2) {
ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
- ax25_disconnect(ax25, ETIMEDOUT);
+ if (!sock_flag(ax25->sk, SOCK_DESTROY))
+ ax25_disconnect(ax25, ETIMEDOUT);
return;
} else {
ax25->n2count++;
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 004467c9e6e1..2c0d6ef66f9d 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -38,6 +38,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
switch (ax25->state) {
case AX25_STATE_0:
+ case AX25_STATE_2:
/* Magic here: If we listen() and a new link dies before it
is accepted() it isn't 'dead' so doesn't get removed. */
if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -47,6 +48,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
sock_hold(sk);
ax25_destroy_socket(ax25);
bh_unlock_sock(sk);
+ /* Ungrab socket and destroy it */
sock_put(sk);
} else
ax25_destroy_socket(ax25);
@@ -144,7 +146,8 @@ void ax25_std_t1timer_expiry(ax25_cb *ax25)
case AX25_STATE_2:
if (ax25->n2count == ax25->n2) {
ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
- ax25_disconnect(ax25, ETIMEDOUT);
+ if (!sock_flag(ax25->sk, SOCK_DESTROY))
+ ax25_disconnect(ax25, ETIMEDOUT);
return;
} else {
ax25->n2count++;
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 3b78e8473a01..655a7d4c96e1 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,8 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
{
ax25_clear_queues(ax25);
- ax25_stop_heartbeat(ax25);
+ if (!sock_flag(ax25->sk, SOCK_DESTROY))
+ ax25_stop_heartbeat(ax25);
ax25_stop_t1timer(ax25);
ax25_stop_t2timer(ax25);
ax25_stop_t3timer(ax25);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index e3857ed4057f..6c2901a86230 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -374,6 +374,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
if (skb_cow(skb, ETH_HLEN) < 0)
goto out;
+ ethhdr = eth_hdr(skb);
icmph = (struct batadv_icmp_header *)skb->data;
icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmph;
if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN)
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 343d2c904399..287a3879ed7e 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1033,7 +1033,9 @@ void batadv_softif_destroy_sysfs(struct net_device *soft_iface)
static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
struct list_head *head)
{
+ struct batadv_priv *bat_priv = netdev_priv(soft_iface);
struct batadv_hard_iface *hard_iface;
+ struct batadv_softif_vlan *vlan;
list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
if (hard_iface->soft_iface == soft_iface)
@@ -1041,6 +1043,13 @@ static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
BATADV_IF_CLEANUP_KEEP);
}
+ /* destroy the "untagged" VLAN */
+ vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS);
+ if (vlan) {
+ batadv_softif_destroy_vlan(bat_priv, vlan);
+ batadv_softif_vlan_put(vlan);
+ }
+
batadv_sysfs_del_meshif(soft_iface);
unregister_netdevice_queue(soft_iface, head);
}
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index feaf492b01ca..57ec87f37050 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -650,8 +650,10 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
/* increase the refcounter of the related vlan */
vlan = batadv_softif_vlan_get(bat_priv, vid);
- if (WARN(!vlan, "adding TT local entry %pM to non-existent VLAN %d",
- addr, BATADV_PRINT_VID(vid))) {
+ if (!vlan) {
+ net_ratelimited_function(batadv_info, soft_iface,
+ "adding TT local entry %pM to non-existent VLAN %d\n",
+ addr, BATADV_PRINT_VID(vid));
kfree(tt_local);
tt_local = NULL;
goto out;
@@ -691,7 +693,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
if (unlikely(hash_added != 0)) {
/* remove the reference for the hash */
batadv_tt_local_entry_put(tt_local);
- batadv_softif_vlan_put(vlan);
goto out;
}
@@ -2269,6 +2270,29 @@ static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv,
return crc;
}
+/**
+ * batadv_tt_req_node_release - free tt_req node entry
+ * @ref: kref pointer of the tt req_node entry
+ */
+static void batadv_tt_req_node_release(struct kref *ref)
+{
+ struct batadv_tt_req_node *tt_req_node;
+
+ tt_req_node = container_of(ref, struct batadv_tt_req_node, refcount);
+
+ kfree(tt_req_node);
+}
+
+/**
+ * batadv_tt_req_node_put - decrement the tt_req_node refcounter and
+ * possibly release it
+ * @tt_req_node: tt_req_node to be free'd
+ */
+static void batadv_tt_req_node_put(struct batadv_tt_req_node *tt_req_node)
+{
+ kref_put(&tt_req_node->refcount, batadv_tt_req_node_release);
+}
+
static void batadv_tt_req_list_free(struct batadv_priv *bat_priv)
{
struct batadv_tt_req_node *node;
@@ -2278,7 +2302,7 @@ static void batadv_tt_req_list_free(struct batadv_priv *bat_priv)
hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) {
hlist_del_init(&node->list);
- kfree(node);
+ batadv_tt_req_node_put(node);
}
spin_unlock_bh(&bat_priv->tt.req_list_lock);
@@ -2315,7 +2339,7 @@ static void batadv_tt_req_purge(struct batadv_priv *bat_priv)
if (batadv_has_timed_out(node->issued_at,
BATADV_TT_REQUEST_TIMEOUT)) {
hlist_del_init(&node->list);
- kfree(node);
+ batadv_tt_req_node_put(node);
}
}
spin_unlock_bh(&bat_priv->tt.req_list_lock);
@@ -2347,9 +2371,11 @@ batadv_tt_req_node_new(struct batadv_priv *bat_priv,
if (!tt_req_node)
goto unlock;
+ kref_init(&tt_req_node->refcount);
ether_addr_copy(tt_req_node->addr, orig_node->orig);
tt_req_node->issued_at = jiffies;
+ kref_get(&tt_req_node->refcount);
hlist_add_head(&tt_req_node->list, &bat_priv->tt.req_list);
unlock:
spin_unlock_bh(&bat_priv->tt.req_list_lock);
@@ -2613,13 +2639,19 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv,
out:
if (primary_if)
batadv_hardif_put(primary_if);
+
if (ret && tt_req_node) {
spin_lock_bh(&bat_priv->tt.req_list_lock);
- /* hlist_del_init() verifies tt_req_node still is in the list */
- hlist_del_init(&tt_req_node->list);
+ if (!hlist_unhashed(&tt_req_node->list)) {
+ hlist_del_init(&tt_req_node->list);
+ batadv_tt_req_node_put(tt_req_node);
+ }
spin_unlock_bh(&bat_priv->tt.req_list_lock);
- kfree(tt_req_node);
}
+
+ if (tt_req_node)
+ batadv_tt_req_node_put(tt_req_node);
+
kfree(tvlv_tt_data);
return ret;
}
@@ -3055,7 +3087,7 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv,
if (!batadv_compare_eth(node->addr, resp_src))
continue;
hlist_del_init(&node->list);
- kfree(node);
+ batadv_tt_req_node_put(node);
}
spin_unlock_bh(&bat_priv->tt.req_list_lock);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 6a577f4f8ba7..ba846b078af8 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1137,11 +1137,13 @@ struct batadv_tt_change_node {
* struct batadv_tt_req_node - data to keep track of the tt requests in flight
* @addr: mac address address of the originator this request was sent to
* @issued_at: timestamp used for purging stale tt requests
+ * @refcount: number of contexts the object is used by
* @list: list node for batadv_priv_tt::req_list
*/
struct batadv_tt_req_node {
u8 addr[ETH_ALEN];
unsigned long issued_at;
+ struct kref refcount;
struct hlist_node list;
};
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index dcea4f4c62b3..c18080ad4085 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -279,6 +279,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
* change from under us.
*/
list_for_each_entry(v, &vg->vlan_list, vlist) {
+ if (!br_vlan_should_use(v))
+ continue;
f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
if (f && f->is_local && !f->dst)
fdb_delete_local(br, NULL, f);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 160797722228..43d2cd862bc2 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -213,8 +213,7 @@ drop:
}
EXPORT_SYMBOL_GPL(br_handle_frame_finish);
-/* note: already called with rcu_read_lock */
-static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static void __br_handle_local_finish(struct sk_buff *skb)
{
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
u16 vid = 0;
@@ -222,6 +221,14 @@ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_bu
/* check if vlan is allowed, to avoid spoofing */
if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
+}
+
+/* note: already called with rcu_read_lock */
+static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct net_bridge_port *p = br_port_get_rcu(skb->dev);
+
+ __br_handle_local_finish(skb);
BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
br_pass_frame_up(skb);
@@ -274,7 +281,9 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
if (p->br->stp_enabled == BR_NO_STP ||
fwd_mask & (1u << dest[5]))
goto forward;
- break;
+ *pskb = skb;
+ __br_handle_local_finish(skb);
+ return RX_HANDLER_PASS;
case 0x01: /* IEEE MAC (Pause) */
goto drop;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 6852f3c7009c..43844144c9c4 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -464,8 +464,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
&ip6h->saddr)) {
kfree_skb(skb);
+ br->has_ipv6_addr = 0;
return NULL;
}
+
+ br->has_ipv6_addr = 1;
ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
hopopt = (u8 *)(ip6h + 1);
@@ -1745,6 +1748,7 @@ void br_multicast_init(struct net_bridge *br)
br->ip6_other_query.delay_time = 0;
br->ip6_querier.port = NULL;
#endif
+ br->has_ipv6_addr = 1;
spin_lock_init(&br->multicast_lock);
setup_timer(&br->multicast_router_timer,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a5343c7232bf..85e89f693589 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1273,7 +1273,7 @@ static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev,
struct bridge_vlan_xstats vxi;
struct br_vlan_stats stats;
- if (vl_idx++ < *prividx)
+ if (++vl_idx < *prividx)
continue;
memset(&vxi, 0, sizeof(vxi));
vxi.vid = v->vid;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index c7fb5d7a7218..52edecf3c294 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -314,6 +314,7 @@ struct net_bridge
u8 multicast_disabled:1;
u8 multicast_querier:1;
u8 multicast_query_use_ifaddr:1;
+ u8 has_ipv6_addr:1;
u32 hash_elasticity;
u32 hash_max;
@@ -588,10 +589,22 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
static inline bool
__br_multicast_querier_exists(struct net_bridge *br,
- struct bridge_mcast_other_query *querier)
+ struct bridge_mcast_other_query *querier,
+ const bool is_ipv6)
{
+ bool own_querier_enabled;
+
+ if (br->multicast_querier) {
+ if (is_ipv6 && !br->has_ipv6_addr)
+ own_querier_enabled = false;
+ else
+ own_querier_enabled = true;
+ } else {
+ own_querier_enabled = false;
+ }
+
return time_is_before_jiffies(querier->delay_time) &&
- (br->multicast_querier || timer_pending(&querier->timer));
+ (own_querier_enabled || timer_pending(&querier->timer));
}
static inline bool br_multicast_querier_exists(struct net_bridge *br,
@@ -599,10 +612,12 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
{
switch (eth->h_proto) {
case (htons(ETH_P_IP)):
- return __br_multicast_querier_exists(br, &br->ip4_other_query);
+ return __br_multicast_querier_exists(br,
+ &br->ip4_other_query, false);
#if IS_ENABLED(CONFIG_IPV6)
case (htons(ETH_P_IPV6)):
- return __br_multicast_querier_exists(br, &br->ip6_other_query);
+ return __br_multicast_querier_exists(br,
+ &br->ip6_other_query, true);
#endif
default:
return false;
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index dcc18c6f7cf9..55d2bfee16d7 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -651,7 +651,7 @@ EXPORT_SYMBOL(ceph_destroy_client);
/*
* true if we have the mon map (and have thus joined the cluster)
*/
-static int have_mon_and_osd_map(struct ceph_client *client)
+static bool have_mon_and_osd_map(struct ceph_client *client)
{
return client->monc.monmap && client->monc.monmap->epoch &&
client->osdc.osdmap && client->osdc.osdmap->epoch;
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 139a9cb19b0c..3773a4fa11e3 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -27,6 +27,22 @@ __CEPH_FORALL_OSD_OPS(GENERATE_CASE)
}
}
+const char *ceph_osd_watch_op_name(int o)
+{
+ switch (o) {
+ case CEPH_OSD_WATCH_OP_UNWATCH:
+ return "unwatch";
+ case CEPH_OSD_WATCH_OP_WATCH:
+ return "watch";
+ case CEPH_OSD_WATCH_OP_RECONNECT:
+ return "reconnect";
+ case CEPH_OSD_WATCH_OP_PING:
+ return "ping";
+ default:
+ return "???";
+ }
+}
+
const char *ceph_osd_state_name(int s)
{
switch (s) {
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index b902fbc7863e..e77b04ca7802 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -54,24 +54,25 @@ static int osdmap_show(struct seq_file *s, void *p)
{
int i;
struct ceph_client *client = s->private;
- struct ceph_osdmap *map = client->osdc.osdmap;
+ struct ceph_osd_client *osdc = &client->osdc;
+ struct ceph_osdmap *map = osdc->osdmap;
struct rb_node *n;
if (map == NULL)
return 0;
- seq_printf(s, "epoch %d\n", map->epoch);
- seq_printf(s, "flags%s%s\n",
- (map->flags & CEPH_OSDMAP_NEARFULL) ? " NEARFULL" : "",
- (map->flags & CEPH_OSDMAP_FULL) ? " FULL" : "");
+ down_read(&osdc->lock);
+ seq_printf(s, "epoch %d flags 0x%x\n", map->epoch, map->flags);
for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) {
- struct ceph_pg_pool_info *pool =
+ struct ceph_pg_pool_info *pi =
rb_entry(n, struct ceph_pg_pool_info, node);
- seq_printf(s, "pool %lld pg_num %u (%d) read_tier %lld write_tier %lld\n",
- pool->id, pool->pg_num, pool->pg_num_mask,
- pool->read_tier, pool->write_tier);
+ seq_printf(s, "pool %lld '%s' type %d size %d min_size %d pg_num %u pg_num_mask %d flags 0x%llx lfor %u read_tier %lld write_tier %lld\n",
+ pi->id, pi->name, pi->type, pi->size, pi->min_size,
+ pi->pg_num, pi->pg_num_mask, pi->flags,
+ pi->last_force_request_resend, pi->read_tier,
+ pi->write_tier);
}
for (i = 0; i < map->max_osd; i++) {
struct ceph_entity_addr *addr = &map->osd_addr[i];
@@ -103,6 +104,7 @@ static int osdmap_show(struct seq_file *s, void *p)
pg->pgid.seed, pg->primary_temp.osd);
}
+ up_read(&osdc->lock);
return 0;
}
@@ -126,6 +128,7 @@ static int monc_show(struct seq_file *s, void *p)
CEPH_SUBSCRIBE_ONETIME ? "" : "+"));
seq_putc(s, '\n');
}
+ seq_printf(s, "fs_cluster_id %d\n", monc->fs_cluster_id);
for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
__u16 op;
@@ -143,43 +146,113 @@ static int monc_show(struct seq_file *s, void *p)
return 0;
}
-static int osdc_show(struct seq_file *s, void *pp)
+static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t)
{
- struct ceph_client *client = s->private;
- struct ceph_osd_client *osdc = &client->osdc;
- struct rb_node *p;
+ int i;
- mutex_lock(&osdc->request_mutex);
- for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
- struct ceph_osd_request *req;
- unsigned int i;
- int opcode;
+ seq_printf(s, "osd%d\t%llu.%x\t[", t->osd, t->pgid.pool, t->pgid.seed);
+ for (i = 0; i < t->up.size; i++)
+ seq_printf(s, "%s%d", (!i ? "" : ","), t->up.osds[i]);
+ seq_printf(s, "]/%d\t[", t->up.primary);
+ for (i = 0; i < t->acting.size; i++)
+ seq_printf(s, "%s%d", (!i ? "" : ","), t->acting.osds[i]);
+ seq_printf(s, "]/%d\t%*pE\t0x%x", t->acting.primary,
+ t->target_oid.name_len, t->target_oid.name, t->flags);
+ if (t->paused)
+ seq_puts(s, "\tP");
+}
- req = rb_entry(p, struct ceph_osd_request, r_node);
+static void dump_request(struct seq_file *s, struct ceph_osd_request *req)
+{
+ int i;
- seq_printf(s, "%lld\tosd%d\t%lld.%x\t", req->r_tid,
- req->r_osd ? req->r_osd->o_osd : -1,
- req->r_pgid.pool, req->r_pgid.seed);
+ seq_printf(s, "%llu\t", req->r_tid);
+ dump_target(s, &req->r_t);
- seq_printf(s, "%.*s", req->r_base_oid.name_len,
- req->r_base_oid.name);
+ seq_printf(s, "\t%d\t%u'%llu", req->r_attempts,
+ le32_to_cpu(req->r_replay_version.epoch),
+ le64_to_cpu(req->r_replay_version.version));
- if (req->r_reassert_version.epoch)
- seq_printf(s, "\t%u'%llu",
- (unsigned int)le32_to_cpu(req->r_reassert_version.epoch),
- le64_to_cpu(req->r_reassert_version.version));
- else
- seq_printf(s, "\t");
+ for (i = 0; i < req->r_num_ops; i++) {
+ struct ceph_osd_req_op *op = &req->r_ops[i];
+
+ seq_printf(s, "%s%s", (i == 0 ? "\t" : ","),
+ ceph_osd_op_name(op->op));
+ if (op->op == CEPH_OSD_OP_WATCH)
+ seq_printf(s, "-%s",
+ ceph_osd_watch_op_name(op->watch.op));
+ }
+
+ seq_putc(s, '\n');
+}
+
+static void dump_requests(struct seq_file *s, struct ceph_osd *osd)
+{
+ struct rb_node *n;
+
+ mutex_lock(&osd->lock);
+ for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) {
+ struct ceph_osd_request *req =
+ rb_entry(n, struct ceph_osd_request, r_node);
+
+ dump_request(s, req);
+ }
+
+ mutex_unlock(&osd->lock);
+}
- for (i = 0; i < req->r_num_ops; i++) {
- opcode = req->r_ops[i].op;
- seq_printf(s, "%s%s", (i == 0 ? "\t" : ","),
- ceph_osd_op_name(opcode));
- }
+static void dump_linger_request(struct seq_file *s,
+ struct ceph_osd_linger_request *lreq)
+{
+ seq_printf(s, "%llu\t", lreq->linger_id);
+ dump_target(s, &lreq->t);
+
+ seq_printf(s, "\t%u\t%s%s/%d\n", lreq->register_gen,
+ lreq->is_watch ? "W" : "N", lreq->committed ? "C" : "",
+ lreq->last_error);
+}
+
+static void dump_linger_requests(struct seq_file *s, struct ceph_osd *osd)
+{
+ struct rb_node *n;
+
+ mutex_lock(&osd->lock);
+ for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) {
+ struct ceph_osd_linger_request *lreq =
+ rb_entry(n, struct ceph_osd_linger_request, node);
+
+ dump_linger_request(s, lreq);
+ }
+
+ mutex_unlock(&osd->lock);
+}
- seq_printf(s, "\n");
+static int osdc_show(struct seq_file *s, void *pp)
+{
+ struct ceph_client *client = s->private;
+ struct ceph_osd_client *osdc = &client->osdc;
+ struct rb_node *n;
+
+ down_read(&osdc->lock);
+ seq_printf(s, "REQUESTS %d homeless %d\n",
+ atomic_read(&osdc->num_requests),
+ atomic_read(&osdc->num_homeless));
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+
+ dump_requests(s, osd);
}
- mutex_unlock(&osdc->request_mutex);
+ dump_requests(s, &osdc->homeless_osd);
+
+ seq_puts(s, "LINGER REQUESTS\n");
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+
+ dump_linger_requests(s, osd);
+ }
+ dump_linger_requests(s, &osdc->homeless_osd);
+
+ up_read(&osdc->lock);
return 0;
}
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index cf638c009cfa..37c38a7fb5c5 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -260,20 +260,26 @@ static void __send_subscribe(struct ceph_mon_client *monc)
BUG_ON(num < 1); /* monmap sub is always there */
ceph_encode_32(&p, num);
for (i = 0; i < ARRAY_SIZE(monc->subs); i++) {
- const char *s = ceph_sub_str[i];
+ char buf[32];
+ int len;
if (!monc->subs[i].want)
continue;
- dout("%s %s start %llu flags 0x%x\n", __func__, s,
+ len = sprintf(buf, "%s", ceph_sub_str[i]);
+ if (i == CEPH_SUB_MDSMAP &&
+ monc->fs_cluster_id != CEPH_FS_CLUSTER_ID_NONE)
+ len += sprintf(buf + len, ".%d", monc->fs_cluster_id);
+
+ dout("%s %s start %llu flags 0x%x\n", __func__, buf,
le64_to_cpu(monc->subs[i].item.start),
monc->subs[i].item.flags);
- ceph_encode_string(&p, end, s, strlen(s));
+ ceph_encode_string(&p, end, buf, len);
memcpy(p, &monc->subs[i].item, sizeof(monc->subs[i].item));
p += sizeof(monc->subs[i].item);
}
- BUG_ON(p != (end - 35 - (ARRAY_SIZE(monc->subs) - num) * 19));
+ BUG_ON(p > end);
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
ceph_msg_revoke(msg);
@@ -376,19 +382,13 @@ void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch)
}
EXPORT_SYMBOL(ceph_monc_got_map);
-/*
- * Register interest in the next osdmap
- */
-void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
+void ceph_monc_renew_subs(struct ceph_mon_client *monc)
{
- dout("%s have %u\n", __func__, monc->subs[CEPH_SUB_OSDMAP].have);
mutex_lock(&monc->mutex);
- if (__ceph_monc_want_map(monc, CEPH_SUB_OSDMAP,
- monc->subs[CEPH_SUB_OSDMAP].have + 1, false))
- __send_subscribe(monc);
+ __send_subscribe(monc);
mutex_unlock(&monc->mutex);
}
-EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
+EXPORT_SYMBOL(ceph_monc_renew_subs);
/*
* Wait for an osdmap with a given epoch.
@@ -478,51 +478,17 @@ out:
/*
* generic requests (currently statfs, mon_get_version)
*/
-static struct ceph_mon_generic_request *__lookup_generic_req(
- struct ceph_mon_client *monc, u64 tid)
-{
- struct ceph_mon_generic_request *req;
- struct rb_node *n = monc->generic_request_tree.rb_node;
-
- while (n) {
- req = rb_entry(n, struct ceph_mon_generic_request, node);
- if (tid < req->tid)
- n = n->rb_left;
- else if (tid > req->tid)
- n = n->rb_right;
- else
- return req;
- }
- return NULL;
-}
-
-static void __insert_generic_request(struct ceph_mon_client *monc,
- struct ceph_mon_generic_request *new)
-{
- struct rb_node **p = &monc->generic_request_tree.rb_node;
- struct rb_node *parent = NULL;
- struct ceph_mon_generic_request *req = NULL;
-
- while (*p) {
- parent = *p;
- req = rb_entry(parent, struct ceph_mon_generic_request, node);
- if (new->tid < req->tid)
- p = &(*p)->rb_left;
- else if (new->tid > req->tid)
- p = &(*p)->rb_right;
- else
- BUG();
- }
-
- rb_link_node(&new->node, parent, p);
- rb_insert_color(&new->node, &monc->generic_request_tree);
-}
+DEFINE_RB_FUNCS(generic_request, struct ceph_mon_generic_request, tid, node)
static void release_generic_request(struct kref *kref)
{
struct ceph_mon_generic_request *req =
container_of(kref, struct ceph_mon_generic_request, kref);
+ dout("%s greq %p request %p reply %p\n", __func__, req, req->request,
+ req->reply);
+ WARN_ON(!RB_EMPTY_NODE(&req->node));
+
if (req->reply)
ceph_msg_put(req->reply);
if (req->request)
@@ -533,7 +499,8 @@ static void release_generic_request(struct kref *kref)
static void put_generic_request(struct ceph_mon_generic_request *req)
{
- kref_put(&req->kref, release_generic_request);
+ if (req)
+ kref_put(&req->kref, release_generic_request);
}
static void get_generic_request(struct ceph_mon_generic_request *req)
@@ -541,6 +508,103 @@ static void get_generic_request(struct ceph_mon_generic_request *req)
kref_get(&req->kref);
}
+static struct ceph_mon_generic_request *
+alloc_generic_request(struct ceph_mon_client *monc, gfp_t gfp)
+{
+ struct ceph_mon_generic_request *req;
+
+ req = kzalloc(sizeof(*req), gfp);
+ if (!req)
+ return NULL;
+
+ req->monc = monc;
+ kref_init(&req->kref);
+ RB_CLEAR_NODE(&req->node);
+ init_completion(&req->completion);
+
+ dout("%s greq %p\n", __func__, req);
+ return req;
+}
+
+static void register_generic_request(struct ceph_mon_generic_request *req)
+{
+ struct ceph_mon_client *monc = req->monc;
+
+ WARN_ON(req->tid);
+
+ get_generic_request(req);
+ req->tid = ++monc->last_tid;
+ insert_generic_request(&monc->generic_request_tree, req);
+}
+
+static void send_generic_request(struct ceph_mon_client *monc,
+ struct ceph_mon_generic_request *req)
+{
+ WARN_ON(!req->tid);
+
+ dout("%s greq %p tid %llu\n", __func__, req, req->tid);
+ req->request->hdr.tid = cpu_to_le64(req->tid);
+ ceph_con_send(&monc->con, ceph_msg_get(req->request));
+}
+
+static void __finish_generic_request(struct ceph_mon_generic_request *req)
+{
+ struct ceph_mon_client *monc = req->monc;
+
+ dout("%s greq %p tid %llu\n", __func__, req, req->tid);
+ erase_generic_request(&monc->generic_request_tree, req);
+
+ ceph_msg_revoke(req->request);
+ ceph_msg_revoke_incoming(req->reply);
+}
+
+static void finish_generic_request(struct ceph_mon_generic_request *req)
+{
+ __finish_generic_request(req);
+ put_generic_request(req);
+}
+
+static void complete_generic_request(struct ceph_mon_generic_request *req)
+{
+ if (req->complete_cb)
+ req->complete_cb(req);
+ else
+ complete_all(&req->completion);
+ put_generic_request(req);
+}
+
+void cancel_generic_request(struct ceph_mon_generic_request *req)
+{
+ struct ceph_mon_client *monc = req->monc;
+ struct ceph_mon_generic_request *lookup_req;
+
+ dout("%s greq %p tid %llu\n", __func__, req, req->tid);
+
+ mutex_lock(&monc->mutex);
+ lookup_req = lookup_generic_request(&monc->generic_request_tree,
+ req->tid);
+ if (lookup_req) {
+ WARN_ON(lookup_req != req);
+ finish_generic_request(req);
+ }
+
+ mutex_unlock(&monc->mutex);
+}
+
+static int wait_generic_request(struct ceph_mon_generic_request *req)
+{
+ int ret;
+
+ dout("%s greq %p tid %llu\n", __func__, req, req->tid);
+ ret = wait_for_completion_interruptible(&req->completion);
+ if (ret)
+ cancel_generic_request(req);
+ else
+ ret = req->result; /* completed */
+
+ return ret;
+}
+
static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
struct ceph_msg_header *hdr,
int *skip)
@@ -551,7 +615,7 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
struct ceph_msg *m;
mutex_lock(&monc->mutex);
- req = __lookup_generic_req(monc, tid);
+ req = lookup_generic_request(&monc->generic_request_tree, tid);
if (!req) {
dout("get_generic_reply %lld dne\n", tid);
*skip = 1;
@@ -570,42 +634,6 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
return m;
}
-static int __do_generic_request(struct ceph_mon_client *monc, u64 tid,
- struct ceph_mon_generic_request *req)
-{
- int err;
-
- /* register request */
- req->tid = tid != 0 ? tid : ++monc->last_tid;
- req->request->hdr.tid = cpu_to_le64(req->tid);
- __insert_generic_request(monc, req);
- monc->num_generic_requests++;
- ceph_con_send(&monc->con, ceph_msg_get(req->request));
- mutex_unlock(&monc->mutex);
-
- err = wait_for_completion_interruptible(&req->completion);
-
- mutex_lock(&monc->mutex);
- rb_erase(&req->node, &monc->generic_request_tree);
- monc->num_generic_requests--;
-
- if (!err)
- err = req->result;
- return err;
-}
-
-static int do_generic_request(struct ceph_mon_client *monc,
- struct ceph_mon_generic_request *req)
-{
- int err;
-
- mutex_lock(&monc->mutex);
- err = __do_generic_request(monc, 0, req);
- mutex_unlock(&monc->mutex);
-
- return err;
-}
-
/*
* statfs
*/
@@ -616,22 +644,24 @@ static void handle_statfs_reply(struct ceph_mon_client *monc,
struct ceph_mon_statfs_reply *reply = msg->front.iov_base;
u64 tid = le64_to_cpu(msg->hdr.tid);
+ dout("%s msg %p tid %llu\n", __func__, msg, tid);
+
if (msg->front.iov_len != sizeof(*reply))
goto bad;
- dout("handle_statfs_reply %p tid %llu\n", msg, tid);
mutex_lock(&monc->mutex);
- req = __lookup_generic_req(monc, tid);
- if (req) {
- *(struct ceph_statfs *)req->buf = reply->st;
- req->result = 0;
- get_generic_request(req);
+ req = lookup_generic_request(&monc->generic_request_tree, tid);
+ if (!req) {
+ mutex_unlock(&monc->mutex);
+ return;
}
+
+ req->result = 0;
+ *req->u.st = reply->st; /* struct */
+ __finish_generic_request(req);
mutex_unlock(&monc->mutex);
- if (req) {
- complete_all(&req->completion);
- put_generic_request(req);
- }
+
+ complete_generic_request(req);
return;
bad:
@@ -646,38 +676,38 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
{
struct ceph_mon_generic_request *req;
struct ceph_mon_statfs *h;
- int err;
+ int ret = -ENOMEM;
- req = kzalloc(sizeof(*req), GFP_NOFS);
+ req = alloc_generic_request(monc, GFP_NOFS);
if (!req)
- return -ENOMEM;
-
- kref_init(&req->kref);
- req->buf = buf;
- init_completion(&req->completion);
+ goto out;
- err = -ENOMEM;
req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS,
true);
if (!req->request)
goto out;
- req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 1024, GFP_NOFS,
- true);
+
+ req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 64, GFP_NOFS, true);
if (!req->reply)
goto out;
+ req->u.st = buf;
+
+ mutex_lock(&monc->mutex);
+ register_generic_request(req);
/* fill out request */
h = req->request->front.iov_base;
h->monhdr.have_version = 0;
h->monhdr.session_mon = cpu_to_le16(-1);
h->monhdr.session_mon_tid = 0;
h->fsid = monc->monmap->fsid;
+ send_generic_request(monc, req);
+ mutex_unlock(&monc->mutex);
- err = do_generic_request(monc, req);
-
+ ret = wait_generic_request(req);
out:
put_generic_request(req);
- return err;
+ return ret;
}
EXPORT_SYMBOL(ceph_monc_do_statfs);
@@ -690,7 +720,7 @@ static void handle_get_version_reply(struct ceph_mon_client *monc,
void *end = p + msg->front_alloc_len;
u64 handle;
- dout("%s %p tid %llu\n", __func__, msg, tid);
+ dout("%s msg %p tid %llu\n", __func__, msg, tid);
ceph_decode_need(&p, end, 2*sizeof(u64), bad);
handle = ceph_decode_64(&p);
@@ -698,77 +728,111 @@ static void handle_get_version_reply(struct ceph_mon_client *monc,
goto bad;
mutex_lock(&monc->mutex);
- req = __lookup_generic_req(monc, handle);
- if (req) {
- *(u64 *)req->buf = ceph_decode_64(&p);
- req->result = 0;
- get_generic_request(req);
+ req = lookup_generic_request(&monc->generic_request_tree, handle);
+ if (!req) {
+ mutex_unlock(&monc->mutex);
+ return;
}
+
+ req->result = 0;
+ req->u.newest = ceph_decode_64(&p);
+ __finish_generic_request(req);
mutex_unlock(&monc->mutex);
- if (req) {
- complete_all(&req->completion);
- put_generic_request(req);
- }
+ complete_generic_request(req);
return;
+
bad:
pr_err("corrupt mon_get_version reply, tid %llu\n", tid);
ceph_msg_dump(msg);
}
-/*
- * Send MMonGetVersion and wait for the reply.
- *
- * @what: one of "mdsmap", "osdmap" or "monmap"
- */
-int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
- u64 *newest)
+static struct ceph_mon_generic_request *
+__ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
+ ceph_monc_callback_t cb, u64 private_data)
{
struct ceph_mon_generic_request *req;
- void *p, *end;
- u64 tid;
- int err;
- req = kzalloc(sizeof(*req), GFP_NOFS);
+ req = alloc_generic_request(monc, GFP_NOIO);
if (!req)
- return -ENOMEM;
-
- kref_init(&req->kref);
- req->buf = newest;
- init_completion(&req->completion);
+ goto err_put_req;
req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
sizeof(u64) + sizeof(u32) + strlen(what),
- GFP_NOFS, true);
- if (!req->request) {
- err = -ENOMEM;
- goto out;
- }
+ GFP_NOIO, true);
+ if (!req->request)
+ goto err_put_req;
- req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 1024,
- GFP_NOFS, true);
- if (!req->reply) {
- err = -ENOMEM;
- goto out;
- }
+ req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 32, GFP_NOIO,
+ true);
+ if (!req->reply)
+ goto err_put_req;
- p = req->request->front.iov_base;
- end = p + req->request->front_alloc_len;
+ req->complete_cb = cb;
+ req->private_data = private_data;
- /* fill out request */
mutex_lock(&monc->mutex);
- tid = ++monc->last_tid;
- ceph_encode_64(&p, tid); /* handle */
- ceph_encode_string(&p, end, what, strlen(what));
+ register_generic_request(req);
+ {
+ void *p = req->request->front.iov_base;
+ void *const end = p + req->request->front_alloc_len;
+
+ ceph_encode_64(&p, req->tid); /* handle */
+ ceph_encode_string(&p, end, what, strlen(what));
+ WARN_ON(p != end);
+ }
+ send_generic_request(monc, req);
+ mutex_unlock(&monc->mutex);
- err = __do_generic_request(monc, tid, req);
+ return req;
- mutex_unlock(&monc->mutex);
-out:
+err_put_req:
put_generic_request(req);
- return err;
+ return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * Send MMonGetVersion and wait for the reply.
+ *
+ * @what: one of "mdsmap", "osdmap" or "monmap"
+ */
+int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
+ u64 *newest)
+{
+ struct ceph_mon_generic_request *req;
+ int ret;
+
+ req = __ceph_monc_get_version(monc, what, NULL, 0);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ ret = wait_generic_request(req);
+ if (!ret)
+ *newest = req->u.newest;
+
+ put_generic_request(req);
+ return ret;
}
-EXPORT_SYMBOL(ceph_monc_do_get_version);
+EXPORT_SYMBOL(ceph_monc_get_version);
+
+/*
+ * Send MMonGetVersion,
+ *
+ * @what: one of "mdsmap", "osdmap" or "monmap"
+ */
+int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what,
+ ceph_monc_callback_t cb, u64 private_data)
+{
+ struct ceph_mon_generic_request *req;
+
+ req = __ceph_monc_get_version(monc, what, cb, private_data);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ put_generic_request(req);
+ return 0;
+}
+EXPORT_SYMBOL(ceph_monc_get_version_async);
/*
* Resend pending generic requests.
@@ -890,7 +954,7 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
if (!monc->m_subscribe_ack)
goto out_auth;
- monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, GFP_NOFS,
+ monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 128, GFP_NOFS,
true);
if (!monc->m_subscribe)
goto out_subscribe_ack;
@@ -914,9 +978,10 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
INIT_DELAYED_WORK(&monc->delayed_work, delayed_work);
monc->generic_request_tree = RB_ROOT;
- monc->num_generic_requests = 0;
monc->last_tid = 0;
+ monc->fs_cluster_id = CEPH_FS_CLUSTER_ID_NONE;
+
return 0;
out_auth_reply:
@@ -954,6 +1019,8 @@ void ceph_monc_stop(struct ceph_mon_client *monc)
ceph_auth_destroy(monc->auth);
+ WARN_ON(!RB_EMPTY_ROOT(&monc->generic_request_tree));
+
ceph_msg_put(monc->m_auth);
ceph_msg_put(monc->m_auth_reply);
ceph_msg_put(monc->m_subscribe);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 40a53a70efdf..89469592076c 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -19,25 +19,12 @@
#include <linux/ceph/auth.h>
#include <linux/ceph/pagelist.h>
-#define OSD_OP_FRONT_LEN 4096
#define OSD_OPREPLY_FRONT_LEN 512
static struct kmem_cache *ceph_osd_request_cache;
static const struct ceph_connection_operations osd_con_ops;
-static void __send_queued(struct ceph_osd_client *osdc);
-static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd);
-static void __register_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req);
-static void __unregister_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req);
-static void __unregister_linger_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req);
-static void __enqueue_request(struct ceph_osd_request *req);
-static void __send_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req);
-
/*
* Implement client access to distributed object storage cluster.
*
@@ -56,6 +43,52 @@ static void __send_request(struct ceph_osd_client *osdc,
* channel with an OSD is reset.
*/
+static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req);
+static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req);
+static void link_linger(struct ceph_osd *osd,
+ struct ceph_osd_linger_request *lreq);
+static void unlink_linger(struct ceph_osd *osd,
+ struct ceph_osd_linger_request *lreq);
+
+#if 1
+static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem)
+{
+ bool wrlocked = true;
+
+ if (unlikely(down_read_trylock(sem))) {
+ wrlocked = false;
+ up_read(sem);
+ }
+
+ return wrlocked;
+}
+static inline void verify_osdc_locked(struct ceph_osd_client *osdc)
+{
+ WARN_ON(!rwsem_is_locked(&osdc->lock));
+}
+static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc)
+{
+ WARN_ON(!rwsem_is_wrlocked(&osdc->lock));
+}
+static inline void verify_osd_locked(struct ceph_osd *osd)
+{
+ struct ceph_osd_client *osdc = osd->o_osdc;
+
+ WARN_ON(!(mutex_is_locked(&osd->lock) &&
+ rwsem_is_locked(&osdc->lock)) &&
+ !rwsem_is_wrlocked(&osdc->lock));
+}
+static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq)
+{
+ WARN_ON(!mutex_is_locked(&lreq->lock));
+}
+#else
+static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { }
+static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { }
+static inline void verify_osd_locked(struct ceph_osd *osd) { }
+static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { }
+#endif
+
/*
* calculate the mapping of a file extent onto an object, and fill out the
* request accordingly. shorten extent as necessary if it crosses an
@@ -144,14 +177,6 @@ osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req,
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data);
-struct ceph_osd_data *
-osd_req_op_cls_response_data(struct ceph_osd_request *osd_req,
- unsigned int which)
-{
- return osd_req_op_data(osd_req, which, cls, response_data);
-}
-EXPORT_SYMBOL(osd_req_op_cls_response_data); /* ??? */
-
void osd_req_op_raw_data_in_pages(struct ceph_osd_request *osd_req,
unsigned int which, struct page **pages,
u64 length, u32 alignment,
@@ -218,6 +243,8 @@ void osd_req_op_cls_request_data_pagelist(
osd_data = osd_req_op_data(osd_req, which, cls, request_data);
ceph_osd_data_pagelist_init(osd_data, pagelist);
+ osd_req->r_ops[which].cls.indata_len += pagelist->length;
+ osd_req->r_ops[which].indata_len += pagelist->length;
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);
@@ -230,6 +257,8 @@ void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
osd_data = osd_req_op_data(osd_req, which, cls, request_data);
ceph_osd_data_pages_init(osd_data, pages, length, alignment,
pages_from_pool, own_pages);
+ osd_req->r_ops[which].cls.indata_len += length;
+ osd_req->r_ops[which].indata_len += length;
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_pages);
@@ -302,14 +331,76 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_STAT:
ceph_osd_data_release(&op->raw_data_in);
break;
+ case CEPH_OSD_OP_NOTIFY_ACK:
+ ceph_osd_data_release(&op->notify_ack.request_data);
+ break;
+ case CEPH_OSD_OP_NOTIFY:
+ ceph_osd_data_release(&op->notify.request_data);
+ ceph_osd_data_release(&op->notify.response_data);
+ break;
default:
break;
}
}
/*
+ * Assumes @t is zero-initialized.
+ */
+static void target_init(struct ceph_osd_request_target *t)
+{
+ ceph_oid_init(&t->base_oid);
+ ceph_oloc_init(&t->base_oloc);
+ ceph_oid_init(&t->target_oid);
+ ceph_oloc_init(&t->target_oloc);
+
+ ceph_osds_init(&t->acting);
+ ceph_osds_init(&t->up);
+ t->size = -1;
+ t->min_size = -1;
+
+ t->osd = CEPH_HOMELESS_OSD;
+}
+
+static void target_copy(struct ceph_osd_request_target *dest,
+ const struct ceph_osd_request_target *src)
+{
+ ceph_oid_copy(&dest->base_oid, &src->base_oid);
+ ceph_oloc_copy(&dest->base_oloc, &src->base_oloc);
+ ceph_oid_copy(&dest->target_oid, &src->target_oid);
+ ceph_oloc_copy(&dest->target_oloc, &src->target_oloc);
+
+ dest->pgid = src->pgid; /* struct */
+ dest->pg_num = src->pg_num;
+ dest->pg_num_mask = src->pg_num_mask;
+ ceph_osds_copy(&dest->acting, &src->acting);
+ ceph_osds_copy(&dest->up, &src->up);
+ dest->size = src->size;
+ dest->min_size = src->min_size;
+ dest->sort_bitwise = src->sort_bitwise;
+
+ dest->flags = src->flags;
+ dest->paused = src->paused;
+
+ dest->osd = src->osd;
+}
+
+static void target_destroy(struct ceph_osd_request_target *t)
+{
+ ceph_oid_destroy(&t->base_oid);
+ ceph_oid_destroy(&t->target_oid);
+}
+
+/*
* requests
*/
+static void request_release_checks(struct ceph_osd_request *req)
+{
+ WARN_ON(!RB_EMPTY_NODE(&req->r_node));
+ WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
+ WARN_ON(!list_empty(&req->r_unsafe_item));
+ WARN_ON(req->r_osd);
+}
+
static void ceph_osdc_release_request(struct kref *kref)
{
struct ceph_osd_request *req = container_of(kref,
@@ -318,24 +409,19 @@ static void ceph_osdc_release_request(struct kref *kref)
dout("%s %p (r_request %p r_reply %p)\n", __func__, req,
req->r_request, req->r_reply);
- WARN_ON(!RB_EMPTY_NODE(&req->r_node));
- WARN_ON(!list_empty(&req->r_req_lru_item));
- WARN_ON(!list_empty(&req->r_osd_item));
- WARN_ON(!list_empty(&req->r_linger_item));
- WARN_ON(!list_empty(&req->r_linger_osd_item));
- WARN_ON(req->r_osd);
+ request_release_checks(req);
if (req->r_request)
ceph_msg_put(req->r_request);
- if (req->r_reply) {
- ceph_msg_revoke_incoming(req->r_reply);
+ if (req->r_reply)
ceph_msg_put(req->r_reply);
- }
for (which = 0; which < req->r_num_ops; which++)
osd_req_op_data_release(req, which);
+ target_destroy(&req->r_t);
ceph_put_snap_context(req->r_snapc);
+
if (req->r_mempool)
mempool_free(req, req->r_osdc->req_mempool);
else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS)
@@ -354,12 +440,66 @@ EXPORT_SYMBOL(ceph_osdc_get_request);
void ceph_osdc_put_request(struct ceph_osd_request *req)
{
- dout("%s %p (was %d)\n", __func__, req,
- atomic_read(&req->r_kref.refcount));
- kref_put(&req->r_kref, ceph_osdc_release_request);
+ if (req) {
+ dout("%s %p (was %d)\n", __func__, req,
+ atomic_read(&req->r_kref.refcount));
+ kref_put(&req->r_kref, ceph_osdc_release_request);
+ }
}
EXPORT_SYMBOL(ceph_osdc_put_request);
+static void request_init(struct ceph_osd_request *req)
+{
+ /* req only, each op is zeroed in _osd_req_op_init() */
+ memset(req, 0, sizeof(*req));
+
+ kref_init(&req->r_kref);
+ init_completion(&req->r_completion);
+ init_completion(&req->r_safe_completion);
+ RB_CLEAR_NODE(&req->r_node);
+ RB_CLEAR_NODE(&req->r_mc_node);
+ INIT_LIST_HEAD(&req->r_unsafe_item);
+
+ target_init(&req->r_t);
+}
+
+/*
+ * This is ugly, but it allows us to reuse linger registration and ping
+ * requests, keeping the structure of the code around send_linger{_ping}()
+ * reasonable. Setting up a min_nr=2 mempool for each linger request
+ * and dealing with copying ops (this blasts req only, watch op remains
+ * intact) isn't any better.
+ */
+static void request_reinit(struct ceph_osd_request *req)
+{
+ struct ceph_osd_client *osdc = req->r_osdc;
+ bool mempool = req->r_mempool;
+ unsigned int num_ops = req->r_num_ops;
+ u64 snapid = req->r_snapid;
+ struct ceph_snap_context *snapc = req->r_snapc;
+ bool linger = req->r_linger;
+ struct ceph_msg *request_msg = req->r_request;
+ struct ceph_msg *reply_msg = req->r_reply;
+
+ dout("%s req %p\n", __func__, req);
+ WARN_ON(atomic_read(&req->r_kref.refcount) != 1);
+ request_release_checks(req);
+
+ WARN_ON(atomic_read(&request_msg->kref.refcount) != 1);
+ WARN_ON(atomic_read(&reply_msg->kref.refcount) != 1);
+ target_destroy(&req->r_t);
+
+ request_init(req);
+ req->r_osdc = osdc;
+ req->r_mempool = mempool;
+ req->r_num_ops = num_ops;
+ req->r_snapid = snapid;
+ req->r_snapc = snapc;
+ req->r_linger = linger;
+ req->r_request = request_msg;
+ req->r_reply = reply_msg;
+}
+
struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
struct ceph_snap_context *snapc,
unsigned int num_ops,
@@ -367,8 +507,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
gfp_t gfp_flags)
{
struct ceph_osd_request *req;
- struct ceph_msg *msg;
- size_t msg_size;
if (use_mempool) {
BUG_ON(num_ops > CEPH_OSD_SLAB_OPS);
@@ -383,73 +521,65 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
if (unlikely(!req))
return NULL;
- /* req only, each op is zeroed in _osd_req_op_init() */
- memset(req, 0, sizeof(*req));
-
+ request_init(req);
req->r_osdc = osdc;
req->r_mempool = use_mempool;
req->r_num_ops = num_ops;
+ req->r_snapid = CEPH_NOSNAP;
+ req->r_snapc = ceph_get_snap_context(snapc);
- kref_init(&req->r_kref);
- init_completion(&req->r_completion);
- init_completion(&req->r_safe_completion);
- RB_CLEAR_NODE(&req->r_node);
- INIT_LIST_HEAD(&req->r_unsafe_item);
- INIT_LIST_HEAD(&req->r_linger_item);
- INIT_LIST_HEAD(&req->r_linger_osd_item);
- INIT_LIST_HEAD(&req->r_req_lru_item);
- INIT_LIST_HEAD(&req->r_osd_item);
-
- req->r_base_oloc.pool = -1;
- req->r_target_oloc.pool = -1;
+ dout("%s req %p\n", __func__, req);
+ return req;
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_request);
- msg_size = OSD_OPREPLY_FRONT_LEN;
- if (num_ops > CEPH_OSD_SLAB_OPS) {
- /* ceph_osd_op and rval */
- msg_size += (num_ops - CEPH_OSD_SLAB_OPS) *
- (sizeof(struct ceph_osd_op) + 4);
- }
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+{
+ struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_msg *msg;
+ int msg_size;
- /* create reply message */
- if (use_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
- else
- msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size,
- gfp_flags, true);
- if (!msg) {
- ceph_osdc_put_request(req);
- return NULL;
- }
- req->r_reply = msg;
+ WARN_ON(ceph_oid_empty(&req->r_base_oid));
+ /* create request message */
msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */
msg_size += 1 + 8 + 4 + 4; /* pgid */
- msg_size += 4 + CEPH_MAX_OID_NAME_LEN; /* oid */
- msg_size += 2 + num_ops * sizeof(struct ceph_osd_op);
+ msg_size += 4 + req->r_base_oid.name_len; /* oid */
+ msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
msg_size += 8; /* snapid */
msg_size += 8; /* snap_seq */
- msg_size += 4 + 8 * (snapc ? snapc->num_snaps : 0); /* snaps */
+ msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0);
msg_size += 4; /* retry_attempt */
- /* create request message; allow space for oid */
- if (use_mempool)
+ if (req->r_mempool)
msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags, true);
- if (!msg) {
- ceph_osdc_put_request(req);
- return NULL;
- }
+ msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
+ if (!msg)
+ return -ENOMEM;
memset(msg->front.iov_base, 0, msg->front.iov_len);
-
req->r_request = msg;
- return req;
+ /* create reply message */
+ msg_size = OSD_OPREPLY_FRONT_LEN;
+ msg_size += req->r_base_oid.name_len;
+ msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
+
+ if (req->r_mempool)
+ msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+ else
+ msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true);
+ if (!msg)
+ return -ENOMEM;
+
+ req->r_reply = msg;
+
+ return 0;
}
-EXPORT_SYMBOL(ceph_osdc_alloc_request);
+EXPORT_SYMBOL(ceph_osdc_alloc_messages);
static bool osd_req_opcode_valid(u16 opcode)
{
@@ -587,8 +717,6 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist);
- op->cls.argc = 0; /* currently unused */
-
op->indata_len = payload_len;
}
EXPORT_SYMBOL(osd_req_op_cls_init);
@@ -627,21 +755,19 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
}
EXPORT_SYMBOL(osd_req_op_xattr_init);
-void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
- unsigned int which, u16 opcode,
- u64 cookie, u64 version, int flag)
+/*
+ * @watch_opcode: CEPH_OSD_WATCH_OP_*
+ */
+static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
+ u64 cookie, u8 watch_opcode)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- opcode, 0);
-
- BUG_ON(opcode != CEPH_OSD_OP_NOTIFY_ACK && opcode != CEPH_OSD_OP_WATCH);
+ struct ceph_osd_req_op *op;
+ op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
op->watch.cookie = cookie;
- op->watch.ver = version;
- if (opcode == CEPH_OSD_OP_WATCH && flag)
- op->watch.flag = (u8)1;
+ op->watch.op = watch_opcode;
+ op->watch.gen = 0;
}
-EXPORT_SYMBOL(osd_req_op_watch_init);
void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
unsigned int which,
@@ -686,16 +812,9 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
}
}
-static u64 osd_req_encode_op(struct ceph_osd_request *req,
- struct ceph_osd_op *dst, unsigned int which)
+static u32 osd_req_encode_op(struct ceph_osd_op *dst,
+ const struct ceph_osd_req_op *src)
{
- struct ceph_osd_req_op *src;
- struct ceph_osd_data *osd_data;
- u64 request_data_len = 0;
- u64 data_length;
-
- BUG_ON(which >= req->r_num_ops);
- src = &req->r_ops[which];
if (WARN_ON(!osd_req_opcode_valid(src->op))) {
pr_err("unrecognized osd opcode %d\n", src->op);
@@ -704,57 +823,36 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
switch (src->op) {
case CEPH_OSD_OP_STAT:
- osd_data = &src->raw_data_in;
- ceph_osdc_msg_data_add(req->r_reply, osd_data);
break;
case CEPH_OSD_OP_READ:
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_WRITEFULL:
case CEPH_OSD_OP_ZERO:
case CEPH_OSD_OP_TRUNCATE:
- if (src->op == CEPH_OSD_OP_WRITE ||
- src->op == CEPH_OSD_OP_WRITEFULL)
- request_data_len = src->extent.length;
dst->extent.offset = cpu_to_le64(src->extent.offset);
dst->extent.length = cpu_to_le64(src->extent.length);
dst->extent.truncate_size =
cpu_to_le64(src->extent.truncate_size);
dst->extent.truncate_seq =
cpu_to_le32(src->extent.truncate_seq);
- osd_data = &src->extent.osd_data;
- if (src->op == CEPH_OSD_OP_WRITE ||
- src->op == CEPH_OSD_OP_WRITEFULL)
- ceph_osdc_msg_data_add(req->r_request, osd_data);
- else
- ceph_osdc_msg_data_add(req->r_reply, osd_data);
break;
case CEPH_OSD_OP_CALL:
dst->cls.class_len = src->cls.class_len;
dst->cls.method_len = src->cls.method_len;
- osd_data = &src->cls.request_info;
- ceph_osdc_msg_data_add(req->r_request, osd_data);
- BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGELIST);
- request_data_len = osd_data->pagelist->length;
-
- osd_data = &src->cls.request_data;
- data_length = ceph_osd_data_length(osd_data);
- if (data_length) {
- BUG_ON(osd_data->type == CEPH_OSD_DATA_TYPE_NONE);
- dst->cls.indata_len = cpu_to_le32(data_length);
- ceph_osdc_msg_data_add(req->r_request, osd_data);
- src->indata_len += data_length;
- request_data_len += data_length;
- }
- osd_data = &src->cls.response_data;
- ceph_osdc_msg_data_add(req->r_reply, osd_data);
+ dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
break;
case CEPH_OSD_OP_STARTSYNC:
break;
- case CEPH_OSD_OP_NOTIFY_ACK:
case CEPH_OSD_OP_WATCH:
dst->watch.cookie = cpu_to_le64(src->watch.cookie);
- dst->watch.ver = cpu_to_le64(src->watch.ver);
- dst->watch.flag = src->watch.flag;
+ dst->watch.ver = cpu_to_le64(0);
+ dst->watch.op = src->watch.op;
+ dst->watch.gen = cpu_to_le32(src->watch.gen);
+ break;
+ case CEPH_OSD_OP_NOTIFY_ACK:
+ break;
+ case CEPH_OSD_OP_NOTIFY:
+ dst->notify.cookie = cpu_to_le64(src->notify.cookie);
break;
case CEPH_OSD_OP_SETALLOCHINT:
dst->alloc_hint.expected_object_size =
@@ -768,9 +866,6 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
dst->xattr.cmp_op = src->xattr.cmp_op;
dst->xattr.cmp_mode = src->xattr.cmp_mode;
- osd_data = &src->xattr.osd_data;
- ceph_osdc_msg_data_add(req->r_request, osd_data);
- request_data_len = osd_data->pagelist->length;
break;
case CEPH_OSD_OP_CREATE:
case CEPH_OSD_OP_DELETE:
@@ -787,7 +882,7 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
dst->flags = cpu_to_le32(src->flags);
dst->payload_len = cpu_to_le32(src->indata_len);
- return request_data_len;
+ return src->indata_len;
}
/*
@@ -824,17 +919,15 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
GFP_NOFS);
- if (!req)
- return ERR_PTR(-ENOMEM);
-
- req->r_flags = flags;
+ if (!req) {
+ r = -ENOMEM;
+ goto fail;
+ }
/* calculate max write size */
r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen);
- if (r < 0) {
- ceph_osdc_put_request(req);
- return ERR_PTR(r);
- }
+ if (r)
+ goto fail;
if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
osd_req_op_init(req, which, opcode, 0);
@@ -854,194 +947,71 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
truncate_size, truncate_seq);
}
+ req->r_flags = flags;
req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
+ ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
+
+ req->r_snapid = vino.snap;
+ if (flags & CEPH_OSD_FLAG_WRITE)
+ req->r_data_offset = off;
- snprintf(req->r_base_oid.name, sizeof(req->r_base_oid.name),
- "%llx.%08llx", vino.ino, objnum);
- req->r_base_oid.name_len = strlen(req->r_base_oid.name);
+ r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+ if (r)
+ goto fail;
return req;
+
+fail:
+ ceph_osdc_put_request(req);
+ return ERR_PTR(r);
}
EXPORT_SYMBOL(ceph_osdc_new_request);
/*
* We keep osd requests in an rbtree, sorted by ->r_tid.
*/
-static void __insert_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *new)
-{
- struct rb_node **p = &osdc->requests.rb_node;
- struct rb_node *parent = NULL;
- struct ceph_osd_request *req = NULL;
-
- while (*p) {
- parent = *p;
- req = rb_entry(parent, struct ceph_osd_request, r_node);
- if (new->r_tid < req->r_tid)
- p = &(*p)->rb_left;
- else if (new->r_tid > req->r_tid)
- p = &(*p)->rb_right;
- else
- BUG();
- }
-
- rb_link_node(&new->r_node, parent, p);
- rb_insert_color(&new->r_node, &osdc->requests);
-}
+DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node)
+DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node)
-static struct ceph_osd_request *__lookup_request(struct ceph_osd_client *osdc,
- u64 tid)
+static bool osd_homeless(struct ceph_osd *osd)
{
- struct ceph_osd_request *req;
- struct rb_node *n = osdc->requests.rb_node;
-
- while (n) {
- req = rb_entry(n, struct ceph_osd_request, r_node);
- if (tid < req->r_tid)
- n = n->rb_left;
- else if (tid > req->r_tid)
- n = n->rb_right;
- else
- return req;
- }
- return NULL;
+ return osd->o_osd == CEPH_HOMELESS_OSD;
}
-static struct ceph_osd_request *
-__lookup_request_ge(struct ceph_osd_client *osdc,
- u64 tid)
+static bool osd_registered(struct ceph_osd *osd)
{
- struct ceph_osd_request *req;
- struct rb_node *n = osdc->requests.rb_node;
-
- while (n) {
- req = rb_entry(n, struct ceph_osd_request, r_node);
- if (tid < req->r_tid) {
- if (!n->rb_left)
- return req;
- n = n->rb_left;
- } else if (tid > req->r_tid) {
- n = n->rb_right;
- } else {
- return req;
- }
- }
- return NULL;
-}
-
-static void __kick_linger_request(struct ceph_osd_request *req)
-{
- struct ceph_osd_client *osdc = req->r_osdc;
- struct ceph_osd *osd = req->r_osd;
+ verify_osdc_locked(osd->o_osdc);
- /*
- * Linger requests need to be resent with a new tid to avoid
- * the dup op detection logic on the OSDs. Achieve this with
- * a re-register dance instead of open-coding.
- */
- ceph_osdc_get_request(req);
- if (!list_empty(&req->r_linger_item))
- __unregister_linger_request(osdc, req);
- else
- __unregister_request(osdc, req);
- __register_request(osdc, req);
- ceph_osdc_put_request(req);
-
- /*
- * Unless request has been registered as both normal and
- * lingering, __unregister{,_linger}_request clears r_osd.
- * However, here we need to preserve r_osd to make sure we
- * requeue on the same OSD.
- */
- WARN_ON(req->r_osd || !osd);
- req->r_osd = osd;
-
- dout("%s requeueing %p tid %llu\n", __func__, req, req->r_tid);
- __enqueue_request(req);
+ return !RB_EMPTY_NODE(&osd->o_node);
}
/*
- * Resubmit requests pending on the given osd.
+ * Assumes @osd is zero-initialized.
*/
-static void __kick_osd_requests(struct ceph_osd_client *osdc,
- struct ceph_osd *osd)
+static void osd_init(struct ceph_osd *osd)
{
- struct ceph_osd_request *req, *nreq;
- LIST_HEAD(resend);
- LIST_HEAD(resend_linger);
- int err;
-
- dout("%s osd%d\n", __func__, osd->o_osd);
- err = __reset_osd(osdc, osd);
- if (err)
- return;
-
- /*
- * Build up a list of requests to resend by traversing the
- * osd's list of requests. Requests for a given object are
- * sent in tid order, and that is also the order they're
- * kept on this list. Therefore all requests that are in
- * flight will be found first, followed by all requests that
- * have not yet been sent. And to resend requests while
- * preserving this order we will want to put any sent
- * requests back on the front of the osd client's unsent
- * list.
- *
- * So we build a separate ordered list of already-sent
- * requests for the affected osd and splice it onto the
- * front of the osd client's unsent list. Once we've seen a
- * request that has not yet been sent we're done. Those
- * requests are already sitting right where they belong.
- */
- list_for_each_entry(req, &osd->o_requests, r_osd_item) {
- if (!req->r_sent)
- break;
-
- if (!req->r_linger) {
- dout("%s requeueing %p tid %llu\n", __func__, req,
- req->r_tid);
- list_move_tail(&req->r_req_lru_item, &resend);
- req->r_flags |= CEPH_OSD_FLAG_RETRY;
- } else {
- list_move_tail(&req->r_req_lru_item, &resend_linger);
- }
- }
- list_splice(&resend, &osdc->req_unsent);
-
- /*
- * Both registered and not yet registered linger requests are
- * enqueued with a new tid on the same OSD. We add/move them
- * to req_unsent/o_requests at the end to keep things in tid
- * order.
- */
- list_for_each_entry_safe(req, nreq, &osd->o_linger_requests,
- r_linger_osd_item) {
- WARN_ON(!list_empty(&req->r_req_lru_item));
- __kick_linger_request(req);
- }
-
- list_for_each_entry_safe(req, nreq, &resend_linger, r_req_lru_item)
- __kick_linger_request(req);
+ atomic_set(&osd->o_ref, 1);
+ RB_CLEAR_NODE(&osd->o_node);
+ osd->o_requests = RB_ROOT;
+ osd->o_linger_requests = RB_ROOT;
+ INIT_LIST_HEAD(&osd->o_osd_lru);
+ INIT_LIST_HEAD(&osd->o_keepalive_item);
+ osd->o_incarnation = 1;
+ mutex_init(&osd->lock);
}
-/*
- * If the osd connection drops, we need to resubmit all requests.
- */
-static void osd_reset(struct ceph_connection *con)
+static void osd_cleanup(struct ceph_osd *osd)
{
- struct ceph_osd *osd = con->private;
- struct ceph_osd_client *osdc;
-
- if (!osd)
- return;
- dout("osd_reset osd%d\n", osd->o_osd);
- osdc = osd->o_osdc;
- down_read(&osdc->map_sem);
- mutex_lock(&osdc->request_mutex);
- __kick_osd_requests(osdc, osd);
- __send_queued(osdc);
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
+ WARN_ON(!RB_EMPTY_NODE(&osd->o_node));
+ WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
+ WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
+ WARN_ON(!list_empty(&osd->o_osd_lru));
+ WARN_ON(!list_empty(&osd->o_keepalive_item));
+
+ if (osd->o_auth.authorizer) {
+ WARN_ON(osd_homeless(osd));
+ ceph_auth_destroy_authorizer(osd->o_auth.authorizer);
+ }
}
/*
@@ -1051,22 +1021,15 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
{
struct ceph_osd *osd;
- osd = kzalloc(sizeof(*osd), GFP_NOFS);
- if (!osd)
- return NULL;
+ WARN_ON(onum == CEPH_HOMELESS_OSD);
- atomic_set(&osd->o_ref, 1);
+ osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL);
+ osd_init(osd);
osd->o_osdc = osdc;
osd->o_osd = onum;
- RB_CLEAR_NODE(&osd->o_node);
- INIT_LIST_HEAD(&osd->o_requests);
- INIT_LIST_HEAD(&osd->o_linger_requests);
- INIT_LIST_HEAD(&osd->o_osd_lru);
- osd->o_incarnation = 1;
ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
- INIT_LIST_HEAD(&osd->o_keepalive_item);
return osd;
}
@@ -1087,114 +1050,115 @@ static void put_osd(struct ceph_osd *osd)
dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
atomic_read(&osd->o_ref) - 1);
if (atomic_dec_and_test(&osd->o_ref)) {
- if (osd->o_auth.authorizer)
- ceph_auth_destroy_authorizer(osd->o_auth.authorizer);
+ osd_cleanup(osd);
kfree(osd);
}
}
-/*
- * remove an osd from our map
- */
-static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
-{
- dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
- WARN_ON(!list_empty(&osd->o_requests));
- WARN_ON(!list_empty(&osd->o_linger_requests));
-
- list_del_init(&osd->o_osd_lru);
- rb_erase(&osd->o_node, &osdc->osds);
- RB_CLEAR_NODE(&osd->o_node);
-}
-
-static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
-{
- dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
-
- if (!RB_EMPTY_NODE(&osd->o_node)) {
- ceph_con_close(&osd->o_con);
- __remove_osd(osdc, osd);
- put_osd(osd);
- }
-}
+DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node)
-static void remove_all_osds(struct ceph_osd_client *osdc)
+static void __move_osd_to_lru(struct ceph_osd *osd)
{
- dout("%s %p\n", __func__, osdc);
- mutex_lock(&osdc->request_mutex);
- while (!RB_EMPTY_ROOT(&osdc->osds)) {
- struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
- struct ceph_osd, o_node);
- remove_osd(osdc, osd);
- }
- mutex_unlock(&osdc->request_mutex);
-}
+ struct ceph_osd_client *osdc = osd->o_osdc;
-static void __move_osd_to_lru(struct ceph_osd_client *osdc,
- struct ceph_osd *osd)
-{
- dout("%s %p\n", __func__, osd);
+ dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
BUG_ON(!list_empty(&osd->o_osd_lru));
+ spin_lock(&osdc->osd_lru_lock);
list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
+ spin_unlock(&osdc->osd_lru_lock);
+
osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl;
}
-static void maybe_move_osd_to_lru(struct ceph_osd_client *osdc,
- struct ceph_osd *osd)
+static void maybe_move_osd_to_lru(struct ceph_osd *osd)
{
- dout("%s %p\n", __func__, osd);
-
- if (list_empty(&osd->o_requests) &&
- list_empty(&osd->o_linger_requests))
- __move_osd_to_lru(osdc, osd);
+ if (RB_EMPTY_ROOT(&osd->o_requests) &&
+ RB_EMPTY_ROOT(&osd->o_linger_requests))
+ __move_osd_to_lru(osd);
}
static void __remove_osd_from_lru(struct ceph_osd *osd)
{
- dout("__remove_osd_from_lru %p\n", osd);
+ struct ceph_osd_client *osdc = osd->o_osdc;
+
+ dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
+
+ spin_lock(&osdc->osd_lru_lock);
if (!list_empty(&osd->o_osd_lru))
list_del_init(&osd->o_osd_lru);
+ spin_unlock(&osdc->osd_lru_lock);
}
-static void remove_old_osds(struct ceph_osd_client *osdc)
+/*
+ * Close the connection and assign any leftover requests to the
+ * homeless session.
+ */
+static void close_osd(struct ceph_osd *osd)
{
- struct ceph_osd *osd, *nosd;
+ struct ceph_osd_client *osdc = osd->o_osdc;
+ struct rb_node *n;
- dout("__remove_old_osds %p\n", osdc);
- mutex_lock(&osdc->request_mutex);
- list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
- if (time_before(jiffies, osd->lru_ttl))
- break;
- remove_osd(osdc, osd);
+ verify_osdc_wrlocked(osdc);
+ dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
+
+ ceph_con_close(&osd->o_con);
+
+ for (n = rb_first(&osd->o_requests); n; ) {
+ struct ceph_osd_request *req =
+ rb_entry(n, struct ceph_osd_request, r_node);
+
+ n = rb_next(n); /* unlink_request() */
+
+ dout(" reassigning req %p tid %llu\n", req, req->r_tid);
+ unlink_request(osd, req);
+ link_request(&osdc->homeless_osd, req);
+ }
+ for (n = rb_first(&osd->o_linger_requests); n; ) {
+ struct ceph_osd_linger_request *lreq =
+ rb_entry(n, struct ceph_osd_linger_request, node);
+
+ n = rb_next(n); /* unlink_linger() */
+
+ dout(" reassigning lreq %p linger_id %llu\n", lreq,
+ lreq->linger_id);
+ unlink_linger(osd, lreq);
+ link_linger(&osdc->homeless_osd, lreq);
}
- mutex_unlock(&osdc->request_mutex);
+
+ __remove_osd_from_lru(osd);
+ erase_osd(&osdc->osds, osd);
+ put_osd(osd);
}
/*
* reset osd connect
*/
-static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+static int reopen_osd(struct ceph_osd *osd)
{
struct ceph_entity_addr *peer_addr;
- dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
- if (list_empty(&osd->o_requests) &&
- list_empty(&osd->o_linger_requests)) {
- remove_osd(osdc, osd);
+ dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
+
+ if (RB_EMPTY_ROOT(&osd->o_requests) &&
+ RB_EMPTY_ROOT(&osd->o_linger_requests)) {
+ close_osd(osd);
return -ENODEV;
}
- peer_addr = &osdc->osdmap->osd_addr[osd->o_osd];
+ peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd];
if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) &&
!ceph_con_opened(&osd->o_con)) {
- struct ceph_osd_request *req;
+ struct rb_node *n;
dout("osd addr hasn't changed and connection never opened, "
"letting msgr retry\n");
/* touch each r_stamp for handle_timeout()'s benfit */
- list_for_each_entry(req, &osd->o_requests, r_osd_item)
+ for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) {
+ struct ceph_osd_request *req =
+ rb_entry(n, struct ceph_osd_request, r_node);
req->r_stamp = jiffies;
+ }
return -EAGAIN;
}
@@ -1206,455 +1170,1369 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
return 0;
}
-static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new)
+static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o,
+ bool wrlocked)
{
- struct rb_node **p = &osdc->osds.rb_node;
- struct rb_node *parent = NULL;
- struct ceph_osd *osd = NULL;
+ struct ceph_osd *osd;
- dout("__insert_osd %p osd%d\n", new, new->o_osd);
- while (*p) {
- parent = *p;
- osd = rb_entry(parent, struct ceph_osd, o_node);
- if (new->o_osd < osd->o_osd)
- p = &(*p)->rb_left;
- else if (new->o_osd > osd->o_osd)
- p = &(*p)->rb_right;
- else
- BUG();
+ if (wrlocked)
+ verify_osdc_wrlocked(osdc);
+ else
+ verify_osdc_locked(osdc);
+
+ if (o != CEPH_HOMELESS_OSD)
+ osd = lookup_osd(&osdc->osds, o);
+ else
+ osd = &osdc->homeless_osd;
+ if (!osd) {
+ if (!wrlocked)
+ return ERR_PTR(-EAGAIN);
+
+ osd = create_osd(osdc, o);
+ insert_osd(&osdc->osds, osd);
+ ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd,
+ &osdc->osdmap->osd_addr[osd->o_osd]);
}
- rb_link_node(&new->o_node, parent, p);
- rb_insert_color(&new->o_node, &osdc->osds);
+ dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd);
+ return osd;
}
-static struct ceph_osd *__lookup_osd(struct ceph_osd_client *osdc, int o)
+/*
+ * Create request <-> OSD session relation.
+ *
+ * @req has to be assigned a tid, @osd may be homeless.
+ */
+static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req)
{
- struct ceph_osd *osd;
- struct rb_node *n = osdc->osds.rb_node;
-
- while (n) {
- osd = rb_entry(n, struct ceph_osd, o_node);
- if (o < osd->o_osd)
- n = n->rb_left;
- else if (o > osd->o_osd)
- n = n->rb_right;
- else
- return osd;
- }
- return NULL;
+ verify_osd_locked(osd);
+ WARN_ON(!req->r_tid || req->r_osd);
+ dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd,
+ req, req->r_tid);
+
+ if (!osd_homeless(osd))
+ __remove_osd_from_lru(osd);
+ else
+ atomic_inc(&osd->o_osdc->num_homeless);
+
+ get_osd(osd);
+ insert_request(&osd->o_requests, req);
+ req->r_osd = osd;
}
-static void __schedule_osd_timeout(struct ceph_osd_client *osdc)
+static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req)
{
- schedule_delayed_work(&osdc->timeout_work,
- osdc->client->options->osd_keepalive_timeout);
+ verify_osd_locked(osd);
+ WARN_ON(req->r_osd != osd);
+ dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd,
+ req, req->r_tid);
+
+ req->r_osd = NULL;
+ erase_request(&osd->o_requests, req);
+ put_osd(osd);
+
+ if (!osd_homeless(osd))
+ maybe_move_osd_to_lru(osd);
+ else
+ atomic_dec(&osd->o_osdc->num_homeless);
}
-static void __cancel_osd_timeout(struct ceph_osd_client *osdc)
+static bool __pool_full(struct ceph_pg_pool_info *pi)
{
- cancel_delayed_work(&osdc->timeout_work);
+ return pi->flags & CEPH_POOL_FLAG_FULL;
}
-/*
- * Register request, assign tid. If this is the first request, set up
- * the timeout event.
- */
-static void __register_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static bool have_pool_full(struct ceph_osd_client *osdc)
{
- req->r_tid = ++osdc->last_tid;
- req->r_request->hdr.tid = cpu_to_le64(req->r_tid);
- dout("__register_request %p tid %lld\n", req, req->r_tid);
- __insert_request(osdc, req);
- ceph_osdc_get_request(req);
- osdc->num_requests++;
- if (osdc->num_requests == 1) {
- dout(" first request, scheduling timeout\n");
- __schedule_osd_timeout(osdc);
+ struct rb_node *n;
+
+ for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) {
+ struct ceph_pg_pool_info *pi =
+ rb_entry(n, struct ceph_pg_pool_info, node);
+
+ if (__pool_full(pi))
+ return true;
}
+
+ return false;
+}
+
+static bool pool_full(struct ceph_osd_client *osdc, s64 pool_id)
+{
+ struct ceph_pg_pool_info *pi;
+
+ pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id);
+ if (!pi)
+ return false;
+
+ return __pool_full(pi);
}
/*
- * called under osdc->request_mutex
+ * Returns whether a request should be blocked from being sent
+ * based on the current osdmap and osd_client settings.
*/
-static void __unregister_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static bool target_should_be_paused(struct ceph_osd_client *osdc,
+ const struct ceph_osd_request_target *t,
+ struct ceph_pg_pool_info *pi)
{
- if (RB_EMPTY_NODE(&req->r_node)) {
- dout("__unregister_request %p tid %lld not registered\n",
- req, req->r_tid);
- return;
+ bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+ bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ __pool_full(pi);
+
+ WARN_ON(pi->id != t->base_oloc.pool);
+ return (t->flags & CEPH_OSD_FLAG_READ && pauserd) ||
+ (t->flags & CEPH_OSD_FLAG_WRITE && pausewr);
+}
+
+enum calc_target_result {
+ CALC_TARGET_NO_ACTION = 0,
+ CALC_TARGET_NEED_RESEND,
+ CALC_TARGET_POOL_DNE,
+};
+
+static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
+ struct ceph_osd_request_target *t,
+ u32 *last_force_resend,
+ bool any_change)
+{
+ struct ceph_pg_pool_info *pi;
+ struct ceph_pg pgid, last_pgid;
+ struct ceph_osds up, acting;
+ bool force_resend = false;
+ bool need_check_tiering = false;
+ bool need_resend = false;
+ bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
+ enum calc_target_result ct_res;
+ int ret;
+
+ pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool);
+ if (!pi) {
+ t->osd = CEPH_HOMELESS_OSD;
+ ct_res = CALC_TARGET_POOL_DNE;
+ goto out;
}
- dout("__unregister_request %p tid %lld\n", req, req->r_tid);
- rb_erase(&req->r_node, &osdc->requests);
- RB_CLEAR_NODE(&req->r_node);
- osdc->num_requests--;
+ if (osdc->osdmap->epoch == pi->last_force_request_resend) {
+ if (last_force_resend &&
+ *last_force_resend < pi->last_force_request_resend) {
+ *last_force_resend = pi->last_force_request_resend;
+ force_resend = true;
+ } else if (!last_force_resend) {
+ force_resend = true;
+ }
+ }
+ if (ceph_oid_empty(&t->target_oid) || force_resend) {
+ ceph_oid_copy(&t->target_oid, &t->base_oid);
+ need_check_tiering = true;
+ }
+ if (ceph_oloc_empty(&t->target_oloc) || force_resend) {
+ ceph_oloc_copy(&t->target_oloc, &t->base_oloc);
+ need_check_tiering = true;
+ }
- if (req->r_osd) {
- /* make sure the original request isn't in flight. */
- ceph_msg_revoke(req->r_request);
+ if (need_check_tiering &&
+ (t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) {
+ if (t->flags & CEPH_OSD_FLAG_READ && pi->read_tier >= 0)
+ t->target_oloc.pool = pi->read_tier;
+ if (t->flags & CEPH_OSD_FLAG_WRITE && pi->write_tier >= 0)
+ t->target_oloc.pool = pi->write_tier;
+ }
- list_del_init(&req->r_osd_item);
- maybe_move_osd_to_lru(osdc, req->r_osd);
- if (list_empty(&req->r_linger_osd_item))
- req->r_osd = NULL;
+ ret = ceph_object_locator_to_pg(osdc->osdmap, &t->target_oid,
+ &t->target_oloc, &pgid);
+ if (ret) {
+ WARN_ON(ret != -ENOENT);
+ t->osd = CEPH_HOMELESS_OSD;
+ ct_res = CALC_TARGET_POOL_DNE;
+ goto out;
+ }
+ last_pgid.pool = pgid.pool;
+ last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask);
+
+ ceph_pg_to_up_acting_osds(osdc->osdmap, &pgid, &up, &acting);
+ if (any_change &&
+ ceph_is_new_interval(&t->acting,
+ &acting,
+ &t->up,
+ &up,
+ t->size,
+ pi->size,
+ t->min_size,
+ pi->min_size,
+ t->pg_num,
+ pi->pg_num,
+ t->sort_bitwise,
+ sort_bitwise,
+ &last_pgid))
+ force_resend = true;
+
+ if (t->paused && !target_should_be_paused(osdc, t, pi)) {
+ t->paused = false;
+ need_resend = true;
}
- list_del_init(&req->r_req_lru_item);
- ceph_osdc_put_request(req);
+ if (ceph_pg_compare(&t->pgid, &pgid) ||
+ ceph_osds_changed(&t->acting, &acting, any_change) ||
+ force_resend) {
+ t->pgid = pgid; /* struct */
+ ceph_osds_copy(&t->acting, &acting);
+ ceph_osds_copy(&t->up, &up);
+ t->size = pi->size;
+ t->min_size = pi->min_size;
+ t->pg_num = pi->pg_num;
+ t->pg_num_mask = pi->pg_num_mask;
+ t->sort_bitwise = sort_bitwise;
+
+ t->osd = acting.primary;
+ need_resend = true;
+ }
+
+ ct_res = need_resend ? CALC_TARGET_NEED_RESEND : CALC_TARGET_NO_ACTION;
+out:
+ dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd);
+ return ct_res;
+}
+
+static void setup_request_data(struct ceph_osd_request *req,
+ struct ceph_msg *msg)
+{
+ u32 data_len = 0;
+ int i;
+
+ if (!list_empty(&msg->data))
+ return;
+
+ WARN_ON(msg->data_length);
+ for (i = 0; i < req->r_num_ops; i++) {
+ struct ceph_osd_req_op *op = &req->r_ops[i];
+
+ switch (op->op) {
+ /* request */
+ case CEPH_OSD_OP_WRITE:
+ case CEPH_OSD_OP_WRITEFULL:
+ WARN_ON(op->indata_len != op->extent.length);
+ ceph_osdc_msg_data_add(msg, &op->extent.osd_data);
+ break;
+ case CEPH_OSD_OP_SETXATTR:
+ case CEPH_OSD_OP_CMPXATTR:
+ WARN_ON(op->indata_len != op->xattr.name_len +
+ op->xattr.value_len);
+ ceph_osdc_msg_data_add(msg, &op->xattr.osd_data);
+ break;
+ case CEPH_OSD_OP_NOTIFY_ACK:
+ ceph_osdc_msg_data_add(msg,
+ &op->notify_ack.request_data);
+ break;
+
+ /* reply */
+ case CEPH_OSD_OP_STAT:
+ ceph_osdc_msg_data_add(req->r_reply,
+ &op->raw_data_in);
+ break;
+ case CEPH_OSD_OP_READ:
+ ceph_osdc_msg_data_add(req->r_reply,
+ &op->extent.osd_data);
+ break;
+
+ /* both */
+ case CEPH_OSD_OP_CALL:
+ WARN_ON(op->indata_len != op->cls.class_len +
+ op->cls.method_len +
+ op->cls.indata_len);
+ ceph_osdc_msg_data_add(msg, &op->cls.request_info);
+ /* optional, can be NONE */
+ ceph_osdc_msg_data_add(msg, &op->cls.request_data);
+ /* optional, can be NONE */
+ ceph_osdc_msg_data_add(req->r_reply,
+ &op->cls.response_data);
+ break;
+ case CEPH_OSD_OP_NOTIFY:
+ ceph_osdc_msg_data_add(msg,
+ &op->notify.request_data);
+ ceph_osdc_msg_data_add(req->r_reply,
+ &op->notify.response_data);
+ break;
+ }
+
+ data_len += op->indata_len;
+ }
+
+ WARN_ON(data_len != msg->data_length);
+}
+
+static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
+{
+ void *p = msg->front.iov_base;
+ void *const end = p + msg->front_alloc_len;
+ u32 data_len = 0;
+ int i;
+
+ if (req->r_flags & CEPH_OSD_FLAG_WRITE) {
+ /* snapshots aren't writeable */
+ WARN_ON(req->r_snapid != CEPH_NOSNAP);
+ } else {
+ WARN_ON(req->r_mtime.tv_sec || req->r_mtime.tv_nsec ||
+ req->r_data_offset || req->r_snapc);
+ }
+
+ setup_request_data(req, msg);
+
+ ceph_encode_32(&p, 1); /* client_inc, always 1 */
+ ceph_encode_32(&p, req->r_osdc->osdmap->epoch);
+ ceph_encode_32(&p, req->r_flags);
+ ceph_encode_timespec(p, &req->r_mtime);
+ p += sizeof(struct ceph_timespec);
+ /* aka reassert_version */
+ memcpy(p, &req->r_replay_version, sizeof(req->r_replay_version));
+ p += sizeof(req->r_replay_version);
+
+ /* oloc */
+ ceph_encode_8(&p, 4);
+ ceph_encode_8(&p, 4);
+ ceph_encode_32(&p, 8 + 4 + 4);
+ ceph_encode_64(&p, req->r_t.target_oloc.pool);
+ ceph_encode_32(&p, -1); /* preferred */
+ ceph_encode_32(&p, 0); /* key len */
+
+ /* pgid */
+ ceph_encode_8(&p, 1);
+ ceph_encode_64(&p, req->r_t.pgid.pool);
+ ceph_encode_32(&p, req->r_t.pgid.seed);
+ ceph_encode_32(&p, -1); /* preferred */
+
+ /* oid */
+ ceph_encode_32(&p, req->r_t.target_oid.name_len);
+ memcpy(p, req->r_t.target_oid.name, req->r_t.target_oid.name_len);
+ p += req->r_t.target_oid.name_len;
- if (osdc->num_requests == 0) {
- dout(" no requests, canceling timeout\n");
- __cancel_osd_timeout(osdc);
+ /* ops, can imply data */
+ ceph_encode_16(&p, req->r_num_ops);
+ for (i = 0; i < req->r_num_ops; i++) {
+ data_len += osd_req_encode_op(p, &req->r_ops[i]);
+ p += sizeof(struct ceph_osd_op);
}
+
+ ceph_encode_64(&p, req->r_snapid); /* snapid */
+ if (req->r_snapc) {
+ ceph_encode_64(&p, req->r_snapc->seq);
+ ceph_encode_32(&p, req->r_snapc->num_snaps);
+ for (i = 0; i < req->r_snapc->num_snaps; i++)
+ ceph_encode_64(&p, req->r_snapc->snaps[i]);
+ } else {
+ ceph_encode_64(&p, 0); /* snap_seq */
+ ceph_encode_32(&p, 0); /* snaps len */
+ }
+
+ ceph_encode_32(&p, req->r_attempts); /* retry_attempt */
+
+ BUG_ON(p > end);
+ msg->front.iov_len = p - msg->front.iov_base;
+ msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */
+ msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+ msg->hdr.data_len = cpu_to_le32(data_len);
+ /*
+ * The header "data_off" is a hint to the receiver allowing it
+ * to align received data into its buffers such that there's no
+ * need to re-copy it before writing it to disk (direct I/O).
+ */
+ msg->hdr.data_off = cpu_to_le16(req->r_data_offset);
+
+ dout("%s req %p oid %s oid_len %d front %zu data %u\n", __func__,
+ req, req->r_t.target_oid.name, req->r_t.target_oid.name_len,
+ msg->front.iov_len, data_len);
}
/*
- * Cancel a previously queued request message
+ * @req has to be assigned a tid and registered.
*/
-static void __cancel_request(struct ceph_osd_request *req)
+static void send_request(struct ceph_osd_request *req)
{
- if (req->r_sent && req->r_osd) {
+ struct ceph_osd *osd = req->r_osd;
+
+ verify_osd_locked(osd);
+ WARN_ON(osd->o_osd != req->r_t.osd);
+
+ /*
+ * We may have a previously queued request message hanging
+ * around. Cancel it to avoid corrupting the msgr.
+ */
+ if (req->r_sent)
ceph_msg_revoke(req->r_request);
- req->r_sent = 0;
+
+ req->r_flags |= CEPH_OSD_FLAG_KNOWN_REDIR;
+ if (req->r_attempts)
+ req->r_flags |= CEPH_OSD_FLAG_RETRY;
+ else
+ WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY);
+
+ encode_request(req, req->r_request);
+
+ dout("%s req %p tid %llu to pg %llu.%x osd%d flags 0x%x attempt %d\n",
+ __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed,
+ req->r_t.osd, req->r_flags, req->r_attempts);
+
+ req->r_t.paused = false;
+ req->r_stamp = jiffies;
+ req->r_attempts++;
+
+ req->r_sent = osd->o_incarnation;
+ req->r_request->hdr.tid = cpu_to_le64(req->r_tid);
+ ceph_con_send(&osd->o_con, ceph_msg_get(req->r_request));
+}
+
+static void maybe_request_map(struct ceph_osd_client *osdc)
+{
+ bool continuous = false;
+
+ verify_osdc_locked(osdc);
+ WARN_ON(!osdc->osdmap->epoch);
+
+ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) ||
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
+ dout("%s osdc %p continuous\n", __func__, osdc);
+ continuous = true;
+ } else {
+ dout("%s osdc %p onetime\n", __func__, osdc);
}
+
+ if (ceph_monc_want_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
+ osdc->osdmap->epoch + 1, continuous))
+ ceph_monc_renew_subs(&osdc->client->monc);
}
-static void __register_linger_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static void send_map_check(struct ceph_osd_request *req);
+
+static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
{
- dout("%s %p tid %llu\n", __func__, req, req->r_tid);
- WARN_ON(!req->r_linger);
+ struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_osd *osd;
+ enum calc_target_result ct_res;
+ bool need_send = false;
+ bool promoted = false;
+
+ WARN_ON(req->r_tid || req->r_got_reply);
+ dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
+
+again:
+ ct_res = calc_target(osdc, &req->r_t, &req->r_last_force_resend, false);
+ if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked)
+ goto promote;
+
+ osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked);
+ if (IS_ERR(osd)) {
+ WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked);
+ goto promote;
+ }
+
+ if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
+ dout("req %p pausewr\n", req);
+ req->r_t.paused = true;
+ maybe_request_map(osdc);
+ } else if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
+ dout("req %p pauserd\n", req);
+ req->r_t.paused = true;
+ maybe_request_map(osdc);
+ } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
+ !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY |
+ CEPH_OSD_FLAG_FULL_FORCE)) &&
+ (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ pool_full(osdc, req->r_t.base_oloc.pool))) {
+ dout("req %p full/pool_full\n", req);
+ pr_warn_ratelimited("FULL or reached pool quota\n");
+ req->r_t.paused = true;
+ maybe_request_map(osdc);
+ } else if (!osd_homeless(osd)) {
+ need_send = true;
+ } else {
+ maybe_request_map(osdc);
+ }
+
+ mutex_lock(&osd->lock);
+ /*
+ * Assign the tid atomically with send_request() to protect
+ * multiple writes to the same object from racing with each
+ * other, resulting in out of order ops on the OSDs.
+ */
+ req->r_tid = atomic64_inc_return(&osdc->last_tid);
+ link_request(osd, req);
+ if (need_send)
+ send_request(req);
+ mutex_unlock(&osd->lock);
+ if (ct_res == CALC_TARGET_POOL_DNE)
+ send_map_check(req);
+
+ if (promoted)
+ downgrade_write(&osdc->lock);
+ return;
+
+promote:
+ up_read(&osdc->lock);
+ down_write(&osdc->lock);
+ wrlocked = true;
+ promoted = true;
+ goto again;
+}
+
+static void account_request(struct ceph_osd_request *req)
+{
+ unsigned int mask = CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK;
+
+ if (req->r_flags & CEPH_OSD_FLAG_READ) {
+ WARN_ON(req->r_flags & mask);
+ req->r_flags |= CEPH_OSD_FLAG_ACK;
+ } else if (req->r_flags & CEPH_OSD_FLAG_WRITE)
+ WARN_ON(!(req->r_flags & mask));
+ else
+ WARN_ON(1);
+
+ WARN_ON(req->r_unsafe_callback && (req->r_flags & mask) != mask);
+ atomic_inc(&req->r_osdc->num_requests);
+}
+
+static void submit_request(struct ceph_osd_request *req, bool wrlocked)
+{
ceph_osdc_get_request(req);
- list_add_tail(&req->r_linger_item, &osdc->req_linger);
- if (req->r_osd)
- list_add_tail(&req->r_linger_osd_item,
- &req->r_osd->o_linger_requests);
+ account_request(req);
+ __submit_request(req, wrlocked);
}
-static void __unregister_linger_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static void __finish_request(struct ceph_osd_request *req)
{
- WARN_ON(!req->r_linger);
+ struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_osd *osd = req->r_osd;
- if (list_empty(&req->r_linger_item)) {
- dout("%s %p tid %llu not registered\n", __func__, req,
- req->r_tid);
+ verify_osd_locked(osd);
+ dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
+
+ WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
+ unlink_request(osd, req);
+ atomic_dec(&osdc->num_requests);
+
+ /*
+ * If an OSD has failed or returned and a request has been sent
+ * twice, it's possible to get a reply and end up here while the
+ * request message is queued for delivery. We will ignore the
+ * reply, so not a big deal, but better to try and catch it.
+ */
+ ceph_msg_revoke(req->r_request);
+ ceph_msg_revoke_incoming(req->r_reply);
+}
+
+static void finish_request(struct ceph_osd_request *req)
+{
+ __finish_request(req);
+ ceph_osdc_put_request(req);
+}
+
+static void __complete_request(struct ceph_osd_request *req)
+{
+ if (req->r_callback)
+ req->r_callback(req);
+ else
+ complete_all(&req->r_completion);
+}
+
+/*
+ * Note that this is open-coded in handle_reply(), which has to deal
+ * with ack vs commit, dup acks, etc.
+ */
+static void complete_request(struct ceph_osd_request *req, int err)
+{
+ dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);
+
+ req->r_result = err;
+ __finish_request(req);
+ __complete_request(req);
+ complete_all(&req->r_safe_completion);
+ ceph_osdc_put_request(req);
+}
+
+static void cancel_map_check(struct ceph_osd_request *req)
+{
+ struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_osd_request *lookup_req;
+
+ verify_osdc_wrlocked(osdc);
+
+ lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid);
+ if (!lookup_req)
return;
+
+ WARN_ON(lookup_req != req);
+ erase_request_mc(&osdc->map_checks, req);
+ ceph_osdc_put_request(req);
+}
+
+static void cancel_request(struct ceph_osd_request *req)
+{
+ dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
+
+ cancel_map_check(req);
+ finish_request(req);
+}
+
+static void check_pool_dne(struct ceph_osd_request *req)
+{
+ struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_osdmap *map = osdc->osdmap;
+
+ verify_osdc_wrlocked(osdc);
+ WARN_ON(!map->epoch);
+
+ if (req->r_attempts) {
+ /*
+ * We sent a request earlier, which means that
+ * previously the pool existed, and now it does not
+ * (i.e., it was deleted).
+ */
+ req->r_map_dne_bound = map->epoch;
+ dout("%s req %p tid %llu pool disappeared\n", __func__, req,
+ req->r_tid);
+ } else {
+ dout("%s req %p tid %llu map_dne_bound %u have %u\n", __func__,
+ req, req->r_tid, req->r_map_dne_bound, map->epoch);
+ }
+
+ if (req->r_map_dne_bound) {
+ if (map->epoch >= req->r_map_dne_bound) {
+ /* we had a new enough map */
+ pr_info_ratelimited("tid %llu pool does not exist\n",
+ req->r_tid);
+ complete_request(req, -ENOENT);
+ }
+ } else {
+ send_map_check(req);
}
+}
+
+static void map_check_cb(struct ceph_mon_generic_request *greq)
+{
+ struct ceph_osd_client *osdc = &greq->monc->client->osdc;
+ struct ceph_osd_request *req;
+ u64 tid = greq->private_data;
- dout("%s %p tid %llu\n", __func__, req, req->r_tid);
- list_del_init(&req->r_linger_item);
+ WARN_ON(greq->result || !greq->u.newest);
- if (req->r_osd) {
- list_del_init(&req->r_linger_osd_item);
- maybe_move_osd_to_lru(osdc, req->r_osd);
- if (list_empty(&req->r_osd_item))
- req->r_osd = NULL;
+ down_write(&osdc->lock);
+ req = lookup_request_mc(&osdc->map_checks, tid);
+ if (!req) {
+ dout("%s tid %llu dne\n", __func__, tid);
+ goto out_unlock;
}
+
+ dout("%s req %p tid %llu map_dne_bound %u newest %llu\n", __func__,
+ req, req->r_tid, req->r_map_dne_bound, greq->u.newest);
+ if (!req->r_map_dne_bound)
+ req->r_map_dne_bound = greq->u.newest;
+ erase_request_mc(&osdc->map_checks, req);
+ check_pool_dne(req);
+
ceph_osdc_put_request(req);
+out_unlock:
+ up_write(&osdc->lock);
}
-void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static void send_map_check(struct ceph_osd_request *req)
{
- if (!req->r_linger) {
- dout("set_request_linger %p\n", req);
- req->r_linger = 1;
+ struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_osd_request *lookup_req;
+ int ret;
+
+ verify_osdc_wrlocked(osdc);
+
+ lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid);
+ if (lookup_req) {
+ WARN_ON(lookup_req != req);
+ return;
}
+
+ ceph_osdc_get_request(req);
+ insert_request_mc(&osdc->map_checks, req);
+ ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap",
+ map_check_cb, req->r_tid);
+ WARN_ON(ret);
}
-EXPORT_SYMBOL(ceph_osdc_set_request_linger);
/*
- * Returns whether a request should be blocked from being sent
- * based on the current osdmap and osd_client settings.
- *
- * Caller should hold map_sem for read.
+ * lingering requests, watch/notify v2 infrastructure
*/
-static bool __req_should_be_paused(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static void linger_release(struct kref *kref)
+{
+ struct ceph_osd_linger_request *lreq =
+ container_of(kref, struct ceph_osd_linger_request, kref);
+
+ dout("%s lreq %p reg_req %p ping_req %p\n", __func__, lreq,
+ lreq->reg_req, lreq->ping_req);
+ WARN_ON(!RB_EMPTY_NODE(&lreq->node));
+ WARN_ON(!RB_EMPTY_NODE(&lreq->osdc_node));
+ WARN_ON(!RB_EMPTY_NODE(&lreq->mc_node));
+ WARN_ON(!list_empty(&lreq->scan_item));
+ WARN_ON(!list_empty(&lreq->pending_lworks));
+ WARN_ON(lreq->osd);
+
+ if (lreq->reg_req)
+ ceph_osdc_put_request(lreq->reg_req);
+ if (lreq->ping_req)
+ ceph_osdc_put_request(lreq->ping_req);
+ target_destroy(&lreq->t);
+ kfree(lreq);
+}
+
+static void linger_put(struct ceph_osd_linger_request *lreq)
{
- bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
- bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
- ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
- return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) ||
- (req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr);
+ if (lreq)
+ kref_put(&lreq->kref, linger_release);
+}
+
+static struct ceph_osd_linger_request *
+linger_get(struct ceph_osd_linger_request *lreq)
+{
+ kref_get(&lreq->kref);
+ return lreq;
+}
+
+static struct ceph_osd_linger_request *
+linger_alloc(struct ceph_osd_client *osdc)
+{
+ struct ceph_osd_linger_request *lreq;
+
+ lreq = kzalloc(sizeof(*lreq), GFP_NOIO);
+ if (!lreq)
+ return NULL;
+
+ kref_init(&lreq->kref);
+ mutex_init(&lreq->lock);
+ RB_CLEAR_NODE(&lreq->node);
+ RB_CLEAR_NODE(&lreq->osdc_node);
+ RB_CLEAR_NODE(&lreq->mc_node);
+ INIT_LIST_HEAD(&lreq->scan_item);
+ INIT_LIST_HEAD(&lreq->pending_lworks);
+ init_completion(&lreq->reg_commit_wait);
+ init_completion(&lreq->notify_finish_wait);
+
+ lreq->osdc = osdc;
+ target_init(&lreq->t);
+
+ dout("%s lreq %p\n", __func__, lreq);
+ return lreq;
}
+DEFINE_RB_INSDEL_FUNCS(linger, struct ceph_osd_linger_request, linger_id, node)
+DEFINE_RB_FUNCS(linger_osdc, struct ceph_osd_linger_request, linger_id, osdc_node)
+DEFINE_RB_FUNCS(linger_mc, struct ceph_osd_linger_request, linger_id, mc_node)
+
/*
- * Calculate mapping of a request to a PG. Takes tiering into account.
+ * Create linger request <-> OSD session relation.
+ *
+ * @lreq has to be registered, @osd may be homeless.
*/
-static int __calc_request_pg(struct ceph_osdmap *osdmap,
- struct ceph_osd_request *req,
- struct ceph_pg *pg_out)
+static void link_linger(struct ceph_osd *osd,
+ struct ceph_osd_linger_request *lreq)
{
- bool need_check_tiering;
+ verify_osd_locked(osd);
+ WARN_ON(!lreq->linger_id || lreq->osd);
+ dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd,
+ osd->o_osd, lreq, lreq->linger_id);
- need_check_tiering = false;
- if (req->r_target_oloc.pool == -1) {
- req->r_target_oloc = req->r_base_oloc; /* struct */
- need_check_tiering = true;
+ if (!osd_homeless(osd))
+ __remove_osd_from_lru(osd);
+ else
+ atomic_inc(&osd->o_osdc->num_homeless);
+
+ get_osd(osd);
+ insert_linger(&osd->o_linger_requests, lreq);
+ lreq->osd = osd;
+}
+
+static void unlink_linger(struct ceph_osd *osd,
+ struct ceph_osd_linger_request *lreq)
+{
+ verify_osd_locked(osd);
+ WARN_ON(lreq->osd != osd);
+ dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd,
+ osd->o_osd, lreq, lreq->linger_id);
+
+ lreq->osd = NULL;
+ erase_linger(&osd->o_linger_requests, lreq);
+ put_osd(osd);
+
+ if (!osd_homeless(osd))
+ maybe_move_osd_to_lru(osd);
+ else
+ atomic_dec(&osd->o_osdc->num_homeless);
+}
+
+static bool __linger_registered(struct ceph_osd_linger_request *lreq)
+{
+ verify_osdc_locked(lreq->osdc);
+
+ return !RB_EMPTY_NODE(&lreq->osdc_node);
+}
+
+static bool linger_registered(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+ bool registered;
+
+ down_read(&osdc->lock);
+ registered = __linger_registered(lreq);
+ up_read(&osdc->lock);
+
+ return registered;
+}
+
+static void linger_register(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+
+ verify_osdc_wrlocked(osdc);
+ WARN_ON(lreq->linger_id);
+
+ linger_get(lreq);
+ lreq->linger_id = ++osdc->last_linger_id;
+ insert_linger_osdc(&osdc->linger_requests, lreq);
+}
+
+static void linger_unregister(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+
+ verify_osdc_wrlocked(osdc);
+
+ erase_linger_osdc(&osdc->linger_requests, lreq);
+ linger_put(lreq);
+}
+
+static void cancel_linger_request(struct ceph_osd_request *req)
+{
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ WARN_ON(!req->r_linger);
+ cancel_request(req);
+ linger_put(lreq);
+}
+
+struct linger_work {
+ struct work_struct work;
+ struct ceph_osd_linger_request *lreq;
+ struct list_head pending_item;
+ unsigned long queued_stamp;
+
+ union {
+ struct {
+ u64 notify_id;
+ u64 notifier_id;
+ void *payload; /* points into @msg front */
+ size_t payload_len;
+
+ struct ceph_msg *msg; /* for ceph_msg_put() */
+ } notify;
+ struct {
+ int err;
+ } error;
+ };
+};
+
+static struct linger_work *lwork_alloc(struct ceph_osd_linger_request *lreq,
+ work_func_t workfn)
+{
+ struct linger_work *lwork;
+
+ lwork = kzalloc(sizeof(*lwork), GFP_NOIO);
+ if (!lwork)
+ return NULL;
+
+ INIT_WORK(&lwork->work, workfn);
+ INIT_LIST_HEAD(&lwork->pending_item);
+ lwork->lreq = linger_get(lreq);
+
+ return lwork;
+}
+
+static void lwork_free(struct linger_work *lwork)
+{
+ struct ceph_osd_linger_request *lreq = lwork->lreq;
+
+ mutex_lock(&lreq->lock);
+ list_del(&lwork->pending_item);
+ mutex_unlock(&lreq->lock);
+
+ linger_put(lreq);
+ kfree(lwork);
+}
+
+static void lwork_queue(struct linger_work *lwork)
+{
+ struct ceph_osd_linger_request *lreq = lwork->lreq;
+ struct ceph_osd_client *osdc = lreq->osdc;
+
+ verify_lreq_locked(lreq);
+ WARN_ON(!list_empty(&lwork->pending_item));
+
+ lwork->queued_stamp = jiffies;
+ list_add_tail(&lwork->pending_item, &lreq->pending_lworks);
+ queue_work(osdc->notify_wq, &lwork->work);
+}
+
+static void do_watch_notify(struct work_struct *w)
+{
+ struct linger_work *lwork = container_of(w, struct linger_work, work);
+ struct ceph_osd_linger_request *lreq = lwork->lreq;
+
+ if (!linger_registered(lreq)) {
+ dout("%s lreq %p not registered\n", __func__, lreq);
+ goto out;
}
- if (req->r_target_oid.name_len == 0) {
- ceph_oid_copy(&req->r_target_oid, &req->r_base_oid);
- need_check_tiering = true;
+
+ WARN_ON(!lreq->is_watch);
+ dout("%s lreq %p notify_id %llu notifier_id %llu payload_len %zu\n",
+ __func__, lreq, lwork->notify.notify_id, lwork->notify.notifier_id,
+ lwork->notify.payload_len);
+ lreq->wcb(lreq->data, lwork->notify.notify_id, lreq->linger_id,
+ lwork->notify.notifier_id, lwork->notify.payload,
+ lwork->notify.payload_len);
+
+out:
+ ceph_msg_put(lwork->notify.msg);
+ lwork_free(lwork);
+}
+
+static void do_watch_error(struct work_struct *w)
+{
+ struct linger_work *lwork = container_of(w, struct linger_work, work);
+ struct ceph_osd_linger_request *lreq = lwork->lreq;
+
+ if (!linger_registered(lreq)) {
+ dout("%s lreq %p not registered\n", __func__, lreq);
+ goto out;
}
- if (need_check_tiering &&
- (req->r_flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) {
- struct ceph_pg_pool_info *pi;
-
- pi = ceph_pg_pool_by_id(osdmap, req->r_target_oloc.pool);
- if (pi) {
- if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
- pi->read_tier >= 0)
- req->r_target_oloc.pool = pi->read_tier;
- if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
- pi->write_tier >= 0)
- req->r_target_oloc.pool = pi->write_tier;
+ dout("%s lreq %p err %d\n", __func__, lreq, lwork->error.err);
+ lreq->errcb(lreq->data, lreq->linger_id, lwork->error.err);
+
+out:
+ lwork_free(lwork);
+}
+
+static void queue_watch_error(struct ceph_osd_linger_request *lreq)
+{
+ struct linger_work *lwork;
+
+ lwork = lwork_alloc(lreq, do_watch_error);
+ if (!lwork) {
+ pr_err("failed to allocate error-lwork\n");
+ return;
+ }
+
+ lwork->error.err = lreq->last_error;
+ lwork_queue(lwork);
+}
+
+static void linger_reg_commit_complete(struct ceph_osd_linger_request *lreq,
+ int result)
+{
+ if (!completion_done(&lreq->reg_commit_wait)) {
+ lreq->reg_commit_error = (result <= 0 ? result : 0);
+ complete_all(&lreq->reg_commit_wait);
+ }
+}
+
+static void linger_commit_cb(struct ceph_osd_request *req)
+{
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ mutex_lock(&lreq->lock);
+ dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq,
+ lreq->linger_id, req->r_result);
+ WARN_ON(!__linger_registered(lreq));
+ linger_reg_commit_complete(lreq, req->r_result);
+ lreq->committed = true;
+
+ if (!lreq->is_watch) {
+ struct ceph_osd_data *osd_data =
+ osd_req_op_data(req, 0, notify, response_data);
+ void *p = page_address(osd_data->pages[0]);
+
+ WARN_ON(req->r_ops[0].op != CEPH_OSD_OP_NOTIFY ||
+ osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
+
+ /* make note of the notify_id */
+ if (req->r_ops[0].outdata_len >= sizeof(u64)) {
+ lreq->notify_id = ceph_decode_64(&p);
+ dout("lreq %p notify_id %llu\n", lreq,
+ lreq->notify_id);
+ } else {
+ dout("lreq %p no notify_id\n", lreq);
}
- /* !pi is caught in ceph_oloc_oid_to_pg() */
}
- return ceph_oloc_oid_to_pg(osdmap, &req->r_target_oloc,
- &req->r_target_oid, pg_out);
+ mutex_unlock(&lreq->lock);
+ linger_put(lreq);
}
-static void __enqueue_request(struct ceph_osd_request *req)
+static int normalize_watch_error(int err)
{
- struct ceph_osd_client *osdc = req->r_osdc;
+ /*
+ * Translate ENOENT -> ENOTCONN so that a delete->disconnection
+ * notification and a failure to reconnect because we raced with
+ * the delete appear the same to the user.
+ */
+ if (err == -ENOENT)
+ err = -ENOTCONN;
+
+ return err;
+}
+
+static void linger_reconnect_cb(struct ceph_osd_request *req)
+{
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ mutex_lock(&lreq->lock);
+ dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__,
+ lreq, lreq->linger_id, req->r_result, lreq->last_error);
+ if (req->r_result < 0) {
+ if (!lreq->last_error) {
+ lreq->last_error = normalize_watch_error(req->r_result);
+ queue_watch_error(lreq);
+ }
+ }
+
+ mutex_unlock(&lreq->lock);
+ linger_put(lreq);
+}
+
+static void send_linger(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_request *req = lreq->reg_req;
+ struct ceph_osd_req_op *op = &req->r_ops[0];
- dout("%s %p tid %llu to osd%d\n", __func__, req, req->r_tid,
- req->r_osd ? req->r_osd->o_osd : -1);
+ verify_osdc_wrlocked(req->r_osdc);
+ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
- if (req->r_osd) {
- __remove_osd_from_lru(req->r_osd);
- list_add_tail(&req->r_osd_item, &req->r_osd->o_requests);
- list_move_tail(&req->r_req_lru_item, &osdc->req_unsent);
+ if (req->r_osd)
+ cancel_linger_request(req);
+
+ request_reinit(req);
+ ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
+ ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+ req->r_flags = lreq->t.flags;
+ req->r_mtime = lreq->mtime;
+
+ mutex_lock(&lreq->lock);
+ if (lreq->is_watch && lreq->committed) {
+ WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
+ op->watch.cookie != lreq->linger_id);
+ op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT;
+ op->watch.gen = ++lreq->register_gen;
+ dout("lreq %p reconnect register_gen %u\n", lreq,
+ op->watch.gen);
+ req->r_callback = linger_reconnect_cb;
} else {
- list_move_tail(&req->r_req_lru_item, &osdc->req_notarget);
+ if (!lreq->is_watch)
+ lreq->notify_id = 0;
+ else
+ WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
+ dout("lreq %p register\n", lreq);
+ req->r_callback = linger_commit_cb;
}
+ mutex_unlock(&lreq->lock);
+
+ req->r_priv = linger_get(lreq);
+ req->r_linger = true;
+
+ submit_request(req, true);
}
-/*
- * Pick an osd (the first 'up' osd in the pg), allocate the osd struct
- * (as needed), and set the request r_osd appropriately. If there is
- * no up osd, set r_osd to NULL. Move the request to the appropriate list
- * (unsent, homeless) or leave on in-flight lru.
- *
- * Return 0 if unchanged, 1 if changed, or negative on error.
- *
- * Caller should hold map_sem for read and request_mutex.
- */
-static int __map_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req, int force_resend)
+static void linger_ping_cb(struct ceph_osd_request *req)
{
- struct ceph_pg pgid;
- int acting[CEPH_PG_MAX_SIZE];
- int num, o;
- int err;
- bool was_paused;
-
- dout("map_request %p tid %lld\n", req, req->r_tid);
-
- err = __calc_request_pg(osdc->osdmap, req, &pgid);
- if (err) {
- list_move(&req->r_req_lru_item, &osdc->req_notarget);
- return err;
- }
- req->r_pgid = pgid;
-
- num = ceph_calc_pg_acting(osdc->osdmap, pgid, acting, &o);
- if (num < 0)
- num = 0;
-
- was_paused = req->r_paused;
- req->r_paused = __req_should_be_paused(osdc, req);
- if (was_paused && !req->r_paused)
- force_resend = 1;
-
- if ((!force_resend &&
- req->r_osd && req->r_osd->o_osd == o &&
- req->r_sent >= req->r_osd->o_incarnation &&
- req->r_num_pg_osds == num &&
- memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) ||
- (req->r_osd == NULL && o == -1) ||
- req->r_paused)
- return 0; /* no change */
-
- dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n",
- req->r_tid, pgid.pool, pgid.seed, o,
- req->r_osd ? req->r_osd->o_osd : -1);
-
- /* record full pg acting set */
- memcpy(req->r_pg_osds, acting, sizeof(acting[0]) * num);
- req->r_num_pg_osds = num;
-
- if (req->r_osd) {
- __cancel_request(req);
- list_del_init(&req->r_osd_item);
- list_del_init(&req->r_linger_osd_item);
- req->r_osd = NULL;
- }
-
- req->r_osd = __lookup_osd(osdc, o);
- if (!req->r_osd && o >= 0) {
- err = -ENOMEM;
- req->r_osd = create_osd(osdc, o);
- if (!req->r_osd) {
- list_move(&req->r_req_lru_item, &osdc->req_notarget);
- goto out;
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ mutex_lock(&lreq->lock);
+ dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n",
+ __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent,
+ lreq->last_error);
+ if (lreq->register_gen == req->r_ops[0].watch.gen) {
+ if (!req->r_result) {
+ lreq->watch_valid_thru = lreq->ping_sent;
+ } else if (!lreq->last_error) {
+ lreq->last_error = normalize_watch_error(req->r_result);
+ queue_watch_error(lreq);
}
+ } else {
+ dout("lreq %p register_gen %u ignoring old pong %u\n", lreq,
+ lreq->register_gen, req->r_ops[0].watch.gen);
+ }
+
+ mutex_unlock(&lreq->lock);
+ linger_put(lreq);
+}
- dout("map_request osd %p is osd%d\n", req->r_osd, o);
- __insert_osd(osdc, req->r_osd);
+static void send_linger_ping(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+ struct ceph_osd_request *req = lreq->ping_req;
+ struct ceph_osd_req_op *op = &req->r_ops[0];
- ceph_con_open(&req->r_osd->o_con,
- CEPH_ENTITY_TYPE_OSD, o,
- &osdc->osdmap->osd_addr[o]);
+ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
+ dout("%s PAUSERD\n", __func__);
+ return;
}
- __enqueue_request(req);
- err = 1; /* osd or pg changed */
+ lreq->ping_sent = jiffies;
+ dout("%s lreq %p linger_id %llu ping_sent %lu register_gen %u\n",
+ __func__, lreq, lreq->linger_id, lreq->ping_sent,
+ lreq->register_gen);
-out:
- return err;
+ if (req->r_osd)
+ cancel_linger_request(req);
+
+ request_reinit(req);
+ target_copy(&req->r_t, &lreq->t);
+
+ WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
+ op->watch.cookie != lreq->linger_id ||
+ op->watch.op != CEPH_OSD_WATCH_OP_PING);
+ op->watch.gen = lreq->register_gen;
+ req->r_callback = linger_ping_cb;
+ req->r_priv = linger_get(lreq);
+ req->r_linger = true;
+
+ ceph_osdc_get_request(req);
+ account_request(req);
+ req->r_tid = atomic64_inc_return(&osdc->last_tid);
+ link_request(lreq->osd, req);
+ send_request(req);
}
-/*
- * caller should hold map_sem (for read) and request_mutex
- */
-static void __send_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+static void linger_submit(struct ceph_osd_linger_request *lreq)
{
- void *p;
+ struct ceph_osd_client *osdc = lreq->osdc;
+ struct ceph_osd *osd;
- dout("send_request %p tid %llu to osd%d flags %d pg %lld.%x\n",
- req, req->r_tid, req->r_osd->o_osd, req->r_flags,
- (unsigned long long)req->r_pgid.pool, req->r_pgid.seed);
+ calc_target(osdc, &lreq->t, &lreq->last_force_resend, false);
+ osd = lookup_create_osd(osdc, lreq->t.osd, true);
+ link_linger(osd, lreq);
- /* fill in message content that changes each time we send it */
- put_unaligned_le32(osdc->osdmap->epoch, req->r_request_osdmap_epoch);
- put_unaligned_le32(req->r_flags, req->r_request_flags);
- put_unaligned_le64(req->r_target_oloc.pool, req->r_request_pool);
- p = req->r_request_pgid;
- ceph_encode_64(&p, req->r_pgid.pool);
- ceph_encode_32(&p, req->r_pgid.seed);
- put_unaligned_le64(1, req->r_request_attempts); /* FIXME */
- memcpy(req->r_request_reassert_version, &req->r_reassert_version,
- sizeof(req->r_reassert_version));
+ send_linger(lreq);
+}
- req->r_stamp = jiffies;
- list_move_tail(&req->r_req_lru_item, &osdc->req_lru);
+static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+ struct ceph_osd_linger_request *lookup_lreq;
- ceph_msg_get(req->r_request); /* send consumes a ref */
+ verify_osdc_wrlocked(osdc);
- req->r_sent = req->r_osd->o_incarnation;
+ lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks,
+ lreq->linger_id);
+ if (!lookup_lreq)
+ return;
- ceph_con_send(&req->r_osd->o_con, req->r_request);
+ WARN_ON(lookup_lreq != lreq);
+ erase_linger_mc(&osdc->linger_map_checks, lreq);
+ linger_put(lreq);
}
/*
- * Send any requests in the queue (req_unsent).
+ * @lreq has to be both registered and linked.
*/
-static void __send_queued(struct ceph_osd_client *osdc)
+static void __linger_cancel(struct ceph_osd_linger_request *lreq)
{
- struct ceph_osd_request *req, *tmp;
+ if (lreq->is_watch && lreq->ping_req->r_osd)
+ cancel_linger_request(lreq->ping_req);
+ if (lreq->reg_req->r_osd)
+ cancel_linger_request(lreq->reg_req);
+ cancel_linger_map_check(lreq);
+ unlink_linger(lreq->osd, lreq);
+ linger_unregister(lreq);
+}
+
+static void linger_cancel(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
- dout("__send_queued\n");
- list_for_each_entry_safe(req, tmp, &osdc->req_unsent, r_req_lru_item)
- __send_request(osdc, req);
+ down_write(&osdc->lock);
+ if (__linger_registered(lreq))
+ __linger_cancel(lreq);
+ up_write(&osdc->lock);
}
-/*
- * Caller should hold map_sem for read and request_mutex.
- */
-static int __ceph_osdc_start_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req,
- bool nofail)
-{
- int rc;
-
- __register_request(osdc, req);
- req->r_sent = 0;
- req->r_got_reply = 0;
- rc = __map_request(osdc, req, 0);
- if (rc < 0) {
- if (nofail) {
- dout("osdc_start_request failed map, "
- " will retry %lld\n", req->r_tid);
- rc = 0;
- } else {
- __unregister_request(osdc, req);
- }
- return rc;
+static void send_linger_map_check(struct ceph_osd_linger_request *lreq);
+
+static void check_linger_pool_dne(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+ struct ceph_osdmap *map = osdc->osdmap;
+
+ verify_osdc_wrlocked(osdc);
+ WARN_ON(!map->epoch);
+
+ if (lreq->register_gen) {
+ lreq->map_dne_bound = map->epoch;
+ dout("%s lreq %p linger_id %llu pool disappeared\n", __func__,
+ lreq, lreq->linger_id);
+ } else {
+ dout("%s lreq %p linger_id %llu map_dne_bound %u have %u\n",
+ __func__, lreq, lreq->linger_id, lreq->map_dne_bound,
+ map->epoch);
}
- if (req->r_osd == NULL) {
- dout("send_request %p no up osds in pg\n", req);
- ceph_monc_request_next_osdmap(&osdc->client->monc);
+ if (lreq->map_dne_bound) {
+ if (map->epoch >= lreq->map_dne_bound) {
+ /* we had a new enough map */
+ pr_info("linger_id %llu pool does not exist\n",
+ lreq->linger_id);
+ linger_reg_commit_complete(lreq, -ENOENT);
+ __linger_cancel(lreq);
+ }
} else {
- __send_queued(osdc);
+ send_linger_map_check(lreq);
}
+}
- return 0;
+static void linger_map_check_cb(struct ceph_mon_generic_request *greq)
+{
+ struct ceph_osd_client *osdc = &greq->monc->client->osdc;
+ struct ceph_osd_linger_request *lreq;
+ u64 linger_id = greq->private_data;
+
+ WARN_ON(greq->result || !greq->u.newest);
+
+ down_write(&osdc->lock);
+ lreq = lookup_linger_mc(&osdc->linger_map_checks, linger_id);
+ if (!lreq) {
+ dout("%s linger_id %llu dne\n", __func__, linger_id);
+ goto out_unlock;
+ }
+
+ dout("%s lreq %p linger_id %llu map_dne_bound %u newest %llu\n",
+ __func__, lreq, lreq->linger_id, lreq->map_dne_bound,
+ greq->u.newest);
+ if (!lreq->map_dne_bound)
+ lreq->map_dne_bound = greq->u.newest;
+ erase_linger_mc(&osdc->linger_map_checks, lreq);
+ check_linger_pool_dne(lreq);
+
+ linger_put(lreq);
+out_unlock:
+ up_write(&osdc->lock);
+}
+
+static void send_linger_map_check(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_client *osdc = lreq->osdc;
+ struct ceph_osd_linger_request *lookup_lreq;
+ int ret;
+
+ verify_osdc_wrlocked(osdc);
+
+ lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks,
+ lreq->linger_id);
+ if (lookup_lreq) {
+ WARN_ON(lookup_lreq != lreq);
+ return;
+ }
+
+ linger_get(lreq);
+ insert_linger_mc(&osdc->linger_map_checks, lreq);
+ ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap",
+ linger_map_check_cb, lreq->linger_id);
+ WARN_ON(ret);
+}
+
+static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq)
+{
+ int ret;
+
+ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
+ ret = wait_for_completion_interruptible(&lreq->reg_commit_wait);
+ return ret ?: lreq->reg_commit_error;
+}
+
+static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq)
+{
+ int ret;
+
+ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
+ ret = wait_for_completion_interruptible(&lreq->notify_finish_wait);
+ return ret ?: lreq->notify_finish_error;
}
/*
- * Timeout callback, called every N seconds when 1 or more osd
- * requests has been active for more than N seconds. When this
- * happens, we ping all OSDs with requests who have timed out to
- * ensure any communications channel reset is detected. Reset the
- * request timeouts another N seconds in the future as we go.
- * Reschedule the timeout event another N seconds in future (unless
- * there are no open requests).
+ * Timeout callback, called every N seconds. When 1 or more OSD
+ * requests has been active for more than N seconds, we send a keepalive
+ * (tag + timestamp) to its OSD to ensure any communications channel
+ * reset is detected.
*/
static void handle_timeout(struct work_struct *work)
{
struct ceph_osd_client *osdc =
container_of(work, struct ceph_osd_client, timeout_work.work);
struct ceph_options *opts = osdc->client->options;
- struct ceph_osd_request *req;
- struct ceph_osd *osd;
- struct list_head slow_osds;
- dout("timeout\n");
- down_read(&osdc->map_sem);
-
- ceph_monc_request_next_osdmap(&osdc->client->monc);
+ unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
+ LIST_HEAD(slow_osds);
+ struct rb_node *n, *p;
- mutex_lock(&osdc->request_mutex);
+ dout("%s osdc %p\n", __func__, osdc);
+ down_write(&osdc->lock);
/*
* ping osds that are a bit slow. this ensures that if there
* is a break in the TCP connection we will notice, and reopen
* a connection with that osd (from the fault callback).
*/
- INIT_LIST_HEAD(&slow_osds);
- list_for_each_entry(req, &osdc->req_lru, r_req_lru_item) {
- if (time_before(jiffies,
- req->r_stamp + opts->osd_keepalive_timeout))
- break;
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+ bool found = false;
+
+ for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+ struct ceph_osd_request *req =
+ rb_entry(p, struct ceph_osd_request, r_node);
+
+ if (time_before(req->r_stamp, cutoff)) {
+ dout(" req %p tid %llu on osd%d is laggy\n",
+ req, req->r_tid, osd->o_osd);
+ found = true;
+ }
+ }
+ for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
+ struct ceph_osd_linger_request *lreq =
+ rb_entry(p, struct ceph_osd_linger_request, node);
+
+ dout(" lreq %p linger_id %llu is served by osd%d\n",
+ lreq, lreq->linger_id, osd->o_osd);
+ found = true;
+
+ mutex_lock(&lreq->lock);
+ if (lreq->is_watch && lreq->committed && !lreq->last_error)
+ send_linger_ping(lreq);
+ mutex_unlock(&lreq->lock);
+ }
- osd = req->r_osd;
- BUG_ON(!osd);
- dout(" tid %llu is slow, will send keepalive on osd%d\n",
- req->r_tid, osd->o_osd);
- list_move_tail(&osd->o_keepalive_item, &slow_osds);
+ if (found)
+ list_move_tail(&osd->o_keepalive_item, &slow_osds);
}
+
+ if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
+ maybe_request_map(osdc);
+
while (!list_empty(&slow_osds)) {
- osd = list_entry(slow_osds.next, struct ceph_osd,
- o_keepalive_item);
+ struct ceph_osd *osd = list_first_entry(&slow_osds,
+ struct ceph_osd,
+ o_keepalive_item);
list_del_init(&osd->o_keepalive_item);
ceph_con_keepalive(&osd->o_con);
}
- __schedule_osd_timeout(osdc);
- __send_queued(osdc);
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
+ up_write(&osdc->lock);
+ schedule_delayed_work(&osdc->timeout_work,
+ osdc->client->options->osd_keepalive_timeout);
}
static void handle_osds_timeout(struct work_struct *work)
@@ -1663,12 +2541,20 @@ static void handle_osds_timeout(struct work_struct *work)
container_of(work, struct ceph_osd_client,
osds_timeout_work.work);
unsigned long delay = osdc->client->options->osd_idle_ttl / 4;
+ struct ceph_osd *osd, *nosd;
- dout("osds timeout\n");
- down_read(&osdc->map_sem);
- remove_old_osds(osdc);
- up_read(&osdc->map_sem);
+ dout("%s osdc %p\n", __func__, osdc);
+ down_write(&osdc->lock);
+ list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
+ if (time_before(jiffies, osd->lru_ttl))
+ break;
+ WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
+ WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
+ close_osd(osd);
+ }
+
+ up_write(&osdc->lock);
schedule_delayed_work(&osdc->osds_timeout_work,
round_jiffies_relative(delay));
}
@@ -1776,107 +2662,76 @@ e_inval:
goto out;
}
-static void complete_request(struct ceph_osd_request *req)
-{
- complete_all(&req->r_safe_completion); /* fsync waiter */
-}
+struct MOSDOpReply {
+ struct ceph_pg pgid;
+ u64 flags;
+ int result;
+ u32 epoch;
+ int num_ops;
+ u32 outdata_len[CEPH_OSD_MAX_OPS];
+ s32 rval[CEPH_OSD_MAX_OPS];
+ int retry_attempt;
+ struct ceph_eversion replay_version;
+ u64 user_version;
+ struct ceph_request_redirect redirect;
+};
-/*
- * handle osd op reply. either call the callback if it is specified,
- * or do the completion to wake up the waiting thread.
- */
-static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg)
+static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m)
{
- void *p, *end;
- struct ceph_osd_request *req;
- struct ceph_request_redirect redir;
- u64 tid;
- int object_len;
- unsigned int numops;
- int payload_len, flags;
- s32 result;
- s32 retry_attempt;
- struct ceph_pg pg;
- int err;
- u32 reassert_epoch;
- u64 reassert_version;
- u32 osdmap_epoch;
- int already_completed;
- u32 bytes;
+ void *p = msg->front.iov_base;
+ void *const end = p + msg->front.iov_len;
+ u16 version = le16_to_cpu(msg->hdr.version);
+ struct ceph_eversion bad_replay_version;
u8 decode_redir;
- unsigned int i;
-
- tid = le64_to_cpu(msg->hdr.tid);
- dout("handle_reply %p tid %llu\n", msg, tid);
+ u32 len;
+ int ret;
+ int i;
- p = msg->front.iov_base;
- end = p + msg->front.iov_len;
+ ceph_decode_32_safe(&p, end, len, e_inval);
+ ceph_decode_need(&p, end, len, e_inval);
+ p += len; /* skip oid */
- ceph_decode_need(&p, end, 4, bad);
- object_len = ceph_decode_32(&p);
- ceph_decode_need(&p, end, object_len, bad);
- p += object_len;
+ ret = ceph_decode_pgid(&p, end, &m->pgid);
+ if (ret)
+ return ret;
- err = ceph_decode_pgid(&p, end, &pg);
- if (err)
- goto bad;
+ ceph_decode_64_safe(&p, end, m->flags, e_inval);
+ ceph_decode_32_safe(&p, end, m->result, e_inval);
+ ceph_decode_need(&p, end, sizeof(bad_replay_version), e_inval);
+ memcpy(&bad_replay_version, p, sizeof(bad_replay_version));
+ p += sizeof(bad_replay_version);
+ ceph_decode_32_safe(&p, end, m->epoch, e_inval);
- ceph_decode_need(&p, end, 8 + 4 + 4 + 8 + 4, bad);
- flags = ceph_decode_64(&p);
- result = ceph_decode_32(&p);
- reassert_epoch = ceph_decode_32(&p);
- reassert_version = ceph_decode_64(&p);
- osdmap_epoch = ceph_decode_32(&p);
-
- /* lookup */
- down_read(&osdc->map_sem);
- mutex_lock(&osdc->request_mutex);
- req = __lookup_request(osdc, tid);
- if (req == NULL) {
- dout("handle_reply tid %llu dne\n", tid);
- goto bad_mutex;
- }
- ceph_osdc_get_request(req);
+ ceph_decode_32_safe(&p, end, m->num_ops, e_inval);
+ if (m->num_ops > ARRAY_SIZE(m->outdata_len))
+ goto e_inval;
- dout("handle_reply %p tid %llu req %p result %d\n", msg, tid,
- req, result);
-
- ceph_decode_need(&p, end, 4, bad_put);
- numops = ceph_decode_32(&p);
- if (numops > CEPH_OSD_MAX_OPS)
- goto bad_put;
- if (numops != req->r_num_ops)
- goto bad_put;
- payload_len = 0;
- ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad_put);
- for (i = 0; i < numops; i++) {
+ ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op),
+ e_inval);
+ for (i = 0; i < m->num_ops; i++) {
struct ceph_osd_op *op = p;
- int len;
- len = le32_to_cpu(op->payload_len);
- req->r_ops[i].outdata_len = len;
- dout(" op %d has %d bytes\n", i, len);
- payload_len += len;
+ m->outdata_len[i] = le32_to_cpu(op->payload_len);
p += sizeof(*op);
}
- bytes = le32_to_cpu(msg->hdr.data_len);
- if (payload_len != bytes) {
- pr_warn("sum of op payload lens %d != data_len %d\n",
- payload_len, bytes);
- goto bad_put;
- }
- ceph_decode_need(&p, end, 4 + numops * 4, bad_put);
- retry_attempt = ceph_decode_32(&p);
- for (i = 0; i < numops; i++)
- req->r_ops[i].rval = ceph_decode_32(&p);
+ ceph_decode_32_safe(&p, end, m->retry_attempt, e_inval);
+ for (i = 0; i < m->num_ops; i++)
+ ceph_decode_32_safe(&p, end, m->rval[i], e_inval);
- if (le16_to_cpu(msg->hdr.version) >= 6) {
- p += 8 + 4; /* skip replay_version */
- p += 8; /* skip user_version */
+ if (version >= 5) {
+ ceph_decode_need(&p, end, sizeof(m->replay_version), e_inval);
+ memcpy(&m->replay_version, p, sizeof(m->replay_version));
+ p += sizeof(m->replay_version);
+ ceph_decode_64_safe(&p, end, m->user_version, e_inval);
+ } else {
+ m->replay_version = bad_replay_version; /* struct */
+ m->user_version = le64_to_cpu(m->replay_version.version);
+ }
- if (le16_to_cpu(msg->hdr.version) >= 7)
- ceph_decode_8_safe(&p, end, decode_redir, bad_put);
+ if (version >= 6) {
+ if (version >= 7)
+ ceph_decode_8_safe(&p, end, decode_redir, e_inval);
else
decode_redir = 1;
} else {
@@ -1884,228 +2739,410 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg)
}
if (decode_redir) {
- err = ceph_redirect_decode(&p, end, &redir);
- if (err)
- goto bad_put;
+ ret = ceph_redirect_decode(&p, end, &m->redirect);
+ if (ret)
+ return ret;
} else {
- redir.oloc.pool = -1;
+ ceph_oloc_init(&m->redirect.oloc);
}
- if (redir.oloc.pool != -1) {
- dout("redirect pool %lld\n", redir.oloc.pool);
+ return 0;
- __unregister_request(osdc, req);
+e_inval:
+ return -EINVAL;
+}
- req->r_target_oloc = redir.oloc; /* struct */
+/*
+ * We are done with @req if
+ * - @m is a safe reply, or
+ * - @m is an unsafe reply and we didn't want a safe one
+ */
+static bool done_request(const struct ceph_osd_request *req,
+ const struct MOSDOpReply *m)
+{
+ return (m->result < 0 ||
+ (m->flags & CEPH_OSD_FLAG_ONDISK) ||
+ !(req->r_flags & CEPH_OSD_FLAG_ONDISK));
+}
- /*
- * Start redirect requests with nofail=true. If
- * mapping fails, request will end up on the notarget
- * list, waiting for the new osdmap (which can take
- * a while), even though the original request mapped
- * successfully. In the future we might want to follow
- * original request's nofail setting here.
- */
- err = __ceph_osdc_start_request(osdc, req, true);
- BUG_ON(err);
+/*
+ * handle osd op reply. either call the callback if it is specified,
+ * or do the completion to wake up the waiting thread.
+ *
+ * ->r_unsafe_callback is set? yes no
+ *
+ * first reply is OK (needed r_cb/r_completion, r_cb/r_completion,
+ * any or needed/got safe) r_safe_completion r_safe_completion
+ *
+ * first reply is unsafe r_unsafe_cb(true) (nothing)
+ *
+ * when we get the safe reply r_unsafe_cb(false), r_cb/r_completion,
+ * r_safe_completion r_safe_completion
+ */
+static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
+{
+ struct ceph_osd_client *osdc = osd->o_osdc;
+ struct ceph_osd_request *req;
+ struct MOSDOpReply m;
+ u64 tid = le64_to_cpu(msg->hdr.tid);
+ u32 data_len = 0;
+ bool already_acked;
+ int ret;
+ int i;
- goto out_unlock;
- }
+ dout("%s msg %p tid %llu\n", __func__, msg, tid);
- already_completed = req->r_got_reply;
- if (!req->r_got_reply) {
- req->r_result = result;
- dout("handle_reply result %d bytes %d\n", req->r_result,
- bytes);
- if (req->r_result == 0)
- req->r_result = bytes;
+ down_read(&osdc->lock);
+ if (!osd_registered(osd)) {
+ dout("%s osd%d unknown\n", __func__, osd->o_osd);
+ goto out_unlock_osdc;
+ }
+ WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num));
- /* in case this is a write and we need to replay, */
- req->r_reassert_version.epoch = cpu_to_le32(reassert_epoch);
- req->r_reassert_version.version = cpu_to_le64(reassert_version);
+ mutex_lock(&osd->lock);
+ req = lookup_request(&osd->o_requests, tid);
+ if (!req) {
+ dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid);
+ goto out_unlock_session;
+ }
- req->r_got_reply = 1;
- } else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) {
- dout("handle_reply tid %llu dup ack\n", tid);
- goto out_unlock;
+ ret = decode_MOSDOpReply(msg, &m);
+ if (ret) {
+ pr_err("failed to decode MOSDOpReply for tid %llu: %d\n",
+ req->r_tid, ret);
+ ceph_msg_dump(msg);
+ goto fail_request;
+ }
+ dout("%s req %p tid %llu flags 0x%llx pgid %llu.%x epoch %u attempt %d v %u'%llu uv %llu\n",
+ __func__, req, req->r_tid, m.flags, m.pgid.pool, m.pgid.seed,
+ m.epoch, m.retry_attempt, le32_to_cpu(m.replay_version.epoch),
+ le64_to_cpu(m.replay_version.version), m.user_version);
+
+ if (m.retry_attempt >= 0) {
+ if (m.retry_attempt != req->r_attempts - 1) {
+ dout("req %p tid %llu retry_attempt %d != %d, ignoring\n",
+ req, req->r_tid, m.retry_attempt,
+ req->r_attempts - 1);
+ goto out_unlock_session;
+ }
+ } else {
+ WARN_ON(1); /* MOSDOpReply v4 is assumed */
}
- dout("handle_reply tid %llu flags %d\n", tid, flags);
+ if (!ceph_oloc_empty(&m.redirect.oloc)) {
+ dout("req %p tid %llu redirect pool %lld\n", req, req->r_tid,
+ m.redirect.oloc.pool);
+ unlink_request(osd, req);
+ mutex_unlock(&osd->lock);
+
+ ceph_oloc_copy(&req->r_t.target_oloc, &m.redirect.oloc);
+ req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
+ req->r_tid = 0;
+ __submit_request(req, false);
+ goto out_unlock_osdc;
+ }
- if (req->r_linger && (flags & CEPH_OSD_FLAG_ONDISK))
- __register_linger_request(osdc, req);
+ if (m.num_ops != req->r_num_ops) {
+ pr_err("num_ops %d != %d for tid %llu\n", m.num_ops,
+ req->r_num_ops, req->r_tid);
+ goto fail_request;
+ }
+ for (i = 0; i < req->r_num_ops; i++) {
+ dout(" req %p tid %llu op %d rval %d len %u\n", req,
+ req->r_tid, i, m.rval[i], m.outdata_len[i]);
+ req->r_ops[i].rval = m.rval[i];
+ req->r_ops[i].outdata_len = m.outdata_len[i];
+ data_len += m.outdata_len[i];
+ }
+ if (data_len != le32_to_cpu(msg->hdr.data_len)) {
+ pr_err("sum of lens %u != %u for tid %llu\n", data_len,
+ le32_to_cpu(msg->hdr.data_len), req->r_tid);
+ goto fail_request;
+ }
+ dout("%s req %p tid %llu acked %d result %d data_len %u\n", __func__,
+ req, req->r_tid, req->r_got_reply, m.result, data_len);
+
+ already_acked = req->r_got_reply;
+ if (!already_acked) {
+ req->r_result = m.result ?: data_len;
+ req->r_replay_version = m.replay_version; /* struct */
+ req->r_got_reply = true;
+ } else if (!(m.flags & CEPH_OSD_FLAG_ONDISK)) {
+ dout("req %p tid %llu dup ack\n", req, req->r_tid);
+ goto out_unlock_session;
+ }
- /* either this is a read, or we got the safe response */
- if (result < 0 ||
- (flags & CEPH_OSD_FLAG_ONDISK) ||
- ((flags & CEPH_OSD_FLAG_WRITE) == 0))
- __unregister_request(osdc, req);
+ if (done_request(req, &m)) {
+ __finish_request(req);
+ if (req->r_linger) {
+ WARN_ON(req->r_unsafe_callback);
+ dout("req %p tid %llu cb (locked)\n", req, req->r_tid);
+ __complete_request(req);
+ }
+ }
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
+ mutex_unlock(&osd->lock);
+ up_read(&osdc->lock);
- if (!already_completed) {
- if (req->r_unsafe_callback &&
- result >= 0 && !(flags & CEPH_OSD_FLAG_ONDISK))
+ if (done_request(req, &m)) {
+ if (already_acked && req->r_unsafe_callback) {
+ dout("req %p tid %llu safe-cb\n", req, req->r_tid);
+ req->r_unsafe_callback(req, false);
+ } else if (!req->r_linger) {
+ dout("req %p tid %llu cb\n", req, req->r_tid);
+ __complete_request(req);
+ }
+ if (m.flags & CEPH_OSD_FLAG_ONDISK)
+ complete_all(&req->r_safe_completion);
+ ceph_osdc_put_request(req);
+ } else {
+ if (req->r_unsafe_callback) {
+ dout("req %p tid %llu unsafe-cb\n", req, req->r_tid);
req->r_unsafe_callback(req, true);
- if (req->r_callback)
- req->r_callback(req, msg);
- else
- complete_all(&req->r_completion);
+ } else {
+ WARN_ON(1);
+ }
}
- if (flags & CEPH_OSD_FLAG_ONDISK) {
- if (req->r_unsafe_callback && already_completed)
- req->r_unsafe_callback(req, false);
- complete_request(req);
+ return;
+
+fail_request:
+ complete_request(req, -EIO);
+out_unlock_session:
+ mutex_unlock(&osd->lock);
+out_unlock_osdc:
+ up_read(&osdc->lock);
+}
+
+static void set_pool_was_full(struct ceph_osd_client *osdc)
+{
+ struct rb_node *n;
+
+ for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) {
+ struct ceph_pg_pool_info *pi =
+ rb_entry(n, struct ceph_pg_pool_info, node);
+
+ pi->was_full = __pool_full(pi);
}
+}
-out:
- dout("req=%p req->r_linger=%d\n", req, req->r_linger);
- ceph_osdc_put_request(req);
- return;
-out_unlock:
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
- goto out;
+static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id)
+{
+ struct ceph_pg_pool_info *pi;
-bad_put:
- req->r_result = -EIO;
- __unregister_request(osdc, req);
- if (req->r_callback)
- req->r_callback(req, msg);
- else
- complete_all(&req->r_completion);
- complete_request(req);
- ceph_osdc_put_request(req);
-bad_mutex:
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
-bad:
- pr_err("corrupt osd_op_reply got %d %d\n",
- (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len));
- ceph_msg_dump(msg);
+ pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id);
+ if (!pi)
+ return false;
+
+ return pi->was_full && !__pool_full(pi);
}
-static void reset_changed_osds(struct ceph_osd_client *osdc)
+static enum calc_target_result
+recalc_linger_target(struct ceph_osd_linger_request *lreq)
{
- struct rb_node *p, *n;
+ struct ceph_osd_client *osdc = lreq->osdc;
+ enum calc_target_result ct_res;
- dout("%s %p\n", __func__, osdc);
- for (p = rb_first(&osdc->osds); p; p = n) {
- struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node);
+ ct_res = calc_target(osdc, &lreq->t, &lreq->last_force_resend, true);
+ if (ct_res == CALC_TARGET_NEED_RESEND) {
+ struct ceph_osd *osd;
- n = rb_next(p);
- if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) ||
- memcmp(&osd->o_con.peer_addr,
- ceph_osd_addr(osdc->osdmap,
- osd->o_osd),
- sizeof(struct ceph_entity_addr)) != 0)
- __reset_osd(osdc, osd);
+ osd = lookup_create_osd(osdc, lreq->t.osd, true);
+ if (osd != lreq->osd) {
+ unlink_linger(lreq->osd, lreq);
+ link_linger(osd, lreq);
+ }
}
+
+ return ct_res;
}
/*
- * Requeue requests whose mapping to an OSD has changed. If requests map to
- * no osd, request a new map.
- *
- * Caller should hold map_sem for read.
+ * Requeue requests whose mapping to an OSD has changed.
*/
-static void kick_requests(struct ceph_osd_client *osdc, bool force_resend,
- bool force_resend_writes)
+static void scan_requests(struct ceph_osd *osd,
+ bool force_resend,
+ bool cleared_full,
+ bool check_pool_cleared_full,
+ struct rb_root *need_resend,
+ struct list_head *need_resend_linger)
{
- struct ceph_osd_request *req, *nreq;
- struct rb_node *p;
- int needmap = 0;
- int err;
- bool force_resend_req;
+ struct ceph_osd_client *osdc = osd->o_osdc;
+ struct rb_node *n;
+ bool force_resend_writes;
+
+ for (n = rb_first(&osd->o_linger_requests); n; ) {
+ struct ceph_osd_linger_request *lreq =
+ rb_entry(n, struct ceph_osd_linger_request, node);
+ enum calc_target_result ct_res;
+
+ n = rb_next(n); /* recalc_linger_target() */
+
+ dout("%s lreq %p linger_id %llu\n", __func__, lreq,
+ lreq->linger_id);
+ ct_res = recalc_linger_target(lreq);
+ switch (ct_res) {
+ case CALC_TARGET_NO_ACTION:
+ force_resend_writes = cleared_full ||
+ (check_pool_cleared_full &&
+ pool_cleared_full(osdc, lreq->t.base_oloc.pool));
+ if (!force_resend && !force_resend_writes)
+ break;
+
+ /* fall through */
+ case CALC_TARGET_NEED_RESEND:
+ cancel_linger_map_check(lreq);
+ /*
+ * scan_requests() for the previous epoch(s)
+ * may have already added it to the list, since
+ * it's not unlinked here.
+ */
+ if (list_empty(&lreq->scan_item))
+ list_add_tail(&lreq->scan_item, need_resend_linger);
+ break;
+ case CALC_TARGET_POOL_DNE:
+ check_linger_pool_dne(lreq);
+ break;
+ }
+ }
- dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "",
- force_resend_writes ? " (force resend writes)" : "");
- mutex_lock(&osdc->request_mutex);
- for (p = rb_first(&osdc->requests); p; ) {
- req = rb_entry(p, struct ceph_osd_request, r_node);
- p = rb_next(p);
+ for (n = rb_first(&osd->o_requests); n; ) {
+ struct ceph_osd_request *req =
+ rb_entry(n, struct ceph_osd_request, r_node);
+ enum calc_target_result ct_res;
+
+ n = rb_next(n); /* unlink_request(), check_pool_dne() */
+
+ dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
+ ct_res = calc_target(osdc, &req->r_t,
+ &req->r_last_force_resend, false);
+ switch (ct_res) {
+ case CALC_TARGET_NO_ACTION:
+ force_resend_writes = cleared_full ||
+ (check_pool_cleared_full &&
+ pool_cleared_full(osdc, req->r_t.base_oloc.pool));
+ if (!force_resend &&
+ (!(req->r_flags & CEPH_OSD_FLAG_WRITE) ||
+ !force_resend_writes))
+ break;
+
+ /* fall through */
+ case CALC_TARGET_NEED_RESEND:
+ cancel_map_check(req);
+ unlink_request(osd, req);
+ insert_request(need_resend, req);
+ break;
+ case CALC_TARGET_POOL_DNE:
+ check_pool_dne(req);
+ break;
+ }
+ }
+}
+static int handle_one_map(struct ceph_osd_client *osdc,
+ void *p, void *end, bool incremental,
+ struct rb_root *need_resend,
+ struct list_head *need_resend_linger)
+{
+ struct ceph_osdmap *newmap;
+ struct rb_node *n;
+ bool skipped_map = false;
+ bool was_full;
+
+ was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
+ set_pool_was_full(osdc);
+
+ if (incremental)
+ newmap = osdmap_apply_incremental(&p, end, osdc->osdmap);
+ else
+ newmap = ceph_osdmap_decode(&p, end);
+ if (IS_ERR(newmap))
+ return PTR_ERR(newmap);
+
+ if (newmap != osdc->osdmap) {
/*
- * For linger requests that have not yet been
- * registered, move them to the linger list; they'll
- * be sent to the osd in the loop below. Unregister
- * the request before re-registering it as a linger
- * request to ensure the __map_request() below
- * will decide it needs to be sent.
+ * Preserve ->was_full before destroying the old map.
+ * For pools that weren't in the old map, ->was_full
+ * should be false.
*/
- if (req->r_linger && list_empty(&req->r_linger_item)) {
- dout("%p tid %llu restart on osd%d\n",
- req, req->r_tid,
- req->r_osd ? req->r_osd->o_osd : -1);
- ceph_osdc_get_request(req);
- __unregister_request(osdc, req);
- __register_linger_request(osdc, req);
- ceph_osdc_put_request(req);
- continue;
+ for (n = rb_first(&newmap->pg_pools); n; n = rb_next(n)) {
+ struct ceph_pg_pool_info *pi =
+ rb_entry(n, struct ceph_pg_pool_info, node);
+ struct ceph_pg_pool_info *old_pi;
+
+ old_pi = ceph_pg_pool_by_id(osdc->osdmap, pi->id);
+ if (old_pi)
+ pi->was_full = old_pi->was_full;
+ else
+ WARN_ON(pi->was_full);
}
- force_resend_req = force_resend ||
- (force_resend_writes &&
- req->r_flags & CEPH_OSD_FLAG_WRITE);
- err = __map_request(osdc, req, force_resend_req);
- if (err < 0)
- continue; /* error */
- if (req->r_osd == NULL) {
- dout("%p tid %llu maps to no osd\n", req, req->r_tid);
- needmap++; /* request a newer map */
- } else if (err > 0) {
- if (!req->r_linger) {
- dout("%p tid %llu requeued on osd%d\n", req,
- req->r_tid,
- req->r_osd ? req->r_osd->o_osd : -1);
- req->r_flags |= CEPH_OSD_FLAG_RETRY;
- }
+ if (osdc->osdmap->epoch &&
+ osdc->osdmap->epoch + 1 < newmap->epoch) {
+ WARN_ON(incremental);
+ skipped_map = true;
}
+
+ ceph_osdmap_destroy(osdc->osdmap);
+ osdc->osdmap = newmap;
}
- list_for_each_entry_safe(req, nreq, &osdc->req_linger,
- r_linger_item) {
- dout("linger req=%p req->r_osd=%p\n", req, req->r_osd);
-
- err = __map_request(osdc, req,
- force_resend || force_resend_writes);
- dout("__map_request returned %d\n", err);
- if (err < 0)
- continue; /* hrm! */
- if (req->r_osd == NULL || err > 0) {
- if (req->r_osd == NULL) {
- dout("lingering %p tid %llu maps to no osd\n",
- req, req->r_tid);
- /*
- * A homeless lingering request makes
- * no sense, as it's job is to keep
- * a particular OSD connection open.
- * Request a newer map and kick the
- * request, knowing that it won't be
- * resent until we actually get a map
- * that can tell us where to send it.
- */
- needmap++;
- }
+ was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
+ scan_requests(&osdc->homeless_osd, skipped_map, was_full, true,
+ need_resend, need_resend_linger);
+
+ for (n = rb_first(&osdc->osds); n; ) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+
+ n = rb_next(n); /* close_osd() */
+
+ scan_requests(osd, skipped_map, was_full, true, need_resend,
+ need_resend_linger);
+ if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) ||
+ memcmp(&osd->o_con.peer_addr,
+ ceph_osd_addr(osdc->osdmap, osd->o_osd),
+ sizeof(struct ceph_entity_addr)))
+ close_osd(osd);
+ }
- dout("kicking lingering %p tid %llu osd%d\n", req,
- req->r_tid, req->r_osd ? req->r_osd->o_osd : -1);
- __register_request(osdc, req);
- __unregister_linger_request(osdc, req);
+ return 0;
+}
+
+static void kick_requests(struct ceph_osd_client *osdc,
+ struct rb_root *need_resend,
+ struct list_head *need_resend_linger)
+{
+ struct ceph_osd_linger_request *lreq, *nlreq;
+ struct rb_node *n;
+
+ for (n = rb_first(need_resend); n; ) {
+ struct ceph_osd_request *req =
+ rb_entry(n, struct ceph_osd_request, r_node);
+ struct ceph_osd *osd;
+
+ n = rb_next(n);
+ erase_request(need_resend, req); /* before link_request() */
+
+ WARN_ON(req->r_osd);
+ calc_target(osdc, &req->r_t, NULL, false);
+ osd = lookup_create_osd(osdc, req->r_t.osd, true);
+ link_request(osd, req);
+ if (!req->r_linger) {
+ if (!osd_homeless(osd) && !req->r_t.paused)
+ send_request(req);
+ } else {
+ cancel_linger_request(req);
}
}
- reset_changed_osds(osdc);
- mutex_unlock(&osdc->request_mutex);
- if (needmap) {
- dout("%d requests for down osds, need new map\n", needmap);
- ceph_monc_request_next_osdmap(&osdc->client->monc);
+ list_for_each_entry_safe(lreq, nlreq, need_resend_linger, scan_item) {
+ if (!osd_homeless(lreq->osd))
+ send_linger(lreq);
+
+ list_del_init(&lreq->scan_item);
}
}
-
/*
* Process updated osd map.
*
@@ -2115,27 +3152,31 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend,
*/
void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
{
- void *p, *end, *next;
+ void *p = msg->front.iov_base;
+ void *const end = p + msg->front.iov_len;
u32 nr_maps, maplen;
u32 epoch;
- struct ceph_osdmap *newmap = NULL, *oldmap;
- int err;
struct ceph_fsid fsid;
- bool was_full;
+ struct rb_root need_resend = RB_ROOT;
+ LIST_HEAD(need_resend_linger);
+ bool handled_incremental = false;
+ bool was_pauserd, was_pausewr;
+ bool pauserd, pausewr;
+ int err;
- dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0);
- p = msg->front.iov_base;
- end = p + msg->front.iov_len;
+ dout("%s have %u\n", __func__, osdc->osdmap->epoch);
+ down_write(&osdc->lock);
/* verify fsid */
ceph_decode_need(&p, end, sizeof(fsid), bad);
ceph_decode_copy(&p, &fsid, sizeof(fsid));
if (ceph_check_fsid(osdc->client, &fsid) < 0)
- return;
-
- down_write(&osdc->map_sem);
+ goto bad;
- was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+ was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+ was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ have_pool_full(osdc);
/* incremental maps */
ceph_decode_32_safe(&p, end, nr_maps, bad);
@@ -2145,34 +3186,23 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
epoch = ceph_decode_32(&p);
maplen = ceph_decode_32(&p);
ceph_decode_need(&p, end, maplen, bad);
- next = p + maplen;
- if (osdc->osdmap && osdc->osdmap->epoch+1 == epoch) {
+ if (osdc->osdmap->epoch &&
+ osdc->osdmap->epoch + 1 == epoch) {
dout("applying incremental map %u len %d\n",
epoch, maplen);
- newmap = osdmap_apply_incremental(&p, next,
- osdc->osdmap,
- &osdc->client->msgr);
- if (IS_ERR(newmap)) {
- err = PTR_ERR(newmap);
+ err = handle_one_map(osdc, p, p + maplen, true,
+ &need_resend, &need_resend_linger);
+ if (err)
goto bad;
- }
- BUG_ON(!newmap);
- if (newmap != osdc->osdmap) {
- ceph_osdmap_destroy(osdc->osdmap);
- osdc->osdmap = newmap;
- }
- was_full = was_full ||
- ceph_osdmap_flag(osdc->osdmap,
- CEPH_OSDMAP_FULL);
- kick_requests(osdc, 0, was_full);
+ handled_incremental = true;
} else {
dout("ignoring incremental map %u len %d\n",
epoch, maplen);
}
- p = next;
+ p += maplen;
nr_maps--;
}
- if (newmap)
+ if (handled_incremental)
goto done;
/* full maps */
@@ -2186,455 +3216,647 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
if (nr_maps > 1) {
dout("skipping non-latest full map %u len %d\n",
epoch, maplen);
- } else if (osdc->osdmap && osdc->osdmap->epoch >= epoch) {
+ } else if (osdc->osdmap->epoch >= epoch) {
dout("skipping full map %u len %d, "
"older than our %u\n", epoch, maplen,
osdc->osdmap->epoch);
} else {
- int skipped_map = 0;
-
dout("taking full map %u len %d\n", epoch, maplen);
- newmap = ceph_osdmap_decode(&p, p+maplen);
- if (IS_ERR(newmap)) {
- err = PTR_ERR(newmap);
+ err = handle_one_map(osdc, p, p + maplen, false,
+ &need_resend, &need_resend_linger);
+ if (err)
goto bad;
- }
- BUG_ON(!newmap);
- oldmap = osdc->osdmap;
- osdc->osdmap = newmap;
- if (oldmap) {
- if (oldmap->epoch + 1 < newmap->epoch)
- skipped_map = 1;
- ceph_osdmap_destroy(oldmap);
- }
- was_full = was_full ||
- ceph_osdmap_flag(osdc->osdmap,
- CEPH_OSDMAP_FULL);
- kick_requests(osdc, skipped_map, was_full);
}
p += maplen;
nr_maps--;
}
- if (!osdc->osdmap)
- goto bad;
done:
- downgrade_write(&osdc->map_sem);
- ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
- osdc->osdmap->epoch);
-
/*
* subscribe to subsequent osdmap updates if full to ensure
* we find out when we are no longer full and stop returning
* ENOSPC.
*/
- if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
- ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
- ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR))
- ceph_monc_request_next_osdmap(&osdc->client->monc);
-
- mutex_lock(&osdc->request_mutex);
- __send_queued(osdc);
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
+ pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+ pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ have_pool_full(osdc);
+ if (was_pauserd || was_pausewr || pauserd || pausewr)
+ maybe_request_map(osdc);
+
+ kick_requests(osdc, &need_resend, &need_resend_linger);
+
+ ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
+ osdc->osdmap->epoch);
+ up_write(&osdc->lock);
wake_up_all(&osdc->client->auth_wq);
return;
bad:
pr_err("osdc handle_map corrupt msg\n");
ceph_msg_dump(msg);
- up_write(&osdc->map_sem);
+ up_write(&osdc->lock);
}
/*
- * watch/notify callback event infrastructure
- *
- * These callbacks are used both for watch and notify operations.
+ * Resubmit requests pending on the given osd.
*/
-static void __release_event(struct kref *kref)
+static void kick_osd_requests(struct ceph_osd *osd)
{
- struct ceph_osd_event *event =
- container_of(kref, struct ceph_osd_event, kref);
+ struct rb_node *n;
- dout("__release_event %p\n", event);
- kfree(event);
-}
+ for (n = rb_first(&osd->o_requests); n; ) {
+ struct ceph_osd_request *req =
+ rb_entry(n, struct ceph_osd_request, r_node);
-static void get_event(struct ceph_osd_event *event)
-{
- kref_get(&event->kref);
-}
+ n = rb_next(n); /* cancel_linger_request() */
-void ceph_osdc_put_event(struct ceph_osd_event *event)
-{
- kref_put(&event->kref, __release_event);
+ if (!req->r_linger) {
+ if (!req->r_t.paused)
+ send_request(req);
+ } else {
+ cancel_linger_request(req);
+ }
+ }
+ for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) {
+ struct ceph_osd_linger_request *lreq =
+ rb_entry(n, struct ceph_osd_linger_request, node);
+
+ send_linger(lreq);
+ }
}
-EXPORT_SYMBOL(ceph_osdc_put_event);
-static void __insert_event(struct ceph_osd_client *osdc,
- struct ceph_osd_event *new)
+/*
+ * If the osd connection drops, we need to resubmit all requests.
+ */
+static void osd_fault(struct ceph_connection *con)
{
- struct rb_node **p = &osdc->event_tree.rb_node;
- struct rb_node *parent = NULL;
- struct ceph_osd_event *event = NULL;
+ struct ceph_osd *osd = con->private;
+ struct ceph_osd_client *osdc = osd->o_osdc;
- while (*p) {
- parent = *p;
- event = rb_entry(parent, struct ceph_osd_event, node);
- if (new->cookie < event->cookie)
- p = &(*p)->rb_left;
- else if (new->cookie > event->cookie)
- p = &(*p)->rb_right;
- else
- BUG();
+ dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
+
+ down_write(&osdc->lock);
+ if (!osd_registered(osd)) {
+ dout("%s osd%d unknown\n", __func__, osd->o_osd);
+ goto out_unlock;
}
- rb_link_node(&new->node, parent, p);
- rb_insert_color(&new->node, &osdc->event_tree);
+ if (!reopen_osd(osd))
+ kick_osd_requests(osd);
+ maybe_request_map(osdc);
+
+out_unlock:
+ up_write(&osdc->lock);
}
-static struct ceph_osd_event *__find_event(struct ceph_osd_client *osdc,
- u64 cookie)
+/*
+ * Process osd watch notifications
+ */
+static void handle_watch_notify(struct ceph_osd_client *osdc,
+ struct ceph_msg *msg)
{
- struct rb_node **p = &osdc->event_tree.rb_node;
- struct rb_node *parent = NULL;
- struct ceph_osd_event *event = NULL;
+ void *p = msg->front.iov_base;
+ void *const end = p + msg->front.iov_len;
+ struct ceph_osd_linger_request *lreq;
+ struct linger_work *lwork;
+ u8 proto_ver, opcode;
+ u64 cookie, notify_id;
+ u64 notifier_id = 0;
+ s32 return_code = 0;
+ void *payload = NULL;
+ u32 payload_len = 0;
- while (*p) {
- parent = *p;
- event = rb_entry(parent, struct ceph_osd_event, node);
- if (cookie < event->cookie)
- p = &(*p)->rb_left;
- else if (cookie > event->cookie)
- p = &(*p)->rb_right;
- else
- return event;
+ ceph_decode_8_safe(&p, end, proto_ver, bad);
+ ceph_decode_8_safe(&p, end, opcode, bad);
+ ceph_decode_64_safe(&p, end, cookie, bad);
+ p += 8; /* skip ver */
+ ceph_decode_64_safe(&p, end, notify_id, bad);
+
+ if (proto_ver >= 1) {
+ ceph_decode_32_safe(&p, end, payload_len, bad);
+ ceph_decode_need(&p, end, payload_len, bad);
+ payload = p;
+ p += payload_len;
}
- return NULL;
-}
-static void __remove_event(struct ceph_osd_event *event)
-{
- struct ceph_osd_client *osdc = event->osdc;
+ if (le16_to_cpu(msg->hdr.version) >= 2)
+ ceph_decode_32_safe(&p, end, return_code, bad);
+
+ if (le16_to_cpu(msg->hdr.version) >= 3)
+ ceph_decode_64_safe(&p, end, notifier_id, bad);
- if (!RB_EMPTY_NODE(&event->node)) {
- dout("__remove_event removed %p\n", event);
- rb_erase(&event->node, &osdc->event_tree);
- ceph_osdc_put_event(event);
+ down_read(&osdc->lock);
+ lreq = lookup_linger_osdc(&osdc->linger_requests, cookie);
+ if (!lreq) {
+ dout("%s opcode %d cookie %llu dne\n", __func__, opcode,
+ cookie);
+ goto out_unlock_osdc;
+ }
+
+ mutex_lock(&lreq->lock);
+ dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__,
+ opcode, cookie, lreq, lreq->is_watch);
+ if (opcode == CEPH_WATCH_EVENT_DISCONNECT) {
+ if (!lreq->last_error) {
+ lreq->last_error = -ENOTCONN;
+ queue_watch_error(lreq);
+ }
+ } else if (!lreq->is_watch) {
+ /* CEPH_WATCH_EVENT_NOTIFY_COMPLETE */
+ if (lreq->notify_id && lreq->notify_id != notify_id) {
+ dout("lreq %p notify_id %llu != %llu, ignoring\n", lreq,
+ lreq->notify_id, notify_id);
+ } else if (!completion_done(&lreq->notify_finish_wait)) {
+ struct ceph_msg_data *data =
+ list_first_entry_or_null(&msg->data,
+ struct ceph_msg_data,
+ links);
+
+ if (data) {
+ if (lreq->preply_pages) {
+ WARN_ON(data->type !=
+ CEPH_MSG_DATA_PAGES);
+ *lreq->preply_pages = data->pages;
+ *lreq->preply_len = data->length;
+ } else {
+ ceph_release_page_vector(data->pages,
+ calc_pages_for(0, data->length));
+ }
+ }
+ lreq->notify_finish_error = return_code;
+ complete_all(&lreq->notify_finish_wait);
+ }
} else {
- dout("__remove_event didn't remove %p\n", event);
+ /* CEPH_WATCH_EVENT_NOTIFY */
+ lwork = lwork_alloc(lreq, do_watch_notify);
+ if (!lwork) {
+ pr_err("failed to allocate notify-lwork\n");
+ goto out_unlock_lreq;
+ }
+
+ lwork->notify.notify_id = notify_id;
+ lwork->notify.notifier_id = notifier_id;
+ lwork->notify.payload = payload;
+ lwork->notify.payload_len = payload_len;
+ lwork->notify.msg = ceph_msg_get(msg);
+ lwork_queue(lwork);
}
+
+out_unlock_lreq:
+ mutex_unlock(&lreq->lock);
+out_unlock_osdc:
+ up_read(&osdc->lock);
+ return;
+
+bad:
+ pr_err("osdc handle_watch_notify corrupt msg\n");
}
-int ceph_osdc_create_event(struct ceph_osd_client *osdc,
- void (*event_cb)(u64, u64, u8, void *),
- void *data, struct ceph_osd_event **pevent)
+/*
+ * Register request, send initial attempt.
+ */
+int ceph_osdc_start_request(struct ceph_osd_client *osdc,
+ struct ceph_osd_request *req,
+ bool nofail)
{
- struct ceph_osd_event *event;
+ down_read(&osdc->lock);
+ submit_request(req, false);
+ up_read(&osdc->lock);
- event = kmalloc(sizeof(*event), GFP_NOIO);
- if (!event)
- return -ENOMEM;
-
- dout("create_event %p\n", event);
- event->cb = event_cb;
- event->one_shot = 0;
- event->data = data;
- event->osdc = osdc;
- INIT_LIST_HEAD(&event->osd_node);
- RB_CLEAR_NODE(&event->node);
- kref_init(&event->kref); /* one ref for us */
- kref_get(&event->kref); /* one ref for the caller */
-
- spin_lock(&osdc->event_lock);
- event->cookie = ++osdc->event_count;
- __insert_event(osdc, event);
- spin_unlock(&osdc->event_lock);
-
- *pevent = event;
return 0;
}
-EXPORT_SYMBOL(ceph_osdc_create_event);
+EXPORT_SYMBOL(ceph_osdc_start_request);
-void ceph_osdc_cancel_event(struct ceph_osd_event *event)
+/*
+ * Unregister a registered request. The request is not completed (i.e.
+ * no callbacks or wakeups) - higher layers are supposed to know what
+ * they are canceling.
+ */
+void ceph_osdc_cancel_request(struct ceph_osd_request *req)
{
- struct ceph_osd_client *osdc = event->osdc;
+ struct ceph_osd_client *osdc = req->r_osdc;
- dout("cancel_event %p\n", event);
- spin_lock(&osdc->event_lock);
- __remove_event(event);
- spin_unlock(&osdc->event_lock);
- ceph_osdc_put_event(event); /* caller's */
+ down_write(&osdc->lock);
+ if (req->r_osd)
+ cancel_request(req);
+ up_write(&osdc->lock);
}
-EXPORT_SYMBOL(ceph_osdc_cancel_event);
-
+EXPORT_SYMBOL(ceph_osdc_cancel_request);
-static void do_event_work(struct work_struct *work)
+/*
+ * @timeout: in jiffies, 0 means "wait forever"
+ */
+static int wait_request_timeout(struct ceph_osd_request *req,
+ unsigned long timeout)
{
- struct ceph_osd_event_work *event_work =
- container_of(work, struct ceph_osd_event_work, work);
- struct ceph_osd_event *event = event_work->event;
- u64 ver = event_work->ver;
- u64 notify_id = event_work->notify_id;
- u8 opcode = event_work->opcode;
+ long left;
+
+ dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
+ left = wait_for_completion_killable_timeout(&req->r_completion,
+ ceph_timeout_jiffies(timeout));
+ if (left <= 0) {
+ left = left ?: -ETIMEDOUT;
+ ceph_osdc_cancel_request(req);
- dout("do_event_work completing %p\n", event);
- event->cb(ver, notify_id, opcode, event->data);
- dout("do_event_work completed %p\n", event);
- ceph_osdc_put_event(event);
- kfree(event_work);
+ /* kludge - need to to wake ceph_osdc_sync() */
+ complete_all(&req->r_safe_completion);
+ } else {
+ left = req->r_result; /* completed */
+ }
+
+ return left;
}
+/*
+ * wait for a request to complete
+ */
+int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
+ struct ceph_osd_request *req)
+{
+ return wait_request_timeout(req, 0);
+}
+EXPORT_SYMBOL(ceph_osdc_wait_request);
/*
- * Process osd watch notifications
+ * sync - wait for all in-flight requests to flush. avoid starvation.
*/
-static void handle_watch_notify(struct ceph_osd_client *osdc,
- struct ceph_msg *msg)
+void ceph_osdc_sync(struct ceph_osd_client *osdc)
{
- void *p, *end;
- u8 proto_ver;
- u64 cookie, ver, notify_id;
- u8 opcode;
- struct ceph_osd_event *event;
- struct ceph_osd_event_work *event_work;
+ struct rb_node *n, *p;
+ u64 last_tid = atomic64_read(&osdc->last_tid);
- p = msg->front.iov_base;
- end = p + msg->front.iov_len;
+again:
+ down_read(&osdc->lock);
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
- ceph_decode_8_safe(&p, end, proto_ver, bad);
- ceph_decode_8_safe(&p, end, opcode, bad);
- ceph_decode_64_safe(&p, end, cookie, bad);
- ceph_decode_64_safe(&p, end, ver, bad);
- ceph_decode_64_safe(&p, end, notify_id, bad);
+ mutex_lock(&osd->lock);
+ for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+ struct ceph_osd_request *req =
+ rb_entry(p, struct ceph_osd_request, r_node);
+
+ if (req->r_tid > last_tid)
+ break;
- spin_lock(&osdc->event_lock);
- event = __find_event(osdc, cookie);
- if (event) {
- BUG_ON(event->one_shot);
- get_event(event);
- }
- spin_unlock(&osdc->event_lock);
- dout("handle_watch_notify cookie %lld ver %lld event %p\n",
- cookie, ver, event);
- if (event) {
- event_work = kmalloc(sizeof(*event_work), GFP_NOIO);
- if (!event_work) {
- pr_err("couldn't allocate event_work\n");
- ceph_osdc_put_event(event);
- return;
+ if (!(req->r_flags & CEPH_OSD_FLAG_WRITE))
+ continue;
+
+ ceph_osdc_get_request(req);
+ mutex_unlock(&osd->lock);
+ up_read(&osdc->lock);
+ dout("%s waiting on req %p tid %llu last_tid %llu\n",
+ __func__, req, req->r_tid, last_tid);
+ wait_for_completion(&req->r_safe_completion);
+ ceph_osdc_put_request(req);
+ goto again;
}
- INIT_WORK(&event_work->work, do_event_work);
- event_work->event = event;
- event_work->ver = ver;
- event_work->notify_id = notify_id;
- event_work->opcode = opcode;
- queue_work(osdc->notify_wq, &event_work->work);
+ mutex_unlock(&osd->lock);
}
- return;
+ up_read(&osdc->lock);
+ dout("%s done last_tid %llu\n", __func__, last_tid);
+}
+EXPORT_SYMBOL(ceph_osdc_sync);
-bad:
- pr_err("osdc handle_watch_notify corrupt msg\n");
+static struct ceph_osd_request *
+alloc_linger_request(struct ceph_osd_linger_request *lreq)
+{
+ struct ceph_osd_request *req;
+
+ req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO);
+ if (!req)
+ return NULL;
+
+ ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
+ ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+
+ if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
+ ceph_osdc_put_request(req);
+ return NULL;
+ }
+
+ return req;
}
/*
- * build new request AND message
- *
+ * Returns a handle, caller owns a ref.
*/
-void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off,
- struct ceph_snap_context *snapc, u64 snap_id,
- struct timespec *mtime)
-{
- struct ceph_msg *msg = req->r_request;
- void *p;
- size_t msg_size;
- int flags = req->r_flags;
- u64 data_len;
- unsigned int i;
-
- req->r_snapid = snap_id;
- req->r_snapc = ceph_get_snap_context(snapc);
-
- /* encode request */
- msg->hdr.version = cpu_to_le16(4);
-
- p = msg->front.iov_base;
- ceph_encode_32(&p, 1); /* client_inc is always 1 */
- req->r_request_osdmap_epoch = p;
- p += 4;
- req->r_request_flags = p;
- p += 4;
- if (req->r_flags & CEPH_OSD_FLAG_WRITE)
- ceph_encode_timespec(p, mtime);
- p += sizeof(struct ceph_timespec);
- req->r_request_reassert_version = p;
- p += sizeof(struct ceph_eversion); /* will get filled in */
-
- /* oloc */
- ceph_encode_8(&p, 4);
- ceph_encode_8(&p, 4);
- ceph_encode_32(&p, 8 + 4 + 4);
- req->r_request_pool = p;
- p += 8;
- ceph_encode_32(&p, -1); /* preferred */
- ceph_encode_32(&p, 0); /* key len */
+struct ceph_osd_linger_request *
+ceph_osdc_watch(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ rados_watchcb2_t wcb,
+ rados_watcherrcb_t errcb,
+ void *data)
+{
+ struct ceph_osd_linger_request *lreq;
+ int ret;
- ceph_encode_8(&p, 1);
- req->r_request_pgid = p;
- p += 8 + 4;
- ceph_encode_32(&p, -1); /* preferred */
+ lreq = linger_alloc(osdc);
+ if (!lreq)
+ return ERR_PTR(-ENOMEM);
- /* oid */
- ceph_encode_32(&p, req->r_base_oid.name_len);
- memcpy(p, req->r_base_oid.name, req->r_base_oid.name_len);
- dout("oid '%.*s' len %d\n", req->r_base_oid.name_len,
- req->r_base_oid.name, req->r_base_oid.name_len);
- p += req->r_base_oid.name_len;
-
- /* ops--can imply data */
- ceph_encode_16(&p, (u16)req->r_num_ops);
- data_len = 0;
- for (i = 0; i < req->r_num_ops; i++) {
- data_len += osd_req_encode_op(req, p, i);
- p += sizeof(struct ceph_osd_op);
+ lreq->is_watch = true;
+ lreq->wcb = wcb;
+ lreq->errcb = errcb;
+ lreq->data = data;
+ lreq->watch_valid_thru = jiffies;
+
+ ceph_oid_copy(&lreq->t.base_oid, oid);
+ ceph_oloc_copy(&lreq->t.base_oloc, oloc);
+ lreq->t.flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
+ lreq->mtime = CURRENT_TIME;
+
+ lreq->reg_req = alloc_linger_request(lreq);
+ if (!lreq->reg_req) {
+ ret = -ENOMEM;
+ goto err_put_lreq;
}
- /* snaps */
- ceph_encode_64(&p, req->r_snapid);
- ceph_encode_64(&p, req->r_snapc ? req->r_snapc->seq : 0);
- ceph_encode_32(&p, req->r_snapc ? req->r_snapc->num_snaps : 0);
- if (req->r_snapc) {
- for (i = 0; i < snapc->num_snaps; i++) {
- ceph_encode_64(&p, req->r_snapc->snaps[i]);
- }
+ lreq->ping_req = alloc_linger_request(lreq);
+ if (!lreq->ping_req) {
+ ret = -ENOMEM;
+ goto err_put_lreq;
}
- req->r_request_attempts = p;
- p += 4;
-
- /* data */
- if (flags & CEPH_OSD_FLAG_WRITE) {
- u16 data_off;
-
- /*
- * The header "data_off" is a hint to the receiver
- * allowing it to align received data into its
- * buffers such that there's no need to re-copy
- * it before writing it to disk (direct I/O).
- */
- data_off = (u16) (off & 0xffff);
- req->r_request->hdr.data_off = cpu_to_le16(data_off);
+ down_write(&osdc->lock);
+ linger_register(lreq); /* before osd_req_op_* */
+ osd_req_op_watch_init(lreq->reg_req, 0, lreq->linger_id,
+ CEPH_OSD_WATCH_OP_WATCH);
+ osd_req_op_watch_init(lreq->ping_req, 0, lreq->linger_id,
+ CEPH_OSD_WATCH_OP_PING);
+ linger_submit(lreq);
+ up_write(&osdc->lock);
+
+ ret = linger_reg_commit_wait(lreq);
+ if (ret) {
+ linger_cancel(lreq);
+ goto err_put_lreq;
}
- req->r_request->hdr.data_len = cpu_to_le32(data_len);
- BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
- msg_size = p - msg->front.iov_base;
- msg->front.iov_len = msg_size;
- msg->hdr.front_len = cpu_to_le32(msg_size);
+ return lreq;
- dout("build_request msg_size was %d\n", (int)msg_size);
+err_put_lreq:
+ linger_put(lreq);
+ return ERR_PTR(ret);
}
-EXPORT_SYMBOL(ceph_osdc_build_request);
+EXPORT_SYMBOL(ceph_osdc_watch);
/*
- * Register request, send initial attempt.
+ * Releases a ref.
+ *
+ * Times out after mount_timeout to preserve rbd unmap behaviour
+ * introduced in 2894e1d76974 ("rbd: timeout watch teardown on unmap
+ * with mount_timeout").
*/
-int ceph_osdc_start_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req,
- bool nofail)
+int ceph_osdc_unwatch(struct ceph_osd_client *osdc,
+ struct ceph_osd_linger_request *lreq)
{
- int rc;
+ struct ceph_options *opts = osdc->client->options;
+ struct ceph_osd_request *req;
+ int ret;
- down_read(&osdc->map_sem);
- mutex_lock(&osdc->request_mutex);
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
+ if (!req)
+ return -ENOMEM;
- rc = __ceph_osdc_start_request(osdc, req, nofail);
+ ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
+ ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+ req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
+ req->r_mtime = CURRENT_TIME;
+ osd_req_op_watch_init(req, 0, lreq->linger_id,
+ CEPH_OSD_WATCH_OP_UNWATCH);
- mutex_unlock(&osdc->request_mutex);
- up_read(&osdc->map_sem);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
- return rc;
+ ceph_osdc_start_request(osdc, req, false);
+ linger_cancel(lreq);
+ linger_put(lreq);
+ ret = wait_request_timeout(req, opts->mount_timeout);
+
+out_put_req:
+ ceph_osdc_put_request(req);
+ return ret;
}
-EXPORT_SYMBOL(ceph_osdc_start_request);
+EXPORT_SYMBOL(ceph_osdc_unwatch);
-/*
- * Unregister a registered request. The request is not completed (i.e.
- * no callbacks or wakeups) - higher layers are supposed to know what
- * they are canceling.
- */
-void ceph_osdc_cancel_request(struct ceph_osd_request *req)
+static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
+ u64 notify_id, u64 cookie, void *payload,
+ size_t payload_len)
{
- struct ceph_osd_client *osdc = req->r_osdc;
+ struct ceph_osd_req_op *op;
+ struct ceph_pagelist *pl;
+ int ret;
+
+ op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
+
+ pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ if (!pl)
+ return -ENOMEM;
- mutex_lock(&osdc->request_mutex);
- if (req->r_linger)
- __unregister_linger_request(osdc, req);
- __unregister_request(osdc, req);
- mutex_unlock(&osdc->request_mutex);
+ ceph_pagelist_init(pl);
+ ret = ceph_pagelist_encode_64(pl, notify_id);
+ ret |= ceph_pagelist_encode_64(pl, cookie);
+ if (payload) {
+ ret |= ceph_pagelist_encode_32(pl, payload_len);
+ ret |= ceph_pagelist_append(pl, payload, payload_len);
+ } else {
+ ret |= ceph_pagelist_encode_32(pl, 0);
+ }
+ if (ret) {
+ ceph_pagelist_release(pl);
+ return -ENOMEM;
+ }
- dout("%s %p tid %llu canceled\n", __func__, req, req->r_tid);
+ ceph_osd_data_pagelist_init(&op->notify_ack.request_data, pl);
+ op->indata_len = pl->length;
+ return 0;
}
-EXPORT_SYMBOL(ceph_osdc_cancel_request);
-/*
- * wait for a request to complete
- */
-int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req)
+int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ u64 notify_id,
+ u64 cookie,
+ void *payload,
+ size_t payload_len)
+{
+ struct ceph_osd_request *req;
+ int ret;
+
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
+ if (!req)
+ return -ENOMEM;
+
+ ceph_oid_copy(&req->r_base_oid, oid);
+ ceph_oloc_copy(&req->r_base_oloc, oloc);
+ req->r_flags = CEPH_OSD_FLAG_READ;
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
+
+ ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
+ payload_len);
+ if (ret)
+ goto out_put_req;
+
+ ceph_osdc_start_request(osdc, req, false);
+ ret = ceph_osdc_wait_request(osdc, req);
+
+out_put_req:
+ ceph_osdc_put_request(req);
+ return ret;
+}
+EXPORT_SYMBOL(ceph_osdc_notify_ack);
+
+static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
+ u64 cookie, u32 prot_ver, u32 timeout,
+ void *payload, size_t payload_len)
{
- int rc;
+ struct ceph_osd_req_op *op;
+ struct ceph_pagelist *pl;
+ int ret;
- dout("%s %p tid %llu\n", __func__, req, req->r_tid);
+ op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
+ op->notify.cookie = cookie;
- rc = wait_for_completion_interruptible(&req->r_completion);
- if (rc < 0) {
- dout("%s %p tid %llu interrupted\n", __func__, req, req->r_tid);
- ceph_osdc_cancel_request(req);
- complete_request(req);
- return rc;
+ pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ if (!pl)
+ return -ENOMEM;
+
+ ceph_pagelist_init(pl);
+ ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
+ ret |= ceph_pagelist_encode_32(pl, timeout);
+ ret |= ceph_pagelist_encode_32(pl, payload_len);
+ ret |= ceph_pagelist_append(pl, payload, payload_len);
+ if (ret) {
+ ceph_pagelist_release(pl);
+ return -ENOMEM;
}
- dout("%s %p tid %llu result %d\n", __func__, req, req->r_tid,
- req->r_result);
- return req->r_result;
+ ceph_osd_data_pagelist_init(&op->notify.request_data, pl);
+ op->indata_len = pl->length;
+ return 0;
}
-EXPORT_SYMBOL(ceph_osdc_wait_request);
/*
- * sync - wait for all in-flight requests to flush. avoid starvation.
+ * @timeout: in seconds
+ *
+ * @preply_{pages,len} are initialized both on success and error.
+ * The caller is responsible for:
+ *
+ * ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len))
*/
-void ceph_osdc_sync(struct ceph_osd_client *osdc)
+int ceph_osdc_notify(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ void *payload,
+ size_t payload_len,
+ u32 timeout,
+ struct page ***preply_pages,
+ size_t *preply_len)
{
- struct ceph_osd_request *req;
- u64 last_tid, next_tid = 0;
+ struct ceph_osd_linger_request *lreq;
+ struct page **pages;
+ int ret;
- mutex_lock(&osdc->request_mutex);
- last_tid = osdc->last_tid;
- while (1) {
- req = __lookup_request_ge(osdc, next_tid);
- if (!req)
- break;
- if (req->r_tid > last_tid)
- break;
+ WARN_ON(!timeout);
+ if (preply_pages) {
+ *preply_pages = NULL;
+ *preply_len = 0;
+ }
- next_tid = req->r_tid + 1;
- if ((req->r_flags & CEPH_OSD_FLAG_WRITE) == 0)
- continue;
+ lreq = linger_alloc(osdc);
+ if (!lreq)
+ return -ENOMEM;
- ceph_osdc_get_request(req);
- mutex_unlock(&osdc->request_mutex);
- dout("sync waiting on tid %llu (last is %llu)\n",
- req->r_tid, last_tid);
- wait_for_completion(&req->r_safe_completion);
- mutex_lock(&osdc->request_mutex);
- ceph_osdc_put_request(req);
+ lreq->preply_pages = preply_pages;
+ lreq->preply_len = preply_len;
+
+ ceph_oid_copy(&lreq->t.base_oid, oid);
+ ceph_oloc_copy(&lreq->t.base_oloc, oloc);
+ lreq->t.flags = CEPH_OSD_FLAG_READ;
+
+ lreq->reg_req = alloc_linger_request(lreq);
+ if (!lreq->reg_req) {
+ ret = -ENOMEM;
+ goto out_put_lreq;
}
- mutex_unlock(&osdc->request_mutex);
- dout("sync done (thru tid %llu)\n", last_tid);
+
+ /* for notify_id */
+ pages = ceph_alloc_page_vector(1, GFP_NOIO);
+ if (IS_ERR(pages)) {
+ ret = PTR_ERR(pages);
+ goto out_put_lreq;
+ }
+
+ down_write(&osdc->lock);
+ linger_register(lreq); /* before osd_req_op_* */
+ ret = osd_req_op_notify_init(lreq->reg_req, 0, lreq->linger_id, 1,
+ timeout, payload, payload_len);
+ if (ret) {
+ linger_unregister(lreq);
+ up_write(&osdc->lock);
+ ceph_release_page_vector(pages, 1);
+ goto out_put_lreq;
+ }
+ ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
+ response_data),
+ pages, PAGE_SIZE, 0, false, true);
+ linger_submit(lreq);
+ up_write(&osdc->lock);
+
+ ret = linger_reg_commit_wait(lreq);
+ if (!ret)
+ ret = linger_notify_finish_wait(lreq);
+ else
+ dout("lreq %p failed to initiate notify %d\n", lreq, ret);
+
+ linger_cancel(lreq);
+out_put_lreq:
+ linger_put(lreq);
+ return ret;
+}
+EXPORT_SYMBOL(ceph_osdc_notify);
+
+/*
+ * Return the number of milliseconds since the watch was last
+ * confirmed, or an error. If there is an error, the watch is no
+ * longer valid, and should be destroyed with ceph_osdc_unwatch().
+ */
+int ceph_osdc_watch_check(struct ceph_osd_client *osdc,
+ struct ceph_osd_linger_request *lreq)
+{
+ unsigned long stamp, age;
+ int ret;
+
+ down_read(&osdc->lock);
+ mutex_lock(&lreq->lock);
+ stamp = lreq->watch_valid_thru;
+ if (!list_empty(&lreq->pending_lworks)) {
+ struct linger_work *lwork =
+ list_first_entry(&lreq->pending_lworks,
+ struct linger_work,
+ pending_item);
+
+ if (time_before(lwork->queued_stamp, stamp))
+ stamp = lwork->queued_stamp;
+ }
+ age = jiffies - stamp;
+ dout("%s lreq %p linger_id %llu age %lu last_error %d\n", __func__,
+ lreq, lreq->linger_id, age, lreq->last_error);
+ /* we are truncating to msecs, so return a safe upper bound */
+ ret = lreq->last_error ?: 1 + jiffies_to_msecs(age);
+
+ mutex_unlock(&lreq->lock);
+ up_read(&osdc->lock);
+ return ret;
}
-EXPORT_SYMBOL(ceph_osdc_sync);
/*
* Call all pending notify callbacks - for use after a watch is
@@ -2646,6 +3868,13 @@ void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
}
EXPORT_SYMBOL(ceph_osdc_flush_notifies);
+void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc)
+{
+ down_read(&osdc->lock);
+ maybe_request_map(osdc);
+ up_read(&osdc->lock);
+}
+EXPORT_SYMBOL(ceph_osdc_maybe_request_map);
/*
* init, shutdown
@@ -2656,43 +3885,35 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
dout("init\n");
osdc->client = client;
- osdc->osdmap = NULL;
- init_rwsem(&osdc->map_sem);
- init_completion(&osdc->map_waiters);
- osdc->last_requested_map = 0;
- mutex_init(&osdc->request_mutex);
- osdc->last_tid = 0;
+ init_rwsem(&osdc->lock);
osdc->osds = RB_ROOT;
INIT_LIST_HEAD(&osdc->osd_lru);
- osdc->requests = RB_ROOT;
- INIT_LIST_HEAD(&osdc->req_lru);
- INIT_LIST_HEAD(&osdc->req_unsent);
- INIT_LIST_HEAD(&osdc->req_notarget);
- INIT_LIST_HEAD(&osdc->req_linger);
- osdc->num_requests = 0;
+ spin_lock_init(&osdc->osd_lru_lock);
+ osd_init(&osdc->homeless_osd);
+ osdc->homeless_osd.o_osdc = osdc;
+ osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD;
+ osdc->linger_requests = RB_ROOT;
+ osdc->map_checks = RB_ROOT;
+ osdc->linger_map_checks = RB_ROOT;
INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout);
INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);
- spin_lock_init(&osdc->event_lock);
- osdc->event_tree = RB_ROOT;
- osdc->event_count = 0;
-
- schedule_delayed_work(&osdc->osds_timeout_work,
- round_jiffies_relative(osdc->client->options->osd_idle_ttl));
err = -ENOMEM;
+ osdc->osdmap = ceph_osdmap_alloc();
+ if (!osdc->osdmap)
+ goto out;
+
osdc->req_mempool = mempool_create_slab_pool(10,
ceph_osd_request_cache);
if (!osdc->req_mempool)
- goto out;
+ goto out_map;
err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
- OSD_OP_FRONT_LEN, 10, true,
- "osd_op");
+ PAGE_SIZE, 10, true, "osd_op");
if (err < 0)
goto out_mempool;
err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
- OSD_OPREPLY_FRONT_LEN, 10, true,
- "osd_op_reply");
+ PAGE_SIZE, 10, true, "osd_op_reply");
if (err < 0)
goto out_msgpool;
@@ -2701,6 +3922,11 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
if (!osdc->notify_wq)
goto out_msgpool_reply;
+ schedule_delayed_work(&osdc->timeout_work,
+ osdc->client->options->osd_keepalive_timeout);
+ schedule_delayed_work(&osdc->osds_timeout_work,
+ round_jiffies_relative(osdc->client->options->osd_idle_ttl));
+
return 0;
out_msgpool_reply:
@@ -2709,6 +3935,8 @@ out_msgpool:
ceph_msgpool_destroy(&osdc->msgpool_op);
out_mempool:
mempool_destroy(osdc->req_mempool);
+out_map:
+ ceph_osdmap_destroy(osdc->osdmap);
out:
return err;
}
@@ -2719,11 +3947,25 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc)
destroy_workqueue(osdc->notify_wq);
cancel_delayed_work_sync(&osdc->timeout_work);
cancel_delayed_work_sync(&osdc->osds_timeout_work);
- if (osdc->osdmap) {
- ceph_osdmap_destroy(osdc->osdmap);
- osdc->osdmap = NULL;
+
+ down_write(&osdc->lock);
+ while (!RB_EMPTY_ROOT(&osdc->osds)) {
+ struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
+ struct ceph_osd, o_node);
+ close_osd(osd);
}
- remove_all_osds(osdc);
+ up_write(&osdc->lock);
+ WARN_ON(atomic_read(&osdc->homeless_osd.o_ref) != 1);
+ osd_cleanup(&osdc->homeless_osd);
+
+ WARN_ON(!list_empty(&osdc->osd_lru));
+ WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests));
+ WARN_ON(!RB_EMPTY_ROOT(&osdc->map_checks));
+ WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_map_checks));
+ WARN_ON(atomic_read(&osdc->num_requests));
+ WARN_ON(atomic_read(&osdc->num_homeless));
+
+ ceph_osdmap_destroy(osdc->osdmap);
mempool_destroy(osdc->req_mempool);
ceph_msgpool_destroy(&osdc->msgpool_op);
ceph_msgpool_destroy(&osdc->msgpool_op_reply);
@@ -2752,15 +3994,12 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
return PTR_ERR(req);
/* it may be a short read due to an object boundary */
-
osd_req_op_extent_osd_data_pages(req, 0,
pages, *plen, page_align, false, false);
dout("readpages final extent is %llu~%llu (%llu bytes align %d)\n",
off, *plen, *plen, page_align);
- ceph_osdc_build_request(req, off, NULL, vino.snap, NULL);
-
rc = ceph_osdc_start_request(osdc, req, false);
if (!rc)
rc = ceph_osdc_wait_request(osdc, req);
@@ -2786,7 +4025,6 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
int rc = 0;
int page_align = off & ~PAGE_MASK;
- BUG_ON(vino.snap != CEPH_NOSNAP); /* snapshots aren't writeable */
req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
CEPH_OSD_OP_WRITE,
CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
@@ -2800,8 +4038,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
false, false);
dout("writepages %llu~%llu (%llu bytes)\n", off, len, len);
- ceph_osdc_build_request(req, off, snapc, CEPH_NOSNAP, mtime);
-
+ req->r_mtime = *mtime;
rc = ceph_osdc_start_request(osdc, req, true);
if (!rc)
rc = ceph_osdc_wait_request(osdc, req);
@@ -2841,19 +4078,15 @@ EXPORT_SYMBOL(ceph_osdc_cleanup);
static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
struct ceph_osd *osd = con->private;
- struct ceph_osd_client *osdc;
+ struct ceph_osd_client *osdc = osd->o_osdc;
int type = le16_to_cpu(msg->hdr.type);
- if (!osd)
- goto out;
- osdc = osd->o_osdc;
-
switch (type) {
case CEPH_MSG_OSD_MAP:
ceph_osdc_handle_map(osdc, msg);
break;
case CEPH_MSG_OSD_OPREPLY:
- handle_reply(osdc, msg);
+ handle_reply(osd, msg);
break;
case CEPH_MSG_WATCH_NOTIFY:
handle_watch_notify(osdc, msg);
@@ -2863,7 +4096,7 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
pr_err("received unknown message type %d %s\n", type,
ceph_msg_type_name(type));
}
-out:
+
ceph_msg_put(msg);
}
@@ -2878,21 +4111,27 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
{
struct ceph_osd *osd = con->private;
struct ceph_osd_client *osdc = osd->o_osdc;
- struct ceph_msg *m;
+ struct ceph_msg *m = NULL;
struct ceph_osd_request *req;
int front_len = le32_to_cpu(hdr->front_len);
int data_len = le32_to_cpu(hdr->data_len);
- u64 tid;
+ u64 tid = le64_to_cpu(hdr->tid);
- tid = le64_to_cpu(hdr->tid);
- mutex_lock(&osdc->request_mutex);
- req = __lookup_request(osdc, tid);
+ down_read(&osdc->lock);
+ if (!osd_registered(osd)) {
+ dout("%s osd%d unknown, skipping\n", __func__, osd->o_osd);
+ *skip = 1;
+ goto out_unlock_osdc;
+ }
+ WARN_ON(osd->o_osd != le64_to_cpu(hdr->src.num));
+
+ mutex_lock(&osd->lock);
+ req = lookup_request(&osd->o_requests, tid);
if (!req) {
dout("%s osd%d tid %llu unknown, skipping\n", __func__,
osd->o_osd, tid);
- m = NULL;
*skip = 1;
- goto out;
+ goto out_unlock_session;
}
ceph_msg_revoke_incoming(req->r_reply);
@@ -2904,7 +4143,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS,
false);
if (!m)
- goto out;
+ goto out_unlock_session;
ceph_msg_put(req->r_reply);
req->r_reply = m;
}
@@ -2915,14 +4154,49 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
req->r_reply->data_length);
m = NULL;
*skip = 1;
- goto out;
+ goto out_unlock_session;
}
m = ceph_msg_get(req->r_reply);
dout("get_reply tid %lld %p\n", tid, m);
-out:
- mutex_unlock(&osdc->request_mutex);
+out_unlock_session:
+ mutex_unlock(&osd->lock);
+out_unlock_osdc:
+ up_read(&osdc->lock);
+ return m;
+}
+
+/*
+ * TODO: switch to a msg-owned pagelist
+ */
+static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
+{
+ struct ceph_msg *m;
+ int type = le16_to_cpu(hdr->type);
+ u32 front_len = le32_to_cpu(hdr->front_len);
+ u32 data_len = le32_to_cpu(hdr->data_len);
+
+ m = ceph_msg_new(type, front_len, GFP_NOIO, false);
+ if (!m)
+ return NULL;
+
+ if (data_len) {
+ struct page **pages;
+ struct ceph_osd_data osd_data;
+
+ pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
+ GFP_NOIO);
+ if (!pages) {
+ ceph_msg_put(m);
+ return NULL;
+ }
+
+ ceph_osd_data_pages_init(&osd_data, pages, data_len, 0, false,
+ false);
+ ceph_osdc_msg_data_add(m, &osd_data);
+ }
+
return m;
}
@@ -2932,18 +4206,17 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con,
{
struct ceph_osd *osd = con->private;
int type = le16_to_cpu(hdr->type);
- int front = le32_to_cpu(hdr->front_len);
*skip = 0;
switch (type) {
case CEPH_MSG_OSD_MAP:
case CEPH_MSG_WATCH_NOTIFY:
- return ceph_msg_new(type, front, GFP_NOFS, false);
+ return alloc_msg_with_page_vector(hdr);
case CEPH_MSG_OSD_OPREPLY:
return get_reply(con, hdr, skip);
default:
- pr_info("alloc_msg unexpected msg type %d from osd%d\n", type,
- osd->o_osd);
+ pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__,
+ osd->o_osd, type);
*skip = 1;
return NULL;
}
@@ -3047,5 +4320,5 @@ static const struct ceph_connection_operations osd_con_ops = {
.alloc_msg = alloc_msg,
.sign_message = osd_sign_message,
.check_message_signature = osd_check_message_signature,
- .fault = osd_reset,
+ .fault = osd_fault,
};
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 243574c8cf33..03062bb763b3 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -380,23 +380,24 @@ bad:
return ERR_PTR(err);
}
-/*
- * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
- * to a set of osds) and primary_temp (explicit primary setting)
- */
-static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
+int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs)
{
- if (l.pool < r.pool)
+ if (lhs->pool < rhs->pool)
return -1;
- if (l.pool > r.pool)
+ if (lhs->pool > rhs->pool)
return 1;
- if (l.seed < r.seed)
+ if (lhs->seed < rhs->seed)
return -1;
- if (l.seed > r.seed)
+ if (lhs->seed > rhs->seed)
return 1;
+
return 0;
}
+/*
+ * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
+ * to a set of osds) and primary_temp (explicit primary setting)
+ */
static int __insert_pg_mapping(struct ceph_pg_mapping *new,
struct rb_root *root)
{
@@ -409,7 +410,7 @@ static int __insert_pg_mapping(struct ceph_pg_mapping *new,
while (*p) {
parent = *p;
pg = rb_entry(parent, struct ceph_pg_mapping, node);
- c = pgid_cmp(new->pgid, pg->pgid);
+ c = ceph_pg_compare(&new->pgid, &pg->pgid);
if (c < 0)
p = &(*p)->rb_left;
else if (c > 0)
@@ -432,7 +433,7 @@ static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
while (n) {
pg = rb_entry(n, struct ceph_pg_mapping, node);
- c = pgid_cmp(pgid, pg->pgid);
+ c = ceph_pg_compare(&pgid, &pg->pgid);
if (c < 0) {
n = n->rb_left;
} else if (c > 0) {
@@ -596,7 +597,9 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
*p += 4; /* skip crash_replay_interval */
if (ev >= 7)
- *p += 1; /* skip min_size */
+ pi->min_size = ceph_decode_8(p);
+ else
+ pi->min_size = pi->size - pi->size / 2;
if (ev >= 8)
*p += 8 + 8; /* skip quota_max_* */
@@ -616,6 +619,50 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
pi->write_tier = -1;
}
+ if (ev >= 10) {
+ /* skip properties */
+ num = ceph_decode_32(p);
+ while (num--) {
+ len = ceph_decode_32(p);
+ *p += len; /* key */
+ len = ceph_decode_32(p);
+ *p += len; /* val */
+ }
+ }
+
+ if (ev >= 11) {
+ /* skip hit_set_params */
+ *p += 1 + 1; /* versions */
+ len = ceph_decode_32(p);
+ *p += len;
+
+ *p += 4; /* skip hit_set_period */
+ *p += 4; /* skip hit_set_count */
+ }
+
+ if (ev >= 12)
+ *p += 4; /* skip stripe_width */
+
+ if (ev >= 13) {
+ *p += 8; /* skip target_max_bytes */
+ *p += 8; /* skip target_max_objects */
+ *p += 4; /* skip cache_target_dirty_ratio_micro */
+ *p += 4; /* skip cache_target_full_ratio_micro */
+ *p += 4; /* skip cache_min_flush_age */
+ *p += 4; /* skip cache_min_evict_age */
+ }
+
+ if (ev >= 14) {
+ /* skip erasure_code_profile */
+ len = ceph_decode_32(p);
+ *p += len;
+ }
+
+ if (ev >= 15)
+ pi->last_force_request_resend = ceph_decode_32(p);
+ else
+ pi->last_force_request_resend = 0;
+
/* ignore the rest */
*p = pool_end;
@@ -660,6 +707,23 @@ bad:
/*
* osd map
*/
+struct ceph_osdmap *ceph_osdmap_alloc(void)
+{
+ struct ceph_osdmap *map;
+
+ map = kzalloc(sizeof(*map), GFP_NOIO);
+ if (!map)
+ return NULL;
+
+ map->pg_pools = RB_ROOT;
+ map->pool_max = -1;
+ map->pg_temp = RB_ROOT;
+ map->primary_temp = RB_ROOT;
+ mutex_init(&map->crush_scratch_mutex);
+
+ return map;
+}
+
void ceph_osdmap_destroy(struct ceph_osdmap *map)
{
dout("osdmap_destroy %p\n", map);
@@ -1183,14 +1247,10 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
struct ceph_osdmap *map;
int ret;
- map = kzalloc(sizeof(*map), GFP_NOFS);
+ map = ceph_osdmap_alloc();
if (!map)
return ERR_PTR(-ENOMEM);
- map->pg_temp = RB_ROOT;
- map->primary_temp = RB_ROOT;
- mutex_init(&map->crush_scratch_mutex);
-
ret = osdmap_decode(p, end, map);
if (ret) {
ceph_osdmap_destroy(map);
@@ -1204,8 +1264,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
* decode and apply an incremental map update.
*/
struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
- struct ceph_osdmap *map,
- struct ceph_messenger *msgr)
+ struct ceph_osdmap *map)
{
struct crush_map *newcrush = NULL;
struct ceph_fsid fsid;
@@ -1381,8 +1440,252 @@ bad:
return ERR_PTR(err);
}
+void ceph_oid_copy(struct ceph_object_id *dest,
+ const struct ceph_object_id *src)
+{
+ WARN_ON(!ceph_oid_empty(dest));
+
+ if (src->name != src->inline_name) {
+ /* very rare, see ceph_object_id definition */
+ dest->name = kmalloc(src->name_len + 1,
+ GFP_NOIO | __GFP_NOFAIL);
+ }
+
+ memcpy(dest->name, src->name, src->name_len + 1);
+ dest->name_len = src->name_len;
+}
+EXPORT_SYMBOL(ceph_oid_copy);
+
+static __printf(2, 0)
+int oid_printf_vargs(struct ceph_object_id *oid, const char *fmt, va_list ap)
+{
+ int len;
+
+ WARN_ON(!ceph_oid_empty(oid));
+
+ len = vsnprintf(oid->inline_name, sizeof(oid->inline_name), fmt, ap);
+ if (len >= sizeof(oid->inline_name))
+ return len;
+
+ oid->name_len = len;
+ return 0;
+}
+
+/*
+ * If oid doesn't fit into inline buffer, BUG.
+ */
+void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ BUG_ON(oid_printf_vargs(oid, fmt, ap));
+ va_end(ap);
+}
+EXPORT_SYMBOL(ceph_oid_printf);
+
+static __printf(3, 0)
+int oid_aprintf_vargs(struct ceph_object_id *oid, gfp_t gfp,
+ const char *fmt, va_list ap)
+{
+ va_list aq;
+ int len;
+
+ va_copy(aq, ap);
+ len = oid_printf_vargs(oid, fmt, aq);
+ va_end(aq);
+
+ if (len) {
+ char *external_name;
+
+ external_name = kmalloc(len + 1, gfp);
+ if (!external_name)
+ return -ENOMEM;
+
+ oid->name = external_name;
+ WARN_ON(vsnprintf(oid->name, len + 1, fmt, ap) != len);
+ oid->name_len = len;
+ }
+
+ return 0;
+}
+
+/*
+ * If oid doesn't fit into inline buffer, allocate.
+ */
+int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
+ const char *fmt, ...)
+{
+ va_list ap;
+ int ret;
+
+ va_start(ap, fmt);
+ ret = oid_aprintf_vargs(oid, gfp, fmt, ap);
+ va_end(ap);
+
+ return ret;
+}
+EXPORT_SYMBOL(ceph_oid_aprintf);
+
+void ceph_oid_destroy(struct ceph_object_id *oid)
+{
+ if (oid->name != oid->inline_name)
+ kfree(oid->name);
+}
+EXPORT_SYMBOL(ceph_oid_destroy);
+
+/*
+ * osds only
+ */
+static bool __osds_equal(const struct ceph_osds *lhs,
+ const struct ceph_osds *rhs)
+{
+ if (lhs->size == rhs->size &&
+ !memcmp(lhs->osds, rhs->osds, rhs->size * sizeof(rhs->osds[0])))
+ return true;
+
+ return false;
+}
+
+/*
+ * osds + primary
+ */
+static bool osds_equal(const struct ceph_osds *lhs,
+ const struct ceph_osds *rhs)
+{
+ if (__osds_equal(lhs, rhs) &&
+ lhs->primary == rhs->primary)
+ return true;
+
+ return false;
+}
+
+static bool osds_valid(const struct ceph_osds *set)
+{
+ /* non-empty set */
+ if (set->size > 0 && set->primary >= 0)
+ return true;
+
+ /* empty can_shift_osds set */
+ if (!set->size && set->primary == -1)
+ return true;
+
+ /* empty !can_shift_osds set - all NONE */
+ if (set->size > 0 && set->primary == -1) {
+ int i;
+
+ for (i = 0; i < set->size; i++) {
+ if (set->osds[i] != CRUSH_ITEM_NONE)
+ break;
+ }
+ if (i == set->size)
+ return true;
+ }
+
+ return false;
+}
+
+void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src)
+{
+ memcpy(dest->osds, src->osds, src->size * sizeof(src->osds[0]));
+ dest->size = src->size;
+ dest->primary = src->primary;
+}
+
+static bool is_split(const struct ceph_pg *pgid,
+ u32 old_pg_num,
+ u32 new_pg_num)
+{
+ int old_bits = calc_bits_of(old_pg_num);
+ int old_mask = (1 << old_bits) - 1;
+ int n;
+
+ WARN_ON(pgid->seed >= old_pg_num);
+ if (new_pg_num <= old_pg_num)
+ return false;
+
+ for (n = 1; ; n++) {
+ int next_bit = n << (old_bits - 1);
+ u32 s = next_bit | pgid->seed;
+
+ if (s < old_pg_num || s == pgid->seed)
+ continue;
+ if (s >= new_pg_num)
+ break;
+
+ s = ceph_stable_mod(s, old_pg_num, old_mask);
+ if (s == pgid->seed)
+ return true;
+ }
+
+ return false;
+}
+
+bool ceph_is_new_interval(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting,
+ const struct ceph_osds *old_up,
+ const struct ceph_osds *new_up,
+ int old_size,
+ int new_size,
+ int old_min_size,
+ int new_min_size,
+ u32 old_pg_num,
+ u32 new_pg_num,
+ bool old_sort_bitwise,
+ bool new_sort_bitwise,
+ const struct ceph_pg *pgid)
+{
+ return !osds_equal(old_acting, new_acting) ||
+ !osds_equal(old_up, new_up) ||
+ old_size != new_size ||
+ old_min_size != new_min_size ||
+ is_split(pgid, old_pg_num, new_pg_num) ||
+ old_sort_bitwise != new_sort_bitwise;
+}
+
+static int calc_pg_rank(int osd, const struct ceph_osds *acting)
+{
+ int i;
+
+ for (i = 0; i < acting->size; i++) {
+ if (acting->osds[i] == osd)
+ return i;
+ }
+
+ return -1;
+}
+
+static bool primary_changed(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting)
+{
+ if (!old_acting->size && !new_acting->size)
+ return false; /* both still empty */
+ if (!old_acting->size ^ !new_acting->size)
+ return true; /* was empty, now not, or vice versa */
+ if (old_acting->primary != new_acting->primary)
+ return true; /* primary changed */
+
+ if (calc_pg_rank(old_acting->primary, old_acting) !=
+ calc_pg_rank(new_acting->primary, new_acting))
+ return true;
+
+ return false; /* same primary (tho replicas may have changed) */
+}
+
+bool ceph_osds_changed(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting,
+ bool any_change)
+{
+ if (primary_changed(old_acting, new_acting))
+ return true;
+
+ if (any_change && !__osds_equal(old_acting, new_acting))
+ return true;
+
+ return false;
+}
/*
* calculate file layout from given offset, length.
@@ -1455,30 +1758,71 @@ invalid:
EXPORT_SYMBOL(ceph_calc_file_object_mapping);
/*
- * Calculate mapping of a (oloc, oid) pair to a PG. Should only be
- * called with target's (oloc, oid), since tiering isn't taken into
- * account.
+ * Map an object into a PG.
+ *
+ * Should only be called with target_oid and target_oloc (as opposed to
+ * base_oid and base_oloc), since tiering isn't taken into account.
*/
-int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
- struct ceph_object_locator *oloc,
- struct ceph_object_id *oid,
- struct ceph_pg *pg_out)
+int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ struct ceph_pg *raw_pgid)
{
struct ceph_pg_pool_info *pi;
- pi = __lookup_pg_pool(&osdmap->pg_pools, oloc->pool);
+ pi = ceph_pg_pool_by_id(osdmap, oloc->pool);
if (!pi)
- return -EIO;
+ return -ENOENT;
- pg_out->pool = oloc->pool;
- pg_out->seed = ceph_str_hash(pi->object_hash, oid->name,
- oid->name_len);
+ raw_pgid->pool = oloc->pool;
+ raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
+ oid->name_len);
- dout("%s '%.*s' pgid %llu.%x\n", __func__, oid->name_len, oid->name,
- pg_out->pool, pg_out->seed);
+ dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
+ raw_pgid->pool, raw_pgid->seed);
return 0;
}
-EXPORT_SYMBOL(ceph_oloc_oid_to_pg);
+EXPORT_SYMBOL(ceph_object_locator_to_pg);
+
+/*
+ * Map a raw PG (full precision ps) into an actual PG.
+ */
+static void raw_pg_to_pg(struct ceph_pg_pool_info *pi,
+ const struct ceph_pg *raw_pgid,
+ struct ceph_pg *pgid)
+{
+ pgid->pool = raw_pgid->pool;
+ pgid->seed = ceph_stable_mod(raw_pgid->seed, pi->pg_num,
+ pi->pg_num_mask);
+}
+
+/*
+ * Map a raw PG (full precision ps) into a placement ps (placement
+ * seed). Include pool id in that value so that different pools don't
+ * use the same seeds.
+ */
+static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi,
+ const struct ceph_pg *raw_pgid)
+{
+ if (pi->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
+ /* hash pool id and seed so that pool PGs do not overlap */
+ return crush_hash32_2(CRUSH_HASH_RJENKINS1,
+ ceph_stable_mod(raw_pgid->seed,
+ pi->pgp_num,
+ pi->pgp_num_mask),
+ raw_pgid->pool);
+ } else {
+ /*
+ * legacy behavior: add ps and pool together. this is
+ * not a great approach because the PGs from each pool
+ * will overlap on top of each other: 0.5 == 1.4 ==
+ * 2.3 == ...
+ */
+ return ceph_stable_mod(raw_pgid->seed, pi->pgp_num,
+ pi->pgp_num_mask) +
+ (unsigned)raw_pgid->pool;
+ }
+}
static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
int *result, int result_max,
@@ -1497,84 +1841,92 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
}
/*
- * Calculate raw (crush) set for given pgid.
+ * Calculate raw set (CRUSH output) for given PG. The result may
+ * contain nonexistent OSDs. ->primary is undefined for a raw set.
*
- * Return raw set length, or error.
+ * Placement seed (CRUSH input) is returned through @ppps.
*/
-static int pg_to_raw_osds(struct ceph_osdmap *osdmap,
- struct ceph_pg_pool_info *pool,
- struct ceph_pg pgid, u32 pps, int *osds)
+static void pg_to_raw_osds(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pi,
+ const struct ceph_pg *raw_pgid,
+ struct ceph_osds *raw,
+ u32 *ppps)
{
+ u32 pps = raw_pg_to_pps(pi, raw_pgid);
int ruleno;
int len;
- /* crush */
- ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
- pool->type, pool->size);
+ ceph_osds_init(raw);
+ if (ppps)
+ *ppps = pps;
+
+ ruleno = crush_find_rule(osdmap->crush, pi->crush_ruleset, pi->type,
+ pi->size);
if (ruleno < 0) {
pr_err("no crush rule: pool %lld ruleset %d type %d size %d\n",
- pgid.pool, pool->crush_ruleset, pool->type,
- pool->size);
- return -ENOENT;
+ pi->id, pi->crush_ruleset, pi->type, pi->size);
+ return;
}
- len = do_crush(osdmap, ruleno, pps, osds,
- min_t(int, pool->size, CEPH_PG_MAX_SIZE),
+ len = do_crush(osdmap, ruleno, pps, raw->osds,
+ min_t(int, pi->size, ARRAY_SIZE(raw->osds)),
osdmap->osd_weight, osdmap->max_osd);
if (len < 0) {
pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n",
- len, ruleno, pgid.pool, pool->crush_ruleset,
- pool->type, pool->size);
- return len;
+ len, ruleno, pi->id, pi->crush_ruleset, pi->type,
+ pi->size);
+ return;
}
- return len;
+ raw->size = len;
}
/*
- * Given raw set, calculate up set and up primary.
+ * Given raw set, calculate up set and up primary. By definition of an
+ * up set, the result won't contain nonexistent or down OSDs.
*
- * Return up set length. *primary is set to up primary osd id, or -1
- * if up set is empty.
+ * This is done in-place - on return @set is the up set. If it's
+ * empty, ->primary will remain undefined.
*/
-static int raw_to_up_osds(struct ceph_osdmap *osdmap,
- struct ceph_pg_pool_info *pool,
- int *osds, int len, int *primary)
+static void raw_to_up_osds(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pi,
+ struct ceph_osds *set)
{
- int up_primary = -1;
int i;
- if (ceph_can_shift_osds(pool)) {
+ /* ->primary is undefined for a raw set */
+ BUG_ON(set->primary != -1);
+
+ if (ceph_can_shift_osds(pi)) {
int removed = 0;
- for (i = 0; i < len; i++) {
- if (ceph_osd_is_down(osdmap, osds[i])) {
+ /* shift left */
+ for (i = 0; i < set->size; i++) {
+ if (ceph_osd_is_down(osdmap, set->osds[i])) {
removed++;
continue;
}
if (removed)
- osds[i - removed] = osds[i];
+ set->osds[i - removed] = set->osds[i];
}
-
- len -= removed;
- if (len > 0)
- up_primary = osds[0];
+ set->size -= removed;
+ if (set->size > 0)
+ set->primary = set->osds[0];
} else {
- for (i = len - 1; i >= 0; i--) {
- if (ceph_osd_is_down(osdmap, osds[i]))
- osds[i] = CRUSH_ITEM_NONE;
+ /* set down/dne devices to NONE */
+ for (i = set->size - 1; i >= 0; i--) {
+ if (ceph_osd_is_down(osdmap, set->osds[i]))
+ set->osds[i] = CRUSH_ITEM_NONE;
else
- up_primary = osds[i];
+ set->primary = set->osds[i];
}
}
-
- *primary = up_primary;
- return len;
}
-static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
- struct ceph_pg_pool_info *pool,
- int *osds, int len, int *primary)
+static void apply_primary_affinity(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pi,
+ u32 pps,
+ struct ceph_osds *up)
{
int i;
int pos = -1;
@@ -1586,8 +1938,8 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
if (!osdmap->osd_primary_affinity)
return;
- for (i = 0; i < len; i++) {
- int osd = osds[i];
+ for (i = 0; i < up->size; i++) {
+ int osd = up->osds[i];
if (osd != CRUSH_ITEM_NONE &&
osdmap->osd_primary_affinity[osd] !=
@@ -1595,7 +1947,7 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
break;
}
}
- if (i == len)
+ if (i == up->size)
return;
/*
@@ -1603,8 +1955,8 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
* osd into the hash/rng so that a proportional fraction of an
* osd's pgs get rejected as primary.
*/
- for (i = 0; i < len; i++) {
- int osd = osds[i];
+ for (i = 0; i < up->size; i++) {
+ int osd = up->osds[i];
u32 aff;
if (osd == CRUSH_ITEM_NONE)
@@ -1629,135 +1981,110 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
if (pos < 0)
return;
- *primary = osds[pos];
+ up->primary = up->osds[pos];
- if (ceph_can_shift_osds(pool) && pos > 0) {
+ if (ceph_can_shift_osds(pi) && pos > 0) {
/* move the new primary to the front */
for (i = pos; i > 0; i--)
- osds[i] = osds[i - 1];
- osds[0] = *primary;
+ up->osds[i] = up->osds[i - 1];
+ up->osds[0] = up->primary;
}
}
/*
- * Given up set, apply pg_temp and primary_temp mappings.
+ * Get pg_temp and primary_temp mappings for given PG.
*
- * Return acting set length. *primary is set to acting primary osd id,
- * or -1 if acting set is empty.
+ * Note that a PG may have none, only pg_temp, only primary_temp or
+ * both pg_temp and primary_temp mappings. This means @temp isn't
+ * always a valid OSD set on return: in the "only primary_temp" case,
+ * @temp will have its ->primary >= 0 but ->size == 0.
*/
-static int apply_temps(struct ceph_osdmap *osdmap,
- struct ceph_pg_pool_info *pool, struct ceph_pg pgid,
- int *osds, int len, int *primary)
+static void get_temp_osds(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pi,
+ const struct ceph_pg *raw_pgid,
+ struct ceph_osds *temp)
{
+ struct ceph_pg pgid;
struct ceph_pg_mapping *pg;
- int temp_len;
- int temp_primary;
int i;
- /* raw_pg -> pg */
- pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
- pool->pg_num_mask);
+ raw_pg_to_pg(pi, raw_pgid, &pgid);
+ ceph_osds_init(temp);
/* pg_temp? */
pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
if (pg) {
- temp_len = 0;
- temp_primary = -1;
-
for (i = 0; i < pg->pg_temp.len; i++) {
if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) {
- if (ceph_can_shift_osds(pool))
+ if (ceph_can_shift_osds(pi))
continue;
- else
- osds[temp_len++] = CRUSH_ITEM_NONE;
+
+ temp->osds[temp->size++] = CRUSH_ITEM_NONE;
} else {
- osds[temp_len++] = pg->pg_temp.osds[i];
+ temp->osds[temp->size++] = pg->pg_temp.osds[i];
}
}
/* apply pg_temp's primary */
- for (i = 0; i < temp_len; i++) {
- if (osds[i] != CRUSH_ITEM_NONE) {
- temp_primary = osds[i];
+ for (i = 0; i < temp->size; i++) {
+ if (temp->osds[i] != CRUSH_ITEM_NONE) {
+ temp->primary = temp->osds[i];
break;
}
}
- } else {
- temp_len = len;
- temp_primary = *primary;
}
/* primary_temp? */
pg = __lookup_pg_mapping(&osdmap->primary_temp, pgid);
if (pg)
- temp_primary = pg->primary_temp.osd;
-
- *primary = temp_primary;
- return temp_len;
+ temp->primary = pg->primary_temp.osd;
}
/*
- * Calculate acting set for given pgid.
+ * Map a PG to its acting set as well as its up set.
*
- * Return acting set length, or error. *primary is set to acting
- * primary osd id, or -1 if acting set is empty or on error.
+ * Acting set is used for data mapping purposes, while up set can be
+ * recorded for detecting interval changes and deciding whether to
+ * resend a request.
*/
-int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
- int *osds, int *primary)
+void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *raw_pgid,
+ struct ceph_osds *up,
+ struct ceph_osds *acting)
{
- struct ceph_pg_pool_info *pool;
+ struct ceph_pg_pool_info *pi;
u32 pps;
- int len;
- pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
- if (!pool) {
- *primary = -1;
- return -ENOENT;
+ pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool);
+ if (!pi) {
+ ceph_osds_init(up);
+ ceph_osds_init(acting);
+ goto out;
}
- if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
- /* hash pool id and seed so that pool PGs do not overlap */
- pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
- ceph_stable_mod(pgid.seed, pool->pgp_num,
- pool->pgp_num_mask),
- pgid.pool);
- } else {
- /*
- * legacy behavior: add ps and pool together. this is
- * not a great approach because the PGs from each pool
- * will overlap on top of each other: 0.5 == 1.4 ==
- * 2.3 == ...
- */
- pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
- pool->pgp_num_mask) +
- (unsigned)pgid.pool;
- }
-
- len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
- if (len < 0) {
- *primary = -1;
- return len;
+ pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps);
+ raw_to_up_osds(osdmap, pi, up);
+ apply_primary_affinity(osdmap, pi, pps, up);
+ get_temp_osds(osdmap, pi, raw_pgid, acting);
+ if (!acting->size) {
+ memcpy(acting->osds, up->osds, up->size * sizeof(up->osds[0]));
+ acting->size = up->size;
+ if (acting->primary == -1)
+ acting->primary = up->primary;
}
-
- len = raw_to_up_osds(osdmap, pool, osds, len, primary);
-
- apply_primary_affinity(osdmap, pps, pool, osds, len, primary);
-
- len = apply_temps(osdmap, pool, pgid, osds, len, primary);
-
- return len;
+out:
+ WARN_ON(!osds_valid(up) || !osds_valid(acting));
}
/*
- * Return primary osd for given pgid, or -1 if none.
+ * Return acting primary for given PG, or -1 if none.
*/
-int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
+int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *raw_pgid)
{
- int osds[CEPH_PG_MAX_SIZE];
- int primary;
-
- ceph_calc_pg_acting(osdmap, pgid, osds, &primary);
+ struct ceph_osds up, acting;
- return primary;
+ ceph_pg_to_up_acting_osds(osdmap, raw_pgid, &up, &acting);
+ return acting.primary;
}
-EXPORT_SYMBOL(ceph_calc_pg_primary);
+EXPORT_SYMBOL(ceph_pg_to_acting_primary);
diff --git a/net/compat.c b/net/compat.c
index 5cfd26a0006f..1cd2ec046164 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -309,8 +309,8 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
__scm_destroy(scm);
}
-static int do_set_attach_filter(struct socket *sock, int level, int optname,
- char __user *optval, unsigned int optlen)
+/* allocate a 64-bit sock_fprog on the user stack for duration of syscall. */
+struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval)
{
struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval;
struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog));
@@ -323,6 +323,19 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname,
__get_user(ptr, &fprog32->filter) ||
__put_user(len, &kfprog->len) ||
__put_user(compat_ptr(ptr), &kfprog->filter))
+ return NULL;
+
+ return kfprog;
+}
+EXPORT_SYMBOL_GPL(get_compat_bpf_fprog);
+
+static int do_set_attach_filter(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct sock_fprog __user *kfprog;
+
+ kfprog = get_compat_bpf_fprog(optval);
+ if (!kfprog)
return -EFAULT;
return sock_setsockopt(sock, level, optname, (char __user *)kfprog,
@@ -354,7 +367,8 @@ static int do_set_sock_timeout(struct socket *sock, int level,
static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
- if (optname == SO_ATTACH_FILTER)
+ if (optname == SO_ATTACH_FILTER ||
+ optname == SO_ATTACH_REUSEPORT_CBPF)
return do_set_attach_filter(sock, level, optname,
optval, optlen);
if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
diff --git a/net/core/filter.c b/net/core/filter.c
index 68adb5f52110..c4b330c85c02 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2085,7 +2085,8 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type)
}
static bool sk_filter_is_valid_access(int off, int size,
- enum bpf_access_type type)
+ enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
switch (off) {
case offsetof(struct __sk_buff, tc_classid):
@@ -2108,7 +2109,8 @@ static bool sk_filter_is_valid_access(int off, int size,
}
static bool tc_cls_act_is_valid_access(int off, int size,
- enum bpf_access_type type)
+ enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
if (type == BPF_WRITE) {
switch (off) {
@@ -2123,6 +2125,16 @@ static bool tc_cls_act_is_valid_access(int off, int size,
return false;
}
}
+
+ switch (off) {
+ case offsetof(struct __sk_buff, data):
+ *reg_type = PTR_TO_PACKET;
+ break;
+ case offsetof(struct __sk_buff, data_end):
+ *reg_type = PTR_TO_PACKET_END;
+ break;
+ }
+
return __is_valid_access(off, size, type);
}
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index f96ee8b9478d..be873e4e3125 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -47,6 +47,7 @@ nla_put_failure:
* @xstats_type: TLV type for backward compatibility xstats TLV
* @lock: statistics lock
* @d: dumping handle
+ * @padattr: padding attribute
*
* Initializes the dumping handle, grabs the statistic lock and appends
* an empty TLV header to the socket buffer for use a container for all
@@ -87,6 +88,7 @@ EXPORT_SYMBOL(gnet_stats_start_copy_compat);
* @type: TLV type for top level statistic TLV
* @lock: statistics lock
* @d: dumping handle
+ * @padattr: padding attribute
*
* Initializes the dumping handle, grabs the statistic lock and appends
* an empty TLV header to the socket buffer for use a container for all
diff --git a/net/core/hwbm.c b/net/core/hwbm.c
index 941c28486896..2cab489ae62e 100644
--- a/net/core/hwbm.c
+++ b/net/core/hwbm.c
@@ -55,18 +55,21 @@ int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp)
spin_lock_irqsave(&bm_pool->lock, flags);
if (bm_pool->buf_num == bm_pool->size) {
pr_warn("pool already filled\n");
+ spin_unlock_irqrestore(&bm_pool->lock, flags);
return bm_pool->buf_num;
}
if (buf_num + bm_pool->buf_num > bm_pool->size) {
pr_warn("cannot allocate %d buffers for pool\n",
buf_num);
+ spin_unlock_irqrestore(&bm_pool->lock, flags);
return 0;
}
if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) {
pr_warn("Adding %d buffers to the %d current buffers will overflow\n",
buf_num, bm_pool->buf_num);
+ spin_unlock_irqrestore(&bm_pool->lock, flags);
return 0;
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 29dd8cc22bbf..510cd62fcb99 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2469,13 +2469,17 @@ int neigh_xmit(int index, struct net_device *dev,
tbl = neigh_tables[index];
if (!tbl)
goto out;
+ rcu_read_lock_bh();
neigh = __neigh_lookup_noref(tbl, addr, dev);
if (!neigh)
neigh = __neigh_create(tbl, addr, dev, false);
err = PTR_ERR(neigh);
- if (IS_ERR(neigh))
+ if (IS_ERR(neigh)) {
+ rcu_read_unlock_bh();
goto out_kfree_skb;
+ }
err = neigh->output(neigh, skb);
+ rcu_read_unlock_bh();
}
else if (index == NEIGH_LINK_TABLE) {
err = dev_hard_header(skb, dev, ntohs(skb->protocol),
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 2b3f76fe65f4..7a0b616557ab 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -24,6 +24,7 @@
#include <linux/jiffies.h>
#include <linux/pm_runtime.h>
#include <linux/of.h>
+#include <linux/of_net.h>
#include "net-sysfs.h"
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 8604ae245960..8b02df0d354d 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2245,10 +2245,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
hrtimer_set_expires(&t.timer, spin_until);
remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer));
- if (remaining <= 0) {
- pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay);
- return;
- }
+ if (remaining <= 0)
+ goto out;
start_time = ktime_get();
if (remaining < 100000) {
@@ -2273,7 +2271,9 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
}
pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time));
+out:
pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay);
+ destroy_hrtimer_on_stack(&t.timer);
}
static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index ca207dbf673b..116187b5c267 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1289,8 +1289,8 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla,
nl802154_dev_addr_policy))
return -EINVAL;
- if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] &&
- !attrs[NL802154_DEV_ADDR_ATTR_MODE] &&
+ if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] ||
+ !attrs[NL802154_DEV_ADDR_ATTR_MODE] ||
!(attrs[NL802154_DEV_ADDR_ATTR_SHORT] ||
attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]))
return -EINVAL;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 377424ea17a4..d39e9e47a26e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1681,6 +1681,14 @@ static __net_init int inet_init_net(struct net *net)
*/
net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+
+ /* Default values for sysctl-controlled parameters.
+ * We set them here, in case sysctl is not compiled.
+ */
+ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
+ net->ipv4.sysctl_ip_dynaddr = 0;
+ net->ipv4.sysctl_ip_early_demux = 1;
+
return 0;
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 477937465a20..d95631d09248 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
void *tmp;
};
+struct esp_output_extra {
+ __be32 seqhi;
+ u32 esphoff;
+};
+
#define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
*
* TODO: Use spare space in skb for this where possible.
*/
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
{
unsigned int len;
- len = seqhilen;
+ len = extralen;
len += crypto_aead_ivsize(aead);
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
return kmalloc(len, GFP_ATOMIC);
}
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
{
- return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+ return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
}
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
{
return crypto_aead_ivsize(aead) ?
- PTR_ALIGN((u8 *)tmp + seqhilen,
- crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+ PTR_ALIGN((u8 *)tmp + extralen,
+ crypto_aead_alignmask(aead) + 1) : tmp + extralen;
}
static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
{
struct ip_esp_hdr *esph = (void *)(skb->data + offset);
void *tmp = ESP_SKB_CB(skb)->tmp;
- __be32 *seqhi = esp_tmp_seqhi(tmp);
+ __be32 *seqhi = esp_tmp_extra(tmp);
esph->seq_no = esph->spi;
esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
static void esp_output_restore_header(struct sk_buff *skb)
{
- esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+ void *tmp = ESP_SKB_CB(skb)->tmp;
+ struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+ esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+ sizeof(__be32));
}
static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
+ struct esp_output_extra *extra;
struct ip_esp_hdr *esph;
struct crypto_aead *aead;
struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
int tfclen;
int nfrags;
int assoclen;
- int seqhilen;
- __be32 *seqhi;
+ int extralen;
__be64 seqno;
/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
nfrags = err;
assoclen = sizeof(*esph);
- seqhilen = 0;
+ extralen = 0;
if (x->props.flags & XFRM_STATE_ESN) {
- seqhilen += sizeof(__be32);
- assoclen += seqhilen;
+ extralen += sizeof(*extra);
+ assoclen += sizeof(__be32);
}
- tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+ tmp = esp_alloc_tmp(aead, nfrags, extralen);
if (!tmp) {
err = -ENOMEM;
goto error;
}
- seqhi = esp_tmp_seqhi(tmp);
- iv = esp_tmp_iv(aead, tmp, seqhilen);
+ extra = esp_tmp_extra(tmp);
+ iv = esp_tmp_iv(aead, tmp, extralen);
req = esp_tmp_req(aead, iv);
sg = esp_req_sg(aead, req);
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
* encryption.
*/
if ((x->props.flags & XFRM_STATE_ESN)) {
- esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
- *seqhi = esph->spi;
+ extra->esphoff = (unsigned char *)esph -
+ skb_transport_header(skb);
+ esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+ extra->seqhi = esph->spi;
esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
aead_request_set_callback(req, 0, esp_output_done_esn, skb);
}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
goto out;
ESP_SKB_CB(skb)->tmp = tmp;
- seqhi = esp_tmp_seqhi(tmp);
+ seqhi = esp_tmp_extra(tmp);
iv = esp_tmp_iv(aead, tmp, seqhilen);
req = esp_tmp_req(aead, iv);
sg = esp_req_sg(aead, req);
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 4c39f4fd332a..de1d119a4497 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -62,26 +62,26 @@ EXPORT_SYMBOL_GPL(gre_del_protocol);
/* Fills in tpi and returns header length to be pulled. */
int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
- bool *csum_err, __be16 proto)
+ bool *csum_err, __be16 proto, int nhs)
{
const struct gre_base_hdr *greh;
__be32 *options;
int hdr_len;
- if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
+ if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr))))
return -EINVAL;
- greh = (struct gre_base_hdr *)skb_transport_header(skb);
+ greh = (struct gre_base_hdr *)(skb->data + nhs);
if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
return -EINVAL;
tpi->flags = gre_flags_to_tnl_flags(greh->flags);
hdr_len = gre_calc_hlen(tpi->flags);
- if (!pskb_may_pull(skb, hdr_len))
+ if (!pskb_may_pull(skb, nhs + hdr_len))
return -EINVAL;
- greh = (struct gre_base_hdr *)skb_transport_header(skb);
+ greh = (struct gre_base_hdr *)(skb->data + nhs);
tpi->proto = greh->protocol;
options = (__be32 *)(greh + 1);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 4d2025f7ec57..1d000af7f561 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -49,12 +49,6 @@
#include <net/gre.h>
#include <net/dst_metadata.h>
-#if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/ip6_fib.h>
-#include <net/ip6_route.h>
-#endif
-
/*
Problems & solutions
--------------------
@@ -217,12 +211,14 @@ static void gre_err(struct sk_buff *skb, u32 info)
* by themselves???
*/
+ const struct iphdr *iph = (struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct tnl_ptk_info tpi;
bool csum_err = false;
- if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP)) < 0) {
+ if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP),
+ iph->ihl * 4) < 0) {
if (!csum_err) /* ignore csum errors. */
return;
}
@@ -338,7 +334,7 @@ static int gre_rcv(struct sk_buff *skb)
}
#endif
- hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP));
+ hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0);
if (hdr_len < 0)
goto drop;
@@ -1121,6 +1117,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
{
struct nlattr *tb[IFLA_MAX + 1];
struct net_device *dev;
+ LIST_HEAD(list_kill);
struct ip_tunnel *t;
int err;
@@ -1136,8 +1133,10 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
t->collect_md = true;
err = ipgre_newlink(net, dev, tb, NULL);
- if (err < 0)
- goto out;
+ if (err < 0) {
+ free_netdev(dev);
+ return ERR_PTR(err);
+ }
/* openvswitch users expect packet sizes to be unrestricted,
* so set the largest MTU we can.
@@ -1146,9 +1145,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
if (err)
goto out;
+ err = rtnl_configure_link(dev, NULL);
+ if (err < 0)
+ goto out;
+
return dev;
out:
- free_netdev(dev);
+ ip_tunnel_dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(gretap_fb_dev_create);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 2ed9dd2b5f2f..1d71c40eaaf3 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -127,7 +127,9 @@ __be32 ic_myaddr = NONE; /* My IP address */
static __be32 ic_netmask = NONE; /* Netmask for local subnet */
__be32 ic_gateway = NONE; /* Gateway IP address */
-__be32 ic_addrservaddr = NONE; /* IP Address of the IP addresses'server */
+#ifdef IPCONFIG_DYNAMIC
+static __be32 ic_addrservaddr = NONE; /* IP Address of the IP addresses'server */
+#endif
__be32 ic_servaddr = NONE; /* Boot server IP address */
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 21a38e296fe2..5ad48ec77710 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -891,8 +891,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
{
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
- if (c)
+ if (c) {
+ c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXVIFS;
+ }
return c;
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index bb0419582b8d..1cb67de106fe 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -999,10 +999,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
if (!net->ipv4.sysctl_local_reserved_ports)
goto err_ports;
- net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
- net->ipv4.sysctl_ip_dynaddr = 0;
- net->ipv4.sysctl_ip_early_demux = 1;
-
return 0;
err_ports:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8bd9911fdd16..e00e972c4e6a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2751,7 +2751,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
struct sk_buff *hole = NULL;
- u32 last_lost;
+ u32 max_segs, last_lost;
int mib_idx;
int fwd_rexmitting = 0;
@@ -2771,6 +2771,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
last_lost = tp->snd_una;
}
+ max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk));
tcp_for_write_queue_from(skb, sk) {
__u8 sacked = TCP_SKB_CB(skb)->sacked;
int segs;
@@ -2784,6 +2785,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
segs = tp->snd_cwnd - tcp_packets_in_flight(tp);
if (segs <= 0)
return;
+ /* In case tcp_shift_skb_data() have aggregated large skbs,
+ * we need to make sure not sending too bigs TSO packets
+ */
+ segs = min_t(int, segs, max_segs);
if (fwd_rexmitting) {
begin_fwd:
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d56c0559b477..ca5e8ea29538 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -391,9 +391,9 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr);
}
-static inline int compute_score(struct sock *sk, struct net *net,
- __be32 saddr, unsigned short hnum, __be16 sport,
- __be32 daddr, __be16 dport, int dif)
+static int compute_score(struct sock *sk, struct net *net,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum, int dif)
{
int score;
struct inet_sock *inet;
@@ -434,52 +434,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
-/*
- * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num)
- */
-static inline int compute_score2(struct sock *sk, struct net *net,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned int hnum, int dif)
-{
- int score;
- struct inet_sock *inet;
-
- if (!net_eq(sock_net(sk), net) ||
- ipv6_only_sock(sk))
- return -1;
-
- inet = inet_sk(sk);
-
- if (inet->inet_rcv_saddr != daddr ||
- inet->inet_num != hnum)
- return -1;
-
- score = (sk->sk_family == PF_INET) ? 2 : 1;
-
- if (inet->inet_daddr) {
- if (inet->inet_daddr != saddr)
- return -1;
- score += 4;
- }
-
- if (inet->inet_dport) {
- if (inet->inet_dport != sport)
- return -1;
- score += 4;
- }
-
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
- score += 4;
- }
-
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
- score++;
-
- return score;
-}
-
static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
const __u16 lport, const __be32 faddr,
const __be16 fport)
@@ -492,11 +446,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
udp_ehash_secret + net_hash_mix(net));
}
-/* called with read_rcu_lock() */
+/* called with rcu_read_lock() */
static struct sock *udp4_lib_lookup2(struct net *net,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned int hnum, int dif,
- struct udp_hslot *hslot2, unsigned int slot2,
+ struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
@@ -506,7 +460,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
result = NULL;
badness = 0;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- score = compute_score2(sk, net, saddr, sport,
+ score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
@@ -554,17 +508,22 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
result = udp4_lib_lookup2(net, saddr, sport,
daddr, hnum, dif,
- hslot2, slot2, skb);
+ hslot2, skb);
if (!result) {
+ unsigned int old_slot2 = slot2;
hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
slot2 = hash2 & udptable->mask;
+ /* avoid searching the same slot again. */
+ if (unlikely(slot2 == old_slot2))
+ return result;
+
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
result = udp4_lib_lookup2(net, saddr, sport,
- htonl(INADDR_ANY), hnum, dif,
- hslot2, slot2, skb);
+ daddr, hnum, dif,
+ hslot2, skb);
}
return result;
}
@@ -572,8 +531,8 @@ begin:
result = NULL;
badness = 0;
sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, saddr, hnum, sport,
- daddr, dport, dif);
+ score = compute_score(sk, net, saddr, sport,
+ daddr, hnum, dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
@@ -1618,12 +1577,12 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
}
- if (rcu_access_pointer(sk->sk_filter)) {
- if (udp_lib_checksum_complete(skb))
+ if (rcu_access_pointer(sk->sk_filter) &&
+ udp_lib_checksum_complete(skb))
goto csum_error;
- if (sk_filter(sk, skb))
- goto drop;
- }
+
+ if (sk_filter(sk, skb))
+ goto drop;
udp_csum_pull_header(skb);
if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
@@ -1755,8 +1714,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
return err;
}
- return skb_checksum_init_zero_check(skb, proto, uh->check,
- inet_compute_pseudo);
+ /* Note, we are only interested in != 0 or == 0, thus the
+ * force to int.
+ */
+ return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+ inet_compute_pseudo);
}
/*
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 3f8411328de5..2343e4f2e0bf 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -232,6 +232,15 @@ config IPV6_GRE
Saying M here will produce a module called ip6_gre. If unsure, say N.
+config IPV6_FOU
+ tristate
+ default NET_FOU && IPV6
+
+config IPV6_FOU_TUNNEL
+ tristate
+ default NET_FOU_IP_TUNNELS && IPV6_FOU
+ select IPV6_TUNNEL
+
config IPV6_MULTIPLE_TABLES
bool "IPv6: Multiple Routing Tables"
select FIB_RULES
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 7ec3129c9ace..6d8ea099213e 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -42,7 +42,7 @@ obj-$(CONFIG_IPV6_VTI) += ip6_vti.o
obj-$(CONFIG_IPV6_SIT) += sit.o
obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
obj-$(CONFIG_IPV6_GRE) += ip6_gre.o
-obj-$(CONFIG_NET_FOU) += fou6.o
+obj-$(CONFIG_IPV6_FOU) += fou6.o
obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o
obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload)
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index c972d0b52579..9ea249b9451e 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -69,7 +69,7 @@ int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
}
EXPORT_SYMBOL(gue6_build_header);
-#ifdef CONFIG_NET_FOU_IP_TUNNELS
+#if IS_ENABLED(CONFIG_IPV6_FOU_TUNNEL)
static const struct ip6_tnl_encap_ops fou_ip6tun_ops = {
.encap_hlen = fou_encap_hlen,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4527285fcaa2..a4fa84076969 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -98,7 +98,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
- ping_err(skb, offset, info);
+ ping_err(skb, offset, ntohl(info));
}
static int icmpv6_rcv(struct sk_buff *skb);
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index b2025bf3da4a..c0cbcb259f5a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -78,9 +78,12 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
* we accept a checksum of zero here. When we find the socket
* for the UDP packet we'll check if that socket allows zero checksum
* for IPv6 (set by socket option).
+ *
+ * Note, we are only interested in != 0 or == 0, thus the
+ * force to int.
*/
- return skb_checksum_init_zero_check(skb, proto, uh->check,
- ip6_compute_pseudo);
+ return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+ ip6_compute_pseudo);
}
EXPORT_SYMBOL(udp6_csum_init);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index af503f518278..776d145113e1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -468,7 +468,7 @@ static int gre_rcv(struct sk_buff *skb)
bool csum_err = false;
int hdr_len;
- hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6));
+ hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6), 0);
if (hdr_len < 0)
goto drop;
@@ -712,6 +712,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
fl6->daddr = p->raddr;
fl6->flowi6_oif = p->link;
fl6->flowlabel = 0;
+ fl6->flowi6_proto = IPPROTO_GRE;
if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
@@ -1027,6 +1028,8 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ dev->mtu -= ETH_HLEN;
if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
@@ -1253,6 +1256,8 @@ static int ip6gre_tap_init(struct net_device *dev)
if (ret)
return ret;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
tunnel = netdev_priv(dev);
ip6gre_tnl_link_config(tunnel, 1);
@@ -1286,6 +1291,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
}
static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index cbf127ae7c67..635b8d340cdb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1071,17 +1071,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst)
{
struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
- int err;
dst = ip6_sk_dst_check(sk, dst, fl6);
+ if (!dst)
+ dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
- err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
- if (err)
- return ERR_PTR(err);
- if (final_dst)
- fl6->daddr = *final_dst;
-
- return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+ return dst;
}
EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f2e2013f8346..487ef3bc7bbc 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1074,6 +1074,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (!c)
return NULL;
+ c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXMIFS;
return c;
}
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 6989c70ae29f..4a84b5ad9ecb 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -33,6 +33,7 @@ static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb,
fl6.daddr = *gw;
fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
(iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
+ fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 969913da494f..520b7884d0c2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1782,7 +1782,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
};
struct fib6_table *table;
struct rt6_info *rt;
- int flags = 0;
+ int flags = RT6_LOOKUP_F_IFACE;
table = fib6_get_table(net, cfg->fc_table);
if (!table)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0a5a255277e5..0619ac70836d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -560,13 +560,13 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, IPPROTO_IPV6, 0);
+ t->parms.link, 0, iph->protocol, 0);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
- IPPROTO_IPV6, 0);
+ iph->protocol, 0);
err = 0;
goto out;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 79e33e02f11a..2255d2bf5f6b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -738,7 +738,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr,
int oif, struct tcp_md5sig_key *key, int rst,
- u8 tclass, u32 label)
+ u8 tclass, __be32 label)
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcphdr *t1;
@@ -911,7 +911,7 @@ out:
static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key, u8 tclass,
- u32 label)
+ __be32 label)
{
tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
tclass, label);
@@ -1721,7 +1721,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
destp = ntohs(inet->inet_dport);
srcp = ntohs(inet->inet_sport);
- if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+ if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2da1896af934..005dc82c2138 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -115,11 +115,10 @@ static void udp_v6_rehash(struct sock *sk)
udp_lib_rehash(sk, new_hash);
}
-static inline int compute_score(struct sock *sk, struct net *net,
- unsigned short hnum,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, __be16 dport,
- int dif)
+static int compute_score(struct sock *sk, struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, unsigned short hnum,
+ int dif)
{
int score;
struct inet_sock *inet;
@@ -162,54 +161,11 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
-static inline int compute_score2(struct sock *sk, struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr,
- unsigned short hnum, int dif)
-{
- int score;
- struct inet_sock *inet;
-
- if (!net_eq(sock_net(sk), net) ||
- udp_sk(sk)->udp_port_hash != hnum ||
- sk->sk_family != PF_INET6)
- return -1;
-
- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
- return -1;
-
- score = 0;
- inet = inet_sk(sk);
-
- if (inet->inet_dport) {
- if (inet->inet_dport != sport)
- return -1;
- score++;
- }
-
- if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
- return -1;
- score++;
- }
-
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
- score++;
- }
-
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
- score++;
-
- return score;
-}
-
-/* called with read_rcu_lock() */
+/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned int hnum, int dif,
- struct udp_hslot *hslot2, unsigned int slot2,
+ struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
@@ -219,7 +175,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
result = NULL;
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- score = compute_score2(sk, net, saddr, sport,
+ score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
@@ -268,17 +224,22 @@ struct sock *__udp6_lib_lookup(struct net *net,
result = udp6_lib_lookup2(net, saddr, sport,
daddr, hnum, dif,
- hslot2, slot2, skb);
+ hslot2, skb);
if (!result) {
+ unsigned int old_slot2 = slot2;
hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
slot2 = hash2 & udptable->mask;
+ /* avoid searching the same slot again. */
+ if (unlikely(slot2 == old_slot2))
+ return result;
+
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
result = udp6_lib_lookup2(net, saddr, sport,
- &in6addr_any, hnum, dif,
- hslot2, slot2, skb);
+ daddr, hnum, dif,
+ hslot2, skb);
}
return result;
}
@@ -286,7 +247,7 @@ begin:
result = NULL;
badness = -1;
sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
+ score = compute_score(sk, net, saddr, sport, daddr, hnum, dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
@@ -653,12 +614,12 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
}
- if (rcu_access_pointer(sk->sk_filter)) {
- if (udp_lib_checksum_complete(skb))
- goto csum_error;
- if (sk_filter(sk, skb))
- goto drop;
- }
+ if (rcu_access_pointer(sk->sk_filter) &&
+ udp_lib_checksum_complete(skb))
+ goto csum_error;
+
+ if (sk_filter(sk, skb))
+ goto drop;
udp_csum_pull_header(skb);
if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
index 738008726cc6..fda7f4715c58 100644
--- a/net/kcm/kcmproc.c
+++ b/net/kcm/kcmproc.c
@@ -241,6 +241,7 @@ static const struct file_operations kcm_seq_fops = {
.open = kcm_seq_open,
.read = seq_read,
.llseek = seq_lseek,
+ .release = seq_release_net,
};
static struct kcm_seq_muxinfo kcm_seq_muxinfo = {
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6edfa9980314..1e40dacaa137 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1581,7 +1581,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
tunnel->encap = encap;
if (encap == L2TP_ENCAPTYPE_UDP) {
- struct udp_tunnel_sock_cfg udp_cfg;
+ struct udp_tunnel_sock_cfg udp_cfg = { };
udp_cfg.sk_user_data = tunnel;
udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index c6f5df1bed12..6c54e03fe9c1 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -128,6 +128,7 @@ static inline struct sock *l2tp_ip6_bind_lookup(struct net *net,
*/
static int l2tp_ip6_recv(struct sk_buff *skb)
{
+ struct net *net = dev_net(skb->dev);
struct sock *sk;
u32 session_id;
u32 tunnel_id;
@@ -154,7 +155,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(&init_net, NULL, session_id);
+ session = l2tp_session_find(net, NULL, session_id);
if (session == NULL)
goto discard;
@@ -188,14 +189,14 @@ pass_up:
goto discard;
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
- tunnel = l2tp_tunnel_find(&init_net, tunnel_id);
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
if (tunnel != NULL)
sk = tunnel->sock;
else {
struct ipv6hdr *iph = ipv6_hdr(skb);
read_lock_bh(&l2tp_ip6_lock);
- sk = __l2tp_ip6_bind_lookup(&init_net, &iph->daddr,
+ sk = __l2tp_ip6_bind_lookup(net, &iph->daddr,
0, tunnel_id);
read_unlock_bh(&l2tp_ip6_lock);
}
@@ -263,6 +264,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr;
+ struct net *net = sock_net(sk);
__be32 v4addr = 0;
int addr_type;
int err;
@@ -286,7 +288,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
err = -EADDRINUSE;
read_lock_bh(&l2tp_ip6_lock);
- if (__l2tp_ip6_bind_lookup(&init_net, &addr->l2tp_addr,
+ if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr,
sk->sk_bound_dev_if, addr->l2tp_conn_id))
goto out_in_use;
read_unlock_bh(&l2tp_ip6_lock);
@@ -456,7 +458,7 @@ static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb)
return 0;
drop:
- IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
kfree_skb(skb);
return -1;
}
diff --git a/net/lapb/lapb_in.c b/net/lapb/lapb_in.c
index 5dba899131b3..182470847fcf 100644
--- a/net/lapb/lapb_in.c
+++ b/net/lapb/lapb_in.c
@@ -444,10 +444,9 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb,
break;
case LAPB_FRMR:
- lapb_dbg(1, "(%p) S3 RX FRMR(%d) %02X %02X %02X %02X %02X\n",
+ lapb_dbg(1, "(%p) S3 RX FRMR(%d) %5ph\n",
lapb->dev, frame->pf,
- skb->data[0], skb->data[1], skb->data[2],
- skb->data[3], skb->data[4]);
+ skb->data);
lapb_establish_data_link(lapb);
lapb_dbg(0, "(%p) S3 -> S1\n", lapb->dev);
lapb_requeue_frames(lapb);
diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c
index ba4d015bd1a6..482c94d9d958 100644
--- a/net/lapb/lapb_out.c
+++ b/net/lapb/lapb_out.c
@@ -148,9 +148,7 @@ void lapb_transmit_buffer(struct lapb_cb *lapb, struct sk_buff *skb, int type)
}
}
- lapb_dbg(2, "(%p) S%d TX %02X %02X %02X\n",
- lapb->dev, lapb->state,
- skb->data[0], skb->data[1], skb->data[2]);
+ lapb_dbg(2, "(%p) S%d TX %3ph\n", lapb->dev, lapb->state, skb->data);
if (!lapb_data_transmit(lapb, skb))
kfree_skb(skb);
diff --git a/net/lapb/lapb_subr.c b/net/lapb/lapb_subr.c
index 9d0a426eccbb..3c1914df641f 100644
--- a/net/lapb/lapb_subr.c
+++ b/net/lapb/lapb_subr.c
@@ -113,9 +113,7 @@ int lapb_decode(struct lapb_cb *lapb, struct sk_buff *skb,
{
frame->type = LAPB_ILLEGAL;
- lapb_dbg(2, "(%p) S%d RX %02X %02X %02X\n",
- lapb->dev, lapb->state,
- skb->data[0], skb->data[1], skb->data[2]);
+ lapb_dbg(2, "(%p) S%d RX %3ph\n", lapb->dev, lapb->state, skb->data);
/* We always need to look at 2 bytes, sometimes we need
* to look at 3 and those cases are handled below.
@@ -284,10 +282,9 @@ void lapb_transmit_frmr(struct lapb_cb *lapb)
dptr++;
*dptr++ = lapb->frmr_type;
- lapb_dbg(1, "(%p) S%d TX FRMR %02X %02X %02X %02X %02X\n",
+ lapb_dbg(1, "(%p) S%d TX FRMR %5ph\n",
lapb->dev, lapb->state,
- skb->data[1], skb->data[2], skb->data[3],
- skb->data[4], skb->data[5]);
+ &skb->data[1]);
} else {
dptr = skb_put(skb, 4);
*dptr++ = LAPB_FRMR;
@@ -299,9 +296,8 @@ void lapb_transmit_frmr(struct lapb_cb *lapb)
dptr++;
*dptr++ = lapb->frmr_type;
- lapb_dbg(1, "(%p) S%d TX FRMR %02X %02X %02X\n",
- lapb->dev, lapb->state, skb->data[1],
- skb->data[2], skb->data[3]);
+ lapb_dbg(1, "(%p) S%d TX FRMR %3ph\n",
+ lapb->dev, lapb->state, &skb->data[1]);
}
lapb_transmit_buffer(lapb, skb, LAPB_RESPONSE);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 4c6404e1ad6e..6a1603bcdced 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -148,19 +148,26 @@ u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata)
void mesh_sta_cleanup(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
- u32 changed;
+ u32 changed = 0;
/*
* maybe userspace handles peer allocation and peering, but in either
* case the beacon is still generated by the kernel and we might need
* an update.
*/
- changed = mesh_accept_plinks_update(sdata);
+ if (sdata->u.mesh.user_mpm &&
+ sta->mesh->plink_state == NL80211_PLINK_ESTAB)
+ changed |= mesh_plink_dec_estab_count(sdata);
+ changed |= mesh_accept_plinks_update(sdata);
if (!sdata->u.mesh.user_mpm) {
changed |= mesh_plink_deactivate(sta);
del_timer_sync(&sta->mesh->plink_timer);
}
+ /* make sure no readers can access nexthop sta from here on */
+ mesh_path_flush_by_nexthop(sta);
+ synchronize_net();
+
if (changed)
ieee80211_mbss_info_change_notify(sdata, changed);
}
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index c8b8ccc370eb..78b0ef32dddd 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -280,7 +280,7 @@ struct ieee80211_fast_tx {
u8 sa_offs, da_offs, pn_offs;
u8 band;
u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
- sizeof(rfc1042_header)];
+ sizeof(rfc1042_header)] __aligned(2);
struct rcu_head rcu_head;
};
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 2cb3c626cd43..096a45103f14 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -762,7 +762,7 @@ static int expire_quiescent_template(struct netns_ipvs *ipvs,
* If available, return 1, otherwise invalidate this connection
* template and return 0.
*/
-int ip_vs_check_template(struct ip_vs_conn *ct)
+int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest)
{
struct ip_vs_dest *dest = ct->dest;
struct netns_ipvs *ipvs = ct->ipvs;
@@ -772,7 +772,8 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
*/
if ((dest == NULL) ||
!(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
- expire_quiescent_template(ipvs, dest)) {
+ expire_quiescent_template(ipvs, dest) ||
+ (cdest && (dest != cdest))) {
IP_VS_DBG_BUF(9, "check_template: dest not available for "
"protocol %s s:%s:%d v:%s:%d "
"-> d:%s:%d\n",
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1207f20d24e4..2c1b498a7a27 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -321,7 +321,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
/* Check if a template already exists */
ct = ip_vs_ct_in_get(&param);
- if (!ct || !ip_vs_check_template(ct)) {
+ if (!ct || !ip_vs_check_template(ct, NULL)) {
struct ip_vs_scheduler *sched;
/*
@@ -1154,7 +1154,8 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
vport, &param) < 0)
return NULL;
ct = ip_vs_ct_in_get(&param);
- if (!ct) {
+ /* check if template exists and points to the same dest */
+ if (!ct || !ip_vs_check_template(ct, dest)) {
ct = ip_vs_conn_new(&param, dest->af, daddr, dport,
IP_VS_CONN_F_TEMPLATE, dest, 0);
if (!ct) {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index db2312eeb2a4..f204274a9b6b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1544,6 +1544,8 @@ void nf_conntrack_cleanup_end(void)
nf_conntrack_tstamp_fini();
nf_conntrack_acct_fini();
nf_conntrack_expect_fini();
+
+ kmem_cache_destroy(nf_conntrack_cachep);
}
/*
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 883c691ec8d0..19efeba02abb 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -632,6 +632,7 @@ static int __init nf_conntrack_ftp_init(void)
if (ret) {
pr_err("failed to register helper for pf: %d port: %d\n",
ftp[i][j].tuple.src.l3num, ports[i]);
+ ports_c = i;
nf_conntrack_ftp_fini();
return ret;
}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index f703adb7e5f7..196cb39649e1 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -361,9 +361,10 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_log);
int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
{
- int ret = 0;
- struct nf_conntrack_helper *cur;
+ struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
unsigned int h = helper_hash(&me->tuple);
+ struct nf_conntrack_helper *cur;
+ int ret = 0;
BUG_ON(me->expect_policy == NULL);
BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
@@ -371,9 +372,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
mutex_lock(&nf_ct_helper_mutex);
hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
- if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 &&
- cur->tuple.src.l3num == me->tuple.src.l3num &&
- cur->tuple.dst.protonum == me->tuple.dst.protonum) {
+ if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) {
ret = -EEXIST;
goto out;
}
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 8b6da2719600..f97ac61d2536 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -271,6 +271,7 @@ static int __init nf_conntrack_irc_init(void)
if (ret) {
pr_err("failed to register helper for pf: %u port: %u\n",
irc[i].tuple.src.l3num, ports[i]);
+ ports_c = i;
nf_conntrack_irc_fini();
return ret;
}
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 7523a575f6d1..3fcbaab83b3d 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -223,6 +223,7 @@ static int __init nf_conntrack_sane_init(void)
if (ret) {
pr_err("failed to register helper for pf: %d port: %d\n",
sane[i][j].tuple.src.l3num, ports[i]);
+ ports_c = i;
nf_conntrack_sane_fini();
return ret;
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 3e06402739e0..f72ba5587588 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1669,6 +1669,7 @@ static int __init nf_conntrack_sip_init(void)
if (ret) {
pr_err("failed to register helper for pf: %u port: %u\n",
sip[i][j].tuple.src.l3num, ports[i]);
+ ports_c = i;
nf_conntrack_sip_fini();
return ret;
}
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index f87e84ebcec3..c026c472ea80 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -487,8 +487,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
{ }
};
-#define NET_NF_CONNTRACK_MAX 2089
-
static struct ctl_table nf_ct_netfilter_table[] = {
{
.procname = "nf_conntrack_max",
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index 36f964066461..2e65b5430fba 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -142,6 +142,7 @@ static int __init nf_conntrack_tftp_init(void)
if (ret) {
pr_err("failed to register helper for pf: %u port: %u\n",
tftp[i][j].tuple.src.l3num, ports[i]);
+ ports_c = i;
nf_conntrack_tftp_fini();
return ret;
}
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5baa8e24e6ac..b19ad20a705c 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -26,23 +26,21 @@
* Once the queue is registered it must reinject all packets it
* receives, no matter what.
*/
-static const struct nf_queue_handler __rcu *queue_handler __read_mostly;
/* return EBUSY when somebody else is registered, return EEXIST if the
* same handler is registered, return 0 in case of success. */
-void nf_register_queue_handler(const struct nf_queue_handler *qh)
+void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh)
{
/* should never happen, we only have one queueing backend in kernel */
- WARN_ON(rcu_access_pointer(queue_handler));
- rcu_assign_pointer(queue_handler, qh);
+ WARN_ON(rcu_access_pointer(net->nf.queue_handler));
+ rcu_assign_pointer(net->nf.queue_handler, qh);
}
EXPORT_SYMBOL(nf_register_queue_handler);
/* The caller must flush their queue before this */
-void nf_unregister_queue_handler(void)
+void nf_unregister_queue_handler(struct net *net)
{
- RCU_INIT_POINTER(queue_handler, NULL);
- synchronize_rcu();
+ RCU_INIT_POINTER(net->nf.queue_handler, NULL);
}
EXPORT_SYMBOL(nf_unregister_queue_handler);
@@ -103,7 +101,7 @@ void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops)
const struct nf_queue_handler *qh;
rcu_read_lock();
- qh = rcu_dereference(queue_handler);
+ qh = rcu_dereference(net->nf.queue_handler);
if (qh)
qh->nf_hook_drop(net, ops);
rcu_read_unlock();
@@ -122,9 +120,10 @@ int nf_queue(struct sk_buff *skb,
struct nf_queue_entry *entry = NULL;
const struct nf_afinfo *afinfo;
const struct nf_queue_handler *qh;
+ struct net *net = state->net;
/* QUEUE == DROP if no one is waiting, to be safe. */
- qh = rcu_dereference(queue_handler);
+ qh = rcu_dereference(net->nf.queue_handler);
if (!qh) {
status = -ESRCH;
goto err;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4d292b933b5c..2c881871db38 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2647,6 +2647,8 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
/* Only accept unspec with dump */
if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
return -EAFNOSUPPORT;
+ if (!nla[NFTA_SET_TABLE])
+ return -EINVAL;
set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
if (IS_ERR(set))
@@ -2944,24 +2946,20 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
* jumps are already validated for that chain.
*/
list_for_each_entry(i, &set->bindings, list) {
- if (binding->flags & NFT_SET_MAP &&
+ if (i->flags & NFT_SET_MAP &&
i->chain == binding->chain)
goto bind;
}
+ iter.genmask = nft_genmask_next(ctx->net);
iter.skip = 0;
iter.count = 0;
iter.err = 0;
iter.fn = nf_tables_bind_check_setelem;
set->ops->walk(ctx, set, &iter);
- if (iter.err < 0) {
- /* Destroy anonymous sets if binding fails */
- if (set->flags & NFT_SET_ANONYMOUS)
- nf_tables_set_destroy(ctx, set);
-
+ if (iter.err < 0)
return iter.err;
- }
}
bind:
binding->chain = ctx->chain;
@@ -3190,12 +3188,13 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
if (nest == NULL)
goto nla_put_failure;
- args.cb = cb;
- args.skb = skb;
- args.iter.skip = cb->args[0];
- args.iter.count = 0;
- args.iter.err = 0;
- args.iter.fn = nf_tables_dump_setelem;
+ args.cb = cb;
+ args.skb = skb;
+ args.iter.genmask = nft_genmask_cur(ctx.net);
+ args.iter.skip = cb->args[0];
+ args.iter.count = 0;
+ args.iter.err = 0;
+ args.iter.fn = nf_tables_dump_setelem;
set->ops->walk(&ctx, set, &args.iter);
nla_nest_end(skb, nest);
@@ -4282,6 +4281,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
binding->chain != chain)
continue;
+ iter.genmask = nft_genmask_next(ctx->net);
iter.skip = 0;
iter.count = 0;
iter.err = 0;
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index e9f8dffcc244..fb8b5892b5ff 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -143,7 +143,7 @@ next_rule:
list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
/* This rule is not active, skip. */
- if (unlikely(rule->genmask & (1 << gencursor)))
+ if (unlikely(rule->genmask & gencursor))
continue;
rulenum++;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index aa93877ab6e2..5d36a0926b4a 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -557,7 +557,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
if (entskb->tstamp.tv64) {
struct nfqnl_msg_packet_timestamp ts;
- struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
+ struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
ts.sec = cpu_to_be64(kts.tv_sec);
ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);
@@ -1482,21 +1482,29 @@ static int __net_init nfnl_queue_net_init(struct net *net)
net->nf.proc_netfilter, &nfqnl_file_ops))
return -ENOMEM;
#endif
+ nf_register_queue_handler(net, &nfqh);
return 0;
}
static void __net_exit nfnl_queue_net_exit(struct net *net)
{
+ nf_unregister_queue_handler(net);
#ifdef CONFIG_PROC_FS
remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter);
#endif
}
+static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list)
+{
+ synchronize_rcu();
+}
+
static struct pernet_operations nfnl_queue_net_ops = {
- .init = nfnl_queue_net_init,
- .exit = nfnl_queue_net_exit,
- .id = &nfnl_queue_net_id,
- .size = sizeof(struct nfnl_queue_net),
+ .init = nfnl_queue_net_init,
+ .exit = nfnl_queue_net_exit,
+ .exit_batch = nfnl_queue_net_exit_batch,
+ .id = &nfnl_queue_net_id,
+ .size = sizeof(struct nfnl_queue_net),
};
static int __init nfnetlink_queue_init(void)
@@ -1517,7 +1525,6 @@ static int __init nfnetlink_queue_init(void)
}
register_netdevice_notifier(&nfqnl_dev_notifier);
- nf_register_queue_handler(&nfqh);
return status;
cleanup_netlink_notifier:
@@ -1529,7 +1536,6 @@ out:
static void __exit nfnetlink_queue_fini(void)
{
- nf_unregister_queue_handler();
unregister_netdevice_notifier(&nfqnl_dev_notifier);
nfnetlink_subsys_unregister(&nfqnl_subsys);
netlink_unregister_notifier(&nfqnl_rtnl_notifier);
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 6fa016564f90..f39c53a159eb 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -189,7 +189,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
struct nft_hash_elem *he;
struct rhashtable_iter hti;
struct nft_set_elem elem;
- u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
int err;
err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL);
@@ -218,7 +217,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
goto cont;
if (nft_set_elem_expired(&he->ext))
goto cont;
- if (!nft_set_elem_active(&he->ext, genmask))
+ if (!nft_set_elem_active(&he->ext, iter->genmask))
goto cont;
elem.priv = he;
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index f762094af7c1..7201d57b5a93 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -211,7 +211,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
struct nft_rbtree_elem *rbe;
struct nft_set_elem elem;
struct rb_node *node;
- u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
spin_lock_bh(&nft_rbtree_lock);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
@@ -219,7 +218,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
if (iter->count < iter->skip)
goto cont;
- if (!nft_set_elem_active(&rbe->ext, genmask))
+ if (!nft_set_elem_active(&rbe->ext, iter->genmask))
goto cont;
elem.priv = rbe;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index c69c892231d7..2675d580c490 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -612,7 +612,7 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems,
return -EINVAL;
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
- target_offset + sizeof(struct compat_xt_standard_target) != next_offset)
+ COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
return -EINVAL;
/* compat_xt_entry match has less strict aligment requirements,
@@ -694,7 +694,7 @@ int xt_check_entry_offsets(const void *base,
return -EINVAL;
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
- target_offset + sizeof(struct xt_standard_target) != next_offset)
+ XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
return -EINVAL;
return xt_check_entry_match(elems, base + target_offset,
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 879185fe183f..9a3eb7a0ebf4 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -137,11 +137,23 @@ static bool is_flow_key_valid(const struct sw_flow_key *key)
return !!key->eth.type;
}
+static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
+ __be16 ethertype)
+{
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ __be16 diff[] = { ~(hdr->h_proto), ethertype };
+
+ skb->csum = ~csum_partial((char *)diff, sizeof(diff),
+ ~skb->csum);
+ }
+
+ hdr->h_proto = ethertype;
+}
+
static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_mpls *mpls)
{
__be32 *new_mpls_lse;
- struct ethhdr *hdr;
/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
if (skb->encapsulation)
@@ -160,9 +172,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
- hdr = eth_hdr(skb);
- hdr->h_proto = mpls->mpls_ethertype;
-
+ update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
if (!skb->inner_protocol)
skb_set_inner_protocol(skb, skb->protocol);
skb->protocol = mpls->mpls_ethertype;
@@ -193,7 +203,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
* field correctly in the presence of VLAN tags.
*/
hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
- hdr->h_proto = ethertype;
+ update_ethertype(skb, hdr, ethertype);
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3d5feede962d..d84312584ee4 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -818,8 +818,18 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
*/
state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED;
__ovs_ct_update_key(key, state, &info->zone, exp->master);
- } else
- return __ovs_ct_lookup(net, key, info, skb);
+ } else {
+ struct nf_conn *ct;
+ int err;
+
+ err = __ovs_ct_lookup(net, key, info, skb);
+ if (err)
+ return err;
+
+ ct = (struct nf_conn *)skb->nfct;
+ if (ct)
+ nf_ct_deliver_cached_events(ct);
+ }
return 0;
}
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4040eb92d9c9..9bff6ef16fa7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -93,6 +93,7 @@
#include <net/inet_common.h>
#endif
#include <linux/bpf.h>
+#include <net/compat.h>
#include "internal.h"
@@ -3940,6 +3941,27 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
}
+#ifdef CONFIG_COMPAT
+static int compat_packet_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct packet_sock *po = pkt_sk(sock->sk);
+
+ if (level != SOL_PACKET)
+ return -ENOPROTOOPT;
+
+ if (optname == PACKET_FANOUT_DATA &&
+ po->fanout && po->fanout->type == PACKET_FANOUT_CBPF) {
+ optval = (char __user *)get_compat_bpf_fprog(optval);
+ if (!optval)
+ return -EFAULT;
+ optlen = sizeof(struct sock_fprog);
+ }
+
+ return packet_setsockopt(sock, level, optname, optval, optlen);
+}
+#endif
+
static int packet_notifier(struct notifier_block *this,
unsigned long msg, void *ptr)
{
@@ -4416,6 +4438,9 @@ static const struct proto_ops packet_ops = {
.shutdown = sock_no_shutdown,
.setsockopt = packet_setsockopt,
.getsockopt = packet_getsockopt,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_packet_setsockopt,
+#endif
.sendmsg = packet_sendmsg,
.recvmsg = packet_recvmsg,
.mmap = packet_mmap,
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 310cabce2311..7c2a65a6af5c 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -111,7 +111,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
}
}
- if (conn->c_version < RDS_PROTOCOL(3,1)) {
+ if (conn->c_version < RDS_PROTOCOL(3, 1)) {
printk(KERN_NOTICE "RDS/IB: Connection to %pI4 version %u.%u failed,"
" no longer supported\n",
&conn->c_faddr,
diff --git a/net/rds/loop.c b/net/rds/loop.c
index 6b12b68541ae..814173b466d9 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -95,8 +95,9 @@ out:
*/
static void rds_loop_inc_free(struct rds_incoming *inc)
{
- struct rds_message *rm = container_of(inc, struct rds_message, m_inc);
- rds_message_put(rm);
+ struct rds_message *rm = container_of(inc, struct rds_message, m_inc);
+
+ rds_message_put(rm);
}
/* we need to at least give the thread something to succeed */
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 80256b08eac0..387df5f32e49 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -74,6 +74,7 @@ enum {
RDS_CONN_CONNECTING,
RDS_CONN_DISCONNECTING,
RDS_CONN_UP,
+ RDS_CONN_RESETTING,
RDS_CONN_ERROR,
};
@@ -813,6 +814,7 @@ void rds_connect_worker(struct work_struct *);
void rds_shutdown_worker(struct work_struct *);
void rds_send_worker(struct work_struct *);
void rds_recv_worker(struct work_struct *);
+void rds_connect_path_complete(struct rds_connection *conn, int curr);
void rds_connect_complete(struct rds_connection *conn);
/* transport.c */
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c0be1ecd11c9..8413f6c99e13 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -561,5 +561,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
minfo.fport = inc->i_hdr.h_dport;
}
+ minfo.flags = 0;
+
rds_info_copy(iter, &minfo, sizeof(minfo));
}
diff --git a/net/rds/send.c b/net/rds/send.c
index c9cdb358ea88..b1962f8e30f7 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -99,6 +99,7 @@ void rds_send_reset(struct rds_connection *conn)
list_splice_init(&conn->c_retrans, &conn->c_send_queue);
spin_unlock_irqrestore(&conn->c_lock, flags);
}
+EXPORT_SYMBOL_GPL(rds_send_reset);
static int acquire_in_xmit(struct rds_connection *conn)
{
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index c173f69e1479..e381bbcd9cc1 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -102,7 +102,8 @@ int rds_sysctl_init(void)
rds_sysctl_reconnect_min = msecs_to_jiffies(1);
rds_sysctl_reconnect_min_jiffies = rds_sysctl_reconnect_min;
- rds_sysctl_reg_table = register_net_sysctl(&init_net,"net/rds", rds_sysctl_rds_table);
+ rds_sysctl_reg_table =
+ register_net_sysctl(&init_net, "net/rds", rds_sysctl_rds_table);
if (!rds_sysctl_reg_table)
return -ENOMEM;
return 0;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 86187dad1440..74ee126a6fe6 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -126,9 +126,81 @@ void rds_tcp_restore_callbacks(struct socket *sock,
}
/*
- * This is the only path that sets tc->t_sock. Send and receive trust that
- * it is set. The RDS_CONN_UP bit protects those paths from being
- * called while it isn't set.
+ * rds_tcp_reset_callbacks() switches the to the new sock and
+ * returns the existing tc->t_sock.
+ *
+ * The only functions that set tc->t_sock are rds_tcp_set_callbacks
+ * and rds_tcp_reset_callbacks. Send and receive trust that
+ * it is set. The absence of RDS_CONN_UP bit protects those paths
+ * from being called while it isn't set.
+ */
+void rds_tcp_reset_callbacks(struct socket *sock,
+ struct rds_connection *conn)
+{
+ struct rds_tcp_connection *tc = conn->c_transport_data;
+ struct socket *osock = tc->t_sock;
+
+ if (!osock)
+ goto newsock;
+
+ /* Need to resolve a duelling SYN between peers.
+ * We have an outstanding SYN to this peer, which may
+ * potentially have transitioned to the RDS_CONN_UP state,
+ * so we must quiesce any send threads before resetting
+ * c_transport_data. We quiesce these threads by setting
+ * c_state to something other than RDS_CONN_UP, and then
+ * waiting for any existing threads in rds_send_xmit to
+ * complete release_in_xmit(). (Subsequent threads entering
+ * rds_send_xmit() will bail on !rds_conn_up().
+ *
+ * However an incoming syn-ack at this point would end up
+ * marking the conn as RDS_CONN_UP, and would again permit
+ * rds_send_xmi() threads through, so ideally we would
+ * synchronize on RDS_CONN_UP after lock_sock(), but cannot
+ * do that: waiting on !RDS_IN_XMIT after lock_sock() may
+ * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT
+ * would not get set. As a result, we set c_state to
+ * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change
+ * cannot mark rds_conn_path_up() in the window before lock_sock()
+ */
+ atomic_set(&conn->c_state, RDS_CONN_RESETTING);
+ wait_event(conn->c_waitq, !test_bit(RDS_IN_XMIT, &conn->c_flags));
+ lock_sock(osock->sk);
+ /* reset receive side state for rds_tcp_data_recv() for osock */
+ if (tc->t_tinc) {
+ rds_inc_put(&tc->t_tinc->ti_inc);
+ tc->t_tinc = NULL;
+ }
+ tc->t_tinc_hdr_rem = sizeof(struct rds_header);
+ tc->t_tinc_data_rem = 0;
+ tc->t_sock = NULL;
+
+ write_lock_bh(&osock->sk->sk_callback_lock);
+
+ osock->sk->sk_user_data = NULL;
+ osock->sk->sk_data_ready = tc->t_orig_data_ready;
+ osock->sk->sk_write_space = tc->t_orig_write_space;
+ osock->sk->sk_state_change = tc->t_orig_state_change;
+ write_unlock_bh(&osock->sk->sk_callback_lock);
+ release_sock(osock->sk);
+ sock_release(osock);
+newsock:
+ rds_send_reset(conn);
+ lock_sock(sock->sk);
+ write_lock_bh(&sock->sk->sk_callback_lock);
+ tc->t_sock = sock;
+ sock->sk->sk_user_data = conn;
+ sock->sk->sk_data_ready = rds_tcp_data_ready;
+ sock->sk->sk_write_space = rds_tcp_write_space;
+ sock->sk->sk_state_change = rds_tcp_state_change;
+
+ write_unlock_bh(&sock->sk->sk_callback_lock);
+ release_sock(sock->sk);
+}
+
+/* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments
+ * above rds_tcp_reset_callbacks for notes about synchronization
+ * with data path
*/
void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
{
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 41c228300525..7940babf6c71 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -50,6 +50,7 @@ struct rds_tcp_statistics {
void rds_tcp_tune(struct socket *sock);
void rds_tcp_nonagle(struct socket *sock);
void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn);
+void rds_tcp_reset_callbacks(struct socket *sock, struct rds_connection *conn);
void rds_tcp_restore_callbacks(struct socket *sock,
struct rds_tcp_connection *tc);
u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc);
@@ -82,7 +83,7 @@ int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
void rds_tcp_xmit_prepare(struct rds_connection *conn);
void rds_tcp_xmit_complete(struct rds_connection *conn);
int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
- unsigned int hdr_off, unsigned int sg, unsigned int off);
+ unsigned int hdr_off, unsigned int sg, unsigned int off);
void rds_tcp_write_space(struct sock *sk);
/* tcp_stats.c */
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index fb82e0a0bf89..f6e95d60db54 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -54,19 +54,19 @@ void rds_tcp_state_change(struct sock *sk)
rdsdebug("sock %p state_change to %d\n", tc->t_sock, sk->sk_state);
- switch(sk->sk_state) {
- /* ignore connecting sockets as they make progress */
- case TCP_SYN_SENT:
- case TCP_SYN_RECV:
- break;
- case TCP_ESTABLISHED:
- rds_connect_complete(conn);
- break;
- case TCP_CLOSE_WAIT:
- case TCP_CLOSE:
- rds_conn_drop(conn);
- default:
- break;
+ switch (sk->sk_state) {
+ /* ignore connecting sockets as they make progress */
+ case TCP_SYN_SENT:
+ case TCP_SYN_RECV:
+ break;
+ case TCP_ESTABLISHED:
+ rds_connect_path_complete(conn, RDS_CONN_CONNECTING);
+ break;
+ case TCP_CLOSE_WAIT:
+ case TCP_CLOSE:
+ rds_conn_drop(conn);
+ default:
+ break;
}
out:
read_unlock_bh(&sk->sk_callback_lock);
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 4bf4befe5066..245542ca4718 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -78,7 +78,6 @@ int rds_tcp_accept_one(struct socket *sock)
struct inet_sock *inet;
struct rds_tcp_connection *rs_tcp = NULL;
int conn_state;
- struct sock *nsk;
if (!sock) /* module unload or netns delete in progress */
return -ENETUNREACH;
@@ -136,26 +135,21 @@ int rds_tcp_accept_one(struct socket *sock)
!conn->c_outgoing) {
goto rst_nsk;
} else {
- atomic_set(&conn->c_state, RDS_CONN_CONNECTING);
- wait_event(conn->c_waitq,
- !test_bit(RDS_IN_XMIT, &conn->c_flags));
- rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
+ rds_tcp_reset_callbacks(new_sock, conn);
conn->c_outgoing = 0;
+ /* rds_connect_path_complete() marks RDS_CONN_UP */
+ rds_connect_path_complete(conn, RDS_CONN_RESETTING);
}
+ } else {
+ rds_tcp_set_callbacks(new_sock, conn);
+ rds_connect_path_complete(conn, RDS_CONN_CONNECTING);
}
- rds_tcp_set_callbacks(new_sock, conn);
- rds_connect_complete(conn); /* marks RDS_CONN_UP */
new_sock = NULL;
ret = 0;
goto out;
rst_nsk:
/* reset the newly returned accept sock and bail */
- nsk = new_sock->sk;
- rds_tcp_stats_inc(s_tcp_listen_closed_stale);
- nsk->sk_user_data = NULL;
- nsk->sk_prot->disconnect(nsk, 0);
- tcp_done(nsk);
- new_sock = NULL;
+ kernel_sock_shutdown(new_sock, SHUT_RDWR);
ret = 0;
out:
if (rs_tcp)
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index c3196f9d070a..6e6a7111a034 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -171,7 +171,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
while (left) {
if (!tinc) {
tinc = kmem_cache_alloc(rds_tcp_incoming_slab,
- arg->gfp);
+ arg->gfp);
if (!tinc) {
desc->error = -ENOMEM;
goto out;
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 22d0f2020a79..618be69c9c3b 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -66,19 +66,19 @@ void rds_tcp_xmit_complete(struct rds_connection *conn)
static int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len)
{
struct kvec vec = {
- .iov_base = data,
- .iov_len = len,
+ .iov_base = data,
+ .iov_len = len,
+ };
+ struct msghdr msg = {
+ .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
};
- struct msghdr msg = {
- .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
- };
return kernel_sendmsg(sock, &msg, &vec, 1, vec.iov_len);
}
/* the core send_sem serializes this with other xmit and shutdown */
int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
- unsigned int hdr_off, unsigned int sg, unsigned int off)
+ unsigned int hdr_off, unsigned int sg, unsigned int off)
{
struct rds_tcp_connection *tc = conn->c_transport_data;
int done = 0;
@@ -196,7 +196,7 @@ void rds_tcp_write_space(struct sock *sk)
tc->t_last_seen_una = rds_tcp_snd_una(tc);
rds_send_drop_acked(conn, rds_tcp_snd_una(tc), rds_tcp_is_acked);
- if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf)
+ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf)
queue_delayed_work(rds_wq, &conn->c_send_w, 0);
out:
diff --git a/net/rds/threads.c b/net/rds/threads.c
index 454aa6d23327..4a323045719b 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -71,9 +71,9 @@
struct workqueue_struct *rds_wq;
EXPORT_SYMBOL_GPL(rds_wq);
-void rds_connect_complete(struct rds_connection *conn)
+void rds_connect_path_complete(struct rds_connection *conn, int curr)
{
- if (!rds_conn_transition(conn, RDS_CONN_CONNECTING, RDS_CONN_UP)) {
+ if (!rds_conn_transition(conn, curr, RDS_CONN_UP)) {
printk(KERN_WARNING "%s: Cannot transition to state UP, "
"current state is %d\n",
__func__,
@@ -90,6 +90,12 @@ void rds_connect_complete(struct rds_connection *conn)
queue_delayed_work(rds_wq, &conn->c_send_w, 0);
queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
}
+EXPORT_SYMBOL_GPL(rds_connect_path_complete);
+
+void rds_connect_complete(struct rds_connection *conn)
+{
+ rds_connect_path_complete(conn, RDS_CONN_CONNECTING);
+}
EXPORT_SYMBOL_GPL(rds_connect_complete);
/*
diff --git a/net/rds/transport.c b/net/rds/transport.c
index f3afd1d60d3c..2ffd3e30c643 100644
--- a/net/rds/transport.c
+++ b/net/rds/transport.c
@@ -140,8 +140,7 @@ unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
rds_info_iter_unmap(iter);
down_read(&rds_trans_sem);
- for (i = 0; i < RDS_TRANS_COUNT; i++)
- {
+ for (i = 0; i < RDS_TRANS_COUNT; i++) {
trans = transports[i];
if (!trans || !trans->stats_info_copy)
continue;
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 6b726a046a7d..bab56ed649ba 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1162,9 +1162,7 @@ static int rxkad_init(void)
/* pin the cipher we need so that the crypto layer doesn't invoke
* keventd to go get it */
rxkad_ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(rxkad_ci))
- return PTR_ERR(rxkad_ci);
- return 0;
+ return PTR_ERR_OR_ZERO(rxkad_ci);
}
/*
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 336774a535c3..c7a0b0d481c0 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1118,7 +1118,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
nla_nest_end(skb, nest);
ret = skb->len;
} else
- nla_nest_cancel(skb, nest);
+ nlmsg_trim(skb, b);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
if (NETLINK_CB(cb->skb).portid && ret)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 658046dfe02d..ea4a2fef1b71 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -106,9 +106,9 @@ int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi)
}
EXPORT_SYMBOL_GPL(ife_get_meta_u16);
-int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval)
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
{
- mi->metaval = kmemdup(metaval, sizeof(u32), GFP_KERNEL);
+ mi->metaval = kmemdup(metaval, sizeof(u32), gfp);
if (!mi->metaval)
return -ENOMEM;
@@ -116,9 +116,9 @@ int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval)
}
EXPORT_SYMBOL_GPL(ife_alloc_meta_u32);
-int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval)
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
{
- mi->metaval = kmemdup(metaval, sizeof(u16), GFP_KERNEL);
+ mi->metaval = kmemdup(metaval, sizeof(u16), gfp);
if (!mi->metaval)
return -ENOMEM;
@@ -240,10 +240,10 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len)
}
/* called when adding new meta information
- * under ife->tcf_lock
+ * under ife->tcf_lock for existing action
*/
static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
- void *val, int len)
+ void *val, int len, bool exists)
{
struct tcf_meta_ops *ops = find_ife_oplist(metaid);
int ret = 0;
@@ -251,11 +251,13 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
if (!ops) {
ret = -ENOENT;
#ifdef CONFIG_MODULES
- spin_unlock_bh(&ife->tcf_lock);
+ if (exists)
+ spin_unlock_bh(&ife->tcf_lock);
rtnl_unlock();
request_module("ifemeta%u", metaid);
rtnl_lock();
- spin_lock_bh(&ife->tcf_lock);
+ if (exists)
+ spin_lock_bh(&ife->tcf_lock);
ops = find_ife_oplist(metaid);
#endif
}
@@ -272,10 +274,10 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
}
/* called when adding new meta information
- * under ife->tcf_lock
+ * under ife->tcf_lock for existing action
*/
static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
- int len)
+ int len, bool atomic)
{
struct tcf_meta_info *mi = NULL;
struct tcf_meta_ops *ops = find_ife_oplist(metaid);
@@ -284,7 +286,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
if (!ops)
return -ENOENT;
- mi = kzalloc(sizeof(*mi), GFP_KERNEL);
+ mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
if (!mi) {
/*put back what find_ife_oplist took */
module_put(ops->owner);
@@ -294,7 +296,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
mi->metaid = metaid;
mi->ops = ops;
if (len > 0) {
- ret = ops->alloc(mi, metaval);
+ ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
if (ret != 0) {
kfree(mi);
module_put(ops->owner);
@@ -313,11 +315,13 @@ static int use_all_metadata(struct tcf_ife_info *ife)
int rc = 0;
int installed = 0;
+ read_lock(&ife_mod_lock);
list_for_each_entry(o, &ifeoplist, list) {
- rc = add_metainfo(ife, o->metaid, NULL, 0);
+ rc = add_metainfo(ife, o->metaid, NULL, 0, true);
if (rc == 0)
installed += 1;
}
+ read_unlock(&ife_mod_lock);
if (installed)
return 0;
@@ -385,8 +389,9 @@ static void tcf_ife_cleanup(struct tc_action *a, int bind)
spin_unlock_bh(&ife->tcf_lock);
}
-/* under ife->tcf_lock */
-static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb)
+/* under ife->tcf_lock for existing action */
+static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
+ bool exists)
{
int len = 0;
int rc = 0;
@@ -398,11 +403,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb)
val = nla_data(tb[i]);
len = nla_len(tb[i]);
- rc = load_metaops_and_vet(ife, i, val, len);
+ rc = load_metaops_and_vet(ife, i, val, len, exists);
if (rc != 0)
return rc;
- rc = add_metainfo(ife, i, val, len);
+ rc = add_metainfo(ife, i, val, len, exists);
if (rc)
return rc;
}
@@ -474,7 +479,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
saddr = nla_data(tb[TCA_IFE_SMAC]);
}
- spin_lock_bh(&ife->tcf_lock);
+ if (exists)
+ spin_lock_bh(&ife->tcf_lock);
ife->tcf_action = parm->action;
if (parm->flags & IFE_ENCODE) {
@@ -504,11 +510,12 @@ metadata_parse_err:
if (ret == ACT_P_CREATED)
_tcf_ife_cleanup(a, bind);
- spin_unlock_bh(&ife->tcf_lock);
+ if (exists)
+ spin_unlock_bh(&ife->tcf_lock);
return err;
}
- err = populate_metalist(ife, tb2);
+ err = populate_metalist(ife, tb2, exists);
if (err)
goto metadata_parse_err;
@@ -523,12 +530,14 @@ metadata_parse_err:
if (ret == ACT_P_CREATED)
_tcf_ife_cleanup(a, bind);
- spin_unlock_bh(&ife->tcf_lock);
+ if (exists)
+ spin_unlock_bh(&ife->tcf_lock);
return err;
}
}
- spin_unlock_bh(&ife->tcf_lock);
+ if (exists)
+ spin_unlock_bh(&ife->tcf_lock);
if (ret == ACT_P_CREATED)
tcf_hash_insert(tn, a);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 9f002ada7074..d4bd19ee5822 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -121,10 +121,13 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
}
td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
- if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size)
+ if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
+ if (exists)
+ tcf_hash_release(a, bind);
return -EINVAL;
+ }
- if (!tcf_hash_check(tn, index, a, bind)) {
+ if (!exists) {
ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind,
false);
if (ret)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 330f14e302e8..c557789765dc 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -38,7 +38,7 @@ struct tcf_police {
bool peak_present;
};
#define to_police(pc) \
- container_of(pc, struct tcf_police, common)
+ container_of(pc->priv, struct tcf_police, common)
#define POL_TAB_MASK 15
@@ -119,14 +119,12 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action *a,
int ovr, int bind)
{
- unsigned int h;
int ret = 0, err;
struct nlattr *tb[TCA_POLICE_MAX + 1];
struct tc_police *parm;
struct tcf_police *police;
struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
struct tc_action_net *tn = net_generic(net, police_net_id);
- struct tcf_hashinfo *hinfo = tn->hinfo;
int size;
if (nla == NULL)
@@ -145,7 +143,7 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
if (parm->index) {
if (tcf_hash_search(tn, a, parm->index)) {
- police = to_police(a->priv);
+ police = to_police(a);
if (bind) {
police->tcf_bindcnt += 1;
police->tcf_refcnt += 1;
@@ -156,16 +154,15 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
/* not replacing */
return -EEXIST;
}
+ } else {
+ ret = tcf_hash_create(tn, parm->index, NULL, a,
+ sizeof(*police), bind, false);
+ if (ret)
+ return ret;
+ ret = ACT_P_CREATED;
}
- police = kzalloc(sizeof(*police), GFP_KERNEL);
- if (police == NULL)
- return -ENOMEM;
- ret = ACT_P_CREATED;
- police->tcf_refcnt = 1;
- spin_lock_init(&police->tcf_lock);
- if (bind)
- police->tcf_bindcnt = 1;
+ police = to_police(a);
override:
if (parm->rate.rate) {
err = -ENOMEM;
@@ -237,14 +234,8 @@ override:
return ret;
police->tcfp_t_c = ktime_get_ns();
- police->tcf_index = parm->index ? parm->index :
- tcf_hash_new_index(tn);
- h = tcf_hash(police->tcf_index, POL_TAB_MASK);
- spin_lock_bh(&hinfo->lock);
- hlist_add_head(&police->tcf_head, &hinfo->htab[h]);
- spin_unlock_bh(&hinfo->lock);
+ tcf_hash_insert(tn, a);
- a->priv = police;
return ret;
failure_unlock:
@@ -253,7 +244,7 @@ failure:
qdisc_put_rtab(P_tab);
qdisc_put_rtab(R_tab);
if (ret == ACT_P_CREATED)
- kfree(police);
+ tcf_hash_cleanup(a, est);
return err;
}
@@ -268,6 +259,7 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
spin_lock(&police->tcf_lock);
bstats_update(&police->tcf_bstats, skb);
+ tcf_lastuse_update(&police->tcf_tm);
if (police->tcfp_ewma_rate &&
police->tcf_rate_est.bps >= police->tcfp_ewma_rate) {
@@ -327,6 +319,7 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
.refcnt = police->tcf_refcnt - ref,
.bindcnt = police->tcf_bindcnt - bind,
};
+ struct tcf_t t;
if (police->rate_present)
psched_ratecfg_getrate(&opt.rate, &police->rate);
@@ -340,6 +333,13 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
if (police->tcfp_ewma_rate &&
nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate))
goto nla_put_failure;
+
+ t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install);
+ t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse);
+ t.expires = jiffies_to_clock_t(police->tcf_tm.expires);
+ if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
+ goto nla_put_failure;
+
return skb->len;
nla_put_failure:
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 730aacafc22d..b3b7978f4182 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -171,7 +171,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie)
struct tc_cls_flower_offload offload = {0};
struct tc_to_netdev tc;
- if (!tc_should_offload(dev, 0))
+ if (!tc_should_offload(dev, tp, 0))
return;
offload.command = TC_CLSFLOWER_DESTROY;
@@ -194,7 +194,7 @@ static void fl_hw_replace_filter(struct tcf_proto *tp,
struct tc_cls_flower_offload offload = {0};
struct tc_to_netdev tc;
- if (!tc_should_offload(dev, flags))
+ if (!tc_should_offload(dev, tp, flags))
return;
offload.command = TC_CLSFLOWER_REPLACE;
@@ -216,7 +216,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
struct tc_cls_flower_offload offload = {0};
struct tc_to_netdev tc;
- if (!tc_should_offload(dev, 0))
+ if (!tc_should_offload(dev, tp, 0))
return;
offload.command = TC_CLSFLOWER_STATS;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 079b43b3c5d2..ffe593efe930 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -440,7 +440,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
offload.type = TC_SETUP_CLSU32;
offload.cls_u32 = &u32_offload;
- if (tc_should_offload(dev, 0)) {
+ if (tc_should_offload(dev, tp, 0)) {
offload.cls_u32->command = TC_CLSU32_DELETE_KNODE;
offload.cls_u32->knode.handle = handle;
dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
@@ -457,20 +457,21 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp,
struct tc_to_netdev offload;
int err;
+ if (!tc_should_offload(dev, tp, flags))
+ return tc_skip_sw(flags) ? -EINVAL : 0;
+
offload.type = TC_SETUP_CLSU32;
offload.cls_u32 = &u32_offload;
- if (tc_should_offload(dev, flags)) {
- offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
- offload.cls_u32->hnode.divisor = h->divisor;
- offload.cls_u32->hnode.handle = h->handle;
- offload.cls_u32->hnode.prio = h->prio;
+ offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
+ offload.cls_u32->hnode.divisor = h->divisor;
+ offload.cls_u32->hnode.handle = h->handle;
+ offload.cls_u32->hnode.prio = h->prio;
- err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
- tp->protocol, &offload);
- if (tc_skip_sw(flags))
- return err;
- }
+ err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+ tp->protocol, &offload);
+ if (tc_skip_sw(flags))
+ return err;
return 0;
}
@@ -484,7 +485,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
offload.type = TC_SETUP_CLSU32;
offload.cls_u32 = &u32_offload;
- if (tc_should_offload(dev, 0)) {
+ if (tc_should_offload(dev, tp, 0)) {
offload.cls_u32->command = TC_CLSU32_DELETE_HNODE;
offload.cls_u32->hnode.divisor = h->divisor;
offload.cls_u32->hnode.handle = h->handle;
@@ -507,27 +508,28 @@ static int u32_replace_hw_knode(struct tcf_proto *tp,
offload.type = TC_SETUP_CLSU32;
offload.cls_u32 = &u32_offload;
- if (tc_should_offload(dev, flags)) {
- offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
- offload.cls_u32->knode.handle = n->handle;
- offload.cls_u32->knode.fshift = n->fshift;
+ if (!tc_should_offload(dev, tp, flags))
+ return tc_skip_sw(flags) ? -EINVAL : 0;
+
+ offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
+ offload.cls_u32->knode.handle = n->handle;
+ offload.cls_u32->knode.fshift = n->fshift;
#ifdef CONFIG_CLS_U32_MARK
- offload.cls_u32->knode.val = n->val;
- offload.cls_u32->knode.mask = n->mask;
+ offload.cls_u32->knode.val = n->val;
+ offload.cls_u32->knode.mask = n->mask;
#else
- offload.cls_u32->knode.val = 0;
- offload.cls_u32->knode.mask = 0;
+ offload.cls_u32->knode.val = 0;
+ offload.cls_u32->knode.mask = 0;
#endif
- offload.cls_u32->knode.sel = &n->sel;
- offload.cls_u32->knode.exts = &n->exts;
- if (n->ht_down)
- offload.cls_u32->knode.link_handle = n->ht_down->handle;
-
- err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
- tp->protocol, &offload);
- if (tc_skip_sw(flags))
- return err;
- }
+ offload.cls_u32->knode.sel = &n->sel;
+ offload.cls_u32->knode.exts = &n->exts;
+ if (n->ht_down)
+ offload.cls_u32->knode.link_handle = n->ht_down->handle;
+
+ err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+ tp->protocol, &offload);
+ if (tc_skip_sw(flags))
+ return err;
return 0;
}
@@ -863,7 +865,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
if (tb[TCA_U32_FLAGS]) {
flags = nla_get_u32(tb[TCA_U32_FLAGS]);
if (!tc_flags_valid(flags))
- return err;
+ return -EINVAL;
}
n = (struct tc_u_knode *)*arg;
@@ -921,11 +923,17 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
ht->divisor = divisor;
ht->handle = handle;
ht->prio = tp->prio;
+
+ err = u32_replace_hw_hnode(tp, ht, flags);
+ if (err) {
+ kfree(ht);
+ return err;
+ }
+
RCU_INIT_POINTER(ht->next, tp_c->hlist);
rcu_assign_pointer(tp_c->hlist, ht);
*arg = (unsigned long)ht;
- u32_replace_hw_hnode(tp, ht, flags);
return 0;
}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 64f71a2155f3..ddf047df5361 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -607,6 +607,10 @@ void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool thr
if (throttle)
qdisc_throttled(wd->qdisc);
+ if (wd->last_expires == expires)
+ return;
+
+ wd->last_expires = expires;
hrtimer_start(&wd->timer,
ns_to_ktime(expires),
HRTIMER_MODE_ABS_PINNED);
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index a63e879e8975..bf8af2c43c2c 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -375,6 +375,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
cl->deficit = cl->quantum;
}
+ qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
return err;
}
@@ -407,6 +408,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
bstats_update(&cl->bstats, skb);
qdisc_bstats_update(sch, skb);
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
return skb;
}
@@ -428,6 +430,7 @@ static unsigned int drr_drop(struct Qdisc *sch)
if (cl->qdisc->ops->drop) {
len = cl->qdisc->ops->drop(cl->qdisc);
if (len > 0) {
+ sch->qstats.backlog -= len;
sch->q.qlen--;
if (cl->qdisc->q.qlen == 0)
list_del(&cl->alist);
@@ -463,6 +466,7 @@ static void drr_reset_qdisc(struct Qdisc *sch)
qdisc_reset(cl->qdisc);
}
}
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 2177eac0a61e..2e4bd2c0a50c 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -37,14 +37,18 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
+ unsigned int prev_backlog;
+
if (likely(skb_queue_len(&sch->q) < sch->limit))
return qdisc_enqueue_tail(skb, sch);
+ prev_backlog = sch->qstats.backlog;
/* queue full, remove one skb to fulfill the limit */
__qdisc_queue_drop_head(sch, &sch->q);
qdisc_qstats_drop(sch);
qdisc_enqueue_tail(skb, sch);
+ qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
return NET_XMIT_CN;
}
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6883a8971562..da250b2e06ae 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -199,6 +199,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
unsigned int idx, prev_backlog, prev_qlen;
struct fq_codel_flow *flow;
int uninitialized_var(ret);
+ unsigned int pkt_len;
bool memory_limited;
idx = fq_codel_classify(skb, sch, &ret);
@@ -230,6 +231,8 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
prev_backlog = sch->qstats.backlog;
prev_qlen = sch->q.qlen;
+ /* save this packet length as it might be dropped by fq_codel_drop() */
+ pkt_len = qdisc_pkt_len(skb);
/* fq_codel_drop() is quite expensive, as it performs a linear search
* in q->backlogs[] to find a fat flow.
* So instead of dropping a single packet, drop half of its backlog
@@ -237,14 +240,23 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
*/
ret = fq_codel_drop(sch, q->drop_batch_size);
- q->drop_overlimit += prev_qlen - sch->q.qlen;
+ prev_qlen -= sch->q.qlen;
+ prev_backlog -= sch->qstats.backlog;
+ q->drop_overlimit += prev_qlen;
if (memory_limited)
- q->drop_overmemory += prev_qlen - sch->q.qlen;
- /* As we dropped packet(s), better let upper stack know this */
- qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
- prev_backlog - sch->qstats.backlog);
+ q->drop_overmemory += prev_qlen;
- return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
+ /* As we dropped packet(s), better let upper stack know this.
+ * If we dropped a packet for this flow, return NET_XMIT_CN,
+ * but in this case, our parents wont increase their backlogs.
+ */
+ if (ret == idx) {
+ qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
+ prev_backlog - pkt_len);
+ return NET_XMIT_CN;
+ }
+ qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
+ return NET_XMIT_SUCCESS;
}
/* This is the specific function called from codel_dequeue()
@@ -649,7 +661,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl,
qs.backlog = q->backlogs[idx];
qs.drops = flow->dropped;
}
- if (gnet_stats_copy_queue(d, NULL, &qs, 0) < 0)
+ if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
return -1;
if (idx < q->flows_cnt)
return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 269dd71b3828..f9e0e9c03d0a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -49,6 +49,7 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
{
q->gso_skb = skb;
q->qstats.requeues++;
+ qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++; /* it's still part of the queue */
__netif_schedule(q);
@@ -92,6 +93,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
txq = skb_get_tx_queue(txq->dev, skb);
if (!netif_xmit_frozen_or_stopped(txq)) {
q->gso_skb = NULL;
+ qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
} else
skb = NULL;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d783d7cc3348..1ac9f9f03fe3 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1529,6 +1529,7 @@ hfsc_reset_qdisc(struct Qdisc *sch)
q->eligible = RB_ROOT;
INIT_LIST_HEAD(&q->droplist);
qdisc_watchdog_cancel(&q->watchdog);
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
@@ -1559,14 +1560,6 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
struct hfsc_sched *q = qdisc_priv(sch);
unsigned char *b = skb_tail_pointer(skb);
struct tc_hfsc_qopt qopt;
- struct hfsc_class *cl;
- unsigned int i;
-
- sch->qstats.backlog = 0;
- for (i = 0; i < q->clhash.hashsize; i++) {
- hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode)
- sch->qstats.backlog += cl->qdisc->qstats.backlog;
- }
qopt.defcls = q->defcls;
if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt))
@@ -1604,6 +1597,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (cl->qdisc->q.qlen == 1)
set_active(cl, qdisc_pkt_len(skb));
+ qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
return NET_XMIT_SUCCESS;
@@ -1672,6 +1666,7 @@ hfsc_dequeue(struct Qdisc *sch)
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
return skb;
@@ -1695,6 +1690,7 @@ hfsc_drop(struct Qdisc *sch)
}
cl->qstats.drops++;
qdisc_qstats_drop(sch);
+ sch->qstats.backlog -= len;
sch->q.qlen--;
return len;
}
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index f6bf5818ed4d..62f9d8100c6e 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -928,17 +928,10 @@ ok:
}
}
qdisc_qstats_overlimit(sch);
- if (likely(next_event > q->now)) {
- if (!test_bit(__QDISC_STATE_DEACTIVATED,
- &qdisc_root_sleeping(q->watchdog.qdisc)->state)) {
- ktime_t time = ns_to_ktime(next_event);
- qdisc_throttled(q->watchdog.qdisc);
- hrtimer_start(&q->watchdog.timer, time,
- HRTIMER_MODE_ABS_PINNED);
- }
- } else {
+ if (likely(next_event > q->now))
+ qdisc_watchdog_schedule_ns(&q->watchdog, next_event, true);
+ else
schedule_work(&q->work);
- }
fin:
return skb;
}
@@ -1014,7 +1007,9 @@ static void htb_work_func(struct work_struct *work)
struct htb_sched *q = container_of(work, struct htb_sched, work);
struct Qdisc *sch = q->watchdog.qdisc;
+ rcu_read_lock();
__netif_schedule(qdisc_root(sch));
+ rcu_read_unlock();
}
static int htb_init(struct Qdisc *sch, struct nlattr *opt)
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 10adbc617905..8fe6999b642a 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -27,6 +27,11 @@ static unsigned long ingress_get(struct Qdisc *sch, u32 classid)
return TC_H_MIN(classid) + 1;
}
+static bool ingress_cl_offload(u32 classid)
+{
+ return true;
+}
+
static unsigned long ingress_bind_filter(struct Qdisc *sch,
unsigned long parent, u32 classid)
{
@@ -86,6 +91,7 @@ static const struct Qdisc_class_ops ingress_class_ops = {
.put = ingress_put,
.walk = ingress_walk,
.tcf_chain = ingress_find_tcf,
+ .tcf_cl_offload = ingress_cl_offload,
.bind_tcf = ingress_bind_filter,
.unbind_tcf = ingress_put,
};
@@ -110,6 +116,11 @@ static unsigned long clsact_get(struct Qdisc *sch, u32 classid)
}
}
+static bool clsact_cl_offload(u32 classid)
+{
+ return TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS);
+}
+
static unsigned long clsact_bind_filter(struct Qdisc *sch,
unsigned long parent, u32 classid)
{
@@ -158,6 +169,7 @@ static const struct Qdisc_class_ops clsact_class_ops = {
.put = ingress_put,
.walk = ingress_walk,
.tcf_chain = clsact_find_tcf,
+ .tcf_cl_offload = clsact_cl_offload,
.bind_tcf = clsact_bind_filter,
.unbind_tcf = ingress_put,
};
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 205bed00dd34..178f1630a036 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -650,14 +650,14 @@ deliver:
#endif
if (q->qdisc) {
+ unsigned int pkt_len = qdisc_pkt_len(skb);
int err = qdisc_enqueue(skb, q->qdisc);
- if (unlikely(err != NET_XMIT_SUCCESS)) {
- if (net_xmit_drop_count(err)) {
- qdisc_qstats_drop(sch);
- qdisc_tree_reduce_backlog(sch, 1,
- qdisc_pkt_len(skb));
- }
+ if (err != NET_XMIT_SUCCESS &&
+ net_xmit_drop_count(err)) {
+ qdisc_qstats_drop(sch);
+ qdisc_tree_reduce_backlog(sch, 1,
+ pkt_len);
}
goto tfifo_dequeue;
}
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index fee1b15506b2..a356450b747b 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -85,6 +85,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
ret = qdisc_enqueue(skb, qdisc);
if (ret == NET_XMIT_SUCCESS) {
+ qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
@@ -117,6 +118,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
if (skb) {
qdisc_bstats_update(sch, skb);
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
return skb;
}
@@ -135,6 +137,7 @@ static unsigned int prio_drop(struct Qdisc *sch)
for (prio = q->bands-1; prio >= 0; prio--) {
qdisc = q->queues[prio];
if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) {
+ sch->qstats.backlog -= len;
sch->q.qlen--;
return len;
}
@@ -151,6 +154,7 @@ prio_reset(struct Qdisc *sch)
for (prio = 0; prio < q->bands; prio++)
qdisc_reset(q->queues[prio]);
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
@@ -168,8 +172,9 @@ prio_destroy(struct Qdisc *sch)
static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
{
struct prio_sched_data *q = qdisc_priv(sch);
+ struct Qdisc *queues[TCQ_PRIO_BANDS];
+ int oldbands = q->bands, i;
struct tc_prio_qopt *qopt;
- int i;
if (nla_len(opt) < sizeof(*qopt))
return -EINVAL;
@@ -183,62 +188,42 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
return -EINVAL;
}
+ /* Before commit, make sure we can allocate all new qdiscs */
+ for (i = oldbands; i < qopt->bands; i++) {
+ queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+ TC_H_MAKE(sch->handle, i + 1));
+ if (!queues[i]) {
+ while (i > oldbands)
+ qdisc_destroy(queues[--i]);
+ return -ENOMEM;
+ }
+ }
+
sch_tree_lock(sch);
q->bands = qopt->bands;
memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
- for (i = q->bands; i < TCQ_PRIO_BANDS; i++) {
+ for (i = q->bands; i < oldbands; i++) {
struct Qdisc *child = q->queues[i];
- q->queues[i] = &noop_qdisc;
- if (child != &noop_qdisc) {
- qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
- qdisc_destroy(child);
- }
- }
- sch_tree_unlock(sch);
- for (i = 0; i < q->bands; i++) {
- if (q->queues[i] == &noop_qdisc) {
- struct Qdisc *child, *old;
-
- child = qdisc_create_dflt(sch->dev_queue,
- &pfifo_qdisc_ops,
- TC_H_MAKE(sch->handle, i + 1));
- if (child) {
- sch_tree_lock(sch);
- old = q->queues[i];
- q->queues[i] = child;
-
- if (old != &noop_qdisc) {
- qdisc_tree_reduce_backlog(old,
- old->q.qlen,
- old->qstats.backlog);
- qdisc_destroy(old);
- }
- sch_tree_unlock(sch);
- }
- }
+ qdisc_tree_reduce_backlog(child, child->q.qlen,
+ child->qstats.backlog);
+ qdisc_destroy(child);
}
+
+ for (i = oldbands; i < q->bands; i++)
+ q->queues[i] = queues[i];
+
+ sch_tree_unlock(sch);
return 0;
}
static int prio_init(struct Qdisc *sch, struct nlattr *opt)
{
- struct prio_sched_data *q = qdisc_priv(sch);
- int i;
-
- for (i = 0; i < TCQ_PRIO_BANDS; i++)
- q->queues[i] = &noop_qdisc;
-
- if (opt == NULL) {
+ if (!opt)
return -EINVAL;
- } else {
- int err;
- if ((err = prio_tune(sch, opt)) != 0)
- return err;
- }
- return 0;
+ return prio_tune(sch, opt);
}
static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8d2d8d953432..f18857febdad 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1235,8 +1235,10 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid);
err = qfq_change_agg(sch, cl, cl->agg->class_weight,
qdisc_pkt_len(skb));
- if (err)
- return err;
+ if (err) {
+ cl->qstats.drops++;
+ return qdisc_drop(skb, sch);
+ }
}
err = qdisc_enqueue(skb, cl->qdisc);
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 8c0508c0e287..91578bdd378c 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -97,6 +97,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
ret = qdisc_enqueue(skb, child);
if (likely(ret == NET_XMIT_SUCCESS)) {
+ qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
} else if (net_xmit_drop_count(ret)) {
q->stats.pdrop++;
@@ -118,6 +119,7 @@ static struct sk_buff *red_dequeue(struct Qdisc *sch)
skb = child->dequeue(child);
if (skb) {
qdisc_bstats_update(sch, skb);
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
} else {
if (!red_is_idling(&q->vars))
@@ -143,6 +145,7 @@ static unsigned int red_drop(struct Qdisc *sch)
if (child->ops->drop && (len = child->ops->drop(child)) > 0) {
q->stats.other++;
qdisc_qstats_drop(sch);
+ sch->qstats.backlog -= len;
sch->q.qlen--;
return len;
}
@@ -158,6 +161,7 @@ static void red_reset(struct Qdisc *sch)
struct red_sched_data *q = qdisc_priv(sch);
qdisc_reset(q->qdisc);
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
red_restart(&q->vars);
}
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 83b90b584fae..3161e491990b 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -207,6 +207,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return ret;
}
+ qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
@@ -217,6 +218,7 @@ static unsigned int tbf_drop(struct Qdisc *sch)
unsigned int len = 0;
if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) {
+ sch->qstats.backlog -= len;
sch->q.qlen--;
qdisc_qstats_drop(sch);
}
@@ -263,6 +265,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
q->t_c = now;
q->tokens = toks;
q->ptokens = ptoks;
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
@@ -294,6 +297,7 @@ static void tbf_reset(struct Qdisc *sch)
struct tbf_sched_data *q = qdisc_priv(sch);
qdisc_reset(q->qdisc);
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
q->t_c = ktime_get_ns();
q->tokens = q->buffer;
diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index 8e3e769dc9ea..f69edcf219e5 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -3,12 +3,6 @@
#include <linux/sock_diag.h>
#include <net/sctp/sctp.h>
-extern void inet_diag_msg_common_fill(struct inet_diag_msg *r,
- struct sock *sk);
-extern int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
- struct inet_diag_msg *r, int ext,
- struct user_namespace *user_ns);
-
static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
void *info);
@@ -356,6 +350,9 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p)
if (cb->args[4] < cb->args[1])
goto next;
+ if ((r->idiag_states & ~TCPF_LISTEN) && !list_empty(&ep->asocs))
+ goto next;
+
if (r->sdiag_family != AF_UNSPEC &&
sk->sk_family != r->sdiag_family)
goto next;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 777d0324594a..67154b848aa9 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4220,6 +4220,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
info->sctpi_s_disable_fragments = sp->disable_fragments;
info->sctpi_s_v4mapped = sp->v4mapped;
info->sctpi_s_frag_interleave = sp->frag_interleave;
+ info->sctpi_s_type = sp->type;
return 0;
}
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 02f53674dc39..040ff627c18a 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -543,7 +543,7 @@ rpcauth_cache_enforce_limit(void)
*/
struct rpc_cred *
rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
- int flags)
+ int flags, gfp_t gfp)
{
LIST_HEAD(free);
struct rpc_cred_cache *cache = auth->au_credcache;
@@ -580,7 +580,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
if (flags & RPCAUTH_LOOKUP_RCU)
return ERR_PTR(-ECHILD);
- new = auth->au_ops->crcreate(auth, acred, flags);
+ new = auth->au_ops->crcreate(auth, acred, flags, gfp);
if (IS_ERR(new)) {
cred = new;
goto out;
@@ -703,8 +703,7 @@ rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
new = rpcauth_bind_new_cred(task, lookupflags);
if (IS_ERR(new))
return PTR_ERR(new);
- if (req->rq_cred != NULL)
- put_rpccred(req->rq_cred);
+ put_rpccred(req->rq_cred);
req->rq_cred = new;
return 0;
}
@@ -712,6 +711,8 @@ rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
void
put_rpccred(struct rpc_cred *cred)
{
+ if (cred == NULL)
+ return;
/* Fast path for unhashed credentials */
if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) == 0) {
if (atomic_dec_and_test(&cred->cr_count))
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 41248b1820c7..54dd3fdead54 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -38,6 +38,13 @@ struct rpc_cred *rpc_lookup_cred(void)
}
EXPORT_SYMBOL_GPL(rpc_lookup_cred);
+struct rpc_cred *
+rpc_lookup_generic_cred(struct auth_cred *acred, int flags, gfp_t gfp)
+{
+ return rpcauth_lookup_credcache(&generic_auth, acred, flags, gfp);
+}
+EXPORT_SYMBOL_GPL(rpc_lookup_generic_cred);
+
struct rpc_cred *rpc_lookup_cred_nonblock(void)
{
return rpcauth_lookupcred(&generic_auth, RPCAUTH_LOOKUP_RCU);
@@ -77,15 +84,15 @@ static struct rpc_cred *generic_bind_cred(struct rpc_task *task,
static struct rpc_cred *
generic_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
- return rpcauth_lookup_credcache(&generic_auth, acred, flags);
+ return rpcauth_lookup_credcache(&generic_auth, acred, flags, GFP_KERNEL);
}
static struct rpc_cred *
-generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp)
{
struct generic_cred *gcred;
- gcred = kmalloc(sizeof(*gcred), GFP_KERNEL);
+ gcred = kmalloc(sizeof(*gcred), gfp);
if (gcred == NULL)
return ERR_PTR(-ENOMEM);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 15612ffa8d57..e64ae93d5b4f 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1299,11 +1299,11 @@ gss_destroy_cred(struct rpc_cred *cred)
static struct rpc_cred *
gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
- return rpcauth_lookup_credcache(auth, acred, flags);
+ return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS);
}
static struct rpc_cred *
-gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp)
{
struct gss_auth *gss_auth = container_of(auth, struct gss_auth, rpc_auth);
struct gss_cred *cred = NULL;
@@ -1313,7 +1313,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
__func__, from_kuid(&init_user_ns, acred->uid),
auth->au_flavor);
- if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS)))
+ if (!(cred = kzalloc(sizeof(*cred), gfp)))
goto out_err;
rpcauth_init_cred(&cred->gc_base, acred, auth, &gss_credops);
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 1095be9c80ab..e085f5ae1548 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -569,10 +569,9 @@ gss_svc_searchbyctx(struct cache_detail *cd, struct xdr_netobj *handle)
struct rsc *found;
memset(&rsci, 0, sizeof(rsci));
- if (dup_to_netobj(&rsci.handle, handle->data, handle->len))
- return NULL;
+ rsci.handle.data = handle->data;
+ rsci.handle.len = handle->len;
found = rsc_lookup(cd, &rsci);
- rsc_free(&rsci);
if (!found)
return NULL;
if (cache_check(cd, &found->h, NULL))
@@ -857,8 +856,8 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
goto out;
if (svc_getnl(&buf->head[0]) != seq)
goto out;
- /* trim off the mic at the end before returning */
- xdr_buf_trim(buf, mic.len + 4);
+ /* trim off the mic and padding at the end before returning */
+ xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4);
stat = 0;
out:
kfree(mic.data);
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 0d3dd364c22f..9f65452b7cbc 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -52,11 +52,11 @@ unx_destroy(struct rpc_auth *auth)
static struct rpc_cred *
unx_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
- return rpcauth_lookup_credcache(auth, acred, flags);
+ return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS);
}
static struct rpc_cred *
-unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp)
{
struct unx_cred *cred;
unsigned int groups = 0;
@@ -66,7 +66,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
from_kuid(&init_user_ns, acred->uid),
from_kgid(&init_user_ns, acred->gid));
- if (!(cred = kmalloc(sizeof(*cred), GFP_NOFS)))
+ if (!(cred = kmalloc(sizeof(*cred), gfp)))
return ERR_PTR(-ENOMEM);
rpcauth_init_cred(&cred->uc_base, acred, auth, &unix_credops);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7e0c9bf22df8..2808d550d273 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -446,16 +446,27 @@ out_no_rpciod:
return ERR_PTR(err);
}
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
struct rpc_xprt *xprt)
{
struct rpc_clnt *clnt = NULL;
struct rpc_xprt_switch *xps;
- xps = xprt_switch_alloc(xprt, GFP_KERNEL);
- if (xps == NULL)
- return ERR_PTR(-ENOMEM);
-
+ if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) {
+ WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+ xps = args->bc_xprt->xpt_bc_xps;
+ xprt_switch_get(xps);
+ } else {
+ xps = xprt_switch_alloc(xprt, GFP_KERNEL);
+ if (xps == NULL) {
+ xprt_put(xprt);
+ return ERR_PTR(-ENOMEM);
+ }
+ if (xprt->bc_xprt) {
+ xprt_switch_get(xps);
+ xprt->bc_xprt->xpt_bc_xps = xps;
+ }
+ }
clnt = rpc_new_client(args, xps, xprt, NULL);
if (IS_ERR(clnt))
return clnt;
@@ -483,7 +494,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
return clnt;
}
-EXPORT_SYMBOL_GPL(rpc_create_xprt);
/**
* rpc_create - create an RPC client and transport with one call
@@ -509,6 +519,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
};
char servername[48];
+ if (args->bc_xprt) {
+ WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+ xprt = args->bc_xprt->xpt_bc_xprt;
+ if (xprt) {
+ xprt_get(xprt);
+ return rpc_create_xprt(args, xprt);
+ }
+ }
+
if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS)
xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS;
if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT)
@@ -1414,6 +1433,23 @@ size_t rpc_max_payload(struct rpc_clnt *clnt)
EXPORT_SYMBOL_GPL(rpc_max_payload);
/**
+ * rpc_max_bc_payload - Get maximum backchannel payload size, in bytes
+ * @clnt: RPC client to query
+ */
+size_t rpc_max_bc_payload(struct rpc_clnt *clnt)
+{
+ struct rpc_xprt *xprt;
+ size_t ret;
+
+ rcu_read_lock();
+ xprt = rcu_dereference(clnt->cl_xprt);
+ ret = xprt->ops->bc_maxpayload(xprt);
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(rpc_max_bc_payload);
+
+/**
* rpc_get_timeout - Get timeout for transport in units of HZ
* @clnt: RPC client to query
*/
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 7422f28818b2..4f01f63102ee 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -136,6 +136,8 @@ static void svc_xprt_free(struct kref *kref)
/* See comment on corresponding get in xs_setup_bc_tcp(): */
if (xprt->xpt_bc_xprt)
xprt_put(xprt->xpt_bc_xprt);
+ if (xprt->xpt_bc_xps)
+ xprt_switch_put(xprt->xpt_bc_xps);
xprt->xpt_ops->xpo_free(xprt);
module_put(owner);
}
@@ -244,13 +246,12 @@ void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new)
svc_xprt_received(new);
}
-int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
+int _svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
struct net *net, const int family,
const unsigned short port, int flags)
{
struct svc_xprt_class *xcl;
- dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
struct svc_xprt *newxprt;
@@ -274,12 +275,28 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
}
err:
spin_unlock(&svc_xprt_class_lock);
- dprintk("svc: transport %s not found\n", xprt_name);
-
/* This errno is exposed to user space. Provide a reasonable
* perror msg for a bad transport. */
return -EPROTONOSUPPORT;
}
+
+int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
+ struct net *net, const int family,
+ const unsigned short port, int flags)
+{
+ int err;
+
+ dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
+ err = _svc_create_xprt(serv, xprt_name, net, family, port, flags);
+ if (err == -EPROTONOSUPPORT) {
+ request_module("svc%s", xprt_name);
+ err = _svc_create_xprt(serv, xprt_name, net, family, port, flags);
+ }
+ if (err)
+ dprintk("svc: transport %s not found, err %d\n",
+ xprt_name, err);
+ return err;
+}
EXPORT_SYMBOL_GPL(svc_create_xprt);
/*
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 6bdb3865212d..c4f3cc0c0775 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -797,6 +797,8 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
xdr_set_iov(xdr, buf->head, buf->len);
else if (buf->page_len != 0)
xdr_set_page_base(xdr, 0, buf->len);
+ else
+ xdr_set_iov(xdr, buf->head, buf->len);
if (p != NULL && p > xdr->p && xdr->end >= p) {
xdr->nwords -= p - xdr->p;
xdr->p = p;
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 2dcd7640eeb5..87762d976b63 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -192,6 +192,22 @@ int xprt_rdma_bc_up(struct svc_serv *serv, struct net *net)
}
/**
+ * xprt_rdma_bc_maxpayload - Return maximum backchannel message size
+ * @xprt: transport
+ *
+ * Returns maximum size, in bytes, of a backchannel message
+ */
+size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *xprt)
+{
+ struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+ struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
+ size_t maxmsg;
+
+ maxmsg = min_t(unsigned int, cdata->inline_rsize, cdata->inline_wsize);
+ return maxmsg - RPCRDMA_HDRLEN_MIN;
+}
+
+/**
* rpcrdma_bc_marshal_reply - Send backwards direction reply
* @rqst: buffer containing RPC reply data
*
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index b289e106540b..6326ebe8b595 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -35,10 +35,71 @@
/* Maximum scatter/gather per FMR */
#define RPCRDMA_MAX_FMR_SGES (64)
+static struct workqueue_struct *fmr_recovery_wq;
+
+#define FMR_RECOVERY_WQ_FLAGS (WQ_UNBOUND)
+
+int
+fmr_alloc_recovery_wq(void)
+{
+ fmr_recovery_wq = alloc_workqueue("fmr_recovery", WQ_UNBOUND, 0);
+ return !fmr_recovery_wq ? -ENOMEM : 0;
+}
+
+void
+fmr_destroy_recovery_wq(void)
+{
+ struct workqueue_struct *wq;
+
+ if (!fmr_recovery_wq)
+ return;
+
+ wq = fmr_recovery_wq;
+ fmr_recovery_wq = NULL;
+ destroy_workqueue(wq);
+}
+
+static int
+__fmr_unmap(struct rpcrdma_mw *mw)
+{
+ LIST_HEAD(l);
+
+ list_add(&mw->fmr.fmr->list, &l);
+ return ib_unmap_fmr(&l);
+}
+
+/* Deferred reset of a single FMR. Generate a fresh rkey by
+ * replacing the MR. There's no recovery if this fails.
+ */
+static void
+__fmr_recovery_worker(struct work_struct *work)
+{
+ struct rpcrdma_mw *mw = container_of(work, struct rpcrdma_mw,
+ mw_work);
+ struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+
+ __fmr_unmap(mw);
+ rpcrdma_put_mw(r_xprt, mw);
+ return;
+}
+
+/* A broken MR was discovered in a context that can't sleep.
+ * Defer recovery to the recovery worker.
+ */
+static void
+__fmr_queue_recovery(struct rpcrdma_mw *mw)
+{
+ INIT_WORK(&mw->mw_work, __fmr_recovery_worker);
+ queue_work(fmr_recovery_wq, &mw->mw_work);
+}
+
static int
fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
struct rpcrdma_create_data_internal *cdata)
{
+ rpcrdma_set_max_header_sizes(ia, cdata, max_t(unsigned int, 1,
+ RPCRDMA_MAX_DATA_SEGS /
+ RPCRDMA_MAX_FMR_SGES));
return 0;
}
@@ -48,7 +109,7 @@ static size_t
fmr_op_maxpages(struct rpcrdma_xprt *r_xprt)
{
return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
- rpcrdma_max_segments(r_xprt) * RPCRDMA_MAX_FMR_SGES);
+ RPCRDMA_MAX_HDR_SEGS * RPCRDMA_MAX_FMR_SGES);
}
static int
@@ -89,6 +150,7 @@ fmr_op_init(struct rpcrdma_xprt *r_xprt)
if (IS_ERR(r->fmr.fmr))
goto out_fmr_err;
+ r->mw_xprt = r_xprt;
list_add(&r->mw_list, &buf->rb_mws);
list_add(&r->mw_all, &buf->rb_all);
}
@@ -104,15 +166,6 @@ out:
return rc;
}
-static int
-__fmr_unmap(struct rpcrdma_mw *r)
-{
- LIST_HEAD(l);
-
- list_add(&r->fmr.fmr->list, &l);
- return ib_unmap_fmr(&l);
-}
-
/* Use the ib_map_phys_fmr() verb to register a memory region
* for remote access via RDMA READ or RDMA WRITE.
*/
@@ -183,15 +236,10 @@ static void
__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
{
struct ib_device *device = r_xprt->rx_ia.ri_device;
- struct rpcrdma_mw *mw = seg->rl_mw;
int nsegs = seg->mr_nsegs;
- seg->rl_mw = NULL;
-
while (nsegs--)
rpcrdma_unmap_one(device, seg++);
-
- rpcrdma_put_mw(r_xprt, mw);
}
/* Invalidate all memory regions that were registered for "req".
@@ -234,42 +282,50 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
seg = &req->rl_segments[i];
__fmr_dma_unmap(r_xprt, seg);
+ rpcrdma_put_mw(r_xprt, seg->rl_mw);
i += seg->mr_nsegs;
seg->mr_nsegs = 0;
+ seg->rl_mw = NULL;
}
req->rl_nchunks = 0;
}
-/* Use the ib_unmap_fmr() verb to prevent further remote
- * access via RDMA READ or RDMA WRITE.
+/* Use a slow, safe mechanism to invalidate all memory regions
+ * that were registered for "req".
+ *
+ * In the asynchronous case, DMA unmapping occurs first here
+ * because the rpcrdma_mr_seg is released immediately after this
+ * call. It's contents won't be available in __fmr_dma_unmap later.
+ * FIXME.
*/
-static int
-fmr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+static void
+fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
+ bool sync)
{
- struct rpcrdma_ia *ia = &r_xprt->rx_ia;
- struct rpcrdma_mr_seg *seg1 = seg;
- struct rpcrdma_mw *mw = seg1->rl_mw;
- int rc, nsegs = seg->mr_nsegs;
+ struct rpcrdma_mr_seg *seg;
+ struct rpcrdma_mw *mw;
+ unsigned int i;
- dprintk("RPC: %s: FMR %p\n", __func__, mw);
+ for (i = 0; req->rl_nchunks; req->rl_nchunks--) {
+ seg = &req->rl_segments[i];
+ mw = seg->rl_mw;
- seg1->rl_mw = NULL;
- while (seg1->mr_nsegs--)
- rpcrdma_unmap_one(ia->ri_device, seg++);
- rc = __fmr_unmap(mw);
- if (rc)
- goto out_err;
- rpcrdma_put_mw(r_xprt, mw);
- return nsegs;
+ if (sync) {
+ /* ORDER */
+ __fmr_unmap(mw);
+ __fmr_dma_unmap(r_xprt, seg);
+ rpcrdma_put_mw(r_xprt, mw);
+ } else {
+ __fmr_dma_unmap(r_xprt, seg);
+ __fmr_queue_recovery(mw);
+ }
-out_err:
- /* The FMR is abandoned, but remains in rb_all. fmr_op_destroy
- * will attempt to release it when the transport is destroyed.
- */
- dprintk("RPC: %s: ib_unmap_fmr status %i\n", __func__, rc);
- return nsegs;
+ i += seg->mr_nsegs;
+ seg->mr_nsegs = 0;
+ seg->rl_mw = NULL;
+ }
}
static void
@@ -295,7 +351,7 @@ fmr_op_destroy(struct rpcrdma_buffer *buf)
const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = {
.ro_map = fmr_op_map,
.ro_unmap_sync = fmr_op_unmap_sync,
- .ro_unmap = fmr_op_unmap,
+ .ro_unmap_safe = fmr_op_unmap_safe,
.ro_open = fmr_op_open,
.ro_maxpages = fmr_op_maxpages,
.ro_init = fmr_op_init,
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 94c3fa910b85..c0947544babe 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -98,6 +98,47 @@ frwr_destroy_recovery_wq(void)
destroy_workqueue(wq);
}
+static int
+__frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r)
+{
+ struct rpcrdma_frmr *f = &r->frmr;
+ int rc;
+
+ rc = ib_dereg_mr(f->fr_mr);
+ if (rc) {
+ pr_warn("rpcrdma: ib_dereg_mr status %d, frwr %p orphaned\n",
+ rc, r);
+ return rc;
+ }
+
+ f->fr_mr = ib_alloc_mr(ia->ri_pd, IB_MR_TYPE_MEM_REG,
+ ia->ri_max_frmr_depth);
+ if (IS_ERR(f->fr_mr)) {
+ pr_warn("rpcrdma: ib_alloc_mr status %ld, frwr %p orphaned\n",
+ PTR_ERR(f->fr_mr), r);
+ return PTR_ERR(f->fr_mr);
+ }
+
+ dprintk("RPC: %s: recovered FRMR %p\n", __func__, r);
+ f->fr_state = FRMR_IS_INVALID;
+ return 0;
+}
+
+static void
+__frwr_reset_and_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
+{
+ struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+ struct rpcrdma_frmr *f = &mw->frmr;
+ int rc;
+
+ rc = __frwr_reset_mr(ia, mw);
+ ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents, f->fr_dir);
+ if (rc)
+ return;
+
+ rpcrdma_put_mw(r_xprt, mw);
+}
+
/* Deferred reset of a single FRMR. Generate a fresh rkey by
* replacing the MR.
*
@@ -109,26 +150,10 @@ static void
__frwr_recovery_worker(struct work_struct *work)
{
struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw,
- frmr.fr_work);
- struct rpcrdma_xprt *r_xprt = r->frmr.fr_xprt;
- unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
- struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
-
- if (ib_dereg_mr(r->frmr.fr_mr))
- goto out_fail;
+ mw_work);
- r->frmr.fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth);
- if (IS_ERR(r->frmr.fr_mr))
- goto out_fail;
-
- dprintk("RPC: %s: recovered FRMR %p\n", __func__, r);
- r->frmr.fr_state = FRMR_IS_INVALID;
- rpcrdma_put_mw(r_xprt, r);
+ __frwr_reset_and_unmap(r->mw_xprt, r);
return;
-
-out_fail:
- pr_warn("RPC: %s: FRMR %p unrecovered\n",
- __func__, r);
}
/* A broken MR was discovered in a context that can't sleep.
@@ -137,8 +162,8 @@ out_fail:
static void
__frwr_queue_recovery(struct rpcrdma_mw *r)
{
- INIT_WORK(&r->frmr.fr_work, __frwr_recovery_worker);
- queue_work(frwr_recovery_wq, &r->frmr.fr_work);
+ INIT_WORK(&r->mw_work, __frwr_recovery_worker);
+ queue_work(frwr_recovery_wq, &r->mw_work);
}
static int
@@ -152,11 +177,11 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
if (IS_ERR(f->fr_mr))
goto out_mr_err;
- f->sg = kcalloc(depth, sizeof(*f->sg), GFP_KERNEL);
- if (!f->sg)
+ f->fr_sg = kcalloc(depth, sizeof(*f->fr_sg), GFP_KERNEL);
+ if (!f->fr_sg)
goto out_list_err;
- sg_init_table(f->sg, depth);
+ sg_init_table(f->fr_sg, depth);
init_completion(&f->fr_linv_done);
@@ -185,7 +210,7 @@ __frwr_release(struct rpcrdma_mw *r)
if (rc)
dprintk("RPC: %s: ib_dereg_mr status %i\n",
__func__, rc);
- kfree(r->frmr.sg);
+ kfree(r->frmr.fr_sg);
}
static int
@@ -231,6 +256,9 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
depth;
}
+ rpcrdma_set_max_header_sizes(ia, cdata, max_t(unsigned int, 1,
+ RPCRDMA_MAX_DATA_SEGS /
+ ia->ri_max_frmr_depth));
return 0;
}
@@ -243,7 +271,7 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt)
struct rpcrdma_ia *ia = &r_xprt->rx_ia;
return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
- rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth);
+ RPCRDMA_MAX_HDR_SEGS * ia->ri_max_frmr_depth);
}
static void
@@ -350,9 +378,9 @@ frwr_op_init(struct rpcrdma_xprt *r_xprt)
return rc;
}
+ r->mw_xprt = r_xprt;
list_add(&r->mw_list, &buf->rb_mws);
list_add(&r->mw_all, &buf->rb_all);
- r->frmr.fr_xprt = r_xprt;
}
return 0;
@@ -396,12 +424,12 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
for (i = 0; i < nsegs;) {
if (seg->mr_page)
- sg_set_page(&frmr->sg[i],
+ sg_set_page(&frmr->fr_sg[i],
seg->mr_page,
seg->mr_len,
offset_in_page(seg->mr_offset));
else
- sg_set_buf(&frmr->sg[i], seg->mr_offset,
+ sg_set_buf(&frmr->fr_sg[i], seg->mr_offset,
seg->mr_len);
++seg;
@@ -412,25 +440,26 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
break;
}
- frmr->sg_nents = i;
+ frmr->fr_nents = i;
+ frmr->fr_dir = direction;
- dma_nents = ib_dma_map_sg(device, frmr->sg, frmr->sg_nents, direction);
+ dma_nents = ib_dma_map_sg(device, frmr->fr_sg, frmr->fr_nents, direction);
if (!dma_nents) {
pr_err("RPC: %s: failed to dma map sg %p sg_nents %u\n",
- __func__, frmr->sg, frmr->sg_nents);
+ __func__, frmr->fr_sg, frmr->fr_nents);
return -ENOMEM;
}
- n = ib_map_mr_sg(mr, frmr->sg, frmr->sg_nents, NULL, PAGE_SIZE);
- if (unlikely(n != frmr->sg_nents)) {
+ n = ib_map_mr_sg(mr, frmr->fr_sg, frmr->fr_nents, NULL, PAGE_SIZE);
+ if (unlikely(n != frmr->fr_nents)) {
pr_err("RPC: %s: failed to map mr %p (%u/%u)\n",
- __func__, frmr->fr_mr, n, frmr->sg_nents);
+ __func__, frmr->fr_mr, n, frmr->fr_nents);
rc = n < 0 ? n : -EINVAL;
goto out_senderr;
}
dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n",
- __func__, mw, frmr->sg_nents, mr->length);
+ __func__, mw, frmr->fr_nents, mr->length);
key = (u8)(mr->rkey & 0x000000FF);
ib_update_fast_reg_key(mr, ++key);
@@ -452,18 +481,16 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
if (rc)
goto out_senderr;
- seg1->mr_dir = direction;
seg1->rl_mw = mw;
seg1->mr_rkey = mr->rkey;
seg1->mr_base = mr->iova;
- seg1->mr_nsegs = frmr->sg_nents;
+ seg1->mr_nsegs = frmr->fr_nents;
seg1->mr_len = mr->length;
- return frmr->sg_nents;
+ return frmr->fr_nents;
out_senderr:
dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc);
- ib_dma_unmap_sg(device, frmr->sg, dma_nents, direction);
__frwr_queue_recovery(mw);
return rc;
}
@@ -487,24 +514,6 @@ __frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg)
return invalidate_wr;
}
-static void
-__frwr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
- int rc)
-{
- struct ib_device *device = r_xprt->rx_ia.ri_device;
- struct rpcrdma_mw *mw = seg->rl_mw;
- struct rpcrdma_frmr *f = &mw->frmr;
-
- seg->rl_mw = NULL;
-
- ib_dma_unmap_sg(device, f->sg, f->sg_nents, seg->mr_dir);
-
- if (!rc)
- rpcrdma_put_mw(r_xprt, mw);
- else
- __frwr_queue_recovery(mw);
-}
-
/* Invalidate all memory regions that were registered for "req".
*
* Sleeps until it is safe for the host CPU to access the
@@ -518,6 +527,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
struct rpcrdma_mr_seg *seg;
unsigned int i, nchunks;
struct rpcrdma_frmr *f;
+ struct rpcrdma_mw *mw;
int rc;
dprintk("RPC: %s: req %p\n", __func__, req);
@@ -558,11 +568,8 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
* unless ri_id->qp is a valid pointer.
*/
rc = ib_post_send(ia->ri_id->qp, invalidate_wrs, &bad_wr);
- if (rc) {
- pr_warn("%s: ib_post_send failed %i\n", __func__, rc);
- rdma_disconnect(ia->ri_id);
- goto unmap;
- }
+ if (rc)
+ goto reset_mrs;
wait_for_completion(&f->fr_linv_done);
@@ -572,56 +579,65 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
unmap:
for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
seg = &req->rl_segments[i];
+ mw = seg->rl_mw;
+ seg->rl_mw = NULL;
- __frwr_dma_unmap(r_xprt, seg, rc);
+ ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents,
+ f->fr_dir);
+ rpcrdma_put_mw(r_xprt, mw);
i += seg->mr_nsegs;
seg->mr_nsegs = 0;
}
req->rl_nchunks = 0;
-}
+ return;
-/* Post a LOCAL_INV Work Request to prevent further remote access
- * via RDMA READ or RDMA WRITE.
- */
-static int
-frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
-{
- struct rpcrdma_mr_seg *seg1 = seg;
- struct rpcrdma_ia *ia = &r_xprt->rx_ia;
- struct rpcrdma_mw *mw = seg1->rl_mw;
- struct rpcrdma_frmr *frmr = &mw->frmr;
- struct ib_send_wr *invalidate_wr, *bad_wr;
- int rc, nsegs = seg->mr_nsegs;
+reset_mrs:
+ pr_warn("%s: ib_post_send failed %i\n", __func__, rc);
- dprintk("RPC: %s: FRMR %p\n", __func__, mw);
+ /* Find and reset the MRs in the LOCAL_INV WRs that did not
+ * get posted. This is synchronous, and slow.
+ */
+ for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
+ seg = &req->rl_segments[i];
+ mw = seg->rl_mw;
+ f = &mw->frmr;
- seg1->rl_mw = NULL;
- frmr->fr_state = FRMR_IS_INVALID;
- invalidate_wr = &mw->frmr.fr_invwr;
+ if (mw->frmr.fr_mr->rkey == bad_wr->ex.invalidate_rkey) {
+ __frwr_reset_mr(ia, mw);
+ bad_wr = bad_wr->next;
+ }
- memset(invalidate_wr, 0, sizeof(*invalidate_wr));
- frmr->fr_cqe.done = frwr_wc_localinv;
- invalidate_wr->wr_cqe = &frmr->fr_cqe;
- invalidate_wr->opcode = IB_WR_LOCAL_INV;
- invalidate_wr->ex.invalidate_rkey = frmr->fr_mr->rkey;
- DECR_CQCOUNT(&r_xprt->rx_ep);
+ i += seg->mr_nsegs;
+ }
+ goto unmap;
+}
- ib_dma_unmap_sg(ia->ri_device, frmr->sg, frmr->sg_nents, seg1->mr_dir);
- read_lock(&ia->ri_qplock);
- rc = ib_post_send(ia->ri_id->qp, invalidate_wr, &bad_wr);
- read_unlock(&ia->ri_qplock);
- if (rc)
- goto out_err;
+/* Use a slow, safe mechanism to invalidate all memory regions
+ * that were registered for "req".
+ */
+static void
+frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
+ bool sync)
+{
+ struct rpcrdma_mr_seg *seg;
+ struct rpcrdma_mw *mw;
+ unsigned int i;
- rpcrdma_put_mw(r_xprt, mw);
- return nsegs;
+ for (i = 0; req->rl_nchunks; req->rl_nchunks--) {
+ seg = &req->rl_segments[i];
+ mw = seg->rl_mw;
-out_err:
- dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc);
- __frwr_queue_recovery(mw);
- return nsegs;
+ if (sync)
+ __frwr_reset_and_unmap(r_xprt, mw);
+ else
+ __frwr_queue_recovery(mw);
+
+ i += seg->mr_nsegs;
+ seg->mr_nsegs = 0;
+ seg->rl_mw = NULL;
+ }
}
static void
@@ -643,7 +659,7 @@ frwr_op_destroy(struct rpcrdma_buffer *buf)
const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = {
.ro_map = frwr_op_map,
.ro_unmap_sync = frwr_op_unmap_sync,
- .ro_unmap = frwr_op_unmap,
+ .ro_unmap_safe = frwr_op_unmap_safe,
.ro_open = frwr_op_open,
.ro_maxpages = frwr_op_maxpages,
.ro_init = frwr_op_init,
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
index 481b9b6f4a15..3750596cc432 100644
--- a/net/sunrpc/xprtrdma/physical_ops.c
+++ b/net/sunrpc/xprtrdma/physical_ops.c
@@ -36,8 +36,11 @@ physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
__func__, PTR_ERR(mr));
return -ENOMEM;
}
-
ia->ri_dma_mr = mr;
+
+ rpcrdma_set_max_header_sizes(ia, cdata, min_t(unsigned int,
+ RPCRDMA_MAX_DATA_SEGS,
+ RPCRDMA_MAX_HDR_SEGS));
return 0;
}
@@ -47,7 +50,7 @@ static size_t
physical_op_maxpages(struct rpcrdma_xprt *r_xprt)
{
return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
- rpcrdma_max_segments(r_xprt));
+ RPCRDMA_MAX_HDR_SEGS);
}
static int
@@ -71,17 +74,6 @@ physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
return 1;
}
-/* Unmap a memory region, but leave it registered.
- */
-static int
-physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
-{
- struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-
- rpcrdma_unmap_one(ia->ri_device, seg);
- return 1;
-}
-
/* DMA unmap all memory regions that were mapped for "req".
*/
static void
@@ -94,6 +86,25 @@ physical_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
rpcrdma_unmap_one(device, &req->rl_segments[i++]);
}
+/* Use a slow, safe mechanism to invalidate all memory regions
+ * that were registered for "req".
+ *
+ * For physical memory registration, there is no good way to
+ * fence a single MR that has been advertised to the server. The
+ * client has already handed the server an R_key that cannot be
+ * invalidated and is shared by all MRs on this connection.
+ * Tearing down the PD might be the only safe choice, but it's
+ * not clear that a freshly acquired DMA R_key would be different
+ * than the one used by the PD that was just destroyed.
+ * FIXME.
+ */
+static void
+physical_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
+ bool sync)
+{
+ physical_op_unmap_sync(r_xprt, req);
+}
+
static void
physical_op_destroy(struct rpcrdma_buffer *buf)
{
@@ -102,7 +113,7 @@ physical_op_destroy(struct rpcrdma_buffer *buf)
const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = {
.ro_map = physical_op_map,
.ro_unmap_sync = physical_op_unmap_sync,
- .ro_unmap = physical_op_unmap,
+ .ro_unmap_safe = physical_op_unmap_safe,
.ro_open = physical_op_open,
.ro_maxpages = physical_op_maxpages,
.ro_init = physical_op_init,
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 888823bb6dae..35a81096e83d 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -61,26 +61,84 @@ enum rpcrdma_chunktype {
rpcrdma_replych
};
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
static const char transfertypes[][12] = {
- "pure inline", /* no chunks */
- " read chunk", /* some argument via rdma read */
- "*read chunk", /* entire request via rdma read */
- "write chunk", /* some result via rdma write */
+ "inline", /* no chunks */
+ "read list", /* some argument via rdma read */
+ "*read list", /* entire request via rdma read */
+ "write list", /* some result via rdma write */
"reply chunk" /* entire reply via rdma write */
};
-#endif
+
+/* Returns size of largest RPC-over-RDMA header in a Call message
+ *
+ * The largest Call header contains a full-size Read list and a
+ * minimal Reply chunk.
+ */
+static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs)
+{
+ unsigned int size;
+
+ /* Fixed header fields and list discriminators */
+ size = RPCRDMA_HDRLEN_MIN;
+
+ /* Maximum Read list size */
+ maxsegs += 2; /* segment for head and tail buffers */
+ size = maxsegs * sizeof(struct rpcrdma_read_chunk);
+
+ /* Minimal Read chunk size */
+ size += sizeof(__be32); /* segment count */
+ size += sizeof(struct rpcrdma_segment);
+ size += sizeof(__be32); /* list discriminator */
+
+ dprintk("RPC: %s: max call header size = %u\n",
+ __func__, size);
+ return size;
+}
+
+/* Returns size of largest RPC-over-RDMA header in a Reply message
+ *
+ * There is only one Write list or one Reply chunk per Reply
+ * message. The larger list is the Write list.
+ */
+static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs)
+{
+ unsigned int size;
+
+ /* Fixed header fields and list discriminators */
+ size = RPCRDMA_HDRLEN_MIN;
+
+ /* Maximum Write list size */
+ maxsegs += 2; /* segment for head and tail buffers */
+ size = sizeof(__be32); /* segment count */
+ size += maxsegs * sizeof(struct rpcrdma_segment);
+ size += sizeof(__be32); /* list discriminator */
+
+ dprintk("RPC: %s: max reply header size = %u\n",
+ __func__, size);
+ return size;
+}
+
+void rpcrdma_set_max_header_sizes(struct rpcrdma_ia *ia,
+ struct rpcrdma_create_data_internal *cdata,
+ unsigned int maxsegs)
+{
+ ia->ri_max_inline_write = cdata->inline_wsize -
+ rpcrdma_max_call_header_size(maxsegs);
+ ia->ri_max_inline_read = cdata->inline_rsize -
+ rpcrdma_max_reply_header_size(maxsegs);
+}
/* The client can send a request inline as long as the RPCRDMA header
* plus the RPC call fit under the transport's inline limit. If the
* combined call message size exceeds that limit, the client must use
* the read chunk list for this operation.
*/
-static bool rpcrdma_args_inline(struct rpc_rqst *rqst)
+static bool rpcrdma_args_inline(struct rpcrdma_xprt *r_xprt,
+ struct rpc_rqst *rqst)
{
- unsigned int callsize = RPCRDMA_HDRLEN_MIN + rqst->rq_snd_buf.len;
+ struct rpcrdma_ia *ia = &r_xprt->rx_ia;
- return callsize <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst);
+ return rqst->rq_snd_buf.len <= ia->ri_max_inline_write;
}
/* The client can't know how large the actual reply will be. Thus it
@@ -89,11 +147,12 @@ static bool rpcrdma_args_inline(struct rpc_rqst *rqst)
* limit, the client must provide a write list or a reply chunk for
* this request.
*/
-static bool rpcrdma_results_inline(struct rpc_rqst *rqst)
+static bool rpcrdma_results_inline(struct rpcrdma_xprt *r_xprt,
+ struct rpc_rqst *rqst)
{
- unsigned int repsize = RPCRDMA_HDRLEN_MIN + rqst->rq_rcv_buf.buflen;
+ struct rpcrdma_ia *ia = &r_xprt->rx_ia;
- return repsize <= RPCRDMA_INLINE_READ_THRESHOLD(rqst);
+ return rqst->rq_rcv_buf.buflen <= ia->ri_max_inline_read;
}
static int
@@ -226,23 +285,16 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
return n;
}
-/*
- * Create read/write chunk lists, and reply chunks, for RDMA
- *
- * Assume check against THRESHOLD has been done, and chunks are required.
- * Assume only encoding one list entry for read|write chunks. The NFSv3
- * protocol is simple enough to allow this as it only has a single "bulk
- * result" in each procedure - complicated NFSv4 COMPOUNDs are not. (The
- * RDMA/Sessions NFSv4 proposal addresses this for future v4 revs.)
- *
- * When used for a single reply chunk (which is a special write
- * chunk used for the entire reply, rather than just the data), it
- * is used primarily for READDIR and READLINK which would otherwise
- * be severely size-limited by a small rdma inline read max. The server
- * response will come back as an RDMA Write, followed by a message
- * of type RDMA_NOMSG carrying the xid and length. As a result, reply
- * chunks do not provide data alignment, however they do not require
- * "fixup" (moving the response to the upper layer buffer) either.
+static inline __be32 *
+xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mr_seg *seg)
+{
+ *iptr++ = cpu_to_be32(seg->mr_rkey);
+ *iptr++ = cpu_to_be32(seg->mr_len);
+ return xdr_encode_hyper(iptr, seg->mr_base);
+}
+
+/* XDR-encode the Read list. Supports encoding a list of read
+ * segments that belong to a single read chunk.
*
* Encoding key for single-list chunks (HLOO = Handle32 Length32 Offset64):
*
@@ -250,131 +302,190 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
* N elements, position P (same P for all chunks of same arg!):
* 1 - PHLOO - 1 - PHLOO - ... - 1 - PHLOO - 0
*
+ * Returns a pointer to the XDR word in the RDMA header following
+ * the end of the Read list, or an error pointer.
+ */
+static __be32 *
+rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
+ struct rpcrdma_req *req, struct rpc_rqst *rqst,
+ __be32 *iptr, enum rpcrdma_chunktype rtype)
+{
+ struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+ unsigned int pos;
+ int n, nsegs;
+
+ if (rtype == rpcrdma_noch) {
+ *iptr++ = xdr_zero; /* item not present */
+ return iptr;
+ }
+
+ pos = rqst->rq_snd_buf.head[0].iov_len;
+ if (rtype == rpcrdma_areadch)
+ pos = 0;
+ nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg,
+ RPCRDMA_MAX_SEGS - req->rl_nchunks);
+ if (nsegs < 0)
+ return ERR_PTR(nsegs);
+
+ do {
+ n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, false);
+ if (n <= 0)
+ return ERR_PTR(n);
+
+ *iptr++ = xdr_one; /* item present */
+
+ /* All read segments in this chunk
+ * have the same "position".
+ */
+ *iptr++ = cpu_to_be32(pos);
+ iptr = xdr_encode_rdma_segment(iptr, seg);
+
+ dprintk("RPC: %5u %s: read segment pos %u "
+ "%d@0x%016llx:0x%08x (%s)\n",
+ rqst->rq_task->tk_pid, __func__, pos,
+ seg->mr_len, (unsigned long long)seg->mr_base,
+ seg->mr_rkey, n < nsegs ? "more" : "last");
+
+ r_xprt->rx_stats.read_chunk_count++;
+ req->rl_nchunks++;
+ seg += n;
+ nsegs -= n;
+ } while (nsegs);
+ req->rl_nextseg = seg;
+
+ /* Finish Read list */
+ *iptr++ = xdr_zero; /* Next item not present */
+ return iptr;
+}
+
+/* XDR-encode the Write list. Supports encoding a list containing
+ * one array of plain segments that belong to a single write chunk.
+ *
+ * Encoding key for single-list chunks (HLOO = Handle32 Length32 Offset64):
+ *
* Write chunklist (a list of (one) counted array):
* N elements:
* 1 - N - HLOO - HLOO - ... - HLOO - 0
*
+ * Returns a pointer to the XDR word in the RDMA header following
+ * the end of the Write list, or an error pointer.
+ */
+static __be32 *
+rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
+ struct rpc_rqst *rqst, __be32 *iptr,
+ enum rpcrdma_chunktype wtype)
+{
+ struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+ int n, nsegs, nchunks;
+ __be32 *segcount;
+
+ if (wtype != rpcrdma_writech) {
+ *iptr++ = xdr_zero; /* no Write list present */
+ return iptr;
+ }
+
+ nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf,
+ rqst->rq_rcv_buf.head[0].iov_len,
+ wtype, seg,
+ RPCRDMA_MAX_SEGS - req->rl_nchunks);
+ if (nsegs < 0)
+ return ERR_PTR(nsegs);
+
+ *iptr++ = xdr_one; /* Write list present */
+ segcount = iptr++; /* save location of segment count */
+
+ nchunks = 0;
+ do {
+ n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true);
+ if (n <= 0)
+ return ERR_PTR(n);
+
+ iptr = xdr_encode_rdma_segment(iptr, seg);
+
+ dprintk("RPC: %5u %s: write segment "
+ "%d@0x016%llx:0x%08x (%s)\n",
+ rqst->rq_task->tk_pid, __func__,
+ seg->mr_len, (unsigned long long)seg->mr_base,
+ seg->mr_rkey, n < nsegs ? "more" : "last");
+
+ r_xprt->rx_stats.write_chunk_count++;
+ r_xprt->rx_stats.total_rdma_request += seg->mr_len;
+ req->rl_nchunks++;
+ nchunks++;
+ seg += n;
+ nsegs -= n;
+ } while (nsegs);
+ req->rl_nextseg = seg;
+
+ /* Update count of segments in this Write chunk */
+ *segcount = cpu_to_be32(nchunks);
+
+ /* Finish Write list */
+ *iptr++ = xdr_zero; /* Next item not present */
+ return iptr;
+}
+
+/* XDR-encode the Reply chunk. Supports encoding an array of plain
+ * segments that belong to a single write (reply) chunk.
+ *
+ * Encoding key for single-list chunks (HLOO = Handle32 Length32 Offset64):
+ *
* Reply chunk (a counted array):
* N elements:
* 1 - N - HLOO - HLOO - ... - HLOO
*
- * Returns positive RPC/RDMA header size, or negative errno.
+ * Returns a pointer to the XDR word in the RDMA header following
+ * the end of the Reply chunk, or an error pointer.
*/
-
-static ssize_t
-rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
- struct rpcrdma_msg *headerp, enum rpcrdma_chunktype type)
+static __be32 *
+rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
+ struct rpcrdma_req *req, struct rpc_rqst *rqst,
+ __be32 *iptr, enum rpcrdma_chunktype wtype)
{
- struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
- struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
- int n, nsegs, nchunks = 0;
- unsigned int pos;
- struct rpcrdma_mr_seg *seg = req->rl_segments;
- struct rpcrdma_read_chunk *cur_rchunk = NULL;
- struct rpcrdma_write_array *warray = NULL;
- struct rpcrdma_write_chunk *cur_wchunk = NULL;
- __be32 *iptr = headerp->rm_body.rm_chunks;
- int (*map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool);
-
- if (type == rpcrdma_readch || type == rpcrdma_areadch) {
- /* a read chunk - server will RDMA Read our memory */
- cur_rchunk = (struct rpcrdma_read_chunk *) iptr;
- } else {
- /* a write or reply chunk - server will RDMA Write our memory */
- *iptr++ = xdr_zero; /* encode a NULL read chunk list */
- if (type == rpcrdma_replych)
- *iptr++ = xdr_zero; /* a NULL write chunk list */
- warray = (struct rpcrdma_write_array *) iptr;
- cur_wchunk = (struct rpcrdma_write_chunk *) (warray + 1);
- }
+ struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+ int n, nsegs, nchunks;
+ __be32 *segcount;
- if (type == rpcrdma_replych || type == rpcrdma_areadch)
- pos = 0;
- else
- pos = target->head[0].iov_len;
+ if (wtype != rpcrdma_replych) {
+ *iptr++ = xdr_zero; /* no Reply chunk present */
+ return iptr;
+ }
- nsegs = rpcrdma_convert_iovs(target, pos, type, seg, RPCRDMA_MAX_SEGS);
+ nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg,
+ RPCRDMA_MAX_SEGS - req->rl_nchunks);
if (nsegs < 0)
- return nsegs;
+ return ERR_PTR(nsegs);
- map = r_xprt->rx_ia.ri_ops->ro_map;
+ *iptr++ = xdr_one; /* Reply chunk present */
+ segcount = iptr++; /* save location of segment count */
+
+ nchunks = 0;
do {
- n = map(r_xprt, seg, nsegs, cur_wchunk != NULL);
+ n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true);
if (n <= 0)
- goto out;
- if (cur_rchunk) { /* read */
- cur_rchunk->rc_discrim = xdr_one;
- /* all read chunks have the same "position" */
- cur_rchunk->rc_position = cpu_to_be32(pos);
- cur_rchunk->rc_target.rs_handle =
- cpu_to_be32(seg->mr_rkey);
- cur_rchunk->rc_target.rs_length =
- cpu_to_be32(seg->mr_len);
- xdr_encode_hyper(
- (__be32 *)&cur_rchunk->rc_target.rs_offset,
- seg->mr_base);
- dprintk("RPC: %s: read chunk "
- "elem %d@0x%llx:0x%x pos %u (%s)\n", __func__,
- seg->mr_len, (unsigned long long)seg->mr_base,
- seg->mr_rkey, pos, n < nsegs ? "more" : "last");
- cur_rchunk++;
- r_xprt->rx_stats.read_chunk_count++;
- } else { /* write/reply */
- cur_wchunk->wc_target.rs_handle =
- cpu_to_be32(seg->mr_rkey);
- cur_wchunk->wc_target.rs_length =
- cpu_to_be32(seg->mr_len);
- xdr_encode_hyper(
- (__be32 *)&cur_wchunk->wc_target.rs_offset,
- seg->mr_base);
- dprintk("RPC: %s: %s chunk "
- "elem %d@0x%llx:0x%x (%s)\n", __func__,
- (type == rpcrdma_replych) ? "reply" : "write",
- seg->mr_len, (unsigned long long)seg->mr_base,
- seg->mr_rkey, n < nsegs ? "more" : "last");
- cur_wchunk++;
- if (type == rpcrdma_replych)
- r_xprt->rx_stats.reply_chunk_count++;
- else
- r_xprt->rx_stats.write_chunk_count++;
- r_xprt->rx_stats.total_rdma_request += seg->mr_len;
- }
+ return ERR_PTR(n);
+
+ iptr = xdr_encode_rdma_segment(iptr, seg);
+
+ dprintk("RPC: %5u %s: reply segment "
+ "%d@0x%016llx:0x%08x (%s)\n",
+ rqst->rq_task->tk_pid, __func__,
+ seg->mr_len, (unsigned long long)seg->mr_base,
+ seg->mr_rkey, n < nsegs ? "more" : "last");
+
+ r_xprt->rx_stats.reply_chunk_count++;
+ r_xprt->rx_stats.total_rdma_request += seg->mr_len;
+ req->rl_nchunks++;
nchunks++;
seg += n;
nsegs -= n;
} while (nsegs);
+ req->rl_nextseg = seg;
- /* success. all failures return above */
- req->rl_nchunks = nchunks;
-
- /*
- * finish off header. If write, marshal discrim and nchunks.
- */
- if (cur_rchunk) {
- iptr = (__be32 *) cur_rchunk;
- *iptr++ = xdr_zero; /* finish the read chunk list */
- *iptr++ = xdr_zero; /* encode a NULL write chunk list */
- *iptr++ = xdr_zero; /* encode a NULL reply chunk */
- } else {
- warray->wc_discrim = xdr_one;
- warray->wc_nchunks = cpu_to_be32(nchunks);
- iptr = (__be32 *) cur_wchunk;
- if (type == rpcrdma_writech) {
- *iptr++ = xdr_zero; /* finish the write chunk list */
- *iptr++ = xdr_zero; /* encode a NULL reply chunk */
- }
- }
-
- /*
- * Return header size.
- */
- return (unsigned char *)iptr - (unsigned char *)headerp;
+ /* Update count of segments in the Reply chunk */
+ *segcount = cpu_to_be32(nchunks);
-out:
- for (pos = 0; nchunks--;)
- pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
- &req->rl_segments[pos]);
- return n;
+ return iptr;
}
/*
@@ -440,13 +551,10 @@ static void rpcrdma_inline_pullup(struct rpc_rqst *rqst)
* Marshal a request: the primary job of this routine is to choose
* the transfer modes. See comments below.
*
- * Uses multiple RDMA IOVs for a request:
- * [0] -- RPC RDMA header, which uses memory from the *start* of the
- * preregistered buffer that already holds the RPC data in
- * its middle.
- * [1] -- the RPC header/data, marshaled by RPC and the NFS protocol.
- * [2] -- optional padding.
- * [3] -- if padded, header only in [1] and data here.
+ * Prepares up to two IOVs per Call message:
+ *
+ * [0] -- RPC RDMA header
+ * [1] -- the RPC header/data
*
* Returns zero on success, otherwise a negative errno.
*/
@@ -457,24 +565,17 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
struct rpc_xprt *xprt = rqst->rq_xprt;
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
- char *base;
- size_t rpclen;
- ssize_t hdrlen;
enum rpcrdma_chunktype rtype, wtype;
struct rpcrdma_msg *headerp;
+ ssize_t hdrlen;
+ size_t rpclen;
+ __be32 *iptr;
#if defined(CONFIG_SUNRPC_BACKCHANNEL)
if (test_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state))
return rpcrdma_bc_marshal_reply(rqst);
#endif
- /*
- * rpclen gets amount of data in first buffer, which is the
- * pre-registered buffer.
- */
- base = rqst->rq_svec[0].iov_base;
- rpclen = rqst->rq_svec[0].iov_len;
-
headerp = rdmab_to_msg(req->rl_rdmabuf);
/* don't byte-swap XID, it's already done in request */
headerp->rm_xid = rqst->rq_xid;
@@ -485,15 +586,16 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
/*
* Chunks needed for results?
*
- * o Read ops return data as write chunk(s), header as inline.
* o If the expected result is under the inline threshold, all ops
* return as inline.
+ * o Large read ops return data as write chunk(s), header as
+ * inline.
* o Large non-read ops return as a single reply chunk.
*/
- if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
- wtype = rpcrdma_writech;
- else if (rpcrdma_results_inline(rqst))
+ if (rpcrdma_results_inline(r_xprt, rqst))
wtype = rpcrdma_noch;
+ else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
+ wtype = rpcrdma_writech;
else
wtype = rpcrdma_replych;
@@ -511,10 +613,14 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
* that both has a data payload, and whose non-data arguments
* by themselves are larger than the inline threshold.
*/
- if (rpcrdma_args_inline(rqst)) {
+ if (rpcrdma_args_inline(r_xprt, rqst)) {
rtype = rpcrdma_noch;
+ rpcrdma_inline_pullup(rqst);
+ rpclen = rqst->rq_svec[0].iov_len;
} else if (rqst->rq_snd_buf.flags & XDRBUF_WRITE) {
rtype = rpcrdma_readch;
+ rpclen = rqst->rq_svec[0].iov_len;
+ rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf);
} else {
r_xprt->rx_stats.nomsg_call_count++;
headerp->rm_type = htonl(RDMA_NOMSG);
@@ -522,57 +628,50 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
rpclen = 0;
}
- /* The following simplification is not true forever */
- if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
- wtype = rpcrdma_noch;
- if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
- dprintk("RPC: %s: cannot marshal multiple chunk lists\n",
- __func__);
- return -EIO;
- }
-
- hdrlen = RPCRDMA_HDRLEN_MIN;
-
- /*
- * Pull up any extra send data into the preregistered buffer.
- * When padding is in use and applies to the transfer, insert
- * it and change the message type.
+ /* This implementation supports the following combinations
+ * of chunk lists in one RPC-over-RDMA Call message:
+ *
+ * - Read list
+ * - Write list
+ * - Reply chunk
+ * - Read list + Reply chunk
+ *
+ * It might not yet support the following combinations:
+ *
+ * - Read list + Write list
+ *
+ * It does not support the following combinations:
+ *
+ * - Write list + Reply chunk
+ * - Read list + Write list + Reply chunk
+ *
+ * This implementation supports only a single chunk in each
+ * Read or Write list. Thus for example the client cannot
+ * send a Call message with a Position Zero Read chunk and a
+ * regular Read chunk at the same time.
*/
- if (rtype == rpcrdma_noch) {
-
- rpcrdma_inline_pullup(rqst);
-
- headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero;
- headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero;
- headerp->rm_body.rm_nochunks.rm_empty[2] = xdr_zero;
- /* new length after pullup */
- rpclen = rqst->rq_svec[0].iov_len;
- } else if (rtype == rpcrdma_readch)
- rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf);
- if (rtype != rpcrdma_noch) {
- hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf,
- headerp, rtype);
- wtype = rtype; /* simplify dprintk */
-
- } else if (wtype != rpcrdma_noch) {
- hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf,
- headerp, wtype);
- }
- if (hdrlen < 0)
- return hdrlen;
+ req->rl_nchunks = 0;
+ req->rl_nextseg = req->rl_segments;
+ iptr = headerp->rm_body.rm_chunks;
+ iptr = rpcrdma_encode_read_list(r_xprt, req, rqst, iptr, rtype);
+ if (IS_ERR(iptr))
+ goto out_unmap;
+ iptr = rpcrdma_encode_write_list(r_xprt, req, rqst, iptr, wtype);
+ if (IS_ERR(iptr))
+ goto out_unmap;
+ iptr = rpcrdma_encode_reply_chunk(r_xprt, req, rqst, iptr, wtype);
+ if (IS_ERR(iptr))
+ goto out_unmap;
+ hdrlen = (unsigned char *)iptr - (unsigned char *)headerp;
+
+ if (hdrlen + rpclen > RPCRDMA_INLINE_WRITE_THRESHOLD(rqst))
+ goto out_overflow;
+
+ dprintk("RPC: %5u %s: %s/%s: hdrlen %zd rpclen %zd\n",
+ rqst->rq_task->tk_pid, __func__,
+ transfertypes[rtype], transfertypes[wtype],
+ hdrlen, rpclen);
- dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd"
- " headerp 0x%p base 0x%p lkey 0x%x\n",
- __func__, transfertypes[wtype], hdrlen, rpclen,
- headerp, base, rdmab_lkey(req->rl_rdmabuf));
-
- /*
- * initialize send_iov's - normally only two: rdma chunk header and
- * single preregistered RPC header buffer, but if padding is present,
- * then use a preregistered (and zeroed) pad buffer between the RPC
- * header and any write data. In all non-rdma cases, any following
- * data has been copied into the RPC header buffer.
- */
req->rl_send_iov[0].addr = rdmab_addr(req->rl_rdmabuf);
req->rl_send_iov[0].length = hdrlen;
req->rl_send_iov[0].lkey = rdmab_lkey(req->rl_rdmabuf);
@@ -587,6 +686,18 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
req->rl_niovs = 2;
return 0;
+
+out_overflow:
+ pr_err("rpcrdma: send overflow: hdrlen %zd rpclen %zu %s/%s\n",
+ hdrlen, rpclen, transfertypes[rtype], transfertypes[wtype]);
+ /* Terminate this RPC. Chunks registered above will be
+ * released by xprt_release -> xprt_rmda_free .
+ */
+ return -EIO;
+
+out_unmap:
+ r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
+ return PTR_ERR(iptr);
}
/*
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 765bca47c74d..0ba9887f3e22 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -145,19 +145,32 @@ static __be32 *decode_reply_array(__be32 *va, __be32 *vaend)
return (__be32 *)&ary->wc_array[nchunks];
}
-int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
+/**
+ * svc_rdma_xdr_decode_req - Parse incoming RPC-over-RDMA header
+ * @rq_arg: Receive buffer
+ *
+ * On entry, xdr->head[0].iov_base points to first byte in the
+ * RPC-over-RDMA header.
+ *
+ * On successful exit, head[0] points to first byte past the
+ * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message.
+ * The length of the RPC-over-RDMA header is returned.
+ */
+int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg)
{
+ struct rpcrdma_msg *rmsgp;
__be32 *va, *vaend;
unsigned int len;
u32 hdr_len;
/* Verify that there's enough bytes for header + something */
- if (rqstp->rq_arg.len <= RPCRDMA_HDRLEN_ERR) {
+ if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) {
dprintk("svcrdma: header too short = %d\n",
- rqstp->rq_arg.len);
+ rq_arg->len);
return -EINVAL;
}
+ rmsgp = (struct rpcrdma_msg *)rq_arg->head[0].iov_base;
if (rmsgp->rm_vers != rpcrdma_version) {
dprintk("%s: bad version %u\n", __func__,
be32_to_cpu(rmsgp->rm_vers));
@@ -189,10 +202,10 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
be32_to_cpu(rmsgp->rm_body.rm_padded.rm_thresh);
va = &rmsgp->rm_body.rm_padded.rm_pempty[4];
- rqstp->rq_arg.head[0].iov_base = va;
+ rq_arg->head[0].iov_base = va;
len = (u32)((unsigned long)va - (unsigned long)rmsgp);
- rqstp->rq_arg.head[0].iov_len -= len;
- if (len > rqstp->rq_arg.len)
+ rq_arg->head[0].iov_len -= len;
+ if (len > rq_arg->len)
return -EINVAL;
return len;
default:
@@ -205,7 +218,7 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
* chunk list and a reply chunk list.
*/
va = &rmsgp->rm_body.rm_chunks[0];
- vaend = (__be32 *)((unsigned long)rmsgp + rqstp->rq_arg.len);
+ vaend = (__be32 *)((unsigned long)rmsgp + rq_arg->len);
va = decode_read_list(va, vaend);
if (!va) {
dprintk("svcrdma: failed to decode read list\n");
@@ -222,10 +235,9 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
return -EINVAL;
}
- rqstp->rq_arg.head[0].iov_base = va;
+ rq_arg->head[0].iov_base = va;
hdr_len = (unsigned long)va - (unsigned long)rmsgp;
- rqstp->rq_arg.head[0].iov_len -= hdr_len;
-
+ rq_arg->head[0].iov_len -= hdr_len;
return hdr_len;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index fbe7444e7de6..2c25606f2561 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -447,10 +447,8 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
head->arg.len = rqstp->rq_arg.len;
head->arg.buflen = rqstp->rq_arg.buflen;
- ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
- position = be32_to_cpu(ch->rc_position);
-
/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+ position = be32_to_cpu(ch->rc_position);
if (position == 0) {
head->arg.pages = &head->pages[0];
page_offset = head->byte_len;
@@ -488,7 +486,7 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
if (page_offset & 3) {
u32 pad = 4 - (page_offset & 3);
- head->arg.page_len += pad;
+ head->arg.tail[0].iov_len += pad;
head->arg.len += pad;
head->arg.buflen += pad;
page_offset += pad;
@@ -510,11 +508,10 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
return ret;
}
-static int rdma_read_complete(struct svc_rqst *rqstp,
- struct svc_rdma_op_ctxt *head)
+static void rdma_read_complete(struct svc_rqst *rqstp,
+ struct svc_rdma_op_ctxt *head)
{
int page_no;
- int ret;
/* Copy RPC pages */
for (page_no = 0; page_no < head->count; page_no++) {
@@ -550,23 +547,6 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
rqstp->rq_arg.tail[0] = head->arg.tail[0];
rqstp->rq_arg.len = head->arg.len;
rqstp->rq_arg.buflen = head->arg.buflen;
-
- /* Free the context */
- svc_rdma_put_context(head, 0);
-
- /* XXX: What should this be? */
- rqstp->rq_prot = IPPROTO_MAX;
- svc_xprt_copy_addrs(rqstp, rqstp->rq_xprt);
-
- ret = rqstp->rq_arg.head[0].iov_len
- + rqstp->rq_arg.page_len
- + rqstp->rq_arg.tail[0].iov_len;
- dprintk("svcrdma: deferred read ret=%d, rq_arg.len=%u, "
- "rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zu\n",
- ret, rqstp->rq_arg.len, rqstp->rq_arg.head[0].iov_base,
- rqstp->rq_arg.head[0].iov_len);
-
- return ret;
}
/* By convention, backchannel calls arrive via rdma_msg type
@@ -624,7 +604,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
dto_q);
list_del_init(&ctxt->dto_q);
spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
- return rdma_read_complete(rqstp, ctxt);
+ rdma_read_complete(rqstp, ctxt);
+ goto complete;
} else if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next,
struct svc_rdma_op_ctxt,
@@ -655,7 +636,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
/* Decode the RDMA header. */
rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
- ret = svc_rdma_xdr_decode_req(rmsgp, rqstp);
+ ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg);
if (ret < 0)
goto out_err;
if (ret == 0)
@@ -682,6 +663,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
return 0;
}
+complete:
ret = rqstp->rq_arg.head[0].iov_len
+ rqstp->rq_arg.page_len
+ rqstp->rq_arg.tail[0].iov_len;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 4f1b1c4f45f9..54d533300620 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -463,25 +463,21 @@ static int send_reply(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
struct page *page,
struct rpcrdma_msg *rdma_resp,
- struct svc_rdma_op_ctxt *ctxt,
struct svc_rdma_req_map *vec,
int byte_count)
{
+ struct svc_rdma_op_ctxt *ctxt;
struct ib_send_wr send_wr;
u32 xdr_off;
int sge_no;
int sge_bytes;
int page_no;
int pages;
- int ret;
-
- ret = svc_rdma_repost_recv(rdma, GFP_KERNEL);
- if (ret) {
- svc_rdma_put_context(ctxt, 0);
- return -ENOTCONN;
- }
+ int ret = -EIO;
/* Prepare the context */
+ ctxt = svc_rdma_get_context(rdma);
+ ctxt->direction = DMA_TO_DEVICE;
ctxt->pages[0] = page;
ctxt->count = 1;
@@ -565,8 +561,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
err:
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 1);
- pr_err("svcrdma: failed to send reply, rc=%d\n", ret);
- return -EIO;
+ return ret;
}
void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp)
@@ -585,7 +580,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
int ret;
int inline_bytes;
struct page *res_page;
- struct svc_rdma_op_ctxt *ctxt;
struct svc_rdma_req_map *vec;
dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);
@@ -598,8 +592,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
rp_ary = svc_rdma_get_reply_array(rdma_argp, wr_ary);
/* Build an req vec for the XDR */
- ctxt = svc_rdma_get_context(rdma);
- ctxt->direction = DMA_TO_DEVICE;
vec = svc_rdma_get_req_map(rdma);
ret = svc_rdma_map_xdr(rdma, &rqstp->rq_res, vec, wr_ary != NULL);
if (ret)
@@ -635,7 +627,12 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
inline_bytes -= ret;
}
- ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, vec,
+ /* Post a fresh Receive buffer _before_ sending the reply */
+ ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
+ if (ret)
+ goto err1;
+
+ ret = send_reply(rdma, rqstp, res_page, rdma_resp, vec,
inline_bytes);
if (ret < 0)
goto err1;
@@ -648,7 +645,8 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
put_page(res_page);
err0:
svc_rdma_put_req_map(rdma, vec);
- svc_rdma_put_context(ctxt, 0);
+ pr_err("svcrdma: Could not send reply, err=%d. Closing transport.\n",
+ ret);
set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
return -ENOTCONN;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 90668969d559..dd9440137834 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -789,7 +789,7 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
int ret;
dprintk("svcrdma: Creating RDMA socket\n");
- if (sa->sa_family != AF_INET) {
+ if ((sa->sa_family != AF_INET) && (sa->sa_family != AF_INET6)) {
dprintk("svcrdma: Address family %d is not supported.\n", sa->sa_family);
return ERR_PTR(-EAFNOSUPPORT);
}
@@ -805,6 +805,16 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
goto err0;
}
+ /* Allow both IPv4 and IPv6 sockets to bind a single port
+ * at the same time.
+ */
+#if IS_ENABLED(CONFIG_IPV6)
+ ret = rdma_set_afonly(listen_id, 1);
+ if (ret) {
+ dprintk("svcrdma: rdma_set_afonly failed = %d\n", ret);
+ goto err1;
+ }
+#endif
ret = rdma_bind_addr(listen_id, sa);
if (ret) {
dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret);
@@ -1073,7 +1083,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV;
/* Post receive buffers */
- for (i = 0; i < newxprt->sc_rq_depth; i++) {
+ for (i = 0; i < newxprt->sc_max_requests; i++) {
ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
if (ret) {
dprintk("svcrdma: failure posting receive buffers\n");
@@ -1170,6 +1180,9 @@ static void __svc_rdma_free(struct work_struct *work)
dprintk("svcrdma: %s(%p)\n", __func__, rdma);
+ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
+ ib_drain_qp(rdma->sc_qp);
+
/* We should only be called from kref_put */
if (atomic_read(&xprt->xpt_ref.refcount) != 0)
pr_err("svcrdma: sc_xprt still in use? (%d)\n",
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index b1b009f10ea3..99d2e5b72726 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -73,6 +73,8 @@ static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE;
static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE;
+static unsigned int min_inline_size = RPCRDMA_MIN_INLINE;
+static unsigned int max_inline_size = RPCRDMA_MAX_INLINE;
static unsigned int zero;
static unsigned int max_padding = PAGE_SIZE;
static unsigned int min_memreg = RPCRDMA_BOUNCEBUFFERS;
@@ -96,6 +98,8 @@ static struct ctl_table xr_tunables_table[] = {
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
+ .extra1 = &min_inline_size,
+ .extra2 = &max_inline_size,
},
{
.procname = "rdma_max_inline_write",
@@ -103,6 +107,8 @@ static struct ctl_table xr_tunables_table[] = {
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
+ .extra1 = &min_inline_size,
+ .extra2 = &max_inline_size,
},
{
.procname = "rdma_inline_write_padding",
@@ -508,6 +514,7 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
out:
dprintk("RPC: %s: size %zd, request 0x%p\n", __func__, size, req);
req->rl_connect_cookie = 0; /* our reserved value */
+ req->rl_task = task;
return req->rl_sendbuf->rg_base;
out_rdmabuf:
@@ -564,7 +571,6 @@ xprt_rdma_free(void *buffer)
struct rpcrdma_req *req;
struct rpcrdma_xprt *r_xprt;
struct rpcrdma_regbuf *rb;
- int i;
if (buffer == NULL)
return;
@@ -578,11 +584,8 @@ xprt_rdma_free(void *buffer)
dprintk("RPC: %s: called on 0x%p\n", __func__, req->rl_reply);
- for (i = 0; req->rl_nchunks;) {
- --req->rl_nchunks;
- i += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
- &req->rl_segments[i]);
- }
+ r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req,
+ !RPC_IS_ASYNC(req->rl_task));
rpcrdma_buffer_put(req);
}
@@ -707,6 +710,7 @@ static struct rpc_xprt_ops xprt_rdma_procs = {
#if defined(CONFIG_SUNRPC_BACKCHANNEL)
.bc_setup = xprt_rdma_bc_setup,
.bc_up = xprt_rdma_bc_up,
+ .bc_maxpayload = xprt_rdma_bc_maxpayload,
.bc_free_rqst = xprt_rdma_bc_free_rqst,
.bc_destroy = xprt_rdma_bc_destroy,
#endif
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index f5ed9f982cd7..b044d98a1370 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -203,15 +203,6 @@ out_fail:
goto out_schedule;
}
-static void
-rpcrdma_flush_cqs(struct rpcrdma_ep *ep)
-{
- struct ib_wc wc;
-
- while (ib_poll_cq(ep->rep_attr.recv_cq, 1, &wc) > 0)
- rpcrdma_receive_wc(NULL, &wc);
-}
-
static int
rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
{
@@ -374,23 +365,6 @@ out:
}
/*
- * Drain any cq, prior to teardown.
- */
-static void
-rpcrdma_clean_cq(struct ib_cq *cq)
-{
- struct ib_wc wc;
- int count = 0;
-
- while (1 == ib_poll_cq(cq, 1, &wc))
- ++count;
-
- if (count)
- dprintk("RPC: %s: flushed %d events (last 0x%x)\n",
- __func__, count, wc.opcode);
-}
-
-/*
* Exported functions.
*/
@@ -459,7 +433,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
dprintk("RPC: %s: memory registration strategy is '%s'\n",
__func__, ia->ri_ops->ro_displayname);
- rwlock_init(&ia->ri_qplock);
return 0;
out3:
@@ -515,7 +488,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
__func__);
return -ENOMEM;
}
- max_qp_wr = ia->ri_device->attrs.max_qp_wr - RPCRDMA_BACKWARD_WRS;
+ max_qp_wr = ia->ri_device->attrs.max_qp_wr - RPCRDMA_BACKWARD_WRS - 1;
/* check provider's send/recv wr limits */
if (cdata->max_requests > max_qp_wr)
@@ -526,11 +499,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
ep->rep_attr.srq = NULL;
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
+ ep->rep_attr.cap.max_send_wr += 1; /* drain cqe */
rc = ia->ri_ops->ro_open(ia, ep, cdata);
if (rc)
return rc;
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
+ ep->rep_attr.cap.max_recv_wr += 1; /* drain cqe */
ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS;
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
@@ -578,6 +553,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
ep->rep_attr.recv_cq = recvcq;
/* Initialize cma parameters */
+ memset(&ep->rep_remote_cma, 0, sizeof(ep->rep_remote_cma));
/* RPC/RDMA does not use private data */
ep->rep_remote_cma.private_data = NULL;
@@ -591,7 +567,16 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
ep->rep_remote_cma.responder_resources =
ia->ri_device->attrs.max_qp_rd_atom;
- ep->rep_remote_cma.retry_count = 7;
+ /* Limit transport retries so client can detect server
+ * GID changes quickly. RPC layer handles re-establishing
+ * transport connection and retransmission.
+ */
+ ep->rep_remote_cma.retry_count = 6;
+
+ /* RPC-over-RDMA handles its own flow control. In addition,
+ * make all RNR NAKs visible so we know that RPC-over-RDMA
+ * flow control is working correctly (no NAKs should be seen).
+ */
ep->rep_remote_cma.flow_control = 0;
ep->rep_remote_cma.rnr_retry_count = 0;
@@ -622,13 +607,8 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
cancel_delayed_work_sync(&ep->rep_connect_worker);
- if (ia->ri_id->qp)
- rpcrdma_ep_disconnect(ep, ia);
-
- rpcrdma_clean_cq(ep->rep_attr.recv_cq);
- rpcrdma_clean_cq(ep->rep_attr.send_cq);
-
if (ia->ri_id->qp) {
+ rpcrdma_ep_disconnect(ep, ia);
rdma_destroy_qp(ia->ri_id);
ia->ri_id->qp = NULL;
}
@@ -659,7 +639,6 @@ retry:
dprintk("RPC: %s: reconnecting...\n", __func__);
rpcrdma_ep_disconnect(ep, ia);
- rpcrdma_flush_cqs(ep);
xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
id = rpcrdma_create_id(xprt, ia,
@@ -692,10 +671,8 @@ retry:
goto out;
}
- write_lock(&ia->ri_qplock);
old = ia->ri_id;
ia->ri_id = id;
- write_unlock(&ia->ri_qplock);
rdma_destroy_qp(old);
rpcrdma_destroy_id(old);
@@ -785,7 +762,6 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
int rc;
- rpcrdma_flush_cqs(ep);
rc = rdma_disconnect(ia->ri_id);
if (!rc) {
/* returns without wait if not connected */
@@ -797,6 +773,8 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
dprintk("RPC: %s: rdma_disconnect %i\n", __func__, rc);
ep->rep_connected = rc;
}
+
+ ib_drain_qp(ia->ri_id->qp);
}
struct rpcrdma_req *
@@ -1271,25 +1249,3 @@ out_rc:
rpcrdma_recv_buffer_put(rep);
return rc;
}
-
-/* How many chunk list items fit within our inline buffers?
- */
-unsigned int
-rpcrdma_max_segments(struct rpcrdma_xprt *r_xprt)
-{
- struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
- int bytes, segments;
-
- bytes = min_t(unsigned int, cdata->inline_wsize, cdata->inline_rsize);
- bytes -= RPCRDMA_HDRLEN_MIN;
- if (bytes < sizeof(struct rpcrdma_segment) * 2) {
- pr_warn("RPC: %s: inline threshold too small\n",
- __func__);
- return 0;
- }
-
- segments = 1 << (fls(bytes / sizeof(struct rpcrdma_segment)) - 1);
- dprintk("RPC: %s: max chunk list size = %d segments\n",
- __func__, segments);
- return segments;
-}
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 2ebc743cb96f..95cdc66225ee 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -65,7 +65,6 @@
*/
struct rpcrdma_ia {
const struct rpcrdma_memreg_ops *ri_ops;
- rwlock_t ri_qplock;
struct ib_device *ri_device;
struct rdma_cm_id *ri_id;
struct ib_pd *ri_pd;
@@ -73,6 +72,8 @@ struct rpcrdma_ia {
struct completion ri_done;
int ri_async_rc;
unsigned int ri_max_frmr_depth;
+ unsigned int ri_max_inline_write;
+ unsigned int ri_max_inline_read;
struct ib_qp_attr ri_qp_attr;
struct ib_qp_init_attr ri_qp_init_attr;
};
@@ -144,6 +145,26 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb)
#define RPCRDMA_DEF_GFP (GFP_NOIO | __GFP_NOWARN)
+/* To ensure a transport can always make forward progress,
+ * the number of RDMA segments allowed in header chunk lists
+ * is capped at 8. This prevents less-capable devices and
+ * memory registrations from overrunning the Send buffer
+ * while building chunk lists.
+ *
+ * Elements of the Read list take up more room than the
+ * Write list or Reply chunk. 8 read segments means the Read
+ * list (or Write list or Reply chunk) cannot consume more
+ * than
+ *
+ * ((8 + 2) * read segment size) + 1 XDR words, or 244 bytes.
+ *
+ * And the fixed part of the header is another 24 bytes.
+ *
+ * The smallest inline threshold is 1024 bytes, ensuring that
+ * at least 750 bytes are available for RPC messages.
+ */
+#define RPCRDMA_MAX_HDR_SEGS (8)
+
/*
* struct rpcrdma_rep -- this structure encapsulates state required to recv
* and complete a reply, asychronously. It needs several pieces of
@@ -162,7 +183,9 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb)
*/
#define RPCRDMA_MAX_DATA_SEGS ((1 * 1024 * 1024) / PAGE_SIZE)
-#define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */
+
+/* data segments + head/tail for Call + head/tail for Reply */
+#define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 4)
struct rpcrdma_buffer;
@@ -198,14 +221,13 @@ enum rpcrdma_frmr_state {
};
struct rpcrdma_frmr {
- struct scatterlist *sg;
- int sg_nents;
+ struct scatterlist *fr_sg;
+ int fr_nents;
+ enum dma_data_direction fr_dir;
struct ib_mr *fr_mr;
struct ib_cqe fr_cqe;
enum rpcrdma_frmr_state fr_state;
struct completion fr_linv_done;
- struct work_struct fr_work;
- struct rpcrdma_xprt *fr_xprt;
union {
struct ib_reg_wr fr_regwr;
struct ib_send_wr fr_invwr;
@@ -222,6 +244,8 @@ struct rpcrdma_mw {
struct rpcrdma_fmr fmr;
struct rpcrdma_frmr frmr;
};
+ struct work_struct mw_work;
+ struct rpcrdma_xprt *mw_xprt;
struct list_head mw_list;
struct list_head mw_all;
};
@@ -270,12 +294,14 @@ struct rpcrdma_req {
unsigned int rl_niovs;
unsigned int rl_nchunks;
unsigned int rl_connect_cookie;
+ struct rpc_task *rl_task;
struct rpcrdma_buffer *rl_buffer;
struct rpcrdma_rep *rl_reply;/* holder for reply buffer */
struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS];
struct rpcrdma_regbuf *rl_rdmabuf;
struct rpcrdma_regbuf *rl_sendbuf;
struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS];
+ struct rpcrdma_mr_seg *rl_nextseg;
struct ib_cqe rl_cqe;
struct list_head rl_all;
@@ -372,8 +398,8 @@ struct rpcrdma_memreg_ops {
struct rpcrdma_mr_seg *, int, bool);
void (*ro_unmap_sync)(struct rpcrdma_xprt *,
struct rpcrdma_req *);
- int (*ro_unmap)(struct rpcrdma_xprt *,
- struct rpcrdma_mr_seg *);
+ void (*ro_unmap_safe)(struct rpcrdma_xprt *,
+ struct rpcrdma_req *, bool);
int (*ro_open)(struct rpcrdma_ia *,
struct rpcrdma_ep *,
struct rpcrdma_create_data_internal *);
@@ -456,7 +482,6 @@ struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *,
void rpcrdma_free_regbuf(struct rpcrdma_ia *,
struct rpcrdma_regbuf *);
-unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *);
int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int);
int frwr_alloc_recovery_wq(void);
@@ -519,6 +544,9 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *);
* RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
*/
int rpcrdma_marshal_req(struct rpc_rqst *);
+void rpcrdma_set_max_header_sizes(struct rpcrdma_ia *,
+ struct rpcrdma_create_data_internal *,
+ unsigned int);
/* RPC/RDMA module init - xprtrdma/transport.c
*/
@@ -534,6 +562,7 @@ void xprt_rdma_cleanup(void);
#if defined(CONFIG_SUNRPC_BACKCHANNEL)
int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int);
int xprt_rdma_bc_up(struct svc_serv *, struct net *);
+size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *);
int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int);
void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *);
int rpcrdma_bc_marshal_reply(struct rpc_rqst *);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index b90c5397b5e1..7e2b2fa189c3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1364,6 +1364,11 @@ static int xs_tcp_bc_up(struct svc_serv *serv, struct net *net)
return ret;
return 0;
}
+
+static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt)
+{
+ return PAGE_SIZE;
+}
#else
static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
struct xdr_skb_reader *desc)
@@ -2661,6 +2666,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
#ifdef CONFIG_SUNRPC_BACKCHANNEL
.bc_setup = xprt_setup_bc,
.bc_up = xs_tcp_bc_up,
+ .bc_maxpayload = xs_tcp_bc_maxpayload,
.bc_free_rqst = xprt_free_bc_rqst,
.bc_destroy = xprt_destroy_bc,
#endif
@@ -3051,6 +3057,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
return xprt;
args->bc_xprt->xpt_bc_xprt = NULL;
+ args->bc_xprt->xpt_bc_xps = NULL;
xprt_put(xprt);
ret = ERR_PTR(-EINVAL);
out_err:
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 6f11c62bc8f9..bf8f05c3eb82 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -405,7 +405,7 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb,
return 0;
/* Send RESET message even if bearer is detached from device */
- tipc_ptr = rtnl_dereference(dev->tipc_ptr);
+ tipc_ptr = rcu_dereference_rtnl(dev->tipc_ptr);
if (unlikely(!tipc_ptr && !msg_is_reset(buf_msg(skb))))
goto drop;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 7059c94f33c5..67b6ab9f4c8d 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -704,7 +704,8 @@ static void link_profile_stats(struct tipc_link *l)
*/
int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
{
- int mtyp, rc = 0;
+ int mtyp = 0;
+ int rc = 0;
bool state = false;
bool probe = false;
bool setup = false;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 8740930f0787..17201aa8423d 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -41,6 +41,8 @@
#include "name_table.h"
#define MAX_FORWARD_SIZE 1024
+#define BUF_HEADROOM (LL_MAX_HEADER + 48)
+#define BUF_TAILROOM 16
static unsigned int align(unsigned int i)
{
@@ -505,6 +507,10 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err)
msg_set_hdr_sz(hdr, BASIC_H_SIZE);
}
+ if (skb_cloned(_skb) &&
+ pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL))
+ goto exit;
+
/* Now reverse the concerned fields */
msg_set_errcode(hdr, err);
msg_set_origport(hdr, msg_destport(&ohdr));
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 024da8af91f0..7cf52fb39bee 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -94,17 +94,6 @@ struct plist;
#define TIPC_MEDIA_INFO_OFFSET 5
-/**
- * TIPC message buffer code
- *
- * TIPC message buffer headroom reserves space for the worst-case
- * link-level device header (in case the message is sent off-node).
- *
- * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields
- * are word aligned for quicker access
- */
-#define BUF_HEADROOM (LL_MAX_HEADER + 48)
-
struct tipc_skb_cb {
void *handle;
struct sk_buff *tail;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 4dfc5c14f8c3..3ad9fab1985f 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -346,9 +346,15 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
struct nlattr **attrs)
{
struct nlattr *bearer[TIPC_NLA_BEARER_MAX + 1];
+ int err;
+
+ if (!attrs[TIPC_NLA_BEARER])
+ return -EINVAL;
- nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, attrs[TIPC_NLA_BEARER],
- NULL);
+ err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX,
+ attrs[TIPC_NLA_BEARER], NULL);
+ if (err)
+ return err;
return tipc_add_tlv(msg->rep, TIPC_TLV_BEARER_NAME,
nla_data(bearer[TIPC_NLA_BEARER_NAME]),
@@ -460,14 +466,31 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
+ int err;
- nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+ if (!attrs[TIPC_NLA_LINK])
+ return -EINVAL;
- nla_parse_nested(prop, TIPC_NLA_PROP_MAX, link[TIPC_NLA_LINK_PROP],
- NULL);
+ err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
+ NULL);
+ if (err)
+ return err;
+
+ if (!link[TIPC_NLA_LINK_PROP])
+ return -EINVAL;
- nla_parse_nested(stats, TIPC_NLA_STATS_MAX, link[TIPC_NLA_LINK_STATS],
- NULL);
+ err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX,
+ link[TIPC_NLA_LINK_PROP], NULL);
+ if (err)
+ return err;
+
+ if (!link[TIPC_NLA_LINK_STATS])
+ return -EINVAL;
+
+ err = nla_parse_nested(stats, TIPC_NLA_STATS_MAX,
+ link[TIPC_NLA_LINK_STATS], NULL);
+ if (err)
+ return err;
name = (char *)TLV_DATA(msg->req);
if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
@@ -569,12 +592,20 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
{
struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
struct tipc_link_info link_info;
+ int err;
- nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+ if (!attrs[TIPC_NLA_LINK])
+ return -EINVAL;
+
+ err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
+ NULL);
+ if (err)
+ return err;
link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
- strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+ nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]),
+ TIPC_MAX_LINK_NAME);
return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
&link_info, sizeof(link_info));
@@ -758,12 +789,23 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
u32 node, depth, type, lowbound, upbound;
static const char * const scope_str[] = {"", " zone", " cluster",
" node"};
+ int err;
- nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
- attrs[TIPC_NLA_NAME_TABLE], NULL);
+ if (!attrs[TIPC_NLA_NAME_TABLE])
+ return -EINVAL;
- nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, nt[TIPC_NLA_NAME_TABLE_PUBL],
- NULL);
+ err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
+ attrs[TIPC_NLA_NAME_TABLE], NULL);
+ if (err)
+ return err;
+
+ if (!nt[TIPC_NLA_NAME_TABLE_PUBL])
+ return -EINVAL;
+
+ err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX,
+ nt[TIPC_NLA_NAME_TABLE_PUBL], NULL);
+ if (err)
+ return err;
ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
@@ -815,8 +857,15 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg,
{
u32 type, lower, upper;
struct nlattr *publ[TIPC_NLA_PUBL_MAX + 1];
+ int err;
- nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL], NULL);
+ if (!attrs[TIPC_NLA_PUBL])
+ return -EINVAL;
+
+ err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL],
+ NULL);
+ if (err)
+ return err;
type = nla_get_u32(publ[TIPC_NLA_PUBL_TYPE]);
lower = nla_get_u32(publ[TIPC_NLA_PUBL_LOWER]);
@@ -876,7 +925,13 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
u32 sock_ref;
struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
- nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], NULL);
+ if (!attrs[TIPC_NLA_SOCK])
+ return -EINVAL;
+
+ err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK],
+ NULL);
+ if (err)
+ return err;
sock_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]);
tipc_tlv_sprintf(msg->rep, "%u:", sock_ref);
@@ -917,9 +972,15 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg,
struct nlattr **attrs)
{
struct nlattr *media[TIPC_NLA_MEDIA_MAX + 1];
+ int err;
+
+ if (!attrs[TIPC_NLA_MEDIA])
+ return -EINVAL;
- nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA],
- NULL);
+ err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA],
+ NULL);
+ if (err)
+ return err;
return tipc_add_tlv(msg->rep, TIPC_TLV_MEDIA_NAME,
nla_data(media[TIPC_NLA_MEDIA_NAME]),
@@ -931,8 +992,15 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg,
{
struct tipc_node_info node_info;
struct nlattr *node[TIPC_NLA_NODE_MAX + 1];
+ int err;
- nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE], NULL);
+ if (!attrs[TIPC_NLA_NODE])
+ return -EINVAL;
+
+ err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE],
+ NULL);
+ if (err)
+ return err;
node_info.addr = htonl(nla_get_u32(node[TIPC_NLA_NODE_ADDR]));
node_info.up = htonl(nla_get_flag(node[TIPC_NLA_NODE_UP]));
@@ -971,8 +1039,16 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg,
{
__be32 id;
struct nlattr *net[TIPC_NLA_NET_MAX + 1];
+ int err;
+
+ if (!attrs[TIPC_NLA_NET])
+ return -EINVAL;
+
+ err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET],
+ NULL);
+ if (err)
+ return err;
- nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET], NULL);
id = htonl(nla_get_u32(net[TIPC_NLA_NET_ID]));
return tipc_add_tlv(msg->rep, TIPC_TLV_UNSIGNED, &id, sizeof(id));
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 88bfcd707064..c49b8df438cb 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -796,9 +796,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
* @tsk: receiving socket
* @skb: pointer to message buffer.
*/
-static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
+static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
struct sock *sk = &tsk->sk;
+ u32 onode = tsk_own_node(tsk);
struct tipc_msg *hdr = buf_msg(skb);
int mtyp = msg_type(hdr);
bool conn_cong;
@@ -811,7 +813,8 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
if (mtyp == CONN_PROBE) {
msg_set_type(hdr, CONN_PROBE_REPLY);
- tipc_sk_respond(sk, skb, TIPC_OK);
+ if (tipc_msg_reverse(onode, &skb, TIPC_OK))
+ __skb_queue_tail(xmitq, skb);
return;
} else if (mtyp == CONN_ACK) {
conn_cong = tsk_conn_cong(tsk);
@@ -1686,7 +1689,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
*
* Returns true if message was added to socket receive queue, otherwise false
*/
-static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
+static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
struct socket *sock = sk->sk_socket;
struct tipc_sock *tsk = tipc_sk(sk);
@@ -1696,7 +1700,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
int usr = msg_user(hdr);
if (unlikely(msg_user(hdr) == CONN_MANAGER)) {
- tipc_sk_proto_rcv(tsk, skb);
+ tipc_sk_proto_rcv(tsk, skb, xmitq);
return false;
}
@@ -1739,7 +1743,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
return true;
reject:
- tipc_sk_respond(sk, skb, err);
+ if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err))
+ __skb_queue_tail(xmitq, skb);
return false;
}
@@ -1755,9 +1760,24 @@ reject:
static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
unsigned int truesize = skb->truesize;
+ struct sk_buff_head xmitq;
+ u32 dnode, selector;
- if (likely(filter_rcv(sk, skb)))
+ __skb_queue_head_init(&xmitq);
+
+ if (likely(filter_rcv(sk, skb, &xmitq))) {
atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt);
+ return 0;
+ }
+
+ if (skb_queue_empty(&xmitq))
+ return 0;
+
+ /* Send response/rejected message */
+ skb = __skb_dequeue(&xmitq);
+ dnode = msg_destnode(buf_msg(skb));
+ selector = msg_origport(buf_msg(skb));
+ tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
return 0;
}
@@ -1771,12 +1791,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
* Caller must hold socket lock
*/
static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
- u32 dport)
+ u32 dport, struct sk_buff_head *xmitq)
{
+ unsigned long time_limit = jiffies + 2;
+ struct sk_buff *skb;
unsigned int lim;
atomic_t *dcnt;
- struct sk_buff *skb;
- unsigned long time_limit = jiffies + 2;
+ u32 onode;
while (skb_queue_len(inputq)) {
if (unlikely(time_after_eq(jiffies, time_limit)))
@@ -1788,7 +1809,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
/* Add message directly to receive queue if possible */
if (!sock_owned_by_user(sk)) {
- filter_rcv(sk, skb);
+ filter_rcv(sk, skb, xmitq);
continue;
}
@@ -1801,7 +1822,9 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
continue;
/* Overload => reject message back to sender */
- tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD);
+ onode = tipc_own_addr(sock_net(sk));
+ if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
+ __skb_queue_tail(xmitq, skb);
break;
}
}
@@ -1814,12 +1837,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
*/
void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
{
+ struct sk_buff_head xmitq;
u32 dnode, dport = 0;
int err;
struct tipc_sock *tsk;
struct sock *sk;
struct sk_buff *skb;
+ __skb_queue_head_init(&xmitq);
while (skb_queue_len(inputq)) {
dport = tipc_skb_peek_port(inputq, dport);
tsk = tipc_sk_lookup(net, dport);
@@ -1827,9 +1852,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
if (likely(tsk)) {
sk = &tsk->sk;
if (likely(spin_trylock_bh(&sk->sk_lock.slock))) {
- tipc_sk_enqueue(inputq, sk, dport);
+ tipc_sk_enqueue(inputq, sk, dport, &xmitq);
spin_unlock_bh(&sk->sk_lock.slock);
}
+ /* Send pending response/rejected messages, if any */
+ while ((skb = __skb_dequeue(&xmitq))) {
+ dnode = msg_destnode(buf_msg(skb));
+ tipc_node_xmit_skb(net, skb, dnode, dport);
+ }
sock_put(sk);
continue;
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 80aa6a3e6817..735362c26c8e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -315,7 +315,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i)
&unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
struct dentry *dentry = unix_sk(s)->path.dentry;
- if (dentry && d_backing_inode(dentry) == i) {
+ if (dentry && d_real_inode(dentry) == i) {
sock_hold(s);
goto found;
}
@@ -911,7 +911,7 @@ static struct sock *unix_find_other(struct net *net,
err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
if (err)
goto fail;
- inode = d_backing_inode(path.dentry);
+ inode = d_real_inode(path.dentry);
err = inode_permission(inode, MAY_WRITE);
if (err)
goto put_fail;
@@ -1048,7 +1048,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out_up;
}
addr->hash = UNIX_HASH_SIZE;
- hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+ hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
spin_lock(&unix_table_lock);
u->path = u_path;
list = &unix_socket_table[hash];
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index b5f1221f48d4..b96ac918e0ba 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -61,6 +61,14 @@
* function will also cleanup rejected sockets, those that reach the connected
* state but leave it before they have been accepted.
*
+ * - Lock ordering for pending or accept queue sockets is:
+ *
+ * lock_sock(listener);
+ * lock_sock_nested(pending, SINGLE_DEPTH_NESTING);
+ *
+ * Using explicit nested locking keeps lockdep happy since normally only one
+ * lock of a given class may be taken at a time.
+ *
* - Sockets created by user action will be cleaned up when the user process
* calls close(2), causing our release implementation to be called. Our release
* implementation will perform some cleanup then drop the last reference so our
@@ -443,7 +451,7 @@ void vsock_pending_work(struct work_struct *work)
cleanup = true;
lock_sock(listener);
- lock_sock(sk);
+ lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
if (vsock_is_pending(sk)) {
vsock_remove_pending(listener, sk);
@@ -1292,7 +1300,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
if (connected) {
listener->sk_ack_backlog--;
- lock_sock(connected);
+ lock_sock_nested(connected, SINGLE_DEPTH_NESTING);
vconnected = vsock_sk(connected);
/* If the listener socket has received an error, then we should
diff --git a/net/wireless/core.c b/net/wireless/core.c
index d25c82bc1bbe..ecca3896b9f7 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -363,8 +363,6 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
WARN_ON(ops->remain_on_channel && !ops->cancel_remain_on_channel);
WARN_ON(ops->tdls_channel_switch && !ops->tdls_cancel_channel_switch);
WARN_ON(ops->add_tx_ts && !ops->del_tx_ts);
- WARN_ON(ops->set_tx_power && !ops->get_tx_power);
- WARN_ON(ops->set_antenna && !ops->get_antenna);
alloc_size = sizeof(*rdev) + sizeof_priv;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 4e809e978b7d..2443ee30ba5b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -509,7 +509,7 @@ static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr,
* replace EtherType */
hdrlen += ETH_ALEN + 2;
else
- tmp.h_proto = htons(skb->len);
+ tmp.h_proto = htons(skb->len - hdrlen);
pskb_pull(skb, hdrlen);
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 6250b1cfcde5..dbb2738e356a 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -958,8 +958,29 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr,
return private(dev, iwr, cmd, info, handler);
}
/* Old driver API : call driver ioctl handler */
- if (dev->netdev_ops->ndo_do_ioctl)
- return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
+ if (dev->netdev_ops->ndo_do_ioctl) {
+#ifdef CONFIG_COMPAT
+ if (info->flags & IW_REQUEST_FLAG_COMPAT) {
+ int ret = 0;
+ struct iwreq iwr_lcl;
+ struct compat_iw_point *iwp_compat = (void *) &iwr->u.data;
+
+ memcpy(&iwr_lcl, iwr, sizeof(struct iwreq));
+ iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer);
+ iwr_lcl.u.data.length = iwp_compat->length;
+ iwr_lcl.u.data.flags = iwp_compat->flags;
+
+ ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd);
+
+ iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer);
+ iwp_compat->length = iwr_lcl.u.data.length;
+ iwp_compat->flags = iwr_lcl.u.data.flags;
+
+ return ret;
+ } else
+#endif
+ return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
+ }
return -EOPNOTSUPP;
}
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index b2ab2a92a375..0f82314621f2 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -7,6 +7,7 @@ quote := "
squote := '
empty :=
space := $(empty) $(empty)
+space_escape := _-_SPACE_-_
###
# Name of target with a '.' as filename prefix. foo/bar.o => foo/.bar.o
@@ -226,10 +227,10 @@ objectify = $(foreach o,$(1),$(if $(filter /%,$(o)),$(o),$(obj)/$(o)))
# See Documentation/kbuild/makefiles.txt for more info
ifneq ($(KBUILD_NOCMDDEP),1)
-# Check if both arguments has same arguments. Result is empty string if equal.
-# User may override this check using make KBUILD_NOCMDDEP=1
-arg-check = $(strip $(filter-out $(cmd_$(1)), $(cmd_$@)) \
- $(filter-out $(cmd_$@), $(cmd_$(1))) )
+# Check if both arguments are the same including their order. Result is empty
+# string if equal. User may override this check using make KBUILD_NOCMDDEP=1
+arg-check = $(filter-out $(subst $(space),$(space_escape),$(strip $(cmd_$@))), \
+ $(subst $(space),$(space_escape),$(strip $(cmd_$1))))
else
arg-check = $(if $(strip $(cmd_$@)),,1)
endif
@@ -256,10 +257,42 @@ if_changed = $(if $(strip $(any-prereq) $(arg-check)), \
# Execute the command and also postprocess generated .d dependencies file.
if_changed_dep = $(if $(strip $(any-prereq) $(arg-check) ), \
@set -e; \
+ $(cmd_and_fixdep), @:)
+
+ifndef CONFIG_TRIM_UNUSED_KSYMS
+
+cmd_and_fixdep = \
$(echo-cmd) $(cmd_$(1)); \
scripts/basic/fixdep $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp;\
rm -f $(depfile); \
- mv -f $(dot-target).tmp $(dot-target).cmd, @:)
+ mv -f $(dot-target).tmp $(dot-target).cmd;
+
+else
+
+# Filter out exported kernel symbol names from the preprocessor output.
+# See also __KSYM_DEPS__ in include/linux/export.h.
+# We disable the depfile generation here, so as not to overwrite the existing
+# depfile while fixdep is parsing it.
+flags_nodeps = $(filter-out -Wp$(comma)-M%, $($(1)))
+ksym_dep_filter = \
+ case "$(1)" in \
+ cc_*_c|cpp_i_c) \
+ $(CPP) $(call flags_nodeps,c_flags) -D__KSYM_DEPS__ $< ;; \
+ as_*_S|cpp_s_S) \
+ $(CPP) $(call flags_nodeps,a_flags) -D__KSYM_DEPS__ $< ;; \
+ boot*|build*|*cpp_lds_S|dtc|host*|vdso*) : ;; \
+ *) echo "Don't know how to preprocess $(1)" >&2; false ;; \
+ esac | tr ";" "\n" | sed -rn 's/^.*=== __KSYM_(.*) ===.*$$/KSYM_\1/p'
+
+cmd_and_fixdep = \
+ $(echo-cmd) $(cmd_$(1)); \
+ $(ksym_dep_filter) | \
+ scripts/basic/fixdep -e $(depfile) $@ '$(make-cmd)' \
+ > $(dot-target).tmp; \
+ rm -f $(depfile); \
+ mv -f $(dot-target).tmp $(dot-target).cmd;
+
+endif
# Usage: $(call if_changed_rule,foo)
# Will check if $(cmd_foo) or any of the prerequisites changed,
@@ -341,8 +374,6 @@ endif
#
###############################################################################
#
-space_escape := %%%SPACE%%%
-#
define config_filename
ifneq ($$(CONFIG_$(1)),"")
$(1)_FILENAME := $$(subst \\,\,$$(subst \$$(quote),$$(quote),$$(subst $$(space_escape),\$$(space),$$(patsubst "%",%,$$(subst $$(space),$$(space_escape),$$(CONFIG_$(1)))))))
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index e1bc1907090e..0d1ca5bf42fb 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -152,11 +152,11 @@ cmd_cc_s_c = $(CC) $(c_flags) $(DISABLE_LTO) -fverbose-asm -S -o $@ $<
$(obj)/%.s: $(src)/%.c FORCE
$(call if_changed_dep,cc_s_c)
-quiet_cmd_cc_i_c = CPP $(quiet_modtag) $@
-cmd_cc_i_c = $(CPP) $(c_flags) -o $@ $<
+quiet_cmd_cpp_i_c = CPP $(quiet_modtag) $@
+cmd_cpp_i_c = $(CPP) $(c_flags) -o $@ $<
$(obj)/%.i: $(src)/%.c FORCE
- $(call if_changed_dep,cc_i_c)
+ $(call if_changed_dep,cpp_i_c)
cmd_gensymtypes = \
$(CPP) -D__GENKSYMS__ $(c_flags) $< | \
@@ -266,26 +266,24 @@ endif # CONFIG_STACK_VALIDATION
define rule_cc_o_c
$(call echo-cmd,checksrc) $(cmd_checksrc) \
- $(call echo-cmd,cc_o_c) $(cmd_cc_o_c); \
+ $(call cmd_and_fixdep,cc_o_c) \
$(cmd_modversions) \
- $(cmd_objtool) \
- $(call echo-cmd,record_mcount) \
- $(cmd_record_mcount) \
- scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,cc_o_c)' > \
- $(dot-target).tmp; \
- rm -f $(depfile); \
- mv -f $(dot-target).tmp $(dot-target).cmd
+ $(cmd_objtool) \
+ $(call echo-cmd,record_mcount) $(cmd_record_mcount)
endef
define rule_as_o_S
- $(call echo-cmd,as_o_S) $(cmd_as_o_S); \
- $(cmd_objtool) \
- scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,as_o_S)' > \
- $(dot-target).tmp; \
- rm -f $(depfile); \
- mv -f $(dot-target).tmp $(dot-target).cmd
+ $(call cmd_and_fixdep,as_o_S) \
+ $(cmd_objtool)
endef
+# List module undefined symbols (or empty line if not enabled)
+ifdef CONFIG_TRIM_UNUSED_KSYMS
+cmd_undef_syms = $(NM) $@ | sed -n 's/^ \+U //p' | xargs echo
+else
+cmd_undef_syms = echo
+endif
+
# Built-in and composite module parts
$(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_obj) FORCE
$(call cmd,force_checksrc)
@@ -296,7 +294,8 @@ $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_obj) FORCE
$(single-used-m): $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_obj) FORCE
$(call cmd,force_checksrc)
$(call if_changed_rule,cc_o_c)
- @{ echo $(@:.o=.ko); echo $@; } > $(MODVERDIR)/$(@F:.o=.mod)
+ @{ echo $(@:.o=.ko); echo $@; \
+ $(cmd_undef_syms); } > $(MODVERDIR)/$(@F:.o=.mod)
quiet_cmd_cc_lst_c = MKLST $@
cmd_cc_lst_c = $(CC) $(c_flags) -g -c -o $*.o $< && \
@@ -314,11 +313,11 @@ modkern_aflags := $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL)
$(real-objs-m) : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
$(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
-quiet_cmd_as_s_S = CPP $(quiet_modtag) $@
-cmd_as_s_S = $(CPP) $(a_flags) -o $@ $<
+quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@
+cmd_cpp_s_S = $(CPP) $(a_flags) -o $@ $<
$(obj)/%.s: $(src)/%.S FORCE
- $(call if_changed_dep,as_s_S)
+ $(call if_changed_dep,cpp_s_S)
quiet_cmd_as_o_S = AS $(quiet_modtag) $@
cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $<
@@ -426,7 +425,8 @@ $(call multi_depend, $(multi-used-y), .o, -objs -y)
$(multi-used-m): FORCE
$(call if_changed,link_multi-m)
- @{ echo $(@:.o=.ko); echo $(link_multi_deps); } > $(MODVERDIR)/$(@F:.o=.mod)
+ @{ echo $(@:.o=.ko); echo $(link_multi_deps); \
+ $(cmd_undef_syms); } > $(MODVERDIR)/$(@F:.o=.mod)
$(call multi_depend, $(multi-used-m), .o, -objs -y -m)
targets += $(multi-used-y) $(multi-used-m)
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index f9e47a70509c..53449a6ff6aa 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -24,6 +24,7 @@ warning-1 += $(call cc-option, -Wmissing-prototypes)
warning-1 += -Wold-style-definition
warning-1 += $(call cc-option, -Wmissing-include-dirs)
warning-1 += $(call cc-option, -Wunused-but-set-variable)
+warning-1 += $(call cc-option, -Wunused-const-variable)
warning-1 += $(call cc-disable-warning, missing-field-initializers)
warning-1 += $(call cc-disable-warning, sign-compare)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index ed1b7c4fb674..e7df0f5db7ec 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -96,10 +96,10 @@ obj-dirs := $(addprefix $(obj)/,$(obj-dirs))
# Note: Files that end up in two or more modules are compiled without the
# KBUILD_MODNAME definition. The reason is that any made-up name would
# differ in different configs.
-name-fix = $(subst $(comma),_,$(subst -,_,$1))
-basename_flags = -D"KBUILD_BASENAME=KBUILD_STR($(call name-fix,$(basetarget)))"
+name-fix = $(squote)$(quote)$(subst $(comma),_,$(subst -,_,$1))$(quote)$(squote)
+basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
modname_flags = $(if $(filter 1,$(words $(modname))),\
- -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))")
+ -DKBUILD_MODNAME=$(call name-fix,$(modname)))
orig_c_flags = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(KBUILD_SUBDIR_CCFLAGS) \
$(ccflags-y) $(CFLAGS_$(basetarget).o)
@@ -162,7 +162,7 @@ endif
c_flags = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
$(__c_flags) $(modkern_cflags) \
- -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags)
+ $(basename_flags) $(modname_flags)
a_flags = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
$(__a_flags) $(modkern_aflags)
diff --git a/scripts/adjust_autoksyms.sh b/scripts/adjust_autoksyms.sh
new file mode 100755
index 000000000000..8dc1918b6783
--- /dev/null
+++ b/scripts/adjust_autoksyms.sh
@@ -0,0 +1,101 @@
+#!/bin/sh
+
+# Script to create/update include/generated/autoksyms.h and dependency files
+#
+# Copyright: (C) 2016 Linaro Limited
+# Created by: Nicolas Pitre, January 2016
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+# Create/update the include/generated/autoksyms.h file from the list
+# of all module's needed symbols as recorded on the third line of
+# .tmp_versions/*.mod files.
+#
+# For each symbol being added or removed, the corresponding dependency
+# file's timestamp is updated to force a rebuild of the affected source
+# file. All arguments passed to this script are assumed to be a command
+# to be exec'd to trigger a rebuild of those files.
+
+set -e
+
+cur_ksyms_file="include/generated/autoksyms.h"
+new_ksyms_file="include/generated/autoksyms.h.tmpnew"
+
+info() {
+ if [ "$quiet" != "silent_" ]; then
+ printf " %-7s %s\n" "$1" "$2"
+ fi
+}
+
+info "CHK" "$cur_ksyms_file"
+
+# Use "make V=1" to debug this script.
+case "$KBUILD_VERBOSE" in
+*1*)
+ set -x
+ ;;
+esac
+
+# We need access to CONFIG_ symbols
+case "${KCONFIG_CONFIG}" in
+*/*)
+ . "${KCONFIG_CONFIG}"
+ ;;
+*)
+ # Force using a file from the current directory
+ . "./${KCONFIG_CONFIG}"
+esac
+
+# In case it doesn't exist yet...
+if [ -e "$cur_ksyms_file" ]; then touch "$cur_ksyms_file"; fi
+
+# Generate a new ksym list file with symbols needed by the current
+# set of modules.
+cat > "$new_ksyms_file" << EOT
+/*
+ * Automatically generated file; DO NOT EDIT.
+ */
+
+EOT
+sed -ns -e '3{s/ /\n/g;/^$/!p;}' "$MODVERDIR"/*.mod | sort -u |
+while read sym; do
+ if [ -n "$CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX" ]; then
+ sym="${sym#_}"
+ fi
+ echo "#define __KSYM_${sym} 1"
+done >> "$new_ksyms_file"
+
+# Special case for modversions (see modpost.c)
+if [ -n "$CONFIG_MODVERSIONS" ]; then
+ echo "#define __KSYM_module_layout 1" >> "$new_ksyms_file"
+fi
+
+# Extract changes between old and new list and touch corresponding
+# dependency files.
+changed=$(
+count=0
+sort "$cur_ksyms_file" "$new_ksyms_file" | uniq -u |
+sed -n 's/^#define __KSYM_\(.*\) 1/\1/p' | tr "A-Z_" "a-z/" |
+while read sympath; do
+ if [ -z "$sympath" ]; then continue; fi
+ depfile="include/config/ksym/${sympath}.h"
+ mkdir -p "$(dirname "$depfile")"
+ touch "$depfile"
+ echo $((count += 1))
+done | tail -1 )
+changed=${changed:-0}
+
+if [ $changed -gt 0 ]; then
+ # Replace the old list with tne new one
+ old=$(grep -c "^#define __KSYM_" "$cur_ksyms_file" || true)
+ new=$(grep -c "^#define __KSYM_" "$new_ksyms_file" || true)
+ info "KSYMS" "symbols: before=$old, after=$new, changed=$changed"
+ info "UPD" "$cur_ksyms_file"
+ mv -f "$new_ksyms_file" "$cur_ksyms_file"
+ # Then trigger a rebuild of affected source files
+ exec $@
+else
+ rm -f "$new_ksyms_file"
+fi
diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c
index caef815d1743..746ec1ece614 100644
--- a/scripts/basic/fixdep.c
+++ b/scripts/basic/fixdep.c
@@ -120,13 +120,15 @@
#define INT_NFIG ntohl(0x4e464947)
#define INT_FIG_ ntohl(0x4649475f)
+int insert_extra_deps;
char *target;
char *depfile;
char *cmdline;
static void usage(void)
{
- fprintf(stderr, "Usage: fixdep <depfile> <target> <cmdline>\n");
+ fprintf(stderr, "Usage: fixdep [-e] <depfile> <target> <cmdline>\n");
+ fprintf(stderr, " -e insert extra dependencies given on stdin\n");
exit(1);
}
@@ -138,6 +140,40 @@ static void print_cmdline(void)
printf("cmd_%s := %s\n\n", target, cmdline);
}
+/*
+ * Print out a dependency path from a symbol name
+ */
+static void print_config(const char *m, int slen)
+{
+ int c, i;
+
+ printf(" $(wildcard include/config/");
+ for (i = 0; i < slen; i++) {
+ c = m[i];
+ if (c == '_')
+ c = '/';
+ else
+ c = tolower(c);
+ putchar(c);
+ }
+ printf(".h) \\\n");
+}
+
+static void do_extra_deps(void)
+{
+ if (insert_extra_deps) {
+ char buf[80];
+ while(fgets(buf, sizeof(buf), stdin)) {
+ int len = strlen(buf);
+ if (len < 2 || buf[len-1] != '\n') {
+ fprintf(stderr, "fixdep: bad data on stdin\n");
+ exit(1);
+ }
+ print_config(buf, len-1);
+ }
+ }
+}
+
struct item {
struct item *next;
unsigned int len;
@@ -197,23 +233,12 @@ static void define_config(const char *name, int len, unsigned int hash)
static void use_config(const char *m, int slen)
{
unsigned int hash = strhash(m, slen);
- int c, i;
if (is_defined_config(m, slen, hash))
return;
define_config(m, slen, hash);
-
- printf(" $(wildcard include/config/");
- for (i = 0; i < slen; i++) {
- c = m[i];
- if (c == '_')
- c = '/';
- else
- c = tolower(c);
- putchar(c);
- }
- printf(".h) \\\n");
+ print_config(m, slen);
}
static void parse_config_file(const char *map, size_t len)
@@ -250,7 +275,7 @@ static void parse_config_file(const char *map, size_t len)
}
}
-/* test is s ends in sub */
+/* test if s ends in sub */
static int strrcmp(const char *s, const char *sub)
{
int slen = strlen(s);
@@ -333,6 +358,7 @@ static void parse_dep_file(void *map, size_t len)
/* Ignore certain dependencies */
if (strrcmp(s, "include/generated/autoconf.h") &&
+ strrcmp(s, "include/generated/autoksyms.h") &&
strrcmp(s, "arch/um/include/uml-config.h") &&
strrcmp(s, "include/linux/kconfig.h") &&
strrcmp(s, ".ver")) {
@@ -378,6 +404,8 @@ static void parse_dep_file(void *map, size_t len)
exit(1);
}
+ do_extra_deps();
+
printf("\n%s: $(deps_%s)\n\n", target, target);
printf("$(deps_%s):\n", target);
}
@@ -434,7 +462,10 @@ int main(int argc, char *argv[])
{
traps();
- if (argc != 4)
+ if (argc == 5 && !strcmp(argv[1], "-e")) {
+ insert_extra_deps = 1;
+ argv++;
+ } else if (argc != 4)
usage();
depfile = argv[1];
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 6750595bd7b8..4904ced676d4 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2454,6 +2454,7 @@ sub process {
# Check for git id commit length and improperly formed commit descriptions
if ($in_commit_log && !$commit_log_possible_stack_dump &&
+ $line !~ /^\s*(?:Link|Patchwork|http|BugLink):/i &&
($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
($line =~ /\b[0-9a-f]{12,40}\b/i &&
$line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
diff --git a/scripts/coccicheck b/scripts/coccicheck
index b2d758188f2f..dd85a455b2ba 100755
--- a/scripts/coccicheck
+++ b/scripts/coccicheck
@@ -98,7 +98,7 @@ run_cmd() {
}
kill_running() {
- for i in $(seq $(( NPROC - 1 )) ); do
+ for i in $(seq 0 $(( NPROC - 1 )) ); do
if [ $VERBOSE -eq 2 ] ; then
echo "Killing ${SPATCH_PID[$i]}"
fi
diff --git a/scripts/coccinelle/api/setup_timer.cocci b/scripts/coccinelle/api/setup_timer.cocci
index 8ee0ac30e547..eb6bd9e4ab1a 100644
--- a/scripts/coccinelle/api/setup_timer.cocci
+++ b/scripts/coccinelle/api/setup_timer.cocci
@@ -106,7 +106,7 @@ position j0, j1, j2;
@match_function_and_data_after_init_timer_context
depends on !patch &&
!match_immediate_function_data_after_init_timer_context &&
-(context || org || report)@
+ (context || org || report)@
expression a, b, e1, e2, e3, e4, e5;
position j0, j1, j2;
@@
@@ -127,7 +127,7 @@ position j0, j1, j2;
@r3_context depends on !patch &&
!match_immediate_function_data_after_init_timer_context &&
!match_function_and_data_after_init_timer_context &&
-(context || org || report)@
+ (context || org || report)@
expression c, e6, e7;
position r1.p;
position j0, j1;
diff --git a/scripts/coccinelle/misc/compare_const_fl.cocci b/scripts/coccinelle/misc/compare_const_fl.cocci
deleted file mode 100644
index b5d4bab60263..000000000000
--- a/scripts/coccinelle/misc/compare_const_fl.cocci
+++ /dev/null
@@ -1,171 +0,0 @@
-/// Move constants to the right of binary operators.
-//# Depends on personal taste in some cases.
-///
-// Confidence: Moderate
-// Copyright: (C) 2015 Copyright: (C) 2015 Julia Lawall, Inria. GPLv2.
-// URL: http://coccinelle.lip6.fr/
-// Options: --no-includes --include-headers
-
-virtual patch
-virtual context
-virtual org
-virtual report
-
-@r1 depends on patch && !context && !org && !report
- disable bitor_comm, neg_if_exp@
-constant c,c1;
-local idexpression i;
-expression e,e1,e2;
-binary operator b = {==,!=,&,|};
-type t;
-@@
-
-(
-c b (c1)
-|
-sizeof(t) b e1
-|
-sizeof e b e1
-|
-i b e1
-|
-c | e1 | e2 | ...
-|
-c | (e ? e1 : e2)
-|
-- c
-+ e
-b
-- e
-+ c
-)
-
-@r2 depends on patch && !context && !org && !report
- disable gtr_lss, gtr_lss_eq, not_int2@
-constant c,c1;
-expression e,e1,e2;
-binary operator b;
-binary operator b1 = {<,<=},b2 = {<,<=};
-binary operator b3 = {>,>=},b4 = {>,>=};
-local idexpression i;
-type t;
-@@
-
-(
-c b c1
-|
-sizeof(t) b e1
-|
-sizeof e b e1
-|
- (e1 b1 e) && (e b2 e2)
-|
- (e1 b3 e) && (e b4 e2)
-|
-i b e
-|
-- c < e
-+ e > c
-|
-- c <= e
-+ e >= c
-|
-- c > e
-+ e < c
-|
-- c >= e
-+ e <= c
-)
-
-// ----------------------------------------------------------------------------
-
-@r1_context depends on !patch && (context || org || report)
- disable bitor_comm, neg_if_exp exists@
-type t;
-binary operator b = {==,!=,&,|};
-constant c, c1;
-expression e, e1, e2;
-local idexpression i;
-position j0;
-@@
-
-(
-c b (c1)
-|
-sizeof(t) b e1
-|
-sizeof e b e1
-|
-i b e1
-|
-c | e1 | e2 | ...
-|
-c | (e ? e1 : e2)
-|
-* c@j0 b e
-)
-
-@r2_context depends on !patch && (context || org || report)
- disable gtr_lss, gtr_lss_eq, not_int2 exists@
-type t;
-binary operator b, b1 = {<,<=}, b2 = {<,<=}, b3 = {>,>=}, b4 = {>,>=};
-constant c, c1;
-expression e, e1, e2;
-local idexpression i;
-position j0;
-@@
-
-(
-c b c1
-|
-sizeof(t) b e1
-|
-sizeof e b e1
-|
- (e1 b1 e) && (e b2 e2)
-|
- (e1 b3 e) && (e b4 e2)
-|
-i b e
-|
-* c@j0 < e
-|
-* c@j0 <= e
-|
-* c@j0 > e
-|
-* c@j0 >= e
-)
-
-// ----------------------------------------------------------------------------
-
-@script:python r1_org depends on org@
-j0 << r1_context.j0;
-@@
-
-msg = "Move constant to right."
-coccilib.org.print_todo(j0[0], msg)
-
-@script:python r2_org depends on org@
-j0 << r2_context.j0;
-@@
-
-msg = "Move constant to right."
-coccilib.org.print_todo(j0[0], msg)
-
-// ----------------------------------------------------------------------------
-
-@script:python r1_report depends on report@
-j0 << r1_context.j0;
-@@
-
-msg = "Move constant to right."
-coccilib.report.print_report(j0[0], msg)
-
-@script:python r2_report depends on report@
-j0 << r2_context.j0;
-@@
-
-msg = "Move constant to right."
-coccilib.report.print_report(j0[0], msg)
-
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index dafaf96e0a34..06121ce524a7 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -873,5 +873,8 @@ int main(int argc, char **argv)
(double)nsyms / (double)HASH_BUCKETS);
}
+ if (dumpfile)
+ fclose(dumpfile);
+
return errors != 0;
}
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index dd243d2abd87..297b079ae4d9 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -375,7 +375,9 @@ load:
continue;
} else {
if (line[0] != '\r' && line[0] != '\n')
- conf_warning("unexpected data");
+ conf_warning("unexpected data: %.*s",
+ (int)strcspn(line, "\r\n"), line);
+
continue;
}
setsym:
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 25cf0c2c0c79..2432298487fb 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -209,12 +209,26 @@ static void sym_set_all_changed(void)
static void sym_calc_visibility(struct symbol *sym)
{
struct property *prop;
+ struct symbol *choice_sym = NULL;
tristate tri;
/* any prompt visible? */
tri = no;
+
+ if (sym_is_choice_value(sym))
+ choice_sym = prop_get_symbol(sym_get_choice_prop(sym));
+
for_all_prompts(sym, prop) {
prop->visible.tri = expr_calc_value(prop->visible.expr);
+ /*
+ * Tristate choice_values with visibility 'mod' are
+ * not visible if the corresponding choice's value is
+ * 'yes'.
+ */
+ if (choice_sym && sym->type == S_TRISTATE &&
+ prop->visible.tri == mod && choice_sym->curr.tri == yes)
+ prop->visible.tri = no;
+
tri = EXPR_OR(tri, prop->visible.tri);
}
if (tri == mod && (sym->type != S_TRISTATE || modules_val == no))
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index a9155077feef..fec75786f75b 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -384,7 +384,7 @@ static void do_of_entry_multi(void *symval, struct module *mod)
len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*",
(*type)[0] ? *type : "*");
- if (compatible[0])
+ if ((*compatible)[0])
sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "",
*compatible);
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index c2c7389bfbab..71b4a8af9d4d 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -52,7 +52,7 @@ rpm-pkg rpm: FORCE
$(call cmd,src_tar,$(KERNELPATH),kernel.spec)
$(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
mv -f $(objtree)/.tmp_version $(objtree)/.version
- rpmbuild --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz
+ rpmbuild $(RPMOPTS) --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz
rm $(KERNELPATH).tar.gz kernel.spec
# binrpm-pkg
@@ -63,7 +63,7 @@ binrpm-pkg: FORCE
$(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
mv -f $(objtree)/.tmp_version $(objtree)/.version
- rpmbuild --define "_builddir $(objtree)" --target \
+ rpmbuild $(RPMOPTS) --define "_builddir $(objtree)" --target \
$(UTS_MACHINE) -bb $(objtree)/binkernel.spec
rm binkernel.spec
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 6c3b038ef40d..86e56fef7473 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -322,7 +322,10 @@ fi
# Build kernel header package
(cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles"
-(cd $srctree; find arch/$SRCARCH/include include scripts -type f) >> "$objtree/debian/hdrsrcfiles"
+if grep -q '^CONFIG_STACK_VALIDATION=y' $KCONFIG_CONFIG ; then
+ (cd $srctree; find tools/objtool -type f -executable) >> "$objtree/debian/hdrsrcfiles"
+fi
+(cd $srctree; find arch/*/include include scripts -type f) >> "$objtree/debian/hdrsrcfiles"
(cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles"
(cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles"
(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f) >> "$objtree/debian/hdrobjfiles"
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index b6de63cb3f23..57673bae5597 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -143,6 +143,11 @@ echo "if [ -x /sbin/new-kernel-pkg ]; then"
echo "new-kernel-pkg --remove $KERNELRELEASE --rminitrd --initrdfile=/boot/initramfs-$KERNELRELEASE.img"
echo "fi"
echo ""
+echo "%postun"
+echo "if [ -x /sbin/update-bootloader ]; then"
+echo "/sbin/update-bootloader --remove $KERNELRELEASE"
+echo "fi"
+echo ""
echo "%files"
echo '%defattr (-, root, root)'
echo "/lib/modules/$KERNELRELEASE"
diff --git a/security/keys/compat.c b/security/keys/compat.c
index c8783b3b628c..36c80bf5b89c 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -134,7 +134,7 @@ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
case KEYCTL_DH_COMPUTE:
return keyctl_dh_compute(compat_ptr(arg2), compat_ptr(arg3),
- arg4);
+ arg4, compat_ptr(arg5));
default:
return -EOPNOTSUPP;
diff --git a/security/keys/dh.c b/security/keys/dh.c
index 880505a4b9f1..531ed2ec132f 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -78,7 +78,8 @@ error:
}
long keyctl_dh_compute(struct keyctl_dh_params __user *params,
- char __user *buffer, size_t buflen)
+ char __user *buffer, size_t buflen,
+ void __user *reserved)
{
long ret;
MPI base, private, prime, result;
@@ -97,6 +98,11 @@ long keyctl_dh_compute(struct keyctl_dh_params __user *params,
goto out;
}
+ if (reserved) {
+ ret = -EINVAL;
+ goto out;
+ }
+
keylen = mpi_from_key(pcopy.prime, buflen, &prime);
if (keylen < 0 || !prime) {
/* buflen == 0 may be used to query the required buffer size,
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 8ec7a528365d..a705a7d92ad7 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -260,10 +260,11 @@ static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
#ifdef CONFIG_KEY_DH_OPERATIONS
extern long keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *,
- size_t);
+ size_t, void __user *);
#else
static inline long keyctl_dh_compute(struct keyctl_dh_params __user *params,
- char __user *buffer, size_t buflen)
+ char __user *buffer, size_t buflen,
+ void __user *reserved)
{
return -EOPNOTSUPP;
}
diff --git a/security/keys/key.c b/security/keys/key.c
index bd5a272f28a6..346fbf201c22 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -597,7 +597,7 @@ int key_reject_and_link(struct key *key,
mutex_unlock(&key_construction_mutex);
- if (keyring)
+ if (keyring && link_ret == 0)
__key_link_end(keyring, &key->index_key, edit);
/* wake up anyone waiting for a key to be constructed */
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 3b135a0af344..d580ad06b792 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1688,8 +1688,8 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
case KEYCTL_DH_COMPUTE:
return keyctl_dh_compute((struct keyctl_dh_params __user *) arg2,
- (char __user *) arg3,
- (size_t) arg4);
+ (char __user *) arg3, (size_t) arg4,
+ (void __user *) arg5);
default:
return -EOPNOTSUPP;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index ff2b8c3cf7a9..6777295f4b2b 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3514,7 +3514,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
*/
if (isp->smk_flags & SMK_INODE_CHANGED) {
isp->smk_flags &= ~SMK_INODE_CHANGED;
- rc = inode->i_op->setxattr(dp,
+ rc = inode->i_op->setxattr(dp, inode,
XATTR_NAME_SMACKTRANSMUTE,
TRANS_TRUE, TRANS_TRUE_SIZE,
0);
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 9b756b1f3dc5..0309f2111c70 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -19,6 +19,9 @@
#include <linux/ratelimit.h>
#include <linux/workqueue.h>
#include <linux/string_helpers.h>
+#include <linux/task_work.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
#define YAMA_SCOPE_DISABLED 0
#define YAMA_SCOPE_RELATIONAL 1
@@ -42,20 +45,71 @@ static DEFINE_SPINLOCK(ptracer_relations_lock);
static void yama_relation_cleanup(struct work_struct *work);
static DECLARE_WORK(yama_relation_work, yama_relation_cleanup);
-static void report_access(const char *access, struct task_struct *target,
- struct task_struct *agent)
+struct access_report_info {
+ struct callback_head work;
+ const char *access;
+ struct task_struct *target;
+ struct task_struct *agent;
+};
+
+static void __report_access(struct callback_head *work)
{
+ struct access_report_info *info =
+ container_of(work, struct access_report_info, work);
char *target_cmd, *agent_cmd;
- target_cmd = kstrdup_quotable_cmdline(target, GFP_ATOMIC);
- agent_cmd = kstrdup_quotable_cmdline(agent, GFP_ATOMIC);
+ target_cmd = kstrdup_quotable_cmdline(info->target, GFP_KERNEL);
+ agent_cmd = kstrdup_quotable_cmdline(info->agent, GFP_KERNEL);
pr_notice_ratelimited(
"ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n",
- access, target_cmd, target->pid, agent_cmd, agent->pid);
+ info->access, target_cmd, info->target->pid, agent_cmd,
+ info->agent->pid);
kfree(agent_cmd);
kfree(target_cmd);
+
+ put_task_struct(info->agent);
+ put_task_struct(info->target);
+ kfree(info);
+}
+
+/* defers execution because cmdline access can sleep */
+static void report_access(const char *access, struct task_struct *target,
+ struct task_struct *agent)
+{
+ struct access_report_info *info;
+ char agent_comm[sizeof(agent->comm)];
+
+ assert_spin_locked(&target->alloc_lock); /* for target->comm */
+
+ if (current->flags & PF_KTHREAD) {
+ /* I don't think kthreads call task_work_run() before exiting.
+ * Imagine angry ranting about procfs here.
+ */
+ pr_notice_ratelimited(
+ "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n",
+ access, target->comm, target->pid,
+ get_task_comm(agent_comm, agent), agent->pid);
+ return;
+ }
+
+ info = kmalloc(sizeof(*info), GFP_ATOMIC);
+ if (!info)
+ return;
+ init_task_work(&info->work, __report_access);
+ get_task_struct(target);
+ get_task_struct(agent);
+ info->access = access;
+ info->target = target;
+ info->agent = agent;
+ if (task_work_add(current, &info->work, true) == 0)
+ return; /* success */
+
+ WARN(1, "report_access called from exiting task");
+ put_task_struct(target);
+ put_task_struct(agent);
+ kfree(info);
}
/**
@@ -351,8 +405,11 @@ int yama_ptrace_traceme(struct task_struct *parent)
break;
}
- if (rc)
+ if (rc) {
+ task_lock(current);
report_access("traceme", current, parent);
+ task_unlock(current);
+ }
return rc;
}
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index c0f8f613f1f1..172dacd925f5 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -420,6 +420,7 @@ static int dummy_hrtimer_stop(struct snd_pcm_substream *substream)
static inline void dummy_hrtimer_sync(struct dummy_hrtimer_pcm *dpcm)
{
+ hrtimer_cancel(&dpcm->timer);
tasklet_kill(&dpcm->tasklet);
}
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index 87041ddd29cb..47a358fab132 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -444,7 +444,7 @@ int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
err = reg_raw_write(codec, reg, val);
if (err == -EAGAIN) {
err = snd_hdac_power_up_pm(codec);
- if (!err)
+ if (err >= 0)
err = reg_raw_write(codec, reg, val);
snd_hdac_power_down_pm(codec);
}
@@ -470,7 +470,7 @@ static int __snd_hdac_regmap_read_raw(struct hdac_device *codec,
err = reg_raw_read(codec, reg, val, uncached);
if (err == -EAGAIN) {
err = snd_hdac_power_up_pm(codec);
- if (!err)
+ if (err >= 0)
err = reg_raw_read(codec, reg, val, uncached);
snd_hdac_power_down_pm(codec);
}
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 9a0d1445ca5c..94089fc71884 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -365,8 +365,11 @@ enum {
#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_KBL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa171)
+#define IS_KBL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d71)
#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) || \
+ IS_KBL(pci) || IS_KBL_LP(pci)
static char *driver_short_names[] = {
[AZX_DRIVER_ICH] = "HDA Intel",
@@ -2181,6 +2184,12 @@ static const struct pci_device_id azx_ids[] = {
/* Sunrise Point-LP */
{ PCI_DEVICE(0x8086, 0x9d70),
.driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+ /* Kabylake */
+ { PCI_DEVICE(0x8086, 0xa171),
+ .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+ /* Kabylake-LP */
+ { PCI_DEVICE(0x8086, 0x9d71),
+ .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
/* Broxton-P(Apollolake) */
{ PCI_DEVICE(0x8086, 0x5a98),
.driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 17fd81736d3d..0621920f7617 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -115,20 +115,20 @@ static int substream_free_pages(struct azx *chip,
/*
* Register access ops. Tegra HDA register access is DWORD only.
*/
-static void hda_tegra_writel(u32 value, u32 *addr)
+static void hda_tegra_writel(u32 value, u32 __iomem *addr)
{
writel(value, addr);
}
-static u32 hda_tegra_readl(u32 *addr)
+static u32 hda_tegra_readl(u32 __iomem *addr)
{
return readl(addr);
}
-static void hda_tegra_writew(u16 value, u16 *addr)
+static void hda_tegra_writew(u16 value, u16 __iomem *addr)
{
unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
- void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+ void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
u32 v;
v = readl(dword_addr);
@@ -137,20 +137,20 @@ static void hda_tegra_writew(u16 value, u16 *addr)
writel(v, dword_addr);
}
-static u16 hda_tegra_readw(u16 *addr)
+static u16 hda_tegra_readw(u16 __iomem *addr)
{
unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
- void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+ void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
u32 v;
v = readl(dword_addr);
return (v >> shift) & 0xffff;
}
-static void hda_tegra_writeb(u8 value, u8 *addr)
+static void hda_tegra_writeb(u8 value, u8 __iomem *addr)
{
unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
- void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+ void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
u32 v;
v = readl(dword_addr);
@@ -159,10 +159,10 @@ static void hda_tegra_writeb(u8 value, u8 *addr)
writel(v, dword_addr);
}
-static u8 hda_tegra_readb(u8 *addr)
+static u8 hda_tegra_readb(u8 __iomem *addr)
{
unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
- void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+ void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
u32 v;
v = readl(dword_addr);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 002f153bc659..900bfbc3368c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -335,6 +335,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0283:
case 0x10ec0286:
case 0x10ec0288:
+ case 0x10ec0295:
case 0x10ec0298:
alc_update_coef_idx(codec, 0x10, 1<<9, 0);
break;
@@ -345,6 +346,9 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0234:
case 0x10ec0274:
case 0x10ec0294:
+ case 0x10ec0700:
+ case 0x10ec0701:
+ case 0x10ec0703:
alc_update_coef_idx(codec, 0x10, 1<<15, 0);
break;
case 0x10ec0662:
@@ -907,6 +911,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = {
{ 0x10ec0298, 0x1028, 0, "ALC3266" },
{ 0x10ec0256, 0x1028, 0, "ALC3246" },
{ 0x10ec0225, 0x1028, 0, "ALC3253" },
+ { 0x10ec0295, 0x1028, 0, "ALC3254" },
{ 0x10ec0670, 0x1025, 0, "ALC669X" },
{ 0x10ec0676, 0x1025, 0, "ALC679X" },
{ 0x10ec0282, 0x1043, 0, "ALC3229" },
@@ -2653,6 +2658,7 @@ enum {
ALC269_TYPE_ALC256,
ALC269_TYPE_ALC225,
ALC269_TYPE_ALC294,
+ ALC269_TYPE_ALC700,
};
/*
@@ -2684,6 +2690,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
case ALC269_TYPE_ALC256:
case ALC269_TYPE_ALC225:
case ALC269_TYPE_ALC294:
+ case ALC269_TYPE_ALC700:
ssids = alc269_ssids;
break;
default:
@@ -3616,13 +3623,20 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
static void alc_headset_mode_unplugged(struct hda_codec *codec)
{
static struct coef_fw coef0255[] = {
- WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
WRITE_COEF(0x06, 0x6104), /* Set MIC2 Vref gate with HP */
WRITE_COEFEX(0x57, 0x03, 0x8aa6), /* Direct Drive HP Amp control */
{}
};
+ static struct coef_fw coef0255_1[] = {
+ WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
+ {}
+ };
+ static struct coef_fw coef0256[] = {
+ WRITE_COEF(0x1b, 0x0c4b), /* LDO and MISC control */
+ {}
+ };
static struct coef_fw coef0233[] = {
WRITE_COEF(0x1b, 0x0c0b),
WRITE_COEF(0x45, 0xc429),
@@ -3675,7 +3689,11 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
switch (codec->core.vendor_id) {
case 0x10ec0255:
+ alc_process_coef_fw(codec, coef0255_1);
+ alc_process_coef_fw(codec, coef0255);
+ break;
case 0x10ec0256:
+ alc_process_coef_fw(codec, coef0256);
alc_process_coef_fw(codec, coef0255);
break;
case 0x10ec0233:
@@ -3697,6 +3715,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
alc_process_coef_fw(codec, coef0668);
break;
case 0x10ec0225:
+ case 0x10ec0295:
alc_process_coef_fw(codec, coef0225);
break;
}
@@ -3797,6 +3816,7 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
break;
case 0x10ec0225:
+ case 0x10ec0295:
alc_update_coef_idx(codec, 0x45, 0x3f<<10, 0x31<<10);
snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
alc_process_coef_fw(codec, coef0225);
@@ -3854,6 +3874,7 @@ static void alc_headset_mode_default(struct hda_codec *codec)
switch (codec->core.vendor_id) {
case 0x10ec0225:
+ case 0x10ec0295:
alc_process_coef_fw(codec, coef0225);
break;
case 0x10ec0255:
@@ -3891,6 +3912,12 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
WRITE_COEFEX(0x57, 0x03, 0x8ea6),
{}
};
+ static struct coef_fw coef0256[] = {
+ WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
+ WRITE_COEF(0x1b, 0x0c6b),
+ WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+ {}
+ };
static struct coef_fw coef0233[] = {
WRITE_COEF(0x45, 0xd429),
WRITE_COEF(0x1b, 0x0c2b),
@@ -3931,9 +3958,11 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
switch (codec->core.vendor_id) {
case 0x10ec0255:
- case 0x10ec0256:
alc_process_coef_fw(codec, coef0255);
break;
+ case 0x10ec0256:
+ alc_process_coef_fw(codec, coef0256);
+ break;
case 0x10ec0233:
case 0x10ec0283:
alc_process_coef_fw(codec, coef0233);
@@ -3957,6 +3986,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
alc_process_coef_fw(codec, coef0688);
break;
case 0x10ec0225:
+ case 0x10ec0295:
alc_process_coef_fw(codec, coef0225);
break;
}
@@ -3972,6 +4002,12 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
WRITE_COEFEX(0x57, 0x03, 0x8ea6),
{}
};
+ static struct coef_fw coef0256[] = {
+ WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
+ WRITE_COEF(0x1b, 0x0c6b),
+ WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+ {}
+ };
static struct coef_fw coef0233[] = {
WRITE_COEF(0x45, 0xe429),
WRITE_COEF(0x1b, 0x0c2b),
@@ -4012,9 +4048,11 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
switch (codec->core.vendor_id) {
case 0x10ec0255:
- case 0x10ec0256:
alc_process_coef_fw(codec, coef0255);
break;
+ case 0x10ec0256:
+ alc_process_coef_fw(codec, coef0256);
+ break;
case 0x10ec0233:
case 0x10ec0283:
alc_process_coef_fw(codec, coef0233);
@@ -4038,6 +4076,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
alc_process_coef_fw(codec, coef0688);
break;
case 0x10ec0225:
+ case 0x10ec0295:
alc_process_coef_fw(codec, coef0225);
break;
}
@@ -4121,6 +4160,7 @@ static void alc_determine_headset_type(struct hda_codec *codec)
is_ctia = (val & 0x1c02) == 0x1c02;
break;
case 0x10ec0225:
+ case 0x10ec0295:
alc_process_coef_fw(codec, coef0225);
msleep(800);
val = alc_read_coef_idx(codec, 0x46);
@@ -4258,7 +4298,7 @@ static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
static void alc255_set_default_jack_type(struct hda_codec *codec)
{
/* Set to iphone type */
- static struct coef_fw fw[] = {
+ static struct coef_fw alc255fw[] = {
WRITE_COEF(0x1b, 0x880b),
WRITE_COEF(0x45, 0xd089),
WRITE_COEF(0x1b, 0x080b),
@@ -4266,7 +4306,22 @@ static void alc255_set_default_jack_type(struct hda_codec *codec)
WRITE_COEF(0x1b, 0x0c0b),
{}
};
- alc_process_coef_fw(codec, fw);
+ static struct coef_fw alc256fw[] = {
+ WRITE_COEF(0x1b, 0x884b),
+ WRITE_COEF(0x45, 0xd089),
+ WRITE_COEF(0x1b, 0x084b),
+ WRITE_COEF(0x46, 0x0004),
+ WRITE_COEF(0x1b, 0x0c4b),
+ {}
+ };
+ switch (codec->core.vendor_id) {
+ case 0x10ec0255:
+ alc_process_coef_fw(codec, alc255fw);
+ break;
+ case 0x10ec0256:
+ alc_process_coef_fw(codec, alc256fw);
+ break;
+ }
msleep(30);
}
@@ -5466,8 +5521,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
- SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+ SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
+ SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -5578,6 +5634,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK),
SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
+ SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460),
SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
@@ -5593,6 +5650,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK),
SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
+ SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460),
+ SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460),
SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
@@ -5711,6 +5770,9 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
{0x14, 0x90170110},
{0x21, 0x02211020}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x14, 0x90170130},
+ {0x21, 0x02211040}),
+ SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60140},
{0x14, 0x90170110},
{0x21, 0x02211020}),
@@ -5763,11 +5825,19 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
{0x12, 0x90a60180},
{0x14, 0x90170130},
{0x21, 0x02211040}),
+ SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5565", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60180},
+ {0x14, 0x90170120},
+ {0x21, 0x02211030}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60160},
{0x14, 0x90170120},
{0x21, 0x02211030}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60170},
+ {0x14, 0x90170120},
+ {0x21, 0x02211030}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC256_STANDARD_PINS),
SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
{0x12, 0x90a60130},
@@ -6033,6 +6103,7 @@ static int patch_alc269(struct hda_codec *codec)
alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/
break;
case 0x10ec0225:
+ case 0x10ec0295:
spec->codec_variant = ALC269_TYPE_ALC225;
break;
case 0x10ec0234:
@@ -6040,6 +6111,14 @@ static int patch_alc269(struct hda_codec *codec)
case 0x10ec0294:
spec->codec_variant = ALC269_TYPE_ALC294;
break;
+ case 0x10ec0700:
+ case 0x10ec0701:
+ case 0x10ec0703:
+ spec->codec_variant = ALC269_TYPE_ALC700;
+ spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */
+ alc_update_coef_idx(codec, 0x4a, 0, 1 << 15); /* Combo jack auto trigger control */
+ break;
+
}
if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) {
@@ -6979,6 +7058,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
HDA_CODEC_ENTRY(0x10ec0292, "ALC292", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0293, "ALC293", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0294, "ALC294", patch_alc269),
+ HDA_CODEC_ENTRY(0x10ec0295, "ALC295", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0298, "ALC298", patch_alc269),
HDA_CODEC_REV_ENTRY(0x10ec0861, 0x100340, "ALC660", patch_alc861),
HDA_CODEC_ENTRY(0x10ec0660, "ALC660-VD", patch_alc861vd),
@@ -6994,6 +7074,9 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
HDA_CODEC_ENTRY(0x10ec0670, "ALC670", patch_alc662),
HDA_CODEC_ENTRY(0x10ec0671, "ALC671", patch_alc662),
HDA_CODEC_ENTRY(0x10ec0680, "ALC680", patch_alc680),
+ HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269),
+ HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269),
+ HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc882),
HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880),
HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882),
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index b3afae990e39..4d82a58ff6b0 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -43,6 +43,7 @@ config SND_SOC_ALL_CODECS
select SND_SOC_AK5386
select SND_SOC_ALC5623 if I2C
select SND_SOC_ALC5632 if I2C
+ select SND_SOC_BT_SCO
select SND_SOC_CQ0093VC if MFD_DAVINCI_VOICECODEC
select SND_SOC_CS35L32 if I2C
select SND_SOC_CS42L51_I2C if I2C
@@ -64,7 +65,6 @@ config SND_SOC_ALL_CODECS
select SND_SOC_DA732X if I2C
select SND_SOC_DA9055 if I2C
select SND_SOC_DMIC
- select SND_SOC_BT_SCO
select SND_SOC_ES8328_SPI if SPI_MASTER
select SND_SOC_ES8328_I2C if I2C
select SND_SOC_GTM601
@@ -79,6 +79,7 @@ config SND_SOC_ALL_CODECS
select SND_SOC_MAX98090 if I2C
select SND_SOC_MAX98095 if I2C
select SND_SOC_MAX98357A if GPIOLIB
+ select SND_SOC_MAX98371 if I2C
select SND_SOC_MAX9867 if I2C
select SND_SOC_MAX98925 if I2C
select SND_SOC_MAX98926 if I2C
@@ -126,12 +127,14 @@ config SND_SOC_ALL_CODECS
select SND_SOC_TAS2552 if I2C
select SND_SOC_TAS5086 if I2C
select SND_SOC_TAS571X if I2C
+ select SND_SOC_TAS5720 if I2C
select SND_SOC_TFA9879 if I2C
select SND_SOC_TLV320AIC23_I2C if I2C
select SND_SOC_TLV320AIC23_SPI if SPI_MASTER
select SND_SOC_TLV320AIC26 if SPI_MASTER
select SND_SOC_TLV320AIC31XX if I2C
- select SND_SOC_TLV320AIC32X4 if I2C
+ select SND_SOC_TLV320AIC32X4_I2C if I2C
+ select SND_SOC_TLV320AIC32X4_SPI if SPI_MASTER
select SND_SOC_TLV320AIC3X if I2C
select SND_SOC_TPA6130A2 if I2C
select SND_SOC_TLV320DAC33 if I2C
@@ -367,6 +370,9 @@ config SND_SOC_ALC5623
config SND_SOC_ALC5632
tristate
+config SND_SOC_BT_SCO
+ tristate
+
config SND_SOC_CQ0093VC
tristate
@@ -473,9 +479,6 @@ config SND_SOC_DA732X
config SND_SOC_DA9055
tristate
-config SND_SOC_BT_SCO
- tristate
-
config SND_SOC_DMIC
tristate
@@ -529,6 +532,9 @@ config SND_SOC_MAX98095
config SND_SOC_MAX98357A
tristate
+config SND_SOC_MAX98371
+ tristate
+
config SND_SOC_MAX9867
tristate
@@ -748,9 +754,16 @@ config SND_SOC_TAS5086
depends on I2C
config SND_SOC_TAS571X
- tristate "Texas Instruments TAS5711/TAS5717/TAS5719 power amplifiers"
+ tristate "Texas Instruments TAS5711/TAS5717/TAS5719/TAS5721 power amplifiers"
depends on I2C
+config SND_SOC_TAS5720
+ tristate "Texas Instruments TAS5720 Mono Audio amplifier"
+ depends on I2C
+ help
+ Enable support for Texas Instruments TAS5720L/M high-efficiency mono
+ Class-D audio power amplifiers.
+
config SND_SOC_TFA9879
tristate "NXP Semiconductors TFA9879 amplifier"
depends on I2C
@@ -780,6 +793,16 @@ config SND_SOC_TLV320AIC31XX
config SND_SOC_TLV320AIC32X4
tristate
+config SND_SOC_TLV320AIC32X4_I2C
+ tristate
+ depends on I2C
+ select SND_SOC_TLV320AIC32X4
+
+config SND_SOC_TLV320AIC32X4_SPI
+ tristate
+ depends on SPI_MASTER
+ select SND_SOC_TLV320AIC32X4
+
config SND_SOC_TLV320AIC3X
tristate "Texas Instruments TLV320AIC3x CODECs"
depends on I2C
@@ -920,7 +943,8 @@ config SND_SOC_WM8955
tristate
config SND_SOC_WM8960
- tristate
+ tristate "Wolfson Microelectronics WM8960 CODEC"
+ depends on I2C
config SND_SOC_WM8961
tristate
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index b7b99416537f..0f548fd34ca3 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -32,6 +32,7 @@ snd-soc-ak4642-objs := ak4642.o
snd-soc-ak4671-objs := ak4671.o
snd-soc-ak5386-objs := ak5386.o
snd-soc-arizona-objs := arizona.o
+snd-soc-bt-sco-objs := bt-sco.o
snd-soc-cq93vc-objs := cq93vc.o
snd-soc-cs35l32-objs := cs35l32.o
snd-soc-cs42l51-objs := cs42l51.o
@@ -55,7 +56,6 @@ snd-soc-da7218-objs := da7218.o
snd-soc-da7219-objs := da7219.o da7219-aad.o
snd-soc-da732x-objs := da732x.o
snd-soc-da9055-objs := da9055.o
-snd-soc-bt-sco-objs := bt-sco.o
snd-soc-dmic-objs := dmic.o
snd-soc-es8328-objs := es8328.o
snd-soc-es8328-i2c-objs := es8328-i2c.o
@@ -74,6 +74,7 @@ snd-soc-max98088-objs := max98088.o
snd-soc-max98090-objs := max98090.o
snd-soc-max98095-objs := max98095.o
snd-soc-max98357a-objs := max98357a.o
+snd-soc-max98371-objs := max98371.o
snd-soc-max9867-objs := max9867.o
snd-soc-max98925-objs := max98925.o
snd-soc-max98926-objs := max98926.o
@@ -131,6 +132,7 @@ snd-soc-stac9766-objs := stac9766.o
snd-soc-sti-sas-objs := sti-sas.o
snd-soc-tas5086-objs := tas5086.o
snd-soc-tas571x-objs := tas571x.o
+snd-soc-tas5720-objs := tas5720.o
snd-soc-tfa9879-objs := tfa9879.o
snd-soc-tlv320aic23-objs := tlv320aic23.o
snd-soc-tlv320aic23-i2c-objs := tlv320aic23-i2c.o
@@ -138,6 +140,8 @@ snd-soc-tlv320aic23-spi-objs := tlv320aic23-spi.o
snd-soc-tlv320aic26-objs := tlv320aic26.o
snd-soc-tlv320aic31xx-objs := tlv320aic31xx.o
snd-soc-tlv320aic32x4-objs := tlv320aic32x4.o
+snd-soc-tlv320aic32x4-i2c-objs := tlv320aic32x4-i2c.o
+snd-soc-tlv320aic32x4-spi-objs := tlv320aic32x4-spi.o
snd-soc-tlv320aic3x-objs := tlv320aic3x.o
snd-soc-tlv320dac33-objs := tlv320dac33.o
snd-soc-ts3a227e-objs := ts3a227e.o
@@ -243,6 +247,7 @@ obj-$(CONFIG_SND_SOC_AK5386) += snd-soc-ak5386.o
obj-$(CONFIG_SND_SOC_ALC5623) += snd-soc-alc5623.o
obj-$(CONFIG_SND_SOC_ALC5632) += snd-soc-alc5632.o
obj-$(CONFIG_SND_SOC_ARIZONA) += snd-soc-arizona.o
+obj-$(CONFIG_SND_SOC_BT_SCO) += snd-soc-bt-sco.o
obj-$(CONFIG_SND_SOC_CQ0093VC) += snd-soc-cq93vc.o
obj-$(CONFIG_SND_SOC_CS35L32) += snd-soc-cs35l32.o
obj-$(CONFIG_SND_SOC_CS42L51) += snd-soc-cs42l51.o
@@ -266,7 +271,6 @@ obj-$(CONFIG_SND_SOC_DA7218) += snd-soc-da7218.o
obj-$(CONFIG_SND_SOC_DA7219) += snd-soc-da7219.o
obj-$(CONFIG_SND_SOC_DA732X) += snd-soc-da732x.o
obj-$(CONFIG_SND_SOC_DA9055) += snd-soc-da9055.o
-obj-$(CONFIG_SND_SOC_BT_SCO) += snd-soc-bt-sco.o
obj-$(CONFIG_SND_SOC_DMIC) += snd-soc-dmic.o
obj-$(CONFIG_SND_SOC_ES8328) += snd-soc-es8328.o
obj-$(CONFIG_SND_SOC_ES8328_I2C)+= snd-soc-es8328-i2c.o
@@ -339,6 +343,7 @@ obj-$(CONFIG_SND_SOC_STI_SAS) += snd-soc-sti-sas.o
obj-$(CONFIG_SND_SOC_TAS2552) += snd-soc-tas2552.o
obj-$(CONFIG_SND_SOC_TAS5086) += snd-soc-tas5086.o
obj-$(CONFIG_SND_SOC_TAS571X) += snd-soc-tas571x.o
+obj-$(CONFIG_SND_SOC_TAS5720) += snd-soc-tas5720.o
obj-$(CONFIG_SND_SOC_TFA9879) += snd-soc-tfa9879.o
obj-$(CONFIG_SND_SOC_TLV320AIC23) += snd-soc-tlv320aic23.o
obj-$(CONFIG_SND_SOC_TLV320AIC23_I2C) += snd-soc-tlv320aic23-i2c.o
@@ -346,6 +351,8 @@ obj-$(CONFIG_SND_SOC_TLV320AIC23_SPI) += snd-soc-tlv320aic23-spi.o
obj-$(CONFIG_SND_SOC_TLV320AIC26) += snd-soc-tlv320aic26.o
obj-$(CONFIG_SND_SOC_TLV320AIC31XX) += snd-soc-tlv320aic31xx.o
obj-$(CONFIG_SND_SOC_TLV320AIC32X4) += snd-soc-tlv320aic32x4.o
+obj-$(CONFIG_SND_SOC_TLV320AIC32X4_I2C) += snd-soc-tlv320aic32x4-i2c.o
+obj-$(CONFIG_SND_SOC_TLV320AIC32X4_SPI) += snd-soc-tlv320aic32x4-spi.o
obj-$(CONFIG_SND_SOC_TLV320AIC3X) += snd-soc-tlv320aic3x.o
obj-$(CONFIG_SND_SOC_TLV320DAC33) += snd-soc-tlv320dac33.o
obj-$(CONFIG_SND_SOC_TS3A227E) += snd-soc-ts3a227e.o
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 1ee8506c06c7..4d8b9e49e8d6 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -560,6 +560,7 @@ static const struct regmap_config ak4642_regmap = {
.max_register = FIL1_3,
.reg_defaults = ak4642_reg,
.num_reg_defaults = NUM_AK4642_REG_DEFAULTS,
+ .cache_type = REGCACHE_RBTREE,
};
static const struct regmap_config ak4643_regmap = {
@@ -568,6 +569,7 @@ static const struct regmap_config ak4643_regmap = {
.max_register = SPK_MS,
.reg_defaults = ak4643_reg,
.num_reg_defaults = ARRAY_SIZE(ak4643_reg),
+ .cache_type = REGCACHE_RBTREE,
};
static const struct regmap_config ak4648_regmap = {
@@ -576,6 +578,7 @@ static const struct regmap_config ak4648_regmap = {
.max_register = EQ_FBEQE,
.reg_defaults = ak4648_reg,
.num_reg_defaults = ARRAY_SIZE(ak4648_reg),
+ .cache_type = REGCACHE_RBTREE,
};
static const struct ak4642_drvdata ak4642_drvdata = {
diff --git a/sound/soc/codecs/max98371.c b/sound/soc/codecs/max98371.c
new file mode 100644
index 000000000000..cf0a39bb631a
--- /dev/null
+++ b/sound/soc/codecs/max98371.c
@@ -0,0 +1,441 @@
+/*
+ * max98371.c -- ALSA SoC Stereo MAX98371 driver
+ *
+ * Copyright 2015-16 Maxim Integrated Products
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/tlv.h>
+#include "max98371.h"
+
+static const char *const monomix_text[] = {
+ "Left", "Right", "LeftRightDiv2",
+};
+
+static const char *const hpf_cutoff_txt[] = {
+ "Disable", "DC Block", "50Hz",
+ "100Hz", "200Hz", "400Hz", "800Hz",
+};
+
+static SOC_ENUM_SINGLE_DECL(max98371_monomix, MAX98371_MONOMIX_CFG, 0,
+ monomix_text);
+
+static SOC_ENUM_SINGLE_DECL(max98371_hpf_cutoff, MAX98371_HPF, 0,
+ hpf_cutoff_txt);
+
+static const DECLARE_TLV_DB_RANGE(max98371_dht_min_gain,
+ 0, 1, TLV_DB_SCALE_ITEM(537, 66, 0),
+ 2, 3, TLV_DB_SCALE_ITEM(677, 82, 0),
+ 4, 5, TLV_DB_SCALE_ITEM(852, 104, 0),
+ 6, 7, TLV_DB_SCALE_ITEM(1072, 131, 0),
+ 8, 9, TLV_DB_SCALE_ITEM(1350, 165, 0),
+ 10, 11, TLV_DB_SCALE_ITEM(1699, 101, 0),
+);
+
+static const DECLARE_TLV_DB_RANGE(max98371_dht_max_gain,
+ 0, 1, TLV_DB_SCALE_ITEM(537, 66, 0),
+ 2, 3, TLV_DB_SCALE_ITEM(677, 82, 0),
+ 4, 5, TLV_DB_SCALE_ITEM(852, 104, 0),
+ 6, 7, TLV_DB_SCALE_ITEM(1072, 131, 0),
+ 8, 9, TLV_DB_SCALE_ITEM(1350, 165, 0),
+ 10, 11, TLV_DB_SCALE_ITEM(1699, 208, 0),
+);
+
+static const DECLARE_TLV_DB_RANGE(max98371_dht_rot_gain,
+ 0, 1, TLV_DB_SCALE_ITEM(-50, -50, 0),
+ 2, 6, TLV_DB_SCALE_ITEM(-100, -100, 0),
+ 7, 8, TLV_DB_SCALE_ITEM(-800, -200, 0),
+ 9, 11, TLV_DB_SCALE_ITEM(-1200, -300, 0),
+ 12, 13, TLV_DB_SCALE_ITEM(-2000, -200, 0),
+ 14, 15, TLV_DB_SCALE_ITEM(-2500, -500, 0),
+);
+
+static const struct reg_default max98371_reg[] = {
+ { 0x01, 0x00 },
+ { 0x02, 0x00 },
+ { 0x03, 0x00 },
+ { 0x04, 0x00 },
+ { 0x05, 0x00 },
+ { 0x06, 0x00 },
+ { 0x07, 0x00 },
+ { 0x08, 0x00 },
+ { 0x09, 0x00 },
+ { 0x0A, 0x00 },
+ { 0x10, 0x06 },
+ { 0x11, 0x08 },
+ { 0x14, 0x80 },
+ { 0x15, 0x00 },
+ { 0x16, 0x00 },
+ { 0x18, 0x00 },
+ { 0x19, 0x00 },
+ { 0x1C, 0x00 },
+ { 0x1D, 0x00 },
+ { 0x1E, 0x00 },
+ { 0x1F, 0x00 },
+ { 0x20, 0x00 },
+ { 0x21, 0x00 },
+ { 0x22, 0x00 },
+ { 0x23, 0x00 },
+ { 0x24, 0x00 },
+ { 0x25, 0x00 },
+ { 0x26, 0x00 },
+ { 0x27, 0x00 },
+ { 0x28, 0x00 },
+ { 0x29, 0x00 },
+ { 0x2A, 0x00 },
+ { 0x2B, 0x00 },
+ { 0x2C, 0x00 },
+ { 0x2D, 0x00 },
+ { 0x2E, 0x0B },
+ { 0x31, 0x00 },
+ { 0x32, 0x18 },
+ { 0x33, 0x00 },
+ { 0x34, 0x00 },
+ { 0x36, 0x00 },
+ { 0x37, 0x00 },
+ { 0x38, 0x00 },
+ { 0x39, 0x00 },
+ { 0x3A, 0x00 },
+ { 0x3B, 0x00 },
+ { 0x3C, 0x00 },
+ { 0x3D, 0x00 },
+ { 0x3E, 0x00 },
+ { 0x3F, 0x00 },
+ { 0x40, 0x00 },
+ { 0x41, 0x00 },
+ { 0x42, 0x00 },
+ { 0x43, 0x00 },
+ { 0x4A, 0x00 },
+ { 0x4B, 0x00 },
+ { 0x4C, 0x00 },
+ { 0x4D, 0x00 },
+ { 0x4E, 0x00 },
+ { 0x50, 0x00 },
+ { 0x51, 0x00 },
+ { 0x55, 0x00 },
+ { 0x58, 0x00 },
+ { 0x59, 0x00 },
+ { 0x5C, 0x00 },
+ { 0xFF, 0x43 },
+};
+
+static bool max98371_volatile_register(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case MAX98371_IRQ_CLEAR1:
+ case MAX98371_IRQ_CLEAR2:
+ case MAX98371_IRQ_CLEAR3:
+ case MAX98371_VERSION:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool max98371_readable_register(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case MAX98371_SOFT_RESET:
+ return false;
+ default:
+ return true;
+ }
+};
+
+static const DECLARE_TLV_DB_RANGE(max98371_gain_tlv,
+ 0, 7, TLV_DB_SCALE_ITEM(0, 50, 0),
+ 8, 10, TLV_DB_SCALE_ITEM(400, 100, 0)
+);
+
+static const DECLARE_TLV_DB_RANGE(max98371_noload_gain_tlv,
+ 0, 11, TLV_DB_SCALE_ITEM(950, 100, 0),
+);
+
+static const DECLARE_TLV_DB_SCALE(digital_tlv, -6300, 50, 1);
+
+static const struct snd_kcontrol_new max98371_snd_controls[] = {
+ SOC_SINGLE_TLV("Speaker Volume", MAX98371_GAIN,
+ MAX98371_GAIN_SHIFT, (1<<MAX98371_GAIN_WIDTH)-1, 0,
+ max98371_gain_tlv),
+ SOC_SINGLE_TLV("Digital Volume", MAX98371_DIGITAL_GAIN, 0,
+ (1<<MAX98371_DIGITAL_GAIN_WIDTH)-1, 1, digital_tlv),
+ SOC_SINGLE_TLV("Speaker DHT Max Volume", MAX98371_GAIN,
+ 0, (1<<MAX98371_DHT_MAX_WIDTH)-1, 0,
+ max98371_dht_max_gain),
+ SOC_SINGLE_TLV("Speaker DHT Min Volume", MAX98371_DHT_GAIN,
+ 0, (1<<MAX98371_DHT_GAIN_WIDTH)-1, 0,
+ max98371_dht_min_gain),
+ SOC_SINGLE_TLV("Speaker DHT Rotation Volume", MAX98371_DHT_GAIN,
+ 0, (1<<MAX98371_DHT_ROT_WIDTH)-1, 0,
+ max98371_dht_rot_gain),
+ SOC_SINGLE("DHT Attack Step", MAX98371_DHT, MAX98371_DHT_STEP, 3, 0),
+ SOC_SINGLE("DHT Attack Rate", MAX98371_DHT, 0, 7, 0),
+ SOC_ENUM("Monomix Select", max98371_monomix),
+ SOC_ENUM("HPF Cutoff", max98371_hpf_cutoff),
+};
+
+static int max98371_dai_set_fmt(struct snd_soc_dai *codec_dai,
+ unsigned int fmt)
+{
+ struct snd_soc_codec *codec = codec_dai->codec;
+ struct max98371_priv *max98371 = snd_soc_codec_get_drvdata(codec);
+ unsigned int val = 0;
+
+ switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+ case SND_SOC_DAIFMT_CBS_CFS:
+ break;
+ default:
+ dev_err(codec->dev, "DAI clock mode unsupported");
+ return -EINVAL;
+ }
+
+ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+ case SND_SOC_DAIFMT_I2S:
+ val |= 0;
+ break;
+ case SND_SOC_DAIFMT_RIGHT_J:
+ val |= MAX98371_DAI_RIGHT;
+ break;
+ case SND_SOC_DAIFMT_LEFT_J:
+ val |= MAX98371_DAI_LEFT;
+ break;
+ default:
+ dev_err(codec->dev, "DAI wrong mode unsupported");
+ return -EINVAL;
+ }
+ regmap_update_bits(max98371->regmap, MAX98371_FMT,
+ MAX98371_FMT_MODE_MASK, val);
+ return 0;
+}
+
+static int max98371_dai_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct snd_soc_dai *dai)
+{
+ struct snd_soc_codec *codec = dai->codec;
+ struct max98371_priv *max98371 = snd_soc_codec_get_drvdata(codec);
+ int blr_clk_ratio, ch_size, channels = params_channels(params);
+ int rate = params_rate(params);
+
+ switch (params_format(params)) {
+ case SNDRV_PCM_FORMAT_S8:
+ regmap_update_bits(max98371->regmap, MAX98371_FMT,
+ MAX98371_FMT_MASK, MAX98371_DAI_CHANSZ_16);
+ ch_size = 8;
+ break;
+ case SNDRV_PCM_FORMAT_S16_LE:
+ regmap_update_bits(max98371->regmap, MAX98371_FMT,
+ MAX98371_FMT_MASK, MAX98371_DAI_CHANSZ_16);
+ ch_size = 16;
+ break;
+ case SNDRV_PCM_FORMAT_S24_LE:
+ regmap_update_bits(max98371->regmap, MAX98371_FMT,
+ MAX98371_FMT_MASK, MAX98371_DAI_CHANSZ_32);
+ ch_size = 24;
+ break;
+ case SNDRV_PCM_FORMAT_S32_LE:
+ regmap_update_bits(max98371->regmap, MAX98371_FMT,
+ MAX98371_FMT_MASK, MAX98371_DAI_CHANSZ_32);
+ ch_size = 32;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* BCLK/LRCLK ratio calculation */
+ blr_clk_ratio = channels * ch_size;
+ switch (blr_clk_ratio) {
+ case 32:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_DAI_CLK,
+ MAX98371_DAI_BSEL_MASK, MAX98371_DAI_BSEL_32);
+ break;
+ case 48:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_DAI_CLK,
+ MAX98371_DAI_BSEL_MASK, MAX98371_DAI_BSEL_48);
+ break;
+ case 64:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_DAI_CLK,
+ MAX98371_DAI_BSEL_MASK, MAX98371_DAI_BSEL_64);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (rate) {
+ case 32000:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_SPK_SR,
+ MAX98371_SPK_SR_MASK, MAX98371_SPK_SR_32);
+ break;
+ case 44100:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_SPK_SR,
+ MAX98371_SPK_SR_MASK, MAX98371_SPK_SR_44);
+ break;
+ case 48000:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_SPK_SR,
+ MAX98371_SPK_SR_MASK, MAX98371_SPK_SR_48);
+ break;
+ case 88200:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_SPK_SR,
+ MAX98371_SPK_SR_MASK, MAX98371_SPK_SR_88);
+ break;
+ case 96000:
+ regmap_update_bits(max98371->regmap,
+ MAX98371_SPK_SR,
+ MAX98371_SPK_SR_MASK, MAX98371_SPK_SR_96);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* enabling both the RX channels*/
+ regmap_update_bits(max98371->regmap, MAX98371_MONOMIX_SRC,
+ MAX98371_MONOMIX_SRC_MASK, MONOMIX_RX_0_1);
+ regmap_update_bits(max98371->regmap, MAX98371_DAI_CHANNEL,
+ MAX98371_CHANNEL_MASK, MAX98371_CHANNEL_MASK);
+ return 0;
+}
+
+static const struct snd_soc_dapm_widget max98371_dapm_widgets[] = {
+ SND_SOC_DAPM_DAC("DAC", NULL, MAX98371_SPK_ENABLE, 0, 0),
+ SND_SOC_DAPM_SUPPLY("Global Enable", MAX98371_GLOBAL_ENABLE,
+ 0, 0, NULL, 0),
+ SND_SOC_DAPM_OUTPUT("SPK_OUT"),
+};
+
+static const struct snd_soc_dapm_route max98371_audio_map[] = {
+ {"DAC", NULL, "HiFi Playback"},
+ {"SPK_OUT", NULL, "DAC"},
+ {"SPK_OUT", NULL, "Global Enable"},
+};
+
+#define MAX98371_RATES SNDRV_PCM_RATE_8000_48000
+#define MAX98371_FORMATS (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_S16_BE | \
+ SNDRV_PCM_FMTBIT_S24_BE | SNDRV_PCM_FMTBIT_S32_BE)
+
+static const struct snd_soc_dai_ops max98371_dai_ops = {
+ .set_fmt = max98371_dai_set_fmt,
+ .hw_params = max98371_dai_hw_params,
+};
+
+static struct snd_soc_dai_driver max98371_dai[] = {
+ {
+ .name = "max98371-aif1",
+ .playback = {
+ .stream_name = "HiFi Playback",
+ .channels_min = 1,
+ .channels_max = 2,
+ .rates = SNDRV_PCM_RATE_8000_48000,
+ .formats = MAX98371_FORMATS,
+ },
+ .ops = &max98371_dai_ops,
+ }
+};
+
+static const struct snd_soc_codec_driver max98371_codec = {
+ .controls = max98371_snd_controls,
+ .num_controls = ARRAY_SIZE(max98371_snd_controls),
+ .dapm_routes = max98371_audio_map,
+ .num_dapm_routes = ARRAY_SIZE(max98371_audio_map),
+ .dapm_widgets = max98371_dapm_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(max98371_dapm_widgets),
+};
+
+static const struct regmap_config max98371_regmap = {
+ .reg_bits = 8,
+ .val_bits = 8,
+ .max_register = MAX98371_VERSION,
+ .reg_defaults = max98371_reg,
+ .num_reg_defaults = ARRAY_SIZE(max98371_reg),
+ .volatile_reg = max98371_volatile_register,
+ .readable_reg = max98371_readable_register,
+ .cache_type = REGCACHE_RBTREE,
+};
+
+static int max98371_i2c_probe(struct i2c_client *i2c,
+ const struct i2c_device_id *id)
+{
+ struct max98371_priv *max98371;
+ int ret, reg;
+
+ max98371 = devm_kzalloc(&i2c->dev,
+ sizeof(*max98371), GFP_KERNEL);
+ if (!max98371)
+ return -ENOMEM;
+
+ i2c_set_clientdata(i2c, max98371);
+ max98371->regmap = devm_regmap_init_i2c(i2c, &max98371_regmap);
+ if (IS_ERR(max98371->regmap)) {
+ ret = PTR_ERR(max98371->regmap);
+ dev_err(&i2c->dev,
+ "Failed to allocate regmap: %d\n", ret);
+ return ret;
+ }
+
+ ret = regmap_read(max98371->regmap, MAX98371_VERSION, &reg);
+ if (ret < 0) {
+ dev_info(&i2c->dev, "device error %d\n", ret);
+ return ret;
+ }
+ dev_info(&i2c->dev, "device version %x\n", reg);
+
+ ret = snd_soc_register_codec(&i2c->dev, &max98371_codec,
+ max98371_dai, ARRAY_SIZE(max98371_dai));
+ if (ret < 0) {
+ dev_err(&i2c->dev, "Failed to register codec: %d\n", ret);
+ return ret;
+ }
+ return ret;
+}
+
+static int max98371_i2c_remove(struct i2c_client *client)
+{
+ snd_soc_unregister_codec(&client->dev);
+ return 0;
+}
+
+static const struct i2c_device_id max98371_i2c_id[] = {
+ { "max98371", 0 },
+};
+
+MODULE_DEVICE_TABLE(i2c, max98371_i2c_id);
+
+static const struct of_device_id max98371_of_match[] = {
+ { .compatible = "maxim,max98371", },
+ { }
+};
+MODULE_DEVICE_TABLE(of, max98371_of_match);
+
+static struct i2c_driver max98371_i2c_driver = {
+ .driver = {
+ .name = "max98371",
+ .owner = THIS_MODULE,
+ .pm = NULL,
+ .of_match_table = of_match_ptr(max98371_of_match),
+ },
+ .probe = max98371_i2c_probe,
+ .remove = max98371_i2c_remove,
+ .id_table = max98371_i2c_id,
+};
+
+module_i2c_driver(max98371_i2c_driver);
+
+MODULE_AUTHOR("anish kumar <yesanishhere@gmail.com>");
+MODULE_DESCRIPTION("ALSA SoC MAX98371 driver");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/max98371.h b/sound/soc/codecs/max98371.h
new file mode 100644
index 000000000000..9f6330964d98
--- /dev/null
+++ b/sound/soc/codecs/max98371.h
@@ -0,0 +1,67 @@
+/*
+ * max98371.h -- MAX98371 ALSA SoC Audio driver
+ *
+ * Copyright 2011-2012 Maxim Integrated Products
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _MAX98371_H
+#define _MAX98371_H
+
+#define MAX98371_IRQ_CLEAR1 0x01
+#define MAX98371_IRQ_CLEAR2 0x02
+#define MAX98371_IRQ_CLEAR3 0x03
+#define MAX98371_DAI_CLK 0x10
+#define MAX98371_DAI_BSEL_MASK 0xF
+#define MAX98371_DAI_BSEL_32 2
+#define MAX98371_DAI_BSEL_48 3
+#define MAX98371_DAI_BSEL_64 4
+#define MAX98371_SPK_SR 0x11
+#define MAX98371_SPK_SR_MASK 0xF
+#define MAX98371_SPK_SR_32 6
+#define MAX98371_SPK_SR_44 7
+#define MAX98371_SPK_SR_48 8
+#define MAX98371_SPK_SR_88 10
+#define MAX98371_SPK_SR_96 11
+#define MAX98371_DAI_CHANNEL 0x15
+#define MAX98371_CHANNEL_MASK 0x3
+#define MAX98371_MONOMIX_SRC 0x18
+#define MAX98371_MONOMIX_CFG 0x19
+#define MAX98371_HPF 0x1C
+#define MAX98371_MONOMIX_SRC_MASK 0xFF
+#define MONOMIX_RX_0_1 ((0x1)<<(4))
+#define M98371_DAI_CHANNEL_I2S 0x3
+#define MAX98371_DIGITAL_GAIN 0x2D
+#define MAX98371_DIGITAL_GAIN_WIDTH 0x7
+#define MAX98371_GAIN 0x2E
+#define MAX98371_GAIN_SHIFT 0x4
+#define MAX98371_GAIN_WIDTH 0x4
+#define MAX98371_DHT_MAX_WIDTH 4
+#define MAX98371_FMT 0x14
+#define MAX98371_CHANSZ_WIDTH 6
+#define MAX98371_FMT_MASK ((0x3)<<(MAX98371_CHANSZ_WIDTH))
+#define MAX98371_FMT_MODE_MASK ((0x7)<<(3))
+#define MAX98371_DAI_LEFT ((0x1)<<(3))
+#define MAX98371_DAI_RIGHT ((0x2)<<(3))
+#define MAX98371_DAI_CHANSZ_16 ((1)<<(MAX98371_CHANSZ_WIDTH))
+#define MAX98371_DAI_CHANSZ_24 ((2)<<(MAX98371_CHANSZ_WIDTH))
+#define MAX98371_DAI_CHANSZ_32 ((3)<<(MAX98371_CHANSZ_WIDTH))
+#define MAX98371_DHT 0x32
+#define MAX98371_DHT_STEP 0x3
+#define MAX98371_DHT_GAIN 0x31
+#define MAX98371_DHT_GAIN_WIDTH 0x4
+#define MAX98371_DHT_ROT_WIDTH 0x4
+#define MAX98371_SPK_ENABLE 0x4A
+#define MAX98371_GLOBAL_ENABLE 0x50
+#define MAX98371_SOFT_RESET 0x51
+#define MAX98371_VERSION 0xFF
+
+
+struct max98371_priv {
+ struct regmap *regmap;
+ struct snd_soc_codec *codec;
+};
+#endif
diff --git a/sound/soc/codecs/rt298.c b/sound/soc/codecs/rt298.c
index a1aaffc20862..f80cfe4d2ef2 100644
--- a/sound/soc/codecs/rt298.c
+++ b/sound/soc/codecs/rt298.c
@@ -276,6 +276,8 @@ static int rt298_jack_detect(struct rt298_priv *rt298, bool *hp, bool *mic)
} else {
*mic = false;
regmap_write(rt298->regmap, RT298_SET_MIC1, 0x20);
+ regmap_update_bits(rt298->regmap,
+ RT298_CBJ_CTRL1, 0x0400, 0x0000);
}
} else {
regmap_read(rt298->regmap, RT298_GET_HP_SENSE, &buf);
@@ -482,6 +484,26 @@ static int rt298_adc_event(struct snd_soc_dapm_widget *w,
snd_soc_update_bits(codec,
VERB_CMD(AC_VERB_SET_AMP_GAIN_MUTE, nid, 0),
0x7080, 0x7000);
+ /* If MCLK doesn't exist, reset AD filter */
+ if (!(snd_soc_read(codec, RT298_VAD_CTRL) & 0x200)) {
+ pr_info("NO MCLK\n");
+ switch (nid) {
+ case RT298_ADC_IN1:
+ snd_soc_update_bits(codec,
+ RT298_D_FILTER_CTRL, 0x2, 0x2);
+ mdelay(10);
+ snd_soc_update_bits(codec,
+ RT298_D_FILTER_CTRL, 0x2, 0x0);
+ break;
+ case RT298_ADC_IN2:
+ snd_soc_update_bits(codec,
+ RT298_D_FILTER_CTRL, 0x4, 0x4);
+ mdelay(10);
+ snd_soc_update_bits(codec,
+ RT298_D_FILTER_CTRL, 0x4, 0x0);
+ break;
+ }
+ }
break;
case SND_SOC_DAPM_PRE_PMD:
snd_soc_update_bits(codec,
@@ -520,30 +542,12 @@ static int rt298_mic1_event(struct snd_soc_dapm_widget *w,
return 0;
}
-static int rt298_vref_event(struct snd_soc_dapm_widget *w,
- struct snd_kcontrol *kcontrol, int event)
-{
- struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
-
- switch (event) {
- case SND_SOC_DAPM_PRE_PMU:
- snd_soc_update_bits(codec,
- RT298_CBJ_CTRL1, 0x0400, 0x0000);
- mdelay(50);
- break;
- default:
- return 0;
- }
-
- return 0;
-}
-
static const struct snd_soc_dapm_widget rt298_dapm_widgets[] = {
SND_SOC_DAPM_SUPPLY_S("HV", 1, RT298_POWER_CTRL1,
12, 1, NULL, 0),
SND_SOC_DAPM_SUPPLY("VREF", RT298_POWER_CTRL1,
- 0, 1, rt298_vref_event, SND_SOC_DAPM_PRE_PMU),
+ 0, 1, NULL, 0),
SND_SOC_DAPM_SUPPLY_S("BG_MBIAS", 1, RT298_POWER_CTRL2,
1, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY_S("LDO1", 1, RT298_POWER_CTRL2,
@@ -934,18 +938,9 @@ static int rt298_set_bias_level(struct snd_soc_codec *codec,
}
break;
- case SND_SOC_BIAS_ON:
- mdelay(30);
- snd_soc_update_bits(codec,
- RT298_CBJ_CTRL1, 0x0400, 0x0400);
-
- break;
-
case SND_SOC_BIAS_STANDBY:
snd_soc_write(codec,
RT298_SET_AUDIO_POWER, AC_PWRST_D3);
- snd_soc_update_bits(codec,
- RT298_CBJ_CTRL1, 0x0400, 0x0000);
break;
default:
diff --git a/sound/soc/codecs/rt298.h b/sound/soc/codecs/rt298.h
index d66f8847b676..3638f3d61209 100644
--- a/sound/soc/codecs/rt298.h
+++ b/sound/soc/codecs/rt298.h
@@ -137,6 +137,7 @@
#define RT298_A_BIAS_CTRL2 0x02
#define RT298_POWER_CTRL1 0x03
#define RT298_A_BIAS_CTRL3 0x04
+#define RT298_D_FILTER_CTRL 0x05
#define RT298_POWER_CTRL2 0x08
#define RT298_I2S_CTRL1 0x09
#define RT298_I2S_CTRL2 0x0a
@@ -148,6 +149,7 @@
#define RT298_IRQ_CTRL 0x33
#define RT298_WIND_FILTER_CTRL 0x46
#define RT298_PLL_CTRL1 0x49
+#define RT298_VAD_CTRL 0x4e
#define RT298_CBJ_CTRL1 0x4f
#define RT298_CBJ_CTRL2 0x50
#define RT298_PLL_CTRL 0x63
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 60212266d5d1..da9483c1c6fb 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -1241,60 +1241,46 @@ static int rt5677_dmic_use_asrc(struct snd_soc_dapm_widget *source,
regmap_read(rt5677->regmap, RT5677_ASRC_5, &asrc_setting);
asrc_setting = (asrc_setting & RT5677_AD_STO1_CLK_SEL_MASK) >>
RT5677_AD_STO1_CLK_SEL_SFT;
- if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
- asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
- return 1;
break;
case 10:
regmap_read(rt5677->regmap, RT5677_ASRC_5, &asrc_setting);
asrc_setting = (asrc_setting & RT5677_AD_STO2_CLK_SEL_MASK) >>
RT5677_AD_STO2_CLK_SEL_SFT;
- if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
- asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
- return 1;
break;
case 9:
regmap_read(rt5677->regmap, RT5677_ASRC_5, &asrc_setting);
asrc_setting = (asrc_setting & RT5677_AD_STO3_CLK_SEL_MASK) >>
RT5677_AD_STO3_CLK_SEL_SFT;
- if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
- asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
- return 1;
break;
case 8:
regmap_read(rt5677->regmap, RT5677_ASRC_5, &asrc_setting);
asrc_setting = (asrc_setting & RT5677_AD_STO4_CLK_SEL_MASK) >>
RT5677_AD_STO4_CLK_SEL_SFT;
- if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
- asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
- return 1;
break;
case 7:
regmap_read(rt5677->regmap, RT5677_ASRC_6, &asrc_setting);
asrc_setting = (asrc_setting & RT5677_AD_MONOL_CLK_SEL_MASK) >>
RT5677_AD_MONOL_CLK_SEL_SFT;
- if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
- asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
- return 1;
break;
case 6:
regmap_read(rt5677->regmap, RT5677_ASRC_6, &asrc_setting);
asrc_setting = (asrc_setting & RT5677_AD_MONOR_CLK_SEL_MASK) >>
RT5677_AD_MONOR_CLK_SEL_SFT;
- if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
- asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
- return 1;
break;
default:
- break;
+ return 0;
}
+ if (asrc_setting >= RT5677_CLK_SEL_I2S1_ASRC &&
+ asrc_setting <= RT5677_CLK_SEL_I2S6_ASRC)
+ return 1;
+
return 0;
}
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index 39307ad41a34..b8d19b77bde9 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -4,6 +4,9 @@
* Copyright (C) 2015 Google, Inc.
* Copyright (c) 2013 Daniel Mack <zonque@gmail.com>
*
+ * TAS5721 support:
+ * Copyright (C) 2016 Petr Kulhavy, Barix AG <petr@barix.com>
+ *
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
@@ -57,6 +60,10 @@ static int tas571x_register_size(struct tas571x_private *priv, unsigned int reg)
case TAS571X_CH1_VOL_REG:
case TAS571X_CH2_VOL_REG:
return priv->chip->vol_reg_size;
+ case TAS571X_INPUT_MUX_REG:
+ case TAS571X_CH4_SRC_SELECT_REG:
+ case TAS571X_PWM_MUX_REG:
+ return 4;
default:
return 1;
}
@@ -167,6 +174,23 @@ static int tas571x_hw_params(struct snd_pcm_substream *substream,
TAS571X_SDI_FMT_MASK, val);
}
+static int tas571x_mute(struct snd_soc_dai *dai, int mute)
+{
+ struct snd_soc_codec *codec = dai->codec;
+ u8 sysctl2;
+ int ret;
+
+ sysctl2 = mute ? TAS571X_SYS_CTRL_2_SDN_MASK : 0;
+
+ ret = snd_soc_update_bits(codec,
+ TAS571X_SYS_CTRL_2_REG,
+ TAS571X_SYS_CTRL_2_SDN_MASK,
+ sysctl2);
+ usleep_range(1000, 2000);
+
+ return ret;
+}
+
static int tas571x_set_bias_level(struct snd_soc_codec *codec,
enum snd_soc_bias_level level)
{
@@ -214,6 +238,7 @@ static int tas571x_set_bias_level(struct snd_soc_codec *codec,
static const struct snd_soc_dai_ops tas571x_dai_ops = {
.set_fmt = tas571x_set_dai_fmt,
.hw_params = tas571x_hw_params,
+ .digital_mute = tas571x_mute,
};
static const char *const tas5711_supply_names[] = {
@@ -241,6 +266,26 @@ static const struct snd_kcontrol_new tas5711_controls[] = {
1, 1),
};
+static const struct regmap_range tas571x_readonly_regs_range[] = {
+ regmap_reg_range(TAS571X_CLK_CTRL_REG, TAS571X_DEV_ID_REG),
+};
+
+static const struct regmap_range tas571x_volatile_regs_range[] = {
+ regmap_reg_range(TAS571X_CLK_CTRL_REG, TAS571X_ERR_STATUS_REG),
+ regmap_reg_range(TAS571X_OSC_TRIM_REG, TAS571X_OSC_TRIM_REG),
+};
+
+static const struct regmap_access_table tas571x_write_regs = {
+ .no_ranges = tas571x_readonly_regs_range,
+ .n_no_ranges = ARRAY_SIZE(tas571x_readonly_regs_range),
+};
+
+static const struct regmap_access_table tas571x_volatile_regs = {
+ .yes_ranges = tas571x_volatile_regs_range,
+ .n_yes_ranges = ARRAY_SIZE(tas571x_volatile_regs_range),
+
+};
+
static const struct reg_default tas5711_reg_defaults[] = {
{ 0x04, 0x05 },
{ 0x05, 0x40 },
@@ -260,6 +305,8 @@ static const struct regmap_config tas5711_regmap_config = {
.reg_defaults = tas5711_reg_defaults,
.num_reg_defaults = ARRAY_SIZE(tas5711_reg_defaults),
.cache_type = REGCACHE_RBTREE,
+ .wr_table = &tas571x_write_regs,
+ .volatile_table = &tas571x_volatile_regs,
};
static const struct tas571x_chip tas5711_chip = {
@@ -314,6 +361,8 @@ static const struct regmap_config tas5717_regmap_config = {
.reg_defaults = tas5717_reg_defaults,
.num_reg_defaults = ARRAY_SIZE(tas5717_reg_defaults),
.cache_type = REGCACHE_RBTREE,
+ .wr_table = &tas571x_write_regs,
+ .volatile_table = &tas571x_volatile_regs,
};
/* This entry is reused for tas5719 as the software interface is identical. */
@@ -326,6 +375,77 @@ static const struct tas571x_chip tas5717_chip = {
.vol_reg_size = 2,
};
+static const char *const tas5721_supply_names[] = {
+ "AVDD",
+ "DVDD",
+ "DRVDD",
+ "PVDD",
+};
+
+static const struct snd_kcontrol_new tas5721_controls[] = {
+ SOC_SINGLE_TLV("Master Volume",
+ TAS571X_MVOL_REG,
+ 0, 0xff, 1, tas5711_volume_tlv),
+ SOC_DOUBLE_R_TLV("Speaker Volume",
+ TAS571X_CH1_VOL_REG,
+ TAS571X_CH2_VOL_REG,
+ 0, 0xff, 1, tas5711_volume_tlv),
+ SOC_DOUBLE("Speaker Switch",
+ TAS571X_SOFT_MUTE_REG,
+ TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
+ 1, 1),
+};
+
+static const struct reg_default tas5721_reg_defaults[] = {
+ {TAS571X_CLK_CTRL_REG, 0x6c},
+ {TAS571X_DEV_ID_REG, 0x00},
+ {TAS571X_ERR_STATUS_REG, 0x00},
+ {TAS571X_SYS_CTRL_1_REG, 0xa0},
+ {TAS571X_SDI_REG, 0x05},
+ {TAS571X_SYS_CTRL_2_REG, 0x40},
+ {TAS571X_SOFT_MUTE_REG, 0x00},
+ {TAS571X_MVOL_REG, 0xff},
+ {TAS571X_CH1_VOL_REG, 0x30},
+ {TAS571X_CH2_VOL_REG, 0x30},
+ {TAS571X_CH3_VOL_REG, 0x30},
+ {TAS571X_VOL_CFG_REG, 0x91},
+ {TAS571X_MODULATION_LIMIT_REG, 0x02},
+ {TAS571X_IC_DELAY_CH1_REG, 0xac},
+ {TAS571X_IC_DELAY_CH2_REG, 0x54},
+ {TAS571X_IC_DELAY_CH3_REG, 0xac},
+ {TAS571X_IC_DELAY_CH4_REG, 0x54},
+ {TAS571X_PWM_CH_SDN_GROUP_REG, 0x30},
+ {TAS571X_START_STOP_PERIOD_REG, 0x0f},
+ {TAS571X_OSC_TRIM_REG, 0x82},
+ {TAS571X_BKND_ERR_REG, 0x02},
+ {TAS571X_INPUT_MUX_REG, 0x17772},
+ {TAS571X_CH4_SRC_SELECT_REG, 0x4303},
+ {TAS571X_PWM_MUX_REG, 0x1021345},
+};
+
+static const struct regmap_config tas5721_regmap_config = {
+ .reg_bits = 8,
+ .val_bits = 32,
+ .max_register = 0xff,
+ .reg_read = tas571x_reg_read,
+ .reg_write = tas571x_reg_write,
+ .reg_defaults = tas5721_reg_defaults,
+ .num_reg_defaults = ARRAY_SIZE(tas5721_reg_defaults),
+ .cache_type = REGCACHE_RBTREE,
+ .wr_table = &tas571x_write_regs,
+ .volatile_table = &tas571x_volatile_regs,
+};
+
+
+static const struct tas571x_chip tas5721_chip = {
+ .supply_names = tas5721_supply_names,
+ .num_supply_names = ARRAY_SIZE(tas5721_supply_names),
+ .controls = tas5711_controls,
+ .num_controls = ARRAY_SIZE(tas5711_controls),
+ .regmap_config = &tas5721_regmap_config,
+ .vol_reg_size = 1,
+};
+
static const struct snd_soc_dapm_widget tas571x_dapm_widgets[] = {
SND_SOC_DAPM_DAC("DACL", NULL, SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_DAC("DACR", NULL, SND_SOC_NOPM, 0, 0),
@@ -386,11 +506,10 @@ static int tas571x_i2c_probe(struct i2c_client *client,
i2c_set_clientdata(client, priv);
of_id = of_match_device(tas571x_of_match, dev);
- if (!of_id) {
- dev_err(dev, "Unknown device type\n");
- return -EINVAL;
- }
- priv->chip = of_id->data;
+ if (of_id)
+ priv->chip = of_id->data;
+ else
+ priv->chip = (void *) id->driver_data;
priv->mclk = devm_clk_get(dev, "mclk");
if (IS_ERR(priv->mclk) && PTR_ERR(priv->mclk) != -ENOENT) {
@@ -445,10 +564,6 @@ static int tas571x_i2c_probe(struct i2c_client *client,
if (ret)
return ret;
- ret = regmap_update_bits(priv->regmap, TAS571X_SYS_CTRL_2_REG,
- TAS571X_SYS_CTRL_2_SDN_MASK, 0);
- if (ret)
- return ret;
memcpy(&priv->codec_driver, &tas571x_codec, sizeof(priv->codec_driver));
priv->codec_driver.controls = priv->chip->controls;
@@ -486,14 +601,16 @@ static const struct of_device_id tas571x_of_match[] = {
{ .compatible = "ti,tas5711", .data = &tas5711_chip, },
{ .compatible = "ti,tas5717", .data = &tas5717_chip, },
{ .compatible = "ti,tas5719", .data = &tas5717_chip, },
+ { .compatible = "ti,tas5721", .data = &tas5721_chip, },
{ }
};
MODULE_DEVICE_TABLE(of, tas571x_of_match);
static const struct i2c_device_id tas571x_i2c_id[] = {
- { "tas5711", 0 },
- { "tas5717", 0 },
- { "tas5719", 0 },
+ { "tas5711", (kernel_ulong_t) &tas5711_chip },
+ { "tas5717", (kernel_ulong_t) &tas5717_chip },
+ { "tas5719", (kernel_ulong_t) &tas5717_chip },
+ { "tas5721", (kernel_ulong_t) &tas5721_chip },
{ }
};
MODULE_DEVICE_TABLE(i2c, tas571x_i2c_id);
diff --git a/sound/soc/codecs/tas571x.h b/sound/soc/codecs/tas571x.h
index 0aee471232cd..cf800c364f0f 100644
--- a/sound/soc/codecs/tas571x.h
+++ b/sound/soc/codecs/tas571x.h
@@ -13,6 +13,10 @@
#define _TAS571X_H
/* device registers */
+#define TAS571X_CLK_CTRL_REG 0x00
+#define TAS571X_DEV_ID_REG 0x01
+#define TAS571X_ERR_STATUS_REG 0x02
+#define TAS571X_SYS_CTRL_1_REG 0x03
#define TAS571X_SDI_REG 0x04
#define TAS571X_SDI_FMT_MASK 0x0f
@@ -27,7 +31,25 @@
#define TAS571X_MVOL_REG 0x07
#define TAS571X_CH1_VOL_REG 0x08
#define TAS571X_CH2_VOL_REG 0x09
+#define TAS571X_CH3_VOL_REG 0x0a
+#define TAS571X_VOL_CFG_REG 0x0e
+#define TAS571X_MODULATION_LIMIT_REG 0x10
+#define TAS571X_IC_DELAY_CH1_REG 0x11
+#define TAS571X_IC_DELAY_CH2_REG 0x12
+#define TAS571X_IC_DELAY_CH3_REG 0x13
+#define TAS571X_IC_DELAY_CH4_REG 0x14
+#define TAS571X_PWM_CH_SDN_GROUP_REG 0x19 /* N/A on TAS5717, TAS5719 */
+#define TAS571X_PWM_CH1_SDN_MASK (1<<0)
+#define TAS571X_PWM_CH2_SDN_SHIFT (1<<1)
+#define TAS571X_PWM_CH3_SDN_SHIFT (1<<2)
+#define TAS571X_PWM_CH4_SDN_SHIFT (1<<3)
+
+#define TAS571X_START_STOP_PERIOD_REG 0x1a
#define TAS571X_OSC_TRIM_REG 0x1b
+#define TAS571X_BKND_ERR_REG 0x1c
+#define TAS571X_INPUT_MUX_REG 0x20
+#define TAS571X_CH4_SRC_SELECT_REG 0x21
+#define TAS571X_PWM_MUX_REG 0x25
#endif /* _TAS571X_H */
diff --git a/sound/soc/codecs/tas5720.c b/sound/soc/codecs/tas5720.c
new file mode 100644
index 000000000000..f54fb46b77c2
--- /dev/null
+++ b/sound/soc/codecs/tas5720.c
@@ -0,0 +1,620 @@
+/*
+ * tas5720.c - ALSA SoC Texas Instruments TAS5720 Mono Audio Amplifier
+ *
+ * Copyright (C)2015-2016 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Andreas Dannenberg <dannenberg@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/regulator/consumer.h>
+#include <linux/delay.h>
+
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/tlv.h>
+
+#include "tas5720.h"
+
+/* Define how often to check (and clear) the fault status register (in ms) */
+#define TAS5720_FAULT_CHECK_INTERVAL 200
+
+static const char * const tas5720_supply_names[] = {
+ "dvdd", /* Digital power supply. Connect to 3.3-V supply. */
+ "pvdd", /* Class-D amp and analog power supply (connected). */
+};
+
+#define TAS5720_NUM_SUPPLIES ARRAY_SIZE(tas5720_supply_names)
+
+struct tas5720_data {
+ struct snd_soc_codec *codec;
+ struct regmap *regmap;
+ struct i2c_client *tas5720_client;
+ struct regulator_bulk_data supplies[TAS5720_NUM_SUPPLIES];
+ struct delayed_work fault_check_work;
+ unsigned int last_fault;
+};
+
+static int tas5720_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct snd_soc_dai *dai)
+{
+ struct snd_soc_codec *codec = dai->codec;
+ unsigned int rate = params_rate(params);
+ bool ssz_ds;
+ int ret;
+
+ switch (rate) {
+ case 44100:
+ case 48000:
+ ssz_ds = false;
+ break;
+ case 88200:
+ case 96000:
+ ssz_ds = true;
+ break;
+ default:
+ dev_err(codec->dev, "unsupported sample rate: %u\n", rate);
+ return -EINVAL;
+ }
+
+ ret = snd_soc_update_bits(codec, TAS5720_DIGITAL_CTRL1_REG,
+ TAS5720_SSZ_DS, ssz_ds);
+ if (ret < 0) {
+ dev_err(codec->dev, "error setting sample rate: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int tas5720_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+ struct snd_soc_codec *codec = dai->codec;
+ u8 serial_format;
+ int ret;
+
+ if ((fmt & SND_SOC_DAIFMT_MASTER_MASK) != SND_SOC_DAIFMT_CBS_CFS) {
+ dev_vdbg(codec->dev, "DAI Format master is not found\n");
+ return -EINVAL;
+ }
+
+ switch (fmt & (SND_SOC_DAIFMT_FORMAT_MASK |
+ SND_SOC_DAIFMT_INV_MASK)) {
+ case (SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF):
+ /* 1st data bit occur one BCLK cycle after the frame sync */
+ serial_format = TAS5720_SAIF_I2S;
+ break;
+ case (SND_SOC_DAIFMT_DSP_A | SND_SOC_DAIFMT_NB_NF):
+ /*
+ * Note that although the TAS5720 does not have a dedicated DSP
+ * mode it doesn't care about the LRCLK duty cycle during TDM
+ * operation. Therefore we can use the device's I2S mode with
+ * its delaying of the 1st data bit to receive DSP_A formatted
+ * data. See device datasheet for additional details.
+ */
+ serial_format = TAS5720_SAIF_I2S;
+ break;
+ case (SND_SOC_DAIFMT_DSP_B | SND_SOC_DAIFMT_NB_NF):
+ /*
+ * Similar to DSP_A, we can use the fact that the TAS5720 does
+ * not care about the LRCLK duty cycle during TDM to receive
+ * DSP_B formatted data in LEFTJ mode (no delaying of the 1st
+ * data bit).
+ */
+ serial_format = TAS5720_SAIF_LEFTJ;
+ break;
+ case (SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_NB_NF):
+ /* No delay after the frame sync */
+ serial_format = TAS5720_SAIF_LEFTJ;
+ break;
+ default:
+ dev_vdbg(codec->dev, "DAI Format is not found\n");
+ return -EINVAL;
+ }
+
+ ret = snd_soc_update_bits(codec, TAS5720_DIGITAL_CTRL1_REG,
+ TAS5720_SAIF_FORMAT_MASK,
+ serial_format);
+ if (ret < 0) {
+ dev_err(codec->dev, "error setting SAIF format: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int tas5720_set_dai_tdm_slot(struct snd_soc_dai *dai,
+ unsigned int tx_mask, unsigned int rx_mask,
+ int slots, int slot_width)
+{
+ struct snd_soc_codec *codec = dai->codec;
+ unsigned int first_slot;
+ int ret;
+
+ if (!tx_mask) {
+ dev_err(codec->dev, "tx masks must not be 0\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Determine the first slot that is being requested. We will only
+ * use the first slot that is found since the TAS5720 is a mono
+ * amplifier.
+ */
+ first_slot = __ffs(tx_mask);
+
+ if (first_slot > 7) {
+ dev_err(codec->dev, "slot selection out of bounds (%u)\n",
+ first_slot);
+ return -EINVAL;
+ }
+
+ /* Enable manual TDM slot selection (instead of I2C ID based) */
+ ret = snd_soc_update_bits(codec, TAS5720_DIGITAL_CTRL1_REG,
+ TAS5720_TDM_CFG_SRC, TAS5720_TDM_CFG_SRC);
+ if (ret < 0)
+ goto error_snd_soc_update_bits;
+
+ /* Configure the TDM slot to process audio from */
+ ret = snd_soc_update_bits(codec, TAS5720_DIGITAL_CTRL2_REG,
+ TAS5720_TDM_SLOT_SEL_MASK, first_slot);
+ if (ret < 0)
+ goto error_snd_soc_update_bits;
+
+ return 0;
+
+error_snd_soc_update_bits:
+ dev_err(codec->dev, "error configuring TDM mode: %d\n", ret);
+ return ret;
+}
+
+static int tas5720_mute(struct snd_soc_dai *dai, int mute)
+{
+ struct snd_soc_codec *codec = dai->codec;
+ int ret;
+
+ ret = snd_soc_update_bits(codec, TAS5720_DIGITAL_CTRL2_REG,
+ TAS5720_MUTE, mute ? TAS5720_MUTE : 0);
+ if (ret < 0) {
+ dev_err(codec->dev, "error (un-)muting device: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void tas5720_fault_check_work(struct work_struct *work)
+{
+ struct tas5720_data *tas5720 = container_of(work, struct tas5720_data,
+ fault_check_work.work);
+ struct device *dev = tas5720->codec->dev;
+ unsigned int curr_fault;
+ int ret;
+
+ ret = regmap_read(tas5720->regmap, TAS5720_FAULT_REG, &curr_fault);
+ if (ret < 0) {
+ dev_err(dev, "failed to read FAULT register: %d\n", ret);
+ goto out;
+ }
+
+ /* Check/handle all errors except SAIF clock errors */
+ curr_fault &= TAS5720_OCE | TAS5720_DCE | TAS5720_OTE;
+
+ /*
+ * Only flag errors once for a given occurrence. This is needed as
+ * the TAS5720 will take time clearing the fault condition internally
+ * during which we don't want to bombard the system with the same
+ * error message over and over.
+ */
+ if ((curr_fault & TAS5720_OCE) && !(tas5720->last_fault & TAS5720_OCE))
+ dev_crit(dev, "experienced an over current hardware fault\n");
+
+ if ((curr_fault & TAS5720_DCE) && !(tas5720->last_fault & TAS5720_DCE))
+ dev_crit(dev, "experienced a DC detection fault\n");
+
+ if ((curr_fault & TAS5720_OTE) && !(tas5720->last_fault & TAS5720_OTE))
+ dev_crit(dev, "experienced an over temperature fault\n");
+
+ /* Store current fault value so we can detect any changes next time */
+ tas5720->last_fault = curr_fault;
+
+ if (!curr_fault)
+ goto out;
+
+ /*
+ * Periodically toggle SDZ (shutdown bit) H->L->H to clear any latching
+ * faults as long as a fault condition persists. Always going through
+ * the full sequence no matter the first return value to minimizes
+ * chances for the device to end up in shutdown mode.
+ */
+ ret = regmap_write_bits(tas5720->regmap, TAS5720_POWER_CTRL_REG,
+ TAS5720_SDZ, 0);
+ if (ret < 0)
+ dev_err(dev, "failed to write POWER_CTRL register: %d\n", ret);
+
+ ret = regmap_write_bits(tas5720->regmap, TAS5720_POWER_CTRL_REG,
+ TAS5720_SDZ, TAS5720_SDZ);
+ if (ret < 0)
+ dev_err(dev, "failed to write POWER_CTRL register: %d\n", ret);
+
+out:
+ /* Schedule the next fault check at the specified interval */
+ schedule_delayed_work(&tas5720->fault_check_work,
+ msecs_to_jiffies(TAS5720_FAULT_CHECK_INTERVAL));
+}
+
+static int tas5720_codec_probe(struct snd_soc_codec *codec)
+{
+ struct tas5720_data *tas5720 = snd_soc_codec_get_drvdata(codec);
+ unsigned int device_id;
+ int ret;
+
+ tas5720->codec = codec;
+
+ ret = regulator_bulk_enable(ARRAY_SIZE(tas5720->supplies),
+ tas5720->supplies);
+ if (ret != 0) {
+ dev_err(codec->dev, "failed to enable supplies: %d\n", ret);
+ return ret;
+ }
+
+ ret = regmap_read(tas5720->regmap, TAS5720_DEVICE_ID_REG, &device_id);
+ if (ret < 0) {
+ dev_err(codec->dev, "failed to read device ID register: %d\n",
+ ret);
+ goto probe_fail;
+ }
+
+ if (device_id != TAS5720_DEVICE_ID) {
+ dev_err(codec->dev, "wrong device ID. expected: %u read: %u\n",
+ TAS5720_DEVICE_ID, device_id);
+ ret = -ENODEV;
+ goto probe_fail;
+ }
+
+ /* Set device to mute */
+ ret = snd_soc_update_bits(codec, TAS5720_DIGITAL_CTRL2_REG,
+ TAS5720_MUTE, TAS5720_MUTE);
+ if (ret < 0)
+ goto error_snd_soc_update_bits;
+
+ /*
+ * Enter shutdown mode - our default when not playing audio - to
+ * minimize current consumption. On the TAS5720 there is no real down
+ * side doing so as all device registers are preserved and the wakeup
+ * of the codec is rather quick which we do using a dapm widget.
+ */
+ ret = snd_soc_update_bits(codec, TAS5720_POWER_CTRL_REG,
+ TAS5720_SDZ, 0);
+ if (ret < 0)
+ goto error_snd_soc_update_bits;
+
+ INIT_DELAYED_WORK(&tas5720->fault_check_work, tas5720_fault_check_work);
+
+ return 0;
+
+error_snd_soc_update_bits:
+ dev_err(codec->dev, "error configuring device registers: %d\n", ret);
+
+probe_fail:
+ regulator_bulk_disable(ARRAY_SIZE(tas5720->supplies),
+ tas5720->supplies);
+ return ret;
+}
+
+static int tas5720_codec_remove(struct snd_soc_codec *codec)
+{
+ struct tas5720_data *tas5720 = snd_soc_codec_get_drvdata(codec);
+ int ret;
+
+ cancel_delayed_work_sync(&tas5720->fault_check_work);
+
+ ret = regulator_bulk_disable(ARRAY_SIZE(tas5720->supplies),
+ tas5720->supplies);
+ if (ret < 0)
+ dev_err(codec->dev, "failed to disable supplies: %d\n", ret);
+
+ return ret;
+};
+
+static int tas5720_dac_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+ struct tas5720_data *tas5720 = snd_soc_codec_get_drvdata(codec);
+ int ret;
+
+ if (event & SND_SOC_DAPM_POST_PMU) {
+ /* Take TAS5720 out of shutdown mode */
+ ret = snd_soc_update_bits(codec, TAS5720_POWER_CTRL_REG,
+ TAS5720_SDZ, TAS5720_SDZ);
+ if (ret < 0) {
+ dev_err(codec->dev, "error waking codec: %d\n", ret);
+ return ret;
+ }
+
+ /*
+ * Observe codec shutdown-to-active time. The datasheet only
+ * lists a nominal value however just use-it as-is without
+ * additional padding to minimize the delay introduced in
+ * starting to play audio (actually there is other setup done
+ * by the ASoC framework that will provide additional delays,
+ * so we should always be safe).
+ */
+ msleep(25);
+
+ /* Turn on TAS5720 periodic fault checking/handling */
+ tas5720->last_fault = 0;
+ schedule_delayed_work(&tas5720->fault_check_work,
+ msecs_to_jiffies(TAS5720_FAULT_CHECK_INTERVAL));
+ } else if (event & SND_SOC_DAPM_PRE_PMD) {
+ /* Disable TAS5720 periodic fault checking/handling */
+ cancel_delayed_work_sync(&tas5720->fault_check_work);
+
+ /* Place TAS5720 in shutdown mode to minimize current draw */
+ ret = snd_soc_update_bits(codec, TAS5720_POWER_CTRL_REG,
+ TAS5720_SDZ, 0);
+ if (ret < 0) {
+ dev_err(codec->dev, "error shutting down codec: %d\n",
+ ret);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_PM
+static int tas5720_suspend(struct snd_soc_codec *codec)
+{
+ struct tas5720_data *tas5720 = snd_soc_codec_get_drvdata(codec);
+ int ret;
+
+ regcache_cache_only(tas5720->regmap, true);
+ regcache_mark_dirty(tas5720->regmap);
+
+ ret = regulator_bulk_disable(ARRAY_SIZE(tas5720->supplies),
+ tas5720->supplies);
+ if (ret < 0)
+ dev_err(codec->dev, "failed to disable supplies: %d\n", ret);
+
+ return ret;
+}
+
+static int tas5720_resume(struct snd_soc_codec *codec)
+{
+ struct tas5720_data *tas5720 = snd_soc_codec_get_drvdata(codec);
+ int ret;
+
+ ret = regulator_bulk_enable(ARRAY_SIZE(tas5720->supplies),
+ tas5720->supplies);
+ if (ret < 0) {
+ dev_err(codec->dev, "failed to enable supplies: %d\n", ret);
+ return ret;
+ }
+
+ regcache_cache_only(tas5720->regmap, false);
+
+ ret = regcache_sync(tas5720->regmap);
+ if (ret < 0) {
+ dev_err(codec->dev, "failed to sync regcache: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+#else
+#define tas5720_suspend NULL
+#define tas5720_resume NULL
+#endif
+
+static bool tas5720_is_volatile_reg(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case TAS5720_DEVICE_ID_REG:
+ case TAS5720_FAULT_REG:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static const struct regmap_config tas5720_regmap_config = {
+ .reg_bits = 8,
+ .val_bits = 8,
+
+ .max_register = TAS5720_MAX_REG,
+ .cache_type = REGCACHE_RBTREE,
+ .volatile_reg = tas5720_is_volatile_reg,
+};
+
+/*
+ * DAC analog gain. There are four discrete values to select from, ranging
+ * from 19.2 dB to 26.3dB.
+ */
+static const DECLARE_TLV_DB_RANGE(dac_analog_tlv,
+ 0x0, 0x0, TLV_DB_SCALE_ITEM(1920, 0, 0),
+ 0x1, 0x1, TLV_DB_SCALE_ITEM(2070, 0, 0),
+ 0x2, 0x2, TLV_DB_SCALE_ITEM(2350, 0, 0),
+ 0x3, 0x3, TLV_DB_SCALE_ITEM(2630, 0, 0),
+);
+
+/*
+ * DAC digital volumes. From -103.5 to 24 dB in 0.5 dB steps. Note that
+ * setting the gain below -100 dB (register value <0x7) is effectively a MUTE
+ * as per device datasheet.
+ */
+static DECLARE_TLV_DB_SCALE(dac_tlv, -10350, 50, 0);
+
+static const struct snd_kcontrol_new tas5720_snd_controls[] = {
+ SOC_SINGLE_TLV("Speaker Driver Playback Volume",
+ TAS5720_VOLUME_CTRL_REG, 0, 0xff, 0, dac_tlv),
+ SOC_SINGLE_TLV("Speaker Driver Analog Gain", TAS5720_ANALOG_CTRL_REG,
+ TAS5720_ANALOG_GAIN_SHIFT, 3, 0, dac_analog_tlv),
+};
+
+static const struct snd_soc_dapm_widget tas5720_dapm_widgets[] = {
+ SND_SOC_DAPM_AIF_IN("DAC IN", "Playback", 0, SND_SOC_NOPM, 0, 0),
+ SND_SOC_DAPM_DAC_E("DAC", NULL, SND_SOC_NOPM, 0, 0, tas5720_dac_event,
+ SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+ SND_SOC_DAPM_OUTPUT("OUT")
+};
+
+static const struct snd_soc_dapm_route tas5720_audio_map[] = {
+ { "DAC", NULL, "DAC IN" },
+ { "OUT", NULL, "DAC" },
+};
+
+static struct snd_soc_codec_driver soc_codec_dev_tas5720 = {
+ .probe = tas5720_codec_probe,
+ .remove = tas5720_codec_remove,
+ .suspend = tas5720_suspend,
+ .resume = tas5720_resume,
+
+ .controls = tas5720_snd_controls,
+ .num_controls = ARRAY_SIZE(tas5720_snd_controls),
+ .dapm_widgets = tas5720_dapm_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(tas5720_dapm_widgets),
+ .dapm_routes = tas5720_audio_map,
+ .num_dapm_routes = ARRAY_SIZE(tas5720_audio_map),
+};
+
+/* PCM rates supported by the TAS5720 driver */
+#define TAS5720_RATES (SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000 |\
+ SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000)
+
+/* Formats supported by TAS5720 driver */
+#define TAS5720_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S18_3LE |\
+ SNDRV_PCM_FMTBIT_S20_3LE | SNDRV_PCM_FMTBIT_S24_LE)
+
+static struct snd_soc_dai_ops tas5720_speaker_dai_ops = {
+ .hw_params = tas5720_hw_params,
+ .set_fmt = tas5720_set_dai_fmt,
+ .set_tdm_slot = tas5720_set_dai_tdm_slot,
+ .digital_mute = tas5720_mute,
+};
+
+/*
+ * TAS5720 DAI structure
+ *
+ * Note that were are advertising .playback.channels_max = 2 despite this being
+ * a mono amplifier. The reason for that is that some serial ports such as TI's
+ * McASP module have a minimum number of channels (2) that they can output.
+ * Advertising more channels than we have will allow us to interface with such
+ * a serial port without really any negative side effects as the TAS5720 will
+ * simply ignore any extra channel(s) asides from the one channel that is
+ * configured to be played back.
+ */
+static struct snd_soc_dai_driver tas5720_dai[] = {
+ {
+ .name = "tas5720-amplifier",
+ .playback = {
+ .stream_name = "Playback",
+ .channels_min = 1,
+ .channels_max = 2,
+ .rates = TAS5720_RATES,
+ .formats = TAS5720_FORMATS,
+ },
+ .ops = &tas5720_speaker_dai_ops,
+ },
+};
+
+static int tas5720_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ struct device *dev = &client->dev;
+ struct tas5720_data *data;
+ int ret;
+ int i;
+
+ data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->tas5720_client = client;
+ data->regmap = devm_regmap_init_i2c(client, &tas5720_regmap_config);
+ if (IS_ERR(data->regmap)) {
+ ret = PTR_ERR(data->regmap);
+ dev_err(dev, "failed to allocate register map: %d\n", ret);
+ return ret;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(data->supplies); i++)
+ data->supplies[i].supply = tas5720_supply_names[i];
+
+ ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(data->supplies),
+ data->supplies);
+ if (ret != 0) {
+ dev_err(dev, "failed to request supplies: %d\n", ret);
+ return ret;
+ }
+
+ dev_set_drvdata(dev, data);
+
+ ret = snd_soc_register_codec(&client->dev,
+ &soc_codec_dev_tas5720,
+ tas5720_dai, ARRAY_SIZE(tas5720_dai));
+ if (ret < 0) {
+ dev_err(dev, "failed to register codec: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int tas5720_remove(struct i2c_client *client)
+{
+ struct device *dev = &client->dev;
+
+ snd_soc_unregister_codec(dev);
+
+ return 0;
+}
+
+static const struct i2c_device_id tas5720_id[] = {
+ { "tas5720", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(i2c, tas5720_id);
+
+#if IS_ENABLED(CONFIG_OF)
+static const struct of_device_id tas5720_of_match[] = {
+ { .compatible = "ti,tas5720", },
+ { },
+};
+MODULE_DEVICE_TABLE(of, tas5720_of_match);
+#endif
+
+static struct i2c_driver tas5720_i2c_driver = {
+ .driver = {
+ .name = "tas5720",
+ .of_match_table = of_match_ptr(tas5720_of_match),
+ },
+ .probe = tas5720_probe,
+ .remove = tas5720_remove,
+ .id_table = tas5720_id,
+};
+
+module_i2c_driver(tas5720_i2c_driver);
+
+MODULE_AUTHOR("Andreas Dannenberg <dannenberg@ti.com>");
+MODULE_DESCRIPTION("TAS5720 Audio amplifier driver");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tas5720.h b/sound/soc/codecs/tas5720.h
new file mode 100644
index 000000000000..3d077c779b12
--- /dev/null
+++ b/sound/soc/codecs/tas5720.h
@@ -0,0 +1,90 @@
+/*
+ * tas5720.h - ALSA SoC Texas Instruments TAS5720 Mono Audio Amplifier
+ *
+ * Copyright (C)2015-2016 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Andreas Dannenberg <dannenberg@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef __TAS5720_H__
+#define __TAS5720_H__
+
+/* Register Address Map */
+#define TAS5720_DEVICE_ID_REG 0x00
+#define TAS5720_POWER_CTRL_REG 0x01
+#define TAS5720_DIGITAL_CTRL1_REG 0x02
+#define TAS5720_DIGITAL_CTRL2_REG 0x03
+#define TAS5720_VOLUME_CTRL_REG 0x04
+#define TAS5720_ANALOG_CTRL_REG 0x06
+#define TAS5720_FAULT_REG 0x08
+#define TAS5720_DIGITAL_CLIP2_REG 0x10
+#define TAS5720_DIGITAL_CLIP1_REG 0x11
+#define TAS5720_MAX_REG TAS5720_DIGITAL_CLIP1_REG
+
+/* TAS5720_DEVICE_ID_REG */
+#define TAS5720_DEVICE_ID 0x01
+
+/* TAS5720_POWER_CTRL_REG */
+#define TAS5720_DIG_CLIP_MASK GENMASK(7, 2)
+#define TAS5720_SLEEP BIT(1)
+#define TAS5720_SDZ BIT(0)
+
+/* TAS5720_DIGITAL_CTRL1_REG */
+#define TAS5720_HPF_BYPASS BIT(7)
+#define TAS5720_TDM_CFG_SRC BIT(6)
+#define TAS5720_SSZ_DS BIT(3)
+#define TAS5720_SAIF_RIGHTJ_24BIT (0x0)
+#define TAS5720_SAIF_RIGHTJ_20BIT (0x1)
+#define TAS5720_SAIF_RIGHTJ_18BIT (0x2)
+#define TAS5720_SAIF_RIGHTJ_16BIT (0x3)
+#define TAS5720_SAIF_I2S (0x4)
+#define TAS5720_SAIF_LEFTJ (0x5)
+#define TAS5720_SAIF_FORMAT_MASK GENMASK(2, 0)
+
+/* TAS5720_DIGITAL_CTRL2_REG */
+#define TAS5720_MUTE BIT(4)
+#define TAS5720_TDM_SLOT_SEL_MASK GENMASK(2, 0)
+
+/* TAS5720_ANALOG_CTRL_REG */
+#define TAS5720_PWM_RATE_6_3_FSYNC (0x0 << 4)
+#define TAS5720_PWM_RATE_8_4_FSYNC (0x1 << 4)
+#define TAS5720_PWM_RATE_10_5_FSYNC (0x2 << 4)
+#define TAS5720_PWM_RATE_12_6_FSYNC (0x3 << 4)
+#define TAS5720_PWM_RATE_14_7_FSYNC (0x4 << 4)
+#define TAS5720_PWM_RATE_16_8_FSYNC (0x5 << 4)
+#define TAS5720_PWM_RATE_20_10_FSYNC (0x6 << 4)
+#define TAS5720_PWM_RATE_24_12_FSYNC (0x7 << 4)
+#define TAS5720_PWM_RATE_MASK GENMASK(6, 4)
+#define TAS5720_ANALOG_GAIN_19_2DBV (0x0 << 2)
+#define TAS5720_ANALOG_GAIN_20_7DBV (0x1 << 2)
+#define TAS5720_ANALOG_GAIN_23_5DBV (0x2 << 2)
+#define TAS5720_ANALOG_GAIN_26_3DBV (0x3 << 2)
+#define TAS5720_ANALOG_GAIN_MASK GENMASK(3, 2)
+#define TAS5720_ANALOG_GAIN_SHIFT (0x2)
+
+/* TAS5720_FAULT_REG */
+#define TAS5720_OC_THRESH_100PCT (0x0 << 4)
+#define TAS5720_OC_THRESH_75PCT (0x1 << 4)
+#define TAS5720_OC_THRESH_50PCT (0x2 << 4)
+#define TAS5720_OC_THRESH_25PCT (0x3 << 4)
+#define TAS5720_OC_THRESH_MASK GENMASK(5, 4)
+#define TAS5720_CLKE BIT(3)
+#define TAS5720_OCE BIT(2)
+#define TAS5720_DCE BIT(1)
+#define TAS5720_OTE BIT(0)
+#define TAS5720_FAULT_MASK GENMASK(3, 0)
+
+/* TAS5720_DIGITAL_CLIP1_REG */
+#define TAS5720_CLIP1_MASK GENMASK(7, 2)
+#define TAS5720_CLIP1_SHIFT (0x2)
+
+#endif /* __TAS5720_H__ */
diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c
index ee4def4f819f..3c5e1df01c19 100644
--- a/sound/soc/codecs/tlv320aic31xx.c
+++ b/sound/soc/codecs/tlv320aic31xx.c
@@ -28,6 +28,7 @@
#include <linux/i2c.h>
#include <linux/gpio.h>
#include <linux/regulator/consumer.h>
+#include <linux/acpi.h>
#include <linux/of.h>
#include <linux/of_gpio.h>
#include <linux/slab.h>
@@ -1280,10 +1281,19 @@ static const struct i2c_device_id aic31xx_i2c_id[] = {
};
MODULE_DEVICE_TABLE(i2c, aic31xx_i2c_id);
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id aic31xx_acpi_match[] = {
+ { "10TI3100", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, aic31xx_acpi_match);
+#endif
+
static struct i2c_driver aic31xx_i2c_driver = {
.driver = {
.name = "tlv320aic31xx-codec",
.of_match_table = of_match_ptr(tlv320aic31xx_of_match),
+ .acpi_match_table = ACPI_PTR(aic31xx_acpi_match),
},
.probe = aic31xx_i2c_probe,
.remove = aic31xx_i2c_remove,
diff --git a/sound/soc/codecs/tlv320aic32x4-i2c.c b/sound/soc/codecs/tlv320aic32x4-i2c.c
new file mode 100644
index 000000000000..59606cf3008f
--- /dev/null
+++ b/sound/soc/codecs/tlv320aic32x4-i2c.c
@@ -0,0 +1,74 @@
+/*
+ * linux/sound/soc/codecs/tlv320aic32x4-i2c.c
+ *
+ * Copyright 2011 NW Digital Radio
+ *
+ * Author: Jeremy McDermond <nh6z@nh6z.net>
+ *
+ * Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+
+#include "tlv320aic32x4.h"
+
+static int aic32x4_i2c_probe(struct i2c_client *i2c,
+ const struct i2c_device_id *id)
+{
+ struct regmap *regmap;
+ struct regmap_config config;
+
+ config = aic32x4_regmap_config;
+ config.reg_bits = 8;
+ config.val_bits = 8;
+
+ regmap = devm_regmap_init_i2c(i2c, &config);
+ return aic32x4_probe(&i2c->dev, regmap);
+}
+
+static int aic32x4_i2c_remove(struct i2c_client *i2c)
+{
+ return aic32x4_remove(&i2c->dev);
+}
+
+static const struct i2c_device_id aic32x4_i2c_id[] = {
+ { "tlv320aic32x4", 0 },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, aic32x4_i2c_id);
+
+static const struct of_device_id aic32x4_of_id[] = {
+ { .compatible = "ti,tlv320aic32x4", },
+ { /* senitel */ }
+};
+MODULE_DEVICE_TABLE(of, aic32x4_of_id);
+
+static struct i2c_driver aic32x4_i2c_driver = {
+ .driver = {
+ .name = "tlv320aic32x4",
+ .of_match_table = aic32x4_of_id,
+ },
+ .probe = aic32x4_i2c_probe,
+ .remove = aic32x4_i2c_remove,
+ .id_table = aic32x4_i2c_id,
+};
+
+module_i2c_driver(aic32x4_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver I2C");
+MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tlv320aic32x4-spi.c b/sound/soc/codecs/tlv320aic32x4-spi.c
new file mode 100644
index 000000000000..724fcdd491b2
--- /dev/null
+++ b/sound/soc/codecs/tlv320aic32x4-spi.c
@@ -0,0 +1,76 @@
+/*
+ * linux/sound/soc/codecs/tlv320aic32x4-spi.c
+ *
+ * Copyright 2011 NW Digital Radio
+ *
+ * Author: Jeremy McDermond <nh6z@nh6z.net>
+ *
+ * Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/spi/spi.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+
+#include "tlv320aic32x4.h"
+
+static int aic32x4_spi_probe(struct spi_device *spi)
+{
+ struct regmap *regmap;
+ struct regmap_config config;
+
+ config = aic32x4_regmap_config;
+ config.reg_bits = 7;
+ config.pad_bits = 1;
+ config.val_bits = 8;
+ config.read_flag_mask = 0x01;
+
+ regmap = devm_regmap_init_spi(spi, &config);
+ return aic32x4_probe(&spi->dev, regmap);
+}
+
+static int aic32x4_spi_remove(struct spi_device *spi)
+{
+ return aic32x4_remove(&spi->dev);
+}
+
+static const struct spi_device_id aic32x4_spi_id[] = {
+ { "tlv320aic32x4", 0 },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(spi, aic32x4_spi_id);
+
+static const struct of_device_id aic32x4_of_id[] = {
+ { .compatible = "ti,tlv320aic32x4", },
+ { /* senitel */ }
+};
+MODULE_DEVICE_TABLE(of, aic32x4_of_id);
+
+static struct spi_driver aic32x4_spi_driver = {
+ .driver = {
+ .name = "tlv320aic32x4",
+ .owner = THIS_MODULE,
+ .of_match_table = aic32x4_of_id,
+ },
+ .probe = aic32x4_spi_probe,
+ .remove = aic32x4_spi_remove,
+ .id_table = aic32x4_spi_id,
+};
+
+module_spi_driver(aic32x4_spi_driver);
+
+MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver SPI");
+MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index f2d3191961e1..85d4978d0384 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -30,7 +30,6 @@
#include <linux/pm.h>
#include <linux/gpio.h>
#include <linux/of_gpio.h>
-#include <linux/i2c.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/clk.h>
@@ -160,7 +159,10 @@ static const struct aic32x4_rate_divs aic32x4_divs[] = {
/* 48k rate */
{AIC32X4_FREQ_12000000, 48000, 1, 8, 1920, 128, 2, 8, 128, 2, 8, 4},
{AIC32X4_FREQ_24000000, 48000, 2, 8, 1920, 128, 8, 2, 64, 8, 4, 4},
- {AIC32X4_FREQ_25000000, 48000, 2, 7, 8643, 128, 8, 2, 64, 8, 4, 4}
+ {AIC32X4_FREQ_25000000, 48000, 2, 7, 8643, 128, 8, 2, 64, 8, 4, 4},
+
+ /* 96k rate */
+ {AIC32X4_FREQ_25000000, 96000, 2, 7, 8643, 64, 4, 4, 64, 4, 4, 1},
};
static const struct snd_kcontrol_new hpl_output_mixer_controls[] = {
@@ -181,16 +183,71 @@ static const struct snd_kcontrol_new lor_output_mixer_controls[] = {
SOC_DAPM_SINGLE("R_DAC Switch", AIC32X4_LORROUTE, 3, 1, 0),
};
-static const struct snd_kcontrol_new left_input_mixer_controls[] = {
- SOC_DAPM_SINGLE("IN1_L P Switch", AIC32X4_LMICPGAPIN, 6, 1, 0),
- SOC_DAPM_SINGLE("IN2_L P Switch", AIC32X4_LMICPGAPIN, 4, 1, 0),
- SOC_DAPM_SINGLE("IN3_L P Switch", AIC32X4_LMICPGAPIN, 2, 1, 0),
+static const char * const resistor_text[] = {
+ "Off", "10 kOhm", "20 kOhm", "40 kOhm",
};
-static const struct snd_kcontrol_new right_input_mixer_controls[] = {
- SOC_DAPM_SINGLE("IN1_R P Switch", AIC32X4_RMICPGAPIN, 6, 1, 0),
- SOC_DAPM_SINGLE("IN2_R P Switch", AIC32X4_RMICPGAPIN, 4, 1, 0),
- SOC_DAPM_SINGLE("IN3_R P Switch", AIC32X4_RMICPGAPIN, 2, 1, 0),
+/* Left mixer pins */
+static SOC_ENUM_SINGLE_DECL(in1l_lpga_p_enum, AIC32X4_LMICPGAPIN, 6, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in2l_lpga_p_enum, AIC32X4_LMICPGAPIN, 4, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in3l_lpga_p_enum, AIC32X4_LMICPGAPIN, 2, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in1r_lpga_p_enum, AIC32X4_LMICPGAPIN, 0, resistor_text);
+
+static SOC_ENUM_SINGLE_DECL(cml_lpga_n_enum, AIC32X4_LMICPGANIN, 6, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in2r_lpga_n_enum, AIC32X4_LMICPGANIN, 4, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in3r_lpga_n_enum, AIC32X4_LMICPGANIN, 2, resistor_text);
+
+static const struct snd_kcontrol_new in1l_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("IN1_L L+ Switch", in1l_lpga_p_enum),
+};
+static const struct snd_kcontrol_new in2l_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("IN2_L L+ Switch", in2l_lpga_p_enum),
+};
+static const struct snd_kcontrol_new in3l_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("IN3_L L+ Switch", in3l_lpga_p_enum),
+};
+static const struct snd_kcontrol_new in1r_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("IN1_R L+ Switch", in1r_lpga_p_enum),
+};
+static const struct snd_kcontrol_new cml_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("CM_L L- Switch", cml_lpga_n_enum),
+};
+static const struct snd_kcontrol_new in2r_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("IN2_R L- Switch", in2r_lpga_n_enum),
+};
+static const struct snd_kcontrol_new in3r_to_lmixer_controls[] = {
+ SOC_DAPM_ENUM("IN3_R L- Switch", in3r_lpga_n_enum),
+};
+
+/* Right mixer pins */
+static SOC_ENUM_SINGLE_DECL(in1r_rpga_p_enum, AIC32X4_RMICPGAPIN, 6, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in2r_rpga_p_enum, AIC32X4_RMICPGAPIN, 4, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in3r_rpga_p_enum, AIC32X4_RMICPGAPIN, 2, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in2l_rpga_p_enum, AIC32X4_RMICPGAPIN, 0, resistor_text);
+static SOC_ENUM_SINGLE_DECL(cmr_rpga_n_enum, AIC32X4_RMICPGANIN, 6, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in1l_rpga_n_enum, AIC32X4_RMICPGANIN, 4, resistor_text);
+static SOC_ENUM_SINGLE_DECL(in3l_rpga_n_enum, AIC32X4_RMICPGANIN, 2, resistor_text);
+
+static const struct snd_kcontrol_new in1r_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("IN1_R R+ Switch", in1r_rpga_p_enum),
+};
+static const struct snd_kcontrol_new in2r_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("IN2_R R+ Switch", in2r_rpga_p_enum),
+};
+static const struct snd_kcontrol_new in3r_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("IN3_R R+ Switch", in3r_rpga_p_enum),
+};
+static const struct snd_kcontrol_new in2l_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("IN2_L R+ Switch", in2l_rpga_p_enum),
+};
+static const struct snd_kcontrol_new cmr_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("CM_R R- Switch", cmr_rpga_n_enum),
+};
+static const struct snd_kcontrol_new in1l_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("IN1_L R- Switch", in1l_rpga_n_enum),
+};
+static const struct snd_kcontrol_new in3l_to_rmixer_controls[] = {
+ SOC_DAPM_ENUM("IN3_L R- Switch", in3l_rpga_n_enum),
};
static const struct snd_soc_dapm_widget aic32x4_dapm_widgets[] = {
@@ -214,14 +271,39 @@ static const struct snd_soc_dapm_widget aic32x4_dapm_widgets[] = {
&lor_output_mixer_controls[0],
ARRAY_SIZE(lor_output_mixer_controls)),
SND_SOC_DAPM_PGA("LOR Power", AIC32X4_OUTPWRCTL, 2, 0, NULL, 0),
- SND_SOC_DAPM_MIXER("Left Input Mixer", SND_SOC_NOPM, 0, 0,
- &left_input_mixer_controls[0],
- ARRAY_SIZE(left_input_mixer_controls)),
- SND_SOC_DAPM_MIXER("Right Input Mixer", SND_SOC_NOPM, 0, 0,
- &right_input_mixer_controls[0],
- ARRAY_SIZE(right_input_mixer_controls)),
- SND_SOC_DAPM_ADC("Left ADC", "Left Capture", AIC32X4_ADCSETUP, 7, 0),
+
SND_SOC_DAPM_ADC("Right ADC", "Right Capture", AIC32X4_ADCSETUP, 6, 0),
+ SND_SOC_DAPM_MUX("IN1_R to Right Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in1r_to_rmixer_controls),
+ SND_SOC_DAPM_MUX("IN2_R to Right Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in2r_to_rmixer_controls),
+ SND_SOC_DAPM_MUX("IN3_R to Right Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in3r_to_rmixer_controls),
+ SND_SOC_DAPM_MUX("IN2_L to Right Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in2l_to_rmixer_controls),
+ SND_SOC_DAPM_MUX("CM_R to Right Mixer Negative Resistor", SND_SOC_NOPM, 0, 0,
+ cmr_to_rmixer_controls),
+ SND_SOC_DAPM_MUX("IN1_L to Right Mixer Negative Resistor", SND_SOC_NOPM, 0, 0,
+ in1l_to_rmixer_controls),
+ SND_SOC_DAPM_MUX("IN3_L to Right Mixer Negative Resistor", SND_SOC_NOPM, 0, 0,
+ in3l_to_rmixer_controls),
+
+ SND_SOC_DAPM_ADC("Left ADC", "Left Capture", AIC32X4_ADCSETUP, 7, 0),
+ SND_SOC_DAPM_MUX("IN1_L to Left Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in1l_to_lmixer_controls),
+ SND_SOC_DAPM_MUX("IN2_L to Left Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in2l_to_lmixer_controls),
+ SND_SOC_DAPM_MUX("IN3_L to Left Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in3l_to_lmixer_controls),
+ SND_SOC_DAPM_MUX("IN1_R to Left Mixer Positive Resistor", SND_SOC_NOPM, 0, 0,
+ in1r_to_lmixer_controls),
+ SND_SOC_DAPM_MUX("CM_L to Left Mixer Negative Resistor", SND_SOC_NOPM, 0, 0,
+ cml_to_lmixer_controls),
+ SND_SOC_DAPM_MUX("IN2_R to Left Mixer Negative Resistor", SND_SOC_NOPM, 0, 0,
+ in2r_to_lmixer_controls),
+ SND_SOC_DAPM_MUX("IN3_R to Left Mixer Negative Resistor", SND_SOC_NOPM, 0, 0,
+ in3r_to_lmixer_controls),
+
SND_SOC_DAPM_MICBIAS("Mic Bias", AIC32X4_MICBIAS, 6, 0),
SND_SOC_DAPM_OUTPUT("HPL"),
@@ -261,19 +343,77 @@ static const struct snd_soc_dapm_route aic32x4_dapm_routes[] = {
{"LOR Power", NULL, "LOR Output Mixer"},
{"LOR", NULL, "LOR Power"},
- /* Left input */
- {"Left Input Mixer", "IN1_L P Switch", "IN1_L"},
- {"Left Input Mixer", "IN2_L P Switch", "IN2_L"},
- {"Left Input Mixer", "IN3_L P Switch", "IN3_L"},
-
- {"Left ADC", NULL, "Left Input Mixer"},
-
/* Right Input */
- {"Right Input Mixer", "IN1_R P Switch", "IN1_R"},
- {"Right Input Mixer", "IN2_R P Switch", "IN2_R"},
- {"Right Input Mixer", "IN3_R P Switch", "IN3_R"},
-
- {"Right ADC", NULL, "Right Input Mixer"},
+ {"Right ADC", NULL, "IN1_R to Right Mixer Positive Resistor"},
+ {"IN1_R to Right Mixer Positive Resistor", "10 kOhm", "IN1_R"},
+ {"IN1_R to Right Mixer Positive Resistor", "20 kOhm", "IN1_R"},
+ {"IN1_R to Right Mixer Positive Resistor", "40 kOhm", "IN1_R"},
+
+ {"Right ADC", NULL, "IN2_R to Right Mixer Positive Resistor"},
+ {"IN2_R to Right Mixer Positive Resistor", "10 kOhm", "IN2_R"},
+ {"IN2_R to Right Mixer Positive Resistor", "20 kOhm", "IN2_R"},
+ {"IN2_R to Right Mixer Positive Resistor", "40 kOhm", "IN2_R"},
+
+ {"Right ADC", NULL, "IN3_R to Right Mixer Positive Resistor"},
+ {"IN3_R to Right Mixer Positive Resistor", "10 kOhm", "IN3_R"},
+ {"IN3_R to Right Mixer Positive Resistor", "20 kOhm", "IN3_R"},
+ {"IN3_R to Right Mixer Positive Resistor", "40 kOhm", "IN3_R"},
+
+ {"Right ADC", NULL, "IN2_L to Right Mixer Positive Resistor"},
+ {"IN2_L to Right Mixer Positive Resistor", "10 kOhm", "IN2_L"},
+ {"IN2_L to Right Mixer Positive Resistor", "20 kOhm", "IN2_L"},
+ {"IN2_L to Right Mixer Positive Resistor", "40 kOhm", "IN2_L"},
+
+ {"Right ADC", NULL, "CM_R to Right Mixer Negative Resistor"},
+ {"CM_R to Right Mixer Negative Resistor", "10 kOhm", "CM_R"},
+ {"CM_R to Right Mixer Negative Resistor", "20 kOhm", "CM_R"},
+ {"CM_R to Right Mixer Negative Resistor", "40 kOhm", "CM_R"},
+
+ {"Right ADC", NULL, "IN1_L to Right Mixer Negative Resistor"},
+ {"IN1_L to Right Mixer Negative Resistor", "10 kOhm", "IN1_L"},
+ {"IN1_L to Right Mixer Negative Resistor", "20 kOhm", "IN1_L"},
+ {"IN1_L to Right Mixer Negative Resistor", "40 kOhm", "IN1_L"},
+
+ {"Right ADC", NULL, "IN3_L to Right Mixer Negative Resistor"},
+ {"IN3_L to Right Mixer Negative Resistor", "10 kOhm", "IN3_L"},
+ {"IN3_L to Right Mixer Negative Resistor", "20 kOhm", "IN3_L"},
+ {"IN3_L to Right Mixer Negative Resistor", "40 kOhm", "IN3_L"},
+
+ /* Left Input */
+ {"Left ADC", NULL, "IN1_L to Left Mixer Positive Resistor"},
+ {"IN1_L to Left Mixer Positive Resistor", "10 kOhm", "IN1_L"},
+ {"IN1_L to Left Mixer Positive Resistor", "20 kOhm", "IN1_L"},
+ {"IN1_L to Left Mixer Positive Resistor", "40 kOhm", "IN1_L"},
+
+ {"Left ADC", NULL, "IN2_L to Left Mixer Positive Resistor"},
+ {"IN2_L to Left Mixer Positive Resistor", "10 kOhm", "IN2_L"},
+ {"IN2_L to Left Mixer Positive Resistor", "20 kOhm", "IN2_L"},
+ {"IN2_L to Left Mixer Positive Resistor", "40 kOhm", "IN2_L"},
+
+ {"Left ADC", NULL, "IN3_L to Left Mixer Positive Resistor"},
+ {"IN3_L to Left Mixer Positive Resistor", "10 kOhm", "IN3_L"},
+ {"IN3_L to Left Mixer Positive Resistor", "20 kOhm", "IN3_L"},
+ {"IN3_L to Left Mixer Positive Resistor", "40 kOhm", "IN3_L"},
+
+ {"Left ADC", NULL, "IN1_R to Left Mixer Positive Resistor"},
+ {"IN1_R to Left Mixer Positive Resistor", "10 kOhm", "IN1_R"},
+ {"IN1_R to Left Mixer Positive Resistor", "20 kOhm", "IN1_R"},
+ {"IN1_R to Left Mixer Positive Resistor", "40 kOhm", "IN1_R"},
+
+ {"Left ADC", NULL, "CM_L to Left Mixer Negative Resistor"},
+ {"CM_L to Left Mixer Negative Resistor", "10 kOhm", "CM_L"},
+ {"CM_L to Left Mixer Negative Resistor", "20 kOhm", "CM_L"},
+ {"CM_L to Left Mixer Negative Resistor", "40 kOhm", "CM_L"},
+
+ {"Left ADC", NULL, "IN2_R to Left Mixer Negative Resistor"},
+ {"IN2_R to Left Mixer Negative Resistor", "10 kOhm", "IN2_R"},
+ {"IN2_R to Left Mixer Negative Resistor", "20 kOhm", "IN2_R"},
+ {"IN2_R to Left Mixer Negative Resistor", "40 kOhm", "IN2_R"},
+
+ {"Left ADC", NULL, "IN3_R to Left Mixer Negative Resistor"},
+ {"IN3_R to Left Mixer Negative Resistor", "10 kOhm", "IN3_R"},
+ {"IN3_R to Left Mixer Negative Resistor", "20 kOhm", "IN3_R"},
+ {"IN3_R to Left Mixer Negative Resistor", "40 kOhm", "IN3_R"},
};
static const struct regmap_range_cfg aic32x4_regmap_pages[] = {
@@ -287,14 +427,12 @@ static const struct regmap_range_cfg aic32x4_regmap_pages[] = {
},
};
-static const struct regmap_config aic32x4_regmap = {
- .reg_bits = 8,
- .val_bits = 8,
-
+const struct regmap_config aic32x4_regmap_config = {
.max_register = AIC32X4_RMICPGAVOL,
.ranges = aic32x4_regmap_pages,
.num_ranges = ARRAY_SIZE(aic32x4_regmap_pages),
};
+EXPORT_SYMBOL(aic32x4_regmap_config);
static inline int aic32x4_get_divs(int mclk, int rate)
{
@@ -567,7 +705,7 @@ static int aic32x4_set_bias_level(struct snd_soc_codec *codec,
return 0;
}
-#define AIC32X4_RATES SNDRV_PCM_RATE_8000_48000
+#define AIC32X4_RATES SNDRV_PCM_RATE_8000_96000
#define AIC32X4_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE \
| SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S32_LE)
@@ -596,7 +734,7 @@ static struct snd_soc_dai_driver aic32x4_dai = {
.symmetric_rates = 1,
};
-static int aic32x4_probe(struct snd_soc_codec *codec)
+static int aic32x4_codec_probe(struct snd_soc_codec *codec)
{
struct aic32x4_priv *aic32x4 = snd_soc_codec_get_drvdata(codec);
u32 tmp_reg;
@@ -655,7 +793,7 @@ static int aic32x4_probe(struct snd_soc_codec *codec)
}
static struct snd_soc_codec_driver soc_codec_dev_aic32x4 = {
- .probe = aic32x4_probe,
+ .probe = aic32x4_codec_probe,
.set_bias_level = aic32x4_set_bias_level,
.suspend_bias_off = true,
@@ -777,24 +915,22 @@ error_ldo:
return ret;
}
-static int aic32x4_i2c_probe(struct i2c_client *i2c,
- const struct i2c_device_id *id)
+int aic32x4_probe(struct device *dev, struct regmap *regmap)
{
- struct aic32x4_pdata *pdata = i2c->dev.platform_data;
struct aic32x4_priv *aic32x4;
- struct device_node *np = i2c->dev.of_node;
+ struct aic32x4_pdata *pdata = dev->platform_data;
+ struct device_node *np = dev->of_node;
int ret;
- aic32x4 = devm_kzalloc(&i2c->dev, sizeof(struct aic32x4_priv),
+ if (IS_ERR(regmap))
+ return PTR_ERR(regmap);
+
+ aic32x4 = devm_kzalloc(dev, sizeof(struct aic32x4_priv),
GFP_KERNEL);
if (aic32x4 == NULL)
return -ENOMEM;
- aic32x4->regmap = devm_regmap_init_i2c(i2c, &aic32x4_regmap);
- if (IS_ERR(aic32x4->regmap))
- return PTR_ERR(aic32x4->regmap);
-
- i2c_set_clientdata(i2c, aic32x4);
+ dev_set_drvdata(dev, aic32x4);
if (pdata) {
aic32x4->power_cfg = pdata->power_cfg;
@@ -804,7 +940,7 @@ static int aic32x4_i2c_probe(struct i2c_client *i2c,
} else if (np) {
ret = aic32x4_parse_dt(aic32x4, np);
if (ret) {
- dev_err(&i2c->dev, "Failed to parse DT node\n");
+ dev_err(dev, "Failed to parse DT node\n");
return ret;
}
} else {
@@ -814,71 +950,48 @@ static int aic32x4_i2c_probe(struct i2c_client *i2c,
aic32x4->rstn_gpio = -1;
}
- aic32x4->mclk = devm_clk_get(&i2c->dev, "mclk");
+ aic32x4->mclk = devm_clk_get(dev, "mclk");
if (IS_ERR(aic32x4->mclk)) {
- dev_err(&i2c->dev, "Failed getting the mclk. The current implementation does not support the usage of this codec without mclk\n");
+ dev_err(dev, "Failed getting the mclk. The current implementation does not support the usage of this codec without mclk\n");
return PTR_ERR(aic32x4->mclk);
}
if (gpio_is_valid(aic32x4->rstn_gpio)) {
- ret = devm_gpio_request_one(&i2c->dev, aic32x4->rstn_gpio,
+ ret = devm_gpio_request_one(dev, aic32x4->rstn_gpio,
GPIOF_OUT_INIT_LOW, "tlv320aic32x4 rstn");
if (ret != 0)
return ret;
}
- ret = aic32x4_setup_regulators(&i2c->dev, aic32x4);
+ ret = aic32x4_setup_regulators(dev, aic32x4);
if (ret) {
- dev_err(&i2c->dev, "Failed to setup regulators\n");
+ dev_err(dev, "Failed to setup regulators\n");
return ret;
}
- ret = snd_soc_register_codec(&i2c->dev,
+ ret = snd_soc_register_codec(dev,
&soc_codec_dev_aic32x4, &aic32x4_dai, 1);
if (ret) {
- dev_err(&i2c->dev, "Failed to register codec\n");
+ dev_err(dev, "Failed to register codec\n");
aic32x4_disable_regulators(aic32x4);
return ret;
}
- i2c_set_clientdata(i2c, aic32x4);
-
return 0;
}
+EXPORT_SYMBOL(aic32x4_probe);
-static int aic32x4_i2c_remove(struct i2c_client *client)
+int aic32x4_remove(struct device *dev)
{
- struct aic32x4_priv *aic32x4 = i2c_get_clientdata(client);
+ struct aic32x4_priv *aic32x4 = dev_get_drvdata(dev);
aic32x4_disable_regulators(aic32x4);
- snd_soc_unregister_codec(&client->dev);
+ snd_soc_unregister_codec(dev);
+
return 0;
}
-
-static const struct i2c_device_id aic32x4_i2c_id[] = {
- { "tlv320aic32x4", 0 },
- { }
-};
-MODULE_DEVICE_TABLE(i2c, aic32x4_i2c_id);
-
-static const struct of_device_id aic32x4_of_id[] = {
- { .compatible = "ti,tlv320aic32x4", },
- { /* senitel */ }
-};
-MODULE_DEVICE_TABLE(of, aic32x4_of_id);
-
-static struct i2c_driver aic32x4_i2c_driver = {
- .driver = {
- .name = "tlv320aic32x4",
- .of_match_table = aic32x4_of_id,
- },
- .probe = aic32x4_i2c_probe,
- .remove = aic32x4_i2c_remove,
- .id_table = aic32x4_i2c_id,
-};
-
-module_i2c_driver(aic32x4_i2c_driver);
+EXPORT_SYMBOL(aic32x4_remove);
MODULE_DESCRIPTION("ASoC tlv320aic32x4 codec driver");
MODULE_AUTHOR("Javier Martin <javier.martin@vista-silicon.com>");
diff --git a/sound/soc/codecs/tlv320aic32x4.h b/sound/soc/codecs/tlv320aic32x4.h
index 995f033a855d..a197dd51addc 100644
--- a/sound/soc/codecs/tlv320aic32x4.h
+++ b/sound/soc/codecs/tlv320aic32x4.h
@@ -10,6 +10,13 @@
#ifndef _TLV320AIC32X4_H
#define _TLV320AIC32X4_H
+struct device;
+struct regmap_config;
+
+extern const struct regmap_config aic32x4_regmap_config;
+int aic32x4_probe(struct device *dev, struct regmap *regmap);
+int aic32x4_remove(struct device *dev);
+
/* tlv320aic32x4 register space (in decimal to match datasheet) */
#define AIC32X4_PAGE1 128
diff --git a/sound/soc/codecs/twl6040.c b/sound/soc/codecs/twl6040.c
index bc3de2e844e6..1f7081043566 100644
--- a/sound/soc/codecs/twl6040.c
+++ b/sound/soc/codecs/twl6040.c
@@ -824,7 +824,7 @@ static int twl6040_set_bias_level(struct snd_soc_codec *codec,
{
struct twl6040 *twl6040 = codec->control_data;
struct twl6040_data *priv = snd_soc_codec_get_drvdata(codec);
- int ret;
+ int ret = 0;
switch (level) {
case SND_SOC_BIAS_ON:
@@ -832,12 +832,16 @@ static int twl6040_set_bias_level(struct snd_soc_codec *codec,
case SND_SOC_BIAS_PREPARE:
break;
case SND_SOC_BIAS_STANDBY:
- if (priv->codec_powered)
+ if (priv->codec_powered) {
+ /* Select low power PLL in standby */
+ ret = twl6040_set_pll(twl6040, TWL6040_SYSCLK_SEL_LPPLL,
+ 32768, 19200000);
break;
+ }
ret = twl6040_power(twl6040, 1);
if (ret)
- return ret;
+ break;
priv->codec_powered = 1;
@@ -853,7 +857,7 @@ static int twl6040_set_bias_level(struct snd_soc_codec *codec,
break;
}
- return 0;
+ return ret;
}
static int twl6040_startup(struct snd_pcm_substream *substream,
@@ -983,9 +987,9 @@ static void twl6040_mute_path(struct snd_soc_codec *codec, enum twl6040_dai_id i
if (mute) {
/* Power down drivers and DACs */
hflctl &= ~(TWL6040_HFDACENA | TWL6040_HFPGAENA |
- TWL6040_HFDRVENA);
+ TWL6040_HFDRVENA | TWL6040_HFSWENA);
hfrctl &= ~(TWL6040_HFDACENA | TWL6040_HFPGAENA |
- TWL6040_HFDRVENA);
+ TWL6040_HFDRVENA | TWL6040_HFSWENA);
}
twl6040_reg_write(twl6040, TWL6040_REG_HFLCTL, hflctl);
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index fc164d69a557..f3109da24769 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -3793,9 +3793,8 @@ static int wm8962_runtime_resume(struct device *dev)
ret = regulator_bulk_enable(ARRAY_SIZE(wm8962->supplies),
wm8962->supplies);
if (ret != 0) {
- dev_err(dev,
- "Failed to enable supplies: %d\n", ret);
- return ret;
+ dev_err(dev, "Failed to enable supplies: %d\n", ret);
+ goto disable_clock;
}
regcache_cache_only(wm8962->regmap, false);
@@ -3833,6 +3832,10 @@ static int wm8962_runtime_resume(struct device *dev)
msleep(5);
return 0;
+
+disable_clock:
+ clk_disable_unprepare(wm8962->pdata.mclk);
+ return ret;
}
static int wm8962_runtime_suspend(struct device *dev)
diff --git a/sound/soc/codecs/wm8962.h b/sound/soc/codecs/wm8962.h
index 910aafd09d21..e63a318a3015 100644
--- a/sound/soc/codecs/wm8962.h
+++ b/sound/soc/codecs/wm8962.h
@@ -16,9 +16,9 @@
#include <asm/types.h>
#include <sound/soc.h>
-#define WM8962_SYSCLK_MCLK 1
-#define WM8962_SYSCLK_FLL 2
-#define WM8962_SYSCLK_PLL3 3
+#define WM8962_SYSCLK_MCLK 0
+#define WM8962_SYSCLK_FLL 1
+#define WM8962_SYSCLK_PLL3 2
#define WM8962_FLL 1
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 2389ab47e25f..466492b7d4f5 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -643,6 +643,7 @@ MODULE_DEVICE_TABLE(of, asoc_simple_of_match);
static struct platform_driver asoc_simple_card = {
.driver = {
.name = "asoc-simple-card",
+ .pm = &snd_soc_pm_ops,
.of_match_table = asoc_simple_of_match,
},
.probe = asoc_simple_card_probe,
diff --git a/sound/soc/kirkwood/Kconfig b/sound/soc/kirkwood/Kconfig
index 132bb83f8e99..bc3c7b5ac752 100644
--- a/sound/soc/kirkwood/Kconfig
+++ b/sound/soc/kirkwood/Kconfig
@@ -1,6 +1,7 @@
config SND_KIRKWOOD_SOC
tristate "SoC Audio for the Marvell Kirkwood and Dove chips"
depends on ARCH_DOVE || ARCH_MVEBU || COMPILE_TEST
+ depends on HAS_DMA
help
Say Y or M if you want to add support for codecs attached to
the Kirkwood I2S interface. You will also need to select the
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index f7e789e97fbc..3abf51c07851 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -43,6 +43,7 @@ config SND_SOC_MT8173_RT5650_RT5676
depends on SND_SOC_MEDIATEK && I2C
select SND_SOC_RT5645
select SND_SOC_RT5677
+ select SND_SOC_HDMI_CODEC
help
This adds ASoC driver for Mediatek MT8173 boards
with the RT5650 and RT5676 codecs.
diff --git a/sound/soc/mediatek/mt8173-rt5650-rt5676.c b/sound/soc/mediatek/mt8173-rt5650-rt5676.c
index 5c4c58c69c51..bb593926c62d 100644
--- a/sound/soc/mediatek/mt8173-rt5650-rt5676.c
+++ b/sound/soc/mediatek/mt8173-rt5650-rt5676.c
@@ -134,7 +134,9 @@ static struct snd_soc_dai_link_component mt8173_rt5650_rt5676_codecs[] = {
enum {
DAI_LINK_PLAYBACK,
DAI_LINK_CAPTURE,
+ DAI_LINK_HDMI,
DAI_LINK_CODEC_I2S,
+ DAI_LINK_HDMI_I2S,
DAI_LINK_INTERCODEC
};
@@ -161,6 +163,16 @@ static struct snd_soc_dai_link mt8173_rt5650_rt5676_dais[] = {
.dynamic = 1,
.dpcm_capture = 1,
},
+ [DAI_LINK_HDMI] = {
+ .name = "HDMI",
+ .stream_name = "HDMI PCM",
+ .cpu_dai_name = "HDMI",
+ .codec_name = "snd-soc-dummy",
+ .codec_dai_name = "snd-soc-dummy-dai",
+ .trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+ .dynamic = 1,
+ .dpcm_playback = 1,
+ },
/* Back End DAI links */
[DAI_LINK_CODEC_I2S] = {
@@ -177,6 +189,13 @@ static struct snd_soc_dai_link mt8173_rt5650_rt5676_dais[] = {
.dpcm_playback = 1,
.dpcm_capture = 1,
},
+ [DAI_LINK_HDMI_I2S] = {
+ .name = "HDMI BE",
+ .cpu_dai_name = "HDMIO",
+ .no_pcm = 1,
+ .codec_dai_name = "i2s-hifi",
+ .dpcm_playback = 1,
+ },
/* rt5676 <-> rt5650 intercodec link: Sets rt5676 I2S2 as master */
[DAI_LINK_INTERCODEC] = {
.name = "rt5650_rt5676 intercodec",
@@ -251,6 +270,14 @@ static int mt8173_rt5650_rt5676_dev_probe(struct platform_device *pdev)
mt8173_rt5650_rt5676_dais[DAI_LINK_INTERCODEC].codec_of_node =
mt8173_rt5650_rt5676_codecs[1].of_node;
+ mt8173_rt5650_rt5676_dais[DAI_LINK_HDMI_I2S].codec_of_node =
+ of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 2);
+ if (!mt8173_rt5650_rt5676_dais[DAI_LINK_HDMI_I2S].codec_of_node) {
+ dev_err(&pdev->dev,
+ "Property 'audio-codec' missing or invalid\n");
+ return -EINVAL;
+ }
+
card->dev = &pdev->dev;
platform_set_drvdata(pdev, card);
diff --git a/sound/soc/mediatek/mt8173-rt5650.c b/sound/soc/mediatek/mt8173-rt5650.c
index bb09bb1b7f1c..a27a6673dbe3 100644
--- a/sound/soc/mediatek/mt8173-rt5650.c
+++ b/sound/soc/mediatek/mt8173-rt5650.c
@@ -85,12 +85,29 @@ static int mt8173_rt5650_init(struct snd_soc_pcm_runtime *runtime)
{
struct snd_soc_card *card = runtime->card;
struct snd_soc_codec *codec = runtime->codec_dais[0]->codec;
+ const char *codec_capture_dai = runtime->codec_dais[1]->name;
int ret;
rt5645_sel_asrc_clk_src(codec,
- RT5645_DA_STEREO_FILTER |
- RT5645_AD_STEREO_FILTER,
+ RT5645_DA_STEREO_FILTER,
RT5645_CLK_SEL_I2S1_ASRC);
+
+ if (!strcmp(codec_capture_dai, "rt5645-aif1")) {
+ rt5645_sel_asrc_clk_src(codec,
+ RT5645_AD_STEREO_FILTER,
+ RT5645_CLK_SEL_I2S1_ASRC);
+ } else if (!strcmp(codec_capture_dai, "rt5645-aif2")) {
+ rt5645_sel_asrc_clk_src(codec,
+ RT5645_AD_STEREO_FILTER,
+ RT5645_CLK_SEL_I2S2_ASRC);
+ } else {
+ dev_warn(card->dev,
+ "Only one dai codec found in DTS, enabled rt5645 AD filter\n");
+ rt5645_sel_asrc_clk_src(codec,
+ RT5645_AD_STEREO_FILTER,
+ RT5645_CLK_SEL_I2S1_ASRC);
+ }
+
/* enable jack detection */
ret = snd_soc_card_jack_new(card, "Headset Jack",
SND_JACK_HEADPHONE | SND_JACK_MICROPHONE |
@@ -110,6 +127,11 @@ static int mt8173_rt5650_init(struct snd_soc_pcm_runtime *runtime)
static struct snd_soc_dai_link_component mt8173_rt5650_codecs[] = {
{
+ /* Playback */
+ .dai_name = "rt5645-aif1",
+ },
+ {
+ /* Capture */
.dai_name = "rt5645-aif1",
},
};
@@ -149,7 +171,7 @@ static struct snd_soc_dai_link mt8173_rt5650_dais[] = {
.cpu_dai_name = "I2S",
.no_pcm = 1,
.codecs = mt8173_rt5650_codecs,
- .num_codecs = 1,
+ .num_codecs = 2,
.init = mt8173_rt5650_init,
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
SND_SOC_DAIFMT_CBS_CFS,
@@ -177,6 +199,8 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
{
struct snd_soc_card *card = &mt8173_rt5650_card;
struct device_node *platform_node;
+ struct device_node *np;
+ const char *codec_capture_dai;
int i, ret;
platform_node = of_parse_phandle(pdev->dev.of_node,
@@ -199,6 +223,26 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
"Property 'audio-codec' missing or invalid\n");
return -EINVAL;
}
+ mt8173_rt5650_codecs[1].of_node = mt8173_rt5650_codecs[0].of_node;
+
+ if (of_find_node_by_name(platform_node, "codec-capture")) {
+ np = of_get_child_by_name(pdev->dev.of_node, "codec-capture");
+ if (!np) {
+ dev_err(&pdev->dev,
+ "%s: Can't find codec-capture DT node\n",
+ __func__);
+ return -EINVAL;
+ }
+ ret = snd_soc_of_get_dai_name(np, &codec_capture_dai);
+ if (ret < 0) {
+ dev_err(&pdev->dev,
+ "%s codec_capture_dai name fail %d\n",
+ __func__, ret);
+ return ret;
+ }
+ mt8173_rt5650_codecs[1].dai_name = codec_capture_dai;
+ }
+
card->dev = &pdev->dev;
platform_set_drvdata(pdev, card);
diff --git a/sound/soc/mediatek/mtk-afe-pcm.c b/sound/soc/mediatek/mtk-afe-pcm.c
index f1c58a2c12fb..2b5df2ef51a3 100644
--- a/sound/soc/mediatek/mtk-afe-pcm.c
+++ b/sound/soc/mediatek/mtk-afe-pcm.c
@@ -123,6 +123,7 @@
#define AFE_TDM_CON1_WLEN_32BIT (0x2 << 8)
#define AFE_TDM_CON1_MSB_ALIGNED (0x1 << 4)
#define AFE_TDM_CON1_1_BCK_DELAY (0x1 << 3)
+#define AFE_TDM_CON1_LRCK_INV (0x1 << 2)
#define AFE_TDM_CON1_BCK_INV (0x1 << 1)
#define AFE_TDM_CON1_EN (0x1 << 0)
@@ -449,6 +450,7 @@ static int mtk_afe_hdmi_prepare(struct snd_pcm_substream *substream,
runtime->rate * runtime->channels * 32);
val = AFE_TDM_CON1_BCK_INV |
+ AFE_TDM_CON1_LRCK_INV |
AFE_TDM_CON1_1_BCK_DELAY |
AFE_TDM_CON1_MSB_ALIGNED | /* I2S mode */
AFE_TDM_CON1_WLEN_32BIT |
diff --git a/sound/soc/omap/mcbsp.c b/sound/soc/omap/mcbsp.c
index c7563e230c7d..4a16e778966b 100644
--- a/sound/soc/omap/mcbsp.c
+++ b/sound/soc/omap/mcbsp.c
@@ -260,6 +260,10 @@ static void omap_st_on(struct omap_mcbsp *mcbsp)
if (mcbsp->pdata->enable_st_clock)
mcbsp->pdata->enable_st_clock(mcbsp->id, 1);
+ /* Disable Sidetone clock auto-gating for normal operation */
+ w = MCBSP_ST_READ(mcbsp, SYSCONFIG);
+ MCBSP_ST_WRITE(mcbsp, SYSCONFIG, w & ~(ST_AUTOIDLE));
+
/* Enable McBSP Sidetone */
w = MCBSP_READ(mcbsp, SSELCR);
MCBSP_WRITE(mcbsp, SSELCR, w | SIDETONEEN);
@@ -279,6 +283,10 @@ static void omap_st_off(struct omap_mcbsp *mcbsp)
w = MCBSP_READ(mcbsp, SSELCR);
MCBSP_WRITE(mcbsp, SSELCR, w & ~(SIDETONEEN));
+ /* Enable Sidetone clock auto-gating to reduce power consumption */
+ w = MCBSP_ST_READ(mcbsp, SYSCONFIG);
+ MCBSP_ST_WRITE(mcbsp, SYSCONFIG, w | ST_AUTOIDLE);
+
if (mcbsp->pdata->enable_st_clock)
mcbsp->pdata->enable_st_clock(mcbsp->id, 0);
}
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
index 99381a27295b..a84f677234f0 100644
--- a/sound/soc/omap/omap-pcm.c
+++ b/sound/soc/omap/omap-pcm.c
@@ -82,6 +82,8 @@ static int omap_pcm_hw_params(struct snd_pcm_substream *substream,
struct dma_chan *chan;
int err = 0;
+ memset(&config, 0x00, sizeof(config));
+
dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
/* return if this is a bufferless transfer e.g.
diff --git a/sound/soc/pxa/brownstone.c b/sound/soc/pxa/brownstone.c
index ec522e94b0e2..b6cb9950f05d 100644
--- a/sound/soc/pxa/brownstone.c
+++ b/sound/soc/pxa/brownstone.c
@@ -133,3 +133,4 @@ module_platform_driver(mmp_driver);
MODULE_AUTHOR("Leo Yan <leoy@marvell.com>");
MODULE_DESCRIPTION("ALSA SoC Brownstone");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:brownstone-audio");
diff --git a/sound/soc/pxa/mioa701_wm9713.c b/sound/soc/pxa/mioa701_wm9713.c
index 5c8f9db50a47..d1661fa6ee08 100644
--- a/sound/soc/pxa/mioa701_wm9713.c
+++ b/sound/soc/pxa/mioa701_wm9713.c
@@ -207,3 +207,4 @@ module_platform_driver(mioa701_wm9713_driver);
MODULE_AUTHOR("Robert Jarzmik (rjarzmik@free.fr)");
MODULE_DESCRIPTION("ALSA SoC WM9713 MIO A701");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mioa701-wm9713");
diff --git a/sound/soc/pxa/mmp-pcm.c b/sound/soc/pxa/mmp-pcm.c
index 51e790d006f5..96df9b2d8fc4 100644
--- a/sound/soc/pxa/mmp-pcm.c
+++ b/sound/soc/pxa/mmp-pcm.c
@@ -248,3 +248,4 @@ module_platform_driver(mmp_pcm_driver);
MODULE_AUTHOR("Leo Yan <leoy@marvell.com>");
MODULE_DESCRIPTION("MMP Soc Audio DMA module");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mmp-pcm-audio");
diff --git a/sound/soc/pxa/mmp-sspa.c b/sound/soc/pxa/mmp-sspa.c
index eca60c29791a..ca8b23f8c525 100644
--- a/sound/soc/pxa/mmp-sspa.c
+++ b/sound/soc/pxa/mmp-sspa.c
@@ -482,3 +482,4 @@ module_platform_driver(asoc_mmp_sspa_driver);
MODULE_AUTHOR("Leo Yan <leoy@marvell.com>");
MODULE_DESCRIPTION("MMP SSPA SoC Interface");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mmp-sspa-dai");
diff --git a/sound/soc/pxa/palm27x.c b/sound/soc/pxa/palm27x.c
index 4e74d9573f03..bcc81e920a67 100644
--- a/sound/soc/pxa/palm27x.c
+++ b/sound/soc/pxa/palm27x.c
@@ -161,3 +161,4 @@ module_platform_driver(palm27x_wm9712_driver);
MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
MODULE_DESCRIPTION("ALSA SoC Palm T|X, T5 and LifeDrive");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:palm27x-asoc");
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index da03fad1b9cd..3cad990dad2c 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -833,3 +833,4 @@ module_platform_driver(asoc_ssp_driver);
MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
MODULE_DESCRIPTION("PXA SSP/PCM SoC Interface");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:pxa-ssp-dai");
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index f3de615aacd7..9615e6de1306 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -287,3 +287,4 @@ module_platform_driver(pxa2xx_ac97_driver);
MODULE_AUTHOR("Nicolas Pitre");
MODULE_DESCRIPTION("AC97 driver for the Intel PXA2xx chip");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:pxa2xx-ac97");
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index 9f390398d518..410d48b93031 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -117,3 +117,4 @@ module_platform_driver(pxa_pcm_driver);
MODULE_AUTHOR("Nicolas Pitre");
MODULE_DESCRIPTION("Intel PXA2xx PCM DMA module");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:pxa-pcm-audio");
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 6e8665430bd5..db000c6987a1 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -474,7 +474,7 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
struct lpass_data *drvdata =
snd_soc_platform_get_drvdata(soc_runtime->platform);
struct lpass_variant *v = drvdata->variant;
- int ret;
+ int ret = -EINVAL;
struct lpass_pcm_data *data;
size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
@@ -491,7 +491,7 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
data->rdma_ch = v->alloc_dma_channel(drvdata,
SNDRV_PCM_STREAM_PLAYBACK);
- if (IS_ERR_VALUE(data->rdma_ch))
+ if (data->rdma_ch < 0)
return data->rdma_ch;
drvdata->substream[data->rdma_ch] = psubstream;
@@ -518,8 +518,10 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
data->wrdma_ch = v->alloc_dma_channel(drvdata,
SNDRV_PCM_STREAM_CAPTURE);
- if (IS_ERR_VALUE(data->wrdma_ch))
+ if (data->wrdma_ch < 0) {
+ ret = data->wrdma_ch;
goto capture_alloc_err;
+ }
drvdata->substream[data->wrdma_ch] = csubstream;
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 606399de684d..49354d17ea55 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -492,9 +492,7 @@ static void rsnd_adg_get_clkout(struct rsnd_priv *priv,
*/
if (!count) {
clk = clk_register_fixed_rate(dev, clkout_name[CLKOUT],
- parent_clk_name,
- (parent_clk_name) ?
- 0 : CLK_IS_ROOT, req_rate);
+ parent_clk_name, 0, req_rate);
if (!IS_ERR(clk)) {
adg->clkout[CLKOUT] = clk;
of_clk_add_provider(np, of_clk_src_simple_get, clk);
@@ -506,9 +504,7 @@ static void rsnd_adg_get_clkout(struct rsnd_priv *priv,
else {
for (i = 0; i < CLKOUTMAX; i++) {
clk = clk_register_fixed_rate(dev, clkout_name[i],
- parent_clk_name,
- (parent_clk_name) ?
- 0 : CLK_IS_ROOT,
+ parent_clk_name, 0,
req_rate);
if (!IS_ERR(clk)) {
adg->onecell.clks = adg->clkout;
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 7658e8fd7bdc..6bc93cbb3049 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -316,11 +316,15 @@ static u32 rsnd_dmapp_get_id(struct rsnd_dai_stream *io,
size = ARRAY_SIZE(gen2_id_table_cmd);
}
- if (!entry)
- return 0xFF;
+ if ((!entry) || (size <= id)) {
+ struct device *dev = rsnd_priv_to_dev(rsnd_io_to_priv(io));
- if (size <= id)
- return 0xFF;
+ dev_err(dev, "unknown connection (%s[%d])\n",
+ rsnd_mod_name(mod), rsnd_mod_id(mod));
+
+ /* use non-prohibited SRS number as error */
+ return 0x00; /* SSI00 */
+ }
return entry[id];
}
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index fc89a67258ca..a8f61d79333b 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -276,8 +276,9 @@ struct rsnd_mod {
/*
* status
*
- * 0xH0000CB0
+ * 0xH0000CBA
*
+ * A 0: probe 1: remove
* B 0: init 1: quit
* C 0: start 1: stop
*
@@ -287,19 +288,19 @@ struct rsnd_mod {
* H 0: fallback
* H 0: hw_params
*/
+#define __rsnd_mod_shift_probe 0
+#define __rsnd_mod_shift_remove 0
#define __rsnd_mod_shift_init 4
#define __rsnd_mod_shift_quit 4
#define __rsnd_mod_shift_start 8
#define __rsnd_mod_shift_stop 8
-#define __rsnd_mod_shift_probe 28 /* always called */
-#define __rsnd_mod_shift_remove 28 /* always called */
#define __rsnd_mod_shift_irq 28 /* always called */
#define __rsnd_mod_shift_pcm_new 28 /* always called */
#define __rsnd_mod_shift_fallback 28 /* always called */
#define __rsnd_mod_shift_hw_params 28 /* always called */
-#define __rsnd_mod_add_probe 0
-#define __rsnd_mod_add_remove 0
+#define __rsnd_mod_add_probe 1
+#define __rsnd_mod_add_remove -1
#define __rsnd_mod_add_init 1
#define __rsnd_mod_add_quit -1
#define __rsnd_mod_add_start 1
@@ -310,7 +311,7 @@ struct rsnd_mod {
#define __rsnd_mod_add_hw_params 0
#define __rsnd_mod_call_probe 0
-#define __rsnd_mod_call_remove 0
+#define __rsnd_mod_call_remove 1
#define __rsnd_mod_call_init 0
#define __rsnd_mod_call_quit 1
#define __rsnd_mod_call_start 0
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 15d6ffe8be74..e39f916d0f2f 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -572,6 +572,9 @@ int rsnd_src_probe(struct rsnd_priv *priv)
i = 0;
for_each_child_of_node(node, np) {
+ if (!of_device_is_available(np))
+ goto skip;
+
src = rsnd_src_get(priv, i);
snprintf(name, RSND_SRC_NAME_SIZE, "%s.%d",
@@ -595,6 +598,7 @@ int rsnd_src_probe(struct rsnd_priv *priv)
if (ret)
goto rsnd_src_probe_done;
+skip:
i++;
}
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 1cf94d7fb9f4..ee7f15aa46fc 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1023,6 +1023,11 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
control_hdr = (struct snd_soc_tplg_ctl_hdr *)tplg->pos;
+ if (control_hdr->size != sizeof(*control_hdr)) {
+ dev_err(tplg->dev, "ASoC: invalid control size\n");
+ return -EINVAL;
+ }
+
switch (control_hdr->ops.info) {
case SND_SOC_TPLG_CTL_VOLSW:
case SND_SOC_TPLG_CTL_STROBE:
@@ -1476,6 +1481,8 @@ widget:
widget->dobj.type = SND_SOC_DOBJ_WIDGET;
widget->dobj.ops = tplg->ops;
widget->dobj.index = tplg->index;
+ kfree(template.sname);
+ kfree(template.name);
list_add(&widget->dobj.list, &tplg->comp->dobj_list);
return 0;
@@ -1499,10 +1506,17 @@ static int soc_tplg_dapm_widget_elems_load(struct soc_tplg *tplg,
for (i = 0; i < count; i++) {
widget = (struct snd_soc_tplg_dapm_widget *) tplg->pos;
+ if (widget->size != sizeof(*widget)) {
+ dev_err(tplg->dev, "ASoC: invalid widget size\n");
+ return -EINVAL;
+ }
+
ret = soc_tplg_dapm_widget_create(tplg, widget);
- if (ret < 0)
+ if (ret < 0) {
dev_err(tplg->dev, "ASoC: failed to load widget %s\n",
widget->name);
+ return ret;
+ }
}
return 0;
@@ -1586,6 +1600,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
return snd_soc_register_dai(tplg->comp, dai_drv);
}
+/* create the FE DAI link */
static int soc_tplg_link_create(struct soc_tplg *tplg,
struct snd_soc_tplg_pcm *pcm)
{
@@ -1598,6 +1613,16 @@ static int soc_tplg_link_create(struct soc_tplg *tplg,
link->name = pcm->pcm_name;
link->stream_name = pcm->pcm_name;
+ link->id = pcm->pcm_id;
+
+ link->cpu_dai_name = pcm->dai_name;
+ link->codec_name = "snd-soc-dummy";
+ link->codec_dai_name = "snd-soc-dummy-dai";
+
+ /* enable DPCM */
+ link->dynamic = 1;
+ link->dpcm_playback = pcm->playback;
+ link->dpcm_capture = pcm->capture;
/* pass control to component driver for optional further init */
ret = soc_tplg_dai_link_load(tplg, link);
@@ -1639,8 +1664,6 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg,
if (tplg->pass != SOC_TPLG_PASS_PCM_DAI)
return 0;
- pcm = (struct snd_soc_tplg_pcm *)tplg->pos;
-
if (soc_tplg_check_elem_count(tplg,
sizeof(struct snd_soc_tplg_pcm), count,
hdr->payload_size, "PCM DAI")) {
@@ -1650,7 +1673,13 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg,
}
/* create the FE DAIs and DAI links */
+ pcm = (struct snd_soc_tplg_pcm *)tplg->pos;
for (i = 0; i < count; i++) {
+ if (pcm->size != sizeof(*pcm)) {
+ dev_err(tplg->dev, "ASoC: invalid pcm size\n");
+ return -EINVAL;
+ }
+
soc_tplg_pcm_create(tplg, pcm);
pcm++;
}
@@ -1670,6 +1699,11 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg,
return 0;
manifest = (struct snd_soc_tplg_manifest *)tplg->pos;
+ if (manifest->size != sizeof(*manifest)) {
+ dev_err(tplg->dev, "ASoC: invalid manifest size\n");
+ return -EINVAL;
+ }
+
tplg->pos += sizeof(struct snd_soc_tplg_manifest);
if (tplg->comp && tplg->ops && tplg->ops->manifest)
@@ -1686,6 +1720,14 @@ static int soc_valid_header(struct soc_tplg *tplg,
if (soc_tplg_get_hdr_offset(tplg) >= tplg->fw->size)
return 0;
+ if (hdr->size != sizeof(*hdr)) {
+ dev_err(tplg->dev,
+ "ASoC: invalid header size for type %d at offset 0x%lx size 0x%zx.\n",
+ hdr->type, soc_tplg_get_hdr_offset(tplg),
+ tplg->fw->size);
+ return -EINVAL;
+ }
+
/* big endian firmware objects not supported atm */
if (hdr->magic == cpu_to_be32(SND_SOC_TPLG_MAGIC)) {
dev_err(tplg->dev,
diff --git a/sound/soc/sti/sti_uniperif.c b/sound/soc/sti/sti_uniperif.c
index 39bcefe5eea0..488ef4ed8fba 100644
--- a/sound/soc/sti/sti_uniperif.c
+++ b/sound/soc/sti/sti_uniperif.c
@@ -11,6 +11,142 @@
#include "uniperif.h"
/*
+ * User frame size shall be 2, 4, 6 or 8 32-bits words length
+ * (i.e. 8, 16, 24 or 32 bytes)
+ * This constraint comes from allowed values for
+ * UNIPERIF_I2S_FMT_NUM_CH register
+ */
+#define UNIPERIF_MAX_FRAME_SZ 0x20
+#define UNIPERIF_ALLOWED_FRAME_SZ (0x08 | 0x10 | 0x18 | UNIPERIF_MAX_FRAME_SZ)
+
+int sti_uniperiph_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+ unsigned int rx_mask, int slots,
+ int slot_width)
+{
+ struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
+ struct uniperif *uni = priv->dai_data.uni;
+ int i, frame_size, avail_slots;
+
+ if (!UNIPERIF_TYPE_IS_TDM(uni)) {
+ dev_err(uni->dev, "cpu dai not in tdm mode\n");
+ return -EINVAL;
+ }
+
+ /* store info in unip context */
+ uni->tdm_slot.slots = slots;
+ uni->tdm_slot.slot_width = slot_width;
+ /* unip is unidirectionnal */
+ uni->tdm_slot.mask = (tx_mask != 0) ? tx_mask : rx_mask;
+
+ /* number of available timeslots */
+ for (i = 0, avail_slots = 0; i < uni->tdm_slot.slots; i++) {
+ if ((uni->tdm_slot.mask >> i) & 0x01)
+ avail_slots++;
+ }
+ uni->tdm_slot.avail_slots = avail_slots;
+
+ /* frame size in bytes */
+ frame_size = uni->tdm_slot.avail_slots * uni->tdm_slot.slot_width / 8;
+
+ /* check frame size is allowed */
+ if ((frame_size > UNIPERIF_MAX_FRAME_SZ) ||
+ (frame_size & ~(int)UNIPERIF_ALLOWED_FRAME_SZ)) {
+ dev_err(uni->dev, "frame size not allowed: %d bytes\n",
+ frame_size);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int sti_uniperiph_fix_tdm_chan(struct snd_pcm_hw_params *params,
+ struct snd_pcm_hw_rule *rule)
+{
+ struct uniperif *uni = rule->private;
+ struct snd_interval t;
+
+ t.min = uni->tdm_slot.avail_slots;
+ t.max = uni->tdm_slot.avail_slots;
+ t.openmin = 0;
+ t.openmax = 0;
+ t.integer = 0;
+
+ return snd_interval_refine(hw_param_interval(params, rule->var), &t);
+}
+
+int sti_uniperiph_fix_tdm_format(struct snd_pcm_hw_params *params,
+ struct snd_pcm_hw_rule *rule)
+{
+ struct uniperif *uni = rule->private;
+ struct snd_mask *maskp = hw_param_mask(params, rule->var);
+ u64 format;
+
+ switch (uni->tdm_slot.slot_width) {
+ case 16:
+ format = SNDRV_PCM_FMTBIT_S16_LE;
+ break;
+ case 32:
+ format = SNDRV_PCM_FMTBIT_S32_LE;
+ break;
+ default:
+ dev_err(uni->dev, "format not supported: %d bits\n",
+ uni->tdm_slot.slot_width);
+ return -EINVAL;
+ }
+
+ maskp->bits[0] &= (u_int32_t)format;
+ maskp->bits[1] &= (u_int32_t)(format >> 32);
+ /* clear remaining indexes */
+ memset(maskp->bits + 2, 0, (SNDRV_MASK_MAX - 64) / 8);
+
+ if (!maskp->bits[0] && !maskp->bits[1])
+ return -EINVAL;
+
+ return 0;
+}
+
+int sti_uniperiph_get_tdm_word_pos(struct uniperif *uni,
+ unsigned int *word_pos)
+{
+ int slot_width = uni->tdm_slot.slot_width / 8;
+ int slots_num = uni->tdm_slot.slots;
+ unsigned int slots_mask = uni->tdm_slot.mask;
+ int i, j, k;
+ unsigned int word16_pos[4];
+
+ /* word16_pos:
+ * word16_pos[0] = WORDX_LSB
+ * word16_pos[1] = WORDX_MSB,
+ * word16_pos[2] = WORDX+1_LSB
+ * word16_pos[3] = WORDX+1_MSB
+ */
+
+ /* set unip word position */
+ for (i = 0, j = 0, k = 0; (i < slots_num) && (k < WORD_MAX); i++) {
+ if ((slots_mask >> i) & 0x01) {
+ word16_pos[j] = i * slot_width;
+
+ if (slot_width == 4) {
+ word16_pos[j + 1] = word16_pos[j] + 2;
+ j++;
+ }
+ j++;
+
+ if (j > 3) {
+ word_pos[k] = word16_pos[1] |
+ (word16_pos[0] << 8) |
+ (word16_pos[3] << 16) |
+ (word16_pos[2] << 24);
+ j = 0;
+ k++;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
* sti_uniperiph_dai_create_ctrl
* This function is used to create Ctrl associated to DAI but also pcm device.
* Request is done by front end to associate ctrl with pcm device id
@@ -45,10 +181,16 @@ int sti_uniperiph_dai_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params,
struct snd_soc_dai *dai)
{
+ struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
+ struct uniperif *uni = priv->dai_data.uni;
struct snd_dmaengine_dai_dma_data *dma_data;
int transfer_size;
- transfer_size = params_channels(params) * UNIPERIF_FIFO_FRAMES;
+ if (uni->info->type == SND_ST_UNIPERIF_TYPE_TDM)
+ /* transfer size = user frame size (in 32-bits FIFO cell) */
+ transfer_size = snd_soc_params_to_frame_size(params) / 32;
+ else
+ transfer_size = params_channels(params) * UNIPERIF_FIFO_FRAMES;
dma_data = snd_soc_dai_get_dma_data(dai, substream);
dma_data->maxburst = transfer_size;
diff --git a/sound/soc/sti/uniperif.h b/sound/soc/sti/uniperif.h
index f0fd5a9944e9..eb9933c62ad6 100644
--- a/sound/soc/sti/uniperif.h
+++ b/sound/soc/sti/uniperif.h
@@ -25,7 +25,7 @@
writel_relaxed((((value) & mask) << shift), ip->base + offset)
/*
- * AUD_UNIPERIF_SOFT_RST reg
+ * UNIPERIF_SOFT_RST reg
*/
#define UNIPERIF_SOFT_RST_OFFSET(ip) 0x0000
@@ -50,7 +50,7 @@
UNIPERIF_SOFT_RST_SOFT_RST_MASK(ip))
/*
- * AUD_UNIPERIF_FIFO_DATA reg
+ * UNIPERIF_FIFO_DATA reg
*/
#define UNIPERIF_FIFO_DATA_OFFSET(ip) 0x0004
@@ -58,7 +58,7 @@
writel_relaxed(value, ip->base + UNIPERIF_FIFO_DATA_OFFSET(ip))
/*
- * AUD_UNIPERIF_CHANNEL_STA_REGN reg
+ * UNIPERIF_CHANNEL_STA_REGN reg
*/
#define UNIPERIF_CHANNEL_STA_REGN(ip, n) (0x0060 + (4 * n))
@@ -105,7 +105,7 @@
writel_relaxed(value, ip->base + UNIPERIF_CHANNEL_STA_REG5_OFFSET(ip))
/*
- * AUD_UNIPERIF_ITS reg
+ * UNIPERIF_ITS reg
*/
#define UNIPERIF_ITS_OFFSET(ip) 0x000C
@@ -143,7 +143,7 @@
0 : (BIT(UNIPERIF_ITS_UNDERFLOW_REC_FAILED_SHIFT(ip))))
/*
- * AUD_UNIPERIF_ITS_BCLR reg
+ * UNIPERIF_ITS_BCLR reg
*/
/* FIFO_ERROR */
@@ -160,7 +160,7 @@
writel_relaxed(value, ip->base + UNIPERIF_ITS_BCLR_OFFSET(ip))
/*
- * AUD_UNIPERIF_ITM reg
+ * UNIPERIF_ITM reg
*/
#define UNIPERIF_ITM_OFFSET(ip) 0x0018
@@ -188,7 +188,7 @@
0 : (BIT(UNIPERIF_ITM_UNDERFLOW_REC_FAILED_SHIFT(ip))))
/*
- * AUD_UNIPERIF_ITM_BCLR reg
+ * UNIPERIF_ITM_BCLR reg
*/
#define UNIPERIF_ITM_BCLR_OFFSET(ip) 0x001c
@@ -213,7 +213,7 @@
UNIPERIF_ITM_BCLR_DMA_ERROR_MASK(ip))
/*
- * AUD_UNIPERIF_ITM_BSET reg
+ * UNIPERIF_ITM_BSET reg
*/
#define UNIPERIF_ITM_BSET_OFFSET(ip) 0x0020
@@ -767,7 +767,7 @@
SET_UNIPERIF_REG(ip, \
UNIPERIF_CTRL_OFFSET(ip), \
UNIPERIF_CTRL_READER_OUT_SEL_SHIFT(ip), \
- CORAUD_UNIPERIF_CTRL_READER_OUT_SEL_MASK(ip), 1)
+ UNIPERIF_CTRL_READER_OUT_SEL_MASK(ip), 1)
/* UNDERFLOW_REC_WINDOW */
#define UNIPERIF_CTRL_UNDERFLOW_REC_WINDOW_SHIFT(ip) 20
@@ -1046,7 +1046,7 @@
UNIPERIF_STATUS_1_UNDERFLOW_DURATION_MASK(ip), value)
/*
- * AUD_UNIPERIF_CHANNEL_STA_REGN reg
+ * UNIPERIF_CHANNEL_STA_REGN reg
*/
#define UNIPERIF_CHANNEL_STA_REGN(ip, n) (0x0060 + (4 * n))
@@ -1057,7 +1057,7 @@
UNIPERIF_CHANNEL_STA_REGN(ip, n))
/*
- * AUD_UNIPERIF_USER_VALIDITY reg
+ * UNIPERIF_USER_VALIDITY reg
*/
#define UNIPERIF_USER_VALIDITY_OFFSET(ip) 0x0090
@@ -1101,12 +1101,136 @@
UNIPERIF_DBG_STANDBY_LEFT_SP_MASK(ip), value)
/*
+ * UNIPERIF_TDM_ENABLE
+ */
+#define UNIPERIF_TDM_ENABLE_OFFSET(ip) 0x0118
+#define GET_UNIPERIF_TDM_ENABLE(ip) \
+ readl_relaxed(ip->base + UNIPERIF_TDM_ENABLE_OFFSET(ip))
+#define SET_UNIPERIF_TDM_ENABLE(ip, value) \
+ writel_relaxed(value, ip->base + UNIPERIF_TDM_ENABLE_OFFSET(ip))
+
+/* TDM_ENABLE */
+#define UNIPERIF_TDM_ENABLE_EN_TDM_SHIFT(ip) 0x0
+#define UNIPERIF_TDM_ENABLE_EN_TDM_MASK(ip) 0x1
+#define GET_UNIPERIF_TDM_ENABLE_EN_TDM(ip) \
+ GET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_ENABLE_OFFSET(ip), \
+ UNIPERIF_TDM_ENABLE_EN_TDM_SHIFT(ip), \
+ UNIPERIF_TDM_ENABLE_EN_TDM_MASK(ip))
+#define SET_UNIPERIF_TDM_ENABLE_TDM_ENABLE(ip) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_ENABLE_OFFSET(ip), \
+ UNIPERIF_TDM_ENABLE_EN_TDM_SHIFT(ip), \
+ UNIPERIF_TDM_ENABLE_EN_TDM_MASK(ip), 1)
+#define SET_UNIPERIF_TDM_ENABLE_TDM_DISABLE(ip) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_ENABLE_OFFSET(ip), \
+ UNIPERIF_TDM_ENABLE_EN_TDM_SHIFT(ip), \
+ UNIPERIF_TDM_ENABLE_EN_TDM_MASK(ip), 0)
+
+/*
+ * UNIPERIF_TDM_FS_REF_FREQ
+ */
+#define UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip) 0x011c
+#define GET_UNIPERIF_TDM_FS_REF_FREQ(ip) \
+ readl_relaxed(ip->base + UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip))
+#define SET_UNIPERIF_TDM_FS_REF_FREQ(ip, value) \
+ writel_relaxed(value, ip->base + \
+ UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip))
+
+/* REF_FREQ */
+#define UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_SHIFT(ip) 0x0
+#define VALUE_UNIPERIF_TDM_FS_REF_FREQ_8KHZ(ip) 0
+#define VALUE_UNIPERIF_TDM_FS_REF_FREQ_16KHZ(ip) 1
+#define VALUE_UNIPERIF_TDM_FS_REF_FREQ_32KHZ(ip) 2
+#define VALUE_UNIPERIF_TDM_FS_REF_FREQ_48KHZ(ip) 3
+#define UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_MASK(ip) 0x3
+#define GET_UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ(ip) \
+ GET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_MASK(ip))
+#define SET_UNIPERIF_TDM_FS_REF_FREQ_8KHZ(ip) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_MASK(ip), \
+ VALUE_UNIPERIF_TDM_FS_REF_FREQ_8KHZ(ip))
+#define SET_UNIPERIF_TDM_FS_REF_FREQ_16KHZ(ip) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_MASK(ip), \
+ VALUE_UNIPERIF_TDM_FS_REF_FREQ_16KHZ(ip))
+#define SET_UNIPERIF_TDM_FS_REF_FREQ_32KHZ(ip) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_MASK(ip), \
+ VALUE_UNIPERIF_TDM_FS_REF_FREQ_32KHZ(ip))
+#define SET_UNIPERIF_TDM_FS_REF_FREQ_48KHZ(ip) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_FREQ_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_FREQ_REF_FREQ_MASK(ip), \
+ VALUE_UNIPERIF_TDM_FS_REF_FREQ_48KHZ(ip))
+
+/*
+ * UNIPERIF_TDM_FS_REF_DIV
+ */
+#define UNIPERIF_TDM_FS_REF_DIV_OFFSET(ip) 0x0120
+#define GET_UNIPERIF_TDM_FS_REF_DIV(ip) \
+ readl_relaxed(ip->base + UNIPERIF_TDM_FS_REF_DIV_OFFSET(ip))
+#define SET_UNIPERIF_TDM_FS_REF_DIV(ip, value) \
+ writel_relaxed(value, ip->base + \
+ UNIPERIF_TDM_FS_REF_DIV_OFFSET(ip))
+
+/* NUM_TIMESLOT */
+#define UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT_SHIFT(ip) 0x0
+#define UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT_MASK(ip) 0xff
+#define GET_UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT(ip) \
+ GET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_DIV_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT_MASK(ip))
+#define SET_UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT(ip, value) \
+ SET_UNIPERIF_REG(ip, \
+ UNIPERIF_TDM_FS_REF_DIV_OFFSET(ip), \
+ UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT_SHIFT(ip), \
+ UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT_MASK(ip), value)
+
+/*
+ * UNIPERIF_TDM_WORD_POS_X_Y
+ * 32 bits of UNIPERIF_TDM_WORD_POS_X_Y register shall be set in 1 shot
+ */
+#define UNIPERIF_TDM_WORD_POS_1_2_OFFSET(ip) 0x013c
+#define UNIPERIF_TDM_WORD_POS_3_4_OFFSET(ip) 0x0140
+#define UNIPERIF_TDM_WORD_POS_5_6_OFFSET(ip) 0x0144
+#define UNIPERIF_TDM_WORD_POS_7_8_OFFSET(ip) 0x0148
+#define GET_UNIPERIF_TDM_WORD_POS(ip, words) \
+ readl_relaxed(ip->base + UNIPERIF_TDM_WORD_POS_##words##_OFFSET(ip))
+#define SET_UNIPERIF_TDM_WORD_POS(ip, words, value) \
+ writel_relaxed(value, ip->base + \
+ UNIPERIF_TDM_WORD_POS_##words##_OFFSET(ip))
+/*
* uniperipheral IP capabilities
*/
#define UNIPERIF_FIFO_SIZE 70 /* FIFO is 70 cells deep */
#define UNIPERIF_FIFO_FRAMES 4 /* FDMA trigger limit in frames */
+#define UNIPERIF_TYPE_IS_HDMI(p) \
+ ((p)->info->type == SND_ST_UNIPERIF_TYPE_HDMI)
+#define UNIPERIF_TYPE_IS_PCM(p) \
+ ((p)->info->type == SND_ST_UNIPERIF_TYPE_PCM)
+#define UNIPERIF_TYPE_IS_SPDIF(p) \
+ ((p)->info->type == SND_ST_UNIPERIF_TYPE_SPDIF)
+#define UNIPERIF_TYPE_IS_IEC958(p) \
+ (UNIPERIF_TYPE_IS_HDMI(p) || \
+ UNIPERIF_TYPE_IS_SPDIF(p))
+#define UNIPERIF_TYPE_IS_TDM(p) \
+ ((p)->info->type == SND_ST_UNIPERIF_TYPE_TDM)
+
/*
* Uniperipheral IP revisions
*/
@@ -1125,10 +1249,11 @@ enum uniperif_version {
};
enum uniperif_type {
- SND_ST_UNIPERIF_PLAYER_TYPE_NONE,
- SND_ST_UNIPERIF_PLAYER_TYPE_HDMI,
- SND_ST_UNIPERIF_PLAYER_TYPE_PCM,
- SND_ST_UNIPERIF_PLAYER_TYPE_SPDIF
+ SND_ST_UNIPERIF_TYPE_NONE,
+ SND_ST_UNIPERIF_TYPE_HDMI,
+ SND_ST_UNIPERIF_TYPE_PCM,
+ SND_ST_UNIPERIF_TYPE_SPDIF,
+ SND_ST_UNIPERIF_TYPE_TDM
};
enum uniperif_state {
@@ -1145,9 +1270,17 @@ enum uniperif_iec958_encoding_mode {
UNIPERIF_IEC958_ENCODING_MODE_ENCODED
};
+enum uniperif_word_pos {
+ WORD_1_2,
+ WORD_3_4,
+ WORD_5_6,
+ WORD_7_8,
+ WORD_MAX
+};
+
struct uniperif_info {
int id; /* instance value of the uniperipheral IP */
- enum uniperif_type player_type;
+ enum uniperif_type type;
int underflow_enabled; /* Underflow recovery mode */
};
@@ -1156,12 +1289,20 @@ struct uniperif_iec958_settings {
struct snd_aes_iec958 iec958;
};
+struct dai_tdm_slot {
+ unsigned int mask;
+ int slots;
+ int slot_width;
+ unsigned int avail_slots;
+};
+
struct uniperif {
/* System information */
struct uniperif_info *info;
struct device *dev;
int ver; /* IP version, used by register access macros */
struct regmap_field *clk_sel;
+ struct regmap_field *valid_sel;
/* capabilities */
const struct snd_pcm_hardware *hw;
@@ -1192,6 +1333,7 @@ struct uniperif {
/* dai properties */
unsigned int daifmt;
+ struct dai_tdm_slot tdm_slot;
/* DAI callbacks */
const struct snd_soc_dai_ops *dai_ops;
@@ -1209,6 +1351,28 @@ struct sti_uniperiph_data {
struct sti_uniperiph_dai dai_data;
};
+static const struct snd_pcm_hardware uni_tdm_hw = {
+ .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER |
+ SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_MMAP |
+ SNDRV_PCM_INFO_MMAP_VALID,
+
+ .formats = SNDRV_PCM_FMTBIT_S32_LE | SNDRV_PCM_FMTBIT_S16_LE,
+
+ .rates = SNDRV_PCM_RATE_CONTINUOUS,
+ .rate_min = 8000,
+ .rate_max = 48000,
+
+ .channels_min = 1,
+ .channels_max = 32,
+
+ .periods_min = 2,
+ .periods_max = 10,
+
+ .period_bytes_min = 128,
+ .period_bytes_max = 64 * PAGE_SIZE,
+ .buffer_bytes_max = 256 * PAGE_SIZE
+};
+
/* uniperiph player*/
int uni_player_init(struct platform_device *pdev,
struct uniperif *uni_player);
@@ -1226,4 +1390,28 @@ int sti_uniperiph_dai_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params,
struct snd_soc_dai *dai);
+static inline int sti_uniperiph_get_user_frame_size(
+ struct snd_pcm_runtime *runtime)
+{
+ return (runtime->channels * snd_pcm_format_width(runtime->format) / 8);
+}
+
+static inline int sti_uniperiph_get_unip_tdm_frame_size(struct uniperif *uni)
+{
+ return (uni->tdm_slot.slots * uni->tdm_slot.slot_width / 8);
+}
+
+int sti_uniperiph_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+ unsigned int rx_mask, int slots,
+ int slot_width);
+
+int sti_uniperiph_get_tdm_word_pos(struct uniperif *uni,
+ unsigned int *word_pos);
+
+int sti_uniperiph_fix_tdm_chan(struct snd_pcm_hw_params *params,
+ struct snd_pcm_hw_rule *rule);
+
+int sti_uniperiph_fix_tdm_format(struct snd_pcm_hw_params *params,
+ struct snd_pcm_hw_rule *rule);
+
#endif
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 7aca6b92f718..ee1c7c245bc7 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -21,23 +21,14 @@
/* sys config registers definitions */
#define SYS_CFG_AUDIO_GLUE 0xA4
-#define SYS_CFG_AUDI0_GLUE_PCM_CLKX 8
/*
* Driver specific types.
*/
-#define UNIPERIF_PLAYER_TYPE_IS_HDMI(p) \
- ((p)->info->player_type == SND_ST_UNIPERIF_PLAYER_TYPE_HDMI)
-#define UNIPERIF_PLAYER_TYPE_IS_PCM(p) \
- ((p)->info->player_type == SND_ST_UNIPERIF_PLAYER_TYPE_PCM)
-#define UNIPERIF_PLAYER_TYPE_IS_SPDIF(p) \
- ((p)->info->player_type == SND_ST_UNIPERIF_PLAYER_TYPE_SPDIF)
-#define UNIPERIF_PLAYER_TYPE_IS_IEC958(p) \
- (UNIPERIF_PLAYER_TYPE_IS_HDMI(p) || \
- UNIPERIF_PLAYER_TYPE_IS_SPDIF(p))
#define UNIPERIF_PLAYER_CLK_ADJ_MIN -999999
#define UNIPERIF_PLAYER_CLK_ADJ_MAX 1000000
+#define UNIPERIF_PLAYER_I2S_OUT 1 /* player id connected to I2S/TDM TX bus */
/*
* Note: snd_pcm_hardware is linked to DMA controller but is declared here to
@@ -444,18 +435,11 @@ static int uni_player_prepare_pcm(struct uniperif *player,
/* Force slot width to 32 in I2S mode (HW constraint) */
if ((player->daifmt & SND_SOC_DAIFMT_FORMAT_MASK) ==
- SND_SOC_DAIFMT_I2S) {
+ SND_SOC_DAIFMT_I2S)
slot_width = 32;
- } else {
- switch (runtime->format) {
- case SNDRV_PCM_FORMAT_S16_LE:
- slot_width = 16;
- break;
- default:
- slot_width = 32;
- break;
- }
- }
+ else
+ slot_width = snd_pcm_format_width(runtime->format);
+
output_frame_size = slot_width * runtime->channels;
clk_div = player->mclk / runtime->rate;
@@ -530,7 +514,6 @@ static int uni_player_prepare_pcm(struct uniperif *player,
SET_UNIPERIF_CONFIG_ONE_BIT_AUD_DISABLE(player);
SET_UNIPERIF_I2S_FMT_ORDER_MSB(player);
- SET_UNIPERIF_I2S_FMT_SCLK_EDGE_FALLING(player);
/* No iec958 formatting as outputting to DAC */
SET_UNIPERIF_CTRL_SPDIF_FMT_OFF(player);
@@ -538,6 +521,55 @@ static int uni_player_prepare_pcm(struct uniperif *player,
return 0;
}
+static int uni_player_prepare_tdm(struct uniperif *player,
+ struct snd_pcm_runtime *runtime)
+{
+ int tdm_frame_size; /* unip tdm frame size in bytes */
+ int user_frame_size; /* user tdm frame size in bytes */
+ /* default unip TDM_WORD_POS_X_Y */
+ unsigned int word_pos[4] = {
+ 0x04060002, 0x0C0E080A, 0x14161012, 0x1C1E181A};
+ int freq, ret;
+
+ tdm_frame_size =
+ sti_uniperiph_get_unip_tdm_frame_size(player);
+ user_frame_size =
+ sti_uniperiph_get_user_frame_size(runtime);
+
+ /* fix 16/0 format */
+ SET_UNIPERIF_CONFIG_MEM_FMT_16_0(player);
+ SET_UNIPERIF_I2S_FMT_DATA_SIZE_32(player);
+
+ /* number of words inserted on the TDM line */
+ SET_UNIPERIF_I2S_FMT_NUM_CH(player, user_frame_size / 4 / 2);
+
+ SET_UNIPERIF_I2S_FMT_ORDER_MSB(player);
+ SET_UNIPERIF_I2S_FMT_ALIGN_LEFT(player);
+
+ /* Enable the tdm functionality */
+ SET_UNIPERIF_TDM_ENABLE_TDM_ENABLE(player);
+
+ /* number of 8 bits timeslots avail in unip tdm frame */
+ SET_UNIPERIF_TDM_FS_REF_DIV_NUM_TIMESLOT(player, tdm_frame_size);
+
+ /* set the timeslot allocation for words in FIFO */
+ sti_uniperiph_get_tdm_word_pos(player, word_pos);
+ SET_UNIPERIF_TDM_WORD_POS(player, 1_2, word_pos[WORD_1_2]);
+ SET_UNIPERIF_TDM_WORD_POS(player, 3_4, word_pos[WORD_3_4]);
+ SET_UNIPERIF_TDM_WORD_POS(player, 5_6, word_pos[WORD_5_6]);
+ SET_UNIPERIF_TDM_WORD_POS(player, 7_8, word_pos[WORD_7_8]);
+
+ /* set unip clk rate (not done vai set_sysclk ops) */
+ freq = runtime->rate * tdm_frame_size * 8;
+ mutex_lock(&player->ctrl_lock);
+ ret = uni_player_clk_set_rate(player, freq);
+ if (!ret)
+ player->mclk = freq;
+ mutex_unlock(&player->ctrl_lock);
+
+ return 0;
+}
+
/*
* ALSA uniperipheral iec958 controls
*/
@@ -668,11 +700,29 @@ static int uni_player_startup(struct snd_pcm_substream *substream,
{
struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
struct uniperif *player = priv->dai_data.uni;
+ int ret;
+
player->substream = substream;
player->clk_adj = 0;
- return 0;
+ if (!UNIPERIF_TYPE_IS_TDM(player))
+ return 0;
+
+ /* refine hw constraint in tdm mode */
+ ret = snd_pcm_hw_rule_add(substream->runtime, 0,
+ SNDRV_PCM_HW_PARAM_CHANNELS,
+ sti_uniperiph_fix_tdm_chan,
+ player, SNDRV_PCM_HW_PARAM_CHANNELS,
+ -1);
+ if (ret < 0)
+ return ret;
+
+ return snd_pcm_hw_rule_add(substream->runtime, 0,
+ SNDRV_PCM_HW_PARAM_FORMAT,
+ sti_uniperiph_fix_tdm_format,
+ player, SNDRV_PCM_HW_PARAM_FORMAT,
+ -1);
}
static int uni_player_set_sysclk(struct snd_soc_dai *dai, int clk_id,
@@ -682,7 +732,7 @@ static int uni_player_set_sysclk(struct snd_soc_dai *dai, int clk_id,
struct uniperif *player = priv->dai_data.uni;
int ret;
- if (dir == SND_SOC_CLOCK_IN)
+ if (UNIPERIF_TYPE_IS_TDM(player) || (dir == SND_SOC_CLOCK_IN))
return 0;
if (clk_id != 0)
@@ -714,7 +764,13 @@ static int uni_player_prepare(struct snd_pcm_substream *substream,
}
/* Calculate transfer size (in fifo cells and bytes) for frame count */
- transfer_size = runtime->channels * UNIPERIF_FIFO_FRAMES;
+ if (player->info->type == SND_ST_UNIPERIF_TYPE_TDM) {
+ /* transfer size = user frame size (in 32 bits FIFO cell) */
+ transfer_size =
+ sti_uniperiph_get_user_frame_size(runtime) / 4;
+ } else {
+ transfer_size = runtime->channels * UNIPERIF_FIFO_FRAMES;
+ }
/* Calculate number of empty cells available before asserting DREQ */
if (player->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0) {
@@ -738,16 +794,19 @@ static int uni_player_prepare(struct snd_pcm_substream *substream,
SET_UNIPERIF_CONFIG_DMA_TRIG_LIMIT(player, trigger_limit);
/* Uniperipheral setup depends on player type */
- switch (player->info->player_type) {
- case SND_ST_UNIPERIF_PLAYER_TYPE_HDMI:
+ switch (player->info->type) {
+ case SND_ST_UNIPERIF_TYPE_HDMI:
ret = uni_player_prepare_iec958(player, runtime);
break;
- case SND_ST_UNIPERIF_PLAYER_TYPE_PCM:
+ case SND_ST_UNIPERIF_TYPE_PCM:
ret = uni_player_prepare_pcm(player, runtime);
break;
- case SND_ST_UNIPERIF_PLAYER_TYPE_SPDIF:
+ case SND_ST_UNIPERIF_TYPE_SPDIF:
ret = uni_player_prepare_iec958(player, runtime);
break;
+ case SND_ST_UNIPERIF_TYPE_TDM:
+ ret = uni_player_prepare_tdm(player, runtime);
+ break;
default:
dev_err(player->dev, "invalid player type");
return -EINVAL;
@@ -852,8 +911,8 @@ static int uni_player_start(struct uniperif *player)
* will not take affect and hang the player.
*/
if (player->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
- if (UNIPERIF_PLAYER_TYPE_IS_IEC958(player))
- SET_UNIPERIF_CTRL_SPDIF_FMT_ON(player);
+ if (UNIPERIF_TYPE_IS_IEC958(player))
+ SET_UNIPERIF_CTRL_SPDIF_FMT_ON(player);
/* Force channel status update (no update if clk disable) */
if (player->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
@@ -954,27 +1013,30 @@ static void uni_player_shutdown(struct snd_pcm_substream *substream,
player->substream = NULL;
}
-static int uni_player_parse_dt_clk_glue(struct platform_device *pdev,
- struct uniperif *player)
+static int uni_player_parse_dt_audio_glue(struct platform_device *pdev,
+ struct uniperif *player)
{
- int bit_offset;
struct device_node *node = pdev->dev.of_node;
struct regmap *regmap;
-
- bit_offset = SYS_CFG_AUDI0_GLUE_PCM_CLKX + player->info->id;
+ struct reg_field regfield[2] = {
+ /* PCM_CLK_SEL */
+ REG_FIELD(SYS_CFG_AUDIO_GLUE,
+ 8 + player->info->id,
+ 8 + player->info->id),
+ /* PCMP_VALID_SEL */
+ REG_FIELD(SYS_CFG_AUDIO_GLUE, 0, 1)
+ };
regmap = syscon_regmap_lookup_by_phandle(node, "st,syscfg");
- if (regmap) {
- struct reg_field regfield =
- REG_FIELD(SYS_CFG_AUDIO_GLUE, bit_offset, bit_offset);
-
- player->clk_sel = regmap_field_alloc(regmap, regfield);
- } else {
+ if (!regmap) {
dev_err(&pdev->dev, "sti-audio-clk-glue syscf not found\n");
return -EINVAL;
}
+ player->clk_sel = regmap_field_alloc(regmap, regfield[0]);
+ player->valid_sel = regmap_field_alloc(regmap, regfield[1]);
+
return 0;
}
@@ -1012,19 +1074,21 @@ static int uni_player_parse_dt(struct platform_device *pdev,
}
if (strcasecmp(mode, "hdmi") == 0)
- info->player_type = SND_ST_UNIPERIF_PLAYER_TYPE_HDMI;
+ info->type = SND_ST_UNIPERIF_TYPE_HDMI;
else if (strcasecmp(mode, "pcm") == 0)
- info->player_type = SND_ST_UNIPERIF_PLAYER_TYPE_PCM;
+ info->type = SND_ST_UNIPERIF_TYPE_PCM;
else if (strcasecmp(mode, "spdif") == 0)
- info->player_type = SND_ST_UNIPERIF_PLAYER_TYPE_SPDIF;
+ info->type = SND_ST_UNIPERIF_TYPE_SPDIF;
+ else if (strcasecmp(mode, "tdm") == 0)
+ info->type = SND_ST_UNIPERIF_TYPE_TDM;
else
- info->player_type = SND_ST_UNIPERIF_PLAYER_TYPE_NONE;
+ info->type = SND_ST_UNIPERIF_TYPE_NONE;
/* Save the info structure */
player->info = info;
- /* Get the PCM_CLK_SEL bit from audio-glue-ctrl SoC register */
- if (uni_player_parse_dt_clk_glue(pdev, player))
+ /* Get PCM_CLK_SEL & PCMP_VALID_SEL from audio-glue-ctrl SoC reg */
+ if (uni_player_parse_dt_audio_glue(pdev, player))
return -EINVAL;
return 0;
@@ -1037,7 +1101,8 @@ static const struct snd_soc_dai_ops uni_player_dai_ops = {
.trigger = uni_player_trigger,
.hw_params = sti_uniperiph_dai_hw_params,
.set_fmt = sti_uniperiph_dai_set_fmt,
- .set_sysclk = uni_player_set_sysclk
+ .set_sysclk = uni_player_set_sysclk,
+ .set_tdm_slot = sti_uniperiph_set_tdm_slot
};
int uni_player_init(struct platform_device *pdev,
@@ -1047,7 +1112,6 @@ int uni_player_init(struct platform_device *pdev,
player->dev = &pdev->dev;
player->state = UNIPERIF_STATE_STOPPED;
- player->hw = &uni_player_pcm_hw;
player->dai_ops = &uni_player_dai_ops;
ret = uni_player_parse_dt(pdev, player);
@@ -1057,6 +1121,11 @@ int uni_player_init(struct platform_device *pdev,
return ret;
}
+ if (UNIPERIF_TYPE_IS_TDM(player))
+ player->hw = &uni_tdm_hw;
+ else
+ player->hw = &uni_player_pcm_hw;
+
/* Get uniperif resource */
player->clk = of_clk_get(pdev->dev.of_node, 0);
if (IS_ERR(player->clk))
@@ -1073,6 +1142,17 @@ int uni_player_init(struct platform_device *pdev,
}
}
+ /* connect to I2S/TDM TX bus */
+ if (player->valid_sel &&
+ (player->info->id == UNIPERIF_PLAYER_I2S_OUT)) {
+ ret = regmap_field_write(player->valid_sel, player->info->id);
+ if (ret) {
+ dev_err(player->dev,
+ "%s: unable to connect to tdm bus", __func__);
+ return ret;
+ }
+ }
+
ret = devm_request_irq(&pdev->dev, player->irq,
uni_player_irq_handler, IRQF_SHARED,
dev_name(&pdev->dev), player);
@@ -1087,7 +1167,7 @@ int uni_player_init(struct platform_device *pdev,
SET_UNIPERIF_CTRL_SPDIF_LAT_OFF(player);
SET_UNIPERIF_CONFIG_IDLE_MOD_DISABLE(player);
- if (UNIPERIF_PLAYER_TYPE_IS_IEC958(player)) {
+ if (UNIPERIF_TYPE_IS_IEC958(player)) {
/* Set default iec958 status bits */
/* Consumer, PCM, copyright, 2ch, mode 0 */
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index 8a0eb2050169..eb74a328c928 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -73,55 +73,10 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id)
return ret;
}
-static int uni_reader_prepare(struct snd_pcm_substream *substream,
- struct snd_soc_dai *dai)
+static int uni_reader_prepare_pcm(struct snd_pcm_runtime *runtime,
+ struct uniperif *reader)
{
- struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
- struct uniperif *reader = priv->dai_data.uni;
- struct snd_pcm_runtime *runtime = substream->runtime;
- int transfer_size, trigger_limit;
int slot_width;
- int count = 10;
-
- /* The reader should be stopped */
- if (reader->state != UNIPERIF_STATE_STOPPED) {
- dev_err(reader->dev, "%s: invalid reader state %d", __func__,
- reader->state);
- return -EINVAL;
- }
-
- /* Calculate transfer size (in fifo cells and bytes) for frame count */
- transfer_size = runtime->channels * UNIPERIF_FIFO_FRAMES;
-
- /* Calculate number of empty cells available before asserting DREQ */
- if (reader->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
- trigger_limit = UNIPERIF_FIFO_SIZE - transfer_size;
- else
- /*
- * Since SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0
- * FDMA_TRIGGER_LIMIT also controls when the state switches
- * from OFF or STANDBY to AUDIO DATA.
- */
- trigger_limit = transfer_size;
-
- /* Trigger limit must be an even number */
- if ((!trigger_limit % 2) ||
- (trigger_limit != 1 && transfer_size % 2) ||
- (trigger_limit > UNIPERIF_CONFIG_DMA_TRIG_LIMIT_MASK(reader))) {
- dev_err(reader->dev, "invalid trigger limit %d", trigger_limit);
- return -EINVAL;
- }
-
- SET_UNIPERIF_CONFIG_DMA_TRIG_LIMIT(reader, trigger_limit);
-
- switch (reader->daifmt & SND_SOC_DAIFMT_INV_MASK) {
- case SND_SOC_DAIFMT_IB_IF:
- case SND_SOC_DAIFMT_NB_IF:
- SET_UNIPERIF_I2S_FMT_LR_POL_HIG(reader);
- break;
- default:
- SET_UNIPERIF_I2S_FMT_LR_POL_LOW(reader);
- }
/* Force slot width to 32 in I2S mode */
if ((reader->daifmt & SND_SOC_DAIFMT_FORMAT_MASK)
@@ -173,6 +128,109 @@ static int uni_reader_prepare(struct snd_pcm_substream *substream,
return -EINVAL;
}
+ /* Number of channels must be even */
+ if ((runtime->channels % 2) || (runtime->channels < 2) ||
+ (runtime->channels > 10)) {
+ dev_err(reader->dev, "%s: invalid nb of channels", __func__);
+ return -EINVAL;
+ }
+
+ SET_UNIPERIF_I2S_FMT_NUM_CH(reader, runtime->channels / 2);
+ SET_UNIPERIF_I2S_FMT_ORDER_MSB(reader);
+
+ return 0;
+}
+
+static int uni_reader_prepare_tdm(struct snd_pcm_runtime *runtime,
+ struct uniperif *reader)
+{
+ int frame_size; /* user tdm frame size in bytes */
+ /* default unip TDM_WORD_POS_X_Y */
+ unsigned int word_pos[4] = {
+ 0x04060002, 0x0C0E080A, 0x14161012, 0x1C1E181A};
+
+ frame_size = sti_uniperiph_get_user_frame_size(runtime);
+
+ /* fix 16/0 format */
+ SET_UNIPERIF_CONFIG_MEM_FMT_16_0(reader);
+ SET_UNIPERIF_I2S_FMT_DATA_SIZE_32(reader);
+
+ /* number of words inserted on the TDM line */
+ SET_UNIPERIF_I2S_FMT_NUM_CH(reader, frame_size / 4 / 2);
+
+ SET_UNIPERIF_I2S_FMT_ORDER_MSB(reader);
+ SET_UNIPERIF_I2S_FMT_ALIGN_LEFT(reader);
+ SET_UNIPERIF_TDM_ENABLE_TDM_ENABLE(reader);
+
+ /*
+ * set the timeslots allocation for words in FIFO
+ *
+ * HW bug: (LSB word < MSB word) => this config is not possible
+ * So if we want (LSB word < MSB) word, then it shall be
+ * handled by user
+ */
+ sti_uniperiph_get_tdm_word_pos(reader, word_pos);
+ SET_UNIPERIF_TDM_WORD_POS(reader, 1_2, word_pos[WORD_1_2]);
+ SET_UNIPERIF_TDM_WORD_POS(reader, 3_4, word_pos[WORD_3_4]);
+ SET_UNIPERIF_TDM_WORD_POS(reader, 5_6, word_pos[WORD_5_6]);
+ SET_UNIPERIF_TDM_WORD_POS(reader, 7_8, word_pos[WORD_7_8]);
+
+ return 0;
+}
+
+static int uni_reader_prepare(struct snd_pcm_substream *substream,
+ struct snd_soc_dai *dai)
+{
+ struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
+ struct uniperif *reader = priv->dai_data.uni;
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ int transfer_size, trigger_limit, ret;
+ int count = 10;
+
+ /* The reader should be stopped */
+ if (reader->state != UNIPERIF_STATE_STOPPED) {
+ dev_err(reader->dev, "%s: invalid reader state %d", __func__,
+ reader->state);
+ return -EINVAL;
+ }
+
+ /* Calculate transfer size (in fifo cells and bytes) for frame count */
+ if (reader->info->type == SND_ST_UNIPERIF_TYPE_TDM) {
+ /* transfer size = unip frame size (in 32 bits FIFO cell) */
+ transfer_size =
+ sti_uniperiph_get_user_frame_size(runtime) / 4;
+ } else {
+ transfer_size = runtime->channels * UNIPERIF_FIFO_FRAMES;
+ }
+
+ /* Calculate number of empty cells available before asserting DREQ */
+ if (reader->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
+ trigger_limit = UNIPERIF_FIFO_SIZE - transfer_size;
+ else
+ /*
+ * Since SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0
+ * FDMA_TRIGGER_LIMIT also controls when the state switches
+ * from OFF or STANDBY to AUDIO DATA.
+ */
+ trigger_limit = transfer_size;
+
+ /* Trigger limit must be an even number */
+ if ((!trigger_limit % 2) ||
+ (trigger_limit != 1 && transfer_size % 2) ||
+ (trigger_limit > UNIPERIF_CONFIG_DMA_TRIG_LIMIT_MASK(reader))) {
+ dev_err(reader->dev, "invalid trigger limit %d", trigger_limit);
+ return -EINVAL;
+ }
+
+ SET_UNIPERIF_CONFIG_DMA_TRIG_LIMIT(reader, trigger_limit);
+
+ if (UNIPERIF_TYPE_IS_TDM(reader))
+ ret = uni_reader_prepare_tdm(runtime, reader);
+ else
+ ret = uni_reader_prepare_pcm(runtime, reader);
+ if (ret)
+ return ret;
+
switch (reader->daifmt & SND_SOC_DAIFMT_FORMAT_MASK) {
case SND_SOC_DAIFMT_I2S:
SET_UNIPERIF_I2S_FMT_ALIGN_LEFT(reader);
@@ -191,21 +249,26 @@ static int uni_reader_prepare(struct snd_pcm_substream *substream,
return -EINVAL;
}
- SET_UNIPERIF_I2S_FMT_ORDER_MSB(reader);
-
- /* Data clocking (changing) on the rising edge */
- SET_UNIPERIF_I2S_FMT_SCLK_EDGE_RISING(reader);
-
- /* Number of channels must be even */
-
- if ((runtime->channels % 2) || (runtime->channels < 2) ||
- (runtime->channels > 10)) {
- dev_err(reader->dev, "%s: invalid nb of channels", __func__);
- return -EINVAL;
+ /* Data clocking (changing) on the rising/falling edge */
+ switch (reader->daifmt & SND_SOC_DAIFMT_INV_MASK) {
+ case SND_SOC_DAIFMT_NB_NF:
+ SET_UNIPERIF_I2S_FMT_LR_POL_LOW(reader);
+ SET_UNIPERIF_I2S_FMT_SCLK_EDGE_RISING(reader);
+ break;
+ case SND_SOC_DAIFMT_NB_IF:
+ SET_UNIPERIF_I2S_FMT_LR_POL_HIG(reader);
+ SET_UNIPERIF_I2S_FMT_SCLK_EDGE_RISING(reader);
+ break;
+ case SND_SOC_DAIFMT_IB_NF:
+ SET_UNIPERIF_I2S_FMT_LR_POL_LOW(reader);
+ SET_UNIPERIF_I2S_FMT_SCLK_EDGE_FALLING(reader);
+ break;
+ case SND_SOC_DAIFMT_IB_IF:
+ SET_UNIPERIF_I2S_FMT_LR_POL_HIG(reader);
+ SET_UNIPERIF_I2S_FMT_SCLK_EDGE_FALLING(reader);
+ break;
}
- SET_UNIPERIF_I2S_FMT_NUM_CH(reader, runtime->channels / 2);
-
/* Clear any pending interrupts */
SET_UNIPERIF_ITS_BCLR(reader, GET_UNIPERIF_ITS(reader));
@@ -293,6 +356,32 @@ static int uni_reader_trigger(struct snd_pcm_substream *substream,
}
}
+static int uni_reader_startup(struct snd_pcm_substream *substream,
+ struct snd_soc_dai *dai)
+{
+ struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
+ struct uniperif *reader = priv->dai_data.uni;
+ int ret;
+
+ if (!UNIPERIF_TYPE_IS_TDM(reader))
+ return 0;
+
+ /* refine hw constraint in tdm mode */
+ ret = snd_pcm_hw_rule_add(substream->runtime, 0,
+ SNDRV_PCM_HW_PARAM_CHANNELS,
+ sti_uniperiph_fix_tdm_chan,
+ reader, SNDRV_PCM_HW_PARAM_CHANNELS,
+ -1);
+ if (ret < 0)
+ return ret;
+
+ return snd_pcm_hw_rule_add(substream->runtime, 0,
+ SNDRV_PCM_HW_PARAM_FORMAT,
+ sti_uniperiph_fix_tdm_format,
+ reader, SNDRV_PCM_HW_PARAM_FORMAT,
+ -1);
+}
+
static void uni_reader_shutdown(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai)
{
@@ -310,6 +399,7 @@ static int uni_reader_parse_dt(struct platform_device *pdev,
{
struct uniperif_info *info;
struct device_node *node = pdev->dev.of_node;
+ const char *mode;
/* Allocate memory for the info structure */
info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
@@ -322,6 +412,17 @@ static int uni_reader_parse_dt(struct platform_device *pdev,
return -EINVAL;
}
+ /* Read the device mode property */
+ if (of_property_read_string(node, "st,mode", &mode)) {
+ dev_err(&pdev->dev, "uniperipheral mode not defined");
+ return -EINVAL;
+ }
+
+ if (strcasecmp(mode, "tdm") == 0)
+ info->type = SND_ST_UNIPERIF_TYPE_TDM;
+ else
+ info->type = SND_ST_UNIPERIF_TYPE_PCM;
+
/* Save the info structure */
reader->info = info;
@@ -329,11 +430,13 @@ static int uni_reader_parse_dt(struct platform_device *pdev,
}
static const struct snd_soc_dai_ops uni_reader_dai_ops = {
+ .startup = uni_reader_startup,
.shutdown = uni_reader_shutdown,
.prepare = uni_reader_prepare,
.trigger = uni_reader_trigger,
.hw_params = sti_uniperiph_dai_hw_params,
.set_fmt = sti_uniperiph_dai_set_fmt,
+ .set_tdm_slot = sti_uniperiph_set_tdm_slot
};
int uni_reader_init(struct platform_device *pdev,
@@ -343,7 +446,6 @@ int uni_reader_init(struct platform_device *pdev,
reader->dev = &pdev->dev;
reader->state = UNIPERIF_STATE_STOPPED;
- reader->hw = &uni_reader_pcm_hw;
reader->dai_ops = &uni_reader_dai_ops;
ret = uni_reader_parse_dt(pdev, reader);
@@ -352,6 +454,11 @@ int uni_reader_init(struct platform_device *pdev,
return ret;
}
+ if (UNIPERIF_TYPE_IS_TDM(reader))
+ reader->hw = &uni_tdm_hw;
+ else
+ reader->hw = &uni_reader_pcm_hw;
+
ret = devm_request_irq(&pdev->dev, reader->irq,
uni_reader_irq_handler, IRQF_SHARED,
dev_name(&pdev->dev), reader);
diff --git a/tools/Makefile b/tools/Makefile
index 6bf68fe7dd29..f10b64d8c674 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -16,6 +16,7 @@ help:
@echo ' gpio - GPIO tools'
@echo ' hv - tools used when in Hyper-V clients'
@echo ' iio - IIO tools'
+ @echo ' kvm_stat - top-like utility for displaying kvm statistics'
@echo ' lguest - a minimal 32-bit x86 hypervisor'
@echo ' net - misc networking tools'
@echo ' perf - Linux performance measurement and analysis tool'
@@ -110,10 +111,13 @@ tmon_install:
freefall_install:
$(call descend,laptop/$(@:_install=),install)
+kvm_stat_install:
+ $(call descend,kvm/$(@:_install=),install)
+
install: acpi_install cgroup_install cpupower_install hv_install firewire_install lguest_install \
perf_install selftests_install turbostat_install usb_install \
virtio_install vm_install net_install x86_energy_perf_policy_install \
- tmon_install freefall_install objtool_install
+ tmon_install freefall_install objtool_install kvm_stat_install
acpi_clean:
$(call descend,power/acpi,clean)
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index ee566e8bd1cf..27f3583193e6 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -58,8 +58,8 @@ quiet_cmd_mkdir = MKDIR $(dir $@)
quiet_cmd_cc_o_c = CC $@
cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
-quiet_cmd_cc_i_c = CPP $@
- cmd_cc_i_c = $(CC) $(c_flags) -E -o $@ $<
+quiet_cmd_cpp_i_c = CPP $@
+ cmd_cpp_i_c = $(CC) $(c_flags) -E -o $@ $<
quiet_cmd_cc_s_c = AS $@
cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
@@ -83,11 +83,11 @@ $(OUTPUT)%.o: %.S FORCE
$(OUTPUT)%.i: %.c FORCE
$(call rule_mkdir)
- $(call if_changed_dep,cc_i_c)
+ $(call if_changed_dep,cpp_i_c)
$(OUTPUT)%.s: %.S FORCE
$(call rule_mkdir)
- $(call if_changed_dep,cc_i_c)
+ $(call if_changed_dep,cpp_i_c)
$(OUTPUT)%.s: %.c FORCE
$(call rule_mkdir)
diff --git a/tools/kvm/kvm_stat/Makefile b/tools/kvm/kvm_stat/Makefile
new file mode 100644
index 000000000000..5b1cba57e3b3
--- /dev/null
+++ b/tools/kvm/kvm_stat/Makefile
@@ -0,0 +1,41 @@
+include ../../scripts/Makefile.include
+include ../../scripts/utilities.mak
+BINDIR=usr/bin
+MANDIR=usr/share/man
+MAN1DIR=$(MANDIR)/man1
+
+MAN1=kvm_stat.1
+
+A2X=a2x
+a2x_path := $(call get-executable,$(A2X))
+
+all: man
+
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ ifneq ($(V),1)
+ QUIET_A2X = @echo ' A2X '$@;
+ endif
+endif
+
+%.1: %.txt
+ifeq ($(a2x_path),)
+ $(error "You need to install asciidoc for man pages")
+else
+ $(QUIET_A2X)$(A2X) --doctype manpage --format manpage $<
+endif
+
+clean:
+ rm -f $(MAN1)
+
+man: $(MAN1)
+
+install-man: man
+ install -d -m 755 $(INSTALL_ROOT)/$(MAN1DIR)
+ install -m 644 kvm_stat.1 $(INSTALL_ROOT)/$(MAN1DIR)
+
+install-tools:
+ install -d -m 755 $(INSTALL_ROOT)/$(BINDIR)
+ install -m 755 -p "kvm_stat" "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)"
+
+install: install-tools install-man
+.PHONY: all clean man install-tools install-man install
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
new file mode 100755
index 000000000000..581278c58488
--- /dev/null
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -0,0 +1,1127 @@
+#!/usr/bin/python
+#
+# top-like utility for displaying kvm statistics
+#
+# Copyright 2006-2008 Qumranet Technologies
+# Copyright 2008-2011 Red Hat, Inc.
+#
+# Authors:
+# Avi Kivity <avi@redhat.com>
+#
+# This work is licensed under the terms of the GNU GPL, version 2. See
+# the COPYING file in the top-level directory.
+"""The kvm_stat module outputs statistics about running KVM VMs
+
+Three different ways of output formatting are available:
+- as a top-like text ui
+- in a key -> value format
+- in an all keys, all values format
+
+The data is sampled from the KVM's debugfs entries and its perf events.
+"""
+
+import curses
+import sys
+import os
+import time
+import optparse
+import ctypes
+import fcntl
+import resource
+import struct
+import re
+from collections import defaultdict
+from time import sleep
+
+VMX_EXIT_REASONS = {
+ 'EXCEPTION_NMI': 0,
+ 'EXTERNAL_INTERRUPT': 1,
+ 'TRIPLE_FAULT': 2,
+ 'PENDING_INTERRUPT': 7,
+ 'NMI_WINDOW': 8,
+ 'TASK_SWITCH': 9,
+ 'CPUID': 10,
+ 'HLT': 12,
+ 'INVLPG': 14,
+ 'RDPMC': 15,
+ 'RDTSC': 16,
+ 'VMCALL': 18,
+ 'VMCLEAR': 19,
+ 'VMLAUNCH': 20,
+ 'VMPTRLD': 21,
+ 'VMPTRST': 22,
+ 'VMREAD': 23,
+ 'VMRESUME': 24,
+ 'VMWRITE': 25,
+ 'VMOFF': 26,
+ 'VMON': 27,
+ 'CR_ACCESS': 28,
+ 'DR_ACCESS': 29,
+ 'IO_INSTRUCTION': 30,
+ 'MSR_READ': 31,
+ 'MSR_WRITE': 32,
+ 'INVALID_STATE': 33,
+ 'MWAIT_INSTRUCTION': 36,
+ 'MONITOR_INSTRUCTION': 39,
+ 'PAUSE_INSTRUCTION': 40,
+ 'MCE_DURING_VMENTRY': 41,
+ 'TPR_BELOW_THRESHOLD': 43,
+ 'APIC_ACCESS': 44,
+ 'EPT_VIOLATION': 48,
+ 'EPT_MISCONFIG': 49,
+ 'WBINVD': 54,
+ 'XSETBV': 55,
+ 'APIC_WRITE': 56,
+ 'INVPCID': 58,
+}
+
+SVM_EXIT_REASONS = {
+ 'READ_CR0': 0x000,
+ 'READ_CR3': 0x003,
+ 'READ_CR4': 0x004,
+ 'READ_CR8': 0x008,
+ 'WRITE_CR0': 0x010,
+ 'WRITE_CR3': 0x013,
+ 'WRITE_CR4': 0x014,
+ 'WRITE_CR8': 0x018,
+ 'READ_DR0': 0x020,
+ 'READ_DR1': 0x021,
+ 'READ_DR2': 0x022,
+ 'READ_DR3': 0x023,
+ 'READ_DR4': 0x024,
+ 'READ_DR5': 0x025,
+ 'READ_DR6': 0x026,
+ 'READ_DR7': 0x027,
+ 'WRITE_DR0': 0x030,
+ 'WRITE_DR1': 0x031,
+ 'WRITE_DR2': 0x032,
+ 'WRITE_DR3': 0x033,
+ 'WRITE_DR4': 0x034,
+ 'WRITE_DR5': 0x035,
+ 'WRITE_DR6': 0x036,
+ 'WRITE_DR7': 0x037,
+ 'EXCP_BASE': 0x040,
+ 'INTR': 0x060,
+ 'NMI': 0x061,
+ 'SMI': 0x062,
+ 'INIT': 0x063,
+ 'VINTR': 0x064,
+ 'CR0_SEL_WRITE': 0x065,
+ 'IDTR_READ': 0x066,
+ 'GDTR_READ': 0x067,
+ 'LDTR_READ': 0x068,
+ 'TR_READ': 0x069,
+ 'IDTR_WRITE': 0x06a,
+ 'GDTR_WRITE': 0x06b,
+ 'LDTR_WRITE': 0x06c,
+ 'TR_WRITE': 0x06d,
+ 'RDTSC': 0x06e,
+ 'RDPMC': 0x06f,
+ 'PUSHF': 0x070,
+ 'POPF': 0x071,
+ 'CPUID': 0x072,
+ 'RSM': 0x073,
+ 'IRET': 0x074,
+ 'SWINT': 0x075,
+ 'INVD': 0x076,
+ 'PAUSE': 0x077,
+ 'HLT': 0x078,
+ 'INVLPG': 0x079,
+ 'INVLPGA': 0x07a,
+ 'IOIO': 0x07b,
+ 'MSR': 0x07c,
+ 'TASK_SWITCH': 0x07d,
+ 'FERR_FREEZE': 0x07e,
+ 'SHUTDOWN': 0x07f,
+ 'VMRUN': 0x080,
+ 'VMMCALL': 0x081,
+ 'VMLOAD': 0x082,
+ 'VMSAVE': 0x083,
+ 'STGI': 0x084,
+ 'CLGI': 0x085,
+ 'SKINIT': 0x086,
+ 'RDTSCP': 0x087,
+ 'ICEBP': 0x088,
+ 'WBINVD': 0x089,
+ 'MONITOR': 0x08a,
+ 'MWAIT': 0x08b,
+ 'MWAIT_COND': 0x08c,
+ 'XSETBV': 0x08d,
+ 'NPF': 0x400,
+}
+
+# EC definition of HSR (from arch/arm64/include/asm/kvm_arm.h)
+AARCH64_EXIT_REASONS = {
+ 'UNKNOWN': 0x00,
+ 'WFI': 0x01,
+ 'CP15_32': 0x03,
+ 'CP15_64': 0x04,
+ 'CP14_MR': 0x05,
+ 'CP14_LS': 0x06,
+ 'FP_ASIMD': 0x07,
+ 'CP10_ID': 0x08,
+ 'CP14_64': 0x0C,
+ 'ILL_ISS': 0x0E,
+ 'SVC32': 0x11,
+ 'HVC32': 0x12,
+ 'SMC32': 0x13,
+ 'SVC64': 0x15,
+ 'HVC64': 0x16,
+ 'SMC64': 0x17,
+ 'SYS64': 0x18,
+ 'IABT': 0x20,
+ 'IABT_HYP': 0x21,
+ 'PC_ALIGN': 0x22,
+ 'DABT': 0x24,
+ 'DABT_HYP': 0x25,
+ 'SP_ALIGN': 0x26,
+ 'FP_EXC32': 0x28,
+ 'FP_EXC64': 0x2C,
+ 'SERROR': 0x2F,
+ 'BREAKPT': 0x30,
+ 'BREAKPT_HYP': 0x31,
+ 'SOFTSTP': 0x32,
+ 'SOFTSTP_HYP': 0x33,
+ 'WATCHPT': 0x34,
+ 'WATCHPT_HYP': 0x35,
+ 'BKPT32': 0x38,
+ 'VECTOR32': 0x3A,
+ 'BRK64': 0x3C,
+}
+
+# From include/uapi/linux/kvm.h, KVM_EXIT_xxx
+USERSPACE_EXIT_REASONS = {
+ 'UNKNOWN': 0,
+ 'EXCEPTION': 1,
+ 'IO': 2,
+ 'HYPERCALL': 3,
+ 'DEBUG': 4,
+ 'HLT': 5,
+ 'MMIO': 6,
+ 'IRQ_WINDOW_OPEN': 7,
+ 'SHUTDOWN': 8,
+ 'FAIL_ENTRY': 9,
+ 'INTR': 10,
+ 'SET_TPR': 11,
+ 'TPR_ACCESS': 12,
+ 'S390_SIEIC': 13,
+ 'S390_RESET': 14,
+ 'DCR': 15,
+ 'NMI': 16,
+ 'INTERNAL_ERROR': 17,
+ 'OSI': 18,
+ 'PAPR_HCALL': 19,
+ 'S390_UCONTROL': 20,
+ 'WATCHDOG': 21,
+ 'S390_TSCH': 22,
+ 'EPR': 23,
+ 'SYSTEM_EVENT': 24,
+}
+
+IOCTL_NUMBERS = {
+ 'SET_FILTER': 0x40082406,
+ 'ENABLE': 0x00002400,
+ 'DISABLE': 0x00002401,
+ 'RESET': 0x00002403,
+}
+
+class Arch(object):
+ """Encapsulates global architecture specific data.
+
+ Contains the performance event open syscall and ioctl numbers, as
+ well as the VM exit reasons for the architecture it runs on.
+
+ """
+ @staticmethod
+ def get_arch():
+ machine = os.uname()[4]
+
+ if machine.startswith('ppc'):
+ return ArchPPC()
+ elif machine.startswith('aarch64'):
+ return ArchA64()
+ elif machine.startswith('s390'):
+ return ArchS390()
+ else:
+ # X86_64
+ for line in open('/proc/cpuinfo'):
+ if not line.startswith('flags'):
+ continue
+
+ flags = line.split()
+ if 'vmx' in flags:
+ return ArchX86(VMX_EXIT_REASONS)
+ if 'svm' in flags:
+ return ArchX86(SVM_EXIT_REASONS)
+ return
+
+class ArchX86(Arch):
+ def __init__(self, exit_reasons):
+ self.sc_perf_evt_open = 298
+ self.ioctl_numbers = IOCTL_NUMBERS
+ self.exit_reasons = exit_reasons
+
+class ArchPPC(Arch):
+ def __init__(self):
+ self.sc_perf_evt_open = 319
+ self.ioctl_numbers = IOCTL_NUMBERS
+ self.ioctl_numbers['ENABLE'] = 0x20002400
+ self.ioctl_numbers['DISABLE'] = 0x20002401
+ self.ioctl_numbers['RESET'] = 0x20002403
+
+ # PPC comes in 32 and 64 bit and some generated ioctl
+ # numbers depend on the wordsize.
+ char_ptr_size = ctypes.sizeof(ctypes.c_char_p)
+ self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
+ self.exit_reasons = {}
+
+class ArchA64(Arch):
+ def __init__(self):
+ self.sc_perf_evt_open = 241
+ self.ioctl_numbers = IOCTL_NUMBERS
+ self.exit_reasons = AARCH64_EXIT_REASONS
+
+class ArchS390(Arch):
+ def __init__(self):
+ self.sc_perf_evt_open = 331
+ self.ioctl_numbers = IOCTL_NUMBERS
+ self.exit_reasons = None
+
+ARCH = Arch.get_arch()
+
+
+def walkdir(path):
+ """Returns os.walk() data for specified directory.
+
+ As it is only a wrapper it returns the same 3-tuple of (dirpath,
+ dirnames, filenames).
+ """
+ return next(os.walk(path))
+
+
+def parse_int_list(list_string):
+ """Returns an int list from a string of comma separated integers and
+ integer ranges."""
+ integers = []
+ members = list_string.split(',')
+
+ for member in members:
+ if '-' not in member:
+ integers.append(int(member))
+ else:
+ int_range = member.split('-')
+ integers.extend(range(int(int_range[0]),
+ int(int_range[1]) + 1))
+
+ return integers
+
+
+def get_online_cpus():
+ """Returns a list of cpu id integers."""
+ with open('/sys/devices/system/cpu/online') as cpu_list:
+ cpu_string = cpu_list.readline()
+ return parse_int_list(cpu_string)
+
+
+def get_filters():
+ """Returns a dict of trace events, their filter ids and
+ the values that can be filtered.
+
+ Trace events can be filtered for special values by setting a
+ filter string via an ioctl. The string normally has the format
+ identifier==value. For each filter a new event will be created, to
+ be able to distinguish the events.
+
+ """
+ filters = {}
+ filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS)
+ if ARCH.exit_reasons:
+ filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
+ return filters
+
+libc = ctypes.CDLL('libc.so.6', use_errno=True)
+syscall = libc.syscall
+
+class perf_event_attr(ctypes.Structure):
+ """Struct that holds the necessary data to set up a trace event.
+
+ For an extensive explanation see perf_event_open(2) and
+ include/uapi/linux/perf_event.h, struct perf_event_attr
+
+ All fields that are not initialized in the constructor are 0.
+
+ """
+ _fields_ = [('type', ctypes.c_uint32),
+ ('size', ctypes.c_uint32),
+ ('config', ctypes.c_uint64),
+ ('sample_freq', ctypes.c_uint64),
+ ('sample_type', ctypes.c_uint64),
+ ('read_format', ctypes.c_uint64),
+ ('flags', ctypes.c_uint64),
+ ('wakeup_events', ctypes.c_uint32),
+ ('bp_type', ctypes.c_uint32),
+ ('bp_addr', ctypes.c_uint64),
+ ('bp_len', ctypes.c_uint64),
+ ]
+
+ def __init__(self):
+ super(self.__class__, self).__init__()
+ self.type = PERF_TYPE_TRACEPOINT
+ self.size = ctypes.sizeof(self)
+ self.read_format = PERF_FORMAT_GROUP
+
+def perf_event_open(attr, pid, cpu, group_fd, flags):
+ """Wrapper for the sys_perf_evt_open() syscall.
+
+ Used to set up performance events, returns a file descriptor or -1
+ on error.
+
+ Attributes are:
+ - syscall number
+ - struct perf_event_attr *
+ - pid or -1 to monitor all pids
+ - cpu number or -1 to monitor all cpus
+ - The file descriptor of the group leader or -1 to create a group.
+ - flags
+
+ """
+ return syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr),
+ ctypes.c_int(pid), ctypes.c_int(cpu),
+ ctypes.c_int(group_fd), ctypes.c_long(flags))
+
+PERF_TYPE_TRACEPOINT = 2
+PERF_FORMAT_GROUP = 1 << 3
+
+PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing'
+PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm'
+
+class Group(object):
+ """Represents a perf event group."""
+
+ def __init__(self):
+ self.events = []
+
+ def add_event(self, event):
+ self.events.append(event)
+
+ def read(self):
+ """Returns a dict with 'event name: value' for all events in the
+ group.
+
+ Values are read by reading from the file descriptor of the
+ event that is the group leader. See perf_event_open(2) for
+ details.
+
+ Read format for the used event configuration is:
+ struct read_format {
+ u64 nr; /* The number of events */
+ struct {
+ u64 value; /* The value of the event */
+ } values[nr];
+ };
+
+ """
+ length = 8 * (1 + len(self.events))
+ read_format = 'xxxxxxxx' + 'Q' * len(self.events)
+ return dict(zip([event.name for event in self.events],
+ struct.unpack(read_format,
+ os.read(self.events[0].fd, length))))
+
+class Event(object):
+ """Represents a performance event and manages its life cycle."""
+ def __init__(self, name, group, trace_cpu, trace_pid, trace_point,
+ trace_filter, trace_set='kvm'):
+ self.name = name
+ self.fd = None
+ self.setup_event(group, trace_cpu, trace_pid, trace_point,
+ trace_filter, trace_set)
+
+ def __del__(self):
+ """Closes the event's file descriptor.
+
+ As no python file object was created for the file descriptor,
+ python will not reference count the descriptor and will not
+ close it itself automatically, so we do it.
+
+ """
+ if self.fd:
+ os.close(self.fd)
+
+ def setup_event_attribute(self, trace_set, trace_point):
+ """Returns an initialized ctype perf_event_attr struct."""
+
+ id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set,
+ trace_point, 'id')
+
+ event_attr = perf_event_attr()
+ event_attr.config = int(open(id_path).read())
+ return event_attr
+
+ def setup_event(self, group, trace_cpu, trace_pid, trace_point,
+ trace_filter, trace_set):
+ """Sets up the perf event in Linux.
+
+ Issues the syscall to register the event in the kernel and
+ then sets the optional filter.
+
+ """
+
+ event_attr = self.setup_event_attribute(trace_set, trace_point)
+
+ # First event will be group leader.
+ group_leader = -1
+
+ # All others have to pass the leader's descriptor instead.
+ if group.events:
+ group_leader = group.events[0].fd
+
+ fd = perf_event_open(event_attr, trace_pid,
+ trace_cpu, group_leader, 0)
+ if fd == -1:
+ err = ctypes.get_errno()
+ raise OSError(err, os.strerror(err),
+ 'while calling sys_perf_event_open().')
+
+ if trace_filter:
+ fcntl.ioctl(fd, ARCH.ioctl_numbers['SET_FILTER'],
+ trace_filter)
+
+ self.fd = fd
+
+ def enable(self):
+ """Enables the trace event in the kernel.
+
+ Enabling the group leader makes reading counters from it and the
+ events under it possible.
+
+ """
+ fcntl.ioctl(self.fd, ARCH.ioctl_numbers['ENABLE'], 0)
+
+ def disable(self):
+ """Disables the trace event in the kernel.
+
+ Disabling the group leader makes reading all counters under it
+ impossible.
+
+ """
+ fcntl.ioctl(self.fd, ARCH.ioctl_numbers['DISABLE'], 0)
+
+ def reset(self):
+ """Resets the count of the trace event in the kernel."""
+ fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0)
+
+class TracepointProvider(object):
+ """Data provider for the stats class.
+
+ Manages the events/groups from which it acquires its data.
+
+ """
+ def __init__(self):
+ self.group_leaders = []
+ self.filters = get_filters()
+ self._fields = self.get_available_fields()
+ self._pid = 0
+
+ def get_available_fields(self):
+ """Returns a list of available event's of format 'event name(filter
+ name)'.
+
+ All available events have directories under
+ /sys/kernel/debug/tracing/events/ which export information
+ about the specific event. Therefore, listing the dirs gives us
+ a list of all available events.
+
+ Some events like the vm exit reasons can be filtered for
+ specific values. To take account for that, the routine below
+ creates special fields with the following format:
+ event name(filter name)
+
+ """
+ path = os.path.join(PATH_DEBUGFS_TRACING, 'events', 'kvm')
+ fields = walkdir(path)[1]
+ extra = []
+ for field in fields:
+ if field in self.filters:
+ filter_name_, filter_dicts = self.filters[field]
+ for name in filter_dicts:
+ extra.append(field + '(' + name + ')')
+ fields += extra
+ return fields
+
+ def setup_traces(self):
+ """Creates all event and group objects needed to be able to retrieve
+ data."""
+ if self._pid > 0:
+ # Fetch list of all threads of the monitored pid, as qemu
+ # starts a thread for each vcpu.
+ path = os.path.join('/proc', str(self._pid), 'task')
+ groupids = walkdir(path)[1]
+ else:
+ groupids = get_online_cpus()
+
+ # The constant is needed as a buffer for python libs, std
+ # streams and other files that the script opens.
+ newlim = len(groupids) * len(self._fields) + 50
+ try:
+ softlim_, hardlim = resource.getrlimit(resource.RLIMIT_NOFILE)
+
+ if hardlim < newlim:
+ # Now we need CAP_SYS_RESOURCE, to increase the hard limit.
+ resource.setrlimit(resource.RLIMIT_NOFILE, (newlim, newlim))
+ else:
+ # Raising the soft limit is sufficient.
+ resource.setrlimit(resource.RLIMIT_NOFILE, (newlim, hardlim))
+
+ except ValueError:
+ sys.exit("NOFILE rlimit could not be raised to {0}".format(newlim))
+
+ for groupid in groupids:
+ group = Group()
+ for name in self._fields:
+ tracepoint = name
+ tracefilter = None
+ match = re.match(r'(.*)\((.*)\)', name)
+ if match:
+ tracepoint, sub = match.groups()
+ tracefilter = ('%s==%d\0' %
+ (self.filters[tracepoint][0],
+ self.filters[tracepoint][1][sub]))
+
+ # From perf_event_open(2):
+ # pid > 0 and cpu == -1
+ # This measures the specified process/thread on any CPU.
+ #
+ # pid == -1 and cpu >= 0
+ # This measures all processes/threads on the specified CPU.
+ trace_cpu = groupid if self._pid == 0 else -1
+ trace_pid = int(groupid) if self._pid != 0 else -1
+
+ group.add_event(Event(name=name,
+ group=group,
+ trace_cpu=trace_cpu,
+ trace_pid=trace_pid,
+ trace_point=tracepoint,
+ trace_filter=tracefilter))
+
+ self.group_leaders.append(group)
+
+ def available_fields(self):
+ return self.get_available_fields()
+
+ @property
+ def fields(self):
+ return self._fields
+
+ @fields.setter
+ def fields(self, fields):
+ """Enables/disables the (un)wanted events"""
+ self._fields = fields
+ for group in self.group_leaders:
+ for index, event in enumerate(group.events):
+ if event.name in fields:
+ event.reset()
+ event.enable()
+ else:
+ # Do not disable the group leader.
+ # It would disable all of its events.
+ if index != 0:
+ event.disable()
+
+ @property
+ def pid(self):
+ return self._pid
+
+ @pid.setter
+ def pid(self, pid):
+ """Changes the monitored pid by setting new traces."""
+ self._pid = pid
+ # The garbage collector will get rid of all Event/Group
+ # objects and open files after removing the references.
+ self.group_leaders = []
+ self.setup_traces()
+ self.fields = self._fields
+
+ def read(self):
+ """Returns 'event name: current value' for all enabled events."""
+ ret = defaultdict(int)
+ for group in self.group_leaders:
+ for name, val in group.read().iteritems():
+ if name in self._fields:
+ ret[name] += val
+ return ret
+
+class DebugfsProvider(object):
+ """Provides data from the files that KVM creates in the kvm debugfs
+ folder."""
+ def __init__(self):
+ self._fields = self.get_available_fields()
+ self._pid = 0
+ self.do_read = True
+
+ def get_available_fields(self):
+ """"Returns a list of available fields.
+
+ The fields are all available KVM debugfs files
+
+ """
+ return walkdir(PATH_DEBUGFS_KVM)[2]
+
+ @property
+ def fields(self):
+ return self._fields
+
+ @fields.setter
+ def fields(self, fields):
+ self._fields = fields
+
+ @property
+ def pid(self):
+ return self._pid
+
+ @pid.setter
+ def pid(self, pid):
+ if pid != 0:
+ self._pid = pid
+
+ vms = walkdir(PATH_DEBUGFS_KVM)[1]
+ if len(vms) == 0:
+ self.do_read = False
+
+ self.paths = filter(lambda x: "{}-".format(pid) in x, vms)
+
+ else:
+ self.paths = ['']
+ self.do_read = True
+
+ def read(self):
+ """Returns a dict with format:'file name / field -> current value'."""
+ results = {}
+
+ # If no debugfs filtering support is available, then don't read.
+ if not self.do_read:
+ return results
+
+ for path in self.paths:
+ for field in self._fields:
+ results[field] = results.get(field, 0) \
+ + self.read_field(field, path)
+
+ return results
+
+ def read_field(self, field, path):
+ """Returns the value of a single field from a specific VM."""
+ try:
+ return int(open(os.path.join(PATH_DEBUGFS_KVM,
+ path,
+ field))
+ .read())
+ except IOError:
+ return 0
+
+class Stats(object):
+ """Manages the data providers and the data they provide.
+
+ It is used to set filters on the provider's data and collect all
+ provider data.
+
+ """
+ def __init__(self, providers, pid, fields=None):
+ self.providers = providers
+ self._pid_filter = pid
+ self._fields_filter = fields
+ self.values = {}
+ self.update_provider_pid()
+ self.update_provider_filters()
+
+ def update_provider_filters(self):
+ """Propagates fields filters to providers."""
+ def wanted(key):
+ if not self._fields_filter:
+ return True
+ return re.match(self._fields_filter, key) is not None
+
+ # As we reset the counters when updating the fields we can
+ # also clear the cache of old values.
+ self.values = {}
+ for provider in self.providers:
+ provider_fields = [key for key in provider.get_available_fields()
+ if wanted(key)]
+ provider.fields = provider_fields
+
+ def update_provider_pid(self):
+ """Propagates pid filters to providers."""
+ for provider in self.providers:
+ provider.pid = self._pid_filter
+
+ @property
+ def fields_filter(self):
+ return self._fields_filter
+
+ @fields_filter.setter
+ def fields_filter(self, fields_filter):
+ self._fields_filter = fields_filter
+ self.update_provider_filters()
+
+ @property
+ def pid_filter(self):
+ return self._pid_filter
+
+ @pid_filter.setter
+ def pid_filter(self, pid):
+ self._pid_filter = pid
+ self.values = {}
+ self.update_provider_pid()
+
+ def get(self):
+ """Returns a dict with field -> (value, delta to last value) of all
+ provider data."""
+ for provider in self.providers:
+ new = provider.read()
+ for key in provider.fields:
+ oldval = self.values.get(key, (0, 0))
+ newval = new.get(key, 0)
+ newdelta = None
+ if oldval is not None:
+ newdelta = newval - oldval[0]
+ self.values[key] = (newval, newdelta)
+ return self.values
+
+LABEL_WIDTH = 40
+NUMBER_WIDTH = 10
+
+class Tui(object):
+ """Instruments curses to draw a nice text ui."""
+ def __init__(self, stats):
+ self.stats = stats
+ self.screen = None
+ self.drilldown = False
+ self.update_drilldown()
+
+ def __enter__(self):
+ """Initialises curses for later use. Based on curses.wrapper
+ implementation from the Python standard library."""
+ self.screen = curses.initscr()
+ curses.noecho()
+ curses.cbreak()
+
+ # The try/catch works around a minor bit of
+ # over-conscientiousness in the curses module, the error
+ # return from C start_color() is ignorable.
+ try:
+ curses.start_color()
+ except:
+ pass
+
+ curses.use_default_colors()
+ return self
+
+ def __exit__(self, *exception):
+ """Resets the terminal to its normal state. Based on curses.wrappre
+ implementation from the Python standard library."""
+ if self.screen:
+ self.screen.keypad(0)
+ curses.echo()
+ curses.nocbreak()
+ curses.endwin()
+
+ def update_drilldown(self):
+ """Sets or removes a filter that only allows fields without braces."""
+ if not self.stats.fields_filter:
+ self.stats.fields_filter = r'^[^\(]*$'
+
+ elif self.stats.fields_filter == r'^[^\(]*$':
+ self.stats.fields_filter = None
+
+ def update_pid(self, pid):
+ """Propagates pid selection to stats object."""
+ self.stats.pid_filter = pid
+
+ def refresh(self, sleeptime):
+ """Refreshes on-screen data."""
+ self.screen.erase()
+ if self.stats.pid_filter > 0:
+ self.screen.addstr(0, 0, 'kvm statistics - pid {0}'
+ .format(self.stats.pid_filter),
+ curses.A_BOLD)
+ else:
+ self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD)
+ self.screen.addstr(2, 1, 'Event')
+ self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH -
+ len('Total'), 'Total')
+ self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 8 -
+ len('Current'), 'Current')
+ row = 3
+ stats = self.stats.get()
+ def sortkey(x):
+ if stats[x][1]:
+ return (-stats[x][1], -stats[x][0])
+ else:
+ return (0, -stats[x][0])
+ for key in sorted(stats.keys(), key=sortkey):
+
+ if row >= self.screen.getmaxyx()[0]:
+ break
+ values = stats[key]
+ if not values[0] and not values[1]:
+ break
+ col = 1
+ self.screen.addstr(row, col, key)
+ col += LABEL_WIDTH
+ self.screen.addstr(row, col, '%10d' % (values[0],))
+ col += NUMBER_WIDTH
+ if values[1] is not None:
+ self.screen.addstr(row, col, '%8d' % (values[1] / sleeptime,))
+ row += 1
+ self.screen.refresh()
+
+ def show_filter_selection(self):
+ """Draws filter selection mask.
+
+ Asks for a valid regex and sets the fields filter accordingly.
+
+ """
+ while True:
+ self.screen.erase()
+ self.screen.addstr(0, 0,
+ "Show statistics for events matching a regex.",
+ curses.A_BOLD)
+ self.screen.addstr(2, 0,
+ "Current regex: {0}"
+ .format(self.stats.fields_filter))
+ self.screen.addstr(3, 0, "New regex: ")
+ curses.echo()
+ regex = self.screen.getstr()
+ curses.noecho()
+ if len(regex) == 0:
+ return
+ try:
+ re.compile(regex)
+ self.stats.fields_filter = regex
+ return
+ except re.error:
+ continue
+
+ def show_vm_selection(self):
+ """Draws PID selection mask.
+
+ Asks for a pid until a valid pid or 0 has been entered.
+
+ """
+ while True:
+ self.screen.erase()
+ self.screen.addstr(0, 0,
+ 'Show statistics for specific pid.',
+ curses.A_BOLD)
+ self.screen.addstr(1, 0,
+ 'This might limit the shown data to the trace '
+ 'statistics.')
+
+ curses.echo()
+ self.screen.addstr(3, 0, "Pid [0 or pid]: ")
+ pid = self.screen.getstr()
+ curses.noecho()
+
+ try:
+ pid = int(pid)
+
+ if pid == 0:
+ self.update_pid(pid)
+ break
+ else:
+ if not os.path.isdir(os.path.join('/proc/', str(pid))):
+ continue
+ else:
+ self.update_pid(pid)
+ break
+
+ except ValueError:
+ continue
+
+ def show_stats(self):
+ """Refreshes the screen and processes user input."""
+ sleeptime = 0.25
+ while True:
+ self.refresh(sleeptime)
+ curses.halfdelay(int(sleeptime * 10))
+ sleeptime = 3
+ try:
+ char = self.screen.getkey()
+ if char == 'x':
+ self.drilldown = not self.drilldown
+ self.update_drilldown()
+ if char == 'q':
+ break
+ if char == 'f':
+ self.show_filter_selection()
+ if char == 'p':
+ self.show_vm_selection()
+ except KeyboardInterrupt:
+ break
+ except curses.error:
+ continue
+
+def batch(stats):
+ """Prints statistics in a key, value format."""
+ s = stats.get()
+ time.sleep(1)
+ s = stats.get()
+ for key in sorted(s.keys()):
+ values = s[key]
+ print '%-42s%10d%10d' % (key, values[0], values[1])
+
+def log(stats):
+ """Prints statistics as reiterating key block, multiple value blocks."""
+ keys = sorted(stats.get().iterkeys())
+ def banner():
+ for k in keys:
+ print '%s' % k,
+ print
+ def statline():
+ s = stats.get()
+ for k in keys:
+ print ' %9d' % s[k][1],
+ print
+ line = 0
+ banner_repeat = 20
+ while True:
+ time.sleep(1)
+ if line % banner_repeat == 0:
+ banner()
+ statline()
+ line += 1
+
+def get_options():
+ """Returns processed program arguments."""
+ description_text = """
+This script displays various statistics about VMs running under KVM.
+The statistics are gathered from the KVM debugfs entries and / or the
+currently available perf traces.
+
+The monitoring takes additional cpu cycles and might affect the VM's
+performance.
+
+Requirements:
+- Access to:
+ /sys/kernel/debug/kvm
+ /sys/kernel/debug/trace/events/*
+ /proc/pid/task
+- /proc/sys/kernel/perf_event_paranoid < 1 if user has no
+ CAP_SYS_ADMIN and perf events are used.
+- CAP_SYS_RESOURCE if the hard limit is not high enough to allow
+ the large number of files that are possibly opened.
+"""
+
+ class PlainHelpFormatter(optparse.IndentedHelpFormatter):
+ def format_description(self, description):
+ if description:
+ return description + "\n"
+ else:
+ return ""
+
+ optparser = optparse.OptionParser(description=description_text,
+ formatter=PlainHelpFormatter())
+ optparser.add_option('-1', '--once', '--batch',
+ action='store_true',
+ default=False,
+ dest='once',
+ help='run in batch mode for one second',
+ )
+ optparser.add_option('-l', '--log',
+ action='store_true',
+ default=False,
+ dest='log',
+ help='run in logging mode (like vmstat)',
+ )
+ optparser.add_option('-t', '--tracepoints',
+ action='store_true',
+ default=False,
+ dest='tracepoints',
+ help='retrieve statistics from tracepoints',
+ )
+ optparser.add_option('-d', '--debugfs',
+ action='store_true',
+ default=False,
+ dest='debugfs',
+ help='retrieve statistics from debugfs',
+ )
+ optparser.add_option('-f', '--fields',
+ action='store',
+ default=None,
+ dest='fields',
+ help='fields to display (regex)',
+ )
+ optparser.add_option('-p', '--pid',
+ action='store',
+ default=0,
+ type=int,
+ dest='pid',
+ help='restrict statistics to pid',
+ )
+ (options, _) = optparser.parse_args(sys.argv)
+ return options
+
+def get_providers(options):
+ """Returns a list of data providers depending on the passed options."""
+ providers = []
+
+ if options.tracepoints:
+ providers.append(TracepointProvider())
+ if options.debugfs:
+ providers.append(DebugfsProvider())
+ if len(providers) == 0:
+ providers.append(TracepointProvider())
+
+ return providers
+
+def check_access(options):
+ """Exits if the current user can't access all needed directories."""
+ if not os.path.exists('/sys/kernel/debug'):
+ sys.stderr.write('Please enable CONFIG_DEBUG_FS in your kernel.')
+ sys.exit(1)
+
+ if not os.path.exists(PATH_DEBUGFS_KVM):
+ sys.stderr.write("Please make sure, that debugfs is mounted and "
+ "readable by the current user:\n"
+ "('mount -t debugfs debugfs /sys/kernel/debug')\n"
+ "Also ensure, that the kvm modules are loaded.\n")
+ sys.exit(1)
+
+ if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints
+ or not options.debugfs):
+ sys.stderr.write("Please enable CONFIG_TRACING in your kernel "
+ "when using the option -t (default).\n"
+ "If it is enabled, make {0} readable by the "
+ "current user.\n"
+ .format(PATH_DEBUGFS_TRACING))
+ if options.tracepoints:
+ sys.exit(1)
+
+ sys.stderr.write("Falling back to debugfs statistics!\n")
+ options.debugfs = True
+ sleep(5)
+
+ return options
+
+def main():
+ options = get_options()
+ options = check_access(options)
+
+ if (options.pid > 0 and
+ not os.path.isdir(os.path.join('/proc/',
+ str(options.pid)))):
+ sys.stderr.write('Did you use a (unsupported) tid instead of a pid?\n')
+ sys.exit('Specified pid does not exist.')
+
+ providers = get_providers(options)
+ stats = Stats(providers, options.pid, fields=options.fields)
+
+ if options.log:
+ log(stats)
+ elif not options.once:
+ with Tui(stats) as tui:
+ tui.show_stats()
+ else:
+ batch(stats)
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
new file mode 100644
index 000000000000..b92a153d7115
--- /dev/null
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -0,0 +1,63 @@
+kvm_stat(1)
+===========
+
+NAME
+----
+kvm_stat - Report KVM kernel module event counters
+
+SYNOPSIS
+--------
+[verse]
+'kvm_stat' [OPTION]...
+
+DESCRIPTION
+-----------
+kvm_stat prints counts of KVM kernel module trace events. These events signify
+state transitions such as guest mode entry and exit.
+
+This tool is useful for observing guest behavior from the host perspective.
+Often conclusions about performance or buggy behavior can be drawn from the
+output.
+
+The set of KVM kernel module trace events may be specific to the kernel version
+or architecture. It is best to check the KVM kernel module source code for the
+meaning of events.
+
+OPTIONS
+-------
+-1::
+--once::
+--batch::
+ run in batch mode for one second
+
+-l::
+--log::
+ run in logging mode (like vmstat)
+
+-t::
+--tracepoints::
+ retrieve statistics from tracepoints
+
+-d::
+--debugfs::
+ retrieve statistics from debugfs
+
+-p<pid>::
+--pid=<pid>::
+ limit statistics to one virtual machine (pid)
+
+-f<fields>::
+--fields=<fields>::
+ fields to display (regex)
+
+-h::
+--help::
+ show help message
+
+SEE ALSO
+--------
+'perf'(1), 'trace-cmd'(1)
+
+AUTHOR
+------
+Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 6765c7e949f3..f094f3c4ed84 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -30,6 +30,10 @@ INCLUDES := -I$(srctree)/tools/include
CFLAGS += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
LDFLAGS += -lelf $(LIBSUBCMD)
+# Allow old libelf to be used:
+elfshdr := $(shell echo '\#include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
+CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
+
AWK = awk
export srctree OUTPUT CFLAGS ARCH AWK
include $(srctree)/tools/build/Makefile.include
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index 7f3e00a2f907..aa1ff6596684 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -23,6 +23,11 @@
#include <linux/list.h>
#include <linux/hashtable.h>
+#ifdef LIBELF_USE_DEPRECATED
+# define elf_getshdrnum elf_getshnum
+# define elf_getshdrstrndx elf_getshstrndx
+#endif
+
struct section {
struct list_head list;
GElf_Shdr sh;
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index ebaf849e30ef..9cbddc290aff 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -103,12 +103,13 @@ OPTIONS
If --branch-stack option is used, following sort keys are also
available:
- dso_from, dso_to, symbol_from, symbol_to, mispredict.
- dso_from: name of library or module branched from
- dso_to: name of library or module branched to
- symbol_from: name of function branched from
- symbol_to: name of function branched to
+ - srcline_from: source file and line branched from
+ - srcline_to: source file and line branched to
- mispredict: "N" for predicted branch, "Y" for mispredicted branch
- in_tx: branch in TSX transaction
- abort: TSX transaction abort.
@@ -248,7 +249,7 @@ OPTIONS
Note that when using the --itrace option the synthesized callchain size
will override this value if the synthesized callchain size is bigger.
- Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+ Default: 127
-G::
--inverted::
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index a856a1095893..4fc44c75263f 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -267,7 +267,7 @@ include::itrace.txt[]
Note that when using the --itrace option the synthesized callchain size
will override this value if the synthesized callchain size is bigger.
- Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+ Default: 127
--ns::
Use 9 decimal places when displaying time (i.e. show the nanoseconds)
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 6afe20121bc0..1ab0782369b1 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -143,7 +143,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
Implies '--call-graph dwarf' when --call-graph not present on the
command line, on systems where DWARF unwinding was built in.
- Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+ Default: /proc/sys/kernel/perf_event_max_stack when present for
+ live sessions (without --input/-i), 127 otherwise.
--min-stack::
Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 814158393656..25c81734a950 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -324,8 +324,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
"Skip symbols that cannot be annotated"),
OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
- OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
- "Look for files with symbols relative to this directory"),
+ OPT_CALLBACK(0, "symfs", NULL, "directory",
+ "Look for files with symbols relative to this directory",
+ symbol__config_symfs),
OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
"Interleave source code with assembly code (default)"),
OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 632efc6b79a0..d75bded21fe0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -119,8 +119,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
if (build_id_cache__kcore_buildid(from_dir, sbuildid) < 0)
return -1;
- scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
- buildid_dir, sbuildid);
+ scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s",
+ buildid_dir, DSO__NAME_KCORE, sbuildid);
if (!force &&
!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
@@ -131,8 +131,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
if (build_id_cache__kcore_dir(dir, sizeof(dir)))
return -1;
- scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s",
- buildid_dir, sbuildid, dir);
+ scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s/%s",
+ buildid_dir, DSO__NAME_KCORE, sbuildid, dir);
if (mkdir_p(to_dir, 0755))
return -1;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ce354f469dc..f7645a42708e 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -812,8 +812,9 @@ static const struct option options[] = {
OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
- OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
- "Look for files with symbols relative to this directory"),
+ OPT_CALLBACK(0, "symfs", NULL, "directory",
+ "Look for files with symbols relative to this directory",
+ symbol__config_symfs),
OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
"How to display percentage of filtered entries", parse_filter_percentage),
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3679c44d3f3..dc3fcb597e4c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -40,6 +40,7 @@
#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>
+#include <asm/bug.h>
struct record {
@@ -82,27 +83,87 @@ static int process_synthesized_event(struct perf_tool *tool,
return record__write(rec, event, event->header.size);
}
+static int
+backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+{
+ struct perf_event_header *pheader;
+ u64 evt_head = head;
+ int size = mask + 1;
+
+ pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+ pheader = (struct perf_event_header *)(buf + (head & mask));
+ *start = head;
+ while (true) {
+ if (evt_head - head >= (unsigned int)size) {
+ pr_debug("Finshed reading backward ring buffer: rewind\n");
+ if (evt_head - head > (unsigned int)size)
+ evt_head -= pheader->size;
+ *end = evt_head;
+ return 0;
+ }
+
+ pheader = (struct perf_event_header *)(buf + (evt_head & mask));
+
+ if (pheader->size == 0) {
+ pr_debug("Finshed reading backward ring buffer: get start\n");
+ *end = evt_head;
+ return 0;
+ }
+
+ evt_head += pheader->size;
+ pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
+ }
+ WARN_ONCE(1, "Shouldn't get here\n");
+ return -1;
+}
+
+static int
+rb_find_range(struct perf_evlist *evlist,
+ void *data, int mask, u64 head, u64 old,
+ u64 *start, u64 *end)
+{
+ if (!evlist->backward) {
+ *start = old;
+ *end = head;
+ return 0;
+ }
+
+ return backward_rb_find_range(data, mask, head, start, end);
+}
+
static int record__mmap_read(struct record *rec, int idx)
{
struct perf_mmap *md = &rec->evlist->mmap[idx];
u64 head = perf_mmap__read_head(md);
u64 old = md->prev;
+ u64 end = head, start = old;
unsigned char *data = md->base + page_size;
unsigned long size;
void *buf;
int rc = 0;
- if (old == head)
+ if (rb_find_range(rec->evlist, data, md->mask, head,
+ old, &start, &end))
+ return -1;
+
+ if (start == end)
return 0;
rec->samples++;
- size = head - old;
+ size = end - start;
+ if (size > (unsigned long)(md->mask) + 1) {
+ WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+
+ md->prev = head;
+ perf_evlist__mmap_consume(rec->evlist, idx);
+ return 0;
+ }
- if ((old & md->mask) + size != (head & md->mask)) {
- buf = &data[old & md->mask];
- size = md->mask + 1 - (old & md->mask);
- old += size;
+ if ((start & md->mask) + size != (end & md->mask)) {
+ buf = &data[start & md->mask];
+ size = md->mask + 1 - (start & md->mask);
+ start += size;
if (record__write(rec, buf, size) < 0) {
rc = -1;
@@ -110,16 +171,16 @@ static int record__mmap_read(struct record *rec, int idx)
}
}
- buf = &data[old & md->mask];
- size = head - old;
- old += size;
+ buf = &data[start & md->mask];
+ size = end - start;
+ start += size;
if (record__write(rec, buf, size) < 0) {
rc = -1;
goto out;
}
- md->prev = old;
+ md->prev = head;
perf_evlist__mmap_consume(rec->evlist, idx);
out:
return rc;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 87d40e3c4078..a87cb338bdf1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
.ordered_events = true,
.ordering_requires_timestamps = true,
},
- .max_stack = sysctl_perf_event_max_stack,
+ .max_stack = PERF_MAX_STACK_DEPTH,
.pretty_printing_style = "normal",
.socket_filter = -1,
};
@@ -770,8 +770,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"columns '.' is reserved."),
OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
"Only display entries resolved to a symbol"),
- OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
- "Look for files with symbols relative to this directory"),
+ OPT_CALLBACK(0, "symfs", NULL, "directory",
+ "Look for files with symbols relative to this directory",
+ symbol__config_symfs),
OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
"list of cpus to profile"),
OPT_BOOLEAN('I', "show-info", &report.show_full_info,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index efca81679bb3..e3ce2f34d3ad 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2010,8 +2010,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
"file", "kallsyms pathname"),
OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
"When printing symbols do not display call chain"),
- OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
- "Look for files with symbols relative to this directory"),
+ OPT_CALLBACK(0, "symfs", NULL, "directory",
+ "Look for files with symbols relative to this directory",
+ symbol__config_symfs),
OPT_CALLBACK('F', "fields", NULL, "str",
"comma separated output fields prepend with 'type:'. "
"Valid types: hw,sw,trace,raw. "
@@ -2067,8 +2068,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
- scripting_max_stack = sysctl_perf_event_max_stack;
-
setup_scripting();
argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e459b685a4e9..ee7ada78d86f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -66,6 +66,7 @@
#include <stdlib.h>
#include <sys/prctl.h>
#include <locale.h>
+#include <math.h>
#define DEFAULT_SEPARATOR " "
#define CNTR_NOT_SUPPORTED "<not supported>"
@@ -991,12 +992,12 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
const char *fmt;
if (csv_output) {
- fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
+ fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
} else {
if (big_num)
- fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+ fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
else
- fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+ fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
}
aggr_printout(evsel, id, nr);
@@ -1909,6 +1910,9 @@ static int add_default_attributes(void)
}
if (!evsel_list->nr_entries) {
+ if (target__has_cpu(&target))
+ default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
+
if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
return -1;
if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
@@ -2000,7 +2004,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session)
{
- struct stat_round_event *round = &event->stat_round;
+ struct stat_round_event *stat_round = &event->stat_round;
struct perf_evsel *counter;
struct timespec tsh, *ts = NULL;
const char **argv = session->header.env.cmdline_argv;
@@ -2009,12 +2013,12 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
evlist__for_each(evsel_list, counter)
perf_stat_process_counter(&stat_config, counter);
- if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
- update_stats(&walltime_nsecs_stats, round->time);
+ if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
+ update_stats(&walltime_nsecs_stats, stat_round->time);
- if (stat_config.interval && round->time) {
- tsh.tv_sec = round->time / NSECS_PER_SEC;
- tsh.tv_nsec = round->time % NSECS_PER_SEC;
+ if (stat_config.interval && stat_round->time) {
+ tsh.tv_sec = stat_round->time / NSECS_PER_SEC;
+ tsh.tv_nsec = stat_round->time % NSECS_PER_SEC;
ts = &tsh;
}
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 40cc9bb3506c..733a55422d03 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1945,8 +1945,9 @@ int cmd_timechart(int argc, const char **argv,
OPT_CALLBACK('p', "process", NULL, "process",
"process selector. Pass a pid or process name.",
parse_process),
- OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
- "Look for files with symbols relative to this directory"),
+ OPT_CALLBACK(0, "symfs", NULL, "directory",
+ "Look for files with symbols relative to this directory",
+ symbol__config_symfs),
OPT_INTEGER('n', "proc-num", &tchart.proc_num,
"min. number of tasks to print"),
OPT_BOOLEAN('t', "topology", &tchart.topology,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1793da585676..2a6cc254ad0c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -732,7 +732,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
if (machine__resolve(machine, &al, sample) < 0)
return;
- if (!top->kptr_restrict_warned &&
+ if (!machine->kptr_restrict_warned &&
symbol_conf.kptr_restrict &&
al.cpumode == PERF_RECORD_MISC_KERNEL) {
ui__warning(
@@ -743,7 +743,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
" modules" : "");
if (use_browser <= 0)
sleep(5);
- top->kptr_restrict_warned = true;
+ machine->kptr_restrict_warned = true;
}
if (al.sym == NULL) {
@@ -759,7 +759,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
* --hide-kernel-symbols, even if the user specifies an
* invalid --vmlinux ;-)
*/
- if (!top->kptr_restrict_warned && !top->vmlinux_warned &&
+ if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
if (symbol_conf.vmlinux_name) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6e5c325148e4..5c50fe70d6b3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -576,84 +576,54 @@ static struct syscall_fmt {
bool hexret;
} syscall_fmts[] = {
{ .name = "access", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */
- [1] = SCA_ACCMODE, /* mode */ }, },
+ .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
{ .name = "arch_prctl", .errmsg = true, .alias = "prctl", },
{ .name = "bpf", .errmsg = true, STRARRAY(0, cmd, bpf_cmd), },
{ .name = "brk", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
- { .name = "chdir", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
- { .name = "chmod", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
- { .name = "chroot", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+ { .name = "chdir", .errmsg = true, },
+ { .name = "chmod", .errmsg = true, },
+ { .name = "chroot", .errmsg = true, },
{ .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), },
{ .name = "clone", .errpid = true, },
{ .name = "close", .errmsg = true,
.arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
{ .name = "connect", .errmsg = true, },
- { .name = "creat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "dup", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "dup2", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "dup3", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "creat", .errmsg = true, },
+ { .name = "dup", .errmsg = true, },
+ { .name = "dup2", .errmsg = true, },
+ { .name = "dup3", .errmsg = true, },
{ .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
{ .name = "eventfd2", .errmsg = true,
.arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
- { .name = "faccessat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
- [1] = SCA_FILENAME, /* filename */ }, },
- { .name = "fadvise64", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "fallocate", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "fchdir", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "fchmod", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "faccessat", .errmsg = true, },
+ { .name = "fadvise64", .errmsg = true, },
+ { .name = "fallocate", .errmsg = true, },
+ { .name = "fchdir", .errmsg = true, },
+ { .name = "fchmod", .errmsg = true, },
{ .name = "fchmodat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
- [1] = SCA_FILENAME, /* filename */ }, },
- { .name = "fchown", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "fchown", .errmsg = true, },
{ .name = "fchownat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
- [1] = SCA_FILENAME, /* filename */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "fcntl", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [1] = SCA_STRARRAY, /* cmd */ },
+ .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
.arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
- { .name = "fdatasync", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fdatasync", .errmsg = true, },
{ .name = "flock", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [1] = SCA_FLOCK, /* cmd */ }, },
- { .name = "fsetxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "fstat", .errmsg = true, .alias = "newfstat",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "fstatat", .errmsg = true, .alias = "newfstatat",
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
- [1] = SCA_FILENAME, /* filename */ }, },
- { .name = "fstatfs", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "fsync", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "ftruncate", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, },
+ { .name = "fsetxattr", .errmsg = true, },
+ { .name = "fstat", .errmsg = true, .alias = "newfstat", },
+ { .name = "fstatat", .errmsg = true, .alias = "newfstatat", },
+ { .name = "fstatfs", .errmsg = true, },
+ { .name = "fsync", .errmsg = true, },
+ { .name = "ftruncate", .errmsg = true, },
{ .name = "futex", .errmsg = true,
.arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
{ .name = "futimesat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
- [1] = SCA_FILENAME, /* filename */ }, },
- { .name = "getdents", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "getdents64", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "getdents", .errmsg = true, },
+ { .name = "getdents64", .errmsg = true, },
{ .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), },
{ .name = "getpid", .errpid = true, },
{ .name = "getpgid", .errpid = true, },
@@ -661,12 +631,10 @@ static struct syscall_fmt {
{ .name = "getrandom", .errmsg = true,
.arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
{ .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
- { .name = "getxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "inotify_add_watch", .errmsg = true,
- .arg_scnprintf = { [1] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "getxattr", .errmsg = true, },
+ { .name = "inotify_add_watch", .errmsg = true, },
{ .name = "ioctl", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
+ .arg_scnprintf = {
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches.
@@ -680,41 +648,28 @@ static struct syscall_fmt {
{ .name = "keyctl", .errmsg = true, STRARRAY(0, option, keyctl_options), },
{ .name = "kill", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
- { .name = "lchown", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
- { .name = "lgetxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "lchown", .errmsg = true, },
+ { .name = "lgetxattr", .errmsg = true, },
{ .name = "linkat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
- { .name = "listxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "llistxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "lremovexattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "listxattr", .errmsg = true, },
+ { .name = "llistxattr", .errmsg = true, },
+ { .name = "lremovexattr", .errmsg = true, },
{ .name = "lseek", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [2] = SCA_STRARRAY, /* whence */ },
+ .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
.arg_parm = { [2] = &strarray__whences, /* whence */ }, },
- { .name = "lsetxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "lstat", .errmsg = true, .alias = "newlstat",
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
- { .name = "lsxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "lsetxattr", .errmsg = true, },
+ { .name = "lstat", .errmsg = true, .alias = "newlstat", },
+ { .name = "lsxattr", .errmsg = true, },
{ .name = "madvise", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* start */
[2] = SCA_MADV_BHV, /* behavior */ }, },
- { .name = "mkdir", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "mkdir", .errmsg = true, },
{ .name = "mkdirat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
- [1] = SCA_FILENAME, /* pathname */ }, },
- { .name = "mknod", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "mknod", .errmsg = true, },
{ .name = "mknodat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
- [1] = SCA_FILENAME, /* filename */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "mlock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "mlockall", .errmsg = true,
@@ -722,8 +677,7 @@ static struct syscall_fmt {
{ .name = "mmap", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
[2] = SCA_MMAP_PROT, /* prot */
- [3] = SCA_MMAP_FLAGS, /* flags */
- [4] = SCA_FD, /* fd */ }, },
+ [3] = SCA_MMAP_FLAGS, /* flags */ }, },
{ .name = "mprotect", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* start */
[2] = SCA_MMAP_PROT, /* prot */ }, },
@@ -740,17 +694,14 @@ static struct syscall_fmt {
{ .name = "name_to_handle_at", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "newfstatat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
- [1] = SCA_FILENAME, /* filename */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "open", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */
- [1] = SCA_OPEN_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "open_by_handle_at", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "openat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
- [1] = SCA_FILENAME, /* filename */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "perf_event_open", .errmsg = true,
.arg_scnprintf = { [2] = SCA_INT, /* cpu */
@@ -760,39 +711,26 @@ static struct syscall_fmt {
.arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
{ .name = "poll", .errmsg = true, .timeout = true, },
{ .name = "ppoll", .errmsg = true, .timeout = true, },
- { .name = "pread", .errmsg = true, .alias = "pread64",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "preadv", .errmsg = true, .alias = "pread",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "pread", .errmsg = true, .alias = "pread64", },
+ { .name = "preadv", .errmsg = true, .alias = "pread", },
{ .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
- { .name = "pwrite", .errmsg = true, .alias = "pwrite64",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "pwritev", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "read", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "readlink", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, },
+ { .name = "pwrite", .errmsg = true, .alias = "pwrite64", },
+ { .name = "pwritev", .errmsg = true, },
+ { .name = "read", .errmsg = true, },
+ { .name = "readlink", .errmsg = true, },
{ .name = "readlinkat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
- [1] = SCA_FILENAME, /* pathname */ }, },
- { .name = "readv", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "readv", .errmsg = true, },
{ .name = "recvfrom", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "recvmmsg", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "recvmsg", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [2] = SCA_MSG_FLAGS, /* flags */ }, },
- { .name = "removexattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "removexattr", .errmsg = true, },
{ .name = "renameat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
- { .name = "rmdir", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "rmdir", .errmsg = true, },
{ .name = "rt_sigaction", .errmsg = true,
.arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
{ .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), },
@@ -807,22 +745,17 @@ static struct syscall_fmt {
[1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
{ .name = "select", .errmsg = true, .timeout = true, },
{ .name = "sendmmsg", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "sendmsg", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [2] = SCA_MSG_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "sendto", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
- [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "set_tid_address", .errpid = true, },
{ .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), },
{ .name = "setpgid", .errmsg = true, },
{ .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
- { .name = "setxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "shutdown", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "setxattr", .errmsg = true, },
+ { .name = "shutdown", .errmsg = true, },
{ .name = "socket", .errmsg = true,
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
[1] = SCA_SK_TYPE, /* type */ },
@@ -831,10 +764,8 @@ static struct syscall_fmt {
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
[1] = SCA_SK_TYPE, /* type */ },
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
- { .name = "stat", .errmsg = true, .alias = "newstat",
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
- { .name = "statfs", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+ { .name = "stat", .errmsg = true, .alias = "newstat", },
+ { .name = "statfs", .errmsg = true, },
{ .name = "swapoff", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
{ .name = "swapon", .errmsg = true,
@@ -845,29 +776,21 @@ static struct syscall_fmt {
.arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
{ .name = "tkill", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
- { .name = "truncate", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, },
+ { .name = "truncate", .errmsg = true, },
{ .name = "uname", .errmsg = true, .alias = "newuname", },
{ .name = "unlinkat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
- [1] = SCA_FILENAME, /* pathname */ }, },
- { .name = "utime", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "utime", .errmsg = true, },
{ .name = "utimensat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */
- [1] = SCA_FILENAME, /* filename */ }, },
- { .name = "utimes", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
- { .name = "vmsplice", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
+ { .name = "utimes", .errmsg = true, },
+ { .name = "vmsplice", .errmsg = true, },
{ .name = "wait4", .errpid = true,
.arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
{ .name = "waitid", .errpid = true,
.arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
- { .name = "write", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
- { .name = "writev", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "write", .errmsg = true, },
+ { .name = "writev", .errmsg = true, },
};
static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -1160,6 +1083,24 @@ static int trace__tool_process(struct perf_tool *tool,
return trace__process_event(trace, machine, event, sample);
}
+static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+ struct machine *machine = vmachine;
+
+ if (machine->kptr_restrict_warned)
+ return NULL;
+
+ if (symbol_conf.kptr_restrict) {
+ pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+ "Check /proc/sys/kernel/kptr_restrict.\n\n"
+ "Kernel samples will not be resolved.\n");
+ machine->kptr_restrict_warned = true;
+ return NULL;
+ }
+
+ return machine__resolve_kernel_addr(vmachine, addrp, modp);
+}
+
static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
{
int err = symbol__init(NULL);
@@ -1171,7 +1112,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
if (trace->host == NULL)
return -ENOMEM;
- if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0)
+ if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
return -errno;
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
@@ -1186,7 +1127,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
static int syscall__set_arg_fmts(struct syscall *sc)
{
struct format_field *field;
- int idx = 0;
+ int idx = 0, len;
sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
if (sc->arg_scnprintf == NULL)
@@ -1198,12 +1139,31 @@ static int syscall__set_arg_fmts(struct syscall *sc)
for (field = sc->args; field; field = field->next) {
if (sc->fmt && sc->fmt->arg_scnprintf[idx])
sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
+ else if (strcmp(field->type, "const char *") == 0 &&
+ (strcmp(field->name, "filename") == 0 ||
+ strcmp(field->name, "path") == 0 ||
+ strcmp(field->name, "pathname") == 0))
+ sc->arg_scnprintf[idx] = SCA_FILENAME;
else if (field->flags & FIELD_IS_POINTER)
sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
else if (strcmp(field->type, "pid_t") == 0)
sc->arg_scnprintf[idx] = SCA_PID;
else if (strcmp(field->type, "umode_t") == 0)
sc->arg_scnprintf[idx] = SCA_MODE_T;
+ else if ((strcmp(field->type, "int") == 0 ||
+ strcmp(field->type, "unsigned int") == 0 ||
+ strcmp(field->type, "long") == 0) &&
+ (len = strlen(field->name)) >= 2 &&
+ strcmp(field->name + len - 2, "fd") == 0) {
+ /*
+ * /sys/kernel/tracing/events/syscalls/sys_enter*
+ * egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
+ * 65 int
+ * 23 unsigned int
+ * 7 unsigned long
+ */
+ sc->arg_scnprintf[idx] = SCA_FD;
+ }
++idx;
}
@@ -1534,7 +1494,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
if (sc->is_exit) {
if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
- fprintf(trace->output, "%-70s\n", ttrace->entry_str);
+ fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
}
} else {
ttrace->entry_pending = true;
@@ -2887,12 +2847,12 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
mmap_pages_user_set = false;
if (trace.max_stack == UINT_MAX) {
- trace.max_stack = sysctl_perf_event_max_stack;
+ trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
max_stack_user_set = false;
}
#ifdef HAVE_DWARF_UNWIND_SUPPORT
- if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled)
+ if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
#endif
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 797000842d40..15982cee5ef3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -549,6 +549,9 @@ int main(int argc, const char **argv)
if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
sysctl_perf_event_max_stack = value;
+ if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+ sysctl_perf_event_max_contexts_per_stack = value;
+
cmd = extract_argv0_path(argv[0]);
if (!cmd)
cmd = "perf-help";
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4db73d5a0dbc..7e5a1e8874ce 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -354,9 +354,6 @@ static struct ins_ops nop_ops = {
.scnprintf = nop__scnprintf,
};
-/*
- * Must be sorted by name!
- */
static struct ins instructions[] = {
{ .name = "add", .ops = &mov_ops, },
{ .name = "addl", .ops = &mov_ops, },
@@ -372,8 +369,8 @@ static struct ins instructions[] = {
{ .name = "bgt", .ops = &jump_ops, },
{ .name = "bhi", .ops = &jump_ops, },
{ .name = "bl", .ops = &call_ops, },
- { .name = "blt", .ops = &jump_ops, },
{ .name = "bls", .ops = &jump_ops, },
+ { .name = "blt", .ops = &jump_ops, },
{ .name = "blx", .ops = &call_ops, },
{ .name = "bne", .ops = &jump_ops, },
#endif
@@ -449,18 +446,39 @@ static struct ins instructions[] = {
{ .name = "xbeginq", .ops = &jump_ops, },
};
-static int ins__cmp(const void *name, const void *insp)
+static int ins__key_cmp(const void *name, const void *insp)
{
const struct ins *ins = insp;
return strcmp(name, ins->name);
}
+static int ins__cmp(const void *a, const void *b)
+{
+ const struct ins *ia = a;
+ const struct ins *ib = b;
+
+ return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(void)
+{
+ const int nmemb = ARRAY_SIZE(instructions);
+
+ qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
static struct ins *ins__find(const char *name)
{
const int nmemb = ARRAY_SIZE(instructions);
+ static bool sorted;
+
+ if (!sorted) {
+ ins__sort();
+ sorted = true;
+ }
- return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
+ return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
}
int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
@@ -1122,7 +1140,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
} else if (dso__is_kcore(dso)) {
goto fallback;
} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
- strstr(command, "[kernel.kallsyms]") ||
+ strstr(command, DSO__NAME_KALLSYMS) ||
access(symfs_filename, R_OK)) {
free(filename);
fallback:
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff425e1232c..67e5966503b2 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -256,7 +256,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
size_t name_len;
bool in_kernel = false;
- if (!pos->hit)
+ if (!pos->hit && !dso__is_vdso(pos))
continue;
if (dso__is_vdso(pos)) {
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index bbf69d248ec5..9f53020c3269 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -204,6 +204,44 @@ static unsigned long long adjust_signedness(unsigned long long value_int, int si
return (value_int & value_mask) | ~value_mask;
}
+static int string_set_value(struct bt_ctf_field *field, const char *string)
+{
+ char *buffer = NULL;
+ size_t len = strlen(string), i, p;
+ int err;
+
+ for (i = p = 0; i < len; i++, p++) {
+ if (isprint(string[i])) {
+ if (!buffer)
+ continue;
+ buffer[p] = string[i];
+ } else {
+ char numstr[5];
+
+ snprintf(numstr, sizeof(numstr), "\\x%02x",
+ (unsigned int)(string[i]) & 0xff);
+
+ if (!buffer) {
+ buffer = zalloc(i + (len - i) * 4 + 2);
+ if (!buffer) {
+ pr_err("failed to set unprintable string '%s'\n", string);
+ return bt_ctf_field_string_set_value(field, "UNPRINTABLE-STRING");
+ }
+ if (i > 0)
+ strncpy(buffer, string, i);
+ }
+ strncat(buffer + p, numstr, 4);
+ p += 3;
+ }
+ }
+
+ if (!buffer)
+ return bt_ctf_field_string_set_value(field, string);
+ err = bt_ctf_field_string_set_value(field, buffer);
+ free(buffer);
+ return err;
+}
+
static int add_tracepoint_field_value(struct ctf_writer *cw,
struct bt_ctf_event_class *event_class,
struct bt_ctf_event *event,
@@ -270,8 +308,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
}
if (flags & FIELD_IS_STRING)
- ret = bt_ctf_field_string_set_value(field,
- data + offset + i * len);
+ ret = string_set_value(field, data + offset + i * len);
else {
unsigned long long value_int;
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 8d96c80cc67e..c9a6dc173e74 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -298,8 +298,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
*/
callchain_param.order = ORDER_CALLER;
err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
- sample, NULL, NULL,
- sysctl_perf_event_max_stack);
+ sample, NULL, NULL, PERF_MAX_STACK_DEPTH);
if (err) {
callchain_param.order = saved_order;
return NULL;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 3357479082ca..5d286f5d7906 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,6 +7,7 @@
#include "auxtrace.h"
#include "util.h"
#include "debug.h"
+#include "vdso.h"
char dso__symtab_origin(const struct dso *dso)
{
@@ -62,9 +63,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
}
break;
case DSO_BINARY_TYPE__BUILD_ID_CACHE:
- /* skip the locally configured cache if a symfs is given */
- if (symbol_conf.symfs[0] ||
- (dso__build_id_filename(dso, filename, size) == NULL))
+ if (dso__build_id_filename(dso, filename, size) == NULL)
ret = -1;
break;
@@ -1169,7 +1168,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
struct dso *pos;
list_for_each_entry(pos, head, node) {
- if (with_hits && !pos->hit)
+ if (with_hits && !pos->hit && !dso__is_vdso(pos))
continue;
if (pos->has_build_id) {
have_build_id = true;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f6fcc6832949..9b141f12329e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -673,6 +673,8 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
int err;
union perf_event *event;
+ if (symbol_conf.kptr_restrict)
+ return -1;
if (map == NULL)
return -1;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c4bfe11479a0..e82ba90cc969 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -44,6 +44,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
perf_evlist__set_maps(evlist, cpus, threads);
fdarray__init(&evlist->pollfd, 64);
evlist->workload.pid = -1;
+ evlist->backward = false;
}
struct perf_evlist *perf_evlist__new(void)
@@ -679,6 +680,33 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
return NULL;
}
+static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
+{
+ int i;
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ int fd = evlist->mmap[i].fd;
+ int err;
+
+ if (fd < 0)
+ continue;
+ err = ioctl(fd, PERF_EVENT_IOC_PAUSE_OUTPUT, value ? 1 : 0);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+int perf_evlist__pause(struct perf_evlist *evlist)
+{
+ return perf_evlist__set_paused(evlist, true);
+}
+
+int perf_evlist__resume(struct perf_evlist *evlist)
+{
+ return perf_evlist__set_paused(evlist, false);
+}
+
/* When check_messup is true, 'end' must points to a good entry */
static union perf_event *
perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
@@ -881,6 +909,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
if (evlist->mmap[idx].base != NULL) {
munmap(evlist->mmap[idx].base, evlist->mmap_len);
evlist->mmap[idx].base = NULL;
+ evlist->mmap[idx].fd = -1;
atomic_set(&evlist->mmap[idx].refcnt, 0);
}
auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
@@ -901,10 +930,14 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
{
+ int i;
+
evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
if (cpu_map__empty(evlist->cpus))
evlist->nr_mmaps = thread_map__nr(evlist->threads);
evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+ for (i = 0; i < evlist->nr_mmaps; i++)
+ evlist->mmap[i].fd = -1;
return evlist->mmap != NULL ? 0 : -ENOMEM;
}
@@ -941,6 +974,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
evlist->mmap[idx].base = NULL;
return -1;
}
+ evlist->mmap[idx].fd = fd;
if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 85d1b59802e8..d740fb877ab6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -28,6 +28,7 @@ struct record_opts;
struct perf_mmap {
void *base;
int mask;
+ int fd;
atomic_t refcnt;
u64 prev;
struct auxtrace_mmap auxtrace_mmap;
@@ -43,6 +44,7 @@ struct perf_evlist {
bool overwrite;
bool enabled;
bool has_user_cpus;
+ bool backward;
size_t mmap_len;
int id_pos;
int is_pos;
@@ -135,6 +137,8 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
+int perf_evlist__pause(struct perf_evlist *evlist);
+int perf_evlist__resume(struct perf_evlist *evlist);
int perf_evlist__open(struct perf_evlist *evlist);
void perf_evlist__close(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 52c7d8884741..5d7037ef7d3b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -37,6 +37,7 @@ static struct {
bool clockid;
bool clockid_wrong;
bool lbr_flags;
+ bool write_backward;
} perf_missing_features;
static clockid_t clockid;
@@ -1376,6 +1377,8 @@ fallback_missing_features:
if (perf_missing_features.lbr_flags)
evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
PERF_SAMPLE_BRANCH_NO_CYCLES);
+ if (perf_missing_features.write_backward)
+ evsel->attr.write_backward = false;
retry_sample_id:
if (perf_missing_features.sample_id_all)
evsel->attr.sample_id_all = 0;
@@ -1438,6 +1441,12 @@ retry_open:
err = -EINVAL;
goto out_close;
}
+
+ if (evsel->overwrite &&
+ perf_missing_features.write_backward) {
+ err = -EINVAL;
+ goto out_close;
+ }
}
}
@@ -1500,6 +1509,10 @@ try_fallback:
PERF_SAMPLE_BRANCH_NO_FLAGS))) {
perf_missing_features.lbr_flags = true;
goto fallback_missing_features;
+ } else if (!perf_missing_features.write_backward &&
+ evsel->attr.write_backward) {
+ perf_missing_features.write_backward = true;
+ goto fallback_missing_features;
}
out_close:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8a644fef452c..c1f10159804c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -112,6 +112,7 @@ struct perf_evsel {
bool tracking;
bool per_pkg;
bool precise_max;
+ bool overwrite;
/* parse modifier helper */
int exclude_GH;
int nr_members;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cfab531437c7..d1f19e0012d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -117,6 +117,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
}
+
+ if (h->branch_info->srcline_from)
+ hists__new_col_len(hists, HISTC_SRCLINE_FROM,
+ strlen(h->branch_info->srcline_from));
+ if (h->branch_info->srcline_to)
+ hists__new_col_len(hists, HISTC_SRCLINE_TO,
+ strlen(h->branch_info->srcline_to));
}
if (h->mem_info) {
@@ -1042,6 +1049,8 @@ void hist_entry__delete(struct hist_entry *he)
if (he->branch_info) {
map__zput(he->branch_info->from.map);
map__zput(he->branch_info->to.map);
+ free_srcline(he->branch_info->srcline_from);
+ free_srcline(he->branch_info->srcline_to);
zfree(&he->branch_info);
}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 0f84bfb42bb1..7b54ccf1b737 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,6 +52,8 @@ enum hist_column {
HISTC_MEM_IADDR_SYMBOL,
HISTC_TRANSACTION,
HISTC_CYCLES,
+ HISTC_SRCLINE_FROM,
+ HISTC_SRCLINE_TO,
HISTC_TRACE,
HISTC_NR_COLS, /* Last entry */
};
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f9644f79686c..b1772180c820 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -43,6 +43,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
machine->symbol_filter = NULL;
machine->id_hdr_size = 0;
+ machine->kptr_restrict_warned = false;
machine->comm_exec = false;
machine->kernel_start = 0;
@@ -709,7 +710,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
if (machine__is_host(machine)) {
vmlinux_name = symbol_conf.vmlinux_name;
if (!vmlinux_name)
- vmlinux_name = "[kernel.kallsyms]";
+ vmlinux_name = DSO__NAME_KALLSYMS;
kernel = machine__findnew_kernel(machine, vmlinux_name,
"[kernel]", DSO_TYPE_KERNEL);
@@ -1135,10 +1136,10 @@ int machine__create_kernel_maps(struct machine *machine)
{
struct dso *kernel = machine__get_kernel(machine);
const char *name;
- u64 addr = machine__get_running_kernel_start(machine, &name);
+ u64 addr;
int ret;
- if (!addr || kernel == NULL)
+ if (kernel == NULL)
return -1;
ret = __machine__create_kernel_maps(machine, kernel);
@@ -1160,8 +1161,9 @@ int machine__create_kernel_maps(struct machine *machine)
*/
map_groups__fixup_end(&machine->kmaps);
- if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
- addr)) {
+ addr = machine__get_running_kernel_start(machine, &name);
+ if (!addr) {
+ } else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
machine__destroy_kernel_maps(machine);
return -1;
}
@@ -1769,11 +1771,6 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
*/
int mix_chain_nr = i + 1 + lbr_nr + 1;
- if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
- pr_warning("corrupted callchain. skipping...\n");
- return 0;
- }
-
for (j = 0; j < mix_chain_nr; j++) {
if (callchain_param.order == ORDER_CALLEE) {
if (j < i + 1)
@@ -1811,9 +1808,9 @@ static int thread__resolve_callchain_sample(struct thread *thread,
{
struct branch_stack *branch = sample->branch_stack;
struct ip_callchain *chain = sample->callchain;
- int chain_nr = min(max_stack, (int)chain->nr);
+ int chain_nr = chain->nr;
u8 cpumode = PERF_RECORD_MISC_USER;
- int i, j, err;
+ int i, j, err, nr_entries;
int skip_idx = -1;
int first_call = 0;
@@ -1828,8 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
* Based on DWARF debug information, some architectures skip
* a callchain entry saved by the kernel.
*/
- if (chain->nr < sysctl_perf_event_max_stack)
- skip_idx = arch_skip_callchain_idx(thread, chain);
+ skip_idx = arch_skip_callchain_idx(thread, chain);
/*
* Add branches to call stack for easier browsing. This gives
@@ -1889,12 +1885,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
}
check_calls:
- if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
- pr_warning("corrupted callchain. skipping...\n");
- return 0;
- }
-
- for (i = first_call; i < chain_nr; i++) {
+ for (i = first_call, nr_entries = 0;
+ i < chain_nr && nr_entries < max_stack; i++) {
u64 ip;
if (callchain_param.order == ORDER_CALLEE)
@@ -1908,6 +1900,9 @@ check_calls:
#endif
ip = chain->ips[j];
+ if (ip < PERF_CONTEXT_MAX)
+ ++nr_entries;
+
err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
if (err)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 83f46790c52f..41ac9cfd416b 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -28,6 +28,7 @@ struct machine {
pid_t pid;
u16 id_hdr_size;
bool comm_exec;
+ bool kptr_restrict_warned;
char *root_dir;
struct rb_root threads;
pthread_rwlock_t threads_lock;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 62c7f6988e0e..5d1eb1ccd96c 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -264,8 +264,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
goto exit;
if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
- sample, NULL, NULL,
- sysctl_perf_event_max_stack) != 0) {
+ sample, NULL, NULL, scripting_max_stack) != 0) {
pr_err("Failed to resolve callchain. Skipping\n");
goto exit;
}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 20e69edd5006..c4e9bd70723c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -353,6 +353,88 @@ struct sort_entry sort_srcline = {
.se_width_idx = HISTC_SRCLINE,
};
+/* --sort srcline_from */
+
+static int64_t
+sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ if (!left->branch_info->srcline_from) {
+ struct map *map = left->branch_info->from.map;
+ if (!map)
+ left->branch_info->srcline_from = SRCLINE_UNKNOWN;
+ else
+ left->branch_info->srcline_from = get_srcline(map->dso,
+ map__rip_2objdump(map,
+ left->branch_info->from.al_addr),
+ left->branch_info->from.sym, true);
+ }
+ if (!right->branch_info->srcline_from) {
+ struct map *map = right->branch_info->from.map;
+ if (!map)
+ right->branch_info->srcline_from = SRCLINE_UNKNOWN;
+ else
+ right->branch_info->srcline_from = get_srcline(map->dso,
+ map__rip_2objdump(map,
+ right->branch_info->from.al_addr),
+ right->branch_info->from.sym, true);
+ }
+ return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
+}
+
+static int hist_entry__srcline_from_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_from);
+}
+
+struct sort_entry sort_srcline_from = {
+ .se_header = "From Source:Line",
+ .se_cmp = sort__srcline_from_cmp,
+ .se_snprintf = hist_entry__srcline_from_snprintf,
+ .se_width_idx = HISTC_SRCLINE_FROM,
+};
+
+/* --sort srcline_to */
+
+static int64_t
+sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ if (!left->branch_info->srcline_to) {
+ struct map *map = left->branch_info->to.map;
+ if (!map)
+ left->branch_info->srcline_to = SRCLINE_UNKNOWN;
+ else
+ left->branch_info->srcline_to = get_srcline(map->dso,
+ map__rip_2objdump(map,
+ left->branch_info->to.al_addr),
+ left->branch_info->from.sym, true);
+ }
+ if (!right->branch_info->srcline_to) {
+ struct map *map = right->branch_info->to.map;
+ if (!map)
+ right->branch_info->srcline_to = SRCLINE_UNKNOWN;
+ else
+ right->branch_info->srcline_to = get_srcline(map->dso,
+ map__rip_2objdump(map,
+ right->branch_info->to.al_addr),
+ right->branch_info->to.sym, true);
+ }
+ return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
+}
+
+static int hist_entry__srcline_to_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_to);
+}
+
+struct sort_entry sort_srcline_to = {
+ .se_header = "To Source:Line",
+ .se_cmp = sort__srcline_to_cmp,
+ .se_snprintf = hist_entry__srcline_to_snprintf,
+ .se_width_idx = HISTC_SRCLINE_TO,
+};
+
/* --sort srcfile */
static char no_srcfile[1];
@@ -1347,6 +1429,8 @@ static struct sort_dimension bstack_sort_dimensions[] = {
DIM(SORT_IN_TX, "in_tx", sort_in_tx),
DIM(SORT_ABORT, "abort", sort_abort),
DIM(SORT_CYCLES, "cycles", sort_cycles),
+ DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from),
+ DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to),
};
#undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 42927f448bcb..ebb59cacd092 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -215,6 +215,8 @@ enum sort_type {
SORT_ABORT,
SORT_IN_TX,
SORT_CYCLES,
+ SORT_SRCLINE_FROM,
+ SORT_SRCLINE_TO,
/* memory mode specific sort keys */
__SORT_MEMORY_MODE,
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index fdb71961143e..aa9efe08762b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
{
int ctx = evsel_context(counter);
- if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+ if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
+ perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
update_stats(&runtime_nsecs_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
@@ -188,7 +189,7 @@ static void print_stalled_cycles_backend(int cpu,
color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
- out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
+ out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
}
static void print_branch_misses(int cpu,
@@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
ratio = total / avg;
print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
- } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+ } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
+ perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
avg / ratio);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7fb33304fb4e..54c4ff2b1cee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1662,8 +1662,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
- scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
- sbuild_id);
+ scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
+ DSO__NAME_KCORE, sbuild_id);
/* Use /proc/kallsyms if possible */
if (is_host) {
@@ -1699,8 +1699,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
if (!find_matching_kcore(map, path, sizeof(path)))
return strdup(path);
- scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
- buildid_dir, sbuild_id);
+ scnprintf(path, sizeof(path), "%s/%s/%s",
+ buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
if (access(path, F_OK)) {
pr_err("No kallsyms or vmlinux with build-id %s was found\n",
@@ -1769,7 +1769,7 @@ do_kallsyms:
if (err > 0 && !dso__is_kcore(dso)) {
dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
- dso__set_long_name(dso, "[kernel.kallsyms]", false);
+ dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
map__fixup_start(map);
map__fixup_end(map);
}
@@ -1933,17 +1933,17 @@ int setup_intlist(struct intlist **list, const char *list_str,
static bool symbol__read_kptr_restrict(void)
{
bool value = false;
+ FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
- if (geteuid() != 0) {
- FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
- if (fp != NULL) {
- char line[8];
+ if (fp != NULL) {
+ char line[8];
- if (fgets(line, sizeof(line), fp) != NULL)
- value = atoi(line) != 0;
+ if (fgets(line, sizeof(line), fp) != NULL)
+ value = (geteuid() != 0) ?
+ (atoi(line) != 0) :
+ (atoi(line) == 2);
- fclose(fp);
- }
+ fclose(fp);
}
return value;
@@ -2033,3 +2033,26 @@ void symbol__exit(void)
symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
symbol_conf.initialized = false;
}
+
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+ const char *dir, int unset __maybe_unused)
+{
+ char *bf = NULL;
+ int ret;
+
+ symbol_conf.symfs = strdup(dir);
+ if (symbol_conf.symfs == NULL)
+ return -ENOMEM;
+
+ /* skip the locally configured cache if a symfs is given, and
+ * config buildid dir to symfs/.debug
+ */
+ ret = asprintf(&bf, "%s/%s", dir, ".debug");
+ if (ret < 0)
+ return -ENOMEM;
+
+ set_buildid_dir(bf);
+
+ free(bf);
+ return 0;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2b5e4ed76fcb..b10d558a8803 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -44,6 +44,9 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */
#endif
+#define DSO__NAME_KALLSYMS "[kernel.kallsyms]"
+#define DSO__NAME_KCORE "[kernel.kcore]"
+
/** struct symbol - symtab entry
*
* @ignore - resolvable but tools ignore it (e.g. idle routines)
@@ -183,6 +186,8 @@ struct branch_info {
struct addr_map_symbol from;
struct addr_map_symbol to;
struct branch_flags flags;
+ char *srcline_from;
+ char *srcline_to;
};
struct mem_info {
@@ -287,6 +292,8 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
bool symbol__restricted_filename(const char *filename,
const char *restricted_filename);
bool symbol__is_idle(struct symbol *sym);
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+ const char *dir, int unset __maybe_unused);
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, symbol_filter_t filter,
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f92c37abb0a8..b2940c88734a 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -27,7 +27,6 @@ struct perf_top {
int max_stack;
bool hide_kernel_symbols, hide_user_symbols, zero;
bool use_tui, use_stdio;
- bool kptr_restrict_warned;
bool vmlinux_warned;
bool dump_symtab;
struct hist_entry *sym_filter_entry;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eab077ad6ca9..23504ad5d6dd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -33,7 +33,8 @@ struct callchain_param callchain_param = {
unsigned int page_size;
int cacheline_size;
-unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
bool test_attr__enabled;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7651633a8dc7..1e8c3167b9fb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig);
extern unsigned int page_size;
extern int cacheline_size;
-extern unsigned int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
struct parse_tag {
char tag;
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index c2b61c4fda11..0bf5085281f3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -23,15 +23,14 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
exit_unsupported
fi
-reset_tracer
-do_reset
-
-FEATURE=`grep hist events/sched/sched_process_fork/trigger`
-if [ -z "$FEATURE" ]; then
+if [ ! -f events/sched/sched_process_fork/hist ]; then
echo "hist trigger is not supported"
exit_unsupported
fi
+reset_tracer
+do_reset
+
echo "Test histogram with execname modifier"
echo 'hist:keys=common_pid.execname' > events/sched/sched_process_fork/trigger
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
index b2902d42a537..a00184cd9c95 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -23,15 +23,14 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
exit_unsupported
fi
-reset_tracer
-do_reset
-
-FEATURE=`grep hist events/sched/sched_process_fork/trigger`
-if [ -z "$FEATURE" ]; then
+if [ ! -f events/sched/sched_process_fork/hist ]; then
echo "hist trigger is not supported"
exit_unsupported
fi
+reset_tracer
+do_reset
+
echo "Test histogram basic tigger"
echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index 03c4a46561fc..3478b00ead57 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -23,15 +23,14 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
exit_unsupported
fi
-reset_tracer
-do_reset
-
-FEATURE=`grep hist events/sched/sched_process_fork/trigger`
-if [ -z "$FEATURE" ]; then
+if [ ! -f events/sched/sched_process_fork/hist ]; then
echo "hist trigger is not supported"
exit_unsupported
fi
+reset_tracer
+do_reset
+
reset_trigger
echo "Test histogram multiple tiggers"
diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index 96ba386b1b7b..4a8217448f20 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -111,9 +111,9 @@ static void attach_ebpf(int fd, uint16_t mod)
memset(&attr, 0, sizeof(attr));
attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
attr.insn_cnt = ARRAY_SIZE(prog);
- attr.insns = (uint64_t)prog;
- attr.license = (uint64_t)bpf_license;
- attr.log_buf = (uint64_t)bpf_log_buf;
+ attr.insns = (unsigned long) &prog;
+ attr.license = (unsigned long) &bpf_license;
+ attr.log_buf = (unsigned long) &bpf_log_buf;
attr.log_size = sizeof(bpf_log_buf);
attr.log_level = 1;
attr.kern_version = 0;
@@ -351,8 +351,8 @@ static void test_filter_no_reuseport(const struct test_params p)
memset(&eprog, 0, sizeof(eprog));
eprog.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
eprog.insn_cnt = ARRAY_SIZE(ecode);
- eprog.insns = (uint64_t)ecode;
- eprog.license = (uint64_t)bpf_license;
+ eprog.insns = (unsigned long) &ecode;
+ eprog.license = (unsigned long) &bpf_license;
eprog.kern_version = 0;
memset(&cprog, 0, sizeof(cprog));
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 7947e568e057..2e58549b2f02 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1234,6 +1234,10 @@ TEST_F(TRACE_poke, getpid_runs_normally)
# define ARCH_REGS struct user_pt_regs
# define SYSCALL_NUM regs[8]
# define SYSCALL_RET regs[0]
+#elif defined(__hppa__)
+# define ARCH_REGS struct user_regs_struct
+# define SYSCALL_NUM gr[20]
+# define SYSCALL_RET gr[28]
#elif defined(__powerpc__)
# define ARCH_REGS struct pt_regs
# define SYSCALL_NUM gpr[0]
@@ -1303,7 +1307,7 @@ void change_syscall(struct __test_metadata *_metadata,
EXPECT_EQ(0, ret);
#if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \
- defined(__s390__)
+ defined(__s390__) || defined(__hppa__)
{
regs.SYSCALL_NUM = syscall;
}
@@ -1505,6 +1509,8 @@ TEST_F(TRACE_syscall, syscall_dropped)
# define __NR_seccomp 383
# elif defined(__aarch64__)
# define __NR_seccomp 277
+# elif defined(__hppa__)
+# define __NR_seccomp 338
# elif defined(__powerpc__)
# define __NR_seccomp 358
# elif defined(__s390__)
diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c
index 932ff577ffc0..00c4f65d12da 100644
--- a/tools/testing/selftests/vm/compaction_test.c
+++ b/tools/testing/selftests/vm/compaction_test.c
@@ -136,7 +136,7 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
printf("No of huge pages allocated = %d\n",
(atoi(nr_hugepages)));
- if (write(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages))
+ if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages))
!= strlen(initial_nr_hugepages)) {
perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
goto close_fd;
diff --git a/tools/testing/selftests/vm/thuge-gen.c b/tools/testing/selftests/vm/thuge-gen.c
index c87957295f74..0bc737a75150 100644
--- a/tools/testing/selftests/vm/thuge-gen.c
+++ b/tools/testing/selftests/vm/thuge-gen.c
@@ -30,7 +30,9 @@
#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT)
#define MAP_HUGE_SHIFT 26
#define MAP_HUGE_MASK 0x3f
+#if !defined(MAP_HUGETLB)
#define MAP_HUGETLB 0x40000
+#endif
#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */
#define SHM_HUGE_SHIFT 26
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index feaa64ac4630..6173adae9f08 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -1,6 +1,6 @@
all:
-all: ring virtio_ring_0_9 virtio_ring_poll
+all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder noring
CFLAGS += -Wall
CFLAGS += -pthread -O2 -ggdb
@@ -10,13 +10,18 @@ main.o: main.c main.h
ring.o: ring.c main.h
virtio_ring_0_9.o: virtio_ring_0_9.c main.h
virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h
+virtio_ring_inorder.o: virtio_ring_inorder.c virtio_ring_0_9.c main.h
ring: ring.o main.o
virtio_ring_0_9: virtio_ring_0_9.o main.o
virtio_ring_poll: virtio_ring_poll.o main.o
+virtio_ring_inorder: virtio_ring_inorder.o main.o
+noring: noring.o main.o
clean:
-rm main.o
-rm ring.o ring
-rm virtio_ring_0_9.o virtio_ring_0_9
-rm virtio_ring_poll.o virtio_ring_poll
+ -rm virtio_ring_inorder.o virtio_ring_inorder
+ -rm noring.o noring
.PHONY: all clean
diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
index 34e94c46104f..d83707a336c9 100644
--- a/tools/virtio/ringtest/README
+++ b/tools/virtio/ringtest/README
@@ -1,2 +1,6 @@
Partial implementation of various ring layouts, useful to tune virtio design.
Uses shared memory heavily.
+
+Typical use:
+
+# sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c
index 3a5ff438bd62..147abb452a6c 100644
--- a/tools/virtio/ringtest/main.c
+++ b/tools/virtio/ringtest/main.c
@@ -115,7 +115,7 @@ static void run_guest(void)
do {
if (started < bufs &&
started - completed < max_outstanding) {
- r = add_inbuf(0, NULL, "Hello, world!");
+ r = add_inbuf(0, "Buffer\n", "Hello, world!");
if (__builtin_expect(r == 0, true)) {
++started;
if (!--tokick) {
diff --git a/tools/virtio/ringtest/noring.c b/tools/virtio/ringtest/noring.c
new file mode 100644
index 000000000000..eda2f4824130
--- /dev/null
+++ b/tools/virtio/ringtest/noring.c
@@ -0,0 +1,69 @@
+#define _GNU_SOURCE
+#include "main.h"
+#include <assert.h>
+
+/* stub implementation: useful for measuring overhead */
+void alloc_ring(void)
+{
+}
+
+/* guest side */
+int add_inbuf(unsigned len, void *buf, void *datap)
+{
+ return 0;
+}
+
+/*
+ * skb_array API provides no way for producer to find out whether a given
+ * buffer was consumed. Our tests merely require that a successful get_buf
+ * implies that add_inbuf succeed in the past, and that add_inbuf will succeed,
+ * fake it accordingly.
+ */
+void *get_buf(unsigned *lenp, void **bufp)
+{
+ return "Buffer";
+}
+
+void poll_used(void)
+{
+}
+
+void disable_call()
+{
+ assert(0);
+}
+
+bool enable_call()
+{
+ assert(0);
+}
+
+void kick_available(void)
+{
+ assert(0);
+}
+
+/* host side */
+void disable_kick()
+{
+ assert(0);
+}
+
+bool enable_kick()
+{
+ assert(0);
+}
+
+void poll_avail(void)
+{
+}
+
+bool use_buf(unsigned *lenp, void **bufp)
+{
+ return true;
+}
+
+void call_used(void)
+{
+ assert(0);
+}
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71ffa8d..2e69ca812b4c 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
#run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c
index 47c9a1a18d36..761866212aac 100644
--- a/tools/virtio/ringtest/virtio_ring_0_9.c
+++ b/tools/virtio/ringtest/virtio_ring_0_9.c
@@ -26,6 +26,14 @@ struct vring ring;
* high bits of ring id ^ 0x8000).
*/
/* #ifdef RING_POLL */
+/* enabling the below activates experimental in-order code
+ * (which skips ring updates and reads and writes len in descriptor).
+ */
+/* #ifdef INORDER */
+
+#if defined(RING_POLL) && defined(INORDER)
+#error "RING_POLL and INORDER are mutually exclusive"
+#endif
/* how much padding is needed to avoid false cache sharing */
#define HOST_GUEST_PADDING 0x80
@@ -35,7 +43,11 @@ struct guest {
unsigned short last_used_idx;
unsigned short num_free;
unsigned short kicked_avail_idx;
+#ifndef INORDER
unsigned short free_head;
+#else
+ unsigned short reserved_free_head;
+#endif
unsigned char reserved[HOST_GUEST_PADDING - 10];
} guest;
@@ -66,8 +78,10 @@ void alloc_ring(void)
guest.avail_idx = 0;
guest.kicked_avail_idx = -1;
guest.last_used_idx = 0;
+#ifndef INORDER
/* Put everything in free lists. */
guest.free_head = 0;
+#endif
for (i = 0; i < ring_size - 1; i++)
ring.desc[i].next = i + 1;
host.used_idx = 0;
@@ -84,13 +98,20 @@ void alloc_ring(void)
/* guest side */
int add_inbuf(unsigned len, void *buf, void *datap)
{
- unsigned head, avail;
+ unsigned head;
+#ifndef INORDER
+ unsigned avail;
+#endif
struct vring_desc *desc;
if (!guest.num_free)
return -1;
+#ifdef INORDER
+ head = (ring_size - 1) & (guest.avail_idx++);
+#else
head = guest.free_head;
+#endif
guest.num_free--;
desc = ring.desc;
@@ -102,7 +123,9 @@ int add_inbuf(unsigned len, void *buf, void *datap)
* descriptors.
*/
desc[head].flags &= ~VRING_DESC_F_NEXT;
+#ifndef INORDER
guest.free_head = desc[head].next;
+#endif
data[head].data = datap;
@@ -113,8 +136,12 @@ int add_inbuf(unsigned len, void *buf, void *datap)
ring.avail->ring[avail & (ring_size - 1)] =
(head | (avail & ~(ring_size - 1))) ^ 0x8000;
#else
+#ifndef INORDER
+ /* Barrier A (for pairing) */
+ smp_release();
avail = (ring_size - 1) & (guest.avail_idx++);
ring.avail->ring[avail] = head;
+#endif
/* Barrier A (for pairing) */
smp_release();
#endif
@@ -141,15 +168,27 @@ void *get_buf(unsigned *lenp, void **bufp)
return NULL;
/* Barrier B (for pairing) */
smp_acquire();
+#ifdef INORDER
+ head = (ring_size - 1) & guest.last_used_idx;
+ index = head;
+#else
head = (ring_size - 1) & guest.last_used_idx;
index = ring.used->ring[head].id;
#endif
+
+#endif
+#ifdef INORDER
+ *lenp = ring.desc[index].len;
+#else
*lenp = ring.used->ring[head].len;
+#endif
datap = data[index].data;
*bufp = (void*)(unsigned long)ring.desc[index].addr;
data[index].data = NULL;
+#ifndef INORDER
ring.desc[index].next = guest.free_head;
guest.free_head = index;
+#endif
guest.num_free++;
guest.last_used_idx++;
return datap;
@@ -283,16 +322,24 @@ bool use_buf(unsigned *lenp, void **bufp)
smp_acquire();
used_idx &= ring_size - 1;
+#ifdef INORDER
+ head = used_idx;
+#else
head = ring.avail->ring[used_idx];
+#endif
desc = &ring.desc[head];
#endif
*lenp = desc->len;
*bufp = (void *)(unsigned long)desc->addr;
+#ifdef INORDER
+ desc->len = desc->len - 1;
+#else
/* now update used ring */
ring.used->ring[used_idx].id = head;
ring.used->ring[used_idx].len = desc->len - 1;
+#endif
/* Barrier B (for pairing) */
smp_release();
host.used_idx++;
diff --git a/tools/virtio/ringtest/virtio_ring_inorder.c b/tools/virtio/ringtest/virtio_ring_inorder.c
new file mode 100644
index 000000000000..2438ca58a2ad
--- /dev/null
+++ b/tools/virtio/ringtest/virtio_ring_inorder.c
@@ -0,0 +1,2 @@
+#define INORDER 1
+#include "virtio_ring_0_9.c"
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 1889163f2f05..7cf6e1769903 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -492,7 +492,7 @@ static void slab_stats(struct slabinfo *s)
s->deactivate_to_head + s->deactivate_to_tail + s->deactivate_bypass;
if (total) {
- printf("\nSlab Deactivation Ocurrences %%\n");
+ printf("\nSlab Deactivation Occurrences %%\n");
printf("-------------------------------------------------\n");
printf("Slab full %7lu %3lu%%\n",
s->deactivate_full, (s->deactivate_full * 100) / total);
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 409db3304471..e2d5b6f988fb 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -20,6 +20,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <clocksource/arm_arch_timer.h>
#include <asm/arch_timer.h>
@@ -174,10 +175,10 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
timer->active_cleared_last = false;
timer->irq.level = new_level;
- trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
+ trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->irq.irq,
timer->irq.level);
ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id,
- timer->map,
+ timer->irq.irq,
timer->irq.level);
WARN_ON(ret);
}
@@ -196,7 +197,7 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
* because the guest would never see the interrupt. Instead wait
* until we call this function from kvm_timer_flush_hwstate.
*/
- if (!vgic_initialized(vcpu->kvm))
+ if (!vgic_initialized(vcpu->kvm) || !timer->enabled)
return -ENODEV;
if (kvm_timer_should_fire(vcpu) != timer->irq.level)
@@ -274,10 +275,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
* to ensure that hardware interrupts from the timer triggers a guest
* exit.
*/
- if (timer->irq.level || kvm_vgic_map_is_active(vcpu, timer->map))
- phys_active = true;
- else
- phys_active = false;
+ phys_active = timer->irq.level ||
+ kvm_vgic_map_is_active(vcpu, timer->irq.irq);
/*
* We want to avoid hitting the (re)distributor as much as
@@ -302,7 +301,7 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
if (timer->active_cleared_last && !phys_active)
return;
- ret = irq_set_irqchip_state(timer->map->irq,
+ ret = irq_set_irqchip_state(host_vtimer_irq,
IRQCHIP_STATE_ACTIVE,
phys_active);
WARN_ON(ret);
@@ -334,7 +333,6 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
const struct kvm_irq_level *irq)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
- struct irq_phys_map *map;
/*
* The vcpu timer irq number cannot be determined in
@@ -353,15 +351,6 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
timer->cntv_ctl = 0;
kvm_timer_update_state(vcpu);
- /*
- * Tell the VGIC that the virtual interrupt is tied to a
- * physical interrupt. We do that once per VCPU.
- */
- map = kvm_vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq);
- if (WARN_ON(IS_ERR(map)))
- return PTR_ERR(map);
-
- timer->map = map;
return 0;
}
@@ -487,14 +476,43 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
timer_disarm(timer);
- if (timer->map)
- kvm_vgic_unmap_phys_irq(vcpu, timer->map);
+ kvm_vgic_unmap_phys_irq(vcpu, timer->irq.irq);
}
-void kvm_timer_enable(struct kvm *kvm)
+int kvm_timer_enable(struct kvm_vcpu *vcpu)
{
- if (kvm->arch.timer.enabled)
- return;
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+ struct irq_desc *desc;
+ struct irq_data *data;
+ int phys_irq;
+ int ret;
+
+ if (timer->enabled)
+ return 0;
+
+ /*
+ * Find the physical IRQ number corresponding to the host_vtimer_irq
+ */
+ desc = irq_to_desc(host_vtimer_irq);
+ if (!desc) {
+ kvm_err("%s: no interrupt descriptor\n", __func__);
+ return -EINVAL;
+ }
+
+ data = irq_desc_get_irq_data(desc);
+ while (data->parent_data)
+ data = data->parent_data;
+
+ phys_irq = data->hwirq;
+
+ /*
+ * Tell the VGIC that the virtual interrupt is tied to a
+ * physical interrupt. We do that once per VCPU.
+ */
+ ret = kvm_vgic_map_phys_irq(vcpu, timer->irq.irq, phys_irq);
+ if (ret)
+ return ret;
+
/*
* There is a potential race here between VCPUs starting for the first
@@ -505,7 +523,9 @@ void kvm_timer_enable(struct kvm *kvm)
* the arch timers are enabled.
*/
if (timecounter && wqueue)
- kvm->arch.timer.enabled = 1;
+ timer->enabled = 1;
+
+ return 0;
}
void kvm_timer_init(struct kvm *kvm)
diff --git a/virt/kvm/arm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c
index ea00d69e7078..798866a8d875 100644
--- a/virt/kvm/arm/hyp/timer-sr.c
+++ b/virt/kvm/arm/hyp/timer-sr.c
@@ -24,11 +24,10 @@
/* vcpu is already in the HYP VA space */
void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
{
- struct kvm *kvm = kern_hyp_va(vcpu->kvm);
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
u64 val;
- if (kvm->arch.timer.enabled) {
+ if (timer->enabled) {
timer->cntv_ctl = read_sysreg_el0(cntv_ctl);
timer->cntv_cval = read_sysreg_el0(cntv_cval);
}
@@ -60,7 +59,7 @@ void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu)
val |= CNTHCTL_EL1PCTEN;
write_sysreg(val, cnthctl_el2);
- if (kvm->arch.timer.enabled) {
+ if (timer->enabled) {
write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
write_sysreg_el0(timer->cntv_cval, cntv_cval);
isb();
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
index 674bdf8ecf4f..3a3a699b7489 100644
--- a/virt/kvm/arm/hyp/vgic-v2-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -21,11 +21,18 @@
#include <asm/kvm_hyp.h>
+#ifdef CONFIG_KVM_NEW_VGIC
+extern struct vgic_global kvm_vgic_global_state;
+#define vgic_v2_params kvm_vgic_global_state
+#else
+extern struct vgic_params vgic_v2_params;
+#endif
+
static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
- int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+ int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
u32 eisr0, eisr1;
int i;
bool expect_mi;
@@ -67,7 +74,7 @@ static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
- int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+ int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
u32 elrsr0, elrsr1;
elrsr0 = readl_relaxed(base + GICH_ELRSR0);
@@ -86,19 +93,18 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
- int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+ int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
int i;
for (i = 0; i < nr_lr; i++) {
if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
continue;
- if (cpu_if->vgic_elrsr & (1UL << i)) {
+ if (cpu_if->vgic_elrsr & (1UL << i))
cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
- continue;
- }
+ else
+ cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
- cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
writel_relaxed(0, base + GICH_LR0 + (i * 4));
}
}
@@ -141,13 +147,13 @@ void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
struct vgic_dist *vgic = &kvm->arch.vgic;
void __iomem *base = kern_hyp_va(vgic->vctrl_base);
- int i, nr_lr;
+ int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
+ int i;
u64 live_lrs = 0;
if (!base)
return;
- nr_lr = vcpu->arch.vgic_cpu.nr_lr;
for (i = 0; i < nr_lr; i++)
if (cpu_if->vgic_lr[i] & GICH_LR_STATE)
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 575c7aa30d7e..a027569facfa 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -436,7 +436,14 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
return 0;
}
-static bool irq_is_valid(struct kvm *kvm, int irq, bool is_ppi)
+#define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS)
+
+/*
+ * For one VM the interrupt type must be same for each vcpu.
+ * As a PPI, the interrupt number is the same for all vcpus,
+ * while as an SPI it must be a separate number per vcpu.
+ */
+static bool pmu_irq_is_valid(struct kvm *kvm, int irq)
{
int i;
struct kvm_vcpu *vcpu;
@@ -445,7 +452,7 @@ static bool irq_is_valid(struct kvm *kvm, int irq, bool is_ppi)
if (!kvm_arm_pmu_irq_initialized(vcpu))
continue;
- if (is_ppi) {
+ if (irq_is_ppi(irq)) {
if (vcpu->arch.pmu.irq_num != irq)
return false;
} else {
@@ -457,7 +464,6 @@ static bool irq_is_valid(struct kvm *kvm, int irq, bool is_ppi)
return true;
}
-
int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
switch (attr->attr) {
@@ -471,14 +477,11 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
if (get_user(irq, uaddr))
return -EFAULT;
- /*
- * The PMU overflow interrupt could be a PPI or SPI, but for one
- * VM the interrupt type must be same for each vcpu. As a PPI,
- * the interrupt number is the same for all vcpus, while as an
- * SPI it must be a separate number per vcpu.
- */
- if (irq < VGIC_NR_SGIS || irq >= vcpu->kvm->arch.vgic.nr_irqs ||
- !irq_is_valid(vcpu->kvm, irq, irq < VGIC_NR_PRIVATE_IRQS))
+ /* The PMU overflow interrupt can be a PPI or a valid SPI. */
+ if (!(irq_is_ppi(irq) || vgic_valid_spi(vcpu->kvm, irq)))
+ return -EINVAL;
+
+ if (!pmu_irq_is_valid(vcpu->kvm, irq))
return -EINVAL;
if (kvm_arm_pmu_irq_initialized(vcpu))
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index 7e826c9b2b0a..334cd7a89106 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -171,7 +171,7 @@ static const struct vgic_ops vgic_v2_ops = {
.enable = vgic_v2_enable,
};
-static struct vgic_params vgic_v2_params;
+struct vgic_params __section(.hyp.text) vgic_v2_params;
static void vgic_cpu_init_lrs(void *params)
{
@@ -201,6 +201,8 @@ int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
const struct resource *vctrl_res = &gic_kvm_info->vctrl;
const struct resource *vcpu_res = &gic_kvm_info->vcpu;
+ memset(vgic, 0, sizeof(*vgic));
+
if (!gic_kvm_info->maint_irq) {
kvm_err("error getting vgic maintenance irq\n");
ret = -ENXIO;
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index c02a1b1cf855..75b02fa86436 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -29,12 +29,6 @@
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
-/* These are for GICv2 emulation only */
-#define GICH_LR_VIRTUALID (0x3ffUL << 0)
-#define GICH_LR_PHYSID_CPUID_SHIFT (10)
-#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT)
-#define ICH_LR_VIRTUALID_MASK (BIT_ULL(32) - 1)
-
static u32 ich_vtr_el2;
static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
@@ -43,7 +37,7 @@ static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr];
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
- lr_desc.irq = val & ICH_LR_VIRTUALID_MASK;
+ lr_desc.irq = val & ICH_LR_VIRTUAL_ID_MASK;
else
lr_desc.irq = val & GICH_LR_VIRTUALID;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 60668a7f319a..c3bfbb981e73 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -690,12 +690,11 @@ bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
*/
void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
u64 elrsr = vgic_get_elrsr(vcpu);
unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
int i;
- for_each_clear_bit(i, elrsr_ptr, vgic_cpu->nr_lr) {
+ for_each_clear_bit(i, elrsr_ptr, vgic->nr_lr) {
struct vgic_lr lr = vgic_get_lr(vcpu, i);
/*
@@ -820,7 +819,6 @@ static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu,
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_io_device *iodev = container_of(this,
struct vgic_io_device, dev);
- struct kvm_run *run = vcpu->run;
const struct vgic_io_range *range;
struct kvm_exit_mmio mmio;
bool updated_state;
@@ -849,12 +847,6 @@ static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu,
updated_state = false;
}
spin_unlock(&dist->lock);
- run->mmio.is_write = is_write;
- run->mmio.len = len;
- run->mmio.phys_addr = addr;
- memcpy(run->mmio.data, val, len);
-
- kvm_handle_mmio_return(vcpu, run);
if (updated_state)
vgic_kick_vcpus(vcpu->kvm);
@@ -1102,18 +1094,18 @@ static bool dist_active_irq(struct kvm_vcpu *vcpu)
return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu);
}
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map)
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq)
{
int i;
- for (i = 0; i < vcpu->arch.vgic_cpu.nr_lr; i++) {
+ for (i = 0; i < vgic->nr_lr; i++) {
struct vgic_lr vlr = vgic_get_lr(vcpu, i);
- if (vlr.irq == map->virt_irq && vlr.state & LR_STATE_ACTIVE)
+ if (vlr.irq == virt_irq && vlr.state & LR_STATE_ACTIVE)
return true;
}
- return vgic_irq_is_active(vcpu, map->virt_irq);
+ return vgic_irq_is_active(vcpu, virt_irq);
}
/*
@@ -1521,7 +1513,6 @@ static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
}
static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
- struct irq_phys_map *map,
unsigned int irq_num, bool level)
{
struct vgic_dist *dist = &kvm->arch.vgic;
@@ -1660,14 +1651,14 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
if (map)
return -EINVAL;
- return vgic_update_irq_pending(kvm, cpuid, NULL, irq_num, level);
+ return vgic_update_irq_pending(kvm, cpuid, irq_num, level);
}
/**
* kvm_vgic_inject_mapped_irq - Inject a physically mapped IRQ to the vgic
* @kvm: The VM structure pointer
* @cpuid: The CPU for PPIs
- * @map: Pointer to a irq_phys_map structure describing the mapping
+ * @virt_irq: The virtual IRQ to be injected
* @level: Edge-triggered: true: to trigger the interrupt
* false: to ignore the call
* Level-sensitive true: raise the input signal
@@ -1678,7 +1669,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
* being HIGH and 0 being LOW and all devices being active-HIGH.
*/
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
- struct irq_phys_map *map, bool level)
+ unsigned int virt_irq, bool level)
{
int ret;
@@ -1686,7 +1677,7 @@ int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
if (ret)
return ret;
- return vgic_update_irq_pending(kvm, cpuid, map, map->virt_irq, level);
+ return vgic_update_irq_pending(kvm, cpuid, virt_irq, level);
}
static irqreturn_t vgic_maintenance_handler(int irq, void *data)
@@ -1712,43 +1703,28 @@ static struct list_head *vgic_get_irq_phys_map_list(struct kvm_vcpu *vcpu,
/**
* kvm_vgic_map_phys_irq - map a virtual IRQ to a physical IRQ
* @vcpu: The VCPU pointer
- * @virt_irq: The virtual irq number
- * @irq: The Linux IRQ number
+ * @virt_irq: The virtual IRQ number for the guest
+ * @phys_irq: The hardware IRQ number of the host
*
* Establish a mapping between a guest visible irq (@virt_irq) and a
- * Linux irq (@irq). On injection, @virt_irq will be associated with
- * the physical interrupt represented by @irq. This mapping can be
+ * hardware irq (@phys_irq). On injection, @virt_irq will be associated with
+ * the physical interrupt represented by @phys_irq. This mapping can be
* established multiple times as long as the parameters are the same.
*
- * Returns a valid pointer on success, and an error pointer otherwise
+ * Returns 0 on success or an error value otherwise.
*/
-struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
- int virt_irq, int irq)
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct list_head *root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
struct irq_phys_map *map;
struct irq_phys_map_entry *entry;
- struct irq_desc *desc;
- struct irq_data *data;
- int phys_irq;
-
- desc = irq_to_desc(irq);
- if (!desc) {
- kvm_err("%s: no interrupt descriptor\n", __func__);
- return ERR_PTR(-EINVAL);
- }
-
- data = irq_desc_get_irq_data(desc);
- while (data->parent_data)
- data = data->parent_data;
-
- phys_irq = data->hwirq;
+ int ret = 0;
/* Create a new mapping */
entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
spin_lock(&dist->irq_phys_map_lock);
@@ -1756,9 +1732,8 @@ struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
map = vgic_irq_map_search(vcpu, virt_irq);
if (map) {
/* Make sure this mapping matches */
- if (map->phys_irq != phys_irq ||
- map->irq != irq)
- map = ERR_PTR(-EINVAL);
+ if (map->phys_irq != phys_irq)
+ ret = -EINVAL;
/* Found an existing, valid mapping */
goto out;
@@ -1767,7 +1742,6 @@ struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
map = &entry->map;
map->virt_irq = virt_irq;
map->phys_irq = phys_irq;
- map->irq = irq;
list_add_tail_rcu(&entry->entry, root);
@@ -1775,9 +1749,9 @@ out:
spin_unlock(&dist->irq_phys_map_lock);
/* If we've found a hit in the existing list, free the useless
* entry */
- if (IS_ERR(map) || map != &entry->map)
+ if (ret || map != &entry->map)
kfree(entry);
- return map;
+ return ret;
}
static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
@@ -1813,25 +1787,22 @@ static void vgic_free_phys_irq_map_rcu(struct rcu_head *rcu)
/**
* kvm_vgic_unmap_phys_irq - Remove a virtual to physical IRQ mapping
* @vcpu: The VCPU pointer
- * @map: The pointer to a mapping obtained through kvm_vgic_map_phys_irq
+ * @virt_irq: The virtual IRQ number to be unmapped
*
* Remove an existing mapping between virtual and physical interrupts.
*/
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map)
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct irq_phys_map_entry *entry;
struct list_head *root;
- if (!map)
- return -EINVAL;
-
- root = vgic_get_irq_phys_map_list(vcpu, map->virt_irq);
+ root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
spin_lock(&dist->irq_phys_map_lock);
list_for_each_entry(entry, root, entry) {
- if (&entry->map == map) {
+ if (entry->map.virt_irq == virt_irq) {
list_del_rcu(&entry->entry);
call_rcu(&entry->rcu, vgic_free_phys_irq_map_rcu);
break;
@@ -1887,13 +1858,6 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
return -ENOMEM;
}
- /*
- * Store the number of LRs per vcpu, so we don't have to go
- * all the way to the distributor structure to find out. Only
- * assembly code should use this one.
- */
- vgic_cpu->nr_lr = vgic->nr_lr;
-
return 0;
}
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
new file mode 100644
index 000000000000..a1442f7c9c4d
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -0,0 +1,452 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/kvm_host.h>
+#include <kvm/arm_vgic.h>
+#include <asm/kvm_mmu.h>
+#include "vgic.h"
+
+/*
+ * Initialization rules: there are multiple stages to the vgic
+ * initialization, both for the distributor and the CPU interfaces.
+ *
+ * Distributor:
+ *
+ * - kvm_vgic_early_init(): initialization of static data that doesn't
+ * depend on any sizing information or emulation type. No allocation
+ * is allowed there.
+ *
+ * - vgic_init(): allocation and initialization of the generic data
+ * structures that depend on sizing information (number of CPUs,
+ * number of interrupts). Also initializes the vcpu specific data
+ * structures. Can be executed lazily for GICv2.
+ *
+ * CPU Interface:
+ *
+ * - kvm_vgic_cpu_early_init(): initialization of static data that
+ * doesn't depend on any sizing information or emulation type. No
+ * allocation is allowed there.
+ */
+
+/* EARLY INIT */
+
+/*
+ * Those 2 functions should not be needed anymore but they
+ * still are called from arm.c
+ */
+void kvm_vgic_early_init(struct kvm *kvm)
+{
+}
+
+void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu)
+{
+}
+
+/* CREATION */
+
+/**
+ * kvm_vgic_create: triggered by the instantiation of the VGIC device by
+ * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only)
+ * or through the generic KVM_CREATE_DEVICE API ioctl.
+ * irqchip_in_kernel() tells you if this function succeeded or not.
+ * @kvm: kvm struct pointer
+ * @type: KVM_DEV_TYPE_ARM_VGIC_V[23]
+ */
+int kvm_vgic_create(struct kvm *kvm, u32 type)
+{
+ int i, vcpu_lock_idx = -1, ret;
+ struct kvm_vcpu *vcpu;
+
+ mutex_lock(&kvm->lock);
+
+ if (irqchip_in_kernel(kvm)) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ /*
+ * This function is also called by the KVM_CREATE_IRQCHIP handler,
+ * which had no chance yet to check the availability of the GICv2
+ * emulation. So check this here again. KVM_CREATE_DEVICE does
+ * the proper checks already.
+ */
+ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
+ !kvm_vgic_global_state.can_emulate_gicv2) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ /*
+ * Any time a vcpu is run, vcpu_load is called which tries to grab the
+ * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure
+ * that no other VCPUs are run while we create the vgic.
+ */
+ ret = -EBUSY;
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!mutex_trylock(&vcpu->mutex))
+ goto out_unlock;
+ vcpu_lock_idx = i;
+ }
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu->arch.has_run_once)
+ goto out_unlock;
+ }
+ ret = 0;
+
+ if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
+ kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS;
+ else
+ kvm->arch.max_vcpus = VGIC_V3_MAX_CPUS;
+
+ if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus) {
+ ret = -E2BIG;
+ goto out_unlock;
+ }
+
+ kvm->arch.vgic.in_kernel = true;
+ kvm->arch.vgic.vgic_model = type;
+
+ /*
+ * kvm_vgic_global_state.vctrl_base is set on vgic probe (kvm_arch_init)
+ * it is stored in distributor struct for asm save/restore purpose
+ */
+ kvm->arch.vgic.vctrl_base = kvm_vgic_global_state.vctrl_base;
+
+ kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
+ kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+ kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;
+
+out_unlock:
+ for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
+ vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
+ mutex_unlock(&vcpu->mutex);
+ }
+
+out:
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+/* INIT/DESTROY */
+
+/**
+ * kvm_vgic_dist_init: initialize the dist data structures
+ * @kvm: kvm struct pointer
+ * @nr_spis: number of spis, frozen by caller
+ */
+static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
+ int i;
+
+ dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL);
+ if (!dist->spis)
+ return -ENOMEM;
+
+ /*
+ * In the following code we do not take the irq struct lock since
+ * no other action on irq structs can happen while the VGIC is
+ * not initialized yet:
+ * If someone wants to inject an interrupt or does a MMIO access, we
+ * require prior initialization in case of a virtual GICv3 or trigger
+ * initialization when using a virtual GICv2.
+ */
+ for (i = 0; i < nr_spis; i++) {
+ struct vgic_irq *irq = &dist->spis[i];
+
+ irq->intid = i + VGIC_NR_PRIVATE_IRQS;
+ INIT_LIST_HEAD(&irq->ap_list);
+ spin_lock_init(&irq->irq_lock);
+ irq->vcpu = NULL;
+ irq->target_vcpu = vcpu0;
+ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
+ irq->targets = 0;
+ else
+ irq->mpidr = 0;
+ }
+ return 0;
+}
+
+/**
+ * kvm_vgic_vcpu_init: initialize the vcpu data structures and
+ * enable the VCPU interface
+ * @vcpu: the VCPU which's VGIC should be initialized
+ */
+static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ int i;
+
+ INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+ spin_lock_init(&vgic_cpu->ap_list_lock);
+
+ /*
+ * Enable and configure all SGIs to be edge-triggered and
+ * configure all PPIs as level-triggered.
+ */
+ for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
+ struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
+
+ INIT_LIST_HEAD(&irq->ap_list);
+ spin_lock_init(&irq->irq_lock);
+ irq->intid = i;
+ irq->vcpu = NULL;
+ irq->target_vcpu = vcpu;
+ irq->targets = 1U << vcpu->vcpu_id;
+ if (vgic_irq_is_sgi(i)) {
+ /* SGIs */
+ irq->enabled = 1;
+ irq->config = VGIC_CONFIG_EDGE;
+ } else {
+ /* PPIs */
+ irq->config = VGIC_CONFIG_LEVEL;
+ }
+ }
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_enable(vcpu);
+ else
+ vgic_v3_enable(vcpu);
+}
+
+/*
+ * vgic_init: allocates and initializes dist and vcpu data structures
+ * depending on two dimensioning parameters:
+ * - the number of spis
+ * - the number of vcpus
+ * The function is generally called when nr_spis has been explicitly set
+ * by the guest through the KVM DEVICE API. If not nr_spis is set to 256.
+ * vgic_initialized() returns true when this function has succeeded.
+ * Must be called with kvm->lock held!
+ */
+int vgic_init(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int ret = 0, i;
+
+ if (vgic_initialized(kvm))
+ return 0;
+
+ /* freeze the number of spis */
+ if (!dist->nr_spis)
+ dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS;
+
+ ret = kvm_vgic_dist_init(kvm, dist->nr_spis);
+ if (ret)
+ goto out;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vgic_vcpu_init(vcpu);
+
+ dist->initialized = true;
+out:
+ return ret;
+}
+
+static void kvm_vgic_dist_destroy(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+
+ mutex_lock(&kvm->lock);
+
+ dist->ready = false;
+ dist->initialized = false;
+
+ kfree(dist->spis);
+ kfree(dist->redist_iodevs);
+ dist->nr_spis = 0;
+
+ mutex_unlock(&kvm->lock);
+}
+
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+}
+
+void kvm_vgic_destroy(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_vgic_dist_destroy(kvm);
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vgic_vcpu_destroy(vcpu);
+}
+
+/**
+ * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
+ * is a GICv2. A GICv3 must be explicitly initialized by the guest using the
+ * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group.
+ * @kvm: kvm struct pointer
+ */
+int vgic_lazy_init(struct kvm *kvm)
+{
+ int ret = 0;
+
+ if (unlikely(!vgic_initialized(kvm))) {
+ /*
+ * We only provide the automatic initialization of the VGIC
+ * for the legacy case of a GICv2. Any other type must
+ * be explicitly initialized once setup with the respective
+ * KVM device call.
+ */
+ if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
+ return -EBUSY;
+
+ mutex_lock(&kvm->lock);
+ ret = vgic_init(kvm);
+ mutex_unlock(&kvm->lock);
+ }
+
+ return ret;
+}
+
+/* RESOURCE MAPPING */
+
+/**
+ * Map the MMIO regions depending on the VGIC model exposed to the guest
+ * called on the first VCPU run.
+ * Also map the virtual CPU interface into the VM.
+ * v2/v3 derivatives call vgic_init if not already done.
+ * vgic_ready() returns true if this function has succeeded.
+ * @kvm: kvm struct pointer
+ */
+int kvm_vgic_map_resources(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int ret = 0;
+
+ mutex_lock(&kvm->lock);
+ if (!irqchip_in_kernel(kvm))
+ goto out;
+
+ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
+ ret = vgic_v2_map_resources(kvm);
+ else
+ ret = vgic_v3_map_resources(kvm);
+out:
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+/* GENERIC PROBE */
+
+static void vgic_init_maintenance_interrupt(void *info)
+{
+ enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
+}
+
+static int vgic_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *cpu)
+{
+ switch (action) {
+ case CPU_STARTING:
+ case CPU_STARTING_FROZEN:
+ vgic_init_maintenance_interrupt(NULL);
+ break;
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ disable_percpu_irq(kvm_vgic_global_state.maint_irq);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block vgic_cpu_nb = {
+ .notifier_call = vgic_cpu_notify,
+};
+
+static irqreturn_t vgic_maintenance_handler(int irq, void *data)
+{
+ /*
+ * We cannot rely on the vgic maintenance interrupt to be
+ * delivered synchronously. This means we can only use it to
+ * exit the VM, and we perform the handling of EOIed
+ * interrupts on the exit path (see vgic_process_maintenance).
+ */
+ return IRQ_HANDLED;
+}
+
+/**
+ * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
+ * according to the host GIC model. Accordingly calls either
+ * vgic_v2/v3_probe which registers the KVM_DEVICE that can be
+ * instantiated by a guest later on .
+ */
+int kvm_vgic_hyp_init(void)
+{
+ const struct gic_kvm_info *gic_kvm_info;
+ int ret;
+
+ gic_kvm_info = gic_get_kvm_info();
+ if (!gic_kvm_info)
+ return -ENODEV;
+
+ if (!gic_kvm_info->maint_irq) {
+ kvm_err("No vgic maintenance irq\n");
+ return -ENXIO;
+ }
+
+ switch (gic_kvm_info->type) {
+ case GIC_V2:
+ ret = vgic_v2_probe(gic_kvm_info);
+ break;
+ case GIC_V3:
+ ret = vgic_v3_probe(gic_kvm_info);
+ break;
+ default:
+ ret = -ENODEV;
+ };
+
+ if (ret)
+ return ret;
+
+ kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;
+ ret = request_percpu_irq(kvm_vgic_global_state.maint_irq,
+ vgic_maintenance_handler,
+ "vgic", kvm_get_running_vcpus());
+ if (ret) {
+ kvm_err("Cannot register interrupt %d\n",
+ kvm_vgic_global_state.maint_irq);
+ return ret;
+ }
+
+ ret = __register_cpu_notifier(&vgic_cpu_nb);
+ if (ret) {
+ kvm_err("Cannot register vgic CPU notifier\n");
+ goto out_free_irq;
+ }
+
+ on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
+ kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
+ return 0;
+
+out_free_irq:
+ free_percpu_irq(kvm_vgic_global_state.maint_irq,
+ kvm_get_running_vcpus());
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic/vgic-irqfd.c b/virt/kvm/arm/vgic/vgic-irqfd.c
new file mode 100644
index 000000000000..c675513270bb
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-irqfd.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries,
+ int gsi)
+{
+ return 0;
+}
+
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned int irqchip,
+ unsigned int pin)
+{
+ return pin;
+}
+
+int kvm_set_irq(struct kvm *kvm, int irq_source_id,
+ u32 irq, int level, bool line_status)
+{
+ unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS;
+
+ trace_kvm_set_irq(irq, level, irq_source_id);
+
+ BUG_ON(!vgic_initialized(kvm));
+
+ return kvm_vgic_inject_irq(kvm, 0, spi, level);
+}
+
+/* MSI not implemented yet */
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id,
+ int level, bool line_status)
+{
+ return 0;
+}
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
new file mode 100644
index 000000000000..0130c4b147b7
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -0,0 +1,431 @@
+/*
+ * VGIC: KVM DEVICE API
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kvm_host.h>
+#include <kvm/arm_vgic.h>
+#include <linux/uaccess.h>
+#include <asm/kvm_mmu.h>
+#include "vgic.h"
+
+/* common helpers */
+
+static int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
+ phys_addr_t addr, phys_addr_t alignment)
+{
+ if (addr & ~KVM_PHYS_MASK)
+ return -E2BIG;
+
+ if (!IS_ALIGNED(addr, alignment))
+ return -EINVAL;
+
+ if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
+ return -EEXIST;
+
+ return 0;
+}
+
+/**
+ * kvm_vgic_addr - set or get vgic VM base addresses
+ * @kvm: pointer to the vm struct
+ * @type: the VGIC addr type, one of KVM_VGIC_V[23]_ADDR_TYPE_XXX
+ * @addr: pointer to address value
+ * @write: if true set the address in the VM address space, if false read the
+ * address
+ *
+ * Set or get the vgic base addresses for the distributor and the virtual CPU
+ * interface in the VM physical address space. These addresses are properties
+ * of the emulated core/SoC and therefore user space initially knows this
+ * information.
+ * Check them for sanity (alignment, double assignment). We can't check for
+ * overlapping regions in case of a virtual GICv3 here, since we don't know
+ * the number of VCPUs yet, so we defer this check to map_resources().
+ */
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+ int r = 0;
+ struct vgic_dist *vgic = &kvm->arch.vgic;
+ int type_needed;
+ phys_addr_t *addr_ptr, alignment;
+
+ mutex_lock(&kvm->lock);
+ switch (type) {
+ case KVM_VGIC_V2_ADDR_TYPE_DIST:
+ type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+ addr_ptr = &vgic->vgic_dist_base;
+ alignment = SZ_4K;
+ break;
+ case KVM_VGIC_V2_ADDR_TYPE_CPU:
+ type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+ addr_ptr = &vgic->vgic_cpu_base;
+ alignment = SZ_4K;
+ break;
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+ case KVM_VGIC_V3_ADDR_TYPE_DIST:
+ type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+ addr_ptr = &vgic->vgic_dist_base;
+ alignment = SZ_64K;
+ break;
+ case KVM_VGIC_V3_ADDR_TYPE_REDIST:
+ type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+ addr_ptr = &vgic->vgic_redist_base;
+ alignment = SZ_64K;
+ break;
+#endif
+ default:
+ r = -ENODEV;
+ goto out;
+ }
+
+ if (vgic->vgic_model != type_needed) {
+ r = -ENODEV;
+ goto out;
+ }
+
+ if (write) {
+ r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment);
+ if (!r)
+ *addr_ptr = *addr;
+ } else {
+ *addr = *addr_ptr;
+ }
+
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int vgic_set_common_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ int r;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 addr;
+ unsigned long type = (unsigned long)attr->attr;
+
+ if (copy_from_user(&addr, uaddr, sizeof(addr)))
+ return -EFAULT;
+
+ r = kvm_vgic_addr(dev->kvm, type, &addr, true);
+ return (r == -ENODEV) ? -ENXIO : r;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 val;
+ int ret = 0;
+
+ if (get_user(val, uaddr))
+ return -EFAULT;
+
+ /*
+ * We require:
+ * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
+ * - at most 1024 interrupts
+ * - a multiple of 32 interrupts
+ */
+ if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
+ val > VGIC_MAX_RESERVED ||
+ (val & 31))
+ return -EINVAL;
+
+ mutex_lock(&dev->kvm->lock);
+
+ if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
+ ret = -EBUSY;
+ else
+ dev->kvm->arch.vgic.nr_spis =
+ val - VGIC_NR_PRIVATE_IRQS;
+
+ mutex_unlock(&dev->kvm->lock);
+
+ return ret;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+ switch (attr->attr) {
+ case KVM_DEV_ARM_VGIC_CTRL_INIT:
+ mutex_lock(&dev->kvm->lock);
+ r = vgic_init(dev->kvm);
+ mutex_unlock(&dev->kvm->lock);
+ return r;
+ }
+ break;
+ }
+ }
+
+ return -ENXIO;
+}
+
+static int vgic_get_common_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ int r = -ENXIO;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 addr;
+ unsigned long type = (unsigned long)attr->attr;
+
+ r = kvm_vgic_addr(dev->kvm, type, &addr, false);
+ if (r)
+ return (r == -ENODEV) ? -ENXIO : r;
+
+ if (copy_to_user(uaddr, &addr, sizeof(addr)))
+ return -EFAULT;
+ break;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+
+ r = put_user(dev->kvm->arch.vgic.nr_spis +
+ VGIC_NR_PRIVATE_IRQS, uaddr);
+ break;
+ }
+ }
+
+ return r;
+}
+
+static int vgic_create(struct kvm_device *dev, u32 type)
+{
+ return kvm_vgic_create(dev->kvm, type);
+}
+
+static void vgic_destroy(struct kvm_device *dev)
+{
+ kfree(dev);
+}
+
+void kvm_register_vgic_device(unsigned long type)
+{
+ switch (type) {
+ case KVM_DEV_TYPE_ARM_VGIC_V2:
+ kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+ KVM_DEV_TYPE_ARM_VGIC_V2);
+ break;
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+ case KVM_DEV_TYPE_ARM_VGIC_V3:
+ kvm_register_device_ops(&kvm_arm_vgic_v3_ops,
+ KVM_DEV_TYPE_ARM_VGIC_V3);
+ break;
+#endif
+ }
+}
+
+/** vgic_attr_regs_access: allows user space to read/write VGIC registers
+ *
+ * @dev: kvm device handle
+ * @attr: kvm device attribute
+ * @reg: address the value is read or written
+ * @is_write: write flag
+ *
+ */
+static int vgic_attr_regs_access(struct kvm_device *dev,
+ struct kvm_device_attr *attr,
+ u32 *reg, bool is_write)
+{
+ gpa_t addr;
+ int cpuid, ret, c;
+ struct kvm_vcpu *vcpu, *tmp_vcpu;
+ int vcpu_lock_idx = -1;
+
+ cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
+ KVM_DEV_ARM_VGIC_CPUID_SHIFT;
+ vcpu = kvm_get_vcpu(dev->kvm, cpuid);
+ addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+
+ mutex_lock(&dev->kvm->lock);
+
+ ret = vgic_init(dev->kvm);
+ if (ret)
+ goto out;
+
+ if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Any time a vcpu is run, vcpu_load is called which tries to grab the
+ * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure
+ * that no other VCPUs are run and fiddle with the vgic state while we
+ * access it.
+ */
+ ret = -EBUSY;
+ kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) {
+ if (!mutex_trylock(&tmp_vcpu->mutex))
+ goto out;
+ vcpu_lock_idx = c;
+ }
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+ ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, reg);
+ break;
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, reg);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+out:
+ for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
+ tmp_vcpu = kvm_get_vcpu(dev->kvm, vcpu_lock_idx);
+ mutex_unlock(&tmp_vcpu->mutex);
+ }
+
+ mutex_unlock(&dev->kvm->lock);
+ return ret;
+}
+
+/* V2 ops */
+
+static int vgic_v2_set_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ int ret;
+
+ ret = vgic_set_common_attr(dev, attr);
+ if (ret != -ENXIO)
+ return ret;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 reg;
+
+ if (get_user(reg, uaddr))
+ return -EFAULT;
+
+ return vgic_attr_regs_access(dev, attr, &reg, true);
+ }
+ }
+
+ return -ENXIO;
+}
+
+static int vgic_v2_get_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ int ret;
+
+ ret = vgic_get_common_attr(dev, attr);
+ if (ret != -ENXIO)
+ return ret;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 reg = 0;
+
+ ret = vgic_attr_regs_access(dev, attr, &reg, false);
+ if (ret)
+ return ret;
+ return put_user(reg, uaddr);
+ }
+ }
+
+ return -ENXIO;
+}
+
+static int vgic_v2_has_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR:
+ switch (attr->attr) {
+ case KVM_VGIC_V2_ADDR_TYPE_DIST:
+ case KVM_VGIC_V2_ADDR_TYPE_CPU:
+ return 0;
+ }
+ break;
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+ return vgic_v2_has_attr_regs(dev, attr);
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+ return 0;
+ case KVM_DEV_ARM_VGIC_GRP_CTRL:
+ switch (attr->attr) {
+ case KVM_DEV_ARM_VGIC_CTRL_INIT:
+ return 0;
+ }
+ }
+ return -ENXIO;
+}
+
+struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+ .name = "kvm-arm-vgic-v2",
+ .create = vgic_create,
+ .destroy = vgic_destroy,
+ .set_attr = vgic_v2_set_attr,
+ .get_attr = vgic_v2_get_attr,
+ .has_attr = vgic_v2_has_attr,
+};
+
+/* V3 ops */
+
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+
+static int vgic_v3_set_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ return vgic_set_common_attr(dev, attr);
+}
+
+static int vgic_v3_get_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ return vgic_get_common_attr(dev, attr);
+}
+
+static int vgic_v3_has_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR:
+ switch (attr->attr) {
+ case KVM_VGIC_V3_ADDR_TYPE_DIST:
+ case KVM_VGIC_V3_ADDR_TYPE_REDIST:
+ return 0;
+ }
+ break;
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+ return 0;
+ case KVM_DEV_ARM_VGIC_GRP_CTRL:
+ switch (attr->attr) {
+ case KVM_DEV_ARM_VGIC_CTRL_INIT:
+ return 0;
+ }
+ }
+ return -ENXIO;
+}
+
+struct kvm_device_ops kvm_arm_vgic_v3_ops = {
+ .name = "kvm-arm-vgic-v3",
+ .create = vgic_create,
+ .destroy = vgic_destroy,
+ .set_attr = vgic_v3_set_attr,
+ .get_attr = vgic_v3_get_attr,
+ .has_attr = vgic_v3_has_attr,
+};
+
+#endif /* CONFIG_KVM_ARM_VGIC_V3 */
+
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
new file mode 100644
index 000000000000..a21393637e4b
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -0,0 +1,446 @@
+/*
+ * VGICv2 MMIO handling functions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <kvm/iodev.h>
+#include <kvm/arm_vgic.h>
+
+#include "vgic.h"
+#include "vgic-mmio.h"
+
+static unsigned long vgic_mmio_read_v2_misc(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 value;
+
+ switch (addr & 0x0c) {
+ case GIC_DIST_CTRL:
+ value = vcpu->kvm->arch.vgic.enabled ? GICD_ENABLE : 0;
+ break;
+ case GIC_DIST_CTR:
+ value = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
+ value = (value >> 5) - 1;
+ value |= (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
+ break;
+ case GIC_DIST_IIDR:
+ value = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+ break;
+ default:
+ return 0;
+ }
+
+ return value;
+}
+
+static void vgic_mmio_write_v2_misc(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ bool was_enabled = dist->enabled;
+
+ switch (addr & 0x0c) {
+ case GIC_DIST_CTRL:
+ dist->enabled = val & GICD_ENABLE;
+ if (!was_enabled && dist->enabled)
+ vgic_kick_vcpus(vcpu->kvm);
+ break;
+ case GIC_DIST_CTR:
+ case GIC_DIST_IIDR:
+ /* Nothing to do */
+ return;
+ }
+}
+
+static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ int nr_vcpus = atomic_read(&source_vcpu->kvm->online_vcpus);
+ int intid = val & 0xf;
+ int targets = (val >> 16) & 0xff;
+ int mode = (val >> 24) & 0x03;
+ int c;
+ struct kvm_vcpu *vcpu;
+
+ switch (mode) {
+ case 0x0: /* as specified by targets */
+ break;
+ case 0x1:
+ targets = (1U << nr_vcpus) - 1; /* all, ... */
+ targets &= ~(1U << source_vcpu->vcpu_id); /* but self */
+ break;
+ case 0x2: /* this very vCPU only */
+ targets = (1U << source_vcpu->vcpu_id);
+ break;
+ case 0x3: /* reserved */
+ return;
+ }
+
+ kvm_for_each_vcpu(c, vcpu, source_vcpu->kvm) {
+ struct vgic_irq *irq;
+
+ if (!(targets & (1U << c)))
+ continue;
+
+ irq = vgic_get_irq(source_vcpu->kvm, vcpu, intid);
+
+ spin_lock(&irq->irq_lock);
+ irq->pending = true;
+ irq->source |= 1U << source_vcpu->vcpu_id;
+
+ vgic_queue_irq_unlock(source_vcpu->kvm, irq);
+ }
+}
+
+static unsigned long vgic_mmio_read_target(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
+ int i;
+ u64 val = 0;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ val |= (u64)irq->targets << (i * 8);
+ }
+
+ return val;
+}
+
+static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
+ int i;
+
+ /* GICD_ITARGETSR[0-7] are read-only */
+ if (intid < VGIC_NR_PRIVATE_IRQS)
+ return;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid + i);
+ int target;
+
+ spin_lock(&irq->irq_lock);
+
+ irq->targets = (val >> (i * 8)) & 0xff;
+ target = irq->targets ? __ffs(irq->targets) : 0;
+ irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target);
+
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+static unsigned long vgic_mmio_read_sgipend(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = addr & 0x0f;
+ int i;
+ u64 val = 0;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ val |= (u64)irq->source << (i * 8);
+ }
+ return val;
+}
+
+static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = addr & 0x0f;
+ int i;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+
+ irq->source &= ~((val >> (i * 8)) & 0xff);
+ if (!irq->source)
+ irq->pending = false;
+
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = addr & 0x0f;
+ int i;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+
+ irq->source |= (val >> (i * 8)) & 0xff;
+
+ if (irq->source) {
+ irq->pending = true;
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+ } else {
+ spin_unlock(&irq->irq_lock);
+ }
+ }
+}
+
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_set_vmcr(vcpu, vmcr);
+ else
+ vgic_v3_set_vmcr(vcpu, vmcr);
+}
+
+static void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_get_vmcr(vcpu, vmcr);
+ else
+ vgic_v3_get_vmcr(vcpu, vmcr);
+}
+
+#define GICC_ARCH_VERSION_V2 0x2
+
+/* These are for userland accesses only, there is no guest-facing emulation. */
+static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ struct vgic_vmcr vmcr;
+ u32 val;
+
+ vgic_get_vmcr(vcpu, &vmcr);
+
+ switch (addr & 0xff) {
+ case GIC_CPU_CTRL:
+ val = vmcr.ctlr;
+ break;
+ case GIC_CPU_PRIMASK:
+ val = vmcr.pmr;
+ break;
+ case GIC_CPU_BINPOINT:
+ val = vmcr.bpr;
+ break;
+ case GIC_CPU_ALIAS_BINPOINT:
+ val = vmcr.abpr;
+ break;
+ case GIC_CPU_IDENT:
+ val = ((PRODUCT_ID_KVM << 20) |
+ (GICC_ARCH_VERSION_V2 << 16) |
+ IMPLEMENTER_ARM);
+ break;
+ default:
+ return 0;
+ }
+
+ return val;
+}
+
+static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ struct vgic_vmcr vmcr;
+
+ vgic_get_vmcr(vcpu, &vmcr);
+
+ switch (addr & 0xff) {
+ case GIC_CPU_CTRL:
+ vmcr.ctlr = val;
+ break;
+ case GIC_CPU_PRIMASK:
+ vmcr.pmr = val;
+ break;
+ case GIC_CPU_BINPOINT:
+ vmcr.bpr = val;
+ break;
+ case GIC_CPU_ALIAS_BINPOINT:
+ vmcr.abpr = val;
+ break;
+ }
+
+ vgic_set_vmcr(vcpu, &vmcr);
+}
+
+static const struct vgic_register_region vgic_v2_dist_registers[] = {
+ REGISTER_DESC_WITH_LENGTH(GIC_DIST_CTRL,
+ vgic_mmio_read_v2_misc, vgic_mmio_write_v2_misc, 12,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_IGROUP,
+ vgic_mmio_read_rao, vgic_mmio_write_wi, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET,
+ vgic_mmio_read_enable, vgic_mmio_write_senable, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR,
+ vgic_mmio_read_enable, vgic_mmio_write_cenable, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
+ vgic_mmio_read_pending, vgic_mmio_write_spending, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
+ vgic_mmio_read_pending, vgic_mmio_write_cpending, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
+ vgic_mmio_read_active, vgic_mmio_write_sactive, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR,
+ vgic_mmio_read_active, vgic_mmio_write_cactive, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI,
+ vgic_mmio_read_priority, vgic_mmio_write_priority, 8,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_TARGET,
+ vgic_mmio_read_target, vgic_mmio_write_target, 8,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_CONFIG,
+ vgic_mmio_read_config, vgic_mmio_write_config, 2,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_DIST_SOFTINT,
+ vgic_mmio_read_raz, vgic_mmio_write_sgir, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_DIST_SGI_PENDING_CLEAR,
+ vgic_mmio_read_sgipend, vgic_mmio_write_sgipendc, 16,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_DIST_SGI_PENDING_SET,
+ vgic_mmio_read_sgipend, vgic_mmio_write_sgipends, 16,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+};
+
+static const struct vgic_register_region vgic_v2_cpu_registers[] = {
+ REGISTER_DESC_WITH_LENGTH(GIC_CPU_CTRL,
+ vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_CPU_PRIMASK,
+ vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_CPU_BINPOINT,
+ vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_CPU_ALIAS_BINPOINT,
+ vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_CPU_ACTIVEPRIO,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 16,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GIC_CPU_IDENT,
+ vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4,
+ VGIC_ACCESS_32bit),
+};
+
+unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev)
+{
+ dev->regions = vgic_v2_dist_registers;
+ dev->nr_regions = ARRAY_SIZE(vgic_v2_dist_registers);
+
+ kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops);
+
+ return SZ_4K;
+}
+
+int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ int nr_irqs = dev->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
+ const struct vgic_register_region *regions;
+ gpa_t addr;
+ int nr_regions, i, len;
+
+ addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ regions = vgic_v2_dist_registers;
+ nr_regions = ARRAY_SIZE(vgic_v2_dist_registers);
+ break;
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+ regions = vgic_v2_cpu_registers;
+ nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers);
+ break;
+ default:
+ return -ENXIO;
+ }
+
+ /* We only support aligned 32-bit accesses. */
+ if (addr & 3)
+ return -ENXIO;
+
+ for (i = 0; i < nr_regions; i++) {
+ if (regions[i].bits_per_irq)
+ len = (regions[i].bits_per_irq * nr_irqs) / 8;
+ else
+ len = regions[i].len;
+
+ if (regions[i].reg_offset <= addr &&
+ regions[i].reg_offset + len > addr)
+ return 0;
+ }
+
+ return -ENXIO;
+}
+
+/*
+ * When userland tries to access the VGIC register handlers, we need to
+ * create a usable struct vgic_io_device to be passed to the handlers and we
+ * have to set up a buffer similar to what would have happened if a guest MMIO
+ * access occurred, including doing endian conversions on BE systems.
+ */
+static int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev,
+ bool is_write, int offset, u32 *val)
+{
+ unsigned int len = 4;
+ u8 buf[4];
+ int ret;
+
+ if (is_write) {
+ vgic_data_host_to_mmio_bus(buf, len, *val);
+ ret = kvm_io_gic_ops.write(vcpu, &dev->dev, offset, len, buf);
+ } else {
+ ret = kvm_io_gic_ops.read(vcpu, &dev->dev, offset, len, buf);
+ if (!ret)
+ *val = vgic_data_mmio_bus_to_host(buf, len);
+ }
+
+ return ret;
+}
+
+int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+ int offset, u32 *val)
+{
+ struct vgic_io_device dev = {
+ .regions = vgic_v2_cpu_registers,
+ .nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers),
+ };
+
+ return vgic_uaccess(vcpu, &dev, is_write, offset, val);
+}
+
+int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+ int offset, u32 *val)
+{
+ struct vgic_io_device dev = {
+ .regions = vgic_v2_dist_registers,
+ .nr_regions = ARRAY_SIZE(vgic_v2_dist_registers),
+ };
+
+ return vgic_uaccess(vcpu, &dev, is_write, offset, val);
+}
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
new file mode 100644
index 000000000000..a0c515a412a7
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -0,0 +1,455 @@
+/*
+ * VGICv3 MMIO handling functions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/irqchip/arm-gic-v3.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <kvm/iodev.h>
+#include <kvm/arm_vgic.h>
+
+#include <asm/kvm_emulate.h>
+
+#include "vgic.h"
+#include "vgic-mmio.h"
+
+/* extract @num bytes at @offset bytes offset in data */
+static unsigned long extract_bytes(unsigned long data, unsigned int offset,
+ unsigned int num)
+{
+ return (data >> (offset * 8)) & GENMASK_ULL(num * 8 - 1, 0);
+}
+
+static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 value = 0;
+
+ switch (addr & 0x0c) {
+ case GICD_CTLR:
+ if (vcpu->kvm->arch.vgic.enabled)
+ value |= GICD_CTLR_ENABLE_SS_G1;
+ value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS;
+ break;
+ case GICD_TYPER:
+ value = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
+ value = (value >> 5) - 1;
+ value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19;
+ break;
+ case GICD_IIDR:
+ value = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+ break;
+ default:
+ return 0;
+ }
+
+ return value;
+}
+
+static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ bool was_enabled = dist->enabled;
+
+ switch (addr & 0x0c) {
+ case GICD_CTLR:
+ dist->enabled = val & GICD_CTLR_ENABLE_SS_G1;
+
+ if (!was_enabled && dist->enabled)
+ vgic_kick_vcpus(vcpu->kvm);
+ break;
+ case GICD_TYPER:
+ case GICD_IIDR:
+ return;
+ }
+}
+
+static unsigned long vgic_mmio_read_irouter(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ int intid = VGIC_ADDR_TO_INTID(addr, 64);
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid);
+
+ if (!irq)
+ return 0;
+
+ /* The upper word is RAZ for us. */
+ if (addr & 4)
+ return 0;
+
+ return extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len);
+}
+
+static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ int intid = VGIC_ADDR_TO_INTID(addr, 64);
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid);
+
+ if (!irq)
+ return;
+
+ /* The upper word is WI for us since we don't implement Aff3. */
+ if (addr & 4)
+ return;
+
+ spin_lock(&irq->irq_lock);
+
+ /* We only care about and preserve Aff0, Aff1 and Aff2. */
+ irq->mpidr = val & GENMASK(23, 0);
+ irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr);
+
+ spin_unlock(&irq->irq_lock);
+}
+
+static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+ int target_vcpu_id = vcpu->vcpu_id;
+ u64 value;
+
+ value = (mpidr & GENMASK(23, 0)) << 32;
+ value |= ((target_vcpu_id & 0xffff) << 8);
+ if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
+ value |= GICR_TYPER_LAST;
+
+ return extract_bytes(value, addr & 7, len);
+}
+
+static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+}
+
+static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ switch (addr & 0xffff) {
+ case GICD_PIDR2:
+ /* report a GICv3 compliant implementation */
+ return 0x3b;
+ }
+
+ return 0;
+}
+
+/*
+ * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the
+ * redistributors, while SPIs are covered by registers in the distributor
+ * block. Trying to set private IRQs in this block gets ignored.
+ * We take some special care here to fix the calculation of the register
+ * offset.
+ */
+#define REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(off, rd, wr, bpi, acc) \
+ { \
+ .reg_offset = off, \
+ .bits_per_irq = bpi, \
+ .len = (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \
+ .access_flags = acc, \
+ .read = vgic_mmio_read_raz, \
+ .write = vgic_mmio_write_wi, \
+ }, { \
+ .reg_offset = off + (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \
+ .bits_per_irq = bpi, \
+ .len = (bpi * (1024 - VGIC_NR_PRIVATE_IRQS)) / 8, \
+ .access_flags = acc, \
+ .read = rd, \
+ .write = wr, \
+ }
+
+static const struct vgic_register_region vgic_v3_dist_registers[] = {
+ REGISTER_DESC_WITH_LENGTH(GICD_CTLR,
+ vgic_mmio_read_v3_misc, vgic_mmio_write_v3_misc, 16,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGROUPR,
+ vgic_mmio_read_rao, vgic_mmio_write_wi, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER,
+ vgic_mmio_read_enable, vgic_mmio_write_senable, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER,
+ vgic_mmio_read_enable, vgic_mmio_write_cenable, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR,
+ vgic_mmio_read_pending, vgic_mmio_write_spending, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR,
+ vgic_mmio_read_pending, vgic_mmio_write_cpending, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER,
+ vgic_mmio_read_active, vgic_mmio_write_sactive, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER,
+ vgic_mmio_read_active, vgic_mmio_write_cactive, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR,
+ vgic_mmio_read_priority, vgic_mmio_write_priority, 8,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ITARGETSR,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 8,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICFGR,
+ vgic_mmio_read_config, vgic_mmio_write_config, 2,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGRPMODR,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 1,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IROUTER,
+ vgic_mmio_read_irouter, vgic_mmio_write_irouter, 64,
+ VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICD_IDREGS,
+ vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
+ VGIC_ACCESS_32bit),
+};
+
+static const struct vgic_register_region vgic_v3_rdbase_registers[] = {
+ REGISTER_DESC_WITH_LENGTH(GICR_CTLR,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_IIDR,
+ vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_TYPER,
+ vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8,
+ VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 8,
+ VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 8,
+ VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_IDREGS,
+ vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
+ VGIC_ACCESS_32bit),
+};
+
+static const struct vgic_register_region vgic_v3_sgibase_registers[] = {
+ REGISTER_DESC_WITH_LENGTH(GICR_IGROUPR0,
+ vgic_mmio_read_rao, vgic_mmio_write_wi, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ISENABLER0,
+ vgic_mmio_read_enable, vgic_mmio_write_senable, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ICENABLER0,
+ vgic_mmio_read_enable, vgic_mmio_write_cenable, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ISPENDR0,
+ vgic_mmio_read_pending, vgic_mmio_write_spending, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ICPENDR0,
+ vgic_mmio_read_pending, vgic_mmio_write_cpending, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ISACTIVER0,
+ vgic_mmio_read_active, vgic_mmio_write_sactive, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ICACTIVER0,
+ vgic_mmio_read_active, vgic_mmio_write_cactive, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_IPRIORITYR0,
+ vgic_mmio_read_priority, vgic_mmio_write_priority, 32,
+ VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_ICFGR0,
+ vgic_mmio_read_config, vgic_mmio_write_config, 8,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_IGRPMODR0,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
+ VGIC_ACCESS_32bit),
+ REGISTER_DESC_WITH_LENGTH(GICR_NSACR,
+ vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
+ VGIC_ACCESS_32bit),
+};
+
+unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev)
+{
+ dev->regions = vgic_v3_dist_registers;
+ dev->nr_regions = ARRAY_SIZE(vgic_v3_dist_registers);
+
+ kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops);
+
+ return SZ_64K;
+}
+
+int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
+{
+ int nr_vcpus = atomic_read(&kvm->online_vcpus);
+ struct kvm_vcpu *vcpu;
+ struct vgic_io_device *devices;
+ int c, ret = 0;
+
+ devices = kmalloc(sizeof(struct vgic_io_device) * nr_vcpus * 2,
+ GFP_KERNEL);
+ if (!devices)
+ return -ENOMEM;
+
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ gpa_t rd_base = redist_base_address + c * SZ_64K * 2;
+ gpa_t sgi_base = rd_base + SZ_64K;
+ struct vgic_io_device *rd_dev = &devices[c * 2];
+ struct vgic_io_device *sgi_dev = &devices[c * 2 + 1];
+
+ kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
+ rd_dev->base_addr = rd_base;
+ rd_dev->regions = vgic_v3_rdbase_registers;
+ rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
+ rd_dev->redist_vcpu = vcpu;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
+ SZ_64K, &rd_dev->dev);
+ mutex_unlock(&kvm->slots_lock);
+
+ if (ret)
+ break;
+
+ kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
+ sgi_dev->base_addr = sgi_base;
+ sgi_dev->regions = vgic_v3_sgibase_registers;
+ sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
+ sgi_dev->redist_vcpu = vcpu;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
+ SZ_64K, &sgi_dev->dev);
+ mutex_unlock(&kvm->slots_lock);
+ if (ret) {
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+ &rd_dev->dev);
+ break;
+ }
+ }
+
+ if (ret) {
+ /* The current c failed, so we start with the previous one. */
+ for (c--; c >= 0; c--) {
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+ &devices[c * 2].dev);
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+ &devices[c * 2 + 1].dev);
+ }
+ kfree(devices);
+ } else {
+ kvm->arch.vgic.redist_iodevs = devices;
+ }
+
+ return ret;
+}
+
+/*
+ * Compare a given affinity (level 1-3 and a level 0 mask, from the SGI
+ * generation register ICC_SGI1R_EL1) with a given VCPU.
+ * If the VCPU's MPIDR matches, return the level0 affinity, otherwise
+ * return -1.
+ */
+static int match_mpidr(u64 sgi_aff, u16 sgi_cpu_mask, struct kvm_vcpu *vcpu)
+{
+ unsigned long affinity;
+ int level0;
+
+ /*
+ * Split the current VCPU's MPIDR into affinity level 0 and the
+ * rest as this is what we have to compare against.
+ */
+ affinity = kvm_vcpu_get_mpidr_aff(vcpu);
+ level0 = MPIDR_AFFINITY_LEVEL(affinity, 0);
+ affinity &= ~MPIDR_LEVEL_MASK;
+
+ /* bail out if the upper three levels don't match */
+ if (sgi_aff != affinity)
+ return -1;
+
+ /* Is this VCPU's bit set in the mask ? */
+ if (!(sgi_cpu_mask & BIT(level0)))
+ return -1;
+
+ return level0;
+}
+
+/*
+ * The ICC_SGI* registers encode the affinity differently from the MPIDR,
+ * so provide a wrapper to use the existing defines to isolate a certain
+ * affinity level.
+ */
+#define SGI_AFFINITY_LEVEL(reg, level) \
+ ((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \
+ >> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level))
+
+/**
+ * vgic_v3_dispatch_sgi - handle SGI requests from VCPUs
+ * @vcpu: The VCPU requesting a SGI
+ * @reg: The value written into the ICC_SGI1R_EL1 register by that VCPU
+ *
+ * With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register.
+ * This will trap in sys_regs.c and call this function.
+ * This ICC_SGI1R_EL1 register contains the upper three affinity levels of the
+ * target processors as well as a bitmask of 16 Aff0 CPUs.
+ * If the interrupt routing mode bit is not set, we iterate over all VCPUs to
+ * check for matching ones. If this bit is set, we signal all, but not the
+ * calling VCPU.
+ */
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_vcpu *c_vcpu;
+ u16 target_cpus;
+ u64 mpidr;
+ int sgi, c;
+ int vcpu_id = vcpu->vcpu_id;
+ bool broadcast;
+
+ sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT;
+ broadcast = reg & BIT(ICC_SGI1R_IRQ_ROUTING_MODE_BIT);
+ target_cpus = (reg & ICC_SGI1R_TARGET_LIST_MASK) >> ICC_SGI1R_TARGET_LIST_SHIFT;
+ mpidr = SGI_AFFINITY_LEVEL(reg, 3);
+ mpidr |= SGI_AFFINITY_LEVEL(reg, 2);
+ mpidr |= SGI_AFFINITY_LEVEL(reg, 1);
+
+ /*
+ * We iterate over all VCPUs to find the MPIDRs matching the request.
+ * If we have handled one CPU, we clear its bit to detect early
+ * if we are already finished. This avoids iterating through all
+ * VCPUs when most of the times we just signal a single VCPU.
+ */
+ kvm_for_each_vcpu(c, c_vcpu, kvm) {
+ struct vgic_irq *irq;
+
+ /* Exit early if we have dealt with all requested CPUs */
+ if (!broadcast && target_cpus == 0)
+ break;
+
+ /* Don't signal the calling VCPU */
+ if (broadcast && c == vcpu_id)
+ continue;
+
+ if (!broadcast) {
+ int level0;
+
+ level0 = match_mpidr(mpidr, target_cpus, c_vcpu);
+ if (level0 == -1)
+ continue;
+
+ /* remove this matching VCPU from the mask */
+ target_cpus &= ~BIT(level0);
+ }
+
+ irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi);
+
+ spin_lock(&irq->irq_lock);
+ irq->pending = true;
+
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+ }
+}
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
new file mode 100644
index 000000000000..9f6fab74dce7
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -0,0 +1,524 @@
+/*
+ * VGIC MMIO handling functions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/bsearch.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <kvm/iodev.h>
+#include <kvm/arm_vgic.h>
+
+#include "vgic.h"
+#include "vgic-mmio.h"
+
+unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ return 0;
+}
+
+unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ return -1UL;
+}
+
+void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr,
+ unsigned int len, unsigned long val)
+{
+ /* Ignore */
+}
+
+/*
+ * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value
+ * of the enabled bit, so there is only one function for both here.
+ */
+unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ u32 value = 0;
+ int i;
+
+ /* Loop over all IRQs affected by this read */
+ for (i = 0; i < len * 8; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ if (irq->enabled)
+ value |= (1U << i);
+ }
+
+ return value;
+}
+
+void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ int i;
+
+ for_each_set_bit(i, &val, len * 8) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+ irq->enabled = true;
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+ }
+}
+
+void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ int i;
+
+ for_each_set_bit(i, &val, len * 8) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+
+ irq->enabled = false;
+
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ u32 value = 0;
+ int i;
+
+ /* Loop over all IRQs affected by this read */
+ for (i = 0; i < len * 8; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ if (irq->pending)
+ value |= (1U << i);
+ }
+
+ return value;
+}
+
+void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ int i;
+
+ for_each_set_bit(i, &val, len * 8) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+ irq->pending = true;
+ if (irq->config == VGIC_CONFIG_LEVEL)
+ irq->soft_pending = true;
+
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+ }
+}
+
+void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ int i;
+
+ for_each_set_bit(i, &val, len * 8) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+
+ if (irq->config == VGIC_CONFIG_LEVEL) {
+ irq->soft_pending = false;
+ irq->pending = irq->line_level;
+ } else {
+ irq->pending = false;
+ }
+
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ u32 value = 0;
+ int i;
+
+ /* Loop over all IRQs affected by this read */
+ for (i = 0; i < len * 8; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ if (irq->active)
+ value |= (1U << i);
+ }
+
+ return value;
+}
+
+static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+ bool new_active_state)
+{
+ spin_lock(&irq->irq_lock);
+ /*
+ * If this virtual IRQ was written into a list register, we
+ * have to make sure the CPU that runs the VCPU thread has
+ * synced back LR state to the struct vgic_irq. We can only
+ * know this for sure, when either this irq is not assigned to
+ * anyone's AP list anymore, or the VCPU thread is not
+ * running on any CPUs.
+ *
+ * In the opposite case, we know the VCPU thread may be on its
+ * way back from the guest and still has to sync back this
+ * IRQ, so we release and re-acquire the spin_lock to let the
+ * other thread sync back the IRQ.
+ */
+ while (irq->vcpu && /* IRQ may have state in an LR somewhere */
+ irq->vcpu->cpu != -1) /* VCPU thread is running */
+ cond_resched_lock(&irq->irq_lock);
+
+ irq->active = new_active_state;
+ if (new_active_state)
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+ else
+ spin_unlock(&irq->irq_lock);
+}
+
+/*
+ * If we are fiddling with an IRQ's active state, we have to make sure the IRQ
+ * is not queued on some running VCPU's LRs, because then the change to the
+ * active state can be overwritten when the VCPU's state is synced coming back
+ * from the guest.
+ *
+ * For shared interrupts, we have to stop all the VCPUs because interrupts can
+ * be migrated while we don't hold the IRQ locks and we don't want to be
+ * chasing moving targets.
+ *
+ * For private interrupts, we only have to make sure the single and only VCPU
+ * that can potentially queue the IRQ is stopped.
+ */
+static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
+{
+ if (intid < VGIC_NR_PRIVATE_IRQS)
+ kvm_arm_halt_vcpu(vcpu);
+ else
+ kvm_arm_halt_guest(vcpu->kvm);
+}
+
+/* See vgic_change_active_prepare */
+static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid)
+{
+ if (intid < VGIC_NR_PRIVATE_IRQS)
+ kvm_arm_resume_vcpu(vcpu);
+ else
+ kvm_arm_resume_guest(vcpu->kvm);
+}
+
+void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ int i;
+
+ vgic_change_active_prepare(vcpu, intid);
+ for_each_set_bit(i, &val, len * 8) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+ vgic_mmio_change_active(vcpu, irq, false);
+ }
+ vgic_change_active_finish(vcpu, intid);
+}
+
+void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+ int i;
+
+ vgic_change_active_prepare(vcpu, intid);
+ for_each_set_bit(i, &val, len * 8) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+ vgic_mmio_change_active(vcpu, irq, true);
+ }
+ vgic_change_active_finish(vcpu, intid);
+}
+
+unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
+ int i;
+ u64 val = 0;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ val |= (u64)irq->priority << (i * 8);
+ }
+
+ return val;
+}
+
+/*
+ * We currently don't handle changing the priority of an interrupt that
+ * is already pending on a VCPU. If there is a need for this, we would
+ * need to make this VCPU exit and re-evaluate the priorities, potentially
+ * leading to this interrupt getting presented now to the guest (if it has
+ * been masked by the priority mask before).
+ */
+void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
+ int i;
+
+ for (i = 0; i < len; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ spin_lock(&irq->irq_lock);
+ /* Narrow the priority range to what we actually support */
+ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS);
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 2);
+ u32 value = 0;
+ int i;
+
+ for (i = 0; i < len * 4; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ if (irq->config == VGIC_CONFIG_EDGE)
+ value |= (2U << (i * 2));
+ }
+
+ return value;
+}
+
+void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 intid = VGIC_ADDR_TO_INTID(addr, 2);
+ int i;
+
+ for (i = 0; i < len * 4; i++) {
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+ /*
+ * The configuration cannot be changed for SGIs in general,
+ * for PPIs this is IMPLEMENTATION DEFINED. The arch timer
+ * code relies on PPIs being level triggered, so we also
+ * make them read-only here.
+ */
+ if (intid + i < VGIC_NR_PRIVATE_IRQS)
+ continue;
+
+ spin_lock(&irq->irq_lock);
+ if (test_bit(i * 2 + 1, &val)) {
+ irq->config = VGIC_CONFIG_EDGE;
+ } else {
+ irq->config = VGIC_CONFIG_LEVEL;
+ irq->pending = irq->line_level | irq->soft_pending;
+ }
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+static int match_region(const void *key, const void *elt)
+{
+ const unsigned int offset = (unsigned long)key;
+ const struct vgic_register_region *region = elt;
+
+ if (offset < region->reg_offset)
+ return -1;
+
+ if (offset >= region->reg_offset + region->len)
+ return 1;
+
+ return 0;
+}
+
+/* Find the proper register handler entry given a certain address offset. */
+static const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *region, int nr_regions,
+ unsigned int offset)
+{
+ return bsearch((void *)(uintptr_t)offset, region, nr_regions,
+ sizeof(region[0]), match_region);
+}
+
+/*
+ * kvm_mmio_read_buf() returns a value in a format where it can be converted
+ * to a byte array and be directly observed as the guest wanted it to appear
+ * in memory if it had done the store itself, which is LE for the GIC, as the
+ * guest knows the GIC is always LE.
+ *
+ * We convert this value to the CPUs native format to deal with it as a data
+ * value.
+ */
+unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len)
+{
+ unsigned long data = kvm_mmio_read_buf(val, len);
+
+ switch (len) {
+ case 1:
+ return data;
+ case 2:
+ return le16_to_cpu(data);
+ case 4:
+ return le32_to_cpu(data);
+ default:
+ return le64_to_cpu(data);
+ }
+}
+
+/*
+ * kvm_mmio_write_buf() expects a value in a format such that if converted to
+ * a byte array it is observed as the guest would see it if it could perform
+ * the load directly. Since the GIC is LE, and the guest knows this, the
+ * guest expects a value in little endian format.
+ *
+ * We convert the data value from the CPUs native format to LE so that the
+ * value is returned in the proper format.
+ */
+void vgic_data_host_to_mmio_bus(void *buf, unsigned int len,
+ unsigned long data)
+{
+ switch (len) {
+ case 1:
+ break;
+ case 2:
+ data = cpu_to_le16(data);
+ break;
+ case 4:
+ data = cpu_to_le32(data);
+ break;
+ default:
+ data = cpu_to_le64(data);
+ }
+
+ kvm_mmio_write_buf(buf, len, data);
+}
+
+static
+struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev)
+{
+ return container_of(dev, struct vgic_io_device, dev);
+}
+
+static bool check_region(const struct vgic_register_region *region,
+ gpa_t addr, int len)
+{
+ if ((region->access_flags & VGIC_ACCESS_8bit) && len == 1)
+ return true;
+ if ((region->access_flags & VGIC_ACCESS_32bit) &&
+ len == sizeof(u32) && !(addr & 3))
+ return true;
+ if ((region->access_flags & VGIC_ACCESS_64bit) &&
+ len == sizeof(u64) && !(addr & 7))
+ return true;
+
+ return false;
+}
+
+static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+ gpa_t addr, int len, void *val)
+{
+ struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
+ const struct vgic_register_region *region;
+ struct kvm_vcpu *r_vcpu;
+ unsigned long data;
+
+ region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
+ addr - iodev->base_addr);
+ if (!region || !check_region(region, addr, len)) {
+ memset(val, 0, len);
+ return 0;
+ }
+
+ r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
+ data = region->read(r_vcpu, addr, len);
+ vgic_data_host_to_mmio_bus(val, len, data);
+ return 0;
+}
+
+static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+ gpa_t addr, int len, const void *val)
+{
+ struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
+ const struct vgic_register_region *region;
+ struct kvm_vcpu *r_vcpu;
+ unsigned long data = vgic_data_mmio_bus_to_host(val, len);
+
+ region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
+ addr - iodev->base_addr);
+ if (!region)
+ return 0;
+
+ if (!check_region(region, addr, len))
+ return 0;
+
+ r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
+ region->write(r_vcpu, addr, len, data);
+ return 0;
+}
+
+struct kvm_io_device_ops kvm_io_gic_ops = {
+ .read = dispatch_mmio_read,
+ .write = dispatch_mmio_write,
+};
+
+int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
+ enum vgic_type type)
+{
+ struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev;
+ int ret = 0;
+ unsigned int len;
+
+ switch (type) {
+ case VGIC_V2:
+ len = vgic_v2_init_dist_iodev(io_device);
+ break;
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+ case VGIC_V3:
+ len = vgic_v3_init_dist_iodev(io_device);
+ break;
+#endif
+ default:
+ BUG_ON(1);
+ }
+
+ io_device->base_addr = dist_base_address;
+ io_device->redist_vcpu = NULL;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address,
+ len, &io_device->dev);
+ mutex_unlock(&kvm->slots_lock);
+
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
new file mode 100644
index 000000000000..850901482aec
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -0,0 +1,150 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __KVM_ARM_VGIC_MMIO_H__
+#define __KVM_ARM_VGIC_MMIO_H__
+
+struct vgic_register_region {
+ unsigned int reg_offset;
+ unsigned int len;
+ unsigned int bits_per_irq;
+ unsigned int access_flags;
+ unsigned long (*read)(struct kvm_vcpu *vcpu, gpa_t addr,
+ unsigned int len);
+ void (*write)(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len,
+ unsigned long val);
+};
+
+extern struct kvm_io_device_ops kvm_io_gic_ops;
+
+#define VGIC_ACCESS_8bit 1
+#define VGIC_ACCESS_32bit 2
+#define VGIC_ACCESS_64bit 4
+
+/*
+ * Generate a mask that covers the number of bytes required to address
+ * up to 1024 interrupts, each represented by <bits> bits. This assumes
+ * that <bits> is a power of two.
+ */
+#define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1)
+
+/*
+ * (addr & mask) gives us the byte offset for the INT ID, so we want to
+ * divide this with 'bytes per irq' to get the INT ID, which is given
+ * by '(bits) / 8'. But we do this with fixed-point-arithmetic and
+ * take advantage of the fact that division by a fraction equals
+ * multiplication with the inverted fraction, and scale up both the
+ * numerator and denominator with 8 to support at most 64 bits per IRQ:
+ */
+#define VGIC_ADDR_TO_INTID(addr, bits) (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \
+ 64 / (bits) / 8)
+
+/*
+ * Some VGIC registers store per-IRQ information, with a different number
+ * of bits per IRQ. For those registers this macro is used.
+ * The _WITH_LENGTH version instantiates registers with a fixed length
+ * and is mutually exclusive with the _PER_IRQ version.
+ */
+#define REGISTER_DESC_WITH_BITS_PER_IRQ(off, rd, wr, bpi, acc) \
+ { \
+ .reg_offset = off, \
+ .bits_per_irq = bpi, \
+ .len = bpi * 1024 / 8, \
+ .access_flags = acc, \
+ .read = rd, \
+ .write = wr, \
+ }
+
+#define REGISTER_DESC_WITH_LENGTH(off, rd, wr, length, acc) \
+ { \
+ .reg_offset = off, \
+ .bits_per_irq = 0, \
+ .len = length, \
+ .access_flags = acc, \
+ .read = rd, \
+ .write = wr, \
+ }
+
+int kvm_vgic_register_mmio_region(struct kvm *kvm, struct kvm_vcpu *vcpu,
+ struct vgic_register_region *reg_desc,
+ struct vgic_io_device *region,
+ int nr_irqs, bool offset_private);
+
+unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len);
+
+void vgic_data_host_to_mmio_bus(void *buf, unsigned int len,
+ unsigned long data);
+
+unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr,
+ unsigned int len, unsigned long val);
+
+unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len);
+
+void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+
+unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev);
+
+unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev);
+
+#endif
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
new file mode 100644
index 000000000000..e31405ee5515
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -0,0 +1,356 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <kvm/arm_vgic.h>
+#include <asm/kvm_mmu.h>
+
+#include "vgic.h"
+
+/*
+ * Call this function to convert a u64 value to an unsigned long * bitmask
+ * in a way that works on both 32-bit and 64-bit LE and BE platforms.
+ *
+ * Warning: Calling this function may modify *val.
+ */
+static unsigned long *u64_to_bitmask(u64 *val)
+{
+#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
+ *val = (*val >> 32) | (*val << 32);
+#endif
+ return (unsigned long *)val;
+}
+
+void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
+
+ if (cpuif->vgic_misr & GICH_MISR_EOI) {
+ u64 eisr = cpuif->vgic_eisr;
+ unsigned long *eisr_bmap = u64_to_bitmask(&eisr);
+ int lr;
+
+ for_each_set_bit(lr, eisr_bmap, kvm_vgic_global_state.nr_lr) {
+ u32 intid = cpuif->vgic_lr[lr] & GICH_LR_VIRTUALID;
+
+ WARN_ON(cpuif->vgic_lr[lr] & GICH_LR_STATE);
+
+ kvm_notify_acked_irq(vcpu->kvm, 0,
+ intid - VGIC_NR_PRIVATE_IRQS);
+ }
+ }
+
+ /* check and disable underflow maintenance IRQ */
+ cpuif->vgic_hcr &= ~GICH_HCR_UIE;
+
+ /*
+ * In the next iterations of the vcpu loop, if we sync the
+ * vgic state after flushing it, but before entering the guest
+ * (this happens for pending signals and vmid rollovers), then
+ * make sure we don't pick up any old maintenance interrupts
+ * here.
+ */
+ cpuif->vgic_eisr = 0;
+}
+
+void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
+
+ cpuif->vgic_hcr |= GICH_HCR_UIE;
+}
+
+/*
+ * transfer the content of the LRs back into the corresponding ap_list:
+ * - active bit is transferred as is
+ * - pending bit is
+ * - transferred as is in case of edge sensitive IRQs
+ * - set to the line-level (resample time) for level sensitive IRQs
+ */
+void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
+ int lr;
+
+ for (lr = 0; lr < vcpu->arch.vgic_cpu.used_lrs; lr++) {
+ u32 val = cpuif->vgic_lr[lr];
+ u32 intid = val & GICH_LR_VIRTUALID;
+ struct vgic_irq *irq;
+
+ irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
+
+ spin_lock(&irq->irq_lock);
+
+ /* Always preserve the active bit */
+ irq->active = !!(val & GICH_LR_ACTIVE_BIT);
+
+ /* Edge is the only case where we preserve the pending bit */
+ if (irq->config == VGIC_CONFIG_EDGE &&
+ (val & GICH_LR_PENDING_BIT)) {
+ irq->pending = true;
+
+ if (vgic_irq_is_sgi(intid)) {
+ u32 cpuid = val & GICH_LR_PHYSID_CPUID;
+
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ irq->source |= (1 << cpuid);
+ }
+ }
+
+ /*
+ * Clear soft pending state when level irqs have been acked.
+ * Always regenerate the pending state.
+ */
+ if (irq->config == VGIC_CONFIG_LEVEL) {
+ if (!(val & GICH_LR_PENDING_BIT))
+ irq->soft_pending = false;
+
+ irq->pending = irq->line_level || irq->soft_pending;
+ }
+
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+/*
+ * Populates the particular LR with the state of a given IRQ:
+ * - for an edge sensitive IRQ the pending state is cleared in struct vgic_irq
+ * - for a level sensitive IRQ the pending state value is unchanged;
+ * it is dictated directly by the input level
+ *
+ * If @irq describes an SGI with multiple sources, we choose the
+ * lowest-numbered source VCPU and clear that bit in the source bitmap.
+ *
+ * The irq_lock must be held by the caller.
+ */
+void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
+{
+ u32 val = irq->intid;
+
+ if (irq->pending) {
+ val |= GICH_LR_PENDING_BIT;
+
+ if (irq->config == VGIC_CONFIG_EDGE)
+ irq->pending = false;
+
+ if (vgic_irq_is_sgi(irq->intid)) {
+ u32 src = ffs(irq->source);
+
+ BUG_ON(!src);
+ val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
+ irq->source &= ~(1 << (src - 1));
+ if (irq->source)
+ irq->pending = true;
+ }
+ }
+
+ if (irq->active)
+ val |= GICH_LR_ACTIVE_BIT;
+
+ if (irq->hw) {
+ val |= GICH_LR_HW;
+ val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT;
+ } else {
+ if (irq->config == VGIC_CONFIG_LEVEL)
+ val |= GICH_LR_EOI;
+ }
+
+ /* The GICv2 LR only holds five bits of priority. */
+ val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT;
+
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = val;
+}
+
+void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr)
+{
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = 0;
+}
+
+void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr;
+
+ vmcr = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+ vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) &
+ GICH_VMCR_ALIAS_BINPOINT_MASK;
+ vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
+ GICH_VMCR_BINPOINT_MASK;
+ vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) &
+ GICH_VMCR_PRIMASK_MASK;
+
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
+}
+
+void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
+
+ vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >>
+ GICH_VMCR_CTRL_SHIFT;
+ vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >>
+ GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+ vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
+ GICH_VMCR_BINPOINT_SHIFT;
+ vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >>
+ GICH_VMCR_PRIMASK_SHIFT;
+}
+
+void vgic_v2_enable(struct kvm_vcpu *vcpu)
+{
+ /*
+ * By forcing VMCR to zero, the GIC will restore the binary
+ * points to their reset values. Anything else resets to zero
+ * anyway.
+ */
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0;
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr = ~0;
+
+ /* Get the show on the road... */
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN;
+}
+
+/* check for overlapping regions and for regions crossing the end of memory */
+static bool vgic_v2_check_base(gpa_t dist_base, gpa_t cpu_base)
+{
+ if (dist_base + KVM_VGIC_V2_DIST_SIZE < dist_base)
+ return false;
+ if (cpu_base + KVM_VGIC_V2_CPU_SIZE < cpu_base)
+ return false;
+
+ if (dist_base + KVM_VGIC_V2_DIST_SIZE <= cpu_base)
+ return true;
+ if (cpu_base + KVM_VGIC_V2_CPU_SIZE <= dist_base)
+ return true;
+
+ return false;
+}
+
+int vgic_v2_map_resources(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int ret = 0;
+
+ if (vgic_ready(kvm))
+ goto out;
+
+ if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
+ IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
+ kvm_err("Need to set vgic cpu and dist addresses first\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) {
+ kvm_err("VGIC CPU and dist frames overlap\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Initialize the vgic if this hasn't already been done on demand by
+ * accessing the vgic state from userspace.
+ */
+ ret = vgic_init(kvm);
+ if (ret) {
+ kvm_err("Unable to initialize VGIC dynamic data structures\n");
+ goto out;
+ }
+
+ ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2);
+ if (ret) {
+ kvm_err("Unable to register VGIC MMIO regions\n");
+ goto out;
+ }
+
+ ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base,
+ kvm_vgic_global_state.vcpu_base,
+ KVM_VGIC_V2_CPU_SIZE, true);
+ if (ret) {
+ kvm_err("Unable to remap VGIC CPU to VCPU\n");
+ goto out;
+ }
+
+ dist->ready = true;
+
+out:
+ if (ret)
+ kvm_vgic_destroy(kvm);
+ return ret;
+}
+
+/**
+ * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
+ * @node: pointer to the DT node
+ *
+ * Returns 0 if a GICv2 has been found, returns an error code otherwise
+ */
+int vgic_v2_probe(const struct gic_kvm_info *info)
+{
+ int ret;
+ u32 vtr;
+
+ if (!info->vctrl.start) {
+ kvm_err("GICH not present in the firmware table\n");
+ return -ENXIO;
+ }
+
+ if (!PAGE_ALIGNED(info->vcpu.start)) {
+ kvm_err("GICV physical address 0x%llx not page aligned\n",
+ (unsigned long long)info->vcpu.start);
+ return -ENXIO;
+ }
+
+ if (!PAGE_ALIGNED(resource_size(&info->vcpu))) {
+ kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+ (unsigned long long)resource_size(&info->vcpu),
+ PAGE_SIZE);
+ return -ENXIO;
+ }
+
+ kvm_vgic_global_state.vctrl_base = ioremap(info->vctrl.start,
+ resource_size(&info->vctrl));
+ if (!kvm_vgic_global_state.vctrl_base) {
+ kvm_err("Cannot ioremap GICH\n");
+ return -ENOMEM;
+ }
+
+ vtr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VTR);
+ kvm_vgic_global_state.nr_lr = (vtr & 0x3f) + 1;
+
+ ret = create_hyp_io_mappings(kvm_vgic_global_state.vctrl_base,
+ kvm_vgic_global_state.vctrl_base +
+ resource_size(&info->vctrl),
+ info->vctrl.start);
+
+ if (ret) {
+ kvm_err("Cannot map VCTRL into hyp\n");
+ iounmap(kvm_vgic_global_state.vctrl_base);
+ return ret;
+ }
+
+ kvm_vgic_global_state.can_emulate_gicv2 = true;
+ kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
+
+ kvm_vgic_global_state.vcpu_base = info->vcpu.start;
+ kvm_vgic_global_state.type = VGIC_V2;
+ kvm_vgic_global_state.max_gic_vcpus = VGIC_V2_MAX_CPUS;
+
+ kvm_info("vgic-v2@%llx\n", info->vctrl.start);
+
+ return 0;
+}
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
new file mode 100644
index 000000000000..346b4ad12b49
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -0,0 +1,334 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irqchip/arm-gic-v3.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <kvm/arm_vgic.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_asm.h>
+
+#include "vgic.h"
+
+void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
+
+ if (cpuif->vgic_misr & ICH_MISR_EOI) {
+ unsigned long eisr_bmap = cpuif->vgic_eisr;
+ int lr;
+
+ for_each_set_bit(lr, &eisr_bmap, kvm_vgic_global_state.nr_lr) {
+ u32 intid;
+ u64 val = cpuif->vgic_lr[lr];
+
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ intid = val & ICH_LR_VIRTUAL_ID_MASK;
+ else
+ intid = val & GICH_LR_VIRTUALID;
+
+ WARN_ON(cpuif->vgic_lr[lr] & ICH_LR_STATE);
+
+ kvm_notify_acked_irq(vcpu->kvm, 0,
+ intid - VGIC_NR_PRIVATE_IRQS);
+ }
+
+ /*
+ * In the next iterations of the vcpu loop, if we sync
+ * the vgic state after flushing it, but before
+ * entering the guest (this happens for pending
+ * signals and vmid rollovers), then make sure we
+ * don't pick up any old maintenance interrupts here.
+ */
+ cpuif->vgic_eisr = 0;
+ }
+
+ cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+}
+
+void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
+
+ cpuif->vgic_hcr |= ICH_HCR_UIE;
+}
+
+void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
+ int lr;
+
+ for (lr = 0; lr < vcpu->arch.vgic_cpu.used_lrs; lr++) {
+ u64 val = cpuif->vgic_lr[lr];
+ u32 intid;
+ struct vgic_irq *irq;
+
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ intid = val & ICH_LR_VIRTUAL_ID_MASK;
+ else
+ intid = val & GICH_LR_VIRTUALID;
+ irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
+
+ spin_lock(&irq->irq_lock);
+
+ /* Always preserve the active bit */
+ irq->active = !!(val & ICH_LR_ACTIVE_BIT);
+
+ /* Edge is the only case where we preserve the pending bit */
+ if (irq->config == VGIC_CONFIG_EDGE &&
+ (val & ICH_LR_PENDING_BIT)) {
+ irq->pending = true;
+
+ if (vgic_irq_is_sgi(intid) &&
+ model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+ u32 cpuid = val & GICH_LR_PHYSID_CPUID;
+
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ irq->source |= (1 << cpuid);
+ }
+ }
+
+ /*
+ * Clear soft pending state when level irqs have been acked.
+ * Always regenerate the pending state.
+ */
+ if (irq->config == VGIC_CONFIG_LEVEL) {
+ if (!(val & ICH_LR_PENDING_BIT))
+ irq->soft_pending = false;
+
+ irq->pending = irq->line_level || irq->soft_pending;
+ }
+
+ spin_unlock(&irq->irq_lock);
+ }
+}
+
+/* Requires the irq to be locked already */
+void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
+{
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
+ u64 val = irq->intid;
+
+ if (irq->pending) {
+ val |= ICH_LR_PENDING_BIT;
+
+ if (irq->config == VGIC_CONFIG_EDGE)
+ irq->pending = false;
+
+ if (vgic_irq_is_sgi(irq->intid) &&
+ model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+ u32 src = ffs(irq->source);
+
+ BUG_ON(!src);
+ val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
+ irq->source &= ~(1 << (src - 1));
+ if (irq->source)
+ irq->pending = true;
+ }
+ }
+
+ if (irq->active)
+ val |= ICH_LR_ACTIVE_BIT;
+
+ if (irq->hw) {
+ val |= ICH_LR_HW;
+ val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT;
+ } else {
+ if (irq->config == VGIC_CONFIG_LEVEL)
+ val |= ICH_LR_EOI;
+ }
+
+ /*
+ * We currently only support Group1 interrupts, which is a
+ * known defect. This needs to be addressed at some point.
+ */
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ val |= ICH_LR_GROUP;
+
+ val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT;
+
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val;
+}
+
+void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr)
+{
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0;
+}
+
+void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr;
+
+ vmcr = (vmcrp->ctlr << ICH_VMCR_CTLR_SHIFT) & ICH_VMCR_CTLR_MASK;
+ vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
+ vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
+ vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
+
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
+}
+
+void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
+
+ vmcrp->ctlr = (vmcr & ICH_VMCR_CTLR_MASK) >> ICH_VMCR_CTLR_SHIFT;
+ vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
+ vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
+ vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
+}
+
+void vgic_v3_enable(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
+
+ /*
+ * By forcing VMCR to zero, the GIC will restore the binary
+ * points to their reset values. Anything else resets to zero
+ * anyway.
+ */
+ vgic_v3->vgic_vmcr = 0;
+ vgic_v3->vgic_elrsr = ~0;
+
+ /*
+ * If we are emulating a GICv3, we do it in an non-GICv2-compatible
+ * way, so we force SRE to 1 to demonstrate this to the guest.
+ * This goes with the spec allowing the value to be RAO/WI.
+ */
+ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
+ else
+ vgic_v3->vgic_sre = 0;
+
+ /* Get the show on the road... */
+ vgic_v3->vgic_hcr = ICH_HCR_EN;
+}
+
+/* check for overlapping regions and for regions crossing the end of memory */
+static bool vgic_v3_check_base(struct kvm *kvm)
+{
+ struct vgic_dist *d = &kvm->arch.vgic;
+ gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE;
+
+ redist_size *= atomic_read(&kvm->online_vcpus);
+
+ if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
+ return false;
+ if (d->vgic_redist_base + redist_size < d->vgic_redist_base)
+ return false;
+
+ if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base)
+ return true;
+ if (d->vgic_redist_base + redist_size <= d->vgic_dist_base)
+ return true;
+
+ return false;
+}
+
+int vgic_v3_map_resources(struct kvm *kvm)
+{
+ int ret = 0;
+ struct vgic_dist *dist = &kvm->arch.vgic;
+
+ if (vgic_ready(kvm))
+ goto out;
+
+ if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
+ IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) {
+ kvm_err("Need to set vgic distributor addresses first\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!vgic_v3_check_base(kvm)) {
+ kvm_err("VGIC redist and dist frames overlap\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * For a VGICv3 we require the userland to explicitly initialize
+ * the VGIC before we need to use it.
+ */
+ if (!vgic_initialized(kvm)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3);
+ if (ret) {
+ kvm_err("Unable to register VGICv3 dist MMIO regions\n");
+ goto out;
+ }
+
+ ret = vgic_register_redist_iodevs(kvm, dist->vgic_redist_base);
+ if (ret) {
+ kvm_err("Unable to register VGICv3 redist MMIO regions\n");
+ goto out;
+ }
+
+ dist->ready = true;
+
+out:
+ if (ret)
+ kvm_vgic_destroy(kvm);
+ return ret;
+}
+
+/**
+ * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
+ * @node: pointer to the DT node
+ *
+ * Returns 0 if a GICv3 has been found, returns an error code otherwise
+ */
+int vgic_v3_probe(const struct gic_kvm_info *info)
+{
+ u32 ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
+
+ /*
+ * The ListRegs field is 5 bits, but there is a architectural
+ * maximum of 16 list registers. Just ignore bit 4...
+ */
+ kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1;
+ kvm_vgic_global_state.can_emulate_gicv2 = false;
+
+ if (!info->vcpu.start) {
+ kvm_info("GICv3: no GICV resource entry\n");
+ kvm_vgic_global_state.vcpu_base = 0;
+ } else if (!PAGE_ALIGNED(info->vcpu.start)) {
+ pr_warn("GICV physical address 0x%llx not page aligned\n",
+ (unsigned long long)info->vcpu.start);
+ kvm_vgic_global_state.vcpu_base = 0;
+ } else if (!PAGE_ALIGNED(resource_size(&info->vcpu))) {
+ pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+ (unsigned long long)resource_size(&info->vcpu),
+ PAGE_SIZE);
+ kvm_vgic_global_state.vcpu_base = 0;
+ } else {
+ kvm_vgic_global_state.vcpu_base = info->vcpu.start;
+ kvm_vgic_global_state.can_emulate_gicv2 = true;
+ kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
+ kvm_info("vgic-v2@%llx\n", info->vcpu.start);
+ }
+ if (kvm_vgic_global_state.vcpu_base == 0)
+ kvm_info("disabling GICv2 emulation\n");
+ kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3);
+
+ kvm_vgic_global_state.vctrl_base = NULL;
+ kvm_vgic_global_state.type = VGIC_V3;
+ kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS;
+
+ return 0;
+}
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
new file mode 100644
index 000000000000..69b61abefa19
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -0,0 +1,619 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/list_sort.h>
+
+#include "vgic.h"
+
+#define CREATE_TRACE_POINTS
+#include "../trace.h"
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p)
+#else
+#define DEBUG_SPINLOCK_BUG_ON(p)
+#endif
+
+struct vgic_global __section(.hyp.text) kvm_vgic_global_state;
+
+/*
+ * Locking order is always:
+ * vgic_cpu->ap_list_lock
+ * vgic_irq->irq_lock
+ *
+ * (that is, always take the ap_list_lock before the struct vgic_irq lock).
+ *
+ * When taking more than one ap_list_lock at the same time, always take the
+ * lowest numbered VCPU's ap_list_lock first, so:
+ * vcpuX->vcpu_id < vcpuY->vcpu_id:
+ * spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock);
+ * spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock);
+ */
+
+struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
+ u32 intid)
+{
+ /* SGIs and PPIs */
+ if (intid <= VGIC_MAX_PRIVATE)
+ return &vcpu->arch.vgic_cpu.private_irqs[intid];
+
+ /* SPIs */
+ if (intid <= VGIC_MAX_SPI)
+ return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
+
+ /* LPIs are not yet covered */
+ if (intid >= VGIC_MIN_LPI)
+ return NULL;
+
+ WARN(1, "Looking up struct vgic_irq for reserved INTID");
+ return NULL;
+}
+
+/**
+ * kvm_vgic_target_oracle - compute the target vcpu for an irq
+ *
+ * @irq: The irq to route. Must be already locked.
+ *
+ * Based on the current state of the interrupt (enabled, pending,
+ * active, vcpu and target_vcpu), compute the next vcpu this should be
+ * given to. Return NULL if this shouldn't be injected at all.
+ *
+ * Requires the IRQ lock to be held.
+ */
+static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq)
+{
+ DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));
+
+ /* If the interrupt is active, it must stay on the current vcpu */
+ if (irq->active)
+ return irq->vcpu ? : irq->target_vcpu;
+
+ /*
+ * If the IRQ is not active but enabled and pending, we should direct
+ * it to its configured target VCPU.
+ * If the distributor is disabled, pending interrupts shouldn't be
+ * forwarded.
+ */
+ if (irq->enabled && irq->pending) {
+ if (unlikely(irq->target_vcpu &&
+ !irq->target_vcpu->kvm->arch.vgic.enabled))
+ return NULL;
+
+ return irq->target_vcpu;
+ }
+
+ /* If neither active nor pending and enabled, then this IRQ should not
+ * be queued to any VCPU.
+ */
+ return NULL;
+}
+
+/*
+ * The order of items in the ap_lists defines how we'll pack things in LRs as
+ * well, the first items in the list being the first things populated in the
+ * LRs.
+ *
+ * A hard rule is that active interrupts can never be pushed out of the LRs
+ * (and therefore take priority) since we cannot reliably trap on deactivation
+ * of IRQs and therefore they have to be present in the LRs.
+ *
+ * Otherwise things should be sorted by the priority field and the GIC
+ * hardware support will take care of preemption of priority groups etc.
+ *
+ * Return negative if "a" sorts before "b", 0 to preserve order, and positive
+ * to sort "b" before "a".
+ */
+static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+ struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list);
+ struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list);
+ bool penda, pendb;
+ int ret;
+
+ spin_lock(&irqa->irq_lock);
+ spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING);
+
+ if (irqa->active || irqb->active) {
+ ret = (int)irqb->active - (int)irqa->active;
+ goto out;
+ }
+
+ penda = irqa->enabled && irqa->pending;
+ pendb = irqb->enabled && irqb->pending;
+
+ if (!penda || !pendb) {
+ ret = (int)pendb - (int)penda;
+ goto out;
+ }
+
+ /* Both pending and enabled, sort by priority */
+ ret = irqa->priority - irqb->priority;
+out:
+ spin_unlock(&irqb->irq_lock);
+ spin_unlock(&irqa->irq_lock);
+ return ret;
+}
+
+/* Must be called with the ap_list_lock held */
+static void vgic_sort_ap_list(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
+
+ list_sort(NULL, &vgic_cpu->ap_list_head, vgic_irq_cmp);
+}
+
+/*
+ * Only valid injection if changing level for level-triggered IRQs or for a
+ * rising edge.
+ */
+static bool vgic_validate_injection(struct vgic_irq *irq, bool level)
+{
+ switch (irq->config) {
+ case VGIC_CONFIG_LEVEL:
+ return irq->line_level != level;
+ case VGIC_CONFIG_EDGE:
+ return level;
+ }
+
+ return false;
+}
+
+/*
+ * Check whether an IRQ needs to (and can) be queued to a VCPU's ap list.
+ * Do the queuing if necessary, taking the right locks in the right order.
+ * Returns true when the IRQ was queued, false otherwise.
+ *
+ * Needs to be entered with the IRQ lock already held, but will return
+ * with all locks dropped.
+ */
+bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq)
+{
+ struct kvm_vcpu *vcpu;
+
+ DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));
+
+retry:
+ vcpu = vgic_target_oracle(irq);
+ if (irq->vcpu || !vcpu) {
+ /*
+ * If this IRQ is already on a VCPU's ap_list, then it
+ * cannot be moved or modified and there is no more work for
+ * us to do.
+ *
+ * Otherwise, if the irq is not pending and enabled, it does
+ * not need to be inserted into an ap_list and there is also
+ * no more work for us to do.
+ */
+ spin_unlock(&irq->irq_lock);
+ return false;
+ }
+
+ /*
+ * We must unlock the irq lock to take the ap_list_lock where
+ * we are going to insert this new pending interrupt.
+ */
+ spin_unlock(&irq->irq_lock);
+
+ /* someone can do stuff here, which we re-check below */
+
+ spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
+ spin_lock(&irq->irq_lock);
+
+ /*
+ * Did something change behind our backs?
+ *
+ * There are two cases:
+ * 1) The irq lost its pending state or was disabled behind our
+ * backs and/or it was queued to another VCPU's ap_list.
+ * 2) Someone changed the affinity on this irq behind our
+ * backs and we are now holding the wrong ap_list_lock.
+ *
+ * In both cases, drop the locks and retry.
+ */
+
+ if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) {
+ spin_unlock(&irq->irq_lock);
+ spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+
+ spin_lock(&irq->irq_lock);
+ goto retry;
+ }
+
+ list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
+ irq->vcpu = vcpu;
+
+ spin_unlock(&irq->irq_lock);
+ spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+
+ kvm_vcpu_kick(vcpu);
+
+ return true;
+}
+
+static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
+ unsigned int intid, bool level,
+ bool mapped_irq)
+{
+ struct kvm_vcpu *vcpu;
+ struct vgic_irq *irq;
+ int ret;
+
+ trace_vgic_update_irq_pending(cpuid, intid, level);
+
+ ret = vgic_lazy_init(kvm);
+ if (ret)
+ return ret;
+
+ vcpu = kvm_get_vcpu(kvm, cpuid);
+ if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS)
+ return -EINVAL;
+
+ irq = vgic_get_irq(kvm, vcpu, intid);
+ if (!irq)
+ return -EINVAL;
+
+ if (irq->hw != mapped_irq)
+ return -EINVAL;
+
+ spin_lock(&irq->irq_lock);
+
+ if (!vgic_validate_injection(irq, level)) {
+ /* Nothing to see here, move along... */
+ spin_unlock(&irq->irq_lock);
+ return 0;
+ }
+
+ if (irq->config == VGIC_CONFIG_LEVEL) {
+ irq->line_level = level;
+ irq->pending = level || irq->soft_pending;
+ } else {
+ irq->pending = true;
+ }
+
+ vgic_queue_irq_unlock(kvm, irq);
+
+ return 0;
+}
+
+/**
+ * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
+ * @kvm: The VM structure pointer
+ * @cpuid: The CPU for PPIs
+ * @intid: The INTID to inject a new state to.
+ * @level: Edge-triggered: true: to trigger the interrupt
+ * false: to ignore the call
+ * Level-sensitive true: raise the input signal
+ * false: lower the input signal
+ *
+ * The VGIC is not concerned with devices being active-LOW or active-HIGH for
+ * level-sensitive interrupts. You can think of the level parameter as 1
+ * being HIGH and 0 being LOW and all devices being active-HIGH.
+ */
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+ bool level)
+{
+ return vgic_update_irq_pending(kvm, cpuid, intid, level, false);
+}
+
+int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+ bool level)
+{
+ return vgic_update_irq_pending(kvm, cpuid, intid, level, true);
+}
+
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq)
+{
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, virt_irq);
+
+ BUG_ON(!irq);
+
+ spin_lock(&irq->irq_lock);
+
+ irq->hw = true;
+ irq->hwintid = phys_irq;
+
+ spin_unlock(&irq->irq_lock);
+
+ return 0;
+}
+
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq)
+{
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, virt_irq);
+
+ BUG_ON(!irq);
+
+ if (!vgic_initialized(vcpu->kvm))
+ return -EAGAIN;
+
+ spin_lock(&irq->irq_lock);
+
+ irq->hw = false;
+ irq->hwintid = 0;
+
+ spin_unlock(&irq->irq_lock);
+
+ return 0;
+}
+
+/**
+ * vgic_prune_ap_list - Remove non-relevant interrupts from the list
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Go over the list of "interesting" interrupts, and prune those that we
+ * won't have to consider in the near future.
+ */
+static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_irq *irq, *tmp;
+
+retry:
+ spin_lock(&vgic_cpu->ap_list_lock);
+
+ list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
+ struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB;
+
+ spin_lock(&irq->irq_lock);
+
+ BUG_ON(vcpu != irq->vcpu);
+
+ target_vcpu = vgic_target_oracle(irq);
+
+ if (!target_vcpu) {
+ /*
+ * We don't need to process this interrupt any
+ * further, move it off the list.
+ */
+ list_del(&irq->ap_list);
+ irq->vcpu = NULL;
+ spin_unlock(&irq->irq_lock);
+ continue;
+ }
+
+ if (target_vcpu == vcpu) {
+ /* We're on the right CPU */
+ spin_unlock(&irq->irq_lock);
+ continue;
+ }
+
+ /* This interrupt looks like it has to be migrated. */
+
+ spin_unlock(&irq->irq_lock);
+ spin_unlock(&vgic_cpu->ap_list_lock);
+
+ /*
+ * Ensure locking order by always locking the smallest
+ * ID first.
+ */
+ if (vcpu->vcpu_id < target_vcpu->vcpu_id) {
+ vcpuA = vcpu;
+ vcpuB = target_vcpu;
+ } else {
+ vcpuA = target_vcpu;
+ vcpuB = vcpu;
+ }
+
+ spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock);
+ spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock,
+ SINGLE_DEPTH_NESTING);
+ spin_lock(&irq->irq_lock);
+
+ /*
+ * If the affinity has been preserved, move the
+ * interrupt around. Otherwise, it means things have
+ * changed while the interrupt was unlocked, and we
+ * need to replay this.
+ *
+ * In all cases, we cannot trust the list not to have
+ * changed, so we restart from the beginning.
+ */
+ if (target_vcpu == vgic_target_oracle(irq)) {
+ struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu;
+
+ list_del(&irq->ap_list);
+ irq->vcpu = target_vcpu;
+ list_add_tail(&irq->ap_list, &new_cpu->ap_list_head);
+ }
+
+ spin_unlock(&irq->irq_lock);
+ spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock);
+ spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock);
+ goto retry;
+ }
+
+ spin_unlock(&vgic_cpu->ap_list_lock);
+}
+
+static inline void vgic_process_maintenance_interrupt(struct kvm_vcpu *vcpu)
+{
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_process_maintenance(vcpu);
+ else
+ vgic_v3_process_maintenance(vcpu);
+}
+
+static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
+{
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_fold_lr_state(vcpu);
+ else
+ vgic_v3_fold_lr_state(vcpu);
+}
+
+/* Requires the irq_lock to be held. */
+static inline void vgic_populate_lr(struct kvm_vcpu *vcpu,
+ struct vgic_irq *irq, int lr)
+{
+ DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));
+
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_populate_lr(vcpu, irq, lr);
+ else
+ vgic_v3_populate_lr(vcpu, irq, lr);
+}
+
+static inline void vgic_clear_lr(struct kvm_vcpu *vcpu, int lr)
+{
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_clear_lr(vcpu, lr);
+ else
+ vgic_v3_clear_lr(vcpu, lr);
+}
+
+static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
+{
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_set_underflow(vcpu);
+ else
+ vgic_v3_set_underflow(vcpu);
+}
+
+/* Requires the ap_list_lock to be held. */
+static int compute_ap_list_depth(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_irq *irq;
+ int count = 0;
+
+ DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
+
+ list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+ spin_lock(&irq->irq_lock);
+ /* GICv2 SGIs can count for more than one... */
+ if (vgic_irq_is_sgi(irq->intid) && irq->source)
+ count += hweight8(irq->source);
+ else
+ count++;
+ spin_unlock(&irq->irq_lock);
+ }
+ return count;
+}
+
+/* Requires the VCPU's ap_list_lock to be held. */
+static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_irq *irq;
+ int count = 0;
+
+ DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
+
+ if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr) {
+ vgic_set_underflow(vcpu);
+ vgic_sort_ap_list(vcpu);
+ }
+
+ list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+ spin_lock(&irq->irq_lock);
+
+ if (unlikely(vgic_target_oracle(irq) != vcpu))
+ goto next;
+
+ /*
+ * If we get an SGI with multiple sources, try to get
+ * them in all at once.
+ */
+ do {
+ vgic_populate_lr(vcpu, irq, count++);
+ } while (irq->source && count < kvm_vgic_global_state.nr_lr);
+
+next:
+ spin_unlock(&irq->irq_lock);
+
+ if (count == kvm_vgic_global_state.nr_lr)
+ break;
+ }
+
+ vcpu->arch.vgic_cpu.used_lrs = count;
+
+ /* Nuke remaining LRs */
+ for ( ; count < kvm_vgic_global_state.nr_lr; count++)
+ vgic_clear_lr(vcpu, count);
+}
+
+/* Sync back the hardware VGIC state into our emulation after a guest's run. */
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+ vgic_process_maintenance_interrupt(vcpu);
+ vgic_fold_lr_state(vcpu);
+ vgic_prune_ap_list(vcpu);
+}
+
+/* Flush our emulation state into the GIC hardware before entering the guest. */
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+ spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
+ vgic_flush_lr_state(vcpu);
+ spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+}
+
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_irq *irq;
+ bool pending = false;
+
+ if (!vcpu->kvm->arch.vgic.enabled)
+ return false;
+
+ spin_lock(&vgic_cpu->ap_list_lock);
+
+ list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+ spin_lock(&irq->irq_lock);
+ pending = irq->pending && irq->enabled;
+ spin_unlock(&irq->irq_lock);
+
+ if (pending)
+ break;
+ }
+
+ spin_unlock(&vgic_cpu->ap_list_lock);
+
+ return pending;
+}
+
+void vgic_kick_vcpus(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int c;
+
+ /*
+ * We've injected an interrupt, time to find out who deserves
+ * a good kick...
+ */
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ if (kvm_vgic_vcpu_pending_irq(vcpu))
+ kvm_vcpu_kick(vcpu);
+ }
+}
+
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq)
+{
+ struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, virt_irq);
+ bool map_is_active;
+
+ spin_lock(&irq->irq_lock);
+ map_is_active = irq->hw && irq->active;
+ spin_unlock(&irq->irq_lock);
+
+ return map_is_active;
+}
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
new file mode 100644
index 000000000000..7b300ca370b7
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __KVM_ARM_VGIC_NEW_H__
+#define __KVM_ARM_VGIC_NEW_H__
+
+#include <linux/irqchip/arm-gic-common.h>
+
+#define PRODUCT_ID_KVM 0x4b /* ASCII code K */
+#define IMPLEMENTER_ARM 0x43b
+
+#define VGIC_ADDR_UNDEF (-1)
+#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF)
+
+#define INTERRUPT_ID_BITS_SPIS 10
+#define VGIC_PRI_BITS 5
+
+#define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS)
+
+struct vgic_vmcr {
+ u32 ctlr;
+ u32 abpr;
+ u32 bpr;
+ u32 pmr;
+};
+
+struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
+ u32 intid);
+bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq);
+void vgic_kick_vcpus(struct kvm *kvm);
+
+void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu);
+void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
+void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
+void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr);
+void vgic_v2_set_underflow(struct kvm_vcpu *vcpu);
+int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
+int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+ int offset, u32 *val);
+int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+ int offset, u32 *val);
+void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+void vgic_v2_enable(struct kvm_vcpu *vcpu);
+int vgic_v2_probe(const struct gic_kvm_info *info);
+int vgic_v2_map_resources(struct kvm *kvm);
+int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
+ enum vgic_type);
+
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu);
+void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
+void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
+void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr);
+void vgic_v3_set_underflow(struct kvm_vcpu *vcpu);
+void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+void vgic_v3_enable(struct kvm_vcpu *vcpu);
+int vgic_v3_probe(const struct gic_kvm_info *info);
+int vgic_v3_map_resources(struct kvm *kvm);
+int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+#else
+static inline void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void vgic_v3_populate_lr(struct kvm_vcpu *vcpu,
+ struct vgic_irq *irq, int lr)
+{
+}
+
+static inline void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr)
+{
+}
+
+static inline void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline
+void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+}
+
+static inline
+void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+}
+
+static inline void vgic_v3_enable(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline int vgic_v3_probe(const struct gic_kvm_info *info)
+{
+ return -ENODEV;
+}
+
+static inline int vgic_v3_map_resources(struct kvm *kvm)
+{
+ return -ENODEV;
+}
+
+static inline int vgic_register_redist_iodevs(struct kvm *kvm,
+ gpa_t dist_base_address)
+{
+ return -ENODEV;
+}
+#endif
+
+void kvm_register_vgic_device(unsigned long type);
+int vgic_lazy_init(struct kvm *kvm);
+int vgic_init(struct kvm *kvm);
+
+#endif
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index fe84e1a95dd5..8db197bb6c7a 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -40,7 +40,7 @@ int kvm_irq_map_gsi(struct kvm *kvm,
irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
lockdep_is_held(&kvm->irq_lock));
- if (gsi < irq_rt->nr_rt_entries) {
+ if (irq_rt && gsi < irq_rt->nr_rt_entries) {
hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
entries[n] = *e;
++n;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dd4ac9d9e8f5..48bd520fc702 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -63,6 +63,9 @@
#define CREATE_TRACE_POINTS
#include <trace/events/kvm.h>
+/* Worst case buffer size needed for holding an integer. */
+#define ITOA_MAX_LEN 12
+
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -100,6 +103,9 @@ static __read_mostly struct preempt_ops kvm_preempt_ops;
struct dentry *kvm_debugfs_dir;
EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
+static int kvm_debugfs_num_entries;
+static const struct file_operations *stat_fops_per_vm[];
+
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
#ifdef CONFIG_KVM_COMPAT
@@ -542,6 +548,58 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
kvfree(slots);
}
+static void kvm_destroy_vm_debugfs(struct kvm *kvm)
+{
+ int i;
+
+ if (!kvm->debugfs_dentry)
+ return;
+
+ debugfs_remove_recursive(kvm->debugfs_dentry);
+
+ for (i = 0; i < kvm_debugfs_num_entries; i++)
+ kfree(kvm->debugfs_stat_data[i]);
+ kfree(kvm->debugfs_stat_data);
+}
+
+static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
+{
+ char dir_name[ITOA_MAX_LEN * 2];
+ struct kvm_stat_data *stat_data;
+ struct kvm_stats_debugfs_item *p;
+
+ if (!debugfs_initialized())
+ return 0;
+
+ snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
+ kvm->debugfs_dentry = debugfs_create_dir(dir_name,
+ kvm_debugfs_dir);
+ if (!kvm->debugfs_dentry)
+ return -ENOMEM;
+
+ kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
+ sizeof(*kvm->debugfs_stat_data),
+ GFP_KERNEL);
+ if (!kvm->debugfs_stat_data)
+ return -ENOMEM;
+
+ for (p = debugfs_entries; p->name; p++) {
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL);
+ if (!stat_data)
+ return -ENOMEM;
+
+ stat_data->kvm = kvm;
+ stat_data->offset = p->offset;
+ kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
+ if (!debugfs_create_file(p->name, 0444,
+ kvm->debugfs_dentry,
+ stat_data,
+ stat_fops_per_vm[p->kind]))
+ return -ENOMEM;
+ }
+ return 0;
+}
+
static struct kvm *kvm_create_vm(unsigned long type)
{
int r, i;
@@ -647,6 +705,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
int i;
struct mm_struct *mm = kvm->mm;
+ kvm_destroy_vm_debugfs(kvm);
kvm_arch_sync_events(kvm);
spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
@@ -2876,25 +2935,27 @@ static long kvm_vm_ioctl(struct file *filp,
case KVM_SET_GSI_ROUTING: {
struct kvm_irq_routing routing;
struct kvm_irq_routing __user *urouting;
- struct kvm_irq_routing_entry *entries;
+ struct kvm_irq_routing_entry *entries = NULL;
r = -EFAULT;
if (copy_from_user(&routing, argp, sizeof(routing)))
goto out;
r = -EINVAL;
- if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+ if (routing.nr > KVM_MAX_IRQ_ROUTES)
goto out;
if (routing.flags)
goto out;
- r = -ENOMEM;
- entries = vmalloc(routing.nr * sizeof(*entries));
- if (!entries)
- goto out;
- r = -EFAULT;
- urouting = argp;
- if (copy_from_user(entries, urouting->entries,
- routing.nr * sizeof(*entries)))
- goto out_free_irq_routing;
+ if (routing.nr) {
+ r = -ENOMEM;
+ entries = vmalloc(routing.nr * sizeof(*entries));
+ if (!entries)
+ goto out;
+ r = -EFAULT;
+ urouting = argp;
+ if (copy_from_user(entries, urouting->entries,
+ routing.nr * sizeof(*entries)))
+ goto out_free_irq_routing;
+ }
r = kvm_set_irq_routing(kvm, entries, routing.nr,
routing.flags);
out_free_irq_routing:
@@ -2999,8 +3060,15 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
}
#endif
r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
- if (r < 0)
+ if (r < 0) {
+ kvm_put_kvm(kvm);
+ return r;
+ }
+
+ if (kvm_create_vm_debugfs(kvm, r) < 0) {
kvm_put_kvm(kvm);
+ return -ENOMEM;
+ }
return r;
}
@@ -3425,15 +3493,114 @@ static struct notifier_block kvm_cpu_notifier = {
.notifier_call = kvm_cpu_hotplug,
};
+static int kvm_debugfs_open(struct inode *inode, struct file *file,
+ int (*get)(void *, u64 *), int (*set)(void *, u64),
+ const char *fmt)
+{
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
+ inode->i_private;
+
+ /* The debugfs files are a reference to the kvm struct which
+ * is still valid when kvm_destroy_vm is called.
+ * To avoid the race between open and the removal of the debugfs
+ * directory we test against the users count.
+ */
+ if (!atomic_add_unless(&stat_data->kvm->users_count, 1, 0))
+ return -ENOENT;
+
+ if (simple_attr_open(inode, file, get, set, fmt)) {
+ kvm_put_kvm(stat_data->kvm);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int kvm_debugfs_release(struct inode *inode, struct file *file)
+{
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
+ inode->i_private;
+
+ simple_attr_release(inode, file);
+ kvm_put_kvm(stat_data->kvm);
+
+ return 0;
+}
+
+static int vm_stat_get_per_vm(void *data, u64 *val)
+{
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+
+ *val = *(u32 *)((void *)stat_data->kvm + stat_data->offset);
+
+ return 0;
+}
+
+static int vm_stat_get_per_vm_open(struct inode *inode, struct file *file)
+{
+ __simple_attr_check_format("%llu\n", 0ull);
+ return kvm_debugfs_open(inode, file, vm_stat_get_per_vm,
+ NULL, "%llu\n");
+}
+
+static const struct file_operations vm_stat_get_per_vm_fops = {
+ .owner = THIS_MODULE,
+ .open = vm_stat_get_per_vm_open,
+ .release = kvm_debugfs_release,
+ .read = simple_attr_read,
+ .write = simple_attr_write,
+ .llseek = generic_file_llseek,
+};
+
+static int vcpu_stat_get_per_vm(void *data, u64 *val)
+{
+ int i;
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+ struct kvm_vcpu *vcpu;
+
+ *val = 0;
+
+ kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
+ *val += *(u32 *)((void *)vcpu + stat_data->offset);
+
+ return 0;
+}
+
+static int vcpu_stat_get_per_vm_open(struct inode *inode, struct file *file)
+{
+ __simple_attr_check_format("%llu\n", 0ull);
+ return kvm_debugfs_open(inode, file, vcpu_stat_get_per_vm,
+ NULL, "%llu\n");
+}
+
+static const struct file_operations vcpu_stat_get_per_vm_fops = {
+ .owner = THIS_MODULE,
+ .open = vcpu_stat_get_per_vm_open,
+ .release = kvm_debugfs_release,
+ .read = simple_attr_read,
+ .write = simple_attr_write,
+ .llseek = generic_file_llseek,
+};
+
+static const struct file_operations *stat_fops_per_vm[] = {
+ [KVM_STAT_VCPU] = &vcpu_stat_get_per_vm_fops,
+ [KVM_STAT_VM] = &vm_stat_get_per_vm_fops,
+};
+
static int vm_stat_get(void *_offset, u64 *val)
{
unsigned offset = (long)_offset;
struct kvm *kvm;
+ struct kvm_stat_data stat_tmp = {.offset = offset};
+ u64 tmp_val;
*val = 0;
spin_lock(&kvm_lock);
- list_for_each_entry(kvm, &vm_list, vm_list)
- *val += *(u32 *)((void *)kvm + offset);
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ stat_tmp.kvm = kvm;
+ vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
+ *val += tmp_val;
+ }
spin_unlock(&kvm_lock);
return 0;
}
@@ -3444,15 +3611,16 @@ static int vcpu_stat_get(void *_offset, u64 *val)
{
unsigned offset = (long)_offset;
struct kvm *kvm;
- struct kvm_vcpu *vcpu;
- int i;
+ struct kvm_stat_data stat_tmp = {.offset = offset};
+ u64 tmp_val;
*val = 0;
spin_lock(&kvm_lock);
- list_for_each_entry(kvm, &vm_list, vm_list)
- kvm_for_each_vcpu(i, vcpu, kvm)
- *val += *(u32 *)((void *)vcpu + offset);
-
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ stat_tmp.kvm = kvm;
+ vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
+ *val += tmp_val;
+ }
spin_unlock(&kvm_lock);
return 0;
}
@@ -3473,7 +3641,8 @@ static int kvm_init_debug(void)
if (kvm_debugfs_dir == NULL)
goto out;
- for (p = debugfs_entries; p->name; ++p) {
+ kvm_debugfs_num_entries = 0;
+ for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
if (!debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
(void *)(long)p->offset,
stat_fops[p->kind]))