summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/block/inline-encryption.rst453
-rw-r--r--Documentation/block/queue-sysfs.rst33
-rw-r--r--Documentation/cdrom/cdrom-standard.rst11
-rw-r--r--Documentation/core-api/cachetlb.rst6
-rw-r--r--Documentation/core-api/mm-api.rst5
-rw-r--r--Documentation/filesystems/erofs.rst12
-rw-r--r--Documentation/filesystems/fscrypt.rst83
-rw-r--r--Documentation/filesystems/index.rst1
-rw-r--r--Documentation/filesystems/locks.rst17
-rw-r--r--Documentation/filesystems/netfs_library.rst2
-rw-r--r--Documentation/userspace-api/ioctl/cdrom.rst113
-rw-r--r--Documentation/userspace-api/ioctl/ioctl-number.rst1
-rw-r--r--MAINTAINERS17
-rw-r--r--Makefile7
-rw-r--r--arch/arc/include/asm/cacheflush.h1
-rw-r--r--arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts2
-rw-r--r--arch/arm/include/asm/cacheflush.h1
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts8
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi8
-rw-r--r--arch/arm64/boot/dts/qcom/sm8250.dtsi3
-rw-r--r--arch/arm64/net/bpf_jit_comp.c5
-rw-r--r--arch/m68k/emu/nfblock.c12
-rw-r--r--arch/m68k/include/asm/cacheflush_mm.h1
-rw-r--r--arch/mips/include/asm/cacheflush.h2
-rw-r--r--arch/mips/rb532/prom.c1
-rw-r--r--arch/mips/sibyte/common/cfe.c1
-rw-r--r--arch/mips/sibyte/swarm/setup.c1
-rw-r--r--arch/nds32/include/asm/cacheflush.h1
-rw-r--r--arch/nds32/kernel/ftrace.c2
-rw-r--r--arch/nios2/include/asm/cacheflush.h3
-rw-r--r--arch/nios2/platform/Kconfig.platform1
-rw-r--r--arch/openrisc/mm/init.c1
-rw-r--r--arch/parisc/include/asm/cacheflush.h3
-rw-r--r--arch/powerpc/platforms/cell/spufs/inode.c1
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c27
-rw-r--r--arch/riscv/Kconfig6
-rw-r--r--arch/riscv/include/asm/kasan.h3
-rw-r--r--arch/riscv/kernel/head.S1
-rw-r--r--arch/riscv/mm/kasan_init.c14
-rw-r--r--arch/riscv/net/bpf_jit_core.c8
-rw-r--r--arch/s390/kvm/interrupt.c5
-rw-r--r--arch/s390/kvm/kvm-s390.c1
-rw-r--r--arch/sh/include/asm/cacheflush.h3
-rw-r--r--arch/um/drivers/ubd_kern.c14
-rw-r--r--arch/x86/crypto/sm4-aesni-avx-asm_64.S6
-rw-r--r--arch/x86/crypto/sm4-aesni-avx2-asm_64.S6
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/kvm/svm/sev.c15
-rw-r--r--arch/x86/kvm/x86.c36
-rw-r--r--arch/x86/kvm/xen.c27
-rw-r--r--arch/xtensa/include/asm/cacheflush.h5
-rw-r--r--arch/xtensa/platforms/iss/simdisk.c16
-rw-r--r--block/Kconfig28
-rw-r--r--block/Kconfig.iosched4
-rw-r--r--block/Makefile6
-rw-r--r--block/bdev.c46
-rw-r--r--block/bfq-cgroup.c14
-rw-r--r--block/bfq-iosched.c6
-rw-r--r--block/bio-integrity.c4
-rw-r--r--block/bio.c171
-rw-r--r--block/blk-cgroup.c27
-rw-r--r--block/blk-core.c432
-rw-r--r--block/blk-crypto-fallback.c119
-rw-r--r--block/blk-crypto-internal.h2
-rw-r--r--block/blk-crypto-profile.c565
-rw-r--r--block/blk-crypto.c29
-rw-r--r--block/blk-exec.c10
-rw-r--r--block/blk-flush.c12
-rw-r--r--block/blk-ia-ranges.c348
-rw-r--r--block/blk-integrity.c6
-rw-r--r--block/blk-iocost.c12
-rw-r--r--block/blk-iolatency.c1
-rw-r--r--block/blk-merge.c127
-rw-r--r--block/blk-mq-debugfs.c134
-rw-r--r--block/blk-mq-sched.c129
-rw-r--r--block/blk-mq-sched.h49
-rw-r--r--block/blk-mq-tag.c163
-rw-r--r--block/blk-mq-tag.h38
-rw-r--r--block/blk-mq.c1047
-rw-r--r--block/blk-mq.h79
-rw-r--r--block/blk-rq-qos.h5
-rw-r--r--block/blk-settings.c20
-rw-r--r--block/blk-sysfs.c50
-rw-r--r--block/blk-throttle.c163
-rw-r--r--block/blk-throttle.h182
-rw-r--r--block/blk-wbt.c3
-rw-r--r--block/blk.h131
-rw-r--r--block/bounce.c1
-rw-r--r--block/bsg-lib.c32
-rw-r--r--block/elevator.c4
-rw-r--r--block/elevator.h (renamed from include/linux/elevator.h)21
-rw-r--r--block/fops.c286
-rw-r--r--block/genhd.c58
-rw-r--r--block/holder.c1
-rw-r--r--block/ioctl.c37
-rw-r--r--block/keyslot-manager.c578
-rw-r--r--block/kyber-iosched.c6
-rw-r--r--block/mq-deadline.c224
-rw-r--r--block/partitions/Kconfig4
-rw-r--r--block/partitions/core.c6
-rw-r--r--block/partitions/efi.c2
-rw-r--r--block/partitions/ibm.c19
-rw-r--r--block/t10-pi.c2
-rw-r--r--crypto/af_alg.c2
-rw-r--r--drivers/ata/libata-core.c57
-rw-r--r--drivers/ata/libata-scsi.c48
-rw-r--r--drivers/base/regmap/regcache-rbtree.c7
-rw-r--r--drivers/block/Kconfig25
-rw-r--r--drivers/block/Makefile1
-rw-r--r--drivers/block/amiflop.c9
-rw-r--r--drivers/block/aoe/aoeblk.c19
-rw-r--r--drivers/block/ataflop.c110
-rw-r--r--drivers/block/brd.c12
-rw-r--r--drivers/block/cryptoloop.c206
-rw-r--r--drivers/block/drbd/drbd_int.h5
-rw-r--r--drivers/block/drbd/drbd_main.c6
-rw-r--r--drivers/block/drbd/drbd_req.c3
-rw-r--r--drivers/block/floppy.c35
-rw-r--r--drivers/block/loop.c420
-rw-r--r--drivers/block/loop.h30
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c6
-rw-r--r--drivers/block/n64cart.c24
-rw-r--r--drivers/block/nbd.c176
-rw-r--r--drivers/block/null_blk/main.c195
-rw-r--r--drivers/block/null_blk/null_blk.h6
-rw-r--r--drivers/block/paride/pcd.c312
-rw-r--r--drivers/block/paride/pd.c148
-rw-r--r--drivers/block/paride/pf.c236
-rw-r--r--drivers/block/pktcdvd.c20
-rw-r--r--drivers/block/ps3vram.c6
-rw-r--r--drivers/block/rbd.c8
-rw-r--r--drivers/block/rnbd/rnbd-clt.c15
-rw-r--r--drivers/block/rnbd/rnbd-proto.h2
-rw-r--r--drivers/block/rsxx/core.c4
-rw-r--r--drivers/block/rsxx/dev.c19
-rw-r--r--drivers/block/swim.c36
-rw-r--r--drivers/block/swim3.c5
-rw-r--r--drivers/block/sx8.c15
-rw-r--r--drivers/block/virtio_blk.c16
-rw-r--r--drivers/block/xen-blkback/xenbus.c2
-rw-r--r--drivers/block/xen-blkfront.c9
-rw-r--r--drivers/block/zram/zram_drv.c10
-rw-r--r--drivers/cdrom/cdrom.c63
-rw-r--r--drivers/cdrom/gdrom.c7
-rw-r--r--drivers/char/tpm/Kconfig2
-rw-r--r--drivers/char/tpm/tpm2-space.c3
-rw-r--r--drivers/char/tpm/tpm_tis_core.c26
-rw-r--r--drivers/char/tpm/tpm_tis_core.h4
-rw-r--r--drivers/char/tpm/tpm_tis_spi_main.c1
-rw-r--r--drivers/clk/clk-composite.c10
-rw-r--r--drivers/gpio/gpio-mlxbf2.c5
-rw-r--r--drivers/gpio/gpio-xgs-iproc.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nv.c2
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c20
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c29
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c7
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c13
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c6
-rw-r--r--drivers/gpu/drm/amd/display/include/dal_asic_id.h2
-rw-r--r--drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c6
-rw-r--r--drivers/gpu/drm/drm_panel_orientation_quirks.c12
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.c3
-rw-r--r--drivers/gpu/drm/i915/gt/intel_timeline.c4
-rw-r--r--drivers/gpu/drm/i915/i915_reg.h8
-rw-r--r--drivers/gpu/drm/i915/i915_trace.h7
-rw-r--r--drivers/gpu/drm/i915/i915_utils.h1
-rw-r--r--drivers/gpu/drm/i915/intel_dram.c30
-rw-r--r--drivers/gpu/drm/selftests/test-drm_damage_helper.c1
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo_util.c1
-rw-r--r--drivers/infiniband/core/sa_query.c5
-rw-r--r--drivers/infiniband/hw/hfi1/pio.c9
-rw-r--r--drivers/infiniband/hw/irdma/uk.c4
-rw-r--r--drivers/infiniband/hw/irdma/verbs.c8
-rw-r--r--drivers/infiniband/hw/irdma/ws.c13
-rw-r--r--drivers/infiniband/hw/mlx5/mr.c2
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c2
-rw-r--r--drivers/infiniband/hw/qedr/qedr.h1
-rw-r--r--drivers/infiniband/hw/qedr/qedr_iw_cm.c2
-rw-r--r--drivers/infiniband/hw/qedr/verbs.c5
-rw-r--r--drivers/infiniband/hw/qib/qib_user_sdma.c33
-rw-r--r--drivers/infiniband/sw/rdmavt/qp.c2
-rw-r--r--drivers/md/bcache/bcache.h6
-rw-r--r--drivers/md/bcache/bcache_ondisk.h (renamed from include/uapi/linux/bcache.h)4
-rw-r--r--drivers/md/bcache/bset.h2
-rw-r--r--drivers/md/bcache/btree.c2
-rw-r--r--drivers/md/bcache/debug.c15
-rw-r--r--drivers/md/bcache/features.c2
-rw-r--r--drivers/md/bcache/features.h3
-rw-r--r--drivers/md/bcache/io.c16
-rw-r--r--drivers/md/bcache/request.c19
-rw-r--r--drivers/md/bcache/request.h4
-rw-r--r--drivers/md/bcache/super.c91
-rw-r--r--drivers/md/bcache/sysfs.c2
-rw-r--r--drivers/md/bcache/sysfs.h18
-rw-r--r--drivers/md/bcache/util.h29
-rw-r--r--drivers/md/bcache/writeback.c2
-rw-r--r--drivers/md/dm-bio-record.h1
-rw-r--r--drivers/md/dm-bufio.c2
-rw-r--r--drivers/md/dm-cache-metadata.c2
-rw-r--r--drivers/md/dm-cache-target.c2
-rw-r--r--drivers/md/dm-clone-target.c2
-rw-r--r--drivers/md/dm-core.h4
-rw-r--r--drivers/md/dm-crypt.c1
-rw-r--r--drivers/md/dm-dust.c5
-rw-r--r--drivers/md/dm-ebs-target.c2
-rw-r--r--drivers/md/dm-era-target.c2
-rw-r--r--drivers/md/dm-exception-store.h2
-rw-r--r--drivers/md/dm-flakey.c3
-rw-r--r--drivers/md/dm-ima.c1
-rw-r--r--drivers/md/dm-integrity.c6
-rw-r--r--drivers/md/dm-linear.c3
-rw-r--r--drivers/md/dm-log-writes.c4
-rw-r--r--drivers/md/dm-log.c2
-rw-r--r--drivers/md/dm-mpath.c6
-rw-r--r--drivers/md/dm-ps-historical-service-time.c1
-rw-r--r--drivers/md/dm-raid.c6
-rw-r--r--drivers/md/dm-rq.c1
-rw-r--r--drivers/md/dm-switch.c2
-rw-r--r--drivers/md/dm-table.c172
-rw-r--r--drivers/md/dm-thin-metadata.c2
-rw-r--r--drivers/md/dm-thin.c2
-rw-r--r--drivers/md/dm-verity-target.c4
-rw-r--r--drivers/md/dm-writecache.c2
-rw-r--r--drivers/md/dm-zoned-target.c2
-rw-r--r--drivers/md/dm.c42
-rw-r--r--drivers/md/md.c130
-rw-r--r--drivers/md/md.h2
-rw-r--r--drivers/md/raid1.c13
-rw-r--r--drivers/md/raid10.c2
-rw-r--r--drivers/md/raid5.c7
-rw-r--r--drivers/mmc/core/block.c20
-rw-r--r--drivers/mmc/core/crypto.c11
-rw-r--r--drivers/mmc/core/sd.c1
-rw-r--r--drivers/mmc/host/Kconfig2
-rw-r--r--drivers/mmc/host/cqhci-core.c3
-rw-r--r--drivers/mmc/host/cqhci-crypto.c33
-rw-r--r--drivers/mmc/host/dw_mmc-exynos.c14
-rw-r--r--drivers/mmc/host/mtk-sd.c38
-rw-r--r--drivers/mmc/host/sdhci-esdhc-imx.c16
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c29
-rw-r--r--drivers/mmc/host/sdhci.c6
-rw-r--r--drivers/mmc/host/tmio_mmc_core.c17
-rw-r--r--drivers/mmc/host/vub300.c18
-rw-r--r--drivers/mtd/mtd_blkdevs.c6
-rw-r--r--drivers/mtd/mtdsuper.c1
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c16
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c30
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c35
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h1
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c5
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h1
-rw-r--r--drivers/net/ethernet/intel/ice/ice_lag.c18
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ptp.c3
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c148
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/pci.c25
-rw-r--r--drivers/net/ethernet/microchip/lan743x_main.c35
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/main.c16
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/main.h2
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/offload.c17
-rw-r--r--drivers/net/ethernet/nxp/lpc_eth.c5
-rw-r--r--drivers/net/ethernet/realtek/r8169_main.c1
-rw-r--r--drivers/net/phy/phy.c140
-rw-r--r--drivers/net/usb/lan78xx.c6
-rw-r--r--drivers/net/usb/usbnet.c1
-rw-r--r--drivers/net/vmxnet3/vmxnet3_drv.c1
-rw-r--r--drivers/net/xen-netfront.c8
-rw-r--r--drivers/nfc/port100.c4
-rw-r--r--drivers/nvdimm/blk.c5
-rw-r--r--drivers/nvdimm/btt.c5
-rw-r--r--drivers/nvdimm/core.c1
-rw-r--r--drivers/nvdimm/pmem.c36
-rw-r--r--drivers/nvme/host/core.c140
-rw-r--r--drivers/nvme/host/fabrics.c6
-rw-r--r--drivers/nvme/host/fabrics.h8
-rw-r--r--drivers/nvme/host/fc.c34
-rw-r--r--drivers/nvme/host/multipath.c54
-rw-r--r--drivers/nvme/host/nvme.h19
-rw-r--r--drivers/nvme/host/pci.c58
-rw-r--r--drivers/nvme/host/rdma.c28
-rw-r--r--drivers/nvme/host/tcp.c29
-rw-r--r--drivers/nvme/host/zns.c2
-rw-r--r--drivers/nvme/target/admin-cmd.c18
-rw-r--r--drivers/nvme/target/configfs.c41
-rw-r--r--drivers/nvme/target/core.c18
-rw-r--r--drivers/nvme/target/discovery.c19
-rw-r--r--drivers/nvme/target/fabrics-cmd.c3
-rw-r--r--drivers/nvme/target/io-cmd-bdev.c5
-rw-r--r--drivers/nvme/target/io-cmd-file.c4
-rw-r--r--drivers/nvme/target/loop.c6
-rw-r--r--drivers/nvme/target/nvmet.h6
-rw-r--r--drivers/nvme/target/rdma.c31
-rw-r--r--drivers/nvme/target/tcp.c23
-rw-r--r--drivers/reset/Kconfig4
-rw-r--r--drivers/reset/reset-brcmstb-rescal.c2
-rw-r--r--drivers/reset/reset-socfpga.c26
-rw-r--r--drivers/reset/tegra/reset-bpmp.c9
-rw-r--r--drivers/s390/block/dasd.c9
-rw-r--r--drivers/s390/block/dasd_3990_erp.c6
-rw-r--r--drivers/s390/block/dasd_eckd.c294
-rw-r--r--drivers/s390/block/dasd_eckd.h13
-rw-r--r--drivers/s390/block/dasd_erp.c8
-rw-r--r--drivers/s390/block/dasd_genhd.c1
-rw-r--r--drivers/s390/block/dasd_int.h11
-rw-r--r--drivers/s390/block/dasd_ioctl.c4
-rw-r--r--drivers/s390/block/dcssblk.c7
-rw-r--r--drivers/scsi/hisi_sas/hisi_sas_v3_hw.c1
-rw-r--r--drivers/scsi/ibmvscsi/ibmvfc.c3
-rw-r--r--drivers/scsi/lpfc/lpfc.h1
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_scsih.c9
-rw-r--r--drivers/scsi/qla2xxx/qla_nvme.c15
-rw-r--r--drivers/scsi/scsi_bsg.c6
-rw-r--r--drivers/scsi/scsi_debug.c10
-rw-r--r--drivers/scsi/scsi_error.c4
-rw-r--r--drivers/scsi/scsi_ioctl.c8
-rw-r--r--drivers/scsi/scsi_lib.c32
-rw-r--r--drivers/scsi/scsi_scan.c1
-rw-r--r--drivers/scsi/sd.c121
-rw-r--r--drivers/scsi/sd.h1
-rw-r--r--drivers/scsi/sd_dif.c2
-rw-r--r--drivers/scsi/sg.c11
-rw-r--r--drivers/scsi/sr.c5
-rw-r--r--drivers/scsi/st.c7
-rw-r--r--drivers/scsi/ufs/ufs-exynos.c6
-rw-r--r--drivers/scsi/ufs/ufshcd-crypto.c32
-rw-r--r--drivers/scsi/ufs/ufshcd-crypto.h9
-rw-r--r--drivers/scsi/ufs/ufshcd.c29
-rw-r--r--drivers/scsi/ufs/ufshcd.h6
-rw-r--r--drivers/scsi/ufs/ufshpb.c287
-rw-r--r--drivers/scsi/ufs/ufshpb.h2
-rw-r--r--drivers/scsi/virtio_scsi.c1
-rw-r--r--drivers/spi/spi-altera-dfl.c2
-rw-r--r--drivers/spi/spi-altera-platform.c2
-rw-r--r--drivers/spi/spi-pl022.c5
-rw-r--r--drivers/target/target_core_file.c5
-rw-r--r--drivers/target/target_core_iblock.c6
-rw-r--r--drivers/target/target_core_pscsi.c7
-rw-r--r--drivers/usb/gadget/function/f_fs.c2
-rw-r--r--drivers/usb/gadget/legacy/inode.c7
-rw-r--r--drivers/vdpa/vdpa_user/vduse_dev.c29
-rw-r--r--drivers/virtio/virtio_ring.c2
-rw-r--r--drivers/watchdog/iTCO_wdt.c12
-rw-r--r--drivers/watchdog/ixp4xx_wdt.c2
-rw-r--r--drivers/watchdog/omap_wdt.c6
-rw-r--r--drivers/watchdog/sbsa_gwdt.c5
-rw-r--r--fs/affs/super.c2
-rw-r--r--fs/afs/write.c9
-rw-r--r--fs/aio.c6
-rw-r--r--fs/btrfs/compression.c4
-rw-r--r--fs/btrfs/ctree.c1
-rw-r--r--fs/btrfs/dev-replace.c3
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/inode.c12
-rw-r--r--fs/btrfs/ioctl.c4
-rw-r--r--fs/btrfs/lzo.c43
-rw-r--r--fs/btrfs/volumes.c10
-rw-r--r--fs/btrfs/zlib.c36
-rw-r--r--fs/btrfs/zstd.c27
-rw-r--r--fs/buffer.c4
-rw-r--r--fs/cachefiles/io.c12
-rw-r--r--fs/cachefiles/rdwr.c16
-rw-r--r--fs/ceph/file.c2
-rw-r--r--fs/ceph/locks.c3
-rw-r--r--fs/cifs/file.c4
-rw-r--r--fs/cramfs/inode.c2
-rw-r--r--fs/crypto/bio.c32
-rw-r--r--fs/crypto/fname.c3
-rw-r--r--fs/crypto/fscrypt_private.h16
-rw-r--r--fs/crypto/hkdf.c11
-rw-r--r--fs/crypto/keysetup.c62
-rw-r--r--fs/direct-io.c16
-rw-r--r--fs/erofs/Kconfig40
-rw-r--r--fs/erofs/Makefile1
-rw-r--r--fs/erofs/compress.h28
-rw-r--r--fs/erofs/data.c73
-rw-r--r--fs/erofs/decompressor.c139
-rw-r--r--fs/erofs/decompressor_lzma.c290
-rw-r--r--fs/erofs/erofs_fs.h73
-rw-r--r--fs/erofs/inode.c2
-rw-r--r--fs/erofs/internal.h105
-rw-r--r--fs/erofs/pcpubuf.c6
-rw-r--r--fs/erofs/super.c231
-rw-r--r--fs/erofs/utils.c19
-rw-r--r--fs/erofs/xattr.c4
-rw-r--r--fs/erofs/zdata.c175
-rw-r--r--fs/erofs/zdata.h7
-rw-r--r--fs/erofs/zmap.c65
-rw-r--r--fs/exfat/inode.c2
-rw-r--r--fs/ext4/file.c2
-rw-r--r--fs/ext4/super.c3
-rw-r--r--fs/f2fs/compress.c1
-rw-r--r--fs/f2fs/super.c1
-rw-r--r--fs/fat/inode.c11
-rw-r--r--fs/fs-writeback.c5
-rw-r--r--fs/fuse/file.c2
-rw-r--r--fs/gfs2/file.c6
-rw-r--r--fs/hfs/mdb.c2
-rw-r--r--fs/hfsplus/wrapper.c2
-rw-r--r--fs/internal.h11
-rw-r--r--fs/io-wq.c58
-rw-r--r--fs/io-wq.h59
-rw-r--r--fs/io_uring.c1744
-rw-r--r--fs/iomap/direct-io.c59
-rw-r--r--fs/jfs/jfs_metapage.c1
-rw-r--r--fs/jfs/resize.c5
-rw-r--r--fs/jfs/super.c5
-rw-r--r--fs/locks.c161
-rw-r--r--fs/namei.c4
-rw-r--r--fs/nfs/blocklayout/dev.c4
-rw-r--r--fs/nfs/direct.c2
-rw-r--r--fs/nfs/file.c9
-rw-r--r--fs/nfsd/Kconfig1
-rw-r--r--fs/nfsd/blocklayout.c158
-rw-r--r--fs/nfsd/nfs4layouts.c5
-rw-r--r--fs/nilfs2/ioctl.c2
-rw-r--r--fs/nilfs2/super.c2
-rw-r--r--fs/nilfs2/the_nilfs.c2
-rw-r--r--fs/ntfs/file.c1
-rw-r--r--fs/ntfs/super.c8
-rw-r--r--fs/ntfs3/file.c1
-rw-r--r--fs/ntfs3/inode.c2
-rw-r--r--fs/ntfs3/super.c2
-rw-r--r--fs/ocfs2/suballoc.c22
-rw-r--r--fs/orangefs/inode.c2
-rw-r--r--fs/orangefs/super.c1
-rw-r--r--fs/overlayfs/file.c4
-rw-r--r--fs/pstore/blk.c8
-rw-r--r--fs/quota/quota.c1
-rw-r--r--fs/ramfs/inode.c1
-rw-r--r--fs/read_write.c4
-rw-r--r--fs/reiserfs/super.c8
-rw-r--r--fs/squashfs/super.c5
-rw-r--r--fs/sync.c62
-rw-r--r--fs/ubifs/crypto.c1
-rw-r--r--fs/udf/lowlevel.c5
-rw-r--r--fs/udf/super.c9
-rw-r--r--fs/xfs/xfs_file.c2
-rw-r--r--fs/zonefs/super.c2
-rw-r--r--include/asm-generic/cacheflush.h6
-rw-r--r--include/linux/ata.h1
-rw-r--r--include/linux/backing-dev.h25
-rw-r--r--include/linux/bio.h147
-rw-r--r--include/linux/blk-crypto-profile.h166
-rw-r--r--include/linux/blk-integrity.h183
-rw-r--r--include/linux/blk-mq.h583
-rw-r--r--include/linux/blk_types.h55
-rw-r--r--include/linux/blkdev.h949
-rw-r--r--include/linux/blktrace_api.h2
-rw-r--r--include/linux/bpf.h7
-rw-r--r--include/linux/bpf_types.h8
-rw-r--r--include/linux/bvec.h2
-rw-r--r--include/linux/cdrom.h1
-rw-r--r--include/linux/device-mapper.h4
-rw-r--r--include/linux/filter.h1
-rw-r--r--include/linux/flex_proportions.h9
-rw-r--r--include/linux/fs.h12
-rw-r--r--include/linux/fscrypt.h3
-rw-r--r--include/linux/genhd.h38
-rw-r--r--include/linux/gfp.h22
-rw-r--r--include/linux/highmem-internal.h11
-rw-r--r--include/linux/highmem.h37
-rw-r--r--include/linux/huge_mm.h15
-rw-r--r--include/linux/iomap.h5
-rw-r--r--include/linux/keyslot-manager.h120
-rw-r--r--include/linux/ksm.h4
-rw-r--r--include/linux/libata.h15
-rw-r--r--include/linux/memcontrol.h264
-rw-r--r--include/linux/migrate.h4
-rw-r--r--include/linux/mm.h239
-rw-r--r--include/linux/mm_inline.h103
-rw-r--r--include/linux/mm_types.h77
-rw-r--r--include/linux/mmc/host.h4
-rw-r--r--include/linux/mmdebug.h20
-rw-r--r--include/linux/netfs.h77
-rw-r--r--include/linux/nvme-fc-driver.h7
-rw-r--r--include/linux/nvme-rdma.h2
-rw-r--r--include/linux/nvme.h30
-rw-r--r--include/linux/page-flags.h290
-rw-r--r--include/linux/page_idle.h99
-rw-r--r--include/linux/page_owner.h8
-rw-r--r--include/linux/page_ref.h158
-rw-r--r--include/linux/pagemap.h585
-rw-r--r--include/linux/part_stat.h1
-rw-r--r--include/linux/percpu-refcount.h33
-rw-r--r--include/linux/rmap.h10
-rw-r--r--include/linux/sbitmap.h24
-rw-r--r--include/linux/sched.h2
-rw-r--r--include/linux/skmsg.h1
-rw-r--r--include/linux/swap.h17
-rw-r--r--include/linux/t10-pi.h2
-rw-r--r--include/linux/tpm.h1
-rw-r--r--include/linux/vmstat.h113
-rw-r--r--include/linux/writeback.h23
-rw-r--r--include/linux/xz.h106
-rw-r--r--include/net/cfg80211.h2
-rw-r--r--include/net/mptcp.h4
-rw-r--r--include/net/sock.h8
-rw-r--r--include/net/tls.h11
-rw-r--r--include/net/udp.h5
-rw-r--r--include/scsi/scsi_cmnd.h3
-rw-r--r--include/scsi/scsi_device.h2
-rw-r--r--include/trace/events/block.h6
-rw-r--r--include/trace/events/erofs.h2
-rw-r--r--include/trace/events/io_uring.h61
-rw-r--r--include/trace/events/pagemap.h46
-rw-r--r--include/trace/events/writeback.h28
-rw-r--r--include/uapi/asm-generic/fcntl.h4
-rw-r--r--include/uapi/linux/cdrom.h19
-rw-r--r--include/uapi/linux/io_uring.h1
-rw-r--r--init/main.c1
-rw-r--r--kernel/acct.c1
-rw-r--r--kernel/bpf/arraymap.c1
-rw-r--r--kernel/bpf/core.c24
-rw-r--r--kernel/bpf/syscall.c11
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/cgroup/cgroup.c4
-rw-r--r--kernel/events/uprobes.c3
-rw-r--r--kernel/exit.c1
-rw-r--r--kernel/fork.c1
-rw-r--r--kernel/sched/core.c7
-rw-r--r--kernel/sched/sched.h1
-rw-r--r--kernel/trace/blktrace.c7
-rw-r--r--kernel/trace/ftrace.c18
-rw-r--r--kernel/trace/trace_eprobe.c4
-rw-r--r--lib/decompress_unxz.c10
-rw-r--r--lib/flex_proportions.c28
-rw-r--r--lib/random32.c1
-rw-r--r--lib/sbitmap.c95
-rw-r--r--lib/xz/Kconfig13
-rw-r--r--lib/xz/xz_dec_lzma2.c182
-rw-r--r--lib/xz/xz_dec_stream.c6
-rw-r--r--lib/xz/xz_dec_syms.c9
-rw-r--r--lib/xz/xz_private.h3
-rw-r--r--mm/Makefile2
-rw-r--r--mm/backing-dev.c19
-rw-r--r--mm/compaction.c4
-rw-r--r--mm/damon/core-test.h4
-rw-r--r--mm/filemap.c568
-rw-r--r--mm/folio-compat.c142
-rw-r--r--mm/highmem.c1
-rw-r--r--mm/huge_memory.c9
-rw-r--r--mm/hugetlb.c2
-rw-r--r--mm/internal.h36
-rw-r--r--mm/khugepaged.c34
-rw-r--r--mm/ksm.c34
-rw-r--r--mm/memcontrol.c356
-rw-r--r--mm/memory-failure.c30
-rw-r--r--mm/memory.c29
-rw-r--r--mm/mempolicy.c10
-rw-r--r--mm/mempool.c1
-rw-r--r--mm/memremap.c2
-rw-r--r--mm/migrate.c189
-rw-r--r--mm/mlock.c3
-rw-r--r--mm/nommu.c1
-rw-r--r--mm/oom_kill.c23
-rw-r--r--mm/page-writeback.c476
-rw-r--r--mm/page_alloc.c22
-rw-r--r--mm/page_io.c14
-rw-r--r--mm/page_owner.c10
-rw-r--r--mm/readahead.c1
-rw-r--r--mm/rmap.c14
-rw-r--r--mm/secretmem.c2
-rw-r--r--mm/shmem.c8
-rw-r--r--mm/swap.c197
-rw-r--r--mm/swap_state.c2
-rw-r--r--mm/swapfile.c10
-rw-r--r--mm/userfaultfd.c2
-rw-r--r--mm/util.c111
-rw-r--r--mm/vmalloc.c15
-rw-r--r--mm/vmscan.c8
-rw-r--r--mm/workingset.c52
-rw-r--r--net/batman-adv/bridge_loop_avoidance.c8
-rw-r--r--net/batman-adv/main.c56
-rw-r--r--net/batman-adv/network-coding.c4
-rw-r--r--net/batman-adv/translation-table.c4
-rw-r--r--net/core/dev.c9
-rw-r--r--net/core/net-sysfs.c4
-rw-r--r--net/core/skbuff.c36
-rw-r--r--net/core/skmsg.c14
-rw-r--r--net/core/sock_destructor.h12
-rw-r--r--net/core/sysctl_net_core.c2
-rw-r--r--net/ipv4/tcp.c5
-rw-r--r--net/ipv4/tcp_bpf.c27
-rw-r--r--net/ipv4/udp.c3
-rw-r--r--net/ipv4/udp_bpf.c1
-rw-r--r--net/mac80211/mesh.c9
-rw-r--r--net/mptcp/options.c39
-rw-r--r--net/sctp/sm_statefuns.c139
-rw-r--r--net/smc/af_smc.c2
-rw-r--r--net/smc/smc_llc.c2
-rw-r--r--net/tipc/crypto.c32
-rw-r--r--net/tls/tls_main.c4
-rw-r--r--net/tls/tls_sw.c21
-rw-r--r--net/unix/af_unix.c4
-rw-r--r--net/unix/unix_bpf.c2
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/wireless/core.h2
-rw-r--r--net/wireless/mlme.c26
-rw-r--r--net/wireless/scan.c7
-rw-r--r--net/wireless/util.c14
-rw-r--r--tools/perf/Makefile.perf2
-rw-r--r--tools/perf/arch/powerpc/util/skip-callchain-idx.c2
-rw-r--r--tools/perf/builtin-script.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c75
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh3
-rw-r--r--tools/testing/selftests/vm/split_huge_page_test.c2
607 files changed, 14217 insertions, 10430 deletions
diff --git a/Documentation/block/inline-encryption.rst b/Documentation/block/inline-encryption.rst
index 7f9b40d6b416..4d151fbe2058 100644
--- a/Documentation/block/inline-encryption.rst
+++ b/Documentation/block/inline-encryption.rst
@@ -1,5 +1,7 @@
.. SPDX-License-Identifier: GPL-2.0
+.. _inline_encryption:
+
=================
Inline Encryption
=================
@@ -7,230 +9,269 @@ Inline Encryption
Background
==========
-Inline encryption hardware sits logically between memory and the disk, and can
-en/decrypt data as it goes in/out of the disk. Inline encryption hardware has a
-fixed number of "keyslots" - slots into which encryption contexts (i.e. the
-encryption key, encryption algorithm, data unit size) can be programmed by the
-kernel at any time. Each request sent to the disk can be tagged with the index
-of a keyslot (and also a data unit number to act as an encryption tweak), and
-the inline encryption hardware will en/decrypt the data in the request with the
-encryption context programmed into that keyslot. This is very different from
-full disk encryption solutions like self encrypting drives/TCG OPAL/ATA
-Security standards, since with inline encryption, any block on disk could be
-encrypted with any encryption context the kernel chooses.
-
+Inline encryption hardware sits logically between memory and disk, and can
+en/decrypt data as it goes in/out of the disk. For each I/O request, software
+can control exactly how the inline encryption hardware will en/decrypt the data
+in terms of key, algorithm, data unit size (the granularity of en/decryption),
+and data unit number (a value that determines the initialization vector(s)).
+
+Some inline encryption hardware accepts all encryption parameters including raw
+keys directly in low-level I/O requests. However, most inline encryption
+hardware instead has a fixed number of "keyslots" and requires that the key,
+algorithm, and data unit size first be programmed into a keyslot. Each
+low-level I/O request then just contains a keyslot index and data unit number.
+
+Note that inline encryption hardware is very different from traditional crypto
+accelerators, which are supported through the kernel crypto API. Traditional
+crypto accelerators operate on memory regions, whereas inline encryption
+hardware operates on I/O requests. Thus, inline encryption hardware needs to be
+managed by the block layer, not the kernel crypto API.
+
+Inline encryption hardware is also very different from "self-encrypting drives",
+such as those based on the TCG Opal or ATA Security standards. Self-encrypting
+drives don't provide fine-grained control of encryption and provide no way to
+verify the correctness of the resulting ciphertext. Inline encryption hardware
+provides fine-grained control of encryption, including the choice of key and
+initialization vector for each sector, and can be tested for correctness.
Objective
=========
-We want to support inline encryption (IE) in the kernel.
-To allow for testing, we also want a crypto API fallback when actual
-IE hardware is absent. We also want IE to work with layered devices
-like dm and loopback (i.e. we want to be able to use the IE hardware
-of the underlying devices if present, or else fall back to crypto API
-en/decryption).
-
+We want to support inline encryption in the kernel. To make testing easier, we
+also want support for falling back to the kernel crypto API when actual inline
+encryption hardware is absent. We also want inline encryption to work with
+layered devices like device-mapper and loopback (i.e. we want to be able to use
+the inline encryption hardware of the underlying devices if present, or else
+fall back to crypto API en/decryption).
Constraints and notes
=====================
-- IE hardware has a limited number of "keyslots" that can be programmed
- with an encryption context (key, algorithm, data unit size, etc.) at any time.
- One can specify a keyslot in a data request made to the device, and the
- device will en/decrypt the data using the encryption context programmed into
- that specified keyslot. When possible, we want to make multiple requests with
- the same encryption context share the same keyslot.
-
-- We need a way for upper layers like filesystems to specify an encryption
- context to use for en/decrypting a struct bio, and a device driver (like UFS)
- needs to be able to use that encryption context when it processes the bio.
-
-- We need a way for device drivers to expose their inline encryption
- capabilities in a unified way to the upper layers.
-
-
-Design
-======
-
-We add a struct bio_crypt_ctx to struct bio that can
-represent an encryption context, because we need to be able to pass this
-encryption context from the upper layers (like the fs layer) to the
-device driver to act upon.
-
-While IE hardware works on the notion of keyslots, the FS layer has no
-knowledge of keyslots - it simply wants to specify an encryption context to
-use while en/decrypting a bio.
-
-We introduce a keyslot manager (KSM) that handles the translation from
-encryption contexts specified by the FS to keyslots on the IE hardware.
-This KSM also serves as the way IE hardware can expose its capabilities to
-upper layers. The generic mode of operation is: each device driver that wants
-to support IE will construct a KSM and set it up in its struct request_queue.
-Upper layers that want to use IE on this device can then use this KSM in
-the device's struct request_queue to translate an encryption context into
-a keyslot. The presence of the KSM in the request queue shall be used to mean
-that the device supports IE.
-
-The KSM uses refcounts to track which keyslots are idle (either they have no
-encryption context programmed, or there are no in-flight struct bios
-referencing that keyslot). When a new encryption context needs a keyslot, it
-tries to find a keyslot that has already been programmed with the same
-encryption context, and if there is no such keyslot, it evicts the least
-recently used idle keyslot and programs the new encryption context into that
-one. If no idle keyslots are available, then the caller will sleep until there
-is at least one.
-
-
-blk-mq changes, other block layer changes and blk-crypto-fallback
-=================================================================
-
-We add a pointer to a ``bi_crypt_context`` and ``keyslot`` to
-struct request. These will be referred to as the ``crypto fields``
-for the request. This ``keyslot`` is the keyslot into which the
-``bi_crypt_context`` has been programmed in the KSM of the ``request_queue``
-that this request is being sent to.
-
-We introduce ``block/blk-crypto-fallback.c``, which allows upper layers to remain
-blissfully unaware of whether or not real inline encryption hardware is present
-underneath. When a bio is submitted with a target ``request_queue`` that doesn't
-support the encryption context specified with the bio, the block layer will
-en/decrypt the bio with the blk-crypto-fallback.
-
-If the bio is a ``WRITE`` bio, a bounce bio is allocated, and the data in the bio
-is encrypted stored in the bounce bio - blk-mq will then proceed to process the
-bounce bio as if it were not encrypted at all (except when blk-integrity is
-concerned). ``blk-crypto-fallback`` sets the bounce bio's ``bi_end_io`` to an
-internal function that cleans up the bounce bio and ends the original bio.
-
-If the bio is a ``READ`` bio, the bio's ``bi_end_io`` (and also ``bi_private``)
-is saved and overwritten by ``blk-crypto-fallback`` to
-``bio_crypto_fallback_decrypt_bio``. The bio's ``bi_crypt_context`` is also
-overwritten with ``NULL``, so that to the rest of the stack, the bio looks
-as if it was a regular bio that never had an encryption context specified.
-``bio_crypto_fallback_decrypt_bio`` will decrypt the bio, restore the original
-``bi_end_io`` (and also ``bi_private``) and end the bio again.
-
-Regardless of whether real inline encryption hardware is used or the
+- We need a way for upper layers (e.g. filesystems) to specify an encryption
+ context to use for en/decrypting a bio, and device drivers (e.g. UFSHCD) need
+ to be able to use that encryption context when they process the request.
+ Encryption contexts also introduce constraints on bio merging; the block layer
+ needs to be aware of these constraints.
+
+- Different inline encryption hardware has different supported algorithms,
+ supported data unit sizes, maximum data unit numbers, etc. We call these
+ properties the "crypto capabilities". We need a way for device drivers to
+ advertise crypto capabilities to upper layers in a generic way.
+
+- Inline encryption hardware usually (but not always) requires that keys be
+ programmed into keyslots before being used. Since programming keyslots may be
+ slow and there may not be very many keyslots, we shouldn't just program the
+ key for every I/O request, but rather keep track of which keys are in the
+ keyslots and reuse an already-programmed keyslot when possible.
+
+- Upper layers typically define a specific end-of-life for crypto keys, e.g.
+ when an encrypted directory is locked or when a crypto mapping is torn down.
+ At these times, keys are wiped from memory. We must provide a way for upper
+ layers to also evict keys from any keyslots they are present in.
+
+- When possible, device-mapper devices must be able to pass through the inline
+ encryption support of their underlying devices. However, it doesn't make
+ sense for device-mapper devices to have keyslots themselves.
+
+Basic design
+============
+
+We introduce ``struct blk_crypto_key`` to represent an inline encryption key and
+how it will be used. This includes the actual bytes of the key; the size of the
+key; the algorithm and data unit size the key will be used with; and the number
+of bytes needed to represent the maximum data unit number the key will be used
+with.
+
+We introduce ``struct bio_crypt_ctx`` to represent an encryption context. It
+contains a data unit number and a pointer to a blk_crypto_key. We add pointers
+to a bio_crypt_ctx to ``struct bio`` and ``struct request``; this allows users
+of the block layer (e.g. filesystems) to provide an encryption context when
+creating a bio and have it be passed down the stack for processing by the block
+layer and device drivers. Note that the encryption context doesn't explicitly
+say whether to encrypt or decrypt, as that is implicit from the direction of the
+bio; WRITE means encrypt, and READ means decrypt.
+
+We also introduce ``struct blk_crypto_profile`` to contain all generic inline
+encryption-related state for a particular inline encryption device. The
+blk_crypto_profile serves as the way that drivers for inline encryption hardware
+advertise their crypto capabilities and provide certain functions (e.g.,
+functions to program and evict keys) to upper layers. Each device driver that
+wants to support inline encryption will construct a blk_crypto_profile, then
+associate it with the disk's request_queue.
+
+The blk_crypto_profile also manages the hardware's keyslots, when applicable.
+This happens in the block layer, so that users of the block layer can just
+specify encryption contexts and don't need to know about keyslots at all, nor do
+device drivers need to care about most details of keyslot management.
+
+Specifically, for each keyslot, the block layer (via the blk_crypto_profile)
+keeps track of which blk_crypto_key that keyslot contains (if any), and how many
+in-flight I/O requests are using it. When the block layer creates a
+``struct request`` for a bio that has an encryption context, it grabs a keyslot
+that already contains the key if possible. Otherwise it waits for an idle
+keyslot (a keyslot that isn't in-use by any I/O), then programs the key into the
+least-recently-used idle keyslot using the function the device driver provided.
+In both cases, the resulting keyslot is stored in the ``crypt_keyslot`` field of
+the request, where it is then accessible to device drivers and is released after
+the request completes.
+
+``struct request`` also contains a pointer to the original bio_crypt_ctx.
+Requests can be built from multiple bios, and the block layer must take the
+encryption context into account when trying to merge bios and requests. For two
+bios/requests to be merged, they must have compatible encryption contexts: both
+unencrypted, or both encrypted with the same key and contiguous data unit
+numbers. Only the encryption context for the first bio in a request is
+retained, since the remaining bios have been verified to be merge-compatible
+with the first bio.
+
+To make it possible for inline encryption to work with request_queue based
+layered devices, when a request is cloned, its encryption context is cloned as
+well. When the cloned request is submitted, it is then processed as usual; this
+includes getting a keyslot from the clone's target device if needed.
+
+blk-crypto-fallback
+===================
+
+It is desirable for the inline encryption support of upper layers (e.g.
+filesystems) to be testable without real inline encryption hardware, and
+likewise for the block layer's keyslot management logic. It is also desirable
+to allow upper layers to just always use inline encryption rather than have to
+implement encryption in multiple ways.
+
+Therefore, we also introduce *blk-crypto-fallback*, which is an implementation
+of inline encryption using the kernel crypto API. blk-crypto-fallback is built
+into the block layer, so it works on any block device without any special setup.
+Essentially, when a bio with an encryption context is submitted to a
+request_queue that doesn't support that encryption context, the block layer will
+handle en/decryption of the bio using blk-crypto-fallback.
+
+For encryption, the data cannot be encrypted in-place, as callers usually rely
+on it being unmodified. Instead, blk-crypto-fallback allocates bounce pages,
+fills a new bio with those bounce pages, encrypts the data into those bounce
+pages, and submits that "bounce" bio. When the bounce bio completes,
+blk-crypto-fallback completes the original bio. If the original bio is too
+large, multiple bounce bios may be required; see the code for details.
+
+For decryption, blk-crypto-fallback "wraps" the bio's completion callback
+(``bi_complete``) and private data (``bi_private``) with its own, unsets the
+bio's encryption context, then submits the bio. If the read completes
+successfully, blk-crypto-fallback restores the bio's original completion
+callback and private data, then decrypts the bio's data in-place using the
+kernel crypto API. Decryption happens from a workqueue, as it may sleep.
+Afterwards, blk-crypto-fallback completes the bio.
+
+In both cases, the bios that blk-crypto-fallback submits no longer have an
+encryption context. Therefore, lower layers only see standard unencrypted I/O.
+
+blk-crypto-fallback also defines its own blk_crypto_profile and has its own
+"keyslots"; its keyslots contain ``struct crypto_skcipher`` objects. The reason
+for this is twofold. First, it allows the keyslot management logic to be tested
+without actual inline encryption hardware. Second, similar to actual inline
+encryption hardware, the crypto API doesn't accept keys directly in requests but
+rather requires that keys be set ahead of time, and setting keys can be
+expensive; moreover, allocating a crypto_skcipher can't happen on the I/O path
+at all due to the locks it takes. Therefore, the concept of keyslots still
+makes sense for blk-crypto-fallback.
+
+Note that regardless of whether real inline encryption hardware or
blk-crypto-fallback is used, the ciphertext written to disk (and hence the
-on-disk format of data) will be the same (assuming the hardware's implementation
-of the algorithm being used adheres to spec and functions correctly).
-
-If a ``request queue``'s inline encryption hardware claimed to support the
-encryption context specified with a bio, then it will not be handled by the
-``blk-crypto-fallback``. We will eventually reach a point in blk-mq when a
-struct request needs to be allocated for that bio. At that point,
-blk-mq tries to program the encryption context into the ``request_queue``'s
-keyslot_manager, and obtain a keyslot, which it stores in its newly added
-``keyslot`` field. This keyslot is released when the request is completed.
-
-When the first bio is added to a request, ``blk_crypto_rq_bio_prep`` is called,
-which sets the request's ``crypt_ctx`` to a copy of the bio's
-``bi_crypt_context``. bio_crypt_do_front_merge is called whenever a subsequent
-bio is merged to the front of the request, which updates the ``crypt_ctx`` of
-the request so that it matches the newly merged bio's ``bi_crypt_context``. In particular, the request keeps a copy of the ``bi_crypt_context`` of the first
-bio in its bio-list (blk-mq needs to be careful to maintain this invariant
-during bio and request merges).
-
-To make it possible for inline encryption to work with request queue based
-layered devices, when a request is cloned, its ``crypto fields`` are cloned as
-well. When the cloned request is submitted, blk-mq programs the
-``bi_crypt_context`` of the request into the clone's request_queue's keyslot
-manager, and stores the returned keyslot in the clone's ``keyslot``.
+on-disk format of data) will be the same (assuming that both the inline
+encryption hardware's implementation and the kernel crypto API's implementation
+of the algorithm being used adhere to spec and function correctly).
+blk-crypto-fallback is optional and is controlled by the
+``CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK`` kernel configuration option.
API presented to users of the block layer
=========================================
-``struct blk_crypto_key`` represents a crypto key (the raw key, size of the
-key, the crypto algorithm to use, the data unit size to use, and the number of
-bytes required to represent data unit numbers that will be specified with the
-``bi_crypt_context``).
-
-``blk_crypto_init_key`` allows upper layers to initialize such a
-``blk_crypto_key``.
-
-``bio_crypt_set_ctx`` should be called on any bio that a user of
-the block layer wants en/decrypted via inline encryption (or the
-blk-crypto-fallback, if hardware support isn't available for the desired
-crypto configuration). This function takes the ``blk_crypto_key`` and the
-data unit number (DUN) to use when en/decrypting the bio.
-
-``blk_crypto_config_supported`` allows upper layers to query whether or not the
-an encryption context passed to request queue can be handled by blk-crypto
-(either by real inline encryption hardware, or by the blk-crypto-fallback).
-This is useful e.g. when blk-crypto-fallback is disabled, and the upper layer
-wants to use an algorithm that may not supported by hardware - this function
-lets the upper layer know ahead of time that the algorithm isn't supported,
-and the upper layer can fallback to something else if appropriate.
-
-``blk_crypto_start_using_key`` - Upper layers must call this function on
-``blk_crypto_key`` and a ``request_queue`` before using the key with any bio
-headed for that ``request_queue``. This function ensures that either the
-hardware supports the key's crypto settings, or the crypto API fallback has
-transforms for the needed mode allocated and ready to go. Note that this
-function may allocate an ``skcipher``, and must not be called from the data
-path, since allocating ``skciphers`` from the data path can deadlock.
-
-``blk_crypto_evict_key`` *must* be called by upper layers before a
-``blk_crypto_key`` is freed. Further, it *must* only be called only once
-there are no more in-flight requests that use that ``blk_crypto_key``.
-``blk_crypto_evict_key`` will ensure that a key is removed from any keyslots in
-inline encryption hardware that the key might have been programmed into (or the blk-crypto-fallback).
+``blk_crypto_config_supported()`` allows users to check ahead of time whether
+inline encryption with particular crypto settings will work on a particular
+request_queue -- either via hardware or via blk-crypto-fallback. This function
+takes in a ``struct blk_crypto_config`` which is like blk_crypto_key, but omits
+the actual bytes of the key and instead just contains the algorithm, data unit
+size, etc. This function can be useful if blk-crypto-fallback is disabled.
+
+``blk_crypto_init_key()`` allows users to initialize a blk_crypto_key.
+
+Users must call ``blk_crypto_start_using_key()`` before actually starting to use
+a blk_crypto_key on a request_queue (even if ``blk_crypto_config_supported()``
+was called earlier). This is needed to initialize blk-crypto-fallback if it
+will be needed. This must not be called from the data path, as this may have to
+allocate resources, which may deadlock in that case.
+
+Next, to attach an encryption context to a bio, users should call
+``bio_crypt_set_ctx()``. This function allocates a bio_crypt_ctx and attaches
+it to a bio, given the blk_crypto_key and the data unit number that will be used
+for en/decryption. Users don't need to worry about freeing the bio_crypt_ctx
+later, as that happens automatically when the bio is freed or reset.
+
+Finally, when done using inline encryption with a blk_crypto_key on a
+request_queue, users must call ``blk_crypto_evict_key()``. This ensures that
+the key is evicted from all keyslots it may be programmed into and unlinked from
+any kernel data structures it may be linked into.
+
+In summary, for users of the block layer, the lifecycle of a blk_crypto_key is
+as follows:
+
+1. ``blk_crypto_config_supported()`` (optional)
+2. ``blk_crypto_init_key()``
+3. ``blk_crypto_start_using_key()``
+4. ``bio_crypt_set_ctx()`` (potentially many times)
+5. ``blk_crypto_evict_key()`` (after all I/O has completed)
+6. Zeroize the blk_crypto_key (this has no dedicated function)
+
+If a blk_crypto_key is being used on multiple request_queues, then
+``blk_crypto_config_supported()`` (if used), ``blk_crypto_start_using_key()``,
+and ``blk_crypto_evict_key()`` must be called on each request_queue.
API presented to device drivers
===============================
-A :c:type:``struct blk_keyslot_manager`` should be set up by device drivers in
-the ``request_queue`` of the device. The device driver needs to call
-``blk_ksm_init`` (or its resource-managed variant ``devm_blk_ksm_init``) on the
-``blk_keyslot_manager``, while specifying the number of keyslots supported by
-the hardware.
-
-The device driver also needs to tell the KSM how to actually manipulate the
-IE hardware in the device to do things like programming the crypto key into
-the IE hardware into a particular keyslot. All this is achieved through the
-struct blk_ksm_ll_ops field in the KSM that the device driver
-must fill up after initing the ``blk_keyslot_manager``.
-
-The KSM also handles runtime power management for the device when applicable
-(e.g. when it wants to program a crypto key into the IE hardware, the device
-must be runtime powered on) - so the device driver must also set the ``dev``
-field in the ksm to point to the `struct device` for the KSM to use for runtime
-power management.
-
-``blk_ksm_reprogram_all_keys`` can be called by device drivers if the device
-needs each and every of its keyslots to be reprogrammed with the key it
-"should have" at the point in time when the function is called. This is useful
-e.g. if a device loses all its keys on runtime power down/up.
-
-If the driver used ``blk_ksm_init`` instead of ``devm_blk_ksm_init``, then
-``blk_ksm_destroy`` should be called to free up all resources used by a
-``blk_keyslot_manager`` once it is no longer needed.
+A device driver that wants to support inline encryption must set up a
+blk_crypto_profile in the request_queue of its device. To do this, it first
+must call ``blk_crypto_profile_init()`` (or its resource-managed variant
+``devm_blk_crypto_profile_init()``), providing the number of keyslots.
+
+Next, it must advertise its crypto capabilities by setting fields in the
+blk_crypto_profile, e.g. ``modes_supported`` and ``max_dun_bytes_supported``.
+
+It then must set function pointers in the ``ll_ops`` field of the
+blk_crypto_profile to tell upper layers how to control the inline encryption
+hardware, e.g. how to program and evict keyslots. Most drivers will need to
+implement ``keyslot_program`` and ``keyslot_evict``. For details, see the
+comments for ``struct blk_crypto_ll_ops``.
+
+Once the driver registers a blk_crypto_profile with a request_queue, I/O
+requests the driver receives via that queue may have an encryption context. All
+encryption contexts will be compatible with the crypto capabilities declared in
+the blk_crypto_profile, so drivers don't need to worry about handling
+unsupported requests. Also, if a nonzero number of keyslots was declared in the
+blk_crypto_profile, then all I/O requests that have an encryption context will
+also have a keyslot which was already programmed with the appropriate key.
+
+If the driver implements runtime suspend and its blk_crypto_ll_ops don't work
+while the device is runtime-suspended, then the driver must also set the ``dev``
+field of the blk_crypto_profile to point to the ``struct device`` that will be
+resumed before any of the low-level operations are called.
+
+If there are situations where the inline encryption hardware loses the contents
+of its keyslots, e.g. device resets, the driver must handle reprogramming the
+keyslots. To do this, the driver may call ``blk_crypto_reprogram_all_keys()``.
+
+Finally, if the driver used ``blk_crypto_profile_init()`` instead of
+``devm_blk_crypto_profile_init()``, then it is responsible for calling
+``blk_crypto_profile_destroy()`` when the crypto profile is no longer needed.
Layered Devices
===============
-Request queue based layered devices like dm-rq that wish to support IE need to
-create their own keyslot manager for their request queue, and expose whatever
-functionality they choose. When a layered device wants to pass a clone of that
-request to another ``request_queue``, blk-crypto will initialize and prepare the
-clone as necessary - see ``blk_crypto_insert_cloned_request`` in
-``blk-crypto.c``.
-
-
-Future Optimizations for layered devices
-========================================
-
-Creating a keyslot manager for a layered device uses up memory for each
-keyslot, and in general, a layered device merely passes the request on to a
-"child" device, so the keyslots in the layered device itself are completely
-unused, and don't need any refcounting or keyslot programming. We can instead
-define a new type of KSM; the "passthrough KSM", that layered devices can use
-to advertise an unlimited number of keyslots, and support for any encryption
-algorithms they choose, while not actually using any memory for each keyslot.
-Another use case for the "passthrough KSM" is for IE devices that do not have a
-limited number of keyslots.
-
+Request queue based layered devices like dm-rq that wish to support inline
+encryption need to create their own blk_crypto_profile for their request_queue,
+and expose whatever functionality they choose. When a layered device wants to
+pass a clone of that request to another request_queue, blk-crypto will
+initialize and prepare the clone as necessary; see
+``blk_crypto_insert_cloned_request()``.
Interaction between inline encryption and blk integrity
=======================================================
@@ -257,7 +298,7 @@ Because there isn't any real hardware yet, it seems prudent to assume that
hardware implementations might not implement both features together correctly,
and disallow the combination for now. Whenever a device supports integrity, the
kernel will pretend that the device does not support hardware inline encryption
-(by essentially setting the keyslot manager in the request_queue of the device
-to NULL). When the crypto API fallback is enabled, this means that all bios with
-and encryption context will use the fallback, and IO will complete as usual.
-When the fallback is disabled, a bio with an encryption context will be failed.
+(by setting the blk_crypto_profile in the request_queue of the device to NULL).
+When the crypto API fallback is enabled, this means that all bios with and
+encryption context will use the fallback, and IO will complete as usual. When
+the fallback is disabled, a bio with an encryption context will be failed.
diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index 4dc7f0d499a8..e8c74306f70a 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -4,7 +4,7 @@ Queue sysfs files
This text file will detail the queue files that are located in the sysfs tree
for each block device. Note that stacked devices typically do not export
-any settings, since their queue merely functions are a remapping target.
+any settings, since their queue merely functions as a remapping target.
These files are the ones found in the /sys/block/xxx/queue/ directory.
Files denoted with a RO postfix are readonly and the RW postfix means
@@ -286,4 +286,35 @@ sequential zones of zoned block devices (devices with a zoned attributed
that reports "host-managed" or "host-aware"). This value is always 0 for
regular block devices.
+independent_access_ranges (RO)
+------------------------------
+
+The presence of this sub-directory of the /sys/block/xxx/queue/ directory
+indicates that the device is capable of executing requests targeting
+different sector ranges in parallel. For instance, single LUN multi-actuator
+hard-disks will have an independent_access_ranges directory if the device
+correctly advertizes the sector ranges of its actuators.
+
+The independent_access_ranges directory contains one directory per access
+range, with each range described using the sector (RO) attribute file to
+indicate the first sector of the range and the nr_sectors (RO) attribute file
+to indicate the total number of sectors in the range starting from the first
+sector of the range. For example, a dual-actuator hard-disk will have the
+following independent_access_ranges entries.::
+
+ $ tree /sys/block/<device>/queue/independent_access_ranges/
+ /sys/block/<device>/queue/independent_access_ranges/
+ |-- 0
+ | |-- nr_sectors
+ | `-- sector
+ `-- 1
+ |-- nr_sectors
+ `-- sector
+
+The sector and nr_sectors attributes use 512B sector unit, regardless of
+the actual block size of the device. Independent access ranges do not
+overlap and include all sectors within the device capacity. The access
+ranges are numbered in increasing order of the range start sector,
+that is, the sector attribute of range 0 always has the value 0.
+
Jens Axboe <jens.axboe@oracle.com>, February 2009
diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst
index 5845960ca382..52ea7b6b2fe8 100644
--- a/Documentation/cdrom/cdrom-standard.rst
+++ b/Documentation/cdrom/cdrom-standard.rst
@@ -907,6 +907,17 @@ commands can be identified by the underscores in their names.
specifies the slot for which the information is given. The special
value *CDSL_CURRENT* requests that information about the currently
selected slot be returned.
+`CDROM_TIMED_MEDIA_CHANGE`
+ Checks whether the disc has been changed since a user supplied time
+ and returns the time of the last disc change.
+
+ *arg* is a pointer to a *cdrom_timed_media_change_info* struct.
+ *arg->last_media_change* may be set by calling code to signal
+ the timestamp of the last known media change (by the caller).
+ Upon successful return, this ioctl call will set
+ *arg->last_media_change* to the latest media change timestamp (in ms)
+ known by the kernel/driver and set *arg->has_changed* to 1 if
+ that timestamp is more recent than the timestamp set by the caller.
`CDROM_DRIVE_STATUS`
Returns the status of the drive by a call to
*drive_status()*. Return values are defined in cdrom_drive_status_.
diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst
index 8aed9103e48a..5c0552e78c58 100644
--- a/Documentation/core-api/cachetlb.rst
+++ b/Documentation/core-api/cachetlb.rst
@@ -326,6 +326,12 @@ maps this page at its virtual address.
dirty. Again, see sparc64 for examples of how
to deal with this.
+ ``void flush_dcache_folio(struct folio *folio)``
+ This function is called under the same circumstances as
+ flush_dcache_page(). It allows the architecture to
+ optimise for flushing the entire folio of pages instead
+ of flushing one page at a time.
+
``void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long user_vaddr, void *dst, void *src, int len)``
``void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index a42f9baddfbf..395835f9289f 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -95,6 +95,11 @@ More Memory Management Functions
.. kernel-doc:: mm/mempolicy.c
.. kernel-doc:: include/linux/mm_types.h
:internal:
+.. kernel-doc:: include/linux/mm_inline.h
+.. kernel-doc:: include/linux/page-flags.h
.. kernel-doc:: include/linux/mm.h
:internal:
+.. kernel-doc:: include/linux/page_ref.h
.. kernel-doc:: include/linux/mmzone.h
+.. kernel-doc:: mm/util.c
+ :functions: folio_mapping
diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index b97579b7d8fb..01df283c7d04 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -19,9 +19,10 @@ It is designed as a better filesystem solution for the following scenarios:
immutable and bit-for-bit identical to the official golden image for
their releases due to security and other considerations and
- - hope to save some extra storage space with guaranteed end-to-end performance
- by using reduced metadata and transparent file compression, especially
- for those embedded devices with limited memory (ex, smartphone);
+ - hope to minimize extra storage space with guaranteed end-to-end performance
+ by using compact layout, transparent file compression and direct access,
+ especially for those embedded devices with limited memory and high-density
+ hosts with numerous containers;
Here is the main features of EROFS:
@@ -51,7 +52,9 @@ Here is the main features of EROFS:
- Support POSIX.1e ACLs by using xattrs;
- Support transparent data compression as an option:
- LZ4 algorithm with the fixed-sized output compression for high performance.
+ LZ4 algorithm with the fixed-sized output compression for high performance;
+
+ - Multiple device support for multi-layer container images.
The following git tree provides the file system user-space tools under
development (ex, formatting tool mkfs.erofs):
@@ -87,6 +90,7 @@ cache_strategy=%s Select a strategy for cached decompression from now on:
dax={always,never} Use direct access (no page cache). See
Documentation/filesystems/dax.rst.
dax A legacy option which is an alias for ``dax=always``.
+device=%s Specify a path to an extra device to be used together.
=================== =========================================================
On-disk details
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index 0eb799d9d05a..4d5d50dca65c 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -77,11 +77,11 @@ Side-channel attacks
fscrypt is only resistant to side-channel attacks, such as timing or
electromagnetic attacks, to the extent that the underlying Linux
-Cryptographic API algorithms are. If a vulnerable algorithm is used,
-such as a table-based implementation of AES, it may be possible for an
-attacker to mount a side channel attack against the online system.
-Side channel attacks may also be mounted against applications
-consuming decrypted data.
+Cryptographic API algorithms or inline encryption hardware are. If a
+vulnerable algorithm is used, such as a table-based implementation of
+AES, it may be possible for an attacker to mount a side channel attack
+against the online system. Side channel attacks may also be mounted
+against applications consuming decrypted data.
Unauthorized file access
~~~~~~~~~~~~~~~~~~~~~~~~
@@ -176,11 +176,11 @@ Master Keys
Each encrypted directory tree is protected by a *master key*. Master
keys can be up to 64 bytes long, and must be at least as long as the
-greater of the key length needed by the contents and filenames
-encryption modes being used. For example, if AES-256-XTS is used for
-contents encryption, the master key must be 64 bytes (512 bits). Note
-that the XTS mode is defined to require a key twice as long as that
-required by the underlying block cipher.
+greater of the security strength of the contents and filenames
+encryption modes being used. For example, if any AES-256 mode is
+used, the master key must be at least 256 bits, i.e. 32 bytes. A
+stricter requirement applies if the key is used by a v1 encryption
+policy and AES-256-XTS is used; such keys must be 64 bytes.
To "unlock" an encrypted directory tree, userspace must provide the
appropriate master key. There can be any number of master keys, each
@@ -1135,6 +1135,50 @@ where applications may later write sensitive data. It is recommended
that systems implementing a form of "verified boot" take advantage of
this by validating all top-level encryption policies prior to access.
+Inline encryption support
+=========================
+
+By default, fscrypt uses the kernel crypto API for all cryptographic
+operations (other than HKDF, which fscrypt partially implements
+itself). The kernel crypto API supports hardware crypto accelerators,
+but only ones that work in the traditional way where all inputs and
+outputs (e.g. plaintexts and ciphertexts) are in memory. fscrypt can
+take advantage of such hardware, but the traditional acceleration
+model isn't particularly efficient and fscrypt hasn't been optimized
+for it.
+
+Instead, many newer systems (especially mobile SoCs) have *inline
+encryption hardware* that can encrypt/decrypt data while it is on its
+way to/from the storage device. Linux supports inline encryption
+through a set of extensions to the block layer called *blk-crypto*.
+blk-crypto allows filesystems to attach encryption contexts to bios
+(I/O requests) to specify how the data will be encrypted or decrypted
+in-line. For more information about blk-crypto, see
+:ref:`Documentation/block/inline-encryption.rst <inline_encryption>`.
+
+On supported filesystems (currently ext4 and f2fs), fscrypt can use
+blk-crypto instead of the kernel crypto API to encrypt/decrypt file
+contents. To enable this, set CONFIG_FS_ENCRYPTION_INLINE_CRYPT=y in
+the kernel configuration, and specify the "inlinecrypt" mount option
+when mounting the filesystem.
+
+Note that the "inlinecrypt" mount option just specifies to use inline
+encryption when possible; it doesn't force its use. fscrypt will
+still fall back to using the kernel crypto API on files where the
+inline encryption hardware doesn't have the needed crypto capabilities
+(e.g. support for the needed encryption algorithm and data unit size)
+and where blk-crypto-fallback is unusable. (For blk-crypto-fallback
+to be usable, it must be enabled in the kernel configuration with
+CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y.)
+
+Currently fscrypt always uses the filesystem block size (which is
+usually 4096 bytes) as the data unit size. Therefore, it can only use
+inline encryption hardware that supports that data unit size.
+
+Inline encryption doesn't affect the ciphertext or other aspects of
+the on-disk format, so users may freely switch back and forth between
+using "inlinecrypt" and not using "inlinecrypt".
+
Implementation details
======================
@@ -1184,6 +1228,13 @@ keys`_ and `DIRECT_KEY policies`_.
Data path changes
-----------------
+When inline encryption is used, filesystems just need to associate
+encryption contexts with bios to specify how the block layer or the
+inline encryption hardware will encrypt/decrypt the file contents.
+
+When inline encryption isn't used, filesystems must encrypt/decrypt
+the file contents themselves, as described below:
+
For the read path (->readpage()) of regular files, filesystems can
read the ciphertext into the page cache and decrypt it in-place. The
page lock must be held until decryption has finished, to prevent the
@@ -1197,18 +1248,6 @@ buffer. Some filesystems, such as UBIFS, already use temporary
buffers regardless of encryption. Other filesystems, such as ext4 and
F2FS, have to allocate bounce pages specially for encryption.
-Fscrypt is also able to use inline encryption hardware instead of the
-kernel crypto API for en/decryption of file contents. When possible,
-and if directed to do so (by specifying the 'inlinecrypt' mount option
-for an ext4/F2FS filesystem), it adds encryption contexts to bios and
-uses blk-crypto to perform the en/decryption instead of making use of
-the above read/write path changes. Of course, even if directed to
-make use of inline encryption, fscrypt will only be able to do so if
-either hardware inline encryption support is available for the
-selected encryption algorithm or CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK
-is selected. If neither is the case, fscrypt will fall back to using
-the above mentioned read/write path changes for en/decryption.
-
Filename hashing and encoding
-----------------------------
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index c0ad233963ae..bee63d42e5ec 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -29,7 +29,6 @@ algorithms work.
fiemap
files
locks
- mandatory-locking
mount_api
quota
seq_file
diff --git a/Documentation/filesystems/locks.rst b/Documentation/filesystems/locks.rst
index c5ae858b1aac..26429317dbbc 100644
--- a/Documentation/filesystems/locks.rst
+++ b/Documentation/filesystems/locks.rst
@@ -57,16 +57,9 @@ fcntl(), with all the problems that implies.
1.3 Mandatory Locking As A Mount Option
---------------------------------------
-Mandatory locking, as described in
-'Documentation/filesystems/mandatory-locking.rst' was prior to this release a
-general configuration option that was valid for all mounted filesystems. This
-had a number of inherent dangers, not the least of which was the ability to
-freeze an NFS server by asking it to read a file for which a mandatory lock
-existed.
-
-From this release of the kernel, mandatory locking can be turned on and off
-on a per-filesystem basis, using the mount options 'mand' and 'nomand'.
-The default is to disallow mandatory locking. The intention is that
-mandatory locking only be enabled on a local filesystem as the specific need
-arises.
+Mandatory locking was prior to this release a general configuration option
+that was valid for all mounted filesystems. This had a number of inherent
+dangers, not the least of which was the ability to freeze an NFS server by
+asking it to read a file for which a mandatory lock existed.
+Such option was dropped in Kernel v5.14.
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 57a641847818..bb68d39f03b7 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -524,3 +524,5 @@ Note that these methods are passed a pointer to the cache resource structure,
not the read request structure as they could be used in other situations where
there isn't a read request structure as well, such as writing dirty data to the
cache.
+
+.. kernel-doc:: include/linux/netfs.h
diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst
index 3b4c0506de46..682948fc88a3 100644
--- a/Documentation/userspace-api/ioctl/cdrom.rst
+++ b/Documentation/userspace-api/ioctl/cdrom.rst
@@ -13,61 +13,64 @@ in drivers/cdrom/cdrom.c and drivers/block/scsi_ioctl.c
ioctl values are listed in <linux/cdrom.h>. As of this writing, they
are as follows:
- ====================== ===============================================
- CDROMPAUSE Pause Audio Operation
- CDROMRESUME Resume paused Audio Operation
- CDROMPLAYMSF Play Audio MSF (struct cdrom_msf)
- CDROMPLAYTRKIND Play Audio Track/index (struct cdrom_ti)
- CDROMREADTOCHDR Read TOC header (struct cdrom_tochdr)
- CDROMREADTOCENTRY Read TOC entry (struct cdrom_tocentry)
- CDROMSTOP Stop the cdrom drive
- CDROMSTART Start the cdrom drive
- CDROMEJECT Ejects the cdrom media
- CDROMVOLCTRL Control output volume (struct cdrom_volctrl)
- CDROMSUBCHNL Read subchannel data (struct cdrom_subchnl)
- CDROMREADMODE2 Read CDROM mode 2 data (2336 Bytes)
- (struct cdrom_read)
- CDROMREADMODE1 Read CDROM mode 1 data (2048 Bytes)
- (struct cdrom_read)
- CDROMREADAUDIO (struct cdrom_read_audio)
- CDROMEJECT_SW enable(1)/disable(0) auto-ejecting
- CDROMMULTISESSION Obtain the start-of-last-session
- address of multi session disks
- (struct cdrom_multisession)
- CDROM_GET_MCN Obtain the "Universal Product Code"
- if available (struct cdrom_mcn)
- CDROM_GET_UPC Deprecated, use CDROM_GET_MCN instead.
- CDROMRESET hard-reset the drive
- CDROMVOLREAD Get the drive's volume setting
- (struct cdrom_volctrl)
- CDROMREADRAW read data in raw mode (2352 Bytes)
- (struct cdrom_read)
- CDROMREADCOOKED read data in cooked mode
- CDROMSEEK seek msf address
- CDROMPLAYBLK scsi-cd only, (struct cdrom_blk)
- CDROMREADALL read all 2646 bytes
- CDROMGETSPINDOWN return 4-bit spindown value
- CDROMSETSPINDOWN set 4-bit spindown value
- CDROMCLOSETRAY pendant of CDROMEJECT
- CDROM_SET_OPTIONS Set behavior options
- CDROM_CLEAR_OPTIONS Clear behavior options
- CDROM_SELECT_SPEED Set the CD-ROM speed
- CDROM_SELECT_DISC Select disc (for juke-boxes)
- CDROM_MEDIA_CHANGED Check is media changed
- CDROM_DRIVE_STATUS Get tray position, etc.
- CDROM_DISC_STATUS Get disc type, etc.
- CDROM_CHANGER_NSLOTS Get number of slots
- CDROM_LOCKDOOR lock or unlock door
- CDROM_DEBUG Turn debug messages on/off
- CDROM_GET_CAPABILITY get capabilities
- CDROMAUDIOBUFSIZ set the audio buffer size
- DVD_READ_STRUCT Read structure
- DVD_WRITE_STRUCT Write structure
- DVD_AUTH Authentication
- CDROM_SEND_PACKET send a packet to the drive
- CDROM_NEXT_WRITABLE get next writable block
- CDROM_LAST_WRITTEN get last block written on disc
- ====================== ===============================================
+ ======================== ===============================================
+ CDROMPAUSE Pause Audio Operation
+ CDROMRESUME Resume paused Audio Operation
+ CDROMPLAYMSF Play Audio MSF (struct cdrom_msf)
+ CDROMPLAYTRKIND Play Audio Track/index (struct cdrom_ti)
+ CDROMREADTOCHDR Read TOC header (struct cdrom_tochdr)
+ CDROMREADTOCENTRY Read TOC entry (struct cdrom_tocentry)
+ CDROMSTOP Stop the cdrom drive
+ CDROMSTART Start the cdrom drive
+ CDROMEJECT Ejects the cdrom media
+ CDROMVOLCTRL Control output volume (struct cdrom_volctrl)
+ CDROMSUBCHNL Read subchannel data (struct cdrom_subchnl)
+ CDROMREADMODE2 Read CDROM mode 2 data (2336 Bytes)
+ (struct cdrom_read)
+ CDROMREADMODE1 Read CDROM mode 1 data (2048 Bytes)
+ (struct cdrom_read)
+ CDROMREADAUDIO (struct cdrom_read_audio)
+ CDROMEJECT_SW enable(1)/disable(0) auto-ejecting
+ CDROMMULTISESSION Obtain the start-of-last-session
+ address of multi session disks
+ (struct cdrom_multisession)
+ CDROM_GET_MCN Obtain the "Universal Product Code"
+ if available (struct cdrom_mcn)
+ CDROM_GET_UPC Deprecated, use CDROM_GET_MCN instead.
+ CDROMRESET hard-reset the drive
+ CDROMVOLREAD Get the drive's volume setting
+ (struct cdrom_volctrl)
+ CDROMREADRAW read data in raw mode (2352 Bytes)
+ (struct cdrom_read)
+ CDROMREADCOOKED read data in cooked mode
+ CDROMSEEK seek msf address
+ CDROMPLAYBLK scsi-cd only, (struct cdrom_blk)
+ CDROMREADALL read all 2646 bytes
+ CDROMGETSPINDOWN return 4-bit spindown value
+ CDROMSETSPINDOWN set 4-bit spindown value
+ CDROMCLOSETRAY pendant of CDROMEJECT
+ CDROM_SET_OPTIONS Set behavior options
+ CDROM_CLEAR_OPTIONS Clear behavior options
+ CDROM_SELECT_SPEED Set the CD-ROM speed
+ CDROM_SELECT_DISC Select disc (for juke-boxes)
+ CDROM_MEDIA_CHANGED Check is media changed
+ CDROM_TIMED_MEDIA_CHANGE Check if media changed
+ since given time
+ (struct cdrom_timed_media_change_info)
+ CDROM_DRIVE_STATUS Get tray position, etc.
+ CDROM_DISC_STATUS Get disc type, etc.
+ CDROM_CHANGER_NSLOTS Get number of slots
+ CDROM_LOCKDOOR lock or unlock door
+ CDROM_DEBUG Turn debug messages on/off
+ CDROM_GET_CAPABILITY get capabilities
+ CDROMAUDIOBUFSIZ set the audio buffer size
+ DVD_READ_STRUCT Read structure
+ DVD_WRITE_STRUCT Write structure
+ DVD_AUTH Authentication
+ CDROM_SEND_PACKET send a packet to the drive
+ CDROM_NEXT_WRITABLE get next writable block
+ CDROM_LAST_WRITTEN get last block written on disc
+ ======================== ===============================================
The information that follows was determined from reading kernel source
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2e8134059c87..6655d929a351 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -104,6 +104,7 @@ Code Seq# Include File Comments
'8' all SNP8023 advanced NIC card
<mailto:mcr@solidum.com>
';' 64-7F linux/vfio.h
+'=' 00-3f uapi/linux/ptp_clock.h <mailto:richardcochran@gmail.com>
'@' 00-0F linux/radeonfb.h conflict!
'@' 00-0F drivers/video/aty/aty128fb.c conflict!
'A' 00-1F linux/apm_bios.h conflict!
diff --git a/MAINTAINERS b/MAINTAINERS
index f26920f0fa65..3b79fd441dde 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5458,6 +5458,19 @@ F: include/net/devlink.h
F: include/uapi/linux/devlink.h
F: net/core/devlink.c
+DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT
+M: Christoph Niedermaier <cniedermaier@dh-electronics.com>
+L: kernel@dh-electronics.com
+S: Maintained
+F: arch/arm/boot/dts/imx6*-dhcom-*
+
+DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT
+M: Marek Vasut <marex@denx.de>
+L: kernel@dh-electronics.com
+S: Maintained
+F: arch/arm/boot/dts/stm32mp1*-dhcom-*
+F: arch/arm/boot/dts/stm32mp1*-dhcor-*
+
DIALOG SEMICONDUCTOR DRIVERS
M: Support Opensource <support.opensource@diasemi.com>
S: Supported
@@ -6147,8 +6160,7 @@ T: git git://anongit.freedesktop.org/drm/drm
F: Documentation/devicetree/bindings/display/
F: Documentation/devicetree/bindings/gpu/
F: Documentation/gpu/
-F: drivers/gpu/drm/
-F: drivers/gpu/vga/
+F: drivers/gpu/
F: include/drm/
F: include/linux/vga*
F: include/uapi/drm/
@@ -11278,7 +11290,6 @@ F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
F: drivers/net/ethernet/marvell/octeontx2/af/
MARVELL PRESTERA ETHERNET SWITCH DRIVER
-M: Vadym Kochan <vkochan@marvell.com>
M: Taras Chornyi <tchornyi@marvell.com>
S: Supported
W: https://github.com/Marvell-switching/switchdev-prestera
diff --git a/Makefile b/Makefile
index 30c7c81d0437..a5231635ed43 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
VERSION = 5
PATCHLEVEL = 15
SUBLEVEL = 0
-EXTRAVERSION = -rc7
-NAME = Opossums on Parade
+EXTRAVERSION =
+NAME = Trick or Treat
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
@@ -1115,7 +1115,8 @@ export MODORDER := $(extmod_prefix)modules.order
export MODULES_NSDEPS := $(extmod_prefix)modules.nsdeps
ifeq ($(KBUILD_EXTMOD),)
-core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
+core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/
+core-$(CONFIG_BLOCK) += block/
vmlinux-dirs := $(patsubst %/,%,$(filter %/, \
$(core-y) $(core-m) $(drivers-y) $(drivers-m) \
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index e201b4b1655a..e8c2c7469e10 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -36,6 +36,7 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
void dma_cache_inv(phys_addr_t start, unsigned long sz);
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
index 8077f1716fbc..ecb91fb899ff 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
@@ -112,7 +112,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 5e56288e343b..e68fb879e4f9 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -290,6 +290,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
*/
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *folio);
#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
static inline void flush_kernel_vmap_range(void *addr, int size)
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
index 02f8e72f0cad..05486cccee1c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
@@ -75,7 +75,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <&reg_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
index d17abb515835..e99e7644ff39 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
@@ -70,7 +70,9 @@
regulator-name = "rst-usb-eth2";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb_eth2>;
- gpio = <&gpio3 2 GPIO_ACTIVE_LOW>;
+ gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ regulator-always-on;
};
reg_vdd_5v: regulator-5v {
@@ -95,7 +97,7 @@
clocks = <&osc_can>;
interrupt-parent = <&gpio4>;
interrupts = <28 IRQ_TYPE_EDGE_FALLING>;
- spi-max-frequency = <100000>;
+ spi-max-frequency = <10000000>;
vdd-supply = <&reg_vdd_3v3>;
xceiver-supply = <&reg_vdd_5v>;
};
@@ -111,7 +113,7 @@
&fec1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_enet>;
- phy-connection-type = "rgmii";
+ phy-connection-type = "rgmii-rxid";
phy-handle = <&ethphy>;
status = "okay";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
index 9db9b90bf2bc..42bbbb3f532b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
@@ -91,10 +91,12 @@
reg_vdd_soc: BUCK1 {
regulator-name = "buck1";
regulator-min-microvolt = <800000>;
- regulator-max-microvolt = <900000>;
+ regulator-max-microvolt = <850000>;
regulator-boot-on;
regulator-always-on;
regulator-ramp-delay = <3125>;
+ nxp,dvs-run-voltage = <850000>;
+ nxp,dvs-standby-voltage = <800000>;
};
reg_vdd_arm: BUCK2 {
@@ -111,7 +113,7 @@
reg_vdd_dram: BUCK3 {
regulator-name = "buck3";
regulator-min-microvolt = <850000>;
- regulator-max-microvolt = <900000>;
+ regulator-max-microvolt = <950000>;
regulator-boot-on;
regulator-always-on;
};
@@ -150,7 +152,7 @@
reg_vdd_snvs: LDO2 {
regulator-name = "ldo2";
- regulator-min-microvolt = <850000>;
+ regulator-min-microvolt = <800000>;
regulator-max-microvolt = <900000>;
regulator-boot-on;
regulator-always-on;
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index 8c15d9fed08f..d12e4cbfc852 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -2590,9 +2590,10 @@
power-domains = <&dispcc MDSS_GDSC>;
clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+ <&gcc GCC_DISP_HF_AXI_CLK>,
<&gcc GCC_DISP_SF_AXI_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>;
- clock-names = "iface", "nrt_bus", "core";
+ clock-names = "iface", "bus", "nrt_bus", "core";
assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>;
assigned-clock-rates = <460000000>;
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 41c23f474ea6..803e7773fa86 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1136,6 +1136,11 @@ out:
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 9a8394e96388..9c57b245dc12 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -58,7 +58,7 @@ struct nfhd_device {
struct gendisk *disk;
};
-static blk_qc_t nfhd_submit_bio(struct bio *bio)
+static void nfhd_submit_bio(struct bio *bio)
{
struct nfhd_device *dev = bio->bi_bdev->bd_disk->private_data;
struct bio_vec bvec;
@@ -76,7 +76,6 @@ static blk_qc_t nfhd_submit_bio(struct bio *bio)
sec += len;
}
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
@@ -100,6 +99,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
{
struct nfhd_device *dev;
int dev_id = id - NFHD_DEV_OFFSET;
+ int err = -ENOMEM;
pr_info("nfhd%u: found device with %u blocks (%u bytes)\n", dev_id,
blocks, bsize);
@@ -130,16 +130,20 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
sprintf(dev->disk->disk_name, "nfhd%u", dev_id);
set_capacity(dev->disk, (sector_t)blocks * (bsize / 512));
blk_queue_logical_block_size(dev->disk->queue, bsize);
- add_disk(dev->disk);
+ err = add_disk(dev->disk);
+ if (err)
+ goto out_cleanup_disk;
list_add_tail(&dev->list, &nfhd_list);
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(dev->disk);
free_dev:
kfree(dev);
out:
- return -ENOMEM;
+ return err;
}
static int __init nfhd_init(void)
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index 1ac55e7b47f0..8ab46625ddd3 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -250,6 +250,7 @@ static inline void __flush_page_to_ram(void *vaddr)
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
#define flush_dcache_page(page) __flush_page_to_ram(page_address(page))
+void flush_dcache_folio(struct folio *folio);
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
#define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page))
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index b3dc9c589442..f207388541d5 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -61,6 +61,8 @@ static inline void flush_dcache_page(struct page *page)
SetPageDcacheDirty(page);
}
+void flush_dcache_folio(struct folio *folio);
+
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
diff --git a/arch/mips/rb532/prom.c b/arch/mips/rb532/prom.c
index 23ad8dd9aa5e..b11693715547 100644
--- a/arch/mips/rb532/prom.c
+++ b/arch/mips/rb532/prom.c
@@ -16,7 +16,6 @@
#include <linux/console.h>
#include <linux/memblock.h>
#include <linux/ioport.h>
-#include <linux/blkdev.h>
#include <asm/bootinfo.h>
#include <asm/mach-rc32434/ddr.h>
diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c
index a3323f8dcc1b..1a504294d85f 100644
--- a/arch/mips/sibyte/common/cfe.c
+++ b/arch/mips/sibyte/common/cfe.c
@@ -7,7 +7,6 @@
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/mm.h>
-#include <linux/blkdev.h>
#include <linux/memblock.h>
#include <linux/pm.h>
#include <linux/smp.h>
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index 538a2791b48c..f07b15dd1c1a 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -11,7 +11,6 @@
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/memblock.h>
-#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/screen_info.h>
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index c2a222ebfa2a..3fc0bb7d6487 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -27,6 +27,7 @@ void flush_cache_vunmap(unsigned long start, unsigned long end);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long vaddr, void *dst, void *src, int len);
void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 0e23e3a8df6b..d55b73b18149 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -6,7 +6,7 @@
#ifndef CONFIG_DYNAMIC_FTRACE
extern void (*ftrace_trace_function)(unsigned long, unsigned long,
- struct ftrace_ops*, struct pt_regs*);
+ struct ftrace_ops*, struct ftrace_regs*);
extern void ftrace_graph_caller(void);
noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 18eb9f69f806..1999561b22aa 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -28,7 +28,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
unsigned long pfn);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);
diff --git a/arch/nios2/platform/Kconfig.platform b/arch/nios2/platform/Kconfig.platform
index 9e32fb7f3d4c..e849daff6fd1 100644
--- a/arch/nios2/platform/Kconfig.platform
+++ b/arch/nios2/platform/Kconfig.platform
@@ -37,6 +37,7 @@ config NIOS2_DTB_PHYS_ADDR
config NIOS2_DTB_SOURCE_BOOL
bool "Compile and link device tree into kernel image"
+ depends on !COMPILE_TEST
help
This allows you to specify a dts (device tree source) file
which will be compiled and linked into the kernel image.
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index cfef61a7b6c2..97305bde1b16 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -25,7 +25,6 @@
#include <linux/memblock.h>
#include <linux/init.h>
#include <linux/delay.h>
-#include <linux/blkdev.h> /* for initrd_* */
#include <linux/pagemap.h>
#include <asm/pgalloc.h>
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index eef0096db5f8..da0cd4b3a28f 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -49,7 +49,8 @@ void invalidate_kernel_vmap_range(void *vaddr, int size);
#define flush_cache_vunmap(start, end) flush_cache_all()
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages)
#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages)
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index bed05b644c2c..cb25acccd746 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -21,6 +21,7 @@
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/poll.h>
+#include <linux/seq_file.h>
#include <linux/slab.h>
#include <asm/prom.h>
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index dab5c56ffd0e..a52af8fbf571 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1302,6 +1302,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
struct property *default_win;
int reset_win_ext;
+ /* DDW + IOMMU on single window may fail if there is any allocation */
+ if (iommu_table_in_use(tbl)) {
+ dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
+ goto out_failed;
+ }
+
default_win = of_find_property(pdn, "ibm,dma-window", NULL);
if (!default_win)
goto out_failed;
@@ -1356,12 +1362,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
query.largest_available_block,
1ULL << page_shift);
- /* DDW + IOMMU on single window may fail if there is any allocation */
- if (default_win_removed && iommu_table_in_use(tbl)) {
- dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
- goto out_failed;
- }
-
len = order_base_2(query.largest_available_block << page_shift);
win_name = DMA64_PROPNAME;
} else {
@@ -1411,18 +1411,19 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
} else {
struct iommu_table *newtbl;
int i;
+ unsigned long start = 0, end = 0;
for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
/* Look for MMIO32 */
- if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM)
+ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+ start = pci->phb->mem_resources[i].start;
+ end = pci->phb->mem_resources[i].end;
break;
+ }
}
- if (i == ARRAY_SIZE(pci->phb->mem_resources))
- goto out_del_list;
-
/* New table for using DDW instead of the default DMA window */
newtbl = iommu_pseries_alloc_table(pci->phb->node);
if (!newtbl) {
@@ -1432,15 +1433,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
- iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start,
- pci->phb->mem_resources[i].end);
+ iommu_init_table(newtbl, pci->phb->node, start, end);
pci->table_group->tables[1] = newtbl;
/* Keep default DMA window stuct if removed */
if (default_win_removed) {
tbl->it_size = 0;
- kfree(tbl->it_map);
+ vfree(tbl->it_map);
+ tbl->it_map = NULL;
}
set_iommu_table_base(&dev->dev, newtbl);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 6a6fa9e976d5..f076cee11af6 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -163,6 +163,12 @@ config PAGE_OFFSET
default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
+config KASAN_SHADOW_OFFSET
+ hex
+ depends on KASAN_GENERIC
+ default 0xdfffffc800000000 if 64BIT
+ default 0xffffffff if 32BIT
+
config ARCH_FLATMEM_ENABLE
def_bool !NUMA
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
index a2b3d9cdbc86..b00f503ec124 100644
--- a/arch/riscv/include/asm/kasan.h
+++ b/arch/riscv/include/asm/kasan.h
@@ -30,8 +30,7 @@
#define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
#define KASAN_SHADOW_START KERN_VIRT_START
#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
-#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \
- (64 - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
void kasan_init(void);
asmlinkage void kasan_early_init(void);
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index fce5184b22c3..52c5ff9804c5 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -193,6 +193,7 @@ setup_trap_vector:
csrw CSR_SCRATCH, zero
ret
+.align 2
.Lsecondary_park:
/* We lack SMP support or have too many harts, so park this hart */
wfi
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index d7189c8714a9..54294f83513d 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -17,6 +17,9 @@ asmlinkage void __init kasan_early_init(void)
uintptr_t i;
pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+ KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
for (i = 0; i < PTRS_PER_PTE; ++i)
set_pte(kasan_early_shadow_pte + i,
mk_pte(virt_to_page(kasan_early_shadow_page),
@@ -172,21 +175,10 @@ void __init kasan_init(void)
phys_addr_t p_start, p_end;
u64 i;
- /*
- * Populate all kernel virtual address space with kasan_early_shadow_page
- * except for the linear mapping and the modules/kernel/BPF mapping.
- */
- kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
- (void *)kasan_mem_to_shadow((void *)
- VMEMMAP_END));
if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
kasan_shallow_populate(
(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
- else
- kasan_populate_early_shadow(
- (void *)kasan_mem_to_shadow((void *)VMALLOC_START),
- (void *)kasan_mem_to_shadow((void *)VMALLOC_END));
/* Populate the linear mapping */
for_each_mem_range(i, &p_start, &p_end) {
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index fed86f42dfbe..753d85bdfad0 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
if (i == NR_JIT_ITERATIONS) {
pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
- bpf_jit_binary_free(jit_data->header);
+ if (jit_data->header)
+ bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
@@ -166,6 +167,11 @@ out:
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 10722455fd02..2245f4b8d362 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_vcpu *vcpu;
+ u8 vcpu_isc_mask;
for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
vcpu = kvm_get_vcpu(kvm, vcpu_idx);
if (psw_ioint_disabled(vcpu))
continue;
- deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
- if (deliverable_mask) {
+ vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+ if (deliverable_mask & vcpu_isc_mask) {
/* lately kicked but not yet running */
if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
return;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6a6dd5e1daf6..1c97493d21e1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3363,6 +3363,7 @@ out_free_sie_block:
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
+ clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
return kvm_s390_vcpu_has_irq(vcpu, 0);
}
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 372afa82fee6..c7a97f32432f 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -42,7 +42,8 @@ extern void flush_cache_page(struct vm_area_struct *vma,
extern void flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
extern void flush_icache_range(unsigned long start, unsigned long end);
#define flush_icache_user_range flush_icache_range
extern void flush_icache_page(struct vm_area_struct *vma,
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index cd9dc0556e91..69d2d0049a61 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -27,6 +27,7 @@
#include <linux/blk-mq.h>
#include <linux/ata.h>
#include <linux/hdreg.h>
+#include <linux/major.h>
#include <linux/cdrom.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
@@ -854,8 +855,8 @@ static const struct attribute_group *ubd_attr_groups[] = {
NULL,
};
-static void ubd_disk_register(int major, u64 size, int unit,
- struct gendisk *disk)
+static int ubd_disk_register(int major, u64 size, int unit,
+ struct gendisk *disk)
{
disk->major = major;
disk->first_minor = unit << UBD_SHIFT;
@@ -872,7 +873,7 @@ static void ubd_disk_register(int major, u64 size, int unit,
disk->private_data = &ubd_devs[unit];
disk->queue = ubd_devs[unit].queue;
- device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
+ return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
}
#define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE))
@@ -919,10 +920,15 @@ static int ubd_add(int n, char **error_out)
blk_queue_write_cache(ubd_dev->queue, true, false);
blk_queue_max_segments(ubd_dev->queue, MAX_SG);
blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1);
- ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+ err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+ if (err)
+ goto out_cleanup_disk;
+
ubd_gendisk[n] = disk;
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_cleanup_tags:
blk_mq_free_tag_set(&ubd_dev->tag_set);
out:
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index 18d2f5199194..1cc72b4804fa 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -78,7 +78,7 @@
vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164
+.section .rodata.cst16, "aM", @progbits, 16
.align 16
/*
@@ -133,6 +133,10 @@
.L0f0f0f0f:
.long 0x0f0f0f0f
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
.text
.align 16
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
index d2ffd7f76ee2..9c5d3f3ad45a 100644
--- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -93,7 +93,7 @@
vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164
+.section .rodata.cst16, "aM", @progbits, 16
.align 16
/*
@@ -148,6 +148,10 @@
.L0f0f0f0f:
.long 0x0f0f0f0f
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
.text
.align 16
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5a0298aa56ba..13f64654dfff 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1098,7 +1098,7 @@ struct kvm_arch {
u64 cur_tsc_generation;
int nr_vcpus_matched_tsc;
- spinlock_t pvclock_gtod_sync_lock;
+ raw_spinlock_t pvclock_gtod_sync_lock;
bool use_master_clock;
u64 master_kernel_ns;
u64 master_cycle_now;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 2e4916be290e..7e34d7163ada 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2591,11 +2591,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
{
- if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+ int count;
+ int bytes;
+
+ if (svm->vmcb->control.exit_info_2 > INT_MAX)
+ return -EINVAL;
+
+ count = svm->vmcb->control.exit_info_2;
+ if (unlikely(check_mul_overflow(count, size, &bytes)))
+ return -EINVAL;
+
+ if (!setup_vmgexit_scratch(svm, in, bytes))
return -EINVAL;
- return kvm_sev_es_string_io(&svm->vcpu, size, port,
- svm->ghcb_sa, svm->ghcb_sa_len / size, in);
+ return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
}
void sev_es_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b26647a5ea22..bfe0de3008a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2542,7 +2542,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
- spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
if (!matched) {
kvm->arch.nr_vcpus_matched_tsc = 0;
} else if (!already_matched) {
@@ -2550,7 +2550,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
}
kvm_track_tsc_matching(vcpu);
- spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2780,9 +2780,9 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
kvm_make_mclock_inprogress_request(kvm);
/* no guest entries from this point */
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2800,15 +2800,15 @@ u64 get_kvmclock_ns(struct kvm *kvm)
unsigned long flags;
u64 ret;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
if (!ka->use_master_clock) {
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
return get_kvmclock_base_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
@@ -2902,13 +2902,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
*/
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
use_master_clock = ka->use_master_clock;
if (use_master_clock) {
host_tsc = ka->master_cycle_now;
kernel_ns = ka->master_kernel_ns;
}
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
@@ -6100,13 +6100,13 @@ set_pit2_out:
* is slightly ahead) here we risk going negative on unsigned
* 'system_time' when 'user_ns.clock' is very small.
*/
- spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock);
if (kvm->arch.use_master_clock)
now_ns = ka->master_kernel_ns;
else
now_ns = get_kvmclock_base_ns();
ka->kvmclock_offset = user_ns.clock - now_ns;
- spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
break;
@@ -8156,9 +8156,9 @@ static void kvm_hyperv_tsc_notifier(void)
list_for_each_entry(kvm, &vm_list, vm_list) {
struct kvm_arch *ka = &kvm->arch;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -8800,9 +8800,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
+
+ /*
+ * The call to kvm_ready_for_interrupt_injection() may end up in
+ * kvm_xen_has_interrupt() which may require the srcu lock to be
+ * held, to protect against changes in the vcpu_info address.
+ */
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_run->ready_for_interrupt_injection =
pic_in_kernel(vcpu->kvm) ||
kvm_vcpu_ready_for_interrupt_injection(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (is_smm(vcpu))
kvm_run->flags |= KVM_RUN_X86_SMM;
@@ -11199,7 +11207,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
mutex_init(&kvm->arch.apic_map_lock);
- spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+ raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
pvclock_update_vm_gtod_copy(kvm);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9ea9c3dabe37..8f62baebd028 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
{
+ int err;
u8 rc = 0;
/*
@@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
if (likely(slots->generation == ghc->generation &&
!kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
/* Fast path */
- __get_user(rc, (u8 __user *)ghc->hva + offset);
- } else {
- /* Slow path */
- kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
- sizeof(rc));
+ pagefault_disable();
+ err = __get_user(rc, (u8 __user *)ghc->hva + offset);
+ pagefault_enable();
+ if (!err)
+ return rc;
}
+ /* Slow path */
+
+ /*
+ * This function gets called from kvm_vcpu_block() after setting the
+ * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
+ * from a HLT. So we really mustn't sleep. If the page ended up absent
+ * at that point, just return 1 in order to trigger an immediate wake,
+ * and we'll end up getting called again from a context where we *can*
+ * fault in the page and wait for it.
+ */
+ if (in_atomic() || !task_is_running(current))
+ return 1;
+
+ kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+ sizeof(rc));
+
return rc;
}
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index cf907e5bf2f2..a8a041609c5d 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -120,7 +120,8 @@ void flush_cache_page(struct vm_area_struct*,
#define flush_cache_vunmap(start,end) flush_cache_all()
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page*);
+void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *);
void local_flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
@@ -137,7 +138,9 @@ void local_flush_cache_page(struct vm_area_struct *vma,
#define flush_cache_vunmap(start,end) do { } while (0)
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
#define flush_dcache_page(page) do { } while (0)
+static inline void flush_dcache_folio(struct folio *folio) { }
#define flush_icache_range local_flush_icache_range
#define flush_cache_page(vma, addr, pfn) do { } while (0)
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 3cdfa00738e0..07b642c1916a 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -100,7 +100,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
spin_unlock(&dev->lock);
}
-static blk_qc_t simdisk_submit_bio(struct bio *bio)
+static void simdisk_submit_bio(struct bio *bio)
{
struct simdisk *dev = bio->bi_bdev->bd_disk->private_data;
struct bio_vec bvec;
@@ -118,7 +118,6 @@ static blk_qc_t simdisk_submit_bio(struct bio *bio)
}
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int simdisk_open(struct block_device *bdev, fmode_t mode)
@@ -259,6 +258,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
struct proc_dir_entry *procdir)
{
char tmp[2] = { '0' + which, 0 };
+ int err = -ENOMEM;
dev->fd = -1;
dev->filename = NULL;
@@ -267,7 +267,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
dev->gd = blk_alloc_disk(NUMA_NO_NODE);
if (!dev->gd)
- return -ENOMEM;
+ goto out;
dev->gd->major = simdisk_major;
dev->gd->first_minor = which;
dev->gd->minors = SIMDISK_MINORS;
@@ -275,10 +275,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
dev->gd->private_data = dev;
snprintf(dev->gd->disk_name, 32, "simdisk%d", which);
set_capacity(dev->gd, 0);
- add_disk(dev->gd);
+ err = add_disk(dev->gd);
+ if (err)
+ goto out_cleanup_disk;
dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev);
+
return 0;
+
+out_cleanup_disk:
+ blk_cleanup_disk(dev->gd);
+out:
+ return err;
}
static int __init simdisk_init(void)
diff --git a/block/Kconfig b/block/Kconfig
index 8e28ae7718bd..c6ce41a5e5b2 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -73,7 +73,7 @@ config BLK_DEV_ZONED
config BLK_DEV_THROTTLING
bool "Block layer bio throttling support"
- depends on BLK_CGROUP=y
+ depends on BLK_CGROUP
select BLK_CGROUP_RWSTAT
help
Block layer bio throttling support. It can be used to limit
@@ -112,7 +112,7 @@ config BLK_WBT_MQ
config BLK_CGROUP_IOLATENCY
bool "Enable support for latency based cgroup IO protection"
- depends on BLK_CGROUP=y
+ depends on BLK_CGROUP
help
Enabling this option enables the .latency interface for IO throttling.
The IO controller will attempt to maintain average IO latencies below
@@ -132,7 +132,7 @@ config BLK_CGROUP_FC_APPID
config BLK_CGROUP_IOCOST
bool "Enable support for cost model based cgroup IO controller"
- depends on BLK_CGROUP=y
+ depends on BLK_CGROUP
select BLK_RQ_IO_DATA_LEN
select BLK_RQ_ALLOC_TIME
help
@@ -190,39 +190,31 @@ config BLK_INLINE_ENCRYPTION_FALLBACK
by falling back to the kernel crypto API when inline
encryption hardware is not present.
-menu "Partition Types"
-
source "block/partitions/Kconfig"
-endmenu
-
-endif # BLOCK
-
config BLOCK_COMPAT
- bool
- depends on BLOCK && COMPAT
- default y
+ def_bool COMPAT
config BLK_MQ_PCI
- bool
- depends on BLOCK && PCI
- default y
+ def_bool PCI
config BLK_MQ_VIRTIO
bool
- depends on BLOCK && VIRTIO
+ depends on VIRTIO
default y
config BLK_MQ_RDMA
bool
- depends on BLOCK && INFINIBAND
+ depends on INFINIBAND
default y
config BLK_PM
- def_bool BLOCK && PM
+ def_bool PM
# do not use in new code
config BLOCK_HOLDER_DEPRECATED
bool
source "block/Kconfig.iosched"
+
+endif # BLOCK
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 2f2158e05a91..885fee86dfca 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -1,6 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
-if BLOCK
-
menu "IO Schedulers"
config MQ_IOSCHED_DEADLINE
@@ -45,5 +43,3 @@ config BFQ_CGROUP_DEBUG
files in a cgroup which can be useful for debugging.
endmenu
-
-endif
diff --git a/block/Makefile b/block/Makefile
index 41aa1ba69c90..44df57e562bf 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -3,13 +3,13 @@
# Makefile for the kernel block layer
#
-obj-$(CONFIG_BLOCK) := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
+obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
- disk-events.o
+ disk-events.o blk-ia-ranges.o
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o
@@ -36,6 +36,6 @@ obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o
obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o
obj-$(CONFIG_BLK_PM) += blk-pm.o
-obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o blk-crypto.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += blk-crypto.o blk-crypto-profile.o
obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o
obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED) += holder.o
diff --git a/block/bdev.c b/block/bdev.c
index 485a258b0ab3..b4dab2fb6a74 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -12,6 +12,7 @@
#include <linux/major.h>
#include <linux/device_cgroup.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
@@ -184,14 +185,13 @@ int sb_min_blocksize(struct super_block *sb, int size)
EXPORT_SYMBOL(sb_min_blocksize);
-int __sync_blockdev(struct block_device *bdev, int wait)
+int sync_blockdev_nowait(struct block_device *bdev)
{
if (!bdev)
return 0;
- if (!wait)
- return filemap_flush(bdev->bd_inode->i_mapping);
- return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+ return filemap_flush(bdev->bd_inode->i_mapping);
}
+EXPORT_SYMBOL_GPL(sync_blockdev_nowait);
/*
* Write out and wait upon all the dirty data associated with a block
@@ -199,7 +199,9 @@ int __sync_blockdev(struct block_device *bdev, int wait)
*/
int sync_blockdev(struct block_device *bdev)
{
- return __sync_blockdev(bdev, 1);
+ if (!bdev)
+ return 0;
+ return filemap_write_and_wait(bdev->bd_inode->i_mapping);
}
EXPORT_SYMBOL(sync_blockdev);
@@ -326,12 +328,12 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
if (!ops->rw_page || bdev_get_integrity(bdev))
return result;
- result = blk_queue_enter(bdev->bd_disk->queue, 0);
+ result = blk_queue_enter(bdev_get_queue(bdev), 0);
if (result)
return result;
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
REQ_OP_READ);
- blk_queue_exit(bdev->bd_disk->queue);
+ blk_queue_exit(bdev_get_queue(bdev));
return result;
}
@@ -362,7 +364,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
if (!ops->rw_page || bdev_get_integrity(bdev))
return -EOPNOTSUPP;
- result = blk_queue_enter(bdev->bd_disk->queue, 0);
+ result = blk_queue_enter(bdev_get_queue(bdev), 0);
if (result)
return result;
@@ -375,7 +377,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
clean_page_buffers(page);
unlock_page(page);
}
- blk_queue_exit(bdev->bd_disk->queue);
+ blk_queue_exit(bdev_get_queue(bdev));
return result;
}
@@ -492,6 +494,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
spin_lock_init(&bdev->bd_size_lock);
bdev->bd_partno = partno;
bdev->bd_inode = inode;
+ bdev->bd_queue = disk->queue;
bdev->bd_stats = alloc_percpu(struct disk_stats);
if (!bdev->bd_stats) {
iput(inode);
@@ -962,9 +965,11 @@ EXPORT_SYMBOL(blkdev_put);
* @pathname: special file representing the block device
* @dev: return value of the block device's dev_t
*
- * Get a reference to the blockdevice at @pathname in the current
- * namespace if possible and return it. Return ERR_PTR(error)
- * otherwise.
+ * Lookup the block device's dev_t at @pathname in the current
+ * namespace if possible and return it by @dev.
+ *
+ * RETURNS:
+ * 0 if succeeded, errno otherwise.
*/
int lookup_bdev(const char *pathname, dev_t *dev)
{
@@ -1016,7 +1021,7 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty)
}
EXPORT_SYMBOL(__invalidate_device);
-void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
+void sync_bdevs(bool wait)
{
struct inode *inode, *old_inode = NULL;
@@ -1047,8 +1052,19 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
bdev = I_BDEV(inode);
mutex_lock(&bdev->bd_disk->open_mutex);
- if (bdev->bd_openers)
- func(bdev, arg);
+ if (!bdev->bd_openers) {
+ ; /* skip */
+ } else if (wait) {
+ /*
+ * We keep the error status of individual mapping so
+ * that applications can catch the writeback error using
+ * fsync(2). See filemap_fdatawait_keep_errors() for
+ * details.
+ */
+ filemap_fdatawait_keep_errors(inode->i_mapping);
+ } else {
+ filemap_fdatawrite(inode->i_mapping);
+ }
mutex_unlock(&bdev->bd_disk->open_mutex);
spin_lock(&blockdev_superblock->s_inode_list_lock);
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 85b8e1c3a762..24a5c5329bcd 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -6,13 +6,13 @@
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/cgroup.h>
-#include <linux/elevator.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/sbitmap.h>
#include <linux/delay.h>
+#include "elevator.h"
#include "bfq-iosched.h"
#ifdef CONFIG_BFQ_CGROUP_DEBUG
@@ -463,7 +463,7 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
{
if (blkg_rwstat_init(&stats->bytes, gfp) ||
blkg_rwstat_init(&stats->ios, gfp))
- return -ENOMEM;
+ goto error;
#ifdef CONFIG_BFQ_CGROUP_DEBUG
if (blkg_rwstat_init(&stats->merged, gfp) ||
@@ -476,13 +476,15 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
bfq_stat_init(&stats->dequeue, gfp) ||
bfq_stat_init(&stats->group_wait_time, gfp) ||
bfq_stat_init(&stats->idle_time, gfp) ||
- bfq_stat_init(&stats->empty_time, gfp)) {
- bfqg_stats_exit(stats);
- return -ENOMEM;
- }
+ bfq_stat_init(&stats->empty_time, gfp))
+ goto error;
#endif
return 0;
+
+error:
+ bfqg_stats_exit(stats);
+ return -ENOMEM;
}
static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 480e1a134859..fec18118dc30 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -117,7 +117,6 @@
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/cgroup.h>
-#include <linux/elevator.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
@@ -127,6 +126,7 @@
#include <trace/events/block.h>
+#include "elevator.h"
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
@@ -6884,8 +6884,8 @@ static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
struct blk_mq_tags *tags = hctx->sched_tags;
unsigned int min_shallow;
- min_shallow = bfq_update_depths(bfqd, tags->bitmap_tags);
- sbitmap_queue_min_shallow_depth(tags->bitmap_tags, min_shallow);
+ min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
+ sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
}
static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 6b47cddbbca1..d25114715459 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -6,7 +6,7 @@
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*/
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/mempool.h>
#include <linux/export.h>
#include <linux/bio.h>
@@ -134,7 +134,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
iv = bip->bip_vec + bip->bip_vcnt;
if (bip->bip_vcnt &&
- bvec_gap_to_prev(bio->bi_bdev->bd_disk->queue,
+ bvec_gap_to_prev(bdev_get_queue(bio->bi_bdev),
&bip->bip_vec[bip->bip_vcnt - 1], offset))
return 0;
diff --git a/block/bio.c b/block/bio.c
index a6fb6a0b4295..15ab0d6d1c06 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -87,7 +87,8 @@ static struct bio_slab *create_bio_slab(unsigned int size)
snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size);
bslab->slab = kmem_cache_create(bslab->name, size,
- ARCH_KMALLOC_MINALIGN, SLAB_HWCACHE_ALIGN, NULL);
+ ARCH_KMALLOC_MINALIGN,
+ SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL);
if (!bslab->slab)
goto fail_alloc_slab;
@@ -156,7 +157,7 @@ out:
void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
{
- BIO_BUG_ON(nr_vecs > BIO_MAX_VECS);
+ BUG_ON(nr_vecs > BIO_MAX_VECS);
if (nr_vecs == BIO_MAX_VECS)
mempool_free(bv, pool);
@@ -281,6 +282,7 @@ void bio_init(struct bio *bio, struct bio_vec *table,
atomic_set(&bio->__bi_remaining, 1);
atomic_set(&bio->__bi_cnt, 1);
+ bio->bi_cookie = BLK_QC_T_NONE;
bio->bi_max_vecs = max_vecs;
bio->bi_io_vec = table;
@@ -546,7 +548,7 @@ EXPORT_SYMBOL(zero_fill_bio);
* REQ_OP_READ, zero the truncated part. This function should only
* be used for handling corner cases, such as bio eod.
*/
-void bio_truncate(struct bio *bio, unsigned new_size)
+static void bio_truncate(struct bio *bio, unsigned new_size)
{
struct bio_vec bv;
struct bvec_iter iter;
@@ -677,7 +679,7 @@ static void bio_alloc_cache_destroy(struct bio_set *bs)
void bio_put(struct bio *bio)
{
if (unlikely(bio_flagged(bio, BIO_REFFED))) {
- BIO_BUG_ON(!atomic_read(&bio->__bi_cnt));
+ BUG_ON(!atomic_read(&bio->__bi_cnt));
if (!atomic_dec_and_test(&bio->__bi_cnt))
return;
}
@@ -772,6 +774,23 @@ const char *bio_devname(struct bio *bio, char *buf)
}
EXPORT_SYMBOL(bio_devname);
+/**
+ * bio_full - check if the bio is full
+ * @bio: bio to check
+ * @len: length of one segment to be added
+ *
+ * Return true if @bio is full and one segment with @len bytes can't be
+ * added to the bio, otherwise return false
+ */
+static inline bool bio_full(struct bio *bio, unsigned len)
+{
+ if (bio->bi_vcnt >= bio->bi_max_vecs)
+ return true;
+ if (bio->bi_iter.bi_size > UINT_MAX - len)
+ return true;
+ return false;
+}
+
static inline bool page_is_mergeable(const struct bio_vec *bv,
struct page *page, unsigned int len, unsigned int off,
bool *same_page)
@@ -791,6 +810,44 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
}
+/**
+ * __bio_try_merge_page - try appending data to an existing bvec.
+ * @bio: destination bio
+ * @page: start page to add
+ * @len: length of the data to add
+ * @off: offset of the data relative to @page
+ * @same_page: return if the segment has been merged inside the same page
+ *
+ * Try to add the data at @page + @off to the last bvec of @bio. This is a
+ * useful optimisation for file systems with a block size smaller than the
+ * page size.
+ *
+ * Warn if (@len, @off) crosses pages in case that @same_page is true.
+ *
+ * Return %true on success or %false on failure.
+ */
+static bool __bio_try_merge_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int off, bool *same_page)
+{
+ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+ return false;
+
+ if (bio->bi_vcnt > 0) {
+ struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+ if (page_is_mergeable(bv, page, len, off, same_page)) {
+ if (bio->bi_iter.bi_size > UINT_MAX - len) {
+ *same_page = false;
+ return false;
+ }
+ bv->bv_len += len;
+ bio->bi_iter.bi_size += len;
+ return true;
+ }
+ }
+ return false;
+}
+
/*
* Try to merge a page into a segment, while obeying the hardware segment
* size limit. This is not for normal read/write bios, but for passthrough
@@ -908,7 +965,7 @@ EXPORT_SYMBOL(bio_add_pc_page);
int bio_add_zone_append_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
bool same_page = false;
if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
@@ -923,45 +980,6 @@ int bio_add_zone_append_page(struct bio *bio, struct page *page,
EXPORT_SYMBOL_GPL(bio_add_zone_append_page);
/**
- * __bio_try_merge_page - try appending data to an existing bvec.
- * @bio: destination bio
- * @page: start page to add
- * @len: length of the data to add
- * @off: offset of the data relative to @page
- * @same_page: return if the segment has been merged inside the same page
- *
- * Try to add the data at @page + @off to the last bvec of @bio. This is a
- * useful optimisation for file systems with a block size smaller than the
- * page size.
- *
- * Warn if (@len, @off) crosses pages in case that @same_page is true.
- *
- * Return %true on success or %false on failure.
- */
-bool __bio_try_merge_page(struct bio *bio, struct page *page,
- unsigned int len, unsigned int off, bool *same_page)
-{
- if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
- return false;
-
- if (bio->bi_vcnt > 0) {
- struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
- if (page_is_mergeable(bv, page, len, off, same_page)) {
- if (bio->bi_iter.bi_size > UINT_MAX - len) {
- *same_page = false;
- return false;
- }
- bv->bv_len += len;
- bio->bi_iter.bi_size += len;
- return true;
- }
- }
- return false;
-}
-EXPORT_SYMBOL_GPL(__bio_try_merge_page);
-
-/**
* __bio_add_page - add page(s) to a bio in a new segment
* @bio: destination bio
* @page: start page to add
@@ -1015,52 +1033,40 @@ int bio_add_page(struct bio *bio, struct page *page,
}
EXPORT_SYMBOL(bio_add_page);
-void bio_release_pages(struct bio *bio, bool mark_dirty)
+void __bio_release_pages(struct bio *bio, bool mark_dirty)
{
struct bvec_iter_all iter_all;
struct bio_vec *bvec;
- if (bio_flagged(bio, BIO_NO_PAGE_REF))
- return;
-
bio_for_each_segment_all(bvec, bio, iter_all) {
if (mark_dirty && !PageCompound(bvec->bv_page))
set_page_dirty_lock(bvec->bv_page);
put_page(bvec->bv_page);
}
}
-EXPORT_SYMBOL_GPL(bio_release_pages);
+EXPORT_SYMBOL_GPL(__bio_release_pages);
-static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
{
+ size_t size = iov_iter_count(iter);
+
WARN_ON_ONCE(bio->bi_max_vecs);
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+ size_t max_sectors = queue_max_zone_append_sectors(q);
+
+ size = min(size, max_sectors << SECTOR_SHIFT);
+ }
+
bio->bi_vcnt = iter->nr_segs;
bio->bi_io_vec = (struct bio_vec *)iter->bvec;
bio->bi_iter.bi_bvec_done = iter->iov_offset;
- bio->bi_iter.bi_size = iter->count;
+ bio->bi_iter.bi_size = size;
bio_set_flag(bio, BIO_NO_PAGE_REF);
bio_set_flag(bio, BIO_CLONED);
}
-static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
-{
- __bio_iov_bvec_set(bio, iter);
- iov_iter_advance(iter, iter->count);
- return 0;
-}
-
-static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
-{
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
- struct iov_iter i = *iter;
-
- iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
- __bio_iov_bvec_set(bio, &i);
- iov_iter_advance(iter, i.count);
- return 0;
-}
-
static void bio_put_pages(struct page **pages, size_t size, size_t off)
{
size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);
@@ -1130,7 +1136,7 @@ static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
{
unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
struct page **pages = (struct page **)bv;
@@ -1202,9 +1208,9 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
int ret = 0;
if (iov_iter_is_bvec(iter)) {
- if (bio_op(bio) == REQ_OP_ZONE_APPEND)
- return bio_iov_bvec_set_append(bio, iter);
- return bio_iov_bvec_set(bio, iter);
+ bio_iov_bvec_set(bio, iter);
+ iov_iter_advance(iter, bio->bi_iter.bi_size);
+ return 0;
}
do {
@@ -1260,18 +1266,7 @@ int submit_bio_wait(struct bio *bio)
}
EXPORT_SYMBOL(submit_bio_wait);
-/**
- * bio_advance - increment/complete a bio by some number of bytes
- * @bio: bio to advance
- * @bytes: number of bytes to complete
- *
- * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
- * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
- * be updated on the last bvec as well.
- *
- * @bio will then represent the remaining, uncompleted portion of the io.
- */
-void bio_advance(struct bio *bio, unsigned bytes)
+void __bio_advance(struct bio *bio, unsigned bytes)
{
if (bio_integrity(bio))
bio_integrity_advance(bio, bytes);
@@ -1279,7 +1274,7 @@ void bio_advance(struct bio *bio, unsigned bytes)
bio_crypt_advance(bio, bytes);
bio_advance_iter(bio, &bio->bi_iter, bytes);
}
-EXPORT_SYMBOL(bio_advance);
+EXPORT_SYMBOL(__bio_advance);
void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
struct bio *src, struct bvec_iter *src_iter)
@@ -1467,10 +1462,10 @@ again:
return;
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACKED))
- rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio);
+ rq_qos_done_bio(bdev_get_queue(bio->bi_bdev), bio);
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
- trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio);
+ trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio);
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
}
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9a1c5839dd46..88b1fce90520 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -32,6 +32,7 @@
#include <linux/psi.h>
#include "blk.h"
#include "blk-ioprio.h"
+#include "blk-throttle.h"
/*
* blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
@@ -620,7 +621,7 @@ struct block_device *blkcg_conf_open_bdev(char **inputp)
*/
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
char *input, struct blkg_conf_ctx *ctx)
- __acquires(rcu) __acquires(&bdev->bd_disk->queue->queue_lock)
+ __acquires(rcu) __acquires(&bdev->bd_queue->queue_lock)
{
struct block_device *bdev;
struct request_queue *q;
@@ -631,7 +632,15 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
if (IS_ERR(bdev))
return PTR_ERR(bdev);
- q = bdev->bd_disk->queue;
+ q = bdev_get_queue(bdev);
+
+ /*
+ * blkcg_deactivate_policy() requires queue to be frozen, we can grab
+ * q_usage_counter to prevent concurrent with blkcg_deactivate_policy().
+ */
+ ret = blk_queue_enter(q, 0);
+ if (ret)
+ return ret;
rcu_read_lock();
spin_lock_irq(&q->queue_lock);
@@ -702,6 +711,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
goto success;
}
success:
+ blk_queue_exit(q);
ctx->bdev = bdev;
ctx->blkg = blkg;
ctx->body = input;
@@ -714,6 +724,7 @@ fail_unlock:
rcu_read_unlock();
fail:
blkdev_put_no_open(bdev);
+ blk_queue_exit(q);
/*
* If queue was bypassing, we should retry. Do so after a
* short msleep(). It isn't strictly necessary but queue
@@ -736,9 +747,9 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
* with blkg_conf_prep().
*/
void blkg_conf_finish(struct blkg_conf_ctx *ctx)
- __releases(&ctx->bdev->bd_disk->queue->queue_lock) __releases(rcu)
+ __releases(&ctx->bdev->bd_queue->queue_lock) __releases(rcu)
{
- spin_unlock_irq(&ctx->bdev->bd_disk->queue->queue_lock);
+ spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock);
rcu_read_unlock();
blkdev_put_no_open(ctx->bdev);
}
@@ -841,7 +852,7 @@ static void blkcg_fill_root_iostats(void)
while ((dev = class_dev_iter_next(&iter))) {
struct block_device *bdev = dev_to_bdev(dev);
struct blkcg_gq *blkg =
- blk_queue_root_blkg(bdev->bd_disk->queue);
+ blk_queue_root_blkg(bdev_get_queue(bdev));
struct blkg_iostat tmp;
int cpu;
@@ -1800,7 +1811,7 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio,
rcu_read_lock();
blkg = blkg_lookup_create(css_to_blkcg(css),
- bio->bi_bdev->bd_disk->queue);
+ bdev_get_queue(bio->bi_bdev));
while (blkg) {
if (blkg_tryget(blkg)) {
ret_blkg = blkg;
@@ -1836,8 +1847,8 @@ void bio_associate_blkg_from_css(struct bio *bio,
if (css && css->parent) {
bio->bi_blkg = blkg_tryget_closest(bio, css);
} else {
- blkg_get(bio->bi_bdev->bd_disk->queue->root_blkg);
- bio->bi_blkg = bio->bi_bdev->bd_disk->queue->root_blkg;
+ blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg);
+ bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg;
}
}
EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
diff --git a/block/blk-core.c b/block/blk-core.c
index 4d8f5fe91588..ac1de7d73a45 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -18,6 +18,7 @@
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-pm.h>
+#include <linux/blk-integrity.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
@@ -49,6 +50,7 @@
#include "blk-mq.h"
#include "blk-mq-sched.h"
#include "blk-pm.h"
+#include "blk-throttle.h"
struct dentry *blk_debugfs_root;
@@ -214,8 +216,7 @@ int blk_status_to_errno(blk_status_t status)
}
EXPORT_SYMBOL_GPL(blk_status_to_errno);
-static void print_req_error(struct request *req, blk_status_t status,
- const char *caller)
+void blk_print_req_error(struct request *req, blk_status_t status)
{
int idx = (__force int)status;
@@ -223,9 +224,9 @@ static void print_req_error(struct request *req, blk_status_t status,
return;
printk_ratelimited(KERN_ERR
- "%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
+ "%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
"phys_seg %u prio class %u\n",
- caller, blk_errors[idx].name,
+ blk_errors[idx].name,
req->rq_disk ? req->rq_disk->disk_name : "?",
blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
req->cmd_flags & ~REQ_OP_MASK,
@@ -233,33 +234,6 @@ static void print_req_error(struct request *req, blk_status_t status,
IOPRIO_PRIO_CLASS(req->ioprio));
}
-static void req_bio_endio(struct request *rq, struct bio *bio,
- unsigned int nbytes, blk_status_t error)
-{
- if (error)
- bio->bi_status = error;
-
- if (unlikely(rq->rq_flags & RQF_QUIET))
- bio_set_flag(bio, BIO_QUIET);
-
- bio_advance(bio, nbytes);
-
- if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
- /*
- * Partial zone append completions cannot be supported as the
- * BIO fragments may end up not being written sequentially.
- */
- if (bio->bi_iter.bi_size)
- bio->bi_status = BLK_STS_IOERR;
- else
- bio->bi_iter.bi_sector = rq->__sector;
- }
-
- /* don't actually finish bio if it's part of flush sequence */
- if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
- bio_endio(bio);
-}
-
void blk_dump_rq_flags(struct request *rq, char *msg)
{
printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
@@ -402,7 +376,7 @@ void blk_cleanup_queue(struct request_queue *q)
*/
mutex_lock(&q->sysfs_lock);
if (q->elevator)
- blk_mq_sched_free_requests(q);
+ blk_mq_sched_free_rqs(q);
mutex_unlock(&q->sysfs_lock);
percpu_ref_exit(&q->q_usage_counter);
@@ -415,7 +389,7 @@ EXPORT_SYMBOL(blk_cleanup_queue);
static bool blk_try_enter_queue(struct request_queue *q, bool pm)
{
rcu_read_lock();
- if (!percpu_ref_tryget_live(&q->q_usage_counter))
+ if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter))
goto fail;
/*
@@ -430,7 +404,7 @@ static bool blk_try_enter_queue(struct request_queue *q, bool pm)
return true;
fail_put:
- percpu_ref_put(&q->q_usage_counter);
+ blk_queue_exit(q);
fail:
rcu_read_unlock();
return false;
@@ -470,10 +444,11 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
static inline int bio_queue_enter(struct bio *bio)
{
- struct gendisk *disk = bio->bi_bdev->bd_disk;
- struct request_queue *q = disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
while (!blk_try_enter_queue(q, false)) {
+ struct gendisk *disk = bio->bi_bdev->bd_disk;
+
if (bio->bi_opf & REQ_NOWAIT) {
if (test_bit(GD_DEAD, &disk->state))
goto dead;
@@ -553,7 +528,7 @@ struct request_queue *blk_alloc_queue(int node_id)
q->node = node_id;
- atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+ atomic_set(&q->nr_active_requests_shared_tags, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
INIT_WORK(&q->timeout_work, blk_timeout_work);
@@ -586,7 +561,7 @@ struct request_queue *blk_alloc_queue(int node_id)
blk_queue_dma_alignment(q, 511);
blk_set_default_limits(&q->limits);
- q->nr_requests = BLKDEV_MAX_RQ;
+ q->nr_requests = BLKDEV_DEFAULT_RQ;
return q;
@@ -622,40 +597,13 @@ bool blk_get_queue(struct request_queue *q)
}
EXPORT_SYMBOL(blk_get_queue);
-/**
- * blk_get_request - allocate a request
- * @q: request queue to allocate a request for
- * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC.
- * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
- */
-struct request *blk_get_request(struct request_queue *q, unsigned int op,
- blk_mq_req_flags_t flags)
-{
- struct request *req;
-
- WARN_ON_ONCE(op & REQ_NOWAIT);
- WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM));
-
- req = blk_mq_alloc_request(q, op, flags);
- if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
- q->mq_ops->initialize_rq_fn(req);
-
- return req;
-}
-EXPORT_SYMBOL(blk_get_request);
-
-void blk_put_request(struct request *req)
-{
- blk_mq_free_request(req);
-}
-EXPORT_SYMBOL(blk_put_request);
-
static void handle_bad_sector(struct bio *bio, sector_t maxsector)
{
char b[BDEVNAME_SIZE];
- pr_info_ratelimited("attempt to access beyond end of device\n"
+ pr_info_ratelimited("%s: attempt to access beyond end of device\n"
"%s: rw=%d, want=%llu, limit=%llu\n",
+ current->comm,
bio_devname(bio, b), bio->bi_opf,
bio_end_sector(bio), maxsector);
}
@@ -797,7 +745,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
static noinline_for_stack bool submit_bio_checks(struct bio *bio)
{
struct block_device *bdev = bio->bi_bdev;
- struct request_queue *q = bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bdev);
blk_status_t status = BLK_STS_IOERR;
struct blk_plug *plug;
@@ -839,7 +787,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
}
if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
- bio_clear_hipri(bio);
+ bio_clear_polled(bio);
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
@@ -912,25 +860,22 @@ end_io:
return false;
}
-static blk_qc_t __submit_bio(struct bio *bio)
+static void __submit_bio(struct bio *bio)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
- blk_qc_t ret = BLK_QC_T_NONE;
if (unlikely(bio_queue_enter(bio) != 0))
- return BLK_QC_T_NONE;
+ return;
if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio))
goto queue_exit;
- if (disk->fops->submit_bio) {
- ret = disk->fops->submit_bio(bio);
- goto queue_exit;
+ if (!disk->fops->submit_bio) {
+ blk_mq_submit_bio(bio);
+ return;
}
- return blk_mq_submit_bio(bio);
-
+ disk->fops->submit_bio(bio);
queue_exit:
blk_queue_exit(disk->queue);
- return ret;
}
/*
@@ -952,10 +897,9 @@ queue_exit:
* bio_list_on_stack[1] contains bios that were submitted before the current
* ->submit_bio_bio, but that haven't been processed yet.
*/
-static blk_qc_t __submit_bio_noacct(struct bio *bio)
+static void __submit_bio_noacct(struct bio *bio)
{
struct bio_list bio_list_on_stack[2];
- blk_qc_t ret = BLK_QC_T_NONE;
BUG_ON(bio->bi_next);
@@ -963,7 +907,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
current->bio_list = bio_list_on_stack;
do {
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
struct bio_list lower, same;
/*
@@ -972,7 +916,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
bio_list_on_stack[1] = bio_list_on_stack[0];
bio_list_init(&bio_list_on_stack[0]);
- ret = __submit_bio(bio);
+ __submit_bio(bio);
/*
* Sort new bios into those for a lower level and those for the
@@ -981,7 +925,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
bio_list_init(&lower);
bio_list_init(&same);
while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
- if (q == bio->bi_bdev->bd_disk->queue)
+ if (q == bdev_get_queue(bio->bi_bdev))
bio_list_add(&same, bio);
else
bio_list_add(&lower, bio);
@@ -995,22 +939,19 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
current->bio_list = NULL;
- return ret;
}
-static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
+static void __submit_bio_noacct_mq(struct bio *bio)
{
struct bio_list bio_list[2] = { };
- blk_qc_t ret;
current->bio_list = bio_list;
do {
- ret = __submit_bio(bio);
+ __submit_bio(bio);
} while ((bio = bio_list_pop(&bio_list[0])));
current->bio_list = NULL;
- return ret;
}
/**
@@ -1022,7 +963,7 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
* systems and other upper level users of the block layer should use
* submit_bio() instead.
*/
-blk_qc_t submit_bio_noacct(struct bio *bio)
+void submit_bio_noacct(struct bio *bio)
{
/*
* We only want one ->submit_bio to be active at a time, else stack
@@ -1030,14 +971,12 @@ blk_qc_t submit_bio_noacct(struct bio *bio)
* to collect a list of requests submited by a ->submit_bio method while
* it is active, and then process them after it returned.
*/
- if (current->bio_list) {
+ if (current->bio_list)
bio_list_add(&current->bio_list[0], bio);
- return BLK_QC_T_NONE;
- }
-
- if (!bio->bi_bdev->bd_disk->fops->submit_bio)
- return __submit_bio_noacct_mq(bio);
- return __submit_bio_noacct(bio);
+ else if (!bio->bi_bdev->bd_disk->fops->submit_bio)
+ __submit_bio_noacct_mq(bio);
+ else
+ __submit_bio_noacct(bio);
}
EXPORT_SYMBOL(submit_bio_noacct);
@@ -1054,10 +993,10 @@ EXPORT_SYMBOL(submit_bio_noacct);
* in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has
* been called.
*/
-blk_qc_t submit_bio(struct bio *bio)
+void submit_bio(struct bio *bio)
{
if (blkcg_punt_bio_submit(bio))
- return BLK_QC_T_NONE;
+ return;
/*
* If it's a regular read/write or a barrier with data attached,
@@ -1068,7 +1007,7 @@ blk_qc_t submit_bio(struct bio *bio)
if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
count = queue_logical_block_size(
- bio->bi_bdev->bd_disk->queue) >> 9;
+ bdev_get_queue(bio->bi_bdev)) >> 9;
else
count = bio_sectors(bio);
@@ -1089,20 +1028,93 @@ blk_qc_t submit_bio(struct bio *bio)
if (unlikely(bio_op(bio) == REQ_OP_READ &&
bio_flagged(bio, BIO_WORKINGSET))) {
unsigned long pflags;
- blk_qc_t ret;
psi_memstall_enter(&pflags);
- ret = submit_bio_noacct(bio);
+ submit_bio_noacct(bio);
psi_memstall_leave(&pflags);
-
- return ret;
+ return;
}
- return submit_bio_noacct(bio);
+ submit_bio_noacct(bio);
}
EXPORT_SYMBOL(submit_bio);
/**
+ * bio_poll - poll for BIO completions
+ * @bio: bio to poll for
+ * @flags: BLK_POLL_* flags that control the behavior
+ *
+ * Poll for completions on queue associated with the bio. Returns number of
+ * completed entries found.
+ *
+ * Note: the caller must either be the context that submitted @bio, or
+ * be in a RCU critical section to prevent freeing of @bio.
+ */
+int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
+{
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+ blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
+ int ret;
+
+ if (cookie == BLK_QC_T_NONE ||
+ !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ return 0;
+
+ if (current->plug)
+ blk_flush_plug(current->plug, false);
+
+ if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT))
+ return 0;
+ if (WARN_ON_ONCE(!queue_is_mq(q)))
+ ret = 0; /* not yet implemented, should not happen */
+ else
+ ret = blk_mq_poll(q, cookie, iob, flags);
+ blk_queue_exit(q);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(bio_poll);
+
+/*
+ * Helper to implement file_operations.iopoll. Requires the bio to be stored
+ * in iocb->private, and cleared before freeing the bio.
+ */
+int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
+ unsigned int flags)
+{
+ struct bio *bio;
+ int ret = 0;
+
+ /*
+ * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can
+ * point to a freshly allocated bio at this point. If that happens
+ * we have a few cases to consider:
+ *
+ * 1) the bio is beeing initialized and bi_bdev is NULL. We can just
+ * simply nothing in this case
+ * 2) the bio points to a not poll enabled device. bio_poll will catch
+ * this and return 0
+ * 3) the bio points to a poll capable device, including but not
+ * limited to the one that the original bio pointed to. In this
+ * case we will call into the actual poll method and poll for I/O,
+ * even if we don't need to, but it won't cause harm either.
+ *
+ * For cases 2) and 3) above the RCU grace period ensures that bi_bdev
+ * is still allocated. Because partitions hold a reference to the whole
+ * device bdev and thus disk, the disk is also still valid. Grabbing
+ * a reference to the queue in bio_poll() ensures the hctxs and requests
+ * are still valid as well.
+ */
+ rcu_read_lock();
+ bio = READ_ONCE(kiocb->private);
+ if (bio && bio->bi_bdev)
+ ret = bio_poll(bio, iob, flags);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iocb_bio_iopoll);
+
+/**
* blk_cloned_rq_check_limits - Helper function to check a cloned request
* for the new queue limits
* @q: the queue
@@ -1177,8 +1189,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
if (blk_crypto_insert_cloned_request(rq))
return BLK_STS_IOERR;
- if (blk_queue_io_stat(q))
- blk_account_io_start(rq);
+ blk_account_io_start(rq);
/*
* Since we have a scheduler attached on the top device,
@@ -1246,41 +1257,19 @@ again:
}
}
-static void blk_account_io_completion(struct request *req, unsigned int bytes)
+void __blk_account_io_done(struct request *req, u64 now)
{
- if (req->part && blk_do_io_stat(req)) {
- const int sgrp = op_stat_group(req_op(req));
+ const int sgrp = op_stat_group(req_op(req));
- part_stat_lock();
- part_stat_add(req->part, sectors[sgrp], bytes >> 9);
- part_stat_unlock();
- }
-}
-
-void blk_account_io_done(struct request *req, u64 now)
-{
- /*
- * Account IO completion. flush_rq isn't accounted as a
- * normal IO on queueing nor completion. Accounting the
- * containing request is enough.
- */
- if (req->part && blk_do_io_stat(req) &&
- !(req->rq_flags & RQF_FLUSH_SEQ)) {
- const int sgrp = op_stat_group(req_op(req));
-
- part_stat_lock();
- update_io_ticks(req->part, jiffies, true);
- part_stat_inc(req->part, ios[sgrp]);
- part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
- part_stat_unlock();
- }
+ part_stat_lock();
+ update_io_ticks(req->part, jiffies, true);
+ part_stat_inc(req->part, ios[sgrp]);
+ part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+ part_stat_unlock();
}
-void blk_account_io_start(struct request *rq)
+void __blk_account_io_start(struct request *rq)
{
- if (!blk_do_io_stat(rq))
- return;
-
/* passthrough requests can hold bios that do not have ->bi_bdev set */
if (rq->bio && rq->bio->bi_bdev)
rq->part = rq->bio->bi_bdev;
@@ -1376,112 +1365,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq)
}
EXPORT_SYMBOL_GPL(blk_steal_bios);
-/**
- * blk_update_request - Complete multiple bytes without completing the request
- * @req: the request being processed
- * @error: block status code
- * @nr_bytes: number of bytes to complete for @req
- *
- * Description:
- * Ends I/O on a number of bytes attached to @req, but doesn't complete
- * the request structure even if @req doesn't have leftover.
- * If @req has leftover, sets it up for the next range of segments.
- *
- * Passing the result of blk_rq_bytes() as @nr_bytes guarantees
- * %false return from this function.
- *
- * Note:
- * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function
- * except in the consistency check at the end of this function.
- *
- * Return:
- * %false - this request doesn't have any more data
- * %true - this request has more data
- **/
-bool blk_update_request(struct request *req, blk_status_t error,
- unsigned int nr_bytes)
-{
- int total_bytes;
-
- trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes);
-
- if (!req->bio)
- return false;
-
-#ifdef CONFIG_BLK_DEV_INTEGRITY
- if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
- error == BLK_STS_OK)
- req->q->integrity.profile->complete_fn(req, nr_bytes);
-#endif
-
- if (unlikely(error && !blk_rq_is_passthrough(req) &&
- !(req->rq_flags & RQF_QUIET)))
- print_req_error(req, error, __func__);
-
- blk_account_io_completion(req, nr_bytes);
-
- total_bytes = 0;
- while (req->bio) {
- struct bio *bio = req->bio;
- unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
-
- if (bio_bytes == bio->bi_iter.bi_size)
- req->bio = bio->bi_next;
-
- /* Completion has already been traced */
- bio_clear_flag(bio, BIO_TRACE_COMPLETION);
- req_bio_endio(req, bio, bio_bytes, error);
-
- total_bytes += bio_bytes;
- nr_bytes -= bio_bytes;
-
- if (!nr_bytes)
- break;
- }
-
- /*
- * completely done
- */
- if (!req->bio) {
- /*
- * Reset counters so that the request stacking driver
- * can find how many bytes remain in the request
- * later.
- */
- req->__data_len = 0;
- return false;
- }
-
- req->__data_len -= total_bytes;
-
- /* update sector only for requests with clear definition of sector */
- if (!blk_rq_is_passthrough(req))
- req->__sector += total_bytes >> 9;
-
- /* mixed attributes always follow the first bio */
- if (req->rq_flags & RQF_MIXED_MERGE) {
- req->cmd_flags &= ~REQ_FAILFAST_MASK;
- req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
- }
-
- if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) {
- /*
- * If total number of sectors is less than the first segment
- * size, something has gone terribly wrong.
- */
- if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
- blk_dump_rq_flags(req, "request botched");
- req->__data_len = blk_rq_cur_bytes(req);
- }
-
- /* recalculate the number of segments */
- req->nr_phys_segments = blk_recalc_rq_segments(req);
- }
-
- return true;
-}
-EXPORT_SYMBOL_GPL(blk_update_request);
-
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
/**
* rq_flush_dcache_pages - Helper function to flush all pages in a request
@@ -1629,6 +1512,32 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
}
EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
+void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
+{
+ struct task_struct *tsk = current;
+
+ /*
+ * If this is a nested plug, don't actually assign it.
+ */
+ if (tsk->plug)
+ return;
+
+ plug->mq_list = NULL;
+ plug->cached_rq = NULL;
+ plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
+ plug->rq_count = 0;
+ plug->multiple_queues = false;
+ plug->has_elevator = false;
+ plug->nowait = false;
+ INIT_LIST_HEAD(&plug->cb_list);
+
+ /*
+ * Store ordering should not be needed here, since a potential
+ * preempt will imply a full memory barrier
+ */
+ tsk->plug = plug;
+}
+
/**
* blk_start_plug - initialize blk_plug and track it inside the task_struct
* @plug: The &struct blk_plug that needs to be initialized
@@ -1654,25 +1563,7 @@ EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
*/
void blk_start_plug(struct blk_plug *plug)
{
- struct task_struct *tsk = current;
-
- /*
- * If this is a nested plug, don't actually assign it.
- */
- if (tsk->plug)
- return;
-
- INIT_LIST_HEAD(&plug->mq_list);
- INIT_LIST_HEAD(&plug->cb_list);
- plug->rq_count = 0;
- plug->multiple_queues = false;
- plug->nowait = false;
-
- /*
- * Store ordering should not be needed here, since a potential
- * preempt will imply a full memory barrier
- */
- tsk->plug = plug;
+ blk_start_plug_nr_ios(plug, 1);
}
EXPORT_SYMBOL(blk_start_plug);
@@ -1718,12 +1609,14 @@ struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
}
EXPORT_SYMBOL(blk_check_plugged);
-void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule)
{
- flush_plug_callbacks(plug, from_schedule);
-
- if (!list_empty(&plug->mq_list))
+ if (!list_empty(&plug->cb_list))
+ flush_plug_callbacks(plug, from_schedule);
+ if (!rq_list_empty(plug->mq_list))
blk_mq_flush_plug_list(plug, from_schedule);
+ if (unlikely(!from_schedule && plug->cached_rq))
+ blk_mq_free_plug_rqs(plug);
}
/**
@@ -1738,11 +1631,10 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
*/
void blk_finish_plug(struct blk_plug *plug)
{
- if (plug != current->plug)
- return;
- blk_flush_plug_list(plug, false);
-
- current->plug = NULL;
+ if (plug == current->plug) {
+ blk_flush_plug(plug, false);
+ current->plug = NULL;
+ }
}
EXPORT_SYMBOL(blk_finish_plug);
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index c322176a1e09..c87aba8584c6 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -12,12 +12,13 @@
#include <crypto/skcipher.h>
#include <linux/blk-cgroup.h>
#include <linux/blk-crypto.h>
+#include <linux/blk-crypto-profile.h>
#include <linux/blkdev.h>
#include <linux/crypto.h>
-#include <linux/keyslot-manager.h>
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/random.h>
+#include <linux/scatterlist.h>
#include "blk-crypto-internal.h"
@@ -72,12 +73,12 @@ static mempool_t *bio_fallback_crypt_ctx_pool;
static DEFINE_MUTEX(tfms_init_lock);
static bool tfms_inited[BLK_ENCRYPTION_MODE_MAX];
-static struct blk_crypto_keyslot {
+static struct blk_crypto_fallback_keyslot {
enum blk_crypto_mode_num crypto_mode;
struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX];
} *blk_crypto_keyslots;
-static struct blk_keyslot_manager blk_crypto_ksm;
+static struct blk_crypto_profile blk_crypto_fallback_profile;
static struct workqueue_struct *blk_crypto_wq;
static mempool_t *blk_crypto_bounce_page_pool;
static struct bio_set crypto_bio_split;
@@ -88,9 +89,9 @@ static struct bio_set crypto_bio_split;
*/
static u8 blank_key[BLK_CRYPTO_MAX_KEY_SIZE];
-static void blk_crypto_evict_keyslot(unsigned int slot)
+static void blk_crypto_fallback_evict_keyslot(unsigned int slot)
{
- struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot];
+ struct blk_crypto_fallback_keyslot *slotp = &blk_crypto_keyslots[slot];
enum blk_crypto_mode_num crypto_mode = slotp->crypto_mode;
int err;
@@ -103,45 +104,41 @@ static void blk_crypto_evict_keyslot(unsigned int slot)
slotp->crypto_mode = BLK_ENCRYPTION_MODE_INVALID;
}
-static int blk_crypto_keyslot_program(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot)
+static int
+blk_crypto_fallback_keyslot_program(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot)
{
- struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot];
+ struct blk_crypto_fallback_keyslot *slotp = &blk_crypto_keyslots[slot];
const enum blk_crypto_mode_num crypto_mode =
key->crypto_cfg.crypto_mode;
int err;
if (crypto_mode != slotp->crypto_mode &&
slotp->crypto_mode != BLK_ENCRYPTION_MODE_INVALID)
- blk_crypto_evict_keyslot(slot);
+ blk_crypto_fallback_evict_keyslot(slot);
slotp->crypto_mode = crypto_mode;
err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], key->raw,
key->size);
if (err) {
- blk_crypto_evict_keyslot(slot);
+ blk_crypto_fallback_evict_keyslot(slot);
return err;
}
return 0;
}
-static int blk_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot)
+static int blk_crypto_fallback_keyslot_evict(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot)
{
- blk_crypto_evict_keyslot(slot);
+ blk_crypto_fallback_evict_keyslot(slot);
return 0;
}
-/*
- * The crypto API fallback KSM ops - only used for a bio when it specifies a
- * blk_crypto_key that was not supported by the device's inline encryption
- * hardware.
- */
-static const struct blk_ksm_ll_ops blk_crypto_ksm_ll_ops = {
- .keyslot_program = blk_crypto_keyslot_program,
- .keyslot_evict = blk_crypto_keyslot_evict,
+static const struct blk_crypto_ll_ops blk_crypto_fallback_ll_ops = {
+ .keyslot_program = blk_crypto_fallback_keyslot_program,
+ .keyslot_evict = blk_crypto_fallback_keyslot_evict,
};
static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio)
@@ -159,7 +156,7 @@ static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio)
bio_endio(src_bio);
}
-static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
+static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src)
{
struct bvec_iter iter;
struct bio_vec bv;
@@ -186,13 +183,14 @@ static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
return bio;
}
-static bool blk_crypto_alloc_cipher_req(struct blk_ksm_keyslot *slot,
- struct skcipher_request **ciph_req_ret,
- struct crypto_wait *wait)
+static bool
+blk_crypto_fallback_alloc_cipher_req(struct blk_crypto_keyslot *slot,
+ struct skcipher_request **ciph_req_ret,
+ struct crypto_wait *wait)
{
struct skcipher_request *ciph_req;
- const struct blk_crypto_keyslot *slotp;
- int keyslot_idx = blk_ksm_get_slot_idx(slot);
+ const struct blk_crypto_fallback_keyslot *slotp;
+ int keyslot_idx = blk_crypto_keyslot_index(slot);
slotp = &blk_crypto_keyslots[keyslot_idx];
ciph_req = skcipher_request_alloc(slotp->tfms[slotp->crypto_mode],
@@ -209,7 +207,7 @@ static bool blk_crypto_alloc_cipher_req(struct blk_ksm_keyslot *slot,
return true;
}
-static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr)
+static bool blk_crypto_fallback_split_bio_if_needed(struct bio **bio_ptr)
{
struct bio *bio = *bio_ptr;
unsigned int i = 0;
@@ -264,7 +262,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr)
{
struct bio *src_bio, *enc_bio;
struct bio_crypt_ctx *bc;
- struct blk_ksm_keyslot *slot;
+ struct blk_crypto_keyslot *slot;
int data_unit_size;
struct skcipher_request *ciph_req = NULL;
DECLARE_CRYPTO_WAIT(wait);
@@ -276,7 +274,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr)
blk_status_t blk_st;
/* Split the bio if it's too big for single page bvec */
- if (!blk_crypto_split_bio_if_needed(bio_ptr))
+ if (!blk_crypto_fallback_split_bio_if_needed(bio_ptr))
return false;
src_bio = *bio_ptr;
@@ -284,24 +282,25 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr)
data_unit_size = bc->bc_key->crypto_cfg.data_unit_size;
/* Allocate bounce bio for encryption */
- enc_bio = blk_crypto_clone_bio(src_bio);
+ enc_bio = blk_crypto_fallback_clone_bio(src_bio);
if (!enc_bio) {
src_bio->bi_status = BLK_STS_RESOURCE;
return false;
}
/*
- * Use the crypto API fallback keyslot manager to get a crypto_skcipher
- * for the algorithm and key specified for this bio.
+ * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for
+ * this bio's algorithm and key.
*/
- blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot);
+ blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile,
+ bc->bc_key, &slot);
if (blk_st != BLK_STS_OK) {
src_bio->bi_status = blk_st;
goto out_put_enc_bio;
}
/* and then allocate an skcipher_request for it */
- if (!blk_crypto_alloc_cipher_req(slot, &ciph_req, &wait)) {
+ if (!blk_crypto_fallback_alloc_cipher_req(slot, &ciph_req, &wait)) {
src_bio->bi_status = BLK_STS_RESOURCE;
goto out_release_keyslot;
}
@@ -362,7 +361,7 @@ out_free_bounce_pages:
out_free_ciph_req:
skcipher_request_free(ciph_req);
out_release_keyslot:
- blk_ksm_put_slot(slot);
+ blk_crypto_put_keyslot(slot);
out_put_enc_bio:
if (enc_bio)
bio_put(enc_bio);
@@ -380,7 +379,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work)
container_of(work, struct bio_fallback_crypt_ctx, work);
struct bio *bio = f_ctx->bio;
struct bio_crypt_ctx *bc = &f_ctx->crypt_ctx;
- struct blk_ksm_keyslot *slot;
+ struct blk_crypto_keyslot *slot;
struct skcipher_request *ciph_req = NULL;
DECLARE_CRYPTO_WAIT(wait);
u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
@@ -393,17 +392,18 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work)
blk_status_t blk_st;
/*
- * Use the crypto API fallback keyslot manager to get a crypto_skcipher
- * for the algorithm and key specified for this bio.
+ * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for
+ * this bio's algorithm and key.
*/
- blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot);
+ blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile,
+ bc->bc_key, &slot);
if (blk_st != BLK_STS_OK) {
bio->bi_status = blk_st;
goto out_no_keyslot;
}
/* and then allocate an skcipher_request for it */
- if (!blk_crypto_alloc_cipher_req(slot, &ciph_req, &wait)) {
+ if (!blk_crypto_fallback_alloc_cipher_req(slot, &ciph_req, &wait)) {
bio->bi_status = BLK_STS_RESOURCE;
goto out;
}
@@ -434,7 +434,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work)
out:
skcipher_request_free(ciph_req);
- blk_ksm_put_slot(slot);
+ blk_crypto_put_keyslot(slot);
out_no_keyslot:
mempool_free(f_ctx, bio_fallback_crypt_ctx_pool);
bio_endio(bio);
@@ -473,9 +473,9 @@ static void blk_crypto_fallback_decrypt_endio(struct bio *bio)
* @bio_ptr: pointer to the bio to prepare
*
* If bio is doing a WRITE operation, this splits the bio into two parts if it's
- * too big (see blk_crypto_split_bio_if_needed). It then allocates a bounce bio
- * for the first part, encrypts it, and update bio_ptr to point to the bounce
- * bio.
+ * too big (see blk_crypto_fallback_split_bio_if_needed()). It then allocates a
+ * bounce bio for the first part, encrypts it, and updates bio_ptr to point to
+ * the bounce bio.
*
* For a READ operation, we mark the bio for decryption by using bi_private and
* bi_end_io.
@@ -499,8 +499,8 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr)
return false;
}
- if (!blk_ksm_crypto_cfg_supported(&blk_crypto_ksm,
- &bc->bc_key->crypto_cfg)) {
+ if (!__blk_crypto_cfg_supported(&blk_crypto_fallback_profile,
+ &bc->bc_key->crypto_cfg)) {
bio->bi_status = BLK_STS_NOTSUPP;
return false;
}
@@ -526,7 +526,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr)
int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key)
{
- return blk_ksm_evict_key(&blk_crypto_ksm, key);
+ return __blk_crypto_evict_key(&blk_crypto_fallback_profile, key);
}
static bool blk_crypto_fallback_inited;
@@ -534,6 +534,7 @@ static int blk_crypto_fallback_init(void)
{
int i;
int err;
+ struct blk_crypto_profile *profile = &blk_crypto_fallback_profile;
if (blk_crypto_fallback_inited)
return 0;
@@ -544,24 +545,24 @@ static int blk_crypto_fallback_init(void)
if (err)
goto out;
- err = blk_ksm_init(&blk_crypto_ksm, blk_crypto_num_keyslots);
+ err = blk_crypto_profile_init(profile, blk_crypto_num_keyslots);
if (err)
goto fail_free_bioset;
err = -ENOMEM;
- blk_crypto_ksm.ksm_ll_ops = blk_crypto_ksm_ll_ops;
- blk_crypto_ksm.max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE;
+ profile->ll_ops = blk_crypto_fallback_ll_ops;
+ profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE;
/* All blk-crypto modes have a crypto API fallback. */
for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++)
- blk_crypto_ksm.crypto_modes_supported[i] = 0xFFFFFFFF;
- blk_crypto_ksm.crypto_modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0;
+ profile->modes_supported[i] = 0xFFFFFFFF;
+ profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0;
blk_crypto_wq = alloc_workqueue("blk_crypto_wq",
WQ_UNBOUND | WQ_HIGHPRI |
WQ_MEM_RECLAIM, num_online_cpus());
if (!blk_crypto_wq)
- goto fail_free_ksm;
+ goto fail_destroy_profile;
blk_crypto_keyslots = kcalloc(blk_crypto_num_keyslots,
sizeof(blk_crypto_keyslots[0]),
@@ -595,8 +596,8 @@ fail_free_keyslots:
kfree(blk_crypto_keyslots);
fail_free_wq:
destroy_workqueue(blk_crypto_wq);
-fail_free_ksm:
- blk_ksm_destroy(&blk_crypto_ksm);
+fail_destroy_profile:
+ blk_crypto_profile_destroy(profile);
fail_free_bioset:
bioset_exit(&crypto_bio_split);
out:
@@ -610,7 +611,7 @@ out:
int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num)
{
const char *cipher_str = blk_crypto_modes[mode_num].cipher_str;
- struct blk_crypto_keyslot *slotp;
+ struct blk_crypto_fallback_keyslot *slotp;
unsigned int i;
int err = 0;
diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
index 0d36aae538d7..2fb0d65a464c 100644
--- a/block/blk-crypto-internal.h
+++ b/block/blk-crypto-internal.h
@@ -7,7 +7,7 @@
#define __LINUX_BLK_CRYPTO_INTERNAL_H
#include <linux/bio.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
/* Represents a crypto mode supported by blk-crypto */
struct blk_crypto_mode {
diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
new file mode 100644
index 000000000000..605ba0626a5c
--- /dev/null
+++ b/block/blk-crypto-profile.c
@@ -0,0 +1,565 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Google LLC
+ */
+
+/**
+ * DOC: blk-crypto profiles
+ *
+ * 'struct blk_crypto_profile' contains all generic inline encryption-related
+ * state for a particular inline encryption device. blk_crypto_profile serves
+ * as the way that drivers for inline encryption hardware expose their crypto
+ * capabilities and certain functions (e.g., functions to program and evict
+ * keys) to upper layers. Device drivers that want to support inline encryption
+ * construct a crypto profile, then associate it with the disk's request_queue.
+ *
+ * If the device has keyslots, then its blk_crypto_profile also handles managing
+ * these keyslots in a device-independent way, using the driver-provided
+ * functions to program and evict keys as needed. This includes keeping track
+ * of which key and how many I/O requests are using each keyslot, getting
+ * keyslots for I/O requests, and handling key eviction requests.
+ *
+ * For more information, see Documentation/block/inline-encryption.rst.
+ */
+
+#define pr_fmt(fmt) "blk-crypto: " fmt
+
+#include <linux/blk-crypto-profile.h>
+#include <linux/device.h>
+#include <linux/atomic.h>
+#include <linux/mutex.h>
+#include <linux/pm_runtime.h>
+#include <linux/wait.h>
+#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
+
+struct blk_crypto_keyslot {
+ atomic_t slot_refs;
+ struct list_head idle_slot_node;
+ struct hlist_node hash_node;
+ const struct blk_crypto_key *key;
+ struct blk_crypto_profile *profile;
+};
+
+static inline void blk_crypto_hw_enter(struct blk_crypto_profile *profile)
+{
+ /*
+ * Calling into the driver requires profile->lock held and the device
+ * resumed. But we must resume the device first, since that can acquire
+ * and release profile->lock via blk_crypto_reprogram_all_keys().
+ */
+ if (profile->dev)
+ pm_runtime_get_sync(profile->dev);
+ down_write(&profile->lock);
+}
+
+static inline void blk_crypto_hw_exit(struct blk_crypto_profile *profile)
+{
+ up_write(&profile->lock);
+ if (profile->dev)
+ pm_runtime_put_sync(profile->dev);
+}
+
+/**
+ * blk_crypto_profile_init() - Initialize a blk_crypto_profile
+ * @profile: the blk_crypto_profile to initialize
+ * @num_slots: the number of keyslots
+ *
+ * Storage drivers must call this when starting to set up a blk_crypto_profile,
+ * before filling in additional fields.
+ *
+ * Return: 0 on success, or else a negative error code.
+ */
+int blk_crypto_profile_init(struct blk_crypto_profile *profile,
+ unsigned int num_slots)
+{
+ unsigned int slot;
+ unsigned int i;
+ unsigned int slot_hashtable_size;
+
+ memset(profile, 0, sizeof(*profile));
+ init_rwsem(&profile->lock);
+
+ if (num_slots == 0)
+ return 0;
+
+ /* Initialize keyslot management data. */
+
+ profile->slots = kvcalloc(num_slots, sizeof(profile->slots[0]),
+ GFP_KERNEL);
+ if (!profile->slots)
+ return -ENOMEM;
+
+ profile->num_slots = num_slots;
+
+ init_waitqueue_head(&profile->idle_slots_wait_queue);
+ INIT_LIST_HEAD(&profile->idle_slots);
+
+ for (slot = 0; slot < num_slots; slot++) {
+ profile->slots[slot].profile = profile;
+ list_add_tail(&profile->slots[slot].idle_slot_node,
+ &profile->idle_slots);
+ }
+
+ spin_lock_init(&profile->idle_slots_lock);
+
+ slot_hashtable_size = roundup_pow_of_two(num_slots);
+ /*
+ * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2
+ * buckets. This only makes a difference when there is only 1 keyslot.
+ */
+ if (slot_hashtable_size < 2)
+ slot_hashtable_size = 2;
+
+ profile->log_slot_ht_size = ilog2(slot_hashtable_size);
+ profile->slot_hashtable =
+ kvmalloc_array(slot_hashtable_size,
+ sizeof(profile->slot_hashtable[0]), GFP_KERNEL);
+ if (!profile->slot_hashtable)
+ goto err_destroy;
+ for (i = 0; i < slot_hashtable_size; i++)
+ INIT_HLIST_HEAD(&profile->slot_hashtable[i]);
+
+ return 0;
+
+err_destroy:
+ blk_crypto_profile_destroy(profile);
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_profile_init);
+
+static void blk_crypto_profile_destroy_callback(void *profile)
+{
+ blk_crypto_profile_destroy(profile);
+}
+
+/**
+ * devm_blk_crypto_profile_init() - Resource-managed blk_crypto_profile_init()
+ * @dev: the device which owns the blk_crypto_profile
+ * @profile: the blk_crypto_profile to initialize
+ * @num_slots: the number of keyslots
+ *
+ * Like blk_crypto_profile_init(), but causes blk_crypto_profile_destroy() to be
+ * called automatically on driver detach.
+ *
+ * Return: 0 on success, or else a negative error code.
+ */
+int devm_blk_crypto_profile_init(struct device *dev,
+ struct blk_crypto_profile *profile,
+ unsigned int num_slots)
+{
+ int err = blk_crypto_profile_init(profile, num_slots);
+
+ if (err)
+ return err;
+
+ return devm_add_action_or_reset(dev,
+ blk_crypto_profile_destroy_callback,
+ profile);
+}
+EXPORT_SYMBOL_GPL(devm_blk_crypto_profile_init);
+
+static inline struct hlist_head *
+blk_crypto_hash_bucket_for_key(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ return &profile->slot_hashtable[
+ hash_ptr(key, profile->log_slot_ht_size)];
+}
+
+static void
+blk_crypto_remove_slot_from_lru_list(struct blk_crypto_keyslot *slot)
+{
+ struct blk_crypto_profile *profile = slot->profile;
+ unsigned long flags;
+
+ spin_lock_irqsave(&profile->idle_slots_lock, flags);
+ list_del(&slot->idle_slot_node);
+ spin_unlock_irqrestore(&profile->idle_slots_lock, flags);
+}
+
+static struct blk_crypto_keyslot *
+blk_crypto_find_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ const struct hlist_head *head =
+ blk_crypto_hash_bucket_for_key(profile, key);
+ struct blk_crypto_keyslot *slotp;
+
+ hlist_for_each_entry(slotp, head, hash_node) {
+ if (slotp->key == key)
+ return slotp;
+ }
+ return NULL;
+}
+
+static struct blk_crypto_keyslot *
+blk_crypto_find_and_grab_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ struct blk_crypto_keyslot *slot;
+
+ slot = blk_crypto_find_keyslot(profile, key);
+ if (!slot)
+ return NULL;
+ if (atomic_inc_return(&slot->slot_refs) == 1) {
+ /* Took first reference to this slot; remove it from LRU list */
+ blk_crypto_remove_slot_from_lru_list(slot);
+ }
+ return slot;
+}
+
+/**
+ * blk_crypto_keyslot_index() - Get the index of a keyslot
+ * @slot: a keyslot that blk_crypto_get_keyslot() returned
+ *
+ * Return: the 0-based index of the keyslot within the device's keyslots.
+ */
+unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot)
+{
+ return slot - slot->profile->slots;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_keyslot_index);
+
+/**
+ * blk_crypto_get_keyslot() - Get a keyslot for a key, if needed.
+ * @profile: the crypto profile of the device the key will be used on
+ * @key: the key that will be used
+ * @slot_ptr: If a keyslot is allocated, an opaque pointer to the keyslot struct
+ * will be stored here; otherwise NULL will be stored here.
+ *
+ * If the device has keyslots, this gets a keyslot that's been programmed with
+ * the specified key. If the key is already in a slot, this reuses it;
+ * otherwise this waits for a slot to become idle and programs the key into it.
+ *
+ * This must be paired with a call to blk_crypto_put_keyslot().
+ *
+ * Context: Process context. Takes and releases profile->lock.
+ * Return: BLK_STS_OK on success, meaning that either a keyslot was allocated or
+ * one wasn't needed; or a blk_status_t error on failure.
+ */
+blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ struct blk_crypto_keyslot **slot_ptr)
+{
+ struct blk_crypto_keyslot *slot;
+ int slot_idx;
+ int err;
+
+ *slot_ptr = NULL;
+
+ /*
+ * If the device has no concept of "keyslots", then there is no need to
+ * get one.
+ */
+ if (profile->num_slots == 0)
+ return BLK_STS_OK;
+
+ down_read(&profile->lock);
+ slot = blk_crypto_find_and_grab_keyslot(profile, key);
+ up_read(&profile->lock);
+ if (slot)
+ goto success;
+
+ for (;;) {
+ blk_crypto_hw_enter(profile);
+ slot = blk_crypto_find_and_grab_keyslot(profile, key);
+ if (slot) {
+ blk_crypto_hw_exit(profile);
+ goto success;
+ }
+
+ /*
+ * If we're here, that means there wasn't a slot that was
+ * already programmed with the key. So try to program it.
+ */
+ if (!list_empty(&profile->idle_slots))
+ break;
+
+ blk_crypto_hw_exit(profile);
+ wait_event(profile->idle_slots_wait_queue,
+ !list_empty(&profile->idle_slots));
+ }
+
+ slot = list_first_entry(&profile->idle_slots, struct blk_crypto_keyslot,
+ idle_slot_node);
+ slot_idx = blk_crypto_keyslot_index(slot);
+
+ err = profile->ll_ops.keyslot_program(profile, key, slot_idx);
+ if (err) {
+ wake_up(&profile->idle_slots_wait_queue);
+ blk_crypto_hw_exit(profile);
+ return errno_to_blk_status(err);
+ }
+
+ /* Move this slot to the hash list for the new key. */
+ if (slot->key)
+ hlist_del(&slot->hash_node);
+ slot->key = key;
+ hlist_add_head(&slot->hash_node,
+ blk_crypto_hash_bucket_for_key(profile, key));
+
+ atomic_set(&slot->slot_refs, 1);
+
+ blk_crypto_remove_slot_from_lru_list(slot);
+
+ blk_crypto_hw_exit(profile);
+success:
+ *slot_ptr = slot;
+ return BLK_STS_OK;
+}
+
+/**
+ * blk_crypto_put_keyslot() - Release a reference to a keyslot
+ * @slot: The keyslot to release the reference of (may be NULL).
+ *
+ * Context: Any context.
+ */
+void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot)
+{
+ struct blk_crypto_profile *profile;
+ unsigned long flags;
+
+ if (!slot)
+ return;
+
+ profile = slot->profile;
+
+ if (atomic_dec_and_lock_irqsave(&slot->slot_refs,
+ &profile->idle_slots_lock, flags)) {
+ list_add_tail(&slot->idle_slot_node, &profile->idle_slots);
+ spin_unlock_irqrestore(&profile->idle_slots_lock, flags);
+ wake_up(&profile->idle_slots_wait_queue);
+ }
+}
+
+/**
+ * __blk_crypto_cfg_supported() - Check whether the given crypto profile
+ * supports the given crypto configuration.
+ * @profile: the crypto profile to check
+ * @cfg: the crypto configuration to check for
+ *
+ * Return: %true if @profile supports the given @cfg.
+ */
+bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
+ const struct blk_crypto_config *cfg)
+{
+ if (!profile)
+ return false;
+ if (!(profile->modes_supported[cfg->crypto_mode] & cfg->data_unit_size))
+ return false;
+ if (profile->max_dun_bytes_supported < cfg->dun_bytes)
+ return false;
+ return true;
+}
+
+/**
+ * __blk_crypto_evict_key() - Evict a key from a device.
+ * @profile: the crypto profile of the device
+ * @key: the key to evict. It must not still be used in any I/O.
+ *
+ * If the device has keyslots, this finds the keyslot (if any) that contains the
+ * specified key and calls the driver's keyslot_evict function to evict it.
+ *
+ * Otherwise, this just calls the driver's keyslot_evict function if it is
+ * implemented, passing just the key (without any particular keyslot). This
+ * allows layered devices to evict the key from their underlying devices.
+ *
+ * Context: Process context. Takes and releases profile->lock.
+ * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY
+ * if the keyslot is still in use, or another -errno value on other
+ * error.
+ */
+int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ struct blk_crypto_keyslot *slot;
+ int err = 0;
+
+ if (profile->num_slots == 0) {
+ if (profile->ll_ops.keyslot_evict) {
+ blk_crypto_hw_enter(profile);
+ err = profile->ll_ops.keyslot_evict(profile, key, -1);
+ blk_crypto_hw_exit(profile);
+ return err;
+ }
+ return 0;
+ }
+
+ blk_crypto_hw_enter(profile);
+ slot = blk_crypto_find_keyslot(profile, key);
+ if (!slot)
+ goto out_unlock;
+
+ if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
+ err = -EBUSY;
+ goto out_unlock;
+ }
+ err = profile->ll_ops.keyslot_evict(profile, key,
+ blk_crypto_keyslot_index(slot));
+ if (err)
+ goto out_unlock;
+
+ hlist_del(&slot->hash_node);
+ slot->key = NULL;
+ err = 0;
+out_unlock:
+ blk_crypto_hw_exit(profile);
+ return err;
+}
+
+/**
+ * blk_crypto_reprogram_all_keys() - Re-program all keyslots.
+ * @profile: The crypto profile
+ *
+ * Re-program all keyslots that are supposed to have a key programmed. This is
+ * intended only for use by drivers for hardware that loses its keys on reset.
+ *
+ * Context: Process context. Takes and releases profile->lock.
+ */
+void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile)
+{
+ unsigned int slot;
+
+ if (profile->num_slots == 0)
+ return;
+
+ /* This is for device initialization, so don't resume the device */
+ down_write(&profile->lock);
+ for (slot = 0; slot < profile->num_slots; slot++) {
+ const struct blk_crypto_key *key = profile->slots[slot].key;
+ int err;
+
+ if (!key)
+ continue;
+
+ err = profile->ll_ops.keyslot_program(profile, key, slot);
+ WARN_ON(err);
+ }
+ up_write(&profile->lock);
+}
+EXPORT_SYMBOL_GPL(blk_crypto_reprogram_all_keys);
+
+void blk_crypto_profile_destroy(struct blk_crypto_profile *profile)
+{
+ if (!profile)
+ return;
+ kvfree(profile->slot_hashtable);
+ kvfree_sensitive(profile->slots,
+ sizeof(profile->slots[0]) * profile->num_slots);
+ memzero_explicit(profile, sizeof(*profile));
+}
+EXPORT_SYMBOL_GPL(blk_crypto_profile_destroy);
+
+bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q)
+{
+ if (blk_integrity_queue_supports_integrity(q)) {
+ pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
+ return false;
+ }
+ q->crypto_profile = profile;
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_register);
+
+void blk_crypto_unregister(struct request_queue *q)
+{
+ q->crypto_profile = NULL;
+}
+
+/**
+ * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities
+ * by child device
+ * @parent: the crypto profile for the parent device
+ * @child: the crypto profile for the child device, or NULL
+ *
+ * This clears all crypto capabilities in @parent that aren't set in @child. If
+ * @child is NULL, then this clears all parent capabilities.
+ *
+ * Only use this when setting up the crypto profile for a layered device, before
+ * it's been exposed yet.
+ */
+void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent,
+ const struct blk_crypto_profile *child)
+{
+ if (child) {
+ unsigned int i;
+
+ parent->max_dun_bytes_supported =
+ min(parent->max_dun_bytes_supported,
+ child->max_dun_bytes_supported);
+ for (i = 0; i < ARRAY_SIZE(child->modes_supported); i++)
+ parent->modes_supported[i] &= child->modes_supported[i];
+ } else {
+ parent->max_dun_bytes_supported = 0;
+ memset(parent->modes_supported, 0,
+ sizeof(parent->modes_supported));
+ }
+}
+EXPORT_SYMBOL_GPL(blk_crypto_intersect_capabilities);
+
+/**
+ * blk_crypto_has_capabilities() - Check whether @target supports at least all
+ * the crypto capabilities that @reference does.
+ * @target: the target profile
+ * @reference: the reference profile
+ *
+ * Return: %true if @target supports all the crypto capabilities of @reference.
+ */
+bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target,
+ const struct blk_crypto_profile *reference)
+{
+ int i;
+
+ if (!reference)
+ return true;
+
+ if (!target)
+ return false;
+
+ for (i = 0; i < ARRAY_SIZE(target->modes_supported); i++) {
+ if (reference->modes_supported[i] & ~target->modes_supported[i])
+ return false;
+ }
+
+ if (reference->max_dun_bytes_supported >
+ target->max_dun_bytes_supported)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_has_capabilities);
+
+/**
+ * blk_crypto_update_capabilities() - Update the capabilities of a crypto
+ * profile to match those of another crypto
+ * profile.
+ * @dst: The crypto profile whose capabilities to update.
+ * @src: The crypto profile whose capabilities this function will update @dst's
+ * capabilities to.
+ *
+ * Blk-crypto requires that crypto capabilities that were
+ * advertised when a bio was created continue to be supported by the
+ * device until that bio is ended. This is turn means that a device cannot
+ * shrink its advertised crypto capabilities without any explicit
+ * synchronization with upper layers. So if there's no such explicit
+ * synchronization, @src must support all the crypto capabilities that
+ * @dst does (i.e. we need blk_crypto_has_capabilities(@src, @dst)).
+ *
+ * Note also that as long as the crypto capabilities are being expanded, the
+ * order of updates becoming visible is not important because it's alright
+ * for blk-crypto to see stale values - they only cause blk-crypto to
+ * believe that a crypto capability isn't supported when it actually is (which
+ * might result in blk-crypto-fallback being used if available, or the bio being
+ * failed).
+ */
+void blk_crypto_update_capabilities(struct blk_crypto_profile *dst,
+ const struct blk_crypto_profile *src)
+{
+ memcpy(dst->modes_supported, src->modes_supported,
+ sizeof(dst->modes_supported));
+
+ dst->max_dun_bytes_supported = src->max_dun_bytes_supported;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_update_capabilities);
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 103c2e2d50d6..ec9efeeeca91 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -11,7 +11,7 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -218,8 +218,9 @@ static bool bio_crypt_check_alignment(struct bio *bio)
blk_status_t __blk_crypto_init_request(struct request *rq)
{
- return blk_ksm_get_slot_for_key(rq->q->ksm, rq->crypt_ctx->bc_key,
- &rq->crypt_keyslot);
+ return blk_crypto_get_keyslot(rq->q->crypto_profile,
+ rq->crypt_ctx->bc_key,
+ &rq->crypt_keyslot);
}
/**
@@ -233,7 +234,7 @@ blk_status_t __blk_crypto_init_request(struct request *rq)
*/
void __blk_crypto_free_request(struct request *rq)
{
- blk_ksm_put_slot(rq->crypt_keyslot);
+ blk_crypto_put_keyslot(rq->crypt_keyslot);
mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool);
blk_crypto_rq_set_defaults(rq);
}
@@ -264,6 +265,7 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr)
{
struct bio *bio = *bio_ptr;
const struct blk_crypto_key *bc_key = bio->bi_crypt_context->bc_key;
+ struct blk_crypto_profile *profile;
/* Error if bio has no data. */
if (WARN_ON_ONCE(!bio_has_data(bio))) {
@@ -280,8 +282,8 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr)
* Success if device supports the encryption context, or if we succeeded
* in falling back to the crypto API.
*/
- if (blk_ksm_crypto_cfg_supported(bio->bi_bdev->bd_disk->queue->ksm,
- &bc_key->crypto_cfg))
+ profile = bdev_get_queue(bio->bi_bdev)->crypto_profile;
+ if (__blk_crypto_cfg_supported(profile, &bc_key->crypto_cfg))
return true;
if (blk_crypto_fallback_bio_prep(bio_ptr))
@@ -357,7 +359,7 @@ bool blk_crypto_config_supported(struct request_queue *q,
const struct blk_crypto_config *cfg)
{
return IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) ||
- blk_ksm_crypto_cfg_supported(q->ksm, cfg);
+ __blk_crypto_cfg_supported(q->crypto_profile, cfg);
}
/**
@@ -378,7 +380,7 @@ bool blk_crypto_config_supported(struct request_queue *q,
int blk_crypto_start_using_key(const struct blk_crypto_key *key,
struct request_queue *q)
{
- if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg))
+ if (__blk_crypto_cfg_supported(q->crypto_profile, &key->crypto_cfg))
return 0;
return blk_crypto_fallback_start_using_mode(key->crypto_cfg.crypto_mode);
}
@@ -394,18 +396,17 @@ int blk_crypto_start_using_key(const struct blk_crypto_key *key,
* evicted from any hardware that it might have been programmed into. The key
* must not be in use by any in-flight IO when this function is called.
*
- * Return: 0 on success or if key is not present in the q's ksm, -err on error.
+ * Return: 0 on success or if the key wasn't in any keyslot; -errno on error.
*/
int blk_crypto_evict_key(struct request_queue *q,
const struct blk_crypto_key *key)
{
- if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg))
- return blk_ksm_evict_key(q->ksm, key);
+ if (__blk_crypto_cfg_supported(q->crypto_profile, &key->crypto_cfg))
+ return __blk_crypto_evict_key(q->crypto_profile, key);
/*
- * If the request queue's associated inline encryption hardware didn't
- * have support for the key, then the key might have been programmed
- * into the fallback keyslot manager, so try to evict from there.
+ * If the request_queue didn't support the key, then blk-crypto-fallback
+ * may have been used, so try to evict the key from blk-crypto-fallback.
*/
return blk_crypto_fallback_evict_key(key);
}
diff --git a/block/blk-exec.c b/block/blk-exec.c
index d6cd501c0d34..1b8b47f6e79b 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,13 +65,19 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
static bool blk_rq_is_poll(struct request *rq)
{
- return rq->mq_hctx && rq->mq_hctx->type == HCTX_TYPE_POLL;
+ if (!rq->mq_hctx)
+ return false;
+ if (rq->mq_hctx->type != HCTX_TYPE_POLL)
+ return false;
+ if (WARN_ON_ONCE(!rq->bio))
+ return false;
+ return true;
}
static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
{
do {
- blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), true);
+ bio_poll(rq->bio, NULL, 0);
cond_resched();
} while (!completion_done(wait));
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 4201728bf3a5..8e364bda5166 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -379,7 +379,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
* @rq is being submitted. Analyze what needs to be done and put it on the
* right queue.
*/
-void blk_insert_flush(struct request *rq)
+bool blk_insert_flush(struct request *rq)
{
struct request_queue *q = rq->q;
unsigned long fflags = q->queue_flags; /* may change, cache */
@@ -409,7 +409,7 @@ void blk_insert_flush(struct request *rq)
*/
if (!policy) {
blk_mq_end_request(rq, 0);
- return;
+ return true;
}
BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */
@@ -420,10 +420,8 @@ void blk_insert_flush(struct request *rq)
* for normal execution.
*/
if ((policy & REQ_FSEQ_DATA) &&
- !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
- blk_mq_request_bypass_insert(rq, false, false);
- return;
- }
+ !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH)))
+ return false;
/*
* @rq should go through flush machinery. Mark it part of flush
@@ -439,6 +437,8 @@ void blk_insert_flush(struct request *rq)
spin_lock_irq(&fq->mq_flush_lock);
blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
spin_unlock_irq(&fq->mq_flush_lock);
+
+ return true;
}
/**
diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c
new file mode 100644
index 000000000000..c246c425d0d7
--- /dev/null
+++ b/block/blk-ia-ranges.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Block device concurrent positioning ranges.
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its Affiliates.
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+
+#include "blk.h"
+
+static ssize_t
+blk_ia_range_sector_show(struct blk_independent_access_range *iar,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n", iar->sector);
+}
+
+static ssize_t
+blk_ia_range_nr_sectors_show(struct blk_independent_access_range *iar,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n", iar->nr_sectors);
+}
+
+struct blk_ia_range_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(struct blk_independent_access_range *iar, char *buf);
+};
+
+static struct blk_ia_range_sysfs_entry blk_ia_range_sector_entry = {
+ .attr = { .name = "sector", .mode = 0444 },
+ .show = blk_ia_range_sector_show,
+};
+
+static struct blk_ia_range_sysfs_entry blk_ia_range_nr_sectors_entry = {
+ .attr = { .name = "nr_sectors", .mode = 0444 },
+ .show = blk_ia_range_nr_sectors_show,
+};
+
+static struct attribute *blk_ia_range_attrs[] = {
+ &blk_ia_range_sector_entry.attr,
+ &blk_ia_range_nr_sectors_entry.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(blk_ia_range);
+
+static ssize_t blk_ia_range_sysfs_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct blk_ia_range_sysfs_entry *entry =
+ container_of(attr, struct blk_ia_range_sysfs_entry, attr);
+ struct blk_independent_access_range *iar =
+ container_of(kobj, struct blk_independent_access_range, kobj);
+ ssize_t ret;
+
+ mutex_lock(&iar->queue->sysfs_lock);
+ ret = entry->show(iar, buf);
+ mutex_unlock(&iar->queue->sysfs_lock);
+
+ return ret;
+}
+
+static const struct sysfs_ops blk_ia_range_sysfs_ops = {
+ .show = blk_ia_range_sysfs_show,
+};
+
+/*
+ * Independent access range entries are not freed individually, but alltogether
+ * with struct blk_independent_access_ranges and its array of ranges. Since
+ * kobject_add() takes a reference on the parent kobject contained in
+ * struct blk_independent_access_ranges, the array of independent access range
+ * entries cannot be freed until kobject_del() is called for all entries.
+ * So we do not need to do anything here, but still need this no-op release
+ * operation to avoid complaints from the kobject code.
+ */
+static void blk_ia_range_sysfs_nop_release(struct kobject *kobj)
+{
+}
+
+static struct kobj_type blk_ia_range_ktype = {
+ .sysfs_ops = &blk_ia_range_sysfs_ops,
+ .default_groups = blk_ia_range_groups,
+ .release = blk_ia_range_sysfs_nop_release,
+};
+
+/*
+ * This will be executed only after all independent access range entries are
+ * removed with kobject_del(), at which point, it is safe to free everything,
+ * including the array of ranges.
+ */
+static void blk_ia_ranges_sysfs_release(struct kobject *kobj)
+{
+ struct blk_independent_access_ranges *iars =
+ container_of(kobj, struct blk_independent_access_ranges, kobj);
+
+ kfree(iars);
+}
+
+static struct kobj_type blk_ia_ranges_ktype = {
+ .release = blk_ia_ranges_sysfs_release,
+};
+
+/**
+ * disk_register_ia_ranges - register with sysfs a set of independent
+ * access ranges
+ * @disk: Target disk
+ * @new_iars: New set of independent access ranges
+ *
+ * Register with sysfs a set of independent access ranges for @disk.
+ * If @new_iars is not NULL, this set of ranges is registered and the old set
+ * specified by q->ia_ranges is unregistered. Otherwise, q->ia_ranges is
+ * registered if it is not already.
+ */
+int disk_register_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *new_iars)
+{
+ struct request_queue *q = disk->queue;
+ struct blk_independent_access_ranges *iars;
+ int i, ret;
+
+ lockdep_assert_held(&q->sysfs_dir_lock);
+ lockdep_assert_held(&q->sysfs_lock);
+
+ /* If a new range set is specified, unregister the old one */
+ if (new_iars) {
+ if (q->ia_ranges)
+ disk_unregister_independent_access_ranges(disk);
+ q->ia_ranges = new_iars;
+ }
+
+ iars = q->ia_ranges;
+ if (!iars)
+ return 0;
+
+ /*
+ * At this point, iars is the new set of sector access ranges that needs
+ * to be registered with sysfs.
+ */
+ WARN_ON(iars->sysfs_registered);
+ ret = kobject_init_and_add(&iars->kobj, &blk_ia_ranges_ktype,
+ &q->kobj, "%s", "independent_access_ranges");
+ if (ret) {
+ q->ia_ranges = NULL;
+ kfree(iars);
+ return ret;
+ }
+
+ for (i = 0; i < iars->nr_ia_ranges; i++) {
+ iars->ia_range[i].queue = q;
+ ret = kobject_init_and_add(&iars->ia_range[i].kobj,
+ &blk_ia_range_ktype, &iars->kobj,
+ "%d", i);
+ if (ret) {
+ while (--i >= 0)
+ kobject_del(&iars->ia_range[i].kobj);
+ kobject_del(&iars->kobj);
+ kobject_put(&iars->kobj);
+ return ret;
+ }
+ }
+
+ iars->sysfs_registered = true;
+
+ return 0;
+}
+
+void disk_unregister_independent_access_ranges(struct gendisk *disk)
+{
+ struct request_queue *q = disk->queue;
+ struct blk_independent_access_ranges *iars = q->ia_ranges;
+ int i;
+
+ lockdep_assert_held(&q->sysfs_dir_lock);
+ lockdep_assert_held(&q->sysfs_lock);
+
+ if (!iars)
+ return;
+
+ if (iars->sysfs_registered) {
+ for (i = 0; i < iars->nr_ia_ranges; i++)
+ kobject_del(&iars->ia_range[i].kobj);
+ kobject_del(&iars->kobj);
+ kobject_put(&iars->kobj);
+ } else {
+ kfree(iars);
+ }
+
+ q->ia_ranges = NULL;
+}
+
+static struct blk_independent_access_range *
+disk_find_ia_range(struct blk_independent_access_ranges *iars,
+ sector_t sector)
+{
+ struct blk_independent_access_range *iar;
+ int i;
+
+ for (i = 0; i < iars->nr_ia_ranges; i++) {
+ iar = &iars->ia_range[i];
+ if (sector >= iar->sector &&
+ sector < iar->sector + iar->nr_sectors)
+ return iar;
+ }
+
+ return NULL;
+}
+
+static bool disk_check_ia_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars)
+{
+ struct blk_independent_access_range *iar, *tmp;
+ sector_t capacity = get_capacity(disk);
+ sector_t sector = 0;
+ int i;
+
+ /*
+ * While sorting the ranges in increasing LBA order, check that the
+ * ranges do not overlap, that there are no sector holes and that all
+ * sectors belong to one range.
+ */
+ for (i = 0; i < iars->nr_ia_ranges; i++) {
+ tmp = disk_find_ia_range(iars, sector);
+ if (!tmp || tmp->sector != sector) {
+ pr_warn("Invalid non-contiguous independent access ranges\n");
+ return false;
+ }
+
+ iar = &iars->ia_range[i];
+ if (tmp != iar) {
+ swap(iar->sector, tmp->sector);
+ swap(iar->nr_sectors, tmp->nr_sectors);
+ }
+
+ sector += iar->nr_sectors;
+ }
+
+ if (sector != capacity) {
+ pr_warn("Independent access ranges do not match disk capacity\n");
+ return false;
+ }
+
+ return true;
+}
+
+static bool disk_ia_ranges_changed(struct gendisk *disk,
+ struct blk_independent_access_ranges *new)
+{
+ struct blk_independent_access_ranges *old = disk->queue->ia_ranges;
+ int i;
+
+ if (!old)
+ return true;
+
+ if (old->nr_ia_ranges != new->nr_ia_ranges)
+ return true;
+
+ for (i = 0; i < old->nr_ia_ranges; i++) {
+ if (new->ia_range[i].sector != old->ia_range[i].sector ||
+ new->ia_range[i].nr_sectors != old->ia_range[i].nr_sectors)
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * disk_alloc_independent_access_ranges - Allocate an independent access ranges
+ * data structure
+ * @disk: target disk
+ * @nr_ia_ranges: Number of independent access ranges
+ *
+ * Allocate a struct blk_independent_access_ranges structure with @nr_ia_ranges
+ * access range descriptors.
+ */
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges)
+{
+ struct blk_independent_access_ranges *iars;
+
+ iars = kzalloc_node(struct_size(iars, ia_range, nr_ia_ranges),
+ GFP_KERNEL, disk->queue->node);
+ if (iars)
+ iars->nr_ia_ranges = nr_ia_ranges;
+ return iars;
+}
+EXPORT_SYMBOL_GPL(disk_alloc_independent_access_ranges);
+
+/**
+ * disk_set_independent_access_ranges - Set a disk independent access ranges
+ * @disk: target disk
+ * @iars: independent access ranges structure
+ *
+ * Set the independent access ranges information of the request queue
+ * of @disk to @iars. If @iars is NULL and the independent access ranges
+ * structure already set is cleared. If there are no differences between
+ * @iars and the independent access ranges structure already set, @iars
+ * is freed.
+ */
+void disk_set_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars)
+{
+ struct request_queue *q = disk->queue;
+
+ if (WARN_ON_ONCE(iars && !iars->nr_ia_ranges)) {
+ kfree(iars);
+ iars = NULL;
+ }
+
+ mutex_lock(&q->sysfs_dir_lock);
+ mutex_lock(&q->sysfs_lock);
+
+ if (iars) {
+ if (!disk_check_ia_ranges(disk, iars)) {
+ kfree(iars);
+ iars = NULL;
+ goto reg;
+ }
+
+ if (!disk_ia_ranges_changed(disk, iars)) {
+ kfree(iars);
+ goto unlock;
+ }
+ }
+
+ /*
+ * This may be called for a registered queue. E.g. during a device
+ * revalidation. If that is the case, we need to unregister the old
+ * set of independent access ranges and register the new set. If the
+ * queue is not registered, registration of the device request queue
+ * will register the independent access ranges, so only swap in the
+ * new set and free the old one.
+ */
+reg:
+ if (blk_queue_registered(q)) {
+ disk_register_independent_access_ranges(disk, iars);
+ } else {
+ swap(q->ia_ranges, iars);
+ kfree(iars);
+ }
+
+unlock:
+ mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
+}
+EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 16d5d5338392..d670d54e5f7a 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -6,7 +6,7 @@
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*/
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/backing-dev.h>
#include <linux/mempool.h>
#include <linux/bio.h>
@@ -409,9 +409,9 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- if (disk->queue->ksm) {
+ if (disk->queue->crypto_profile) {
pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
- blk_ksm_unregister(disk->queue);
+ blk_crypto_unregister(disk->queue);
}
#endif
}
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index b3880e4ba22a..a5b37cc65b17 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -3165,12 +3165,12 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
if (IS_ERR(bdev))
return PTR_ERR(bdev);
- ioc = q_to_ioc(bdev->bd_disk->queue);
+ ioc = q_to_ioc(bdev_get_queue(bdev));
if (!ioc) {
- ret = blk_iocost_init(bdev->bd_disk->queue);
+ ret = blk_iocost_init(bdev_get_queue(bdev));
if (ret)
goto err;
- ioc = q_to_ioc(bdev->bd_disk->queue);
+ ioc = q_to_ioc(bdev_get_queue(bdev));
}
spin_lock_irq(&ioc->lock);
@@ -3332,12 +3332,12 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
if (IS_ERR(bdev))
return PTR_ERR(bdev);
- ioc = q_to_ioc(bdev->bd_disk->queue);
+ ioc = q_to_ioc(bdev_get_queue(bdev));
if (!ioc) {
- ret = blk_iocost_init(bdev->bd_disk->queue);
+ ret = blk_iocost_init(bdev_get_queue(bdev));
if (ret)
goto err;
- ioc = q_to_ioc(bdev->bd_disk->queue);
+ ioc = q_to_ioc(bdev_get_queue(bdev));
}
spin_lock_irq(&ioc->lock);
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index c0545f9da549..6593c7123b97 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -74,6 +74,7 @@
#include <linux/sched/signal.h>
#include <trace/events/block.h>
#include <linux/blk-mq.h>
+#include <linux/blk-cgroup.h>
#include "blk-rq-qos.h"
#include "blk-stat.h"
#include "blk.h"
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 7a5c81c02c80..df69f4bb7717 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -6,12 +6,45 @@
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/scatterlist.h>
#include <trace/events/block.h>
#include "blk.h"
#include "blk-rq-qos.h"
+#include "blk-throttle.h"
+
+static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
+{
+ *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+}
+
+static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
+{
+ struct bvec_iter iter = bio->bi_iter;
+ int idx;
+
+ bio_get_first_bvec(bio, bv);
+ if (bv->bv_len == bio->bi_iter.bi_size)
+ return; /* this bio only has a single bvec */
+
+ bio_advance_iter(bio, &iter, iter.bi_size);
+
+ if (!iter.bi_bvec_done)
+ idx = iter.bi_idx - 1;
+ else /* in the middle of bvec */
+ idx = iter.bi_idx;
+
+ *bv = bio->bi_io_vec[idx];
+
+ /*
+ * iter.bi_bvec_done records actual length of the last bvec
+ * if this bio ends in the middle of one io vector
+ */
+ if (iter.bi_bvec_done)
+ bv->bv_len = iter.bi_bvec_done;
+}
static inline bool bio_will_gap(struct request_queue *q,
struct request *prev_rq, struct bio *prev, struct bio *next)
@@ -285,13 +318,13 @@ split:
* iopoll in direct IO routine. Given performance gain of iopoll for
* big IO can be trival, disable iopoll when split needed.
*/
- bio_clear_hipri(bio);
-
+ bio_clear_polled(bio);
return bio_split(bio, sectors, GFP_NOIO, bs);
}
/**
* __blk_queue_split - split a bio and submit the second half
+ * @q: [in] request_queue new bio is being queued at
* @bio: [in, out] bio to be split
* @nr_segs: [out] number of segments in the first bio
*
@@ -302,9 +335,9 @@ split:
* of the caller to ensure that q->bio_split is only released after processing
* of the split bio has finished.
*/
-void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
+void __blk_queue_split(struct request_queue *q, struct bio **bio,
+ unsigned int *nr_segs)
{
- struct request_queue *q = (*bio)->bi_bdev->bd_disk->queue;
struct bio *split = NULL;
switch (bio_op(*bio)) {
@@ -321,21 +354,6 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
nr_segs);
break;
default:
- /*
- * All drivers must accept single-segments bios that are <=
- * PAGE_SIZE. This is a quick and dirty check that relies on
- * the fact that bi_io_vec[0] is always valid if a bio has data.
- * The check might lead to occasional false negatives when bios
- * are cloned, but compared to the performance impact of cloned
- * bios themselves the loop below doesn't matter anyway.
- */
- if (!q->limits.chunk_sectors &&
- (*bio)->bi_vcnt == 1 &&
- ((*bio)->bi_io_vec[0].bv_len +
- (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) {
- *nr_segs = 1;
- break;
- }
split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
break;
}
@@ -365,9 +383,11 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
*/
void blk_queue_split(struct bio **bio)
{
+ struct request_queue *q = bdev_get_queue((*bio)->bi_bdev);
unsigned int nr_segs;
- __blk_queue_split(bio, &nr_segs);
+ if (blk_may_split(q, *bio))
+ __blk_queue_split(q, bio, &nr_segs);
}
EXPORT_SYMBOL(blk_queue_split);
@@ -558,6 +578,23 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq)
return queue_max_segments(rq->q);
}
+static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
+ sector_t offset)
+{
+ struct request_queue *q = rq->q;
+
+ if (blk_rq_is_passthrough(rq))
+ return q->limits.max_hw_sectors;
+
+ if (!q->limits.chunk_sectors ||
+ req_op(rq) == REQ_OP_DISCARD ||
+ req_op(rq) == REQ_OP_SECURE_ERASE)
+ return blk_queue_get_max_sectors(q, req_op(rq));
+
+ return min(blk_max_size_offset(q, offset, 0),
+ blk_queue_get_max_sectors(q, req_op(rq)));
+}
+
static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
unsigned int nr_phys_segs)
{
@@ -718,6 +755,13 @@ static enum elv_merge blk_try_req_merge(struct request *req,
return ELEVATOR_NO_MERGE;
}
+static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
+{
+ if (bio_page(a) == bio_page(b) && bio_offset(a) == bio_offset(b))
+ return true;
+ return false;
+}
+
/*
* For non-mq, this has to be called with the request spinlock acquired.
* For mq with scheduling, the appropriate queue wide lock should be held.
@@ -1023,12 +1067,11 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
* @q: request_queue new bio is being queued at
* @bio: new bio being queued
* @nr_segs: number of segments in @bio
- * @same_queue_rq: pointer to &struct request that gets filled in when
- * another request associated with @q is found on the plug list
- * (optional, may be %NULL)
+ * @same_queue_rq: output value, will be true if there's an existing request
+ * from the passed in @q already in the plug list
*
- * Determine whether @bio being queued on @q can be merged with a request
- * on %current's plugged list. Returns %true if merge was successful,
+ * Determine whether @bio being queued on @q can be merged with the previous
+ * request on %current's plugged list. Returns %true if merge was successful,
* otherwise %false.
*
* Plugging coalesces IOs from the same issuer for the same purpose without
@@ -1041,36 +1084,26 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
* Caller must ensure !blk_queue_nomerges(q) beforehand.
*/
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int nr_segs, struct request **same_queue_rq)
+ unsigned int nr_segs, bool *same_queue_rq)
{
struct blk_plug *plug;
struct request *rq;
- struct list_head *plug_list;
plug = blk_mq_plug(q, bio);
- if (!plug)
+ if (!plug || rq_list_empty(plug->mq_list))
return false;
- plug_list = &plug->mq_list;
-
- list_for_each_entry_reverse(rq, plug_list, queuelist) {
- if (rq->q == q && same_queue_rq) {
- /*
- * Only blk-mq multiple hardware queues case checks the
- * rq in the same queue, there should be only one such
- * rq in a queue
- **/
- *same_queue_rq = rq;
- }
-
- if (rq->q != q)
- continue;
-
- if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
- BIO_MERGE_OK)
- return true;
+ /* check the previously added entry for a quick merge attempt */
+ rq = rq_list_peek(&plug->mq_list);
+ if (rq->q == q) {
+ /*
+ * Only blk-mq multiple hardware queues case checks the rq in
+ * the same queue, there should be only one such rq in a queue
+ */
+ *same_queue_rq = true;
}
-
+ if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK)
+ return true;
return false;
}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3b38d15723de..f5076c173477 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -124,7 +124,6 @@ static const char *const blk_queue_flag_name[] = {
QUEUE_FLAG_NAME(STATS),
QUEUE_FLAG_NAME(POLL_STATS),
QUEUE_FLAG_NAME(REGISTERED),
- QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
QUEUE_FLAG_NAME(QUIESCED),
QUEUE_FLAG_NAME(PCI_P2PDMA),
QUEUE_FLAG_NAME(ZONE_RESETALL),
@@ -287,7 +286,7 @@ static const char *const cmd_flag_name[] = {
CMD_FLAG_NAME(BACKGROUND),
CMD_FLAG_NAME(NOWAIT),
CMD_FLAG_NAME(NOUNMAP),
- CMD_FLAG_NAME(HIPRI),
+ CMD_FLAG_NAME(POLLED),
};
#undef CMD_FLAG_NAME
@@ -453,11 +452,11 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m,
atomic_read(&tags->active_queues));
seq_puts(m, "\nbitmap_tags:\n");
- sbitmap_queue_show(tags->bitmap_tags, m);
+ sbitmap_queue_show(&tags->bitmap_tags, m);
if (tags->nr_reserved_tags) {
seq_puts(m, "\nbreserved_tags:\n");
- sbitmap_queue_show(tags->breserved_tags, m);
+ sbitmap_queue_show(&tags->breserved_tags, m);
}
}
@@ -488,7 +487,7 @@ static int hctx_tags_bitmap_show(void *data, struct seq_file *m)
if (res)
goto out;
if (hctx->tags)
- sbitmap_bitmap_show(&hctx->tags->bitmap_tags->sb, m);
+ sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
mutex_unlock(&q->sysfs_lock);
out:
@@ -522,77 +521,13 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
if (res)
goto out;
if (hctx->sched_tags)
- sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags->sb, m);
+ sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
mutex_unlock(&q->sysfs_lock);
out:
return res;
}
-static int hctx_io_poll_show(void *data, struct seq_file *m)
-{
- struct blk_mq_hw_ctx *hctx = data;
-
- seq_printf(m, "considered=%lu\n", hctx->poll_considered);
- seq_printf(m, "invoked=%lu\n", hctx->poll_invoked);
- seq_printf(m, "success=%lu\n", hctx->poll_success);
- return 0;
-}
-
-static ssize_t hctx_io_poll_write(void *data, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct blk_mq_hw_ctx *hctx = data;
-
- hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
- return count;
-}
-
-static int hctx_dispatched_show(void *data, struct seq_file *m)
-{
- struct blk_mq_hw_ctx *hctx = data;
- int i;
-
- seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
-
- for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
- unsigned int d = 1U << (i - 1);
-
- seq_printf(m, "%8u\t%lu\n", d, hctx->dispatched[i]);
- }
-
- seq_printf(m, "%8u+\t%lu\n", 1U << (i - 1), hctx->dispatched[i]);
- return 0;
-}
-
-static ssize_t hctx_dispatched_write(void *data, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct blk_mq_hw_ctx *hctx = data;
- int i;
-
- for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++)
- hctx->dispatched[i] = 0;
- return count;
-}
-
-static int hctx_queued_show(void *data, struct seq_file *m)
-{
- struct blk_mq_hw_ctx *hctx = data;
-
- seq_printf(m, "%lu\n", hctx->queued);
- return 0;
-}
-
-static ssize_t hctx_queued_write(void *data, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct blk_mq_hw_ctx *hctx = data;
-
- hctx->queued = 0;
- return count;
-}
-
static int hctx_run_show(void *data, struct seq_file *m)
{
struct blk_mq_hw_ctx *hctx = data;
@@ -614,7 +549,7 @@ static int hctx_active_show(void *data, struct seq_file *m)
{
struct blk_mq_hw_ctx *hctx = data;
- seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
+ seq_printf(m, "%d\n", __blk_mq_active_requests(hctx));
return 0;
}
@@ -663,57 +598,6 @@ CTX_RQ_SEQ_OPS(default, HCTX_TYPE_DEFAULT);
CTX_RQ_SEQ_OPS(read, HCTX_TYPE_READ);
CTX_RQ_SEQ_OPS(poll, HCTX_TYPE_POLL);
-static int ctx_dispatched_show(void *data, struct seq_file *m)
-{
- struct blk_mq_ctx *ctx = data;
-
- seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
- return 0;
-}
-
-static ssize_t ctx_dispatched_write(void *data, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct blk_mq_ctx *ctx = data;
-
- ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
- return count;
-}
-
-static int ctx_merged_show(void *data, struct seq_file *m)
-{
- struct blk_mq_ctx *ctx = data;
-
- seq_printf(m, "%lu\n", ctx->rq_merged);
- return 0;
-}
-
-static ssize_t ctx_merged_write(void *data, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct blk_mq_ctx *ctx = data;
-
- ctx->rq_merged = 0;
- return count;
-}
-
-static int ctx_completed_show(void *data, struct seq_file *m)
-{
- struct blk_mq_ctx *ctx = data;
-
- seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
- return 0;
-}
-
-static ssize_t ctx_completed_write(void *data, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct blk_mq_ctx *ctx = data;
-
- ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
- return count;
-}
-
static int blk_mq_debugfs_show(struct seq_file *m, void *v)
{
const struct blk_mq_debugfs_attr *attr = m->private;
@@ -789,9 +673,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
{"tags_bitmap", 0400, hctx_tags_bitmap_show},
{"sched_tags", 0400, hctx_sched_tags_show},
{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
- {"io_poll", 0600, hctx_io_poll_show, hctx_io_poll_write},
- {"dispatched", 0600, hctx_dispatched_show, hctx_dispatched_write},
- {"queued", 0600, hctx_queued_show, hctx_queued_write},
{"run", 0600, hctx_run_show, hctx_run_write},
{"active", 0400, hctx_active_show},
{"dispatch_busy", 0400, hctx_dispatch_busy_show},
@@ -803,9 +684,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
{"default_rq_list", 0400, .seq_ops = &ctx_default_rq_list_seq_ops},
{"read_rq_list", 0400, .seq_ops = &ctx_read_rq_list_seq_ops},
{"poll_rq_list", 0400, .seq_ops = &ctx_poll_rq_list_seq_ops},
- {"dispatched", 0600, ctx_dispatched_show, ctx_dispatched_write},
- {"merged", 0600, ctx_merged_show, ctx_merged_write},
- {"completed", 0600, ctx_completed_show, ctx_completed_write},
{},
};
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 0f006cabfd91..c62b966dfaba 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -57,10 +57,8 @@ void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
}
EXPORT_SYMBOL_GPL(blk_mq_sched_mark_restart_hctx);
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
+void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
{
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- return;
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
/*
@@ -363,7 +361,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
}
}
-bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
+bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs)
{
struct elevator_queue *e = q->elevator;
@@ -389,13 +387,10 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
* potentially merge with. Currently includes a hand-wavy stop
* count of 8, to not spend too much time checking for merges.
*/
- if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
- ctx->rq_merged++;
+ if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs))
ret = true;
- }
spin_unlock(&ctx->lock);
-
return ret;
}
@@ -515,83 +510,71 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
percpu_ref_put(&q->q_usage_counter);
}
-static int blk_mq_sched_alloc_tags(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
- unsigned int hctx_idx)
+static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q,
+ struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
{
- struct blk_mq_tag_set *set = q->tag_set;
- int ret;
+ if (blk_mq_is_shared_tags(q->tag_set->flags)) {
+ hctx->sched_tags = q->sched_shared_tags;
+ return 0;
+ }
+
+ hctx->sched_tags = blk_mq_alloc_map_and_rqs(q->tag_set, hctx_idx,
+ q->nr_requests);
- hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
- set->reserved_tags, set->flags);
if (!hctx->sched_tags)
return -ENOMEM;
+ return 0;
+}
- ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
- if (ret) {
- blk_mq_free_rq_map(hctx->sched_tags, set->flags);
- hctx->sched_tags = NULL;
- }
-
- return ret;
+static void blk_mq_exit_sched_shared_tags(struct request_queue *queue)
+{
+ blk_mq_free_rq_map(queue->sched_shared_tags);
+ queue->sched_shared_tags = NULL;
}
/* called in queue's release handler, tagset has gone away */
-static void blk_mq_sched_tags_teardown(struct request_queue *q)
+static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags)
{
struct blk_mq_hw_ctx *hctx;
int i;
queue_for_each_hw_ctx(q, hctx, i) {
if (hctx->sched_tags) {
- blk_mq_free_rq_map(hctx->sched_tags, hctx->flags);
+ if (!blk_mq_is_shared_tags(flags))
+ blk_mq_free_rq_map(hctx->sched_tags);
hctx->sched_tags = NULL;
}
}
+
+ if (blk_mq_is_shared_tags(flags))
+ blk_mq_exit_sched_shared_tags(q);
}
-static int blk_mq_init_sched_shared_sbitmap(struct request_queue *queue)
+static int blk_mq_init_sched_shared_tags(struct request_queue *queue)
{
struct blk_mq_tag_set *set = queue->tag_set;
- int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags);
- struct blk_mq_hw_ctx *hctx;
- int ret, i;
/*
* Set initial depth at max so that we don't need to reallocate for
* updating nr_requests.
*/
- ret = blk_mq_init_bitmaps(&queue->sched_bitmap_tags,
- &queue->sched_breserved_tags,
- MAX_SCHED_RQ, set->reserved_tags,
- set->numa_node, alloc_policy);
- if (ret)
- return ret;
-
- queue_for_each_hw_ctx(queue, hctx, i) {
- hctx->sched_tags->bitmap_tags =
- &queue->sched_bitmap_tags;
- hctx->sched_tags->breserved_tags =
- &queue->sched_breserved_tags;
- }
+ queue->sched_shared_tags = blk_mq_alloc_map_and_rqs(set,
+ BLK_MQ_NO_HCTX_IDX,
+ MAX_SCHED_RQ);
+ if (!queue->sched_shared_tags)
+ return -ENOMEM;
- sbitmap_queue_resize(&queue->sched_bitmap_tags,
- queue->nr_requests - set->reserved_tags);
+ blk_mq_tag_update_sched_shared_tags(queue);
return 0;
}
-static void blk_mq_exit_sched_shared_sbitmap(struct request_queue *queue)
-{
- sbitmap_queue_free(&queue->sched_bitmap_tags);
- sbitmap_queue_free(&queue->sched_breserved_tags);
-}
-
int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
{
+ unsigned int i, flags = q->tag_set->flags;
struct blk_mq_hw_ctx *hctx;
struct elevator_queue *eq;
- unsigned int i;
int ret;
if (!e) {
@@ -606,23 +589,23 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
* Additionally, this is a per-hw queue depth.
*/
q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth,
- BLKDEV_MAX_RQ);
+ BLKDEV_DEFAULT_RQ);
- queue_for_each_hw_ctx(q, hctx, i) {
- ret = blk_mq_sched_alloc_tags(q, hctx, i);
+ if (blk_mq_is_shared_tags(flags)) {
+ ret = blk_mq_init_sched_shared_tags(q);
if (ret)
- goto err_free_tags;
+ return ret;
}
- if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) {
- ret = blk_mq_init_sched_shared_sbitmap(q);
+ queue_for_each_hw_ctx(q, hctx, i) {
+ ret = blk_mq_sched_alloc_map_and_rqs(q, hctx, i);
if (ret)
- goto err_free_tags;
+ goto err_free_map_and_rqs;
}
ret = e->ops.init_sched(q, e);
if (ret)
- goto err_free_sbitmap;
+ goto err_free_map_and_rqs;
blk_mq_debugfs_register_sched(q);
@@ -631,7 +614,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
ret = e->ops.init_hctx(hctx, i);
if (ret) {
eq = q->elevator;
- blk_mq_sched_free_requests(q);
+ blk_mq_sched_free_rqs(q);
blk_mq_exit_sched(q, eq);
kobject_put(&eq->kobj);
return ret;
@@ -642,12 +625,10 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
return 0;
-err_free_sbitmap:
- if (blk_mq_is_sbitmap_shared(q->tag_set->flags))
- blk_mq_exit_sched_shared_sbitmap(q);
-err_free_tags:
- blk_mq_sched_free_requests(q);
- blk_mq_sched_tags_teardown(q);
+err_free_map_and_rqs:
+ blk_mq_sched_free_rqs(q);
+ blk_mq_sched_tags_teardown(q, flags);
+
q->elevator = NULL;
return ret;
}
@@ -656,14 +637,20 @@ err_free_tags:
* called in either blk_queue_cleanup or elevator_switch, tagset
* is required for freeing requests
*/
-void blk_mq_sched_free_requests(struct request_queue *q)
+void blk_mq_sched_free_rqs(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
int i;
- queue_for_each_hw_ctx(q, hctx, i) {
- if (hctx->sched_tags)
- blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i);
+ if (blk_mq_is_shared_tags(q->tag_set->flags)) {
+ blk_mq_free_rqs(q->tag_set, q->sched_shared_tags,
+ BLK_MQ_NO_HCTX_IDX);
+ } else {
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (hctx->sched_tags)
+ blk_mq_free_rqs(q->tag_set,
+ hctx->sched_tags, i);
+ }
}
}
@@ -684,8 +671,6 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
blk_mq_debugfs_unregister_sched(q);
if (e->type->ops.exit_sched)
e->type->ops.exit_sched(e);
- blk_mq_sched_tags_teardown(q);
- if (blk_mq_is_sbitmap_shared(flags))
- blk_mq_exit_sched_shared_sbitmap(q);
+ blk_mq_sched_tags_teardown(q, flags);
q->elevator = NULL;
}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 5246ae040704..25d1034952b6 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -2,21 +2,22 @@
#ifndef BLK_MQ_SCHED_H
#define BLK_MQ_SCHED_H
+#include "elevator.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
-#define MAX_SCHED_RQ (16 * BLKDEV_MAX_RQ)
+#define MAX_SCHED_RQ (16 * BLKDEV_DEFAULT_RQ)
void blk_mq_sched_assign_ioc(struct request *rq);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs, struct request **merged_request);
-bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
+bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq,
struct list_head *free);
void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx);
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
+void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
bool run_queue, bool async);
@@ -28,45 +29,51 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
-void blk_mq_sched_free_requests(struct request_queue *q);
+void blk_mq_sched_free_rqs(struct request_queue *q);
-static inline bool
-blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
- unsigned int nr_segs)
+static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
{
- if (blk_queue_nomerges(q) || !bio_mergeable(bio))
- return false;
+ if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ __blk_mq_sched_restart(hctx);
+}
- return __blk_mq_sched_bio_merge(q, bio, nr_segs);
+static inline bool bio_mergeable(struct bio *bio)
+{
+ return !(bio->bi_opf & REQ_NOMERGE_FLAGS);
}
static inline bool
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
{
- struct elevator_queue *e = q->elevator;
-
- if (e && e->type->ops.allow_merge)
- return e->type->ops.allow_merge(q, rq, bio);
+ if (rq->rq_flags & RQF_ELV) {
+ struct elevator_queue *e = q->elevator;
+ if (e->type->ops.allow_merge)
+ return e->type->ops.allow_merge(q, rq, bio);
+ }
return true;
}
static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
{
- struct elevator_queue *e = rq->q->elevator;
+ if (rq->rq_flags & RQF_ELV) {
+ struct elevator_queue *e = rq->q->elevator;
- if (e && e->type->ops.completed_request)
- e->type->ops.completed_request(rq, now);
+ if (e->type->ops.completed_request)
+ e->type->ops.completed_request(rq, now);
+ }
}
static inline void blk_mq_sched_requeue_request(struct request *rq)
{
- struct request_queue *q = rq->q;
- struct elevator_queue *e = q->elevator;
+ if (rq->rq_flags & RQF_ELV) {
+ struct request_queue *q = rq->q;
+ struct elevator_queue *e = q->elevator;
- if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
- e->type->ops.requeue_request(rq);
+ if ((rq->rq_flags & RQF_ELVPRIV) && e->type->ops.requeue_request)
+ e->type->ops.requeue_request(rq);
+ }
}
static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index ff5caeb82542..995336abee33 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -24,13 +24,12 @@
*/
bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
- if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+ if (blk_mq_is_shared_tags(hctx->flags)) {
struct request_queue *q = hctx->queue;
- struct blk_mq_tag_set *set = q->tag_set;
if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
!test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
- atomic_inc(&set->active_queues_shared_sbitmap);
+ atomic_inc(&hctx->tags->active_queues);
} else {
if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
!test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
@@ -45,9 +44,9 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
*/
void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
{
- sbitmap_queue_wake_all(tags->bitmap_tags);
+ sbitmap_queue_wake_all(&tags->bitmap_tags);
if (include_reserve)
- sbitmap_queue_wake_all(tags->breserved_tags);
+ sbitmap_queue_wake_all(&tags->breserved_tags);
}
/*
@@ -57,20 +56,20 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
{
struct blk_mq_tags *tags = hctx->tags;
- struct request_queue *q = hctx->queue;
- struct blk_mq_tag_set *set = q->tag_set;
- if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+ if (blk_mq_is_shared_tags(hctx->flags)) {
+ struct request_queue *q = hctx->queue;
+
if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
&q->queue_flags))
return;
- atomic_dec(&set->active_queues_shared_sbitmap);
} else {
if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
return;
- atomic_dec(&tags->active_queues);
}
+ atomic_dec(&tags->active_queues);
+
blk_mq_tag_wakeup_all(tags, false);
}
@@ -87,6 +86,21 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
return __sbitmap_queue_get(bt);
}
+unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,
+ unsigned int *offset)
+{
+ struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ struct sbitmap_queue *bt = &tags->bitmap_tags;
+ unsigned long ret;
+
+ if (data->shallow_depth ||data->flags & BLK_MQ_REQ_RESERVED ||
+ data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+ return 0;
+ ret = __sbitmap_queue_get_batch(bt, nr_tags, offset);
+ *offset += tags->nr_reserved_tags;
+ return ret;
+}
+
unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
{
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
@@ -101,10 +115,10 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
WARN_ON_ONCE(1);
return BLK_MQ_NO_TAG;
}
- bt = tags->breserved_tags;
+ bt = &tags->breserved_tags;
tag_offset = 0;
} else {
- bt = tags->bitmap_tags;
+ bt = &tags->bitmap_tags;
tag_offset = tags->nr_reserved_tags;
}
@@ -150,9 +164,9 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
data->ctx);
tags = blk_mq_tags_from_data(data);
if (data->flags & BLK_MQ_REQ_RESERVED)
- bt = tags->breserved_tags;
+ bt = &tags->breserved_tags;
else
- bt = tags->bitmap_tags;
+ bt = &tags->bitmap_tags;
/*
* If destination hw queue is changed, fake wake up on
@@ -186,13 +200,19 @@ void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
const int real_tag = tag - tags->nr_reserved_tags;
BUG_ON(real_tag >= tags->nr_tags);
- sbitmap_queue_clear(tags->bitmap_tags, real_tag, ctx->cpu);
+ sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu);
} else {
BUG_ON(tag >= tags->nr_reserved_tags);
- sbitmap_queue_clear(tags->breserved_tags, tag, ctx->cpu);
+ sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu);
}
}
+void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags)
+{
+ sbitmap_queue_clear_batch(&tags->bitmap_tags, tags->nr_reserved_tags,
+ tag_array, nr_tags);
+}
+
struct bt_iter_data {
struct blk_mq_hw_ctx *hctx;
busy_iter_fn *fn;
@@ -340,9 +360,9 @@ static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags,
WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED);
if (tags->nr_reserved_tags)
- bt_tags_for_each(tags, tags->breserved_tags, fn, priv,
+ bt_tags_for_each(tags, &tags->breserved_tags, fn, priv,
flags | BT_TAG_ITER_RESERVED);
- bt_tags_for_each(tags, tags->bitmap_tags, fn, priv, flags);
+ bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags);
}
/**
@@ -379,9 +399,12 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv)
{
- int i;
+ unsigned int flags = tagset->flags;
+ int i, nr_tags;
+
+ nr_tags = blk_mq_is_shared_tags(flags) ? 1 : tagset->nr_hw_queues;
- for (i = 0; i < tagset->nr_hw_queues; i++) {
+ for (i = 0; i < nr_tags; i++) {
if (tagset->tags && tagset->tags[i])
__blk_mq_all_tag_iter(tagset->tags[i], fn, priv,
BT_TAG_ITER_STARTED);
@@ -459,8 +482,8 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
continue;
if (tags->nr_reserved_tags)
- bt_for_each(hctx, tags->breserved_tags, fn, priv, true);
- bt_for_each(hctx, tags->bitmap_tags, fn, priv, false);
+ bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
+ bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
}
blk_queue_exit(q);
}
@@ -492,56 +515,10 @@ free_bitmap_tags:
return -ENOMEM;
}
-static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
- int node, int alloc_policy)
-{
- int ret;
-
- ret = blk_mq_init_bitmaps(&tags->__bitmap_tags,
- &tags->__breserved_tags,
- tags->nr_tags, tags->nr_reserved_tags,
- node, alloc_policy);
- if (ret)
- return ret;
-
- tags->bitmap_tags = &tags->__bitmap_tags;
- tags->breserved_tags = &tags->__breserved_tags;
-
- return 0;
-}
-
-int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set)
-{
- int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags);
- int i, ret;
-
- ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags,
- set->queue_depth, set->reserved_tags,
- set->numa_node, alloc_policy);
- if (ret)
- return ret;
-
- for (i = 0; i < set->nr_hw_queues; i++) {
- struct blk_mq_tags *tags = set->tags[i];
-
- tags->bitmap_tags = &set->__bitmap_tags;
- tags->breserved_tags = &set->__breserved_tags;
- }
-
- return 0;
-}
-
-void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set)
-{
- sbitmap_queue_free(&set->__bitmap_tags);
- sbitmap_queue_free(&set->__breserved_tags);
-}
-
struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
unsigned int reserved_tags,
- int node, unsigned int flags)
+ int node, int alloc_policy)
{
- int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags);
struct blk_mq_tags *tags;
if (total_tags > BLK_MQ_TAG_MAX) {
@@ -557,22 +534,19 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
tags->nr_reserved_tags = reserved_tags;
spin_lock_init(&tags->lock);
- if (blk_mq_is_sbitmap_shared(flags))
- return tags;
-
- if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) {
+ if (blk_mq_init_bitmaps(&tags->bitmap_tags, &tags->breserved_tags,
+ total_tags, reserved_tags, node,
+ alloc_policy) < 0) {
kfree(tags);
return NULL;
}
return tags;
}
-void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags)
+void blk_mq_free_tags(struct blk_mq_tags *tags)
{
- if (!blk_mq_is_sbitmap_shared(flags)) {
- sbitmap_queue_free(tags->bitmap_tags);
- sbitmap_queue_free(tags->breserved_tags);
- }
+ sbitmap_queue_free(&tags->bitmap_tags);
+ sbitmap_queue_free(&tags->breserved_tags);
kfree(tags);
}
@@ -592,7 +566,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
if (tdepth > tags->nr_tags) {
struct blk_mq_tag_set *set = hctx->queue->tag_set;
struct blk_mq_tags *new;
- bool ret;
if (!can_grow)
return -EINVAL;
@@ -604,34 +577,42 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
if (tdepth > MAX_SCHED_RQ)
return -EINVAL;
- new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth,
- tags->nr_reserved_tags, set->flags);
+ /*
+ * Only the sbitmap needs resizing since we allocated the max
+ * initially.
+ */
+ if (blk_mq_is_shared_tags(set->flags))
+ return 0;
+
+ new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth);
if (!new)
return -ENOMEM;
- ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
- if (ret) {
- blk_mq_free_rq_map(new, set->flags);
- return -ENOMEM;
- }
- blk_mq_free_rqs(set, *tagsptr, hctx->queue_num);
- blk_mq_free_rq_map(*tagsptr, set->flags);
+ blk_mq_free_map_and_rqs(set, *tagsptr, hctx->queue_num);
*tagsptr = new;
} else {
/*
* Don't need (or can't) update reserved tags here, they
* remain static and should never need resizing.
*/
- sbitmap_queue_resize(tags->bitmap_tags,
+ sbitmap_queue_resize(&tags->bitmap_tags,
tdepth - tags->nr_reserved_tags);
}
return 0;
}
-void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size)
+void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size)
+{
+ struct blk_mq_tags *tags = set->shared_tags;
+
+ sbitmap_queue_resize(&tags->bitmap_tags, size - set->reserved_tags);
+}
+
+void blk_mq_tag_update_sched_shared_tags(struct request_queue *q)
{
- sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags);
+ sbitmap_queue_resize(&q->sched_shared_tags->bitmap_tags,
+ q->nr_requests - q->tag_set->reserved_tags);
}
/**
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 8ed55af08427..df787b5a23bd 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -2,52 +2,30 @@
#ifndef INT_BLK_MQ_TAG_H
#define INT_BLK_MQ_TAG_H
-/*
- * Tag address space map.
- */
-struct blk_mq_tags {
- unsigned int nr_tags;
- unsigned int nr_reserved_tags;
-
- atomic_t active_queues;
-
- struct sbitmap_queue *bitmap_tags;
- struct sbitmap_queue *breserved_tags;
-
- struct sbitmap_queue __bitmap_tags;
- struct sbitmap_queue __breserved_tags;
-
- struct request **rqs;
- struct request **static_rqs;
- struct list_head page_list;
-
- /*
- * used to clear request reference in rqs[] before freeing one
- * request pool
- */
- spinlock_t lock;
-};
+struct blk_mq_alloc_data;
extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
unsigned int reserved_tags,
- int node, unsigned int flags);
-extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags);
+ int node, int alloc_policy);
+extern void blk_mq_free_tags(struct blk_mq_tags *tags);
extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
struct sbitmap_queue *breserved_tags,
unsigned int queue_depth,
unsigned int reserved,
int node, int alloc_policy);
-extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set);
-extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set);
extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
+unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,
+ unsigned int *offset);
extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
unsigned int tag);
+void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags);
extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
struct blk_mq_tags **tags,
unsigned int depth, bool can_grow);
-extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set,
+extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set,
unsigned int size);
+extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q);
extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index bc026372de43..07eb1412760b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -10,14 +10,15 @@
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/kmemleak.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
+#include <linux/interrupt.h>
#include <linux/llist.h>
-#include <linux/list_sort.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
@@ -63,6 +64,32 @@ static int blk_mq_poll_stats_bkt(const struct request *rq)
return bucket;
}
+#define BLK_QC_T_SHIFT 16
+#define BLK_QC_T_INTERNAL (1U << 31)
+
+static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
+ blk_qc_t qc)
+{
+ return q->queue_hw_ctx[(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT];
+}
+
+static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
+ blk_qc_t qc)
+{
+ unsigned int tag = qc & ((1U << BLK_QC_T_SHIFT) - 1);
+
+ if (qc & BLK_QC_T_INTERNAL)
+ return blk_mq_tag_to_rq(hctx->sched_tags, tag);
+ return blk_mq_tag_to_rq(hctx->tags, tag);
+}
+
+static inline blk_qc_t blk_rq_to_qc(struct request *rq)
+{
+ return (rq->mq_hctx->queue_num << BLK_QC_T_SHIFT) |
+ (rq->tag != -1 ?
+ rq->tag : (rq->internal_tag | BLK_QC_T_INTERNAL));
+}
+
/*
* Check if any of the ctx, dispatch list or elevator
* have pending work in this hardware queue.
@@ -214,7 +241,12 @@ EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
*/
void blk_mq_quiesce_queue_nowait(struct request_queue *q)
{
- blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->queue_lock, flags);
+ if (!q->quiesce_depth++)
+ blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+ spin_unlock_irqrestore(&q->queue_lock, flags);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
@@ -255,10 +287,21 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
*/
void blk_mq_unquiesce_queue(struct request_queue *q)
{
- blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ unsigned long flags;
+ bool run_queue = false;
+
+ spin_lock_irqsave(&q->queue_lock, flags);
+ if (WARN_ON_ONCE(q->quiesce_depth <= 0)) {
+ ;
+ } else if (!--q->quiesce_depth) {
+ blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ run_queue = true;
+ }
+ spin_unlock_irqrestore(&q->queue_lock, flags);
/* dispatch requests which are inserted during quiescing */
- blk_mq_run_hw_queues(q, true);
+ if (run_queue)
+ blk_mq_run_hw_queues(q, true);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
@@ -272,74 +315,67 @@ void blk_mq_wake_waiters(struct request_queue *q)
blk_mq_tag_wakeup_all(hctx->tags, true);
}
-/*
- * Only need start/end time stamping if we have iostat or
- * blk stats enabled, or using an IO scheduler.
- */
-static inline bool blk_mq_need_time_stamp(struct request *rq)
-{
- return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator;
-}
-
static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
- unsigned int tag, u64 alloc_time_ns)
+ struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns)
{
- struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ struct blk_mq_ctx *ctx = data->ctx;
+ struct blk_mq_hw_ctx *hctx = data->hctx;
+ struct request_queue *q = data->q;
struct request *rq = tags->static_rqs[tag];
- if (data->q->elevator) {
- rq->tag = BLK_MQ_NO_TAG;
- rq->internal_tag = tag;
- } else {
+ rq->q = q;
+ rq->mq_ctx = ctx;
+ rq->mq_hctx = hctx;
+ rq->cmd_flags = data->cmd_flags;
+
+ if (data->flags & BLK_MQ_REQ_PM)
+ data->rq_flags |= RQF_PM;
+ if (blk_queue_io_stat(q))
+ data->rq_flags |= RQF_IO_STAT;
+ rq->rq_flags = data->rq_flags;
+
+ if (!(data->rq_flags & RQF_ELV)) {
rq->tag = tag;
rq->internal_tag = BLK_MQ_NO_TAG;
+ } else {
+ rq->tag = BLK_MQ_NO_TAG;
+ rq->internal_tag = tag;
}
+ rq->timeout = 0;
- /* csd/requeue_work/fifo_time is initialized before use */
- rq->q = data->q;
- rq->mq_ctx = data->ctx;
- rq->mq_hctx = data->hctx;
- rq->rq_flags = 0;
- rq->cmd_flags = data->cmd_flags;
- if (data->flags & BLK_MQ_REQ_PM)
- rq->rq_flags |= RQF_PM;
- if (blk_queue_io_stat(data->q))
- rq->rq_flags |= RQF_IO_STAT;
- INIT_LIST_HEAD(&rq->queuelist);
- INIT_HLIST_NODE(&rq->hash);
- RB_CLEAR_NODE(&rq->rb_node);
+ if (blk_mq_need_time_stamp(rq))
+ rq->start_time_ns = ktime_get_ns();
+ else
+ rq->start_time_ns = 0;
rq->rq_disk = NULL;
rq->part = NULL;
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
rq->alloc_time_ns = alloc_time_ns;
#endif
- if (blk_mq_need_time_stamp(rq))
- rq->start_time_ns = ktime_get_ns();
- else
- rq->start_time_ns = 0;
rq->io_start_time_ns = 0;
rq->stats_sectors = 0;
rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
rq->nr_integrity_segments = 0;
#endif
- blk_crypto_rq_set_defaults(rq);
- /* tag was already set */
- WRITE_ONCE(rq->deadline, 0);
-
- rq->timeout = 0;
-
rq->end_io = NULL;
rq->end_io_data = NULL;
- data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++;
+ blk_crypto_rq_set_defaults(rq);
+ INIT_LIST_HEAD(&rq->queuelist);
+ /* tag was already set */
+ WRITE_ONCE(rq->deadline, 0);
refcount_set(&rq->ref, 1);
- if (!op_is_flush(data->cmd_flags)) {
+ if (rq->rq_flags & RQF_ELV) {
struct elevator_queue *e = data->q->elevator;
rq->elv.icq = NULL;
- if (e && e->type->ops.prepare_request) {
+ INIT_HLIST_NODE(&rq->hash);
+ RB_CLEAR_NODE(&rq->rb_node);
+
+ if (!op_is_flush(data->cmd_flags) &&
+ e->type->ops.prepare_request) {
if (e->type->icq_cache)
blk_mq_sched_assign_ioc(rq);
@@ -348,15 +384,44 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
}
}
- data->hctx->queued++;
return rq;
}
-static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
+static inline struct request *
+__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
+ u64 alloc_time_ns)
+{
+ unsigned int tag, tag_offset;
+ struct blk_mq_tags *tags;
+ struct request *rq;
+ unsigned long tag_mask;
+ int i, nr = 0;
+
+ tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
+ if (unlikely(!tag_mask))
+ return NULL;
+
+ tags = blk_mq_tags_from_data(data);
+ for (i = 0; tag_mask; i++) {
+ if (!(tag_mask & (1UL << i)))
+ continue;
+ prefetch(tags->static_rqs[tag]);
+ tag = tag_offset + i;
+ tag_mask &= ~(1UL << i);
+ rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
+ rq_list_add(data->cached_rq, rq);
+ }
+ data->nr_tags -= nr;
+
+ return rq_list_pop(data->cached_rq);
+}
+
+static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
{
struct request_queue *q = data->q;
struct elevator_queue *e = q->elevator;
u64 alloc_time_ns = 0;
+ struct request *rq;
unsigned int tag;
/* alloc_time includes depth and tag waits */
@@ -386,6 +451,16 @@ retry:
blk_mq_tag_busy(data->hctx);
/*
+ * Try batched alloc if we want more than 1 tag.
+ */
+ if (data->nr_tags > 1) {
+ rq = __blk_mq_alloc_requests_batch(data, alloc_time_ns);
+ if (rq)
+ return rq;
+ data->nr_tags = 1;
+ }
+
+ /*
* Waiting allocations only fail because of an inactive hctx. In that
* case just retry the hctx assignment and tag allocation as CPU hotplug
* should have migrated us to an online CPU by now.
@@ -394,16 +469,18 @@ retry:
if (tag == BLK_MQ_NO_TAG) {
if (data->flags & BLK_MQ_REQ_NOWAIT)
return NULL;
-
/*
- * Give up the CPU and sleep for a random short time to ensure
- * that thread using a realtime scheduling class are migrated
- * off the CPU, and thus off the hctx that is going away.
+ * Give up the CPU and sleep for a random short time to
+ * ensure that thread using a realtime scheduling class
+ * are migrated off the CPU, and thus off the hctx that
+ * is going away.
*/
msleep(3);
goto retry;
}
- return blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
+
+ return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag,
+ alloc_time_ns);
}
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
@@ -413,6 +490,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
.q = q,
.flags = flags,
.cmd_flags = op,
+ .rq_flags = q->elevator ? RQF_ELV : 0,
+ .nr_tags = 1,
};
struct request *rq;
int ret;
@@ -421,7 +500,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
if (ret)
return ERR_PTR(ret);
- rq = __blk_mq_alloc_request(&data);
+ rq = __blk_mq_alloc_requests(&data);
if (!rq)
goto out_queue_exit;
rq->__data_len = 0;
@@ -441,6 +520,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
.q = q,
.flags = flags,
.cmd_flags = op,
+ .rq_flags = q->elevator ? RQF_ELV : 0,
+ .nr_tags = 1,
};
u64 alloc_time_ns = 0;
unsigned int cpu;
@@ -485,7 +566,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
tag = blk_mq_get_tag(&data);
if (tag == BLK_MQ_NO_TAG)
goto out_queue_exit;
- return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns);
+ return blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
+ alloc_time_ns);
out_queue_exit:
blk_queue_exit(q);
@@ -514,12 +596,12 @@ static void __blk_mq_free_request(struct request *rq)
void blk_mq_free_request(struct request *rq)
{
struct request_queue *q = rq->q;
- struct elevator_queue *e = q->elevator;
- struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
if (rq->rq_flags & RQF_ELVPRIV) {
- if (e && e->type->ops.finish_request)
+ struct elevator_queue *e = q->elevator;
+
+ if (e->type->ops.finish_request)
e->type->ops.finish_request(rq);
if (rq->elv.icq) {
put_io_context(rq->elv.icq->ioc);
@@ -527,7 +609,6 @@ void blk_mq_free_request(struct request *rq)
}
}
- ctx->rq_completed[rq_is_sync(rq)]++;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
__blk_mq_dec_active_requests(hctx);
@@ -542,21 +623,173 @@ void blk_mq_free_request(struct request *rq)
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
-inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
+void blk_mq_free_plug_rqs(struct blk_plug *plug)
{
- u64 now = 0;
+ struct request *rq;
- if (blk_mq_need_time_stamp(rq))
- now = ktime_get_ns();
+ while ((rq = rq_list_pop(&plug->cached_rq)) != NULL) {
+ percpu_ref_get(&rq->q->q_usage_counter);
+ blk_mq_free_request(rq);
+ }
+}
+static void req_bio_endio(struct request *rq, struct bio *bio,
+ unsigned int nbytes, blk_status_t error)
+{
+ if (unlikely(error)) {
+ bio->bi_status = error;
+ } else if (req_op(rq) == REQ_OP_ZONE_APPEND) {
+ /*
+ * Partial zone append completions cannot be supported as the
+ * BIO fragments may end up not being written sequentially.
+ */
+ if (bio->bi_iter.bi_size != nbytes)
+ bio->bi_status = BLK_STS_IOERR;
+ else
+ bio->bi_iter.bi_sector = rq->__sector;
+ }
+
+ bio_advance(bio, nbytes);
+
+ if (unlikely(rq->rq_flags & RQF_QUIET))
+ bio_set_flag(bio, BIO_QUIET);
+ /* don't actually finish bio if it's part of flush sequence */
+ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
+ bio_endio(bio);
+}
+
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+ if (req->part && blk_do_io_stat(req)) {
+ const int sgrp = op_stat_group(req_op(req));
+
+ part_stat_lock();
+ part_stat_add(req->part, sectors[sgrp], bytes >> 9);
+ part_stat_unlock();
+ }
+}
+
+/**
+ * blk_update_request - Complete multiple bytes without completing the request
+ * @req: the request being processed
+ * @error: block status code
+ * @nr_bytes: number of bytes to complete for @req
+ *
+ * Description:
+ * Ends I/O on a number of bytes attached to @req, but doesn't complete
+ * the request structure even if @req doesn't have leftover.
+ * If @req has leftover, sets it up for the next range of segments.
+ *
+ * Passing the result of blk_rq_bytes() as @nr_bytes guarantees
+ * %false return from this function.
+ *
+ * Note:
+ * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function
+ * except in the consistency check at the end of this function.
+ *
+ * Return:
+ * %false - this request doesn't have any more data
+ * %true - this request has more data
+ **/
+bool blk_update_request(struct request *req, blk_status_t error,
+ unsigned int nr_bytes)
+{
+ int total_bytes;
+
+ trace_block_rq_complete(req, error, nr_bytes);
+
+ if (!req->bio)
+ return false;
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+ if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
+ error == BLK_STS_OK)
+ req->q->integrity.profile->complete_fn(req, nr_bytes);
+#endif
+
+ if (unlikely(error && !blk_rq_is_passthrough(req) &&
+ !(req->rq_flags & RQF_QUIET)))
+ blk_print_req_error(req, error);
+
+ blk_account_io_completion(req, nr_bytes);
+
+ total_bytes = 0;
+ while (req->bio) {
+ struct bio *bio = req->bio;
+ unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
+
+ if (bio_bytes == bio->bi_iter.bi_size)
+ req->bio = bio->bi_next;
+
+ /* Completion has already been traced */
+ bio_clear_flag(bio, BIO_TRACE_COMPLETION);
+ req_bio_endio(req, bio, bio_bytes, error);
+
+ total_bytes += bio_bytes;
+ nr_bytes -= bio_bytes;
+
+ if (!nr_bytes)
+ break;
+ }
+
+ /*
+ * completely done
+ */
+ if (!req->bio) {
+ /*
+ * Reset counters so that the request stacking driver
+ * can find how many bytes remain in the request
+ * later.
+ */
+ req->__data_len = 0;
+ return false;
+ }
+
+ req->__data_len -= total_bytes;
+
+ /* update sector only for requests with clear definition of sector */
+ if (!blk_rq_is_passthrough(req))
+ req->__sector += total_bytes >> 9;
+
+ /* mixed attributes always follow the first bio */
+ if (req->rq_flags & RQF_MIXED_MERGE) {
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
+ }
+
+ if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) {
+ /*
+ * If total number of sectors is less than the first segment
+ * size, something has gone terribly wrong.
+ */
+ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
+ blk_dump_rq_flags(req, "request botched");
+ req->__data_len = blk_rq_cur_bytes(req);
+ }
+
+ /* recalculate the number of segments */
+ req->nr_phys_segments = blk_recalc_rq_segments(req);
+ }
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_update_request);
+
+static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
+{
if (rq->rq_flags & RQF_STATS) {
blk_mq_poll_stats_start(rq->q);
blk_stat_add(rq, now);
}
blk_mq_sched_completed_request(rq, now);
-
blk_account_io_done(rq, now);
+}
+
+inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
+{
+ if (blk_mq_need_time_stamp(rq))
+ __blk_mq_end_request_acct(rq, ktime_get_ns());
if (rq->end_io) {
rq_qos_done(rq->q, rq);
@@ -575,6 +808,57 @@ void blk_mq_end_request(struct request *rq, blk_status_t error)
}
EXPORT_SYMBOL(blk_mq_end_request);
+#define TAG_COMP_BATCH 32
+
+static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
+ int *tag_array, int nr_tags)
+{
+ struct request_queue *q = hctx->queue;
+
+ blk_mq_put_tags(hctx->tags, tag_array, nr_tags);
+ percpu_ref_put_many(&q->q_usage_counter, nr_tags);
+}
+
+void blk_mq_end_request_batch(struct io_comp_batch *iob)
+{
+ int tags[TAG_COMP_BATCH], nr_tags = 0;
+ struct blk_mq_hw_ctx *cur_hctx = NULL;
+ struct request *rq;
+ u64 now = 0;
+
+ if (iob->need_ts)
+ now = ktime_get_ns();
+
+ while ((rq = rq_list_pop(&iob->req_list)) != NULL) {
+ prefetch(rq->bio);
+ prefetch(rq->rq_next);
+
+ blk_update_request(rq, BLK_STS_OK, blk_rq_bytes(rq));
+ if (iob->need_ts)
+ __blk_mq_end_request_acct(rq, now);
+
+ WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+ if (!refcount_dec_and_test(&rq->ref))
+ continue;
+
+ blk_crypto_free_request(rq);
+ blk_pm_mark_last_busy(rq);
+ rq_qos_done(rq->q, rq);
+
+ if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) {
+ if (cur_hctx)
+ blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
+ nr_tags = 0;
+ cur_hctx = rq->mq_hctx;
+ }
+ tags[nr_tags++] = rq->tag;
+ }
+
+ if (nr_tags)
+ blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
+}
+EXPORT_SYMBOL_GPL(blk_mq_end_request_batch);
+
static void blk_complete_reqs(struct llist_head *list)
{
struct llist_node *entry = llist_reverse_order(llist_del_all(list));
@@ -658,7 +942,7 @@ bool blk_mq_complete_request_remote(struct request *rq)
* For a polled request, always complete locallly, it's pointless
* to redirect the completion.
*/
- if (rq->cmd_flags & REQ_HIPRI)
+ if (rq->cmd_flags & REQ_POLLED)
return false;
if (blk_mq_complete_need_ipi(rq)) {
@@ -723,7 +1007,14 @@ void blk_mq_start_request(struct request *rq)
trace_block_rq_issue(rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
- rq->io_start_time_ns = ktime_get_ns();
+ u64 start_time;
+#ifdef CONFIG_BLK_CGROUP
+ if (rq->bio)
+ start_time = bio_issue_time(&rq->bio->bi_issue);
+ else
+#endif
+ start_time = ktime_get_ns();
+ rq->io_start_time_ns = start_time;
rq->stats_sectors = blk_rq_sectors(rq);
rq->rq_flags |= RQF_STATS;
rq_qos_issue(q, rq);
@@ -738,6 +1029,8 @@ void blk_mq_start_request(struct request *rq)
if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
q->integrity.profile->prepare_fn(rq);
#endif
+ if (rq->bio && rq->bio->bi_opf & REQ_POLLED)
+ WRITE_ONCE(rq->bio->bi_cookie, blk_rq_to_qc(rq));
}
EXPORT_SYMBOL(blk_mq_start_request);
@@ -763,7 +1056,6 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
/* this request will be re-inserted to io scheduler queue */
blk_mq_sched_requeue_request(rq);
- BUG_ON(!list_empty(&rq->queuelist));
blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
EXPORT_SYMBOL(blk_mq_requeue_request);
@@ -844,17 +1136,6 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
-struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
-{
- if (tag < tags->nr_tags) {
- prefetch(tags->rqs[tag]);
- return tags->rqs[tag];
- }
-
- return NULL;
-}
-EXPORT_SYMBOL(blk_mq_tag_to_rq);
-
static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
void *priv, bool reserved)
{
@@ -1059,24 +1340,16 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
return data.rq;
}
-static inline unsigned int queued_to_index(unsigned int queued)
-{
- if (!queued)
- return 0;
-
- return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
-}
-
-static bool __blk_mq_get_driver_tag(struct request *rq)
+static bool __blk_mq_alloc_driver_tag(struct request *rq)
{
- struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags;
+ struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
int tag;
blk_mq_tag_busy(rq->mq_hctx);
if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
- bt = rq->mq_hctx->tags->breserved_tags;
+ bt = &rq->mq_hctx->tags->breserved_tags;
tag_offset = 0;
} else {
if (!hctx_may_queue(rq->mq_hctx, bt))
@@ -1091,11 +1364,9 @@ static bool __blk_mq_get_driver_tag(struct request *rq)
return true;
}
-bool blk_mq_get_driver_tag(struct request *rq)
+bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
- struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
-
- if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
+ if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
return false;
if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
@@ -1119,7 +1390,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
struct sbitmap_queue *sbq;
list_del_init(&wait->entry);
- sbq = hctx->tags->bitmap_tags;
+ sbq = &hctx->tags->bitmap_tags;
atomic_dec(&sbq->ws_active);
}
spin_unlock(&hctx->dispatch_wait_lock);
@@ -1137,7 +1408,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
- struct sbitmap_queue *sbq = hctx->tags->bitmap_tags;
+ struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
struct wait_queue_head *wq;
wait_queue_entry_t *wait;
bool ret;
@@ -1325,6 +1596,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
int errors, queued;
blk_status_t ret = BLK_STS_OK;
LIST_HEAD(zone_list);
+ bool needs_resource = false;
if (list_empty(list))
return false;
@@ -1370,6 +1642,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
queued++;
break;
case BLK_STS_RESOURCE:
+ needs_resource = true;
+ fallthrough;
case BLK_STS_DEV_RESOURCE:
blk_mq_handle_dev_resource(rq, list);
goto out;
@@ -1380,6 +1654,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
* accept.
*/
blk_mq_handle_zone_resource(rq, &zone_list);
+ needs_resource = true;
break;
default:
errors++;
@@ -1390,8 +1665,6 @@ out:
if (!list_empty(&zone_list))
list_splice_tail_init(&zone_list, list);
- hctx->dispatched[queued_to_index(queued)]++;
-
/* If we didn't flush the entire list, we could have told the driver
* there was more coming, but that turned out to be a lie.
*/
@@ -1406,7 +1679,6 @@ out:
/* For non-shared tags, the RESTART check will suffice */
bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
- bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
if (nr_budgets)
blk_mq_release_budgets(q, list);
@@ -1447,14 +1719,16 @@ out:
* If driver returns BLK_STS_RESOURCE and SCHED_RESTART
* bit is set, run queue after a delay to avoid IO stalls
* that could otherwise occur if the queue is idle. We'll do
- * similar if we couldn't get budget and SCHED_RESTART is set.
+ * similar if we couldn't get budget or couldn't lock a zone
+ * and SCHED_RESTART is set.
*/
needs_restart = blk_mq_sched_needs_restart(hctx);
+ if (prep == PREP_DISPATCH_NO_BUDGET)
+ needs_resource = true;
if (!needs_restart ||
(no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
blk_mq_run_hw_queue(hctx, true);
- else if (needs_restart && (ret == BLK_STS_RESOURCE ||
- no_budget_avail))
+ else if (needs_restart && needs_resource)
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
blk_mq_update_dispatch_busy(hctx, true);
@@ -1894,54 +2168,106 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
spin_unlock(&ctx->lock);
}
-static int plug_rq_cmp(void *priv, const struct list_head *a,
- const struct list_head *b)
+static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int *queued,
+ bool from_schedule)
{
- struct request *rqa = container_of(a, struct request, queuelist);
- struct request *rqb = container_of(b, struct request, queuelist);
+ if (hctx->queue->mq_ops->commit_rqs) {
+ trace_block_unplug(hctx->queue, *queued, !from_schedule);
+ hctx->queue->mq_ops->commit_rqs(hctx);
+ }
+ *queued = 0;
+}
- if (rqa->mq_ctx != rqb->mq_ctx)
- return rqa->mq_ctx > rqb->mq_ctx;
- if (rqa->mq_hctx != rqb->mq_hctx)
- return rqa->mq_hctx > rqb->mq_hctx;
+static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule)
+{
+ struct blk_mq_hw_ctx *hctx = NULL;
+ struct request *rq;
+ int queued = 0;
+ int errors = 0;
- return blk_rq_pos(rqa) > blk_rq_pos(rqb);
+ while ((rq = rq_list_pop(&plug->mq_list))) {
+ bool last = rq_list_empty(plug->mq_list);
+ blk_status_t ret;
+
+ if (hctx != rq->mq_hctx) {
+ if (hctx)
+ blk_mq_commit_rqs(hctx, &queued, from_schedule);
+ hctx = rq->mq_hctx;
+ }
+
+ ret = blk_mq_request_issue_directly(rq, last);
+ switch (ret) {
+ case BLK_STS_OK:
+ queued++;
+ break;
+ case BLK_STS_RESOURCE:
+ case BLK_STS_DEV_RESOURCE:
+ blk_mq_request_bypass_insert(rq, false, last);
+ blk_mq_commit_rqs(hctx, &queued, from_schedule);
+ return;
+ default:
+ blk_mq_end_request(rq, ret);
+ errors++;
+ break;
+ }
+ }
+
+ /*
+ * If we didn't flush the entire list, we could have told the driver
+ * there was more coming, but that turned out to be a lie.
+ */
+ if (errors)
+ blk_mq_commit_rqs(hctx, &queued, from_schedule);
}
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
+ struct blk_mq_hw_ctx *this_hctx;
+ struct blk_mq_ctx *this_ctx;
+ unsigned int depth;
LIST_HEAD(list);
- if (list_empty(&plug->mq_list))
+ if (rq_list_empty(plug->mq_list))
return;
- list_splice_init(&plug->mq_list, &list);
-
- if (plug->rq_count > 2 && plug->multiple_queues)
- list_sort(NULL, &list, plug_rq_cmp);
-
plug->rq_count = 0;
+ if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
+ blk_mq_plug_issue_direct(plug, from_schedule);
+ if (rq_list_empty(plug->mq_list))
+ return;
+ }
+
+ this_hctx = NULL;
+ this_ctx = NULL;
+ depth = 0;
do {
- struct list_head rq_list;
- struct request *rq, *head_rq = list_entry_rq(list.next);
- struct list_head *pos = &head_rq->queuelist; /* skip first */
- struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx;
- struct blk_mq_ctx *this_ctx = head_rq->mq_ctx;
- unsigned int depth = 1;
-
- list_for_each_continue(pos, &list) {
- rq = list_entry_rq(pos);
- BUG_ON(!rq->q);
- if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx)
- break;
- depth++;
+ struct request *rq;
+
+ rq = rq_list_pop(&plug->mq_list);
+
+ if (!this_hctx) {
+ this_hctx = rq->mq_hctx;
+ this_ctx = rq->mq_ctx;
+ } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
+ trace_block_unplug(this_hctx->queue, depth,
+ !from_schedule);
+ blk_mq_sched_insert_requests(this_hctx, this_ctx,
+ &list, from_schedule);
+ depth = 0;
+ this_hctx = rq->mq_hctx;
+ this_ctx = rq->mq_ctx;
+
}
- list_cut_before(&rq_list, &list, pos);
- trace_block_unplug(head_rq->q, depth, !from_schedule);
- blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
+ list_add(&rq->queuelist, &list);
+ depth++;
+ } while (!rq_list_empty(plug->mq_list));
+
+ if (!list_empty(&list)) {
+ trace_block_unplug(this_hctx->queue, depth, !from_schedule);
+ blk_mq_sched_insert_requests(this_hctx, this_ctx, &list,
from_schedule);
- } while(!list_empty(&list));
+ }
}
static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
@@ -1964,19 +2290,15 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
}
static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
- struct request *rq,
- blk_qc_t *cookie, bool last)
+ struct request *rq, bool last)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
.rq = rq,
.last = last,
};
- blk_qc_t new_cookie;
blk_status_t ret;
- new_cookie = request_to_qc_t(hctx, rq);
-
/*
* For OK queue, we are done. For error, caller may kill it.
* Any other error (busy), just add it to our list as we
@@ -1986,7 +2308,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
switch (ret) {
case BLK_STS_OK:
blk_mq_update_dispatch_busy(hctx, false);
- *cookie = new_cookie;
break;
case BLK_STS_RESOURCE:
case BLK_STS_DEV_RESOURCE:
@@ -1995,7 +2316,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
break;
default:
blk_mq_update_dispatch_busy(hctx, false);
- *cookie = BLK_QC_T_NONE;
break;
}
@@ -2004,7 +2324,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq,
- blk_qc_t *cookie,
bool bypass_insert, bool last)
{
struct request_queue *q = rq->q;
@@ -2024,7 +2343,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
goto insert;
}
- if (q->elevator && !bypass_insert)
+ if ((rq->rq_flags & RQF_ELV) && !bypass_insert)
goto insert;
budget_token = blk_mq_get_dispatch_budget(q);
@@ -2038,7 +2357,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
goto insert;
}
- return __blk_mq_issue_directly(hctx, rq, cookie, last);
+ return __blk_mq_issue_directly(hctx, rq, last);
insert:
if (bypass_insert)
return BLK_STS_RESOURCE;
@@ -2052,7 +2371,6 @@ insert:
* blk_mq_try_issue_directly - Try to send a request directly to device driver.
* @hctx: Pointer of the associated hardware queue.
* @rq: Pointer to request to be sent.
- * @cookie: Request queue cookie.
*
* If the device has enough resources to accept a new request now, send the
* request directly to device driver. Else, insert at hctx->dispatch queue, so
@@ -2060,7 +2378,7 @@ insert:
* queue have higher priority.
*/
static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
- struct request *rq, blk_qc_t *cookie)
+ struct request *rq)
{
blk_status_t ret;
int srcu_idx;
@@ -2069,7 +2387,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
hctx_lock(hctx, &srcu_idx);
- ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
+ ret = __blk_mq_try_issue_directly(hctx, rq, false, true);
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
blk_mq_request_bypass_insert(rq, false, true);
else if (ret != BLK_STS_OK)
@@ -2082,11 +2400,10 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
{
blk_status_t ret;
int srcu_idx;
- blk_qc_t unused_cookie;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
hctx_lock(hctx, &srcu_idx);
- ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
+ ret = __blk_mq_try_issue_directly(hctx, rq, true, last);
hctx_unlock(hctx, srcu_idx);
return ret;
@@ -2130,27 +2447,28 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
{
- list_add_tail(&rq->queuelist, &plug->mq_list);
- plug->rq_count++;
- if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) {
- struct request *tmp;
+ if (!plug->multiple_queues) {
+ struct request *nxt = rq_list_peek(&plug->mq_list);
- tmp = list_first_entry(&plug->mq_list, struct request,
- queuelist);
- if (tmp->q != rq->q)
+ if (nxt && nxt->q != rq->q)
plug->multiple_queues = true;
}
+ if (!plug->has_elevator && (rq->rq_flags & RQF_ELV))
+ plug->has_elevator = true;
+ rq->rq_next = NULL;
+ rq_list_add(&plug->mq_list, rq);
+ plug->rq_count++;
}
/*
- * Allow 4x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
+ * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
* queues. This is important for md arrays to benefit from merging
* requests.
*/
static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
{
if (plug->multiple_queues)
- return BLK_MAX_REQUEST_COUNT * 4;
+ return BLK_MAX_REQUEST_COUNT * 2;
return BLK_MAX_REQUEST_COUNT;
}
@@ -2166,57 +2484,63 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
*
* It will not queue the request if there is an error with the bio, or at the
* request creation.
- *
- * Returns: Request queue cookie.
*/
-blk_qc_t blk_mq_submit_bio(struct bio *bio)
+void blk_mq_submit_bio(struct bio *bio)
{
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
const int is_sync = op_is_sync(bio->bi_opf);
- const int is_flush_fua = op_is_flush(bio->bi_opf);
- struct blk_mq_alloc_data data = {
- .q = q,
- };
struct request *rq;
struct blk_plug *plug;
- struct request *same_queue_rq = NULL;
- unsigned int nr_segs;
- blk_qc_t cookie;
+ bool same_queue_rq = false;
+ unsigned int nr_segs = 1;
blk_status_t ret;
- bool hipri;
blk_queue_bounce(q, &bio);
- __blk_queue_split(&bio, &nr_segs);
+ if (blk_may_split(q, bio))
+ __blk_queue_split(q, &bio, &nr_segs);
if (!bio_integrity_prep(bio))
goto queue_exit;
- if (!is_flush_fua && !blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
- goto queue_exit;
-
- if (blk_mq_sched_bio_merge(q, bio, nr_segs))
- goto queue_exit;
+ if (!blk_queue_nomerges(q) && bio_mergeable(bio)) {
+ if (blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
+ goto queue_exit;
+ if (blk_mq_sched_bio_merge(q, bio, nr_segs))
+ goto queue_exit;
+ }
rq_qos_throttle(q, bio);
- hipri = bio->bi_opf & REQ_HIPRI;
-
- data.cmd_flags = bio->bi_opf;
- rq = __blk_mq_alloc_request(&data);
- if (unlikely(!rq)) {
- rq_qos_cleanup(q, bio);
- if (bio->bi_opf & REQ_NOWAIT)
- bio_wouldblock_error(bio);
- goto queue_exit;
+ plug = blk_mq_plug(q, bio);
+ if (plug && plug->cached_rq) {
+ rq = rq_list_pop(&plug->cached_rq);
+ INIT_LIST_HEAD(&rq->queuelist);
+ } else {
+ struct blk_mq_alloc_data data = {
+ .q = q,
+ .nr_tags = 1,
+ .cmd_flags = bio->bi_opf,
+ .rq_flags = q->elevator ? RQF_ELV : 0,
+ };
+
+ if (plug) {
+ data.nr_tags = plug->nr_ios;
+ plug->nr_ios = 1;
+ data.cached_rq = &plug->cached_rq;
+ }
+ rq = __blk_mq_alloc_requests(&data);
+ if (unlikely(!rq)) {
+ rq_qos_cleanup(q, bio);
+ if (bio->bi_opf & REQ_NOWAIT)
+ bio_wouldblock_error(bio);
+ goto queue_exit;
+ }
}
trace_block_getrq(bio);
rq_qos_track(q, rq, bio);
- cookie = request_to_qc_t(data.hctx, rq);
-
blk_mq_bio_to_request(rq, bio, nr_segs);
ret = blk_crypto_init_request(rq);
@@ -2224,17 +2548,15 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
bio->bi_status = ret;
bio_endio(bio);
blk_mq_free_request(rq);
- return BLK_QC_T_NONE;
+ return;
}
- plug = blk_mq_plug(q, bio);
- if (unlikely(is_flush_fua)) {
- /* Bypass scheduler for flush requests */
- blk_insert_flush(rq);
- blk_mq_run_hw_queue(data.hctx, true);
- } else if (plug && (q->nr_hw_queues == 1 ||
- blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) ||
- q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) {
+ if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
+ return;
+
+ if (plug && (q->nr_hw_queues == 1 ||
+ blk_mq_is_shared_tags(rq->mq_hctx->flags) ||
+ q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) {
/*
* Use plugging if we have a ->commit_rqs() hook as well, as
* we know the driver uses bd->last in a smart fashion.
@@ -2245,22 +2567,26 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
unsigned int request_count = plug->rq_count;
struct request *last = NULL;
- if (!request_count)
+ if (!request_count) {
trace_block_plug(q);
- else
- last = list_entry_rq(plug->mq_list.prev);
+ } else if (!blk_queue_nomerges(q)) {
+ last = rq_list_peek(&plug->mq_list);
+ if (blk_rq_bytes(last) < BLK_PLUG_FLUSH_SIZE)
+ last = NULL;
+ }
- if (request_count >= blk_plug_max_rq_count(plug) || (last &&
- blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
- blk_flush_plug_list(plug, false);
+ if (request_count >= blk_plug_max_rq_count(plug) || last) {
+ blk_mq_flush_plug_list(plug, false);
trace_block_plug(q);
}
blk_add_rq_to_plug(plug, rq);
- } else if (q->elevator) {
+ } else if (rq->rq_flags & RQF_ELV) {
/* Insert the request at the IO scheduler queue */
blk_mq_sched_insert_request(rq, false, true, true);
} else if (plug && !blk_queue_nomerges(q)) {
+ struct request *next_rq = NULL;
+
/*
* We do limited plugging. If the bio can be merged, do that.
* Otherwise the existing request in the plug list will be
@@ -2268,39 +2594,32 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
* The plug list might get flushed before this. If that happens,
* the plug list is empty, and same_queue_rq is invalid.
*/
- if (list_empty(&plug->mq_list))
- same_queue_rq = NULL;
if (same_queue_rq) {
- list_del_init(&same_queue_rq->queuelist);
+ next_rq = rq_list_pop(&plug->mq_list);
plug->rq_count--;
}
blk_add_rq_to_plug(plug, rq);
trace_block_plug(q);
- if (same_queue_rq) {
- data.hctx = same_queue_rq->mq_hctx;
+ if (next_rq) {
trace_block_unplug(q, 1, true);
- blk_mq_try_issue_directly(data.hctx, same_queue_rq,
- &cookie);
+ blk_mq_try_issue_directly(next_rq->mq_hctx, next_rq);
}
} else if ((q->nr_hw_queues > 1 && is_sync) ||
- !data.hctx->dispatch_busy) {
+ !rq->mq_hctx->dispatch_busy) {
/*
* There is no scheduler and we can try to send directly
* to the hardware.
*/
- blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+ blk_mq_try_issue_directly(rq->mq_hctx, rq);
} else {
/* Default case. */
blk_mq_sched_insert_request(rq, false, true, true);
}
- if (!hipri)
- return BLK_QC_T_NONE;
- return cookie;
+ return;
queue_exit:
blk_queue_exit(q);
- return BLK_QC_T_NONE;
}
static size_t order_to_size(unsigned int order)
@@ -2309,19 +2628,22 @@ static size_t order_to_size(unsigned int order)
}
/* called before freeing request pool in @tags */
-static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set,
- struct blk_mq_tags *tags, unsigned int hctx_idx)
+static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags,
+ struct blk_mq_tags *tags)
{
- struct blk_mq_tags *drv_tags = set->tags[hctx_idx];
struct page *page;
unsigned long flags;
+ /* There is no need to clear a driver tags own mapping */
+ if (drv_tags == tags)
+ return;
+
list_for_each_entry(page, &tags->page_list, lru) {
unsigned long start = (unsigned long)page_address(page);
unsigned long end = start + order_to_size(page->private);
int i;
- for (i = 0; i < set->queue_depth; i++) {
+ for (i = 0; i < drv_tags->nr_tags; i++) {
struct request *rq = drv_tags->rqs[i];
unsigned long rq_addr = (unsigned long)rq;
@@ -2345,9 +2667,15 @@ static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set,
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx)
{
+ struct blk_mq_tags *drv_tags;
struct page *page;
- if (tags->rqs && set->ops->exit_request) {
+ if (blk_mq_is_shared_tags(set->flags))
+ drv_tags = set->shared_tags;
+ else
+ drv_tags = set->tags[hctx_idx];
+
+ if (tags->static_rqs && set->ops->exit_request) {
int i;
for (i = 0; i < tags->nr_tags; i++) {
@@ -2360,7 +2688,7 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
}
}
- blk_mq_clear_rq_mapping(set, tags, hctx_idx);
+ blk_mq_clear_rq_mapping(drv_tags, tags);
while (!list_empty(&tags->page_list)) {
page = list_first_entry(&tags->page_list, struct page, lru);
@@ -2374,21 +2702,20 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
}
}
-void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags)
+void blk_mq_free_rq_map(struct blk_mq_tags *tags)
{
kfree(tags->rqs);
tags->rqs = NULL;
kfree(tags->static_rqs);
tags->static_rqs = NULL;
- blk_mq_free_tags(tags, flags);
+ blk_mq_free_tags(tags);
}
-struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
- unsigned int hctx_idx,
- unsigned int nr_tags,
- unsigned int reserved_tags,
- unsigned int flags)
+static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
+ unsigned int hctx_idx,
+ unsigned int nr_tags,
+ unsigned int reserved_tags)
{
struct blk_mq_tags *tags;
int node;
@@ -2397,7 +2724,8 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
if (node == NUMA_NO_NODE)
node = set->numa_node;
- tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags);
+ tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
+ BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
if (!tags)
return NULL;
@@ -2405,7 +2733,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
node);
if (!tags->rqs) {
- blk_mq_free_tags(tags, flags);
+ blk_mq_free_tags(tags);
return NULL;
}
@@ -2414,7 +2742,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
node);
if (!tags->static_rqs) {
kfree(tags->rqs);
- blk_mq_free_tags(tags, flags);
+ blk_mq_free_tags(tags);
return NULL;
}
@@ -2436,8 +2764,9 @@ static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
return 0;
}
-int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
- unsigned int hctx_idx, unsigned int depth)
+static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set,
+ struct blk_mq_tags *tags,
+ unsigned int hctx_idx, unsigned int depth)
{
unsigned int i, j, entries_per_page, max_order = 4;
size_t rq_size, left;
@@ -2848,37 +3177,58 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
}
}
-static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
- int hctx_idx)
+struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
+ unsigned int hctx_idx,
+ unsigned int depth)
{
- unsigned int flags = set->flags;
- int ret = 0;
+ struct blk_mq_tags *tags;
+ int ret;
- set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
- set->queue_depth, set->reserved_tags, flags);
- if (!set->tags[hctx_idx])
- return false;
+ tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags);
+ if (!tags)
+ return NULL;
- ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx,
- set->queue_depth);
- if (!ret)
- return true;
+ ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth);
+ if (ret) {
+ blk_mq_free_rq_map(tags);
+ return NULL;
+ }
- blk_mq_free_rq_map(set->tags[hctx_idx], flags);
- set->tags[hctx_idx] = NULL;
- return false;
+ return tags;
}
-static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
- unsigned int hctx_idx)
+static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
+ int hctx_idx)
{
- unsigned int flags = set->flags;
+ if (blk_mq_is_shared_tags(set->flags)) {
+ set->tags[hctx_idx] = set->shared_tags;
- if (set->tags && set->tags[hctx_idx]) {
- blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
- blk_mq_free_rq_map(set->tags[hctx_idx], flags);
- set->tags[hctx_idx] = NULL;
+ return true;
}
+
+ set->tags[hctx_idx] = blk_mq_alloc_map_and_rqs(set, hctx_idx,
+ set->queue_depth);
+
+ return set->tags[hctx_idx];
+}
+
+void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
+ struct blk_mq_tags *tags,
+ unsigned int hctx_idx)
+{
+ if (tags) {
+ blk_mq_free_rqs(set, tags, hctx_idx);
+ blk_mq_free_rq_map(tags);
+ }
+}
+
+static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
+ unsigned int hctx_idx)
+{
+ if (!blk_mq_is_shared_tags(set->flags))
+ blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx);
+
+ set->tags[hctx_idx] = NULL;
}
static void blk_mq_map_swqueue(struct request_queue *q)
@@ -2911,7 +3261,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
hctx_idx = set->map[j].mq_map[i];
/* unmapped hw queue can be remapped after CPU topo changed */
if (!set->tags[hctx_idx] &&
- !__blk_mq_alloc_map_and_request(set, hctx_idx)) {
+ !__blk_mq_alloc_map_and_rqs(set, hctx_idx)) {
/*
* If tags initialization fail for some hctx,
* that hctx won't be brought online. In this
@@ -2958,8 +3308,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
* fallback in case of a new remap fails
* allocation
*/
- if (i && set->tags[i])
- blk_mq_free_map_and_requests(set, i);
+ if (i)
+ __blk_mq_free_map_and_rqs(set, i);
hctx->tags = NULL;
continue;
@@ -3255,8 +3605,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx = hctxs[j];
if (hctx) {
- if (hctx->tags)
- blk_mq_free_map_and_requests(set, j);
+ __blk_mq_free_map_and_rqs(set, j);
blk_mq_exit_hctx(q, set, hctx, j);
hctxs[j] = NULL;
}
@@ -3343,8 +3692,16 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
{
int i;
+ if (blk_mq_is_shared_tags(set->flags)) {
+ set->shared_tags = blk_mq_alloc_map_and_rqs(set,
+ BLK_MQ_NO_HCTX_IDX,
+ set->queue_depth);
+ if (!set->shared_tags)
+ return -ENOMEM;
+ }
+
for (i = 0; i < set->nr_hw_queues; i++) {
- if (!__blk_mq_alloc_map_and_request(set, i))
+ if (!__blk_mq_alloc_map_and_rqs(set, i))
goto out_unwind;
cond_resched();
}
@@ -3353,7 +3710,12 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
out_unwind:
while (--i >= 0)
- blk_mq_free_map_and_requests(set, i);
+ __blk_mq_free_map_and_rqs(set, i);
+
+ if (blk_mq_is_shared_tags(set->flags)) {
+ blk_mq_free_map_and_rqs(set, set->shared_tags,
+ BLK_MQ_NO_HCTX_IDX);
+ }
return -ENOMEM;
}
@@ -3363,7 +3725,7 @@ out_unwind:
* may reduce the depth asked for, if memory is tight. set->queue_depth
* will be updated to reflect the allocated depth.
*/
-static int blk_mq_alloc_map_and_requests(struct blk_mq_tag_set *set)
+static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set)
{
unsigned int depth;
int err;
@@ -3529,27 +3891,15 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
if (ret)
goto out_free_mq_map;
- ret = blk_mq_alloc_map_and_requests(set);
+ ret = blk_mq_alloc_set_map_and_rqs(set);
if (ret)
goto out_free_mq_map;
- if (blk_mq_is_sbitmap_shared(set->flags)) {
- atomic_set(&set->active_queues_shared_sbitmap, 0);
-
- if (blk_mq_init_shared_sbitmap(set)) {
- ret = -ENOMEM;
- goto out_free_mq_rq_maps;
- }
- }
-
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
-out_free_mq_rq_maps:
- for (i = 0; i < set->nr_hw_queues; i++)
- blk_mq_free_map_and_requests(set, i);
out_free_mq_map:
for (i = 0; i < set->nr_maps; i++) {
kfree(set->map[i].mq_map);
@@ -3582,10 +3932,12 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
int i, j;
for (i = 0; i < set->nr_hw_queues; i++)
- blk_mq_free_map_and_requests(set, i);
+ __blk_mq_free_map_and_rqs(set, i);
- if (blk_mq_is_sbitmap_shared(set->flags))
- blk_mq_exit_shared_sbitmap(set);
+ if (blk_mq_is_shared_tags(set->flags)) {
+ blk_mq_free_map_and_rqs(set, set->shared_tags,
+ BLK_MQ_NO_HCTX_IDX);
+ }
for (j = 0; j < set->nr_maps; j++) {
kfree(set->map[j].mq_map);
@@ -3620,20 +3972,12 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
* If we're using an MQ scheduler, just update the scheduler
* queue depth. This is similar to what the old code would do.
*/
- if (!hctx->sched_tags) {
- ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
- false);
- if (!ret && blk_mq_is_sbitmap_shared(set->flags))
- blk_mq_tag_resize_shared_sbitmap(set, nr);
- } else {
+ if (hctx->sched_tags) {
ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
- nr, true);
- if (blk_mq_is_sbitmap_shared(set->flags)) {
- hctx->sched_tags->bitmap_tags =
- &q->sched_bitmap_tags;
- hctx->sched_tags->breserved_tags =
- &q->sched_breserved_tags;
- }
+ nr, true);
+ } else {
+ ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
+ false);
}
if (ret)
break;
@@ -3642,9 +3986,12 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
}
if (!ret) {
q->nr_requests = nr;
- if (q->elevator && blk_mq_is_sbitmap_shared(set->flags))
- sbitmap_queue_resize(&q->sched_bitmap_tags,
- nr - set->reserved_tags);
+ if (blk_mq_is_shared_tags(set->flags)) {
+ if (q->elevator)
+ blk_mq_tag_update_sched_shared_tags(q);
+ else
+ blk_mq_tag_resize_shared_tags(set, nr);
+ }
}
blk_mq_unquiesce_queue(q);
@@ -3863,15 +4210,20 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
return ret;
}
-static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
- struct request *rq)
+static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc)
{
+ struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, qc);
+ struct request *rq = blk_qc_to_rq(hctx, qc);
struct hrtimer_sleeper hs;
enum hrtimer_mode mode;
unsigned int nsecs;
ktime_t kt;
- if (rq->rq_flags & RQF_MQ_POLL_SLEPT)
+ /*
+ * If a request has completed on queue that uses an I/O scheduler, we
+ * won't get back a request from blk_qc_to_rq.
+ */
+ if (!rq || (rq->rq_flags & RQF_MQ_POLL_SLEPT))
return false;
/*
@@ -3913,92 +4265,37 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
__set_current_state(TASK_RUNNING);
destroy_hrtimer_on_stack(&hs.timer);
- return true;
-}
-
-static bool blk_mq_poll_hybrid(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx, blk_qc_t cookie)
-{
- struct request *rq;
-
- if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
- return false;
-
- if (!blk_qc_t_is_internal(cookie))
- rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
- else {
- rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
- /*
- * With scheduling, if the request has completed, we'll
- * get a NULL return here, as we clear the sched tag when
- * that happens. The request still remains valid, like always,
- * so we should be safe with just the NULL check.
- */
- if (!rq)
- return false;
- }
-
- return blk_mq_poll_hybrid_sleep(q, rq);
-}
-
-/**
- * blk_poll - poll for IO completions
- * @q: the queue
- * @cookie: cookie passed back at IO submission time
- * @spin: whether to spin for completions
- *
- * Description:
- * Poll for completions on the passed in queue. Returns number of
- * completed entries found. If @spin is true, then blk_poll will continue
- * looping until at least one completion is found, unless the task is
- * otherwise marked running (or we need to reschedule).
- */
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
-{
- struct blk_mq_hw_ctx *hctx;
- unsigned int state;
-
- if (!blk_qc_t_valid(cookie) ||
- !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
- return 0;
-
- if (current->plug)
- blk_flush_plug_list(current->plug, false);
-
- hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
/*
- * If we sleep, have the caller restart the poll loop to reset
- * the state. Like for the other success return cases, the
- * caller is responsible for checking if the IO completed. If
- * the IO isn't complete, we'll get called again and will go
- * straight to the busy poll loop. If specified not to spin,
- * we also should not sleep.
+ * If we sleep, have the caller restart the poll loop to reset the
+ * state. Like for the other success return cases, the caller is
+ * responsible for checking if the IO completed. If the IO isn't
+ * complete, we'll get called again and will go straight to the busy
+ * poll loop.
*/
- if (spin && blk_mq_poll_hybrid(q, hctx, cookie))
- return 1;
+ return true;
+}
- hctx->poll_considered++;
+static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
+ struct io_comp_batch *iob, unsigned int flags)
+{
+ struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie);
+ long state = get_current_state();
+ int ret;
- state = get_current_state();
do {
- int ret;
-
- hctx->poll_invoked++;
-
- ret = q->mq_ops->poll(hctx);
+ ret = q->mq_ops->poll(hctx, iob);
if (ret > 0) {
- hctx->poll_success++;
__set_current_state(TASK_RUNNING);
return ret;
}
if (signal_pending_state(state, current))
__set_current_state(TASK_RUNNING);
-
if (task_is_running(current))
return 1;
- if (ret < 0 || !spin)
+
+ if (ret < 0 || (flags & BLK_POLL_ONESHOT))
break;
cpu_relax();
} while (!need_resched());
@@ -4006,7 +4303,17 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
__set_current_state(TASK_RUNNING);
return 0;
}
-EXPORT_SYMBOL_GPL(blk_poll);
+
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
+ unsigned int flags)
+{
+ if (!(flags & BLK_POLL_NOSLEEP) &&
+ q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
+ if (blk_mq_poll_hybrid(q, cookie))
+ return 1;
+ }
+ return blk_mq_poll_classic(q, cookie, iob, flags);
+}
unsigned int blk_mq_rq_cpu(struct request *rq)
{
diff --git a/block/blk-mq.h b/block/blk-mq.h
index d08779f77a26..28859fc5faee 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -25,18 +25,14 @@ struct blk_mq_ctx {
unsigned short index_hw[HCTX_MAX_TYPES];
struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES];
- /* incremented at dispatch time */
- unsigned long rq_dispatched[2];
- unsigned long rq_merged;
-
- /* incremented at completion time */
- unsigned long ____cacheline_aligned_in_smp rq_completed[2];
-
struct request_queue *queue;
struct blk_mq_ctxs *ctxs;
struct kobject kobj;
} ____cacheline_aligned_in_smp;
+void blk_mq_submit_bio(struct bio *bio);
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
+ unsigned int flags);
void blk_mq_exit_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
@@ -54,15 +50,12 @@ void blk_mq_put_rq_ref(struct request *rq);
*/
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx);
-void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags);
-struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
- unsigned int hctx_idx,
- unsigned int nr_tags,
- unsigned int reserved_tags,
- unsigned int flags);
-int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
- unsigned int hctx_idx, unsigned int depth);
-
+void blk_mq_free_rq_map(struct blk_mq_tags *tags);
+struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
+ unsigned int hctx_idx, unsigned int depth);
+void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
+ struct blk_mq_tags *tags,
+ unsigned int hctx_idx);
/*
* Internal helpers for request insertion into sw queues
*/
@@ -109,9 +102,9 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
enum hctx_type type = HCTX_TYPE_DEFAULT;
/*
- * The caller ensure that if REQ_HIPRI, poll must be enabled.
+ * The caller ensure that if REQ_POLLED, poll must be enabled.
*/
- if (flags & REQ_HIPRI)
+ if (flags & REQ_POLLED)
type = HCTX_TYPE_POLL;
else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
type = HCTX_TYPE_READ;
@@ -128,6 +121,8 @@ extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
+void blk_mq_free_plug_rqs(struct blk_plug *plug);
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
void blk_mq_release(struct request_queue *q);
@@ -154,23 +149,27 @@ struct blk_mq_alloc_data {
blk_mq_req_flags_t flags;
unsigned int shallow_depth;
unsigned int cmd_flags;
+ unsigned int rq_flags;
+
+ /* allocate multiple requests/tags in one go */
+ unsigned int nr_tags;
+ struct request **cached_rq;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
-static inline bool blk_mq_is_sbitmap_shared(unsigned int flags)
+static inline bool blk_mq_is_shared_tags(unsigned int flags)
{
return flags & BLK_MQ_F_TAG_HCTX_SHARED;
}
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
- if (data->q->elevator)
- return data->hctx->sched_tags;
-
- return data->hctx->tags;
+ if (!(data->rq_flags & RQF_ELV))
+ return data->hctx->tags;
+ return data->hctx->sched_tags;
}
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
@@ -220,24 +219,24 @@ static inline int blk_mq_get_rq_budget_token(struct request *rq)
static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
{
- if (blk_mq_is_sbitmap_shared(hctx->flags))
- atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap);
+ if (blk_mq_is_shared_tags(hctx->flags))
+ atomic_inc(&hctx->queue->nr_active_requests_shared_tags);
else
atomic_inc(&hctx->nr_active);
}
static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
{
- if (blk_mq_is_sbitmap_shared(hctx->flags))
- atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap);
+ if (blk_mq_is_shared_tags(hctx->flags))
+ atomic_dec(&hctx->queue->nr_active_requests_shared_tags);
else
atomic_dec(&hctx->nr_active);
}
static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
{
- if (blk_mq_is_sbitmap_shared(hctx->flags))
- return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap);
+ if (blk_mq_is_shared_tags(hctx->flags))
+ return atomic_read(&hctx->queue->nr_active_requests_shared_tags);
return atomic_read(&hctx->nr_active);
}
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
@@ -260,7 +259,20 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
__blk_mq_put_driver_tag(rq->mq_hctx, rq);
}
-bool blk_mq_get_driver_tag(struct request *rq);
+bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq);
+
+static inline bool blk_mq_get_driver_tag(struct request *rq)
+{
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+ if (rq->tag != BLK_MQ_NO_TAG &&
+ !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+ hctx->tags->rqs[rq->tag] = rq;
+ return true;
+ }
+
+ return __blk_mq_get_driver_tag(hctx, rq);
+}
static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
{
@@ -331,19 +343,18 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
if (bt->sb.depth == 1)
return true;
- if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+ if (blk_mq_is_shared_tags(hctx->flags)) {
struct request_queue *q = hctx->queue;
- struct blk_mq_tag_set *set = q->tag_set;
if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
return true;
- users = atomic_read(&set->active_queues_shared_sbitmap);
} else {
if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
return true;
- users = atomic_read(&hctx->tags->active_queues);
}
+ users = atomic_read(&hctx->tags->active_queues);
+
if (!users)
return true;
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index f000f83e0621..3cfbc8668cba 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -189,9 +189,10 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
* BIO_TRACKED lets controllers know that a bio went through the
* normal rq_qos path.
*/
- bio_set_flag(bio, BIO_TRACKED);
- if (q->rq_qos)
+ if (q->rq_qos) {
+ bio_set_flag(bio, BIO_TRACKED);
__rq_qos_throttle(q->rq_qos, bio);
+ }
}
static inline void rq_qos_track(struct request_queue *q, struct request *rq,
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a7c857ad7d10..b880c70e22e4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
+static bool disk_has_partitions(struct gendisk *disk)
+{
+ unsigned long idx;
+ struct block_device *part;
+ bool ret = false;
+
+ rcu_read_lock();
+ xa_for_each(&disk->part_tbl, idx, part) {
+ if (bdev_is_partition(part)) {
+ ret = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
/**
* blk_queue_set_zoned - configure a disk queue zoned model.
* @disk: the gendisk of the queue to configure
@@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
* we do nothing special as far as the block layer is concerned.
*/
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
- !xa_empty(&disk->part_tbl))
+ disk_has_partitions(disk))
model = BLK_ZONED_NONE;
break;
case BLK_ZONED_NONE:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 614d9d47de36..cef1f713370b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -17,6 +17,7 @@
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-wbt.h"
+#include "blk-throttle.h"
struct queue_sysfs_entry {
struct attribute attr;
@@ -432,26 +433,11 @@ static ssize_t queue_poll_show(struct request_queue *q, char *page)
static ssize_t queue_poll_store(struct request_queue *q, const char *page,
size_t count)
{
- unsigned long poll_on;
- ssize_t ret;
-
- if (!q->tag_set || q->tag_set->nr_maps <= HCTX_TYPE_POLL ||
- !q->tag_set->map[HCTX_TYPE_POLL].nr_queues)
+ if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
return -EINVAL;
-
- ret = queue_var_store(&poll_on, page, count);
- if (ret < 0)
- return ret;
-
- if (poll_on) {
- blk_queue_flag_set(QUEUE_FLAG_POLL, q);
- } else {
- blk_mq_freeze_queue(q);
- blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
- blk_mq_unfreeze_queue(q);
- }
-
- return ret;
+ pr_info_ratelimited("writes to the poll attribute are ignored.\n");
+ pr_info_ratelimited("please use driver specific parameters instead.\n");
+ return count;
}
static ssize_t queue_io_timeout_show(struct request_queue *q, char *page)
@@ -887,16 +873,15 @@ int blk_register_queue(struct gendisk *disk)
}
mutex_lock(&q->sysfs_lock);
+
+ ret = disk_register_independent_access_ranges(disk, NULL);
+ if (ret)
+ goto put_dev;
+
if (q->elevator) {
ret = elv_register_queue(q, false);
- if (ret) {
- mutex_unlock(&q->sysfs_lock);
- mutex_unlock(&q->sysfs_dir_lock);
- kobject_del(&q->kobj);
- blk_trace_remove_sysfs(dev);
- kobject_put(&dev->kobj);
- return ret;
- }
+ if (ret)
+ goto put_dev;
}
blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
@@ -928,6 +913,16 @@ unlock:
}
return ret;
+
+put_dev:
+ disk_unregister_independent_access_ranges(disk);
+ mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
+ kobject_del(&q->kobj);
+ blk_trace_remove_sysfs(dev);
+ kobject_put(&dev->kobj);
+
+ return ret;
}
/**
@@ -972,6 +967,7 @@ void blk_unregister_queue(struct gendisk *disk)
mutex_lock(&q->sysfs_lock);
if (q->elevator)
elv_unregister_queue(q);
+ disk_unregister_independent_access_ranges(disk);
mutex_unlock(&q->sysfs_lock);
mutex_unlock(&q->sysfs_dir_lock);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7c4e7993ba97..39bb6e68a9a2 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -13,6 +13,7 @@
#include <linux/blk-cgroup.h>
#include "blk.h"
#include "blk-cgroup-rwstat.h"
+#include "blk-throttle.h"
/* Max dispatch from a group in 1 round */
#define THROTL_GRP_QUANTUM 8
@@ -37,60 +38,9 @@
*/
#define LATENCY_FILTERED_HD (1000L) /* 1ms */
-static struct blkcg_policy blkcg_policy_throtl;
-
/* A workqueue to queue throttle related work */
static struct workqueue_struct *kthrotld_workqueue;
-/*
- * To implement hierarchical throttling, throtl_grps form a tree and bios
- * are dispatched upwards level by level until they reach the top and get
- * issued. When dispatching bios from the children and local group at each
- * level, if the bios are dispatched into a single bio_list, there's a risk
- * of a local or child group which can queue many bios at once filling up
- * the list starving others.
- *
- * To avoid such starvation, dispatched bios are queued separately
- * according to where they came from. When they are again dispatched to
- * the parent, they're popped in round-robin order so that no single source
- * hogs the dispatch window.
- *
- * throtl_qnode is used to keep the queued bios separated by their sources.
- * Bios are queued to throtl_qnode which in turn is queued to
- * throtl_service_queue and then dispatched in round-robin order.
- *
- * It's also used to track the reference counts on blkg's. A qnode always
- * belongs to a throtl_grp and gets queued on itself or the parent, so
- * incrementing the reference of the associated throtl_grp when a qnode is
- * queued and decrementing when dequeued is enough to keep the whole blkg
- * tree pinned while bios are in flight.
- */
-struct throtl_qnode {
- struct list_head node; /* service_queue->queued[] */
- struct bio_list bios; /* queued bios */
- struct throtl_grp *tg; /* tg this qnode belongs to */
-};
-
-struct throtl_service_queue {
- struct throtl_service_queue *parent_sq; /* the parent service_queue */
-
- /*
- * Bios queued directly to this service_queue or dispatched from
- * children throtl_grp's.
- */
- struct list_head queued[2]; /* throtl_qnode [READ/WRITE] */
- unsigned int nr_queued[2]; /* number of queued bios */
-
- /*
- * RB tree of active children throtl_grp's, which are sorted by
- * their ->disptime.
- */
- struct rb_root_cached pending_tree; /* RB tree of active tgs */
- unsigned int nr_pending; /* # queued in the tree */
- unsigned long first_pending_disptime; /* disptime of the first tg */
- struct timer_list pending_timer; /* fires on first_pending_disptime */
-};
-
enum tg_state_flags {
THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */
THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */
@@ -98,93 +48,6 @@ enum tg_state_flags {
#define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node)
-enum {
- LIMIT_LOW,
- LIMIT_MAX,
- LIMIT_CNT,
-};
-
-struct throtl_grp {
- /* must be the first member */
- struct blkg_policy_data pd;
-
- /* active throtl group service_queue member */
- struct rb_node rb_node;
-
- /* throtl_data this group belongs to */
- struct throtl_data *td;
-
- /* this group's service queue */
- struct throtl_service_queue service_queue;
-
- /*
- * qnode_on_self is used when bios are directly queued to this
- * throtl_grp so that local bios compete fairly with bios
- * dispatched from children. qnode_on_parent is used when bios are
- * dispatched from this throtl_grp into its parent and will compete
- * with the sibling qnode_on_parents and the parent's
- * qnode_on_self.
- */
- struct throtl_qnode qnode_on_self[2];
- struct throtl_qnode qnode_on_parent[2];
-
- /*
- * Dispatch time in jiffies. This is the estimated time when group
- * will unthrottle and is ready to dispatch more bio. It is used as
- * key to sort active groups in service tree.
- */
- unsigned long disptime;
-
- unsigned int flags;
-
- /* are there any throtl rules between this group and td? */
- bool has_rules[2];
-
- /* internally used bytes per second rate limits */
- uint64_t bps[2][LIMIT_CNT];
- /* user configured bps limits */
- uint64_t bps_conf[2][LIMIT_CNT];
-
- /* internally used IOPS limits */
- unsigned int iops[2][LIMIT_CNT];
- /* user configured IOPS limits */
- unsigned int iops_conf[2][LIMIT_CNT];
-
- /* Number of bytes dispatched in current slice */
- uint64_t bytes_disp[2];
- /* Number of bio's dispatched in current slice */
- unsigned int io_disp[2];
-
- unsigned long last_low_overflow_time[2];
-
- uint64_t last_bytes_disp[2];
- unsigned int last_io_disp[2];
-
- unsigned long last_check_time;
-
- unsigned long latency_target; /* us */
- unsigned long latency_target_conf; /* us */
- /* When did we start a new slice */
- unsigned long slice_start[2];
- unsigned long slice_end[2];
-
- unsigned long last_finish_time; /* ns / 1024 */
- unsigned long checked_last_finish_time; /* ns / 1024 */
- unsigned long avg_idletime; /* ns / 1024 */
- unsigned long idletime_threshold; /* us */
- unsigned long idletime_threshold_conf; /* us */
-
- unsigned int bio_cnt; /* total bios */
- unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
- unsigned long bio_cnt_reset_time;
-
- atomic_t io_split_cnt[2];
- atomic_t last_io_split_cnt[2];
-
- struct blkg_rwstat stat_bytes;
- struct blkg_rwstat stat_ios;
-};
-
/* We measure latency for request size from <= 4k to >= 1M */
#define LATENCY_BUCKET_SIZE 9
@@ -231,16 +94,6 @@ struct throtl_data
static void throtl_pending_timer_fn(struct timer_list *t);
-static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd)
-{
- return pd ? container_of(pd, struct throtl_grp, pd) : NULL;
-}
-
-static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
-{
- return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl));
-}
-
static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg)
{
return pd_to_blkg(&tg->pd);
@@ -1794,7 +1647,7 @@ static void throtl_shutdown_wq(struct request_queue *q)
cancel_work_sync(&td->dispatch_work);
}
-static struct blkcg_policy blkcg_policy_throtl = {
+struct blkcg_policy blkcg_policy_throtl = {
.dfl_cftypes = throtl_files,
.legacy_cftypes = throtl_legacy_files,
@@ -2208,9 +2061,9 @@ void blk_throtl_charge_bio_split(struct bio *bio)
} while (parent);
}
-bool blk_throtl_bio(struct bio *bio)
+bool __blk_throtl_bio(struct bio *bio)
{
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
struct blkcg_gq *blkg = bio->bi_blkg;
struct throtl_qnode *qn = NULL;
struct throtl_grp *tg = blkg_to_tg(blkg);
@@ -2221,19 +2074,12 @@ bool blk_throtl_bio(struct bio *bio)
rcu_read_lock();
- /* see throtl_charge_bio() */
- if (bio_flagged(bio, BIO_THROTTLED))
- goto out;
-
if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
bio->bi_iter.bi_size);
blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
}
- if (!tg->has_rules[rw])
- goto out;
-
spin_lock_irq(&q->queue_lock);
throtl_update_latency_buckets(td);
@@ -2317,7 +2163,6 @@ again:
out_unlock:
spin_unlock_irq(&q->queue_lock);
-out:
bio_set_flag(bio, BIO_THROTTLED);
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
new file mode 100644
index 000000000000..175f03abd9e4
--- /dev/null
+++ b/block/blk-throttle.h
@@ -0,0 +1,182 @@
+#ifndef BLK_THROTTLE_H
+#define BLK_THROTTLE_H
+
+#include "blk-cgroup-rwstat.h"
+
+/*
+ * To implement hierarchical throttling, throtl_grps form a tree and bios
+ * are dispatched upwards level by level until they reach the top and get
+ * issued. When dispatching bios from the children and local group at each
+ * level, if the bios are dispatched into a single bio_list, there's a risk
+ * of a local or child group which can queue many bios at once filling up
+ * the list starving others.
+ *
+ * To avoid such starvation, dispatched bios are queued separately
+ * according to where they came from. When they are again dispatched to
+ * the parent, they're popped in round-robin order so that no single source
+ * hogs the dispatch window.
+ *
+ * throtl_qnode is used to keep the queued bios separated by their sources.
+ * Bios are queued to throtl_qnode which in turn is queued to
+ * throtl_service_queue and then dispatched in round-robin order.
+ *
+ * It's also used to track the reference counts on blkg's. A qnode always
+ * belongs to a throtl_grp and gets queued on itself or the parent, so
+ * incrementing the reference of the associated throtl_grp when a qnode is
+ * queued and decrementing when dequeued is enough to keep the whole blkg
+ * tree pinned while bios are in flight.
+ */
+struct throtl_qnode {
+ struct list_head node; /* service_queue->queued[] */
+ struct bio_list bios; /* queued bios */
+ struct throtl_grp *tg; /* tg this qnode belongs to */
+};
+
+struct throtl_service_queue {
+ struct throtl_service_queue *parent_sq; /* the parent service_queue */
+
+ /*
+ * Bios queued directly to this service_queue or dispatched from
+ * children throtl_grp's.
+ */
+ struct list_head queued[2]; /* throtl_qnode [READ/WRITE] */
+ unsigned int nr_queued[2]; /* number of queued bios */
+
+ /*
+ * RB tree of active children throtl_grp's, which are sorted by
+ * their ->disptime.
+ */
+ struct rb_root_cached pending_tree; /* RB tree of active tgs */
+ unsigned int nr_pending; /* # queued in the tree */
+ unsigned long first_pending_disptime; /* disptime of the first tg */
+ struct timer_list pending_timer; /* fires on first_pending_disptime */
+};
+
+enum {
+ LIMIT_LOW,
+ LIMIT_MAX,
+ LIMIT_CNT,
+};
+
+struct throtl_grp {
+ /* must be the first member */
+ struct blkg_policy_data pd;
+
+ /* active throtl group service_queue member */
+ struct rb_node rb_node;
+
+ /* throtl_data this group belongs to */
+ struct throtl_data *td;
+
+ /* this group's service queue */
+ struct throtl_service_queue service_queue;
+
+ /*
+ * qnode_on_self is used when bios are directly queued to this
+ * throtl_grp so that local bios compete fairly with bios
+ * dispatched from children. qnode_on_parent is used when bios are
+ * dispatched from this throtl_grp into its parent and will compete
+ * with the sibling qnode_on_parents and the parent's
+ * qnode_on_self.
+ */
+ struct throtl_qnode qnode_on_self[2];
+ struct throtl_qnode qnode_on_parent[2];
+
+ /*
+ * Dispatch time in jiffies. This is the estimated time when group
+ * will unthrottle and is ready to dispatch more bio. It is used as
+ * key to sort active groups in service tree.
+ */
+ unsigned long disptime;
+
+ unsigned int flags;
+
+ /* are there any throtl rules between this group and td? */
+ bool has_rules[2];
+
+ /* internally used bytes per second rate limits */
+ uint64_t bps[2][LIMIT_CNT];
+ /* user configured bps limits */
+ uint64_t bps_conf[2][LIMIT_CNT];
+
+ /* internally used IOPS limits */
+ unsigned int iops[2][LIMIT_CNT];
+ /* user configured IOPS limits */
+ unsigned int iops_conf[2][LIMIT_CNT];
+
+ /* Number of bytes dispatched in current slice */
+ uint64_t bytes_disp[2];
+ /* Number of bio's dispatched in current slice */
+ unsigned int io_disp[2];
+
+ unsigned long last_low_overflow_time[2];
+
+ uint64_t last_bytes_disp[2];
+ unsigned int last_io_disp[2];
+
+ unsigned long last_check_time;
+
+ unsigned long latency_target; /* us */
+ unsigned long latency_target_conf; /* us */
+ /* When did we start a new slice */
+ unsigned long slice_start[2];
+ unsigned long slice_end[2];
+
+ unsigned long last_finish_time; /* ns / 1024 */
+ unsigned long checked_last_finish_time; /* ns / 1024 */
+ unsigned long avg_idletime; /* ns / 1024 */
+ unsigned long idletime_threshold; /* us */
+ unsigned long idletime_threshold_conf; /* us */
+
+ unsigned int bio_cnt; /* total bios */
+ unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
+ unsigned long bio_cnt_reset_time;
+
+ atomic_t io_split_cnt[2];
+ atomic_t last_io_split_cnt[2];
+
+ struct blkg_rwstat stat_bytes;
+ struct blkg_rwstat stat_ios;
+};
+
+extern struct blkcg_policy blkcg_policy_throtl;
+
+static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd)
+{
+ return pd ? container_of(pd, struct throtl_grp, pd) : NULL;
+}
+
+static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
+{
+ return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl));
+}
+
+/*
+ * Internal throttling interface
+ */
+#ifndef CONFIG_BLK_DEV_THROTTLING
+static inline int blk_throtl_init(struct request_queue *q) { return 0; }
+static inline void blk_throtl_exit(struct request_queue *q) { }
+static inline void blk_throtl_register_queue(struct request_queue *q) { }
+static inline void blk_throtl_charge_bio_split(struct bio *bio) { }
+static inline bool blk_throtl_bio(struct bio *bio) { return false; }
+#else /* CONFIG_BLK_DEV_THROTTLING */
+int blk_throtl_init(struct request_queue *q);
+void blk_throtl_exit(struct request_queue *q);
+void blk_throtl_register_queue(struct request_queue *q);
+void blk_throtl_charge_bio_split(struct bio *bio);
+bool __blk_throtl_bio(struct bio *bio);
+static inline bool blk_throtl_bio(struct bio *bio)
+{
+ struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg);
+
+ if (bio_flagged(bio, BIO_THROTTLED))
+ return false;
+ if (!tg->has_rules[bio_data_dir(bio)])
+ return false;
+
+ return __blk_throtl_bio(bio);
+}
+#endif /* CONFIG_BLK_DEV_THROTTLING */
+
+#endif
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 874c1c37bf0c..0c119be0e813 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -357,6 +357,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
unsigned int inflight = wbt_inflight(rwb);
int status;
+ if (!rwb->rqos.q->disk)
+ return;
+
status = latency_exceeded(rwb, cb->stat);
trace_wbt_timer(rwb->rqos.q->disk->bdi, status, rqd->scale_step,
diff --git a/block/blk.h b/block/blk.h
index 6c3c00a8fe19..7afffd548daf 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -12,6 +12,8 @@
#include "blk-mq.h"
#include "blk-mq-sched.h"
+struct elevator_type;
+
/* Max future timer expiry for timeouts */
#define BLK_MAX_TIMEOUT (5 * HZ)
@@ -94,6 +96,44 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
return __bvec_gap_to_prev(q, bprv, offset);
}
+static inline bool rq_mergeable(struct request *rq)
+{
+ if (blk_rq_is_passthrough(rq))
+ return false;
+
+ if (req_op(rq) == REQ_OP_FLUSH)
+ return false;
+
+ if (req_op(rq) == REQ_OP_WRITE_ZEROES)
+ return false;
+
+ if (req_op(rq) == REQ_OP_ZONE_APPEND)
+ return false;
+
+ if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
+ return false;
+ if (rq->rq_flags & RQF_NOMERGE_FLAGS)
+ return false;
+
+ return true;
+}
+
+/*
+ * There are two different ways to handle DISCARD merges:
+ * 1) If max_discard_segments > 1, the driver treats every bio as a range and
+ * send the bios to controller together. The ranges don't need to be
+ * contiguous.
+ * 2) Otherwise, the request will be normal read/write requests. The ranges
+ * need to be contiguous.
+ */
+static inline bool blk_discard_mergable(struct request *req)
+{
+ if (req_op(req) == REQ_OP_DISCARD &&
+ queue_max_discard_segments(req->q) > 1)
+ return true;
+ return false;
+}
+
#ifdef CONFIG_BLK_DEV_INTEGRITY
void blk_flush_integrity(void);
bool __bio_integrity_endio(struct bio *);
@@ -175,21 +215,28 @@ static inline void blk_integrity_del(struct gendisk *disk)
unsigned long blk_rq_timeout(unsigned long timeout);
void blk_add_timer(struct request *req);
+void blk_print_req_error(struct request *req, blk_status_t status);
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int nr_segs, struct request **same_queue_rq);
+ unsigned int nr_segs, bool *same_queue_rq);
bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
struct bio *bio, unsigned int nr_segs);
-void blk_account_io_start(struct request *req);
-void blk_account_io_done(struct request *req, u64 now);
+void __blk_account_io_start(struct request *req);
+void __blk_account_io_done(struct request *req, u64 now);
+
+/*
+ * Plug flush limits
+ */
+#define BLK_MAX_REQUEST_COUNT 32
+#define BLK_PLUG_FLUSH_SIZE (128 * 1024)
/*
* Internal elevator interface
*/
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
-void blk_insert_flush(struct request *rq);
+bool blk_insert_flush(struct request *rq);
int elevator_switch_mq(struct request_queue *q,
struct elevator_type *new_e);
@@ -202,7 +249,7 @@ static inline void elevator_exit(struct request_queue *q,
{
lockdep_assert_held(&q->sysfs_lock);
- blk_mq_sched_free_requests(q);
+ blk_mq_sched_free_rqs(q);
__elevator_exit(q, e);
}
@@ -220,7 +267,32 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
ssize_t part_timeout_store(struct device *, struct device_attribute *,
const char *, size_t);
-void __blk_queue_split(struct bio **bio, unsigned int *nr_segs);
+static inline bool blk_may_split(struct request_queue *q, struct bio *bio)
+{
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
+ case REQ_OP_WRITE_ZEROES:
+ case REQ_OP_WRITE_SAME:
+ return true; /* non-trivial splitting decisions */
+ default:
+ break;
+ }
+
+ /*
+ * All drivers must accept single-segments bios that are <= PAGE_SIZE.
+ * This is a quick and dirty check that relies on the fact that
+ * bi_io_vec[0] is always valid if a bio has data. The check might
+ * lead to occasional false negatives when bios are cloned, but compared
+ * to the performance impact of cloned bios themselves the loop below
+ * doesn't matter anyway.
+ */
+ return q->limits.chunk_sectors || bio->bi_vcnt != 1 ||
+ bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
+}
+
+void __blk_queue_split(struct request_queue *q, struct bio **bio,
+ unsigned int *nr_segs);
int ll_back_merge_fn(struct request *req, struct bio *bio,
unsigned int nr_segs);
bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
@@ -240,7 +312,25 @@ int blk_dev_init(void);
*/
static inline bool blk_do_io_stat(struct request *rq)
{
- return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
+ return (rq->rq_flags & RQF_IO_STAT) && rq->rq_disk;
+}
+
+static inline void blk_account_io_done(struct request *req, u64 now)
+{
+ /*
+ * Account IO completion. flush_rq isn't accounted as a
+ * normal IO on queueing nor completion. Accounting the
+ * containing request is enough.
+ */
+ if (blk_do_io_stat(req) && req->part &&
+ !(req->rq_flags & RQF_FLUSH_SEQ))
+ __blk_account_io_done(req, now);
+}
+
+static inline void blk_account_io_start(struct request *req)
+{
+ if (blk_do_io_stat(req))
+ __blk_account_io_start(req);
}
static inline void req_set_nomerge(struct request_queue *q, struct request *req)
@@ -285,22 +375,6 @@ void ioc_clear_queue(struct request_queue *q);
int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
-/*
- * Internal throttling interface
- */
-#ifdef CONFIG_BLK_DEV_THROTTLING
-extern int blk_throtl_init(struct request_queue *q);
-extern void blk_throtl_exit(struct request_queue *q);
-extern void blk_throtl_register_queue(struct request_queue *q);
-extern void blk_throtl_charge_bio_split(struct bio *bio);
-bool blk_throtl_bio(struct bio *bio);
-#else /* CONFIG_BLK_DEV_THROTTLING */
-static inline int blk_throtl_init(struct request_queue *q) { return 0; }
-static inline void blk_throtl_exit(struct request_queue *q) { }
-static inline void blk_throtl_register_queue(struct request_queue *q) { }
-static inline void blk_throtl_charge_bio_split(struct bio *bio) { }
-static inline bool blk_throtl_bio(struct bio *bio) { return false; }
-#endif /* CONFIG_BLK_DEV_THROTTLING */
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
@@ -368,13 +442,20 @@ extern struct device_attribute dev_attr_events;
extern struct device_attribute dev_attr_events_async;
extern struct device_attribute dev_attr_events_poll_msecs;
-static inline void bio_clear_hipri(struct bio *bio)
+static inline void bio_clear_polled(struct bio *bio)
{
/* can't support alloc cache if we turn off polling */
bio_clear_flag(bio, BIO_PERCPU_CACHE);
- bio->bi_opf &= ~REQ_HIPRI;
+ bio->bi_opf &= ~REQ_POLLED;
}
+long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
+long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
+
extern const struct address_space_operations def_blk_aops;
+int disk_register_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *new_iars);
+void disk_unregister_independent_access_ranges(struct gendisk *disk);
+
#endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index 05fc7148489d..7af1a72835b9 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -14,6 +14,7 @@
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
+#include <linux/blk-cgroup.h>
#include <linux/backing-dev.h>
#include <linux/init.h>
#include <linux/hash.h>
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index ccb98276c964..10aa378702fa 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -31,6 +31,7 @@ static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
struct bsg_job *job;
struct request *rq;
struct bio *bio;
+ void *reply;
int ret;
if (hdr->protocol != BSG_PROTOCOL_SCSI ||
@@ -39,22 +40,28 @@ static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
- rq = blk_get_request(q, hdr->dout_xfer_len ?
+ rq = blk_mq_alloc_request(q, hdr->dout_xfer_len ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
rq->timeout = timeout;
job = blk_mq_rq_to_pdu(rq);
+ reply = job->reply;
+ memset(job, 0, sizeof(*job));
+ job->reply = reply;
+ job->reply_len = SCSI_SENSE_BUFFERSIZE;
+ job->dd_data = job + 1;
+
job->request_len = hdr->request_len;
job->request = memdup_user(uptr64(hdr->request), hdr->request_len);
if (IS_ERR(job->request)) {
ret = PTR_ERR(job->request);
- goto out_put_request;
+ goto out_free_rq;
}
if (hdr->dout_xfer_len && hdr->din_xfer_len) {
- job->bidi_rq = blk_get_request(rq->q, REQ_OP_DRV_IN, 0);
+ job->bidi_rq = blk_mq_alloc_request(rq->q, REQ_OP_DRV_IN, 0);
if (IS_ERR(job->bidi_rq)) {
ret = PTR_ERR(job->bidi_rq);
goto out_free_job_request;
@@ -134,11 +141,11 @@ out_unmap_bidi_rq:
blk_rq_unmap_user(job->bidi_bio);
out_free_bidi_rq:
if (job->bidi_rq)
- blk_put_request(job->bidi_rq);
+ blk_mq_free_request(job->bidi_rq);
out_free_job_request:
kfree(job->request);
-out_put_request:
- blk_put_request(rq);
+out_free_rq:
+ blk_mq_free_request(rq);
return ret;
}
@@ -302,18 +309,6 @@ static int bsg_init_rq(struct blk_mq_tag_set *set, struct request *req,
return 0;
}
-/* called right before the request is given to the request_queue user */
-static void bsg_initialize_rq(struct request *req)
-{
- struct bsg_job *job = blk_mq_rq_to_pdu(req);
- void *reply = job->reply;
-
- memset(job, 0, sizeof(*job));
- job->reply = reply;
- job->reply_len = SCSI_SENSE_BUFFERSIZE;
- job->dd_data = job + 1;
-}
-
static void bsg_exit_rq(struct blk_mq_tag_set *set, struct request *req,
unsigned int hctx_idx)
{
@@ -350,7 +345,6 @@ static const struct blk_mq_ops bsg_mq_ops = {
.queue_rq = bsg_queue_rq,
.init_request = bsg_init_rq,
.exit_request = bsg_exit_rq,
- .initialize_rq_fn = bsg_initialize_rq,
.complete = bsg_complete,
.timeout = bsg_timeout,
};
diff --git a/block/elevator.c b/block/elevator.c
index ff45d8388f48..1f39f6e8ebb9 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -26,7 +26,6 @@
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
-#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -40,6 +39,7 @@
#include <trace/events/block.h>
+#include "elevator.h"
#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-pm.h"
@@ -637,7 +637,7 @@ static struct elevator_type *elevator_get_default(struct request_queue *q)
return NULL;
if (q->nr_hw_queues != 1 &&
- !blk_mq_is_sbitmap_shared(q->tag_set->flags))
+ !blk_mq_is_shared_tags(q->tag_set->flags))
return NULL;
return elevator_get(q, "mq-deadline", false);
diff --git a/include/linux/elevator.h b/block/elevator.h
index ef9ceead3db1..16cd8bdedb7e 100644
--- a/include/linux/elevator.h
+++ b/block/elevator.h
@@ -1,17 +1,13 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_ELEVATOR_H
-#define _LINUX_ELEVATOR_H
+#ifndef _ELEVATOR_H
+#define _ELEVATOR_H
#include <linux/percpu.h>
#include <linux/hashtable.h>
-#ifdef CONFIG_BLOCK
-
struct io_cq;
struct elevator_type;
-#ifdef CONFIG_BLK_DEBUG_FS
struct blk_mq_debugfs_attr;
-#endif
/*
* Return values from elevator merger
@@ -162,20 +158,9 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t);
#define ELEVATOR_INSERT_FLUSH 5
#define ELEVATOR_INSERT_SORT_MERGE 6
-#define rq_end_sector(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
#define rb_entry_rq(node) rb_entry((node), struct request, rb_node)
#define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist)
#define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist)
-/*
- * Elevator features.
- */
-
-/* Supports zoned block devices sequential write constraint */
-#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0)
-/* Supports scheduling on multiple hardware queues */
-#define ELEVATOR_F_MQ_AWARE (1U << 1)
-
-#endif /* CONFIG_BLOCK */
-#endif
+#endif /* _ELEVATOR_H */
diff --git a/block/fops.c b/block/fops.c
index 1e970c247e0e..4e22b0794c82 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -17,7 +17,7 @@
#include <linux/fs.h>
#include "blk.h"
-static struct inode *bdev_file_inode(struct file *file)
+static inline struct inode *bdev_file_inode(struct file *file)
{
return file->f_mapping->host;
}
@@ -54,14 +54,12 @@ static void blkdev_bio_end_io_simple(struct bio *bio)
static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
struct iov_iter *iter, unsigned int nr_pages)
{
- struct file *file = iocb->ki_filp;
- struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+ struct block_device *bdev = iocb->ki_filp->private_data;
struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
loff_t pos = iocb->ki_pos;
bool should_dirty = false;
struct bio bio;
ssize_t ret;
- blk_qc_t qc;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
@@ -78,7 +76,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
bio_init(&bio, vecs, nr_pages);
bio_set_dev(&bio, bdev);
- bio.bi_iter.bi_sector = pos >> 9;
+ bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
bio.bi_write_hint = iocb->ki_hint;
bio.bi_private = current;
bio.bi_end_io = blkdev_bio_end_io_simple;
@@ -102,13 +100,12 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
if (iocb->ki_flags & IOCB_HIPRI)
bio_set_polled(&bio, iocb);
- qc = submit_bio(&bio);
+ submit_bio(&bio);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio.bi_private))
break;
- if (!(iocb->ki_flags & IOCB_HIPRI) ||
- !blk_poll(bdev_get_queue(bdev), qc, true))
+ if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, NULL, 0))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
@@ -126,6 +123,11 @@ out:
return ret;
}
+enum {
+ DIO_SHOULD_DIRTY = 1,
+ DIO_IS_SYNC = 2,
+};
+
struct blkdev_dio {
union {
struct kiocb *iocb;
@@ -133,35 +135,27 @@ struct blkdev_dio {
};
size_t size;
atomic_t ref;
- bool multi_bio : 1;
- bool should_dirty : 1;
- bool is_sync : 1;
- struct bio bio;
+ unsigned int flags;
+ struct bio bio ____cacheline_aligned_in_smp;
};
static struct bio_set blkdev_dio_pool;
-static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
-{
- struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
- struct request_queue *q = bdev_get_queue(bdev);
-
- return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
-}
-
static void blkdev_bio_end_io(struct bio *bio)
{
struct blkdev_dio *dio = bio->bi_private;
- bool should_dirty = dio->should_dirty;
+ bool should_dirty = dio->flags & DIO_SHOULD_DIRTY;
if (bio->bi_status && !dio->bio.bi_status)
dio->bio.bi_status = bio->bi_status;
- if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
- if (!dio->is_sync) {
+ if (atomic_dec_and_test(&dio->ref)) {
+ if (!(dio->flags & DIO_IS_SYNC)) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
+ WRITE_ONCE(iocb->private, NULL);
+
if (likely(!dio->bio.bi_status)) {
ret = dio->size;
iocb->ki_pos += ret;
@@ -169,9 +163,8 @@ static void blkdev_bio_end_io(struct bio *bio)
ret = blk_status_to_errno(dio->bio.bi_status);
}
- dio->iocb->ki_complete(iocb, ret, 0);
- if (dio->multi_bio)
- bio_put(&dio->bio);
+ dio->iocb->ki_complete(iocb, ret);
+ bio_put(&dio->bio);
} else {
struct task_struct *waiter = dio->waiter;
@@ -191,16 +184,12 @@ static void blkdev_bio_end_io(struct bio *bio)
static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
unsigned int nr_pages)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = bdev_file_inode(file);
- struct block_device *bdev = I_BDEV(inode);
+ struct block_device *bdev = iocb->ki_filp->private_data;
struct blk_plug plug;
struct blkdev_dio *dio;
struct bio *bio;
- bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
loff_t pos = iocb->ki_pos;
- blk_qc_t qc = BLK_QC_T_NONE;
int ret = 0;
if ((pos | iov_iter_alignment(iter)) &
@@ -210,28 +199,31 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
dio = container_of(bio, struct blkdev_dio, bio);
- dio->is_sync = is_sync = is_sync_kiocb(iocb);
- if (dio->is_sync) {
+ atomic_set(&dio->ref, 1);
+ /*
+ * Grab an extra reference to ensure the dio structure which is embedded
+ * into the first bio stays around.
+ */
+ bio_get(bio);
+
+ is_sync = is_sync_kiocb(iocb);
+ if (is_sync) {
+ dio->flags = DIO_IS_SYNC;
dio->waiter = current;
- bio_get(bio);
} else {
+ dio->flags = 0;
dio->iocb = iocb;
}
dio->size = 0;
- dio->multi_bio = false;
- dio->should_dirty = is_read && iter_is_iovec(iter);
+ if (is_read && iter_is_iovec(iter))
+ dio->flags |= DIO_SHOULD_DIRTY;
- /*
- * Don't plug for HIPRI/polled IO, as those should go straight
- * to issue
- */
- if (!is_poll)
- blk_start_plug(&plug);
+ blk_start_plug(&plug);
for (;;) {
bio_set_dev(bio, bdev);
- bio->bi_iter.bi_sector = pos >> 9;
+ bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
bio->bi_write_hint = iocb->ki_hint;
bio->bi_private = dio;
bio->bi_end_io = blkdev_bio_end_io;
@@ -246,7 +238,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
if (is_read) {
bio->bi_opf = REQ_OP_READ;
- if (dio->should_dirty)
+ if (dio->flags & DIO_SHOULD_DIRTY)
bio_set_pages_dirty(bio);
} else {
bio->bi_opf = dio_bio_write_op(iocb);
@@ -260,40 +252,15 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
if (!nr_pages) {
- bool polled = false;
-
- if (iocb->ki_flags & IOCB_HIPRI) {
- bio_set_polled(bio, iocb);
- polled = true;
- }
-
- qc = submit_bio(bio);
-
- if (polled)
- WRITE_ONCE(iocb->ki_cookie, qc);
+ submit_bio(bio);
break;
}
-
- if (!dio->multi_bio) {
- /*
- * AIO needs an extra reference to ensure the dio
- * structure which is embedded into the first bio
- * stays around.
- */
- if (!is_sync)
- bio_get(bio);
- dio->multi_bio = true;
- atomic_set(&dio->ref, 2);
- } else {
- atomic_inc(&dio->ref);
- }
-
+ atomic_inc(&dio->ref);
submit_bio(bio);
bio = bio_alloc(GFP_KERNEL, nr_pages);
}
- if (!is_poll)
- blk_finish_plug(&plug);
+ blk_finish_plug(&plug);
if (!is_sync)
return -EIOCBQUEUED;
@@ -302,10 +269,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(dio->waiter))
break;
-
- if (!(iocb->ki_flags & IOCB_HIPRI) ||
- !blk_poll(bdev_get_queue(bdev), qc, true))
- blk_io_schedule();
+ blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
@@ -318,6 +282,94 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
return ret;
}
+static void blkdev_bio_end_io_async(struct bio *bio)
+{
+ struct blkdev_dio *dio = container_of(bio, struct blkdev_dio, bio);
+ struct kiocb *iocb = dio->iocb;
+ ssize_t ret;
+
+ if (likely(!bio->bi_status)) {
+ ret = dio->size;
+ iocb->ki_pos += ret;
+ } else {
+ ret = blk_status_to_errno(bio->bi_status);
+ }
+
+ iocb->ki_complete(iocb, ret);
+
+ if (dio->flags & DIO_SHOULD_DIRTY) {
+ bio_check_pages_dirty(bio);
+ } else {
+ bio_release_pages(bio, false);
+ bio_put(bio);
+ }
+}
+
+static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
+ struct iov_iter *iter,
+ unsigned int nr_pages)
+{
+ struct block_device *bdev = iocb->ki_filp->private_data;
+ struct blkdev_dio *dio;
+ struct bio *bio;
+ loff_t pos = iocb->ki_pos;
+ int ret = 0;
+
+ if ((pos | iov_iter_alignment(iter)) &
+ (bdev_logical_block_size(bdev) - 1))
+ return -EINVAL;
+
+ bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
+ dio = container_of(bio, struct blkdev_dio, bio);
+ dio->flags = 0;
+ dio->iocb = iocb;
+ bio_set_dev(bio, bdev);
+ bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+ bio->bi_write_hint = iocb->ki_hint;
+ bio->bi_end_io = blkdev_bio_end_io_async;
+ bio->bi_ioprio = iocb->ki_ioprio;
+
+ if (iov_iter_is_bvec(iter)) {
+ /*
+ * Users don't rely on the iterator being in any particular
+ * state for async I/O returning -EIOCBQUEUED, hence we can
+ * avoid expensive iov_iter_advance(). Bypass
+ * bio_iov_iter_get_pages() and set the bvec directly.
+ */
+ bio_iov_bvec_set(bio, iter);
+ } else {
+ ret = bio_iov_iter_get_pages(bio, iter);
+ if (unlikely(ret)) {
+ bio->bi_status = BLK_STS_IOERR;
+ bio_endio(bio);
+ return ret;
+ }
+ }
+ dio->size = bio->bi_iter.bi_size;
+
+ if (iov_iter_rw(iter) == READ) {
+ bio->bi_opf = REQ_OP_READ;
+ if (iter_is_iovec(iter)) {
+ dio->flags |= DIO_SHOULD_DIRTY;
+ bio_set_pages_dirty(bio);
+ }
+ } else {
+ bio->bi_opf = dio_bio_write_op(iocb);
+ task_io_account_write(bio->bi_iter.bi_size);
+ }
+
+ if (iocb->ki_flags & IOCB_HIPRI) {
+ bio->bi_opf |= REQ_POLLED | REQ_NOWAIT;
+ submit_bio(bio);
+ WRITE_ONCE(iocb->private, bio);
+ } else {
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio->bi_opf |= REQ_NOWAIT;
+ submit_bio(bio);
+ }
+ return -EIOCBQUEUED;
+}
+
static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
unsigned int nr_pages;
@@ -326,9 +378,11 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
return 0;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
- if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
- return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
-
+ if (likely(nr_pages <= BIO_MAX_VECS)) {
+ if (is_sync_kiocb(iocb))
+ return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
+ return __blkdev_direct_IO_async(iocb, iter, nr_pages);
+ }
return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
}
@@ -405,8 +459,7 @@ static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence)
static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
- struct inode *bd_inode = bdev_file_inode(filp);
- struct block_device *bdev = I_BDEV(bd_inode);
+ struct block_device *bdev = filp->private_data;
int error;
error = file_write_and_wait_range(filp, start, end);
@@ -448,6 +501,8 @@ static int blkdev_open(struct inode *inode, struct file *filp)
bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
+
+ filp->private_data = bdev;
filp->f_mapping = bdev->bd_inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
return 0;
@@ -455,29 +510,12 @@ static int blkdev_open(struct inode *inode, struct file *filp)
static int blkdev_close(struct inode *inode, struct file *filp)
{
- struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
+ struct block_device *bdev = filp->private_data;
blkdev_put(bdev, filp->f_mode);
return 0;
}
-static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
-{
- struct block_device *bdev = I_BDEV(bdev_file_inode(file));
- fmode_t mode = file->f_mode;
-
- /*
- * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
- * to updated it before every ioctl.
- */
- if (file->f_flags & O_NDELAY)
- mode |= FMODE_NDELAY;
- else
- mode &= ~FMODE_NDELAY;
-
- return blkdev_ioctl(bdev, mode, cmd, arg);
-}
-
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
@@ -487,14 +525,14 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
*/
static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct file *file = iocb->ki_filp;
- struct inode *bd_inode = bdev_file_inode(file);
+ struct block_device *bdev = iocb->ki_filp->private_data;
+ struct inode *bd_inode = bdev->bd_inode;
loff_t size = i_size_read(bd_inode);
struct blk_plug plug;
size_t shorted = 0;
ssize_t ret;
- if (bdev_read_only(I_BDEV(bd_inode)))
+ if (bdev_read_only(bdev))
return -EPERM;
if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
@@ -526,24 +564,26 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
- struct file *file = iocb->ki_filp;
- struct inode *bd_inode = bdev_file_inode(file);
- loff_t size = i_size_read(bd_inode);
+ struct block_device *bdev = iocb->ki_filp->private_data;
+ loff_t size = i_size_read(bdev->bd_inode);
loff_t pos = iocb->ki_pos;
size_t shorted = 0;
ssize_t ret;
- if (pos >= size)
- return 0;
-
- size -= pos;
- if (iov_iter_count(to) > size) {
- shorted = iov_iter_count(to) - size;
- iov_iter_truncate(to, size);
+ if (unlikely(pos + iov_iter_count(to) > size)) {
+ if (pos >= size)
+ return 0;
+ size -= pos;
+ if (iov_iter_count(to) > size) {
+ shorted = iov_iter_count(to) - size;
+ iov_iter_truncate(to, size);
+ }
}
ret = generic_file_read_iter(iocb, to);
- iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+
+ if (unlikely(shorted))
+ iov_iter_reexpand(to, iov_iter_count(to) + shorted);
return ret;
}
@@ -565,7 +605,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
return -EOPNOTSUPP;
/* Don't go off the end of the device. */
- isize = i_size_read(bdev->bd_inode);
+ isize = bdev_nr_bytes(bdev);
if (start >= isize)
return -EINVAL;
if (end >= isize) {
@@ -592,16 +632,18 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
switch (mode) {
case FALLOC_FL_ZERO_RANGE:
case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
- error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
- GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
+ error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
+ len >> SECTOR_SHIFT, GFP_KERNEL,
+ BLKDEV_ZERO_NOUNMAP);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
- error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
- GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
+ error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
+ len >> SECTOR_SHIFT, GFP_KERNEL,
+ BLKDEV_ZERO_NOFALLBACK);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
- error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
- GFP_KERNEL, 0);
+ error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
+ len >> SECTOR_SHIFT, GFP_KERNEL, 0);
break;
default:
error = -EOPNOTSUPP;
@@ -618,10 +660,10 @@ const struct file_operations def_blk_fops = {
.llseek = blkdev_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
- .iopoll = blkdev_iopoll,
+ .iopoll = iocb_bio_iopoll,
.mmap = generic_file_mmap,
.fsync = blkdev_fsync,
- .unlocked_ioctl = block_ioctl,
+ .unlocked_ioctl = blkdev_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_blkdev_ioctl,
#endif
diff --git a/block/genhd.c b/block/genhd.c
index b49858550fa6..febaaa55125a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -19,6 +19,7 @@
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/kmod.h>
+#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
@@ -57,6 +58,7 @@ void set_capacity(struct gendisk *disk, sector_t sectors)
spin_lock(&bdev->bd_size_lock);
i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+ bdev->bd_nr_sectors = sectors;
spin_unlock(&bdev->bd_size_lock);
}
EXPORT_SYMBOL(set_capacity);
@@ -588,16 +590,6 @@ void del_gendisk(struct gendisk *disk)
* Prevent new I/O from crossing bio_queue_enter().
*/
blk_queue_start_drain(q);
- blk_mq_freeze_queue_wait(q);
-
- rq_qos_exit(q);
- blk_sync_queue(q);
- blk_flush_integrity();
- /*
- * Allow using passthrough request again after the queue is torn down.
- */
- blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
- __blk_mq_unfreeze_queue(q, true);
if (!(disk->flags & GENHD_FL_HIDDEN)) {
sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -620,9 +612,41 @@ void del_gendisk(struct gendisk *disk)
sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
device_del(disk_to_dev(disk));
+
+ blk_mq_freeze_queue_wait(q);
+
+ rq_qos_exit(q);
+ blk_sync_queue(q);
+ blk_flush_integrity();
+ /*
+ * Allow using passthrough request again after the queue is torn down.
+ */
+ blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+ __blk_mq_unfreeze_queue(q, true);
+
}
EXPORT_SYMBOL(del_gendisk);
+/**
+ * invalidate_disk - invalidate the disk
+ * @disk: the struct gendisk to invalidate
+ *
+ * A helper to invalidates the disk. It will clean the disk's associated
+ * buffer/page caches and reset its internal states so that the disk
+ * can be reused by the drivers.
+ *
+ * Context: can sleep
+ */
+void invalidate_disk(struct gendisk *disk)
+{
+ struct block_device *bdev = disk->part0;
+
+ invalidate_bdev(bdev);
+ bdev->bd_inode->i_mapping->wb_err = 0;
+ set_capacity(disk, 0);
+}
+EXPORT_SYMBOL(invalidate_disk);
+
/* sysfs access to bad-blocks list. */
static ssize_t disk_badblocks_show(struct device *dev,
struct device_attribute *attr,
@@ -882,7 +906,7 @@ ssize_t part_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct block_device *bdev = dev_to_bdev(dev);
- struct request_queue *q = bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bdev);
struct disk_stats stat;
unsigned int inflight;
@@ -926,7 +950,7 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct block_device *bdev = dev_to_bdev(dev);
- struct request_queue *q = bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bdev);
unsigned int inflight[2];
if (queue_is_mq(q))
@@ -1266,6 +1290,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
if (!disk->bdi)
goto out_free_disk;
+ /* bdev_alloc() might need the queue, set before the first call */
+ disk->queue = q;
+
disk->part0 = bdev_alloc(disk, 0);
if (!disk->part0)
goto out_free_bdi;
@@ -1281,7 +1308,6 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
disk_to_dev(disk)->type = &disk_type;
device_initialize(disk_to_dev(disk));
inc_diskseq(disk);
- disk->queue = q;
q->disk = disk;
lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0);
#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
@@ -1386,12 +1412,6 @@ void set_disk_ro(struct gendisk *disk, bool read_only)
}
EXPORT_SYMBOL(set_disk_ro);
-int bdev_read_only(struct block_device *bdev)
-{
- return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
-}
-EXPORT_SYMBOL(bdev_read_only);
-
void inc_diskseq(struct gendisk *disk)
{
disk->diskseq = atomic64_inc_return(&diskseq);
diff --git a/block/holder.c b/block/holder.c
index 9dc084182337..27cddce1b446 100644
--- a/block/holder.c
+++ b/block/holder.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/genhd.h>
+#include <linux/slab.h>
struct bd_holder_disk {
struct list_head list;
diff --git a/block/ioctl.c b/block/ioctl.c
index eb0491e90b9a..d6af0ac97e57 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -132,7 +132,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
if (len & 511)
return -EINVAL;
- if (start + len > i_size_read(bdev->bd_inode))
+ if (start + len > bdev_nr_bytes(bdev))
return -EINVAL;
err = truncate_bdev_range(bdev, mode, start, start + len - 1);
@@ -164,7 +164,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
return -EINVAL;
if (len & 511)
return -EINVAL;
- if (end >= (uint64_t)i_size_read(bdev->bd_inode))
+ if (end >= (uint64_t)bdev_nr_bytes(bdev))
return -EINVAL;
if (end < start)
return -EINVAL;
@@ -538,12 +538,21 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
*
* New commands must be compatible and go into blkdev_common_ioctl
*/
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
- unsigned long arg)
+long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
- int ret;
- loff_t size;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
void __user *argp = (void __user *)arg;
+ fmode_t mode = file->f_mode;
+ int ret;
+
+ /*
+ * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+ * to updated it before every ioctl.
+ */
+ if (file->f_flags & O_NDELAY)
+ mode |= FMODE_NDELAY;
+ else
+ mode &= ~FMODE_NDELAY;
switch (cmd) {
/* These need separate implementations for the data structure */
@@ -560,10 +569,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
return put_long(argp,
(bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512);
case BLKGETSIZE:
- size = i_size_read(bdev->bd_inode);
- if ((size >> 9) > ~0UL)
+ if (bdev_nr_sectors(bdev) > ~0UL)
return -EFBIG;
- return put_ulong(argp, size >> 9);
+ return put_ulong(argp, bdev_nr_sectors(bdev));
/* The data is compatible, but the command number is different */
case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
@@ -571,7 +579,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKBSZSET:
return blkdev_bszset(bdev, mode, argp);
case BLKGETSIZE64:
- return put_u64(argp, i_size_read(bdev->bd_inode));
+ return put_u64(argp, bdev_nr_bytes(bdev));
/* Incompatible alignment on i386 */
case BLKTRACESETUP:
@@ -588,7 +596,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
return -ENOTTY;
return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
}
-EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */
#ifdef CONFIG_COMPAT
@@ -606,7 +613,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct gendisk *disk = bdev->bd_disk;
fmode_t mode = file->f_mode;
- loff_t size;
/*
* O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
@@ -632,10 +638,9 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
return compat_put_long(argp,
(bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512);
case BLKGETSIZE:
- size = i_size_read(bdev->bd_inode);
- if ((size >> 9) > ~0UL)
+ if (bdev_nr_sectors(bdev) > ~0UL)
return -EFBIG;
- return compat_put_ulong(argp, size >> 9);
+ return compat_put_ulong(argp, bdev_nr_sectors(bdev));
/* The data is compatible, but the command number is different */
case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
@@ -643,7 +648,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
case BLKBSZSET_32:
return blkdev_bszset(bdev, mode, argp);
case BLKGETSIZE64_32:
- return put_u64(argp, i_size_read(bdev->bd_inode));
+ return put_u64(argp, bdev_nr_bytes(bdev));
/* Incompatible alignment on i386 */
case BLKTRACESETUP32:
diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c
deleted file mode 100644
index 2c4a55bea6ca..000000000000
--- a/block/keyslot-manager.c
+++ /dev/null
@@ -1,578 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright 2019 Google LLC
- */
-
-/**
- * DOC: The Keyslot Manager
- *
- * Many devices with inline encryption support have a limited number of "slots"
- * into which encryption contexts may be programmed, and requests can be tagged
- * with a slot number to specify the key to use for en/decryption.
- *
- * As the number of slots is limited, and programming keys is expensive on
- * many inline encryption hardware, we don't want to program the same key into
- * multiple slots - if multiple requests are using the same key, we want to
- * program just one slot with that key and use that slot for all requests.
- *
- * The keyslot manager manages these keyslots appropriately, and also acts as
- * an abstraction between the inline encryption hardware and the upper layers.
- *
- * Lower layer devices will set up a keyslot manager in their request queue
- * and tell it how to perform device specific operations like programming/
- * evicting keys from keyslots.
- *
- * Upper layers will call blk_ksm_get_slot_for_key() to program a
- * key into some slot in the inline encryption hardware.
- */
-
-#define pr_fmt(fmt) "blk-crypto: " fmt
-
-#include <linux/keyslot-manager.h>
-#include <linux/device.h>
-#include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/pm_runtime.h>
-#include <linux/wait.h>
-#include <linux/blkdev.h>
-
-struct blk_ksm_keyslot {
- atomic_t slot_refs;
- struct list_head idle_slot_node;
- struct hlist_node hash_node;
- const struct blk_crypto_key *key;
- struct blk_keyslot_manager *ksm;
-};
-
-static inline void blk_ksm_hw_enter(struct blk_keyslot_manager *ksm)
-{
- /*
- * Calling into the driver requires ksm->lock held and the device
- * resumed. But we must resume the device first, since that can acquire
- * and release ksm->lock via blk_ksm_reprogram_all_keys().
- */
- if (ksm->dev)
- pm_runtime_get_sync(ksm->dev);
- down_write(&ksm->lock);
-}
-
-static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm)
-{
- up_write(&ksm->lock);
- if (ksm->dev)
- pm_runtime_put_sync(ksm->dev);
-}
-
-static inline bool blk_ksm_is_passthrough(struct blk_keyslot_manager *ksm)
-{
- return ksm->num_slots == 0;
-}
-
-/**
- * blk_ksm_init() - Initialize a keyslot manager
- * @ksm: The keyslot_manager to initialize.
- * @num_slots: The number of key slots to manage.
- *
- * Allocate memory for keyslots and initialize a keyslot manager. Called by
- * e.g. storage drivers to set up a keyslot manager in their request_queue.
- *
- * Return: 0 on success, or else a negative error code.
- */
-int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots)
-{
- unsigned int slot;
- unsigned int i;
- unsigned int slot_hashtable_size;
-
- memset(ksm, 0, sizeof(*ksm));
-
- if (num_slots == 0)
- return -EINVAL;
-
- ksm->slots = kvcalloc(num_slots, sizeof(ksm->slots[0]), GFP_KERNEL);
- if (!ksm->slots)
- return -ENOMEM;
-
- ksm->num_slots = num_slots;
-
- init_rwsem(&ksm->lock);
-
- init_waitqueue_head(&ksm->idle_slots_wait_queue);
- INIT_LIST_HEAD(&ksm->idle_slots);
-
- for (slot = 0; slot < num_slots; slot++) {
- ksm->slots[slot].ksm = ksm;
- list_add_tail(&ksm->slots[slot].idle_slot_node,
- &ksm->idle_slots);
- }
-
- spin_lock_init(&ksm->idle_slots_lock);
-
- slot_hashtable_size = roundup_pow_of_two(num_slots);
- /*
- * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2
- * buckets. This only makes a difference when there is only 1 keyslot.
- */
- if (slot_hashtable_size < 2)
- slot_hashtable_size = 2;
-
- ksm->log_slot_ht_size = ilog2(slot_hashtable_size);
- ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size,
- sizeof(ksm->slot_hashtable[0]),
- GFP_KERNEL);
- if (!ksm->slot_hashtable)
- goto err_destroy_ksm;
- for (i = 0; i < slot_hashtable_size; i++)
- INIT_HLIST_HEAD(&ksm->slot_hashtable[i]);
-
- return 0;
-
-err_destroy_ksm:
- blk_ksm_destroy(ksm);
- return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_init);
-
-static void blk_ksm_destroy_callback(void *ksm)
-{
- blk_ksm_destroy(ksm);
-}
-
-/**
- * devm_blk_ksm_init() - Resource-managed blk_ksm_init()
- * @dev: The device which owns the blk_keyslot_manager.
- * @ksm: The blk_keyslot_manager to initialize.
- * @num_slots: The number of key slots to manage.
- *
- * Like blk_ksm_init(), but causes blk_ksm_destroy() to be called automatically
- * on driver detach.
- *
- * Return: 0 on success, or else a negative error code.
- */
-int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm,
- unsigned int num_slots)
-{
- int err = blk_ksm_init(ksm, num_slots);
-
- if (err)
- return err;
-
- return devm_add_action_or_reset(dev, blk_ksm_destroy_callback, ksm);
-}
-EXPORT_SYMBOL_GPL(devm_blk_ksm_init);
-
-static inline struct hlist_head *
-blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- return &ksm->slot_hashtable[hash_ptr(key, ksm->log_slot_ht_size)];
-}
-
-static void blk_ksm_remove_slot_from_lru_list(struct blk_ksm_keyslot *slot)
-{
- struct blk_keyslot_manager *ksm = slot->ksm;
- unsigned long flags;
-
- spin_lock_irqsave(&ksm->idle_slots_lock, flags);
- list_del(&slot->idle_slot_node);
- spin_unlock_irqrestore(&ksm->idle_slots_lock, flags);
-}
-
-static struct blk_ksm_keyslot *blk_ksm_find_keyslot(
- struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- const struct hlist_head *head = blk_ksm_hash_bucket_for_key(ksm, key);
- struct blk_ksm_keyslot *slotp;
-
- hlist_for_each_entry(slotp, head, hash_node) {
- if (slotp->key == key)
- return slotp;
- }
- return NULL;
-}
-
-static struct blk_ksm_keyslot *blk_ksm_find_and_grab_keyslot(
- struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- struct blk_ksm_keyslot *slot;
-
- slot = blk_ksm_find_keyslot(ksm, key);
- if (!slot)
- return NULL;
- if (atomic_inc_return(&slot->slot_refs) == 1) {
- /* Took first reference to this slot; remove it from LRU list */
- blk_ksm_remove_slot_from_lru_list(slot);
- }
- return slot;
-}
-
-unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot)
-{
- return slot - slot->ksm->slots;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_get_slot_idx);
-
-/**
- * blk_ksm_get_slot_for_key() - Program a key into a keyslot.
- * @ksm: The keyslot manager to program the key into.
- * @key: Pointer to the key object to program, including the raw key, crypto
- * mode, and data unit size.
- * @slot_ptr: A pointer to return the pointer of the allocated keyslot.
- *
- * Get a keyslot that's been programmed with the specified key. If one already
- * exists, return it with incremented refcount. Otherwise, wait for a keyslot
- * to become idle and program it.
- *
- * Context: Process context. Takes and releases ksm->lock.
- * Return: BLK_STS_OK on success (and keyslot is set to the pointer of the
- * allocated keyslot), or some other blk_status_t otherwise (and
- * keyslot is set to NULL).
- */
-blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- struct blk_ksm_keyslot **slot_ptr)
-{
- struct blk_ksm_keyslot *slot;
- int slot_idx;
- int err;
-
- *slot_ptr = NULL;
-
- if (blk_ksm_is_passthrough(ksm))
- return BLK_STS_OK;
-
- down_read(&ksm->lock);
- slot = blk_ksm_find_and_grab_keyslot(ksm, key);
- up_read(&ksm->lock);
- if (slot)
- goto success;
-
- for (;;) {
- blk_ksm_hw_enter(ksm);
- slot = blk_ksm_find_and_grab_keyslot(ksm, key);
- if (slot) {
- blk_ksm_hw_exit(ksm);
- goto success;
- }
-
- /*
- * If we're here, that means there wasn't a slot that was
- * already programmed with the key. So try to program it.
- */
- if (!list_empty(&ksm->idle_slots))
- break;
-
- blk_ksm_hw_exit(ksm);
- wait_event(ksm->idle_slots_wait_queue,
- !list_empty(&ksm->idle_slots));
- }
-
- slot = list_first_entry(&ksm->idle_slots, struct blk_ksm_keyslot,
- idle_slot_node);
- slot_idx = blk_ksm_get_slot_idx(slot);
-
- err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot_idx);
- if (err) {
- wake_up(&ksm->idle_slots_wait_queue);
- blk_ksm_hw_exit(ksm);
- return errno_to_blk_status(err);
- }
-
- /* Move this slot to the hash list for the new key. */
- if (slot->key)
- hlist_del(&slot->hash_node);
- slot->key = key;
- hlist_add_head(&slot->hash_node, blk_ksm_hash_bucket_for_key(ksm, key));
-
- atomic_set(&slot->slot_refs, 1);
-
- blk_ksm_remove_slot_from_lru_list(slot);
-
- blk_ksm_hw_exit(ksm);
-success:
- *slot_ptr = slot;
- return BLK_STS_OK;
-}
-
-/**
- * blk_ksm_put_slot() - Release a reference to a slot
- * @slot: The keyslot to release the reference of.
- *
- * Context: Any context.
- */
-void blk_ksm_put_slot(struct blk_ksm_keyslot *slot)
-{
- struct blk_keyslot_manager *ksm;
- unsigned long flags;
-
- if (!slot)
- return;
-
- ksm = slot->ksm;
-
- if (atomic_dec_and_lock_irqsave(&slot->slot_refs,
- &ksm->idle_slots_lock, flags)) {
- list_add_tail(&slot->idle_slot_node, &ksm->idle_slots);
- spin_unlock_irqrestore(&ksm->idle_slots_lock, flags);
- wake_up(&ksm->idle_slots_wait_queue);
- }
-}
-
-/**
- * blk_ksm_crypto_cfg_supported() - Find out if a crypto configuration is
- * supported by a ksm.
- * @ksm: The keyslot manager to check
- * @cfg: The crypto configuration to check for.
- *
- * Checks for crypto_mode/data unit size/dun bytes support.
- *
- * Return: Whether or not this ksm supports the specified crypto config.
- */
-bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_config *cfg)
-{
- if (!ksm)
- return false;
- if (!(ksm->crypto_modes_supported[cfg->crypto_mode] &
- cfg->data_unit_size))
- return false;
- if (ksm->max_dun_bytes_supported < cfg->dun_bytes)
- return false;
- return true;
-}
-
-/**
- * blk_ksm_evict_key() - Evict a key from the lower layer device.
- * @ksm: The keyslot manager to evict from
- * @key: The key to evict
- *
- * Find the keyslot that the specified key was programmed into, and evict that
- * slot from the lower layer device. The slot must not be in use by any
- * in-flight IO when this function is called.
- *
- * Context: Process context. Takes and releases ksm->lock.
- * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY
- * if the keyslot is still in use, or another -errno value on other
- * error.
- */
-int blk_ksm_evict_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- struct blk_ksm_keyslot *slot;
- int err = 0;
-
- if (blk_ksm_is_passthrough(ksm)) {
- if (ksm->ksm_ll_ops.keyslot_evict) {
- blk_ksm_hw_enter(ksm);
- err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1);
- blk_ksm_hw_exit(ksm);
- return err;
- }
- return 0;
- }
-
- blk_ksm_hw_enter(ksm);
- slot = blk_ksm_find_keyslot(ksm, key);
- if (!slot)
- goto out_unlock;
-
- if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
- err = -EBUSY;
- goto out_unlock;
- }
- err = ksm->ksm_ll_ops.keyslot_evict(ksm, key,
- blk_ksm_get_slot_idx(slot));
- if (err)
- goto out_unlock;
-
- hlist_del(&slot->hash_node);
- slot->key = NULL;
- err = 0;
-out_unlock:
- blk_ksm_hw_exit(ksm);
- return err;
-}
-
-/**
- * blk_ksm_reprogram_all_keys() - Re-program all keyslots.
- * @ksm: The keyslot manager
- *
- * Re-program all keyslots that are supposed to have a key programmed. This is
- * intended only for use by drivers for hardware that loses its keys on reset.
- *
- * Context: Process context. Takes and releases ksm->lock.
- */
-void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm)
-{
- unsigned int slot;
-
- if (blk_ksm_is_passthrough(ksm))
- return;
-
- /* This is for device initialization, so don't resume the device */
- down_write(&ksm->lock);
- for (slot = 0; slot < ksm->num_slots; slot++) {
- const struct blk_crypto_key *key = ksm->slots[slot].key;
- int err;
-
- if (!key)
- continue;
-
- err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot);
- WARN_ON(err);
- }
- up_write(&ksm->lock);
-}
-EXPORT_SYMBOL_GPL(blk_ksm_reprogram_all_keys);
-
-void blk_ksm_destroy(struct blk_keyslot_manager *ksm)
-{
- if (!ksm)
- return;
- kvfree(ksm->slot_hashtable);
- kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots);
- memzero_explicit(ksm, sizeof(*ksm));
-}
-EXPORT_SYMBOL_GPL(blk_ksm_destroy);
-
-bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q)
-{
- if (blk_integrity_queue_supports_integrity(q)) {
- pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
- return false;
- }
- q->ksm = ksm;
- return true;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_register);
-
-void blk_ksm_unregister(struct request_queue *q)
-{
- q->ksm = NULL;
-}
-
-/**
- * blk_ksm_intersect_modes() - restrict supported modes by child device
- * @parent: The keyslot manager for parent device
- * @child: The keyslot manager for child device, or NULL
- *
- * Clear any crypto mode support bits in @parent that aren't set in @child.
- * If @child is NULL, then all parent bits are cleared.
- *
- * Only use this when setting up the keyslot manager for a layered device,
- * before it's been exposed yet.
- */
-void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent,
- const struct blk_keyslot_manager *child)
-{
- if (child) {
- unsigned int i;
-
- parent->max_dun_bytes_supported =
- min(parent->max_dun_bytes_supported,
- child->max_dun_bytes_supported);
- for (i = 0; i < ARRAY_SIZE(child->crypto_modes_supported);
- i++) {
- parent->crypto_modes_supported[i] &=
- child->crypto_modes_supported[i];
- }
- } else {
- parent->max_dun_bytes_supported = 0;
- memset(parent->crypto_modes_supported, 0,
- sizeof(parent->crypto_modes_supported));
- }
-}
-EXPORT_SYMBOL_GPL(blk_ksm_intersect_modes);
-
-/**
- * blk_ksm_is_superset() - Check if a KSM supports a superset of crypto modes
- * and DUN bytes that another KSM supports. Here,
- * "superset" refers to the mathematical meaning of the
- * word - i.e. if two KSMs have the *same* capabilities,
- * they *are* considered supersets of each other.
- * @ksm_superset: The KSM that we want to verify is a superset
- * @ksm_subset: The KSM that we want to verify is a subset
- *
- * Return: True if @ksm_superset supports a superset of the crypto modes and DUN
- * bytes that @ksm_subset supports.
- */
-bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset,
- struct blk_keyslot_manager *ksm_subset)
-{
- int i;
-
- if (!ksm_subset)
- return true;
-
- if (!ksm_superset)
- return false;
-
- for (i = 0; i < ARRAY_SIZE(ksm_superset->crypto_modes_supported); i++) {
- if (ksm_subset->crypto_modes_supported[i] &
- (~ksm_superset->crypto_modes_supported[i])) {
- return false;
- }
- }
-
- if (ksm_subset->max_dun_bytes_supported >
- ksm_superset->max_dun_bytes_supported) {
- return false;
- }
-
- return true;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_is_superset);
-
-/**
- * blk_ksm_update_capabilities() - Update the restrictions of a KSM to those of
- * another KSM
- * @target_ksm: The KSM whose restrictions to update.
- * @reference_ksm: The KSM to whose restrictions this function will update
- * @target_ksm's restrictions to.
- *
- * Blk-crypto requires that crypto capabilities that were
- * advertised when a bio was created continue to be supported by the
- * device until that bio is ended. This is turn means that a device cannot
- * shrink its advertised crypto capabilities without any explicit
- * synchronization with upper layers. So if there's no such explicit
- * synchronization, @reference_ksm must support all the crypto capabilities that
- * @target_ksm does
- * (i.e. we need blk_ksm_is_superset(@reference_ksm, @target_ksm) == true).
- *
- * Note also that as long as the crypto capabilities are being expanded, the
- * order of updates becoming visible is not important because it's alright
- * for blk-crypto to see stale values - they only cause blk-crypto to
- * believe that a crypto capability isn't supported when it actually is (which
- * might result in blk-crypto-fallback being used if available, or the bio being
- * failed).
- */
-void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm,
- struct blk_keyslot_manager *reference_ksm)
-{
- memcpy(target_ksm->crypto_modes_supported,
- reference_ksm->crypto_modes_supported,
- sizeof(target_ksm->crypto_modes_supported));
-
- target_ksm->max_dun_bytes_supported =
- reference_ksm->max_dun_bytes_supported;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_update_capabilities);
-
-/**
- * blk_ksm_init_passthrough() - Init a passthrough keyslot manager
- * @ksm: The keyslot manager to init
- *
- * Initialize a passthrough keyslot manager.
- * Called by e.g. storage drivers to set up a keyslot manager in their
- * request_queue, when the storage driver wants to manage its keys by itself.
- * This is useful for inline encryption hardware that doesn't have the concept
- * of keyslots, and for layered devices.
- */
-void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm)
-{
- memset(ksm, 0, sizeof(*ksm));
- init_rwsem(&ksm->lock);
-}
-EXPORT_SYMBOL_GPL(blk_ksm_init_passthrough);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index a0ffbabfac2c..fdd74a4df56f 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -9,12 +9,12 @@
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
-#include <linux/elevator.h>
#include <linux/module.h>
#include <linux/sbitmap.h>
#include <trace/events/block.h>
+#include "elevator.h"
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
@@ -453,11 +453,11 @@ static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx)
{
struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
struct blk_mq_tags *tags = hctx->sched_tags;
- unsigned int shift = tags->bitmap_tags->sb.shift;
+ unsigned int shift = tags->bitmap_tags.sb.shift;
kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U;
- sbitmap_queue_min_shallow_depth(tags->bitmap_tags, kqd->async_depth);
+ sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth);
}
static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 7f3c3932b723..85d919bf60c7 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -9,7 +9,6 @@
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
-#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -20,6 +19,7 @@
#include <trace/events/block.h>
+#include "elevator.h"
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
@@ -31,6 +31,11 @@
*/
static const int read_expire = HZ / 2; /* max time before a read is submitted. */
static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
+/*
+ * Time after which to dispatch lower priority requests even if higher
+ * priority requests are pending.
+ */
+static const int prio_aging_expire = 10 * HZ;
static const int writes_starved = 2; /* max times reads can starve a write */
static const int fifo_batch = 16; /* # of sequential requests treated as one
by the above parameters. For throughput. */
@@ -51,17 +56,16 @@ enum dd_prio {
enum { DD_PRIO_COUNT = 3 };
-/* I/O statistics per I/O priority. */
+/*
+ * I/O statistics per I/O priority. It is fine if these counters overflow.
+ * What matters is that these counters are at least as wide as
+ * log2(max_outstanding_requests).
+ */
struct io_stats_per_prio {
- local_t inserted;
- local_t merged;
- local_t dispatched;
- local_t completed;
-};
-
-/* I/O statistics for all I/O priorities (enum dd_prio). */
-struct io_stats {
- struct io_stats_per_prio stats[DD_PRIO_COUNT];
+ uint32_t inserted;
+ uint32_t merged;
+ uint32_t dispatched;
+ atomic_t completed;
};
/*
@@ -74,6 +78,7 @@ struct dd_per_prio {
struct list_head fifo_list[DD_DIR_COUNT];
/* Next request in FIFO order. Read, write or both are NULL. */
struct request *next_rq[DD_DIR_COUNT];
+ struct io_stats_per_prio stats;
};
struct deadline_data {
@@ -88,8 +93,6 @@ struct deadline_data {
unsigned int batching; /* number of sequential requests made */
unsigned int starved; /* times reads have starved writes */
- struct io_stats __percpu *stats;
-
/*
* settings that change how the i/o scheduler behaves
*/
@@ -98,38 +101,12 @@ struct deadline_data {
int writes_starved;
int front_merges;
u32 async_depth;
+ int prio_aging_expire;
spinlock_t lock;
spinlock_t zone_lock;
};
-/* Count one event of type 'event_type' and with I/O priority 'prio' */
-#define dd_count(dd, event_type, prio) do { \
- struct io_stats *io_stats = get_cpu_ptr((dd)->stats); \
- \
- BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \
- BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \
- local_inc(&io_stats->stats[(prio)].event_type); \
- put_cpu_ptr(io_stats); \
-} while (0)
-
-/*
- * Returns the total number of dd_count(dd, event_type, prio) calls across all
- * CPUs. No locking or barriers since it is fine if the returned sum is slightly
- * outdated.
- */
-#define dd_sum(dd, event_type, prio) ({ \
- unsigned int cpu; \
- u32 sum = 0; \
- \
- BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \
- BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \
- for_each_present_cpu(cpu) \
- sum += local_read(&per_cpu_ptr((dd)->stats, cpu)-> \
- stats[(prio)].event_type); \
- sum; \
-})
-
/* Maps an I/O priority class to a deadline scheduler priority. */
static const enum dd_prio ioprio_class_to_prio[] = {
[IOPRIO_CLASS_NONE] = DD_BE_PRIO,
@@ -233,7 +210,9 @@ static void dd_merged_requests(struct request_queue *q, struct request *req,
const u8 ioprio_class = dd_rq_ioclass(next);
const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
- dd_count(dd, merged, prio);
+ lockdep_assert_held(&dd->lock);
+
+ dd->per_prio[prio].stats.merged++;
/*
* if next expires before rq, assign its expire time to rq
@@ -270,6 +249,16 @@ deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
deadline_remove_request(rq->q, per_prio, rq);
}
+/* Number of requests queued for a given priority level. */
+static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio)
+{
+ const struct io_stats_per_prio *stats = &dd->per_prio[prio].stats;
+
+ lockdep_assert_held(&dd->lock);
+
+ return stats->inserted - atomic_read(&stats->completed);
+}
+
/*
* deadline_check_fifo returns 0 if there are no expired requests on the fifo,
* 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
@@ -356,11 +345,26 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
}
/*
+ * Returns true if and only if @rq started after @latest_start where
+ * @latest_start is in jiffies.
+ */
+static bool started_after(struct deadline_data *dd, struct request *rq,
+ unsigned long latest_start)
+{
+ unsigned long start_time = (unsigned long)rq->fifo_time;
+
+ start_time -= dd->fifo_expire[rq_data_dir(rq)];
+
+ return time_after(start_time, latest_start);
+}
+
+/*
* deadline_dispatch_requests selects the best request according to
- * read/write expire, fifo_batch, etc
+ * read/write expire, fifo_batch, etc and with a start time <= @latest_start.
*/
static struct request *__dd_dispatch_request(struct deadline_data *dd,
- struct dd_per_prio *per_prio)
+ struct dd_per_prio *per_prio,
+ unsigned long latest_start)
{
struct request *rq, *next_rq;
enum dd_data_dir data_dir;
@@ -372,6 +376,8 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
if (!list_empty(&per_prio->dispatch)) {
rq = list_first_entry(&per_prio->dispatch, struct request,
queuelist);
+ if (started_after(dd, rq, latest_start))
+ return NULL;
list_del_init(&rq->queuelist);
goto done;
}
@@ -449,6 +455,9 @@ dispatch_find_request:
dd->batching = 0;
dispatch_request:
+ if (started_after(dd, rq, latest_start))
+ return NULL;
+
/*
* rq is the selected appropriate request.
*/
@@ -457,7 +466,7 @@ dispatch_request:
done:
ioprio_class = dd_rq_ioclass(rq);
prio = ioprio_class_to_prio[ioprio_class];
- dd_count(dd, dispatched, prio);
+ dd->per_prio[prio].stats.dispatched++;
/*
* If the request needs its target zone locked, do it.
*/
@@ -467,6 +476,34 @@ done:
}
/*
+ * Check whether there are any requests with priority other than DD_RT_PRIO
+ * that were inserted more than prio_aging_expire jiffies ago.
+ */
+static struct request *dd_dispatch_prio_aged_requests(struct deadline_data *dd,
+ unsigned long now)
+{
+ struct request *rq;
+ enum dd_prio prio;
+ int prio_cnt;
+
+ lockdep_assert_held(&dd->lock);
+
+ prio_cnt = !!dd_queued(dd, DD_RT_PRIO) + !!dd_queued(dd, DD_BE_PRIO) +
+ !!dd_queued(dd, DD_IDLE_PRIO);
+ if (prio_cnt < 2)
+ return NULL;
+
+ for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) {
+ rq = __dd_dispatch_request(dd, &dd->per_prio[prio],
+ now - dd->prio_aging_expire);
+ if (rq)
+ return rq;
+ }
+
+ return NULL;
+}
+
+/*
* Called from blk_mq_run_hw_queue() -> __blk_mq_sched_dispatch_requests().
*
* One confusing aspect here is that we get called for a specific
@@ -477,15 +514,26 @@ done:
static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+ const unsigned long now = jiffies;
struct request *rq;
enum dd_prio prio;
spin_lock(&dd->lock);
+ rq = dd_dispatch_prio_aged_requests(dd, now);
+ if (rq)
+ goto unlock;
+
+ /*
+ * Next, dispatch requests in priority order. Ignore lower priority
+ * requests if any higher priority requests are pending.
+ */
for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
- rq = __dd_dispatch_request(dd, &dd->per_prio[prio]);
- if (rq)
+ rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now);
+ if (rq || dd_queued(dd, prio))
break;
}
+
+unlock:
spin_unlock(&dd->lock);
return rq;
@@ -519,7 +567,7 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
dd->async_depth = max(1UL, 3 * q->nr_requests / 4);
- sbitmap_queue_min_shallow_depth(tags->bitmap_tags, dd->async_depth);
+ sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth);
}
/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */
@@ -536,12 +584,21 @@ static void dd_exit_sched(struct elevator_queue *e)
for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
struct dd_per_prio *per_prio = &dd->per_prio[prio];
+ const struct io_stats_per_prio *stats = &per_prio->stats;
+ uint32_t queued;
WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ]));
WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE]));
- }
- free_percpu(dd->stats);
+ spin_lock(&dd->lock);
+ queued = dd_queued(dd, prio);
+ spin_unlock(&dd->lock);
+
+ WARN_ONCE(queued != 0,
+ "statistics for priority %d: i %u m %u d %u c %u\n",
+ prio, stats->inserted, stats->merged,
+ stats->dispatched, atomic_read(&stats->completed));
+ }
kfree(dd);
}
@@ -566,11 +623,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
eq->elevator_data = dd;
- dd->stats = alloc_percpu_gfp(typeof(*dd->stats),
- GFP_KERNEL | __GFP_ZERO);
- if (!dd->stats)
- goto free_dd;
-
for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
struct dd_per_prio *per_prio = &dd->per_prio[prio];
@@ -586,15 +638,13 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
dd->front_merges = 1;
dd->last_dir = DD_WRITE;
dd->fifo_batch = fifo_batch;
+ dd->prio_aging_expire = prio_aging_expire;
spin_lock_init(&dd->lock);
spin_lock_init(&dd->zone_lock);
q->elevator = eq;
return 0;
-free_dd:
- kfree(dd);
-
put_eq:
kobject_put(&eq->kobj);
return ret;
@@ -677,8 +727,11 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
blk_req_zone_write_unlock(rq);
prio = ioprio_class_to_prio[ioprio_class];
- dd_count(dd, inserted, prio);
- rq->elv.priv[0] = (void *)(uintptr_t)1;
+ per_prio = &dd->per_prio[prio];
+ if (!rq->elv.priv[0]) {
+ per_prio->stats.inserted++;
+ rq->elv.priv[0] = (void *)(uintptr_t)1;
+ }
if (blk_mq_sched_try_insert_merge(q, rq, &free)) {
blk_mq_free_requests(&free);
@@ -687,7 +740,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
trace_block_rq_insert(rq);
- per_prio = &dd->per_prio[prio];
if (at_head) {
list_add(&rq->queuelist, &per_prio->dispatch);
} else {
@@ -759,12 +811,13 @@ static void dd_finish_request(struct request *rq)
/*
* The block layer core may call dd_finish_request() without having
- * called dd_insert_requests(). Hence only update statistics for
- * requests for which dd_insert_requests() has been called. See also
- * blk_mq_request_bypass_insert().
+ * called dd_insert_requests(). Skip requests that bypassed I/O
+ * scheduling. See also blk_mq_request_bypass_insert().
*/
- if (rq->elv.priv[0])
- dd_count(dd, completed, prio);
+ if (!rq->elv.priv[0])
+ return;
+
+ atomic_inc(&per_prio->stats.completed);
if (blk_queue_is_zoned(q)) {
unsigned long flags;
@@ -809,6 +862,7 @@ static ssize_t __FUNC(struct elevator_queue *e, char *page) \
#define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR))
SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]);
SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]);
+SHOW_JIFFIES(deadline_prio_aging_expire_show, dd->prio_aging_expire);
SHOW_INT(deadline_writes_starved_show, dd->writes_starved);
SHOW_INT(deadline_front_merges_show, dd->front_merges);
SHOW_INT(deadline_async_depth_show, dd->front_merges);
@@ -838,6 +892,7 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies)
STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX);
STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX);
+STORE_JIFFIES(deadline_prio_aging_expire_store, &dd->prio_aging_expire, 0, INT_MAX);
STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX);
STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1);
STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX);
@@ -856,6 +911,7 @@ static struct elv_fs_entry deadline_attrs[] = {
DD_ATTR(front_merges),
DD_ATTR(async_depth),
DD_ATTR(fifo_batch),
+ DD_ATTR(prio_aging_expire),
__ATTR_NULL
};
@@ -947,38 +1003,48 @@ static int dd_async_depth_show(void *data, struct seq_file *m)
return 0;
}
-/* Number of requests queued for a given priority level. */
-static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio)
-{
- return dd_sum(dd, inserted, prio) - dd_sum(dd, completed, prio);
-}
-
static int dd_queued_show(void *data, struct seq_file *m)
{
struct request_queue *q = data;
struct deadline_data *dd = q->elevator->elevator_data;
+ u32 rt, be, idle;
+
+ spin_lock(&dd->lock);
+ rt = dd_queued(dd, DD_RT_PRIO);
+ be = dd_queued(dd, DD_BE_PRIO);
+ idle = dd_queued(dd, DD_IDLE_PRIO);
+ spin_unlock(&dd->lock);
+
+ seq_printf(m, "%u %u %u\n", rt, be, idle);
- seq_printf(m, "%u %u %u\n", dd_queued(dd, DD_RT_PRIO),
- dd_queued(dd, DD_BE_PRIO),
- dd_queued(dd, DD_IDLE_PRIO));
return 0;
}
/* Number of requests owned by the block driver for a given priority. */
static u32 dd_owned_by_driver(struct deadline_data *dd, enum dd_prio prio)
{
- return dd_sum(dd, dispatched, prio) + dd_sum(dd, merged, prio)
- - dd_sum(dd, completed, prio);
+ const struct io_stats_per_prio *stats = &dd->per_prio[prio].stats;
+
+ lockdep_assert_held(&dd->lock);
+
+ return stats->dispatched + stats->merged -
+ atomic_read(&stats->completed);
}
static int dd_owned_by_driver_show(void *data, struct seq_file *m)
{
struct request_queue *q = data;
struct deadline_data *dd = q->elevator->elevator_data;
+ u32 rt, be, idle;
+
+ spin_lock(&dd->lock);
+ rt = dd_owned_by_driver(dd, DD_RT_PRIO);
+ be = dd_owned_by_driver(dd, DD_BE_PRIO);
+ idle = dd_owned_by_driver(dd, DD_IDLE_PRIO);
+ spin_unlock(&dd->lock);
+
+ seq_printf(m, "%u %u %u\n", rt, be, idle);
- seq_printf(m, "%u %u %u\n", dd_owned_by_driver(dd, DD_RT_PRIO),
- dd_owned_by_driver(dd, DD_BE_PRIO),
- dd_owned_by_driver(dd, DD_IDLE_PRIO));
return 0;
}
diff --git a/block/partitions/Kconfig b/block/partitions/Kconfig
index 278593b8e4e9..7aff4eb81c60 100644
--- a/block/partitions/Kconfig
+++ b/block/partitions/Kconfig
@@ -2,6 +2,8 @@
#
# Partition configuration
#
+menu "Partition Types"
+
config PARTITION_ADVANCED
bool "Advanced partition selection"
help
@@ -267,3 +269,5 @@ config CMDLINE_PARTITION
help
Say Y here if you want to read the partition table from bootargs.
The format for the command line is just like mtdparts.
+
+endmenu
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 7bea19dd9458..334b72ef1d73 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -5,6 +5,7 @@
* Copyright (C) 2020 Christoph Hellwig
*/
#include <linux/fs.h>
+#include <linux/major.h>
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
@@ -90,6 +91,7 @@ static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
{
spin_lock(&bdev->bd_size_lock);
i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+ bdev->bd_nr_sectors = sectors;
spin_unlock(&bdev->bd_size_lock);
}
@@ -203,7 +205,7 @@ static ssize_t part_alignment_offset_show(struct device *dev,
struct block_device *bdev = dev_to_bdev(dev);
return sprintf(buf, "%u\n",
- queue_limit_alignment_offset(&bdev->bd_disk->queue->limits,
+ queue_limit_alignment_offset(&bdev_get_queue(bdev)->limits,
bdev->bd_start_sect));
}
@@ -213,7 +215,7 @@ static ssize_t part_discard_alignment_show(struct device *dev,
struct block_device *bdev = dev_to_bdev(dev);
return sprintf(buf, "%u\n",
- queue_limit_discard_alignment(&bdev->bd_disk->queue->limits,
+ queue_limit_discard_alignment(&bdev_get_queue(bdev)->limits,
bdev->bd_start_sect));
}
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 7ca5c4c374d4..5e9be13a56a8 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -133,7 +133,7 @@ efi_crc32(const void *buf, unsigned long len)
*/
static u64 last_lba(struct gendisk *disk)
{
- return div_u64(disk->part0->bd_inode->i_size,
+ return div_u64(bdev_nr_bytes(disk->part0),
queue_logical_block_size(disk->queue)) - 1ULL;
}
diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c
index 9bca396aef4a..403756dbd50d 100644
--- a/block/partitions/ibm.c
+++ b/block/partitions/ibm.c
@@ -198,7 +198,7 @@ static int find_lnx1_partitions(struct parsed_partitions *state,
char name[],
union label_t *label,
sector_t labelsect,
- loff_t i_size,
+ sector_t nr_sectors,
dasd_information2_t *info)
{
loff_t offset, geo_size, size;
@@ -213,14 +213,14 @@ static int find_lnx1_partitions(struct parsed_partitions *state,
} else {
/*
* Formated w/o large volume support. If the sanity check
- * 'size based on geo == size based on i_size' is true, then
+ * 'size based on geo == size based on nr_sectors' is true, then
* we can safely assume that we know the formatted size of
* the disk, otherwise we need additional information
* that we can only get from a real DASD device.
*/
geo_size = geo->cylinders * geo->heads
* geo->sectors * secperblk;
- size = i_size >> 9;
+ size = nr_sectors;
if (size != geo_size) {
if (!info) {
strlcat(state->pp_buf, "\n", PAGE_SIZE);
@@ -229,7 +229,7 @@ static int find_lnx1_partitions(struct parsed_partitions *state,
if (!strcmp(info->type, "ECKD"))
if (geo_size < size)
size = geo_size;
- /* else keep size based on i_size */
+ /* else keep size based on nr_sectors */
}
}
/* first and only partition starts in the first block after the label */
@@ -293,7 +293,8 @@ int ibm_partition(struct parsed_partitions *state)
struct gendisk *disk = state->disk;
struct block_device *bdev = disk->part0;
int blocksize, res;
- loff_t i_size, offset, size;
+ loff_t offset, size;
+ sector_t nr_sectors;
dasd_information2_t *info;
struct hd_geometry *geo;
char type[5] = {0,};
@@ -308,8 +309,8 @@ int ibm_partition(struct parsed_partitions *state)
blocksize = bdev_logical_block_size(bdev);
if (blocksize <= 0)
goto out_symbol;
- i_size = i_size_read(bdev->bd_inode);
- if (i_size == 0)
+ nr_sectors = bdev_nr_sectors(bdev);
+ if (nr_sectors == 0)
goto out_symbol;
info = kmalloc(sizeof(dasd_information2_t), GFP_KERNEL);
if (info == NULL)
@@ -336,7 +337,7 @@ int ibm_partition(struct parsed_partitions *state)
label);
} else if (!strncmp(type, "LNX1", 4)) {
res = find_lnx1_partitions(state, geo, blocksize, name,
- label, labelsect, i_size,
+ label, labelsect, nr_sectors,
info);
} else if (!strncmp(type, "CMS1", 4)) {
res = find_cms1_partitions(state, geo, blocksize, name,
@@ -353,7 +354,7 @@ int ibm_partition(struct parsed_partitions *state)
res = 1;
if (info->format == DASD_FORMAT_LDL) {
strlcat(state->pp_buf, "(nonl)", PAGE_SIZE);
- size = i_size >> 9;
+ size = nr_sectors;
offset = (info->label_block + 1) * (blocksize >> 9);
put_partition(state, 1, offset, size-offset);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 00c203b2a921..25a52a2a09a8 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -5,7 +5,7 @@
*/
#include <linux/t10-pi.h>
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/crc-t10dif.h>
#include <linux/module.h>
#include <net/checksum.h>
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 8bd288d2b089..3dd5a773c320 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1076,7 +1076,7 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
af_alg_free_resources(areq);
sock_put(sk);
- iocb->ki_complete(iocb, err ? err : (int)resultlen, 0);
+ iocb->ki_complete(iocb, err ? err : (int)resultlen);
}
EXPORT_SYMBOL_GPL(af_alg_async_cb);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index eed65311b5d1..75f1a6cd6621 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2459,18 +2459,70 @@ static void ata_dev_config_devslp(struct ata_device *dev)
}
}
+static void ata_dev_config_cpr(struct ata_device *dev)
+{
+ unsigned int err_mask;
+ size_t buf_len;
+ int i, nr_cpr = 0;
+ struct ata_cpr_log *cpr_log = NULL;
+ u8 *desc, *buf = NULL;
+
+ if (!ata_identify_page_supported(dev,
+ ATA_LOG_CONCURRENT_POSITIONING_RANGES))
+ goto out;
+
+ /*
+ * Read IDENTIFY DEVICE data log, page 0x47
+ * (concurrent positioning ranges). We can have at most 255 32B range
+ * descriptors plus a 64B header.
+ */
+ buf_len = (64 + 255 * 32 + 511) & ~511;
+ buf = kzalloc(buf_len, GFP_KERNEL);
+ if (!buf)
+ goto out;
+
+ err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE,
+ ATA_LOG_CONCURRENT_POSITIONING_RANGES,
+ buf, buf_len >> 9);
+ if (err_mask)
+ goto out;
+
+ nr_cpr = buf[0];
+ if (!nr_cpr)
+ goto out;
+
+ cpr_log = kzalloc(struct_size(cpr_log, cpr, nr_cpr), GFP_KERNEL);
+ if (!cpr_log)
+ goto out;
+
+ cpr_log->nr_cpr = nr_cpr;
+ desc = &buf[64];
+ for (i = 0; i < nr_cpr; i++, desc += 32) {
+ cpr_log->cpr[i].num = desc[0];
+ cpr_log->cpr[i].num_storage_elements = desc[1];
+ cpr_log->cpr[i].start_lba = get_unaligned_le64(&desc[8]);
+ cpr_log->cpr[i].num_lbas = get_unaligned_le64(&desc[16]);
+ }
+
+out:
+ swap(dev->cpr_log, cpr_log);
+ kfree(cpr_log);
+ kfree(buf);
+}
+
static void ata_dev_print_features(struct ata_device *dev)
{
if (!(dev->flags & ATA_DFLAG_FEATURES_MASK))
return;
ata_dev_info(dev,
- "Features:%s%s%s%s%s\n",
+ "Features:%s%s%s%s%s%s\n",
dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "",
dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "",
dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "",
dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "",
- dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "");
+ dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "",
+ dev->cpr_log ? " CPR" : "");
}
/**
@@ -2634,6 +2686,7 @@ int ata_dev_configure(struct ata_device *dev)
ata_dev_config_sense_reporting(dev);
ata_dev_config_zac(dev);
ata_dev_config_trusted(dev);
+ ata_dev_config_cpr(dev);
dev->cdb_len = 32;
if (ata_msg_drv(ap) && print_info)
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 1fb4611f7eeb..15a279f773c7 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1895,7 +1895,7 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
*/
static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf)
{
- int num_pages;
+ int i, num_pages = 0;
static const u8 pages[] = {
0x00, /* page 0x00, this page */
0x80, /* page 0x80, unit serial no page */
@@ -1905,13 +1905,17 @@ static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf)
0xb1, /* page 0xb1, block device characteristics page */
0xb2, /* page 0xb2, thin provisioning page */
0xb6, /* page 0xb6, zoned block device characteristics */
+ 0xb9, /* page 0xb9, concurrent positioning ranges */
};
- num_pages = sizeof(pages);
- if (!(args->dev->flags & ATA_DFLAG_ZAC))
- num_pages--;
+ for (i = 0; i < sizeof(pages); i++) {
+ if (pages[i] == 0xb6 &&
+ !(args->dev->flags & ATA_DFLAG_ZAC))
+ continue;
+ rbuf[num_pages + 4] = pages[i];
+ num_pages++;
+ }
rbuf[3] = num_pages; /* number of supported VPD pages */
- memcpy(rbuf + 4, pages, num_pages);
return 0;
}
@@ -2121,6 +2125,26 @@ static unsigned int ata_scsiop_inq_b6(struct ata_scsi_args *args, u8 *rbuf)
return 0;
}
+static unsigned int ata_scsiop_inq_b9(struct ata_scsi_args *args, u8 *rbuf)
+{
+ struct ata_cpr_log *cpr_log = args->dev->cpr_log;
+ u8 *desc = &rbuf[64];
+ int i;
+
+ /* SCSI Concurrent Positioning Ranges VPD page: SBC-5 rev 1 or later */
+ rbuf[1] = 0xb9;
+ put_unaligned_be16(64 + (int)cpr_log->nr_cpr * 32 - 4, &rbuf[3]);
+
+ for (i = 0; i < cpr_log->nr_cpr; i++, desc += 32) {
+ desc[0] = cpr_log->cpr[i].num;
+ desc[1] = cpr_log->cpr[i].num_storage_elements;
+ put_unaligned_be64(cpr_log->cpr[i].start_lba, &desc[8]);
+ put_unaligned_be64(cpr_log->cpr[i].num_lbas, &desc[16]);
+ }
+
+ return 0;
+}
+
/**
* modecpy - Prepare response for MODE SENSE
* @dest: output buffer
@@ -4120,11 +4144,17 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b2);
break;
case 0xb6:
- if (dev->flags & ATA_DFLAG_ZAC) {
+ if (dev->flags & ATA_DFLAG_ZAC)
ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b6);
- break;
- }
- fallthrough;
+ else
+ ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
+ break;
+ case 0xb9:
+ if (dev->cpr_log)
+ ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b9);
+ else
+ ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
+ break;
default:
ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
break;
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index cfa29dc89bbf..fabf87058d80 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -281,14 +281,14 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
if (!blk)
return -ENOMEM;
+ rbnode->block = blk;
+
if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) {
present = krealloc(rbnode->cache_present,
BITS_TO_LONGS(blklen) * sizeof(*present),
GFP_KERNEL);
- if (!present) {
- kfree(blk);
+ if (!present)
return -ENOMEM;
- }
memset(present + BITS_TO_LONGS(rbnode->blklen), 0,
(BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen))
@@ -305,7 +305,6 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
}
/* update the rbnode block, its size and the base register */
- rbnode->block = blk;
rbnode->blklen = blklen;
rbnode->base_reg = base_reg;
rbnode->cache_present = present;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ab3e37aa1830..d97eaf6adb6d 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -180,14 +180,6 @@ config BLK_DEV_LOOP
bits of, say, a sound file). This is also safe if the file resides
on a remote file server.
- There are several ways of encrypting disks. Some of these require
- kernel patches. The vanilla kernel offers the cryptoloop option
- and a Device Mapper target (which is superior, as it supports all
- file systems). If you want to use the cryptoloop, say Y to both
- LOOP and CRYPTOLOOP, and make sure you have a recent (version 2.12
- or later) version of util-linux. Additionally, be aware that
- the cryptoloop is not safe for storing journaled filesystems.
-
Note that this loop device has nothing to do with the loopback
device used for network connections from the machine to itself.
@@ -211,21 +203,6 @@ config BLK_DEV_LOOP_MIN_COUNT
is used, it can be set to 0, since needed loop devices can be
dynamically allocated with the /dev/loop-control interface.
-config BLK_DEV_CRYPTOLOOP
- tristate "Cryptoloop Support (DEPRECATED)"
- select CRYPTO
- select CRYPTO_CBC
- depends on BLK_DEV_LOOP
- help
- Say Y here if you want to be able to use the ciphers that are
- provided by the CryptoAPI as loop transformation. This might be
- used as hard disk encryption.
-
- WARNING: This device is not safe for journaled file systems like
- ext3 or Reiserfs. Please use the Device Mapper crypto module
- instead, which can be configured to be on-disk compatible with the
- cryptoloop device. cryptoloop support will be removed in Linux 5.16.
-
source "drivers/block/drbd/Kconfig"
config BLK_DEV_NBD
@@ -304,8 +281,8 @@ config BLK_DEV_RAM_SIZE
config CDROM_PKTCDVD
tristate "Packet writing on CD/DVD media (DEPRECATED)"
depends on !UML
+ depends on SCSI
select CDROM
- select SCSI_COMMON
help
Note: This driver is deprecated and will be removed from the
kernel in the near future!
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index bc68817ef496..11a74f17c9ad 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -24,7 +24,6 @@ obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
-obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o
obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o
obj-$(CONFIG_BLK_DEV_SX8) += sx8.o
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 8b1714021498..bf5c124c5452 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -61,10 +61,10 @@
#include <linux/hdreg.h>
#include <linux/delay.h>
#include <linux/init.h>
+#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/fs.h>
#include <linux/blk-mq.h>
-#include <linux/elevator.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
@@ -1780,6 +1780,7 @@ static const struct blk_mq_ops amiflop_mq_ops = {
static int fd_alloc_disk(int drive, int system)
{
struct gendisk *disk;
+ int err;
disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
if (IS_ERR(disk))
@@ -1798,8 +1799,10 @@ static int fd_alloc_disk(int drive, int system)
set_capacity(disk, 880 * 2);
unit[drive].gendisk[system] = disk;
- add_disk(disk);
- return 0;
+ err = add_disk(disk);
+ if (err)
+ blk_cleanup_disk(disk);
+ return err;
}
static int fd_alloc_drive(int drive)
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 06b360f7123a..52484bcdedb9 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -37,8 +37,7 @@ static ssize_t aoedisk_show_state(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct aoedev *d = disk->private_data;
- return snprintf(page, PAGE_SIZE,
- "%s%s\n",
+ return sysfs_emit(page, "%s%s\n",
(d->flags & DEVFL_UP) ? "up" : "down",
(d->flags & DEVFL_KICKME) ? ",kickme" :
(d->nopen && !(d->flags & DEVFL_UP)) ? ",closewait" : "");
@@ -52,8 +51,8 @@ static ssize_t aoedisk_show_mac(struct device *dev,
struct aoetgt *t = d->targets[0];
if (t == NULL)
- return snprintf(page, PAGE_SIZE, "none\n");
- return snprintf(page, PAGE_SIZE, "%pm\n", t->addr);
+ return sysfs_emit(page, "none\n");
+ return sysfs_emit(page, "%pm\n", t->addr);
}
static ssize_t aoedisk_show_netif(struct device *dev,
struct device_attribute *attr, char *page)
@@ -85,7 +84,7 @@ static ssize_t aoedisk_show_netif(struct device *dev,
ne = nd;
nd = nds;
if (*nd == NULL)
- return snprintf(page, PAGE_SIZE, "none\n");
+ return sysfs_emit(page, "none\n");
for (p = page; nd < ne; nd++)
p += scnprintf(p, PAGE_SIZE - (p-page), "%s%s",
p == page ? "" : ",", (*nd)->name);
@@ -99,7 +98,7 @@ static ssize_t aoedisk_show_fwver(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct aoedev *d = disk->private_data;
- return snprintf(page, PAGE_SIZE, "0x%04x\n", (unsigned int) d->fw_ver);
+ return sysfs_emit(page, "0x%04x\n", (unsigned int) d->fw_ver);
}
static ssize_t aoedisk_show_payload(struct device *dev,
struct device_attribute *attr, char *page)
@@ -107,7 +106,7 @@ static ssize_t aoedisk_show_payload(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct aoedev *d = disk->private_data;
- return snprintf(page, PAGE_SIZE, "%lu\n", d->maxbcnt);
+ return sysfs_emit(page, "%lu\n", d->maxbcnt);
}
static int aoedisk_debugfs_show(struct seq_file *s, void *ignored)
@@ -417,7 +416,9 @@ aoeblk_gdalloc(void *vp)
spin_unlock_irqrestore(&d->lock, flags);
- device_add_disk(NULL, gd, aoe_attr_groups);
+ err = device_add_disk(NULL, gd, aoe_attr_groups);
+ if (err)
+ goto out_disk_cleanup;
aoedisk_add_debugfs(d);
spin_lock_irqsave(&d->lock, flags);
@@ -426,6 +427,8 @@ aoeblk_gdalloc(void *vp)
spin_unlock_irqrestore(&d->lock, flags);
return;
+out_disk_cleanup:
+ blk_cleanup_disk(gd);
err_tagset:
blk_mq_free_tag_set(set);
err_mempool:
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index a093644ac39f..d14bdc3589b2 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -68,6 +68,7 @@
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/blk-mq.h>
+#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/completion.h>
#include <linux/wait.h>
@@ -298,6 +299,7 @@ static struct atari_floppy_struct {
disk change detection) */
int flags; /* flags */
struct gendisk *disk[NUM_DISK_MINORS];
+ bool registered[NUM_DISK_MINORS];
int ref;
int type;
struct blk_mq_tag_set tag_set;
@@ -456,10 +458,20 @@ static DEFINE_TIMER(fd_timer, check_change);
static void fd_end_request_cur(blk_status_t err)
{
+ DPRINT(("fd_end_request_cur(), bytes %d of %d\n",
+ blk_rq_cur_bytes(fd_request),
+ blk_rq_bytes(fd_request)));
+
if (!blk_update_request(fd_request, err,
blk_rq_cur_bytes(fd_request))) {
+ DPRINT(("calling __blk_mq_end_request()\n"));
__blk_mq_end_request(fd_request, err);
fd_request = NULL;
+ } else {
+ /* requeue rest of request */
+ DPRINT(("calling blk_mq_requeue_request()\n"));
+ blk_mq_requeue_request(fd_request, true);
+ fd_request = NULL;
}
}
@@ -653,9 +665,6 @@ static inline void copy_buffer(void *from, void *to)
*p2++ = *p1++;
}
-
-
-
/* General Interrupt Handling */
static void (*FloppyIRQHandler)( int status ) = NULL;
@@ -700,12 +709,21 @@ static void fd_error( void )
if (fd_request->error_count >= MAX_ERRORS) {
printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
fd_end_request_cur(BLK_STS_IOERR);
+ finish_fdc();
+ return;
}
else if (fd_request->error_count == RECALIBRATE_ERRORS) {
printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
if (SelectedDrive != -1)
SUD.track = -1;
}
+ /* need to re-run request to recalibrate */
+ atari_disable_irq( IRQ_MFP_FDC );
+
+ setup_req_params( SelectedDrive );
+ do_fd_action( SelectedDrive );
+
+ atari_enable_irq( IRQ_MFP_FDC );
}
@@ -732,8 +750,10 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
if (type) {
type--;
if (type >= NUM_DISK_MINORS ||
- minor2disktype[type].drive_types > DriveType)
+ minor2disktype[type].drive_types > DriveType) {
+ finish_fdc();
return -EINVAL;
+ }
}
q = unit[drive].disk[type]->queue;
@@ -751,6 +771,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
}
if (!UDT || desc->track >= UDT->blocks/UDT->spt/2 || desc->head >= 2) {
+ finish_fdc();
ret = -EINVAL;
goto out;
}
@@ -791,6 +812,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
wait_for_completion(&format_wait);
+ finish_fdc();
ret = FormatError ? -EIO : 0;
out:
blk_mq_unquiesce_queue(q);
@@ -825,6 +847,7 @@ static void do_fd_action( int drive )
else {
/* all sectors finished */
fd_end_request_cur(BLK_STS_OK);
+ finish_fdc();
return;
}
}
@@ -1229,6 +1252,7 @@ static void fd_rwsec_done1(int status)
else {
/* all sectors finished */
fd_end_request_cur(BLK_STS_OK);
+ finish_fdc();
}
return;
@@ -1350,7 +1374,7 @@ static void fd_times_out(struct timer_list *unused)
static void finish_fdc( void )
{
- if (!NeedSeek) {
+ if (!NeedSeek || !stdma_is_locked_by(floppy_irq)) {
finish_fdc_done( 0 );
}
else {
@@ -1385,7 +1409,8 @@ static void finish_fdc_done( int dummy )
start_motor_off_timer();
local_irq_save(flags);
- stdma_release();
+ if (stdma_is_locked_by(floppy_irq))
+ stdma_release();
local_irq_restore(flags);
DPRINT(("finish_fdc() finished\n"));
@@ -1435,8 +1460,7 @@ static int floppy_revalidate(struct gendisk *disk)
unsigned int drive = p - unit;
if (test_bit(drive, &changed_floppies) ||
- test_bit(drive, &fake_change) ||
- p->disktype == 0) {
+ test_bit(drive, &fake_change) || !p->disktype) {
if (UD.flags & FTD_MSG)
printk(KERN_ERR "floppy: clear format %p!\n", UDT);
BufferDrive = -1;
@@ -1475,15 +1499,6 @@ static void setup_req_params( int drive )
ReqTrack, ReqSector, (unsigned long)ReqData ));
}
-static void ataflop_commit_rqs(struct blk_mq_hw_ctx *hctx)
-{
- spin_lock_irq(&ataflop_lock);
- atari_disable_irq(IRQ_MFP_FDC);
- finish_fdc();
- atari_enable_irq(IRQ_MFP_FDC);
- spin_unlock_irq(&ataflop_lock);
-}
-
static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -1491,6 +1506,10 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
int drive = floppy - unit;
int type = floppy->type;
+ DPRINT(("Queue request: drive %d type %d sectors %d of %d last %d\n",
+ drive, type, blk_rq_cur_sectors(bd->rq),
+ blk_rq_sectors(bd->rq), bd->last));
+
spin_lock_irq(&ataflop_lock);
if (fd_request) {
spin_unlock_irq(&ataflop_lock);
@@ -1511,6 +1530,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
/* drive not connected */
printk(KERN_ERR "Unknown Device: fd%d\n", drive );
fd_end_request_cur(BLK_STS_IOERR);
+ stdma_release();
goto out;
}
@@ -1527,11 +1547,13 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
if (--type >= NUM_DISK_MINORS) {
printk(KERN_WARNING "fd%d: invalid disk format", drive );
fd_end_request_cur(BLK_STS_IOERR);
+ stdma_release();
goto out;
}
if (minor2disktype[type].drive_types > DriveType) {
printk(KERN_WARNING "fd%d: unsupported disk format", drive );
fd_end_request_cur(BLK_STS_IOERR);
+ stdma_release();
goto out;
}
type = minor2disktype[type].index;
@@ -1550,8 +1572,6 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
setup_req_params( drive );
do_fd_action( drive );
- if (bd->last)
- finish_fdc();
atari_enable_irq( IRQ_MFP_FDC );
out:
@@ -1634,6 +1654,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
/* what if type > 0 here? Overwrite specified entry ? */
if (type) {
/* refuse to re-set a predefined type for now */
+ finish_fdc();
return -EINVAL;
}
@@ -1701,8 +1722,10 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
/* sanity check */
if (setprm.track != dtp->blocks/dtp->spt/2 ||
- setprm.head != 2)
+ setprm.head != 2) {
+ finish_fdc();
return -EINVAL;
+ }
UDT = dtp;
set_capacity(disk, UDT->blocks);
@@ -1962,7 +1985,6 @@ static const struct block_device_operations floppy_fops = {
static const struct blk_mq_ops ataflop_mq_ops = {
.queue_rq = ataflop_queue_rq,
- .commit_rqs = ataflop_commit_rqs,
};
static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
@@ -2000,12 +2022,28 @@ static void ataflop_probe(dev_t dev)
return;
mutex_lock(&ataflop_probe_lock);
if (!unit[drive].disk[type]) {
- if (ataflop_alloc_disk(drive, type) == 0)
+ if (ataflop_alloc_disk(drive, type) == 0) {
add_disk(unit[drive].disk[type]);
+ unit[drive].registered[type] = true;
+ }
}
mutex_unlock(&ataflop_probe_lock);
}
+static void atari_cleanup_floppy_disk(struct atari_floppy_struct *fs)
+{
+ int type;
+
+ for (type = 0; type < NUM_DISK_MINORS; type++) {
+ if (!fs->disk[type])
+ continue;
+ if (fs->registered[type])
+ del_gendisk(fs->disk[type]);
+ blk_cleanup_disk(fs->disk[type]);
+ }
+ blk_mq_free_tag_set(&fs->tag_set);
+}
+
static int __init atari_floppy_init (void)
{
int i;
@@ -2064,7 +2102,10 @@ static int __init atari_floppy_init (void)
for (i = 0; i < FD_MAX_UNITS; i++) {
unit[i].track = -1;
unit[i].flags = 0;
- add_disk(unit[i].disk[0]);
+ ret = add_disk(unit[i].disk[0]);
+ if (ret)
+ goto err_out_dma;
+ unit[i].registered[0] = true;
}
printk(KERN_INFO "Atari floppy driver: max. %cD, %strack buffering\n",
@@ -2074,12 +2115,11 @@ static int __init atari_floppy_init (void)
return 0;
+err_out_dma:
+ atari_stram_free(DMABuffer);
err:
- while (--i >= 0) {
- blk_cleanup_queue(unit[i].disk[0]->queue);
- put_disk(unit[i].disk[0]);
- blk_mq_free_tag_set(&unit[i].tag_set);
- }
+ while (--i >= 0)
+ atari_cleanup_floppy_disk(&unit[i]);
unregister_blkdev(FLOPPY_MAJOR, "fd");
out_unlock:
@@ -2128,18 +2168,10 @@ __setup("floppy=", atari_floppy_setup);
static void __exit atari_floppy_exit(void)
{
- int i, type;
+ int i;
- for (i = 0; i < FD_MAX_UNITS; i++) {
- for (type = 0; type < NUM_DISK_MINORS; type++) {
- if (!unit[i].disk[type])
- continue;
- del_gendisk(unit[i].disk[type]);
- blk_cleanup_queue(unit[i].disk[type]->queue);
- put_disk(unit[i].disk[type]);
- }
- blk_mq_free_tag_set(&unit[i].tag_set);
- }
+ for (i = 0; i < FD_MAX_UNITS; i++)
+ atari_cleanup_floppy_disk(&unit[i]);
unregister_blkdev(FLOPPY_MAJOR, "fd");
del_timer_sync(&fd_timer);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 530b31240203..aa0472718dce 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -282,7 +282,7 @@ out:
return err;
}
-static blk_qc_t brd_submit_bio(struct bio *bio)
+static void brd_submit_bio(struct bio *bio)
{
struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
sector_t sector = bio->bi_iter.bi_sector;
@@ -299,16 +299,14 @@ static blk_qc_t brd_submit_bio(struct bio *bio)
err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
bio_op(bio), sector);
- if (err)
- goto io_error;
+ if (err) {
+ bio_io_error(bio);
+ return;
+ }
sector += len >> SECTOR_SHIFT;
}
bio_endio(bio);
- return BLK_QC_T_NONE;
-io_error:
- bio_io_error(bio);
- return BLK_QC_T_NONE;
}
static int brd_rw_page(struct block_device *bdev, sector_t sector,
diff --git a/drivers/block/cryptoloop.c b/drivers/block/cryptoloop.c
deleted file mode 100644
index f0a91faa43a8..000000000000
--- a/drivers/block/cryptoloop.c
+++ /dev/null
@@ -1,206 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- Linux loop encryption enabling module
-
- Copyright (C) 2002 Herbert Valerio Riedel <hvr@gnu.org>
- Copyright (C) 2003 Fruhwirth Clemens <clemens@endorphin.org>
-
- */
-
-#include <linux/module.h>
-
-#include <crypto/skcipher.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/blkdev.h>
-#include <linux/scatterlist.h>
-#include <linux/uaccess.h>
-#include "loop.h"
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("loop blockdevice transferfunction adaptor / CryptoAPI");
-MODULE_AUTHOR("Herbert Valerio Riedel <hvr@gnu.org>");
-
-#define LOOP_IV_SECTOR_BITS 9
-#define LOOP_IV_SECTOR_SIZE (1 << LOOP_IV_SECTOR_BITS)
-
-static int
-cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
-{
- int err = -EINVAL;
- int cipher_len;
- int mode_len;
- char cms[LO_NAME_SIZE]; /* cipher-mode string */
- char *mode;
- char *cmsp = cms; /* c-m string pointer */
- struct crypto_sync_skcipher *tfm;
-
- /* encryption breaks for non sector aligned offsets */
-
- if (info->lo_offset % LOOP_IV_SECTOR_SIZE)
- goto out;
-
- strncpy(cms, info->lo_crypt_name, LO_NAME_SIZE);
- cms[LO_NAME_SIZE - 1] = 0;
-
- cipher_len = strcspn(cmsp, "-");
-
- mode = cmsp + cipher_len;
- mode_len = 0;
- if (*mode) {
- mode++;
- mode_len = strcspn(mode, "-");
- }
-
- if (!mode_len) {
- mode = "cbc";
- mode_len = 3;
- }
-
- if (cipher_len + mode_len + 3 > LO_NAME_SIZE)
- return -EINVAL;
-
- memmove(cms, mode, mode_len);
- cmsp = cms + mode_len;
- *cmsp++ = '(';
- memcpy(cmsp, info->lo_crypt_name, cipher_len);
- cmsp += cipher_len;
- *cmsp++ = ')';
- *cmsp = 0;
-
- tfm = crypto_alloc_sync_skcipher(cms, 0, 0);
- if (IS_ERR(tfm))
- return PTR_ERR(tfm);
-
- err = crypto_sync_skcipher_setkey(tfm, info->lo_encrypt_key,
- info->lo_encrypt_key_size);
-
- if (err != 0)
- goto out_free_tfm;
-
- lo->key_data = tfm;
- return 0;
-
- out_free_tfm:
- crypto_free_sync_skcipher(tfm);
-
- out:
- return err;
-}
-
-
-typedef int (*encdec_cbc_t)(struct skcipher_request *req);
-
-static int
-cryptoloop_transfer(struct loop_device *lo, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t IV)
-{
- struct crypto_sync_skcipher *tfm = lo->key_data;
- SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
- struct scatterlist sg_out;
- struct scatterlist sg_in;
-
- encdec_cbc_t encdecfunc;
- struct page *in_page, *out_page;
- unsigned in_offs, out_offs;
- int err;
-
- skcipher_request_set_sync_tfm(req, tfm);
- skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
- NULL, NULL);
-
- sg_init_table(&sg_out, 1);
- sg_init_table(&sg_in, 1);
-
- if (cmd == READ) {
- in_page = raw_page;
- in_offs = raw_off;
- out_page = loop_page;
- out_offs = loop_off;
- encdecfunc = crypto_skcipher_decrypt;
- } else {
- in_page = loop_page;
- in_offs = loop_off;
- out_page = raw_page;
- out_offs = raw_off;
- encdecfunc = crypto_skcipher_encrypt;
- }
-
- while (size > 0) {
- const int sz = min(size, LOOP_IV_SECTOR_SIZE);
- u32 iv[4] = { 0, };
- iv[0] = cpu_to_le32(IV & 0xffffffff);
-
- sg_set_page(&sg_in, in_page, sz, in_offs);
- sg_set_page(&sg_out, out_page, sz, out_offs);
-
- skcipher_request_set_crypt(req, &sg_in, &sg_out, sz, iv);
- err = encdecfunc(req);
- if (err)
- goto out;
-
- IV++;
- size -= sz;
- in_offs += sz;
- out_offs += sz;
- }
-
- err = 0;
-
-out:
- skcipher_request_zero(req);
- return err;
-}
-
-static int
-cryptoloop_ioctl(struct loop_device *lo, int cmd, unsigned long arg)
-{
- return -EINVAL;
-}
-
-static int
-cryptoloop_release(struct loop_device *lo)
-{
- struct crypto_sync_skcipher *tfm = lo->key_data;
- if (tfm != NULL) {
- crypto_free_sync_skcipher(tfm);
- lo->key_data = NULL;
- return 0;
- }
- printk(KERN_ERR "cryptoloop_release(): tfm == NULL?\n");
- return -EINVAL;
-}
-
-static struct loop_func_table cryptoloop_funcs = {
- .number = LO_CRYPT_CRYPTOAPI,
- .init = cryptoloop_init,
- .ioctl = cryptoloop_ioctl,
- .transfer = cryptoloop_transfer,
- .release = cryptoloop_release,
- .owner = THIS_MODULE
-};
-
-static int __init
-init_cryptoloop(void)
-{
- int rc = loop_register_transfer(&cryptoloop_funcs);
-
- if (rc)
- printk(KERN_ERR "cryptoloop: loop_register_transfer failed\n");
- else
- pr_warn("the cryptoloop driver has been deprecated and will be removed in in Linux 5.16\n");
- return rc;
-}
-
-static void __exit
-cleanup_cryptoloop(void)
-{
- if (loop_unregister_transfer(LO_CRYPT_CRYPTOAPI))
- printk(KERN_ERR
- "cryptoloop: loop_unregister_transfer failed\n");
-}
-
-module_init(init_cryptoloop);
-module_exit(cleanup_cryptoloop);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 5d9181382ce1..f27d5b0f9a0b 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1448,7 +1448,7 @@ extern void conn_free_crypto(struct drbd_connection *connection);
/* drbd_req */
extern void do_submit(struct work_struct *ws);
extern void __drbd_make_request(struct drbd_device *, struct bio *);
-extern blk_qc_t drbd_submit_bio(struct bio *bio);
+void drbd_submit_bio(struct bio *bio);
extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
extern int is_valid_ar_handle(struct drbd_request *, sector_t);
@@ -1826,8 +1826,7 @@ static inline sector_t drbd_md_last_sector(struct drbd_backing_dev *bdev)
/* Returns the number of 512 byte sectors of the device */
static inline sector_t drbd_get_capacity(struct block_device *bdev)
{
- /* return bdev ? get_capacity(bdev->bd_disk) : 0; */
- return bdev ? i_size_read(bdev->bd_inode) >> 9 : 0;
+ return bdev ? bdev_nr_sectors(bdev) : 0;
}
/**
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 55234a558e98..19db80a1e409 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2794,7 +2794,9 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
goto out_idr_remove_vol;
}
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_cleanup_disk;
/* inherit the connection state */
device->state.conn = first_connection(resource)->cstate;
@@ -2808,6 +2810,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
drbd_debugfs_device_add(device);
return NO_ERROR;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_idr_remove_vol:
idr_remove(&connection->peer_devices, vnr);
out_idr_remove_from_resource:
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 5ca233644d70..3235532ae077 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1596,7 +1596,7 @@ void do_submit(struct work_struct *ws)
}
}
-blk_qc_t drbd_submit_bio(struct bio *bio)
+void drbd_submit_bio(struct bio *bio)
{
struct drbd_device *device = bio->bi_bdev->bd_disk->private_data;
@@ -1609,7 +1609,6 @@ blk_qc_t drbd_submit_bio(struct bio *bio)
inc_ap_bio(device);
__drbd_make_request(device, bio);
- return BLK_QC_T_NONE;
}
static bool net_timeout_reached(struct drbd_request *net_req,
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index fef79ea52e3e..3873e789478e 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -184,6 +184,7 @@ static int print_unex = 1;
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/major.h>
#include <linux/platform_device.h>
#include <linux/mod_devicetable.h>
#include <linux/mutex.h>
@@ -4478,6 +4479,7 @@ static const struct blk_mq_ops floppy_mq_ops = {
};
static struct platform_device floppy_device[N_DRIVE];
+static bool registered[N_DRIVE];
static bool floppy_available(int drive)
{
@@ -4693,8 +4695,12 @@ static int __init do_floppy_init(void)
if (err)
goto out_remove_drives;
- device_add_disk(&floppy_device[drive].dev, disks[drive][0],
- NULL);
+ registered[drive] = true;
+
+ err = device_add_disk(&floppy_device[drive].dev,
+ disks[drive][0], NULL);
+ if (err)
+ goto out_remove_drives;
}
return 0;
@@ -4703,7 +4709,8 @@ out_remove_drives:
while (drive--) {
if (floppy_available(drive)) {
del_gendisk(disks[drive][0]);
- platform_device_unregister(&floppy_device[drive]);
+ if (registered[drive])
+ platform_device_unregister(&floppy_device[drive]);
}
}
out_release_dma:
@@ -4946,30 +4953,14 @@ static void __exit floppy_module_exit(void)
if (disks[drive][i])
del_gendisk(disks[drive][i]);
}
- platform_device_unregister(&floppy_device[drive]);
+ if (registered[drive])
+ platform_device_unregister(&floppy_device[drive]);
}
for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
if (disks[drive][i])
- blk_cleanup_queue(disks[drive][i]->queue);
+ blk_cleanup_disk(disks[drive][i]);
}
blk_mq_free_tag_set(&tag_sets[drive]);
-
- /*
- * These disks have not called add_disk(). Don't put down
- * queue reference in put_disk().
- */
- if (!(allowed_drive_mask & (1 << drive)) ||
- fdc_state[FDC(drive)].version == FDC_NONE) {
- for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
- if (disks[drive][i])
- disks[drive][i]->queue = NULL;
- }
- }
-
- for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
- if (disks[drive][i])
- put_disk(disks[drive][i]);
- }
}
cancel_delayed_work_sync(&fd_timeout);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 7bf4686af774..3c09a33fa1c7 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -133,58 +133,6 @@ static void loop_global_unlock(struct loop_device *lo, bool global)
static int max_part;
static int part_shift;
-static int transfer_xor(struct loop_device *lo, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t real_block)
-{
- char *raw_buf = kmap_atomic(raw_page) + raw_off;
- char *loop_buf = kmap_atomic(loop_page) + loop_off;
- char *in, *out, *key;
- int i, keysize;
-
- if (cmd == READ) {
- in = raw_buf;
- out = loop_buf;
- } else {
- in = loop_buf;
- out = raw_buf;
- }
-
- key = lo->lo_encrypt_key;
- keysize = lo->lo_encrypt_key_size;
- for (i = 0; i < size; i++)
- *out++ = *in++ ^ key[(i & 511) % keysize];
-
- kunmap_atomic(loop_buf);
- kunmap_atomic(raw_buf);
- cond_resched();
- return 0;
-}
-
-static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
-{
- if (unlikely(info->lo_encrypt_key_size <= 0))
- return -EINVAL;
- return 0;
-}
-
-static struct loop_func_table none_funcs = {
- .number = LO_CRYPT_NONE,
-};
-
-static struct loop_func_table xor_funcs = {
- .number = LO_CRYPT_XOR,
- .transfer = transfer_xor,
- .init = xor_init
-};
-
-/* xfer_funcs[0] is special - its release function is never called */
-static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
- &none_funcs,
- &xor_funcs
-};
-
static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
loff_t loopsize;
@@ -228,8 +176,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
/*
* We support direct I/O only if lo_offset is aligned with the
* logical I/O size of backing device, and the logical block
- * size of loop is bigger than the backing device's and the loop
- * needn't transform transfer.
+ * size of loop is bigger than the backing device's.
*
* TODO: the above condition may be loosed in the future, and
* direct I/O may be switched runtime at that time because most
@@ -238,8 +185,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
if (dio) {
if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
!(lo->lo_offset & dio_align) &&
- mapping->a_ops->direct_IO &&
- !lo->transfer)
+ mapping->a_ops->direct_IO)
use_dio = true;
else
use_dio = false;
@@ -273,19 +219,6 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
}
/**
- * loop_validate_block_size() - validates the passed in block size
- * @bsize: size to validate
- */
-static int
-loop_validate_block_size(unsigned short bsize)
-{
- if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
- return -EINVAL;
-
- return 0;
-}
-
-/**
* loop_set_size() - sets device size and notifies userspace
* @lo: struct loop_device to set the size for
* @size: new size of the loop device
@@ -299,24 +232,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
}
-static inline int
-lo_do_transfer(struct loop_device *lo, int cmd,
- struct page *rpage, unsigned roffs,
- struct page *lpage, unsigned loffs,
- int size, sector_t rblock)
-{
- int ret;
-
- ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
- if (likely(!ret))
- return 0;
-
- printk_ratelimited(KERN_ERR
- "loop: Transfer error at byte offset %llu, length %i.\n",
- (unsigned long long)rblock << 9, size);
- return ret;
-}
-
static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
{
struct iov_iter i;
@@ -356,41 +271,6 @@ static int lo_write_simple(struct loop_device *lo, struct request *rq,
return ret;
}
-/*
- * This is the slow, transforming version that needs to double buffer the
- * data as it cannot do the transformations in place without having direct
- * access to the destination pages of the backing file.
- */
-static int lo_write_transfer(struct loop_device *lo, struct request *rq,
- loff_t pos)
-{
- struct bio_vec bvec, b;
- struct req_iterator iter;
- struct page *page;
- int ret = 0;
-
- page = alloc_page(GFP_NOIO);
- if (unlikely(!page))
- return -ENOMEM;
-
- rq_for_each_segment(bvec, rq, iter) {
- ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page,
- bvec.bv_offset, bvec.bv_len, pos >> 9);
- if (unlikely(ret))
- break;
-
- b.bv_page = page;
- b.bv_offset = 0;
- b.bv_len = bvec.bv_len;
- ret = lo_write_bvec(lo->lo_backing_file, &b, &pos);
- if (ret < 0)
- break;
- }
-
- __free_page(page);
- return ret;
-}
-
static int lo_read_simple(struct loop_device *lo, struct request *rq,
loff_t pos)
{
@@ -420,64 +300,12 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq,
return 0;
}
-static int lo_read_transfer(struct loop_device *lo, struct request *rq,
- loff_t pos)
-{
- struct bio_vec bvec, b;
- struct req_iterator iter;
- struct iov_iter i;
- struct page *page;
- ssize_t len;
- int ret = 0;
-
- page = alloc_page(GFP_NOIO);
- if (unlikely(!page))
- return -ENOMEM;
-
- rq_for_each_segment(bvec, rq, iter) {
- loff_t offset = pos;
-
- b.bv_page = page;
- b.bv_offset = 0;
- b.bv_len = bvec.bv_len;
-
- iov_iter_bvec(&i, READ, &b, 1, b.bv_len);
- len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
- if (len < 0) {
- ret = len;
- goto out_free_page;
- }
-
- ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page,
- bvec.bv_offset, len, offset >> 9);
- if (ret)
- goto out_free_page;
-
- flush_dcache_page(bvec.bv_page);
-
- if (len != bvec.bv_len) {
- struct bio *bio;
-
- __rq_for_each_bio(bio, rq)
- zero_fill_bio(bio);
- break;
- }
- }
-
- ret = 0;
-out_free_page:
- __free_page(page);
- return ret;
-}
-
static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
int mode)
{
/*
* We use fallocate to manipulate the space mappings used by the image
- * a.k.a. discard/zerorange. However we do not support this if
- * encryption is enabled, because it may give an attacker useful
- * information.
+ * a.k.a. discard/zerorange.
*/
struct file *file = lo->lo_backing_file;
struct request_queue *q = lo->lo_queue;
@@ -554,7 +382,7 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
blk_mq_complete_request(rq);
}
-static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
+static void lo_rw_aio_complete(struct kiocb *iocb, long ret)
{
struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
@@ -627,7 +455,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
lo_rw_aio_do_completion(cmd);
if (ret != -EIOCBQUEUED)
- cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
+ lo_rw_aio_complete(&cmd->iocb, ret);
return 0;
}
@@ -660,16 +488,12 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
case REQ_OP_DISCARD:
return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
case REQ_OP_WRITE:
- if (lo->transfer)
- return lo_write_transfer(lo, rq, pos);
- else if (cmd->use_aio)
+ if (cmd->use_aio)
return lo_rw_aio(lo, cmd, pos, WRITE);
else
return lo_write_simple(lo, rq, pos);
case REQ_OP_READ:
- if (lo->transfer)
- return lo_read_transfer(lo, rq, pos);
- else if (cmd->use_aio)
+ if (cmd->use_aio)
return lo_rw_aio(lo, cmd, pos, READ);
else
return lo_read_simple(lo, rq, pos);
@@ -934,7 +758,7 @@ static void loop_config_discard(struct loop_device *lo)
* not blkdev_issue_discard(). This maintains consistent behavior with
* file-backed loop devices: discarded regions read back as zero.
*/
- if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
+ if (S_ISBLK(inode->i_mode)) {
struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
@@ -943,11 +767,9 @@ static void loop_config_discard(struct loop_device *lo)
/*
* We use punch hole to reclaim the free space used by the
- * image a.k.a. discard. However we do not support discard if
- * encryption is enabled, because it may give an attacker
- * useful information.
+ * image a.k.a. discard.
*/
- } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
+ } else if (!file->f_op->fallocate) {
max_discard_sectors = 0;
granularity = 0;
@@ -1084,43 +906,6 @@ static void loop_update_rotational(struct loop_device *lo)
blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
}
-static int
-loop_release_xfer(struct loop_device *lo)
-{
- int err = 0;
- struct loop_func_table *xfer = lo->lo_encryption;
-
- if (xfer) {
- if (xfer->release)
- err = xfer->release(lo);
- lo->transfer = NULL;
- lo->lo_encryption = NULL;
- module_put(xfer->owner);
- }
- return err;
-}
-
-static int
-loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
- const struct loop_info64 *i)
-{
- int err = 0;
-
- if (xfer) {
- struct module *owner = xfer->owner;
-
- if (!try_module_get(owner))
- return -EINVAL;
- if (xfer->init)
- err = xfer->init(lo, i);
- if (err)
- module_put(owner);
- else
- lo->lo_encryption = xfer;
- }
- return err;
-}
-
/**
* loop_set_status_from_info - configure device from loop_info
* @lo: struct loop_device to configure
@@ -1133,55 +918,27 @@ static int
loop_set_status_from_info(struct loop_device *lo,
const struct loop_info64 *info)
{
- int err;
- struct loop_func_table *xfer;
- kuid_t uid = current_uid();
-
if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
return -EINVAL;
- err = loop_release_xfer(lo);
- if (err)
- return err;
-
- if (info->lo_encrypt_type) {
- unsigned int type = info->lo_encrypt_type;
-
- if (type >= MAX_LO_CRYPT)
- return -EINVAL;
- xfer = xfer_funcs[type];
- if (xfer == NULL)
- return -EINVAL;
- } else
- xfer = NULL;
-
- err = loop_init_xfer(lo, xfer, info);
- if (err)
- return err;
+ switch (info->lo_encrypt_type) {
+ case LO_CRYPT_NONE:
+ break;
+ case LO_CRYPT_XOR:
+ pr_warn("support for the xor transformation has been removed.\n");
+ return -EINVAL;
+ case LO_CRYPT_CRYPTOAPI:
+ pr_warn("support for cryptoloop has been removed. Use dm-crypt instead.\n");
+ return -EINVAL;
+ default:
+ return -EINVAL;
+ }
lo->lo_offset = info->lo_offset;
lo->lo_sizelimit = info->lo_sizelimit;
memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
- memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
lo->lo_file_name[LO_NAME_SIZE-1] = 0;
- lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
-
- if (!xfer)
- xfer = &none_funcs;
- lo->transfer = xfer->transfer;
- lo->ioctl = xfer->ioctl;
-
lo->lo_flags = info->lo_flags;
-
- lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
- lo->lo_init[0] = info->lo_init[0];
- lo->lo_init[1] = info->lo_init[1];
- if (info->lo_encrypt_key_size) {
- memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
- info->lo_encrypt_key_size);
- lo->lo_key_owner = uid;
- }
-
return 0;
}
@@ -1236,7 +993,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
}
if (config->block_size) {
- error = loop_validate_block_size(config->block_size);
+ error = blk_validate_block_size(config->block_size);
if (error)
goto out_unlock;
}
@@ -1329,7 +1086,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
{
struct file *filp = NULL;
gfp_t gfp = lo->old_gfp_mask;
- struct block_device *bdev = lo->lo_device;
int err = 0;
bool partscan = false;
int lo_number;
@@ -1381,36 +1137,23 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
lo->lo_backing_file = NULL;
spin_unlock_irq(&lo->lo_lock);
- loop_release_xfer(lo);
- lo->transfer = NULL;
- lo->ioctl = NULL;
lo->lo_device = NULL;
- lo->lo_encryption = NULL;
lo->lo_offset = 0;
lo->lo_sizelimit = 0;
- lo->lo_encrypt_key_size = 0;
- memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
- memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
blk_queue_logical_block_size(lo->lo_queue, 512);
blk_queue_physical_block_size(lo->lo_queue, 512);
blk_queue_io_min(lo->lo_queue, 512);
- if (bdev) {
- invalidate_bdev(bdev);
- bdev->bd_inode->i_mapping->wb_err = 0;
- }
- set_capacity(lo->lo_disk, 0);
+ invalidate_disk(lo->lo_disk);
loop_sysfs_exit(lo);
- if (bdev) {
- /* let user-space know about this change */
- kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
- }
+ /* let user-space know about this change */
+ kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
mapping_set_gfp_mask(filp->f_mapping, gfp);
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
blk_mq_unfreeze_queue(lo->lo_queue);
- partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
+ partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
lo_number = lo->lo_number;
disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE);
out_unlock:
@@ -1498,7 +1241,6 @@ static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
int err;
- kuid_t uid = current_uid();
int prev_lo_flags;
bool partscan = false;
bool size_changed = false;
@@ -1506,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
err = mutex_lock_killable(&lo->lo_mutex);
if (err)
return err;
- if (lo->lo_encrypt_key_size &&
- !uid_eq(lo->lo_key_owner, uid) &&
- !capable(CAP_SYS_ADMIN)) {
- err = -EPERM;
- goto out_unlock;
- }
if (lo->lo_state != Lo_bound) {
err = -ENXIO;
goto out_unlock;
@@ -1597,14 +1333,6 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
info->lo_sizelimit = lo->lo_sizelimit;
info->lo_flags = lo->lo_flags;
memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE);
- memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);
- info->lo_encrypt_type =
- lo->lo_encryption ? lo->lo_encryption->number : 0;
- if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) {
- info->lo_encrypt_key_size = lo->lo_encrypt_key_size;
- memcpy(info->lo_encrypt_key, lo->lo_encrypt_key,
- lo->lo_encrypt_key_size);
- }
/* Drop lo_mutex while we call into the filesystem. */
path = lo->lo_backing_file->f_path;
@@ -1630,16 +1358,8 @@ loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64)
info64->lo_rdevice = info->lo_rdevice;
info64->lo_offset = info->lo_offset;
info64->lo_sizelimit = 0;
- info64->lo_encrypt_type = info->lo_encrypt_type;
- info64->lo_encrypt_key_size = info->lo_encrypt_key_size;
info64->lo_flags = info->lo_flags;
- info64->lo_init[0] = info->lo_init[0];
- info64->lo_init[1] = info->lo_init[1];
- if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE);
- else
- memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
- memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
}
static int
@@ -1651,16 +1371,8 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
info->lo_inode = info64->lo_inode;
info->lo_rdevice = info64->lo_rdevice;
info->lo_offset = info64->lo_offset;
- info->lo_encrypt_type = info64->lo_encrypt_type;
- info->lo_encrypt_key_size = info64->lo_encrypt_key_size;
info->lo_flags = info64->lo_flags;
- info->lo_init[0] = info64->lo_init[0];
- info->lo_init[1] = info64->lo_init[1];
- if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
- else
- memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
- memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
/* error in case values were truncated */
if (info->lo_device != info64->lo_device ||
@@ -1759,7 +1471,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
if (lo->lo_state != Lo_bound)
return -ENXIO;
- err = loop_validate_block_size(arg);
+ err = blk_validate_block_size(arg);
if (err)
return err;
@@ -1809,7 +1521,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
err = loop_set_block_size(lo, arg);
break;
default:
- err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
+ err = -EINVAL;
}
mutex_unlock(&lo->lo_mutex);
return err;
@@ -1885,7 +1597,6 @@ struct compat_loop_info {
compat_ulong_t lo_inode; /* ioctl r/o */
compat_dev_t lo_rdevice; /* ioctl r/o */
compat_int_t lo_offset;
- compat_int_t lo_encrypt_type;
compat_int_t lo_encrypt_key_size; /* ioctl w/o */
compat_int_t lo_flags; /* ioctl r/o */
char lo_name[LO_NAME_SIZE];
@@ -1914,16 +1625,8 @@ loop_info64_from_compat(const struct compat_loop_info __user *arg,
info64->lo_rdevice = info.lo_rdevice;
info64->lo_offset = info.lo_offset;
info64->lo_sizelimit = 0;
- info64->lo_encrypt_type = info.lo_encrypt_type;
- info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
info64->lo_flags = info.lo_flags;
- info64->lo_init[0] = info.lo_init[0];
- info64->lo_init[1] = info.lo_init[1];
- if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
- else
- memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
- memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
return 0;
}
@@ -1943,24 +1646,14 @@ loop_info64_to_compat(const struct loop_info64 *info64,
info.lo_inode = info64->lo_inode;
info.lo_rdevice = info64->lo_rdevice;
info.lo_offset = info64->lo_offset;
- info.lo_encrypt_type = info64->lo_encrypt_type;
- info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
info.lo_flags = info64->lo_flags;
- info.lo_init[0] = info64->lo_init[0];
- info.lo_init[1] = info64->lo_init[1];
- if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
- else
- memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
- memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
/* error in case values were truncated */
if (info.lo_device != info64->lo_device ||
info.lo_rdevice != info64->lo_rdevice ||
info.lo_inode != info64->lo_inode ||
- info.lo_offset != info64->lo_offset ||
- info.lo_init[0] != info64->lo_init[0] ||
- info.lo_init[1] != info64->lo_init[1])
+ info.lo_offset != info64->lo_offset)
return -EOVERFLOW;
if (copy_to_user(arg, &info, sizeof(info)))
@@ -2101,43 +1794,6 @@ MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
-int loop_register_transfer(struct loop_func_table *funcs)
-{
- unsigned int n = funcs->number;
-
- if (n >= MAX_LO_CRYPT || xfer_funcs[n])
- return -EINVAL;
- xfer_funcs[n] = funcs;
- return 0;
-}
-
-int loop_unregister_transfer(int number)
-{
- unsigned int n = number;
- struct loop_func_table *xfer;
-
- if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
- return -EINVAL;
- /*
- * This function is called from only cleanup_cryptoloop().
- * Given that each loop device that has a transfer enabled holds a
- * reference to the module implementing it we should never get here
- * with a transfer that is set (unless forced module unloading is
- * requested). Thus, check module's refcount and warn if this is
- * not a clean unloading.
- */
-#ifdef CONFIG_MODULE_UNLOAD
- if (xfer->owner && module_refcount(xfer->owner) != -1)
- pr_err("Danger! Unregistering an in use transfer function.\n");
-#endif
-
- xfer_funcs[n] = NULL;
- return 0;
-}
-
-EXPORT_SYMBOL(loop_register_transfer);
-EXPORT_SYMBOL(loop_unregister_transfer);
-
static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -2394,13 +2050,19 @@ static int loop_add(int i)
disk->event_flags = DISK_EVENT_FLAG_UEVENT;
sprintf(disk->disk_name, "loop%d", i);
/* Make this loop device reachable from pathname. */
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_cleanup_disk;
+
/* Show this loop device. */
mutex_lock(&loop_ctl_mutex);
lo->idr_visible = true;
mutex_unlock(&loop_ctl_mutex);
+
return i;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_cleanup_tags:
blk_mq_free_tag_set(&lo->tag_set);
out_free_idr:
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 04c88dd6eabd..082d4b6bfc6a 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -32,23 +32,10 @@ struct loop_device {
loff_t lo_offset;
loff_t lo_sizelimit;
int lo_flags;
- int (*transfer)(struct loop_device *, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t real_block);
char lo_file_name[LO_NAME_SIZE];
- char lo_crypt_name[LO_NAME_SIZE];
- char lo_encrypt_key[LO_KEY_SIZE];
- int lo_encrypt_key_size;
- struct loop_func_table *lo_encryption;
- __u32 lo_init[2];
- kuid_t lo_key_owner; /* Who set the key */
- int (*ioctl)(struct loop_device *, int cmd,
- unsigned long arg);
struct file * lo_backing_file;
struct block_device *lo_device;
- void *key_data;
gfp_t old_gfp_mask;
@@ -82,21 +69,4 @@ struct loop_cmd {
struct cgroup_subsys_state *memcg_css;
};
-/* Support for loadable transfer modules */
-struct loop_func_table {
- int number; /* filter type */
- int (*transfer)(struct loop_device *lo, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t real_block);
- int (*init)(struct loop_device *, const struct loop_info64 *);
- /* release is called from loop_unregister_transfer or clr_fd */
- int (*release)(struct loop_device *);
- int (*ioctl)(struct loop_device *, int cmd, unsigned long arg);
- struct module *owner;
-};
-
-int loop_register_transfer(struct loop_func_table *funcs);
-int loop_unregister_transfer(int number);
-
#endif
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 901855717cb5..c91b9010c1a6 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3633,7 +3633,9 @@ skip_create_disk:
set_capacity(dd->disk, capacity);
/* Enable the block device and add it to /dev */
- device_add_disk(&dd->pdev->dev, dd->disk, mtip_disk_attr_groups);
+ rv = device_add_disk(&dd->pdev->dev, dd->disk, mtip_disk_attr_groups);
+ if (rv)
+ goto read_capacity_error;
if (dd->mtip_svc_handler) {
set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag);
@@ -4061,7 +4063,6 @@ block_initialize_err:
msi_initialize_err:
if (dd->isr_workq) {
- flush_workqueue(dd->isr_workq);
destroy_workqueue(dd->isr_workq);
drop_cpu(dd->work[0].cpu_binding);
drop_cpu(dd->work[1].cpu_binding);
@@ -4119,7 +4120,6 @@ static void mtip_pci_remove(struct pci_dev *pdev)
mtip_block_remove(dd);
if (dd->isr_workq) {
- flush_workqueue(dd->isr_workq);
destroy_workqueue(dd->isr_workq);
drop_cpu(dd->work[0].cpu_binding);
drop_cpu(dd->work[1].cpu_binding);
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index 26798da661bd..78282f01f581 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -84,7 +84,7 @@ static bool n64cart_do_bvec(struct device *dev, struct bio_vec *bv, u32 pos)
return true;
}
-static blk_qc_t n64cart_submit_bio(struct bio *bio)
+static void n64cart_submit_bio(struct bio *bio)
{
struct bio_vec bvec;
struct bvec_iter iter;
@@ -92,16 +92,14 @@ static blk_qc_t n64cart_submit_bio(struct bio *bio)
u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT;
bio_for_each_segment(bvec, bio, iter) {
- if (!n64cart_do_bvec(dev, &bvec, pos))
- goto io_error;
+ if (!n64cart_do_bvec(dev, &bvec, pos)) {
+ bio_io_error(bio);
+ return;
+ }
pos += bvec.bv_len;
}
bio_endio(bio);
- return BLK_QC_T_NONE;
-io_error:
- bio_io_error(bio);
- return BLK_QC_T_NONE;
}
static const struct block_device_operations n64cart_fops = {
@@ -117,6 +115,7 @@ static const struct block_device_operations n64cart_fops = {
static int __init n64cart_probe(struct platform_device *pdev)
{
struct gendisk *disk;
+ int err = -ENOMEM;
if (!start || !size) {
pr_err("start or size not specified\n");
@@ -134,7 +133,7 @@ static int __init n64cart_probe(struct platform_device *pdev)
disk = blk_alloc_disk(NUMA_NO_NODE);
if (!disk)
- return -ENOMEM;
+ goto out;
disk->first_minor = 0;
disk->flags = GENHD_FL_NO_PART_SCAN;
@@ -149,11 +148,18 @@ static int __init n64cart_probe(struct platform_device *pdev)
blk_queue_physical_block_size(disk->queue, 4096);
blk_queue_logical_block_size(disk->queue, 4096);
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_cleanup_disk;
pr_info("n64cart: %u kb disk\n", size / 1024);
return 0;
+
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
+out:
+ return err;
}
static struct platform_driver n64cart_driver = {
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 1183f7872b71..b47b2a87ae8f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -122,15 +122,21 @@ struct nbd_device {
struct work_struct remove_work;
struct list_head list;
- struct task_struct *task_recv;
struct task_struct *task_setup;
unsigned long flags;
+ pid_t pid; /* pid of nbd-client, if attached */
char *backend;
};
#define NBD_CMD_REQUEUED 1
+/*
+ * This flag will be set if nbd_queue_rq() succeed, and will be checked and
+ * cleared in completion. Both setting and clearing of the flag are protected
+ * by cmd->lock.
+ */
+#define NBD_CMD_INFLIGHT 2
struct nbd_cmd {
struct nbd_device *nbd;
@@ -217,7 +223,7 @@ static ssize_t pid_show(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
- return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
+ return sprintf(buf, "%d\n", nbd->pid);
}
static const struct device_attribute pid_attr = {
@@ -310,26 +316,19 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
nsock->sent = 0;
}
-static void nbd_size_clear(struct nbd_device *nbd)
-{
- if (nbd->config->bytesize) {
- set_capacity(nbd->disk, 0);
- kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
- }
-}
-
static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
loff_t blksize)
{
if (!blksize)
blksize = 1u << NBD_DEF_BLKSIZE_BITS;
- if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize))
+
+ if (blk_validate_block_size(blksize))
return -EINVAL;
nbd->config->bytesize = bytesize;
nbd->config->blksize_bits = __ffs(blksize);
- if (!nbd->task_recv)
+ if (!nbd->pid)
return 0;
if (nbd->config->flags & NBD_FLAG_SEND_TRIM) {
@@ -405,6 +404,11 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
if (!mutex_trylock(&cmd->lock))
return BLK_EH_RESET_TIMER;
+ if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+ mutex_unlock(&cmd->lock);
+ return BLK_EH_DONE;
+ }
+
if (!refcount_inc_not_zero(&nbd->config_refs)) {
cmd->status = BLK_STS_TIMEOUT;
mutex_unlock(&cmd->lock);
@@ -484,7 +488,8 @@ done:
}
/*
- * Send or receive packet.
+ * Send or receive packet. Return a positive value on success and
+ * negtive value on failue, and never return 0.
*/
static int sock_xmit(struct nbd_device *nbd, int index, int send,
struct iov_iter *iter, int msg_flags, int *sent)
@@ -610,7 +615,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
result = sock_xmit(nbd, index, 1, &from,
(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
trace_nbd_header_sent(req, handle);
- if (result <= 0) {
+ if (result < 0) {
if (was_interrupted(result)) {
/* If we havne't sent anything we can just return BUSY,
* however if we have sent something we need to make
@@ -654,7 +659,7 @@ send_pages:
skip = 0;
}
result = sock_xmit(nbd, index, 1, &from, flags, &sent);
- if (result <= 0) {
+ if (result < 0) {
if (was_interrupted(result)) {
/* We've already sent the header, we
* have no choice but to set pending and
@@ -688,38 +693,45 @@ out:
return 0;
}
-/* NULL returned = something went wrong, inform userspace */
-static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
+static int nbd_read_reply(struct nbd_device *nbd, int index,
+ struct nbd_reply *reply)
{
- struct nbd_config *config = nbd->config;
- int result;
- struct nbd_reply reply;
- struct nbd_cmd *cmd;
- struct request *req = NULL;
- u64 handle;
- u16 hwq;
- u32 tag;
- struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
+ struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)};
struct iov_iter to;
- int ret = 0;
+ int result;
- reply.magic = 0;
- iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply));
+ reply->magic = 0;
+ iov_iter_kvec(&to, READ, &iov, 1, sizeof(*reply));
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
- if (result <= 0) {
- if (!nbd_disconnected(config))
+ if (result < 0) {
+ if (!nbd_disconnected(nbd->config))
dev_err(disk_to_dev(nbd->disk),
"Receive control failed (result %d)\n", result);
- return ERR_PTR(result);
+ return result;
}
- if (ntohl(reply.magic) != NBD_REPLY_MAGIC) {
+ if (ntohl(reply->magic) != NBD_REPLY_MAGIC) {
dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n",
- (unsigned long)ntohl(reply.magic));
- return ERR_PTR(-EPROTO);
+ (unsigned long)ntohl(reply->magic));
+ return -EPROTO;
}
- memcpy(&handle, reply.handle, sizeof(handle));
+ return 0;
+}
+
+/* NULL returned = something went wrong, inform userspace */
+static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index,
+ struct nbd_reply *reply)
+{
+ int result;
+ struct nbd_cmd *cmd;
+ struct request *req = NULL;
+ u64 handle;
+ u16 hwq;
+ u32 tag;
+ int ret = 0;
+
+ memcpy(&handle, reply->handle, sizeof(handle));
tag = nbd_handle_to_tag(handle);
hwq = blk_mq_unique_tag_to_hwq(tag);
if (hwq < nbd->tag_set.nr_hw_queues)
@@ -734,6 +746,16 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
cmd = blk_mq_rq_to_pdu(req);
mutex_lock(&cmd->lock);
+ if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+ dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)",
+ tag, cmd->status, cmd->flags);
+ ret = -ENOENT;
+ goto out;
+ }
+ if (cmd->index != index) {
+ dev_err(disk_to_dev(nbd->disk), "Unexpected reply %d from different sock %d (expected %d)",
+ tag, index, cmd->index);
+ }
if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
@@ -752,9 +774,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
ret = -ENOENT;
goto out;
}
- if (ntohl(reply.error)) {
+ if (ntohl(reply->error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
- ntohl(reply.error));
+ ntohl(reply->error));
cmd->status = BLK_STS_IOERR;
goto out;
}
@@ -763,11 +785,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
if (rq_data_dir(req) != WRITE) {
struct req_iterator iter;
struct bio_vec bvec;
+ struct iov_iter to;
rq_for_each_segment(bvec, req, iter) {
iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len);
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
- if (result <= 0) {
+ if (result < 0) {
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
/*
@@ -776,7 +799,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
* and let the timeout stuff handle resubmitting
* this request onto another connection.
*/
- if (nbd_disconnected(config)) {
+ if (nbd_disconnected(nbd->config)) {
cmd->status = BLK_STS_IOERR;
goto out;
}
@@ -800,24 +823,46 @@ static void recv_work(struct work_struct *work)
work);
struct nbd_device *nbd = args->nbd;
struct nbd_config *config = nbd->config;
+ struct request_queue *q = nbd->disk->queue;
+ struct nbd_sock *nsock;
struct nbd_cmd *cmd;
struct request *rq;
while (1) {
- cmd = nbd_read_stat(nbd, args->index);
- if (IS_ERR(cmd)) {
- struct nbd_sock *nsock = config->socks[args->index];
+ struct nbd_reply reply;
- mutex_lock(&nsock->tx_lock);
- nbd_mark_nsock_dead(nbd, nsock, 1);
- mutex_unlock(&nsock->tx_lock);
+ if (nbd_read_reply(nbd, args->index, &reply))
+ break;
+
+ /*
+ * Grab .q_usage_counter so request pool won't go away, then no
+ * request use-after-free is possible during nbd_handle_reply().
+ * If queue is frozen, there won't be any inflight requests, we
+ * needn't to handle the incoming garbage message.
+ */
+ if (!percpu_ref_tryget(&q->q_usage_counter)) {
+ dev_err(disk_to_dev(nbd->disk), "%s: no io inflight\n",
+ __func__);
+ break;
+ }
+
+ cmd = nbd_handle_reply(nbd, args->index, &reply);
+ if (IS_ERR(cmd)) {
+ percpu_ref_put(&q->q_usage_counter);
break;
}
rq = blk_mq_rq_from_pdu(cmd);
if (likely(!blk_should_fake_timeout(rq->q)))
blk_mq_complete_request(rq);
+ percpu_ref_put(&q->q_usage_counter);
}
+
+ nsock = config->socks[args->index];
+ mutex_lock(&nsock->tx_lock);
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+
nbd_config_put(nbd);
atomic_dec(&config->recv_threads);
wake_up(&config->recv_wq);
@@ -833,6 +878,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved)
return true;
mutex_lock(&cmd->lock);
+ if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+ mutex_unlock(&cmd->lock);
+ return true;
+ }
cmd->status = BLK_STS_IOERR;
mutex_unlock(&cmd->lock);
@@ -914,7 +963,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
if (!refcount_inc_not_zero(&nbd->config_refs)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Socks array is empty\n");
- blk_mq_start_request(req);
return -EINVAL;
}
config = nbd->config;
@@ -923,7 +971,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on invalid socket\n");
nbd_config_put(nbd);
- blk_mq_start_request(req);
return -EINVAL;
}
cmd->status = BLK_STS_OK;
@@ -947,7 +994,6 @@ again:
*/
sock_shutdown(nbd);
nbd_config_put(nbd);
- blk_mq_start_request(req);
return -EIO;
}
goto again;
@@ -969,7 +1015,13 @@ again:
* returns EAGAIN can be retried on a different socket.
*/
ret = nbd_send_cmd(nbd, cmd, index);
- if (ret == -EAGAIN) {
+ /*
+ * Access to this flag is protected by cmd->lock, thus it's safe to set
+ * the flag after nbd_send_cmd() succeed to send request to server.
+ */
+ if (!ret)
+ __set_bit(NBD_CMD_INFLIGHT, &cmd->flags);
+ else if (ret == -EAGAIN) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Request send failed, requeueing\n");
nbd_mark_nsock_dead(nbd, nsock, 1);
@@ -1206,7 +1258,7 @@ static void send_disconnects(struct nbd_device *nbd)
iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request));
mutex_lock(&nsock->tx_lock);
ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
- if (ret <= 0)
+ if (ret < 0)
dev_err(disk_to_dev(nbd->disk),
"Send disconnect failed %d\n", ret);
mutex_unlock(&nsock->tx_lock);
@@ -1237,11 +1289,13 @@ static void nbd_config_put(struct nbd_device *nbd)
&nbd->config_lock)) {
struct nbd_config *config = nbd->config;
nbd_dev_dbg_close(nbd);
- nbd_size_clear(nbd);
+ invalidate_disk(nbd->disk);
+ if (nbd->config->bytesize)
+ kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
if (test_and_clear_bit(NBD_RT_HAS_PID_FILE,
&config->runtime_flags))
device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
- nbd->task_recv = NULL;
+ nbd->pid = 0;
if (test_and_clear_bit(NBD_RT_HAS_BACKEND_FILE,
&config->runtime_flags)) {
device_remove_file(disk_to_dev(nbd->disk), &backend_attr);
@@ -1282,7 +1336,7 @@ static int nbd_start_device(struct nbd_device *nbd)
int num_connections = config->num_connections;
int error = 0, i;
- if (nbd->task_recv)
+ if (nbd->pid)
return -EBUSY;
if (!config->socks)
return -EINVAL;
@@ -1301,7 +1355,7 @@ static int nbd_start_device(struct nbd_device *nbd)
}
blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
- nbd->task_recv = current;
+ nbd->pid = task_pid_nr(current);
nbd_parse_flags(nbd);
@@ -1557,8 +1611,8 @@ static int nbd_dbg_tasks_show(struct seq_file *s, void *unused)
{
struct nbd_device *nbd = s->private;
- if (nbd->task_recv)
- seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv));
+ if (nbd->pid)
+ seq_printf(s, "recv: %d\n", nbd->pid);
return 0;
}
@@ -1762,7 +1816,9 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
disk->fops = &nbd_fops;
disk->private_data = nbd;
sprintf(disk->disk_name, "nbd%d", index);
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_err_disk;
/*
* Now publish the device.
@@ -1771,6 +1827,8 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
nbd_total_devices++;
return nbd;
+out_err_disk:
+ blk_cleanup_disk(disk);
out_free_idr:
mutex_lock(&nbd_index_mutex);
idr_remove(&nbd_index_idr, index);
@@ -2135,7 +2193,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&nbd->config_lock);
config = nbd->config;
if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) ||
- !nbd->task_recv) {
+ !nbd->pid) {
dev_err(nbd_to_dev(nbd),
"not configured, cannot reconfigure\n");
ret = -EINVAL;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 187d779c8ca0..323af5c9c802 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -92,6 +92,10 @@ static int g_submit_queues = 1;
module_param_named(submit_queues, g_submit_queues, int, 0444);
MODULE_PARM_DESC(submit_queues, "Number of submission queues");
+static int g_poll_queues = 1;
+module_param_named(poll_queues, g_poll_queues, int, 0444);
+MODULE_PARM_DESC(poll_queues, "Number of IOPOLL submission queues");
+
static int g_home_node = NUMA_NO_NODE;
module_param_named(home_node, g_home_node, int, 0444);
MODULE_PARM_DESC(home_node, "Home node for the device");
@@ -324,29 +328,69 @@ nullb_device_##NAME##_store(struct config_item *item, const char *page, \
} \
CONFIGFS_ATTR(nullb_device_, NAME);
-static int nullb_apply_submit_queues(struct nullb_device *dev,
- unsigned int submit_queues)
+static int nullb_update_nr_hw_queues(struct nullb_device *dev,
+ unsigned int submit_queues,
+ unsigned int poll_queues)
+
{
- struct nullb *nullb = dev->nullb;
struct blk_mq_tag_set *set;
+ int ret, nr_hw_queues;
- if (!nullb)
+ if (!dev->nullb)
return 0;
/*
+ * Make sure at least one queue exists for each of submit and poll.
+ */
+ if (!submit_queues || !poll_queues)
+ return -EINVAL;
+
+ /*
* Make sure that null_init_hctx() does not access nullb->queues[] past
* the end of that array.
*/
- if (submit_queues > nr_cpu_ids)
+ if (submit_queues > nr_cpu_ids || poll_queues > g_poll_queues)
return -EINVAL;
- set = nullb->tag_set;
- blk_mq_update_nr_hw_queues(set, submit_queues);
- return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
+
+ /*
+ * Keep previous and new queue numbers in nullb_device for reference in
+ * the call back function null_map_queues().
+ */
+ dev->prev_submit_queues = dev->submit_queues;
+ dev->prev_poll_queues = dev->poll_queues;
+ dev->submit_queues = submit_queues;
+ dev->poll_queues = poll_queues;
+
+ set = dev->nullb->tag_set;
+ nr_hw_queues = submit_queues + poll_queues;
+ blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+ ret = set->nr_hw_queues == nr_hw_queues ? 0 : -ENOMEM;
+
+ if (ret) {
+ /* on error, revert the queue numbers */
+ dev->submit_queues = dev->prev_submit_queues;
+ dev->poll_queues = dev->prev_poll_queues;
+ }
+
+ return ret;
+}
+
+static int nullb_apply_submit_queues(struct nullb_device *dev,
+ unsigned int submit_queues)
+{
+ return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues);
+}
+
+static int nullb_apply_poll_queues(struct nullb_device *dev,
+ unsigned int poll_queues)
+{
+ return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues);
}
NULLB_DEVICE_ATTR(size, ulong, NULL);
NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL);
NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
+NULLB_DEVICE_ATTR(poll_queues, uint, nullb_apply_poll_queues);
NULLB_DEVICE_ATTR(home_node, uint, NULL);
NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
NULLB_DEVICE_ATTR(blocksize, uint, NULL);
@@ -466,6 +510,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
&nullb_device_attr_size,
&nullb_device_attr_completion_nsec,
&nullb_device_attr_submit_queues,
+ &nullb_device_attr_poll_queues,
&nullb_device_attr_home_node,
&nullb_device_attr_queue_mode,
&nullb_device_attr_blocksize,
@@ -593,6 +638,9 @@ static struct nullb_device *null_alloc_dev(void)
dev->size = g_gb * 1024;
dev->completion_nsec = g_completion_nsec;
dev->submit_queues = g_submit_queues;
+ dev->prev_submit_queues = g_submit_queues;
+ dev->poll_queues = g_poll_queues;
+ dev->prev_poll_queues = g_poll_queues;
dev->home_node = g_home_node;
dev->queue_mode = g_queue_mode;
dev->blocksize = g_bs;
@@ -1422,7 +1470,7 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
return &nullb->queues[index];
}
-static blk_qc_t null_submit_bio(struct bio *bio)
+static void null_submit_bio(struct bio *bio)
{
sector_t sector = bio->bi_iter.bi_sector;
sector_t nr_sectors = bio_sectors(bio);
@@ -1434,7 +1482,6 @@ static blk_qc_t null_submit_bio(struct bio *bio)
cmd->bio = bio;
null_handle_cmd(cmd, sector, nr_sectors, bio_op(bio));
- return BLK_QC_T_NONE;
}
static bool should_timeout_request(struct request *rq)
@@ -1455,12 +1502,100 @@ static bool should_requeue_request(struct request *rq)
return false;
}
+static int null_map_queues(struct blk_mq_tag_set *set)
+{
+ struct nullb *nullb = set->driver_data;
+ int i, qoff;
+ unsigned int submit_queues = g_submit_queues;
+ unsigned int poll_queues = g_poll_queues;
+
+ if (nullb) {
+ struct nullb_device *dev = nullb->dev;
+
+ /*
+ * Refer nr_hw_queues of the tag set to check if the expected
+ * number of hardware queues are prepared. If block layer failed
+ * to prepare them, use previous numbers of submit queues and
+ * poll queues to map queues.
+ */
+ if (set->nr_hw_queues ==
+ dev->submit_queues + dev->poll_queues) {
+ submit_queues = dev->submit_queues;
+ poll_queues = dev->poll_queues;
+ } else if (set->nr_hw_queues ==
+ dev->prev_submit_queues + dev->prev_poll_queues) {
+ submit_queues = dev->prev_submit_queues;
+ poll_queues = dev->prev_poll_queues;
+ } else {
+ pr_warn("tag set has unexpected nr_hw_queues: %d\n",
+ set->nr_hw_queues);
+ return -EINVAL;
+ }
+ }
+
+ for (i = 0, qoff = 0; i < set->nr_maps; i++) {
+ struct blk_mq_queue_map *map = &set->map[i];
+
+ switch (i) {
+ case HCTX_TYPE_DEFAULT:
+ map->nr_queues = submit_queues;
+ break;
+ case HCTX_TYPE_READ:
+ map->nr_queues = 0;
+ continue;
+ case HCTX_TYPE_POLL:
+ map->nr_queues = poll_queues;
+ break;
+ }
+ map->queue_offset = qoff;
+ qoff += map->nr_queues;
+ blk_mq_map_queues(map);
+ }
+
+ return 0;
+}
+
+static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
+{
+ struct nullb_queue *nq = hctx->driver_data;
+ LIST_HEAD(list);
+ int nr = 0;
+
+ spin_lock(&nq->poll_lock);
+ list_splice_init(&nq->poll_list, &list);
+ spin_unlock(&nq->poll_lock);
+
+ while (!list_empty(&list)) {
+ struct nullb_cmd *cmd;
+ struct request *req;
+
+ req = list_first_entry(&list, struct request, queuelist);
+ list_del_init(&req->queuelist);
+ cmd = blk_mq_rq_to_pdu(req);
+ cmd->error = null_process_cmd(cmd, req_op(req), blk_rq_pos(req),
+ blk_rq_sectors(req));
+ end_cmd(cmd);
+ nr++;
+ }
+
+ return nr;
+}
+
static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
{
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
pr_info("rq %p timed out\n", rq);
+ if (hctx->type == HCTX_TYPE_POLL) {
+ struct nullb_queue *nq = hctx->driver_data;
+
+ spin_lock(&nq->poll_lock);
+ list_del_init(&rq->queuelist);
+ spin_unlock(&nq->poll_lock);
+ }
+
/*
* If the device is marked as blocking (i.e. memory backed or zoned
* device), the submission path may be blocked waiting for resources
@@ -1481,10 +1616,11 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
struct nullb_queue *nq = hctx->driver_data;
sector_t nr_sectors = blk_rq_sectors(bd->rq);
sector_t sector = blk_rq_pos(bd->rq);
+ const bool is_poll = hctx->type == HCTX_TYPE_POLL;
might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
- if (nq->dev->irqmode == NULL_IRQ_TIMER) {
+ if (!is_poll && nq->dev->irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cmd->timer.function = null_cmd_timer_expired;
}
@@ -1508,6 +1644,13 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
return BLK_STS_OK;
}
}
+
+ if (is_poll) {
+ spin_lock(&nq->poll_lock);
+ list_add_tail(&bd->rq->queuelist, &nq->poll_list);
+ spin_unlock(&nq->poll_lock);
+ return BLK_STS_OK;
+ }
if (cmd->fake_timeout)
return BLK_STS_OK;
@@ -1543,6 +1686,8 @@ static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
init_waitqueue_head(&nq->wait);
nq->queue_depth = nullb->queue_depth;
nq->dev = nullb->dev;
+ INIT_LIST_HEAD(&nq->poll_list);
+ spin_lock_init(&nq->poll_lock);
}
static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
@@ -1568,6 +1713,8 @@ static const struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
.complete = null_complete_rq,
.timeout = null_timeout_rq,
+ .poll = null_poll,
+ .map_queues = null_map_queues,
.init_hctx = null_init_hctx,
.exit_hctx = null_exit_hctx,
};
@@ -1664,13 +1811,17 @@ static int setup_commands(struct nullb_queue *nq)
static int setup_queues(struct nullb *nullb)
{
- nullb->queues = kcalloc(nr_cpu_ids, sizeof(struct nullb_queue),
+ int nqueues = nr_cpu_ids;
+
+ if (g_poll_queues)
+ nqueues += g_poll_queues;
+
+ nullb->queues = kcalloc(nqueues, sizeof(struct nullb_queue),
GFP_KERNEL);
if (!nullb->queues)
return -ENOMEM;
nullb->queue_depth = nullb->dev->hw_queue_depth;
-
return 0;
}
@@ -1722,9 +1873,14 @@ static int null_gendisk_register(struct nullb *nullb)
static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
{
+ int poll_queues;
+
set->ops = &null_mq_ops;
set->nr_hw_queues = nullb ? nullb->dev->submit_queues :
g_submit_queues;
+ poll_queues = nullb ? nullb->dev->poll_queues : g_poll_queues;
+ if (poll_queues)
+ set->nr_hw_queues += poll_queues;
set->queue_depth = nullb ? nullb->dev->hw_queue_depth :
g_hw_queue_depth;
set->numa_node = nullb ? nullb->dev->home_node : g_home_node;
@@ -1734,7 +1890,11 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
set->flags |= BLK_MQ_F_NO_SCHED;
if (g_shared_tag_bitmap)
set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
- set->driver_data = NULL;
+ set->driver_data = nullb;
+ if (g_poll_queues)
+ set->nr_maps = 3;
+ else
+ set->nr_maps = 1;
if ((nullb && nullb->dev->blocking) || g_blocking)
set->flags |= BLK_MQ_F_BLOCKING;
@@ -1754,6 +1914,13 @@ static int null_validate_conf(struct nullb_device *dev)
dev->submit_queues = nr_cpu_ids;
else if (dev->submit_queues == 0)
dev->submit_queues = 1;
+ dev->prev_submit_queues = dev->submit_queues;
+
+ if (dev->poll_queues > g_poll_queues)
+ dev->poll_queues = g_poll_queues;
+ else if (dev->poll_queues == 0)
+ dev->poll_queues = 1;
+ dev->prev_poll_queues = dev->poll_queues;
dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 64bef125d1df..78eb56b0ca55 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -32,6 +32,9 @@ struct nullb_queue {
struct nullb_device *dev;
unsigned int requeue_selection;
+ struct list_head poll_list;
+ spinlock_t poll_lock;
+
struct nullb_cmd *cmds;
};
@@ -83,6 +86,9 @@ struct nullb_device {
unsigned int zone_max_open; /* max number of open zones */
unsigned int zone_max_active; /* max number of active zones */
unsigned int submit_queues; /* number of submission queues */
+ unsigned int prev_submit_queues; /* number of submission queues before change */
+ unsigned int poll_queues; /* number of IOPOLL submission queues */
+ unsigned int prev_poll_queues; /* number of IOPOLL submission queues before change */
unsigned int home_node; /* home node for the device */
unsigned int queue_mode; /* block interface */
unsigned int blocksize; /* block size */
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index f9cdd11f02f5..f6b1d63e96e1 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -183,8 +183,6 @@ static int pcd_audio_ioctl(struct cdrom_device_info *cdi,
static int pcd_packet(struct cdrom_device_info *cdi,
struct packet_command *cgc);
-static int pcd_detect(void);
-static void pcd_probe_capabilities(void);
static void do_pcd_read_drq(void);
static blk_status_t pcd_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd);
@@ -302,53 +300,6 @@ static const struct blk_mq_ops pcd_mq_ops = {
.queue_rq = pcd_queue_rq,
};
-static void pcd_init_units(void)
-{
- struct pcd_unit *cd;
- int unit;
-
- pcd_drive_count = 0;
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- struct gendisk *disk;
-
- if (blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1,
- BLK_MQ_F_SHOULD_MERGE))
- continue;
-
- disk = blk_mq_alloc_disk(&cd->tag_set, cd);
- if (IS_ERR(disk)) {
- blk_mq_free_tag_set(&cd->tag_set);
- continue;
- }
-
- INIT_LIST_HEAD(&cd->rq_list);
- blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
- cd->disk = disk;
- cd->pi = &cd->pia;
- cd->present = 0;
- cd->last_sense = 0;
- cd->changed = 1;
- cd->drive = (*drives[unit])[D_SLV];
- if ((*drives[unit])[D_PRT])
- pcd_drive_count++;
-
- cd->name = &cd->info.name[0];
- snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit);
- cd->info.ops = &pcd_dops;
- cd->info.handle = cd;
- cd->info.speed = 0;
- cd->info.capacity = 1;
- cd->info.mask = 0;
- disk->major = major;
- disk->first_minor = unit;
- disk->minors = 1;
- strcpy(disk->disk_name, cd->name); /* umm... */
- disk->fops = &pcd_bdops;
- disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
- disk->events = DISK_EVENT_MEDIA_CHANGE;
- }
-}
-
static int pcd_open(struct cdrom_device_info *cdi, int purpose)
{
struct pcd_unit *cd = cdi->handle;
@@ -630,10 +581,11 @@ static int pcd_drive_status(struct cdrom_device_info *cdi, int slot_nr)
return CDS_DISC_OK;
}
-static int pcd_identify(struct pcd_unit *cd, char *id)
+static int pcd_identify(struct pcd_unit *cd)
{
- int k, s;
char id_cmd[12] = { 0x12, 0, 0, 0, 36, 0, 0, 0, 0, 0, 0, 0 };
+ char id[18];
+ int k, s;
pcd_bufblk = -1;
@@ -661,108 +613,47 @@ static int pcd_identify(struct pcd_unit *cd, char *id)
}
/*
- * returns 0, with id set if drive is detected
- * -1, if drive detection failed
+ * returns 0, with id set if drive is detected, otherwise an error code.
*/
-static int pcd_probe(struct pcd_unit *cd, int ms, char *id)
+static int pcd_probe(struct pcd_unit *cd, int ms)
{
if (ms == -1) {
for (cd->drive = 0; cd->drive <= 1; cd->drive++)
- if (!pcd_reset(cd) && !pcd_identify(cd, id))
+ if (!pcd_reset(cd) && !pcd_identify(cd))
return 0;
} else {
cd->drive = ms;
- if (!pcd_reset(cd) && !pcd_identify(cd, id))
+ if (!pcd_reset(cd) && !pcd_identify(cd))
return 0;
}
- return -1;
+ return -ENODEV;
}
-static void pcd_probe_capabilities(void)
+static int pcd_probe_capabilities(struct pcd_unit *cd)
{
- int unit, r;
- char buffer[32];
char cmd[12] = { 0x5a, 1 << 3, 0x2a, 0, 0, 0, 0, 18, 0, 0, 0, 0 };
- struct pcd_unit *cd;
-
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->present)
- continue;
- r = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities");
- if (r)
- continue;
- /* we should now have the cap page */
- if ((buffer[11] & 1) == 0)
- cd->info.mask |= CDC_CD_R;
- if ((buffer[11] & 2) == 0)
- cd->info.mask |= CDC_CD_RW;
- if ((buffer[12] & 1) == 0)
- cd->info.mask |= CDC_PLAY_AUDIO;
- if ((buffer[14] & 1) == 0)
- cd->info.mask |= CDC_LOCK;
- if ((buffer[14] & 8) == 0)
- cd->info.mask |= CDC_OPEN_TRAY;
- if ((buffer[14] >> 6) == 0)
- cd->info.mask |= CDC_CLOSE_TRAY;
- }
-}
-
-static int pcd_detect(void)
-{
- char id[18];
- int k, unit;
- struct pcd_unit *cd;
+ char buffer[32];
+ int ret;
- printk("%s: %s version %s, major %d, nice %d\n",
- name, name, PCD_VERSION, major, nice);
+ ret = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities");
+ if (ret)
+ return ret;
+
+ /* we should now have the cap page */
+ if ((buffer[11] & 1) == 0)
+ cd->info.mask |= CDC_CD_R;
+ if ((buffer[11] & 2) == 0)
+ cd->info.mask |= CDC_CD_RW;
+ if ((buffer[12] & 1) == 0)
+ cd->info.mask |= CDC_PLAY_AUDIO;
+ if ((buffer[14] & 1) == 0)
+ cd->info.mask |= CDC_LOCK;
+ if ((buffer[14] & 8) == 0)
+ cd->info.mask |= CDC_OPEN_TRAY;
+ if ((buffer[14] >> 6) == 0)
+ cd->info.mask |= CDC_CLOSE_TRAY;
- par_drv = pi_register_driver(name);
- if (!par_drv) {
- pr_err("failed to register %s driver\n", name);
- return -1;
- }
-
- k = 0;
- if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
- cd = pcd;
- if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1,
- pcd_buffer, PI_PCD, verbose, cd->name)) {
- if (!pcd_probe(cd, -1, id)) {
- cd->present = 1;
- k++;
- } else
- pi_release(cd->pi);
- }
- } else {
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- int *conf = *drives[unit];
- if (!conf[D_PRT])
- continue;
- if (!cd->disk)
- continue;
- if (!pi_init(cd->pi, 0, conf[D_PRT], conf[D_MOD],
- conf[D_UNI], conf[D_PRO], conf[D_DLY],
- pcd_buffer, PI_PCD, verbose, cd->name))
- continue;
- if (!pcd_probe(cd, conf[D_SLV], id)) {
- cd->present = 1;
- k++;
- } else
- pi_release(cd->pi);
- }
- }
- if (k)
- return 0;
-
- printk("%s: No CD-ROM drive found\n", name);
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->disk)
- continue;
- blk_cleanup_disk(cd->disk);
- blk_mq_free_tag_set(&cd->tag_set);
- }
- pi_unregister_driver(par_drv);
- return -1;
+ return 0;
}
/* I/O request processing */
@@ -999,43 +890,130 @@ static int pcd_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn)
return 0;
}
+static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port,
+ int mode, int unit, int protocol, int delay, int ms)
+{
+ struct gendisk *disk;
+ int ret;
+
+ ret = blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1,
+ BLK_MQ_F_SHOULD_MERGE);
+ if (ret)
+ return ret;
+
+ disk = blk_mq_alloc_disk(&cd->tag_set, cd);
+ if (IS_ERR(disk)) {
+ ret = PTR_ERR(disk);
+ goto out_free_tag_set;
+ }
+
+ INIT_LIST_HEAD(&cd->rq_list);
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
+ cd->disk = disk;
+ cd->pi = &cd->pia;
+ cd->present = 0;
+ cd->last_sense = 0;
+ cd->changed = 1;
+ cd->drive = (*drives[cd - pcd])[D_SLV];
+
+ cd->name = &cd->info.name[0];
+ snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit);
+ cd->info.ops = &pcd_dops;
+ cd->info.handle = cd;
+ cd->info.speed = 0;
+ cd->info.capacity = 1;
+ cd->info.mask = 0;
+ disk->major = major;
+ disk->first_minor = unit;
+ disk->minors = 1;
+ strcpy(disk->disk_name, cd->name); /* umm... */
+ disk->fops = &pcd_bdops;
+ disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
+
+ if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay,
+ pcd_buffer, PI_PCD, verbose, cd->name)) {
+ ret = -ENODEV;
+ goto out_free_disk;
+ }
+ ret = pcd_probe(cd, ms);
+ if (ret)
+ goto out_pi_release;
+
+ cd->present = 1;
+ pcd_probe_capabilities(cd);
+ ret = register_cdrom(cd->disk, &cd->info);
+ if (ret)
+ goto out_pi_release;
+ ret = add_disk(cd->disk);
+ if (ret)
+ goto out_unreg_cdrom;
+ return 0;
+
+out_unreg_cdrom:
+ unregister_cdrom(&cd->info);
+out_pi_release:
+ pi_release(cd->pi);
+out_free_disk:
+ blk_cleanup_disk(cd->disk);
+out_free_tag_set:
+ blk_mq_free_tag_set(&cd->tag_set);
+ return ret;
+}
+
static int __init pcd_init(void)
{
- struct pcd_unit *cd;
- int unit;
+ int found = 0, unit;
if (disable)
return -EINVAL;
- pcd_init_units();
+ if (register_blkdev(major, name))
+ return -EBUSY;
- if (pcd_detect())
- return -ENODEV;
+ pr_info("%s: %s version %s, major %d, nice %d\n",
+ name, name, PCD_VERSION, major, nice);
- /* get the atapi capabilities page */
- pcd_probe_capabilities();
+ par_drv = pi_register_driver(name);
+ if (!par_drv) {
+ pr_err("failed to register %s driver\n", name);
+ goto out_unregister_blkdev;
+ }
- if (register_blkdev(major, name)) {
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->disk)
- continue;
+ for (unit = 0; unit < PCD_UNITS; unit++) {
+ if ((*drives[unit])[D_PRT])
+ pcd_drive_count++;
+ }
+
+ if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
+ if (!pcd_init_unit(pcd, 1, -1, -1, -1, -1, -1, -1))
+ found++;
+ } else {
+ for (unit = 0; unit < PCD_UNITS; unit++) {
+ struct pcd_unit *cd = &pcd[unit];
+ int *conf = *drives[unit];
- blk_cleanup_queue(cd->disk->queue);
- blk_mq_free_tag_set(&cd->tag_set);
- put_disk(cd->disk);
+ if (!conf[D_PRT])
+ continue;
+ if (!pcd_init_unit(cd, 0, conf[D_PRT], conf[D_MOD],
+ conf[D_UNI], conf[D_PRO], conf[D_DLY],
+ conf[D_SLV]))
+ found++;
}
- return -EBUSY;
}
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (cd->present) {
- register_cdrom(cd->disk, &cd->info);
- cd->disk->private_data = cd;
- add_disk(cd->disk);
- }
+ if (!found) {
+ pr_info("%s: No CD-ROM drive found\n", name);
+ goto out_unregister_pi_driver;
}
return 0;
+
+out_unregister_pi_driver:
+ pi_unregister_driver(par_drv);
+out_unregister_blkdev:
+ unregister_blkdev(major, name);
+ return -ENODEV;
}
static void __exit pcd_exit(void)
@@ -1044,20 +1022,18 @@ static void __exit pcd_exit(void)
int unit;
for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->disk)
+ if (!cd->present)
continue;
- if (cd->present) {
- del_gendisk(cd->disk);
- pi_release(cd->pi);
- unregister_cdrom(&cd->info);
- }
- blk_cleanup_queue(cd->disk->queue);
+ unregister_cdrom(&cd->info);
+ del_gendisk(cd->disk);
+ pi_release(cd->pi);
+ blk_cleanup_disk(cd->disk);
+
blk_mq_free_tag_set(&cd->tag_set);
- put_disk(cd->disk);
}
- unregister_blkdev(major, name);
pi_unregister_driver(par_drv);
+ unregister_blkdev(major, name);
}
MODULE_LICENSE("GPL");
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 675327df6aff..fba865058a17 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -775,14 +775,14 @@ static int pd_special_command(struct pd_unit *disk,
struct request *rq;
struct pd_req *req;
- rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, 0);
+ rq = blk_mq_alloc_request(disk->gd->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
req = blk_mq_rq_to_pdu(rq);
req->func = func;
blk_execute_rq(disk->gd, rq, 0);
- blk_put_request(rq);
+ blk_mq_free_request(rq);
return 0;
}
@@ -875,9 +875,27 @@ static const struct blk_mq_ops pd_mq_ops = {
.queue_rq = pd_queue_rq,
};
-static void pd_probe_drive(struct pd_unit *disk)
+static int pd_probe_drive(struct pd_unit *disk, int autoprobe, int port,
+ int mode, int unit, int protocol, int delay)
{
+ int index = disk - pd;
+ int *parm = *drives[index];
struct gendisk *p;
+ int ret;
+
+ disk->pi = &disk->pia;
+ disk->access = 0;
+ disk->changed = 1;
+ disk->capacity = 0;
+ disk->drive = parm[D_SLV];
+ snprintf(disk->name, PD_NAMELEN, "%s%c", name, 'a' + index);
+ disk->alt_geom = parm[D_GEO];
+ disk->standby = parm[D_SBY];
+ INIT_LIST_HEAD(&disk->rq_list);
+
+ if (!pi_init(disk->pi, autoprobe, port, mode, unit, protocol, delay,
+ pd_scratch, PI_PD, verbose, disk->name))
+ return -ENXIO;
memset(&disk->tag_set, 0, sizeof(disk->tag_set));
disk->tag_set.ops = &pd_mq_ops;
@@ -887,14 +905,14 @@ static void pd_probe_drive(struct pd_unit *disk)
disk->tag_set.queue_depth = 2;
disk->tag_set.numa_node = NUMA_NO_NODE;
disk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
-
- if (blk_mq_alloc_tag_set(&disk->tag_set))
- return;
+ ret = blk_mq_alloc_tag_set(&disk->tag_set);
+ if (ret)
+ goto pi_release;
p = blk_mq_alloc_disk(&disk->tag_set, disk);
if (IS_ERR(p)) {
- blk_mq_free_tag_set(&disk->tag_set);
- return;
+ ret = PTR_ERR(p);
+ goto free_tag_set;
}
disk->gd = p;
@@ -905,102 +923,88 @@ static void pd_probe_drive(struct pd_unit *disk)
p->minors = 1 << PD_BITS;
p->events = DISK_EVENT_MEDIA_CHANGE;
p->private_data = disk;
-
blk_queue_max_hw_sectors(p->queue, cluster);
blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH);
if (disk->drive == -1) {
- for (disk->drive = 0; disk->drive <= 1; disk->drive++)
- if (pd_special_command(disk, pd_identify) == 0)
- return;
- } else if (pd_special_command(disk, pd_identify) == 0)
- return;
- disk->gd = NULL;
+ for (disk->drive = 0; disk->drive <= 1; disk->drive++) {
+ ret = pd_special_command(disk, pd_identify);
+ if (ret == 0)
+ break;
+ }
+ } else {
+ ret = pd_special_command(disk, pd_identify);
+ }
+ if (ret)
+ goto put_disk;
+ set_capacity(disk->gd, disk->capacity);
+ ret = add_disk(disk->gd);
+ if (ret)
+ goto cleanup_disk;
+ return 0;
+cleanup_disk:
+ blk_cleanup_disk(disk->gd);
+put_disk:
put_disk(p);
+ disk->gd = NULL;
+free_tag_set:
+ blk_mq_free_tag_set(&disk->tag_set);
+pi_release:
+ pi_release(disk->pi);
+ return ret;
}
-static int pd_detect(void)
+static int __init pd_init(void)
{
int found = 0, unit, pd_drive_count = 0;
struct pd_unit *disk;
- for (unit = 0; unit < PD_UNITS; unit++) {
- int *parm = *drives[unit];
- struct pd_unit *disk = pd + unit;
- disk->pi = &disk->pia;
- disk->access = 0;
- disk->changed = 1;
- disk->capacity = 0;
- disk->drive = parm[D_SLV];
- snprintf(disk->name, PD_NAMELEN, "%s%c", name, 'a'+unit);
- disk->alt_geom = parm[D_GEO];
- disk->standby = parm[D_SBY];
- if (parm[D_PRT])
- pd_drive_count++;
- INIT_LIST_HEAD(&disk->rq_list);
- }
+ if (disable)
+ return -ENODEV;
+
+ if (register_blkdev(major, name))
+ return -ENODEV;
+
+ printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
+ name, name, PD_VERSION, major, cluster, nice);
par_drv = pi_register_driver(name);
if (!par_drv) {
pr_err("failed to register %s driver\n", name);
- return -1;
+ goto out_unregister_blkdev;
}
- if (pd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
- disk = pd;
- if (pi_init(disk->pi, 1, -1, -1, -1, -1, -1, pd_scratch,
- PI_PD, verbose, disk->name)) {
- pd_probe_drive(disk);
- if (!disk->gd)
- pi_release(disk->pi);
- }
+ for (unit = 0; unit < PD_UNITS; unit++) {
+ int *parm = *drives[unit];
+ if (parm[D_PRT])
+ pd_drive_count++;
+ }
+
+ if (pd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
+ if (!pd_probe_drive(pd, 1, -1, -1, -1, -1, -1))
+ found++;
} else {
for (unit = 0, disk = pd; unit < PD_UNITS; unit++, disk++) {
int *parm = *drives[unit];
if (!parm[D_PRT])
continue;
- if (pi_init(disk->pi, 0, parm[D_PRT], parm[D_MOD],
- parm[D_UNI], parm[D_PRO], parm[D_DLY],
- pd_scratch, PI_PD, verbose, disk->name)) {
- pd_probe_drive(disk);
- if (!disk->gd)
- pi_release(disk->pi);
- }
- }
- }
- for (unit = 0, disk = pd; unit < PD_UNITS; unit++, disk++) {
- if (disk->gd) {
- set_capacity(disk->gd, disk->capacity);
- add_disk(disk->gd);
- found = 1;
+ if (!pd_probe_drive(disk, 0, parm[D_PRT], parm[D_MOD],
+ parm[D_UNI], parm[D_PRO], parm[D_DLY]))
+ found++;
}
}
if (!found) {
printk("%s: no valid drive found\n", name);
- pi_unregister_driver(par_drv);
+ goto out_pi_unregister_driver;
}
- return found;
-}
-
-static int __init pd_init(void)
-{
- if (disable)
- goto out1;
-
- if (register_blkdev(major, name))
- goto out1;
-
- printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
- name, name, PD_VERSION, major, cluster, nice);
- if (!pd_detect())
- goto out2;
return 0;
-out2:
+out_pi_unregister_driver:
+ pi_unregister_driver(par_drv);
+out_unregister_blkdev:
unregister_blkdev(major, name);
-out1:
return -ENODEV;
}
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index d5b9c88ba76f..bf8d0ef41a0a 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -214,7 +214,6 @@ static int pf_getgeo(struct block_device *bdev, struct hd_geometry *geo);
static void pf_release(struct gendisk *disk, fmode_t mode);
-static int pf_detect(void);
static void do_pf_read(void);
static void do_pf_read_start(void);
static void do_pf_write(void);
@@ -285,45 +284,6 @@ static const struct blk_mq_ops pf_mq_ops = {
.queue_rq = pf_queue_rq,
};
-static void __init pf_init_units(void)
-{
- struct pf_unit *pf;
- int unit;
-
- pf_drive_count = 0;
- for (unit = 0, pf = units; unit < PF_UNITS; unit++, pf++) {
- struct gendisk *disk;
-
- if (blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1,
- BLK_MQ_F_SHOULD_MERGE))
- continue;
-
- disk = blk_mq_alloc_disk(&pf->tag_set, pf);
- if (IS_ERR(disk)) {
- blk_mq_free_tag_set(&pf->tag_set);
- continue;
- }
-
- INIT_LIST_HEAD(&pf->rq_list);
- blk_queue_max_segments(disk->queue, cluster);
- blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
- pf->disk = disk;
- pf->pi = &pf->pia;
- pf->media_status = PF_NM;
- pf->drive = (*drives[unit])[D_SLV];
- pf->lun = (*drives[unit])[D_LUN];
- snprintf(pf->name, PF_NAMELEN, "%s%d", name, unit);
- disk->major = major;
- disk->first_minor = unit;
- disk->minors = 1;
- strcpy(disk->disk_name, pf->name);
- disk->fops = &pf_fops;
- disk->events = DISK_EVENT_MEDIA_CHANGE;
- if (!(*drives[unit])[D_PRT])
- pf_drive_count++;
- }
-}
-
static int pf_open(struct block_device *bdev, fmode_t mode)
{
struct pf_unit *pf = bdev->bd_disk->private_data;
@@ -691,9 +651,9 @@ static int pf_identify(struct pf_unit *pf)
return 0;
}
-/* returns 0, with id set if drive is detected
- -1, if drive detection failed
-*/
+/*
+ * returns 0, with id set if drive is detected, otherwise an error code.
+ */
static int pf_probe(struct pf_unit *pf)
{
if (pf->drive == -1) {
@@ -715,60 +675,7 @@ static int pf_probe(struct pf_unit *pf)
if (!pf_identify(pf))
return 0;
}
- return -1;
-}
-
-static int pf_detect(void)
-{
- struct pf_unit *pf = units;
- int k, unit;
-
- printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
- name, name, PF_VERSION, major, cluster, nice);
-
- par_drv = pi_register_driver(name);
- if (!par_drv) {
- pr_err("failed to register %s driver\n", name);
- return -1;
- }
- k = 0;
- if (pf_drive_count == 0) {
- if (pi_init(pf->pi, 1, -1, -1, -1, -1, -1, pf_scratch, PI_PF,
- verbose, pf->name)) {
- if (!pf_probe(pf) && pf->disk) {
- pf->present = 1;
- k++;
- } else
- pi_release(pf->pi);
- }
-
- } else
- for (unit = 0; unit < PF_UNITS; unit++, pf++) {
- int *conf = *drives[unit];
- if (!conf[D_PRT])
- continue;
- if (pi_init(pf->pi, 0, conf[D_PRT], conf[D_MOD],
- conf[D_UNI], conf[D_PRO], conf[D_DLY],
- pf_scratch, PI_PF, verbose, pf->name)) {
- if (pf->disk && !pf_probe(pf)) {
- pf->present = 1;
- k++;
- } else
- pi_release(pf->pi);
- }
- }
- if (k)
- return 0;
-
- printk("%s: No ATAPI disk detected\n", name);
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- if (!pf->disk)
- continue;
- blk_cleanup_disk(pf->disk);
- blk_mq_free_tag_set(&pf->tag_set);
- }
- pi_unregister_driver(par_drv);
- return -1;
+ return -ENODEV;
}
/* The i/o request engine */
@@ -1014,61 +921,134 @@ static void do_pf_write_done(void)
next_request(0);
}
+static int __init pf_init_unit(struct pf_unit *pf, bool autoprobe, int port,
+ int mode, int unit, int protocol, int delay, int ms)
+{
+ struct gendisk *disk;
+ int ret;
+
+ ret = blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1,
+ BLK_MQ_F_SHOULD_MERGE);
+ if (ret)
+ return ret;
+
+ disk = blk_mq_alloc_disk(&pf->tag_set, pf);
+ if (IS_ERR(disk)) {
+ ret = PTR_ERR(disk);
+ goto out_free_tag_set;
+ }
+ disk->major = major;
+ disk->first_minor = pf - units;
+ disk->minors = 1;
+ strcpy(disk->disk_name, pf->name);
+ disk->fops = &pf_fops;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
+ disk->private_data = pf;
+
+ blk_queue_max_segments(disk->queue, cluster);
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
+
+ INIT_LIST_HEAD(&pf->rq_list);
+ pf->disk = disk;
+ pf->pi = &pf->pia;
+ pf->media_status = PF_NM;
+ pf->drive = (*drives[disk->first_minor])[D_SLV];
+ pf->lun = (*drives[disk->first_minor])[D_LUN];
+ snprintf(pf->name, PF_NAMELEN, "%s%d", name, disk->first_minor);
+
+ if (!pi_init(pf->pi, autoprobe, port, mode, unit, protocol, delay,
+ pf_scratch, PI_PF, verbose, pf->name)) {
+ ret = -ENODEV;
+ goto out_free_disk;
+ }
+ ret = pf_probe(pf);
+ if (ret)
+ goto out_pi_release;
+
+ ret = add_disk(disk);
+ if (ret)
+ goto out_pi_release;
+ pf->present = 1;
+ return 0;
+
+out_pi_release:
+ pi_release(pf->pi);
+out_free_disk:
+ blk_cleanup_disk(pf->disk);
+out_free_tag_set:
+ blk_mq_free_tag_set(&pf->tag_set);
+ return ret;
+}
+
static int __init pf_init(void)
{ /* preliminary initialisation */
struct pf_unit *pf;
- int unit;
+ int found = 0, unit;
if (disable)
return -EINVAL;
- pf_init_units();
+ if (register_blkdev(major, name))
+ return -EBUSY;
- if (pf_detect())
- return -ENODEV;
- pf_busy = 0;
+ printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
+ name, name, PF_VERSION, major, cluster, nice);
- if (register_blkdev(major, name)) {
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- if (!pf->disk)
- continue;
- blk_cleanup_queue(pf->disk->queue);
- blk_mq_free_tag_set(&pf->tag_set);
- put_disk(pf->disk);
- }
- return -EBUSY;
+ par_drv = pi_register_driver(name);
+ if (!par_drv) {
+ pr_err("failed to register %s driver\n", name);
+ goto out_unregister_blkdev;
}
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- struct gendisk *disk = pf->disk;
+ for (unit = 0; unit < PF_UNITS; unit++) {
+ if (!(*drives[unit])[D_PRT])
+ pf_drive_count++;
+ }
- if (!pf->present)
- continue;
- disk->private_data = pf;
- add_disk(disk);
+ pf = units;
+ if (pf_drive_count == 0) {
+ if (pf_init_unit(pf, 1, -1, -1, -1, -1, -1, verbose))
+ found++;
+ } else {
+ for (unit = 0; unit < PF_UNITS; unit++, pf++) {
+ int *conf = *drives[unit];
+ if (!conf[D_PRT])
+ continue;
+ if (pf_init_unit(pf, 0, conf[D_PRT], conf[D_MOD],
+ conf[D_UNI], conf[D_PRO], conf[D_DLY],
+ verbose))
+ found++;
+ }
+ }
+ if (!found) {
+ printk("%s: No ATAPI disk detected\n", name);
+ goto out_unregister_pi_driver;
}
+ pf_busy = 0;
return 0;
+
+out_unregister_pi_driver:
+ pi_unregister_driver(par_drv);
+out_unregister_blkdev:
+ unregister_blkdev(major, name);
+ return -ENODEV;
}
static void __exit pf_exit(void)
{
struct pf_unit *pf;
int unit;
- unregister_blkdev(major, name);
+
for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- if (!pf->disk)
+ if (!pf->present)
continue;
-
- if (pf->present)
- del_gendisk(pf->disk);
-
- blk_cleanup_queue(pf->disk->queue);
+ del_gendisk(pf->disk);
+ blk_cleanup_disk(pf->disk);
blk_mq_free_tag_set(&pf->tag_set);
- put_disk(pf->disk);
-
- if (pf->present)
- pi_release(pf->pi);
+ pi_release(pf->pi);
}
+
+ unregister_blkdev(major, name);
}
MODULE_LICENSE("GPL");
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 0f26b2510a75..b53f648302c1 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -703,7 +703,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
struct request *rq;
int ret = 0;
- rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
+ rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
@@ -726,7 +726,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
if (scsi_req(rq)->result)
ret = -EIO;
out:
- blk_put_request(rq);
+ blk_mq_free_request(rq);
return ret;
}
@@ -2400,7 +2400,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
}
}
-static blk_qc_t pkt_submit_bio(struct bio *bio)
+static void pkt_submit_bio(struct bio *bio)
{
struct pktcdvd_device *pd;
char b[BDEVNAME_SIZE];
@@ -2423,7 +2423,7 @@ static blk_qc_t pkt_submit_bio(struct bio *bio)
*/
if (bio_data_dir(bio) == READ) {
pkt_make_request_read(pd, bio);
- return BLK_QC_T_NONE;
+ return;
}
if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
@@ -2455,10 +2455,9 @@ static blk_qc_t pkt_submit_bio(struct bio *bio)
pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
} while (split != bio);
- return BLK_QC_T_NONE;
+ return;
end_io:
bio_io_error(bio);
- return BLK_QC_T_NONE;
}
static void pkt_init_queue(struct pktcdvd_device *pd)
@@ -2537,6 +2536,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
int i;
char b[BDEVNAME_SIZE];
struct block_device *bdev;
+ struct scsi_device *sdev;
if (pd->pkt_dev == dev) {
pkt_err(pd, "recursive setup not allowed\n");
@@ -2560,10 +2560,12 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
- if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
+ sdev = scsi_device_from_queue(bdev->bd_disk->queue);
+ if (!sdev) {
blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
return -EINVAL;
}
+ put_device(&sdev->sdev_gendev);
/* This is safe, since we have a reference from open(). */
__module_get(THIS_MODULE);
@@ -2729,7 +2731,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
/* inherit events of the host device */
disk->events = pd->bdev->bd_disk->events;
- add_disk(disk);
+ ret = add_disk(disk);
+ if (ret)
+ goto out_mem2;
pkt_sysfs_dev_new(pd);
pkt_debugfs_dev_new(pd);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index c7b19e128b03..d1ebf193cb9a 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -578,7 +578,7 @@ out:
return next;
}
-static blk_qc_t ps3vram_submit_bio(struct bio *bio)
+static void ps3vram_submit_bio(struct bio *bio)
{
struct ps3_system_bus_device *dev = bio->bi_bdev->bd_disk->private_data;
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -594,13 +594,11 @@ static blk_qc_t ps3vram_submit_bio(struct bio *bio)
spin_unlock_irq(&priv->lock);
if (busy)
- return BLK_QC_T_NONE;
+ return;
do {
bio = ps3vram_do_bio(dev, bio);
} while (bio);
-
- return BLK_QC_T_NONE;
}
static const struct block_device_operations ps3vram_fops = {
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index e65c9d706f6f..953fa134cd3d 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -836,7 +836,7 @@ struct rbd_options {
u32 alloc_hint_flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */
};
-#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ
+#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_DEFAULT_RQ
#define RBD_ALLOC_SIZE_DEFAULT (64 * 1024)
#define RBD_LOCK_TIMEOUT_DEFAULT 0 /* no timeout */
#define RBD_READ_ONLY_DEFAULT false
@@ -7054,7 +7054,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
if (rc)
goto err_out_image_lock;
- device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL);
+ rc = device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL);
+ if (rc)
+ goto err_out_cleanup_disk;
spin_lock(&rbd_dev_list_lock);
list_add_tail(&rbd_dev->node, &rbd_dev_list);
@@ -7068,6 +7070,8 @@ out:
module_put(THIS_MODULE);
return rc;
+err_out_cleanup_disk:
+ rbd_free_disk(rbd_dev);
err_out_image_lock:
rbd_dev_image_unlock(rbd_dev);
rbd_dev_device_release(rbd_dev);
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index bd4a41afbbfc..2df0657cdf00 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1176,7 +1176,7 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
return ret;
}
-static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx)
+static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct rnbd_queue *q = hctx->driver_data;
struct rnbd_clt_dev *dev = q->dev;
@@ -1384,8 +1384,10 @@ static void setup_request_queue(struct rnbd_clt_dev *dev)
blk_queue_write_cache(dev->queue, dev->wc, dev->fua);
}
-static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
+static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
{
+ int err;
+
dev->gd->major = rnbd_client_major;
dev->gd->first_minor = idx << RNBD_PART_BITS;
dev->gd->minors = 1 << RNBD_PART_BITS;
@@ -1410,7 +1412,11 @@ static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
if (!dev->rotational)
blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
- add_disk(dev->gd);
+ err = add_disk(dev->gd);
+ if (err)
+ blk_cleanup_disk(dev->gd);
+
+ return err;
}
static int rnbd_client_setup_device(struct rnbd_clt_dev *dev)
@@ -1426,8 +1432,7 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev)
rnbd_init_mq_hw_queues(dev);
setup_request_queue(dev);
- rnbd_clt_setup_gen_disk(dev, idx);
- return 0;
+ return rnbd_clt_setup_gen_disk(dev, idx);
}
static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h
index c1bc5c0fef71..de5d5a8df81d 100644
--- a/drivers/block/rnbd/rnbd-proto.h
+++ b/drivers/block/rnbd/rnbd-proto.h
@@ -10,7 +10,7 @@
#define RNBD_PROTO_H
#include <linux/types.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
#include <linux/limits.h>
#include <linux/inet.h>
#include <linux/in.h>
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 83636714b8d7..8d9d69f5dfbc 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -935,7 +935,9 @@ static int rsxx_pci_probe(struct pci_dev *dev,
card->size8 = 0;
}
- rsxx_attach_dev(card);
+ st = rsxx_attach_dev(card);
+ if (st)
+ goto failed_create_dev;
/************* Setup Debugfs *************/
rsxx_debugfs_dev_new(card);
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 1cc40b0ea761..dd33f1bdf3b8 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -50,7 +50,7 @@ struct rsxx_bio_meta {
static struct kmem_cache *bio_meta_pool;
-static blk_qc_t rsxx_submit_bio(struct bio *bio);
+static void rsxx_submit_bio(struct bio *bio);
/*----------------- Block Device Operations -----------------*/
static int rsxx_blkdev_ioctl(struct block_device *bdev,
@@ -120,7 +120,7 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
}
}
-static blk_qc_t rsxx_submit_bio(struct bio *bio)
+static void rsxx_submit_bio(struct bio *bio)
{
struct rsxx_cardinfo *card = bio->bi_bdev->bd_disk->private_data;
struct rsxx_bio_meta *bio_meta;
@@ -169,7 +169,7 @@ static blk_qc_t rsxx_submit_bio(struct bio *bio)
if (st)
goto queue_err;
- return BLK_QC_T_NONE;
+ return;
queue_err:
kmem_cache_free(bio_meta_pool, bio_meta);
@@ -177,7 +177,6 @@ req_err:
if (st)
bio->bi_status = st;
bio_endio(bio);
- return BLK_QC_T_NONE;
}
/*----------------- Device Setup -------------------*/
@@ -192,6 +191,8 @@ static bool rsxx_discard_supported(struct rsxx_cardinfo *card)
int rsxx_attach_dev(struct rsxx_cardinfo *card)
{
+ int err = 0;
+
mutex_lock(&card->dev_lock);
/* The block device requires the stripe size from the config. */
@@ -200,13 +201,17 @@ int rsxx_attach_dev(struct rsxx_cardinfo *card)
set_capacity(card->gendisk, card->size8 >> 9);
else
set_capacity(card->gendisk, 0);
- device_add_disk(CARD_TO_DEV(card), card->gendisk, NULL);
- card->bdev_attached = 1;
+ err = device_add_disk(CARD_TO_DEV(card), card->gendisk, NULL);
+ if (err == 0)
+ card->bdev_attached = 1;
}
mutex_unlock(&card->dev_lock);
- return 0;
+ if (err)
+ blk_cleanup_disk(card->gendisk);
+
+ return err;
}
void rsxx_detach_dev(struct rsxx_cardinfo *card)
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 7ccc8d2a41bc..821594cd1315 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -16,6 +16,7 @@
#include <linux/fd.h>
#include <linux/slab.h>
#include <linux/blk-mq.h>
+#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/hdreg.h>
#include <linux/kernel.h>
@@ -184,6 +185,7 @@ struct floppy_state {
int track;
int ref_count;
+ bool registered;
struct gendisk *disk;
struct blk_mq_tag_set tag_set;
@@ -771,6 +773,20 @@ static const struct blk_mq_ops swim_mq_ops = {
.queue_rq = swim_queue_rq,
};
+static void swim_cleanup_floppy_disk(struct floppy_state *fs)
+{
+ struct gendisk *disk = fs->disk;
+
+ if (!disk)
+ return;
+
+ if (fs->registered)
+ del_gendisk(fs->disk);
+
+ blk_cleanup_disk(disk);
+ blk_mq_free_tag_set(&fs->tag_set);
+}
+
static int swim_floppy_init(struct swim_priv *swd)
{
int err;
@@ -827,7 +843,10 @@ static int swim_floppy_init(struct swim_priv *swd)
swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE;
swd->unit[drive].disk->private_data = &swd->unit[drive];
set_capacity(swd->unit[drive].disk, 2880);
- add_disk(swd->unit[drive].disk);
+ err = add_disk(swd->unit[drive].disk);
+ if (err)
+ goto exit_put_disks;
+ swd->unit[drive].registered = true;
}
return 0;
@@ -835,12 +854,7 @@ static int swim_floppy_init(struct swim_priv *swd)
exit_put_disks:
unregister_blkdev(FLOPPY_MAJOR, "fd");
do {
- struct gendisk *disk = swd->unit[drive].disk;
-
- if (!disk)
- continue;
- blk_cleanup_disk(disk);
- blk_mq_free_tag_set(&swd->unit[drive].tag_set);
+ swim_cleanup_floppy_disk(&swd->unit[drive]);
} while (drive--);
return err;
}
@@ -909,12 +923,8 @@ static int swim_remove(struct platform_device *dev)
int drive;
struct resource *res;
- for (drive = 0; drive < swd->floppy_count; drive++) {
- del_gendisk(swd->unit[drive].disk);
- blk_cleanup_queue(swd->unit[drive].disk->queue);
- blk_mq_free_tag_set(&swd->unit[drive].tag_set);
- put_disk(swd->unit[drive].disk);
- }
+ for (drive = 0; drive < swd->floppy_count; drive++)
+ swim_cleanup_floppy_disk(&swd->unit[drive]);
unregister_blkdev(FLOPPY_MAJOR, "fd");
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 965af0a3e95b..4b91c9aa5892 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -27,6 +27,7 @@
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
+#include <linux/major.h>
#include <asm/io.h>
#include <asm/dbdma.h>
#include <asm/prom.h>
@@ -1229,7 +1230,9 @@ static int swim3_attach(struct macio_dev *mdev,
disk->flags |= GENHD_FL_REMOVABLE;
sprintf(disk->disk_name, "fd%d", floppy_count);
set_capacity(disk, 2880);
- add_disk(disk);
+ rc = add_disk(disk);
+ if (rc)
+ goto out_cleanup_disk;
disks[floppy_count++] = disk;
return 0;
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index 420cd952ddc4..d1676fe0da1a 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -297,6 +297,7 @@ struct carm_host {
struct work_struct fsm_task;
+ int probe_err;
struct completion probe_comp;
};
@@ -1181,8 +1182,11 @@ static void carm_fsm_task (struct work_struct *work)
struct gendisk *disk = port->disk;
set_capacity(disk, port->capacity);
- add_disk(disk);
- activated++;
+ host->probe_err = add_disk(disk);
+ if (!host->probe_err)
+ activated++;
+ else
+ break;
}
printk(KERN_INFO DRV_NAME "(%s): %d ports activated\n",
@@ -1192,11 +1196,9 @@ static void carm_fsm_task (struct work_struct *work)
reschedule = 1;
break;
}
-
case HST_PROBE_FINISHED:
complete(&host->probe_comp);
break;
-
case HST_ERROR:
/* FIXME: TODO */
break;
@@ -1507,7 +1509,12 @@ static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_out_free_irq;
DPRINTK("waiting for probe_comp\n");
+ host->probe_err = -ENODEV;
wait_for_completion(&host->probe_comp);
+ if (host->probe_err) {
+ rc = host->probe_err;
+ goto err_out_free_irq;
+ }
printk(KERN_INFO "%s: pci %s, ports %d, io %llx, irq %u, major %d\n",
host->name, pci_name(pdev), (int) CARM_MAX_PORTS,
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 303caf2d17d0..fc4fc951dba7 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -312,7 +312,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
struct request *req;
int err;
- req = blk_get_request(q, REQ_OP_DRV_IN, 0);
+ req = blk_mq_alloc_request(q, REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -323,7 +323,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
blk_execute_rq(vblk->disk, req, false);
err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req)));
out:
- blk_put_request(req);
+ blk_mq_free_request(req);
return err;
}
@@ -815,9 +815,17 @@ static int virtblk_probe(struct virtio_device *vdev)
err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
struct virtio_blk_config, blk_size,
&blk_size);
- if (!err)
+ if (!err) {
+ err = blk_validate_block_size(blk_size);
+ if (err) {
+ dev_err(&vdev->dev,
+ "virtio_blk: invalid block size: 0x%x\n",
+ blk_size);
+ goto out_cleanup_disk;
+ }
+
blk_queue_logical_block_size(q, blk_size);
- else
+ } else
blk_size = queue_logical_block_size(q);
/* Use topology information if available */
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 33eba3df4dd9..914587aabca0 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -98,7 +98,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
return;
}
- err = filemap_write_and_wait(blkif->vbd.bdev->bd_inode->i_mapping);
+ err = sync_blockdev(blkif->vbd.bdev);
if (err) {
xenbus_dev_error(blkif->be->dev, err, "block flush");
return;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 72902104f111..8e3983e456f3 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -42,6 +42,7 @@
#include <linux/cdrom.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/bitmap.h>
@@ -2385,7 +2386,13 @@ static void blkfront_connect(struct blkfront_info *info)
for_each_rinfo(info, rinfo, i)
kick_pending_request_queues(rinfo);
- device_add_disk(&info->xbdev->dev, info->gd, NULL);
+ err = device_add_disk(&info->xbdev->dev, info->gd, NULL);
+ if (err) {
+ blk_cleanup_disk(info->gd);
+ blk_mq_free_tag_set(&info->tag_set);
+ info->rq = NULL;
+ goto fail;
+ }
info->is_ready = 1;
return;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fcaf2750f68f..a68297fb51a2 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1598,22 +1598,18 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
/*
* Handler function for all zram I/O requests.
*/
-static blk_qc_t zram_submit_bio(struct bio *bio)
+static void zram_submit_bio(struct bio *bio)
{
struct zram *zram = bio->bi_bdev->bd_disk->private_data;
if (!valid_io_request(zram, bio->bi_iter.bi_sector,
bio->bi_iter.bi_size)) {
atomic64_inc(&zram->stats.invalid_io);
- goto error;
+ bio_io_error(bio);
+ return;
}
__zram_make_request(zram, bio);
- return BLK_QC_T_NONE;
-
-error:
- bio_io_error(bio);
- return BLK_QC_T_NONE;
}
static void zram_slot_free_notify(struct block_device *bdev,
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index bd2e5b1560f5..9877e413fce3 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -344,6 +344,12 @@ static void cdrom_sysctl_register(void);
static LIST_HEAD(cdrom_list);
+static void signal_media_change(struct cdrom_device_info *cdi)
+{
+ cdi->mc_flags = 0x3; /* set media changed bits, on both queues */
+ cdi->last_media_change_ms = ktime_to_ms(ktime_get());
+}
+
int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
struct packet_command *cgc)
{
@@ -616,6 +622,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi)
ENSURE(cdo, generic_packet, CDC_GENERIC_PACKET);
cdi->mc_flags = 0;
cdi->options = CDO_USE_FFLAGS;
+ cdi->last_media_change_ms = ktime_to_ms(ktime_get());
if (autoclose == 1 && CDROM_CAN(CDC_CLOSE_TRAY))
cdi->options |= (int) CDO_AUTO_CLOSE;
@@ -864,7 +871,7 @@ static void cdrom_mmc3_profile(struct cdrom_device_info *cdi)
{
struct packet_command cgc;
char buffer[32];
- int ret, mmc3_profile;
+ int mmc3_profile;
init_cdrom_command(&cgc, buffer, sizeof(buffer), CGC_DATA_READ);
@@ -874,7 +881,7 @@ static void cdrom_mmc3_profile(struct cdrom_device_info *cdi)
cgc.cmd[8] = sizeof(buffer); /* Allocation Length */
cgc.quiet = 1;
- if ((ret = cdi->ops->generic_packet(cdi, &cgc)))
+ if (cdi->ops->generic_packet(cdi, &cgc))
mmc3_profile = 0xffff;
else
mmc3_profile = (buffer[6] << 8) | buffer[7];
@@ -1421,8 +1428,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot)
cdi->ops->check_events(cdi, 0, slot);
if (slot == CDSL_NONE) {
- /* set media changed bits, on both queues */
- cdi->mc_flags = 0x3;
+ signal_media_change(cdi);
return cdrom_load_unload(cdi, -1);
}
@@ -1455,7 +1461,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot)
slot = curslot;
/* set media changed bits on both queues */
- cdi->mc_flags = 0x3;
+ signal_media_change(cdi);
if ((ret = cdrom_load_unload(cdi, slot)))
return ret;
@@ -1521,7 +1527,7 @@ int media_changed(struct cdrom_device_info *cdi, int queue)
cdi->ioctl_events = 0;
if (changed) {
- cdi->mc_flags = 0x3; /* set bit on both queues */
+ signal_media_change(cdi);
ret |= 1;
cdi->media_written = 0;
}
@@ -2336,6 +2342,49 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi,
return ret;
}
+/*
+ * Media change detection with timing information.
+ *
+ * arg is a pointer to a cdrom_timed_media_change_info struct.
+ * arg->last_media_change may be set by calling code to signal
+ * the timestamp (in ms) of the last known media change (by the caller).
+ * Upon successful return, ioctl call will set arg->last_media_change
+ * to the latest media change timestamp known by the kernel/driver
+ * and set arg->has_changed to 1 if that timestamp is more recent
+ * than the timestamp set by the caller.
+ */
+static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi,
+ unsigned long arg)
+{
+ int ret;
+ struct cdrom_timed_media_change_info __user *info;
+ struct cdrom_timed_media_change_info tmp_info;
+
+ if (!CDROM_CAN(CDC_MEDIA_CHANGED))
+ return -ENOSYS;
+
+ info = (struct cdrom_timed_media_change_info __user *)arg;
+ cd_dbg(CD_DO_IOCTL, "entering CDROM_TIMED_MEDIA_CHANGE\n");
+
+ ret = cdrom_ioctl_media_changed(cdi, CDSL_CURRENT);
+ if (ret < 0)
+ return ret;
+
+ if (copy_from_user(&tmp_info, info, sizeof(tmp_info)) != 0)
+ return -EFAULT;
+
+ tmp_info.media_flags = 0;
+ if (tmp_info.last_media_change - cdi->last_media_change_ms < 0)
+ tmp_info.media_flags |= MEDIA_CHANGED_FLAG;
+
+ tmp_info.last_media_change = cdi->last_media_change_ms;
+
+ if (copy_to_user(info, &tmp_info, sizeof(*info)) != 0)
+ return -EFAULT;
+
+ return 0;
+}
+
static int cdrom_ioctl_set_options(struct cdrom_device_info *cdi,
unsigned long arg)
{
@@ -3313,6 +3362,8 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
return cdrom_ioctl_eject_sw(cdi, arg);
case CDROM_MEDIA_CHANGED:
return cdrom_ioctl_media_changed(cdi, arg);
+ case CDROM_TIMED_MEDIA_CHANGE:
+ return cdrom_ioctl_timed_media_change(cdi, arg);
case CDROM_SET_OPTIONS:
return cdrom_ioctl_set_options(cdi, arg);
case CDROM_CLEAR_OPTIONS:
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 8e1fe75af93f..d50cc1fd34d5 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -805,9 +805,14 @@ static int probe_gdrom(struct platform_device *devptr)
err = -ENOMEM;
goto probe_fail_free_irqs;
}
- add_disk(gd.disk);
+ err = add_disk(gd.disk);
+ if (err)
+ goto probe_fail_add_disk;
+
return 0;
+probe_fail_add_disk:
+ kfree(gd.toc);
probe_fail_free_irqs:
free_irq(HW_EVENT_GDROM_DMA, &gd);
free_irq(HW_EVENT_GDROM_CMD, &gd);
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index d6ba644f6b00..4a5516406c22 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -76,7 +76,7 @@ config TCG_TIS_SPI_CR50
config TCG_TIS_SYNQUACER
tristate "TPM Interface Specification 1.2 Interface / TPM 2.0 FIFO Interface (MMIO - SynQuacer)"
- depends on ARCH_SYNQUACER
+ depends on ARCH_SYNQUACER || COMPILE_TEST
select TCG_TIS_CORE
help
If you have a TPM security chip that is compliant with the
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 784b8b3cb903..97e916856cf3 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -455,6 +455,9 @@ static int tpm2_map_response_body(struct tpm_chip *chip, u32 cc, u8 *rsp,
if (be32_to_cpu(data->capability) != TPM2_CAP_HANDLES)
return 0;
+ if (be32_to_cpu(data->count) > (UINT_MAX - TPM_HEADER_SIZE - 9) / 4)
+ return -EFAULT;
+
if (len != TPM_HEADER_SIZE + 9 + 4 * be32_to_cpu(data->count))
return -EFAULT;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 69579efb247b..b2659a4c4016 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -48,6 +48,7 @@ static int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask,
unsigned long timeout, wait_queue_head_t *queue,
bool check_cancel)
{
+ struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
unsigned long stop;
long rc;
u8 status;
@@ -80,8 +81,8 @@ again:
}
} else {
do {
- usleep_range(TPM_TIMEOUT_USECS_MIN,
- TPM_TIMEOUT_USECS_MAX);
+ usleep_range(priv->timeout_min,
+ priv->timeout_max);
status = chip->ops->status(chip);
if ((status & mask) == mask)
return 0;
@@ -945,7 +946,22 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
chip->timeout_b = msecs_to_jiffies(TIS_TIMEOUT_B_MAX);
chip->timeout_c = msecs_to_jiffies(TIS_TIMEOUT_C_MAX);
chip->timeout_d = msecs_to_jiffies(TIS_TIMEOUT_D_MAX);
+ priv->timeout_min = TPM_TIMEOUT_USECS_MIN;
+ priv->timeout_max = TPM_TIMEOUT_USECS_MAX;
priv->phy_ops = phy_ops;
+
+ rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor);
+ if (rc < 0)
+ goto out_err;
+
+ priv->manufacturer_id = vendor;
+
+ if (priv->manufacturer_id == TPM_VID_ATML &&
+ !(chip->flags & TPM_CHIP_FLAG_TPM2)) {
+ priv->timeout_min = TIS_TIMEOUT_MIN_ATML;
+ priv->timeout_max = TIS_TIMEOUT_MAX_ATML;
+ }
+
dev_set_drvdata(&chip->dev, priv);
if (is_bsw()) {
@@ -988,12 +1004,6 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
if (rc)
goto out_err;
- rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor);
- if (rc < 0)
- goto out_err;
-
- priv->manufacturer_id = vendor;
-
rc = tpm_tis_read8(priv, TPM_RID(0), &rid);
if (rc < 0)
goto out_err;
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index b2a3c6c72882..3be24f221e32 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -54,6 +54,8 @@ enum tis_defaults {
TIS_MEM_LEN = 0x5000,
TIS_SHORT_TIMEOUT = 750, /* ms */
TIS_LONG_TIMEOUT = 2000, /* 2 sec */
+ TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */
+ TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */
};
/* Some timeout values are needed before it is known whether the chip is
@@ -98,6 +100,8 @@ struct tpm_tis_data {
wait_queue_head_t read_queue;
const struct tpm_tis_phy_ops *phy_ops;
unsigned short rng_quality;
+ unsigned int timeout_min; /* usecs */
+ unsigned int timeout_max; /* usecs */
};
struct tpm_tis_phy_ops {
diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c
index 54584b4b00d1..aaa59a00eeae 100644
--- a/drivers/char/tpm/tpm_tis_spi_main.c
+++ b/drivers/char/tpm/tpm_tis_spi_main.c
@@ -267,6 +267,7 @@ static const struct spi_device_id tpm_tis_spi_id[] = {
{ "st33htpm-spi", (unsigned long)tpm_tis_spi_probe },
{ "slb9670", (unsigned long)tpm_tis_spi_probe },
{ "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
+ { "tpm_tis-spi", (unsigned long)tpm_tis_spi_probe },
{ "cr50", (unsigned long)cr50_spi_probe },
{}
};
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 0506046a5f4b..510a9965633b 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -58,11 +58,8 @@ static int clk_composite_determine_rate(struct clk_hw *hw,
long rate;
int i;
- if (rate_hw && rate_ops && rate_ops->determine_rate) {
- __clk_hw_set_clk(rate_hw, hw);
- return rate_ops->determine_rate(rate_hw, req);
- } else if (rate_hw && rate_ops && rate_ops->round_rate &&
- mux_hw && mux_ops && mux_ops->set_parent) {
+ if (rate_hw && rate_ops && rate_ops->round_rate &&
+ mux_hw && mux_ops && mux_ops->set_parent) {
req->best_parent_hw = NULL;
if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) {
@@ -107,6 +104,9 @@ static int clk_composite_determine_rate(struct clk_hw *hw,
req->rate = best_rate;
return 0;
+ } else if (rate_hw && rate_ops && rate_ops->determine_rate) {
+ __clk_hw_set_clk(rate_hw, hw);
+ return rate_ops->determine_rate(rate_hw, req);
} else if (mux_hw && mux_ops && mux_ops->determine_rate) {
__clk_hw_set_clk(mux_hw, hw);
return mux_ops->determine_rate(mux_hw, req);
diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c
index 177d03ef4529..40a052bc6784 100644
--- a/drivers/gpio/gpio-mlxbf2.c
+++ b/drivers/gpio/gpio-mlxbf2.c
@@ -256,6 +256,11 @@ mlxbf2_gpio_probe(struct platform_device *pdev)
NULL,
0);
+ if (ret) {
+ dev_err(dev, "bgpio_init failed\n");
+ return ret;
+ }
+
gc->direction_input = mlxbf2_gpio_direction_input;
gc->direction_output = mlxbf2_gpio_direction_output;
gc->ngpio = npins;
diff --git a/drivers/gpio/gpio-xgs-iproc.c b/drivers/gpio/gpio-xgs-iproc.c
index fa9b4d8c3ff5..43ca52fa6f9a 100644
--- a/drivers/gpio/gpio-xgs-iproc.c
+++ b/drivers/gpio/gpio-xgs-iproc.c
@@ -224,7 +224,7 @@ static int iproc_gpio_probe(struct platform_device *pdev)
}
chip->gc.label = dev_name(dev);
- if (of_property_read_u32(dn, "ngpios", &num_gpios))
+ if (!of_property_read_u32(dn, "ngpios", &num_gpios))
chip->gc.ngpio = num_gpios;
irq = platform_get_irq(pdev, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index ff80786e3918..01efda4398e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -1257,7 +1257,7 @@ static int nv_common_early_init(void *handle)
AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
if (adev->pdev->device == 0x1681)
- adev->external_rev_id = adev->rev_id + 0x19;
+ adev->external_rev_id = 0x20;
else
adev->external_rev_id = adev->rev_id + 0x01;
break;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 87daa78a32b8..8080bba5b7a7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -263,7 +263,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
if (!wr_buf)
return -ENOSPC;
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -487,7 +487,7 @@ static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf,
if (!wr_buf)
return -ENOSPC;
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -639,7 +639,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
if (!wr_buf)
return -ENOSPC;
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -914,7 +914,7 @@ static ssize_t dp_dsc_passthrough_set(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
&param, buf,
max_param_num,
&param_nums)) {
@@ -1211,7 +1211,7 @@ static ssize_t trigger_hotplug(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1396,7 +1396,7 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1581,7 +1581,7 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1766,7 +1766,7 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1944,7 +1944,7 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -2382,7 +2382,7 @@ static ssize_t dp_max_bpc_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index 4a4894e9d9c9..377c4e53a2b3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -366,32 +366,32 @@ static struct wm_table lpddr5_wm_table = {
.wm_inst = WM_A,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 5.32,
- .sr_enter_plus_exit_time_us = 6.38,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
{
.wm_inst = WM_B,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 9.82,
- .sr_enter_plus_exit_time_us = 11.196,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
{
.wm_inst = WM_C,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 9.89,
- .sr_enter_plus_exit_time_us = 11.24,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
{
.wm_inst = WM_D,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 9.748,
- .sr_enter_plus_exit_time_us = 11.102,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
}
@@ -518,14 +518,21 @@ static unsigned int find_clk_for_voltage(
unsigned int voltage)
{
int i;
+ int max_voltage = 0;
+ int clock = 0;
for (i = 0; i < NUM_SOC_VOLTAGE_LEVELS; i++) {
- if (clock_table->SocVoltage[i] == voltage)
+ if (clock_table->SocVoltage[i] == voltage) {
return clocks[i];
+ } else if (clock_table->SocVoltage[i] >= max_voltage &&
+ clock_table->SocVoltage[i] < voltage) {
+ max_voltage = clock_table->SocVoltage[i];
+ clock = clocks[i];
+ }
}
- ASSERT(0);
- return 0;
+ ASSERT(clock);
+ return clock;
}
void dcn31_clk_mgr_helper_populate_bw_params(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 3f2333ec67e2..3afa1159a5f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -76,10 +76,6 @@ void dcn31_init_hw(struct dc *dc)
if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks)
dc->clk_mgr->funcs->init_clocks(dc->clk_mgr);
- // Initialize the dccg
- if (res_pool->dccg->funcs->dccg_init)
- res_pool->dccg->funcs->dccg_init(res_pool->dccg);
-
if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
REG_WRITE(REFCLK_CNTL, 0);
@@ -106,6 +102,9 @@ void dcn31_init_hw(struct dc *dc)
hws->funcs.bios_golden_init(dc);
hws->funcs.disable_vga(dc->hwseq);
}
+ // Initialize the dccg
+ if (res_pool->dccg->funcs->dccg_init)
+ res_pool->dccg->funcs->dccg_init(res_pool->dccg);
if (dc->debug.enable_mem_low_power.bits.dmcu) {
// Force ERAM to shutdown if DMCU is not enabled
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 0006bbac466c..79e92ecca96c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -217,8 +217,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
.num_states = 5,
.sr_exit_time_us = 9.0,
.sr_enter_plus_exit_time_us = 11.0,
- .sr_exit_z8_time_us = 402.0,
- .sr_enter_plus_exit_z8_time_us = 520.0,
+ .sr_exit_z8_time_us = 442.0,
+ .sr_enter_plus_exit_z8_time_us = 560.0,
.writeback_latency_us = 12.0,
.dram_channel_width_bytes = 4,
.round_trip_ping_latency_dcfclk_cycles = 106,
@@ -928,7 +928,7 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_dcc = DCC_ENABLE,
.vsr_support = true,
.performance_trace = false,
- .max_downscale_src_width = 3840,/*upto 4K*/
+ .max_downscale_src_width = 4096,/*upto true 4K*/
.disable_pplib_wm_range = false,
.scl_reset_length10 = true,
.sanity_checks = false,
@@ -1590,6 +1590,13 @@ static int dcn31_populate_dml_pipes_from_context(
pipe = &res_ctx->pipe_ctx[i];
timing = &pipe->stream->timing;
+ /*
+ * Immediate flip can be set dynamically after enabling the plane.
+ * We need to require support for immediate flip or underflow can be
+ * intermittently experienced depending on peak b/w requirements.
+ */
+ pipes[pipe_cnt].pipe.src.immediate_flip = true;
+
pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
pipes[pipe_cnt].pipe.src.gpuvm = true;
pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index ce55c9caf9a2..d58925cff420 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -5398,9 +5398,9 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
v->MaximumReadBandwidthWithPrefetch =
v->MaximumReadBandwidthWithPrefetch
- + dml_max4(
- v->VActivePixelBandwidth[i][j][k],
- v->VActiveCursorBandwidth[i][j][k]
+ + dml_max3(
+ v->VActivePixelBandwidth[i][j][k]
+ + v->VActiveCursorBandwidth[i][j][k]
+ v->NoOfDPP[i][j][k]
* (v->meta_row_bandwidth[i][j][k]
+ v->dpte_row_bandwidth[i][j][k]),
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 5adc471bef57..3d2f0817e40a 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -227,7 +227,7 @@ enum {
#define FAMILY_YELLOW_CARP 146
#define YELLOW_CARP_A0 0x01
-#define YELLOW_CARP_B0 0x1A
+#define YELLOW_CARP_B0 0x20
#define YELLOW_CARP_UNKNOWN 0xFF
#ifndef ASICREV_IS_YELLOW_CARP
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index e9bd84ec027d..be61975f1470 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -105,6 +105,7 @@ static enum mod_hdcp_status remove_display_from_topology_v3(
dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE;
psp_dtm_invoke(psp, dtm_cmd->cmd_id);
+ mutex_unlock(&psp->dtm_context.mutex);
if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) {
status = remove_display_from_topology_v2(hdcp, index);
@@ -115,8 +116,6 @@ static enum mod_hdcp_status remove_display_from_topology_v3(
HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, display->index);
}
- mutex_unlock(&psp->dtm_context.mutex);
-
return status;
}
@@ -205,6 +204,7 @@ static enum mod_hdcp_status add_display_to_topology_v3(
dtm_cmd->dtm_in_message.topology_update_v3.link_hdcp_cap = link->hdcp_supported_informational;
psp_dtm_invoke(psp, dtm_cmd->cmd_id);
+ mutex_unlock(&psp->dtm_context.mutex);
if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) {
status = add_display_to_topology_v2(hdcp, display);
@@ -214,8 +214,6 @@ static enum mod_hdcp_status add_display_to_topology_v3(
HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, display->index);
}
- mutex_unlock(&psp->dtm_context.mutex);
-
return status;
}
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index f6bdec7fa925..e1b2ce4921ae 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"),
},
.driver_data = (void *)&lcd800x1280_rightside_up,
+ }, { /* AYA NEO 2021 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYADEVICE"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "AYA NEO 2021"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* GPD MicroPC (generic strings, also match on bios date) */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
@@ -185,6 +191,12 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "Default string"),
},
.driver_data = (void *)&gpd_win2,
+ }, { /* GPD Win 3 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1618-03")
+ },
+ .driver_data = (void *)&lcd720x1280_rightside_up,
}, { /* I.T.Works TW891 */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index abe3d61b6243..5cf152be4487 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1916,6 +1916,9 @@ void intel_dp_sync_state(struct intel_encoder *encoder,
{
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+ if (!crtc_state)
+ return;
+
/*
* Don't clobber DPCD if it's been already read out during output
* setup (eDP) or detect.
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 1257f4f11e66..438bbc7b8147 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -64,7 +64,7 @@ intel_timeline_pin_map(struct intel_timeline *timeline)
timeline->hwsp_map = vaddr;
timeline->hwsp_seqno = memset(vaddr + ofs, 0, TIMELINE_SEQNO_BYTES);
- clflush(vaddr + ofs);
+ drm_clflush_virt_range(vaddr + ofs, TIMELINE_SEQNO_BYTES);
return 0;
}
@@ -225,7 +225,7 @@ void intel_timeline_reset_seqno(const struct intel_timeline *tl)
memset(hwsp_seqno + 1, 0, TIMELINE_SEQNO_BYTES - sizeof(*hwsp_seqno));
WRITE_ONCE(*hwsp_seqno, tl->seqno);
- clflush(hwsp_seqno);
+ drm_clflush_virt_range(hwsp_seqno, TIMELINE_SEQNO_BYTES);
}
void intel_timeline_enter(struct intel_timeline *tl)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4037030f0984..9023d4ecf3b3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11048,12 +11048,6 @@ enum skl_power_gate {
#define DC_STATE_DEBUG_MASK_CORES (1 << 0)
#define DC_STATE_DEBUG_MASK_MEMORY_UP (1 << 1)
-#define BXT_P_CR_MC_BIOS_REQ_0_0_0 _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x7114)
-#define BXT_REQ_DATA_MASK 0x3F
-#define BXT_DRAM_CHANNEL_ACTIVE_SHIFT 12
-#define BXT_DRAM_CHANNEL_ACTIVE_MASK (0xF << 12)
-#define BXT_MEMORY_FREQ_MULTIPLIER_HZ 133333333
-
#define BXT_D_CR_DRP0_DUNIT8 0x1000
#define BXT_D_CR_DRP0_DUNIT9 0x1200
#define BXT_D_CR_DRP0_DUNIT_START 8
@@ -11084,9 +11078,7 @@ enum skl_power_gate {
#define BXT_DRAM_TYPE_LPDDR4 (0x2 << 22)
#define BXT_DRAM_TYPE_DDR4 (0x4 << 22)
-#define SKL_MEMORY_FREQ_MULTIPLIER_HZ 266666666
#define SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5E04)
-#define SKL_REQ_DATA_MASK (0xF << 0)
#define DG1_GEAR_TYPE REG_BIT(16)
#define SKL_MAD_INTER_CHANNEL_0_0_0_MCHBAR_MCMAIN _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5000)
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 806ad688274b..63fec1c3c132 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -794,7 +794,6 @@ DECLARE_EVENT_CLASS(i915_request,
TP_STRUCT__entry(
__field(u32, dev)
__field(u64, ctx)
- __field(u32, guc_id)
__field(u16, class)
__field(u16, instance)
__field(u32, seqno)
@@ -805,16 +804,14 @@ DECLARE_EVENT_CLASS(i915_request,
__entry->dev = rq->engine->i915->drm.primary->index;
__entry->class = rq->engine->uabi_class;
__entry->instance = rq->engine->uabi_instance;
- __entry->guc_id = rq->context->guc_id;
__entry->ctx = rq->fence.context;
__entry->seqno = rq->fence.seqno;
__entry->tail = rq->tail;
),
- TP_printk("dev=%u, engine=%u:%u, guc_id=%u, ctx=%llu, seqno=%u, tail=%u",
+ TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, tail=%u",
__entry->dev, __entry->class, __entry->instance,
- __entry->guc_id, __entry->ctx, __entry->seqno,
- __entry->tail)
+ __entry->ctx, __entry->seqno, __entry->tail)
);
DEFINE_EVENT(i915_request, i915_request_add,
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 5259edacde38..066a9118c374 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -30,6 +30,7 @@
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/workqueue.h>
+#include <linux/sched/clock.h>
struct drm_i915_private;
struct timer_list;
diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c
index 91866520c173..7acce64b0941 100644
--- a/drivers/gpu/drm/i915/intel_dram.c
+++ b/drivers/gpu/drm/i915/intel_dram.c
@@ -244,7 +244,6 @@ static int
skl_get_dram_info(struct drm_i915_private *i915)
{
struct dram_info *dram_info = &i915->dram_info;
- u32 mem_freq_khz, val;
int ret;
dram_info->type = skl_get_dram_type(i915);
@@ -255,17 +254,6 @@ skl_get_dram_info(struct drm_i915_private *i915)
if (ret)
return ret;
- val = intel_uncore_read(&i915->uncore,
- SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU);
- mem_freq_khz = DIV_ROUND_UP((val & SKL_REQ_DATA_MASK) *
- SKL_MEMORY_FREQ_MULTIPLIER_HZ, 1000);
-
- if (dram_info->num_channels * mem_freq_khz == 0) {
- drm_info(&i915->drm,
- "Couldn't get system memory bandwidth\n");
- return -EINVAL;
- }
-
return 0;
}
@@ -350,24 +338,10 @@ static void bxt_get_dimm_info(struct dram_dimm_info *dimm, u32 val)
static int bxt_get_dram_info(struct drm_i915_private *i915)
{
struct dram_info *dram_info = &i915->dram_info;
- u32 dram_channels;
- u32 mem_freq_khz, val;
- u8 num_active_channels, valid_ranks = 0;
+ u32 val;
+ u8 valid_ranks = 0;
int i;
- val = intel_uncore_read(&i915->uncore, BXT_P_CR_MC_BIOS_REQ_0_0_0);
- mem_freq_khz = DIV_ROUND_UP((val & BXT_REQ_DATA_MASK) *
- BXT_MEMORY_FREQ_MULTIPLIER_HZ, 1000);
-
- dram_channels = val & BXT_DRAM_CHANNEL_ACTIVE_MASK;
- num_active_channels = hweight32(dram_channels);
-
- if (mem_freq_khz * num_active_channels == 0) {
- drm_info(&i915->drm,
- "Couldn't get system memory bandwidth\n");
- return -EINVAL;
- }
-
/*
* Now read each DUNIT8/9/10/11 to check the rank of each dimms.
*/
diff --git a/drivers/gpu/drm/selftests/test-drm_damage_helper.c b/drivers/gpu/drm/selftests/test-drm_damage_helper.c
index 1c19a5d3eefb..8d8d8e214c28 100644
--- a/drivers/gpu/drm/selftests/test-drm_damage_helper.c
+++ b/drivers/gpu/drm/selftests/test-drm_damage_helper.c
@@ -30,6 +30,7 @@ static void mock_setup(struct drm_plane_state *state)
mock_device.driver = &mock_driver;
mock_device.mode_config.prop_fb_damage_clips = &mock_prop;
mock_plane.dev = &mock_device;
+ mock_obj_props.count = 0;
mock_plane.base.properties = &mock_obj_props;
mock_prop.base.id = 1; /* 0 is an invalid id */
mock_prop.dev = &mock_device;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 1c5ffe2935af..abf2d7a4fdf1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -190,6 +190,7 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
struct ttm_transfer_obj *fbo;
fbo = container_of(bo, struct ttm_transfer_obj, base);
+ dma_resv_fini(&fbo->base.base._resv);
ttm_bo_put(fbo->bo);
kfree(fbo);
}
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index a20b8108e160..c00f8e28aab7 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -706,8 +706,9 @@ static void ib_nl_set_path_rec_attrs(struct sk_buff *skb,
/* Construct the family header first */
header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
- memcpy(header->device_name, dev_name(&query->port->agent->device->dev),
- LS_DEVICE_NAME_MAX);
+ strscpy_pad(header->device_name,
+ dev_name(&query->port->agent->device->dev),
+ LS_DEVICE_NAME_MAX);
header->port_num = query->port->port_num;
if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) &&
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 489b436f19bb..3d42bd2b36bd 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -878,6 +878,7 @@ void sc_disable(struct send_context *sc)
{
u64 reg;
struct pio_buf *pbuf;
+ LIST_HEAD(wake_list);
if (!sc)
return;
@@ -912,19 +913,21 @@ void sc_disable(struct send_context *sc)
spin_unlock(&sc->release_lock);
write_seqlock(&sc->waitlock);
- while (!list_empty(&sc->piowait)) {
+ if (!list_empty(&sc->piowait))
+ list_move(&sc->piowait, &wake_list);
+ write_sequnlock(&sc->waitlock);
+ while (!list_empty(&wake_list)) {
struct iowait *wait;
struct rvt_qp *qp;
struct hfi1_qp_priv *priv;
- wait = list_first_entry(&sc->piowait, struct iowait, list);
+ wait = list_first_entry(&wake_list, struct iowait, list);
qp = iowait_to_qp(wait);
priv = qp->priv;
list_del_init(&priv->s_iowait.list);
priv->s_iowait.lock = NULL;
hfi1_qp_wakeup(qp, RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN);
}
- write_sequnlock(&sc->waitlock);
spin_unlock_irq(&sc->alloc_lock);
}
diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c
index 5fb92de1f015..9b544a3b1288 100644
--- a/drivers/infiniband/hw/irdma/uk.c
+++ b/drivers/infiniband/hw/irdma/uk.c
@@ -1092,12 +1092,12 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info)
if (cq->avoid_mem_cflct) {
ext_cqe = (__le64 *)((u8 *)cqe + 32);
get_64bit_val(ext_cqe, 24, &qword7);
- polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+ polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7);
} else {
peek_head = (cq->cq_ring.head + 1) % cq->cq_ring.size;
ext_cqe = cq->cq_base[peek_head].buf;
get_64bit_val(ext_cqe, 24, &qword7);
- polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+ polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7);
if (!peek_head)
polarity ^= 1;
}
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 7110ebf834f9..102dc9342f2a 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -3399,9 +3399,13 @@ static void irdma_process_cqe(struct ib_wc *entry,
}
if (cq_poll_info->ud_vlan_valid) {
- entry->vlan_id = cq_poll_info->ud_vlan & VLAN_VID_MASK;
- entry->wc_flags |= IB_WC_WITH_VLAN;
+ u16 vlan = cq_poll_info->ud_vlan & VLAN_VID_MASK;
+
entry->sl = cq_poll_info->ud_vlan >> VLAN_PRIO_SHIFT;
+ if (vlan) {
+ entry->vlan_id = vlan;
+ entry->wc_flags |= IB_WC_WITH_VLAN;
+ }
} else {
entry->sl = 0;
}
diff --git a/drivers/infiniband/hw/irdma/ws.c b/drivers/infiniband/hw/irdma/ws.c
index b68c575eb78e..b0d6ee0739f5 100644
--- a/drivers/infiniband/hw/irdma/ws.c
+++ b/drivers/infiniband/hw/irdma/ws.c
@@ -330,8 +330,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
tc_node->enable = true;
ret = irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_MODIFY_NODE);
- if (ret)
+ if (ret) {
+ vsi->unregister_qset(vsi, tc_node);
goto reg_err;
+ }
}
ibdev_dbg(to_ibdev(vsi->dev),
"WS: Using node %d which represents VSI %d TC %d\n",
@@ -350,6 +352,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
}
goto exit;
+reg_err:
+ irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_DELETE_NODE);
+ list_del(&tc_node->siblings);
+ irdma_free_node(vsi, tc_node);
leaf_add_err:
if (list_empty(&vsi_node->child_list_head)) {
if (irdma_ws_cqp_cmd(vsi, vsi_node, IRDMA_OP_WS_DELETE_NODE))
@@ -369,11 +375,6 @@ vsi_add_err:
exit:
mutex_unlock(&vsi->dev->ws_mutex);
return ret;
-
-reg_err:
- mutex_unlock(&vsi->dev->ws_mutex);
- irdma_ws_remove(vsi, user_pri);
- return ret;
}
/**
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3be36ebbf67a..22e2f4d79743 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1339,7 +1339,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
goto err_2;
}
mr->mmkey.type = MLX5_MKEY_MR;
- mr->desc_size = sizeof(struct mlx5_mtt);
mr->umem = umem;
set_mr_fields(dev, mr, umem->length, access_flags);
kvfree(in);
@@ -1533,6 +1532,7 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length,
ib_umem_release(&odp->umem);
return ERR_CAST(mr);
}
+ xa_init(&mr->implicit_children);
odp->private = mr;
err = mlx5r_store_odp_mkey(dev, &mr->mmkey);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index b2fca110346c..e5abbcfc1d57 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4458,6 +4458,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
MLX5_SET(dctc, dctc, mtu, attr->path_mtu);
MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index);
MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
+ if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
+ MLX5_SET(dctc, dctc, eth_prio, attr->ah_attr.sl & 0x7);
err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in,
MLX5_ST_SZ_BYTES(create_dct_in), out,
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 3cb4febaad0f..8def88cfa300 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -455,6 +455,7 @@ struct qedr_qp {
/* synchronization objects used with iwarp ep */
struct kref refcnt;
struct completion iwarp_cm_comp;
+ struct completion qp_rel_comp;
unsigned long iwarp_cm_flags; /* enum iwarp_cm_flags */
};
diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
index 1715fbe0719d..a51fc6854984 100644
--- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
@@ -83,7 +83,7 @@ static void qedr_iw_free_qp(struct kref *ref)
{
struct qedr_qp *qp = container_of(ref, struct qedr_qp, refcnt);
- kfree(qp);
+ complete(&qp->qp_rel_comp);
}
static void
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 3fbf172dbbef..dcb3653db72d 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1357,6 +1357,7 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev,
if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
kref_init(&qp->refcnt);
init_completion(&qp->iwarp_cm_comp);
+ init_completion(&qp->qp_rel_comp);
}
qp->pd = pd;
@@ -2857,8 +2858,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
qedr_free_qp_resources(dev, qp, udata);
- if (rdma_protocol_iwarp(&dev->ibdev, 1))
+ if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
qedr_iw_qp_rem_ref(&qp->ibqp);
+ wait_for_completion(&qp->qp_rel_comp);
+ }
return 0;
}
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index a67599b5a550..ac11943a5ddb 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -602,7 +602,7 @@ done:
/*
* How many pages in this iovec element?
*/
-static int qib_user_sdma_num_pages(const struct iovec *iov)
+static size_t qib_user_sdma_num_pages(const struct iovec *iov)
{
const unsigned long addr = (unsigned long) iov->iov_base;
const unsigned long len = iov->iov_len;
@@ -658,7 +658,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
struct qib_user_sdma_queue *pq,
struct qib_user_sdma_pkt *pkt,
- unsigned long addr, int tlen, int npages)
+ unsigned long addr, int tlen, size_t npages)
{
struct page *pages[8];
int i, j;
@@ -722,7 +722,7 @@ static int qib_user_sdma_pin_pkt(const struct qib_devdata *dd,
unsigned long idx;
for (idx = 0; idx < niov; idx++) {
- const int npages = qib_user_sdma_num_pages(iov + idx);
+ const size_t npages = qib_user_sdma_num_pages(iov + idx);
const unsigned long addr = (unsigned long) iov[idx].iov_base;
ret = qib_user_sdma_pin_pages(dd, pq, pkt, addr,
@@ -824,8 +824,8 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
unsigned pktnw;
unsigned pktnwc;
int nfrags = 0;
- int npages = 0;
- int bytes_togo = 0;
+ size_t npages = 0;
+ size_t bytes_togo = 0;
int tiddma = 0;
int cfur;
@@ -885,7 +885,11 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
npages += qib_user_sdma_num_pages(&iov[idx]);
- bytes_togo += slen;
+ if (check_add_overflow(bytes_togo, slen, &bytes_togo) ||
+ bytes_togo > type_max(typeof(pkt->bytes_togo))) {
+ ret = -EINVAL;
+ goto free_pbc;
+ }
pktnwc += slen >> 2;
idx++;
nfrags++;
@@ -904,8 +908,7 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
}
if (frag_size) {
- int tidsmsize, n;
- size_t pktsize;
+ size_t tidsmsize, n, pktsize, sz, addrlimit;
n = npages*((2*PAGE_SIZE/frag_size)+1);
pktsize = struct_size(pkt, addr, n);
@@ -923,14 +926,24 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
else
tidsmsize = 0;
- pkt = kmalloc(pktsize+tidsmsize, GFP_KERNEL);
+ if (check_add_overflow(pktsize, tidsmsize, &sz)) {
+ ret = -EINVAL;
+ goto free_pbc;
+ }
+ pkt = kmalloc(sz, GFP_KERNEL);
if (!pkt) {
ret = -ENOMEM;
goto free_pbc;
}
pkt->largepkt = 1;
pkt->frag_size = frag_size;
- pkt->addrlimit = n + ARRAY_SIZE(pkt->addr);
+ if (check_add_overflow(n, ARRAY_SIZE(pkt->addr),
+ &addrlimit) ||
+ addrlimit > type_max(typeof(pkt->addrlimit))) {
+ ret = -EINVAL;
+ goto free_pbc;
+ }
+ pkt->addrlimit = addrlimit;
if (tiddma) {
char *tidsm = (char *)pkt + pktsize;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 49bdd78ac664..3305f2744bfa 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1223,7 +1223,7 @@ int rvt_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
spin_lock(&rdi->n_qps_lock);
if (rdi->n_qps_allocated == rdi->dparms.props.max_qp) {
spin_unlock(&rdi->n_qps_lock);
- ret = ENOMEM;
+ ret = -ENOMEM;
goto bail_ip;
}
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 5fc989a6d452..9ed9c955add7 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -178,7 +178,6 @@
#define pr_fmt(fmt) "bcache: %s() " fmt, __func__
-#include <linux/bcache.h>
#include <linux/bio.h>
#include <linux/kobject.h>
#include <linux/list.h>
@@ -190,6 +189,7 @@
#include <linux/workqueue.h>
#include <linux/kthread.h>
+#include "bcache_ondisk.h"
#include "bset.h"
#include "util.h"
#include "closure.h"
@@ -395,8 +395,6 @@ struct cached_dev {
atomic_t io_errors;
unsigned int error_limit;
unsigned int offline_seconds;
-
- char backing_dev_name[BDEVNAME_SIZE];
};
enum alloc_reserve {
@@ -470,8 +468,6 @@ struct cache {
atomic_long_t meta_sectors_written;
atomic_long_t btree_sectors_written;
atomic_long_t sectors_written;
-
- char cache_dev_name[BDEVNAME_SIZE];
};
struct gc_stat {
diff --git a/include/uapi/linux/bcache.h b/drivers/md/bcache/bcache_ondisk.h
index cf7399f03b71..97413586195b 100644
--- a/include/uapi/linux/bcache.h
+++ b/drivers/md/bcache/bcache_ondisk.h
@@ -43,9 +43,9 @@ static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \
#define KEY_MAX_U64S 8
KEY_FIELD(KEY_PTRS, high, 60, 3)
-KEY_FIELD(HEADER_SIZE, high, 58, 2)
+KEY_FIELD(__PAD0, high, 58, 2)
KEY_FIELD(KEY_CSUM, high, 56, 2)
-KEY_FIELD(KEY_PINNED, high, 55, 1)
+KEY_FIELD(__PAD1, high, 55, 1)
KEY_FIELD(KEY_DIRTY, high, 36, 1)
KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS)
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index a50dcfda656f..d795c84246b0 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -2,10 +2,10 @@
#ifndef _BCACHE_BSET_H
#define _BCACHE_BSET_H
-#include <linux/bcache.h>
#include <linux/kernel.h>
#include <linux/types.h>
+#include "bcache_ondisk.h"
#include "util.h" /* for time_stats */
/*
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 0595559de174..93b67b8d31c3 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -141,7 +141,7 @@ static uint64_t btree_csum_set(struct btree *b, struct bset *i)
uint64_t crc = b->key.ptr[0];
void *data = (void *) i + 8, *end = bset_bkey_last(i);
- crc = bch_crc64_update(crc, data, end - data);
+ crc = crc64_be(crc, data, end - data);
return crc ^ 0xffffffffffffffffULL;
}
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 116edda845c3..6230dfdd9286 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -127,21 +127,20 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
citer.bi_size = UINT_MAX;
bio_for_each_segment(bv, bio, iter) {
- void *p1 = kmap_atomic(bv.bv_page);
+ void *p1 = bvec_kmap_local(&bv);
void *p2;
cbv = bio_iter_iovec(check, citer);
- p2 = page_address(cbv.bv_page);
+ p2 = bvec_kmap_local(&cbv);
- cache_set_err_on(memcmp(p1 + bv.bv_offset,
- p2 + bv.bv_offset,
- bv.bv_len),
+ cache_set_err_on(memcmp(p1, p2, bv.bv_len),
dc->disk.c,
- "verify failed at dev %s sector %llu",
- dc->backing_dev_name,
+ "verify failed at dev %pg sector %llu",
+ dc->bdev,
(uint64_t) bio->bi_iter.bi_sector);
- kunmap_atomic(p1);
+ kunmap_local(p2);
+ kunmap_local(p1);
bio_advance_iter(check, &citer, bv.bv_len);
}
diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c
index 6d2b7b84a7b7..634922c5601d 100644
--- a/drivers/md/bcache/features.c
+++ b/drivers/md/bcache/features.c
@@ -6,7 +6,7 @@
* Copyright 2020 Coly Li <colyli@suse.de>
*
*/
-#include <linux/bcache.h>
+#include "bcache_ondisk.h"
#include "bcache.h"
#include "features.h"
diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h
index d1c8fd3977fc..09161b89c63e 100644
--- a/drivers/md/bcache/features.h
+++ b/drivers/md/bcache/features.h
@@ -2,10 +2,11 @@
#ifndef _BCACHE_FEATURES_H
#define _BCACHE_FEATURES_H
-#include <linux/bcache.h>
#include <linux/kernel.h>
#include <linux/types.h>
+#include "bcache_ondisk.h"
+
#define BCH_FEATURE_COMPAT 0
#define BCH_FEATURE_RO_COMPAT 1
#define BCH_FEATURE_INCOMPAT 2
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index e4388fe3ab7e..9c6f9ec55b72 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -65,15 +65,15 @@ void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
* we shouldn't count failed REQ_RAHEAD bio to dc->io_errors.
*/
if (bio->bi_opf & REQ_RAHEAD) {
- pr_warn_ratelimited("%s: Read-ahead I/O failed on backing device, ignore\n",
- dc->backing_dev_name);
+ pr_warn_ratelimited("%pg: Read-ahead I/O failed on backing device, ignore\n",
+ dc->bdev);
return;
}
errors = atomic_add_return(1, &dc->io_errors);
if (errors < dc->error_limit)
- pr_err("%s: IO error on backing device, unrecoverable\n",
- dc->backing_dev_name);
+ pr_err("%pg: IO error on backing device, unrecoverable\n",
+ dc->bdev);
else
bch_cached_dev_error(dc);
}
@@ -123,13 +123,13 @@ void bch_count_io_errors(struct cache *ca,
errors >>= IO_ERROR_SHIFT;
if (errors < ca->set->error_limit)
- pr_err("%s: IO error on %s%s\n",
- ca->cache_dev_name, m,
+ pr_err("%pg: IO error on %s%s\n",
+ ca->bdev, m,
is_read ? ", recovering." : ".");
else
bch_cache_set_error(ca->set,
- "%s: too many IO errors %s\n",
- ca->cache_dev_name, m);
+ "%pg: too many IO errors %s\n",
+ ca->bdev, m);
}
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 6d1de889baeb..d15aae6c51c1 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -46,7 +46,7 @@ static void bio_csum(struct bio *bio, struct bkey *k)
bio_for_each_segment(bv, bio, iter) {
void *d = kmap(bv.bv_page) + bv.bv_offset;
- csum = bch_crc64_update(csum, d, bv.bv_len);
+ csum = crc64_be(csum, d, bv.bv_len);
kunmap(bv.bv_page);
}
@@ -651,8 +651,8 @@ static void backing_request_endio(struct bio *bio)
*/
if (unlikely(s->iop.writeback &&
bio->bi_opf & REQ_PREFLUSH)) {
- pr_err("Can't flush %s: returned bi_status %i\n",
- dc->backing_dev_name, bio->bi_status);
+ pr_err("Can't flush %pg: returned bi_status %i\n",
+ dc->bdev, bio->bi_status);
} else {
/* set to orig_bio->bi_status in bio_complete() */
s->iop.status = bio->bi_status;
@@ -1163,7 +1163,7 @@ static void quit_max_writeback_rate(struct cache_set *c,
/* Cached devices - read & write stuff */
-blk_qc_t cached_dev_submit_bio(struct bio *bio)
+void cached_dev_submit_bio(struct bio *bio)
{
struct search *s;
struct block_device *orig_bdev = bio->bi_bdev;
@@ -1176,7 +1176,7 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
dc->io_disable)) {
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
- return BLK_QC_T_NONE;
+ return;
}
if (likely(d->c)) {
@@ -1222,8 +1222,6 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
} else
/* I/O request sent to backing device */
detached_dev_do_request(d, bio, orig_bdev, start_time);
-
- return BLK_QC_T_NONE;
}
static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
@@ -1273,7 +1271,7 @@ static void flash_dev_nodata(struct closure *cl)
continue_at(cl, search_free, NULL);
}
-blk_qc_t flash_dev_submit_bio(struct bio *bio)
+void flash_dev_submit_bio(struct bio *bio)
{
struct search *s;
struct closure *cl;
@@ -1282,7 +1280,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
- return BLK_QC_T_NONE;
+ return;
}
s = search_alloc(bio, d, bio->bi_bdev, bio_start_io_acct(bio));
@@ -1298,7 +1296,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
continue_at_nobarrier(&s->cl,
flash_dev_nodata,
bcache_wq);
- return BLK_QC_T_NONE;
+ return;
} else if (bio_data_dir(bio)) {
bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
&KEY(d->id, bio->bi_iter.bi_sector, 0),
@@ -1314,7 +1312,6 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
}
continue_at(cl, search_free, NULL);
- return BLK_QC_T_NONE;
}
static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 82b38366a95d..38ab4856eaab 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -37,10 +37,10 @@ unsigned int bch_get_congested(const struct cache_set *c);
void bch_data_insert(struct closure *cl);
void bch_cached_dev_request_init(struct cached_dev *dc);
-blk_qc_t cached_dev_submit_bio(struct bio *bio);
+void cached_dev_submit_bio(struct bio *bio);
void bch_flash_dev_request_init(struct bcache_device *d);
-blk_qc_t flash_dev_submit_bio(struct bio *bio);
+void flash_dev_submit_bio(struct bio *bio);
extern struct kmem_cache *bch_search_cache;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index f2874c77ff79..4a9a65dff95e 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1002,7 +1002,7 @@ static void calc_cached_dev_sectors(struct cache_set *c)
struct cached_dev *dc;
list_for_each_entry(dc, &c->cached_devs, list)
- sectors += bdev_sectors(dc->bdev);
+ sectors += bdev_nr_sectors(dc->bdev);
c->cached_dev_sectors = sectors;
}
@@ -1026,8 +1026,8 @@ static int cached_dev_status_update(void *arg)
dc->offline_seconds = 0;
if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) {
- pr_err("%s: device offline for %d seconds\n",
- dc->backing_dev_name,
+ pr_err("%pg: device offline for %d seconds\n",
+ dc->bdev,
BACKING_DEV_OFFLINE_TIMEOUT);
pr_err("%s: disable I/O request due to backing device offline\n",
dc->disk.name);
@@ -1058,15 +1058,13 @@ int bch_cached_dev_run(struct cached_dev *dc)
};
if (dc->io_disable) {
- pr_err("I/O disabled on cached dev %s\n",
- dc->backing_dev_name);
+ pr_err("I/O disabled on cached dev %pg\n", dc->bdev);
ret = -EIO;
goto out;
}
if (atomic_xchg(&dc->running, 1)) {
- pr_info("cached dev %s is running already\n",
- dc->backing_dev_name);
+ pr_info("cached dev %pg is running already\n", dc->bdev);
ret = -EBUSY;
goto out;
}
@@ -1082,7 +1080,9 @@ int bch_cached_dev_run(struct cached_dev *dc)
closure_sync(&cl);
}
- add_disk(d->disk);
+ ret = add_disk(d->disk);
+ if (ret)
+ goto out;
bd_link_disk_holder(dc->bdev, dc->disk.disk);
/*
* won't show up in the uevent file, use udevadm monitor -e instead
@@ -1154,16 +1154,16 @@ static void cached_dev_detach_finish(struct work_struct *w)
mutex_lock(&bch_register_lock);
- calc_cached_dev_sectors(dc->disk.c);
bcache_device_detach(&dc->disk);
list_move(&dc->list, &uncached_devices);
+ calc_cached_dev_sectors(dc->disk.c);
clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags);
clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags);
mutex_unlock(&bch_register_lock);
- pr_info("Caching disabled for %s\n", dc->backing_dev_name);
+ pr_info("Caching disabled for %pg\n", dc->bdev);
/* Drop ref we took in cached_dev_detach() */
closure_put(&dc->disk.cl);
@@ -1203,29 +1203,27 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
return -ENOENT;
if (dc->disk.c) {
- pr_err("Can't attach %s: already attached\n",
- dc->backing_dev_name);
+ pr_err("Can't attach %pg: already attached\n", dc->bdev);
return -EINVAL;
}
if (test_bit(CACHE_SET_STOPPING, &c->flags)) {
- pr_err("Can't attach %s: shutting down\n",
- dc->backing_dev_name);
+ pr_err("Can't attach %pg: shutting down\n", dc->bdev);
return -EINVAL;
}
if (dc->sb.block_size < c->cache->sb.block_size) {
/* Will die */
- pr_err("Couldn't attach %s: block size less than set's block size\n",
- dc->backing_dev_name);
+ pr_err("Couldn't attach %pg: block size less than set's block size\n",
+ dc->bdev);
return -EINVAL;
}
/* Check whether already attached */
list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
- pr_err("Tried to attach %s but duplicate UUID already attached\n",
- dc->backing_dev_name);
+ pr_err("Tried to attach %pg but duplicate UUID already attached\n",
+ dc->bdev);
return -EINVAL;
}
@@ -1243,15 +1241,13 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
if (!u) {
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
- pr_err("Couldn't find uuid for %s in set\n",
- dc->backing_dev_name);
+ pr_err("Couldn't find uuid for %pg in set\n", dc->bdev);
return -ENOENT;
}
u = uuid_find_empty(c);
if (!u) {
- pr_err("Not caching %s, no room for UUID\n",
- dc->backing_dev_name);
+ pr_err("Not caching %pg, no room for UUID\n", dc->bdev);
return -EINVAL;
}
}
@@ -1319,8 +1315,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
*/
kthread_stop(dc->writeback_thread);
cancel_writeback_rate_update_dwork(dc);
- pr_err("Couldn't run cached device %s\n",
- dc->backing_dev_name);
+ pr_err("Couldn't run cached device %pg\n", dc->bdev);
return ret;
}
@@ -1336,8 +1331,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
/* Allow the writeback thread to proceed */
up_write(&dc->writeback_lock);
- pr_info("Caching %s as %s on set %pU\n",
- dc->backing_dev_name,
+ pr_info("Caching %pg as %s on set %pU\n",
+ dc->bdev,
dc->disk.disk->disk_name,
dc->disk.c->set_uuid);
return 0;
@@ -1461,7 +1456,6 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
struct cache_set *c;
int ret = -ENOMEM;
- bdevname(bdev, dc->backing_dev_name);
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
dc->bdev = bdev;
dc->bdev->bd_holder = dc;
@@ -1476,7 +1470,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
goto err;
- pr_info("registered backing device %s\n", dc->backing_dev_name);
+ pr_info("registered backing device %pg\n", dc->bdev);
list_add(&dc->list, &uncached_devices);
/* attach to a matched cache set if it exists */
@@ -1493,7 +1487,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
return 0;
err:
- pr_notice("error %s: %s\n", dc->backing_dev_name, err);
+ pr_notice("error %pg: %s\n", dc->bdev, err);
bcache_device_stop(&dc->disk);
return ret;
}
@@ -1534,10 +1528,11 @@ static void flash_dev_flush(struct closure *cl)
static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
{
+ int err = -ENOMEM;
struct bcache_device *d = kzalloc(sizeof(struct bcache_device),
GFP_KERNEL);
if (!d)
- return -ENOMEM;
+ goto err_ret;
closure_init(&d->cl, NULL);
set_closure_fn(&d->cl, flash_dev_flush, system_wq);
@@ -1551,9 +1546,12 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
bcache_device_attach(d, c, u - c->uuids);
bch_sectors_dirty_init(d);
bch_flash_dev_request_init(d);
- add_disk(d->disk);
+ err = add_disk(d->disk);
+ if (err)
+ goto err;
- if (kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache"))
+ err = kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache");
+ if (err)
goto err;
bcache_device_link(d, c, "volume");
@@ -1567,7 +1565,8 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
return 0;
err:
kobject_put(&d->kobj);
- return -ENOMEM;
+err_ret:
+ return err;
}
static int flash_devs_run(struct cache_set *c)
@@ -1621,8 +1620,8 @@ bool bch_cached_dev_error(struct cached_dev *dc)
/* make others know io_disable is true earlier */
smp_mb();
- pr_err("stop %s: too many IO errors on backing device %s\n",
- dc->disk.disk->disk_name, dc->backing_dev_name);
+ pr_err("stop %s: too many IO errors on backing device %pg\n",
+ dc->disk.disk->disk_name, dc->bdev);
bcache_device_stop(&dc->disk);
return true;
@@ -2338,7 +2337,7 @@ err_btree_alloc:
err_free:
module_put(THIS_MODULE);
if (err)
- pr_notice("error %s: %s\n", ca->cache_dev_name, err);
+ pr_notice("error %pg: %s\n", ca->bdev, err);
return ret;
}
@@ -2348,7 +2347,6 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
const char *err = NULL; /* must be set for any error case */
int ret = 0;
- bdevname(bdev, ca->cache_dev_name);
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->bdev = bdev;
ca->bdev->bd_holder = ca;
@@ -2390,14 +2388,14 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
goto out;
}
- pr_info("registered cache device %s\n", ca->cache_dev_name);
+ pr_info("registered cache device %pg\n", ca->bdev);
out:
kobject_put(&ca->kobj);
err:
if (err)
- pr_notice("error %s: %s\n", ca->cache_dev_name, err);
+ pr_notice("error %pg: %s\n", ca->bdev, err);
return ret;
}
@@ -2617,8 +2615,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (SB_IS_BDEV(sb)) {
struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
- if (!dc)
+ if (!dc) {
+ ret = -ENOMEM;
+ err = "cannot allocate memory";
goto out_put_sb_page;
+ }
mutex_lock(&bch_register_lock);
ret = register_bdev(sb, sb_disk, bdev, dc);
@@ -2629,11 +2630,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
} else {
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
- if (!ca)
+ if (!ca) {
+ ret = -ENOMEM;
+ err = "cannot allocate memory";
goto out_put_sb_page;
+ }
/* blkdev_put() will be called in bch_cache_release() */
- if (register_cache(sb, sb_disk, bdev, ca) != 0)
+ ret = register_cache(sb, sb_disk, bdev, ca);
+ if (ret)
goto out_free_sb;
}
@@ -2750,7 +2755,7 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
* The reason bch_register_lock is not held to call
* bch_cache_set_stop() and bcache_device_stop() is to
* avoid potential deadlock during reboot, because cache
- * set or bcache device stopping process will acqurie
+ * set or bcache device stopping process will acquire
* bch_register_lock too.
*
* We are safe here because bcache_is_reboot sets to
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 05ac1d6fbbf3..1f0dce30fa75 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -271,7 +271,7 @@ SHOW(__bch_cached_dev)
}
if (attr == &sysfs_backing_dev_name) {
- snprintf(buf, BDEVNAME_SIZE + 1, "%s", dc->backing_dev_name);
+ snprintf(buf, BDEVNAME_SIZE + 1, "%pg", dc->bdev);
strcat(buf, "\n");
return strlen(buf);
}
diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h
index 215df32f567b..c1752ba2e05b 100644
--- a/drivers/md/bcache/sysfs.h
+++ b/drivers/md/bcache/sysfs.h
@@ -51,13 +51,27 @@ STORE(fn) \
#define sysfs_printf(file, fmt, ...) \
do { \
if (attr == &sysfs_ ## file) \
- return snprintf(buf, PAGE_SIZE, fmt "\n", __VA_ARGS__); \
+ return sysfs_emit(buf, fmt "\n", __VA_ARGS__); \
} while (0)
#define sysfs_print(file, var) \
do { \
if (attr == &sysfs_ ## file) \
- return snprint(buf, PAGE_SIZE, var); \
+ return sysfs_emit(buf, \
+ __builtin_types_compatible_p(typeof(var), int) \
+ ? "%i\n" : \
+ __builtin_types_compatible_p(typeof(var), unsigned int) \
+ ? "%u\n" : \
+ __builtin_types_compatible_p(typeof(var), long) \
+ ? "%li\n" : \
+ __builtin_types_compatible_p(typeof(var), unsigned long)\
+ ? "%lu\n" : \
+ __builtin_types_compatible_p(typeof(var), int64_t) \
+ ? "%lli\n" : \
+ __builtin_types_compatible_p(typeof(var), uint64_t) \
+ ? "%llu\n" : \
+ __builtin_types_compatible_p(typeof(var), const char *) \
+ ? "%s\n" : "%i\n", var); \
} while (0)
#define sysfs_hprint(file, val) \
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index b64460a76267..6f3cb7c92130 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -340,23 +340,6 @@ static inline int bch_strtoul_h(const char *cp, long *res)
_r; \
})
-#define snprint(buf, size, var) \
- snprintf(buf, size, \
- __builtin_types_compatible_p(typeof(var), int) \
- ? "%i\n" : \
- __builtin_types_compatible_p(typeof(var), unsigned int) \
- ? "%u\n" : \
- __builtin_types_compatible_p(typeof(var), long) \
- ? "%li\n" : \
- __builtin_types_compatible_p(typeof(var), unsigned long)\
- ? "%lu\n" : \
- __builtin_types_compatible_p(typeof(var), int64_t) \
- ? "%lli\n" : \
- __builtin_types_compatible_p(typeof(var), uint64_t) \
- ? "%llu\n" : \
- __builtin_types_compatible_p(typeof(var), const char *) \
- ? "%s\n" : "%i\n", var)
-
ssize_t bch_hprint(char *buf, int64_t v);
bool bch_is_zero(const char *p, size_t n);
@@ -548,14 +531,6 @@ static inline uint64_t bch_crc64(const void *p, size_t len)
return crc ^ 0xffffffffffffffffULL;
}
-static inline uint64_t bch_crc64_update(uint64_t crc,
- const void *p,
- size_t len)
-{
- crc = crc64_be(crc, p, len);
- return crc;
-}
-
/*
* A stepwise-linear pseudo-exponential. This returns 1 << (x >>
* frac_bits), with the less-significant bits filled in by linear
@@ -584,8 +559,4 @@ static inline unsigned int fract_exp_two(unsigned int x,
void bch_bio_map(struct bio *bio, void *base);
int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp_mask);
-static inline sector_t bdev_sectors(struct block_device *bdev)
-{
- return bdev->bd_inode->i_size >> 9;
-}
#endif /* _BCACHE_UTIL_H */
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 8120da278161..c7560f66dca8 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -45,7 +45,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc)
* backing volume uses about 2% of the cache for dirty data.
*/
uint32_t bdev_share =
- div64_u64(bdev_sectors(dc->bdev) << WRITEBACK_SHARE_SHIFT,
+ div64_u64(bdev_nr_sectors(dc->bdev) << WRITEBACK_SHARE_SHIFT,
c->cached_dev_sectors);
uint64_t cache_dirty_target =
diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h
index a3b71350eec8..745e3ab4aa0a 100644
--- a/drivers/md/dm-bio-record.h
+++ b/drivers/md/dm-bio-record.h
@@ -8,6 +8,7 @@
#define DM_BIO_RECORD_H
#include <linux/bio.h>
+#include <linux/blk-integrity.h>
/*
* There are lots of mutable fields in the bio struct that get
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 50f3e673729c..104ebc1f08dc 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1525,7 +1525,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_get_block_size);
sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
{
- sector_t s = i_size_read(c->bdev->bd_inode) >> SECTOR_SHIFT;
+ sector_t s = bdev_nr_sectors(c->bdev);
if (s >= c->start)
s -= c->start;
else
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 89a73204dbf4..2874f222c313 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -334,7 +334,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
int r;
struct dm_block *sblock;
struct cache_disk_superblock *disk_super;
- sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT;
+ sector_t bdev_size = bdev_nr_sectors(cmd->bdev);
/* FIXME: see if we can lose the max sectors limit */
if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index bdd500447dea..447d030036d1 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -1940,7 +1940,7 @@ static void cache_dtr(struct dm_target *ti)
static sector_t get_dev_size(struct dm_dev *dev)
{
- return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ return bdev_nr_sectors(dev->bdev);
}
/*----------------------------------------------------------------*/
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index edd22e4d65df..4599632d7a84 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -1514,7 +1514,7 @@ error:
static sector_t get_dev_size(struct dm_dev *dev)
{
- return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ return bdev_nr_sectors(dev->bdev);
}
/*---------------------------------------------------------------------------*/
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 55dccdfbcb22..b855fef4f38a 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -13,7 +13,7 @@
#include <linux/ktime.h>
#include <linux/genhd.h>
#include <linux/blk-mq.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include <trace/events/block.h>
@@ -200,7 +200,7 @@ struct dm_table {
struct dm_md_mempools *mempools;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- struct blk_keyslot_manager *ksm;
+ struct blk_crypto_profile *crypto_profile;
#endif
};
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 916b7da16de2..292f7896f733 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -15,6 +15,7 @@
#include <linux/key.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/crypto.h>
diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c
index 3163e2b1418e..03672204b0e3 100644
--- a/drivers/md/dm-dust.c
+++ b/drivers/md/dm-dust.c
@@ -415,7 +415,7 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
char *result, unsigned int maxlen)
{
struct dust_device *dd = ti->private;
- sector_t size = i_size_read(dd->dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ sector_t size = bdev_nr_sectors(dd->dev->bdev);
bool invalid_msg = false;
int r = -EINVAL;
unsigned long long tmp, block;
@@ -544,8 +544,7 @@ static int dust_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (dd->start ||
- ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
+ if (dd->start || ti->len != bdev_nr_sectors(dev->bdev))
return 1;
return 0;
diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c
index d25989660a76..7ce5d509b940 100644
--- a/drivers/md/dm-ebs-target.c
+++ b/drivers/md/dm-ebs-target.c
@@ -416,7 +416,7 @@ static int ebs_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
* Only pass ioctls through if the device sizes match exactly.
*/
*bdev = dev->bdev;
- return !!(ec->start || ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT);
+ return !!(ec->start || ti->len != bdev_nr_sectors(dev->bdev));
}
static void ebs_io_hints(struct dm_target *ti, struct queue_limits *limits)
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 2a78f6874143..1f6bf152b3c7 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1681,7 +1681,7 @@ static int era_message(struct dm_target *ti, unsigned argc, char **argv,
static sector_t get_dev_size(struct dm_dev *dev)
{
- return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ return bdev_nr_sectors(dev->bdev);
}
static int era_iterate_devices(struct dm_target *ti,
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index 3f4139ac1f60..b5f20eba3641 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -168,7 +168,7 @@ static inline void dm_consecutive_chunk_count_dec(struct dm_exception *e)
*/
static inline sector_t get_dev_size(struct block_device *bdev)
{
- return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ return bdev_nr_sectors(bdev);
}
static inline chunk_t sector_to_chunk(struct dm_exception_store *store,
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 4b94ffe6f2d4..345229d7e59c 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -456,8 +456,7 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (fc->start ||
- ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ if (fc->start || ti->len != bdev_nr_sectors((*bdev)))
return 1;
return 0;
}
diff --git a/drivers/md/dm-ima.c b/drivers/md/dm-ima.c
index 2c5edfbd7711..957999998d70 100644
--- a/drivers/md/dm-ima.c
+++ b/drivers/md/dm-ima.c
@@ -12,6 +12,7 @@
#include "dm-ima.h"
#include <linux/ima.h>
+#include <linux/sched/mm.h>
#include <crypto/hash.h>
#include <linux/crypto.h>
#include <crypto/hash_info.h>
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index dc03b70f6e65..d0f788e72abf 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -4113,11 +4113,11 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
}
}
- ic->data_device_sectors = i_size_read(ic->dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ ic->data_device_sectors = bdev_nr_sectors(ic->dev->bdev);
if (!ic->meta_dev)
ic->meta_device_sectors = ic->data_device_sectors;
else
- ic->meta_device_sectors = i_size_read(ic->meta_dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ ic->meta_device_sectors = bdev_nr_sectors(ic->meta_dev->bdev);
if (!journal_sectors) {
journal_sectors = min((sector_t)DEFAULT_MAX_JOURNAL_SECTORS,
@@ -4367,7 +4367,7 @@ try_smaller_buffer:
DEBUG_print(" journal_sections %u\n", (unsigned)le32_to_cpu(ic->sb->journal_sections));
DEBUG_print(" journal_entries %u\n", ic->journal_entries);
DEBUG_print(" log2_interleave_sectors %d\n", ic->sb->log2_interleave_sectors);
- DEBUG_print(" data_device_sectors 0x%llx\n", i_size_read(ic->dev->bdev->bd_inode) >> SECTOR_SHIFT);
+ DEBUG_print(" data_device_sectors 0x%llx\n", bdev_nr_sectors(ic->dev->bdev));
DEBUG_print(" initial_sectors 0x%x\n", ic->initial_sectors);
DEBUG_print(" metadata_run 0x%x\n", ic->metadata_run);
DEBUG_print(" log2_metadata_run %d\n", ic->log2_metadata_run);
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 679b4c0a2eea..66ba16713f69 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -135,8 +135,7 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (lc->start ||
- ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
+ if (lc->start || ti->len != bdev_nr_sectors(dev->bdev))
return 1;
return 0;
}
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index d93a4db23512..46de085a9670 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -446,7 +446,7 @@ static int log_super(struct log_writes_c *lc)
static inline sector_t logdev_last_sector(struct log_writes_c *lc)
{
- return i_size_read(lc->logdev->bdev->bd_inode) >> SECTOR_SHIFT;
+ return bdev_nr_sectors(lc->logdev->bdev);
}
static int log_writes_kthread(void *arg)
@@ -851,7 +851,7 @@ static int log_writes_prepare_ioctl(struct dm_target *ti,
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
+ if (ti->len != bdev_nr_sectors(dev->bdev))
return 1;
return 0;
}
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 1ecf75ef276a..06f328928a7f 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -447,7 +447,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
bdev_logical_block_size(lc->header_location.
bdev));
- if (buf_size > i_size_read(dev->bdev->bd_inode)) {
+ if (buf_size > bdev_nr_bytes(dev->bdev)) {
DMWARN("log device %s too small: need %llu bytes",
dev->name, (unsigned long long)buf_size);
kfree(lc);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 694aaca4eea2..90dc9cc48881 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -530,7 +530,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
bdev = pgpath->path.dev->bdev;
q = bdev_get_queue(bdev);
- clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE,
+ clone = blk_mq_alloc_request(q, rq->cmd_flags | REQ_NOMERGE,
BLK_MQ_REQ_NOWAIT);
if (IS_ERR(clone)) {
/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
@@ -579,7 +579,7 @@ static void multipath_release_clone(struct request *clone,
clone->io_start_time_ns);
}
- blk_put_request(clone);
+ blk_mq_free_request(clone);
}
/*
@@ -2061,7 +2061,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (!r && ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ if (!r && ti->len != bdev_nr_sectors((*bdev)))
return 1;
return r;
}
diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c
index 1856a1b125cc..875bca30a0dd 100644
--- a/drivers/md/dm-ps-historical-service-time.c
+++ b/drivers/md/dm-ps-historical-service-time.c
@@ -27,6 +27,7 @@
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/sched/clock.h>
#define DM_MSG_PREFIX "multipath historical-service-time"
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index d9ef52159a22..2b26435a6946 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1261,7 +1261,7 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
md_rdev_init(jdev);
jdev->mddev = &rs->md;
jdev->bdev = rs->journal_dev.dev->bdev;
- jdev->sectors = to_sector(i_size_read(jdev->bdev->bd_inode));
+ jdev->sectors = bdev_nr_sectors(jdev->bdev);
if (jdev->sectors < MIN_RAID456_JOURNAL_SPACE) {
rs->ti->error = "No space for raid4/5/6 journal";
return -ENOSPC;
@@ -1607,7 +1607,7 @@ static int _check_data_dev_sectors(struct raid_set *rs)
rdev_for_each(rdev, &rs->md)
if (!test_bit(Journal, &rdev->flags) && rdev->bdev) {
- ds = min(ds, to_sector(i_size_read(rdev->bdev->bd_inode)));
+ ds = min(ds, bdev_nr_sectors(rdev->bdev));
if (ds < rs->md.dev_sectors) {
rs->ti->error = "Component device(s) too small";
return -EINVAL;
@@ -2662,7 +2662,7 @@ static int rs_adjust_data_offsets(struct raid_set *rs)
* Make sure we got a minimum amount of free sectors per device
*/
if (rs->data_offset &&
- to_sector(i_size_read(rdev->bdev->bd_inode)) - rs->md.dev_sectors < MIN_FREE_RESHAPE_SPACE) {
+ bdev_nr_sectors(rdev->bdev) - rs->md.dev_sectors < MIN_FREE_RESHAPE_SPACE) {
rs->ti->error = data_offset ? "No space for forward reshape" :
"No space for backward reshape";
return -ENOSPC;
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index a896dea9750e..579ab6183d4d 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -7,7 +7,6 @@
#include "dm-core.h"
#include "dm-rq.h"
-#include <linux/elevator.h> /* for rq_end_sector() */
#include <linux/blk-mq.h>
#define DM_MSG_PREFIX "core-rq"
diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c
index 028a92ff6d57..534dc2ca8bb0 100644
--- a/drivers/md/dm-switch.c
+++ b/drivers/md/dm-switch.c
@@ -529,7 +529,7 @@ static int switch_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
* Only pass ioctls through if the device sizes match exactly.
*/
if (ti->len + sctx->path_list[path_nr].start !=
- i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ bdev_nr_sectors((*bdev)))
return 1;
return 0;
}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 2111daaacaba..bcddc5effd15 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/string.h>
@@ -169,7 +170,7 @@ static void free_devices(struct list_head *devices, struct mapped_device *md)
}
}
-static void dm_table_destroy_keyslot_manager(struct dm_table *t);
+static void dm_table_destroy_crypto_profile(struct dm_table *t);
void dm_table_destroy(struct dm_table *t)
{
@@ -199,7 +200,7 @@ void dm_table_destroy(struct dm_table *t)
dm_free_md_mempools(t->mempools);
- dm_table_destroy_keyslot_manager(t);
+ dm_table_destroy_crypto_profile(t);
kfree(t);
}
@@ -226,8 +227,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
{
struct queue_limits *limits = data;
struct block_device *bdev = dev->bdev;
- sector_t dev_size =
- i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ sector_t dev_size = bdev_nr_sectors(bdev);
unsigned short logical_block_size_sectors =
limits->logical_block_size >> SECTOR_SHIFT;
char b[BDEVNAME_SIZE];
@@ -1186,8 +1186,8 @@ static int dm_table_register_integrity(struct dm_table *t)
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-struct dm_keyslot_manager {
- struct blk_keyslot_manager ksm;
+struct dm_crypto_profile {
+ struct blk_crypto_profile profile;
struct mapped_device *md;
};
@@ -1213,13 +1213,11 @@ static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev,
* When an inline encryption key is evicted from a device-mapper device, evict
* it from all the underlying devices.
*/
-static int dm_keyslot_evict(struct blk_keyslot_manager *ksm,
+static int dm_keyslot_evict(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key, unsigned int slot)
{
- struct dm_keyslot_manager *dksm = container_of(ksm,
- struct dm_keyslot_manager,
- ksm);
- struct mapped_device *md = dksm->md;
+ struct mapped_device *md =
+ container_of(profile, struct dm_crypto_profile, profile)->md;
struct dm_keyslot_evict_args args = { key };
struct dm_table *t;
int srcu_idx;
@@ -1239,150 +1237,148 @@ static int dm_keyslot_evict(struct blk_keyslot_manager *ksm,
return args.err;
}
-static const struct blk_ksm_ll_ops dm_ksm_ll_ops = {
- .keyslot_evict = dm_keyslot_evict,
-};
-
-static int device_intersect_crypto_modes(struct dm_target *ti,
- struct dm_dev *dev, sector_t start,
- sector_t len, void *data)
+static int
+device_intersect_crypto_capabilities(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
{
- struct blk_keyslot_manager *parent = data;
- struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm;
+ struct blk_crypto_profile *parent = data;
+ struct blk_crypto_profile *child =
+ bdev_get_queue(dev->bdev)->crypto_profile;
- blk_ksm_intersect_modes(parent, child);
+ blk_crypto_intersect_capabilities(parent, child);
return 0;
}
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile)
{
- struct dm_keyslot_manager *dksm = container_of(ksm,
- struct dm_keyslot_manager,
- ksm);
+ struct dm_crypto_profile *dmcp = container_of(profile,
+ struct dm_crypto_profile,
+ profile);
- if (!ksm)
+ if (!profile)
return;
- blk_ksm_destroy(ksm);
- kfree(dksm);
+ blk_crypto_profile_destroy(profile);
+ kfree(dmcp);
}
-static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+static void dm_table_destroy_crypto_profile(struct dm_table *t)
{
- dm_destroy_keyslot_manager(t->ksm);
- t->ksm = NULL;
+ dm_destroy_crypto_profile(t->crypto_profile);
+ t->crypto_profile = NULL;
}
/*
- * Constructs and initializes t->ksm with a keyslot manager that
- * represents the common set of crypto capabilities of the devices
- * described by the dm_table. However, if the constructed keyslot
- * manager does not support a superset of the crypto capabilities
- * supported by the current keyslot manager of the mapped_device,
- * it returns an error instead, since we don't support restricting
- * crypto capabilities on table changes. Finally, if the constructed
- * keyslot manager doesn't actually support any crypto modes at all,
- * it just returns NULL.
+ * Constructs and initializes t->crypto_profile with a crypto profile that
+ * represents the common set of crypto capabilities of the devices described by
+ * the dm_table. However, if the constructed crypto profile doesn't support all
+ * crypto capabilities that are supported by the current mapped_device, it
+ * returns an error instead, since we don't support removing crypto capabilities
+ * on table changes. Finally, if the constructed crypto profile is "empty" (has
+ * no crypto capabilities at all), it just sets t->crypto_profile to NULL.
*/
-static int dm_table_construct_keyslot_manager(struct dm_table *t)
+static int dm_table_construct_crypto_profile(struct dm_table *t)
{
- struct dm_keyslot_manager *dksm;
- struct blk_keyslot_manager *ksm;
+ struct dm_crypto_profile *dmcp;
+ struct blk_crypto_profile *profile;
struct dm_target *ti;
unsigned int i;
- bool ksm_is_empty = true;
+ bool empty_profile = true;
- dksm = kmalloc(sizeof(*dksm), GFP_KERNEL);
- if (!dksm)
+ dmcp = kmalloc(sizeof(*dmcp), GFP_KERNEL);
+ if (!dmcp)
return -ENOMEM;
- dksm->md = t->md;
+ dmcp->md = t->md;
- ksm = &dksm->ksm;
- blk_ksm_init_passthrough(ksm);
- ksm->ksm_ll_ops = dm_ksm_ll_ops;
- ksm->max_dun_bytes_supported = UINT_MAX;
- memset(ksm->crypto_modes_supported, 0xFF,
- sizeof(ksm->crypto_modes_supported));
+ profile = &dmcp->profile;
+ blk_crypto_profile_init(profile, 0);
+ profile->ll_ops.keyslot_evict = dm_keyslot_evict;
+ profile->max_dun_bytes_supported = UINT_MAX;
+ memset(profile->modes_supported, 0xFF,
+ sizeof(profile->modes_supported));
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!dm_target_passes_crypto(ti->type)) {
- blk_ksm_intersect_modes(ksm, NULL);
+ blk_crypto_intersect_capabilities(profile, NULL);
break;
}
if (!ti->type->iterate_devices)
continue;
- ti->type->iterate_devices(ti, device_intersect_crypto_modes,
- ksm);
+ ti->type->iterate_devices(ti,
+ device_intersect_crypto_capabilities,
+ profile);
}
- if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) {
+ if (t->md->queue &&
+ !blk_crypto_has_capabilities(profile,
+ t->md->queue->crypto_profile)) {
DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!");
- dm_destroy_keyslot_manager(ksm);
+ dm_destroy_crypto_profile(profile);
return -EINVAL;
}
/*
- * If the new KSM doesn't actually support any crypto modes, we may as
- * well represent it with a NULL ksm.
+ * If the new profile doesn't actually support any crypto capabilities,
+ * we may as well represent it with a NULL profile.
*/
- ksm_is_empty = true;
- for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) {
- if (ksm->crypto_modes_supported[i]) {
- ksm_is_empty = false;
+ for (i = 0; i < ARRAY_SIZE(profile->modes_supported); i++) {
+ if (profile->modes_supported[i]) {
+ empty_profile = false;
break;
}
}
- if (ksm_is_empty) {
- dm_destroy_keyslot_manager(ksm);
- ksm = NULL;
+ if (empty_profile) {
+ dm_destroy_crypto_profile(profile);
+ profile = NULL;
}
/*
- * t->ksm is only set temporarily while the table is being set
- * up, and it gets set to NULL after the capabilities have
- * been transferred to the request_queue.
+ * t->crypto_profile is only set temporarily while the table is being
+ * set up, and it gets set to NULL after the profile has been
+ * transferred to the request_queue.
*/
- t->ksm = ksm;
+ t->crypto_profile = profile;
return 0;
}
-static void dm_update_keyslot_manager(struct request_queue *q,
- struct dm_table *t)
+static void dm_update_crypto_profile(struct request_queue *q,
+ struct dm_table *t)
{
- if (!t->ksm)
+ if (!t->crypto_profile)
return;
- /* Make the ksm less restrictive */
- if (!q->ksm) {
- blk_ksm_register(t->ksm, q);
+ /* Make the crypto profile less restrictive. */
+ if (!q->crypto_profile) {
+ blk_crypto_register(t->crypto_profile, q);
} else {
- blk_ksm_update_capabilities(q->ksm, t->ksm);
- dm_destroy_keyslot_manager(t->ksm);
+ blk_crypto_update_capabilities(q->crypto_profile,
+ t->crypto_profile);
+ dm_destroy_crypto_profile(t->crypto_profile);
}
- t->ksm = NULL;
+ t->crypto_profile = NULL;
}
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static int dm_table_construct_keyslot_manager(struct dm_table *t)
+static int dm_table_construct_crypto_profile(struct dm_table *t)
{
return 0;
}
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile)
{
}
-static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+static void dm_table_destroy_crypto_profile(struct dm_table *t)
{
}
-static void dm_update_keyslot_manager(struct request_queue *q,
- struct dm_table *t)
+static void dm_update_crypto_profile(struct request_queue *q,
+ struct dm_table *t)
{
}
@@ -1414,9 +1410,9 @@ int dm_table_complete(struct dm_table *t)
return r;
}
- r = dm_table_construct_keyslot_manager(t);
+ r = dm_table_construct_crypto_profile(t);
if (r) {
- DMERR("could not construct keyslot manager.");
+ DMERR("could not construct crypto profile.");
return r;
}
@@ -2070,7 +2066,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
return r;
}
- dm_update_keyslot_manager(q, t);
+ dm_update_crypto_profile(q, t);
disk_update_readahead(t->md->disk);
return 0;
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index c88ed14d49e6..1a96a07cbf44 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -549,7 +549,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
int r;
struct dm_block *sblock;
struct thin_disk_superblock *disk_super;
- sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT;
+ sector_t bdev_size = bdev_nr_sectors(pmd->bdev);
if (bdev_size > THIN_METADATA_MAX_SECTORS)
bdev_size = THIN_METADATA_MAX_SECTORS;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 4c67b77c23c1..ec119d2422d5 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3212,7 +3212,7 @@ static int metadata_pre_commit_callback(void *context)
static sector_t get_dev_size(struct block_device *bdev)
{
- return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ return bdev_nr_sectors(bdev);
}
static void warn_if_metadata_device_too_big(struct block_device *bdev)
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 88288c8d6bc8..a7efe83aad29 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -18,6 +18,7 @@
#include "dm-verity-verify-sig.h"
#include <linux/module.h>
#include <linux/reboot.h>
+#include <linux/scatterlist.h>
#define DM_MSG_PREFIX "verity"
@@ -833,8 +834,7 @@ static int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
*bdev = v->data_dev->bdev;
- if (v->data_start ||
- ti->len != i_size_read(v->data_dev->bdev->bd_inode) >> SECTOR_SHIFT)
+ if (v->data_start || ti->len != bdev_nr_sectors(v->data_dev->bdev))
return 1;
return 0;
}
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 18320444fb0a..017806096b91 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -2341,7 +2341,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
ti->error = "Cache data device lookup failed";
goto bad;
}
- wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode);
+ wc->memory_map_size = bdev_nr_bytes(wc->ssd_dev->bdev);
/*
* Parse the cache block size
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index ae1bc48c0043..8dc21c09329f 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -733,7 +733,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path,
dev->dev_idx = idx;
(void)bdevname(dev->bdev, dev->name);
- dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ dev->capacity = bdev_nr_sectors(bdev);
if (ti->begin) {
ti->error = "Partial mapping is not supported";
goto err;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 76d9da49fda7..63aa52263658 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -29,7 +29,7 @@
#include <linux/refcount.h>
#include <linux/part_stat.h>
#include <linux/blk-crypto.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#define DM_MSG_PREFIX "core"
@@ -1183,14 +1183,13 @@ static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch)
mutex_unlock(&md->swap_bios_lock);
}
-static blk_qc_t __map_bio(struct dm_target_io *tio)
+static void __map_bio(struct dm_target_io *tio)
{
int r;
sector_t sector;
struct bio *clone = &tio->clone;
struct dm_io *io = tio->io;
struct dm_target *ti = tio->ti;
- blk_qc_t ret = BLK_QC_T_NONE;
clone->bi_end_io = clone_endio;
@@ -1226,7 +1225,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
case DM_MAPIO_REMAPPED:
/* the bio has been remapped so dispatch it */
trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector);
- ret = submit_bio_noacct(clone);
+ submit_bio_noacct(clone);
break;
case DM_MAPIO_KILL:
if (unlikely(swap_bios_limit(ti, clone))) {
@@ -1248,8 +1247,6 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
DMWARN("unimplemented target map return value: %d", r);
BUG();
}
-
- return ret;
}
static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
@@ -1336,7 +1333,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
}
}
-static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci,
+static void __clone_and_map_simple_bio(struct clone_info *ci,
struct dm_target_io *tio, unsigned *len)
{
struct bio *clone = &tio->clone;
@@ -1346,8 +1343,7 @@ static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci,
__bio_clone_fast(clone, ci->bio);
if (len)
bio_setup_sector(clone, ci->sector, *len);
-
- return __map_bio(tio);
+ __map_bio(tio);
}
static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
@@ -1361,7 +1357,7 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
while ((bio = bio_list_pop(&blist))) {
tio = container_of(bio, struct dm_target_io, clone);
- (void) __clone_and_map_simple_bio(ci, tio, len);
+ __clone_and_map_simple_bio(ci, tio, len);
}
}
@@ -1405,7 +1401,7 @@ static int __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
free_tio(tio);
return r;
}
- (void) __map_bio(tio);
+ __map_bio(tio);
return 0;
}
@@ -1520,11 +1516,10 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
/*
* Entry point to split a bio into clones and submit them to the targets.
*/
-static blk_qc_t __split_and_process_bio(struct mapped_device *md,
+static void __split_and_process_bio(struct mapped_device *md,
struct dm_table *map, struct bio *bio)
{
struct clone_info ci;
- blk_qc_t ret = BLK_QC_T_NONE;
int error = 0;
init_clone_info(&ci, md, map, bio);
@@ -1567,19 +1562,17 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
bio_chain(b, bio);
trace_block_split(b, bio->bi_iter.bi_sector);
- ret = submit_bio_noacct(bio);
+ submit_bio_noacct(bio);
}
}
/* drop the extra reference count */
dm_io_dec_pending(ci.io, errno_to_blk_status(error));
- return ret;
}
-static blk_qc_t dm_submit_bio(struct bio *bio)
+static void dm_submit_bio(struct bio *bio)
{
struct mapped_device *md = bio->bi_bdev->bd_disk->private_data;
- blk_qc_t ret = BLK_QC_T_NONE;
int srcu_idx;
struct dm_table *map;
@@ -1609,10 +1602,9 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
if (is_abnormal_io(bio))
blk_queue_split(&bio);
- ret = __split_and_process_bio(md, map, bio);
+ __split_and_process_bio(md, map, bio);
out:
dm_put_live_table(md, srcu_idx);
- return ret;
}
/*-----------------------------------------------------------------
@@ -1671,14 +1663,14 @@ static const struct dax_operations dm_dax_ops;
static void dm_wq_work(struct work_struct *work);
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-static void dm_queue_destroy_keyslot_manager(struct request_queue *q)
+static void dm_queue_destroy_crypto_profile(struct request_queue *q)
{
- dm_destroy_keyslot_manager(q->ksm);
+ dm_destroy_crypto_profile(q->crypto_profile);
}
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static inline void dm_queue_destroy_keyslot_manager(struct request_queue *q)
+static inline void dm_queue_destroy_crypto_profile(struct request_queue *q)
{
}
#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */
@@ -1704,7 +1696,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
dm_sysfs_exit(md);
del_gendisk(md->disk);
}
- dm_queue_destroy_keyslot_manager(md->queue);
+ dm_queue_destroy_crypto_profile(md->queue);
blk_cleanup_disk(md->disk);
}
@@ -2086,7 +2078,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
if (r)
return r;
- add_disk(md->disk);
+ r = add_disk(md->disk);
+ if (r)
+ return r;
r = dm_sysfs_init(md);
if (r) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6c0c3d0d905a..5111ed966947 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -41,6 +41,7 @@
#include <linux/sched/signal.h>
#include <linux/kthread.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/badblocks.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
@@ -51,6 +52,7 @@
#include <linux/hdreg.h>
#include <linux/proc_fs.h>
#include <linux/random.h>
+#include <linux/major.h>
#include <linux/module.h>
#include <linux/reboot.h>
#include <linux/file.h>
@@ -352,7 +354,7 @@ static bool create_on_open = true;
*/
static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
static atomic_t md_event_count;
-void md_new_event(struct mddev *mddev)
+void md_new_event(void)
{
atomic_inc(&md_event_count);
wake_up(&md_event_waiters);
@@ -441,19 +443,19 @@ check_suspended:
}
EXPORT_SYMBOL(md_handle_request);
-static blk_qc_t md_submit_bio(struct bio *bio)
+static void md_submit_bio(struct bio *bio)
{
const int rw = bio_data_dir(bio);
struct mddev *mddev = bio->bi_bdev->bd_disk->private_data;
if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
- return BLK_QC_T_NONE;
+ return;
}
if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
bio_io_error(bio);
- return BLK_QC_T_NONE;
+ return;
}
blk_queue_split(&bio);
@@ -462,15 +464,13 @@ static blk_qc_t md_submit_bio(struct bio *bio)
if (bio_sectors(bio) != 0)
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
- return BLK_QC_T_NONE;
+ return;
}
/* bio could be mergeable after passing to underlayer */
bio->bi_opf &= ~REQ_NOMERGE;
md_handle_request(mddev, bio);
-
- return BLK_QC_T_NONE;
}
/* mddev_suspend makes sure no new requests are submitted
@@ -888,8 +888,7 @@ static struct md_personality *find_pers(int level, char *clevel)
/* return the offset of the super block in 512byte sectors */
static inline sector_t calc_dev_sboffset(struct md_rdev *rdev)
{
- sector_t num_sectors = i_size_read(rdev->bdev->bd_inode) / 512;
- return MD_NEW_SIZE_SECTORS(num_sectors);
+ return MD_NEW_SIZE_SECTORS(bdev_nr_sectors(rdev->bdev));
}
static int alloc_disk_sb(struct md_rdev *rdev)
@@ -1631,8 +1630,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
*/
switch(minor_version) {
case 0:
- sb_start = i_size_read(rdev->bdev->bd_inode) >> 9;
- sb_start -= 8*2;
+ sb_start = bdev_nr_sectors(rdev->bdev) - 8 * 2;
sb_start &= ~(sector_t)(4*2-1);
break;
case 1:
@@ -1787,10 +1785,9 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
else
ret = 0;
}
- if (minor_version) {
- sectors = (i_size_read(rdev->bdev->bd_inode) >> 9);
- sectors -= rdev->data_offset;
- } else
+ if (minor_version)
+ sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset;
+ else
sectors = rdev->sb_start;
if (sectors < le64_to_cpu(sb->data_size))
return -EINVAL;
@@ -2168,8 +2165,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
return 0; /* too confusing */
if (rdev->sb_start < rdev->data_offset) {
/* minor versions 1 and 2; superblock before data */
- max_sectors = i_size_read(rdev->bdev->bd_inode) >> 9;
- max_sectors -= rdev->data_offset;
+ max_sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset;
if (!num_sectors || num_sectors > max_sectors)
num_sectors = max_sectors;
} else if (rdev->mddev->bitmap_info.offset) {
@@ -2178,7 +2174,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
} else {
/* minor version 0; superblock after data */
sector_t sb_start, bm_space;
- sector_t dev_size = i_size_read(rdev->bdev->bd_inode) >> 9;
+ sector_t dev_size = bdev_nr_sectors(rdev->bdev);
/* 8K is for superblock */
sb_start = dev_size - 8*2;
@@ -2886,7 +2882,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- md_new_event(mddev);
+ md_new_event();
md_wakeup_thread(mddev->thread);
return 0;
}
@@ -2976,7 +2972,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
* -write_error - clears WriteErrorSeen
* {,-}failfast - set/clear FailFast
*/
+
+ struct mddev *mddev = rdev->mddev;
int err = -EINVAL;
+ bool need_update_sb = false;
+
if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
md_error(rdev->mddev, rdev);
if (test_bit(Faulty, &rdev->flags))
@@ -2991,7 +2991,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
if (rdev->raid_disk >= 0)
err = -EBUSY;
else {
- struct mddev *mddev = rdev->mddev;
err = 0;
if (mddev_is_clustered(mddev))
err = md_cluster_ops->remove_disk(mddev, rdev);
@@ -3002,16 +3001,18 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
md_wakeup_thread(mddev->thread);
}
- md_new_event(mddev);
+ md_new_event();
}
}
} else if (cmd_match(buf, "writemostly")) {
set_bit(WriteMostly, &rdev->flags);
mddev_create_serial_pool(rdev->mddev, rdev, false);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "-writemostly")) {
mddev_destroy_serial_pool(rdev->mddev, rdev, false);
clear_bit(WriteMostly, &rdev->flags);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "blocked")) {
set_bit(Blocked, &rdev->flags);
@@ -3037,9 +3038,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
err = 0;
} else if (cmd_match(buf, "failfast")) {
set_bit(FailFast, &rdev->flags);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "-failfast")) {
clear_bit(FailFast, &rdev->flags);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 &&
!test_bit(Journal, &rdev->flags)) {
@@ -3118,6 +3121,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
clear_bit(ExternalBbl, &rdev->flags);
err = 0;
}
+ if (need_update_sb)
+ md_update_sb(mddev, 1);
if (!err)
sysfs_notify_dirent_safe(rdev->sysfs_state);
return err ? err : len;
@@ -3382,7 +3387,7 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
if (!sectors)
return -EBUSY;
} else if (!sectors)
- sectors = (i_size_read(rdev->bdev->bd_inode) >> 9) -
+ sectors = bdev_nr_sectors(rdev->bdev) -
rdev->data_offset;
if (!my_mddev->pers->resize)
/* Cannot change size for RAID0 or Linear etc */
@@ -3709,7 +3714,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
kobject_init(&rdev->kobj, &rdev_ktype);
- size = i_size_read(rdev->bdev->bd_inode) >> BLOCK_SIZE_BITS;
+ size = bdev_nr_bytes(rdev->bdev) >> BLOCK_SIZE_BITS;
if (!size) {
pr_warn("md: %s has zero or unknown size, marking faulty!\n",
bdevname(rdev->bdev,b));
@@ -4099,7 +4104,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
if (!mddev->thread)
md_update_sb(mddev, 1);
sysfs_notify_dirent_safe(mddev->sysfs_level);
- md_new_event(mddev);
+ md_new_event();
rv = len;
out_unlock:
mddev_unlock(mddev);
@@ -4620,7 +4625,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
export_rdev(rdev);
mddev_unlock(mddev);
if (!err)
- md_new_event(mddev);
+ md_new_event();
return err ? err : len;
}
@@ -5490,6 +5495,10 @@ static struct attribute *md_default_attrs[] = {
NULL,
};
+static const struct attribute_group md_default_group = {
+ .attrs = md_default_attrs,
+};
+
static struct attribute *md_redundancy_attrs[] = {
&md_scan_mode.attr,
&md_last_scan_mode.attr,
@@ -5512,6 +5521,12 @@ static const struct attribute_group md_redundancy_group = {
.attrs = md_redundancy_attrs,
};
+static const struct attribute_group *md_attr_groups[] = {
+ &md_default_group,
+ &md_bitmap_group,
+ NULL,
+};
+
static ssize_t
md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
@@ -5587,7 +5602,7 @@ static const struct sysfs_ops md_sysfs_ops = {
static struct kobj_type md_ktype = {
.release = md_free,
.sysfs_ops = &md_sysfs_ops,
- .default_attrs = md_default_attrs,
+ .default_groups = md_attr_groups,
};
int mdp_major = 0;
@@ -5596,7 +5611,6 @@ static void mddev_delayed_delete(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, del_work);
- sysfs_remove_group(&mddev->kobj, &md_bitmap_group);
kobject_del(&mddev->kobj);
kobject_put(&mddev->kobj);
}
@@ -5663,7 +5677,7 @@ static int md_alloc(dev_t dev, char *name)
strcmp(mddev2->gendisk->disk_name, name) == 0) {
spin_unlock(&all_mddevs_lock);
error = -EEXIST;
- goto abort;
+ goto out_unlock_disks_mutex;
}
spin_unlock(&all_mddevs_lock);
}
@@ -5676,7 +5690,7 @@ static int md_alloc(dev_t dev, char *name)
error = -ENOMEM;
disk = blk_alloc_disk(NUMA_NO_NODE);
if (!disk)
- goto abort;
+ goto out_unlock_disks_mutex;
disk->major = MAJOR(mddev->unit);
disk->first_minor = unit << shift;
@@ -5700,27 +5714,25 @@ static int md_alloc(dev_t dev, char *name)
disk->flags |= GENHD_FL_EXT_DEVT;
disk->events |= DISK_EVENT_MEDIA_CHANGE;
mddev->gendisk = disk;
- add_disk(disk);
+ error = add_disk(disk);
+ if (error)
+ goto out_cleanup_disk;
error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md");
- if (error) {
- /* This isn't possible, but as kobject_init_and_add is marked
- * __must_check, we must do something with the result
- */
- pr_debug("md: cannot register %s/md - name in use\n",
- disk->disk_name);
- error = 0;
- }
- if (mddev->kobj.sd &&
- sysfs_create_group(&mddev->kobj, &md_bitmap_group))
- pr_debug("pointless warning\n");
- abort:
+ if (error)
+ goto out_del_gendisk;
+
+ kobject_uevent(&mddev->kobj, KOBJ_ADD);
+ mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
+ mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
+ goto out_unlock_disks_mutex;
+
+out_del_gendisk:
+ del_gendisk(disk);
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
+out_unlock_disks_mutex:
mutex_unlock(&disks_mutex);
- if (!error && mddev->kobj.sd) {
- kobject_uevent(&mddev->kobj, KOBJ_ADD);
- mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
- mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
- }
mddev_put(mddev);
return error;
}
@@ -6034,7 +6046,7 @@ int md_run(struct mddev *mddev)
if (mddev->sb_flags)
md_update_sb(mddev, 0);
- md_new_event(mddev);
+ md_new_event();
return 0;
bitmap_abort:
@@ -6424,7 +6436,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
if (mddev->hold_active == UNTIL_STOP)
mddev->hold_active = 0;
}
- md_new_event(mddev);
+ md_new_event();
sysfs_notify_dirent_safe(mddev->sysfs_state);
return 0;
}
@@ -6880,7 +6892,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info)
if (!mddev->persistent) {
pr_debug("md: nonpersistent superblock ...\n");
- rdev->sb_start = i_size_read(rdev->bdev->bd_inode) / 512;
+ rdev->sb_start = bdev_nr_sectors(rdev->bdev);
} else
rdev->sb_start = calc_dev_sboffset(rdev);
rdev->sectors = rdev->sb_start;
@@ -6928,7 +6940,7 @@ kick_rdev:
md_wakeup_thread(mddev->thread);
else
md_update_sb(mddev, 1);
- md_new_event(mddev);
+ md_new_event();
return 0;
busy:
@@ -6967,7 +6979,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
if (mddev->persistent)
rdev->sb_start = calc_dev_sboffset(rdev);
else
- rdev->sb_start = i_size_read(rdev->bdev->bd_inode) / 512;
+ rdev->sb_start = bdev_nr_sectors(rdev->bdev);
rdev->sectors = rdev->sb_start;
@@ -7001,7 +7013,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- md_new_event(mddev);
+ md_new_event();
return 0;
abort_export:
@@ -7975,7 +7987,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
md_wakeup_thread(mddev->thread);
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
- md_new_event(mddev);
+ md_new_event();
}
EXPORT_SYMBOL(md_error);
@@ -8859,7 +8871,7 @@ void md_do_sync(struct md_thread *thread)
mddev->curr_resync = 3; /* no longer delayed */
mddev->curr_resync_completed = j;
sysfs_notify_dirent_safe(mddev->sysfs_completed);
- md_new_event(mddev);
+ md_new_event();
update_time = jiffies;
blk_start_plug(&plug);
@@ -8930,7 +8942,7 @@ void md_do_sync(struct md_thread *thread)
/* this is the earliest that rebuild will be
* visible in /proc/mdstat
*/
- md_new_event(mddev);
+ md_new_event();
if (last_check + window > io_sectors || j == max_sectors)
continue;
@@ -9154,7 +9166,7 @@ static int remove_and_add_spares(struct mddev *mddev,
sysfs_link_rdev(mddev, rdev);
if (!test_bit(Journal, &rdev->flags))
spares++;
- md_new_event(mddev);
+ md_new_event();
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
}
}
@@ -9188,7 +9200,7 @@ static void md_start_sync(struct work_struct *ws)
} else
md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent_safe(mddev->sysfs_action);
- md_new_event(mddev);
+ md_new_event();
}
/*
@@ -9447,7 +9459,7 @@ void md_reap_sync_thread(struct mddev *mddev)
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
sysfs_notify_dirent_safe(mddev->sysfs_action);
- md_new_event(mddev);
+ md_new_event();
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 4c96c36bd01a..53ea7a6961de 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -731,7 +731,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
struct page *page, int op, int op_flags,
bool metadata_op);
extern void md_do_sync(struct md_thread *thread);
-extern void md_new_event(struct mddev *mddev);
+extern void md_new_event(void);
extern void md_allow_write(struct mddev *mddev);
extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 19598bd38939..7dc8026cf6ee 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1496,7 +1496,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (!r1_bio->bios[i])
continue;
- if (first_clone) {
+ if (first_clone && test_bit(WriteMostly, &rdev->flags)) {
/* do behind I/O ?
* Not if there are too many, or cannot
* allocate memory, or a reader on WriteMostly
@@ -1529,13 +1529,12 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
r1_bio->bios[i] = mbio;
- mbio->bi_iter.bi_sector = (r1_bio->sector +
- conf->mirrors[i].rdev->data_offset);
- bio_set_dev(mbio, conf->mirrors[i].rdev->bdev);
+ mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset);
+ bio_set_dev(mbio, rdev->bdev);
mbio->bi_end_io = raid1_end_write_request;
mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
- if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
- !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
+ if (test_bit(FailFast, &rdev->flags) &&
+ !test_bit(WriteMostly, &rdev->flags) &&
conf->raid_disks - mddev->degraded > 1)
mbio->bi_opf |= MD_FAILFAST;
mbio->bi_private = r1_bio;
@@ -1546,7 +1545,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
r1_bio->sector);
/* flush_pending_writes() needs access to the rdev so...*/
- mbio->bi_bdev = (void *)conf->mirrors[i].rdev;
+ mbio->bi_bdev = (void *)rdev;
cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
if (cb)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index aa2636582841..dde98f65bd04 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4647,7 +4647,7 @@ out:
}
conf->reshape_checkpoint = jiffies;
md_wakeup_thread(mddev->sync_thread);
- md_new_event(mddev);
+ md_new_event();
return 0;
abort:
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 02ed53b20654..9c1a5877cf9f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7732,10 +7732,7 @@ static int raid5_run(struct mddev *mddev)
* discard data disk but write parity disk
*/
stripe = stripe * PAGE_SIZE;
- /* Round up to power of 2, as discard handling
- * currently assumes that */
- while ((stripe-1) & stripe)
- stripe = (stripe | (stripe-1)) + 1;
+ stripe = roundup_pow_of_two(stripe);
mddev->queue->limits.discard_alignment = stripe;
mddev->queue->limits.discard_granularity = stripe;
@@ -8282,7 +8279,7 @@ static int raid5_start_reshape(struct mddev *mddev)
}
conf->reshape_checkpoint = jiffies;
md_wakeup_thread(mddev->sync_thread);
- md_new_event(mddev);
+ md_new_event();
return 0;
}
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 431af5e8be2f..74882fa0f86d 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -258,7 +258,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
mq = &md->queue;
/* Dispatch locking to the block layer */
- req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, 0);
+ req = blk_mq_alloc_request(mq->queue, REQ_OP_DRV_OUT, 0);
if (IS_ERR(req)) {
count = PTR_ERR(req);
goto out_put;
@@ -266,7 +266,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP;
blk_execute_rq(NULL, req, 0);
ret = req_to_mmc_queue_req(req)->drv_op_result;
- blk_put_request(req);
+ blk_mq_free_request(req);
if (!ret) {
pr_info("%s: Locking boot partition ro until next power on\n",
@@ -646,7 +646,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
* Dispatch the ioctl() into the block request queue.
*/
mq = &md->queue;
- req = blk_get_request(mq->queue,
+ req = blk_mq_alloc_request(mq->queue,
idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
@@ -660,7 +660,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
blk_execute_rq(NULL, req, 0);
ioc_err = req_to_mmc_queue_req(req)->drv_op_result;
err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata);
- blk_put_request(req);
+ blk_mq_free_request(req);
cmd_done:
kfree(idata->buf);
@@ -716,7 +716,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
* Dispatch the ioctl()s into the block request queue.
*/
mq = &md->queue;
- req = blk_get_request(mq->queue,
+ req = blk_mq_alloc_request(mq->queue,
idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
@@ -733,7 +733,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
for (i = 0; i < num_of_cmds && !err; i++)
err = mmc_blk_ioctl_copy_to_user(&cmds[i], idata[i]);
- blk_put_request(req);
+ blk_mq_free_request(req);
cmd_err:
for (i = 0; i < num_of_cmds; i++) {
@@ -2730,7 +2730,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
int ret;
/* Ask the block layer about the card status */
- req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0);
+ req = blk_mq_alloc_request(mq->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
return PTR_ERR(req);
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
@@ -2740,7 +2740,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
*val = ret;
ret = 0;
}
- blk_put_request(req);
+ blk_mq_free_request(req);
return ret;
}
@@ -2766,7 +2766,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
return -ENOMEM;
/* Ask the block layer for the EXT CSD */
- req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0);
+ req = blk_mq_alloc_request(mq->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_free;
@@ -2775,7 +2775,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
req_to_mmc_queue_req(req)->drv_op_data = &ext_csd;
blk_execute_rq(NULL, req, 0);
err = req_to_mmc_queue_req(req)->drv_op_result;
- blk_put_request(req);
+ blk_mq_free_request(req);
if (err) {
pr_err("FAILED %d\n", err);
goto out_free;
diff --git a/drivers/mmc/core/crypto.c b/drivers/mmc/core/crypto.c
index 67557808cada..fec4fbf16a5b 100644
--- a/drivers/mmc/core/crypto.c
+++ b/drivers/mmc/core/crypto.c
@@ -16,13 +16,13 @@ void mmc_crypto_set_initial_state(struct mmc_host *host)
{
/* Reset might clear all keys, so reprogram all the keys. */
if (host->caps2 & MMC_CAP2_CRYPTO)
- blk_ksm_reprogram_all_keys(&host->ksm);
+ blk_crypto_reprogram_all_keys(&host->crypto_profile);
}
void mmc_crypto_setup_queue(struct request_queue *q, struct mmc_host *host)
{
if (host->caps2 & MMC_CAP2_CRYPTO)
- blk_ksm_register(&host->ksm, q);
+ blk_crypto_register(&host->crypto_profile, q);
}
EXPORT_SYMBOL_GPL(mmc_crypto_setup_queue);
@@ -30,12 +30,15 @@ void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq)
{
struct request *req = mmc_queue_req_to_req(mqrq);
struct mmc_request *mrq = &mqrq->brq.mrq;
+ struct blk_crypto_keyslot *keyslot;
if (!req->crypt_ctx)
return;
mrq->crypto_ctx = req->crypt_ctx;
- if (req->crypt_keyslot)
- mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot);
+
+ keyslot = req->crypt_keyslot;
+ if (keyslot)
+ mrq->crypto_key_slot = blk_crypto_keyslot_index(keyslot);
}
EXPORT_SYMBOL_GPL(mmc_crypto_prepare_req);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 4646b7a03db6..c9db24e16af1 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -12,6 +12,7 @@
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/pm_runtime.h>
+#include <linux/scatterlist.h>
#include <linux/mmc/host.h>
#include <linux/mmc/card.h>
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 95b3511b0560..ccc148cdb5ee 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -506,7 +506,7 @@ config MMC_OMAP_HS
config MMC_WBSD
tristate "Winbond W83L51xD SD/MMC Card Interface support"
- depends on ISA_DMA_API
+ depends on ISA_DMA_API && !M68K
help
This selects the Winbond(R) W83L51xD Secure digital and
Multimedia card Interface.
diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c
index 38559a956330..31f841231609 100644
--- a/drivers/mmc/host/cqhci-core.c
+++ b/drivers/mmc/host/cqhci-core.c
@@ -282,6 +282,9 @@ static void __cqhci_enable(struct cqhci_host *cq_host)
cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+ if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT)
+ cqhci_writel(cq_host, 0, CQHCI_CTL);
+
mmc->cqe_on = true;
if (cq_host->ops->enable)
diff --git a/drivers/mmc/host/cqhci-crypto.c b/drivers/mmc/host/cqhci-crypto.c
index 6419cfbb4ab7..d5f4b6972f63 100644
--- a/drivers/mmc/host/cqhci-crypto.c
+++ b/drivers/mmc/host/cqhci-crypto.c
@@ -6,7 +6,7 @@
*/
#include <linux/blk-crypto.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include <linux/mmc/host.h>
#include "cqhci-crypto.h"
@@ -23,9 +23,10 @@ static const struct cqhci_crypto_alg_entry {
};
static inline struct cqhci_host *
-cqhci_host_from_ksm(struct blk_keyslot_manager *ksm)
+cqhci_host_from_crypto_profile(struct blk_crypto_profile *profile)
{
- struct mmc_host *mmc = container_of(ksm, struct mmc_host, ksm);
+ struct mmc_host *mmc =
+ container_of(profile, struct mmc_host, crypto_profile);
return mmc->cqe_private;
}
@@ -57,12 +58,12 @@ static int cqhci_crypto_program_key(struct cqhci_host *cq_host,
return 0;
}
-static int cqhci_crypto_keyslot_program(struct blk_keyslot_manager *ksm,
+static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct cqhci_host *cq_host = cqhci_host_from_ksm(ksm);
+ struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile);
const union cqhci_crypto_cap_entry *ccap_array =
cq_host->crypto_cap_array;
const struct cqhci_crypto_alg_entry *alg =
@@ -115,11 +116,11 @@ static int cqhci_crypto_clear_keyslot(struct cqhci_host *cq_host, int slot)
return cqhci_crypto_program_key(cq_host, &cfg, slot);
}
-static int cqhci_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
+static int cqhci_crypto_keyslot_evict(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct cqhci_host *cq_host = cqhci_host_from_ksm(ksm);
+ struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile);
return cqhci_crypto_clear_keyslot(cq_host, slot);
}
@@ -132,7 +133,7 @@ static int cqhci_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
* "enabled" when these are called, i.e. CQHCI_ENABLE might not be set in the
* CQHCI_CFG register. But the hardware allows that.
*/
-static const struct blk_ksm_ll_ops cqhci_ksm_ops = {
+static const struct blk_crypto_ll_ops cqhci_crypto_ops = {
.keyslot_program = cqhci_crypto_keyslot_program,
.keyslot_evict = cqhci_crypto_keyslot_evict,
};
@@ -157,8 +158,8 @@ cqhci_find_blk_crypto_mode(union cqhci_crypto_cap_entry cap)
*
* If the driver previously set MMC_CAP2_CRYPTO and the CQE declares
* CQHCI_CAP_CS, initialize the crypto support. This involves reading the
- * crypto capability registers, initializing the keyslot manager, clearing all
- * keyslots, and enabling 128-bit task descriptors.
+ * crypto capability registers, initializing the blk_crypto_profile, clearing
+ * all keyslots, and enabling 128-bit task descriptors.
*
* Return: 0 if crypto was initialized or isn't supported; whether
* MMC_CAP2_CRYPTO remains set indicates which one of those cases it is.
@@ -168,7 +169,7 @@ int cqhci_crypto_init(struct cqhci_host *cq_host)
{
struct mmc_host *mmc = cq_host->mmc;
struct device *dev = mmc_dev(mmc);
- struct blk_keyslot_manager *ksm = &mmc->ksm;
+ struct blk_crypto_profile *profile = &mmc->crypto_profile;
unsigned int num_keyslots;
unsigned int cap_idx;
enum blk_crypto_mode_num blk_mode_num;
@@ -199,15 +200,15 @@ int cqhci_crypto_init(struct cqhci_host *cq_host)
*/
num_keyslots = cq_host->crypto_capabilities.config_count + 1;
- err = devm_blk_ksm_init(dev, ksm, num_keyslots);
+ err = devm_blk_crypto_profile_init(dev, profile, num_keyslots);
if (err)
goto out;
- ksm->ksm_ll_ops = cqhci_ksm_ops;
- ksm->dev = dev;
+ profile->ll_ops = cqhci_crypto_ops;
+ profile->dev = dev;
/* Unfortunately, CQHCI crypto only supports 32 DUN bits. */
- ksm->max_dun_bytes_supported = 4;
+ profile->max_dun_bytes_supported = 4;
/*
* Cache all the crypto capabilities and advertise the supported crypto
@@ -223,7 +224,7 @@ int cqhci_crypto_init(struct cqhci_host *cq_host)
cq_host->crypto_cap_array[cap_idx]);
if (blk_mode_num == BLK_ENCRYPTION_MODE_INVALID)
continue;
- ksm->crypto_modes_supported[blk_mode_num] |=
+ profile->modes_supported[blk_mode_num] |=
cq_host->crypto_cap_array[cap_idx].sdus_mask * 512;
}
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 0c75810812a0..1f8a3c0ddfe1 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -464,6 +464,18 @@ static s8 dw_mci_exynos_get_best_clksmpl(u8 candiates)
}
}
+ /*
+ * If there is no cadiates value, then it needs to return -EIO.
+ * If there are candiates values and don't find bset clk sample value,
+ * then use a first candiates clock sample value.
+ */
+ for (i = 0; i < iter; i++) {
+ __c = ror8(candiates, i);
+ if ((__c & 0x1) == 0x1) {
+ loc = i;
+ goto out;
+ }
+ }
out:
return loc;
}
@@ -494,6 +506,8 @@ static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
priv->tuned_sample = found;
} else {
ret = -EIO;
+ dev_warn(&mmc->class_dev,
+ "There is no candiates value about clksmpl!\n");
}
return ret;
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 4dfc246c5f95..b06b4dcb7c78 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2577,6 +2577,25 @@ static int msdc_drv_probe(struct platform_device *pdev)
host->dma_mask = DMA_BIT_MASK(32);
mmc_dev(mmc)->dma_mask = &host->dma_mask;
+ host->timeout_clks = 3 * 1048576;
+ host->dma.gpd = dma_alloc_coherent(&pdev->dev,
+ 2 * sizeof(struct mt_gpdma_desc),
+ &host->dma.gpd_addr, GFP_KERNEL);
+ host->dma.bd = dma_alloc_coherent(&pdev->dev,
+ MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+ &host->dma.bd_addr, GFP_KERNEL);
+ if (!host->dma.gpd || !host->dma.bd) {
+ ret = -ENOMEM;
+ goto release_mem;
+ }
+ msdc_init_gpd_bd(host, &host->dma);
+ INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout);
+ spin_lock_init(&host->lock);
+
+ platform_set_drvdata(pdev, mmc);
+ msdc_ungate_clock(host);
+ msdc_init_hw(host);
+
if (mmc->caps2 & MMC_CAP2_CQE) {
host->cq_host = devm_kzalloc(mmc->parent,
sizeof(*host->cq_host),
@@ -2597,25 +2616,6 @@ static int msdc_drv_probe(struct platform_device *pdev)
mmc->max_seg_size = 64 * 1024;
}
- host->timeout_clks = 3 * 1048576;
- host->dma.gpd = dma_alloc_coherent(&pdev->dev,
- 2 * sizeof(struct mt_gpdma_desc),
- &host->dma.gpd_addr, GFP_KERNEL);
- host->dma.bd = dma_alloc_coherent(&pdev->dev,
- MAX_BD_NUM * sizeof(struct mt_bdma_desc),
- &host->dma.bd_addr, GFP_KERNEL);
- if (!host->dma.gpd || !host->dma.bd) {
- ret = -ENOMEM;
- goto release_mem;
- }
- msdc_init_gpd_bd(host, &host->dma);
- INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout);
- spin_lock_init(&host->lock);
-
- platform_set_drvdata(pdev, mmc);
- msdc_ungate_clock(host);
- msdc_init_hw(host);
-
ret = devm_request_irq(&pdev->dev, host->irq, msdc_irq,
IRQF_TRIGGER_NONE, pdev->name, host);
if (ret)
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index f18d169bc8ff..e658f0174242 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1187,6 +1187,7 @@ static void esdhc_reset_tuning(struct sdhci_host *host)
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
u32 ctrl;
+ int ret;
/* Reset the tuning circuit */
if (esdhc_is_usdhc(imx_data)) {
@@ -1199,7 +1200,22 @@ static void esdhc_reset_tuning(struct sdhci_host *host)
} else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
ctrl = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS);
ctrl &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
+ ctrl &= ~ESDHC_MIX_CTRL_EXE_TUNE;
writel(ctrl, host->ioaddr + SDHCI_AUTO_CMD_STATUS);
+ /* Make sure ESDHC_MIX_CTRL_EXE_TUNE cleared */
+ ret = readl_poll_timeout(host->ioaddr + SDHCI_AUTO_CMD_STATUS,
+ ctrl, !(ctrl & ESDHC_MIX_CTRL_EXE_TUNE), 1, 50);
+ if (ret == -ETIMEDOUT)
+ dev_warn(mmc_dev(host->mmc),
+ "Warning! clear execute tuning bit failed\n");
+ /*
+ * SDHCI_INT_DATA_AVAIL is W1C bit, set this bit will clear the
+ * usdhc IP internal logic flag execute_tuning_with_clr_buf, which
+ * will finally make sure the normal data transfer logic correct.
+ */
+ ctrl = readl(host->ioaddr + SDHCI_INT_STATUS);
+ ctrl |= SDHCI_INT_DATA_AVAIL;
+ writel(ctrl, host->ioaddr + SDHCI_INT_STATUS);
}
}
}
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index be19785227fe..d0f2edfe296c 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -616,16 +616,12 @@ static int intel_select_drive_strength(struct mmc_card *card,
return intel_host->drv_strength;
}
-static int bxt_get_cd(struct mmc_host *mmc)
+static int sdhci_get_cd_nogpio(struct mmc_host *mmc)
{
- int gpio_cd = mmc_gpio_get_cd(mmc);
struct sdhci_host *host = mmc_priv(mmc);
unsigned long flags;
int ret = 0;
- if (!gpio_cd)
- return 0;
-
spin_lock_irqsave(&host->lock, flags);
if (host->flags & SDHCI_DEVICE_DEAD)
@@ -638,6 +634,21 @@ out:
return ret;
}
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+ int gpio_cd = mmc_gpio_get_cd(mmc);
+
+ if (!gpio_cd)
+ return 0;
+
+ return sdhci_get_cd_nogpio(mmc);
+}
+
+static int mrfld_get_cd(struct mmc_host *mmc)
+{
+ return sdhci_get_cd_nogpio(mmc);
+}
+
#define SDHCI_INTEL_PWR_TIMEOUT_CNT 20
#define SDHCI_INTEL_PWR_TIMEOUT_UDELAY 100
@@ -1341,6 +1352,14 @@ static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot)
MMC_CAP_1_8V_DDR;
break;
case INTEL_MRFLD_SD:
+ slot->cd_idx = 0;
+ slot->cd_override_level = true;
+ /*
+ * There are two PCB designs of SD card slot with the opposite
+ * card detection sense. Quirk this out by ignoring GPIO state
+ * completely in the custom ->get_cd() callback.
+ */
+ slot->host->mmc_host_ops.get_cd = mrfld_get_cd;
slot->host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
break;
case INTEL_MRFLD_SDIO:
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 8eefa7d5fe85..2d80a04e11d8 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2042,6 +2042,12 @@ void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
break;
case MMC_VDD_32_33:
case MMC_VDD_33_34:
+ /*
+ * 3.4 ~ 3.6V are valid only for those platforms where it's
+ * known that the voltage range is supported by hardware.
+ */
+ case MMC_VDD_34_35:
+ case MMC_VDD_35_36:
pwr = SDHCI_POWER_330;
break;
default:
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 7dfc26f48c18..e2affa52ef46 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -195,6 +195,10 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host)
sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask_all);
host->sdcard_irq_mask = host->sdcard_irq_mask_all;
+ if (host->native_hotplug)
+ tmio_mmc_enable_mmc_irqs(host,
+ TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT);
+
tmio_mmc_set_bus_width(host, host->mmc->ios.bus_width);
if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) {
@@ -956,8 +960,15 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
case MMC_POWER_OFF:
tmio_mmc_power_off(host);
/* For R-Car Gen2+, we need to reset SDHI specific SCC */
- if (host->pdata->flags & TMIO_MMC_MIN_RCAR2)
+ if (host->pdata->flags & TMIO_MMC_MIN_RCAR2) {
host->reset(host);
+
+ if (host->native_hotplug)
+ tmio_mmc_enable_mmc_irqs(host,
+ TMIO_STAT_CARD_REMOVE |
+ TMIO_STAT_CARD_INSERT);
+ }
+
host->set_clock(host, 0);
break;
case MMC_POWER_UP:
@@ -1185,10 +1196,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host)
_host->set_clock(_host, 0);
tmio_mmc_reset(_host);
- if (_host->native_hotplug)
- tmio_mmc_enable_mmc_irqs(_host,
- TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT);
-
spin_lock_init(&_host->lock);
mutex_init(&_host->ios_lock);
diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index 4950d10d3a19..97beece62fec 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -576,7 +576,7 @@ static void check_vub300_port_status(struct vub300_mmc_host *vub300)
GET_SYSTEM_PORT_STATUS,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x0000, 0x0000, &vub300->system_port_status,
- sizeof(vub300->system_port_status), HZ);
+ sizeof(vub300->system_port_status), 1000);
if (sizeof(vub300->system_port_status) == retval)
new_system_port_status(vub300);
}
@@ -1241,7 +1241,7 @@ static void __download_offload_pseudocode(struct vub300_mmc_host *vub300,
SET_INTERRUPT_PSEUDOCODE,
USB_DIR_OUT | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0x0000, 0x0000,
- xfer_buffer, xfer_length, HZ);
+ xfer_buffer, xfer_length, 1000);
kfree(xfer_buffer);
if (retval < 0)
goto copy_error_message;
@@ -1284,7 +1284,7 @@ static void __download_offload_pseudocode(struct vub300_mmc_host *vub300,
SET_TRANSFER_PSEUDOCODE,
USB_DIR_OUT | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0x0000, 0x0000,
- xfer_buffer, xfer_length, HZ);
+ xfer_buffer, xfer_length, 1000);
kfree(xfer_buffer);
if (retval < 0)
goto copy_error_message;
@@ -1991,7 +1991,7 @@ static void __set_clock_speed(struct vub300_mmc_host *vub300, u8 buf[8],
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_CLOCK_SPEED,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x00, 0x00, buf, buf_array_size, HZ);
+ 0x00, 0x00, buf, buf_array_size, 1000);
if (retval != 8) {
dev_err(&vub300->udev->dev, "SET_CLOCK_SPEED"
" %dkHz failed with retval=%d\n", kHzClock, retval);
@@ -2013,14 +2013,14 @@ static void vub300_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_SD_POWER,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x0000, 0x0000, NULL, 0, HZ);
+ 0x0000, 0x0000, NULL, 0, 1000);
/* must wait for the VUB300 u-proc to boot up */
msleep(600);
} else if ((ios->power_mode == MMC_POWER_UP) && !vub300->card_powered) {
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_SD_POWER,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x0001, 0x0000, NULL, 0, HZ);
+ 0x0001, 0x0000, NULL, 0, 1000);
msleep(600);
vub300->card_powered = 1;
} else if (ios->power_mode == MMC_POWER_ON) {
@@ -2275,14 +2275,14 @@ static int vub300_probe(struct usb_interface *interface,
GET_HC_INF0,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x0000, 0x0000, &vub300->hc_info,
- sizeof(vub300->hc_info), HZ);
+ sizeof(vub300->hc_info), 1000);
if (retval < 0)
goto error5;
retval =
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_ROM_WAIT_STATES,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- firmware_rom_wait_states, 0x0000, NULL, 0, HZ);
+ firmware_rom_wait_states, 0x0000, NULL, 0, 1000);
if (retval < 0)
goto error5;
dev_info(&vub300->udev->dev,
@@ -2297,7 +2297,7 @@ static int vub300_probe(struct usb_interface *interface,
GET_SYSTEM_PORT_STATUS,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x0000, 0x0000, &vub300->system_port_status,
- sizeof(vub300->system_port_status), HZ);
+ sizeof(vub300->system_port_status), 1000);
if (retval < 0) {
goto error4;
} else if (sizeof(vub300->system_port_status) == retval) {
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index b8ae1ec14e17..4eaba6f4ec68 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -384,7 +384,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
if (new->readonly)
set_disk_ro(gd, 1);
- device_add_disk(&new->mtd->dev, gd, NULL);
+ ret = device_add_disk(&new->mtd->dev, gd, NULL);
+ if (ret)
+ goto out_cleanup_disk;
if (new->disk_attributes) {
ret = sysfs_create_group(&disk_to_dev(gd)->kobj,
@@ -393,6 +395,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
}
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(new->disk);
out_free_tag_set:
blk_mq_free_tag_set(new->tag_set);
out_kfree_tag_set:
diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c
index 38b6aa849c63..5ff001140ef4 100644
--- a/drivers/mtd/mtdsuper.c
+++ b/drivers/mtd/mtdsuper.c
@@ -15,6 +15,7 @@
#include <linux/slab.h>
#include <linux/major.h>
#include <linux/backing-dev.h>
+#include <linux/blkdev.h>
#include <linux/fs_context.h>
#include "mtdcore.h"
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 2b66c59f5eaf..e54f96251fea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -137,7 +137,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "uc",
.cmd = HNAE3_DBG_CMD_MAC_UC,
.dentry = HNS3_DBG_DENTRY_MAC,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_128KB,
.init = hns3_dbg_common_file_init,
},
{
@@ -256,7 +256,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "tqp",
.cmd = HNAE3_DBG_CMD_REG_TQP,
.dentry = HNS3_DBG_DENTRY_REG,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_128KB,
.init = hns3_dbg_common_file_init,
},
{
@@ -298,7 +298,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "fd_tcam",
.cmd = HNAE3_DBG_CMD_FD_TCAM,
.dentry = HNS3_DBG_DENTRY_FD,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_1MB,
.init = hns3_dbg_common_file_init,
},
{
@@ -462,7 +462,7 @@ static const struct hns3_dbg_item rx_queue_info_items[] = {
{ "TAIL", 2 },
{ "HEAD", 2 },
{ "FBDNUM", 2 },
- { "PKTNUM", 2 },
+ { "PKTNUM", 5 },
{ "COPYBREAK", 2 },
{ "RING_EN", 2 },
{ "RX_RING_EN", 2 },
@@ -565,7 +565,7 @@ static const struct hns3_dbg_item tx_queue_info_items[] = {
{ "HEAD", 2 },
{ "FBDNUM", 2 },
{ "OFFSET", 2 },
- { "PKTNUM", 2 },
+ { "PKTNUM", 5 },
{ "RING_EN", 2 },
{ "TX_RING_EN", 2 },
{ "BASE_ADDR", 10 },
@@ -790,13 +790,13 @@ static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len)
}
static const struct hns3_dbg_item tx_bd_info_items[] = {
- { "BD_IDX", 5 },
- { "ADDRESS", 2 },
+ { "BD_IDX", 2 },
+ { "ADDRESS", 13 },
{ "VLAN_TAG", 2 },
{ "SIZE", 2 },
{ "T_CS_VLAN_TSO", 2 },
{ "OT_VLAN_TAG", 3 },
- { "TV", 2 },
+ { "TV", 5 },
{ "OLT_VLAN_LEN", 2 },
{ "PAYLEN_OL4CS", 2 },
{ "BD_FE_SC_VLD", 2 },
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 32f62cd2dd99..9cda8b3562b8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -391,7 +391,7 @@ static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len)
static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u16 qset_id, qset_num;
int ret;
@@ -408,12 +408,12 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%04u %#x %#x %#x %#x\n",
- qset_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2, bitmap->bit3);
+ qset_id, req.bit0, req.bit1, req.bit2,
+ req.bit3);
}
return 0;
@@ -422,7 +422,7 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 pri_id, pri_num;
int ret;
@@ -439,12 +439,11 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%03u %#x %#x %#x\n",
- pri_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2);
+ pri_id, req.bit0, req.bit1, req.bit2);
}
return 0;
@@ -453,7 +452,7 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 pg_id;
int ret;
@@ -466,12 +465,11 @@ static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%03u %#x %#x %#x\n",
- pg_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2);
+ pg_id, req.bit0, req.bit1, req.bit2);
}
return 0;
@@ -511,7 +509,7 @@ static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len,
static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 port_id = 0;
int ret;
@@ -521,12 +519,12 @@ static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n",
- bitmap->bit0);
+ req.bit0);
*pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n",
- bitmap->bit1);
+ req.bit1);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index dcd40cc73082..d891390d492f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2847,33 +2847,29 @@ static void hclge_mbx_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
static void hclge_reset_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
+ test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
static void hclge_errhand_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_bit(HCLGE_STATE_RST_FAIL, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task,
- delay_time);
+ mod_delayed_work(hclge_wq, &hdev->service_task, delay_time);
}
static int hclge_get_mac_link_status(struct hclge_dev *hdev, int *link_status)
@@ -3491,33 +3487,14 @@ static void hclge_get_misc_vector(struct hclge_dev *hdev)
hdev->num_msi_used += 1;
}
-static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify,
- const cpumask_t *mask)
-{
- struct hclge_dev *hdev = container_of(notify, struct hclge_dev,
- affinity_notify);
-
- cpumask_copy(&hdev->affinity_mask, mask);
-}
-
-static void hclge_irq_affinity_release(struct kref *ref)
-{
-}
-
static void hclge_misc_affinity_setup(struct hclge_dev *hdev)
{
irq_set_affinity_hint(hdev->misc_vector.vector_irq,
&hdev->affinity_mask);
-
- hdev->affinity_notify.notify = hclge_irq_affinity_notify;
- hdev->affinity_notify.release = hclge_irq_affinity_release;
- irq_set_affinity_notifier(hdev->misc_vector.vector_irq,
- &hdev->affinity_notify);
}
static void hclge_misc_affinity_teardown(struct hclge_dev *hdev)
{
- irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL);
irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL);
}
@@ -13052,7 +13029,7 @@ static int hclge_init(void)
{
pr_info("%s is initializing\n", HCLGE_NAME);
- hclge_wq = alloc_workqueue("%s", 0, 0, HCLGE_NAME);
+ hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME);
if (!hclge_wq) {
pr_err("%s: failed to create workqueue\n", HCLGE_NAME);
return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index de6afbcbfbac..69cd8f87b4c8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -944,7 +944,6 @@ struct hclge_dev {
/* affinity mask and notify for misc interrupt */
cpumask_t affinity_mask;
- struct irq_affinity_notify affinity_notify;
struct hclge_ptp *ptp;
struct devlink *devlink;
};
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index bef6b98e2f50..cf00ad7bb881 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2232,6 +2232,7 @@ static void hclgevf_get_misc_vector(struct hclgevf_dev *hdev)
void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev)
{
if (!test_bit(HCLGEVF_STATE_REMOVING, &hdev->state) &&
+ test_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state) &&
!test_and_set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED,
&hdev->state))
mod_delayed_work(hclgevf_wq, &hdev->service_task, 0);
@@ -3449,6 +3450,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
hclgevf_init_rxd_adv_layout(hdev);
+ set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state);
+
hdev->last_reset_time = jiffies;
dev_info(&hdev->pdev->dev, "finished initializing %s driver\n",
HCLGEVF_DRIVER_NAME);
@@ -3899,7 +3902,7 @@ static int hclgevf_init(void)
{
pr_info("%s is initializing\n", HCLGEVF_NAME);
- hclgevf_wq = alloc_workqueue("%s", 0, 0, HCLGEVF_NAME);
+ hclgevf_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGEVF_NAME);
if (!hclgevf_wq) {
pr_err("%s: failed to create workqueue\n", HCLGEVF_NAME);
return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 883130a9b48f..28288d7e3303 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -146,6 +146,7 @@ enum hclgevf_states {
HCLGEVF_STATE_REMOVING,
HCLGEVF_STATE_NIC_REGISTERED,
HCLGEVF_STATE_ROCE_REGISTERED,
+ HCLGEVF_STATE_SERVICE_INITED,
/* task states */
HCLGEVF_STATE_RST_SERVICE_SCHED,
HCLGEVF_STATE_RST_HANDLING,
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 37c18c66b5c7..e375ac849aec 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -100,9 +100,9 @@ static void ice_display_lag_info(struct ice_lag *lag)
*/
static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
{
- struct net_device *event_netdev, *netdev_tmp;
struct netdev_notifier_bonding_info *info;
struct netdev_bonding_info *bonding_info;
+ struct net_device *event_netdev;
const char *lag_netdev_name;
event_netdev = netdev_notifier_info_to_dev(ptr);
@@ -123,19 +123,6 @@ static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
goto lag_out;
}
- rcu_read_lock();
- for_each_netdev_in_bond_rcu(lag->upper_netdev, netdev_tmp) {
- if (!netif_is_ice(netdev_tmp))
- continue;
-
- if (netdev_tmp && netdev_tmp != lag->netdev &&
- lag->peer_netdev != netdev_tmp) {
- dev_hold(netdev_tmp);
- lag->peer_netdev = netdev_tmp;
- }
- }
- rcu_read_unlock();
-
if (bonding_info->slave.state)
ice_lag_set_backup(lag);
else
@@ -319,6 +306,9 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
case NETDEV_BONDING_INFO:
ice_lag_info_event(lag, ptr);
break;
+ case NETDEV_UNREGISTER:
+ ice_lag_unlink(lag, ptr);
+ break;
default:
break;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 80380aed8882..d1ef3d48a4b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1571,6 +1571,9 @@ err_kworker:
*/
void ice_ptp_release(struct ice_pf *pf)
{
+ if (!test_bit(ICE_FLAG_PTP, pf->flags))
+ return;
+
/* Disable timestamping for both Tx and Rx */
ice_ptp_cfg_timestamp(pf, false);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 9338765da048..49d822a98ada 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -226,18 +226,85 @@ static const struct file_operations rvu_dbg_##name##_fops = { \
static void print_nix_qsize(struct seq_file *filp, struct rvu_pfvf *pfvf);
+static void get_lf_str_list(struct rvu_block block, int pcifunc,
+ char *lfs)
+{
+ int lf = 0, seq = 0, len = 0, prev_lf = block.lf.max;
+
+ for_each_set_bit(lf, block.lf.bmap, block.lf.max) {
+ if (lf >= block.lf.max)
+ break;
+
+ if (block.fn_map[lf] != pcifunc)
+ continue;
+
+ if (lf == prev_lf + 1) {
+ prev_lf = lf;
+ seq = 1;
+ continue;
+ }
+
+ if (seq)
+ len += sprintf(lfs + len, "-%d,%d", prev_lf, lf);
+ else
+ len += (len ? sprintf(lfs + len, ",%d", lf) :
+ sprintf(lfs + len, "%d", lf));
+
+ prev_lf = lf;
+ seq = 0;
+ }
+
+ if (seq)
+ len += sprintf(lfs + len, "-%d", prev_lf);
+
+ lfs[len] = '\0';
+}
+
+static int get_max_column_width(struct rvu *rvu)
+{
+ int index, pf, vf, lf_str_size = 12, buf_size = 256;
+ struct rvu_block block;
+ u16 pcifunc;
+ char *buf;
+
+ buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+ for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
+ pcifunc = pf << 10 | vf;
+ if (!pcifunc)
+ continue;
+
+ for (index = 0; index < BLK_COUNT; index++) {
+ block = rvu->hw->block[index];
+ if (!strlen(block.name))
+ continue;
+
+ get_lf_str_list(block, pcifunc, buf);
+ if (lf_str_size <= strlen(buf))
+ lf_str_size = strlen(buf) + 1;
+ }
+ }
+ }
+
+ kfree(buf);
+ return lf_str_size;
+}
+
/* Dumps current provisioning status of all RVU block LFs */
static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
char __user *buffer,
size_t count, loff_t *ppos)
{
- int index, off = 0, flag = 0, go_back = 0, len = 0;
+ int index, off = 0, flag = 0, len = 0, i = 0;
struct rvu *rvu = filp->private_data;
- int lf, pf, vf, pcifunc;
+ int bytes_not_copied = 0;
struct rvu_block block;
- int bytes_not_copied;
- int lf_str_size = 12;
+ int pf, vf, pcifunc;
int buf_size = 2048;
+ int lf_str_size;
char *lfs;
char *buf;
@@ -249,6 +316,9 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
if (!buf)
return -ENOSPC;
+ /* Get the maximum width of a column */
+ lf_str_size = get_max_column_width(rvu);
+
lfs = kzalloc(lf_str_size, GFP_KERNEL);
if (!lfs) {
kfree(buf);
@@ -262,65 +332,69 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
"%-*s", lf_str_size,
rvu->hw->block[index].name);
}
+
off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
+ bytes_not_copied = copy_to_user(buffer + (i * off), buf, off);
+ if (bytes_not_copied)
+ goto out;
+
+ i++;
+ *ppos += off;
for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
+ off = 0;
+ flag = 0;
pcifunc = pf << 10 | vf;
if (!pcifunc)
continue;
if (vf) {
sprintf(lfs, "PF%d:VF%d", pf, vf - 1);
- go_back = scnprintf(&buf[off],
- buf_size - 1 - off,
- "%-*s", lf_str_size, lfs);
+ off = scnprintf(&buf[off],
+ buf_size - 1 - off,
+ "%-*s", lf_str_size, lfs);
} else {
sprintf(lfs, "PF%d", pf);
- go_back = scnprintf(&buf[off],
- buf_size - 1 - off,
- "%-*s", lf_str_size, lfs);
+ off = scnprintf(&buf[off],
+ buf_size - 1 - off,
+ "%-*s", lf_str_size, lfs);
}
- off += go_back;
- for (index = 0; index < BLKTYPE_MAX; index++) {
+ for (index = 0; index < BLK_COUNT; index++) {
block = rvu->hw->block[index];
if (!strlen(block.name))
continue;
len = 0;
lfs[len] = '\0';
- for (lf = 0; lf < block.lf.max; lf++) {
- if (block.fn_map[lf] != pcifunc)
- continue;
+ get_lf_str_list(block, pcifunc, lfs);
+ if (strlen(lfs))
flag = 1;
- len += sprintf(&lfs[len], "%d,", lf);
- }
- if (flag)
- len--;
- lfs[len] = '\0';
off += scnprintf(&buf[off], buf_size - 1 - off,
"%-*s", lf_str_size, lfs);
- if (!strlen(lfs))
- go_back += lf_str_size;
}
- if (!flag)
- off -= go_back;
- else
- flag = 0;
- off--;
- off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
+ if (flag) {
+ off += scnprintf(&buf[off],
+ buf_size - 1 - off, "\n");
+ bytes_not_copied = copy_to_user(buffer +
+ (i * off),
+ buf, off);
+ if (bytes_not_copied)
+ goto out;
+
+ i++;
+ *ppos += off;
+ }
}
}
- bytes_not_copied = copy_to_user(buffer, buf, off);
+out:
kfree(lfs);
kfree(buf);
-
if (bytes_not_copied)
return -EFAULT;
- *ppos = off;
- return off;
+ return *ppos;
}
RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL);
@@ -504,7 +578,7 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp,
if (cmd_buf)
ret = -EINVAL;
- if (!strncmp(subtoken, "help", 4) || ret < 0) {
+ if (ret < 0 || !strncmp(subtoken, "help", 4)) {
dev_info(rvu->dev, "Use echo <%s-lf > qsize\n", blk_string);
goto qsize_write_done;
}
@@ -1719,6 +1793,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused)
u16 pcifunc;
char *str;
+ /* Ingress policers do not exist on all platforms */
+ if (!nix_hw->ipolicer)
+ return 0;
+
for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
if (layer == BAND_PROF_INVAL_LAYER)
continue;
@@ -1768,6 +1846,10 @@ static int rvu_dbg_nix_band_prof_rsrc_display(struct seq_file *m, void *unused)
int layer;
char *str;
+ /* Ingress policers do not exist on all platforms */
+ if (!nix_hw->ipolicer)
+ return 0;
+
seq_puts(m, "\nBandwidth profile resource free count\n");
seq_puts(m, "=====================================\n");
for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 9ef4e942e31e..6970540dc470 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2507,6 +2507,9 @@ static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc)
return;
nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ if (!nix_hw)
+ return;
+
vlan = &nix_hw->txvlan;
mutex_lock(&vlan->rsrc_lock);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 13b0259f7ea6..fcace73eae40 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -353,13 +353,10 @@ static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci,
struct sk_buff *skb;
int err;
- elem_info->u.rdq.skb = NULL;
skb = netdev_alloc_skb_ip_align(NULL, buf_len);
if (!skb)
return -ENOMEM;
- /* Assume that wqe was previously zeroed. */
-
err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data,
buf_len, DMA_FROM_DEVICE);
if (err)
@@ -597,21 +594,26 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
struct pci_dev *pdev = mlxsw_pci->pdev;
struct mlxsw_pci_queue_elem_info *elem_info;
struct mlxsw_rx_info rx_info = {};
- char *wqe;
+ char wqe[MLXSW_PCI_WQE_SIZE];
struct sk_buff *skb;
u16 byte_count;
int err;
elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
- skb = elem_info->u.sdq.skb;
- if (!skb)
- return;
- wqe = elem_info->elem;
- mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+ skb = elem_info->u.rdq.skb;
+ memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE);
if (q->consumer_counter++ != consumer_counter_limit)
dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
+ err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
+ if (err) {
+ dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+ goto out;
+ }
+
+ mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+
if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
rx_info.is_lag = true;
rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe);
@@ -647,10 +649,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
skb_put(skb, byte_count);
mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
- memset(wqe, 0, q->elem_size);
- err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
- if (err)
- dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+out:
/* Everything is set up, ring doorbell to pass elem to HW */
q->producer_counter++;
mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 9e8561cdc32a..4d5a5d6595b3 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1743,6 +1743,16 @@ static int lan743x_tx_ring_init(struct lan743x_tx *tx)
ret = -EINVAL;
goto cleanup;
}
+ if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev,
+ DMA_BIT_MASK(64))) {
+ if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev,
+ DMA_BIT_MASK(32))) {
+ dev_warn(&tx->adapter->pdev->dev,
+ "lan743x_: No suitable DMA available\n");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ }
ring_allocation_size = ALIGN(tx->ring_size *
sizeof(struct lan743x_tx_descriptor),
PAGE_SIZE);
@@ -1934,7 +1944,8 @@ static void lan743x_rx_update_tail(struct lan743x_rx *rx, int index)
index);
}
-static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index)
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+ gfp_t gfp)
{
struct net_device *netdev = rx->adapter->netdev;
struct device *dev = &rx->adapter->pdev->dev;
@@ -1948,7 +1959,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index)
descriptor = &rx->ring_cpu_ptr[index];
buffer_info = &rx->buffer_info[index];
- skb = __netdev_alloc_skb(netdev, buffer_length, GFP_ATOMIC | GFP_DMA);
+ skb = __netdev_alloc_skb(netdev, buffer_length, gfp);
if (!skb)
return -ENOMEM;
dma_ptr = dma_map_single(dev, skb->data, buffer_length, DMA_FROM_DEVICE);
@@ -2110,7 +2121,8 @@ static int lan743x_rx_process_buffer(struct lan743x_rx *rx)
/* save existing skb, allocate new skb and map to dma */
skb = buffer_info->skb;
- if (lan743x_rx_init_ring_element(rx, rx->last_head)) {
+ if (lan743x_rx_init_ring_element(rx, rx->last_head,
+ GFP_ATOMIC | GFP_DMA)) {
/* failed to allocate next skb.
* Memory is very low.
* Drop this packet and reuse buffer.
@@ -2276,6 +2288,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
ret = -EINVAL;
goto cleanup;
}
+ if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev,
+ DMA_BIT_MASK(64))) {
+ if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev,
+ DMA_BIT_MASK(32))) {
+ dev_warn(&rx->adapter->pdev->dev,
+ "lan743x_: No suitable DMA available\n");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ }
ring_allocation_size = ALIGN(rx->ring_size *
sizeof(struct lan743x_rx_descriptor),
PAGE_SIZE);
@@ -2315,13 +2337,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
rx->last_head = 0;
for (index = 0; index < rx->ring_size; index++) {
- ret = lan743x_rx_init_ring_element(rx, index);
+ ret = lan743x_rx_init_ring_element(rx, index, GFP_KERNEL);
if (ret)
goto cleanup;
}
return 0;
cleanup:
+ netif_warn(rx->adapter, ifup, rx->adapter->netdev,
+ "Error allocating memory for LAN743x\n");
+
lan743x_rx_ring_cleanup(rx);
return ret;
}
@@ -3019,6 +3044,8 @@ static int lan743x_pm_resume(struct device *dev)
if (ret) {
netif_err(adapter, probe, adapter->netdev,
"lan743x_hardware_init returned %d\n", ret);
+ lan743x_pci_cleanup(adapter);
+ return ret;
}
/* open netdev when netdev is at running state while resume.
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 11c83a99b014..f469950c7265 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -182,15 +182,21 @@ static int
nfp_bpf_check_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu)
{
struct nfp_net *nn = netdev_priv(netdev);
- unsigned int max_mtu;
+ struct nfp_bpf_vnic *bv;
+ struct bpf_prog *prog;
if (~nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
return 0;
- max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- if (new_mtu > max_mtu) {
- nn_info(nn, "BPF offload active, MTU over %u not supported\n",
- max_mtu);
+ if (nn->xdp_hw.prog) {
+ prog = nn->xdp_hw.prog;
+ } else {
+ bv = nn->app_priv;
+ prog = bv->tc_prog;
+ }
+
+ if (nfp_bpf_offload_check_mtu(nn, prog, new_mtu)) {
+ nn_info(nn, "BPF offload active, potential packet access beyond hardware packet boundary");
return -EBUSY;
}
return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index d0e17eebddd9..16841bb750b7 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -560,6 +560,8 @@ bool nfp_is_subprog_start(struct nfp_insn_meta *meta);
void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog);
int nfp_bpf_jit(struct nfp_prog *prog);
bool nfp_bpf_supported_opcode(u8 code);
+bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog,
+ unsigned int mtu);
int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
int prev_insn_idx);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 53851853562c..9d97cd281f18 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -481,19 +481,28 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
return 0;
}
+bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog,
+ unsigned int mtu)
+{
+ unsigned int fw_mtu, pkt_off;
+
+ fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
+ pkt_off = min(prog->aux->max_pkt_offset, mtu);
+
+ return fw_mtu < pkt_off;
+}
+
static int
nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
- unsigned int fw_mtu, pkt_off, max_stack, max_prog_len;
+ unsigned int max_stack, max_prog_len;
dma_addr_t dma_addr;
void *img;
int err;
- fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu);
- if (fw_mtu < pkt_off) {
+ if (nfp_bpf_offload_check_mtu(nn, prog, nn->dp.netdev->mtu)) {
NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary");
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index d29fe562b3de..c910fa2f40a4 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1015,9 +1015,6 @@ static int lpc_eth_close(struct net_device *ndev)
napi_disable(&pldat->napi);
netif_stop_queue(ndev);
- if (ndev->phydev)
- phy_stop(ndev->phydev);
-
spin_lock_irqsave(&pldat->lock, flags);
__lpc_eth_reset(pldat);
netif_carrier_off(ndev);
@@ -1025,6 +1022,8 @@ static int lpc_eth_close(struct net_device *ndev)
writel(0, LPC_ENET_MAC2(pldat->net_base));
spin_unlock_irqrestore(&pldat->lock, flags);
+ if (ndev->phydev)
+ phy_stop(ndev->phydev);
clk_disable_unprepare(pldat->clk);
return 0;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 46a6ff9a782d..2918947dd57c 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -157,6 +157,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
{ PCI_VDEVICE(REALTEK, 0x8129) },
{ PCI_VDEVICE(REALTEK, 0x8136), RTL_CFG_NO_GBIT },
{ PCI_VDEVICE(REALTEK, 0x8161) },
+ { PCI_VDEVICE(REALTEK, 0x8162) },
{ PCI_VDEVICE(REALTEK, 0x8167) },
{ PCI_VDEVICE(REALTEK, 0x8168) },
{ PCI_VDEVICE(NCUBE, 0x8168) },
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index f124a8a58bd4..a3bfb156c83d 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -243,62 +243,10 @@ static void phy_sanitize_settings(struct phy_device *phydev)
}
}
-int phy_ethtool_ksettings_set(struct phy_device *phydev,
- const struct ethtool_link_ksettings *cmd)
-{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
- u8 autoneg = cmd->base.autoneg;
- u8 duplex = cmd->base.duplex;
- u32 speed = cmd->base.speed;
-
- if (cmd->base.phy_address != phydev->mdio.addr)
- return -EINVAL;
-
- linkmode_copy(advertising, cmd->link_modes.advertising);
-
- /* We make sure that we don't pass unsupported values in to the PHY */
- linkmode_and(advertising, advertising, phydev->supported);
-
- /* Verify the settings we care about. */
- if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
- return -EINVAL;
-
- if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
- return -EINVAL;
-
- if (autoneg == AUTONEG_DISABLE &&
- ((speed != SPEED_1000 &&
- speed != SPEED_100 &&
- speed != SPEED_10) ||
- (duplex != DUPLEX_HALF &&
- duplex != DUPLEX_FULL)))
- return -EINVAL;
-
- phydev->autoneg = autoneg;
-
- if (autoneg == AUTONEG_DISABLE) {
- phydev->speed = speed;
- phydev->duplex = duplex;
- }
-
- linkmode_copy(phydev->advertising, advertising);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
- phydev->advertising, autoneg == AUTONEG_ENABLE);
-
- phydev->master_slave_set = cmd->base.master_slave_cfg;
- phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
-
- /* Restart the PHY */
- phy_start_aneg(phydev);
-
- return 0;
-}
-EXPORT_SYMBOL(phy_ethtool_ksettings_set);
-
void phy_ethtool_ksettings_get(struct phy_device *phydev,
struct ethtool_link_ksettings *cmd)
{
+ mutex_lock(&phydev->lock);
linkmode_copy(cmd->link_modes.supported, phydev->supported);
linkmode_copy(cmd->link_modes.advertising, phydev->advertising);
linkmode_copy(cmd->link_modes.lp_advertising, phydev->lp_advertising);
@@ -317,6 +265,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev,
cmd->base.autoneg = phydev->autoneg;
cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl;
cmd->base.eth_tp_mdix = phydev->mdix;
+ mutex_unlock(&phydev->lock);
}
EXPORT_SYMBOL(phy_ethtool_ksettings_get);
@@ -751,7 +700,7 @@ static int phy_check_link_status(struct phy_device *phydev)
}
/**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * _phy_start_aneg - start auto-negotiation for this PHY device
* @phydev: the phy_device struct
*
* Description: Sanitizes the settings (if we're not autonegotiating
@@ -759,25 +708,43 @@ static int phy_check_link_status(struct phy_device *phydev)
* If the PHYCONTROL Layer is operating, we change the state to
* reflect the beginning of Auto-negotiation or forcing.
*/
-int phy_start_aneg(struct phy_device *phydev)
+static int _phy_start_aneg(struct phy_device *phydev)
{
int err;
+ lockdep_assert_held(&phydev->lock);
+
if (!phydev->drv)
return -EIO;
- mutex_lock(&phydev->lock);
-
if (AUTONEG_DISABLE == phydev->autoneg)
phy_sanitize_settings(phydev);
err = phy_config_aneg(phydev);
if (err < 0)
- goto out_unlock;
+ return err;
if (phy_is_started(phydev))
err = phy_check_link_status(phydev);
-out_unlock:
+
+ return err;
+}
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ * them), and then calls the driver's config_aneg function.
+ * If the PHYCONTROL Layer is operating, we change the state to
+ * reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+ int err;
+
+ mutex_lock(&phydev->lock);
+ err = _phy_start_aneg(phydev);
mutex_unlock(&phydev->lock);
return err;
@@ -800,6 +767,61 @@ static int phy_poll_aneg_done(struct phy_device *phydev)
return ret < 0 ? ret : 0;
}
+int phy_ethtool_ksettings_set(struct phy_device *phydev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+ u8 autoneg = cmd->base.autoneg;
+ u8 duplex = cmd->base.duplex;
+ u32 speed = cmd->base.speed;
+
+ if (cmd->base.phy_address != phydev->mdio.addr)
+ return -EINVAL;
+
+ linkmode_copy(advertising, cmd->link_modes.advertising);
+
+ /* We make sure that we don't pass unsupported values in to the PHY */
+ linkmode_and(advertising, advertising, phydev->supported);
+
+ /* Verify the settings we care about. */
+ if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
+ return -EINVAL;
+
+ if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
+ return -EINVAL;
+
+ if (autoneg == AUTONEG_DISABLE &&
+ ((speed != SPEED_1000 &&
+ speed != SPEED_100 &&
+ speed != SPEED_10) ||
+ (duplex != DUPLEX_HALF &&
+ duplex != DUPLEX_FULL)))
+ return -EINVAL;
+
+ mutex_lock(&phydev->lock);
+ phydev->autoneg = autoneg;
+
+ if (autoneg == AUTONEG_DISABLE) {
+ phydev->speed = speed;
+ phydev->duplex = duplex;
+ }
+
+ linkmode_copy(phydev->advertising, advertising);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+ phydev->advertising, autoneg == AUTONEG_ENABLE);
+
+ phydev->master_slave_set = cmd->base.master_slave_cfg;
+ phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
+
+ /* Restart the PHY */
+ _phy_start_aneg(phydev);
+
+ mutex_unlock(&phydev->lock);
+ return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_ksettings_set);
+
/**
* phy_speed_down - set speed to lowest speed supported by both link partners
* @phydev: the phy_device struct
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 793f8fbe0069..63cd72c5f580 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4122,6 +4122,12 @@ static int lan78xx_probe(struct usb_interface *intf,
dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out, 1);
+ /* Reject broken descriptors. */
+ if (dev->maxpacket == 0) {
+ ret = -ENODEV;
+ goto out4;
+ }
+
/* driver requires remote-wakeup capability during autosuspend. */
intf->needs_remote_wakeup = 1;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 80432ee0ce69..a33d7fb82a00 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1790,6 +1790,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1);
if (dev->maxpacket == 0) {
/* that is a broken device */
+ status = -ENODEV;
goto out4;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 142f70670f5c..8799854bacb2 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3833,7 +3833,6 @@ vmxnet3_suspend(struct device *device)
vmxnet3_free_intr_resources(adapter);
netif_device_detach(netdev);
- netif_tx_stop_all_queues(netdev);
/* Create wake-up filters. */
pmConf = adapter->pm_conf;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e31b98403f31..fc41ba95f81d 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1730,6 +1730,10 @@ static int netfront_resume(struct xenbus_device *dev)
dev_dbg(&dev->dev, "%s\n", dev->nodename);
+ netif_tx_lock_bh(info->netdev);
+ netif_device_detach(info->netdev);
+ netif_tx_unlock_bh(info->netdev);
+
xennet_disconnect_backend(info);
return 0;
}
@@ -2349,6 +2353,10 @@ static int xennet_connect(struct net_device *dev)
* domain a kick because we've probably just requeued some
* packets.
*/
+ netif_tx_lock_bh(np->netdev);
+ netif_device_attach(np->netdev);
+ netif_tx_unlock_bh(np->netdev);
+
netif_carrier_on(np->netdev);
for (j = 0; j < num_queues; ++j) {
queue = &np->queues[j];
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index 517376c43b86..16ceb763594f 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -1006,11 +1006,11 @@ static u64 port100_get_command_type_mask(struct port100 *dev)
skb = port100_alloc_skb(dev, 0);
if (!skb)
- return -ENOMEM;
+ return 0;
resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_COMMAND_TYPE, skb);
if (IS_ERR(resp))
- return PTR_ERR(resp);
+ return 0;
if (resp->len < 8)
mask = 0;
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 088d3dd6f6fa..b6c6866f9259 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -162,7 +162,7 @@ static int nsblk_do_bvec(struct nd_namespace_blk *nsblk,
return err;
}
-static blk_qc_t nd_blk_submit_bio(struct bio *bio)
+static void nd_blk_submit_bio(struct bio *bio)
{
struct bio_integrity_payload *bip;
struct nd_namespace_blk *nsblk = bio->bi_bdev->bd_disk->private_data;
@@ -173,7 +173,7 @@ static blk_qc_t nd_blk_submit_bio(struct bio *bio)
bool do_acct;
if (!bio_integrity_prep(bio))
- return BLK_QC_T_NONE;
+ return;
bip = bio_integrity(bio);
rw = bio_data_dir(bio);
@@ -199,7 +199,6 @@ static blk_qc_t nd_blk_submit_bio(struct bio *bio)
bio_end_io_acct(bio, start);
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 92dec4952297..4295fa809420 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1440,7 +1440,7 @@ static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
return ret;
}
-static blk_qc_t btt_submit_bio(struct bio *bio)
+static void btt_submit_bio(struct bio *bio)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct btt *btt = bio->bi_bdev->bd_disk->private_data;
@@ -1451,7 +1451,7 @@ static blk_qc_t btt_submit_bio(struct bio *bio)
bool do_acct;
if (!bio_integrity_prep(bio))
- return BLK_QC_T_NONE;
+ return;
do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue);
if (do_acct)
@@ -1483,7 +1483,6 @@ static blk_qc_t btt_submit_bio(struct bio *bio)
bio_end_io_acct(bio, start);
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int btt_rw_page(struct block_device *bdev, sector_t sector,
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 7de592d7eff4..6a45fa91e8a3 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -7,6 +7,7 @@
#include <linux/export.h>
#include <linux/module.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/device.h>
#include <linux/ctype.h>
#include <linux/ndctl.h>
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index ef4950f80832..c74d7bceb222 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -190,7 +190,7 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem,
return rc;
}
-static blk_qc_t pmem_submit_bio(struct bio *bio)
+static void pmem_submit_bio(struct bio *bio)
{
int ret = 0;
blk_status_t rc = 0;
@@ -229,7 +229,6 @@ static blk_qc_t pmem_submit_bio(struct bio *bio)
bio->bi_status = errno_to_blk_status(ret);
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
@@ -333,26 +332,6 @@ static const struct attribute_group *pmem_attribute_groups[] = {
NULL,
};
-static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
- struct pmem_device *pmem = pgmap->owner;
-
- blk_cleanup_disk(pmem->disk);
-}
-
-static void pmem_release_queue(void *pgmap)
-{
- pmem_pagemap_cleanup(pgmap);
-}
-
-static void pmem_pagemap_kill(struct dev_pagemap *pgmap)
-{
- struct request_queue *q =
- container_of(pgmap->ref, struct request_queue, q_usage_counter);
-
- blk_freeze_queue_start(q);
-}
-
static void pmem_release_disk(void *__pmem)
{
struct pmem_device *pmem = __pmem;
@@ -360,12 +339,9 @@ static void pmem_release_disk(void *__pmem)
kill_dax(pmem->dax_dev);
put_dax(pmem->dax_dev);
del_gendisk(pmem->disk);
-}
-static const struct dev_pagemap_ops fsdax_pagemap_ops = {
- .kill = pmem_pagemap_kill,
- .cleanup = pmem_pagemap_cleanup,
-};
+ blk_cleanup_disk(pmem->disk);
+}
static int pmem_attach_disk(struct device *dev,
struct nd_namespace_common *ndns)
@@ -427,10 +403,8 @@ static int pmem_attach_disk(struct device *dev,
pmem->disk = disk;
pmem->pgmap.owner = pmem;
pmem->pfn_flags = PFN_DEV;
- pmem->pgmap.ref = &q->q_usage_counter;
if (is_nd_pfn(dev)) {
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
- pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pfn_sb = nd_pfn->pfn_sb;
pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -444,16 +418,12 @@ static int pmem_attach_disk(struct device *dev,
pmem->pgmap.range.end = res->end;
pmem->pgmap.nr_range = 1;
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
- pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pmem->pfn_flags |= PFN_MAP;
bb_range = pmem->pgmap.range;
} else {
addr = devm_memremap(dev, pmem->phys_addr,
pmem->size, ARCH_MEMREMAP_PMEM);
- if (devm_add_action_or_reset(dev, pmem_release_queue,
- &pmem->pgmap))
- return -ENOMEM;
bb_range.start = res->start;
bb_range.end = res->end;
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f8dd664b2eda..838b5e2058be 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -6,6 +6,7 @@
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
+#include <linux/blk-integrity.h>
#include <linux/compat.h>
#include <linux/delay.h>
#include <linux/errno.h>
@@ -118,25 +119,6 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
struct nvme_command *cmd);
-/*
- * Prepare a queue for teardown.
- *
- * This must forcibly unquiesce queues to avoid blocking dispatch, and only set
- * the capacity to 0 after that to avoid blocking dispatchers that may be
- * holding bd_butex. This will end buffered writers dirtying pages that can't
- * be synced.
- */
-static void nvme_set_queue_dying(struct nvme_ns *ns)
-{
- if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
- return;
-
- blk_set_queue_dying(ns->queue);
- blk_mq_unquiesce_queue(ns->queue);
-
- set_capacity_and_notify(ns->disk, 0);
-}
-
void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
/*
@@ -221,7 +203,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
{
dev_info(ctrl->device,
- "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn);
+ "Removing ctrl: NQN \"%s\"\n", nvmf_ctrl_subsysnqn(ctrl));
flush_work(&ctrl->reset_work);
nvme_stop_ctrl(ctrl);
@@ -345,15 +327,19 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
return RETRY;
}
-static inline void nvme_end_req(struct request *req)
+static inline void nvme_end_req_zoned(struct request *req)
{
- blk_status_t status = nvme_error_status(nvme_req(req)->status);
-
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
req_op(req) == REQ_OP_ZONE_APPEND)
req->__sector = nvme_lba_to_sect(req->q->queuedata,
le64_to_cpu(nvme_req(req)->result.u64));
+}
+
+static inline void nvme_end_req(struct request *req)
+{
+ blk_status_t status = nvme_error_status(nvme_req(req)->status);
+ nvme_end_req_zoned(req);
nvme_trace_bio_complete(req);
blk_mq_end_request(req, status);
}
@@ -380,6 +366,13 @@ void nvme_complete_rq(struct request *req)
}
EXPORT_SYMBOL_GPL(nvme_complete_rq);
+void nvme_complete_batch_req(struct request *req)
+{
+ nvme_cleanup_cmd(req);
+ nvme_end_req_zoned(req);
+}
+EXPORT_SYMBOL_GPL(nvme_complete_batch_req);
+
/*
* Called to unwind from ->queue_rq on a failed command submission so that the
* multipathing code gets called to potentially failover to another path.
@@ -631,7 +624,7 @@ static inline void nvme_init_request(struct request *req,
req->cmd_flags |= REQ_FAILFAST_DRIVER;
if (req->mq_hctx->type == HCTX_TYPE_POLL)
- req->cmd_flags |= REQ_HIPRI;
+ req->cmd_flags |= REQ_POLLED;
nvme_clear_nvme_request(req);
memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
}
@@ -822,6 +815,7 @@ static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
static inline void nvme_setup_flush(struct nvme_ns *ns,
struct nvme_command *cmnd)
{
+ memset(cmnd, 0, sizeof(*cmnd));
cmnd->common.opcode = nvme_cmd_flush;
cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
}
@@ -873,6 +867,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
return BLK_STS_IOERR;
}
+ memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->dsm.nr = cpu_to_le32(segments - 1);
@@ -889,6 +884,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd)
{
+ memset(cmnd, 0, sizeof(*cmnd));
+
if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
return nvme_setup_discard(ns, req, cmnd);
@@ -922,9 +919,15 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
cmnd->rw.opcode = op;
+ cmnd->rw.flags = 0;
cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
+ cmnd->rw.rsvd2 = 0;
+ cmnd->rw.metadata = 0;
cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+ cmnd->rw.reftag = 0;
+ cmnd->rw.apptag = 0;
+ cmnd->rw.appmask = 0;
if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);
@@ -981,10 +984,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
blk_status_t ret = BLK_STS_OK;
- if (!(req->rq_flags & RQF_DONTPREP)) {
+ if (!(req->rq_flags & RQF_DONTPREP))
nvme_clear_nvme_request(req);
- memset(cmd, 0, sizeof(*cmd));
- }
switch (req_op(req)) {
case REQ_OP_DRV_IN:
@@ -2600,6 +2601,24 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev,
}
static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);
+static ssize_t nvme_subsys_show_type(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_subsystem *subsys =
+ container_of(dev, struct nvme_subsystem, dev);
+
+ switch (subsys->subtype) {
+ case NVME_NQN_DISC:
+ return sysfs_emit(buf, "discovery\n");
+ case NVME_NQN_NVME:
+ return sysfs_emit(buf, "nvm\n");
+ default:
+ return sysfs_emit(buf, "reserved\n");
+ }
+}
+static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type);
+
#define nvme_subsys_show_str_function(field) \
static ssize_t subsys_##field##_show(struct device *dev, \
struct device_attribute *attr, char *buf) \
@@ -2620,6 +2639,7 @@ static struct attribute *nvme_subsys_attrs[] = {
&subsys_attr_serial.attr,
&subsys_attr_firmware_rev.attr,
&subsys_attr_subsysnqn.attr,
+ &subsys_attr_subsystype.attr,
#ifdef CONFIG_NVME_MULTIPATH
&subsys_attr_iopolicy.attr,
#endif
@@ -2690,6 +2710,21 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
subsys->vendor_id = le16_to_cpu(id->vid);
subsys->cmic = id->cmic;
+
+ /* Versions prior to 1.4 don't necessarily report a valid type */
+ if (id->cntrltype == NVME_CTRL_DISC ||
+ !strcmp(subsys->subnqn, NVME_DISC_SUBSYS_NAME))
+ subsys->subtype = NVME_NQN_DISC;
+ else
+ subsys->subtype = NVME_NQN_NVME;
+
+ if (nvme_discovery_ctrl(ctrl) && subsys->subtype != NVME_NQN_DISC) {
+ dev_err(ctrl->device,
+ "Subsystem %s is not a discovery controller",
+ subsys->subnqn);
+ kfree(subsys);
+ return -EINVAL;
+ }
subsys->awupf = le16_to_cpu(id->awupf);
#ifdef CONFIG_NVME_MULTIPATH
subsys->iopolicy = NVME_IOPOLICY_NUMA;
@@ -4473,6 +4508,37 @@ out:
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+static void nvme_start_ns_queue(struct nvme_ns *ns)
+{
+ if (test_and_clear_bit(NVME_NS_STOPPED, &ns->flags))
+ blk_mq_unquiesce_queue(ns->queue);
+}
+
+static void nvme_stop_ns_queue(struct nvme_ns *ns)
+{
+ if (!test_and_set_bit(NVME_NS_STOPPED, &ns->flags))
+ blk_mq_quiesce_queue(ns->queue);
+}
+
+/*
+ * Prepare a queue for teardown.
+ *
+ * This must forcibly unquiesce queues to avoid blocking dispatch, and only set
+ * the capacity to 0 after that to avoid blocking dispatchers that may be
+ * holding bd_butex. This will end buffered writers dirtying pages that can't
+ * be synced.
+ */
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+ if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+ return;
+
+ blk_set_queue_dying(ns->queue);
+ nvme_start_ns_queue(ns);
+
+ set_capacity_and_notify(ns->disk, 0);
+}
+
/**
* nvme_kill_queues(): Ends all namespace queues
* @ctrl: the dead controller that needs to end
@@ -4488,7 +4554,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
/* Forcibly unquiesce queues to avoid blocking dispatch */
if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
list_for_each_entry(ns, &ctrl->namespaces, list)
nvme_set_queue_dying(ns);
@@ -4551,7 +4617,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_quiesce_queue(ns->queue);
+ nvme_stop_ns_queue(ns);
up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_stop_queues);
@@ -4562,11 +4628,25 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_unquiesce_queue(ns->queue);
+ nvme_start_ns_queue(ns);
up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
+void nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
+{
+ if (!test_and_set_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
+ blk_mq_quiesce_queue(ctrl->admin_q);
+}
+EXPORT_SYMBOL_GPL(nvme_stop_admin_queue);
+
+void nvme_start_admin_queue(struct nvme_ctrl *ctrl)
+{
+ if (test_and_clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
+ blk_mq_unquiesce_queue(ctrl->admin_q);
+}
+EXPORT_SYMBOL_GPL(nvme_start_admin_queue);
+
void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 668c6bb7a567..c5a2b71c5268 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -548,6 +548,7 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" },
{ NVMF_OPT_TOS, "tos=%d" },
{ NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" },
+ { NVMF_OPT_DISCOVERY, "discovery" },
{ NVMF_OPT_ERR, NULL }
};
@@ -823,6 +824,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
opts->tos = token;
break;
+ case NVMF_OPT_DISCOVERY:
+ opts->discovery_nqn = true;
+ break;
default:
pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
p);
@@ -949,7 +953,7 @@ EXPORT_SYMBOL_GPL(nvmf_free_options);
#define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \
NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\
- NVMF_OPT_DISABLE_SQFLOW |\
+ NVMF_OPT_DISABLE_SQFLOW | NVMF_OPT_DISCOVERY |\
NVMF_OPT_FAIL_FAST_TMO)
static struct nvme_ctrl *
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index a146cb903869..c3203ff1c654 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -67,6 +67,7 @@ enum {
NVMF_OPT_TOS = 1 << 19,
NVMF_OPT_FAIL_FAST_TMO = 1 << 20,
NVMF_OPT_HOST_IFACE = 1 << 21,
+ NVMF_OPT_DISCOVERY = 1 << 22,
};
/**
@@ -178,6 +179,13 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
return true;
}
+static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl)
+{
+ if (!ctrl->subsys)
+ return ctrl->opts->subsysnqn;
+ return ctrl->subsys->subnqn;
+}
+
int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index aa14ad963d91..71b3108c22f0 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -16,6 +16,7 @@
#include <linux/nvme-fc.h>
#include "fc.h"
#include <scsi/scsi_transport_fc.h>
+#include <linux/blk-mq-pci.h>
/* *************************** Data Structures/Defines ****************** */
@@ -2382,7 +2383,7 @@ nvme_fc_ctrl_free(struct kref *ref)
list_del(&ctrl->ctrl_list);
spin_unlock_irqrestore(&ctrl->rport->lock, flags);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
blk_cleanup_queue(ctrl->ctrl.admin_q);
blk_cleanup_queue(ctrl->ctrl.fabrics_q);
blk_mq_free_tag_set(&ctrl->admin_tag_set);
@@ -2510,7 +2511,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
/*
* clean up the admin queue. Same thing as above.
*/
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_fc_terminate_exchange, &ctrl->ctrl);
@@ -2841,6 +2842,28 @@ nvme_fc_complete_rq(struct request *rq)
nvme_fc_ctrl_put(ctrl);
}
+static int nvme_fc_map_queues(struct blk_mq_tag_set *set)
+{
+ struct nvme_fc_ctrl *ctrl = set->driver_data;
+ int i;
+
+ for (i = 0; i < set->nr_maps; i++) {
+ struct blk_mq_queue_map *map = &set->map[i];
+
+ if (!map->nr_queues) {
+ WARN_ON(i == HCTX_TYPE_DEFAULT);
+ continue;
+ }
+
+ /* Call LLDD map queue functionality if defined */
+ if (ctrl->lport->ops->map_queues)
+ ctrl->lport->ops->map_queues(&ctrl->lport->localport,
+ map);
+ else
+ blk_mq_map_queues(map);
+ }
+ return 0;
+}
static const struct blk_mq_ops nvme_fc_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
@@ -2849,6 +2872,7 @@ static const struct blk_mq_ops nvme_fc_mq_ops = {
.exit_request = nvme_fc_exit_request,
.init_hctx = nvme_fc_init_hctx,
.timeout = nvme_fc_timeout,
+ .map_queues = nvme_fc_map_queues,
};
static int
@@ -3095,7 +3119,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
ctrl->ctrl.max_hw_sectors = ctrl->ctrl.max_segments <<
(ilog2(SZ_4K) - 9);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
ret = nvme_init_ctrl_finish(&ctrl->ctrl);
if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
@@ -3249,7 +3273,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
nvme_fc_free_queue(&ctrl->queues[0]);
/* re-enable the admin_q so anything new can fast fail */
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
/* resume the io queues so that things will fast fail */
nvme_start_queues(&ctrl->ctrl);
@@ -3572,7 +3596,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
- ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
+ ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
return &ctrl->ctrl;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index fba06618c6c2..7f2071f2460c 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -85,8 +85,13 @@ void nvme_failover_req(struct request *req)
}
spin_lock_irqsave(&ns->head->requeue_lock, flags);
- for (bio = req->bio; bio; bio = bio->bi_next)
+ for (bio = req->bio; bio; bio = bio->bi_next) {
bio_set_dev(bio, ns->head->disk->part0);
+ if (bio->bi_opf & REQ_POLLED) {
+ bio->bi_opf &= ~REQ_POLLED;
+ bio->bi_cookie = BLK_QC_T_NONE;
+ }
+ }
blk_steal_bios(&ns->head->requeue_list, req);
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
@@ -100,8 +105,11 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list) {
- if (ns->head->disk)
- kblockd_schedule_work(&ns->head->requeue_work);
+ if (!ns->head->disk)
+ continue;
+ kblockd_schedule_work(&ns->head->requeue_work);
+ if (ctrl->state == NVME_CTRL_LIVE)
+ disk_uevent(ns->head->disk, KOBJ_CHANGE);
}
up_read(&ctrl->namespaces_rwsem);
}
@@ -138,13 +146,12 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
- mutex_lock(&ctrl->scan_lock);
down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
- if (nvme_mpath_clear_current_path(ns))
- kblockd_schedule_work(&ns->head->requeue_work);
+ list_for_each_entry(ns, &ctrl->namespaces, list) {
+ nvme_mpath_clear_current_path(ns);
+ kblockd_schedule_work(&ns->head->requeue_work);
+ }
up_read(&ctrl->namespaces_rwsem);
- mutex_unlock(&ctrl->scan_lock);
}
void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -312,12 +319,11 @@ static bool nvme_available_path(struct nvme_ns_head *head)
return false;
}
-static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
+static void nvme_ns_head_submit_bio(struct bio *bio)
{
struct nvme_ns_head *head = bio->bi_bdev->bd_disk->private_data;
struct device *dev = disk_to_dev(head->disk);
struct nvme_ns *ns;
- blk_qc_t ret = BLK_QC_T_NONE;
int srcu_idx;
/*
@@ -334,7 +340,7 @@ static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
bio->bi_opf |= REQ_NVME_MPATH;
trace_block_bio_remap(bio, disk_devt(ns->head->disk),
bio->bi_iter.bi_sector);
- ret = submit_bio_noacct(bio);
+ submit_bio_noacct(bio);
} else if (nvme_available_path(head)) {
dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
@@ -349,7 +355,6 @@ static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
}
srcu_read_unlock(&head->srcu, srcu_idx);
- return ret;
}
static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode)
@@ -479,6 +484,15 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
+ /*
+ * This assumes all controllers that refer to a namespace either
+ * support poll queues or not. That is not a strict guarantee,
+ * but if the assumption is wrong the effect is only suboptimal
+ * performance but not correctness problem.
+ */
+ if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL &&
+ ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
+ blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
/* set to a default value of 512 until the disk is validated */
blk_queue_logical_block_size(head->disk->queue, 512);
@@ -494,13 +508,23 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
static void nvme_mpath_set_live(struct nvme_ns *ns)
{
struct nvme_ns_head *head = ns->head;
+ int rc;
if (!head->disk)
return;
+ /*
+ * test_and_set_bit() is used because it is protecting against two nvme
+ * paths simultaneously calling device_add_disk() on the same namespace
+ * head.
+ */
if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
- device_add_disk(&head->subsys->dev, head->disk,
- nvme_ns_id_attr_groups);
+ rc = device_add_disk(&head->subsys->dev, head->disk,
+ nvme_ns_id_attr_groups);
+ if (rc) {
+ clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+ return;
+ }
nvme_add_ns_head_cdev(head);
}
@@ -538,7 +562,7 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
return -EINVAL;
nr_nsids = le32_to_cpu(desc->nnsids);
- nsid_buf_size = nr_nsids * sizeof(__le32);
+ nsid_buf_size = flex_array_size(desc, nsids, nr_nsids);
if (WARN_ON_ONCE(desc->grpid == 0))
return -EINVAL;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ed79a6c7e804..b334af8aa264 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -342,6 +342,7 @@ struct nvme_ctrl {
int nr_reconnects;
unsigned long flags;
#define NVME_CTRL_FAILFAST_EXPIRED 0
+#define NVME_CTRL_ADMIN_Q_STOPPED 1
struct nvmf_ctrl_options *opts;
struct page *discard_page;
@@ -372,6 +373,7 @@ struct nvme_subsystem {
char model[40];
char firmware_rev[8];
u8 cmic;
+ enum nvme_subsys_type subtype;
u16 vendor_id;
u16 awupf; /* 0's based awupf value. */
struct ida ns_ida;
@@ -463,6 +465,7 @@ struct nvme_ns {
#define NVME_NS_ANA_PENDING 2
#define NVME_NS_FORCE_RO 3
#define NVME_NS_READY 4
+#define NVME_NS_STOPPED 5
struct cdev cdev;
struct device cdev_device;
@@ -638,6 +641,20 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
}
void nvme_complete_rq(struct request *req);
+void nvme_complete_batch_req(struct request *req);
+
+static __always_inline void nvme_complete_batch(struct io_comp_batch *iob,
+ void (*fn)(struct request *rq))
+{
+ struct request *req;
+
+ rq_list_for_each(&iob->req_list, req) {
+ fn(req);
+ nvme_complete_batch_req(req);
+ }
+ blk_mq_end_request_batch(iob);
+}
+
blk_status_t nvme_host_path_error(struct request *req);
bool nvme_cancel_request(struct request *req, void *data, bool reserved);
void nvme_cancel_tagset(struct nvme_ctrl *ctrl);
@@ -665,6 +682,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
+void nvme_stop_admin_queue(struct nvme_ctrl *ctrl);
+void nvme_start_admin_queue(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_sync_queues(struct nvme_ctrl *ctrl);
void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 149ecf73df38..ca2ee806d74b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -10,6 +10,7 @@
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-mq-pci.h>
+#include <linux/blk-integrity.h>
#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/interrupt.h>
@@ -244,8 +245,15 @@ static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
{
unsigned int mem_size = nvme_dbbuf_size(dev);
- if (dev->dbbuf_dbs)
+ if (dev->dbbuf_dbs) {
+ /*
+ * Clear the dbbuf memory so the driver doesn't observe stale
+ * values from the previous instantiation.
+ */
+ memset(dev->dbbuf_dbs, 0, mem_size);
+ memset(dev->dbbuf_eis, 0, mem_size);
return 0;
+ }
dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
&dev->dbbuf_dbs_dma_addr,
@@ -958,7 +966,7 @@ out_free_cmd:
return ret;
}
-static void nvme_pci_complete_rq(struct request *req)
+static __always_inline void nvme_pci_unmap_rq(struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct nvme_dev *dev = iod->nvmeq->dev;
@@ -968,9 +976,19 @@ static void nvme_pci_complete_rq(struct request *req)
rq_integrity_vec(req)->bv_len, rq_data_dir(req));
if (blk_rq_nr_phys_segments(req))
nvme_unmap_data(dev, req);
+}
+
+static void nvme_pci_complete_rq(struct request *req)
+{
+ nvme_pci_unmap_rq(req);
nvme_complete_rq(req);
}
+static void nvme_pci_complete_batch(struct io_comp_batch *iob)
+{
+ nvme_complete_batch(iob, nvme_pci_unmap_rq);
+}
+
/* We read the CQE phase first to check if the rest of the entry is valid */
static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
{
@@ -995,7 +1013,8 @@ static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
}
-static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
+static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
+ struct io_comp_batch *iob, u16 idx)
{
struct nvme_completion *cqe = &nvmeq->cqes[idx];
__u16 command_id = READ_ONCE(cqe->command_id);
@@ -1022,7 +1041,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
}
trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
- if (!nvme_try_complete_req(req, cqe->status, cqe->result))
+ if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
+ !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
+ nvme_pci_complete_batch))
nvme_pci_complete_rq(req);
}
@@ -1038,7 +1059,8 @@ static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
}
}
-static inline int nvme_process_cq(struct nvme_queue *nvmeq)
+static inline int nvme_poll_cq(struct nvme_queue *nvmeq,
+ struct io_comp_batch *iob)
{
int found = 0;
@@ -1049,7 +1071,7 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq)
* the cqe requires a full read memory barrier
*/
dma_rmb();
- nvme_handle_cqe(nvmeq, nvmeq->cq_head);
+ nvme_handle_cqe(nvmeq, iob, nvmeq->cq_head);
nvme_update_cq_head(nvmeq);
}
@@ -1061,9 +1083,13 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq)
static irqreturn_t nvme_irq(int irq, void *data)
{
struct nvme_queue *nvmeq = data;
+ DEFINE_IO_COMP_BATCH(iob);
- if (nvme_process_cq(nvmeq))
+ if (nvme_poll_cq(nvmeq, &iob)) {
+ if (!rq_list_empty(iob.req_list))
+ nvme_pci_complete_batch(&iob);
return IRQ_HANDLED;
+ }
return IRQ_NONE;
}
@@ -1087,11 +1113,11 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
- nvme_process_cq(nvmeq);
+ nvme_poll_cq(nvmeq, NULL);
enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
}
-static int nvme_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct nvme_queue *nvmeq = hctx->driver_data;
bool found;
@@ -1100,7 +1126,7 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx)
return 0;
spin_lock(&nvmeq->cq_poll_lock);
- found = nvme_process_cq(nvmeq);
+ found = nvme_poll_cq(nvmeq, iob);
spin_unlock(&nvmeq->cq_poll_lock);
return found;
@@ -1273,7 +1299,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
* Did we miss an interrupt?
*/
if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
- nvme_poll(req->mq_hctx);
+ nvme_poll(req->mq_hctx, NULL);
else
nvme_poll_irqdisable(nvmeq);
@@ -1395,7 +1421,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
nvmeq->dev->online_queues--;
if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
- blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
+ nvme_stop_admin_queue(&nvmeq->dev->ctrl);
if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags))
pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq);
return 0;
@@ -1433,7 +1459,7 @@ static void nvme_reap_pending_cqes(struct nvme_dev *dev)
for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
spin_lock(&dev->queues[i].cq_poll_lock);
- nvme_process_cq(&dev->queues[i]);
+ nvme_poll_cq(&dev->queues[i], NULL);
spin_unlock(&dev->queues[i].cq_poll_lock);
}
}
@@ -1654,7 +1680,7 @@ static void nvme_dev_remove_admin(struct nvme_dev *dev)
* user requests may be waiting on a stopped queue. Start the
* queue to flush these to completion.
*/
- blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+ nvme_start_admin_queue(&dev->ctrl);
blk_cleanup_queue(dev->ctrl.admin_q);
blk_mq_free_tag_set(&dev->admin_tagset);
}
@@ -1688,7 +1714,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
return -ENODEV;
}
} else
- blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+ nvme_start_admin_queue(&dev->ctrl);
return 0;
}
@@ -2623,7 +2649,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
if (shutdown) {
nvme_start_queues(&dev->ctrl);
if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
- blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+ nvme_start_admin_queue(&dev->ctrl);
}
mutex_unlock(&dev->shutdown_lock);
}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 042c594bc57e..850f84d204d0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -13,6 +13,7 @@
#include <linux/atomic.h>
#include <linux/blk-mq.h>
#include <linux/blk-mq-rdma.h>
+#include <linux/blk-integrity.h>
#include <linux/types.h>
#include <linux/list.h>
#include <linux/mutex.h>
@@ -918,7 +919,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
else
ctrl->ctrl.max_integrity_segments = 0;
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
error = nvme_init_ctrl_finish(&ctrl->ctrl);
if (error)
@@ -927,7 +928,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
return 0;
out_quiesce_queue:
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
out_stop_queue:
nvme_rdma_stop_queue(&ctrl->queues[0]);
@@ -1025,12 +1026,12 @@ out_free_io_queues:
static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_cancel_admin_tagset(&ctrl->ctrl);
if (remove)
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
nvme_rdma_destroy_admin_queue(ctrl, remove);
}
@@ -1095,11 +1096,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
return ret;
if (ctrl->ctrl.icdoff) {
+ ret = -EOPNOTSUPP;
dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
goto destroy_admin;
}
if (!(ctrl->ctrl.sgls & (1 << 2))) {
+ ret = -EOPNOTSUPP;
dev_err(ctrl->ctrl.device,
"Mandatory keyed sgls are not supported!\n");
goto destroy_admin;
@@ -1111,6 +1114,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
}
+ if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+ dev_warn(ctrl->ctrl.device,
+ "ctrl sqsize %u > max queue size %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
+ ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+ }
+
if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
dev_warn(ctrl->ctrl.device,
"sqsize %u > ctrl maxcmd %u, clamping down\n",
@@ -1153,7 +1163,7 @@ destroy_io:
nvme_rdma_destroy_io_queues(ctrl, new);
}
destroy_admin:
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_cancel_admin_tagset(&ctrl->ctrl);
@@ -1193,7 +1203,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
nvme_rdma_teardown_io_queues(ctrl, false);
nvme_start_queues(&ctrl->ctrl);
nvme_rdma_teardown_admin_queue(ctrl, false);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
/* state change failure is ok if we started ctrl delete */
@@ -2105,7 +2115,7 @@ unmap_qe:
return ret;
}
-static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct nvme_rdma_queue *queue = hctx->driver_data;
@@ -2231,7 +2241,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
cancel_delayed_work_sync(&ctrl->reconnect_work);
nvme_rdma_teardown_io_queues(ctrl, shutdown);
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
if (shutdown)
nvme_shutdown_ctrl(&ctrl->ctrl);
else
@@ -2385,7 +2395,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
goto out_uninit_ctrl;
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
- ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
mutex_lock(&nvme_rdma_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 3c1c29dd3020..33bc83d8d992 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -926,12 +926,14 @@ static void nvme_tcp_fail_request(struct nvme_tcp_request *req)
static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
{
struct nvme_tcp_queue *queue = req->queue;
+ int req_data_len = req->data_len;
while (true) {
struct page *page = nvme_tcp_req_cur_page(req);
size_t offset = nvme_tcp_req_cur_offset(req);
size_t len = nvme_tcp_req_cur_length(req);
bool last = nvme_tcp_pdu_last_send(req, len);
+ int req_data_sent = req->data_sent;
int ret, flags = MSG_DONTWAIT;
if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
@@ -958,7 +960,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
* in the request where we don't want to modify it as we may
* compete with the RX path completing the request.
*/
- if (req->data_sent + ret < req->data_len)
+ if (req_data_sent + ret < req_data_len)
nvme_tcp_advance_req(req, ret);
/* fully successful last send in current PDU */
@@ -1048,10 +1050,11 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
{
struct nvme_tcp_queue *queue = req->queue;
+ size_t offset = req->offset;
int ret;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
struct kvec iov = {
- .iov_base = &req->ddgst + req->offset,
+ .iov_base = (u8 *)&req->ddgst + req->offset,
.iov_len = NVME_TCP_DIGEST_LENGTH - req->offset
};
@@ -1064,7 +1067,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
if (unlikely(ret <= 0))
return ret;
- if (req->offset + ret == NVME_TCP_DIGEST_LENGTH) {
+ if (offset + ret == NVME_TCP_DIGEST_LENGTH) {
nvme_tcp_done_send_req(queue);
return 1;
}
@@ -1915,7 +1918,7 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
if (error)
goto out_stop_queue;
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
error = nvme_init_ctrl_finish(ctrl);
if (error)
@@ -1924,7 +1927,7 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
return 0;
out_quiesce_queue:
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
blk_sync_queue(ctrl->admin_q);
out_stop_queue:
nvme_tcp_stop_queue(ctrl, 0);
@@ -1946,12 +1949,12 @@ out_free_queue:
static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
bool remove)
{
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
nvme_cancel_admin_tagset(ctrl);
if (remove)
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
nvme_tcp_destroy_admin_queue(ctrl, remove);
}
@@ -1960,7 +1963,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
{
if (ctrl->queue_count <= 1)
return;
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
nvme_start_freeze(ctrl);
nvme_stop_queues(ctrl);
nvme_sync_io_queues(ctrl);
@@ -2055,7 +2058,7 @@ destroy_io:
nvme_tcp_destroy_io_queues(ctrl, new);
}
destroy_admin:
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
nvme_cancel_admin_tagset(ctrl);
@@ -2098,7 +2101,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
/* unquiesce to fail fast pending requests */
nvme_start_queues(ctrl);
nvme_tcp_teardown_admin_queue(ctrl, false);
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
/* state change failure is ok if we started ctrl delete */
@@ -2116,7 +2119,7 @@ static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
nvme_tcp_teardown_io_queues(ctrl, shutdown);
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
if (shutdown)
nvme_shutdown_ctrl(ctrl);
else
@@ -2429,7 +2432,7 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set)
return 0;
}
-static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct nvme_tcp_queue *queue = hctx->driver_data;
struct sock *sk = queue->sock->sk;
@@ -2582,7 +2585,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
goto out_uninit_ctrl;
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
- ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
mutex_lock(&nvme_tcp_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index d95010481fce..bfc259e0d7b8 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -233,6 +233,8 @@ out_free:
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *c, enum nvme_zone_mgmt_action action)
{
+ memset(c, 0, sizeof(*c));
+
c->zms.opcode = nvme_cmd_zone_mgmt_send;
c->zms.nsid = cpu_to_le32(ns->head->ns_id);
c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index aa6d84d8848e..6fb24746de06 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -264,7 +264,7 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
desc->state = req->port->ana_state[grpid];
memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
- return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+ return struct_size(desc, nsids, count);
}
static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
@@ -278,8 +278,8 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
u16 status;
status = NVME_SC_INTERNAL;
- desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
- NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+ desc = kmalloc(struct_size(desc, nsids, NVMET_MAX_NAMESPACES),
+ GFP_KERNEL);
if (!desc)
goto out;
@@ -374,13 +374,19 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->rab = 6;
+ if (nvmet_is_disc_subsys(ctrl->subsys))
+ id->cntrltype = NVME_CTRL_DISC;
+ else
+ id->cntrltype = NVME_CTRL_IO;
+
/*
* XXX: figure out how we can assign a IEEE OUI, but until then
* the safest is to leave it as zeroes.
*/
/* we support multiple ports, multiples hosts and ANA: */
- id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
+ id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL |
+ NVME_CTRL_CMIC_ANA;
/* Limit MDTS according to transport capability */
if (ctrl->ops->get_mdts)
@@ -536,7 +542,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
* Our namespace might always be shared. Not just with other
* controllers, but also with any other user of the block device.
*/
- id->nmic = (1 << 0);
+ id->nmic = NVME_NS_NMIC_SHARED;
id->anagrpid = cpu_to_le32(req->ns->anagrpid);
memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid));
@@ -1008,7 +1014,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
if (nvme_is_fabrics(cmd))
return nvmet_parse_fabrics_cmd(req);
- if (nvmet_req_subsys(req)->type == NVME_NQN_DISC)
+ if (nvmet_is_disc_subsys(nvmet_req_subsys(req)))
return nvmet_parse_discovery_cmd(req);
ret = nvmet_check_ctrl_status(req);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index be5d82421e3a..091a0ca16361 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1233,6 +1233,44 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
}
CONFIGFS_ATTR(nvmet_subsys_, attr_model);
+static ssize_t nvmet_subsys_attr_discovery_nqn_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%s\n",
+ nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_subsys_attr_discovery_nqn_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_subsys *subsys = to_subsys(item);
+ char *subsysnqn;
+ int len;
+
+ len = strcspn(page, "\n");
+ if (!len)
+ return -EINVAL;
+
+ subsysnqn = kmemdup_nul(page, len, GFP_KERNEL);
+ if (!subsysnqn)
+ return -ENOMEM;
+
+ /*
+ * The discovery NQN must be different from subsystem NQN.
+ */
+ if (!strcmp(subsysnqn, subsys->subsysnqn)) {
+ kfree(subsysnqn);
+ return -EBUSY;
+ }
+ down_write(&nvmet_config_sem);
+ kfree(nvmet_disc_subsys->subsysnqn);
+ nvmet_disc_subsys->subsysnqn = subsysnqn;
+ up_write(&nvmet_config_sem);
+
+ return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_discovery_nqn);
+
#ifdef CONFIG_BLK_DEV_INTEGRITY
static ssize_t nvmet_subsys_attr_pi_enable_show(struct config_item *item,
char *page)
@@ -1262,6 +1300,7 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = {
&nvmet_subsys_attr_attr_cntlid_min,
&nvmet_subsys_attr_attr_cntlid_max,
&nvmet_subsys_attr_attr_model,
+ &nvmet_subsys_attr_attr_discovery_nqn,
#ifdef CONFIG_BLK_DEV_INTEGRITY
&nvmet_subsys_attr_attr_pi_enable,
#endif
@@ -1553,6 +1592,8 @@ static void nvmet_port_release(struct config_item *item)
{
struct nvmet_port *port = to_nvmet_port(item);
+ /* Let inflight controllers teardown complete */
+ flush_scheduled_work();
list_del(&port->global_entry);
kfree(port->ana_state);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b8425fa34300..5119c687de68 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1140,7 +1140,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
* should verify iosqes,iocqes are zeroed, however that
* would break backwards compatibility, so don't enforce it.
*/
- if (ctrl->subsys->type != NVME_NQN_DISC &&
+ if (!nvmet_is_disc_subsys(ctrl->subsys) &&
(nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
ctrl->csts = NVME_CSTS_CFS;
@@ -1205,7 +1205,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
/* CC.EN timeout in 500msec units: */
ctrl->cap |= (15ULL << 24);
/* maximum queue entries supported: */
- ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+ if (ctrl->ops->get_max_queue_size)
+ ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+ else
+ ctrl->cap |= NVMET_QUEUE_SIZE - 1;
if (nvmet_is_passthru_subsys(ctrl->subsys))
nvmet_passthrough_override_cap(ctrl);
@@ -1278,7 +1281,7 @@ bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn)
if (subsys->allow_any_host)
return true;
- if (subsys->type == NVME_NQN_DISC) /* allow all access to disc subsys */
+ if (nvmet_is_disc_subsys(subsys)) /* allow all access to disc subsys */
return true;
list_for_each_entry(p, &subsys->hosts, entry) {
@@ -1367,6 +1370,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
mutex_init(&ctrl->lock);
ctrl->port = req->port;
+ ctrl->ops = req->ops;
INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
INIT_LIST_HEAD(&ctrl->async_events);
@@ -1405,13 +1409,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
}
ctrl->cntlid = ret;
- ctrl->ops = req->ops;
-
/*
* Discovery controllers may use some arbitrary high value
* in order to cleanup stale discovery sessions
*/
- if ((ctrl->subsys->type == NVME_NQN_DISC) && !kato)
+ if (nvmet_is_disc_subsys(ctrl->subsys) && !kato)
kato = NVMET_DISC_KATO_MS;
/* keep-alive timeout in seconds */
@@ -1491,7 +1493,8 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
if (!port)
return NULL;
- if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn)) {
+ if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn) ||
+ !strcmp(nvmet_disc_subsys->subsysnqn, subsysnqn)) {
if (!kref_get_unless_zero(&nvmet_disc_subsys->ref))
return NULL;
return nvmet_disc_subsys;
@@ -1538,6 +1541,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
subsys->max_qid = NVMET_NR_QUEUES;
break;
case NVME_NQN_DISC:
+ case NVME_NQN_CURR:
subsys->max_qid = 0;
break;
default:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 7aa62bc6ae84..c2162eef8ce1 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -146,7 +146,7 @@ static size_t discovery_log_entries(struct nvmet_req *req)
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmet_subsys_link *p;
struct nvmet_port *r;
- size_t entries = 0;
+ size_t entries = 1;
list_for_each_entry(p, &req->port->subsystems, entry) {
if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
@@ -171,6 +171,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
u32 numrec = 0;
u16 status = 0;
void *buffer;
+ char traddr[NVMF_TRADDR_SIZE];
if (!nvmet_check_transfer_len(req, data_len))
return;
@@ -203,15 +204,19 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
status = NVME_SC_INTERNAL;
goto out;
}
-
hdr = buffer;
- list_for_each_entry(p, &req->port->subsystems, entry) {
- char traddr[NVMF_TRADDR_SIZE];
+ nvmet_set_disc_traddr(req, req->port, traddr);
+
+ nvmet_format_discovery_entry(hdr, req->port,
+ nvmet_disc_subsys->subsysnqn,
+ traddr, NVME_NQN_CURR, numrec);
+ numrec++;
+
+ list_for_each_entry(p, &req->port->subsystems, entry) {
if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
continue;
- nvmet_set_disc_traddr(req, req->port, traddr);
nvmet_format_discovery_entry(hdr, req->port,
p->subsys->subsysnqn, traddr,
NVME_NQN_NVME, numrec);
@@ -268,6 +273,8 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
memcpy_and_pad(id->fr, sizeof(id->fr),
UTS_RELEASE, strlen(UTS_RELEASE), ' ');
+ id->cntrltype = NVME_CTRL_DISC;
+
/* no limit on data transfer sizes for now */
id->mdts = 0;
id->cntlid = cpu_to_le16(ctrl->cntlid);
@@ -387,7 +394,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
int __init nvmet_init_discovery(void)
{
nvmet_disc_subsys =
- nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC);
+ nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_CURR);
return PTR_ERR_OR_ZERO(nvmet_disc_subsys);
}
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 7d0454cee920..70fb587e9413 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -221,7 +221,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
goto out;
}
- pr_info("creating controller %d for subsystem %s for NQN %s%s.\n",
+ pr_info("creating %s controller %d for subsystem %s for NQN %s%s.\n",
+ nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm",
ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn,
ctrl->pi_support ? " T10-PI is enabled" : "");
req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 0fc2781ab970..70ca9dfc1771 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -5,6 +5,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/module.h>
#include "nvmet.h"
@@ -86,7 +87,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
ns->bdev = NULL;
return ret;
}
- ns->size = i_size_read(ns->bdev->bd_inode);
+ ns->size = bdev_nr_bytes(ns->bdev);
ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
ns->pi_type = 0;
@@ -107,7 +108,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns)
{
- ns->size = i_size_read(ns->bdev->bd_inode);
+ ns->size = bdev_nr_bytes(ns->bdev);
}
u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 1dd1a0fe2e81..6aa30f30b572 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -125,7 +125,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
return call_iter(iocb, &iter);
}
-static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
+static void nvmet_file_io_done(struct kiocb *iocb, long ret)
{
struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
u16 status = NVME_SC_SUCCESS;
@@ -222,7 +222,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
}
complete:
- nvmet_file_io_done(&req->f.iocb, ret, 0);
+ nvmet_file_io_done(&req->f.iocb, ret);
return true;
}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 0285ccc7541f..eb1094254c82 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -384,6 +384,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
error = PTR_ERR(ctrl->ctrl.admin_q);
goto out_cleanup_fabrics_q;
}
+ /* reset stopped state for the fresh admin queue */
+ clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->ctrl.flags);
error = nvmf_connect_admin_queue(&ctrl->ctrl);
if (error)
@@ -398,7 +400,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
ctrl->ctrl.max_hw_sectors =
(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
error = nvme_init_ctrl_finish(&ctrl->ctrl);
if (error)
@@ -428,7 +430,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
nvme_loop_destroy_io_queues(ctrl);
}
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
if (ctrl->ctrl.state == NVME_CTRL_LIVE)
nvme_shutdown_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 7143c7fa7464..af193423c10b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -309,6 +309,7 @@ struct nvmet_fabrics_ops {
u16 (*install_queue)(struct nvmet_sq *nvme_sq);
void (*discovery_chg)(struct nvmet_port *port);
u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
+ u16 (*get_max_queue_size)(const struct nvmet_ctrl *ctrl);
};
#define NVMET_MAX_INLINE_BIOVEC 8
@@ -576,6 +577,11 @@ static inline struct nvmet_subsys *nvmet_req_subsys(struct nvmet_req *req)
return req->sq->ctrl->subsys;
}
+static inline bool nvmet_is_disc_subsys(struct nvmet_subsys *subsys)
+{
+ return subsys->type != NVME_NQN_NVME;
+}
+
#ifdef CONFIG_NVME_TARGET_PASSTHRU
void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys);
int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 891174ccd44b..1deb4043e242 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -5,6 +5,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/atomic.h>
+#include <linux/blk-integrity.h>
#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/err.h>
@@ -1818,12 +1819,36 @@ restart:
mutex_unlock(&nvmet_rdma_queue_mutex);
}
+static void nvmet_rdma_destroy_port_queues(struct nvmet_rdma_port *port)
+{
+ struct nvmet_rdma_queue *queue, *tmp;
+ struct nvmet_port *nport = port->nport;
+
+ mutex_lock(&nvmet_rdma_queue_mutex);
+ list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list,
+ queue_list) {
+ if (queue->port != nport)
+ continue;
+
+ list_del_init(&queue->queue_list);
+ __nvmet_rdma_queue_disconnect(queue);
+ }
+ mutex_unlock(&nvmet_rdma_queue_mutex);
+}
+
static void nvmet_rdma_disable_port(struct nvmet_rdma_port *port)
{
struct rdma_cm_id *cm_id = xchg(&port->cm_id, NULL);
if (cm_id)
rdma_destroy_id(cm_id);
+
+ /*
+ * Destroy the remaining queues, which are not belong to any
+ * controller yet. Do it here after the RDMA-CM was destroyed
+ * guarantees that no new queue will be created.
+ */
+ nvmet_rdma_destroy_port_queues(port);
}
static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
@@ -1975,6 +2000,11 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
return NVMET_RDMA_MAX_MDTS;
}
+static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
+{
+ return NVME_RDMA_MAX_QUEUE_SIZE;
+}
+
static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_RDMA,
@@ -1986,6 +2016,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.delete_ctrl = nvmet_rdma_delete_ctrl,
.disc_traddr = nvmet_rdma_disc_port_addr,
.get_mdts = nvmet_rdma_get_mdts,
+ .get_max_queue_size = nvmet_rdma_get_max_queue_size,
};
static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 07ee347ea3f3..84c387e4bf43 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -702,7 +702,7 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
struct nvmet_tcp_queue *queue = cmd->queue;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
struct kvec iov = {
- .iov_base = &cmd->exp_ddgst + cmd->offset,
+ .iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset,
.iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset
};
int ret;
@@ -1096,7 +1096,7 @@ recv:
}
if (queue->hdr_digest &&
- nvmet_tcp_verify_hdgst(queue, &queue->pdu, queue->offset)) {
+ nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) {
nvmet_tcp_fatal_error(queue); /* fatal */
return -EPROTO;
}
@@ -1428,6 +1428,7 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
static void nvmet_tcp_release_queue_work(struct work_struct *w)
{
+ struct page *page;
struct nvmet_tcp_queue *queue =
container_of(w, struct nvmet_tcp_queue, release_work);
@@ -1447,6 +1448,8 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
nvmet_tcp_free_crypto(queue);
ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
+ page = virt_to_head_page(queue->pf_cache.va);
+ __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
kfree(queue);
}
@@ -1737,6 +1740,17 @@ err_port:
return ret;
}
+static void nvmet_tcp_destroy_port_queues(struct nvmet_tcp_port *port)
+{
+ struct nvmet_tcp_queue *queue;
+
+ mutex_lock(&nvmet_tcp_queue_mutex);
+ list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
+ if (queue->port == port)
+ kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+ mutex_unlock(&nvmet_tcp_queue_mutex);
+}
+
static void nvmet_tcp_remove_port(struct nvmet_port *nport)
{
struct nvmet_tcp_port *port = nport->priv;
@@ -1746,6 +1760,11 @@ static void nvmet_tcp_remove_port(struct nvmet_port *nport)
port->sock->sk->sk_user_data = NULL;
write_unlock_bh(&port->sock->sk->sk_callback_lock);
cancel_work_sync(&port->accept_work);
+ /*
+ * Destroy the remaining queues, which are not belong to any
+ * controller yet.
+ */
+ nvmet_tcp_destroy_port_queues(port);
sock_release(port->sock);
kfree(port);
diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig
index be799a5abf8a..b0056ae5d463 100644
--- a/drivers/reset/Kconfig
+++ b/drivers/reset/Kconfig
@@ -147,8 +147,8 @@ config RESET_OXNAS
bool
config RESET_PISTACHIO
- bool "Pistachio Reset Driver" if COMPILE_TEST
- default MACH_PISTACHIO
+ bool "Pistachio Reset Driver"
+ depends on MIPS || COMPILE_TEST
help
This enables the reset driver for ImgTec Pistachio SoCs.
diff --git a/drivers/reset/reset-brcmstb-rescal.c b/drivers/reset/reset-brcmstb-rescal.c
index b6f074d6a65f..433fa0c40e47 100644
--- a/drivers/reset/reset-brcmstb-rescal.c
+++ b/drivers/reset/reset-brcmstb-rescal.c
@@ -38,7 +38,7 @@ static int brcm_rescal_reset_set(struct reset_controller_dev *rcdev,
}
ret = readl_poll_timeout(base + BRCM_RESCAL_STATUS, reg,
- !(reg & BRCM_RESCAL_STATUS_BIT), 100, 1000);
+ (reg & BRCM_RESCAL_STATUS_BIT), 100, 1000);
if (ret) {
dev_err(data->dev, "time out on SATA/PCIe rescal\n");
return ret;
diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c
index 2a72f861f798..8c6492e5693c 100644
--- a/drivers/reset/reset-socfpga.c
+++ b/drivers/reset/reset-socfpga.c
@@ -92,3 +92,29 @@ void __init socfpga_reset_init(void)
for_each_matching_node(np, socfpga_early_reset_dt_ids)
a10_reset_init(np);
}
+
+/*
+ * The early driver is problematic, because it doesn't register
+ * itself as a driver. This causes certain device links to prevent
+ * consumer devices from probing. The hacky solution is to register
+ * an empty driver, whose only job is to attach itself to the reset
+ * manager and call probe.
+ */
+static const struct of_device_id socfpga_reset_dt_ids[] = {
+ { .compatible = "altr,rst-mgr", },
+ { /* sentinel */ },
+};
+
+static int reset_simple_probe(struct platform_device *pdev)
+{
+ return 0;
+}
+
+static struct platform_driver reset_socfpga_driver = {
+ .probe = reset_simple_probe,
+ .driver = {
+ .name = "socfpga-reset",
+ .of_match_table = socfpga_reset_dt_ids,
+ },
+};
+builtin_platform_driver(reset_socfpga_driver);
diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c
index 24d3395964cc..4c5bba52b105 100644
--- a/drivers/reset/tegra/reset-bpmp.c
+++ b/drivers/reset/tegra/reset-bpmp.c
@@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc,
struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc);
struct mrq_reset_request request;
struct tegra_bpmp_message msg;
+ int err;
memset(&request, 0, sizeof(request));
request.cmd = command;
@@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc,
msg.tx.data = &request;
msg.tx.size = sizeof(request);
- return tegra_bpmp_transfer(bpmp, &msg);
+ err = tegra_bpmp_transfer(bpmp, &msg);
+ if (err)
+ return err;
+ if (msg.rx.ret)
+ return -EINVAL;
+
+ return 0;
}
static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc,
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index e34c6cc61983..8e87a31e329d 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2077,12 +2077,15 @@ static void __dasd_device_check_path_events(struct dasd_device *device)
if (device->stopped & ~(DASD_STOPPED_DC_WAIT))
return;
+
+ dasd_path_clear_all_verify(device);
+ dasd_path_clear_all_fcsec(device);
+
rc = device->discipline->pe_handler(device, tbvpm, fcsecpm);
if (rc) {
+ dasd_path_add_tbvpm(device, tbvpm);
+ dasd_path_add_fcsecpm(device, fcsecpm);
dasd_device_set_timer(device, 50);
- } else {
- dasd_path_clear_all_verify(device);
- dasd_path_clear_all_fcsec(device);
}
};
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index 4691a3c35d72..299001ad9a32 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -201,7 +201,7 @@ dasd_3990_erp_DCTL(struct dasd_ccw_req * erp, char modifier)
struct ccw1 *ccw;
struct dasd_ccw_req *dctl_cqr;
- dctl_cqr = dasd_alloc_erp_request((char *) &erp->magic, 1,
+ dctl_cqr = dasd_alloc_erp_request(erp->magic, 1,
sizeof(struct DCTL_data),
device);
if (IS_ERR(dctl_cqr)) {
@@ -1652,7 +1652,7 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense)
}
/* Build new ERP request including DE/LO */
- erp = dasd_alloc_erp_request((char *) &cqr->magic,
+ erp = dasd_alloc_erp_request(cqr->magic,
2 + 1,/* DE/LO + TIC */
sizeof(struct DE_eckd_data) +
sizeof(struct LO_eckd_data), device);
@@ -2388,7 +2388,7 @@ static struct dasd_ccw_req *dasd_3990_erp_add_erp(struct dasd_ccw_req *cqr)
}
/* allocate additional request block */
- erp = dasd_alloc_erp_request((char *) &cqr->magic,
+ erp = dasd_alloc_erp_request(cqr->magic,
cplength, datasize, device);
if (IS_ERR(erp)) {
if (cqr->retries <= 0) {
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 460e0f1cca53..8410a25a65c1 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -560,8 +560,8 @@ static int prefix_LRE(struct ccw1 *ccw, struct PFX_eckd_data *pfxdata,
return -EINVAL;
}
pfxdata->format = format;
- pfxdata->base_address = basepriv->ned->unit_addr;
- pfxdata->base_lss = basepriv->ned->ID;
+ pfxdata->base_address = basepriv->conf.ned->unit_addr;
+ pfxdata->base_lss = basepriv->conf.ned->ID;
pfxdata->validity.define_extent = 1;
/* private uid is kept up to date, conf_data may be outdated */
@@ -736,32 +736,30 @@ dasd_eckd_cdl_reclen(int recid)
return LABEL_SIZE;
}
/* create unique id from private structure. */
-static void create_uid(struct dasd_eckd_private *private)
+static void create_uid(struct dasd_conf *conf, struct dasd_uid *uid)
{
int count;
- struct dasd_uid *uid;
- uid = &private->uid;
memset(uid, 0, sizeof(struct dasd_uid));
- memcpy(uid->vendor, private->ned->HDA_manufacturer,
+ memcpy(uid->vendor, conf->ned->HDA_manufacturer,
sizeof(uid->vendor) - 1);
EBCASC(uid->vendor, sizeof(uid->vendor) - 1);
- memcpy(uid->serial, &private->ned->serial,
+ memcpy(uid->serial, &conf->ned->serial,
sizeof(uid->serial) - 1);
EBCASC(uid->serial, sizeof(uid->serial) - 1);
- uid->ssid = private->gneq->subsystemID;
- uid->real_unit_addr = private->ned->unit_addr;
- if (private->sneq) {
- uid->type = private->sneq->sua_flags;
+ uid->ssid = conf->gneq->subsystemID;
+ uid->real_unit_addr = conf->ned->unit_addr;
+ if (conf->sneq) {
+ uid->type = conf->sneq->sua_flags;
if (uid->type == UA_BASE_PAV_ALIAS)
- uid->base_unit_addr = private->sneq->base_unit_addr;
+ uid->base_unit_addr = conf->sneq->base_unit_addr;
} else {
uid->type = UA_BASE_DEVICE;
}
- if (private->vdsneq) {
+ if (conf->vdsneq) {
for (count = 0; count < 16; count++) {
sprintf(uid->vduit+2*count, "%02x",
- private->vdsneq->uit[count]);
+ conf->vdsneq->uit[count]);
}
}
}
@@ -776,10 +774,10 @@ static int dasd_eckd_generate_uid(struct dasd_device *device)
if (!private)
return -ENODEV;
- if (!private->ned || !private->gneq)
+ if (!private->conf.ned || !private->conf.gneq)
return -ENODEV;
spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
- create_uid(private);
+ create_uid(&private->conf, &private->uid);
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
return 0;
}
@@ -803,14 +801,15 @@ static int dasd_eckd_get_uid(struct dasd_device *device, struct dasd_uid *uid)
* return 0 for match
*/
static int dasd_eckd_compare_path_uid(struct dasd_device *device,
- struct dasd_eckd_private *private)
+ struct dasd_conf *path_conf)
{
struct dasd_uid device_uid;
+ struct dasd_uid path_uid;
- create_uid(private);
+ create_uid(path_conf, &path_uid);
dasd_eckd_get_uid(device, &device_uid);
- return memcmp(&device_uid, &private->uid, sizeof(struct dasd_uid));
+ return memcmp(&device_uid, &path_uid, sizeof(struct dasd_uid));
}
static void dasd_eckd_fill_rcd_cqr(struct dasd_device *device,
@@ -946,34 +945,34 @@ out_error:
return ret;
}
-static int dasd_eckd_identify_conf_parts(struct dasd_eckd_private *private)
+static int dasd_eckd_identify_conf_parts(struct dasd_conf *conf)
{
struct dasd_sneq *sneq;
int i, count;
- private->ned = NULL;
- private->sneq = NULL;
- private->vdsneq = NULL;
- private->gneq = NULL;
- count = private->conf_len / sizeof(struct dasd_sneq);
- sneq = (struct dasd_sneq *)private->conf_data;
+ conf->ned = NULL;
+ conf->sneq = NULL;
+ conf->vdsneq = NULL;
+ conf->gneq = NULL;
+ count = conf->len / sizeof(struct dasd_sneq);
+ sneq = (struct dasd_sneq *)conf->data;
for (i = 0; i < count; ++i) {
if (sneq->flags.identifier == 1 && sneq->format == 1)
- private->sneq = sneq;
+ conf->sneq = sneq;
else if (sneq->flags.identifier == 1 && sneq->format == 4)
- private->vdsneq = (struct vd_sneq *)sneq;
+ conf->vdsneq = (struct vd_sneq *)sneq;
else if (sneq->flags.identifier == 2)
- private->gneq = (struct dasd_gneq *)sneq;
+ conf->gneq = (struct dasd_gneq *)sneq;
else if (sneq->flags.identifier == 3 && sneq->res1 == 1)
- private->ned = (struct dasd_ned *)sneq;
+ conf->ned = (struct dasd_ned *)sneq;
sneq++;
}
- if (!private->ned || !private->gneq) {
- private->ned = NULL;
- private->sneq = NULL;
- private->vdsneq = NULL;
- private->gneq = NULL;
+ if (!conf->ned || !conf->gneq) {
+ conf->ned = NULL;
+ conf->sneq = NULL;
+ conf->vdsneq = NULL;
+ conf->gneq = NULL;
return -EINVAL;
}
return 0;
@@ -1016,9 +1015,9 @@ static void dasd_eckd_store_conf_data(struct dasd_device *device,
* with the new one if this points to the same data
*/
cdp = device->path[chp].conf_data;
- if (private->conf_data == cdp) {
- private->conf_data = (void *)conf_data;
- dasd_eckd_identify_conf_parts(private);
+ if (private->conf.data == cdp) {
+ private->conf.data = (void *)conf_data;
+ dasd_eckd_identify_conf_parts(&private->conf);
}
ccw_device_get_schid(device->cdev, &sch_id);
device->path[chp].conf_data = conf_data;
@@ -1036,8 +1035,8 @@ static void dasd_eckd_clear_conf_data(struct dasd_device *device)
struct dasd_eckd_private *private = device->private;
int i;
- private->conf_data = NULL;
- private->conf_len = 0;
+ private->conf.data = NULL;
+ private->conf.len = 0;
for (i = 0; i < 8; i++) {
kfree(device->path[i].conf_data);
device->path[i].conf_data = NULL;
@@ -1071,15 +1070,55 @@ static void dasd_eckd_read_fc_security(struct dasd_device *device)
}
}
+static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
+ char *print_uid)
+{
+ struct dasd_uid uid;
+
+ create_uid(conf, &uid);
+ if (strlen(uid.vduit) > 0)
+ snprintf(print_uid, sizeof(*print_uid),
+ "%s.%s.%04x.%02x.%s",
+ uid.vendor, uid.serial, uid.ssid,
+ uid.real_unit_addr, uid.vduit);
+ else
+ snprintf(print_uid, sizeof(*print_uid),
+ "%s.%s.%04x.%02x",
+ uid.vendor, uid.serial, uid.ssid,
+ uid.real_unit_addr);
+}
+
+static int dasd_eckd_check_cabling(struct dasd_device *device,
+ void *conf_data, __u8 lpm)
+{
+ struct dasd_eckd_private *private = device->private;
+ char print_path_uid[60], print_device_uid[60];
+ struct dasd_conf path_conf;
+
+ path_conf.data = conf_data;
+ path_conf.len = DASD_ECKD_RCD_DATA_SIZE;
+ if (dasd_eckd_identify_conf_parts(&path_conf))
+ return 1;
+
+ if (dasd_eckd_compare_path_uid(device, &path_conf)) {
+ dasd_eckd_get_uid_string(&path_conf, print_path_uid);
+ dasd_eckd_get_uid_string(&private->conf, print_device_uid);
+ dev_err(&device->cdev->dev,
+ "Not all channel paths lead to the same device, path %02X leads to device %s instead of %s\n",
+ lpm, print_path_uid, print_device_uid);
+ return 1;
+ }
+
+ return 0;
+}
+
static int dasd_eckd_read_conf(struct dasd_device *device)
{
void *conf_data;
int conf_len, conf_data_saved;
int rc, path_err, pos;
__u8 lpm, opm;
- struct dasd_eckd_private *private, path_private;
- struct dasd_uid *uid;
- char print_path_uid[60], print_device_uid[60];
+ struct dasd_eckd_private *private;
private = device->private;
opm = ccw_device_get_path_mask(device->cdev);
@@ -1109,11 +1148,11 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
if (!conf_data_saved) {
/* initially clear previously stored conf_data */
dasd_eckd_clear_conf_data(device);
- private->conf_data = conf_data;
- private->conf_len = conf_len;
- if (dasd_eckd_identify_conf_parts(private)) {
- private->conf_data = NULL;
- private->conf_len = 0;
+ private->conf.data = conf_data;
+ private->conf.len = conf_len;
+ if (dasd_eckd_identify_conf_parts(&private->conf)) {
+ private->conf.data = NULL;
+ private->conf.len = 0;
kfree(conf_data);
continue;
}
@@ -1123,59 +1162,11 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
*/
dasd_eckd_generate_uid(device);
conf_data_saved++;
- } else {
- path_private.conf_data = conf_data;
- path_private.conf_len = DASD_ECKD_RCD_DATA_SIZE;
- if (dasd_eckd_identify_conf_parts(
- &path_private)) {
- path_private.conf_data = NULL;
- path_private.conf_len = 0;
- kfree(conf_data);
- continue;
- }
- if (dasd_eckd_compare_path_uid(
- device, &path_private)) {
- uid = &path_private.uid;
- if (strlen(uid->vduit) > 0)
- snprintf(print_path_uid,
- sizeof(print_path_uid),
- "%s.%s.%04x.%02x.%s",
- uid->vendor, uid->serial,
- uid->ssid, uid->real_unit_addr,
- uid->vduit);
- else
- snprintf(print_path_uid,
- sizeof(print_path_uid),
- "%s.%s.%04x.%02x",
- uid->vendor, uid->serial,
- uid->ssid,
- uid->real_unit_addr);
- uid = &private->uid;
- if (strlen(uid->vduit) > 0)
- snprintf(print_device_uid,
- sizeof(print_device_uid),
- "%s.%s.%04x.%02x.%s",
- uid->vendor, uid->serial,
- uid->ssid, uid->real_unit_addr,
- uid->vduit);
- else
- snprintf(print_device_uid,
- sizeof(print_device_uid),
- "%s.%s.%04x.%02x",
- uid->vendor, uid->serial,
- uid->ssid,
- uid->real_unit_addr);
- dev_err(&device->cdev->dev,
- "Not all channel paths lead to "
- "the same device, path %02X leads to "
- "device %s instead of %s\n", lpm,
- print_path_uid, print_device_uid);
- path_err = -EINVAL;
- dasd_path_add_cablepm(device, lpm);
- continue;
- }
- path_private.conf_data = NULL;
- path_private.conf_len = 0;
+ } else if (dasd_eckd_check_cabling(device, conf_data, lpm)) {
+ dasd_path_add_cablepm(device, lpm);
+ path_err = -EINVAL;
+ kfree(conf_data);
+ continue;
}
pos = pathmask_to_pos(lpm);
@@ -1197,8 +1188,6 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
}
}
- dasd_eckd_read_fc_security(device);
-
return path_err;
}
@@ -1213,7 +1202,7 @@ static u32 get_fcx_max_data(struct dasd_device *device)
return 0;
/* is transport mode supported? */
fcx_in_css = css_general_characteristics.fcx;
- fcx_in_gneq = private->gneq->reserved2[7] & 0x04;
+ fcx_in_gneq = private->conf.gneq->reserved2[7] & 0x04;
fcx_in_features = private->features.feature[40] & 0x80;
tpm = fcx_in_css && fcx_in_gneq && fcx_in_features;
@@ -1282,9 +1271,9 @@ static int rebuild_device_uid(struct dasd_device *device,
"returned error %d", rc);
break;
}
- memcpy(private->conf_data, data->rcd_buffer,
+ memcpy(private->conf.data, data->rcd_buffer,
DASD_ECKD_RCD_DATA_SIZE);
- if (dasd_eckd_identify_conf_parts(private)) {
+ if (dasd_eckd_identify_conf_parts(&private->conf)) {
rc = -ENODEV;
} else /* first valid path is enough */
break;
@@ -1299,11 +1288,10 @@ static int rebuild_device_uid(struct dasd_device *device,
static void dasd_eckd_path_available_action(struct dasd_device *device,
struct pe_handler_work_data *data)
{
- struct dasd_eckd_private path_private;
- struct dasd_uid *uid;
__u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE];
__u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm;
struct dasd_conf_data *conf_data;
+ struct dasd_conf path_conf;
unsigned long flags;
char print_uid[60];
int rc, pos;
@@ -1367,11 +1355,11 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
*/
memcpy(&path_rcd_buf, data->rcd_buffer,
DASD_ECKD_RCD_DATA_SIZE);
- path_private.conf_data = (void *) &path_rcd_buf;
- path_private.conf_len = DASD_ECKD_RCD_DATA_SIZE;
- if (dasd_eckd_identify_conf_parts(&path_private)) {
- path_private.conf_data = NULL;
- path_private.conf_len = 0;
+ path_conf.data = (void *)&path_rcd_buf;
+ path_conf.len = DASD_ECKD_RCD_DATA_SIZE;
+ if (dasd_eckd_identify_conf_parts(&path_conf)) {
+ path_conf.data = NULL;
+ path_conf.len = 0;
continue;
}
@@ -1382,7 +1370,7 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
* the first working path UID will be used as device UID
*/
if (dasd_path_get_opm(device) &&
- dasd_eckd_compare_path_uid(device, &path_private)) {
+ dasd_eckd_compare_path_uid(device, &path_conf)) {
/*
* the comparison was not successful
* rebuild the device UID with at least one
@@ -1396,20 +1384,8 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
*/
if (rebuild_device_uid(device, data) ||
dasd_eckd_compare_path_uid(
- device, &path_private)) {
- uid = &path_private.uid;
- if (strlen(uid->vduit) > 0)
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x.%s",
- uid->vendor, uid->serial,
- uid->ssid, uid->real_unit_addr,
- uid->vduit);
- else
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x",
- uid->vendor, uid->serial,
- uid->ssid,
- uid->real_unit_addr);
+ device, &path_conf)) {
+ dasd_eckd_get_uid_string(&path_conf, print_uid);
dev_err(&device->cdev->dev,
"The newly added channel path %02X "
"will not be used because it leads "
@@ -1427,6 +1403,14 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
if (conf_data) {
memcpy(conf_data, data->rcd_buffer,
DASD_ECKD_RCD_DATA_SIZE);
+ } else {
+ /*
+ * path is operational but path config data could not
+ * be stored due to low mem condition
+ * add it to the error path mask and schedule a path
+ * verification later that this could be added again
+ */
+ epm |= lpm;
}
pos = pathmask_to_pos(lpm);
dasd_eckd_store_conf_data(device, conf_data, pos);
@@ -1447,7 +1431,10 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
}
dasd_path_add_nppm(device, npm);
dasd_path_add_ppm(device, ppm);
- dasd_path_add_tbvpm(device, epm);
+ if (epm) {
+ dasd_path_add_tbvpm(device, epm);
+ dasd_device_set_timer(device, 50);
+ }
dasd_path_add_cablepm(device, cablepm);
dasd_path_add_nohpfpm(device, hpfpm);
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
@@ -1625,8 +1612,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device)
prssdp = cqr->data;
prssdp->order = PSF_ORDER_PRSSD;
prssdp->suborder = PSF_SUBORDER_VSQ; /* Volume Storage Query */
- prssdp->lss = private->ned->ID;
- prssdp->volume = private->ned->unit_addr;
+ prssdp->lss = private->conf.ned->ID;
+ prssdp->volume = private->conf.ned->unit_addr;
ccw = cqr->cpaddr;
ccw->cmd_code = DASD_ECKD_CCW_PSF;
@@ -2085,11 +2072,11 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
device->path_thrhld = DASD_ECKD_PATH_THRHLD;
device->path_interval = DASD_ECKD_PATH_INTERVAL;
- if (private->gneq) {
+ if (private->conf.gneq) {
value = 1;
- for (i = 0; i < private->gneq->timeout.value; i++)
+ for (i = 0; i < private->conf.gneq->timeout.value; i++)
value = 10 * value;
- value = value * private->gneq->timeout.number;
+ value = value * private->conf.gneq->timeout.number;
/* do not accept useless values */
if (value != 0 && value <= DASD_EXPIRES_MAX)
device->default_expires = value;
@@ -2121,6 +2108,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
if (rc)
goto out_err3;
+ dasd_eckd_read_fc_security(device);
dasd_path_create_kobjects(device);
/* Read Feature Codes */
@@ -2195,10 +2183,10 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
return;
dasd_alias_disconnect_device_from_lcu(device);
- private->ned = NULL;
- private->sneq = NULL;
- private->vdsneq = NULL;
- private->gneq = NULL;
+ private->conf.ned = NULL;
+ private->conf.sneq = NULL;
+ private->conf.vdsneq = NULL;
+ private->conf.gneq = NULL;
dasd_eckd_clear_conf_data(device);
dasd_path_remove_kobjects(device);
}
@@ -3750,8 +3738,8 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block,
* subset.
*/
ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01);
- ras_data->lss = private->ned->ID;
- ras_data->dev_addr = private->ned->unit_addr;
+ ras_data->lss = private->conf.ned->ID;
+ ras_data->dev_addr = private->conf.ned->unit_addr;
ras_data->nr_exts = nr_exts;
if (by_extent) {
@@ -4293,8 +4281,8 @@ static int prepare_itcw(struct itcw *itcw,
memset(&pfxdata, 0, sizeof(pfxdata));
pfxdata.format = 1; /* PFX with LRE */
- pfxdata.base_address = basepriv->ned->unit_addr;
- pfxdata.base_lss = basepriv->ned->ID;
+ pfxdata.base_address = basepriv->conf.ned->unit_addr;
+ pfxdata.base_lss = basepriv->conf.ned->ID;
pfxdata.validity.define_extent = 1;
/* private uid is kept up to date, conf_data may be outdated */
@@ -4963,9 +4951,9 @@ dasd_eckd_fill_info(struct dasd_device * device,
info->characteristics_size = sizeof(private->rdc_data);
memcpy(info->characteristics, &private->rdc_data,
sizeof(private->rdc_data));
- info->confdata_size = min((unsigned long)private->conf_len,
- sizeof(info->configuration_data));
- memcpy(info->configuration_data, private->conf_data,
+ info->confdata_size = min_t(unsigned long, private->conf.len,
+ sizeof(info->configuration_data));
+ memcpy(info->configuration_data, private->conf.data,
info->confdata_size);
return 0;
}
@@ -5808,6 +5796,8 @@ static int dasd_eckd_reload_device(struct dasd_device *device)
if (rc)
goto out_err;
+ dasd_eckd_read_fc_security(device);
+
rc = dasd_eckd_generate_uid(device);
if (rc)
goto out_err;
@@ -5820,15 +5810,7 @@ static int dasd_eckd_reload_device(struct dasd_device *device)
dasd_eckd_get_uid(device, &uid);
if (old_base != uid.base_unit_addr) {
- if (strlen(uid.vduit) > 0)
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x.%s", uid.vendor, uid.serial,
- uid.ssid, uid.base_unit_addr, uid.vduit);
- else
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x", uid.vendor, uid.serial,
- uid.ssid, uid.base_unit_addr);
-
+ dasd_eckd_get_uid_string(&private->conf, print_uid);
dev_info(&device->cdev->dev,
"An Alias device was reassigned to a new base device "
"with UID: %s\n", print_uid);
@@ -5966,8 +5948,8 @@ static int dasd_eckd_query_host_access(struct dasd_device *device,
prssdp->order = PSF_ORDER_PRSSD;
prssdp->suborder = PSF_SUBORDER_QHA; /* query host access */
/* LSS and Volume that will be queried */
- prssdp->lss = private->ned->ID;
- prssdp->volume = private->ned->unit_addr;
+ prssdp->lss = private->conf.ned->ID;
+ prssdp->volume = private->conf.ned->unit_addr;
/* all other bytes of prssdp must be zero */
ccw = cqr->cpaddr;
diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h
index 65e4630ad2ae..a91b265441cc 100644
--- a/drivers/s390/block/dasd_eckd.h
+++ b/drivers/s390/block/dasd_eckd.h
@@ -658,16 +658,19 @@ struct dasd_conf_data {
struct dasd_gneq gneq;
} __packed;
-struct dasd_eckd_private {
- struct dasd_eckd_characteristics rdc_data;
- u8 *conf_data;
- int conf_len;
-
+struct dasd_conf {
+ u8 *data;
+ int len;
/* pointers to specific parts in the conf_data */
struct dasd_ned *ned;
struct dasd_sneq *sneq;
struct vd_sneq *vdsneq;
struct dasd_gneq *gneq;
+};
+
+struct dasd_eckd_private {
+ struct dasd_eckd_characteristics rdc_data;
+ struct dasd_conf conf;
struct eckd_count count_area[5];
int init_cqr_status;
diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c
index ba4fa372d02d..c07e6e713518 100644
--- a/drivers/s390/block/dasd_erp.c
+++ b/drivers/s390/block/dasd_erp.c
@@ -24,7 +24,7 @@
#include "dasd_int.h"
struct dasd_ccw_req *
-dasd_alloc_erp_request(char *magic, int cplength, int datasize,
+dasd_alloc_erp_request(unsigned int magic, int cplength, int datasize,
struct dasd_device * device)
{
unsigned long flags;
@@ -33,8 +33,8 @@ dasd_alloc_erp_request(char *magic, int cplength, int datasize,
int size;
/* Sanity checks */
- BUG_ON( magic == NULL || datasize > PAGE_SIZE ||
- (cplength*sizeof(struct ccw1)) > PAGE_SIZE);
+ BUG_ON(datasize > PAGE_SIZE ||
+ (cplength*sizeof(struct ccw1)) > PAGE_SIZE);
size = (sizeof(struct dasd_ccw_req) + 7L) & -8L;
if (cplength > 0)
@@ -62,7 +62,7 @@ dasd_alloc_erp_request(char *magic, int cplength, int datasize,
cqr->data = data;
memset(cqr->data, 0, datasize);
}
- strncpy((char *) &cqr->magic, magic, 4);
+ cqr->magic = magic;
ASCEBC((char *) &cqr->magic, 4);
set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
dasd_get_device(device);
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index fa966e0db6ca..3a6f3af240fa 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -14,6 +14,7 @@
#define KMSG_COMPONENT "dasd"
#include <linux/interrupt.h>
+#include <linux/major.h>
#include <linux/fs.h>
#include <linux/blkpg.h>
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 155428bfed8a..8b458010f88a 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -887,7 +887,7 @@ void dasd_proc_exit(void);
/* externals in dasd_erp.c */
struct dasd_ccw_req *dasd_default_erp_action(struct dasd_ccw_req *);
struct dasd_ccw_req *dasd_default_erp_postaction(struct dasd_ccw_req *);
-struct dasd_ccw_req *dasd_alloc_erp_request(char *, int, int,
+struct dasd_ccw_req *dasd_alloc_erp_request(unsigned int, int, int,
struct dasd_device *);
void dasd_free_erp_request(struct dasd_ccw_req *, struct dasd_device *);
void dasd_log_sense(struct dasd_ccw_req *, struct irb *);
@@ -1305,6 +1305,15 @@ static inline void dasd_path_add_ppm(struct dasd_device *device, __u8 pm)
dasd_path_preferred(device, chp);
}
+static inline void dasd_path_add_fcsecpm(struct dasd_device *device, __u8 pm)
+{
+ int chp;
+
+ for (chp = 0; chp < 8; chp++)
+ if (pm & (0x80 >> chp))
+ dasd_path_fcsec(device, chp);
+}
+
/*
* set functions for path masks
* the existing path mask will be replaced by the given path mask
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 468cbeb539ff..95349f95758c 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -650,8 +650,8 @@ int dasd_ioctl(struct block_device *bdev, fmode_t mode,
/**
* dasd_biodasdinfo() - fill out the dasd information structure
- * @disk [in]: pointer to gendisk structure that references a DASD
- * @info [out]: pointer to the dasd_information2_t structure
+ * @disk: [in] pointer to gendisk structure that references a DASD
+ * @info: [out] pointer to the dasd_information2_t structure
*
* Provide access to DASD specific information.
* The gendisk structure is checked if it belongs to the DASD driver by
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 5be3d1c39a78..59e513d34b0f 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -30,7 +30,7 @@
static int dcssblk_open(struct block_device *bdev, fmode_t mode);
static void dcssblk_release(struct gendisk *disk, fmode_t mode);
-static blk_qc_t dcssblk_submit_bio(struct bio *bio);
+static void dcssblk_submit_bio(struct bio *bio);
static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
long nr_pages, void **kaddr, pfn_t *pfn);
@@ -854,7 +854,7 @@ dcssblk_release(struct gendisk *disk, fmode_t mode)
up_write(&dcssblk_devices_sem);
}
-static blk_qc_t
+static void
dcssblk_submit_bio(struct bio *bio)
{
struct dcssblk_dev_info *dev_info;
@@ -907,10 +907,9 @@ dcssblk_submit_bio(struct bio *bio)
bytes_done += bvec.bv_len;
}
bio_endio(bio);
- return BLK_QC_T_NONE;
+ return;
fail:
bio_io_error(bio);
- return BLK_QC_T_NONE;
}
static long
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 3ab669dc806f..27884f3106ab 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3,6 +3,7 @@
* Copyright (c) 2017 Hisilicon Limited.
*/
+#include <linux/sched/clock.h>
#include "hisi_sas.h"
#define DRV_NAME "hisi_sas_v3_hw"
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 1f1586ad48fe..01f79991bf4a 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1696,6 +1696,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
spin_lock_irqsave(&evt->queue->l_lock, flags);
list_add_tail(&evt->queue_list, &evt->queue->sent);
+ atomic_set(&evt->active, 1);
mb();
@@ -1710,6 +1711,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
be64_to_cpu(crq_as_u64[1]));
if (rc) {
+ atomic_set(&evt->active, 0);
list_del(&evt->queue_list);
spin_unlock_irqrestore(&evt->queue->l_lock, flags);
del_timer(&evt->timer);
@@ -1737,7 +1739,6 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
evt->done(evt);
} else {
- atomic_set(&evt->active, 1);
spin_unlock_irqrestore(&evt->queue->l_lock, flags);
ibmvfc_trc_start(evt);
}
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index befeb7c34290..337e6ed24821 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -22,6 +22,7 @@
*******************************************************************/
#include <scsi/scsi_host.h>
+#include <linux/hashtable.h>
#include <linux/ktime.h>
#include <linux/workqueue.h>
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index d383d4a03436..ad1b6c2b37a7 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -5065,9 +5065,12 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
if (scmd->prot_flags & SCSI_PROT_GUARD_CHECK)
eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
- if (scmd->prot_flags & SCSI_PROT_REF_CHECK) {
- eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG |
- MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG;
+ if (scmd->prot_flags & SCSI_PROT_REF_CHECK)
+ eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG;
+
+ if (scmd->prot_flags & SCSI_PROT_REF_INCREMENT) {
+ eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG;
+
mpi_request->CDB.EEDP32.PrimaryReferenceTag =
cpu_to_be32(scsi_prot_ref_tag(scmd));
}
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1c5da2dbd6f9..253055cf9daf 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -8,6 +8,8 @@
#include <linux/delay.h>
#include <linux/nvme.h>
#include <linux/nvme-fc.h>
+#include <linux/blk-mq-pci.h>
+#include <linux/blk-mq.h>
static struct nvme_fc_port_template qla_nvme_fc_transport;
@@ -642,6 +644,18 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport,
return rval;
}
+static void qla_nvme_map_queues(struct nvme_fc_local_port *lport,
+ struct blk_mq_queue_map *map)
+{
+ struct scsi_qla_host *vha = lport->private;
+ int rc;
+
+ rc = blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset);
+ if (rc)
+ ql_log(ql_log_warn, vha, 0x21de,
+ "pci map queue failed 0x%x", rc);
+}
+
static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport)
{
struct scsi_qla_host *vha = lport->private;
@@ -676,6 +690,7 @@ static struct nvme_fc_port_template qla_nvme_fc_transport = {
.ls_abort = qla_nvme_ls_abort,
.fcp_io = qla_nvme_post_cmd,
.fcp_abort = qla_nvme_fcp_abort,
+ .map_queues = qla_nvme_map_queues,
.max_hw_queues = 8,
.max_sgl_segments = 1024,
.max_dif_sgl_segments = 64,
diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c
index 81c3853a2a80..081b84bb7985 100644
--- a/drivers/scsi/scsi_bsg.c
+++ b/drivers/scsi/scsi_bsg.c
@@ -25,8 +25,8 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
return -EOPNOTSUPP;
}
- rq = blk_get_request(q, hdr->dout_xfer_len ?
- REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
+ rq = scsi_alloc_request(q, hdr->dout_xfer_len ?
+ REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
rq->timeout = timeout;
@@ -95,7 +95,7 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
out_free_cmd:
scsi_req_free_cmd(scsi_req(rq));
out_put_request:
- blk_put_request(rq);
+ blk_mq_free_request(rq);
return ret;
}
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 66f507469a31..40b473eea357 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5384,7 +5384,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
{
bool new_sd_dp;
bool inject = false;
- bool hipri = scsi_cmd_to_rq(cmnd)->cmd_flags & REQ_HIPRI;
+ bool polled = scsi_cmd_to_rq(cmnd)->cmd_flags & REQ_POLLED;
int k, num_in_q, qdepth;
unsigned long iflags;
u64 ns_from_boot = 0;
@@ -5471,7 +5471,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
if (sdebug_host_max_queue)
sd_dp->hc_idx = get_tag(cmnd);
- if (hipri)
+ if (polled)
ns_from_boot = ktime_get_boottime_ns();
/* one of the resp_*() response functions is called here */
@@ -5531,7 +5531,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
kt -= d;
}
}
- if (hipri) {
+ if (polled) {
sd_dp->cmpl_ts = ktime_add(ns_to_ktime(ns_from_boot), kt);
spin_lock_irqsave(&sqp->qc_lock, iflags);
if (!sd_dp->init_poll) {
@@ -5562,7 +5562,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
if (unlikely((sdebug_opts & SDEBUG_OPT_CMD_ABORT) &&
atomic_read(&sdeb_inject_pending)))
sd_dp->aborted = true;
- if (hipri) {
+ if (polled) {
sd_dp->cmpl_ts = ns_to_ktime(ns_from_boot);
spin_lock_irqsave(&sqp->qc_lock, iflags);
if (!sd_dp->init_poll) {
@@ -7331,7 +7331,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
if (kt_from_boot < sd_dp->cmpl_ts)
continue;
- } else /* ignoring non REQ_HIPRI requests */
+ } else /* ignoring non REQ_POLLED requests */
continue;
devip = (struct sdebug_dev_info *)scp->device->hostdata;
if (likely(devip))
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index b6c86cce57bf..36870b41c888 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1979,7 +1979,7 @@ maybe_retry:
static void eh_lock_door_done(struct request *req, blk_status_t status)
{
- blk_put_request(req);
+ blk_mq_free_request(req);
}
/**
@@ -1998,7 +1998,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
struct request *req;
struct scsi_request *rq;
- req = blk_get_request(sdev->request_queue, REQ_OP_DRV_IN, 0);
+ req = scsi_alloc_request(sdev->request_queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
return;
rq = scsi_req(req);
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 6ff2207bd45a..34412eac4566 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -438,7 +438,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk,
at_head = 1;
ret = -ENOMEM;
- rq = blk_get_request(sdev->request_queue, writing ?
+ rq = scsi_alloc_request(sdev->request_queue, writing ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
@@ -490,7 +490,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk,
out_free_cdb:
scsi_req_free_cmd(req);
out_put_request:
- blk_put_request(rq);
+ blk_mq_free_request(rq);
return ret;
}
@@ -561,7 +561,7 @@ static int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk,
}
- rq = blk_get_request(q, in_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
+ rq = scsi_alloc_request(q, in_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
goto error_free_buffer;
@@ -634,7 +634,7 @@ static int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk,
}
error:
- blk_put_request(rq);
+ blk_mq_free_request(rq);
error_free_buffer:
kfree(buffer);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 572673873ddf..9c2b99e12ce3 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -21,6 +21,7 @@
#include <linux/hardirq.h>
#include <linux/scatterlist.h>
#include <linux/blk-mq.h>
+#include <linux/blk-integrity.h>
#include <linux/ratelimit.h>
#include <asm/unaligned.h>
@@ -215,7 +216,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
struct scsi_request *rq;
int ret;
- req = blk_get_request(sdev->request_queue,
+ req = scsi_alloc_request(sdev->request_queue,
data_direction == DMA_TO_DEVICE ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0);
@@ -259,7 +260,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
ret = rq->result;
out:
- blk_put_request(req);
+ blk_mq_free_request(req);
return ret;
}
@@ -1078,9 +1079,6 @@ EXPORT_SYMBOL(scsi_alloc_sgtables);
* This function initializes the members of struct scsi_cmnd that must be
* initialized before request processing starts and that won't be
* reinitialized if a SCSI command is requeued.
- *
- * Called from inside blk_get_request() for pass-through requests and from
- * inside scsi_init_command() for filesystem requests.
*/
static void scsi_initialize_rq(struct request *rq)
{
@@ -1097,6 +1095,18 @@ static void scsi_initialize_rq(struct request *rq)
cmd->retries = 0;
}
+struct request *scsi_alloc_request(struct request_queue *q,
+ unsigned int op, blk_mq_req_flags_t flags)
+{
+ struct request *rq;
+
+ rq = blk_mq_alloc_request(q, op, flags);
+ if (!IS_ERR(rq))
+ scsi_initialize_rq(rq);
+ return rq;
+}
+EXPORT_SYMBOL_GPL(scsi_alloc_request);
+
/*
* Only called when the request isn't completed by SCSI, and not freed by
* SCSI
@@ -1783,7 +1793,7 @@ static void scsi_mq_exit_request(struct blk_mq_tag_set *set, struct request *rq,
}
-static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx)
+static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct Scsi_Host *shost = hctx->driver_data;
@@ -1863,7 +1873,6 @@ static const struct blk_mq_ops scsi_mq_ops_no_commit = {
#endif
.init_request = scsi_mq_init_request,
.exit_request = scsi_mq_exit_request,
- .initialize_rq_fn = scsi_initialize_rq,
.cleanup_rq = scsi_cleanup_rq,
.busy = scsi_mq_lld_busy,
.map_queues = scsi_map_queues,
@@ -1893,7 +1902,6 @@ static const struct blk_mq_ops scsi_mq_ops = {
#endif
.init_request = scsi_mq_init_request,
.exit_request = scsi_mq_exit_request,
- .initialize_rq_fn = scsi_initialize_rq,
.cleanup_rq = scsi_cleanup_rq,
.busy = scsi_mq_lld_busy,
.map_queues = scsi_map_queues,
@@ -1959,6 +1967,14 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q)
return sdev;
}
+/*
+ * pktcdvd should have been integrated into the SCSI layers, but for historical
+ * reasons like the old IDE driver it isn't. This export allows it to safely
+ * probe if a given device is a SCSI one and only attach to that.
+ */
+#ifdef CONFIG_CDROM_PKTCDVD_MODULE
+EXPORT_SYMBOL_GPL(scsi_device_from_queue);
+#endif
/**
* scsi_block_requests - Utility function used by low-level drivers to prevent
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index fe22191522a3..2808c0cb5711 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -280,7 +280,6 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
sdev->request_queue = q;
q->queuedata = sdev;
__scsi_init_queue(sdev->host, q);
- blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
WARN_ON_ONCE(!blk_get_queue(q));
depth = sdev->host->cmd_per_lun ?: 1;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index fce63335084e..252e43d7c73f 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -48,6 +48,7 @@
#include <linux/blkpg.h>
#include <linux/blk-pm.h>
#include <linux/delay.h>
+#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/string_helpers.h>
#include <linux/async.h>
@@ -1756,6 +1757,44 @@ static void sd_rescan(struct device *dev)
sd_revalidate_disk(sdkp->disk);
}
+static int sd_get_unique_id(struct gendisk *disk, u8 id[16],
+ enum blk_unique_id type)
+{
+ struct scsi_device *sdev = scsi_disk(disk)->device;
+ const struct scsi_vpd *vpd;
+ const unsigned char *d;
+ int ret = -ENXIO, len;
+
+ rcu_read_lock();
+ vpd = rcu_dereference(sdev->vpd_pg83);
+ if (!vpd)
+ goto out_unlock;
+
+ ret = -EINVAL;
+ for (d = vpd->data + 4; d < vpd->data + vpd->len; d += d[3] + 4) {
+ /* we only care about designators with LU association */
+ if (((d[1] >> 4) & 0x3) != 0x00)
+ continue;
+ if ((d[1] & 0xf) != type)
+ continue;
+
+ /*
+ * Only exit early if a 16-byte descriptor was found. Otherwise
+ * keep looking as one with more entropy might still show up.
+ */
+ len = d[3];
+ if (len != 8 && len != 12 && len != 16)
+ continue;
+ ret = len;
+ memcpy(id, d + 4, len);
+ if (len == 16)
+ break;
+ }
+out_unlock:
+ rcu_read_unlock();
+ return ret;
+}
+
static char sd_pr_type(enum pr_type type)
{
switch (type) {
@@ -1860,6 +1899,7 @@ static const struct block_device_operations sd_fops = {
.check_events = sd_check_events,
.unlock_native_capacity = sd_unlock_native_capacity,
.report_zones = sd_zbc_report_zones,
+ .get_unique_id = sd_get_unique_id,
.pr_ops = &sd_pr_ops,
};
@@ -3087,6 +3127,86 @@ static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer)
sdkp->security = 1;
}
+static inline sector_t sd64_to_sectors(struct scsi_disk *sdkp, u8 *buf)
+{
+ return logical_to_sectors(sdkp->device, get_unaligned_be64(buf));
+}
+
+/**
+ * sd_read_cpr - Query concurrent positioning ranges
+ * @sdkp: disk to query
+ */
+static void sd_read_cpr(struct scsi_disk *sdkp)
+{
+ struct blk_independent_access_ranges *iars = NULL;
+ unsigned char *buffer = NULL;
+ unsigned int nr_cpr = 0;
+ int i, vpd_len, buf_len = SD_BUF_SIZE;
+ u8 *desc;
+
+ /*
+ * We need to have the capacity set first for the block layer to be
+ * able to check the ranges.
+ */
+ if (sdkp->first_scan)
+ return;
+
+ if (!sdkp->capacity)
+ goto out;
+
+ /*
+ * Concurrent Positioning Ranges VPD: there can be at most 256 ranges,
+ * leading to a maximum page size of 64 + 256*32 bytes.
+ */
+ buf_len = 64 + 256*32;
+ buffer = kmalloc(buf_len, GFP_KERNEL);
+ if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb9, buffer, buf_len))
+ goto out;
+
+ /* We must have at least a 64B header and one 32B range descriptor */
+ vpd_len = get_unaligned_be16(&buffer[2]) + 3;
+ if (vpd_len > buf_len || vpd_len < 64 + 32 || (vpd_len & 31)) {
+ sd_printk(KERN_ERR, sdkp,
+ "Invalid Concurrent Positioning Ranges VPD page\n");
+ goto out;
+ }
+
+ nr_cpr = (vpd_len - 64) / 32;
+ if (nr_cpr == 1) {
+ nr_cpr = 0;
+ goto out;
+ }
+
+ iars = disk_alloc_independent_access_ranges(sdkp->disk, nr_cpr);
+ if (!iars) {
+ nr_cpr = 0;
+ goto out;
+ }
+
+ desc = &buffer[64];
+ for (i = 0; i < nr_cpr; i++, desc += 32) {
+ if (desc[0] != i) {
+ sd_printk(KERN_ERR, sdkp,
+ "Invalid Concurrent Positioning Range number\n");
+ nr_cpr = 0;
+ break;
+ }
+
+ iars->ia_range[i].sector = sd64_to_sectors(sdkp, desc + 8);
+ iars->ia_range[i].nr_sectors = sd64_to_sectors(sdkp, desc + 16);
+ }
+
+out:
+ disk_set_independent_access_ranges(sdkp->disk, iars);
+ if (nr_cpr && sdkp->nr_actuators != nr_cpr) {
+ sd_printk(KERN_NOTICE, sdkp,
+ "%u concurrent positioning ranges\n", nr_cpr);
+ sdkp->nr_actuators = nr_cpr;
+ }
+
+ kfree(buffer);
+}
+
/*
* Determine the device's preferred I/O size for reads and writes
* unless the reported value is unreasonably small, large, not a
@@ -3202,6 +3322,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
sd_read_app_tag_own(sdkp, buffer);
sd_read_write_same(sdkp, buffer);
sd_read_security(sdkp, buffer);
+ sd_read_cpr(sdkp);
}
/*
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index b59136c4125b..2e5932bde43d 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -106,6 +106,7 @@ struct scsi_disk {
u8 protection_type;/* Data Integrity Field */
u8 provisioning_mode;
u8 zeroing_mode;
+ u8 nr_actuators; /* Number of actuators */
unsigned ATO : 1; /* state of disk ATO bit */
unsigned cache_override : 1; /* temp override of WCE,RCD */
unsigned WCE : 1; /* state of disk WCE bit */
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 4cadb26070a8..349950616adc 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -6,7 +6,7 @@
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*/
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/t10-pi.h>
#include <scsi/scsi.h>
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 8f05248920e8..141099ab9092 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -31,6 +31,7 @@ static int sg_version_num = 30536; /* 2 digits for each component */
#include <linux/errno.h>
#include <linux/mtio.h>
#include <linux/ioctl.h>
+#include <linux/major.h>
#include <linux/slab.h>
#include <linux/fcntl.h>
#include <linux/init.h>
@@ -814,7 +815,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
if (atomic_read(&sdp->detaching)) {
if (srp->bio) {
scsi_req_free_cmd(scsi_req(srp->rq));
- blk_put_request(srp->rq);
+ blk_mq_free_request(srp->rq);
srp->rq = NULL;
}
@@ -1389,7 +1390,7 @@ sg_rq_end_io(struct request *rq, blk_status_t status)
*/
srp->rq = NULL;
scsi_req_free_cmd(scsi_req(rq));
- blk_put_request(rq);
+ blk_mq_free_request(rq);
write_lock_irqsave(&sfp->rq_list_lock, iflags);
if (unlikely(srp->orphan)) {
@@ -1717,13 +1718,13 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
*
* With scsi-mq enabled, there are a fixed number of preallocated
* requests equal in number to shost->can_queue. If all of the
- * preallocated requests are already in use, then blk_get_request()
+ * preallocated requests are already in use, then scsi_alloc_request()
* will sleep until an active command completes, freeing up a request.
* Although waiting in an asynchronous interface is less than ideal, we
* do not want to use BLK_MQ_REQ_NOWAIT here because userspace might
* not expect an EWOULDBLOCK from this condition.
*/
- rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
+ rq = scsi_alloc_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(rq)) {
kfree(long_cmdp);
@@ -1829,7 +1830,7 @@ sg_finish_rem_req(Sg_request *srp)
if (srp->rq) {
scsi_req_free_cmd(scsi_req(srp->rq));
- blk_put_request(srp->rq);
+ blk_mq_free_request(srp->rq);
}
if (srp->res_used)
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 8b17b35283aa..3009b986d1d7 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -44,6 +44,7 @@
#include <linux/cdrom.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/major.h>
#include <linux/blkdev.h>
#include <linux/blk-pm.h>
#include <linux/mutex.h>
@@ -966,7 +967,7 @@ static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf,
struct bio *bio;
int ret;
- rq = blk_get_request(disk->queue, REQ_OP_DRV_IN, 0);
+ rq = scsi_alloc_request(disk->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
req = scsi_req(rq);
@@ -1002,7 +1003,7 @@ static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf,
if (blk_rq_unmap_user(bio))
ret = -EFAULT;
out_put_request:
- blk_put_request(rq);
+ blk_mq_free_request(rq);
return ret;
}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index ae8636d3780b..c2d5608f6b1a 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -32,6 +32,7 @@ static const char *verstr = "20160209";
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/mtio.h>
+#include <linux/major.h>
#include <linux/cdrom.h>
#include <linux/ioctl.h>
#include <linux/fcntl.h>
@@ -529,7 +530,7 @@ static void st_scsi_execute_end(struct request *req, blk_status_t status)
complete(SRpnt->waiting);
blk_rq_unmap_user(tmp);
- blk_put_request(req);
+ blk_mq_free_request(req);
}
static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
@@ -542,7 +543,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
int err = 0;
struct scsi_tape *STp = SRpnt->stp;
- req = blk_get_request(SRpnt->stp->device->request_queue,
+ req = scsi_alloc_request(SRpnt->stp->device->request_queue,
data_direction == DMA_TO_DEVICE ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
@@ -556,7 +557,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
err = blk_rq_map_user(req->q, req, mdata, NULL, bufflen,
GFP_KERNEL);
if (err) {
- blk_put_request(req);
+ blk_mq_free_request(req);
return err;
}
}
diff --git a/drivers/scsi/ufs/ufs-exynos.c b/drivers/scsi/ufs/ufs-exynos.c
index a14dd8ce56d4..bb2dd79a1bcd 100644
--- a/drivers/scsi/ufs/ufs-exynos.c
+++ b/drivers/scsi/ufs/ufs-exynos.c
@@ -642,9 +642,9 @@ static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba,
}
/* setting for three timeout values for traffic class #0 */
- ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA0), 8064);
- ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA1), 28224);
- ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA2), 20160);
+ ufshcd_dme_set(hba, UIC_ARG_MIB(DL_FC0PROTTIMEOUTVAL), 8064);
+ ufshcd_dme_set(hba, UIC_ARG_MIB(DL_TC0REPLAYTIMEOUTVAL), 28224);
+ ufshcd_dme_set(hba, UIC_ARG_MIB(DL_AFC0REQTIMEOUTVAL), 20160);
return 0;
out:
diff --git a/drivers/scsi/ufs/ufshcd-crypto.c b/drivers/scsi/ufs/ufshcd-crypto.c
index d70cdcd35e43..67402baf6fae 100644
--- a/drivers/scsi/ufs/ufshcd-crypto.c
+++ b/drivers/scsi/ufs/ufshcd-crypto.c
@@ -48,11 +48,12 @@ out:
return err;
}
-static int ufshcd_crypto_keyslot_program(struct blk_keyslot_manager *ksm,
+static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct ufs_hba *hba = container_of(ksm, struct ufs_hba, ksm);
+ struct ufs_hba *hba =
+ container_of(profile, struct ufs_hba, crypto_profile);
const union ufs_crypto_cap_entry *ccap_array = hba->crypto_cap_array;
const struct ufs_crypto_alg_entry *alg =
&ufs_crypto_algs[key->crypto_cfg.crypto_mode];
@@ -105,11 +106,12 @@ static int ufshcd_clear_keyslot(struct ufs_hba *hba, int slot)
return ufshcd_program_key(hba, &cfg, slot);
}
-static int ufshcd_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
+static int ufshcd_crypto_keyslot_evict(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct ufs_hba *hba = container_of(ksm, struct ufs_hba, ksm);
+ struct ufs_hba *hba =
+ container_of(profile, struct ufs_hba, crypto_profile);
return ufshcd_clear_keyslot(hba, slot);
}
@@ -120,11 +122,11 @@ bool ufshcd_crypto_enable(struct ufs_hba *hba)
return false;
/* Reset might clear all keys, so reprogram all the keys. */
- blk_ksm_reprogram_all_keys(&hba->ksm);
+ blk_crypto_reprogram_all_keys(&hba->crypto_profile);
return true;
}
-static const struct blk_ksm_ll_ops ufshcd_ksm_ops = {
+static const struct blk_crypto_ll_ops ufshcd_crypto_ops = {
.keyslot_program = ufshcd_crypto_keyslot_program,
.keyslot_evict = ufshcd_crypto_keyslot_evict,
};
@@ -179,15 +181,16 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba)
}
/* The actual number of configurations supported is (CFGC+1) */
- err = devm_blk_ksm_init(hba->dev, &hba->ksm,
- hba->crypto_capabilities.config_count + 1);
+ err = devm_blk_crypto_profile_init(
+ hba->dev, &hba->crypto_profile,
+ hba->crypto_capabilities.config_count + 1);
if (err)
goto out;
- hba->ksm.ksm_ll_ops = ufshcd_ksm_ops;
+ hba->crypto_profile.ll_ops = ufshcd_crypto_ops;
/* UFS only supports 8 bytes for any DUN */
- hba->ksm.max_dun_bytes_supported = 8;
- hba->ksm.dev = hba->dev;
+ hba->crypto_profile.max_dun_bytes_supported = 8;
+ hba->crypto_profile.dev = hba->dev;
/*
* Cache all the UFS crypto capabilities and advertise the supported
@@ -202,7 +205,7 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba)
blk_mode_num = ufshcd_find_blk_crypto_mode(
hba->crypto_cap_array[cap_idx]);
if (blk_mode_num != BLK_ENCRYPTION_MODE_INVALID)
- hba->ksm.crypto_modes_supported[blk_mode_num] |=
+ hba->crypto_profile.modes_supported[blk_mode_num] |=
hba->crypto_cap_array[cap_idx].sdus_mask * 512;
}
@@ -230,9 +233,8 @@ void ufshcd_init_crypto(struct ufs_hba *hba)
ufshcd_clear_keyslot(hba, slot);
}
-void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba,
- struct request_queue *q)
+void ufshcd_crypto_register(struct ufs_hba *hba, struct request_queue *q)
{
if (hba->caps & UFSHCD_CAP_CRYPTO)
- blk_ksm_register(&hba->ksm, q);
+ blk_crypto_register(&hba->crypto_profile, q);
}
diff --git a/drivers/scsi/ufs/ufshcd-crypto.h b/drivers/scsi/ufs/ufshcd-crypto.h
index 78a58e788dff..e18c01276873 100644
--- a/drivers/scsi/ufs/ufshcd-crypto.h
+++ b/drivers/scsi/ufs/ufshcd-crypto.h
@@ -18,7 +18,7 @@ static inline void ufshcd_prepare_lrbp_crypto(struct request *rq,
return;
}
- lrbp->crypto_key_slot = blk_ksm_get_slot_idx(rq->crypt_keyslot);
+ lrbp->crypto_key_slot = blk_crypto_keyslot_index(rq->crypt_keyslot);
lrbp->data_unit_num = rq->crypt_ctx->bc_dun[0];
}
@@ -40,8 +40,7 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba);
void ufshcd_init_crypto(struct ufs_hba *hba);
-void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba,
- struct request_queue *q);
+void ufshcd_crypto_register(struct ufs_hba *hba, struct request_queue *q);
#else /* CONFIG_SCSI_UFS_CRYPTO */
@@ -64,8 +63,8 @@ static inline int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba)
static inline void ufshcd_init_crypto(struct ufs_hba *hba) { }
-static inline void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba,
- struct request_queue *q) { }
+static inline void ufshcd_crypto_register(struct ufs_hba *hba,
+ struct request_queue *q) { }
#endif /* CONFIG_SCSI_UFS_CRYPTO */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 95be7ecdfe10..db1bc8655d46 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2737,12 +2737,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
lrbp->req_abort_skip = false;
- err = ufshpb_prep(hba, lrbp);
- if (err == -EAGAIN) {
- lrbp->cmd = NULL;
- ufshcd_release(hba);
- goto out;
- }
+ ufshpb_prep(hba, lrbp);
ufshcd_comp_scsi_upiu(hba, lrbp);
@@ -2925,7 +2920,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
* Even though we use wait_event() which sleeps indefinitely,
* the maximum wait time is bounded by SCSI request timeout.
*/
- req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+ req = blk_mq_alloc_request(q, REQ_OP_DRV_OUT, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_unlock;
@@ -2952,7 +2947,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
(struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
out:
- blk_put_request(req);
+ blk_mq_free_request(req);
out_unlock:
up_read(&hba->clk_scaling_lock);
return err;
@@ -4986,7 +4981,7 @@ static int ufshcd_slave_configure(struct scsi_device *sdev)
else if (ufshcd_is_rpm_autosuspend_allowed(hba))
sdev->rpm_autosuspend = 1;
- ufshcd_crypto_setup_rq_keyslot_manager(hba, q);
+ ufshcd_crypto_register(hba, q);
return 0;
}
@@ -6517,9 +6512,9 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
int task_tag, err;
/*
- * blk_get_request() is used here only to get a free tag.
+ * blk_mq_alloc_request() is used here only to get a free tag.
*/
- req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+ req = blk_mq_alloc_request(q, REQ_OP_DRV_OUT, 0);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -6575,7 +6570,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
spin_unlock_irqrestore(hba->host->host_lock, flags);
ufshcd_release(hba);
- blk_put_request(req);
+ blk_mq_free_request(req);
return err;
}
@@ -6660,7 +6655,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
down_read(&hba->clk_scaling_lock);
- req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+ req = blk_mq_alloc_request(q, REQ_OP_DRV_OUT, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_unlock;
@@ -6741,7 +6736,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
(struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
out:
- blk_put_request(req);
+ blk_mq_free_request(req);
out_unlock:
up_read(&hba->clk_scaling_lock);
return err;
@@ -7912,7 +7907,7 @@ static void ufshcd_request_sense_done(struct request *rq, blk_status_t error)
if (error != BLK_STS_OK)
pr_err("%s: REQUEST SENSE failed (%d)\n", __func__, error);
kfree(rq->end_io_data);
- blk_put_request(rq);
+ blk_mq_free_request(rq);
}
static int
@@ -7932,7 +7927,7 @@ ufshcd_request_sense_async(struct ufs_hba *hba, struct scsi_device *sdev)
if (!buffer)
return -ENOMEM;
- req = blk_get_request(sdev->request_queue, REQ_OP_DRV_IN,
+ req = blk_mq_alloc_request(sdev->request_queue, REQ_OP_DRV_IN,
/*flags=*/BLK_MQ_REQ_PM);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
@@ -7957,7 +7952,7 @@ ufshcd_request_sense_async(struct ufs_hba *hba, struct scsi_device *sdev)
return 0;
out_put:
- blk_put_request(req);
+ blk_mq_free_request(req);
out_free:
kfree(buffer);
return ret;
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 41f6e06f9185..62bdc412d38a 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -32,7 +32,7 @@
#include <linux/regulator/consumer.h>
#include <linux/bitfield.h>
#include <linux/devfreq.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include "unipro.h"
#include <asm/irq.h>
@@ -766,7 +766,7 @@ struct ufs_hba_monitor {
* @crypto_capabilities: Content of crypto capabilities register (0x100)
* @crypto_cap_array: Array of crypto capabilities
* @crypto_cfg_register: Start of the crypto cfg array
- * @ksm: the keyslot manager tied to this hba
+ * @crypto_profile: the crypto profile of this hba (if applicable)
*/
struct ufs_hba {
void __iomem *mmio_base;
@@ -911,7 +911,7 @@ struct ufs_hba {
union ufs_crypto_capabilities crypto_capabilities;
union ufs_crypto_cap_entry *crypto_cap_array;
u32 crypto_cfg_register;
- struct blk_keyslot_manager ksm;
+ struct blk_crypto_profile crypto_profile;
#endif
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_root;
diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 589af5f6b940..182bcbf60f8c 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -84,16 +84,6 @@ static bool ufshpb_is_supported_chunk(struct ufshpb_lu *hpb, int transfer_len)
return transfer_len <= hpb->pre_req_max_tr_len;
}
-/*
- * In this driver, WRITE_BUFFER CMD support 36KB (len=9) ~ 1MB (len=256) as
- * default. It is possible to change range of transfer_len through sysfs.
- */
-static inline bool ufshpb_is_required_wb(struct ufshpb_lu *hpb, int len)
-{
- return len > hpb->pre_req_min_tr_len &&
- len <= hpb->pre_req_max_tr_len;
-}
-
static bool ufshpb_is_general_lun(int lun)
{
return lun < UFS_UPIU_MAX_UNIT_NUM_ID;
@@ -334,7 +324,7 @@ ufshpb_get_pos_from_lpn(struct ufshpb_lu *hpb, unsigned long lpn, int *rgn_idx,
static void
ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
- __be64 ppn, u8 transfer_len, int read_id)
+ __be64 ppn, u8 transfer_len)
{
unsigned char *cdb = lrbp->cmd->cmnd;
__be64 ppn_tmp = ppn;
@@ -346,256 +336,11 @@ ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
/* ppn value is stored as big-endian in the host memory */
memcpy(&cdb[6], &ppn_tmp, sizeof(__be64));
cdb[14] = transfer_len;
- cdb[15] = read_id;
+ cdb[15] = 0;
lrbp->cmd->cmd_len = UFS_CDB_SIZE;
}
-static inline void ufshpb_set_write_buf_cmd(unsigned char *cdb,
- unsigned long lpn, unsigned int len,
- int read_id)
-{
- cdb[0] = UFSHPB_WRITE_BUFFER;
- cdb[1] = UFSHPB_WRITE_BUFFER_PREFETCH_ID;
-
- put_unaligned_be32(lpn, &cdb[2]);
- cdb[6] = read_id;
- put_unaligned_be16(len * HPB_ENTRY_SIZE, &cdb[7]);
-
- cdb[9] = 0x00; /* Control = 0x00 */
-}
-
-static struct ufshpb_req *ufshpb_get_pre_req(struct ufshpb_lu *hpb)
-{
- struct ufshpb_req *pre_req;
-
- if (hpb->num_inflight_pre_req >= hpb->throttle_pre_req) {
- dev_info(&hpb->sdev_ufs_lu->sdev_dev,
- "pre_req throttle. inflight %d throttle %d",
- hpb->num_inflight_pre_req, hpb->throttle_pre_req);
- return NULL;
- }
-
- pre_req = list_first_entry_or_null(&hpb->lh_pre_req_free,
- struct ufshpb_req, list_req);
- if (!pre_req) {
- dev_info(&hpb->sdev_ufs_lu->sdev_dev, "There is no pre_req");
- return NULL;
- }
-
- list_del_init(&pre_req->list_req);
- hpb->num_inflight_pre_req++;
-
- return pre_req;
-}
-
-static inline void ufshpb_put_pre_req(struct ufshpb_lu *hpb,
- struct ufshpb_req *pre_req)
-{
- pre_req->req = NULL;
- bio_reset(pre_req->bio);
- list_add_tail(&pre_req->list_req, &hpb->lh_pre_req_free);
- hpb->num_inflight_pre_req--;
-}
-
-static void ufshpb_pre_req_compl_fn(struct request *req, blk_status_t error)
-{
- struct ufshpb_req *pre_req = (struct ufshpb_req *)req->end_io_data;
- struct ufshpb_lu *hpb = pre_req->hpb;
- unsigned long flags;
-
- if (error) {
- struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
- struct scsi_sense_hdr sshdr;
-
- dev_err(&hpb->sdev_ufs_lu->sdev_dev, "block status %d", error);
- scsi_command_normalize_sense(cmd, &sshdr);
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "code %x sense_key %x asc %x ascq %x",
- sshdr.response_code,
- sshdr.sense_key, sshdr.asc, sshdr.ascq);
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "byte4 %x byte5 %x byte6 %x additional_len %x",
- sshdr.byte4, sshdr.byte5,
- sshdr.byte6, sshdr.additional_length);
- }
-
- blk_mq_free_request(req);
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
- ufshpb_put_pre_req(pre_req->hpb, pre_req);
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
-}
-
-static int ufshpb_prep_entry(struct ufshpb_req *pre_req, struct page *page)
-{
- struct ufshpb_lu *hpb = pre_req->hpb;
- struct ufshpb_region *rgn;
- struct ufshpb_subregion *srgn;
- __be64 *addr;
- int offset = 0;
- int copied;
- unsigned long lpn = pre_req->wb.lpn;
- int rgn_idx, srgn_idx, srgn_offset;
- unsigned long flags;
-
- addr = page_address(page);
- ufshpb_get_pos_from_lpn(hpb, lpn, &rgn_idx, &srgn_idx, &srgn_offset);
-
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
-
-next_offset:
- rgn = hpb->rgn_tbl + rgn_idx;
- srgn = rgn->srgn_tbl + srgn_idx;
-
- if (!ufshpb_is_valid_srgn(rgn, srgn))
- goto mctx_error;
-
- if (!srgn->mctx)
- goto mctx_error;
-
- copied = ufshpb_fill_ppn_from_page(hpb, srgn->mctx, srgn_offset,
- pre_req->wb.len - offset,
- &addr[offset]);
-
- if (copied < 0)
- goto mctx_error;
-
- offset += copied;
- srgn_offset += copied;
-
- if (srgn_offset == hpb->entries_per_srgn) {
- srgn_offset = 0;
-
- if (++srgn_idx == hpb->srgns_per_rgn) {
- srgn_idx = 0;
- rgn_idx++;
- }
- }
-
- if (offset < pre_req->wb.len)
- goto next_offset;
-
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
- return 0;
-mctx_error:
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
- return -ENOMEM;
-}
-
-static int ufshpb_pre_req_add_bio_page(struct ufshpb_lu *hpb,
- struct request_queue *q,
- struct ufshpb_req *pre_req)
-{
- struct page *page = pre_req->wb.m_page;
- struct bio *bio = pre_req->bio;
- int entries_bytes, ret;
-
- if (!page)
- return -ENOMEM;
-
- if (ufshpb_prep_entry(pre_req, page))
- return -ENOMEM;
-
- entries_bytes = pre_req->wb.len * sizeof(__be64);
-
- ret = bio_add_pc_page(q, bio, page, entries_bytes, 0);
- if (ret != entries_bytes) {
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "bio_add_pc_page fail: %d", ret);
- return -ENOMEM;
- }
- return 0;
-}
-
-static inline int ufshpb_get_read_id(struct ufshpb_lu *hpb)
-{
- if (++hpb->cur_read_id >= MAX_HPB_READ_ID)
- hpb->cur_read_id = 1;
- return hpb->cur_read_id;
-}
-
-static int ufshpb_execute_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
- struct ufshpb_req *pre_req, int read_id)
-{
- struct scsi_device *sdev = cmd->device;
- struct request_queue *q = sdev->request_queue;
- struct request *req;
- struct scsi_request *rq;
- struct bio *bio = pre_req->bio;
-
- pre_req->hpb = hpb;
- pre_req->wb.lpn = sectors_to_logical(cmd->device,
- blk_rq_pos(scsi_cmd_to_rq(cmd)));
- pre_req->wb.len = sectors_to_logical(cmd->device,
- blk_rq_sectors(scsi_cmd_to_rq(cmd)));
- if (ufshpb_pre_req_add_bio_page(hpb, q, pre_req))
- return -ENOMEM;
-
- req = pre_req->req;
-
- /* 1. request setup */
- blk_rq_append_bio(req, bio);
- req->rq_disk = NULL;
- req->end_io_data = (void *)pre_req;
- req->end_io = ufshpb_pre_req_compl_fn;
-
- /* 2. scsi_request setup */
- rq = scsi_req(req);
- rq->retries = 1;
-
- ufshpb_set_write_buf_cmd(rq->cmd, pre_req->wb.lpn, pre_req->wb.len,
- read_id);
- rq->cmd_len = scsi_command_size(rq->cmd);
-
- if (blk_insert_cloned_request(q, req) != BLK_STS_OK)
- return -EAGAIN;
-
- hpb->stats.pre_req_cnt++;
-
- return 0;
-}
-
-static int ufshpb_issue_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
- int *read_id)
-{
- struct ufshpb_req *pre_req;
- struct request *req = NULL;
- unsigned long flags;
- int _read_id;
- int ret = 0;
-
- req = blk_get_request(cmd->device->request_queue,
- REQ_OP_DRV_OUT | REQ_SYNC, BLK_MQ_REQ_NOWAIT);
- if (IS_ERR(req))
- return -EAGAIN;
-
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
- pre_req = ufshpb_get_pre_req(hpb);
- if (!pre_req) {
- ret = -EAGAIN;
- goto unlock_out;
- }
- _read_id = ufshpb_get_read_id(hpb);
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
-
- pre_req->req = req;
-
- ret = ufshpb_execute_pre_req(hpb, cmd, pre_req, _read_id);
- if (ret)
- goto free_pre_req;
-
- *read_id = _read_id;
-
- return ret;
-free_pre_req:
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
- ufshpb_put_pre_req(hpb, pre_req);
-unlock_out:
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
- blk_put_request(req);
- return ret;
-}
-
/*
* This function will set up HPB read command using host-side L2P map data.
*/
@@ -609,7 +354,6 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
__be64 ppn;
unsigned long flags;
int transfer_len, rgn_idx, srgn_idx, srgn_offset;
- int read_id = 0;
int err = 0;
hpb = ufshpb_get_hpb_data(cmd->device);
@@ -685,24 +429,8 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
dev_err(hba->dev, "get ppn failed. err %d\n", err);
return err;
}
- if (!ufshpb_is_legacy(hba) &&
- ufshpb_is_required_wb(hpb, transfer_len)) {
- err = ufshpb_issue_pre_req(hpb, cmd, &read_id);
- if (err) {
- unsigned long timeout;
-
- timeout = cmd->jiffies_at_alloc + msecs_to_jiffies(
- hpb->params.requeue_timeout_ms);
-
- if (time_before(jiffies, timeout))
- return -EAGAIN;
-
- hpb->stats.miss_cnt++;
- return 0;
- }
- }
- ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len, read_id);
+ ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len);
hpb->stats.hit_cnt++;
return 0;
@@ -721,7 +449,7 @@ static struct ufshpb_req *ufshpb_get_req(struct ufshpb_lu *hpb,
return NULL;
retry:
- req = blk_get_request(hpb->sdev_ufs_lu->request_queue, dir,
+ req = blk_mq_alloc_request(hpb->sdev_ufs_lu->request_queue, dir,
BLK_MQ_REQ_NOWAIT);
if (!atomic && (PTR_ERR(req) == -EWOULDBLOCK) && (--retries > 0)) {
@@ -745,7 +473,7 @@ free_rq:
static void ufshpb_put_req(struct ufshpb_lu *hpb, struct ufshpb_req *rq)
{
- blk_put_request(rq->req);
+ blk_mq_free_request(rq->req);
kmem_cache_free(hpb->map_req_cache, rq);
}
@@ -1841,16 +1569,11 @@ static void ufshpb_lu_parameter_init(struct ufs_hba *hba,
u32 entries_per_rgn;
u64 rgn_mem_size, tmp;
- /* for pre_req */
- hpb->pre_req_min_tr_len = hpb_dev_info->max_hpb_single_cmd + 1;
-
if (ufshpb_is_legacy(hba))
hpb->pre_req_max_tr_len = HPB_LEGACY_CHUNK_HIGH;
else
hpb->pre_req_max_tr_len = HPB_MULTI_CHUNK_HIGH;
- hpb->cur_read_id = 0;
-
hpb->lu_pinned_start = hpb_lu_info->pinned_start;
hpb->lu_pinned_end = hpb_lu_info->num_pinned ?
(hpb_lu_info->pinned_start + hpb_lu_info->num_pinned - 1)
diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
index a79e07398970..f15d8fdbce2e 100644
--- a/drivers/scsi/ufs/ufshpb.h
+++ b/drivers/scsi/ufs/ufshpb.h
@@ -241,8 +241,6 @@ struct ufshpb_lu {
spinlock_t param_lock;
struct list_head lh_pre_req_free;
- int cur_read_id;
- int pre_req_min_tr_len;
int pre_req_max_tr_len;
/* cached L2P map management worker */
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 07d0250f17c3..b8455fcbf18b 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -22,6 +22,7 @@
#include <linux/virtio_scsi.h>
#include <linux/cpu.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_cmnd.h>
diff --git a/drivers/spi/spi-altera-dfl.c b/drivers/spi/spi-altera-dfl.c
index 44fc9ee13fc7..ca40923258af 100644
--- a/drivers/spi/spi-altera-dfl.c
+++ b/drivers/spi/spi-altera-dfl.c
@@ -134,7 +134,7 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev)
if (!master)
return -ENOMEM;
- master->bus_num = dfl_dev->id;
+ master->bus_num = -1;
hw = spi_master_get_devdata(master);
diff --git a/drivers/spi/spi-altera-platform.c b/drivers/spi/spi-altera-platform.c
index f7a7c14e3679..65147aae82a1 100644
--- a/drivers/spi/spi-altera-platform.c
+++ b/drivers/spi/spi-altera-platform.c
@@ -48,7 +48,7 @@ static int altera_spi_probe(struct platform_device *pdev)
return err;
/* setup the master state. */
- master->bus_num = pdev->id;
+ master->bus_num = -1;
if (pdata) {
if (pdata->num_chipselect > ALTERA_SPI_MAX_CS) {
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index feebda66f56e..e4484ace584e 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1716,12 +1716,13 @@ static int verify_controller_parameters(struct pl022 *pl022,
return -EINVAL;
}
} else {
- if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX)
+ if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX) {
dev_err(&pl022->adev->dev,
"Microwire half duplex mode requested,"
" but this is only available in the"
" ST version of PL022\n");
- return -EINVAL;
+ return -EINVAL;
+ }
}
}
return 0;
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index ef4a8e189fba..8190b840065f 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -20,6 +20,7 @@
#include <linux/vmalloc.h>
#include <linux/falloc.h>
#include <linux/uio.h>
+#include <linux/scatterlist.h>
#include <scsi/scsi_proto.h>
#include <asm/unaligned.h>
@@ -244,7 +245,7 @@ struct target_core_file_cmd {
struct bio_vec bvecs[];
};
-static void cmd_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
+static void cmd_rw_aio_complete(struct kiocb *iocb, long ret)
{
struct target_core_file_cmd *cmd;
@@ -302,7 +303,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
ret = call_read_iter(file, &aio_cmd->iocb, &iter);
if (ret != -EIOCBQUEUED)
- cmd_rw_aio_complete(&aio_cmd->iocb, ret, 0);
+ cmd_rw_aio_complete(&aio_cmd->iocb, ret);
return 0;
}
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 4069a1edcfa3..b1ef041cacd8 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -16,12 +16,14 @@
#include <linux/timer.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/bio.h>
#include <linux/genhd.h>
#include <linux/file.h>
#include <linux/module.h>
+#include <linux/scatterlist.h>
#include <scsi/scsi_proto.h>
#include <asm/unaligned.h>
@@ -230,9 +232,9 @@ static unsigned long long iblock_emulate_read_cap_with_block_size(
struct block_device *bd,
struct request_queue *q)
{
- unsigned long long blocks_long = (div_u64(i_size_read(bd->bd_inode),
- bdev_logical_block_size(bd)) - 1);
u32 block_size = bdev_logical_block_size(bd);
+ unsigned long long blocks_long =
+ div_u64(bdev_nr_bytes(bd), block_size) - 1;
if (block_size == dev->dev_attrib.block_size)
return blocks_long;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 75ef52f008ff..7fa57fb57bf2 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -980,11 +980,10 @@ pscsi_execute_cmd(struct se_cmd *cmd)
memcpy(pt->pscsi_cdb, cmd->t_task_cdb,
scsi_command_size(cmd->t_task_cdb));
- req = blk_get_request(pdv->pdv_sd->request_queue,
+ req = scsi_alloc_request(pdv->pdv_sd->request_queue,
cmd->data_direction == DMA_TO_DEVICE ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
- pr_err("PSCSI: blk_get_request() failed\n");
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
goto fail;
}
@@ -1012,7 +1011,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
return 0;
fail_put_request:
- blk_put_request(req);
+ blk_mq_free_request(req);
fail:
kfree(pt);
return ret;
@@ -1067,7 +1066,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status)
break;
}
- blk_put_request(req);
+ blk_mq_free_request(req);
kfree(pt);
}
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 8260f38025b7..e20c19a0f106 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -831,7 +831,7 @@ static void ffs_user_copy_worker(struct work_struct *work)
kthread_unuse_mm(io_data->mm);
}
- io_data->kiocb->ki_complete(io_data->kiocb, ret, ret);
+ io_data->kiocb->ki_complete(io_data->kiocb, ret);
if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)
eventfd_signal(io_data->ffs->ffs_eventfd, 1);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 539220d7f5b6..78be94750232 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -469,7 +469,7 @@ static void ep_user_copy_worker(struct work_struct *work)
ret = -EFAULT;
/* completing the iocb can drop the ctx and mm, don't touch mm after */
- iocb->ki_complete(iocb, ret, ret);
+ iocb->ki_complete(iocb, ret);
kfree(priv->buf);
kfree(priv->to_free);
@@ -496,11 +496,8 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req)
kfree(priv->to_free);
kfree(priv);
iocb->private = NULL;
- /* aio_complete() reports bytes-transferred _and_ faults */
-
iocb->ki_complete(iocb,
- req->actual ? req->actual : (long)req->status,
- req->status);
+ req->actual ? req->actual : (long)req->status);
} else {
/* ep_copy_to_user() won't report both; we hide some faults */
if (unlikely(0 != req->status))
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 26e3d90d1e7c..841667a896dd 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -80,6 +80,7 @@ struct vduse_dev {
struct vdpa_callback config_cb;
struct work_struct inject;
spinlock_t irq_lock;
+ struct rw_semaphore rwsem;
int minor;
bool broken;
bool connected;
@@ -410,6 +411,8 @@ static void vduse_dev_reset(struct vduse_dev *dev)
if (domain->bounce_map)
vduse_domain_reset_bounce_map(domain);
+ down_write(&dev->rwsem);
+
dev->status = 0;
dev->driver_features = 0;
dev->generation++;
@@ -443,6 +446,8 @@ static void vduse_dev_reset(struct vduse_dev *dev)
flush_work(&vq->inject);
flush_work(&vq->kick);
}
+
+ up_write(&dev->rwsem);
}
static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx,
@@ -885,6 +890,23 @@ static void vduse_vq_irq_inject(struct work_struct *work)
spin_unlock_irq(&vq->irq_lock);
}
+static int vduse_dev_queue_irq_work(struct vduse_dev *dev,
+ struct work_struct *irq_work)
+{
+ int ret = -EINVAL;
+
+ down_read(&dev->rwsem);
+ if (!(dev->status & VIRTIO_CONFIG_S_DRIVER_OK))
+ goto unlock;
+
+ ret = 0;
+ queue_work(vduse_irq_wq, irq_work);
+unlock:
+ up_read(&dev->rwsem);
+
+ return ret;
+}
+
static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
@@ -966,8 +988,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
break;
}
case VDUSE_DEV_INJECT_CONFIG_IRQ:
- ret = 0;
- queue_work(vduse_irq_wq, &dev->inject);
+ ret = vduse_dev_queue_irq_work(dev, &dev->inject);
break;
case VDUSE_VQ_SETUP: {
struct vduse_vq_config config;
@@ -1053,9 +1074,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
if (index >= dev->vq_num)
break;
- ret = 0;
index = array_index_nospec(index, dev->vq_num);
- queue_work(vduse_irq_wq, &dev->vqs[index].inject);
+ ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject);
break;
}
default:
@@ -1136,6 +1156,7 @@ static struct vduse_dev *vduse_dev_create(void)
INIT_LIST_HEAD(&dev->send_list);
INIT_LIST_HEAD(&dev->recv_list);
spin_lock_init(&dev->irq_lock);
+ init_rwsem(&dev->rwsem);
INIT_WORK(&dev->inject, vduse_dev_irq_inject);
init_waitqueue_head(&dev->waitq);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index dd95dfd85e98..3035bb6f5458 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -576,7 +576,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
/* Last one doesn't continue. */
desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
if (!indirect && vq->use_dma_api)
- vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags =
+ vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &=
~VRING_DESC_F_NEXT;
if (indirect) {
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 643c6c2d0b72..ced2fc0deb8c 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -71,8 +71,6 @@
#define TCOBASE(p) ((p)->tco_res->start)
/* SMI Control and Enable Register */
#define SMI_EN(p) ((p)->smi_res->start)
-#define TCO_EN (1 << 13)
-#define GBL_SMI_EN (1 << 0)
#define TCO_RLD(p) (TCOBASE(p) + 0x00) /* TCO Timer Reload/Curr. Value */
#define TCOv1_TMR(p) (TCOBASE(p) + 0x01) /* TCOv1 Timer Initial Value*/
@@ -357,12 +355,8 @@ static int iTCO_wdt_set_timeout(struct watchdog_device *wd_dev, unsigned int t)
tmrval = seconds_to_ticks(p, t);
- /*
- * If TCO SMIs are off, the timer counts down twice before rebooting.
- * Otherwise, the BIOS generally reboots when the SMI triggers.
- */
- if (p->smi_res &&
- (inl(SMI_EN(p)) & (TCO_EN | GBL_SMI_EN)) != (TCO_EN | GBL_SMI_EN))
+ /* For TCO v1 the timer counts down twice before rebooting */
+ if (p->iTCO_version == 1)
tmrval /= 2;
/* from the specs: */
@@ -527,7 +521,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
* Disables TCO logic generating an SMI#
*/
val32 = inl(SMI_EN(p));
- val32 &= ~TCO_EN; /* Turn off SMI clearing watchdog */
+ val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */
outl(val32, SMI_EN(p));
}
diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c
index 2693ffb24ac7..31b03fa71341 100644
--- a/drivers/watchdog/ixp4xx_wdt.c
+++ b/drivers/watchdog/ixp4xx_wdt.c
@@ -119,7 +119,7 @@ static int ixp4xx_wdt_probe(struct platform_device *pdev)
iwdt = devm_kzalloc(dev, sizeof(*iwdt), GFP_KERNEL);
if (!iwdt)
return -ENOMEM;
- iwdt->base = dev->platform_data;
+ iwdt->base = (void __iomem *)dev->platform_data;
/*
* Retrieve rate from a fixed clock from the device tree if
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index 1616f93dfad7..74d785b2b478 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -268,8 +268,12 @@ static int omap_wdt_probe(struct platform_device *pdev)
wdev->wdog.bootstatus = WDIOF_CARDRESET;
}
- if (!early_enable)
+ if (early_enable) {
+ omap_wdt_start(&wdev->wdog);
+ set_bit(WDOG_HW_RUNNING, &wdev->wdog.status);
+ } else {
omap_wdt_disable(wdev);
+ }
ret = watchdog_register_device(&wdev->wdog);
if (ret) {
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index ee9ff38929eb..9791c74aebd4 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -130,7 +130,7 @@ static u64 sbsa_gwdt_reg_read(struct sbsa_gwdt *gwdt)
if (gwdt->version == 0)
return readl(gwdt->control_base + SBSA_GWDT_WOR);
else
- return readq(gwdt->control_base + SBSA_GWDT_WOR);
+ return lo_hi_readq(gwdt->control_base + SBSA_GWDT_WOR);
}
static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt)
@@ -138,7 +138,7 @@ static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt)
if (gwdt->version == 0)
writel((u32)val, gwdt->control_base + SBSA_GWDT_WOR);
else
- writeq(val, gwdt->control_base + SBSA_GWDT_WOR);
+ lo_hi_writeq(val, gwdt->control_base + SBSA_GWDT_WOR);
}
/*
@@ -411,4 +411,3 @@ MODULE_AUTHOR("Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>");
MODULE_AUTHOR("Al Stone <al.stone@linaro.org>");
MODULE_AUTHOR("Timur Tabi <timur@codeaurora.org>");
MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index c6c2a513ec92..c609005a9eaa 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -389,7 +389,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
* blocks, we will have to change it.
*/
- size = i_size_read(sb->s_bdev->bd_inode) >> 9;
+ size = bdev_nr_sectors(sb->s_bdev);
pr_debug("initial blocksize=%d, #blocks=%d\n", 512, size);
affs_set_blocksize(sb, PAGE_SIZE);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index f24370f5c774..8b1d9c2f6bec 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -861,7 +861,8 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
*/
vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
{
- struct page *page = thp_head(vmf->page);
+ struct folio *folio = page_folio(vmf->page);
+ struct page *page = &folio->page;
struct file *file = vmf->vma->vm_file;
struct inode *inode = file_inode(file);
struct afs_vnode *vnode = AFS_FS_I(inode);
@@ -884,7 +885,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
goto out;
#endif
- if (wait_on_page_writeback_killable(page))
+ if (folio_wait_writeback_killable(folio))
goto out;
if (lock_page_killable(page) < 0)
@@ -894,8 +895,8 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
* details the portion of the page we need to write back and we might
* need to redirty the page if there's a problem.
*/
- if (wait_on_page_writeback_killable(page) < 0) {
- unlock_page(page);
+ if (folio_wait_writeback_killable(folio) < 0) {
+ folio_unlock(folio);
goto out;
}
diff --git a/fs/aio.c b/fs/aio.c
index 51b08ab01dff..836dc7e48db7 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1417,7 +1417,7 @@ static void aio_remove_iocb(struct aio_kiocb *iocb)
spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
-static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+static void aio_complete_rw(struct kiocb *kiocb, long res)
{
struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
@@ -1437,7 +1437,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
}
iocb->ki_res.res = res;
- iocb->ki_res.res2 = res2;
+ iocb->ki_res.res2 = 0;
iocb_put(iocb);
}
@@ -1508,7 +1508,7 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
ret = -EINTR;
fallthrough;
default:
- req->ki_complete(req, ret, 0);
+ req->ki_complete(req, ret);
}
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1d071c8d6fff..32da97c3c19d 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -9,6 +9,7 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
+#include <linux/kthread.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
@@ -173,9 +174,10 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
/* Hash through the page sector by sector */
for (pg_offset = 0; pg_offset < bytes_left;
pg_offset += sectorsize) {
- kaddr = page_address(page);
+ kaddr = kmap_atomic(page);
crypto_shash_digest(shash, kaddr + pg_offset,
sectorsize, csum);
+ kunmap_atomic(kaddr);
if (memcmp(&csum, cb_sum, csum_size) != 0) {
btrfs_print_data_csum_error(inode, disk_start,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 74c8e18f3720..c3983bdaf4b8 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -7,6 +7,7 @@
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/mm.h>
+#include <linux/error-injection.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 59ef388d43bc..c85a7d44da79 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -281,8 +281,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
}
- if (i_size_read(bdev->bd_inode) <
- btrfs_device_get_total_bytes(srcdev)) {
+ if (bdev_nr_bytes(bdev) < btrfs_device_get_total_bytes(srcdev)) {
btrfs_err(fs_info,
"target device is smaller than source device!");
ret = -EINVAL;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c7254331cf38..59c3be8c1f4c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3748,7 +3748,7 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
else if (ret)
return ERR_PTR(ret);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode))
+ if (bytenr + BTRFS_SUPER_INFO_SIZE >= bdev_nr_bytes(bdev))
return ERR_PTR(-EINVAL);
page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5fec009fbe63..b8c911a4a320 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6,6 +6,7 @@
#include <crypto/hash.h>
#include <linux/kernel.h>
#include <linux/bio.h>
+#include <linux/blk-cgroup.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
@@ -287,8 +288,9 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
cur_size = min_t(unsigned long, compressed_size,
PAGE_SIZE);
- kaddr = page_address(cpage);
+ kaddr = kmap_atomic(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
+ kunmap_atomic(kaddr);
i++;
ptr += cur_size;
@@ -8261,7 +8263,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
return dip;
}
-static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter,
+static void btrfs_submit_direct(const struct iomap_iter *iter,
struct bio *dio_bio, loff_t file_offset)
{
struct inode *inode = iter->inode;
@@ -8291,7 +8293,7 @@ static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter,
}
dio_bio->bi_status = BLK_STS_RESOURCE;
bio_endio(dio_bio);
- return BLK_QC_T_NONE;
+ return;
}
if (!write) {
@@ -8384,15 +8386,13 @@ static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter,
free_extent_map(em);
} while (submit_len > 0);
- return BLK_QC_T_NONE;
+ return;
out_err_em:
free_extent_map(em);
out_err:
dip->dio_bio->bi_status = status;
btrfs_dio_private_put(dip);
-
- return BLK_QC_T_NONE;
}
const struct iomap_ops btrfs_dio_iomap_ops = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 92424a22d8d6..02ff085c31bf 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1691,7 +1691,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
}
if (!strcmp(sizestr, "max"))
- new_size = device->bdev->bd_inode->i_size;
+ new_size = bdev_nr_bytes(device->bdev);
else {
if (sizestr[0] == '-') {
mod = -1;
@@ -1732,7 +1732,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
ret = -EINVAL;
goto out_finish;
}
- if (new_size > device->bdev->bd_inode->i_size) {
+ if (new_size > bdev_nr_bytes(device->bdev)) {
ret = -EFBIG;
goto out_finish;
}
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 00cffc183ec0..65cb0766e62d 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -131,6 +131,7 @@ static int copy_compressed_data_to_page(char *compressed_data,
u32 sector_bytes_left;
u32 orig_out;
struct page *cur_page;
+ char *kaddr;
/*
* We never allow a segment header crossing sector boundary, previous
@@ -147,7 +148,8 @@ static int copy_compressed_data_to_page(char *compressed_data,
out_pages[*cur_out / PAGE_SIZE] = cur_page;
}
- write_compress_length(page_address(cur_page) + offset_in_page(*cur_out),
+ kaddr = kmap(cur_page);
+ write_compress_length(kaddr + offset_in_page(*cur_out),
compressed_size);
*cur_out += LZO_LEN;
@@ -158,6 +160,7 @@ static int copy_compressed_data_to_page(char *compressed_data,
u32 copy_len = min_t(u32, sectorsize - *cur_out % sectorsize,
orig_out + compressed_size - *cur_out);
+ kunmap(cur_page);
cur_page = out_pages[*cur_out / PAGE_SIZE];
/* Allocate a new page */
if (!cur_page) {
@@ -166,8 +169,9 @@ static int copy_compressed_data_to_page(char *compressed_data,
return -ENOMEM;
out_pages[*cur_out / PAGE_SIZE] = cur_page;
}
+ kaddr = kmap(cur_page);
- memcpy(page_address(cur_page) + offset_in_page(*cur_out),
+ memcpy(kaddr + offset_in_page(*cur_out),
compressed_data + *cur_out - orig_out, copy_len);
*cur_out += copy_len;
@@ -179,12 +183,15 @@ static int copy_compressed_data_to_page(char *compressed_data,
*/
sector_bytes_left = round_up(*cur_out, sectorsize) - *cur_out;
if (sector_bytes_left >= LZO_LEN || sector_bytes_left == 0)
- return 0;
+ goto out;
/* The remaining size is not enough, pad it with zeros */
- memset(page_address(cur_page) + offset_in_page(*cur_out), 0,
+ memset(kaddr + offset_in_page(*cur_out), 0,
sector_bytes_left);
*cur_out += sector_bytes_left;
+
+out:
+ kunmap(cur_page);
return 0;
}
@@ -195,6 +202,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
struct workspace *workspace = list_entry(ws, struct workspace, list);
const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize;
struct page *page_in = NULL;
+ char *sizes_ptr;
int ret = 0;
/* Points to the file offset of input data */
u64 cur_in = start;
@@ -212,6 +220,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
*/
cur_out += LZO_LEN;
while (cur_in < start + len) {
+ char *data_in;
const u32 sectorsize_mask = sectorsize - 1;
u32 sector_off = (cur_in - start) & sectorsize_mask;
u32 in_len;
@@ -226,10 +235,12 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
/* Compress at most one sector of data each time */
in_len = min_t(u32, start + len - cur_in, sectorsize - sector_off);
ASSERT(in_len);
- ret = lzo1x_1_compress(page_address(page_in) +
+ data_in = kmap(page_in);
+ ret = lzo1x_1_compress(data_in +
offset_in_page(cur_in), in_len,
workspace->cbuf, &out_len,
workspace->mem);
+ kunmap(page_in);
if (ret < 0) {
pr_debug("BTRFS: lzo in loop returned %d\n", ret);
ret = -EIO;
@@ -260,7 +271,9 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
}
/* Store the size of all chunks of compressed data */
- write_compress_length(page_address(pages[0]), cur_out);
+ sizes_ptr = kmap_local_page(pages[0]);
+ write_compress_length(sizes_ptr, cur_out);
+ kunmap_local(sizes_ptr);
ret = 0;
*total_out = cur_out;
@@ -281,6 +294,7 @@ static void copy_compressed_segment(struct compressed_bio *cb,
u32 orig_in = *cur_in;
while (*cur_in < orig_in + len) {
+ char *kaddr;
struct page *cur_page;
u32 copy_len = min_t(u32, PAGE_SIZE - offset_in_page(*cur_in),
orig_in + len - *cur_in);
@@ -288,9 +302,11 @@ static void copy_compressed_segment(struct compressed_bio *cb,
ASSERT(copy_len);
cur_page = cb->compressed_pages[*cur_in / PAGE_SIZE];
+ kaddr = kmap(cur_page);
memcpy(dest + *cur_in - orig_in,
- page_address(cur_page) + offset_in_page(*cur_in),
+ kaddr + offset_in_page(*cur_in),
copy_len);
+ kunmap(cur_page);
*cur_in += copy_len;
}
@@ -301,6 +317,7 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
struct workspace *workspace = list_entry(ws, struct workspace, list);
const struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
const u32 sectorsize = fs_info->sectorsize;
+ char *kaddr;
int ret;
/* Compressed data length, can be unaligned */
u32 len_in;
@@ -309,7 +326,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
/* Bytes decompressed so far */
u32 cur_out = 0;
- len_in = read_compress_length(page_address(cb->compressed_pages[0]));
+ kaddr = kmap(cb->compressed_pages[0]);
+ len_in = read_compress_length(kaddr);
+ kunmap(cb->compressed_pages[0]);
cur_in += LZO_LEN;
/*
@@ -343,8 +362,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
(cur_in + LZO_LEN - 1) / sectorsize);
cur_page = cb->compressed_pages[cur_in / PAGE_SIZE];
ASSERT(cur_page);
- seg_len = read_compress_length(page_address(cur_page) +
- offset_in_page(cur_in));
+ kaddr = kmap(cur_page);
+ seg_len = read_compress_length(kaddr + offset_in_page(cur_in));
+ kunmap(cur_page);
cur_in += LZO_LEN;
/* Copy the compressed segment payload into workspace */
@@ -429,7 +449,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
- kaddr = page_address(dest_page);
+ kaddr = kmap_local_page(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
/*
@@ -439,6 +459,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
*/
if (bytes < destlen)
memset(kaddr+bytes, 0, destlen-bytes);
+ kunmap_local(kaddr);
out:
return ret;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 546bf1146b2d..61ac57bcbf1a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -509,7 +509,7 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
}
if (flush)
- filemap_write_and_wait((*bdev)->bd_inode->i_mapping);
+ sync_blockdev(*bdev);
ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE);
if (ret) {
blkdev_put(*bdev, flags);
@@ -1293,7 +1293,7 @@ static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev
pgoff_t index;
/* make sure our super fits in the device */
- if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
+ if (bytenr + PAGE_SIZE >= bdev_nr_bytes(bdev))
return ERR_PTR(-EINVAL);
/* make sure our super fits in the page */
@@ -2657,8 +2657,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
device->io_width = fs_info->sectorsize;
device->io_align = fs_info->sectorsize;
device->sector_size = fs_info->sectorsize;
- device->total_bytes = round_down(i_size_read(bdev->bd_inode),
- fs_info->sectorsize);
+ device->total_bytes =
+ round_down(bdev_nr_bytes(bdev), fs_info->sectorsize);
device->disk_total_bytes = device->total_bytes;
device->commit_total_bytes = device->total_bytes;
set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
@@ -7313,7 +7313,7 @@ static int read_one_dev(struct extent_buffer *leaf,
fill_device_from_item(leaf, dev_item, device);
if (device->bdev) {
- u64 max_total_bytes = i_size_read(device->bdev->bd_inode);
+ u64 max_total_bytes = bdev_nr_bytes(device->bdev);
if (device->total_bytes > max_total_bytes) {
btrfs_err(fs_info,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 8afa90074891..767a0c6c9694 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -126,7 +126,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[0] = out_page;
nr_pages = 1;
@@ -148,22 +148,26 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
int i;
for (i = 0; i < in_buf_pages; i++) {
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
in_page = find_get_page(mapping,
start >> PAGE_SHIFT);
- data_in = page_address(in_page);
+ data_in = kmap(in_page);
memcpy(workspace->buf + i * PAGE_SIZE,
data_in, PAGE_SIZE);
start += PAGE_SIZE;
}
workspace->strm.next_in = workspace->buf;
} else {
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
in_page = find_get_page(mapping,
start >> PAGE_SHIFT);
- data_in = page_address(in_page);
+ data_in = kmap(in_page);
start += PAGE_SIZE;
workspace->strm.next_in = data_in;
}
@@ -192,6 +196,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
* the stream end if required
*/
if (workspace->strm.avail_out == 0) {
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -202,7 +207,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[nr_pages] = out_page;
nr_pages++;
workspace->strm.avail_out = PAGE_SIZE;
@@ -229,6 +234,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
} else if (workspace->strm.avail_out == 0) {
/* get another page for the stream end */
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -239,7 +245,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[nr_pages] = out_page;
nr_pages++;
workspace->strm.avail_out = PAGE_SIZE;
@@ -258,8 +264,13 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
*total_in = workspace->strm.total_in;
out:
*out_pages = nr_pages;
- if (in_page)
+ if (out_page)
+ kunmap(out_page);
+
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
return ret;
}
@@ -276,7 +287,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
unsigned long buf_start;
struct page **pages_in = cb->compressed_pages;
- data_in = page_address(pages_in[page_in_index]);
+ data_in = kmap(pages_in[page_in_index]);
workspace->strm.next_in = data_in;
workspace->strm.avail_in = min_t(size_t, srclen, PAGE_SIZE);
workspace->strm.total_in = 0;
@@ -298,6 +309,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
if (Z_OK != zlib_inflateInit2(&workspace->strm, wbits)) {
pr_warn("BTRFS: inflateInit failed\n");
+ kunmap(pages_in[page_in_index]);
return -EIO;
}
while (workspace->strm.total_in < srclen) {
@@ -324,13 +336,13 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
if (workspace->strm.avail_in == 0) {
unsigned long tmp;
-
+ kunmap(pages_in[page_in_index]);
page_in_index++;
if (page_in_index >= total_pages_in) {
data_in = NULL;
break;
}
- data_in = page_address(pages_in[page_in_index]);
+ data_in = kmap(pages_in[page_in_index]);
workspace->strm.next_in = data_in;
tmp = srclen - workspace->strm.total_in;
workspace->strm.avail_in = min(tmp, PAGE_SIZE);
@@ -342,6 +354,8 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
ret = 0;
done:
zlib_inflateEnd(&workspace->strm);
+ if (data_in)
+ kunmap(pages_in[page_in_index]);
if (!ret)
zero_fill_bio(cb->orig_bio);
return ret;
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 56dce9f00988..f06b68040352 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -399,7 +399,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
/* map in the first page of input data */
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- workspace->in_buf.src = page_address(in_page);
+ workspace->in_buf.src = kmap(in_page);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
@@ -411,7 +411,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
}
pages[nr_pages++] = out_page;
- workspace->out_buf.dst = page_address(out_page);
+ workspace->out_buf.dst = kmap(out_page);
workspace->out_buf.pos = 0;
workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
@@ -446,6 +446,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
if (workspace->out_buf.pos == workspace->out_buf.size) {
tot_out += PAGE_SIZE;
max_out -= PAGE_SIZE;
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -457,7 +458,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
}
pages[nr_pages++] = out_page;
- workspace->out_buf.dst = page_address(out_page);
+ workspace->out_buf.dst = kmap(out_page);
workspace->out_buf.pos = 0;
workspace->out_buf.size = min_t(size_t, max_out,
PAGE_SIZE);
@@ -472,12 +473,13 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
/* Check if we need more input */
if (workspace->in_buf.pos == workspace->in_buf.size) {
tot_in += PAGE_SIZE;
+ kunmap(in_page);
put_page(in_page);
start += PAGE_SIZE;
len -= PAGE_SIZE;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- workspace->in_buf.src = page_address(in_page);
+ workspace->in_buf.src = kmap(in_page);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
}
@@ -504,6 +506,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
tot_out += PAGE_SIZE;
max_out -= PAGE_SIZE;
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -515,7 +518,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
}
pages[nr_pages++] = out_page;
- workspace->out_buf.dst = page_address(out_page);
+ workspace->out_buf.dst = kmap(out_page);
workspace->out_buf.pos = 0;
workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
}
@@ -531,8 +534,12 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
out:
*out_pages = nr_pages;
/* Cleanup */
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
+ if (out_page)
+ kunmap(out_page);
return ret;
}
@@ -556,7 +563,7 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
goto done;
}
- workspace->in_buf.src = page_address(pages_in[page_in_index]);
+ workspace->in_buf.src = kmap(pages_in[page_in_index]);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
@@ -592,14 +599,14 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
break;
if (workspace->in_buf.pos == workspace->in_buf.size) {
- page_in_index++;
+ kunmap(pages_in[page_in_index++]);
if (page_in_index >= total_pages_in) {
workspace->in_buf.src = NULL;
ret = -EIO;
goto done;
}
srclen -= PAGE_SIZE;
- workspace->in_buf.src = page_address(pages_in[page_in_index]);
+ workspace->in_buf.src = kmap(pages_in[page_in_index]);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
}
@@ -607,6 +614,8 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
ret = 0;
zero_fill_bio(cb->orig_bio);
done:
+ if (workspace->in_buf.src)
+ kunmap(pages_in[page_in_index]);
return ret;
}
diff --git a/fs/buffer.c b/fs/buffer.c
index c615387aedca..46bc589b7a03 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -878,7 +878,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
{
sector_t retval = ~((sector_t)0);
- loff_t sz = i_size_read(bdev->bd_inode);
+ loff_t sz = bdev_nr_bytes(bdev);
if (sz) {
unsigned int sizebits = blksize_bits(size);
@@ -897,7 +897,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
int uptodate = PageUptodate(page);
- sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size);
+ sector_t end_block = blkdev_max_block(bdev, size);
do {
if (!buffer_mapped(bh)) {
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index fac2e8e7b533..effe37ef8629 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -37,11 +37,11 @@ static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki)
/*
* Handle completion of a read from the cache.
*/
-static void cachefiles_read_complete(struct kiocb *iocb, long ret, long ret2)
+static void cachefiles_read_complete(struct kiocb *iocb, long ret)
{
struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
- _enter("%ld,%ld", ret, ret2);
+ _enter("%ld", ret);
if (ki->term_func) {
if (ret >= 0)
@@ -139,7 +139,7 @@ static int cachefiles_read(struct netfs_cache_resources *cres,
fallthrough;
default:
ki->was_async = false;
- cachefiles_read_complete(&ki->iocb, ret, 0);
+ cachefiles_read_complete(&ki->iocb, ret);
if (ret > 0)
ret = 0;
break;
@@ -159,12 +159,12 @@ presubmission_error:
/*
* Handle completion of a write to the cache.
*/
-static void cachefiles_write_complete(struct kiocb *iocb, long ret, long ret2)
+static void cachefiles_write_complete(struct kiocb *iocb, long ret)
{
struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
struct inode *inode = file_inode(ki->iocb.ki_filp);
- _enter("%ld,%ld", ret, ret2);
+ _enter("%ld", ret);
/* Tell lockdep we inherited freeze protection from submission thread */
__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
@@ -244,7 +244,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres,
fallthrough;
default:
ki->was_async = false;
- cachefiles_write_complete(&ki->iocb, ret, 0);
+ cachefiles_write_complete(&ki->iocb, ret);
if (ret > 0)
ret = 0;
break;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 8ffc40e84a59..fcf4f3b72923 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -25,20 +25,20 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
struct cachefiles_object *object;
struct fscache_retrieval *op = monitor->op;
struct wait_page_key *key = _key;
- struct page *page = wait->private;
+ struct folio *folio = wait->private;
ASSERT(key);
_enter("{%lu},%u,%d,{%p,%u}",
monitor->netfs_page->index, mode, sync,
- key->page, key->bit_nr);
+ key->folio, key->bit_nr);
- if (key->page != page || key->bit_nr != PG_locked)
+ if (key->folio != folio || key->bit_nr != PG_locked)
return 0;
- _debug("--- monitor %p %lx ---", page, page->flags);
+ _debug("--- monitor %p %lx ---", folio, folio->flags);
- if (!PageUptodate(page) && !PageError(page)) {
+ if (!folio_test_uptodate(folio) && !folio_test_error(folio)) {
/* unlocked, not uptodate and not erronous? */
_debug("page probably truncated");
}
@@ -107,7 +107,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object,
put_page(backpage2);
INIT_LIST_HEAD(&monitor->op_link);
- add_page_wait_queue(backpage, &monitor->monitor);
+ folio_add_wait_queue(page_folio(backpage), &monitor->monitor);
if (trylock_page(backpage)) {
ret = -EIO;
@@ -294,7 +294,7 @@ monitor_backing_page:
get_page(backpage);
monitor->back_page = backpage;
monitor->monitor.private = backpage;
- add_page_wait_queue(backpage, &monitor->monitor);
+ folio_add_wait_queue(page_folio(backpage), &monitor->monitor);
monitor = NULL;
/* but the page may have been read before the monitor was installed, so
@@ -548,7 +548,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
get_page(backpage);
monitor->back_page = backpage;
monitor->monitor.private = backpage;
- add_page_wait_queue(backpage, &monitor->monitor);
+ folio_add_wait_queue(page_folio(backpage), &monitor->monitor);
monitor = NULL;
/* but the page may have been read before the monitor was
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index e61018d9764e..b129ea551378 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1022,7 +1022,7 @@ static void ceph_aio_complete(struct inode *inode,
ceph_put_cap_refs(ci, (aio_req->write ? CEPH_CAP_FILE_WR :
CEPH_CAP_FILE_RD));
- aio_req->iocb->ki_complete(aio_req->iocb, ret, 0);
+ aio_req->iocb->ki_complete(aio_req->iocb, ret);
ceph_free_cap_flush(aio_req->prealloc_cf);
kfree(aio_req);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index bdeb271f47d9..d8c31069fbf2 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -302,9 +302,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- /* No mandatory locks */
- if (fl->fl_type & LOCK_MAND)
- return -EOPNOTSUPP;
dout("ceph_flock, fl_file: %p\n", fl->fl_file);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 13f3182cf796..1b855fcb179e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3184,7 +3184,7 @@ restart_loop:
mutex_unlock(&ctx->aio_mutex);
if (ctx->iocb && ctx->iocb->ki_complete)
- ctx->iocb->ki_complete(ctx->iocb, ctx->rc, 0);
+ ctx->iocb->ki_complete(ctx->iocb, ctx->rc);
else
complete(&ctx->done);
}
@@ -3917,7 +3917,7 @@ again:
mutex_unlock(&ctx->aio_mutex);
if (ctx->iocb && ctx->iocb->ki_complete)
- ctx->iocb->ki_complete(ctx->iocb, ctx->rc, 0);
+ ctx->iocb->ki_complete(ctx->iocb, ctx->rc);
else
complete(&ctx->done);
}
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 2be65269a987..666aa380011e 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -209,7 +209,7 @@ static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset,
return read_buffers[i] + blk_offset;
}
- devsize = mapping->host->i_size >> PAGE_SHIFT;
+ devsize = bdev_nr_bytes(sb->s_bdev) >> PAGE_SHIFT;
/* Ok, read in BLKS_PER_BUF pages completely first. */
for (i = 0; i < BLKS_PER_BUF; i++) {
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 68a2de6b5a9b..bfc2a5b74ed3 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * This contains encryption functions for per-file encryption.
+ * Utility functions for file contents encryption/decryption on
+ * block device-based filesystems.
*
* Copyright (C) 2015, Google, Inc.
* Copyright (C) 2015, Motorola Mobility
- *
- * Written by Michael Halcrow, 2014.
- *
- * Filename encryption additions
- * Uday Savagaonkar, 2014
- * Encryption policy handling additions
- * Ildar Muslukhov, 2014
- * Add fscrypt_pullback_bio_page()
- * Jaegeuk Kim, 2015.
- *
- * This has not yet undergone a rigorous security audit.
- *
- * The usage of AES-XTS should conform to recommendations in NIST
- * Special Publication 800-38E and IEEE P1619/D16.
*/
#include <linux/pagemap.h>
@@ -26,6 +13,21 @@
#include <linux/namei.h>
#include "fscrypt_private.h"
+/**
+ * fscrypt_decrypt_bio() - decrypt the contents of a bio
+ * @bio: the bio to decrypt
+ *
+ * Decrypt the contents of a "read" bio following successful completion of the
+ * underlying disk read. The bio must be reading a whole number of blocks of an
+ * encrypted file directly into the page cache. If the bio is reading the
+ * ciphertext into bounce pages instead of the page cache (for example, because
+ * the file is also compressed, so decompression is required after decryption),
+ * then this function isn't applicable. This function may sleep, so it must be
+ * called from a workqueue rather than from the bio's bi_end_io callback.
+ *
+ * This function sets PG_error on any pages that contain any blocks that failed
+ * to be decrypted. The filesystem must not mark such pages uptodate.
+ */
void fscrypt_decrypt_bio(struct bio *bio)
{
struct bio_vec *bv;
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index eb538c28df94..a9be4bc74a94 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -429,8 +429,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
if (fscrypt_has_encryption_key(dir)) {
if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy,
- iname->len,
- dir->i_sb->s_cop->max_namelen,
+ iname->len, NAME_MAX,
&fname->crypto_buf.len))
return -ENAMETOOLONG;
fname->crypto_buf.name = kmalloc(fname->crypto_buf.len,
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 3fa965eb3336..5b0a9e6478b5 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -20,6 +20,11 @@
#define FSCRYPT_FILE_NONCE_SIZE 16
+/*
+ * Minimum size of an fscrypt master key. Note: a longer key will be required
+ * if ciphers with a 256-bit security strength are used. This is just the
+ * absolute minimum, which applies when only 128-bit encryption is used.
+ */
#define FSCRYPT_MIN_KEY_SIZE 16
#define FSCRYPT_CONTEXT_V1 1
@@ -413,7 +418,11 @@ struct fscrypt_master_key_secret {
*/
struct fscrypt_hkdf hkdf;
- /* Size of the raw key in bytes. Set even if ->raw isn't set. */
+ /*
+ * Size of the raw key in bytes. This remains set even if ->raw was
+ * zeroized due to no longer being needed. I.e. we still remember the
+ * size of the key even if we don't need to remember the key itself.
+ */
u32 size;
/* For v1 policy keys: the raw key. Wiped for v2 policy keys. */
@@ -549,8 +558,9 @@ int __init fscrypt_init_keyring(void);
struct fscrypt_mode {
const char *friendly_name;
const char *cipher_str;
- int keysize;
- int ivsize;
+ int keysize; /* key size in bytes */
+ int security_strength; /* security strength in bytes */
+ int ivsize; /* IV size in bytes */
int logged_impl_name;
enum blk_crypto_mode_num blk_crypto_mode;
};
diff --git a/fs/crypto/hkdf.c b/fs/crypto/hkdf.c
index e0ec21055505..7607d18b35fc 100644
--- a/fs/crypto/hkdf.c
+++ b/fs/crypto/hkdf.c
@@ -16,9 +16,14 @@
/*
* HKDF supports any unkeyed cryptographic hash algorithm, but fscrypt uses
- * SHA-512 because it is reasonably secure and efficient; and since it produces
- * a 64-byte digest, deriving an AES-256-XTS key preserves all 64 bytes of
- * entropy from the master key and requires only one iteration of HKDF-Expand.
+ * SHA-512 because it is well-established, secure, and reasonably efficient.
+ *
+ * HKDF-SHA256 was also considered, as its 256-bit security strength would be
+ * sufficient here. A 512-bit security strength is "nice to have", though.
+ * Also, on 64-bit CPUs, SHA-512 is usually just as fast as SHA-256. In the
+ * common case of deriving an AES-256-XTS key (512 bits), that can result in
+ * HKDF-SHA512 being much faster than HKDF-SHA256, as the longer digest size of
+ * SHA-512 causes HKDF-Expand to only need to do one iteration rather than two.
*/
#define HKDF_HMAC_ALG "hmac(sha512)"
#define HKDF_HASHLEN SHA512_DIGEST_SIZE
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index bca9c6658a7c..eede186b04ce 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -19,6 +19,7 @@ struct fscrypt_mode fscrypt_modes[] = {
.friendly_name = "AES-256-XTS",
.cipher_str = "xts(aes)",
.keysize = 64,
+ .security_strength = 32,
.ivsize = 16,
.blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_256_XTS,
},
@@ -26,12 +27,14 @@ struct fscrypt_mode fscrypt_modes[] = {
.friendly_name = "AES-256-CTS-CBC",
.cipher_str = "cts(cbc(aes))",
.keysize = 32,
+ .security_strength = 32,
.ivsize = 16,
},
[FSCRYPT_MODE_AES_128_CBC] = {
.friendly_name = "AES-128-CBC-ESSIV",
.cipher_str = "essiv(cbc(aes),sha256)",
.keysize = 16,
+ .security_strength = 16,
.ivsize = 16,
.blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV,
},
@@ -39,12 +42,14 @@ struct fscrypt_mode fscrypt_modes[] = {
.friendly_name = "AES-128-CTS-CBC",
.cipher_str = "cts(cbc(aes))",
.keysize = 16,
+ .security_strength = 16,
.ivsize = 16,
},
[FSCRYPT_MODE_ADIANTUM] = {
.friendly_name = "Adiantum",
.cipher_str = "adiantum(xchacha12,aes)",
.keysize = 32,
+ .security_strength = 32,
.ivsize = 32,
.blk_crypto_mode = BLK_ENCRYPTION_MODE_ADIANTUM,
},
@@ -117,8 +122,9 @@ err_free_tfm:
/*
* Prepare the crypto transform object or blk-crypto key in @prep_key, given the
- * raw key, encryption mode, and flag indicating which encryption implementation
- * (fs-layer or blk-crypto) will be used.
+ * raw key, encryption mode (@ci->ci_mode), flag indicating which encryption
+ * implementation (fs-layer or blk-crypto) will be used (@ci->ci_inlinecrypt),
+ * and IV generation method (@ci->ci_policy.flags).
*/
int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key,
const u8 *raw_key, const struct fscrypt_info *ci)
@@ -358,6 +364,45 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
}
/*
+ * Check whether the size of the given master key (@mk) is appropriate for the
+ * encryption settings which a particular file will use (@ci).
+ *
+ * If the file uses a v1 encryption policy, then the master key must be at least
+ * as long as the derived key, as this is a requirement of the v1 KDF.
+ *
+ * Otherwise, the KDF can accept any size key, so we enforce a slightly looser
+ * requirement: we require that the size of the master key be at least the
+ * maximum security strength of any algorithm whose key will be derived from it
+ * (but in practice we only need to consider @ci->ci_mode, since any other
+ * possible subkeys such as DIRHASH and INODE_HASH will never increase the
+ * required key size over @ci->ci_mode). This allows AES-256-XTS keys to be
+ * derived from a 256-bit master key, which is cryptographically sufficient,
+ * rather than requiring a 512-bit master key which is unnecessarily long. (We
+ * still allow 512-bit master keys if the user chooses to use them, though.)
+ */
+static bool fscrypt_valid_master_key_size(const struct fscrypt_master_key *mk,
+ const struct fscrypt_info *ci)
+{
+ unsigned int min_keysize;
+
+ if (ci->ci_policy.version == FSCRYPT_POLICY_V1)
+ min_keysize = ci->ci_mode->keysize;
+ else
+ min_keysize = ci->ci_mode->security_strength;
+
+ if (mk->mk_secret.size < min_keysize) {
+ fscrypt_warn(NULL,
+ "key with %s %*phN is too short (got %u bytes, need %u+ bytes)",
+ master_key_spec_type(&mk->mk_spec),
+ master_key_spec_len(&mk->mk_spec),
+ (u8 *)&mk->mk_spec.u,
+ mk->mk_secret.size, min_keysize);
+ return false;
+ }
+ return true;
+}
+
+/*
* Find the master key, then set up the inode's actual encryption key.
*
* If the master key is found in the filesystem-level keyring, then the
@@ -422,18 +467,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
goto out_release_key;
}
- /*
- * Require that the master key be at least as long as the derived key.
- * Otherwise, the derived key cannot possibly contain as much entropy as
- * that required by the encryption mode it will be used for. For v1
- * policies it's also required for the KDF to work at all.
- */
- if (mk->mk_secret.size < ci->ci_mode->keysize) {
- fscrypt_warn(NULL,
- "key with %s %*phN is too short (got %u bytes, need %u+ bytes)",
- master_key_spec_type(&mk_spec),
- master_key_spec_len(&mk_spec), (u8 *)&mk_spec.u,
- mk->mk_secret.size, ci->ci_mode->keysize);
+ if (!fscrypt_valid_master_key_size(mk, ci)) {
err = -ENOKEY;
goto out_release_key;
}
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b2e86e739d7a..654443558047 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -119,7 +119,6 @@ struct dio {
int flags; /* doesn't change */
int op;
int op_flags;
- blk_qc_t bio_cookie;
struct gendisk *bio_disk;
struct inode *inode;
loff_t i_size; /* i_size when submitted */
@@ -308,7 +307,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
if (ret > 0 && dio->op == REQ_OP_WRITE)
ret = generic_write_sync(dio->iocb, ret);
- dio->iocb->ki_complete(dio->iocb, ret, 0);
+ dio->iocb->ki_complete(dio->iocb, ret);
}
kmem_cache_free(dio_cache, dio);
@@ -438,11 +437,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
dio->bio_disk = bio->bi_bdev->bd_disk;
- if (sdio->submit_io) {
+ if (sdio->submit_io)
sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio);
- dio->bio_cookie = BLK_QC_T_NONE;
- } else
- dio->bio_cookie = submit_bio(bio);
+ else
+ submit_bio(bio);
sdio->bio = NULL;
sdio->boundary = 0;
@@ -481,9 +479,7 @@ static struct bio *dio_await_one(struct dio *dio)
__set_current_state(TASK_UNINTERRUPTIBLE);
dio->waiter = current;
spin_unlock_irqrestore(&dio->bio_lock, flags);
- if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
- !blk_poll(dio->bio_disk->queue, dio->bio_cookie, true))
- blk_io_schedule();
+ blk_io_schedule();
/* wake up sets us TASK_RUNNING */
spin_lock_irqsave(&dio->bio_lock, flags);
dio->waiter = NULL;
@@ -1214,8 +1210,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
} else {
dio->op = REQ_OP_READ;
}
- if (iocb->ki_flags & IOCB_HIPRI)
- dio->op_flags |= REQ_HIPRI;
/*
* For AIO O_(D)SYNC writes we need to defer completions to a workqueue
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 14b747026742..f57255ab88ed 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -6,16 +6,22 @@ config EROFS_FS
select FS_IOMAP
select LIBCRC32C
help
- EROFS (Enhanced Read-Only File System) is a lightweight
- read-only file system with modern designs (eg. page-sized
- blocks, inline xattrs/data, etc.) for scenarios which need
- high-performance read-only requirements, e.g. Android OS
- for mobile phones and LIVECDs.
+ EROFS (Enhanced Read-Only File System) is a lightweight read-only
+ file system with modern designs (e.g. no buffer heads, inline
+ xattrs/data, chunk-based deduplication, multiple devices, etc.) for
+ scenarios which need high-performance read-only solutions, e.g.
+ smartphones with Android OS, LiveCDs and high-density hosts with
+ numerous containers;
- It also provides fixed-sized output compression support,
- which improves storage density, keeps relatively higher
- compression ratios, which is more useful to achieve high
- performance for embedded devices with limited memory.
+ It also provides fixed-sized output compression support in order to
+ improve storage density as well as keep relatively higher compression
+ ratios and implements in-place decompression to reuse the file page
+ for compressed data temporarily with proper strategies, which is
+ quite useful to ensure guaranteed end-to-end runtime decompression
+ performance under extremely memory pressure without extra cost.
+
+ See the documentation at <file:Documentation/filesystems/erofs.rst>
+ for more details.
If unsure, say N.
@@ -76,3 +82,19 @@ config EROFS_FS_ZIP
Enable fixed-sized output compression for EROFS.
If you don't want to enable compression feature, say N.
+
+config EROFS_FS_ZIP_LZMA
+ bool "EROFS LZMA compressed data support"
+ depends on EROFS_FS_ZIP
+ select XZ_DEC
+ select XZ_DEC_MICROLZMA
+ help
+ Saying Y here includes support for reading EROFS file systems
+ containing LZMA compressed data, specifically called microLZMA. it
+ gives better compression ratios than the LZ4 algorithm, at the
+ expense of more CPU overhead.
+
+ LZMA support is an experimental feature for now and so most file
+ systems will be readable without selecting this option.
+
+ If unsure, say N.
diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile
index 1f9aced49070..756fe2d65272 100644
--- a/fs/erofs/Makefile
+++ b/fs/erofs/Makefile
@@ -4,3 +4,4 @@ obj-$(CONFIG_EROFS_FS) += erofs.o
erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o
erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o
erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o
+erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o
diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 3701c72bacb2..579406504919 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -8,11 +8,6 @@
#include "internal.h"
-enum {
- Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
- Z_EROFS_COMPRESSION_RUNTIME_MAX
-};
-
struct z_erofs_decompress_req {
struct super_block *sb;
struct page **in, **out;
@@ -25,6 +20,12 @@ struct z_erofs_decompress_req {
bool inplace_io, partial_decoding;
};
+struct z_erofs_decompressor {
+ int (*decompress)(struct z_erofs_decompress_req *rq,
+ struct page **pagepool);
+ char *name;
+};
+
/* some special page->private (unsigned long, see below) */
#define Z_EROFS_SHORTLIVED_PAGE (-1UL << 2)
#define Z_EROFS_PREALLOCATED_PAGE (-2UL << 2)
@@ -63,7 +64,7 @@ static inline bool z_erofs_is_shortlived_page(struct page *page)
return true;
}
-static inline bool z_erofs_put_shortlivedpage(struct list_head *pagepool,
+static inline bool z_erofs_put_shortlivedpage(struct page **pagepool,
struct page *page)
{
if (!z_erofs_is_shortlived_page(page))
@@ -74,13 +75,22 @@ static inline bool z_erofs_put_shortlivedpage(struct list_head *pagepool,
put_page(page);
} else {
/* follow the pcluster rule above. */
- set_page_private(page, 0);
- list_add(&page->lru, pagepool);
+ erofs_pagepool_add(pagepool, page);
}
return true;
}
+#define MNGD_MAPPING(sbi) ((sbi)->managed_cache->i_mapping)
+static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi,
+ struct page *page)
+{
+ return page->mapping == MNGD_MAPPING(sbi);
+}
+
int z_erofs_decompress(struct z_erofs_decompress_req *rq,
- struct list_head *pagepool);
+ struct page **pagepool);
+/* prototypes for specific algorithms */
+int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
+ struct page **pagepool);
#endif
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 9db829715652..808234d9190c 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -89,6 +89,7 @@ static int erofs_map_blocks(struct inode *inode,
erofs_off_t pos;
int err = 0;
+ map->m_deviceid = 0;
if (map->m_la >= inode->i_size) {
/* leave out-of-bound access unmapped */
map->m_flags = 0;
@@ -135,14 +136,8 @@ static int erofs_map_blocks(struct inode *inode,
map->m_flags = 0;
break;
default:
- /* only one device is supported for now */
- if (idx->device_id) {
- erofs_err(sb, "invalid device id %u @ %llu for nid %llu",
- le16_to_cpu(idx->device_id),
- chunknr, vi->nid);
- err = -EFSCORRUPTED;
- goto out_unlock;
- }
+ map->m_deviceid = le16_to_cpu(idx->device_id) &
+ EROFS_SB(sb)->device_id_mask;
map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr));
map->m_flags = EROFS_MAP_MAPPED;
break;
@@ -155,11 +150,55 @@ out:
return err;
}
+int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
+{
+ struct erofs_dev_context *devs = EROFS_SB(sb)->devs;
+ struct erofs_device_info *dif;
+ int id;
+
+ /* primary device by default */
+ map->m_bdev = sb->s_bdev;
+ map->m_daxdev = EROFS_SB(sb)->dax_dev;
+
+ if (map->m_deviceid) {
+ down_read(&devs->rwsem);
+ dif = idr_find(&devs->tree, map->m_deviceid - 1);
+ if (!dif) {
+ up_read(&devs->rwsem);
+ return -ENODEV;
+ }
+ map->m_bdev = dif->bdev;
+ map->m_daxdev = dif->dax_dev;
+ up_read(&devs->rwsem);
+ } else if (devs->extra_devices) {
+ down_read(&devs->rwsem);
+ idr_for_each_entry(&devs->tree, dif, id) {
+ erofs_off_t startoff, length;
+
+ if (!dif->mapped_blkaddr)
+ continue;
+ startoff = blknr_to_addr(dif->mapped_blkaddr);
+ length = blknr_to_addr(dif->blocks);
+
+ if (map->m_pa >= startoff &&
+ map->m_pa < startoff + length) {
+ map->m_pa -= startoff;
+ map->m_bdev = dif->bdev;
+ map->m_daxdev = dif->dax_dev;
+ break;
+ }
+ }
+ up_read(&devs->rwsem);
+ }
+ return 0;
+}
+
static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
{
int ret;
struct erofs_map_blocks map;
+ struct erofs_map_dev mdev;
map.m_la = offset;
map.m_llen = length;
@@ -168,8 +207,16 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
if (ret < 0)
return ret;
- iomap->bdev = inode->i_sb->s_bdev;
- iomap->dax_dev = EROFS_I_SB(inode)->dax_dev;
+ mdev = (struct erofs_map_dev) {
+ .m_deviceid = map.m_deviceid,
+ .m_pa = map.m_pa,
+ };
+ ret = erofs_map_dev(inode->i_sb, &mdev);
+ if (ret)
+ return ret;
+
+ iomap->bdev = mdev.m_bdev;
+ iomap->dax_dev = mdev.m_daxdev;
iomap->offset = map.m_la;
iomap->length = map.m_llen;
iomap->flags = 0;
@@ -188,15 +235,15 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
iomap->type = IOMAP_INLINE;
ipage = erofs_get_meta_page(inode->i_sb,
- erofs_blknr(map.m_pa));
+ erofs_blknr(mdev.m_pa));
if (IS_ERR(ipage))
return PTR_ERR(ipage);
iomap->inline_data = page_address(ipage) +
- erofs_blkoff(map.m_pa);
+ erofs_blkoff(mdev.m_pa);
iomap->private = ipage;
} else {
iomap->type = IOMAP_MAPPED;
- iomap->addr = map.m_pa;
+ iomap->addr = mdev.m_pa;
}
return 0;
}
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index a5bc4b1b7813..bf37fc76b182 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -16,17 +16,6 @@
#define LZ4_DECOMPRESS_INPLACE_MARGIN(srcsize) (((srcsize) >> 8) + 32)
#endif
-struct z_erofs_decompressor {
- /*
- * if destpages have sparsed pages, fill them with bounce pages.
- * it also check whether destpages indicate continuous physical memory.
- */
- int (*prepare_destpages)(struct z_erofs_decompress_req *rq,
- struct list_head *pagepool);
- int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out);
- char *name;
-};
-
int z_erofs_load_lz4_config(struct super_block *sb,
struct erofs_super_block *dsb,
struct z_erofs_lz4_cfgs *lz4, int size)
@@ -63,8 +52,12 @@ int z_erofs_load_lz4_config(struct super_block *sb,
return erofs_pcpubuf_growsize(sbi->lz4.max_pclusterblks);
}
-static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
- struct list_head *pagepool)
+/*
+ * Fill all gaps with bounce pages if it's a sparse page list. Also check if
+ * all physical pages are consecutive, which can be seen for moderate CR.
+ */
+static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq,
+ struct page **pagepool)
{
const unsigned int nr =
PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -119,7 +112,7 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
return kaddr ? 1 : 0;
}
-static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
+static void *z_erofs_lz4_handle_inplace_io(struct z_erofs_decompress_req *rq,
void *inpage, unsigned int *inputmargin, int *maptype,
bool support_0padding)
{
@@ -189,7 +182,8 @@ docopy:
return src;
}
-static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
+static int z_erofs_lz4_decompress_mem(struct z_erofs_decompress_req *rq,
+ u8 *out)
{
unsigned int inputmargin;
u8 *headpage, *src;
@@ -216,8 +210,8 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
}
rq->inputsize -= inputmargin;
- src = z_erofs_handle_inplace_io(rq, headpage, &inputmargin, &maptype,
- support_0padding);
+ src = z_erofs_lz4_handle_inplace_io(rq, headpage, &inputmargin,
+ &maptype, support_0padding);
if (IS_ERR(src))
return PTR_ERR(src);
@@ -233,7 +227,6 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
ret, rq->inputsize, inputmargin, rq->outputsize);
- WARN_ON(1);
print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
16, 1, src + inputmargin, rq->inputsize, true);
print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
@@ -242,6 +235,8 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
if (ret >= 0)
memset(out + ret, 0, rq->outputsize - ret);
ret = -EIO;
+ } else {
+ ret = 0;
}
if (maptype == 0) {
@@ -257,86 +252,25 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
return ret;
}
-static struct z_erofs_decompressor decompressors[] = {
- [Z_EROFS_COMPRESSION_SHIFTED] = {
- .name = "shifted"
- },
- [Z_EROFS_COMPRESSION_LZ4] = {
- .prepare_destpages = z_erofs_lz4_prepare_destpages,
- .decompress = z_erofs_lz4_decompress,
- .name = "lz4"
- },
-};
-
-static void copy_from_pcpubuf(struct page **out, const char *dst,
- unsigned short pageofs_out,
- unsigned int outputsize)
-{
- const char *end = dst + outputsize;
- const unsigned int righthalf = PAGE_SIZE - pageofs_out;
- const char *cur = dst - pageofs_out;
-
- while (cur < end) {
- struct page *const page = *out++;
-
- if (page) {
- char *buf = kmap_atomic(page);
-
- if (cur >= dst) {
- memcpy(buf, cur, min_t(uint, PAGE_SIZE,
- end - cur));
- } else {
- memcpy(buf + pageofs_out, cur + pageofs_out,
- min_t(uint, righthalf, end - cur));
- }
- kunmap_atomic(buf);
- }
- cur += PAGE_SIZE;
- }
-}
-
-static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq,
- struct list_head *pagepool)
+static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
+ struct page **pagepool)
{
const unsigned int nrpages_out =
PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
- const struct z_erofs_decompressor *alg = decompressors + rq->alg;
unsigned int dst_maptype;
void *dst;
int ret;
- /* two optimized fast paths only for non bigpcluster cases yet */
- if (rq->inputsize <= PAGE_SIZE) {
- if (nrpages_out == 1 && !rq->inplace_io) {
- DBG_BUGON(!*rq->out);
- dst = kmap_atomic(*rq->out);
- dst_maptype = 0;
- goto dstmap_out;
- }
-
- /*
- * For the case of small output size (especially much less
- * than PAGE_SIZE), memcpy the decompressed data rather than
- * compressed data is preferred.
- */
- if (rq->outputsize <= PAGE_SIZE * 7 / 8) {
- dst = erofs_get_pcpubuf(1);
- if (IS_ERR(dst))
- return PTR_ERR(dst);
-
- rq->inplace_io = false;
- ret = alg->decompress(rq, dst);
- if (!ret)
- copy_from_pcpubuf(rq->out, dst, rq->pageofs_out,
- rq->outputsize);
-
- erofs_put_pcpubuf(dst);
- return ret;
- }
+ /* one optimized fast path only for non bigpcluster cases yet */
+ if (rq->inputsize <= PAGE_SIZE && nrpages_out == 1 && !rq->inplace_io) {
+ DBG_BUGON(!*rq->out);
+ dst = kmap_atomic(*rq->out);
+ dst_maptype = 0;
+ goto dstmap_out;
}
/* general decoding path which can be used for all cases */
- ret = alg->prepare_destpages(rq, pagepool);
+ ret = z_erofs_lz4_prepare_dstpages(rq, pagepool);
if (ret < 0)
return ret;
if (ret) {
@@ -351,7 +285,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq,
dst_maptype = 2;
dstmap_out:
- ret = alg->decompress(rq, dst + rq->pageofs_out);
+ ret = z_erofs_lz4_decompress_mem(rq, dst + rq->pageofs_out);
if (!dst_maptype)
kunmap_atomic(dst);
@@ -360,8 +294,8 @@ dstmap_out:
return ret;
}
-static int z_erofs_shifted_transform(const struct z_erofs_decompress_req *rq,
- struct list_head *pagepool)
+static int z_erofs_shifted_transform(struct z_erofs_decompress_req *rq,
+ struct page **pagepool)
{
const unsigned int nrpages_out =
PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -399,10 +333,25 @@ static int z_erofs_shifted_transform(const struct z_erofs_decompress_req *rq,
return 0;
}
+static struct z_erofs_decompressor decompressors[] = {
+ [Z_EROFS_COMPRESSION_SHIFTED] = {
+ .decompress = z_erofs_shifted_transform,
+ .name = "shifted"
+ },
+ [Z_EROFS_COMPRESSION_LZ4] = {
+ .decompress = z_erofs_lz4_decompress,
+ .name = "lz4"
+ },
+#ifdef CONFIG_EROFS_FS_ZIP_LZMA
+ [Z_EROFS_COMPRESSION_LZMA] = {
+ .decompress = z_erofs_lzma_decompress,
+ .name = "lzma"
+ },
+#endif
+};
+
int z_erofs_decompress(struct z_erofs_decompress_req *rq,
- struct list_head *pagepool)
+ struct page **pagepool)
{
- if (rq->alg == Z_EROFS_COMPRESSION_SHIFTED)
- return z_erofs_shifted_transform(rq, pagepool);
- return z_erofs_decompress_generic(rq, pagepool);
+ return decompressors[rq->alg].decompress(rq, pagepool);
}
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
new file mode 100644
index 000000000000..50045510a1f4
--- /dev/null
+++ b/fs/erofs/decompressor_lzma.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/xz.h>
+#include <linux/module.h>
+#include "compress.h"
+
+struct z_erofs_lzma {
+ struct z_erofs_lzma *next;
+ struct xz_dec_microlzma *state;
+ struct xz_buf buf;
+ u8 bounce[PAGE_SIZE];
+};
+
+/* considering the LZMA performance, no need to use a lockless list for now */
+static DEFINE_SPINLOCK(z_erofs_lzma_lock);
+static unsigned int z_erofs_lzma_max_dictsize;
+static unsigned int z_erofs_lzma_nstrms, z_erofs_lzma_avail_strms;
+static struct z_erofs_lzma *z_erofs_lzma_head;
+static DECLARE_WAIT_QUEUE_HEAD(z_erofs_lzma_wq);
+
+module_param_named(lzma_streams, z_erofs_lzma_nstrms, uint, 0444);
+
+void z_erofs_lzma_exit(void)
+{
+ /* there should be no running fs instance */
+ while (z_erofs_lzma_avail_strms) {
+ struct z_erofs_lzma *strm;
+
+ spin_lock(&z_erofs_lzma_lock);
+ strm = z_erofs_lzma_head;
+ if (!strm) {
+ spin_unlock(&z_erofs_lzma_lock);
+ DBG_BUGON(1);
+ return;
+ }
+ z_erofs_lzma_head = NULL;
+ spin_unlock(&z_erofs_lzma_lock);
+
+ while (strm) {
+ struct z_erofs_lzma *n = strm->next;
+
+ if (strm->state)
+ xz_dec_microlzma_end(strm->state);
+ kfree(strm);
+ --z_erofs_lzma_avail_strms;
+ strm = n;
+ }
+ }
+}
+
+int z_erofs_lzma_init(void)
+{
+ unsigned int i;
+
+ /* by default, use # of possible CPUs instead */
+ if (!z_erofs_lzma_nstrms)
+ z_erofs_lzma_nstrms = num_possible_cpus();
+
+ for (i = 0; i < z_erofs_lzma_nstrms; ++i) {
+ struct z_erofs_lzma *strm = kzalloc(sizeof(*strm), GFP_KERNEL);
+
+ if (!strm) {
+ z_erofs_lzma_exit();
+ return -ENOMEM;
+ }
+ spin_lock(&z_erofs_lzma_lock);
+ strm->next = z_erofs_lzma_head;
+ z_erofs_lzma_head = strm;
+ spin_unlock(&z_erofs_lzma_lock);
+ ++z_erofs_lzma_avail_strms;
+ }
+ return 0;
+}
+
+int z_erofs_load_lzma_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lzma_cfgs *lzma, int size)
+{
+ static DEFINE_MUTEX(lzma_resize_mutex);
+ unsigned int dict_size, i;
+ struct z_erofs_lzma *strm, *head = NULL;
+ int err;
+
+ if (!lzma || size < sizeof(struct z_erofs_lzma_cfgs)) {
+ erofs_err(sb, "invalid lzma cfgs, size=%u", size);
+ return -EINVAL;
+ }
+ if (lzma->format) {
+ erofs_err(sb, "unidentified lzma format %x, please check kernel version",
+ le16_to_cpu(lzma->format));
+ return -EINVAL;
+ }
+ dict_size = le32_to_cpu(lzma->dict_size);
+ if (dict_size > Z_EROFS_LZMA_MAX_DICT_SIZE || dict_size < 4096) {
+ erofs_err(sb, "unsupported lzma dictionary size %u",
+ dict_size);
+ return -EINVAL;
+ }
+
+ erofs_info(sb, "EXPERIMENTAL MicroLZMA in use. Use at your own risk!");
+
+ /* in case 2 z_erofs_load_lzma_config() race to avoid deadlock */
+ mutex_lock(&lzma_resize_mutex);
+
+ if (z_erofs_lzma_max_dictsize >= dict_size) {
+ mutex_unlock(&lzma_resize_mutex);
+ return 0;
+ }
+
+ /* 1. collect/isolate all streams for the following check */
+ for (i = 0; i < z_erofs_lzma_avail_strms; ++i) {
+ struct z_erofs_lzma *last;
+
+again:
+ spin_lock(&z_erofs_lzma_lock);
+ strm = z_erofs_lzma_head;
+ if (!strm) {
+ spin_unlock(&z_erofs_lzma_lock);
+ wait_event(z_erofs_lzma_wq,
+ READ_ONCE(z_erofs_lzma_head));
+ goto again;
+ }
+ z_erofs_lzma_head = NULL;
+ spin_unlock(&z_erofs_lzma_lock);
+
+ for (last = strm; last->next; last = last->next)
+ ++i;
+ last->next = head;
+ head = strm;
+ }
+
+ err = 0;
+ /* 2. walk each isolated stream and grow max dict_size if needed */
+ for (strm = head; strm; strm = strm->next) {
+ if (strm->state)
+ xz_dec_microlzma_end(strm->state);
+ strm->state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size);
+ if (!strm->state)
+ err = -ENOMEM;
+ }
+
+ /* 3. push back all to the global list and update max dict_size */
+ spin_lock(&z_erofs_lzma_lock);
+ DBG_BUGON(z_erofs_lzma_head);
+ z_erofs_lzma_head = head;
+ spin_unlock(&z_erofs_lzma_lock);
+
+ z_erofs_lzma_max_dictsize = dict_size;
+ mutex_unlock(&lzma_resize_mutex);
+ return err;
+}
+
+int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
+ struct page **pagepool)
+{
+ const unsigned int nrpages_out =
+ PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
+ const unsigned int nrpages_in =
+ PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT;
+ unsigned int inputmargin, inlen, outlen, pageofs;
+ struct z_erofs_lzma *strm;
+ u8 *kin;
+ bool bounced = false;
+ int no, ni, j, err = 0;
+
+ /* 1. get the exact LZMA compressed size */
+ kin = kmap(*rq->in);
+ inputmargin = 0;
+ while (!kin[inputmargin & ~PAGE_MASK])
+ if (!(++inputmargin & ~PAGE_MASK))
+ break;
+
+ if (inputmargin >= PAGE_SIZE) {
+ kunmap(*rq->in);
+ return -EFSCORRUPTED;
+ }
+ rq->inputsize -= inputmargin;
+
+ /* 2. get an available lzma context */
+again:
+ spin_lock(&z_erofs_lzma_lock);
+ strm = z_erofs_lzma_head;
+ if (!strm) {
+ spin_unlock(&z_erofs_lzma_lock);
+ wait_event(z_erofs_lzma_wq, READ_ONCE(z_erofs_lzma_head));
+ goto again;
+ }
+ z_erofs_lzma_head = strm->next;
+ spin_unlock(&z_erofs_lzma_lock);
+
+ /* 3. multi-call decompress */
+ inlen = rq->inputsize;
+ outlen = rq->outputsize;
+ xz_dec_microlzma_reset(strm->state, inlen, outlen,
+ !rq->partial_decoding);
+ pageofs = rq->pageofs_out;
+ strm->buf.in = kin + inputmargin;
+ strm->buf.in_pos = 0;
+ strm->buf.in_size = min_t(u32, inlen, PAGE_SIZE - inputmargin);
+ inlen -= strm->buf.in_size;
+ strm->buf.out = NULL;
+ strm->buf.out_pos = 0;
+ strm->buf.out_size = 0;
+
+ for (ni = 0, no = -1;;) {
+ enum xz_ret xz_err;
+
+ if (strm->buf.out_pos == strm->buf.out_size) {
+ if (strm->buf.out) {
+ kunmap(rq->out[no]);
+ strm->buf.out = NULL;
+ }
+
+ if (++no >= nrpages_out || !outlen) {
+ erofs_err(rq->sb, "decompressed buf out of bound");
+ err = -EFSCORRUPTED;
+ break;
+ }
+ strm->buf.out_pos = 0;
+ strm->buf.out_size = min_t(u32, outlen,
+ PAGE_SIZE - pageofs);
+ outlen -= strm->buf.out_size;
+ if (rq->out[no])
+ strm->buf.out = kmap(rq->out[no]) + pageofs;
+ pageofs = 0;
+ } else if (strm->buf.in_pos == strm->buf.in_size) {
+ kunmap(rq->in[ni]);
+
+ if (++ni >= nrpages_in || !inlen) {
+ erofs_err(rq->sb, "compressed buf out of bound");
+ err = -EFSCORRUPTED;
+ break;
+ }
+ strm->buf.in_pos = 0;
+ strm->buf.in_size = min_t(u32, inlen, PAGE_SIZE);
+ inlen -= strm->buf.in_size;
+ kin = kmap(rq->in[ni]);
+ strm->buf.in = kin;
+ bounced = false;
+ }
+
+ /*
+ * Handle overlapping: Use bounced buffer if the compressed
+ * data is under processing; Otherwise, Use short-lived pages
+ * from the on-stack pagepool where pages share with the same
+ * request.
+ */
+ if (!bounced && rq->out[no] == rq->in[ni]) {
+ memcpy(strm->bounce, strm->buf.in, strm->buf.in_size);
+ strm->buf.in = strm->bounce;
+ bounced = true;
+ }
+ for (j = ni + 1; j < nrpages_in; ++j) {
+ struct page *tmppage;
+
+ if (rq->out[no] != rq->in[j])
+ continue;
+
+ DBG_BUGON(erofs_page_is_managed(EROFS_SB(rq->sb),
+ rq->in[j]));
+ tmppage = erofs_allocpage(pagepool,
+ GFP_KERNEL | __GFP_NOFAIL);
+ set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
+ copy_highpage(tmppage, rq->in[j]);
+ rq->in[j] = tmppage;
+ }
+ xz_err = xz_dec_microlzma_run(strm->state, &strm->buf);
+ DBG_BUGON(strm->buf.out_pos > strm->buf.out_size);
+ DBG_BUGON(strm->buf.in_pos > strm->buf.in_size);
+
+ if (xz_err != XZ_OK) {
+ if (xz_err == XZ_STREAM_END && !outlen)
+ break;
+ erofs_err(rq->sb, "failed to decompress %d in[%u] out[%u]",
+ xz_err, rq->inputsize, rq->outputsize);
+ err = -EFSCORRUPTED;
+ break;
+ }
+ }
+ if (no < nrpages_out && strm->buf.out)
+ kunmap(rq->in[no]);
+ if (ni < nrpages_in)
+ kunmap(rq->in[ni]);
+ /* 4. push back LZMA stream context to the global list */
+ spin_lock(&z_erofs_lzma_lock);
+ strm->next = z_erofs_lzma_head;
+ z_erofs_lzma_head = strm;
+ spin_unlock(&z_erofs_lzma_lock);
+ wake_up(&z_erofs_lzma_wq);
+ return err;
+}
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index b0b23f41abc3..083997a034e5 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -21,14 +21,29 @@
#define EROFS_FEATURE_INCOMPAT_COMPR_CFGS 0x00000002
#define EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER 0x00000002
#define EROFS_FEATURE_INCOMPAT_CHUNKED_FILE 0x00000004
+#define EROFS_FEATURE_INCOMPAT_DEVICE_TABLE 0x00000008
+#define EROFS_FEATURE_INCOMPAT_COMPR_HEAD2 0x00000008
#define EROFS_ALL_FEATURE_INCOMPAT \
(EROFS_FEATURE_INCOMPAT_LZ4_0PADDING | \
EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \
EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER | \
- EROFS_FEATURE_INCOMPAT_CHUNKED_FILE)
+ EROFS_FEATURE_INCOMPAT_CHUNKED_FILE | \
+ EROFS_FEATURE_INCOMPAT_DEVICE_TABLE | \
+ EROFS_FEATURE_INCOMPAT_COMPR_HEAD2)
#define EROFS_SB_EXTSLOT_SIZE 16
+struct erofs_deviceslot {
+ union {
+ u8 uuid[16]; /* used for device manager later */
+ u8 userdata[64]; /* digest(sha256), etc. */
+ } u;
+ __le32 blocks; /* total fs blocks of this device */
+ __le32 mapped_blkaddr; /* map starting at mapped_blkaddr */
+ u8 reserved[56];
+};
+#define EROFS_DEVT_SLOT_SIZE sizeof(struct erofs_deviceslot)
+
/* erofs on-disk super block (currently 128 bytes) */
struct erofs_super_block {
__le32 magic; /* file system magic number */
@@ -54,7 +69,9 @@ struct erofs_super_block {
/* customized sliding window size instead of 64k by default */
__le16 lz4_max_distance;
} __packed u1;
- __u8 reserved2[42];
+ __le16 extra_devices; /* # of devices besides the primary device */
+ __le16 devt_slotoff; /* startoff = devt_slotoff * devt_slotsize */
+ __u8 reserved2[38];
};
/*
@@ -238,7 +255,7 @@ static inline unsigned int erofs_xattr_entry_size(struct erofs_xattr_entry *e)
/* 8-byte inode chunk indexes */
struct erofs_inode_chunk_index {
__le16 advise; /* always 0, don't care for now */
- __le16 device_id; /* back-end storage id, always 0 for now */
+ __le16 device_id; /* back-end storage id (with bits masked) */
__le32 blkaddr; /* start block address of this inode chunk */
};
@@ -247,10 +264,11 @@ struct erofs_inode_chunk_index {
/* available compression algorithm types (for h_algorithmtype) */
enum {
- Z_EROFS_COMPRESSION_LZ4 = 0,
+ Z_EROFS_COMPRESSION_LZ4 = 0,
+ Z_EROFS_COMPRESSION_LZMA = 1,
Z_EROFS_COMPRESSION_MAX
};
-#define Z_EROFS_ALL_COMPR_ALGS (1 << (Z_EROFS_COMPRESSION_MAX - 1))
+#define Z_EROFS_ALL_COMPR_ALGS ((1 << Z_EROFS_COMPRESSION_MAX) - 1)
/* 14 bytes (+ length field = 16 bytes) */
struct z_erofs_lz4_cfgs {
@@ -259,6 +277,15 @@ struct z_erofs_lz4_cfgs {
u8 reserved[10];
} __packed;
+/* 14 bytes (+ length field = 16 bytes) */
+struct z_erofs_lzma_cfgs {
+ __le32 dict_size;
+ __le16 format;
+ u8 reserved[8];
+} __packed;
+
+#define Z_EROFS_LZMA_MAX_DICT_SIZE (8 * Z_EROFS_PCLUSTER_MAX_SIZE)
+
/*
* bit 0 : COMPACTED_2B indexes (0 - off; 1 - on)
* e.g. for 4k logical cluster size, 4B if compacted 2B is off;
@@ -288,35 +315,34 @@ struct z_erofs_map_header {
#define Z_EROFS_VLE_LEGACY_HEADER_PADDING 8
/*
- * Fixed-sized output compression ondisk Logical Extent cluster type:
- * 0 - literal (uncompressed) cluster
- * 1 - compressed cluster (for the head logical cluster)
- * 2 - compressed cluster (for the other logical clusters)
+ * Fixed-sized output compression on-disk logical cluster type:
+ * 0 - literal (uncompressed) lcluster
+ * 1,3 - compressed lcluster (for HEAD lclusters)
+ * 2 - compressed lcluster (for NONHEAD lclusters)
*
* In detail,
- * 0 - literal (uncompressed) cluster,
+ * 0 - literal (uncompressed) lcluster,
* di_advise = 0
- * di_clusterofs = the literal data offset of the cluster
- * di_blkaddr = the blkaddr of the literal cluster
+ * di_clusterofs = the literal data offset of the lcluster
+ * di_blkaddr = the blkaddr of the literal pcluster
*
- * 1 - compressed cluster (for the head logical cluster)
- * di_advise = 1
- * di_clusterofs = the decompressed data offset of the cluster
- * di_blkaddr = the blkaddr of the compressed cluster
+ * 1,3 - compressed lcluster (for HEAD lclusters)
+ * di_advise = 1 or 3
+ * di_clusterofs = the decompressed data offset of the lcluster
+ * di_blkaddr = the blkaddr of the compressed pcluster
*
- * 2 - compressed cluster (for the other logical clusters)
+ * 2 - compressed lcluster (for NONHEAD lclusters)
* di_advise = 2
* di_clusterofs =
- * the decompressed data offset in its own head cluster
- * di_u.delta[0] = distance to its corresponding head cluster
- * di_u.delta[1] = distance to its corresponding tail cluster
- * (di_advise could be 0, 1 or 2)
+ * the decompressed data offset in its own HEAD lcluster
+ * di_u.delta[0] = distance to this HEAD lcluster
+ * di_u.delta[1] = distance to the next HEAD lcluster
*/
enum {
Z_EROFS_VLE_CLUSTER_TYPE_PLAIN = 0,
- Z_EROFS_VLE_CLUSTER_TYPE_HEAD = 1,
+ Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 = 1,
Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD = 2,
- Z_EROFS_VLE_CLUSTER_TYPE_RESERVED = 3,
+ Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 = 3,
Z_EROFS_VLE_CLUSTER_TYPE_MAX
};
@@ -384,6 +410,7 @@ static inline void erofs_check_ondisk_layout_definitions(void)
/* keep in sync between 2 index structures for better extendibility */
BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) !=
sizeof(struct z_erofs_vle_decompressed_index));
+ BUILD_BUG_ON(sizeof(struct erofs_deviceslot) != 128);
BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) <
Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1);
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index a552399e211d..2345f1de438e 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -192,7 +192,7 @@ static struct page *erofs_read_inode(struct inode *inode,
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;
inode->i_flags &= ~S_DAX;
- if (test_opt(&sbi->ctx, DAX_ALWAYS) && S_ISREG(inode->i_mode) &&
+ if (test_opt(&sbi->opt, DAX_ALWAYS) && S_ISREG(inode->i_mode) &&
vi->datalayout == EROFS_INODE_FLAT_PLAIN)
inode->i_flags |= S_DAX;
if (!nblks)
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 9524e155b38f..3265688af7f9 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -47,7 +47,16 @@ typedef u64 erofs_off_t;
/* data type for filesystem-wide blocks number */
typedef u32 erofs_blk_t;
-struct erofs_fs_context {
+struct erofs_device_info {
+ char *path;
+ struct block_device *bdev;
+ struct dax_device *dax_dev;
+
+ u32 blocks;
+ u32 mapped_blkaddr;
+};
+
+struct erofs_mount_opts {
#ifdef CONFIG_EROFS_FS_ZIP
/* current strategy of how to use managed cache */
unsigned char cache_strategy;
@@ -60,6 +69,18 @@ struct erofs_fs_context {
unsigned int mount_opt;
};
+struct erofs_dev_context {
+ struct idr tree;
+ struct rw_semaphore rwsem;
+
+ unsigned int extra_devices;
+};
+
+struct erofs_fs_context {
+ struct erofs_mount_opts opt;
+ struct erofs_dev_context *devs;
+};
+
/* all filesystem-wide lz4 configurations */
struct erofs_sb_lz4_info {
/* # of pages needed for EROFS lz4 rolling decompression */
@@ -69,6 +90,7 @@ struct erofs_sb_lz4_info {
};
struct erofs_sb_info {
+ struct erofs_mount_opts opt; /* options */
#ifdef CONFIG_EROFS_FS_ZIP
/* list for all registered superblocks, mainly for shrinker */
struct list_head list;
@@ -85,12 +107,16 @@ struct erofs_sb_info {
struct erofs_sb_lz4_info lz4;
#endif /* CONFIG_EROFS_FS_ZIP */
+ struct erofs_dev_context *devs;
struct dax_device *dax_dev;
- u32 blocks;
+ u64 total_blocks;
+ u32 primarydevice_blocks;
+
u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
u32 xattr_blkaddr;
#endif
+ u16 device_id_mask; /* valid bits of device id to be used */
/* inode slot unit size in bit shift */
unsigned char islotbits;
@@ -108,8 +134,6 @@ struct erofs_sb_info {
u8 volume_name[16]; /* volume name */
u32 feature_compat;
u32 feature_incompat;
-
- struct erofs_fs_context ctx; /* options */
};
#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
@@ -121,9 +145,9 @@ struct erofs_sb_info {
#define EROFS_MOUNT_DAX_ALWAYS 0x00000040
#define EROFS_MOUNT_DAX_NEVER 0x00000080
-#define clear_opt(ctx, option) ((ctx)->mount_opt &= ~EROFS_MOUNT_##option)
-#define set_opt(ctx, option) ((ctx)->mount_opt |= EROFS_MOUNT_##option)
-#define test_opt(ctx, option) ((ctx)->mount_opt & EROFS_MOUNT_##option)
+#define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option)
+#define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option)
+#define test_opt(opt, option) ((opt)->mount_opt & EROFS_MOUNT_##option)
enum {
EROFS_ZIP_CACHE_DISABLED,
@@ -237,6 +261,7 @@ static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
EROFS_FEATURE_FUNCS(lz4_0padding, incompat, INCOMPAT_LZ4_0PADDING)
EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS)
EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
+EROFS_FEATURE_FUNCS(device_table, incompat, INCOMPAT_DEVICE_TABLE)
EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
/* atomic flag definitions */
@@ -307,6 +332,19 @@ static inline unsigned int erofs_inode_datalayout(unsigned int value)
EROFS_I_DATALAYOUT_BITS);
}
+/*
+ * Different from grab_cache_page_nowait(), reclaiming is never triggered
+ * when allocating new pages.
+ */
+static inline
+struct page *erofs_grab_cache_page_nowait(struct address_space *mapping,
+ pgoff_t index)
+{
+ return pagecache_get_page(mapping, index,
+ FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
+ readahead_gfp_mask(mapping) & ~__GFP_RECLAIM);
+}
+
extern const struct super_operations erofs_sops;
extern const struct address_space_operations erofs_raw_access_aops;
@@ -338,7 +376,7 @@ extern const struct address_space_operations z_erofs_aops;
* of the corresponding uncompressed data in the file.
*/
enum {
- BH_Zipped = BH_PrivateStart,
+ BH_Encoded = BH_PrivateStart,
BH_FullMapped,
};
@@ -346,8 +384,8 @@ enum {
#define EROFS_MAP_MAPPED (1 << BH_Mapped)
/* Located in metadata (could be copied from bd_inode) */
#define EROFS_MAP_META (1 << BH_Meta)
-/* The extent has been compressed */
-#define EROFS_MAP_ZIPPED (1 << BH_Zipped)
+/* The extent is encoded */
+#define EROFS_MAP_ENCODED (1 << BH_Encoded)
/* The length of extent is full */
#define EROFS_MAP_FULL_MAPPED (1 << BH_FullMapped)
@@ -355,6 +393,8 @@ struct erofs_map_blocks {
erofs_off_t m_pa, m_la;
u64 m_plen, m_llen;
+ unsigned short m_deviceid;
+ char m_algorithmformat;
unsigned int m_flags;
struct page *mpage;
@@ -367,6 +407,13 @@ struct erofs_map_blocks {
* approach instead if possible since it's more metadata lightweight.)
*/
#define EROFS_GET_BLOCKS_FIEMAP 0x0002
+/* Used to map the whole extent if non-negligible data is requested for LZMA */
+#define EROFS_GET_BLOCKS_READMORE 0x0004
+
+enum {
+ Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
+ Z_EROFS_COMPRESSION_RUNTIME_MAX
+};
/* zmap.c */
extern const struct iomap_ops z_erofs_iomap_report_ops;
@@ -386,9 +433,18 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
}
#endif /* !CONFIG_EROFS_FS_ZIP */
+struct erofs_map_dev {
+ struct block_device *m_bdev;
+ struct dax_device *m_daxdev;
+
+ erofs_off_t m_pa;
+ unsigned int m_deviceid;
+};
+
/* data.c */
extern const struct file_operations erofs_file_fops;
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr);
+int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev);
int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
@@ -443,7 +499,14 @@ void erofs_pcpubuf_init(void);
void erofs_pcpubuf_exit(void);
/* utils.c / zdata.c */
-struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);
+struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp);
+static inline void erofs_pagepool_add(struct page **pagepool,
+ struct page *page)
+{
+ set_page_private(page, (unsigned long)*pagepool);
+ *pagepool = page;
+}
+void erofs_release_pages(struct page **pagepool);
#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
@@ -483,6 +546,26 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb,
}
#endif /* !CONFIG_EROFS_FS_ZIP */
+#ifdef CONFIG_EROFS_FS_ZIP_LZMA
+int z_erofs_lzma_init(void);
+void z_erofs_lzma_exit(void);
+int z_erofs_load_lzma_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lzma_cfgs *lzma, int size);
+#else
+static inline int z_erofs_lzma_init(void) { return 0; }
+static inline int z_erofs_lzma_exit(void) { return 0; }
+static inline int z_erofs_load_lzma_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lzma_cfgs *lzma, int size) {
+ if (lzma) {
+ erofs_err(sb, "lzma algorithm isn't enabled");
+ return -EINVAL;
+ }
+ return 0;
+}
+#endif /* !CONFIG_EROFS_FS_ZIP */
+
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
#endif /* __EROFS_INTERNAL_H */
diff --git a/fs/erofs/pcpubuf.c b/fs/erofs/pcpubuf.c
index 6c885575128a..a2efd833d1b6 100644
--- a/fs/erofs/pcpubuf.c
+++ b/fs/erofs/pcpubuf.c
@@ -49,7 +49,7 @@ int erofs_pcpubuf_growsize(unsigned int nrpages)
{
static DEFINE_MUTEX(pcb_resize_mutex);
static unsigned int pcb_nrpages;
- LIST_HEAD(pagepool);
+ struct page *pagepool = NULL;
int delta, cpu, ret, i;
mutex_lock(&pcb_resize_mutex);
@@ -102,13 +102,13 @@ int erofs_pcpubuf_growsize(unsigned int nrpages)
vunmap(old_ptr);
free_pagearray:
while (i)
- list_add(&oldpages[--i]->lru, &pagepool);
+ erofs_pagepool_add(&pagepool, oldpages[--i]);
kfree(oldpages);
if (ret)
break;
}
pcb_nrpages = nrpages;
- put_pages_list(&pagepool);
+ erofs_release_pages(&pagepool);
out:
mutex_unlock(&pcb_resize_mutex);
return ret;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 11b88559f8bf..6a969b1e0ee6 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -225,6 +225,9 @@ static int erofs_load_compr_cfgs(struct super_block *sb,
case Z_EROFS_COMPRESSION_LZ4:
ret = z_erofs_load_lz4_config(sb, dsb, data, size);
break;
+ case Z_EROFS_COMPRESSION_LZMA:
+ ret = z_erofs_load_lzma_config(sb, dsb, data, size);
+ break;
default:
DBG_BUGON(1);
ret = -EFAULT;
@@ -252,6 +255,79 @@ static int erofs_load_compr_cfgs(struct super_block *sb,
}
#endif
+static int erofs_init_devices(struct super_block *sb,
+ struct erofs_super_block *dsb)
+{
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+ unsigned int ondisk_extradevs;
+ erofs_off_t pos;
+ struct page *page = NULL;
+ struct erofs_device_info *dif;
+ struct erofs_deviceslot *dis;
+ void *ptr;
+ int id, err = 0;
+
+ sbi->total_blocks = sbi->primarydevice_blocks;
+ if (!erofs_sb_has_device_table(sbi))
+ ondisk_extradevs = 0;
+ else
+ ondisk_extradevs = le16_to_cpu(dsb->extra_devices);
+
+ if (ondisk_extradevs != sbi->devs->extra_devices) {
+ erofs_err(sb, "extra devices don't match (ondisk %u, given %u)",
+ ondisk_extradevs, sbi->devs->extra_devices);
+ return -EINVAL;
+ }
+ if (!ondisk_extradevs)
+ return 0;
+
+ sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1;
+ pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE;
+ down_read(&sbi->devs->rwsem);
+ idr_for_each_entry(&sbi->devs->tree, dif, id) {
+ erofs_blk_t blk = erofs_blknr(pos);
+ struct block_device *bdev;
+
+ if (!page || page->index != blk) {
+ if (page) {
+ kunmap(page);
+ unlock_page(page);
+ put_page(page);
+ }
+
+ page = erofs_get_meta_page(sb, blk);
+ if (IS_ERR(page)) {
+ up_read(&sbi->devs->rwsem);
+ return PTR_ERR(page);
+ }
+ ptr = kmap(page);
+ }
+ dis = ptr + erofs_blkoff(pos);
+
+ bdev = blkdev_get_by_path(dif->path,
+ FMODE_READ | FMODE_EXCL,
+ sb->s_type);
+ if (IS_ERR(bdev)) {
+ err = PTR_ERR(bdev);
+ goto err_out;
+ }
+ dif->bdev = bdev;
+ dif->dax_dev = fs_dax_get_by_bdev(bdev);
+ dif->blocks = le32_to_cpu(dis->blocks);
+ dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
+ sbi->total_blocks += dif->blocks;
+ pos += EROFS_DEVT_SLOT_SIZE;
+ }
+err_out:
+ up_read(&sbi->devs->rwsem);
+ if (page) {
+ kunmap(page);
+ unlock_page(page);
+ put_page(page);
+ }
+ return err;
+}
+
static int erofs_read_superblock(struct super_block *sb)
{
struct erofs_sb_info *sbi;
@@ -303,7 +379,7 @@ static int erofs_read_superblock(struct super_block *sb)
sbi->sb_size);
goto out;
}
- sbi->blocks = le32_to_cpu(dsb->blocks);
+ sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks);
sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
@@ -330,6 +406,11 @@ static int erofs_read_superblock(struct super_block *sb)
ret = erofs_load_compr_cfgs(sb, dsb);
else
ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0);
+ if (ret < 0)
+ goto out;
+
+ /* handle multiple devices */
+ ret = erofs_init_devices(sb, dsb);
out:
kunmap(page);
put_page(page);
@@ -340,15 +421,15 @@ out:
static void erofs_default_options(struct erofs_fs_context *ctx)
{
#ifdef CONFIG_EROFS_FS_ZIP
- ctx->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
- ctx->max_sync_decompress_pages = 3;
- ctx->readahead_sync_decompress = false;
+ ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND;
+ ctx->opt.max_sync_decompress_pages = 3;
+ ctx->opt.readahead_sync_decompress = false;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
- set_opt(ctx, XATTR_USER);
+ set_opt(&ctx->opt, XATTR_USER);
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
- set_opt(ctx, POSIX_ACL);
+ set_opt(&ctx->opt, POSIX_ACL);
#endif
}
@@ -358,6 +439,7 @@ enum {
Opt_cache_strategy,
Opt_dax,
Opt_dax_enum,
+ Opt_device,
Opt_err
};
@@ -381,6 +463,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
erofs_param_cache_strategy),
fsparam_flag("dax", Opt_dax),
fsparam_enum("dax", Opt_dax_enum, erofs_dax_param_enums),
+ fsparam_string("device", Opt_device),
{}
};
@@ -392,12 +475,12 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
switch (mode) {
case EROFS_MOUNT_DAX_ALWAYS:
warnfc(fc, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
- set_opt(ctx, DAX_ALWAYS);
- clear_opt(ctx, DAX_NEVER);
+ set_opt(&ctx->opt, DAX_ALWAYS);
+ clear_opt(&ctx->opt, DAX_NEVER);
return true;
case EROFS_MOUNT_DAX_NEVER:
- set_opt(ctx, DAX_NEVER);
- clear_opt(ctx, DAX_ALWAYS);
+ set_opt(&ctx->opt, DAX_NEVER);
+ clear_opt(&ctx->opt, DAX_ALWAYS);
return true;
default:
DBG_BUGON(1);
@@ -412,9 +495,10 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
static int erofs_fc_parse_param(struct fs_context *fc,
struct fs_parameter *param)
{
- struct erofs_fs_context *ctx __maybe_unused = fc->fs_private;
+ struct erofs_fs_context *ctx = fc->fs_private;
struct fs_parse_result result;
- int opt;
+ struct erofs_device_info *dif;
+ int opt, ret;
opt = fs_parse(fc, erofs_fs_parameters, param, &result);
if (opt < 0)
@@ -424,9 +508,9 @@ static int erofs_fc_parse_param(struct fs_context *fc,
case Opt_user_xattr:
#ifdef CONFIG_EROFS_FS_XATTR
if (result.boolean)
- set_opt(ctx, XATTR_USER);
+ set_opt(&ctx->opt, XATTR_USER);
else
- clear_opt(ctx, XATTR_USER);
+ clear_opt(&ctx->opt, XATTR_USER);
#else
errorfc(fc, "{,no}user_xattr options not supported");
#endif
@@ -434,16 +518,16 @@ static int erofs_fc_parse_param(struct fs_context *fc,
case Opt_acl:
#ifdef CONFIG_EROFS_FS_POSIX_ACL
if (result.boolean)
- set_opt(ctx, POSIX_ACL);
+ set_opt(&ctx->opt, POSIX_ACL);
else
- clear_opt(ctx, POSIX_ACL);
+ clear_opt(&ctx->opt, POSIX_ACL);
#else
errorfc(fc, "{,no}acl options not supported");
#endif
break;
case Opt_cache_strategy:
#ifdef CONFIG_EROFS_FS_ZIP
- ctx->cache_strategy = result.uint_32;
+ ctx->opt.cache_strategy = result.uint_32;
#else
errorfc(fc, "compression not supported, cache_strategy ignored");
#endif
@@ -456,6 +540,25 @@ static int erofs_fc_parse_param(struct fs_context *fc,
if (!erofs_fc_set_dax_mode(fc, result.uint_32))
return -EINVAL;
break;
+ case Opt_device:
+ dif = kzalloc(sizeof(*dif), GFP_KERNEL);
+ if (!dif)
+ return -ENOMEM;
+ dif->path = kstrdup(param->string, GFP_KERNEL);
+ if (!dif->path) {
+ kfree(dif);
+ return -ENOMEM;
+ }
+ down_write(&ctx->devs->rwsem);
+ ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL);
+ up_write(&ctx->devs->rwsem);
+ if (ret < 0) {
+ kfree(dif->path);
+ kfree(dif);
+ return ret;
+ }
+ ++ctx->devs->extra_devices;
+ break;
default:
return -ENOPARAM;
}
@@ -540,15 +643,19 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
return -ENOMEM;
sb->s_fs_info = sbi;
+ sbi->opt = ctx->opt;
sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
+ sbi->devs = ctx->devs;
+ ctx->devs = NULL;
+
err = erofs_read_superblock(sb);
if (err)
return err;
- if (test_opt(ctx, DAX_ALWAYS) &&
+ if (test_opt(&sbi->opt, DAX_ALWAYS) &&
!dax_supported(sbi->dax_dev, sb->s_bdev, EROFS_BLKSIZ, 0, bdev_nr_sectors(sb->s_bdev))) {
errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
- clear_opt(ctx, DAX_ALWAYS);
+ clear_opt(&sbi->opt, DAX_ALWAYS);
}
sb->s_flags |= SB_RDONLY | SB_NOATIME;
sb->s_maxbytes = MAX_LFS_FILESIZE;
@@ -557,13 +664,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
sb->s_op = &erofs_sops;
sb->s_xattr = erofs_xattr_handlers;
- if (test_opt(ctx, POSIX_ACL))
+ if (test_opt(&sbi->opt, POSIX_ACL))
sb->s_flags |= SB_POSIXACL;
else
sb->s_flags &= ~SB_POSIXACL;
- sbi->ctx = *ctx;
-
#ifdef CONFIG_EROFS_FS_ZIP
xa_init(&sbi->managed_pslots);
#endif
@@ -607,20 +712,44 @@ static int erofs_fc_reconfigure(struct fs_context *fc)
DBG_BUGON(!sb_rdonly(sb));
- if (test_opt(ctx, POSIX_ACL))
+ if (test_opt(&ctx->opt, POSIX_ACL))
fc->sb_flags |= SB_POSIXACL;
else
fc->sb_flags &= ~SB_POSIXACL;
- sbi->ctx = *ctx;
+ sbi->opt = ctx->opt;
fc->sb_flags |= SB_RDONLY;
return 0;
}
+static int erofs_release_device_info(int id, void *ptr, void *data)
+{
+ struct erofs_device_info *dif = ptr;
+
+ fs_put_dax(dif->dax_dev);
+ if (dif->bdev)
+ blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL);
+ kfree(dif->path);
+ kfree(dif);
+ return 0;
+}
+
+static void erofs_free_dev_context(struct erofs_dev_context *devs)
+{
+ if (!devs)
+ return;
+ idr_for_each(&devs->tree, &erofs_release_device_info, NULL);
+ idr_destroy(&devs->tree);
+ kfree(devs);
+}
+
static void erofs_fc_free(struct fs_context *fc)
{
- kfree(fc->fs_private);
+ struct erofs_fs_context *ctx = fc->fs_private;
+
+ erofs_free_dev_context(ctx->devs);
+ kfree(ctx);
}
static const struct fs_context_operations erofs_context_ops = {
@@ -632,15 +761,21 @@ static const struct fs_context_operations erofs_context_ops = {
static int erofs_init_fs_context(struct fs_context *fc)
{
- fc->fs_private = kzalloc(sizeof(struct erofs_fs_context), GFP_KERNEL);
- if (!fc->fs_private)
- return -ENOMEM;
+ struct erofs_fs_context *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
- /* set default mount options */
- erofs_default_options(fc->fs_private);
+ if (!ctx)
+ return -ENOMEM;
+ ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
+ if (!ctx->devs) {
+ kfree(ctx);
+ return -ENOMEM;
+ }
+ fc->fs_private = ctx;
+ idr_init(&ctx->devs->tree);
+ init_rwsem(&ctx->devs->rwsem);
+ erofs_default_options(ctx);
fc->ops = &erofs_context_ops;
-
return 0;
}
@@ -659,6 +794,8 @@ static void erofs_kill_sb(struct super_block *sb)
sbi = EROFS_SB(sb);
if (!sbi)
return;
+
+ erofs_free_dev_context(sbi->devs);
fs_put_dax(sbi->dax_dev);
kfree(sbi);
sb->s_fs_info = NULL;
@@ -706,6 +843,10 @@ static int __init erofs_module_init(void)
if (err)
goto shrinker_err;
+ err = z_erofs_lzma_init();
+ if (err)
+ goto lzma_err;
+
erofs_pcpubuf_init();
err = z_erofs_init_zip_subsystem();
if (err)
@@ -720,6 +861,8 @@ static int __init erofs_module_init(void)
fs_err:
z_erofs_exit_zip_subsystem();
zip_err:
+ z_erofs_lzma_exit();
+lzma_err:
erofs_exit_shrinker();
shrinker_err:
kmem_cache_destroy(erofs_inode_cachep);
@@ -730,11 +873,13 @@ icache_err:
static void __exit erofs_module_exit(void)
{
unregister_filesystem(&erofs_fs_type);
- z_erofs_exit_zip_subsystem();
- erofs_exit_shrinker();
- /* Ensure all RCU free inodes are safe before cache is destroyed. */
+ /* Ensure all RCU free inodes / pclusters are safe to be destroyed. */
rcu_barrier();
+
+ z_erofs_exit_zip_subsystem();
+ z_erofs_lzma_exit();
+ erofs_exit_shrinker();
kmem_cache_destroy(erofs_inode_cachep);
erofs_pcpubuf_exit();
}
@@ -748,7 +893,7 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_type = sb->s_magic;
buf->f_bsize = EROFS_BLKSIZ;
- buf->f_blocks = sbi->blocks;
+ buf->f_blocks = sbi->total_blocks;
buf->f_bfree = buf->f_bavail = 0;
buf->f_files = ULLONG_MAX;
@@ -763,31 +908,31 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
static int erofs_show_options(struct seq_file *seq, struct dentry *root)
{
struct erofs_sb_info *sbi = EROFS_SB(root->d_sb);
- struct erofs_fs_context *ctx = &sbi->ctx;
+ struct erofs_mount_opts *opt = &sbi->opt;
#ifdef CONFIG_EROFS_FS_XATTR
- if (test_opt(ctx, XATTR_USER))
+ if (test_opt(opt, XATTR_USER))
seq_puts(seq, ",user_xattr");
else
seq_puts(seq, ",nouser_xattr");
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
- if (test_opt(ctx, POSIX_ACL))
+ if (test_opt(opt, POSIX_ACL))
seq_puts(seq, ",acl");
else
seq_puts(seq, ",noacl");
#endif
#ifdef CONFIG_EROFS_FS_ZIP
- if (ctx->cache_strategy == EROFS_ZIP_CACHE_DISABLED)
+ if (opt->cache_strategy == EROFS_ZIP_CACHE_DISABLED)
seq_puts(seq, ",cache_strategy=disabled");
- else if (ctx->cache_strategy == EROFS_ZIP_CACHE_READAHEAD)
+ else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAHEAD)
seq_puts(seq, ",cache_strategy=readahead");
- else if (ctx->cache_strategy == EROFS_ZIP_CACHE_READAROUND)
+ else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAROUND)
seq_puts(seq, ",cache_strategy=readaround");
#endif
- if (test_opt(ctx, DAX_ALWAYS))
+ if (test_opt(opt, DAX_ALWAYS))
seq_puts(seq, ",dax=always");
- if (test_opt(ctx, DAX_NEVER))
+ if (test_opt(opt, DAX_NEVER))
seq_puts(seq, ",dax=never");
return 0;
}
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index bd86067a63f7..84da2c280012 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -6,20 +6,29 @@
#include "internal.h"
#include <linux/pagevec.h>
-struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp)
+struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp)
{
- struct page *page;
+ struct page *page = *pagepool;
- if (!list_empty(pool)) {
- page = lru_to_page(pool);
+ if (page) {
DBG_BUGON(page_ref_count(page) != 1);
- list_del(&page->lru);
+ *pagepool = (struct page *)page_private(page);
} else {
page = alloc_page(gfp);
}
return page;
}
+void erofs_release_pages(struct page **pagepool)
+{
+ while (*pagepool) {
+ struct page *page = *pagepool;
+
+ *pagepool = (struct page *)page_private(page);
+ put_page(page);
+ }
+}
+
#ifdef CONFIG_EROFS_FS_ZIP
/* global shrink count (for all mounted EROFS instances) */
static atomic_long_t erofs_global_shrink_cnt;
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 778f2c52295d..01c581e93c5f 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -429,7 +429,7 @@ static int shared_getxattr(struct inode *inode, struct getxattr_iter *it)
static bool erofs_xattr_user_list(struct dentry *dentry)
{
- return test_opt(&EROFS_SB(dentry->d_sb)->ctx, XATTR_USER);
+ return test_opt(&EROFS_SB(dentry->d_sb)->opt, XATTR_USER);
}
static bool erofs_xattr_trusted_list(struct dentry *dentry)
@@ -476,7 +476,7 @@ static int erofs_xattr_generic_get(const struct xattr_handler *handler,
switch (handler->flags) {
case EROFS_XATTR_INDEX_USER:
- if (!test_opt(&sbi->ctx, XATTR_USER))
+ if (!test_opt(&sbi->opt, XATTR_USER))
return -EOPNOTSUPP;
break;
case EROFS_XATTR_INDEX_TRUSTED:
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 11c7a1aaebad..bcb1b91b234f 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -236,7 +236,7 @@ static DEFINE_MUTEX(z_pagemap_global_lock);
static void preload_compressed_pages(struct z_erofs_collector *clt,
struct address_space *mc,
enum z_erofs_cache_alloctype type,
- struct list_head *pagepool)
+ struct page **pagepool)
{
struct z_erofs_pcluster *pcl = clt->pcl;
bool standalone = true;
@@ -287,12 +287,10 @@ static void preload_compressed_pages(struct z_erofs_collector *clt,
if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t)))
continue;
- if (page) {
+ if (page)
put_page(page);
- } else if (newpage) {
- set_page_private(newpage, 0);
- list_add(&newpage->lru, pagepool);
- }
+ else if (newpage)
+ erofs_pagepool_add(pagepool, newpage);
}
/*
@@ -476,6 +474,11 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
struct erofs_workgroup *grp;
int err;
+ if (!(map->m_flags & EROFS_MAP_ENCODED)) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+
/* no available pcluster, let's allocate one */
pcl = z_erofs_alloc_pcluster(map->m_plen >> PAGE_SHIFT);
if (IS_ERR(pcl))
@@ -483,16 +486,11 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
atomic_set(&pcl->obj.refcount, 1);
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
-
+ pcl->algorithmformat = map->m_algorithmformat;
pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) |
(map->m_flags & EROFS_MAP_FULL_MAPPED ?
Z_EROFS_PCLUSTER_FULL_LENGTH : 0);
- if (map->m_flags & EROFS_MAP_ZIPPED)
- pcl->algorithmformat = Z_EROFS_COMPRESSION_LZ4;
- else
- pcl->algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
-
/* new pclusters should be claimed as type 1, primary and followed */
pcl->next = clt->owned_head;
clt->mode = COLLECT_PRIMARY_FOLLOWED;
@@ -643,7 +641,7 @@ static bool should_alloc_managed_pages(struct z_erofs_decompress_frontend *fe,
}
static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
- struct page *page, struct list_head *pagepool)
+ struct page *page, struct page **pagepool)
{
struct inode *const inode = fe->inode;
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
@@ -695,7 +693,7 @@ restart_now:
goto err_out;
/* preload all compressed pages (maybe downgrade role if necessary) */
- if (should_alloc_managed_pages(fe, sbi->ctx.cache_strategy, map->m_la))
+ if (should_alloc_managed_pages(fe, sbi->opt.cache_strategy, map->m_la))
cache_strategy = TRYALLOC;
else
cache_strategy = DONTALLOC;
@@ -796,7 +794,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
/* Use workqueue and sync decompression for atomic contexts only */
if (in_atomic() || irqs_disabled()) {
queue_work(z_erofs_workqueue, &io->u.work);
- sbi->ctx.readahead_sync_decompress = true;
+ sbi->opt.readahead_sync_decompress = true;
return;
}
z_erofs_decompressqueue_work(&io->u.work);
@@ -836,7 +834,7 @@ static void z_erofs_decompressqueue_endio(struct bio *bio)
static int z_erofs_decompress_pcluster(struct super_block *sb,
struct z_erofs_pcluster *pcl,
- struct list_head *pagepool)
+ struct page **pagepool)
{
struct erofs_sb_info *const sbi = EROFS_SB(sb);
struct z_erofs_pagevec_ctor ctor;
@@ -1036,7 +1034,7 @@ out:
}
static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
- struct list_head *pagepool)
+ struct page **pagepool)
{
z_erofs_next_pcluster_t owned = io->head;
@@ -1060,18 +1058,18 @@ static void z_erofs_decompressqueue_work(struct work_struct *work)
{
struct z_erofs_decompressqueue *bgq =
container_of(work, struct z_erofs_decompressqueue, u.work);
- LIST_HEAD(pagepool);
+ struct page *pagepool = NULL;
DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
z_erofs_decompress_queue(bgq, &pagepool);
- put_pages_list(&pagepool);
+ erofs_release_pages(&pagepool);
kvfree(bgq);
}
static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
unsigned int nr,
- struct list_head *pagepool,
+ struct page **pagepool,
struct address_space *mc,
gfp_t gfp)
{
@@ -1173,7 +1171,7 @@ repeat:
out_allocpage:
page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) {
- list_add(&page->lru, pagepool);
+ erofs_pagepool_add(pagepool, page);
cond_resched();
goto repeat;
}
@@ -1257,7 +1255,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
static void z_erofs_submit_queue(struct super_block *sb,
struct z_erofs_decompress_frontend *f,
- struct list_head *pagepool,
+ struct page **pagepool,
struct z_erofs_decompressqueue *fgq,
bool *force_fg)
{
@@ -1266,8 +1264,9 @@ static void z_erofs_submit_queue(struct super_block *sb,
struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
void *bi_private;
z_erofs_next_pcluster_t owned_head = f->clt.owned_head;
- /* since bio will be NULL, no need to initialize last_index */
+ /* bio is NULL initially, so no need to initialize last_{index,bdev} */
pgoff_t last_index;
+ struct block_device *last_bdev;
unsigned int nr_bios = 0;
struct bio *bio = NULL;
@@ -1279,6 +1278,7 @@ static void z_erofs_submit_queue(struct super_block *sb,
q[JQ_SUBMIT]->head = owned_head;
do {
+ struct erofs_map_dev mdev;
struct z_erofs_pcluster *pcl;
pgoff_t cur, end;
unsigned int i = 0;
@@ -1290,7 +1290,13 @@ static void z_erofs_submit_queue(struct super_block *sb,
pcl = container_of(owned_head, struct z_erofs_pcluster, next);
- cur = pcl->obj.index;
+ /* no device id here, thus it will always succeed */
+ mdev = (struct erofs_map_dev) {
+ .m_pa = blknr_to_addr(pcl->obj.index),
+ };
+ (void)erofs_map_dev(sb, &mdev);
+
+ cur = erofs_blknr(mdev.m_pa);
end = cur + pcl->pclusterpages;
/* close the main owned chain at first */
@@ -1306,7 +1312,8 @@ static void z_erofs_submit_queue(struct super_block *sb,
if (!page)
continue;
- if (bio && cur != last_index + 1) {
+ if (bio && (cur != last_index + 1 ||
+ last_bdev != mdev.m_bdev)) {
submit_bio_retry:
submit_bio(bio);
bio = NULL;
@@ -1314,9 +1321,10 @@ submit_bio_retry:
if (!bio) {
bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
-
bio->bi_end_io = z_erofs_decompressqueue_endio;
- bio_set_dev(bio, sb->s_bdev);
+
+ bio_set_dev(bio, mdev.m_bdev);
+ last_bdev = mdev.m_bdev;
bio->bi_iter.bi_sector = (sector_t)cur <<
LOG_SECTORS_PER_BLOCK;
bio->bi_private = bi_private;
@@ -1355,7 +1363,7 @@ submit_bio_retry:
static void z_erofs_runqueue(struct super_block *sb,
struct z_erofs_decompress_frontend *f,
- struct list_head *pagepool, bool force_fg)
+ struct page **pagepool, bool force_fg)
{
struct z_erofs_decompressqueue io[NR_JOBQUEUES];
@@ -1377,18 +1385,87 @@ static void z_erofs_runqueue(struct super_block *sb,
z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool);
}
+/*
+ * Since partial uptodate is still unimplemented for now, we have to use
+ * approximate readmore strategies as a start.
+ */
+static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
+ struct readahead_control *rac,
+ erofs_off_t end,
+ struct page **pagepool,
+ bool backmost)
+{
+ struct inode *inode = f->inode;
+ struct erofs_map_blocks *map = &f->map;
+ erofs_off_t cur;
+ int err;
+
+ if (backmost) {
+ map->m_la = end;
+ err = z_erofs_map_blocks_iter(inode, map,
+ EROFS_GET_BLOCKS_READMORE);
+ if (err)
+ return;
+
+ /* expend ra for the trailing edge if readahead */
+ if (rac) {
+ loff_t newstart = readahead_pos(rac);
+
+ cur = round_up(map->m_la + map->m_llen, PAGE_SIZE);
+ readahead_expand(rac, newstart, cur - newstart);
+ return;
+ }
+ end = round_up(end, PAGE_SIZE);
+ } else {
+ end = round_up(map->m_la, PAGE_SIZE);
+
+ if (!map->m_llen)
+ return;
+ }
+
+ cur = map->m_la + map->m_llen - 1;
+ while (cur >= end) {
+ pgoff_t index = cur >> PAGE_SHIFT;
+ struct page *page;
+
+ page = erofs_grab_cache_page_nowait(inode->i_mapping, index);
+ if (!page)
+ goto skip;
+
+ if (PageUptodate(page)) {
+ unlock_page(page);
+ put_page(page);
+ goto skip;
+ }
+
+ err = z_erofs_do_read_page(f, page, pagepool);
+ if (err)
+ erofs_err(inode->i_sb,
+ "readmore error at page %lu @ nid %llu",
+ index, EROFS_I(inode)->nid);
+ put_page(page);
+skip:
+ if (cur < PAGE_SIZE)
+ break;
+ cur = (index << PAGE_SHIFT) - 1;
+ }
+}
+
static int z_erofs_readpage(struct file *file, struct page *page)
{
struct inode *const inode = page->mapping->host;
struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
+ struct page *pagepool = NULL;
int err;
- LIST_HEAD(pagepool);
trace_erofs_readpage(page, false);
-
f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT;
+ z_erofs_pcluster_readmore(&f, NULL, f.headoffset + PAGE_SIZE - 1,
+ &pagepool, true);
err = z_erofs_do_read_page(&f, page, &pagepool);
+ z_erofs_pcluster_readmore(&f, NULL, 0, &pagepool, false);
+
(void)z_erofs_collector_end(&f.clt);
/* if some compressed cluster ready, need submit them anyway */
@@ -1400,8 +1477,7 @@ static int z_erofs_readpage(struct file *file, struct page *page)
if (f.map.mpage)
put_page(f.map.mpage);
- /* clean up the remaining free pages */
- put_pages_list(&pagepool);
+ erofs_release_pages(&pagepool);
return err;
}
@@ -1409,29 +1485,19 @@ static void z_erofs_readahead(struct readahead_control *rac)
{
struct inode *const inode = rac->mapping->host;
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
-
- unsigned int nr_pages = readahead_count(rac);
- bool sync = (sbi->ctx.readahead_sync_decompress &&
- nr_pages <= sbi->ctx.max_sync_decompress_pages);
struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
- struct page *page, *head = NULL;
- LIST_HEAD(pagepool);
-
- trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false);
+ struct page *pagepool = NULL, *head = NULL, *page;
+ unsigned int nr_pages;
f.readahead = true;
f.headoffset = readahead_pos(rac);
- while ((page = readahead_page(rac))) {
- prefetchw(&page->flags);
-
- /*
- * A pure asynchronous readahead is indicated if
- * a PG_readahead marked page is hitted at first.
- * Let's also do asynchronous decompression for this case.
- */
- sync &= !(PageReadahead(page) && !head);
+ z_erofs_pcluster_readmore(&f, rac, f.headoffset +
+ readahead_length(rac) - 1, &pagepool, true);
+ nr_pages = readahead_count(rac);
+ trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false);
+ while ((page = readahead_page(rac))) {
set_page_private(page, (unsigned long)head);
head = page;
}
@@ -1450,16 +1516,15 @@ static void z_erofs_readahead(struct readahead_control *rac)
page->index, EROFS_I(inode)->nid);
put_page(page);
}
-
+ z_erofs_pcluster_readmore(&f, rac, 0, &pagepool, false);
(void)z_erofs_collector_end(&f.clt);
- z_erofs_runqueue(inode->i_sb, &f, &pagepool, sync);
-
+ z_erofs_runqueue(inode->i_sb, &f, &pagepool,
+ sbi->opt.readahead_sync_decompress &&
+ nr_pages <= sbi->opt.max_sync_decompress_pages);
if (f.map.mpage)
put_page(f.map.mpage);
-
- /* clean up the remaining free pages */
- put_pages_list(&pagepool);
+ erofs_release_pages(&pagepool);
}
const struct address_space_operations z_erofs_aops = {
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index 3a008f1b9f78..879df5362777 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -94,13 +94,6 @@ struct z_erofs_decompressqueue {
} u;
};
-#define MNGD_MAPPING(sbi) ((sbi)->managed_cache->i_mapping)
-static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi,
- struct page *page)
-{
- return page->mapping == MNGD_MAPPING(sbi);
-}
-
#define Z_EROFS_ONLINEPAGE_COUNT_BITS 2
#define Z_EROFS_ONLINEPAGE_COUNT_MASK ((1 << Z_EROFS_ONLINEPAGE_COUNT_BITS) - 1)
#define Z_EROFS_ONLINEPAGE_INDEX_SHIFT (Z_EROFS_ONLINEPAGE_COUNT_BITS)
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 7a6df35fdc91..660489a7fb64 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -28,7 +28,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
{
struct erofs_inode *const vi = EROFS_I(inode);
struct super_block *const sb = inode->i_sb;
- int err;
+ int err, headnr;
erofs_off_t pos;
struct page *page;
void *kaddr;
@@ -68,9 +68,11 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
vi->z_algorithmtype[0] = h->h_algorithmtype & 15;
vi->z_algorithmtype[1] = h->h_algorithmtype >> 4;
- if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX) {
- erofs_err(sb, "unknown compression format %u for nid %llu, please upgrade kernel",
- vi->z_algorithmtype[0], vi->nid);
+ headnr = 0;
+ if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX ||
+ vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) {
+ erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel",
+ headnr + 1, vi->z_algorithmtype[headnr], vi->nid);
err = -EOPNOTSUPP;
goto unmap_done;
}
@@ -111,7 +113,7 @@ struct z_erofs_maprecorder {
unsigned long lcn;
/* compression extent information gathered */
- u8 type;
+ u8 type, headtype;
u16 clusterofs;
u16 delta[2];
erofs_blk_t pblk, compressedlcs;
@@ -178,7 +180,8 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
m->clusterofs = 1 << vi->z_logical_clusterbits;
m->delta[0] = le16_to_cpu(di->di_u.delta[0]);
if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) {
- if (!(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
+ if (!(vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
+ Z_EROFS_ADVISE_BIG_PCLUSTER_2))) {
DBG_BUGON(1);
return -EFSCORRUPTED;
}
@@ -189,7 +192,8 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
m->delta[1] = le16_to_cpu(di->di_u.delta[1]);
break;
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
- case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
m->clusterofs = le16_to_cpu(di->di_clusterofs);
m->pblk = le32_to_cpu(di->di_u.blkaddr);
break;
@@ -446,9 +450,9 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
}
return z_erofs_extent_lookback(m, m->delta[0]);
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
- map->m_flags &= ~EROFS_MAP_ZIPPED;
- fallthrough;
- case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
+ m->headtype = m->type;
map->m_la = (lcn << lclusterbits) | m->clusterofs;
break;
default:
@@ -471,13 +475,18 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
int err;
DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN &&
- m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD);
- if (!(map->m_flags & EROFS_MAP_ZIPPED) ||
- !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
+ m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 &&
+ m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD2);
+ DBG_BUGON(m->type != m->headtype);
+
+ if (m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
+ ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1) &&
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) ||
+ ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) &&
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) {
map->m_plen = 1 << lclusterbits;
return 0;
}
-
lcn = m->lcn + 1;
if (m->compressedlcs)
goto out;
@@ -499,7 +508,8 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
switch (m->type) {
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
- case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
/*
* if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
* rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
@@ -554,7 +564,8 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m)
DBG_BUGON(!m->delta[1] &&
m->clusterofs != 1 << lclusterbits);
} else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
- m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD) {
+ m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 ||
+ m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) {
/* go on until the next HEAD lcluster */
if (lcn != headlcn)
break;
@@ -609,16 +620,15 @@ int z_erofs_map_blocks_iter(struct inode *inode,
if (err)
goto unmap_out;
- map->m_flags = EROFS_MAP_ZIPPED; /* by default, compressed */
+ map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_ENCODED;
end = (m.lcn + 1ULL) << lclusterbits;
switch (m.type) {
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
- if (endoff >= m.clusterofs)
- map->m_flags &= ~EROFS_MAP_ZIPPED;
- fallthrough;
- case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
+ case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
if (endoff >= m.clusterofs) {
+ m.headtype = m.type;
map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
break;
}
@@ -650,13 +660,22 @@ int z_erofs_map_blocks_iter(struct inode *inode,
map->m_llen = end - map->m_la;
map->m_pa = blknr_to_addr(m.pblk);
- map->m_flags |= EROFS_MAP_MAPPED;
err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
if (err)
goto out;
- if (flags & EROFS_GET_BLOCKS_FIEMAP) {
+ if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN)
+ map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
+ else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2)
+ map->m_algorithmformat = vi->z_algorithmtype[1];
+ else
+ map->m_algorithmformat = vi->z_algorithmtype[0];
+
+ if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
+ ((flags & EROFS_GET_BLOCKS_READMORE) &&
+ map->m_algorithmformat == Z_EROFS_COMPRESSION_LZMA &&
+ map->m_llen >= EROFS_BLKSIZ)) {
err = z_erofs_get_extent_decompressedlen(&m);
if (!err)
map->m_flags |= EROFS_MAP_FULL_MAPPED;
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index ca37d4344361..1c7aa1ea4724 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -604,7 +604,7 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info)
exfat_save_attr(inode, info->attr);
inode->i_blocks = ((i_size_read(inode) + (sbi->cluster_size - 1)) &
- ~(sbi->cluster_size - 1)) >> inode->i_blkbits;
+ ~((loff_t)sbi->cluster_size - 1)) >> inode->i_blkbits;
inode->i_mtime = info->mtime;
inode->i_ctime = info->mtime;
ei->i_crtime = info->crtime;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ac0e11bbb445..9c5559faacda 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -915,7 +915,7 @@ const struct file_operations ext4_file_operations = {
.llseek = ext4_llseek,
.read_iter = ext4_file_read_iter,
.write_iter = ext4_file_write_iter,
- .iopoll = iomap_dio_iopoll,
+ .iopoll = iocb_bio_iopoll,
.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 88d5d274a868..79b6a0c47f6f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1572,7 +1572,6 @@ static const struct fscrypt_operations ext4_cryptops = {
.set_context = ext4_set_context,
.get_dummy_policy = ext4_get_dummy_policy,
.empty_dir = ext4_empty_dir,
- .max_namelen = EXT4_NAME_LEN,
.has_stable_inodes = ext4_has_stable_inodes,
.get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits,
};
@@ -4474,7 +4473,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto cantfind_ext4;
/* check blocks count against device size */
- blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+ blocks_count = sb_bdev_nr_blocks(sb);
if (blocks_count && ext4_blocks_count(es) > blocks_count) {
ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu "
"exceeds size of device (%llu blocks)",
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index c1bf9ad4c220..20a083dc9042 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -7,6 +7,7 @@
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
+#include <linux/moduleparam.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/lzo.h>
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 78ebc306ee2b..cf049a042482 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2976,7 +2976,6 @@ static const struct fscrypt_operations f2fs_cryptops = {
.set_context = f2fs_set_context,
.get_dummy_policy = f2fs_get_dummy_policy,
.empty_dir = f2fs_empty_dir,
- .max_namelen = F2FS_NAME_LEN,
.has_stable_inodes = f2fs_has_stable_inodes,
.get_ino_and_lblk_bits = f2fs_get_ino_and_lblk_bits,
.get_num_devices = f2fs_get_num_devices,
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index de0c9b013a85..a6f1c6d426d1 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1536,14 +1536,11 @@ static int fat_read_static_bpb(struct super_block *sb,
struct fat_bios_param_block *bpb)
{
static const char *notdos1x = "This doesn't look like a DOS 1.x volume";
-
+ sector_t bd_sects = bdev_nr_sectors(sb->s_bdev);
struct fat_floppy_defaults *fdefaults = NULL;
int error = -EINVAL;
- sector_t bd_sects;
unsigned i;
- bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE;
-
/* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */
if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) {
if (!silent)
@@ -1943,10 +1940,8 @@ int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2)
ret = writeback_inode(i1);
if (!ret && i2)
ret = writeback_inode(i2);
- if (!ret) {
- struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
- ret = filemap_flush(mapping);
- }
+ if (!ret)
+ ret = sync_blockdev_nowait(sb->s_bdev);
return ret;
}
EXPORT_SYMBOL_GPL(fat_flush_inodes);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 81ec192ce067..4124a89a1a5d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1893,7 +1893,8 @@ static long writeback_sb_inodes(struct super_block *sb,
* unplug, so get our IOs out the door before we
* give up the CPU.
*/
- blk_flush_plug(current);
+ if (current->plug)
+ blk_flush_plug(current->plug, false);
cond_resched();
}
@@ -2291,7 +2292,7 @@ void wakeup_flusher_threads(enum wb_reason reason)
* If we are expecting writeback progress we must submit plugged IO.
*/
if (blk_needs_flush_plug(current))
- blk_schedule_flush_plug(current);
+ blk_flush_plug(current->plug, true);
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 11404f8c21c7..e6039f22311b 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -687,7 +687,7 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
spin_unlock(&fi->lock);
}
- io->iocb->ki_complete(io->iocb, res, 0);
+ io->iocb->ki_complete(io->iocb, res);
}
kref_put(&io->refcnt, fuse_io_release);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index c559827cb6f9..5436a688157a 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1338,8 +1338,6 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
{
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- if (fl->fl_type & LOCK_MAND)
- return -EOPNOTSUPP;
if (fl->fl_type == F_UNLCK) {
do_unflock(file, fl);
@@ -1353,7 +1351,7 @@ const struct file_operations gfs2_file_fops = {
.llseek = gfs2_llseek,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
- .iopoll = iomap_dio_iopoll,
+ .iopoll = iocb_bio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
.compat_ioctl = gfs2_compat_ioctl,
.mmap = gfs2_mmap,
@@ -1386,7 +1384,7 @@ const struct file_operations gfs2_file_fops_nolock = {
.llseek = gfs2_llseek,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
- .iopoll = iomap_dio_iopoll,
+ .iopoll = iocb_bio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
.compat_ioctl = gfs2_compat_ioctl,
.mmap = gfs2_mmap,
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index cdf0edeeb278..5beb82652435 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -36,7 +36,7 @@ static int hfs_get_last_session(struct super_block *sb,
/* default values */
*start = 0;
- *size = i_size_read(sb->s_bdev->bd_inode) >> 9;
+ *size = bdev_nr_sectors(sb->s_bdev);
if (HFS_SB(sb)->session >= 0) {
struct cdrom_tocentry te;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 0350dc7821bf..51ae6f1eb4a5 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -131,7 +131,7 @@ static int hfsplus_get_last_session(struct super_block *sb,
/* default values */
*start = 0;
- *size = i_size_read(sb->s_bdev->bd_inode) >> 9;
+ *size = bdev_nr_sectors(sb->s_bdev);
if (HFSPLUS_SB(sb)->session >= 0) {
struct cdrom_tocentry te;
diff --git a/fs/internal.h b/fs/internal.h
index 3cd065c8a66b..cdd83d4899bb 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -23,22 +23,11 @@ struct pipe_inode_info;
#ifdef CONFIG_BLOCK
extern void __init bdev_cache_init(void);
-extern int __sync_blockdev(struct block_device *bdev, int wait);
-void iterate_bdevs(void (*)(struct block_device *, void *), void *);
void emergency_thaw_bdev(struct super_block *sb);
#else
static inline void bdev_cache_init(void)
{
}
-
-static inline int __sync_blockdev(struct block_device *bdev, int wait)
-{
- return 0;
-}
-static inline void iterate_bdevs(void (*f)(struct block_device *, void *),
- void *arg)
-{
-}
static inline int emergency_thaw_bdev(struct super_block *sb)
{
return 0;
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 422a7ed6a9bd..38b33ad9e8cf 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -140,6 +140,7 @@ static void io_wqe_dec_running(struct io_worker *worker);
static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
struct io_wqe_acct *acct,
struct io_cb_cancel_data *match);
+static void create_worker_cb(struct callback_head *cb);
static bool io_worker_get(struct io_worker *worker)
{
@@ -174,12 +175,46 @@ static void io_worker_ref_put(struct io_wq *wq)
complete(&wq->worker_done);
}
+static void io_worker_cancel_cb(struct io_worker *worker)
+{
+ struct io_wqe_acct *acct = io_wqe_get_acct(worker);
+ struct io_wqe *wqe = worker->wqe;
+ struct io_wq *wq = wqe->wq;
+
+ atomic_dec(&acct->nr_running);
+ raw_spin_lock(&worker->wqe->lock);
+ acct->nr_workers--;
+ raw_spin_unlock(&worker->wqe->lock);
+ io_worker_ref_put(wq);
+ clear_bit_unlock(0, &worker->create_state);
+ io_worker_release(worker);
+}
+
+static bool io_task_worker_match(struct callback_head *cb, void *data)
+{
+ struct io_worker *worker;
+
+ if (cb->func != create_worker_cb)
+ return false;
+ worker = container_of(cb, struct io_worker, create_work);
+ return worker == data;
+}
+
static void io_worker_exit(struct io_worker *worker)
{
struct io_wqe *wqe = worker->wqe;
+ struct io_wq *wq = wqe->wq;
- if (refcount_dec_and_test(&worker->ref))
- complete(&worker->ref_done);
+ while (1) {
+ struct callback_head *cb = task_work_cancel_match(wq->task,
+ io_task_worker_match, worker);
+
+ if (!cb)
+ break;
+ io_worker_cancel_cb(worker);
+ }
+
+ io_worker_release(worker);
wait_for_completion(&worker->ref_done);
raw_spin_lock(&wqe->lock);
@@ -323,8 +358,10 @@ static bool io_queue_worker_create(struct io_worker *worker,
init_task_work(&worker->create_work, func);
worker->create_index = acct->index;
- if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL))
+ if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
+ clear_bit_unlock(0, &worker->create_state);
return true;
+ }
clear_bit_unlock(0, &worker->create_state);
fail_release:
io_worker_release(worker);
@@ -716,11 +753,8 @@ static void io_workqueue_create(struct work_struct *work)
struct io_worker *worker = container_of(work, struct io_worker, work);
struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- if (!io_queue_worker_create(worker, acct, create_worker_cont)) {
- clear_bit_unlock(0, &worker->create_state);
- io_worker_release(worker);
+ if (!io_queue_worker_create(worker, acct, create_worker_cont))
kfree(worker);
- }
}
static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
@@ -1150,17 +1184,9 @@ static void io_wq_exit_workers(struct io_wq *wq)
while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
struct io_worker *worker;
- struct io_wqe_acct *acct;
worker = container_of(cb, struct io_worker, create_work);
- acct = io_wqe_get_acct(worker);
- atomic_dec(&acct->nr_running);
- raw_spin_lock(&worker->wqe->lock);
- acct->nr_workers--;
- raw_spin_unlock(&worker->wqe->lock);
- io_worker_ref_put(wq);
- clear_bit_unlock(0, &worker->create_state);
- io_worker_release(worker);
+ io_worker_cancel_cb(worker);
}
rcu_read_lock();
diff --git a/fs/io-wq.h b/fs/io-wq.h
index bf5c4c533760..41bf37674a49 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -29,6 +29,17 @@ struct io_wq_work_list {
struct io_wq_work_node *last;
};
+#define wq_list_for_each(pos, prv, head) \
+ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
+
+#define wq_list_for_each_resume(pos, prv) \
+ for (; pos; prv = pos, pos = (pos)->next)
+
+#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL)
+#define INIT_WQ_LIST(list) do { \
+ (list)->first = NULL; \
+} while (0)
+
static inline void wq_list_add_after(struct io_wq_work_node *node,
struct io_wq_work_node *pos,
struct io_wq_work_list *list)
@@ -54,6 +65,15 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node,
}
}
+static inline void wq_list_add_head(struct io_wq_work_node *node,
+ struct io_wq_work_list *list)
+{
+ node->next = list->first;
+ if (!node->next)
+ list->last = node;
+ WRITE_ONCE(list->first, node);
+}
+
static inline void wq_list_cut(struct io_wq_work_list *list,
struct io_wq_work_node *last,
struct io_wq_work_node *prev)
@@ -69,6 +89,31 @@ static inline void wq_list_cut(struct io_wq_work_list *list,
last->next = NULL;
}
+static inline void __wq_list_splice(struct io_wq_work_list *list,
+ struct io_wq_work_node *to)
+{
+ list->last->next = to->next;
+ to->next = list->first;
+ INIT_WQ_LIST(list);
+}
+
+static inline bool wq_list_splice(struct io_wq_work_list *list,
+ struct io_wq_work_node *to)
+{
+ if (!wq_list_empty(list)) {
+ __wq_list_splice(list, to);
+ return true;
+ }
+ return false;
+}
+
+static inline void wq_stack_add_head(struct io_wq_work_node *node,
+ struct io_wq_work_node *stack)
+{
+ node->next = stack->next;
+ stack->next = node;
+}
+
static inline void wq_list_del(struct io_wq_work_list *list,
struct io_wq_work_node *node,
struct io_wq_work_node *prev)
@@ -76,14 +121,14 @@ static inline void wq_list_del(struct io_wq_work_list *list,
wq_list_cut(list, node, prev);
}
-#define wq_list_for_each(pos, prv, head) \
- for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
+static inline
+struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack)
+{
+ struct io_wq_work_node *node = stack->next;
-#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL)
-#define INIT_WQ_LIST(list) do { \
- (list)->first = NULL; \
- (list)->last = NULL; \
-} while (0)
+ stack->next = node->next;
+ return node;
+}
struct io_wq_work {
struct io_wq_work_node list;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index bc18af5e0a93..3a4af9799d9a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -103,11 +103,14 @@
#define IORING_MAX_REG_BUFFERS (1U << 14)
-#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \
- IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
- IOSQE_BUFFER_SELECT)
+#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
+ IOSQE_IO_HARDLINK | IOSQE_ASYNC)
+
+#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS|IOSQE_BUFFER_SELECT|IOSQE_IO_DRAIN)
+
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
- REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS)
+ REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
+ REQ_F_ASYNC_DATA)
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
@@ -195,8 +198,10 @@ struct io_rings {
};
enum io_uring_cmd_flags {
- IO_URING_F_NONBLOCK = 1,
- IO_URING_F_COMPLETE_DEFER = 2,
+ IO_URING_F_COMPLETE_DEFER = 1,
+ IO_URING_F_UNLOCKED = 2,
+ /* int's last bit, sign checks are usually faster than a bit test */
+ IO_URING_F_NONBLOCK = INT_MIN,
};
struct io_mapped_ubuf {
@@ -305,26 +310,16 @@ struct io_submit_link {
};
struct io_submit_state {
- struct blk_plug plug;
+ /* inline/task_work completion list, under ->uring_lock */
+ struct io_wq_work_node free_list;
+ /* batch completion logic */
+ struct io_wq_work_list compl_reqs;
struct io_submit_link link;
- /*
- * io_kiocb alloc cache
- */
- void *reqs[IO_REQ_CACHE_SIZE];
- unsigned int free_reqs;
-
bool plug_started;
-
- /*
- * Batch completion logic
- */
- struct io_kiocb *compl_reqs[IO_COMPL_BATCH];
- unsigned int compl_nr;
- /* inline/task_work completion list, under ->uring_lock */
- struct list_head free_list;
-
- unsigned int ios_left;
+ bool need_plug;
+ unsigned short submit_nr;
+ struct blk_plug plug;
};
struct io_ring_ctx {
@@ -368,6 +363,7 @@ struct io_ring_ctx {
* uring_lock, and updated through io_uring_register(2)
*/
struct io_rsrc_node *rsrc_node;
+ int rsrc_cached_refs;
struct io_file_table file_table;
unsigned nr_user_files;
unsigned nr_user_bufs;
@@ -384,7 +380,7 @@ struct io_ring_ctx {
} ____cacheline_aligned_in_smp;
/* IRQ completion list, under ->completion_lock */
- struct list_head locked_free_list;
+ struct io_wq_work_list locked_free_list;
unsigned int locked_free_nr;
const struct cred *sq_creds; /* cred used for __io_sq_thread() */
@@ -399,7 +395,6 @@ struct io_ring_ctx {
unsigned cached_cq_tail;
unsigned cq_entries;
struct eventfd_ctx *cq_ev_fd;
- struct wait_queue_head poll_wait;
struct wait_queue_head cq_wait;
unsigned cq_extra;
atomic_t cq_timeouts;
@@ -417,7 +412,7 @@ struct io_ring_ctx {
* For SQPOLL, only the single threaded io_sq_thread() will
* manipulate the list, hence no extra locking is needed there.
*/
- struct list_head iopoll_list;
+ struct io_wq_work_list iopoll_list;
struct hlist_head *cancel_hash;
unsigned cancel_hash_bits;
bool poll_multi_queue;
@@ -580,7 +575,6 @@ struct io_sr_msg {
int msg_flags;
int bgid;
size_t len;
- struct io_buffer *kbuf;
};
struct io_open {
@@ -692,11 +686,6 @@ struct io_hardlink {
int flags;
};
-struct io_completion {
- struct file *file;
- u32 cflags;
-};
-
struct io_async_connect {
struct sockaddr_storage address;
};
@@ -710,11 +699,15 @@ struct io_async_msghdr {
struct sockaddr_storage addr;
};
-struct io_async_rw {
- struct iovec fast_iov[UIO_FASTIOV];
- const struct iovec *free_iovec;
+struct io_rw_state {
struct iov_iter iter;
struct iov_iter_state iter_state;
+ struct iovec fast_iov[UIO_FASTIOV];
+};
+
+struct io_async_rw {
+ struct io_rw_state s;
+ const struct iovec *free_iovec;
size_t bytes_done;
struct wait_page_queue wpq;
};
@@ -741,9 +734,9 @@ enum {
REQ_F_CREDS_BIT,
REQ_F_REFCOUNT_BIT,
REQ_F_ARM_LTIMEOUT_BIT,
+ REQ_F_ASYNC_DATA_BIT,
/* keep async read/write and isreg together and in order */
- REQ_F_NOWAIT_READ_BIT,
- REQ_F_NOWAIT_WRITE_BIT,
+ REQ_F_SUPPORT_NOWAIT_BIT,
REQ_F_ISREG_BIT,
/* not a real bit, just to check we're not overflowing the space */
@@ -784,10 +777,8 @@ enum {
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
/* caller should reissue async */
REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
- /* supports async reads */
- REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT),
- /* supports async writes */
- REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT),
+ /* supports async reads/writes */
+ REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT),
/* regular file */
REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
/* has creds assigned */
@@ -796,6 +787,8 @@ enum {
REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT),
/* there is a linked timeout that has to be armed */
REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT),
+ /* ->async_data allocated */
+ REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT),
};
struct async_poll {
@@ -852,39 +845,41 @@ struct io_kiocb {
struct io_mkdir mkdir;
struct io_symlink symlink;
struct io_hardlink hardlink;
- /* use only after cleaning per-op data, see io_clean_op() */
- struct io_completion compl;
};
- /* opcode allocated if it needs to store data for async defer */
- void *async_data;
u8 opcode;
/* polled IO has completed */
u8 iopoll_completed;
-
u16 buf_index;
+ unsigned int flags;
+
+ u64 user_data;
u32 result;
+ u32 cflags;
struct io_ring_ctx *ctx;
- unsigned int flags;
- atomic_t refs;
struct task_struct *task;
- u64 user_data;
- struct io_kiocb *link;
struct percpu_ref *fixed_rsrc_refs;
+ /* store used ubuf, so we can prevent reloading */
+ struct io_mapped_ubuf *imu;
- /* used with ctx->iopoll_list with reads/writes */
- struct list_head inflight_entry;
+ /* used by request caches, completion batching and iopoll */
+ struct io_wq_work_node comp_list;
+ atomic_t refs;
+ struct io_kiocb *link;
struct io_task_work io_task_work;
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
struct hlist_node hash_node;
+ /* internal polling, see IORING_FEAT_FAST_POLL */
struct async_poll *apoll;
+ /* opcode allocated if it needs to store data for async defer */
+ void *async_data;
struct io_wq_work work;
+ /* custom credentials, valid IFF REQ_F_CREDS is set */
const struct cred *creds;
-
- /* store used ubuf, so we can prevent reloading */
- struct io_mapped_ubuf *imu;
+ /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
+ struct io_buffer *kbuf;
};
struct io_tctx_node {
@@ -902,12 +897,12 @@ struct io_defer_entry {
struct io_op_def {
/* needs req->file assigned */
unsigned needs_file : 1;
+ /* should block plug */
+ unsigned plug : 1;
/* hash wq insertion if file is a regular file */
unsigned hash_reg_file : 1;
/* unbound wq insertion if file is a non-regular file */
unsigned unbound_nonreg_file : 1;
- /* opcode is not supported by this kernel */
- unsigned not_supported : 1;
/* set if opcode supports polled "wait" */
unsigned pollin : 1;
unsigned pollout : 1;
@@ -915,8 +910,8 @@ struct io_op_def {
unsigned buffer_select : 1;
/* do prep async if is going to be punted */
unsigned needs_async_setup : 1;
- /* should block plug */
- unsigned plug : 1;
+ /* opcode is not supported by this kernel */
+ unsigned not_supported : 1;
/* size of async data needed, if any */
unsigned short async_size;
};
@@ -1080,7 +1075,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags);
+ s32 res, u32 cflags);
static void io_put_req(struct io_kiocb *req);
static void io_put_req_deferred(struct io_kiocb *req);
static void io_dismantle_req(struct io_kiocb *req);
@@ -1095,7 +1090,7 @@ static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);
static void io_req_task_queue(struct io_kiocb *req);
-static void io_submit_flush_completions(struct io_ring_ctx *ctx);
+static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
static int io_req_prep_async(struct io_kiocb *req);
static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
@@ -1167,6 +1162,12 @@ static inline void req_ref_get(struct io_kiocb *req)
atomic_inc(&req->refs);
}
+static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
+{
+ if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+ __io_submit_flush_completions(ctx);
+}
+
static inline void __io_req_set_refcount(struct io_kiocb *req, int nr)
{
if (!(req->flags & REQ_F_REFCOUNT)) {
@@ -1180,13 +1181,52 @@ static inline void io_req_set_refcount(struct io_kiocb *req)
__io_req_set_refcount(req, 1);
}
-static inline void io_req_set_rsrc_node(struct io_kiocb *req)
+#define IO_RSRC_REF_BATCH 100
+
+static inline void io_req_put_rsrc_locked(struct io_kiocb *req,
+ struct io_ring_ctx *ctx)
+ __must_hold(&ctx->uring_lock)
{
- struct io_ring_ctx *ctx = req->ctx;
+ struct percpu_ref *ref = req->fixed_rsrc_refs;
+
+ if (ref) {
+ if (ref == &ctx->rsrc_node->refs)
+ ctx->rsrc_cached_refs++;
+ else
+ percpu_ref_put(ref);
+ }
+}
+
+static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx)
+{
+ if (req->fixed_rsrc_refs)
+ percpu_ref_put(req->fixed_rsrc_refs);
+}
+
+static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
+ __must_hold(&ctx->uring_lock)
+{
+ if (ctx->rsrc_cached_refs) {
+ percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs);
+ ctx->rsrc_cached_refs = 0;
+ }
+}
+static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
+ __must_hold(&ctx->uring_lock)
+{
+ ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH;
+ percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH);
+}
+
+static inline void io_req_set_rsrc_node(struct io_kiocb *req,
+ struct io_ring_ctx *ctx)
+{
if (!req->fixed_rsrc_refs) {
req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
- percpu_ref_get(req->fixed_rsrc_refs);
+ ctx->rsrc_cached_refs--;
+ if (unlikely(ctx->rsrc_cached_refs < 0))
+ io_rsrc_refs_refill(ctx);
}
}
@@ -1219,6 +1259,11 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
return false;
}
+static inline bool req_has_async_data(struct io_kiocb *req)
+{
+ return req->flags & REQ_F_ASYNC_DATA;
+}
+
static inline void req_set_fail(struct io_kiocb *req)
{
req->flags |= REQ_F_FAIL;
@@ -1230,7 +1275,7 @@ static inline void req_fail_link_node(struct io_kiocb *req, int res)
req->result = res;
}
-static void io_ring_ctx_ref_free(struct percpu_ref *ref)
+static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
@@ -1242,7 +1287,7 @@ static inline bool io_is_timeout_noseq(struct io_kiocb *req)
return !req->timeout.off;
}
-static void io_fallback_req_func(struct work_struct *work)
+static __cold void io_fallback_req_func(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
fallback_work.work);
@@ -1255,15 +1300,13 @@ static void io_fallback_req_func(struct work_struct *work)
req->io_task_work.func(req, &locked);
if (locked) {
- if (ctx->submit_state.compl_nr)
- io_submit_flush_completions(ctx);
+ io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
}
percpu_ref_put(&ctx->refs);
-
}
-static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
+static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
int hash_bits;
@@ -1300,7 +1343,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
ctx->flags = p->flags;
init_waitqueue_head(&ctx->sqo_sq_wait);
INIT_LIST_HEAD(&ctx->sqd_list);
- init_waitqueue_head(&ctx->poll_wait);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
init_completion(&ctx->ref_comp);
xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
@@ -1309,7 +1351,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
init_waitqueue_head(&ctx->cq_wait);
spin_lock_init(&ctx->completion_lock);
spin_lock_init(&ctx->timeout_lock);
- INIT_LIST_HEAD(&ctx->iopoll_list);
+ INIT_WQ_LIST(&ctx->iopoll_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
INIT_LIST_HEAD(&ctx->ltimeout_list);
@@ -1318,9 +1360,10 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
init_llist_head(&ctx->rsrc_put_llist);
INIT_LIST_HEAD(&ctx->tctx_list);
- INIT_LIST_HEAD(&ctx->submit_state.free_list);
- INIT_LIST_HEAD(&ctx->locked_free_list);
+ ctx->submit_state.free_list.next = NULL;
+ INIT_WQ_LIST(&ctx->locked_free_list);
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
+ INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
return ctx;
err:
kfree(ctx->dummy_ubuf);
@@ -1348,21 +1391,16 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
return false;
}
-#define FFS_ASYNC_READ 0x1UL
-#define FFS_ASYNC_WRITE 0x2UL
-#ifdef CONFIG_64BIT
-#define FFS_ISREG 0x4UL
-#else
-#define FFS_ISREG 0x0UL
-#endif
-#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG)
+#define FFS_NOWAIT 0x1UL
+#define FFS_ISREG 0x2UL
+#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG)
static inline bool io_req_ffs_set(struct io_kiocb *req)
{
- return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE);
+ return req->flags & REQ_F_FIXED_FILE;
}
-static void io_req_track_inflight(struct io_kiocb *req)
+static inline void io_req_track_inflight(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_INFLIGHT)) {
req->flags |= REQ_F_INFLIGHT;
@@ -1440,15 +1478,19 @@ static void io_prep_async_link(struct io_kiocb *req)
}
}
-static void io_queue_async_work(struct io_kiocb *req, bool *locked)
+static inline void io_req_add_compl_list(struct io_kiocb *req)
+{
+ struct io_submit_state *state = &req->ctx->submit_state;
+
+ wq_list_add_tail(&req->comp_list, &state->compl_reqs);
+}
+
+static void io_queue_async_work(struct io_kiocb *req, bool *dont_use)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *link = io_prep_linked_timeout(req);
struct io_uring_task *tctx = req->task->io_uring;
- /* must not take the lock, NULL it as a precaution */
- locked = NULL;
-
BUG_ON(!tctx);
BUG_ON(!tctx->io_wq);
@@ -1489,7 +1531,7 @@ static void io_kill_timeout(struct io_kiocb *req, int status)
}
}
-static void io_queue_deferred(struct io_ring_ctx *ctx)
+static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
{
while (!list_empty(&ctx->defer_list)) {
struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
@@ -1503,7 +1545,7 @@ static void io_queue_deferred(struct io_ring_ctx *ctx)
}
}
-static void io_flush_timeouts(struct io_ring_ctx *ctx)
+static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
__must_hold(&ctx->completion_lock)
{
u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
@@ -1536,7 +1578,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
spin_unlock_irq(&ctx->timeout_lock);
}
-static void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
+static __cold void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
if (ctx->off_timeout_used)
io_flush_timeouts(ctx);
@@ -1606,12 +1648,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
*/
if (wq_has_sleeper(&ctx->cq_wait))
wake_up_all(&ctx->cq_wait);
- if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait))
- wake_up(&ctx->sq_data->wait);
if (io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
- if (waitqueue_active(&ctx->poll_wait))
- wake_up_interruptible(&ctx->poll_wait);
}
static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
@@ -1625,8 +1663,6 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
}
if (io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
- if (waitqueue_active(&ctx->poll_wait))
- wake_up_interruptible(&ctx->poll_wait);
}
/* Returns true if there are no backlogged entries after the flush */
@@ -1722,7 +1758,7 @@ static inline void io_get_task_refs(int nr)
}
static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags)
+ s32 res, u32 cflags)
{
struct io_overflow_cqe *ocqe;
@@ -1750,7 +1786,7 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
}
static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags)
+ s32 res, u32 cflags)
{
struct io_uring_cqe *cqe;
@@ -1773,13 +1809,13 @@ static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data
/* not as hot to bloat with inlining */
static noinline bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags)
+ s32 res, u32 cflags)
{
return __io_cqring_fill_event(ctx, user_data, res, cflags);
}
-static void io_req_complete_post(struct io_kiocb *req, long res,
- unsigned int cflags)
+static void io_req_complete_post(struct io_kiocb *req, s32 res,
+ u32 cflags)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -1798,40 +1834,27 @@ static void io_req_complete_post(struct io_kiocb *req, long res,
req->link = NULL;
}
}
+ io_req_put_rsrc(req, ctx);
io_dismantle_req(req);
io_put_task(req->task, 1);
- list_add(&req->inflight_entry, &ctx->locked_free_list);
+ wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
ctx->locked_free_nr++;
- } else {
- if (!percpu_ref_tryget(&ctx->refs))
- req = NULL;
}
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
-
- if (req) {
- io_cqring_ev_posted(ctx);
- percpu_ref_put(&ctx->refs);
- }
-}
-
-static inline bool io_req_needs_clean(struct io_kiocb *req)
-{
- return req->flags & IO_REQ_CLEAN_FLAGS;
+ io_cqring_ev_posted(ctx);
}
-static void io_req_complete_state(struct io_kiocb *req, long res,
- unsigned int cflags)
+static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
+ u32 cflags)
{
- if (io_req_needs_clean(req))
- io_clean_op(req);
req->result = res;
- req->compl.cflags = cflags;
+ req->cflags = cflags;
req->flags |= REQ_F_COMPLETE_INLINE;
}
static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
- long res, unsigned cflags)
+ s32 res, u32 cflags)
{
if (issue_flags & IO_URING_F_COMPLETE_DEFER)
io_req_complete_state(req, res, cflags);
@@ -1839,12 +1862,12 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
io_req_complete_post(req, res, cflags);
}
-static inline void io_req_complete(struct io_kiocb *req, long res)
+static inline void io_req_complete(struct io_kiocb *req, s32 res)
{
__io_req_complete(req, 0, res, 0);
}
-static void io_req_complete_failed(struct io_kiocb *req, long res)
+static void io_req_complete_failed(struct io_kiocb *req, s32 res)
{
req_set_fail(req);
io_req_complete_post(req, res, 0);
@@ -1878,7 +1901,7 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
struct io_submit_state *state)
{
spin_lock(&ctx->completion_lock);
- list_splice_init(&ctx->locked_free_list, &state->free_list);
+ wq_list_splice(&ctx->locked_free_list, &state->free_list);
ctx->locked_free_nr = 0;
spin_unlock(&ctx->completion_lock);
}
@@ -1887,7 +1910,6 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
{
struct io_submit_state *state = &ctx->submit_state;
- int nr;
/*
* If we have more than a batch's worth of requests in our IRQ side
@@ -1896,20 +1918,7 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
*/
if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH)
io_flush_cached_locked_reqs(ctx, state);
-
- nr = state->free_reqs;
- while (!list_empty(&state->free_list)) {
- struct io_kiocb *req = list_first_entry(&state->free_list,
- struct io_kiocb, inflight_entry);
-
- list_del(&req->inflight_entry);
- state->reqs[nr++] = req;
- if (nr == ARRAY_SIZE(state->reqs))
- break;
- }
-
- state->free_reqs = nr;
- return nr != 0;
+ return !!state->free_list.next;
}
/*
@@ -1918,38 +1927,54 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
* Because of that, io_alloc_req() should be called only under ->uring_lock
* and with extra caution to not get a request that is still worked on.
*/
-static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
+static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
struct io_submit_state *state = &ctx->submit_state;
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
+ void *reqs[IO_REQ_ALLOC_BATCH];
+ struct io_kiocb *req;
int ret, i;
- BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH);
-
- if (likely(state->free_reqs || io_flush_cached_reqs(ctx)))
- goto got_req;
+ if (likely(state->free_list.next || io_flush_cached_reqs(ctx)))
+ return true;
- ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH,
- state->reqs);
+ ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs);
/*
* Bulk alloc is all-or-nothing. If we fail to get a batch,
* retry single alloc to be on the safe side.
*/
if (unlikely(ret <= 0)) {
- state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
- if (!state->reqs[0])
- return NULL;
+ reqs[0] = kmem_cache_alloc(req_cachep, gfp);
+ if (!reqs[0])
+ return false;
ret = 1;
}
- for (i = 0; i < ret; i++)
- io_preinit_req(state->reqs[i], ctx);
- state->free_reqs = ret;
-got_req:
- state->free_reqs--;
- return state->reqs[state->free_reqs];
+ percpu_ref_get_many(&ctx->refs, ret);
+ for (i = 0; i < ret; i++) {
+ req = reqs[i];
+
+ io_preinit_req(req, ctx);
+ wq_stack_add_head(&req->comp_list, &state->free_list);
+ }
+ return true;
+}
+
+static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx)
+{
+ if (unlikely(!ctx->submit_state.free_list.next))
+ return __io_alloc_req_refill(ctx);
+ return true;
+}
+
+static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
+{
+ struct io_wq_work_node *node;
+
+ node = wq_stack_extract(&ctx->submit_state.free_list);
+ return container_of(node, struct io_kiocb, comp_list);
}
static inline void io_put_file(struct file *file)
@@ -1958,35 +1983,28 @@ static inline void io_put_file(struct file *file)
fput(file);
}
-static void io_dismantle_req(struct io_kiocb *req)
+static inline void io_dismantle_req(struct io_kiocb *req)
{
unsigned int flags = req->flags;
- if (io_req_needs_clean(req))
+ if (unlikely(flags & IO_REQ_CLEAN_FLAGS))
io_clean_op(req);
if (!(flags & REQ_F_FIXED_FILE))
io_put_file(req->file);
- if (req->fixed_rsrc_refs)
- percpu_ref_put(req->fixed_rsrc_refs);
- if (req->async_data) {
- kfree(req->async_data);
- req->async_data = NULL;
- }
}
-static void __io_free_req(struct io_kiocb *req)
+static __cold void __io_free_req(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
+ io_req_put_rsrc(req, ctx);
io_dismantle_req(req);
io_put_task(req->task, 1);
spin_lock(&ctx->completion_lock);
- list_add(&req->inflight_entry, &ctx->locked_free_list);
+ wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
ctx->locked_free_nr++;
spin_unlock(&ctx->completion_lock);
-
- percpu_ref_put(&ctx->refs);
}
static inline void io_remove_next_linked(struct io_kiocb *req)
@@ -2072,47 +2090,45 @@ static bool io_disarm_next(struct io_kiocb *req)
return posted;
}
-static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
+static void __io_req_find_next_prep(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ bool posted;
+
+ spin_lock(&ctx->completion_lock);
+ posted = io_disarm_next(req);
+ if (posted)
+ io_commit_cqring(req->ctx);
+ spin_unlock(&ctx->completion_lock);
+ if (posted)
+ io_cqring_ev_posted(ctx);
+}
+
+static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
{
struct io_kiocb *nxt;
+ if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
+ return NULL;
/*
* If LINK is set, we have dependent requests in this chain. If we
* didn't fail this request, queue the first one up, moving any other
* dependencies to the next request. In case of failure, fail the rest
* of the chain.
*/
- if (req->flags & IO_DISARM_MASK) {
- struct io_ring_ctx *ctx = req->ctx;
- bool posted;
-
- spin_lock(&ctx->completion_lock);
- posted = io_disarm_next(req);
- if (posted)
- io_commit_cqring(req->ctx);
- spin_unlock(&ctx->completion_lock);
- if (posted)
- io_cqring_ev_posted(ctx);
- }
+ if (unlikely(req->flags & IO_DISARM_MASK))
+ __io_req_find_next_prep(req);
nxt = req->link;
req->link = NULL;
return nxt;
}
-static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
-{
- if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
- return NULL;
- return __io_req_find_next(req);
-}
-
static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked)
{
if (!ctx)
return;
if (*locked) {
- if (ctx->submit_state.compl_nr)
- io_submit_flush_completions(ctx);
+ io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
*locked = false;
}
@@ -2129,7 +2145,7 @@ static void tctx_task_work(struct callback_head *cb)
while (1) {
struct io_wq_work_node *node;
- if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr)
+ if (!tctx->task_list.first && locked)
io_submit_flush_completions(ctx);
spin_lock_irq(&tctx->task_lock);
@@ -2192,8 +2208,9 @@ static void io_req_task_work_add(struct io_kiocb *req)
* will do the job.
*/
notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL;
- if (!task_work_add(tsk, &tctx->task_work, notify)) {
- wake_up_process(tsk);
+ if (likely(!task_work_add(tsk, &tctx->task_work, notify))) {
+ if (notify == TWA_NONE)
+ wake_up_process(tsk);
return;
}
@@ -2271,77 +2288,62 @@ static void io_free_req_work(struct io_kiocb *req, bool *locked)
io_free_req(req);
}
-struct req_batch {
- struct task_struct *task;
- int task_refs;
- int ctx_refs;
-};
-
-static inline void io_init_req_batch(struct req_batch *rb)
+static void io_free_batch_list(struct io_ring_ctx *ctx,
+ struct io_wq_work_node *node)
+ __must_hold(&ctx->uring_lock)
{
- rb->task_refs = 0;
- rb->ctx_refs = 0;
- rb->task = NULL;
-}
+ struct task_struct *task = NULL;
+ int task_refs = 0;
-static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
- struct req_batch *rb)
-{
- if (rb->ctx_refs)
- percpu_ref_put_many(&ctx->refs, rb->ctx_refs);
- if (rb->task)
- io_put_task(rb->task, rb->task_refs);
-}
+ do {
+ struct io_kiocb *req = container_of(node, struct io_kiocb,
+ comp_list);
-static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req,
- struct io_submit_state *state)
-{
- io_queue_next(req);
- io_dismantle_req(req);
+ if (unlikely(req->flags & REQ_F_REFCOUNT)) {
+ node = req->comp_list.next;
+ if (!req_ref_put_and_test(req))
+ continue;
+ }
- if (req->task != rb->task) {
- if (rb->task)
- io_put_task(rb->task, rb->task_refs);
- rb->task = req->task;
- rb->task_refs = 0;
- }
- rb->task_refs++;
- rb->ctx_refs++;
+ io_req_put_rsrc_locked(req, ctx);
+ io_queue_next(req);
+ io_dismantle_req(req);
- if (state->free_reqs != ARRAY_SIZE(state->reqs))
- state->reqs[state->free_reqs++] = req;
- else
- list_add(&req->inflight_entry, &state->free_list);
+ if (req->task != task) {
+ if (task)
+ io_put_task(task, task_refs);
+ task = req->task;
+ task_refs = 0;
+ }
+ task_refs++;
+ node = req->comp_list.next;
+ wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
+ } while (node);
+
+ if (task)
+ io_put_task(task, task_refs);
}
-static void io_submit_flush_completions(struct io_ring_ctx *ctx)
+static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
+ struct io_wq_work_node *node, *prev;
struct io_submit_state *state = &ctx->submit_state;
- int i, nr = state->compl_nr;
- struct req_batch rb;
spin_lock(&ctx->completion_lock);
- for (i = 0; i < nr; i++) {
- struct io_kiocb *req = state->compl_reqs[i];
+ wq_list_for_each(node, prev, &state->compl_reqs) {
+ struct io_kiocb *req = container_of(node, struct io_kiocb,
+ comp_list);
__io_cqring_fill_event(ctx, req->user_data, req->result,
- req->compl.cflags);
+ req->cflags);
}
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
- io_init_req_batch(&rb);
- for (i = 0; i < nr; i++) {
- struct io_kiocb *req = state->compl_reqs[i];
-
- if (req_ref_put_and_test(req))
- io_req_free_batch(&rb, req, &ctx->submit_state);
- }
-
- io_req_free_batch_finish(ctx, &rb);
- state->compl_nr = 0;
+ io_free_batch_list(ctx, state->compl_reqs.first);
+ INIT_WQ_LIST(&state->compl_reqs);
}
/*
@@ -2401,12 +2403,9 @@ static unsigned int io_put_kbuf(struct io_kiocb *req, struct io_buffer *kbuf)
static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req)
{
- struct io_buffer *kbuf;
-
if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
return 0;
- kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
- return io_put_kbuf(req, kbuf);
+ return io_put_kbuf(req, req->kbuf);
}
static inline bool io_run_task_work(void)
@@ -2420,50 +2419,22 @@ static inline bool io_run_task_work(void)
return false;
}
-/*
- * Find and free completed poll iocbs
- */
-static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
- struct list_head *done)
+static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
{
- struct req_batch rb;
- struct io_kiocb *req;
-
- /* order with ->result store in io_complete_rw_iopoll() */
- smp_rmb();
-
- io_init_req_batch(&rb);
- while (!list_empty(done)) {
- req = list_first_entry(done, struct io_kiocb, inflight_entry);
- list_del(&req->inflight_entry);
-
- __io_cqring_fill_event(ctx, req->user_data, req->result,
- io_put_rw_kbuf(req));
- (*nr_events)++;
-
- if (req_ref_put_and_test(req))
- io_req_free_batch(&rb, req, &ctx->submit_state);
- }
-
- io_commit_cqring(ctx);
- io_cqring_ev_posted_iopoll(ctx);
- io_req_free_batch_finish(ctx, &rb);
-}
-
-static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
- long min)
-{
- struct io_kiocb *req, *tmp;
- LIST_HEAD(done);
- bool spin;
+ struct io_wq_work_node *pos, *start, *prev;
+ unsigned int poll_flags = BLK_POLL_NOSLEEP;
+ DEFINE_IO_COMP_BATCH(iob);
+ int nr_events = 0;
/*
* Only spin for completions if we don't have multiple devices hanging
- * off our complete list, and we're under the requested amount.
+ * off our complete list.
*/
- spin = !ctx->poll_multi_queue && *nr_events < min;
+ if (ctx->poll_multi_queue || force_nonspin)
+ poll_flags |= BLK_POLL_ONESHOT;
- list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) {
+ wq_list_for_each(pos, start, &ctx->iopoll_list) {
+ struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
struct kiocb *kiocb = &req->rw.kiocb;
int ret;
@@ -2472,47 +2443,62 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
* If we find a request that requires polling, break out
* and complete those lists first, if we have entries there.
*/
- if (READ_ONCE(req->iopoll_completed)) {
- list_move_tail(&req->inflight_entry, &done);
- continue;
- }
- if (!list_empty(&done))
+ if (READ_ONCE(req->iopoll_completed))
break;
- ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
+ ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags);
if (unlikely(ret < 0))
return ret;
else if (ret)
- spin = false;
+ poll_flags |= BLK_POLL_ONESHOT;
/* iopoll may have completed current req */
- if (READ_ONCE(req->iopoll_completed))
- list_move_tail(&req->inflight_entry, &done);
+ if (!rq_list_empty(iob.req_list) ||
+ READ_ONCE(req->iopoll_completed))
+ break;
}
- if (!list_empty(&done))
- io_iopoll_complete(ctx, nr_events, &done);
+ if (!rq_list_empty(iob.req_list))
+ iob.complete(&iob);
+ else if (!pos)
+ return 0;
- return 0;
+ prev = start;
+ wq_list_for_each_resume(pos, prev) {
+ struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
+
+ /* order with io_complete_rw_iopoll(), e.g. ->result updates */
+ if (!smp_load_acquire(&req->iopoll_completed))
+ break;
+ __io_cqring_fill_event(ctx, req->user_data, req->result,
+ io_put_rw_kbuf(req));
+ nr_events++;
+ }
+
+ if (unlikely(!nr_events))
+ return 0;
+
+ io_commit_cqring(ctx);
+ io_cqring_ev_posted_iopoll(ctx);
+ pos = start ? start->next : ctx->iopoll_list.first;
+ wq_list_cut(&ctx->iopoll_list, prev, start);
+ io_free_batch_list(ctx, pos);
+ return nr_events;
}
/*
* We can't just wait for polled events to come to us, we have to actively
* find and complete them.
*/
-static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
+static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
{
if (!(ctx->flags & IORING_SETUP_IOPOLL))
return;
mutex_lock(&ctx->uring_lock);
- while (!list_empty(&ctx->iopoll_list)) {
- unsigned int nr_events = 0;
-
- io_do_iopoll(ctx, &nr_events, 0);
-
+ while (!wq_list_empty(&ctx->iopoll_list)) {
/* let it sleep and repeat later if can't complete a request */
- if (nr_events == 0)
+ if (io_do_iopoll(ctx, true) == 0)
break;
/*
* Ensure we allow local-to-the-cpu processing to take place,
@@ -2559,7 +2545,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
* forever, while the workqueue is stuck trying to acquire the
* very same mutex.
*/
- if (list_empty(&ctx->iopoll_list)) {
+ if (wq_list_empty(&ctx->iopoll_list)) {
u32 tail = ctx->cached_cq_tail;
mutex_unlock(&ctx->uring_lock);
@@ -2568,11 +2554,15 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
/* some requests don't go through iopoll_list */
if (tail != ctx->cached_cq_tail ||
- list_empty(&ctx->iopoll_list))
+ wq_list_empty(&ctx->iopoll_list))
break;
}
- ret = io_do_iopoll(ctx, &nr_events, min);
- } while (!ret && nr_events < min && !need_resched());
+ ret = io_do_iopoll(ctx, !min);
+ if (ret < 0)
+ break;
+ nr_events += ret;
+ ret = 0;
+ } while (nr_events < min && !need_resched());
out:
mutex_unlock(&ctx->uring_lock);
return ret;
@@ -2597,9 +2587,9 @@ static bool io_resubmit_prep(struct io_kiocb *req)
{
struct io_async_rw *rw = req->async_data;
- if (!rw)
+ if (!req_has_async_data(req))
return !io_req_prep_async(req);
- iov_iter_restore(&rw->iter, &rw->iter_state);
+ iov_iter_restore(&rw->s.iter, &rw->s.iter_state);
return true;
}
@@ -2643,7 +2633,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
{
if (req->rw.kiocb.ki_flags & IOCB_WRITE)
kiocb_end_write(req);
- if (res != req->result) {
+ if (unlikely(res != req->result)) {
if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
io_rw_should_reissue(req)) {
req->flags |= REQ_F_REISSUE;
@@ -2658,16 +2648,11 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
static void io_req_task_complete(struct io_kiocb *req, bool *locked)
{
unsigned int cflags = io_put_rw_kbuf(req);
- long res = req->result;
+ int res = req->result;
if (*locked) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_submit_state *state = &ctx->submit_state;
-
io_req_complete_state(req, res, cflags);
- state->compl_reqs[state->compl_nr++] = req;
- if (state->compl_nr == ARRAY_SIZE(state->compl_reqs))
- io_submit_flush_completions(ctx);
+ io_req_add_compl_list(req);
} else {
io_req_complete_post(req, res, cflags);
}
@@ -2681,7 +2666,7 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
__io_req_complete(req, issue_flags, req->result, io_put_rw_kbuf(req));
}
-static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+static void io_complete_rw(struct kiocb *kiocb, long res)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
@@ -2692,7 +2677,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
io_req_task_work_add(req);
}
-static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
@@ -2703,12 +2688,11 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
req->flags |= REQ_F_REISSUE;
return;
}
+ req->result = res;
}
- WRITE_ONCE(req->result, res);
- /* order with io_iopoll_complete() checking ->result */
- smp_wmb();
- WRITE_ONCE(req->iopoll_completed, 1);
+ /* order with io_iopoll_complete() checking ->iopoll_completed */
+ smp_store_release(&req->iopoll_completed, 1);
}
/*
@@ -2717,13 +2701,13 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
* find it from a io_do_iopoll() thread before the issuer is done
* accessing the kiocb cookie.
*/
-static void io_iopoll_req_issued(struct io_kiocb *req)
+static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
- const bool in_async = io_wq_current_is_worker();
+ const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
/* workqueue context doesn't hold uring_lock, grab it now */
- if (unlikely(in_async))
+ if (unlikely(needs_lock))
mutex_lock(&ctx->uring_lock);
/*
@@ -2731,23 +2715,15 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
* how we do polling eventually, not spinning if we're on potentially
* different devices.
*/
- if (list_empty(&ctx->iopoll_list)) {
+ if (wq_list_empty(&ctx->iopoll_list)) {
ctx->poll_multi_queue = false;
} else if (!ctx->poll_multi_queue) {
struct io_kiocb *list_req;
- unsigned int queue_num0, queue_num1;
-
- list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb,
- inflight_entry);
- if (list_req->file != req->file) {
+ list_req = container_of(ctx->iopoll_list.first, struct io_kiocb,
+ comp_list);
+ if (list_req->file != req->file)
ctx->poll_multi_queue = true;
- } else {
- queue_num0 = blk_qc_t_to_queue_num(list_req->rw.kiocb.ki_cookie);
- queue_num1 = blk_qc_t_to_queue_num(req->rw.kiocb.ki_cookie);
- if (queue_num0 != queue_num1)
- ctx->poll_multi_queue = true;
- }
}
/*
@@ -2755,11 +2731,11 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
* it to the front so we find it first.
*/
if (READ_ONCE(req->iopoll_completed))
- list_add(&req->inflight_entry, &ctx->iopoll_list);
+ wq_list_add_head(&req->comp_list, &ctx->iopoll_list);
else
- list_add_tail(&req->inflight_entry, &ctx->iopoll_list);
+ wq_list_add_tail(&req->comp_list, &ctx->iopoll_list);
- if (unlikely(in_async)) {
+ if (unlikely(needs_lock)) {
/*
* If IORING_SETUP_SQPOLL is enabled, sqes are either handle
* in sq thread task context or in io worker task context. If
@@ -2784,10 +2760,8 @@ static bool io_bdev_nowait(struct block_device *bdev)
* any file. For now, just ensure that anything potentially problematic is done
* inline.
*/
-static bool __io_file_supports_nowait(struct file *file, int rw)
+static bool __io_file_supports_nowait(struct file *file, umode_t mode)
{
- umode_t mode = file_inode(file)->i_mode;
-
if (S_ISBLK(mode)) {
if (IS_ENABLED(CONFIG_BLOCK) &&
io_bdev_nowait(I_BDEV(file->f_mapping->host)))
@@ -2807,28 +2781,32 @@ static bool __io_file_supports_nowait(struct file *file, int rw)
/* any ->read/write should understand O_NONBLOCK */
if (file->f_flags & O_NONBLOCK)
return true;
+ return file->f_mode & FMODE_NOWAIT;
+}
- if (!(file->f_mode & FMODE_NOWAIT))
- return false;
-
- if (rw == READ)
- return file->f_op->read_iter != NULL;
+/*
+ * If we tracked the file through the SCM inflight mechanism, we could support
+ * any file. For now, just ensure that anything potentially problematic is done
+ * inline.
+ */
+static unsigned int io_file_get_flags(struct file *file)
+{
+ umode_t mode = file_inode(file)->i_mode;
+ unsigned int res = 0;
- return file->f_op->write_iter != NULL;
+ if (S_ISREG(mode))
+ res |= FFS_ISREG;
+ if (__io_file_supports_nowait(file, mode))
+ res |= FFS_NOWAIT;
+ return res;
}
-static bool io_file_supports_nowait(struct io_kiocb *req, int rw)
+static inline bool io_file_supports_nowait(struct io_kiocb *req)
{
- if (rw == READ && (req->flags & REQ_F_NOWAIT_READ))
- return true;
- else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE))
- return true;
-
- return __io_file_supports_nowait(req->file, rw);
+ return req->flags & REQ_F_SUPPORT_NOWAIT;
}
-static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- int rw)
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw.kiocb;
@@ -2836,16 +2814,15 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
unsigned ioprio;
int ret;
- if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode))
- req->flags |= REQ_F_ISREG;
+ if (!io_req_ffs_set(req))
+ req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
kiocb->ki_pos = READ_ONCE(sqe->off);
if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) {
req->flags |= REQ_F_CUR_POS;
kiocb->ki_pos = file->f_pos;
}
- kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
- kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
+ kiocb->ki_flags = iocb_flags(file);
ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
if (unlikely(ret))
return ret;
@@ -2856,22 +2833,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
* reliably. If not, or it IOCB_NOWAIT is set, don't retry.
*/
if ((kiocb->ki_flags & IOCB_NOWAIT) ||
- ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw)))
+ ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
req->flags |= REQ_F_NOWAIT;
- ioprio = READ_ONCE(sqe->ioprio);
- if (ioprio) {
- ret = ioprio_check_cap(ioprio);
- if (ret)
- return ret;
-
- kiocb->ki_ioprio = ioprio;
- } else
- kiocb->ki_ioprio = get_current_ioprio();
-
if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!(kiocb->ki_flags & IOCB_DIRECT) ||
- !kiocb->ki_filp->f_op->iopoll)
+ if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
return -EOPNOTSUPP;
kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
@@ -2883,12 +2849,18 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
kiocb->ki_complete = io_complete_rw;
}
- if (req->opcode == IORING_OP_READ_FIXED ||
- req->opcode == IORING_OP_WRITE_FIXED) {
- req->imu = NULL;
- io_req_set_rsrc_node(req);
+ ioprio = READ_ONCE(sqe->ioprio);
+ if (ioprio) {
+ ret = ioprio_check_cap(ioprio);
+ if (ret)
+ return ret;
+
+ kiocb->ki_ioprio = ioprio;
+ } else {
+ kiocb->ki_ioprio = get_current_ioprio();
}
+ req->imu = NULL;
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
req->buf_index = READ_ONCE(sqe->buf_index);
@@ -2912,7 +2884,7 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
ret = -EINTR;
fallthrough;
default:
- kiocb->ki_complete(kiocb, ret, 0);
+ kiocb->ki_complete(kiocb, ret);
}
}
@@ -2923,7 +2895,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
struct io_async_rw *io = req->async_data;
/* add previously done IO, if any */
- if (io && io->bytes_done > 0) {
+ if (req_has_async_data(req) && io->bytes_done > 0) {
if (ret < 0)
ret = io->bytes_done;
else
@@ -2946,7 +2918,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
struct io_ring_ctx *ctx = req->ctx;
req_set_fail(req);
- if (!(issue_flags & IO_URING_F_NONBLOCK)) {
+ if (issue_flags & IO_URING_F_UNLOCKED) {
mutex_lock(&ctx->uring_lock);
__io_req_complete(req, issue_flags, ret, cflags);
mutex_unlock(&ctx->uring_lock);
@@ -3017,13 +2989,15 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter
static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
{
- struct io_ring_ctx *ctx = req->ctx;
struct io_mapped_ubuf *imu = req->imu;
u16 index, buf_index = req->buf_index;
if (likely(!imu)) {
+ struct io_ring_ctx *ctx = req->ctx;
+
if (unlikely(buf_index >= ctx->nr_user_bufs))
return -EFAULT;
+ io_req_set_rsrc_node(req, ctx);
index = array_index_nospec(buf_index, ctx->nr_user_bufs);
imu = READ_ONCE(ctx->user_bufs[index]);
req->imu = imu;
@@ -3050,10 +3024,11 @@ static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
}
static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
- int bgid, struct io_buffer *kbuf,
- bool needs_lock)
+ int bgid, unsigned int issue_flags)
{
+ struct io_buffer *kbuf = req->kbuf;
struct io_buffer *head;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
if (req->flags & REQ_F_BUFFER_SELECTED)
return kbuf;
@@ -3074,34 +3049,32 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
}
if (*len > kbuf->len)
*len = kbuf->len;
+ req->flags |= REQ_F_BUFFER_SELECTED;
+ req->kbuf = kbuf;
} else {
kbuf = ERR_PTR(-ENOBUFS);
}
io_ring_submit_unlock(req->ctx, needs_lock);
-
return kbuf;
}
static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct io_buffer *kbuf;
u16 bgid;
- kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
bgid = req->buf_index;
- kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
+ kbuf = io_buffer_select(req, len, bgid, issue_flags);
if (IS_ERR(kbuf))
return kbuf;
- req->rw.addr = (u64) (unsigned long) kbuf;
- req->flags |= REQ_F_BUFFER_SELECTED;
return u64_to_user_ptr(kbuf->addr);
}
#ifdef CONFIG_COMPAT
static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct compat_iovec __user *uiov;
compat_ssize_t clen;
@@ -3117,7 +3090,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
return -EINVAL;
len = clen;
- buf = io_rw_buffer_select(req, &len, needs_lock);
+ buf = io_rw_buffer_select(req, &len, issue_flags);
if (IS_ERR(buf))
return PTR_ERR(buf);
iov[0].iov_base = buf;
@@ -3127,7 +3100,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
#endif
static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
void __user *buf;
@@ -3139,7 +3112,7 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
len = iov[0].iov_len;
if (len < 0)
return -EINVAL;
- buf = io_rw_buffer_select(req, &len, needs_lock);
+ buf = io_rw_buffer_select(req, &len, issue_flags);
if (IS_ERR(buf))
return PTR_ERR(buf);
iov[0].iov_base = buf;
@@ -3148,12 +3121,11 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
}
static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
- bool needs_lock)
+ unsigned int issue_flags)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
- struct io_buffer *kbuf;
+ struct io_buffer *kbuf = req->kbuf;
- kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
iov[0].iov_len = kbuf->len;
return 0;
@@ -3163,52 +3135,72 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
- return io_compat_import(req, iov, needs_lock);
+ return io_compat_import(req, iov, issue_flags);
#endif
- return __io_iov_buffer_select(req, iov, needs_lock);
+ return __io_iov_buffer_select(req, iov, issue_flags);
}
-static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec,
- struct iov_iter *iter, bool needs_lock)
+static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
+ struct io_rw_state *s,
+ unsigned int issue_flags)
{
- void __user *buf = u64_to_user_ptr(req->rw.addr);
- size_t sqe_len = req->rw.len;
+ struct iov_iter *iter = &s->iter;
u8 opcode = req->opcode;
+ struct iovec *iovec;
+ void __user *buf;
+ size_t sqe_len;
ssize_t ret;
- if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
- *iovec = NULL;
- return io_import_fixed(req, rw, iter);
- }
+ BUILD_BUG_ON(ERR_PTR(0) != NULL);
+
+ if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED)
+ return ERR_PTR(io_import_fixed(req, rw, iter));
/* buffer index only valid with fixed read/write, or buffer select */
- if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))
- return -EINVAL;
+ if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)))
+ return ERR_PTR(-EINVAL);
+
+ buf = u64_to_user_ptr(req->rw.addr);
+ sqe_len = req->rw.len;
if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
if (req->flags & REQ_F_BUFFER_SELECT) {
- buf = io_rw_buffer_select(req, &sqe_len, needs_lock);
+ buf = io_rw_buffer_select(req, &sqe_len, issue_flags);
if (IS_ERR(buf))
- return PTR_ERR(buf);
+ return ERR_CAST(buf);
req->rw.len = sqe_len;
}
- ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
- *iovec = NULL;
- return ret;
+ ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter);
+ return ERR_PTR(ret);
}
+ iovec = s->fast_iov;
if (req->flags & REQ_F_BUFFER_SELECT) {
- ret = io_iov_buffer_select(req, *iovec, needs_lock);
+ ret = io_iov_buffer_select(req, iovec, issue_flags);
if (!ret)
- iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len);
- *iovec = NULL;
- return ret;
+ iov_iter_init(iter, rw, iovec, 1, iovec->iov_len);
+ return ERR_PTR(ret);
}
- return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
+ ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
req->ctx->compat);
+ if (unlikely(ret < 0))
+ return ERR_PTR(ret);
+ return iovec;
+}
+
+static inline int io_import_iovec(int rw, struct io_kiocb *req,
+ struct iovec **iovec, struct io_rw_state *s,
+ unsigned int issue_flags)
+{
+ *iovec = __io_import_iovec(rw, req, s, issue_flags);
+ if (unlikely(IS_ERR(*iovec)))
+ return PTR_ERR(*iovec);
+
+ iov_iter_save_state(&s->iter, &s->iter_state);
+ return 0;
}
static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
@@ -3233,7 +3225,8 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter)
*/
if (kiocb->ki_flags & IOCB_HIPRI)
return -EOPNOTSUPP;
- if (kiocb->ki_flags & IOCB_NOWAIT)
+ if ((kiocb->ki_flags & IOCB_NOWAIT) &&
+ !(kiocb->ki_filp->f_flags & O_NONBLOCK))
return -EAGAIN;
while (iov_iter_count(iter)) {
@@ -3279,7 +3272,7 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
{
struct io_async_rw *rw = req->async_data;
- memcpy(&rw->iter, iter, sizeof(*iter));
+ memcpy(&rw->s.iter, iter, sizeof(*iter));
rw->free_iovec = iovec;
rw->bytes_done = 0;
/* can only be fixed buffers, no need to do anything */
@@ -3288,33 +3281,36 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
if (!iovec) {
unsigned iov_off = 0;
- rw->iter.iov = rw->fast_iov;
+ rw->s.iter.iov = rw->s.fast_iov;
if (iter->iov != fast_iov) {
iov_off = iter->iov - fast_iov;
- rw->iter.iov += iov_off;
+ rw->s.iter.iov += iov_off;
}
- if (rw->fast_iov != fast_iov)
- memcpy(rw->fast_iov + iov_off, fast_iov + iov_off,
+ if (rw->s.fast_iov != fast_iov)
+ memcpy(rw->s.fast_iov + iov_off, fast_iov + iov_off,
sizeof(struct iovec) * iter->nr_segs);
} else {
req->flags |= REQ_F_NEED_CLEANUP;
}
}
-static inline int io_alloc_async_data(struct io_kiocb *req)
+static inline bool io_alloc_async_data(struct io_kiocb *req)
{
WARN_ON_ONCE(!io_op_defs[req->opcode].async_size);
req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL);
- return req->async_data == NULL;
+ if (req->async_data) {
+ req->flags |= REQ_F_ASYNC_DATA;
+ return false;
+ }
+ return true;
}
static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
- const struct iovec *fast_iov,
- struct iov_iter *iter, bool force)
+ struct io_rw_state *s, bool force)
{
if (!force && !io_op_defs[req->opcode].needs_async_setup)
return 0;
- if (!req->async_data) {
+ if (!req_has_async_data(req)) {
struct io_async_rw *iorw;
if (io_alloc_async_data(req)) {
@@ -3322,10 +3318,10 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
return -ENOMEM;
}
- io_req_map_rw(req, iovec, fast_iov, iter);
+ io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
iorw = req->async_data;
/* we've copied and mapped the iter, ensure state is saved */
- iov_iter_save_state(&iorw->iter, &iorw->iter_state);
+ iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
}
return 0;
}
@@ -3333,10 +3329,11 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
{
struct io_async_rw *iorw = req->async_data;
- struct iovec *iov = iorw->fast_iov;
+ struct iovec *iov;
int ret;
- ret = io_import_iovec(rw, req, &iov, &iorw->iter, false);
+ /* submission path, ->uring_lock should already be taken */
+ ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
if (unlikely(ret < 0))
return ret;
@@ -3344,7 +3341,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
iorw->free_iovec = iov;
if (iov)
req->flags |= REQ_F_NEED_CLEANUP;
- iov_iter_save_state(&iorw->iter, &iorw->iter_state);
return 0;
}
@@ -3352,11 +3348,11 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
if (unlikely(!(req->file->f_mode & FMODE_READ)))
return -EBADF;
- return io_prep_rw(req, sqe, READ);
+ return io_prep_rw(req, sqe);
}
/*
- * This is our waitqueue callback handler, registered through lock_page_async()
+ * This is our waitqueue callback handler, registered through __folio_lock_async()
* when we initially tried to do the IO with the iocb armed our waitqueue.
* This gets called when the page is unlocked, and we generally expect that to
* happen when the page IO is completed and the page is now uptodate. This will
@@ -3428,7 +3424,7 @@ static bool io_rw_should_retry(struct io_kiocb *req)
static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
{
- if (req->file->f_op->read_iter)
+ if (likely(req->file->f_op->read_iter))
return call_read_iter(req->file, &req->rw.kiocb, iter);
else if (req->file->f_op->read)
return loop_rw_iter(READ, req, iter);
@@ -3444,43 +3440,40 @@ static bool need_read_all(struct io_kiocb *req)
static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
- struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct io_rw_state __s, *s = &__s;
+ struct iovec *iovec;
struct kiocb *kiocb = &req->rw.kiocb;
- struct iov_iter __iter, *iter = &__iter;
- struct io_async_rw *rw = req->async_data;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- struct iov_iter_state __state, *state;
+ struct io_async_rw *rw;
ssize_t ret, ret2;
- if (rw) {
- iter = &rw->iter;
- state = &rw->iter_state;
+ if (!req_has_async_data(req)) {
+ ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
+ return ret;
+ } else {
+ rw = req->async_data;
+ s = &rw->s;
/*
* We come here from an earlier attempt, restore our state to
* match in case it doesn't. It's cheap enough that we don't
* need to make this conditional.
*/
- iov_iter_restore(iter, state);
+ iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
- } else {
- ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock);
- if (ret < 0)
- return ret;
- state = &__state;
- iov_iter_save_state(iter, state);
}
- req->result = iov_iter_count(iter);
+ req->result = iov_iter_count(&s->iter);
- /* Ensure we clear previously set non-block flag */
- if (!force_nonblock)
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- else
+ if (force_nonblock) {
+ /* If the file doesn't support async, just async punt */
+ if (unlikely(!io_file_supports_nowait(req))) {
+ ret = io_setup_async_rw(req, iovec, s, true);
+ return ret ?: -EAGAIN;
+ }
kiocb->ki_flags |= IOCB_NOWAIT;
-
- /* If the file doesn't support async, just async punt */
- if (force_nonblock && !io_file_supports_nowait(req, READ)) {
- ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
- return ret ?: -EAGAIN;
+ } else {
+ /* Ensure we clear previously set non-block flag */
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
}
ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result);
@@ -3489,7 +3482,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
return ret;
}
- ret = io_iter_do_read(req, iter);
+ ret = io_iter_do_read(req, &s->iter);
if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
req->flags &= ~REQ_F_REISSUE;
@@ -3502,7 +3495,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
ret = 0;
} else if (ret == -EIOCBQUEUED) {
goto out_free;
- } else if (ret <= 0 || ret == req->result || !force_nonblock ||
+ } else if (ret == req->result || ret <= 0 || !force_nonblock ||
(req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
/* read all, failed, already did sync or don't want to retry */
goto done;
@@ -3513,22 +3506,19 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
* untouched in case of error. Restore it and we'll advance it
* manually if we need to.
*/
- iov_iter_restore(iter, state);
+ iov_iter_restore(&s->iter, &s->iter_state);
- ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
+ ret2 = io_setup_async_rw(req, iovec, s, true);
if (ret2)
return ret2;
iovec = NULL;
rw = req->async_data;
+ s = &rw->s;
/*
* Now use our persistent iterator and state, if we aren't already.
* We've restored and mapped the iter to match.
*/
- if (iter != &rw->iter) {
- iter = &rw->iter;
- state = &rw->iter_state;
- }
do {
/*
@@ -3536,11 +3526,11 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
* above or inside this loop. Advance the iter by the bytes
* that were consumed.
*/
- iov_iter_advance(iter, ret);
- if (!iov_iter_count(iter))
+ iov_iter_advance(&s->iter, ret);
+ if (!iov_iter_count(&s->iter))
break;
rw->bytes_done += ret;
- iov_iter_save_state(iter, state);
+ iov_iter_save_state(&s->iter, &s->iter_state);
/* if we can retry, do so with the callbacks armed */
if (!io_rw_should_retry(req)) {
@@ -3554,12 +3544,12 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
* desired page gets unlocked. We can also get a partial read
* here, and if we do, then just retry at the new offset.
*/
- ret = io_iter_do_read(req, iter);
+ ret = io_iter_do_read(req, &s->iter);
if (ret == -EIOCBQUEUED)
return 0;
/* we got some bytes, but not all. retry. */
kiocb->ki_flags &= ~IOCB_WAITQ;
- iov_iter_restore(iter, state);
+ iov_iter_restore(&s->iter, &s->iter_state);
} while (ret > 0);
done:
kiocb_done(kiocb, ret, issue_flags);
@@ -3574,47 +3564,46 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
return -EBADF;
- return io_prep_rw(req, sqe, WRITE);
+ req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file));
+ return io_prep_rw(req, sqe);
}
static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
- struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct io_rw_state __s, *s = &__s;
+ struct iovec *iovec;
struct kiocb *kiocb = &req->rw.kiocb;
- struct iov_iter __iter, *iter = &__iter;
- struct io_async_rw *rw = req->async_data;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- struct iov_iter_state __state, *state;
ssize_t ret, ret2;
- if (rw) {
- iter = &rw->iter;
- state = &rw->iter_state;
- iov_iter_restore(iter, state);
- iovec = NULL;
- } else {
- ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock);
- if (ret < 0)
+ if (!req_has_async_data(req)) {
+ ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
return ret;
- state = &__state;
- iov_iter_save_state(iter, state);
+ } else {
+ struct io_async_rw *rw = req->async_data;
+
+ s = &rw->s;
+ iov_iter_restore(&s->iter, &s->iter_state);
+ iovec = NULL;
}
- req->result = iov_iter_count(iter);
+ req->result = iov_iter_count(&s->iter);
- /* Ensure we clear previously set non-block flag */
- if (!force_nonblock)
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- else
- kiocb->ki_flags |= IOCB_NOWAIT;
+ if (force_nonblock) {
+ /* If the file doesn't support async, just async punt */
+ if (unlikely(!io_file_supports_nowait(req)))
+ goto copy_iov;
- /* If the file doesn't support async, just async punt */
- if (force_nonblock && !io_file_supports_nowait(req, WRITE))
- goto copy_iov;
+ /* file path doesn't support NOWAIT for non-direct_IO */
+ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
+ (req->flags & REQ_F_ISREG))
+ goto copy_iov;
- /* file path doesn't support NOWAIT for non-direct_IO */
- if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
- (req->flags & REQ_F_ISREG))
- goto copy_iov;
+ kiocb->ki_flags |= IOCB_NOWAIT;
+ } else {
+ /* Ensure we clear previously set non-block flag */
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
+ }
ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result);
if (unlikely(ret))
@@ -3634,10 +3623,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
}
kiocb->ki_flags |= IOCB_WRITE;
- if (req->file->f_op->write_iter)
- ret2 = call_write_iter(req->file, kiocb, iter);
+ if (likely(req->file->f_op->write_iter))
+ ret2 = call_write_iter(req->file, kiocb, &s->iter);
else if (req->file->f_op->write)
- ret2 = loop_rw_iter(WRITE, req, iter);
+ ret2 = loop_rw_iter(WRITE, req, &s->iter);
else
ret2 = -EINVAL;
@@ -3657,14 +3646,14 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
goto done;
if (!force_nonblock || ret2 != -EAGAIN) {
/* IOPOLL retry should happen for io-wq threads */
- if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
+ if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
goto copy_iov;
done:
kiocb_done(kiocb, ret2, issue_flags);
} else {
copy_iov:
- iov_iter_restore(iter, state);
- ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
+ iov_iter_restore(&s->iter, &s->iter_state);
+ ret = io_setup_async_rw(req, iovec, s, false);
return ret ?: -EAGAIN;
}
out_free:
@@ -3800,7 +3789,7 @@ static int io_mkdirat_prep(struct io_kiocb *req,
return 0;
}
-static int io_mkdirat(struct io_kiocb *req, int issue_flags)
+static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_mkdir *mkd = &req->mkdir;
int ret;
@@ -3849,7 +3838,7 @@ static int io_symlinkat_prep(struct io_kiocb *req,
return 0;
}
-static int io_symlinkat(struct io_kiocb *req, int issue_flags)
+static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_symlink *sl = &req->symlink;
int ret;
@@ -3899,7 +3888,7 @@ static int io_linkat_prep(struct io_kiocb *req,
return 0;
}
-static int io_linkat(struct io_kiocb *req, int issue_flags)
+static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_hardlink *lnk = &req->hardlink;
int ret;
@@ -4318,9 +4307,9 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
struct io_ring_ctx *ctx = req->ctx;
struct io_buffer *head;
int ret = 0;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- io_ring_submit_lock(ctx, !force_nonblock);
+ io_ring_submit_lock(ctx, needs_lock);
lockdep_assert_held(&ctx->uring_lock);
@@ -4333,7 +4322,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
/* complete before unlock, IOPOLL may need the lock */
__io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, !force_nonblock);
+ io_ring_submit_unlock(ctx, needs_lock);
return 0;
}
@@ -4405,9 +4394,9 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
struct io_ring_ctx *ctx = req->ctx;
struct io_buffer *head, *list;
int ret = 0;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- io_ring_submit_lock(ctx, !force_nonblock);
+ io_ring_submit_lock(ctx, needs_lock);
lockdep_assert_held(&ctx->uring_lock);
@@ -4423,7 +4412,7 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
req_set_fail(req);
/* complete before unlock, IOPOLL may need the lock */
__io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, !force_nonblock);
+ io_ring_submit_unlock(ctx, needs_lock);
return 0;
}
@@ -4756,8 +4745,9 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(!sock))
return -ENOTSOCK;
- kmsg = req->async_data;
- if (!kmsg) {
+ if (req_has_async_data(req)) {
+ kmsg = req->async_data;
+ } else {
ret = io_sendmsg_copy_hdr(req, &iomsg);
if (ret)
return ret;
@@ -4916,23 +4906,16 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req,
}
static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct io_sr_msg *sr = &req->sr_msg;
- struct io_buffer *kbuf;
- kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock);
- if (IS_ERR(kbuf))
- return kbuf;
-
- sr->kbuf = kbuf;
- req->flags |= REQ_F_BUFFER_SELECTED;
- return kbuf;
+ return io_buffer_select(req, &sr->len, sr->bgid, issue_flags);
}
static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req)
{
- return io_put_kbuf(req, req->sr_msg.kbuf);
+ return io_put_kbuf(req, req->kbuf);
}
static int io_recvmsg_prep_async(struct io_kiocb *req)
@@ -4980,8 +4963,9 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(!sock))
return -ENOTSOCK;
- kmsg = req->async_data;
- if (!kmsg) {
+ if (req_has_async_data(req)) {
+ kmsg = req->async_data;
+ } else {
ret = io_recvmsg_copy_hdr(req, &iomsg);
if (ret)
return ret;
@@ -4989,7 +4973,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
}
if (req->flags & REQ_F_BUFFER_SELECT) {
- kbuf = io_recv_buffer_select(req, !force_nonblock);
+ kbuf = io_recv_buffer_select(req, issue_flags);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
@@ -5041,7 +5025,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
return -ENOTSOCK;
if (req->flags & REQ_F_BUFFER_SELECT) {
- kbuf = io_recv_buffer_select(req, !force_nonblock);
+ kbuf = io_recv_buffer_select(req, issue_flags);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
buf = u64_to_user_ptr(kbuf->addr);
@@ -5172,7 +5156,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
int ret;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- if (req->async_data) {
+ if (req_has_async_data(req)) {
io = req->async_data;
} else {
ret = move_addr_to_kernel(req->connect.addr,
@@ -5188,7 +5172,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
ret = __sys_connect_file(req->file, &io->address,
req->connect.addr_len, file_flags);
if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
- if (req->async_data)
+ if (req_has_async_data(req))
return -EAGAIN;
if (io_alloc_async_data(req)) {
ret = -ENOMEM;
@@ -5348,16 +5332,6 @@ static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask)
return !(flags & IORING_CQE_F_MORE);
}
-static inline bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
- __must_hold(&req->ctx->completion_lock)
-{
- bool done;
-
- done = __io_poll_complete(req, mask);
- io_commit_cqring(req->ctx);
- return done;
-}
-
static void io_poll_task_func(struct io_kiocb *req, bool *locked)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -5479,7 +5453,10 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake);
req_ref_get(req);
poll->wait.private = req;
+
*poll_ptr = poll;
+ if (req->opcode == IORING_OP_POLL_ADD)
+ req->flags |= REQ_F_ASYNC_DATA;
}
pt->nr_entries++;
@@ -5603,17 +5580,13 @@ static int io_arm_poll_handler(struct io_kiocb *req)
struct async_poll *apoll;
struct io_poll_table ipt;
__poll_t ret, mask = EPOLLONESHOT | POLLERR | POLLPRI;
- int rw;
- if (!req->file || !file_can_poll(req->file))
- return IO_APOLL_ABORTED;
- if (req->flags & REQ_F_POLLED)
- return IO_APOLL_ABORTED;
if (!def->pollin && !def->pollout)
return IO_APOLL_ABORTED;
+ if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED))
+ return IO_APOLL_ABORTED;
if (def->pollin) {
- rw = READ;
mask |= POLLIN | POLLRDNORM;
/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
@@ -5621,14 +5594,9 @@ static int io_arm_poll_handler(struct io_kiocb *req)
(req->sr_msg.msg_flags & MSG_ERRQUEUE))
mask &= ~POLLIN;
} else {
- rw = WRITE;
mask |= POLLOUT | POLLWRNORM;
}
- /* if we can't nonblock try, then no point in arming a poll handler */
- if (!io_file_supports_nowait(req, rw))
- return IO_APOLL_ABORTED;
-
apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
if (unlikely(!apoll))
return IO_APOLL_ABORTED;
@@ -5689,8 +5657,8 @@ static bool io_poll_remove_one(struct io_kiocb *req)
/*
* Returns true if we found and killed one or more poll requests
*/
-static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
- bool cancel_all)
+static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx,
+ struct task_struct *tsk, bool cancel_all)
{
struct hlist_node *tmp;
struct io_kiocb *req;
@@ -5844,7 +5812,8 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
if (mask) { /* no async, we'd stolen it */
ipt.error = 0;
- done = io_poll_complete(req, mask);
+ done = __io_poll_complete(req, mask);
+ io_commit_cqring(req->ctx);
}
spin_unlock(&ctx->completion_lock);
@@ -5920,7 +5889,10 @@ err:
static void io_req_task_timeout(struct io_kiocb *req, bool *locked)
{
- req_set_fail(req);
+ struct io_timeout_data *data = req->async_data;
+
+ if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS))
+ req_set_fail(req);
io_req_complete_post(req, -ETIME, 0);
}
@@ -6126,7 +6098,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (off && is_timeout_link)
return -EINVAL;
flags = READ_ONCE(sqe->timeout_flags);
- if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK))
+ if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK |
+ IORING_TIMEOUT_ETIME_SUCCESS))
return -EINVAL;
/* more than one clock specified is invalid, obviously */
if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
@@ -6137,7 +6110,9 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (unlikely(off && !req->ctx->off_timeout_used))
req->ctx->off_timeout_used = true;
- if (!req->async_data && io_alloc_async_data(req))
+ if (WARN_ON_ONCE(req_has_async_data(req)))
+ return -EFAULT;
+ if (io_alloc_async_data(req))
return -ENOMEM;
data = req->async_data;
@@ -6294,6 +6269,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
u64 sqe_addr = req->cancel.addr;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_tctx_node *node;
int ret;
@@ -6302,7 +6278,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
goto done;
/* slow path, try all io-wq's */
- io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_lock(ctx, needs_lock);
ret = -ENOENT;
list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
struct io_uring_task *tctx = node->task->io_uring;
@@ -6311,7 +6287,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
if (ret != -ENOENT)
break;
}
- io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_unlock(ctx, needs_lock);
done:
if (ret < 0)
req_set_fail(req);
@@ -6338,6 +6314,7 @@ static int io_rsrc_update_prep(struct io_kiocb *req,
static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_uring_rsrc_update2 up;
int ret;
@@ -6347,10 +6324,10 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
up.tags = 0;
up.resv = 0;
- io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_lock(ctx, needs_lock);
ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
&up, req->rsrc_update.nr_args);
- io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_unlock(ctx, needs_lock);
if (ret < 0)
req_set_fail(req);
@@ -6446,7 +6423,7 @@ static int io_req_prep_async(struct io_kiocb *req)
{
if (!io_op_defs[req->opcode].needs_async_setup)
return 0;
- if (WARN_ON_ONCE(req->async_data))
+ if (WARN_ON_ONCE(req_has_async_data(req)))
return -EFAULT;
if (io_alloc_async_data(req))
return -EAGAIN;
@@ -6478,68 +6455,39 @@ static u32 io_get_sequence(struct io_kiocb *req)
return seq;
}
-static bool io_drain_req(struct io_kiocb *req)
+static __cold void io_drain_req(struct io_kiocb *req)
{
- struct io_kiocb *pos;
struct io_ring_ctx *ctx = req->ctx;
struct io_defer_entry *de;
int ret;
- u32 seq;
-
- if (req->flags & REQ_F_FAIL) {
- io_req_complete_fail_submit(req);
- return true;
- }
-
- /*
- * If we need to drain a request in the middle of a link, drain the
- * head request and the next request/link after the current link.
- * Considering sequential execution of links, IOSQE_IO_DRAIN will be
- * maintained for every request of our link.
- */
- if (ctx->drain_next) {
- req->flags |= REQ_F_IO_DRAIN;
- ctx->drain_next = false;
- }
- /* not interested in head, start from the first linked */
- io_for_each_link(pos, req->link) {
- if (pos->flags & REQ_F_IO_DRAIN) {
- ctx->drain_next = true;
- req->flags |= REQ_F_IO_DRAIN;
- break;
- }
- }
+ u32 seq = io_get_sequence(req);
/* Still need defer if there is pending req in defer list. */
- if (likely(list_empty_careful(&ctx->defer_list) &&
- !(req->flags & REQ_F_IO_DRAIN))) {
+ if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) {
+queue:
ctx->drain_active = false;
- return false;
+ io_req_task_queue(req);
+ return;
}
- seq = io_get_sequence(req);
- /* Still a chance to pass the sequence check */
- if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list))
- return false;
-
ret = io_req_prep_async(req);
- if (ret)
- goto fail;
+ if (ret) {
+fail:
+ io_req_complete_failed(req, ret);
+ return;
+ }
io_prep_async_link(req);
de = kmalloc(sizeof(*de), GFP_KERNEL);
if (!de) {
ret = -ENOMEM;
-fail:
- io_req_complete_failed(req, ret);
- return true;
+ goto fail;
}
spin_lock(&ctx->completion_lock);
if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) {
spin_unlock(&ctx->completion_lock);
kfree(de);
- io_queue_async_work(req, NULL);
- return true;
+ goto queue;
}
trace_io_uring_defer(ctx, req, req->user_data);
@@ -6547,23 +6495,13 @@ fail:
de->seq = seq;
list_add_tail(&de->list, &ctx->defer_list);
spin_unlock(&ctx->completion_lock);
- return true;
}
static void io_clean_op(struct io_kiocb *req)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
- switch (req->opcode) {
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
- kfree((void *)(unsigned long)req->rw.addr);
- break;
- case IORING_OP_RECVMSG:
- case IORING_OP_RECV:
- kfree(req->sr_msg.kbuf);
- break;
- }
+ kfree(req->kbuf);
+ req->kbuf = NULL;
}
if (req->flags & REQ_F_NEED_CLEANUP) {
@@ -6628,17 +6566,19 @@ static void io_clean_op(struct io_kiocb *req)
}
if (req->flags & REQ_F_CREDS)
put_cred(req->creds);
-
+ if (req->flags & REQ_F_ASYNC_DATA) {
+ kfree(req->async_data);
+ req->async_data = NULL;
+ }
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
- struct io_ring_ctx *ctx = req->ctx;
const struct cred *creds = NULL;
int ret;
- if ((req->flags & REQ_F_CREDS) && req->creds != current_cred())
+ if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
creds = override_creds(req->creds);
switch (req->opcode) {
@@ -6761,8 +6701,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (ret)
return ret;
/* If the op doesn't have a file, we're not polling for it */
- if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file)
- io_iopoll_req_issued(req);
+ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file)
+ io_iopoll_req_issued(req, issue_flags);
return 0;
}
@@ -6778,6 +6718,8 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
static void io_wq_submit_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ unsigned int issue_flags = IO_URING_F_UNLOCKED;
+ bool needs_poll = false;
struct io_kiocb *timeout;
int ret = 0;
@@ -6792,23 +6734,42 @@ static void io_wq_submit_work(struct io_wq_work *work)
io_queue_linked_timeout(timeout);
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
- if (work->flags & IO_WQ_WORK_CANCEL)
- ret = -ECANCELED;
+ if (work->flags & IO_WQ_WORK_CANCEL) {
+ io_req_task_queue_fail(req, -ECANCELED);
+ return;
+ }
- if (!ret) {
- do {
- ret = io_issue_sqe(req, 0);
- /*
- * We can get EAGAIN for polled IO even though we're
- * forcing a sync submission from here, since we can't
- * wait for request slots on the block side.
- */
- if (ret != -EAGAIN)
- break;
- cond_resched();
- } while (1);
+ if (req->flags & REQ_F_FORCE_ASYNC) {
+ const struct io_op_def *def = &io_op_defs[req->opcode];
+ bool opcode_poll = def->pollin || def->pollout;
+
+ if (opcode_poll && file_can_poll(req->file)) {
+ needs_poll = true;
+ issue_flags |= IO_URING_F_NONBLOCK;
+ }
}
+ do {
+ ret = io_issue_sqe(req, issue_flags);
+ if (ret != -EAGAIN)
+ break;
+ /*
+ * We can get EAGAIN for iopolled IO even though we're
+ * forcing a sync submission from here, since we can't
+ * wait for request slots on the block side.
+ */
+ if (!needs_poll) {
+ cond_resched();
+ continue;
+ }
+
+ if (io_arm_poll_handler(req) == IO_APOLL_OK)
+ return;
+ /* aborted or ready, in either case retry blocking */
+ needs_poll = false;
+ issue_flags &= ~IO_URING_F_NONBLOCK;
+ } while (1);
+
/* avoid locking problems by failing it from a clean context */
if (ret)
io_req_task_queue_fail(req, ret);
@@ -6832,12 +6793,7 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file
{
unsigned long file_ptr = (unsigned long) file;
- if (__io_file_supports_nowait(file, READ))
- file_ptr |= FFS_ASYNC_READ;
- if (__io_file_supports_nowait(file, WRITE))
- file_ptr |= FFS_ASYNC_WRITE;
- if (S_ISREG(file_inode(file)->i_mode))
- file_ptr |= FFS_ISREG;
+ file_ptr |= io_file_get_flags(file);
file_slot->file_ptr = file_ptr;
}
@@ -6854,8 +6810,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
file = (struct file *) (file_ptr & FFS_MASK);
file_ptr &= ~FFS_MASK;
/* mask in overlapping REQ_F and FFS bits */
- req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT);
- io_req_set_rsrc_node(req);
+ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
+ io_req_set_rsrc_node(req, ctx);
return file;
}
@@ -6947,67 +6903,66 @@ static void io_queue_linked_timeout(struct io_kiocb *req)
io_put_req(req);
}
-static void __io_queue_sqe(struct io_kiocb *req)
+static void io_queue_sqe_arm_apoll(struct io_kiocb *req)
+ __must_hold(&req->ctx->uring_lock)
+{
+ struct io_kiocb *linked_timeout = io_prep_linked_timeout(req);
+
+ switch (io_arm_poll_handler(req)) {
+ case IO_APOLL_READY:
+ if (linked_timeout) {
+ io_queue_linked_timeout(linked_timeout);
+ linked_timeout = NULL;
+ }
+ io_req_task_queue(req);
+ break;
+ case IO_APOLL_ABORTED:
+ /*
+ * Queued up for async execution, worker will release
+ * submit reference when the iocb is actually submitted.
+ */
+ io_queue_async_work(req, NULL);
+ break;
+ }
+
+ if (linked_timeout)
+ io_queue_linked_timeout(linked_timeout);
+}
+
+static inline void __io_queue_sqe(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
struct io_kiocb *linked_timeout;
int ret;
-issue_sqe:
ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
+ if (req->flags & REQ_F_COMPLETE_INLINE) {
+ io_req_add_compl_list(req);
+ return;
+ }
/*
* We async punt it if the file wasn't marked NOWAIT, or if the file
* doesn't support non-blocking read/write attempts
*/
if (likely(!ret)) {
- if (req->flags & REQ_F_COMPLETE_INLINE) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_submit_state *state = &ctx->submit_state;
-
- state->compl_reqs[state->compl_nr++] = req;
- if (state->compl_nr == ARRAY_SIZE(state->compl_reqs))
- io_submit_flush_completions(ctx);
- return;
- }
-
linked_timeout = io_prep_linked_timeout(req);
if (linked_timeout)
io_queue_linked_timeout(linked_timeout);
} else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
- linked_timeout = io_prep_linked_timeout(req);
-
- switch (io_arm_poll_handler(req)) {
- case IO_APOLL_READY:
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
- goto issue_sqe;
- case IO_APOLL_ABORTED:
- /*
- * Queued up for async execution, worker will release
- * submit reference when the iocb is actually submitted.
- */
- io_queue_async_work(req, NULL);
- break;
- }
-
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
+ io_queue_sqe_arm_apoll(req);
} else {
io_req_complete_failed(req, ret);
}
}
-static inline void io_queue_sqe(struct io_kiocb *req)
+static void io_queue_sqe_fallback(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
- if (unlikely(req->ctx->drain_active) && io_drain_req(req))
- return;
-
- if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) {
- __io_queue_sqe(req);
- } else if (req->flags & REQ_F_FAIL) {
+ if (req->flags & REQ_F_FAIL) {
io_req_complete_fail_submit(req);
+ } else if (unlikely(req->ctx->drain_active)) {
+ io_drain_req(req);
} else {
int ret = io_req_prep_async(req);
@@ -7018,6 +6973,15 @@ static inline void io_queue_sqe(struct io_kiocb *req)
}
}
+static inline void io_queue_sqe(struct io_kiocb *req)
+ __must_hold(&req->ctx->uring_lock)
+{
+ if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))))
+ __io_queue_sqe(req);
+ else
+ io_queue_sqe_fallback(req);
+}
+
/*
* Check SQE restrictions (opcode and flags).
*
@@ -7027,9 +6991,6 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
struct io_kiocb *req,
unsigned int sqe_flags)
{
- if (likely(!ctx->restricted))
- return true;
-
if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
return false;
@@ -7044,16 +7005,35 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
return true;
}
+static void io_init_req_drain(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_kiocb *head = ctx->submit_state.link.head;
+
+ ctx->drain_active = true;
+ if (head) {
+ /*
+ * If we need to drain a request in the middle of a link, drain
+ * the head request and the next request/link after the current
+ * link. Considering sequential execution of links,
+ * IOSQE_IO_DRAIN will be maintained for every request of our
+ * link.
+ */
+ head->flags |= IOSQE_IO_DRAIN | REQ_F_FORCE_ASYNC;
+ ctx->drain_next = true;
+ }
+}
+
static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
- struct io_submit_state *state;
unsigned int sqe_flags;
- int personality, ret = 0;
+ int personality;
+ u8 opcode;
/* req is partially pre-initialised, see io_preinit_req() */
- req->opcode = READ_ONCE(sqe->opcode);
+ req->opcode = opcode = READ_ONCE(sqe->opcode);
/* same numerical values with corresponding REQ_F_*, safe to copy */
req->flags = sqe_flags = READ_ONCE(sqe->flags);
req->user_data = READ_ONCE(sqe->user_data);
@@ -7061,19 +7041,52 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
req->fixed_rsrc_refs = NULL;
req->task = current;
- /* enforce forwards compatibility on users */
- if (unlikely(sqe_flags & ~SQE_VALID_FLAGS))
- return -EINVAL;
- if (unlikely(req->opcode >= IORING_OP_LAST))
+ if (unlikely(opcode >= IORING_OP_LAST)) {
+ req->opcode = 0;
return -EINVAL;
- if (!io_check_restriction(ctx, req, sqe_flags))
- return -EACCES;
+ }
+ if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
+ /* enforce forwards compatibility on users */
+ if (sqe_flags & ~SQE_VALID_FLAGS)
+ return -EINVAL;
+ if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
+ !io_op_defs[opcode].buffer_select)
+ return -EOPNOTSUPP;
+ if (sqe_flags & IOSQE_IO_DRAIN)
+ io_init_req_drain(req);
+ }
+ if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
+ if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags))
+ return -EACCES;
+ /* knock it to the slow queue path, will be drained there */
+ if (ctx->drain_active)
+ req->flags |= REQ_F_FORCE_ASYNC;
+ /* if there is no link, we're at "next" request and need to drain */
+ if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) {
+ ctx->drain_next = false;
+ ctx->drain_active = true;
+ req->flags |= IOSQE_IO_DRAIN | REQ_F_FORCE_ASYNC;
+ }
+ }
- if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
- !io_op_defs[req->opcode].buffer_select)
- return -EOPNOTSUPP;
- if (unlikely(sqe_flags & IOSQE_IO_DRAIN))
- ctx->drain_active = true;
+ if (io_op_defs[opcode].needs_file) {
+ struct io_submit_state *state = &ctx->submit_state;
+
+ /*
+ * Plug now if we have more than 2 IO left after this, and the
+ * target is potentially a read/write to block based storage.
+ */
+ if (state->need_plug && io_op_defs[opcode].plug) {
+ state->plug_started = true;
+ state->need_plug = false;
+ blk_start_plug_nr_ios(&state->plug, state->submit_nr);
+ }
+
+ req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
+ (sqe_flags & IOSQE_FIXED_FILE));
+ if (unlikely(!req->file))
+ return -EBADF;
+ }
personality = READ_ONCE(sqe->personality);
if (personality) {
@@ -7083,27 +7096,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
get_cred(req->creds);
req->flags |= REQ_F_CREDS;
}
- state = &ctx->submit_state;
-
- /*
- * Plug now if we have more than 1 IO left after this, and the target
- * is potentially a read/write to block based storage.
- */
- if (!state->plug_started && state->ios_left > 1 &&
- io_op_defs[req->opcode].plug) {
- blk_start_plug(&state->plug);
- state->plug_started = true;
- }
-
- if (io_op_defs[req->opcode].needs_file) {
- req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
- (sqe_flags & IOSQE_FIXED_FILE));
- if (unlikely(!req->file))
- ret = -EBADF;
- }
- state->ios_left--;
- return ret;
+ return io_req_prep(req, sqe);
}
static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
@@ -7115,7 +7109,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
ret = io_init_req(ctx, req, sqe);
if (unlikely(ret)) {
-fail_req:
+ trace_io_uring_req_failed(sqe, ret);
+
/* fail even hard links since we don't submit */
if (link->head) {
/*
@@ -7138,10 +7133,6 @@ fail_req:
return ret;
}
req_fail_link_node(req, ret);
- } else {
- ret = io_req_prep(req, sqe);
- if (unlikely(ret))
- goto fail_req;
}
/* don't need @sqe from now on */
@@ -7171,33 +7162,32 @@ fail_req:
link->last->link = req;
link->last = req;
+ if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
+ return 0;
/* last request of a link, enqueue the link */
- if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) {
- link->head = NULL;
- io_queue_sqe(head);
- }
- } else {
- if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
- link->head = req;
- link->last = req;
- } else {
- io_queue_sqe(req);
- }
+ link->head = NULL;
+ req = head;
+ } else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
+ link->head = req;
+ link->last = req;
+ return 0;
}
+ io_queue_sqe(req);
return 0;
}
/*
* Batched submission is done, ensure local IO is flushed out.
*/
-static void io_submit_state_end(struct io_submit_state *state,
- struct io_ring_ctx *ctx)
+static void io_submit_state_end(struct io_ring_ctx *ctx)
{
+ struct io_submit_state *state = &ctx->submit_state;
+
if (state->link.head)
io_queue_sqe(state->link.head);
- if (state->compl_nr)
- io_submit_flush_completions(ctx);
+ /* flush only after queuing links as they can generate completions */
+ io_submit_flush_completions(ctx);
if (state->plug_started)
blk_finish_plug(&state->plug);
}
@@ -7209,7 +7199,8 @@ static void io_submit_state_start(struct io_submit_state *state,
unsigned int max_ios)
{
state->plug_started = false;
- state->ios_left = max_ios;
+ state->need_plug = max_ios > 2;
+ state->submit_nr = max_ios;
/* set only head, no need to init link_last in advance */
state->link.head = NULL;
}
@@ -7261,45 +7252,45 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
__must_hold(&ctx->uring_lock)
{
+ unsigned int entries = io_sqring_entries(ctx);
int submitted = 0;
+ if (unlikely(!entries))
+ return 0;
/* make sure SQ entry isn't read before tail */
- nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx));
- if (!percpu_ref_tryget_many(&ctx->refs, nr))
- return -EAGAIN;
+ nr = min3(nr, ctx->sq_entries, entries);
io_get_task_refs(nr);
io_submit_state_start(&ctx->submit_state, nr);
- while (submitted < nr) {
+ do {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
- req = io_alloc_req(ctx);
- if (unlikely(!req)) {
+ if (unlikely(!io_alloc_req_refill(ctx))) {
if (!submitted)
submitted = -EAGAIN;
break;
}
+ req = io_alloc_req(ctx);
sqe = io_get_sqe(ctx);
if (unlikely(!sqe)) {
- list_add(&req->inflight_entry, &ctx->submit_state.free_list);
+ wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
break;
}
/* will complete beyond this point, count as submitted */
submitted++;
if (io_submit_sqe(ctx, req, sqe))
break;
- }
+ } while (submitted < nr);
if (unlikely(submitted != nr)) {
int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
int unused = nr - ref_used;
current->io_uring->cached_refs += unused;
- percpu_ref_put_many(&ctx->refs, unused);
}
- io_submit_state_end(&ctx->submit_state, ctx);
+ io_submit_state_end(ctx);
/* Commit SQ ring head once we've consumed and submitted all SQEs */
io_commit_sqring(ctx);
@@ -7338,16 +7329,15 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE)
to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE;
- if (!list_empty(&ctx->iopoll_list) || to_submit) {
- unsigned nr_events = 0;
+ if (!wq_list_empty(&ctx->iopoll_list) || to_submit) {
const struct cred *creds = NULL;
if (ctx->sq_creds != current_cred())
creds = override_creds(ctx->sq_creds);
mutex_lock(&ctx->uring_lock);
- if (!list_empty(&ctx->iopoll_list))
- io_do_iopoll(ctx, &nr_events, 0);
+ if (!wq_list_empty(&ctx->iopoll_list))
+ io_do_iopoll(ctx, true);
/*
* Don't submit if refs are dying, good for io_uring_register(),
@@ -7367,7 +7357,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
return ret;
}
-static void io_sqd_update_thread_idle(struct io_sq_data *sqd)
+static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd)
{
struct io_ring_ctx *ctx;
unsigned sq_thread_idle = 0;
@@ -7424,7 +7414,7 @@ static int io_sq_thread(void *data)
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
int ret = __io_sq_thread(ctx, cap_entries);
- if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list)))
+ if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
sqt_spin = true;
}
if (io_run_task_work())
@@ -7445,7 +7435,7 @@ static int io_sq_thread(void *data)
io_ring_set_wakeup_flag(ctx);
if ((ctx->flags & IORING_SETUP_IOPOLL) &&
- !list_empty_careful(&ctx->iopoll_list)) {
+ !wq_list_empty(&ctx->iopoll_list)) {
needs_sched = false;
break;
}
@@ -7621,7 +7611,7 @@ static void io_free_page_table(void **table, size_t size)
kfree(table);
}
-static void **io_alloc_page_table(size_t size)
+static __cold void **io_alloc_page_table(size_t size)
{
unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE);
size_t init_size = size;
@@ -7650,7 +7640,7 @@ static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node)
kfree(ref_node);
}
-static void io_rsrc_node_ref_zero(struct percpu_ref *ref)
+static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref)
{
struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs);
struct io_ring_ctx *ctx = node->rsrc_data->ctx;
@@ -7696,10 +7686,13 @@ static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx)
static void io_rsrc_node_switch(struct io_ring_ctx *ctx,
struct io_rsrc_data *data_to_kill)
+ __must_hold(&ctx->uring_lock)
{
WARN_ON_ONCE(!ctx->rsrc_backup_node);
WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node);
+ io_rsrc_refs_drop(ctx);
+
if (data_to_kill) {
struct io_rsrc_node *rsrc_node = ctx->rsrc_node;
@@ -7727,7 +7720,8 @@ static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx)
return ctx->rsrc_backup_node ? 0 : -ENOMEM;
}
-static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx)
+static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
+ struct io_ring_ctx *ctx)
{
int ret;
@@ -7783,9 +7777,9 @@ static void io_rsrc_data_free(struct io_rsrc_data *data)
kfree(data);
}
-static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put,
- u64 __user *utags, unsigned nr,
- struct io_rsrc_data **pdata)
+static __cold int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put,
+ u64 __user *utags, unsigned nr,
+ struct io_rsrc_data **pdata)
{
struct io_rsrc_data *data;
int ret = -ENOMEM;
@@ -8353,12 +8347,12 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
unsigned int issue_flags, u32 slot_index)
{
struct io_ring_ctx *ctx = req->ctx;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
bool needs_switch = false;
struct io_fixed_file *file_slot;
int ret = -EBADF;
- io_ring_submit_lock(ctx, !force_nonblock);
+ io_ring_submit_lock(ctx, needs_lock);
if (file->f_op == &io_uring_fops)
goto err;
ret = -ENXIO;
@@ -8399,7 +8393,7 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
err:
if (needs_switch)
io_rsrc_node_switch(ctx, ctx->file_data);
- io_ring_submit_unlock(ctx, !force_nonblock);
+ io_ring_submit_unlock(ctx, needs_lock);
if (ret)
fput(file);
return ret;
@@ -8409,11 +8403,12 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
{
unsigned int offset = req->close.file_slot - 1;
struct io_ring_ctx *ctx = req->ctx;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_fixed_file *file_slot;
struct file *file;
int ret, i;
- io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_lock(ctx, needs_lock);
ret = -ENXIO;
if (unlikely(!ctx->file_data))
goto out;
@@ -8439,7 +8434,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
io_rsrc_node_switch(ctx, ctx->file_data);
ret = 0;
out:
- io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_unlock(ctx, needs_lock);
return ret;
}
@@ -8555,8 +8550,8 @@ static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
return io_wq_create(concurrency, &data);
}
-static int io_uring_alloc_task_context(struct task_struct *task,
- struct io_ring_ctx *ctx)
+static __cold int io_uring_alloc_task_context(struct task_struct *task,
+ struct io_ring_ctx *ctx)
{
struct io_uring_task *tctx;
int ret;
@@ -8603,8 +8598,8 @@ void __io_uring_free(struct task_struct *tsk)
tsk->io_uring = NULL;
}
-static int io_sq_offload_create(struct io_ring_ctx *ctx,
- struct io_uring_params *p)
+static __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
{
int ret;
@@ -9215,29 +9210,25 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx)
}
}
-static void io_req_cache_free(struct list_head *list)
-{
- struct io_kiocb *req, *nxt;
-
- list_for_each_entry_safe(req, nxt, list, inflight_entry) {
- list_del(&req->inflight_entry);
- kmem_cache_free(req_cachep, req);
- }
-}
-
static void io_req_caches_free(struct io_ring_ctx *ctx)
{
struct io_submit_state *state = &ctx->submit_state;
+ int nr = 0;
mutex_lock(&ctx->uring_lock);
+ io_flush_cached_locked_reqs(ctx, state);
- if (state->free_reqs) {
- kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs);
- state->free_reqs = 0;
- }
+ while (state->free_list.next) {
+ struct io_wq_work_node *node;
+ struct io_kiocb *req;
- io_flush_cached_locked_reqs(ctx, state);
- io_req_cache_free(&state->free_list);
+ node = wq_stack_extract(&state->free_list);
+ req = container_of(node, struct io_kiocb, comp_list);
+ kmem_cache_free(req_cachep, req);
+ nr++;
+ }
+ if (nr)
+ percpu_ref_put_many(&ctx->refs, nr);
mutex_unlock(&ctx->uring_lock);
}
@@ -9247,7 +9238,7 @@ static void io_wait_rsrc_data(struct io_rsrc_data *data)
wait_for_completion(&data->done);
}
-static void io_ring_ctx_free(struct io_ring_ctx *ctx)
+static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
io_sq_thread_finish(ctx);
@@ -9256,6 +9247,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
ctx->mm_account = NULL;
}
+ io_rsrc_refs_drop(ctx);
/* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */
io_wait_rsrc_data(ctx->buf_data);
io_wait_rsrc_data(ctx->file_data);
@@ -9279,6 +9271,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
if (ctx->rsrc_backup_node)
io_rsrc_node_destroy(ctx->rsrc_backup_node);
flush_delayed_work(&ctx->rsrc_put_work);
+ flush_delayed_work(&ctx->fallback_work);
WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist));
@@ -9309,7 +9302,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
struct io_ring_ctx *ctx = file->private_data;
__poll_t mask = 0;
- poll_wait(file, &ctx->poll_wait, wait);
+ poll_wait(file, &ctx->cq_wait, wait);
/*
* synchronizes with barrier from wq_has_sleeper call in
* io_commit_cqring
@@ -9356,7 +9349,7 @@ struct io_tctx_exit {
struct io_ring_ctx *ctx;
};
-static void io_tctx_exit_cb(struct callback_head *cb)
+static __cold void io_tctx_exit_cb(struct callback_head *cb)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_exit *work;
@@ -9371,14 +9364,14 @@ static void io_tctx_exit_cb(struct callback_head *cb)
complete(&work->completion);
}
-static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
return req->ctx == data;
}
-static void io_ring_exit_work(struct work_struct *work)
+static __cold void io_ring_exit_work(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
unsigned long timeout = jiffies + HZ * 60 * 5;
@@ -9407,6 +9400,8 @@ static void io_ring_exit_work(struct work_struct *work)
io_sq_thread_unpark(sqd);
}
+ io_req_caches_free(ctx);
+
if (WARN_ON_ONCE(time_after(jiffies, timeout))) {
/* there is little hope left, don't run it too often */
interval = HZ * 60;
@@ -9433,7 +9428,6 @@ static void io_ring_exit_work(struct work_struct *work)
ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
if (WARN_ON_ONCE(ret))
continue;
- wake_up_process(node->task);
mutex_unlock(&ctx->uring_lock);
wait_for_completion(&exit.completion);
@@ -9447,8 +9441,8 @@ static void io_ring_exit_work(struct work_struct *work)
}
/* Returns true if we found and killed one or more timeouts */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
- bool cancel_all)
+static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx,
+ struct task_struct *tsk, bool cancel_all)
{
struct io_kiocb *req, *tmp;
int canceled = 0;
@@ -9470,7 +9464,7 @@ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
return canceled != 0;
}
-static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
+static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
unsigned long index;
struct creds *creds;
@@ -9532,8 +9526,9 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
return ret;
}
-static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
- struct task_struct *task, bool cancel_all)
+static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
+ struct task_struct *task,
+ bool cancel_all)
{
struct io_defer_entry *de;
LIST_HEAD(list);
@@ -9558,7 +9553,7 @@ static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
return true;
}
-static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
+static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
{
struct io_tctx_node *node;
enum io_wq_cancel cret;
@@ -9582,9 +9577,9 @@ static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
return ret;
}
-static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
- struct task_struct *task,
- bool cancel_all)
+static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
+ struct task_struct *task,
+ bool cancel_all)
{
struct io_task_cancel cancel = { .task = task, .all = cancel_all, };
struct io_uring_task *tctx = task ? task->io_uring : NULL;
@@ -9608,7 +9603,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
/* SQPOLL thread does its own polling */
if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) ||
(ctx->sq_data && ctx->sq_data->thread == current)) {
- while (!list_empty_careful(&ctx->iopoll_list)) {
+ while (!wq_list_empty(&ctx->iopoll_list)) {
io_iopoll_try_reap_events(ctx);
ret = true;
}
@@ -9683,7 +9678,7 @@ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx)
/*
* Remove this io_uring_file -> task mapping.
*/
-static void io_uring_del_tctx_node(unsigned long index)
+static __cold void io_uring_del_tctx_node(unsigned long index)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_node *node;
@@ -9706,7 +9701,7 @@ static void io_uring_del_tctx_node(unsigned long index)
kfree(node);
}
-static void io_uring_clean_tctx(struct io_uring_task *tctx)
+static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
{
struct io_wq *wq = tctx->io_wq;
struct io_tctx_node *node;
@@ -9733,7 +9728,7 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
return percpu_counter_sum(&tctx->inflight);
}
-static void io_uring_drop_tctx_refs(struct task_struct *task)
+static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
{
struct io_uring_task *tctx = task->io_uring;
unsigned int refs = tctx->cached_refs;
@@ -9749,7 +9744,8 @@ static void io_uring_drop_tctx_refs(struct task_struct *task)
* Find any io_uring ctx that this task has registered or done IO on, and cancel
* requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
*/
-static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
+static __cold void io_uring_cancel_generic(bool cancel_all,
+ struct io_sq_data *sqd)
{
struct io_uring_task *tctx = current->io_uring;
struct io_ring_ctx *ctx;
@@ -9842,7 +9838,7 @@ static void *io_uring_validate_mmap_request(struct file *file,
#ifdef CONFIG_MMU
-static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
{
size_t sz = vma->vm_end - vma->vm_start;
unsigned long pfn;
@@ -10027,7 +10023,7 @@ out_fput:
}
#ifdef CONFIG_PROC_FS
-static int io_uring_show_cred(struct seq_file *m, unsigned int id,
+static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
const struct cred *cred)
{
struct user_namespace *uns = seq_user_ns(m);
@@ -10059,11 +10055,59 @@ static int io_uring_show_cred(struct seq_file *m, unsigned int id,
return 0;
}
-static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
+static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
+ struct seq_file *m)
{
struct io_sq_data *sq = NULL;
+ struct io_overflow_cqe *ocqe;
+ struct io_rings *r = ctx->rings;
+ unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
+ unsigned int sq_head = READ_ONCE(r->sq.head);
+ unsigned int sq_tail = READ_ONCE(r->sq.tail);
+ unsigned int cq_head = READ_ONCE(r->cq.head);
+ unsigned int cq_tail = READ_ONCE(r->cq.tail);
+ unsigned int sq_entries, cq_entries;
bool has_lock;
- int i;
+ unsigned int i;
+
+ /*
+ * we may get imprecise sqe and cqe info if uring is actively running
+ * since we get cached_sq_head and cached_cq_tail without uring_lock
+ * and sq_tail and cq_head are changed by userspace. But it's ok since
+ * we usually use these info when it is stuck.
+ */
+ seq_printf(m, "SqMask:\t\t0x%x\n", sq_mask);
+ seq_printf(m, "SqHead:\t%u\n", sq_head);
+ seq_printf(m, "SqTail:\t%u\n", sq_tail);
+ seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
+ seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
+ seq_printf(m, "CqHead:\t%u\n", cq_head);
+ seq_printf(m, "CqTail:\t%u\n", cq_tail);
+ seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
+ seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head);
+ sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
+ for (i = 0; i < sq_entries; i++) {
+ unsigned int entry = i + sq_head;
+ unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
+ struct io_uring_sqe *sqe = &ctx->sq_sqes[sq_idx];
+
+ if (sq_idx > sq_mask)
+ continue;
+ sqe = &ctx->sq_sqes[sq_idx];
+ seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n",
+ sq_idx, sqe->opcode, sqe->fd, sqe->flags,
+ sqe->user_data);
+ }
+ seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
+ cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
+ for (i = 0; i < cq_entries; i++) {
+ unsigned int entry = i + cq_head;
+ struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask];
+
+ seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
+ entry & cq_mask, cqe->user_data, cqe->res,
+ cqe->flags);
+ }
/*
* Avoid ABBA deadlock between the seq lock and the io_uring mutex,
@@ -10105,7 +10149,10 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
xa_for_each(&ctx->personalities, index, cred)
io_uring_show_cred(m, index, cred);
}
- seq_printf(m, "PollList:\n");
+ if (has_lock)
+ mutex_unlock(&ctx->uring_lock);
+
+ seq_puts(m, "PollList:\n");
spin_lock(&ctx->completion_lock);
for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
struct hlist_head *list = &ctx->cancel_hash[i];
@@ -10115,12 +10162,20 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
req->task->task_works != NULL);
}
+
+ seq_puts(m, "CqOverflowList:\n");
+ list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
+ struct io_uring_cqe *cqe = &ocqe->cqe;
+
+ seq_printf(m, " user_data=%llu, res=%d, flags=%x\n",
+ cqe->user_data, cqe->res, cqe->flags);
+
+ }
+
spin_unlock(&ctx->completion_lock);
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
}
-static void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
+static __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
{
struct io_ring_ctx *ctx = f->private_data;
@@ -10144,8 +10199,8 @@ static const struct file_operations io_uring_fops = {
#endif
};
-static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
- struct io_uring_params *p)
+static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
{
struct io_rings *rings;
size_t size, sq_array_offset;
@@ -10234,8 +10289,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
return file;
}
-static int io_uring_create(unsigned entries, struct io_uring_params *p,
- struct io_uring_params __user *params)
+static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
+ struct io_uring_params __user *params)
{
struct io_ring_ctx *ctx;
struct file *file;
@@ -10393,7 +10448,8 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
return io_uring_setup(entries, params);
}
-static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
+static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
{
struct io_uring_probe *p;
size_t size;
@@ -10449,8 +10505,8 @@ static int io_register_personality(struct io_ring_ctx *ctx)
return id;
}
-static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int nr_args)
+static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
+ void __user *arg, unsigned int nr_args)
{
struct io_uring_restriction *res;
size_t size;
@@ -10584,7 +10640,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
return __io_register_rsrc_update(ctx, type, &up, up.nr);
}
-static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
+static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
unsigned int size, unsigned int type)
{
struct io_uring_rsrc_register rr;
@@ -10610,8 +10666,8 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
return -EINVAL;
}
-static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg,
- unsigned len)
+static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
+ void __user *arg, unsigned len)
{
struct io_uring_task *tctx = current->io_uring;
cpumask_var_t new_mask;
@@ -10637,7 +10693,7 @@ static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg,
return ret;
}
-static int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
+static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
{
struct io_uring_task *tctx = current->io_uring;
@@ -10647,8 +10703,8 @@ static int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
return io_wq_cpu_affinity(tctx->io_wq, NULL);
}
-static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
- void __user *arg)
+static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
+ void __user *arg)
__must_hold(&ctx->uring_lock)
{
struct io_tctx_node *node;
@@ -10753,7 +10809,7 @@ static bool io_register_op_must_quiesce(int op)
}
}
-static int io_ctx_quiesce(struct io_ring_ctx *ctx)
+static __cold int io_ctx_quiesce(struct io_ring_ctx *ctx)
{
long ret;
@@ -10768,10 +10824,14 @@ static int io_ctx_quiesce(struct io_ring_ctx *ctx)
*/
mutex_unlock(&ctx->uring_lock);
do {
- ret = wait_for_completion_interruptible(&ctx->ref_comp);
- if (!ret)
+ ret = wait_for_completion_interruptible_timeout(&ctx->ref_comp, HZ);
+ if (ret) {
+ ret = min(0L, ret);
break;
+ }
+
ret = io_run_task_work_sig();
+ io_req_caches_free(ctx);
} while (ret >= 0);
mutex_lock(&ctx->uring_lock);
@@ -11002,6 +11062,8 @@ static int __init io_uring_init(void)
/* should fit into one byte */
BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
+ BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8));
+ BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS);
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 4ecd255e0511..811c898125a5 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -38,8 +38,7 @@ struct iomap_dio {
struct {
struct iov_iter *iter;
struct task_struct *waiter;
- struct request_queue *last_queue;
- blk_qc_t cookie;
+ struct bio *poll_bio;
} submit;
/* used for aio completion: */
@@ -49,29 +48,20 @@ struct iomap_dio {
};
};
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
-{
- struct request_queue *q = READ_ONCE(kiocb->private);
-
- if (!q)
- return 0;
- return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
-}
-EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
-
static void iomap_dio_submit_bio(const struct iomap_iter *iter,
struct iomap_dio *dio, struct bio *bio, loff_t pos)
{
atomic_inc(&dio->ref);
- if (dio->iocb->ki_flags & IOCB_HIPRI)
+ if (dio->iocb->ki_flags & IOCB_HIPRI) {
bio_set_polled(bio, dio->iocb);
+ dio->submit.poll_bio = bio;
+ }
- dio->submit.last_queue = bdev_get_queue(iter->iomap.bdev);
if (dio->dops && dio->dops->submit_io)
- dio->submit.cookie = dio->dops->submit_io(iter, bio, pos);
+ dio->dops->submit_io(iter, bio, pos);
else
- dio->submit.cookie = submit_bio(bio);
+ submit_bio(bio);
}
ssize_t iomap_dio_complete(struct iomap_dio *dio)
@@ -135,7 +125,7 @@ static void iomap_dio_complete_work(struct work_struct *work)
struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
struct kiocb *iocb = dio->iocb;
- iocb->ki_complete(iocb, iomap_dio_complete(dio), 0);
+ iocb->ki_complete(iocb, iomap_dio_complete(dio));
}
/*
@@ -164,9 +154,11 @@ static void iomap_dio_bio_end_io(struct bio *bio)
} else if (dio->flags & IOMAP_DIO_WRITE) {
struct inode *inode = file_inode(dio->iocb->ki_filp);
+ WRITE_ONCE(dio->iocb->private, NULL);
INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work);
} else {
+ WRITE_ONCE(dio->iocb->private, NULL);
iomap_dio_complete_work(&dio->aio.work);
}
}
@@ -282,6 +274,13 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
if (!iov_iter_count(dio->submit.iter))
goto out;
+ /*
+ * We can only poll for single bio I/Os.
+ */
+ if (need_zeroout ||
+ ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode)))
+ dio->iocb->ki_flags &= ~IOCB_HIPRI;
+
if (need_zeroout) {
/* zero out from the start of the block to the write offset */
pad = pos & (fs_block_size - 1);
@@ -339,6 +338,11 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter,
BIO_MAX_VECS);
+ /*
+ * We can only poll for single bio I/Os.
+ */
+ if (nr_pages)
+ dio->iocb->ki_flags &= ~IOCB_HIPRI;
iomap_dio_submit_bio(iter, dio, bio, pos);
pos += n;
} while (nr_pages);
@@ -485,8 +489,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio->submit.iter = iter;
dio->submit.waiter = current;
- dio->submit.cookie = BLK_QC_T_NONE;
- dio->submit.last_queue = NULL;
+ dio->submit.poll_bio = NULL;
if (iov_iter_rw(iter) == READ) {
if (iomi.pos >= dio->i_size)
@@ -565,8 +568,15 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
inode_dio_begin(inode);
blk_start_plug(&plug);
- while ((ret = iomap_iter(&iomi, ops)) > 0)
+ while ((ret = iomap_iter(&iomi, ops)) > 0) {
iomi.processed = iomap_dio_iter(&iomi, dio);
+
+ /*
+ * We can only poll for single bio I/Os.
+ */
+ iocb->ki_flags &= ~IOCB_HIPRI;
+ }
+
blk_finish_plug(&plug);
/*
@@ -592,8 +602,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;
- WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie);
- WRITE_ONCE(iocb->private, dio->submit.last_queue);
+ WRITE_ONCE(iocb->private, dio->submit.poll_bio);
/*
* We are about to drop our additional submission reference, which
@@ -620,10 +629,8 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (!READ_ONCE(dio->submit.waiter))
break;
- if (!(iocb->ki_flags & IOCB_HIPRI) ||
- !dio->submit.last_queue ||
- !blk_poll(dio->submit.last_queue,
- dio->submit.cookie, true))
+ if (!dio->submit.poll_bio ||
+ !bio_poll(dio->submit.poll_bio, NULL, 0))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 176580f54af9..104ae698443e 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -13,6 +13,7 @@
#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/seq_file.h>
+#include <linux/writeback.h>
#include "jfs_incore.h"
#include "jfs_superblock.h"
#include "jfs_filsys.h"
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index bde787c354fc..8b9a72ae5efa 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -86,8 +86,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
goto out;
}
- VolumeSize = i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits;
-
+ VolumeSize = sb_bdev_nr_blocks(sb);
if (VolumeSize) {
if (newLVSize > VolumeSize) {
printk(KERN_WARNING "jfs_extendfs: invalid size\n");
@@ -199,7 +198,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
txQuiesce(sb);
/* Reset size of direct inode */
- sbi->direct_inode->i_size = i_size_read(sb->s_bdev->bd_inode);
+ sbi->direct_inode->i_size = bdev_nr_bytes(sb->s_bdev);
if (sbi->mntflag & JFS_INLINELOG) {
/*
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 9030aeaf0f88..24cbc9946e01 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -284,8 +284,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
}
case Opt_resize_nosize:
{
- *newLVSize = i_size_read(sb->s_bdev->bd_inode) >>
- sb->s_blocksize_bits;
+ *newLVSize = sb_bdev_nr_blocks(sb);
if (*newLVSize == 0)
pr_err("JFS: Cannot determine volume size\n");
break;
@@ -551,7 +550,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
ret = -ENOMEM;
goto out_unload;
}
- inode->i_size = i_size_read(sb->s_bdev->bd_inode);
+ inode->i_size = bdev_nr_bytes(sb->s_bdev);
inode->i_mapping->a_ops = &jfs_metapage_aops;
inode_fake_hash(inode);
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
diff --git a/fs/locks.c b/fs/locks.c
index 3d6fb4ae847b..0fca9d680978 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2,117 +2,11 @@
/*
* linux/fs/locks.c
*
- * Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls.
- * Doug Evans (dje@spiff.uucp), August 07, 1992
+ * We implement four types of file locks: BSD locks, posix locks, open
+ * file description locks, and leases. For details about BSD locks,
+ * see the flock(2) man page; for details about the other three, see
+ * fcntl(2).
*
- * Deadlock detection added.
- * FIXME: one thing isn't handled yet:
- * - mandatory locks (requires lots of changes elsewhere)
- * Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994.
- *
- * Miscellaneous edits, and a total rewrite of posix_lock_file() code.
- * Kai Petzke (wpp@marie.physik.tu-berlin.de), 1994
- *
- * Converted file_lock_table to a linked list from an array, which eliminates
- * the limits on how many active file locks are open.
- * Chad Page (pageone@netcom.com), November 27, 1994
- *
- * Removed dependency on file descriptors. dup()'ed file descriptors now
- * get the same locks as the original file descriptors, and a close() on
- * any file descriptor removes ALL the locks on the file for the current
- * process. Since locks still depend on the process id, locks are inherited
- * after an exec() but not after a fork(). This agrees with POSIX, and both
- * BSD and SVR4 practice.
- * Andy Walker (andy@lysaker.kvaerner.no), February 14, 1995
- *
- * Scrapped free list which is redundant now that we allocate locks
- * dynamically with kmalloc()/kfree().
- * Andy Walker (andy@lysaker.kvaerner.no), February 21, 1995
- *
- * Implemented two lock personalities - FL_FLOCK and FL_POSIX.
- *
- * FL_POSIX locks are created with calls to fcntl() and lockf() through the
- * fcntl() system call. They have the semantics described above.
- *
- * FL_FLOCK locks are created with calls to flock(), through the flock()
- * system call, which is new. Old C libraries implement flock() via fcntl()
- * and will continue to use the old, broken implementation.
- *
- * FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated
- * with a file pointer (filp). As a result they can be shared by a parent
- * process and its children after a fork(). They are removed when the last
- * file descriptor referring to the file pointer is closed (unless explicitly
- * unlocked).
- *
- * FL_FLOCK locks never deadlock, an existing lock is always removed before
- * upgrading from shared to exclusive (or vice versa). When this happens
- * any processes blocked by the current lock are woken up and allowed to
- * run before the new lock is applied.
- * Andy Walker (andy@lysaker.kvaerner.no), June 09, 1995
- *
- * Removed some race conditions in flock_lock_file(), marked other possible
- * races. Just grep for FIXME to see them.
- * Dmitry Gorodchanin (pgmdsg@ibi.com), February 09, 1996.
- *
- * Addressed Dmitry's concerns. Deadlock checking no longer recursive.
- * Lock allocation changed to GFP_ATOMIC as we can't afford to sleep
- * once we've checked for blocking and deadlocking.
- * Andy Walker (andy@lysaker.kvaerner.no), April 03, 1996.
- *
- * Initial implementation of mandatory locks. SunOS turned out to be
- * a rotten model, so I implemented the "obvious" semantics.
- * See 'Documentation/filesystems/mandatory-locking.rst' for details.
- * Andy Walker (andy@lysaker.kvaerner.no), April 06, 1996.
- *
- * Don't allow mandatory locks on mmap()'ed files. Added simple functions to
- * check if a file has mandatory locks, used by mmap(), open() and creat() to
- * see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference
- * Manual, Section 2.
- * Andy Walker (andy@lysaker.kvaerner.no), April 09, 1996.
- *
- * Tidied up block list handling. Added '/proc/locks' interface.
- * Andy Walker (andy@lysaker.kvaerner.no), April 24, 1996.
- *
- * Fixed deadlock condition for pathological code that mixes calls to
- * flock() and fcntl().
- * Andy Walker (andy@lysaker.kvaerner.no), April 29, 1996.
- *
- * Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use
- * for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to
- * guarantee sensible behaviour in the case where file system modules might
- * be compiled with different options than the kernel itself.
- * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996.
- *
- * Added a couple of missing wake_up() calls. Thanks to Thomas Meckel
- * (Thomas.Meckel@mni.fh-giessen.de) for spotting this.
- * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996.
- *
- * Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK
- * locks. Changed process synchronisation to avoid dereferencing locks that
- * have already been freed.
- * Andy Walker (andy@lysaker.kvaerner.no), Sep 21, 1996.
- *
- * Made the block list a circular list to minimise searching in the list.
- * Andy Walker (andy@lysaker.kvaerner.no), Sep 25, 1996.
- *
- * Made mandatory locking a mount option. Default is not to allow mandatory
- * locking.
- * Andy Walker (andy@lysaker.kvaerner.no), Oct 04, 1996.
- *
- * Some adaptations for NFS support.
- * Olaf Kirch (okir@monad.swb.de), Dec 1996,
- *
- * Fixed /proc/locks interface so that we can't overrun the buffer we are handed.
- * Andy Walker (andy@lysaker.kvaerner.no), May 12, 1997.
- *
- * Use slab allocator instead of kmalloc/kfree.
- * Use generic list implementation from <linux/list.h>.
- * Sped up posix_locks_deadlock by only considering blocked locks.
- * Matthew Wilcox <willy@debian.org>, March, 2000.
- *
- * Leases and LOCK_MAND
- * Matthew Wilcox <willy@debian.org>, June, 2000.
- * Stephen Rothwell <sfr@canb.auug.org.au>, June, 2000.
*
* Locking conflicts and dependencies:
* If multiple threads attempt to lock the same byte (or flock the same file)
@@ -461,8 +355,6 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
}
static inline int flock_translate_cmd(int cmd) {
- if (cmd & LOCK_MAND)
- return cmd & (LOCK_MAND | LOCK_RW);
switch (cmd) {
case LOCK_SH:
return F_RDLCK;
@@ -942,8 +834,6 @@ static bool flock_locks_conflict(struct file_lock *caller_fl,
*/
if (caller_fl->fl_file == sys_fl->fl_file)
return false;
- if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND))
- return false;
return locks_conflict(caller_fl, sys_fl);
}
@@ -2116,11 +2006,9 @@ EXPORT_SYMBOL(locks_lock_inode_wait);
* - %LOCK_SH -- a shared lock.
* - %LOCK_EX -- an exclusive lock.
* - %LOCK_UN -- remove an existing lock.
- * - %LOCK_MAND -- a 'mandatory' flock.
- * This exists to emulate Windows Share Modes.
+ * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED)
*
- * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other
- * processes read and write access respectively.
+ * %LOCK_MAND support has been removed from the kernel.
*/
SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
{
@@ -2137,9 +2025,22 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
cmd &= ~LOCK_NB;
unlock = (cmd == LOCK_UN);
- if (!unlock && !(cmd & LOCK_MAND) &&
- !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
+ if (!unlock && !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
+ goto out_putf;
+
+ /*
+ * LOCK_MAND locks were broken for a long time in that they never
+ * conflicted with one another and didn't prevent any sort of open,
+ * read or write activity.
+ *
+ * Just ignore these requests now, to preserve legacy behavior, but
+ * throw a warning to let people know that they don't actually work.
+ */
+ if (cmd & LOCK_MAND) {
+ pr_warn_once("Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n");
+ error = 0;
goto out_putf;
+ }
lock = flock_make_lock(f.file, cmd, NULL);
if (IS_ERR(lock)) {
@@ -2718,6 +2619,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
struct inode *inode = NULL;
unsigned int fl_pid;
struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
+ int type;
fl_pid = locks_translate_pid(fl, proc_pidns);
/*
@@ -2745,11 +2647,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
seq_printf(f, " %s ",
(inode == NULL) ? "*NOINODE*" : "ADVISORY ");
} else if (IS_FLOCK(fl)) {
- if (fl->fl_type & LOCK_MAND) {
- seq_puts(f, "FLOCK MSNFS ");
- } else {
- seq_puts(f, "FLOCK ADVISORY ");
- }
+ seq_puts(f, "FLOCK ADVISORY ");
} else if (IS_LEASE(fl)) {
if (fl->fl_flags & FL_DELEG)
seq_puts(f, "DELEG ");
@@ -2765,17 +2663,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
} else {
seq_puts(f, "UNKNOWN UNKNOWN ");
}
- if (fl->fl_type & LOCK_MAND) {
- seq_printf(f, "%s ",
- (fl->fl_type & LOCK_READ)
- ? (fl->fl_type & LOCK_WRITE) ? "RW " : "READ "
- : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE ");
- } else {
- int type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;
+ type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;
- seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
- (type == F_RDLCK) ? "READ" : "UNLCK");
- }
+ seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
+ (type == F_RDLCK) ? "READ" : "UNLCK");
if (inode) {
/* userspace relies on this representation of dev_t */
seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
diff --git a/fs/namei.c b/fs/namei.c
index 1946d9667790..1f9d2187c765 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3076,9 +3076,7 @@ static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp)
int error = get_write_access(inode);
if (error)
return error;
- /*
- * Refuse to truncate files with mandatory locks held on them.
- */
+
error = security_path_truncate(path);
if (!error) {
error = do_truncate(mnt_userns, path->dentry, 0,
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index acb1d22907da..5e56da748b2a 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -252,7 +252,7 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
d->bdev = bdev;
- d->len = i_size_read(d->bdev->bd_inode);
+ d->len = bdev_nr_bytes(d->bdev);
d->map = bl_map_simple;
printk(KERN_INFO "pNFS: using block device %s\n",
@@ -367,7 +367,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
return PTR_ERR(bdev);
d->bdev = bdev;
- d->len = i_size_read(d->bdev->bd_inode);
+ d->len = bdev_nr_bytes(d->bdev);
d->map = bl_map_simple;
d->pr_key = v->scsi.pr_key;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 2e894fec036b..7a5f287c5391 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -275,7 +275,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
res = (long) dreq->count;
WARN_ON_ONCE(dreq->count < 0);
}
- dreq->iocb->ki_complete(dreq->iocb, res, 0);
+ dreq->iocb->ki_complete(dreq->iocb, res);
}
complete(&dreq->completion);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index aa353fd58240..24e7dccce355 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -843,15 +843,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- /*
- * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of
- * any standard. In principle we might be able to support LOCK_MAND
- * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the
- * NFS code is not set up for it.
- */
- if (fl->fl_type & LOCK_MAND)
- return -EINVAL;
-
if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
is_local = 1;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 6e9ea4ee0f73..3d1d17256a91 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -109,7 +109,6 @@ config NFSD_SCSILAYOUT
depends on NFSD_V4 && BLOCK
select NFSD_PNFS
select EXPORTFS_BLOCK_OPS
- select SCSI_COMMON
help
This option enables support for the exporting pNFS SCSI layouts
in the kernel's NFS server. The pNFS SCSI layout enables NFS
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index c99dee99a3c1..e5c0982a381d 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -9,9 +9,6 @@
#include <linux/pr.h>
#include <linux/nfsd/debug.h>
-#include <scsi/scsi_proto.h>
-#include <scsi/scsi_common.h>
-#include <scsi/scsi_request.h>
#include "blocklayoutxdr.h"
#include "pnfs.h"
@@ -211,109 +208,6 @@ const struct nfsd4_layout_ops bl_layout_ops = {
#endif /* CONFIG_NFSD_BLOCKLAYOUT */
#ifdef CONFIG_NFSD_SCSILAYOUT
-static int nfsd4_scsi_identify_device(struct block_device *bdev,
- struct pnfs_block_volume *b)
-{
- struct request_queue *q = bdev->bd_disk->queue;
- struct request *rq;
- struct scsi_request *req;
- /*
- * The allocation length (passed in bytes 3 and 4 of the INQUIRY
- * command descriptor block) specifies the number of bytes that have
- * been allocated for the data-in buffer.
- * 252 is the highest one-byte value that is a multiple of 4.
- * 65532 is the highest two-byte value that is a multiple of 4.
- */
- size_t bufflen = 252, maxlen = 65532, len, id_len;
- u8 *buf, *d, type, assoc;
- int retries = 1, error;
-
- if (WARN_ON_ONCE(!blk_queue_scsi_passthrough(q)))
- return -EINVAL;
-
-again:
- buf = kzalloc(bufflen, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- rq = blk_get_request(q, REQ_OP_DRV_IN, 0);
- if (IS_ERR(rq)) {
- error = -ENOMEM;
- goto out_free_buf;
- }
- req = scsi_req(rq);
-
- error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
- if (error)
- goto out_put_request;
-
- req->cmd[0] = INQUIRY;
- req->cmd[1] = 1;
- req->cmd[2] = 0x83;
- req->cmd[3] = bufflen >> 8;
- req->cmd[4] = bufflen & 0xff;
- req->cmd_len = COMMAND_SIZE(INQUIRY);
-
- blk_execute_rq(NULL, rq, 1);
- if (req->result) {
- pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
- req->result);
- error = -EIO;
- goto out_put_request;
- }
-
- len = (buf[2] << 8) + buf[3] + 4;
- if (len > bufflen) {
- if (len <= maxlen && retries--) {
- blk_put_request(rq);
- kfree(buf);
- bufflen = len;
- goto again;
- }
- pr_err("pNFS: INQUIRY 0x83 response invalid (len = %zd)\n",
- len);
- goto out_put_request;
- }
-
- d = buf + 4;
- for (d = buf + 4; d < buf + len; d += id_len + 4) {
- id_len = d[3];
- type = d[1] & 0xf;
- assoc = (d[1] >> 4) & 0x3;
-
- /*
- * We only care about a EUI-64 and NAA designator types
- * with LU association.
- */
- if (assoc != 0x00)
- continue;
- if (type != 0x02 && type != 0x03)
- continue;
- if (id_len != 8 && id_len != 12 && id_len != 16)
- continue;
-
- b->scsi.code_set = PS_CODE_SET_BINARY;
- b->scsi.designator_type = type == 0x02 ?
- PS_DESIGNATOR_EUI64 : PS_DESIGNATOR_NAA;
- b->scsi.designator_len = id_len;
- memcpy(b->scsi.designator, d + 4, id_len);
-
- /*
- * If we found a 8 or 12 byte descriptor continue on to
- * see if a 16 byte one is available. If we find a
- * 16 byte descriptor we're done.
- */
- if (id_len == 16)
- break;
- }
-
-out_put_request:
- blk_put_request(rq);
-out_free_buf:
- kfree(buf);
- return error;
-}
-
#define NFSD_MDS_PR_KEY 0x0100000000000000ULL
/*
@@ -325,6 +219,31 @@ static u64 nfsd4_scsi_pr_key(struct nfs4_client *clp)
return ((u64)clp->cl_clientid.cl_boot << 32) | clp->cl_clientid.cl_id;
}
+static const u8 designator_types[] = {
+ PS_DESIGNATOR_EUI64,
+ PS_DESIGNATOR_NAA,
+};
+
+static int
+nfsd4_block_get_unique_id(struct gendisk *disk, struct pnfs_block_volume *b)
+{
+ int ret, i;
+
+ for (i = 0; i < ARRAY_SIZE(designator_types); i++) {
+ u8 type = designator_types[i];
+
+ ret = disk->fops->get_unique_id(disk, b->scsi.designator, type);
+ if (ret > 0) {
+ b->scsi.code_set = PS_CODE_SET_BINARY;
+ b->scsi.designator_type = type;
+ b->scsi.designator_len = ret;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
+
static int
nfsd4_block_get_device_info_scsi(struct super_block *sb,
struct nfs4_client *clp,
@@ -333,7 +252,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb,
struct pnfs_block_deviceaddr *dev;
struct pnfs_block_volume *b;
const struct pr_ops *ops;
- int error;
+ int ret;
dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
sizeof(struct pnfs_block_volume), GFP_KERNEL);
@@ -347,33 +266,38 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb,
b->type = PNFS_BLOCK_VOLUME_SCSI;
b->scsi.pr_key = nfsd4_scsi_pr_key(clp);
- error = nfsd4_scsi_identify_device(sb->s_bdev, b);
- if (error)
- return error;
+ ret = nfsd4_block_get_unique_id(sb->s_bdev->bd_disk, b);
+ if (ret < 0)
+ goto out_free_dev;
+ ret = -EINVAL;
ops = sb->s_bdev->bd_disk->fops->pr_ops;
if (!ops) {
pr_err("pNFS: device %s does not support PRs.\n",
sb->s_id);
- return -EINVAL;
+ goto out_free_dev;
}
- error = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
- if (error) {
+ ret = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
+ if (ret) {
pr_err("pNFS: failed to register key for device %s.\n",
sb->s_id);
- return -EINVAL;
+ goto out_free_dev;
}
- error = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
+ ret = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
PR_EXCLUSIVE_ACCESS_REG_ONLY, 0);
- if (error) {
+ if (ret) {
pr_err("pNFS: failed to reserve device %s.\n",
sb->s_id);
- return -EINVAL;
+ goto out_free_dev;
}
return 0;
+
+out_free_dev:
+ kfree(dev);
+ return ret;
}
static __be32
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index a97873f2d22b..6d1b5bb051c5 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -145,8 +145,9 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
#ifdef CONFIG_NFSD_SCSILAYOUT
if (sb->s_export_op->map_blocks &&
sb->s_export_op->commit_blocks &&
- sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops &&
- blk_queue_scsi_passthrough(sb->s_bdev->bd_disk->queue))
+ sb->s_bdev &&
+ sb->s_bdev->bd_disk->fops->pr_ops &&
+ sb->s_bdev->bd_disk->fops->get_unique_id)
exp->ex_layout_types |= 1 << LAYOUT_SCSI;
#endif
}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 640ac8fe891e..1d0583cfd970 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1107,7 +1107,7 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
goto out;
ret = -ERANGE;
- if (range[1] > i_size_read(inode->i_sb->s_bdev->bd_inode))
+ if (range[1] > bdev_nr_bytes(inode->i_sb->s_bdev))
goto out;
segbytes = nilfs->ns_blocks_per_segment * nilfs->ns_blocksize;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index f6b2d280aab5..3134c0e42fd4 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -403,7 +403,7 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize)
int ret;
ret = -ERANGE;
- devsize = i_size_read(sb->s_bdev->bd_inode);
+ devsize = bdev_nr_bytes(sb->s_bdev);
if (newsize > devsize)
goto out;
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index c8bfc01da5d7..1bfcb5d3ea48 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -489,7 +489,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
{
struct nilfs_super_block **sbp = nilfs->ns_sbp;
struct buffer_head **sbh = nilfs->ns_sbh;
- u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size);
+ u64 sb2off = NILFS_SB2_OFFSET_BYTES(bdev_nr_bytes(nilfs->ns_bdev));
int valid[2], swp = 0;
sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize,
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index ab4f3362466d..373dbb627657 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -5,6 +5,7 @@
* Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc.
*/
+#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/gfp.h>
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 0d7e948cb29c..5ae8de09b271 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -2772,13 +2772,12 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
ntfs_debug("Set device block size to %i bytes (block size bits %i).",
blocksize, sb->s_blocksize_bits);
/* Determine the size of the device in units of block_size bytes. */
- if (!i_size_read(sb->s_bdev->bd_inode)) {
+ vol->nr_blocks = sb_bdev_nr_blocks(sb);
+ if (!vol->nr_blocks) {
if (!silent)
ntfs_error(sb, "Unable to determine device size.");
goto err_out_now;
}
- vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
- sb->s_blocksize_bits;
/* Read the boot sector and return unlocked buffer head to it. */
if (!(bh = read_ntfs_boot_sector(sb, silent))) {
if (!silent)
@@ -2816,8 +2815,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
goto err_out_now;
}
BUG_ON(blocksize != sb->s_blocksize);
- vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
- sb->s_blocksize_bits;
+ vol->nr_blocks = sb_bdev_nr_blocks(sb);
ntfs_debug("Changed device block size to %i bytes (block size "
"bits %i) to match volume sector size.",
blocksize, sb->s_blocksize_bits);
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 43b1451bff53..a3cd3c3f091e 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -8,6 +8,7 @@
*/
#include <linux/backing-dev.h>
+#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/compat.h>
#include <linux/falloc.h>
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 859951d785cb..a87ab3ad3cd3 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -1046,7 +1046,7 @@ int ntfs_flush_inodes(struct super_block *sb, struct inode *i1,
if (!ret && i2)
ret = writeback_inode(i2);
if (!ret)
- ret = filemap_flush(sb->s_bdev->bd_inode->i_mapping);
+ ret = sync_blockdev_nowait(sb->s_bdev);
return ret;
}
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index d41d76979e12..29813200c7af 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -921,7 +921,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
/* Parse boot. */
err = ntfs_init_from_boot(sb, rq ? queue_logical_block_size(rq) : 512,
- bdev->bd_inode->i_size);
+ bdev_nr_bytes(bdev));
if (err)
goto out;
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 8521942f5af2..481017e1dac5 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1251,7 +1251,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
{
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
struct journal_head *jh;
- int ret;
+ int ret = 1;
if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
return 0;
@@ -1259,14 +1259,18 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
if (!buffer_jbd(bg_bh))
return 1;
- jh = bh2jh(bg_bh);
- spin_lock(&jh->b_state_lock);
- bg = (struct ocfs2_group_desc *) jh->b_committed_data;
- if (bg)
- ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
- else
- ret = 1;
- spin_unlock(&jh->b_state_lock);
+ jbd_lock_bh_journal_head(bg_bh);
+ if (buffer_jbd(bg_bh)) {
+ jh = bh2jh(bg_bh);
+ spin_lock(&jh->b_state_lock);
+ bg = (struct ocfs2_group_desc *) jh->b_committed_data;
+ if (bg)
+ ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+ else
+ ret = 1;
+ spin_unlock(&jh->b_state_lock);
+ }
+ jbd_unlock_bh_journal_head(bg_bh);
return ret;
}
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index c1bb4c4b5d67..e5e3e500ed46 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -10,7 +10,7 @@
* Linux VFS inode operations.
*/
-#include <linux/bvec.h>
+#include <linux/blkdev.h>
#include <linux/fileattr.h>
#include "protocol.h"
#include "orangefs-kernel.h"
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 2f2e430461b2..8bb0a53a658b 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -11,6 +11,7 @@
#include <linux/parser.h>
#include <linux/hashtable.h>
+#include <linux/seq_file.h>
/* a cache for orangefs-inode objects (i.e. orangefs inode private data) */
static struct kmem_cache *orangefs_inode_cache;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index c88ac571593d..ac461a499882 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -272,14 +272,14 @@ static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
kmem_cache_free(ovl_aio_request_cachep, aio_req);
}
-static void ovl_aio_rw_complete(struct kiocb *iocb, long res, long res2)
+static void ovl_aio_rw_complete(struct kiocb *iocb, long res)
{
struct ovl_aio_req *aio_req = container_of(iocb,
struct ovl_aio_req, iocb);
struct kiocb *orig_iocb = aio_req->orig_iocb;
ovl_aio_cleanup_handler(aio_req);
- orig_iocb->ki_complete(orig_iocb, res, res2);
+ orig_iocb->ki_complete(orig_iocb, res);
}
static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index 04ce58c939a0..5d1fbaffd66a 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -205,7 +205,6 @@ static ssize_t psblk_generic_blk_write(const char *buf, size_t bytes,
static int __register_pstore_blk(struct pstore_device_info *dev,
const char *devpath)
{
- struct inode *inode;
int ret = -ENODEV;
lockdep_assert_held(&pstore_blk_lock);
@@ -217,14 +216,13 @@ static int __register_pstore_blk(struct pstore_device_info *dev,
goto err;
}
- inode = file_inode(psblk_file);
- if (!S_ISBLK(inode->i_mode)) {
+ if (!S_ISBLK(file_inode(psblk_file)->i_mode)) {
pr_err("'%s' is not block device!\n", devpath);
goto err_fput;
}
- inode = I_BDEV(psblk_file->f_mapping->host)->bd_inode;
- dev->zone.total_size = i_size_read(inode);
+ dev->zone.total_size =
+ bdev_nr_bytes(I_BDEV(psblk_file->f_mapping->host));
ret = __register_pstore_device(dev);
if (ret)
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 2bcc9a6f1bfc..052f143e2e0e 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -10,6 +10,7 @@
#include <linux/namei.h>
#include <linux/slab.h>
#include <asm/current.h>
+#include <linux/blkdev.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/security.h>
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 65e7e56005b8..e2302342a67f 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -38,6 +38,7 @@
#include <linux/uaccess.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
+#include <linux/seq_file.h>
#include "internal.h"
struct ramfs_mount_opts {
diff --git a/fs/read_write.c b/fs/read_write.c
index af057c57bdc6..0074afa7ecb3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -368,10 +368,6 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
if (unlikely((ssize_t) count < 0))
return -EINVAL;
- /*
- * ranged mandatory locking does not apply to streams - it makes sense
- * only for files where position has a meaning.
- */
if (ppos) {
loff_t pos = *ppos;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 58481f8d63d5..076f9ab94306 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1199,9 +1199,7 @@ static int reiserfs_parse_options(struct super_block *s,
if (!strcmp(arg, "auto")) {
/* From JFS code, to auto-get the size. */
- *blocks =
- i_size_read(s->s_bdev->bd_inode) >> s->
- s_blocksize_bits;
+ *blocks = sb_bdev_nr_blocks(s);
} else {
*blocks = simple_strtoul(arg, &p, 0);
if (*p != '\0') {
@@ -1986,9 +1984,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
* smaller than the filesystem. If the check fails then abort and
* scream, because bad stuff will happen otherwise.
*/
- if (s->s_bdev && s->s_bdev->bd_inode
- && i_size_read(s->s_bdev->bd_inode) <
- sb_block_count(rs) * sb_blocksize(rs)) {
+ if (bdev_nr_bytes(s->s_bdev) < sb_block_count(rs) * sb_blocksize(rs)) {
SWARN(silent, s, "", "Filesystem cannot be "
"mounted because it is bigger than the device");
SWARN(silent, s, "", "You may need to run fsck "
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 60d6951915f4..bb44ff4c5cc6 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -16,6 +16,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/blkdev.h>
#include <linux/fs.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
@@ -179,8 +180,8 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
/* Check the filesystem does not extend beyond the end of the
block device */
msblk->bytes_used = le64_to_cpu(sblk->bytes_used);
- if (msblk->bytes_used < 0 || msblk->bytes_used >
- i_size_read(sb->s_bdev->bd_inode))
+ if (msblk->bytes_used < 0 ||
+ msblk->bytes_used > bdev_nr_bytes(sb->s_bdev))
goto failed_mount;
/* Check block size for sanity */
diff --git a/fs/sync.c b/fs/sync.c
index 1373a610dc78..3ce8e2137f31 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -3,6 +3,7 @@
* High-level sync()-related operations
*/
+#include <linux/blkdev.h>
#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.h>
@@ -22,25 +23,6 @@
SYNC_FILE_RANGE_WAIT_AFTER)
/*
- * Do the filesystem syncing work. For simple filesystems
- * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
- * submit IO for these buffers via __sync_blockdev(). This also speeds up the
- * wait == 1 case since in that case write_inode() functions do
- * sync_dirty_buffer() and thus effectively write one block at a time.
- */
-static int __sync_filesystem(struct super_block *sb, int wait)
-{
- if (wait)
- sync_inodes_sb(sb);
- else
- writeback_inodes_sb(sb, WB_REASON_SYNC);
-
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, wait);
- return __sync_blockdev(sb->s_bdev, wait);
-}
-
-/*
* Write out and wait upon all dirty data associated with this
* superblock. Filesystem data as well as the underlying block
* device. Takes the superblock lock.
@@ -61,10 +43,25 @@ int sync_filesystem(struct super_block *sb)
if (sb_rdonly(sb))
return 0;
- ret = __sync_filesystem(sb, 0);
+ /*
+ * Do the filesystem syncing work. For simple filesystems
+ * writeback_inodes_sb(sb) just dirties buffers with inodes so we have
+ * to submit I/O for these buffers via sync_blockdev(). This also
+ * speeds up the wait == 1 case since in that case write_inode()
+ * methods call sync_dirty_buffer() and thus effectively write one block
+ * at a time.
+ */
+ writeback_inodes_sb(sb, WB_REASON_SYNC);
+ if (sb->s_op->sync_fs)
+ sb->s_op->sync_fs(sb, 0);
+ ret = sync_blockdev_nowait(sb->s_bdev);
if (ret < 0)
return ret;
- return __sync_filesystem(sb, 1);
+
+ sync_inodes_sb(sb);
+ if (sb->s_op->sync_fs)
+ sb->s_op->sync_fs(sb, 1);
+ return sync_blockdev(sb->s_bdev);
}
EXPORT_SYMBOL(sync_filesystem);
@@ -81,21 +78,6 @@ static void sync_fs_one_sb(struct super_block *sb, void *arg)
sb->s_op->sync_fs(sb, *(int *)arg);
}
-static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
-{
- filemap_fdatawrite(bdev->bd_inode->i_mapping);
-}
-
-static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
-{
- /*
- * We keep the error status of individual mapping so that
- * applications can catch the writeback error using fsync(2).
- * See filemap_fdatawait_keep_errors() for details.
- */
- filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping);
-}
-
/*
* Sync everything. We start by waking flusher threads so that most of
* writeback runs on all devices in parallel. Then we sync all inodes reliably
@@ -114,8 +96,8 @@ void ksys_sync(void)
iterate_supers(sync_inodes_one_sb, NULL);
iterate_supers(sync_fs_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &wait);
- iterate_bdevs(fdatawrite_one_bdev, NULL);
- iterate_bdevs(fdatawait_one_bdev, NULL);
+ sync_bdevs(false);
+ sync_bdevs(true);
if (unlikely(laptop_mode))
laptop_sync_completion();
}
@@ -136,10 +118,10 @@ static void do_sync_work(struct work_struct *work)
*/
iterate_supers(sync_inodes_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &nowait);
- iterate_bdevs(fdatawrite_one_bdev, NULL);
+ sync_bdevs(false);
iterate_supers(sync_inodes_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &nowait);
- iterate_bdevs(fdatawrite_one_bdev, NULL);
+ sync_bdevs(false);
printk("Emergency Sync complete\n");
kfree(work);
}
diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
index 22be7aeb96c4..c57b46a352d8 100644
--- a/fs/ubifs/crypto.c
+++ b/fs/ubifs/crypto.c
@@ -82,5 +82,4 @@ const struct fscrypt_operations ubifs_crypt_operations = {
.get_context = ubifs_crypt_get_context,
.set_context = ubifs_crypt_set_context,
.empty_dir = ubifs_crypt_empty_dir,
- .max_namelen = UBIFS_MAX_NLEN,
};
diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c
index f1094cdcd6cd..46d697172197 100644
--- a/fs/udf/lowlevel.c
+++ b/fs/udf/lowlevel.c
@@ -47,8 +47,7 @@ unsigned int udf_get_last_session(struct super_block *sb)
unsigned long udf_get_last_block(struct super_block *sb)
{
- struct block_device *bdev = sb->s_bdev;
- struct cdrom_device_info *cdi = disk_to_cdi(bdev->bd_disk);
+ struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk);
unsigned long lblock = 0;
/*
@@ -56,7 +55,7 @@ unsigned long udf_get_last_block(struct super_block *sb)
* Try using the device size...
*/
if (!cdi || cdrom_get_last_written(cdi, &lblock) || lblock == 0)
- lblock = i_size_read(bdev->bd_inode) >> sb->s_blocksize_bits;
+ lblock = sb_bdev_nr_blocks(sb);
if (lblock)
return lblock - 1;
diff --git a/fs/udf/super.c b/fs/udf/super.c
index b2d7c57d0688..34247fba6df9 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1175,8 +1175,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
struct udf_inode_info *vati;
uint32_t pos;
struct virtualAllocationTable20 *vat20;
- sector_t blocks = i_size_read(sb->s_bdev->bd_inode) >>
- sb->s_blocksize_bits;
+ sector_t blocks = sb_bdev_nr_blocks(sb);
udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block);
if (!sbi->s_vat_inode &&
@@ -1838,8 +1837,7 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block,
int ret;
if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
- udf_fixed_to_variable(block) >=
- i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits)
+ udf_fixed_to_variable(block) >= sb_bdev_nr_blocks(sb))
return -EAGAIN;
bh = udf_read_tagged(sb, block, block, &ident);
@@ -1901,8 +1899,7 @@ static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock,
last[last_count++] = *lastblock - 152;
for (i = 0; i < last_count; i++) {
- if (last[i] >= i_size_read(sb->s_bdev->bd_inode) >>
- sb->s_blocksize_bits)
+ if (last[i] >= sb_bdev_nr_blocks(sb))
continue;
ret = udf_check_anchor_block(sb, last[i], fileset);
if (ret != -EAGAIN) {
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7aa943edfc02..62e7fbe4e54c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1452,7 +1452,7 @@ const struct file_operations xfs_file_operations = {
.write_iter = xfs_file_write_iter,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
- .iopoll = iomap_dio_iopoll,
+ .iopoll = iocb_bio_iopoll,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = xfs_file_compat_ioctl,
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index ddc346a9df9b..3ce5f47338cb 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1128,7 +1128,7 @@ static const struct file_operations zonefs_file_operations = {
.write_iter = zonefs_file_write_iter,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
- .iopoll = iomap_dio_iopoll,
+ .iopoll = iocb_bio_iopoll,
};
static struct kmem_cache *zonefs_inode_cachep;
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 4a674db4e1fa..fedc0dfa4877 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -49,9 +49,15 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
static inline void flush_dcache_page(struct page *page)
{
}
+
+static inline void flush_dcache_folio(struct folio *folio) { }
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
#endif
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio);
+#endif
#ifndef flush_dcache_mmap_lock
static inline void flush_dcache_mmap_lock(struct address_space *mapping)
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 1b44f40c7700..199e47e97d64 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -329,6 +329,7 @@ enum {
ATA_LOG_SECURITY = 0x06,
ATA_LOG_SATA_SETTINGS = 0x08,
ATA_LOG_ZONED_INFORMATION = 0x09,
+ ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47,
/* Identify device SATA settings log:*/
ATA_LOG_DEVSLP_OFFSET = 0x30,
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index ac7f231b8825..9c14f0a8dbe5 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -12,13 +12,13 @@
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/sched.h>
-#include <linux/blkdev.h>
#include <linux/device.h>
#include <linux/writeback.h>
-#include <linux/blk-cgroup.h>
#include <linux/backing-dev-defs.h>
#include <linux/slab.h>
+struct blkcg;
+
static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
{
kref_get(&bdi->refcnt);
@@ -64,7 +64,7 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
return atomic_long_read(&bdi->tot_write_bandwidth);
}
-static inline void __add_wb_stat(struct bdi_writeback *wb,
+static inline void wb_stat_mod(struct bdi_writeback *wb,
enum wb_stat_item item, s64 amount)
{
percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
@@ -72,12 +72,12 @@ static inline void __add_wb_stat(struct bdi_writeback *wb,
static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
- __add_wb_stat(wb, item, 1);
+ wb_stat_mod(wb, item, 1);
}
static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
- __add_wb_stat(wb, item, -1);
+ wb_stat_mod(wb, item, -1);
}
static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
@@ -133,20 +133,7 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb)
return test_bit(WB_writeback_running, &wb->state);
}
-static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
-{
- struct super_block *sb;
-
- if (!inode)
- return &noop_backing_dev_info;
-
- sb = inode->i_sb;
-#ifdef CONFIG_BLOCK
- if (sb_is_blkdev_sb(sb))
- return I_BDEV(inode)->bd_disk->bdi;
-#endif
- return sb->s_bdi;
-}
+struct backing_dev_info *inode_to_bdi(struct inode *inode);
static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
{
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 00952e92eae1..fe6bdfbbef66 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -6,19 +6,10 @@
#define __LINUX_BIO_H
#include <linux/mempool.h>
-#include <linux/ioprio.h>
/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
#include <linux/blk_types.h>
#include <linux/uio.h>
-#define BIO_DEBUG
-
-#ifdef BIO_DEBUG
-#define BIO_BUG_ON BUG_ON
-#else
-#define BIO_BUG_ON
-#endif
-
#define BIO_MAX_VECS 256U
static inline unsigned int bio_max_segs(unsigned int nr_segs)
@@ -78,22 +69,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio)
bio_op(bio) == REQ_OP_WRITE_ZEROES;
}
-static inline bool bio_mergeable(struct bio *bio)
-{
- if (bio->bi_opf & REQ_NOMERGE_FLAGS)
- return false;
-
- return true;
-}
-
-static inline unsigned int bio_cur_bytes(struct bio *bio)
-{
- if (bio_has_data(bio))
- return bio_iovec(bio).bv_len;
- else /* dataless requests such as discard */
- return bio->bi_iter.bi_size;
-}
-
static inline void *bio_data(struct bio *bio)
{
if (bio_has_data(bio))
@@ -102,25 +77,6 @@ static inline void *bio_data(struct bio *bio)
return NULL;
}
-/**
- * bio_full - check if the bio is full
- * @bio: bio to check
- * @len: length of one segment to be added
- *
- * Return true if @bio is full and one segment with @len bytes can't be
- * added to the bio, otherwise return false
- */
-static inline bool bio_full(struct bio *bio, unsigned len)
-{
- if (bio->bi_vcnt >= bio->bi_max_vecs)
- return true;
-
- if (bio->bi_iter.bi_size > UINT_MAX - len)
- return true;
-
- return false;
-}
-
static inline bool bio_next_segment(const struct bio *bio,
struct bvec_iter_all *iter)
{
@@ -163,6 +119,28 @@ static inline void bio_advance_iter_single(const struct bio *bio,
bvec_iter_advance_single(bio->bi_io_vec, iter, bytes);
}
+void __bio_advance(struct bio *, unsigned bytes);
+
+/**
+ * bio_advance - increment/complete a bio by some number of bytes
+ * @bio: bio to advance
+ * @bytes: number of bytes to complete
+ *
+ * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
+ * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
+ * be updated on the last bvec as well.
+ *
+ * @bio will then represent the remaining, uncompleted portion of the io.
+ */
+static inline void bio_advance(struct bio *bio, unsigned int nbytes)
+{
+ if (nbytes == bio->bi_iter.bi_size) {
+ bio->bi_iter.bi_size = 0;
+ return;
+ }
+ __bio_advance(bio, nbytes);
+}
+
#define __bio_for_each_segment(bvl, bio, iter, start) \
for (iter = (start); \
(iter).bi_size && \
@@ -265,37 +243,6 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
bio->bi_flags &= ~(1U << bit);
}
-static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
-{
- *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
-}
-
-static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
-{
- struct bvec_iter iter = bio->bi_iter;
- int idx;
-
- bio_get_first_bvec(bio, bv);
- if (bv->bv_len == bio->bi_iter.bi_size)
- return; /* this bio only has a single bvec */
-
- bio_advance_iter(bio, &iter, iter.bi_size);
-
- if (!iter.bi_bvec_done)
- idx = iter.bi_idx - 1;
- else /* in the middle of bvec */
- idx = iter.bi_idx;
-
- *bv = bio->bi_io_vec[idx];
-
- /*
- * iter.bi_bvec_done records actual length of the last bvec
- * if this bio ends in the middle of one io vector
- */
- if (iter.bi_bvec_done)
- bv->bv_len = iter.bi_bvec_done;
-}
-
static inline struct bio_vec *bio_first_bvec_all(struct bio *bio)
{
WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
@@ -424,7 +371,7 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs)
return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
}
-extern blk_qc_t submit_bio(struct bio *);
+void submit_bio(struct bio *bio);
extern void bio_endio(struct bio *);
@@ -456,8 +403,6 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs)
struct request_queue;
extern int submit_bio_wait(struct bio *bio);
-extern void bio_advance(struct bio *, unsigned);
-
extern void bio_init(struct bio *bio, struct bio_vec *table,
unsigned short max_vecs);
extern void bio_uninit(struct bio *);
@@ -469,12 +414,11 @@ extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
unsigned int, unsigned int);
int bio_add_zone_append_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset);
-bool __bio_try_merge_page(struct bio *bio, struct page *page,
- unsigned int len, unsigned int off, bool *same_page);
void __bio_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int off);
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
-void bio_release_pages(struct bio *bio, bool mark_dirty);
+void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter);
+void __bio_release_pages(struct bio *bio, bool mark_dirty);
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
@@ -482,27 +426,16 @@ extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
struct bio *src, struct bvec_iter *src_iter);
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
-void bio_truncate(struct bio *bio, unsigned new_size);
void guard_bio_eod(struct bio *bio);
void zero_fill_bio(struct bio *bio);
-extern const char *bio_devname(struct bio *bio, char *buffer);
+static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
+{
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ __bio_release_pages(bio, mark_dirty);
+}
-#define bio_set_dev(bio, bdev) \
-do { \
- bio_clear_flag(bio, BIO_REMAPPED); \
- if ((bio)->bi_bdev != (bdev)) \
- bio_clear_flag(bio, BIO_THROTTLED); \
- (bio)->bi_bdev = (bdev); \
- bio_associate_blkg(bio); \
-} while (0)
-
-#define bio_copy_dev(dst, src) \
-do { \
- bio_clear_flag(dst, BIO_REMAPPED); \
- (dst)->bi_bdev = (src)->bi_bdev; \
- bio_clone_blkg_association(dst, src); \
-} while (0)
+extern const char *bio_devname(struct bio *bio, char *buffer);
#define bio_dev(bio) \
disk_devt((bio)->bi_bdev->bd_disk)
@@ -521,6 +454,22 @@ static inline void bio_clone_blkg_association(struct bio *dst,
struct bio *src) { }
#endif /* CONFIG_BLK_CGROUP */
+static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
+{
+ bio_clear_flag(bio, BIO_REMAPPED);
+ if (bio->bi_bdev != bdev)
+ bio_clear_flag(bio, BIO_THROTTLED);
+ bio->bi_bdev = bdev;
+ bio_associate_blkg(bio);
+}
+
+static inline void bio_copy_dev(struct bio *dst, struct bio *src)
+{
+ bio_clear_flag(dst, BIO_REMAPPED);
+ dst->bi_bdev = src->bi_bdev;
+ bio_clone_blkg_association(dst, src);
+}
+
/*
* BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
*
@@ -784,7 +733,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
*/
static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
{
- bio->bi_opf |= REQ_HIPRI;
+ bio->bi_opf |= REQ_POLLED;
if (!is_sync_kiocb(kiocb))
bio->bi_opf |= REQ_NOWAIT;
}
diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h
new file mode 100644
index 000000000000..bbab65bd5428
--- /dev/null
+++ b/include/linux/blk-crypto-profile.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_BLK_CRYPTO_PROFILE_H
+#define __LINUX_BLK_CRYPTO_PROFILE_H
+
+#include <linux/bio.h>
+#include <linux/blk-crypto.h>
+
+struct blk_crypto_profile;
+
+/**
+ * struct blk_crypto_ll_ops - functions to control inline encryption hardware
+ *
+ * Low-level operations for controlling inline encryption hardware. This
+ * interface must be implemented by storage drivers that support inline
+ * encryption. All functions may sleep, are serialized by profile->lock, and
+ * are never called while profile->dev (if set) is runtime-suspended.
+ */
+struct blk_crypto_ll_ops {
+
+ /**
+ * @keyslot_program: Program a key into the inline encryption hardware.
+ *
+ * Program @key into the specified @slot in the inline encryption
+ * hardware, overwriting any key that the keyslot may already contain.
+ * The keyslot is guaranteed to not be in-use by any I/O.
+ *
+ * This is required if the device has keyslots. Otherwise (i.e. if the
+ * device is a layered device, or if the device is real hardware that
+ * simply doesn't have the concept of keyslots) it is never called.
+ *
+ * Must return 0 on success, or -errno on failure.
+ */
+ int (*keyslot_program)(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot);
+
+ /**
+ * @keyslot_evict: Evict a key from the inline encryption hardware.
+ *
+ * If the device has keyslots, this function must evict the key from the
+ * specified @slot. The slot will contain @key, but there should be no
+ * need for the @key argument to be used as @slot should be sufficient.
+ * The keyslot is guaranteed to not be in-use by any I/O.
+ *
+ * If the device doesn't have keyslots itself, this function must evict
+ * @key from any underlying devices. @slot won't be valid in this case.
+ *
+ * If there are no keyslots and no underlying devices, this function
+ * isn't required.
+ *
+ * Must return 0 on success, or -errno on failure.
+ */
+ int (*keyslot_evict)(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot);
+};
+
+/**
+ * struct blk_crypto_profile - inline encryption profile for a device
+ *
+ * This struct contains a storage device's inline encryption capabilities (e.g.
+ * the supported crypto algorithms), driver-provided functions to control the
+ * inline encryption hardware (e.g. programming and evicting keys), and optional
+ * device-independent keyslot management data.
+ */
+struct blk_crypto_profile {
+
+ /* public: Drivers must initialize the following fields. */
+
+ /**
+ * @ll_ops: Driver-provided functions to control the inline encryption
+ * hardware, e.g. program and evict keys.
+ */
+ struct blk_crypto_ll_ops ll_ops;
+
+ /**
+ * @max_dun_bytes_supported: The maximum number of bytes supported for
+ * specifying the data unit number (DUN). Specifically, the range of
+ * supported DUNs is 0 through (1 << (8 * max_dun_bytes_supported)) - 1.
+ */
+ unsigned int max_dun_bytes_supported;
+
+ /**
+ * @modes_supported: Array of bitmasks that specifies whether each
+ * combination of crypto mode and data unit size is supported.
+ * Specifically, the i'th bit of modes_supported[crypto_mode] is set if
+ * crypto_mode can be used with a data unit size of (1 << i). Note that
+ * only data unit sizes that are powers of 2 can be supported.
+ */
+ unsigned int modes_supported[BLK_ENCRYPTION_MODE_MAX];
+
+ /**
+ * @dev: An optional device for runtime power management. If the driver
+ * provides this device, it will be runtime-resumed before any function
+ * in @ll_ops is called and will remain resumed during the call.
+ */
+ struct device *dev;
+
+ /* private: The following fields shouldn't be accessed by drivers. */
+
+ /* Number of keyslots, or 0 if not applicable */
+ unsigned int num_slots;
+
+ /*
+ * Serializes all calls to functions in @ll_ops as well as all changes
+ * to @slot_hashtable. This can also be taken in read mode to look up
+ * keyslots while ensuring that they can't be changed concurrently.
+ */
+ struct rw_semaphore lock;
+
+ /* List of idle slots, with least recently used slot at front */
+ wait_queue_head_t idle_slots_wait_queue;
+ struct list_head idle_slots;
+ spinlock_t idle_slots_lock;
+
+ /*
+ * Hash table which maps struct *blk_crypto_key to keyslots, so that we
+ * can find a key's keyslot in O(1) time rather than O(num_slots).
+ * Protected by 'lock'.
+ */
+ struct hlist_head *slot_hashtable;
+ unsigned int log_slot_ht_size;
+
+ /* Per-keyslot data */
+ struct blk_crypto_keyslot *slots;
+};
+
+int blk_crypto_profile_init(struct blk_crypto_profile *profile,
+ unsigned int num_slots);
+
+int devm_blk_crypto_profile_init(struct device *dev,
+ struct blk_crypto_profile *profile,
+ unsigned int num_slots);
+
+unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot);
+
+blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ struct blk_crypto_keyslot **slot_ptr);
+
+void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot);
+
+bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
+ const struct blk_crypto_config *cfg);
+
+int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key);
+
+void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile);
+
+void blk_crypto_profile_destroy(struct blk_crypto_profile *profile);
+
+void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent,
+ const struct blk_crypto_profile *child);
+
+bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target,
+ const struct blk_crypto_profile *reference);
+
+void blk_crypto_update_capabilities(struct blk_crypto_profile *dst,
+ const struct blk_crypto_profile *src);
+
+#endif /* __LINUX_BLK_CRYPTO_PROFILE_H */
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
new file mode 100644
index 000000000000..8a038ea0717e
--- /dev/null
+++ b/include/linux/blk-integrity.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BLK_INTEGRITY_H
+#define _LINUX_BLK_INTEGRITY_H
+
+#include <linux/blk-mq.h>
+
+struct request;
+
+enum blk_integrity_flags {
+ BLK_INTEGRITY_VERIFY = 1 << 0,
+ BLK_INTEGRITY_GENERATE = 1 << 1,
+ BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2,
+ BLK_INTEGRITY_IP_CHECKSUM = 1 << 3,
+};
+
+struct blk_integrity_iter {
+ void *prot_buf;
+ void *data_buf;
+ sector_t seed;
+ unsigned int data_size;
+ unsigned short interval;
+ const char *disk_name;
+};
+
+typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
+typedef void (integrity_prepare_fn) (struct request *);
+typedef void (integrity_complete_fn) (struct request *, unsigned int);
+
+struct blk_integrity_profile {
+ integrity_processing_fn *generate_fn;
+ integrity_processing_fn *verify_fn;
+ integrity_prepare_fn *prepare_fn;
+ integrity_complete_fn *complete_fn;
+ const char *name;
+};
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+void blk_integrity_register(struct gendisk *, struct blk_integrity *);
+void blk_integrity_unregister(struct gendisk *);
+int blk_integrity_compare(struct gendisk *, struct gendisk *);
+int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
+ struct scatterlist *);
+int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
+
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+ struct blk_integrity *bi = &disk->queue->integrity;
+
+ if (!bi->profile)
+ return NULL;
+
+ return bi;
+}
+
+static inline struct blk_integrity *
+bdev_get_integrity(struct block_device *bdev)
+{
+ return blk_get_integrity(bdev->bd_disk);
+}
+
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+ return q->integrity.profile;
+}
+
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+ unsigned int segs)
+{
+ q->limits.max_integrity_segments = segs;
+}
+
+static inline unsigned short
+queue_max_integrity_segments(const struct request_queue *q)
+{
+ return q->limits.max_integrity_segments;
+}
+
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi: blk_integrity profile for device
+ * @sectors: Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device. Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+ unsigned int sectors)
+{
+ return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+ unsigned int sectors)
+{
+ return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
+static inline bool blk_integrity_rq(struct request *rq)
+{
+ return rq->cmd_flags & REQ_INTEGRITY;
+}
+
+/*
+ * Return the first bvec that contains integrity data. Only drivers that are
+ * limited to a single integrity segment should use this helper.
+ */
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+ if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
+ return NULL;
+ return rq->bio->bi_integrity->bip_vec;
+}
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline int blk_rq_count_integrity_sg(struct request_queue *q,
+ struct bio *b)
+{
+ return 0;
+}
+static inline int blk_rq_map_integrity_sg(struct request_queue *q,
+ struct bio *b,
+ struct scatterlist *s)
+{
+ return 0;
+}
+static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
+{
+ return NULL;
+}
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+ return NULL;
+}
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+ return false;
+}
+static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
+{
+ return 0;
+}
+static inline void blk_integrity_register(struct gendisk *d,
+ struct blk_integrity *b)
+{
+}
+static inline void blk_integrity_unregister(struct gendisk *d)
+{
+}
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+ unsigned int segs)
+{
+}
+static inline unsigned short
+queue_max_integrity_segments(const struct request_queue *q)
+{
+ return 0;
+}
+
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+ unsigned int sectors)
+{
+ return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+ unsigned int sectors)
+{
+ return 0;
+}
+static inline int blk_integrity_rq(struct request *rq)
+{
+ return 0;
+}
+
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+ return NULL;
+}
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+#endif /* _LINUX_BLK_INTEGRITY_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 13ba1861e688..8682663e7368 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -6,10 +6,226 @@
#include <linux/sbitmap.h>
#include <linux/srcu.h>
#include <linux/lockdep.h>
+#include <linux/scatterlist.h>
+#include <linux/prefetch.h>
struct blk_mq_tags;
struct blk_flush_queue;
+#define BLKDEV_MIN_RQ 4
+#define BLKDEV_DEFAULT_RQ 128
+
+typedef void (rq_end_io_fn)(struct request *, blk_status_t);
+
+/*
+ * request flags */
+typedef __u32 __bitwise req_flags_t;
+
+/* drive already may have started this one */
+#define RQF_STARTED ((__force req_flags_t)(1 << 1))
+/* may not be passed by ioscheduler */
+#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3))
+/* request for flush sequence */
+#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4))
+/* merge of different types, fail separately */
+#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5))
+/* track inflight for MQ */
+#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6))
+/* don't call prep for this one */
+#define RQF_DONTPREP ((__force req_flags_t)(1 << 7))
+/* vaguely specified driver internal error. Ignored by the block layer */
+#define RQF_FAILED ((__force req_flags_t)(1 << 10))
+/* don't warn about errors */
+#define RQF_QUIET ((__force req_flags_t)(1 << 11))
+/* elevator private data attached */
+#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12))
+/* account into disk and partition IO statistics */
+#define RQF_IO_STAT ((__force req_flags_t)(1 << 13))
+/* runtime pm request */
+#define RQF_PM ((__force req_flags_t)(1 << 15))
+/* on IO scheduler merge hash */
+#define RQF_HASHED ((__force req_flags_t)(1 << 16))
+/* track IO completion time */
+#define RQF_STATS ((__force req_flags_t)(1 << 17))
+/* Look at ->special_vec for the actual data payload instead of the
+ bio chain. */
+#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18))
+/* The per-zone write lock is held for this request */
+#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19))
+/* already slept for hybrid poll */
+#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20))
+/* ->timeout has been called, don't expire again */
+#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21))
+/* queue has elevator attached */
+#define RQF_ELV ((__force req_flags_t)(1 << 22))
+
+/* flags that prevent us from merging requests: */
+#define RQF_NOMERGE_FLAGS \
+ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
+
+enum mq_rq_state {
+ MQ_RQ_IDLE = 0,
+ MQ_RQ_IN_FLIGHT = 1,
+ MQ_RQ_COMPLETE = 2,
+};
+
+/*
+ * Try to put the fields that are referenced together in the same cacheline.
+ *
+ * If you modify this structure, make sure to update blk_rq_init() and
+ * especially blk_mq_rq_ctx_init() to take care of the added fields.
+ */
+struct request {
+ struct request_queue *q;
+ struct blk_mq_ctx *mq_ctx;
+ struct blk_mq_hw_ctx *mq_hctx;
+
+ unsigned int cmd_flags; /* op and common flags */
+ req_flags_t rq_flags;
+
+ int tag;
+ int internal_tag;
+
+ unsigned int timeout;
+
+ /* the following two fields are internal, NEVER access directly */
+ unsigned int __data_len; /* total data len */
+ sector_t __sector; /* sector cursor */
+
+ struct bio *bio;
+ struct bio *biotail;
+
+ union {
+ struct list_head queuelist;
+ struct request *rq_next;
+ };
+
+ struct gendisk *rq_disk;
+ struct block_device *part;
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+ /* Time that the first bio started allocating this request. */
+ u64 alloc_time_ns;
+#endif
+ /* Time that this request was allocated for this IO. */
+ u64 start_time_ns;
+ /* Time that I/O was submitted to the device. */
+ u64 io_start_time_ns;
+
+#ifdef CONFIG_BLK_WBT
+ unsigned short wbt_flags;
+#endif
+ /*
+ * rq sectors used for blk stats. It has the same value
+ * with blk_rq_sectors(rq), except that it never be zeroed
+ * by completion.
+ */
+ unsigned short stats_sectors;
+
+ /*
+ * Number of scatter-gather DMA addr+len pairs after
+ * physical address coalescing is performed.
+ */
+ unsigned short nr_phys_segments;
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+ unsigned short nr_integrity_segments;
+#endif
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+ struct bio_crypt_ctx *crypt_ctx;
+ struct blk_crypto_keyslot *crypt_keyslot;
+#endif
+
+ unsigned short write_hint;
+ unsigned short ioprio;
+
+ enum mq_rq_state state;
+ refcount_t ref;
+
+ unsigned long deadline;
+
+ /*
+ * The hash is used inside the scheduler, and killed once the
+ * request reaches the dispatch list. The ipi_list is only used
+ * to queue the request for softirq completion, which is long
+ * after the request has been unhashed (and even removed from
+ * the dispatch list).
+ */
+ union {
+ struct hlist_node hash; /* merge hash */
+ struct llist_node ipi_list;
+ };
+
+ /*
+ * The rb_node is only used inside the io scheduler, requests
+ * are pruned when moved to the dispatch queue. So let the
+ * completion_data share space with the rb_node.
+ */
+ union {
+ struct rb_node rb_node; /* sort/lookup */
+ struct bio_vec special_vec;
+ void *completion_data;
+ int error_count; /* for legacy drivers, don't use */
+ };
+
+
+ /*
+ * Three pointers are available for the IO schedulers, if they need
+ * more they have to dynamically allocate it. Flush requests are
+ * never put on the IO scheduler. So let the flush fields share
+ * space with the elevator data.
+ */
+ union {
+ struct {
+ struct io_cq *icq;
+ void *priv[2];
+ } elv;
+
+ struct {
+ unsigned int seq;
+ struct list_head list;
+ rq_end_io_fn *saved_end_io;
+ } flush;
+ };
+
+ union {
+ struct __call_single_data csd;
+ u64 fifo_time;
+ };
+
+ /*
+ * completion callback.
+ */
+ rq_end_io_fn *end_io;
+ void *end_io_data;
+};
+
+#define req_op(req) \
+ ((req)->cmd_flags & REQ_OP_MASK)
+
+static inline bool blk_rq_is_passthrough(struct request *rq)
+{
+ return blk_op_is_passthrough(req_op(rq));
+}
+
+static inline unsigned short req_get_ioprio(struct request *req)
+{
+ return req->ioprio;
+}
+
+#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ)
+
+#define rq_dma_dir(rq) \
+ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
+enum blk_eh_timer_return {
+ BLK_EH_DONE, /* drivers has completed the command */
+ BLK_EH_RESET_TIMER, /* reset timer and try again */
+};
+
+#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
+#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
+
/**
* struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
* block device
@@ -126,9 +342,6 @@ struct blk_mq_hw_ctx {
unsigned long queued;
/** @run: Number of dispatched requests. */
unsigned long run;
-#define BLK_MQ_MAX_DISPATCH_ORDER 7
- /** @dispatched: Number of dispatch requests by queue. */
- unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
/** @numa_node: NUMA node the storage adapter has been connected to. */
unsigned int numa_node;
@@ -148,13 +361,6 @@ struct blk_mq_hw_ctx {
/** @kobj: Kernel object for sysfs. */
struct kobject kobj;
- /** @poll_considered: Count times blk_poll() was called. */
- unsigned long poll_considered;
- /** @poll_invoked: Count how many requests blk_poll() polled. */
- unsigned long poll_invoked;
- /** @poll_success: Count how many polled requests were completed. */
- unsigned long poll_success;
-
#ifdef CONFIG_BLK_DEBUG_FS
/**
* @debugfs_dir: debugfs directory for this hardware queue. Named
@@ -232,13 +438,11 @@ enum hctx_type {
* @flags: Zero or more BLK_MQ_F_* flags.
* @driver_data: Pointer to data owned by the block driver that created this
* tag set.
- * @active_queues_shared_sbitmap:
- * number of active request queues per tag set.
- * @__bitmap_tags: A shared tags sbitmap, used over all hctx's
- * @__breserved_tags:
- * A shared reserved tags sbitmap, used over all hctx's
* @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues
* elements.
+ * @shared_tags:
+ * Shared set of tags. Has @nr_hw_queues elements. If set,
+ * shared by all @tags.
* @tag_list_lock: Serializes tag_list accesses.
* @tag_list: List of the request queues that use this tag set. See also
* request_queue.tag_set_list.
@@ -255,12 +459,11 @@ struct blk_mq_tag_set {
unsigned int timeout;
unsigned int flags;
void *driver_data;
- atomic_t active_queues_shared_sbitmap;
- struct sbitmap_queue __bitmap_tags;
- struct sbitmap_queue __breserved_tags;
struct blk_mq_tags **tags;
+ struct blk_mq_tags *shared_tags;
+
struct mutex tag_list_lock;
struct list_head tag_list;
};
@@ -330,7 +533,7 @@ struct blk_mq_ops {
/**
* @poll: Called to poll for completion of a specific tag.
*/
- int (*poll)(struct blk_mq_hw_ctx *);
+ int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *);
/**
* @complete: Mark the request as complete.
@@ -364,11 +567,6 @@ struct blk_mq_ops {
unsigned int);
/**
- * @initialize_rq_fn: Called from inside blk_get_request().
- */
- void (*initialize_rq_fn)(struct request *rq);
-
- /**
* @cleanup_rq: Called before freeing one request which isn't completed
* yet, and usually for freeing the driver private data.
*/
@@ -432,6 +630,8 @@ enum {
((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
+#define BLK_MQ_NO_HCTX_IDX (-1U)
+
struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
struct lock_class_key *lkclass);
#define blk_mq_alloc_disk(set, queuedata) \
@@ -451,8 +651,6 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
unsigned int set_flags);
void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
-void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
-
void blk_mq_free_request(struct request *rq);
bool blk_mq_queue_inflight(struct request_queue *q);
@@ -471,7 +669,40 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags,
unsigned int hctx_idx);
-struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+
+/*
+ * Tag address space map.
+ */
+struct blk_mq_tags {
+ unsigned int nr_tags;
+ unsigned int nr_reserved_tags;
+
+ atomic_t active_queues;
+
+ struct sbitmap_queue bitmap_tags;
+ struct sbitmap_queue breserved_tags;
+
+ struct request **rqs;
+ struct request **static_rqs;
+ struct list_head page_list;
+
+ /*
+ * used to clear request reference in rqs[] before freeing one
+ * request pool
+ */
+ spinlock_t lock;
+};
+
+static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags,
+ unsigned int tag)
+{
+ if (tag < tags->nr_tags) {
+ prefetch(tags->rqs[tag]);
+ return tags->rqs[tag];
+ }
+
+ return NULL;
+}
enum {
BLK_MQ_UNIQUE_TAG_BITS = 16,
@@ -524,6 +755,35 @@ static inline void blk_mq_set_request_complete(struct request *rq)
void blk_mq_start_request(struct request *rq);
void blk_mq_end_request(struct request *rq, blk_status_t error);
void __blk_mq_end_request(struct request *rq, blk_status_t error);
+void blk_mq_end_request_batch(struct io_comp_batch *ib);
+
+/*
+ * Only need start/end time stamping if we have iostat or
+ * blk stats enabled, or using an IO scheduler.
+ */
+static inline bool blk_mq_need_time_stamp(struct request *rq)
+{
+ return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
+}
+
+/*
+ * Batched completions only work when there is no I/O error and no special
+ * ->end_io handler.
+ */
+static inline bool blk_mq_add_to_batch(struct request *req,
+ struct io_comp_batch *iob, int ioerror,
+ void (*complete)(struct io_comp_batch *))
+{
+ if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror)
+ return false;
+ if (!iob->complete)
+ iob->complete = complete;
+ else if (iob->complete != complete)
+ return false;
+ iob->need_ts |= blk_mq_need_time_stamp(req);
+ rq_list_add(&iob->req_list, req);
+ return true;
+}
void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q);
@@ -605,16 +865,6 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
for ((i) = 0; (i) < (hctx)->nr_ctx && \
({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
-static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
-{
- if (rq->tag != -1)
- return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT);
-
- return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) |
- BLK_QC_T_INTERNAL;
-}
-
static inline void blk_mq_cleanup_rq(struct request *rq)
{
if (rq->q->mq_ops->cleanup_rq)
@@ -633,8 +883,265 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
rq->rq_disk = bio->bi_bdev->bd_disk;
}
-blk_qc_t blk_mq_submit_bio(struct bio *bio);
void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
struct lock_class_key *key);
+static inline bool rq_is_sync(struct request *rq)
+{
+ return op_is_sync(rq->cmd_flags);
+}
+
+void blk_rq_init(struct request_queue *q, struct request *rq);
+int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+ struct bio_set *bs, gfp_t gfp_mask,
+ int (*bio_ctr)(struct bio *, struct bio *, void *), void *data);
+void blk_rq_unprep_clone(struct request *rq);
+blk_status_t blk_insert_cloned_request(struct request_queue *q,
+ struct request *rq);
+
+struct rq_map_data {
+ struct page **pages;
+ int page_order;
+ int nr_entries;
+ unsigned long offset;
+ int null_mapped;
+ int from_user;
+};
+
+int blk_rq_map_user(struct request_queue *, struct request *,
+ struct rq_map_data *, void __user *, unsigned long, gfp_t);
+int blk_rq_map_user_iov(struct request_queue *, struct request *,
+ struct rq_map_data *, const struct iov_iter *, gfp_t);
+int blk_rq_unmap_user(struct bio *);
+int blk_rq_map_kern(struct request_queue *, struct request *, void *,
+ unsigned int, gfp_t);
+int blk_rq_append_bio(struct request *rq, struct bio *bio);
+void blk_execute_rq_nowait(struct gendisk *, struct request *, int,
+ rq_end_io_fn *);
+blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
+ int at_head);
+
+struct req_iterator {
+ struct bvec_iter iter;
+ struct bio *bio;
+};
+
+#define __rq_for_each_bio(_bio, rq) \
+ if ((rq->bio)) \
+ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
+
+#define rq_for_each_segment(bvl, _rq, _iter) \
+ __rq_for_each_bio(_iter.bio, _rq) \
+ bio_for_each_segment(bvl, _iter.bio, _iter.iter)
+
+#define rq_for_each_bvec(bvl, _rq, _iter) \
+ __rq_for_each_bio(_iter.bio, _rq) \
+ bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
+
+#define rq_iter_last(bvec, _iter) \
+ (_iter.bio->bi_next == NULL && \
+ bio_iter_last(bvec, _iter.iter))
+
+/*
+ * blk_rq_pos() : the current sector
+ * blk_rq_bytes() : bytes left in the entire request
+ * blk_rq_cur_bytes() : bytes left in the current segment
+ * blk_rq_err_bytes() : bytes left till the next error boundary
+ * blk_rq_sectors() : sectors left in the entire request
+ * blk_rq_cur_sectors() : sectors left in the current segment
+ * blk_rq_stats_sectors() : sectors of the entire request used for stats
+ */
+static inline sector_t blk_rq_pos(const struct request *rq)
+{
+ return rq->__sector;
+}
+
+static inline unsigned int blk_rq_bytes(const struct request *rq)
+{
+ return rq->__data_len;
+}
+
+static inline int blk_rq_cur_bytes(const struct request *rq)
+{
+ if (!rq->bio)
+ return 0;
+ if (!bio_has_data(rq->bio)) /* dataless requests such as discard */
+ return rq->bio->bi_iter.bi_size;
+ return bio_iovec(rq->bio).bv_len;
+}
+
+unsigned int blk_rq_err_bytes(const struct request *rq);
+
+static inline unsigned int blk_rq_sectors(const struct request *rq)
+{
+ return blk_rq_bytes(rq) >> SECTOR_SHIFT;
+}
+
+static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
+{
+ return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
+}
+
+static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
+{
+ return rq->stats_sectors;
+}
+
+/*
+ * Some commands like WRITE SAME have a payload or data transfer size which
+ * is different from the size of the request. Any driver that supports such
+ * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
+ * calculate the data transfer size.
+ */
+static inline unsigned int blk_rq_payload_bytes(struct request *rq)
+{
+ if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+ return rq->special_vec.bv_len;
+ return blk_rq_bytes(rq);
+}
+
+/*
+ * Return the first full biovec in the request. The caller needs to check that
+ * there are any bvecs before calling this helper.
+ */
+static inline struct bio_vec req_bvec(struct request *rq)
+{
+ if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+ return rq->special_vec;
+ return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
+}
+
+static inline unsigned int blk_rq_count_bios(struct request *rq)
+{
+ unsigned int nr_bios = 0;
+ struct bio *bio;
+
+ __rq_for_each_bio(bio, rq)
+ nr_bios++;
+
+ return nr_bios;
+}
+
+void blk_steal_bios(struct bio_list *list, struct request *rq);
+
+/*
+ * Request completion related functions.
+ *
+ * blk_update_request() completes given number of bytes and updates
+ * the request without completing it.
+ */
+bool blk_update_request(struct request *rq, blk_status_t error,
+ unsigned int nr_bytes);
+void blk_abort_request(struct request *);
+
+/*
+ * Number of physical segments as sent to the device.
+ *
+ * Normally this is the number of discontiguous data segments sent by the
+ * submitter. But for data-less command like discard we might have no
+ * actual data segments submitted, but the driver might have to add it's
+ * own special payload. In that case we still return 1 here so that this
+ * special payload will be mapped.
+ */
+static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
+{
+ if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+ return 1;
+ return rq->nr_phys_segments;
+}
+
+/*
+ * Number of discard segments (or ranges) the driver needs to fill in.
+ * Each discard bio merged into a request is counted as one segment.
+ */
+static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
+{
+ return max_t(unsigned short, rq->nr_phys_segments, 1);
+}
+
+int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
+ struct scatterlist *sglist, struct scatterlist **last_sg);
+static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+ struct scatterlist *sglist)
+{
+ struct scatterlist *last_sg = NULL;
+
+ return __blk_rq_map_sg(q, rq, sglist, &last_sg);
+}
+void blk_dump_rq_flags(struct request *, char *);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int blk_rq_zone_no(struct request *rq)
+{
+ return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
+}
+
+static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
+{
+ return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
+}
+
+bool blk_req_needs_zone_write_lock(struct request *rq);
+bool blk_req_zone_write_trylock(struct request *rq);
+void __blk_req_zone_write_lock(struct request *rq);
+void __blk_req_zone_write_unlock(struct request *rq);
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+ if (blk_req_needs_zone_write_lock(rq))
+ __blk_req_zone_write_lock(rq);
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+ if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
+ __blk_req_zone_write_unlock(rq);
+}
+
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+ return rq->q->seq_zones_wlock &&
+ test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+ if (!blk_req_needs_zone_write_lock(rq))
+ return true;
+ return !blk_req_zone_is_write_locked(rq);
+}
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline bool blk_req_needs_zone_write_lock(struct request *rq)
+{
+ return false;
+}
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+}
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+ return false;
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+ return true;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
#endif
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+void rq_flush_dcache_pages(struct request *rq);
+#else
+static inline void rq_flush_dcache_pages(struct request *rq)
+{
+}
+#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
+#endif /* BLK_MQ_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index be622b5a21ed..fe065c394fff 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -20,8 +20,26 @@ struct cgroup_subsys_state;
typedef void (bio_end_io_t) (struct bio *);
struct bio_crypt_ctx;
+/*
+ * The basic unit of block I/O is a sector. It is used in a number of contexts
+ * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9
+ * bytes. Variables of type sector_t represent an offset or size that is a
+ * multiple of 512 bytes. Hence these two constants.
+ */
+#ifndef SECTOR_SHIFT
+#define SECTOR_SHIFT 9
+#endif
+#ifndef SECTOR_SIZE
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
+#endif
+
+#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
+#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
+#define SECTOR_MASK (PAGE_SECTORS - 1)
+
struct block_device {
sector_t bd_start_sect;
+ sector_t bd_nr_sectors;
struct disk_stats __percpu *bd_stats;
unsigned long bd_stamp;
bool bd_read_only; /* read-only policy */
@@ -38,6 +56,7 @@ struct block_device {
u8 bd_partno;
spinlock_t bd_size_lock; /* for bd_inode->i_size updates */
struct gendisk * bd_disk;
+ struct request_queue * bd_queue;
/* The counter of freeze processes */
int bd_fsfreeze_count;
@@ -208,6 +227,9 @@ static inline void bio_issue_init(struct bio_issue *issue,
((u64)size << BIO_ISSUE_SIZE_SHIFT));
}
+typedef unsigned int blk_qc_t;
+#define BLK_QC_T_NONE -1U
+
/*
* main unit of I/O for the block layer and lower layers (ie drivers and
* stacking drivers)
@@ -227,8 +249,8 @@ struct bio {
struct bvec_iter bi_iter;
+ blk_qc_t bi_cookie;
bio_end_io_t *bi_end_io;
-
void *bi_private;
#ifdef CONFIG_BLK_CGROUP
/*
@@ -384,7 +406,7 @@ enum req_flag_bits {
/* command specific flags for REQ_OP_WRITE_ZEROES: */
__REQ_NOUNMAP, /* do not free blocks when zeroing */
- __REQ_HIPRI,
+ __REQ_POLLED, /* caller polls for completion using bio_poll */
/* for driver use */
__REQ_DRV,
@@ -409,7 +431,7 @@ enum req_flag_bits {
#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT)
#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP)
-#define REQ_HIPRI (1ULL << __REQ_HIPRI)
+#define REQ_POLLED (1ULL << __REQ_POLLED)
#define REQ_DRV (1ULL << __REQ_DRV)
#define REQ_SWAP (1ULL << __REQ_SWAP)
@@ -431,8 +453,6 @@ enum stat_group {
#define bio_op(bio) \
((bio)->bi_opf & REQ_OP_MASK)
-#define req_op(req) \
- ((req)->cmd_flags & REQ_OP_MASK)
/* obsolete, don't use in new code */
static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
@@ -497,31 +517,6 @@ static inline int op_stat_group(unsigned int op)
return op_is_write(op);
}
-typedef unsigned int blk_qc_t;
-#define BLK_QC_T_NONE -1U
-#define BLK_QC_T_SHIFT 16
-#define BLK_QC_T_INTERNAL (1U << 31)
-
-static inline bool blk_qc_t_valid(blk_qc_t cookie)
-{
- return cookie != BLK_QC_T_NONE;
-}
-
-static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
-{
- return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
-}
-
-static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
-{
- return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
-}
-
-static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
-{
- return (cookie & BLK_QC_T_INTERNAL) != 0;
-}
-
struct blk_rq_stat {
u64 mean;
u64 min;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 12b9dbcc980e..bd4370baccca 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -3,8 +3,6 @@
#define _LINUX_BLKDEV_H
#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/major.h>
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/llist.h>
@@ -12,17 +10,11 @@
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/wait.h>
-#include <linux/mempool.h>
-#include <linux/pfn.h>
#include <linux/bio.h>
-#include <linux/stringify.h>
#include <linux/gfp.h>
-#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/percpu-refcount.h>
-#include <linux/scatterlist.h>
#include <linux/blkzoned.h>
-#include <linux/pm.h>
#include <linux/sbitmap.h>
struct module;
@@ -33,14 +25,12 @@ struct request;
struct sg_io_hdr;
struct blkcg_gq;
struct blk_flush_queue;
+struct kiocb;
struct pr_ops;
struct rq_qos;
struct blk_queue_stats;
struct blk_stat_callback;
-struct blk_keyslot_manager;
-
-#define BLKDEV_MIN_RQ 4
-#define BLKDEV_MAX_RQ 128 /* Default maximum */
+struct blk_crypto_profile;
/* Must be consistent with blk_mq_poll_stats_bkt() */
#define BLK_MQ_POLL_STATS_BKTS 16
@@ -54,186 +44,13 @@ struct blk_keyslot_manager;
*/
#define BLKCG_MAX_POLS 6
-typedef void (rq_end_io_fn)(struct request *, blk_status_t);
-
-/*
- * request flags */
-typedef __u32 __bitwise req_flags_t;
-
-/* drive already may have started this one */
-#define RQF_STARTED ((__force req_flags_t)(1 << 1))
-/* may not be passed by ioscheduler */
-#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3))
-/* request for flush sequence */
-#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4))
-/* merge of different types, fail separately */
-#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5))
-/* track inflight for MQ */
-#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6))
-/* don't call prep for this one */
-#define RQF_DONTPREP ((__force req_flags_t)(1 << 7))
-/* vaguely specified driver internal error. Ignored by the block layer */
-#define RQF_FAILED ((__force req_flags_t)(1 << 10))
-/* don't warn about errors */
-#define RQF_QUIET ((__force req_flags_t)(1 << 11))
-/* elevator private data attached */
-#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12))
-/* account into disk and partition IO statistics */
-#define RQF_IO_STAT ((__force req_flags_t)(1 << 13))
-/* runtime pm request */
-#define RQF_PM ((__force req_flags_t)(1 << 15))
-/* on IO scheduler merge hash */
-#define RQF_HASHED ((__force req_flags_t)(1 << 16))
-/* track IO completion time */
-#define RQF_STATS ((__force req_flags_t)(1 << 17))
-/* Look at ->special_vec for the actual data payload instead of the
- bio chain. */
-#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18))
-/* The per-zone write lock is held for this request */
-#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19))
-/* already slept for hybrid poll */
-#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20))
-/* ->timeout has been called, don't expire again */
-#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21))
-
-/* flags that prevent us from merging requests: */
-#define RQF_NOMERGE_FLAGS \
- (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
-
-/*
- * Request state for blk-mq.
- */
-enum mq_rq_state {
- MQ_RQ_IDLE = 0,
- MQ_RQ_IN_FLIGHT = 1,
- MQ_RQ_COMPLETE = 2,
-};
-
-/*
- * Try to put the fields that are referenced together in the same cacheline.
- *
- * If you modify this structure, make sure to update blk_rq_init() and
- * especially blk_mq_rq_ctx_init() to take care of the added fields.
- */
-struct request {
- struct request_queue *q;
- struct blk_mq_ctx *mq_ctx;
- struct blk_mq_hw_ctx *mq_hctx;
-
- unsigned int cmd_flags; /* op and common flags */
- req_flags_t rq_flags;
-
- int tag;
- int internal_tag;
-
- /* the following two fields are internal, NEVER access directly */
- unsigned int __data_len; /* total data len */
- sector_t __sector; /* sector cursor */
-
- struct bio *bio;
- struct bio *biotail;
-
- struct list_head queuelist;
-
- /*
- * The hash is used inside the scheduler, and killed once the
- * request reaches the dispatch list. The ipi_list is only used
- * to queue the request for softirq completion, which is long
- * after the request has been unhashed (and even removed from
- * the dispatch list).
- */
- union {
- struct hlist_node hash; /* merge hash */
- struct llist_node ipi_list;
- };
-
- /*
- * The rb_node is only used inside the io scheduler, requests
- * are pruned when moved to the dispatch queue. So let the
- * completion_data share space with the rb_node.
- */
- union {
- struct rb_node rb_node; /* sort/lookup */
- struct bio_vec special_vec;
- void *completion_data;
- int error_count; /* for legacy drivers, don't use */
- };
-
- /*
- * Three pointers are available for the IO schedulers, if they need
- * more they have to dynamically allocate it. Flush requests are
- * never put on the IO scheduler. So let the flush fields share
- * space with the elevator data.
- */
- union {
- struct {
- struct io_cq *icq;
- void *priv[2];
- } elv;
-
- struct {
- unsigned int seq;
- struct list_head list;
- rq_end_io_fn *saved_end_io;
- } flush;
- };
-
- struct gendisk *rq_disk;
- struct block_device *part;
-#ifdef CONFIG_BLK_RQ_ALLOC_TIME
- /* Time that the first bio started allocating this request. */
- u64 alloc_time_ns;
-#endif
- /* Time that this request was allocated for this IO. */
- u64 start_time_ns;
- /* Time that I/O was submitted to the device. */
- u64 io_start_time_ns;
-
-#ifdef CONFIG_BLK_WBT
- unsigned short wbt_flags;
-#endif
- /*
- * rq sectors used for blk stats. It has the same value
- * with blk_rq_sectors(rq), except that it never be zeroed
- * by completion.
- */
- unsigned short stats_sectors;
-
- /*
- * Number of scatter-gather DMA addr+len pairs after
- * physical address coalescing is performed.
- */
- unsigned short nr_phys_segments;
-
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
- unsigned short nr_integrity_segments;
-#endif
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- struct bio_crypt_ctx *crypt_ctx;
- struct blk_ksm_keyslot *crypt_keyslot;
-#endif
-
- unsigned short write_hint;
- unsigned short ioprio;
-
- enum mq_rq_state state;
- refcount_t ref;
-
- unsigned int timeout;
- unsigned long deadline;
-
- union {
- struct __call_single_data csd;
- u64 fifo_time;
- };
+static inline int blk_validate_block_size(unsigned int bsize)
+{
+ if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+ return -EINVAL;
- /*
- * completion callback.
- */
- rq_end_io_fn *end_io;
- void *end_io_data;
-};
+ return 0;
+}
static inline bool blk_op_is_passthrough(unsigned int op)
{
@@ -241,35 +58,6 @@ static inline bool blk_op_is_passthrough(unsigned int op)
return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
}
-static inline bool blk_rq_is_passthrough(struct request *rq)
-{
- return blk_op_is_passthrough(req_op(rq));
-}
-
-static inline unsigned short req_get_ioprio(struct request *req)
-{
- return req->ioprio;
-}
-
-#include <linux/elevator.h>
-
-struct blk_queue_ctx;
-
-struct bio_vec;
-
-enum blk_eh_timer_return {
- BLK_EH_DONE, /* drivers has completed the command */
- BLK_EH_RESET_TIMER, /* reset timer and try again */
-};
-
-enum blk_queue_state {
- Queue_down,
- Queue_up,
-};
-
-#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
-#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
-
/*
* Zoned block device models (zoned limit).
*
@@ -370,6 +158,34 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
#endif /* CONFIG_BLK_DEV_ZONED */
+/*
+ * Independent access ranges: struct blk_independent_access_range describes
+ * a range of contiguous sectors that can be accessed using device command
+ * execution resources that are independent from the resources used for
+ * other access ranges. This is typically found with single-LUN multi-actuator
+ * HDDs where each access range is served by a different set of heads.
+ * The set of independent ranges supported by the device is defined using
+ * struct blk_independent_access_ranges. The independent ranges must not overlap
+ * and must include all sectors within the disk capacity (no sector holes
+ * allowed).
+ * For a device with multiple ranges, requests targeting sectors in different
+ * ranges can be executed in parallel. A request can straddle an access range
+ * boundary.
+ */
+struct blk_independent_access_range {
+ struct kobject kobj;
+ struct request_queue *queue;
+ sector_t sector;
+ sector_t nr_sectors;
+};
+
+struct blk_independent_access_ranges {
+ struct kobject kobj;
+ bool sysfs_registered;
+ unsigned int nr_ia_ranges;
+ struct blk_independent_access_range ia_range[];
+};
+
struct request_queue {
struct request *last_merge;
struct elevator_queue *elevator;
@@ -444,8 +260,7 @@ struct request_queue {
unsigned int dma_alignment;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- /* Inline crypto capabilities */
- struct blk_keyslot_manager *ksm;
+ struct blk_crypto_profile *crypto_profile;
#endif
unsigned int rq_timeout;
@@ -457,10 +272,9 @@ struct request_queue {
struct timer_list timeout;
struct work_struct timeout_work;
- atomic_t nr_active_requests_shared_sbitmap;
+ atomic_t nr_active_requests_shared_tags;
- struct sbitmap_queue sched_bitmap_tags;
- struct sbitmap_queue sched_breserved_tags;
+ struct blk_mq_tags *sched_shared_tags;
struct list_head icq_list;
#ifdef CONFIG_BLK_CGROUP
@@ -536,6 +350,8 @@ struct request_queue {
*/
struct mutex mq_freeze_lock;
+ int quiesce_depth;
+
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set bio_split;
@@ -549,10 +365,14 @@ struct request_queue {
bool mq_sysfs_init_done;
- size_t cmd_size;
-
#define BLK_MAX_WRITE_HINTS 5
u64 write_hints[BLK_MAX_WRITE_HINTS];
+
+ /*
+ * Independent sector access ranges. This is always NULL for
+ * devices that do not have multiple independent access ranges.
+ */
+ struct blk_independent_access_ranges *ia_ranges;
};
/* Keep blk_queue_flag_name[] in sync with the definitions below */
@@ -579,7 +399,6 @@ struct request_queue {
#define QUEUE_FLAG_STATS 20 /* track IO start and completion times */
#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */
#define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */
-#define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */
#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */
#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */
#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */
@@ -613,8 +432,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_secure_erase(q) \
(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
-#define blk_queue_scsi_passthrough(q) \
- test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags)
#define blk_queue_pci_p2pdma(q) \
test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
@@ -638,11 +455,6 @@ extern void blk_clear_pm_only(struct request_queue *q);
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
-#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ)
-
-#define rq_dma_dir(rq) \
- (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
-
#define dma_map_bvec(dev, bv, dir, attrs) \
dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
(dir), (attrs))
@@ -758,42 +570,6 @@ static inline unsigned int queue_max_active_zones(const struct request_queue *q)
}
#endif /* CONFIG_BLK_DEV_ZONED */
-static inline bool rq_is_sync(struct request *rq)
-{
- return op_is_sync(rq->cmd_flags);
-}
-
-static inline bool rq_mergeable(struct request *rq)
-{
- if (blk_rq_is_passthrough(rq))
- return false;
-
- if (req_op(rq) == REQ_OP_FLUSH)
- return false;
-
- if (req_op(rq) == REQ_OP_WRITE_ZEROES)
- return false;
-
- if (req_op(rq) == REQ_OP_ZONE_APPEND)
- return false;
-
- if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
- return false;
- if (rq->rq_flags & RQF_NOMERGE_FLAGS)
- return false;
-
- return true;
-}
-
-static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
-{
- if (bio_page(a) == bio_page(b) &&
- bio_offset(a) == bio_offset(b))
- return true;
-
- return false;
-}
-
static inline unsigned int blk_queue_depth(struct request_queue *q)
{
if (q->queue_depth)
@@ -808,83 +584,20 @@ static inline unsigned int blk_queue_depth(struct request_queue *q)
#define BLK_DEFAULT_SG_TIMEOUT (60 * HZ)
#define BLK_MIN_SG_TIMEOUT (7 * HZ)
-struct rq_map_data {
- struct page **pages;
- int page_order;
- int nr_entries;
- unsigned long offset;
- int null_mapped;
- int from_user;
-};
-
-struct req_iterator {
- struct bvec_iter iter;
- struct bio *bio;
-};
-
/* This should not be used directly - use rq_for_each_segment */
#define for_each_bio(_bio) \
for (; _bio; _bio = _bio->bi_next)
-#define __rq_for_each_bio(_bio, rq) \
- if ((rq->bio)) \
- for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
-#define rq_for_each_segment(bvl, _rq, _iter) \
- __rq_for_each_bio(_iter.bio, _rq) \
- bio_for_each_segment(bvl, _iter.bio, _iter.iter)
-
-#define rq_for_each_bvec(bvl, _rq, _iter) \
- __rq_for_each_bio(_iter.bio, _rq) \
- bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
-
-#define rq_iter_last(bvec, _iter) \
- (_iter.bio->bi_next == NULL && \
- bio_iter_last(bvec, _iter.iter))
-
-#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
-#endif
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-extern void rq_flush_dcache_pages(struct request *rq);
-#else
-static inline void rq_flush_dcache_pages(struct request *rq)
-{
-}
-#endif
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
-blk_qc_t submit_bio_noacct(struct bio *bio);
-extern void blk_rq_init(struct request_queue *q, struct request *rq);
-extern void blk_put_request(struct request *);
-extern struct request *blk_get_request(struct request_queue *, unsigned int op,
- blk_mq_req_flags_t flags);
+void submit_bio_noacct(struct bio *bio);
+
extern int blk_lld_busy(struct request_queue *q);
-extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
- struct bio_set *bs, gfp_t gfp_mask,
- int (*bio_ctr)(struct bio *, struct bio *, void *),
- void *data);
-extern void blk_rq_unprep_clone(struct request *rq);
-extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
- struct request *rq);
-int blk_rq_append_bio(struct request *rq, struct bio *bio);
extern void blk_queue_split(struct bio **);
extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
extern void blk_queue_exit(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);
-extern int blk_rq_map_user(struct request_queue *, struct request *,
- struct rq_map_data *, void __user *, unsigned long,
- gfp_t);
-extern int blk_rq_unmap_user(struct bio *);
-extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
-extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
- struct rq_map_data *, const struct iov_iter *,
- gfp_t);
-extern void blk_execute_rq_nowait(struct gendisk *,
- struct request *, int, rq_end_io_fn *);
-
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
- int at_head);
/* Helper to convert REQ_OP_XXX to its string format XXX */
extern const char *blk_op_str(unsigned int op);
@@ -892,69 +605,17 @@ extern const char *blk_op_str(unsigned int op);
int blk_status_to_errno(blk_status_t status);
blk_status_t errno_to_blk_status(int errno);
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
+/* only poll the hardware once, don't continue until a completion was found */
+#define BLK_POLL_ONESHOT (1 << 0)
+/* do not sleep to wait for the expected completion time */
+#define BLK_POLL_NOSLEEP (1 << 1)
+int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags);
+int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
+ unsigned int flags);
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
{
- return bdev->bd_disk->queue; /* this is never NULL */
-}
-
-/*
- * The basic unit of block I/O is a sector. It is used in a number of contexts
- * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9
- * bytes. Variables of type sector_t represent an offset or size that is a
- * multiple of 512 bytes. Hence these two constants.
- */
-#ifndef SECTOR_SHIFT
-#define SECTOR_SHIFT 9
-#endif
-#ifndef SECTOR_SIZE
-#define SECTOR_SIZE (1 << SECTOR_SHIFT)
-#endif
-
-#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
-#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
-#define SECTOR_MASK (PAGE_SECTORS - 1)
-
-/*
- * blk_rq_pos() : the current sector
- * blk_rq_bytes() : bytes left in the entire request
- * blk_rq_cur_bytes() : bytes left in the current segment
- * blk_rq_err_bytes() : bytes left till the next error boundary
- * blk_rq_sectors() : sectors left in the entire request
- * blk_rq_cur_sectors() : sectors left in the current segment
- * blk_rq_stats_sectors() : sectors of the entire request used for stats
- */
-static inline sector_t blk_rq_pos(const struct request *rq)
-{
- return rq->__sector;
-}
-
-static inline unsigned int blk_rq_bytes(const struct request *rq)
-{
- return rq->__data_len;
-}
-
-static inline int blk_rq_cur_bytes(const struct request *rq)
-{
- return rq->bio ? bio_cur_bytes(rq->bio) : 0;
-}
-
-extern unsigned int blk_rq_err_bytes(const struct request *rq);
-
-static inline unsigned int blk_rq_sectors(const struct request *rq)
-{
- return blk_rq_bytes(rq) >> SECTOR_SHIFT;
-}
-
-static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
-{
- return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
-}
-
-static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
-{
- return rq->stats_sectors;
+ return bdev->bd_queue; /* this is never NULL */
}
#ifdef CONFIG_BLK_DEV_ZONED
@@ -973,42 +634,8 @@ static inline unsigned int bio_zone_is_seq(struct bio *bio)
return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev),
bio->bi_iter.bi_sector);
}
-
-static inline unsigned int blk_rq_zone_no(struct request *rq)
-{
- return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
-}
-
-static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
-{
- return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
-}
#endif /* CONFIG_BLK_DEV_ZONED */
-/*
- * Some commands like WRITE SAME have a payload or data transfer size which
- * is different from the size of the request. Any driver that supports such
- * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
- * calculate the data transfer size.
- */
-static inline unsigned int blk_rq_payload_bytes(struct request *rq)
-{
- if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
- return rq->special_vec.bv_len;
- return blk_rq_bytes(rq);
-}
-
-/*
- * Return the first full biovec in the request. The caller needs to check that
- * there are any bvecs before calling this helper.
- */
-static inline struct bio_vec req_bvec(struct request *rq)
-{
- if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
- return rq->special_vec;
- return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
-}
-
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
int op)
{
@@ -1048,47 +675,6 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
return min(q->limits.max_sectors, chunk_sectors);
}
-static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
- sector_t offset)
-{
- struct request_queue *q = rq->q;
-
- if (blk_rq_is_passthrough(rq))
- return q->limits.max_hw_sectors;
-
- if (!q->limits.chunk_sectors ||
- req_op(rq) == REQ_OP_DISCARD ||
- req_op(rq) == REQ_OP_SECURE_ERASE)
- return blk_queue_get_max_sectors(q, req_op(rq));
-
- return min(blk_max_size_offset(q, offset, 0),
- blk_queue_get_max_sectors(q, req_op(rq)));
-}
-
-static inline unsigned int blk_rq_count_bios(struct request *rq)
-{
- unsigned int nr_bios = 0;
- struct bio *bio;
-
- __rq_for_each_bio(bio, rq)
- nr_bios++;
-
- return nr_bios;
-}
-
-void blk_steal_bios(struct bio_list *list, struct request *rq);
-
-/*
- * Request completion related functions.
- *
- * blk_update_request() completes given number of bytes and updates
- * the request without completing it.
- */
-extern bool blk_update_request(struct request *rq, blk_status_t error,
- unsigned int nr_bytes);
-
-extern void blk_abort_request(struct request *);
-
/*
* Access functions for manipulating queue properties
*/
@@ -1133,46 +719,24 @@ extern void blk_queue_dma_alignment(struct request_queue *, int);
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
-extern void blk_queue_required_elevator_features(struct request_queue *q,
- unsigned int features);
-extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
- struct device *dev);
-/*
- * Number of physical segments as sent to the device.
- *
- * Normally this is the number of discontiguous data segments sent by the
- * submitter. But for data-less command like discard we might have no
- * actual data segments submitted, but the driver might have to add it's
- * own special payload. In that case we still return 1 here so that this
- * special payload will be mapped.
- */
-static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
-{
- if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
- return 1;
- return rq->nr_phys_segments;
-}
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
+void disk_set_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars);
/*
- * Number of discard segments (or ranges) the driver needs to fill in.
- * Each discard bio merged into a request is counted as one segment.
+ * Elevator features for blk_queue_required_elevator_features:
*/
-static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
-{
- return max_t(unsigned short, rq->nr_phys_segments, 1);
-}
-
-int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
- struct scatterlist *sglist, struct scatterlist **last_sg);
-static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
- struct scatterlist *sglist)
-{
- struct scatterlist *last_sg = NULL;
+/* Supports zoned block devices sequential write constraint */
+#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0)
+/* Supports scheduling on multiple hardware queues */
+#define ELEVATOR_F_MQ_AWARE (1U << 1)
- return __blk_rq_map_sg(q, rq, sglist, &last_sg);
-}
-extern void blk_dump_rq_flags(struct request *, char *);
+extern void blk_queue_required_elevator_features(struct request_queue *q,
+ unsigned int features);
+extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
+ struct device *dev);
bool __must_check blk_get_queue(struct request_queue *);
extern void blk_put_queue(struct request_queue *);
@@ -1187,19 +751,24 @@ extern void blk_set_queue_dying(struct request_queue *);
* as the lock contention for request_queue lock is reduced.
*
* It is ok not to disable preemption when adding the request to the plug list
- * or when attempting a merge, because blk_schedule_flush_list() will only flush
- * the plug list when the task sleeps by itself. For details, please see
- * schedule() where blk_schedule_flush_plug() is called.
+ * or when attempting a merge. For details, please see schedule() where
+ * blk_flush_plug() is called.
*/
struct blk_plug {
- struct list_head mq_list; /* blk-mq requests */
- struct list_head cb_list; /* md requires an unplug callback */
+ struct request *mq_list; /* blk-mq requests */
+
+ /* if ios_left is > 1, we can batch tag/rq allocations */
+ struct request *cached_rq;
+ unsigned short nr_ios;
+
unsigned short rq_count;
+
bool multiple_queues;
+ bool has_elevator;
bool nowait;
+
+ struct list_head cb_list; /* md requires an unplug callback */
};
-#define BLK_MAX_REQUEST_COUNT 16
-#define BLK_PLUG_FLUSH_SIZE (128 * 1024)
struct blk_plug_cb;
typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
@@ -1211,32 +780,17 @@ struct blk_plug_cb {
extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
void *data, int size);
extern void blk_start_plug(struct blk_plug *);
+extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short);
extern void blk_finish_plug(struct blk_plug *);
-extern void blk_flush_plug_list(struct blk_plug *, bool);
-
-static inline void blk_flush_plug(struct task_struct *tsk)
-{
- struct blk_plug *plug = tsk->plug;
- if (plug)
- blk_flush_plug_list(plug, false);
-}
-
-static inline void blk_schedule_flush_plug(struct task_struct *tsk)
-{
- struct blk_plug *plug = tsk->plug;
-
- if (plug)
- blk_flush_plug_list(plug, true);
-}
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule);
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
return plug &&
- (!list_empty(&plug->mq_list) ||
- !list_empty(&plug->cb_list));
+ (plug->mq_list || !list_empty(&plug->cb_list));
}
int blkdev_issue_flush(struct block_device *bdev);
@@ -1245,23 +799,23 @@ long nr_blockdev_pages(void);
struct blk_plug {
};
-static inline void blk_start_plug(struct blk_plug *plug)
+static inline void blk_start_plug_nr_ios(struct blk_plug *plug,
+ unsigned short nr_ios)
{
}
-static inline void blk_finish_plug(struct blk_plug *plug)
+static inline void blk_start_plug(struct blk_plug *plug)
{
}
-static inline void blk_flush_plug(struct task_struct *task)
+static inline void blk_finish_plug(struct blk_plug *plug)
{
}
-static inline void blk_schedule_flush_plug(struct task_struct *task)
+static inline void blk_flush_plug(struct blk_plug *plug, bool async)
{
}
-
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
return false;
@@ -1499,22 +1053,6 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
return offset << SECTOR_SHIFT;
}
-/*
- * Two cases of handling DISCARD merge:
- * If max_discard_segments > 1, the driver takes every bio
- * as a range and send them to controller together. The ranges
- * needn't to be contiguous.
- * Otherwise, the bios/requests will be handled as same as
- * others which should be contiguous.
- */
-static inline bool blk_discard_mergable(struct request *req)
-{
- if (req_op(req) == REQ_OP_DISCARD &&
- queue_max_discard_segments(req->q) > 1)
- return true;
- return false;
-}
-
static inline int bdev_discard_alignment(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
@@ -1628,210 +1166,36 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
MODULE_ALIAS("block-major-" __stringify(major) "-*")
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-enum blk_integrity_flags {
- BLK_INTEGRITY_VERIFY = 1 << 0,
- BLK_INTEGRITY_GENERATE = 1 << 1,
- BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2,
- BLK_INTEGRITY_IP_CHECKSUM = 1 << 3,
-};
-
-struct blk_integrity_iter {
- void *prot_buf;
- void *data_buf;
- sector_t seed;
- unsigned int data_size;
- unsigned short interval;
- const char *disk_name;
-};
-
-typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
-typedef void (integrity_prepare_fn) (struct request *);
-typedef void (integrity_complete_fn) (struct request *, unsigned int);
-
-struct blk_integrity_profile {
- integrity_processing_fn *generate_fn;
- integrity_processing_fn *verify_fn;
- integrity_prepare_fn *prepare_fn;
- integrity_complete_fn *complete_fn;
- const char *name;
-};
-
-extern void blk_integrity_register(struct gendisk *, struct blk_integrity *);
-extern void blk_integrity_unregister(struct gendisk *);
-extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
-extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
- struct scatterlist *);
-extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
-{
- struct blk_integrity *bi = &disk->queue->integrity;
-
- if (!bi->profile)
- return NULL;
-
- return bi;
-}
-
-static inline
-struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
-{
- return blk_get_integrity(bdev->bd_disk);
-}
-
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
- return q->integrity.profile;
-}
-
-static inline bool blk_integrity_rq(struct request *rq)
-{
- return rq->cmd_flags & REQ_INTEGRITY;
-}
-
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
- unsigned int segs)
-{
- q->limits.max_integrity_segments = segs;
-}
-
-static inline unsigned short
-queue_max_integrity_segments(const struct request_queue *q)
-{
- return q->limits.max_integrity_segments;
-}
-
-/**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi: blk_integrity profile for device
- * @sectors: Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device. Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
-/*
- * Return the first bvec that contains integrity data. Only drivers that are
- * limited to a single integrity segment should use this helper.
- */
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
-{
- if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
- return NULL;
- return rq->bio->bi_integrity->bip_vec;
-}
-
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-
-struct bio;
-struct block_device;
-struct gendisk;
-struct blk_integrity;
-
-static inline int blk_integrity_rq(struct request *rq)
-{
- return 0;
-}
-static inline int blk_rq_count_integrity_sg(struct request_queue *q,
- struct bio *b)
-{
- return 0;
-}
-static inline int blk_rq_map_integrity_sg(struct request_queue *q,
- struct bio *b,
- struct scatterlist *s)
-{
- return 0;
-}
-static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
-{
- return NULL;
-}
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
-{
- return NULL;
-}
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
- return false;
-}
-static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
-{
- return 0;
-}
-static inline void blk_integrity_register(struct gendisk *d,
- struct blk_integrity *b)
-{
-}
-static inline void blk_integrity_unregister(struct gendisk *d)
-{
-}
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
- unsigned int segs)
-{
-}
-static inline unsigned short queue_max_integrity_segments(const struct request_queue *q)
-{
- return 0;
-}
-
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return 0;
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return 0;
-}
-
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
-{
- return NULL;
-}
-
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
+bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q);
-void blk_ksm_unregister(struct request_queue *q);
+void blk_crypto_unregister(struct request_queue *q);
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
- struct request_queue *q)
+static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q)
{
return true;
}
-static inline void blk_ksm_unregister(struct request_queue *q) { }
+static inline void blk_crypto_unregister(struct request_queue *q) { }
#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+enum blk_unique_id {
+ /* these match the Designator Types specified in SPC */
+ BLK_UID_T10 = 1,
+ BLK_UID_EUI64 = 2,
+ BLK_UID_NAA = 3,
+};
+
+#define NFL4_UFLG_MASK 0x0000003F
struct block_device_operations {
- blk_qc_t (*submit_bio) (struct bio *bio);
+ void (*submit_bio)(struct bio *bio);
int (*open) (struct block_device *, fmode_t);
void (*release) (struct gendisk *, fmode_t);
int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
@@ -1847,6 +1211,9 @@ struct block_device_operations {
int (*report_zones)(struct gendisk *, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
char *(*devnode)(struct gendisk *disk, umode_t *mode);
+ /* returns the length of the identifier or a negative errno: */
+ int (*get_unique_id)(struct gendisk *disk, u8 id[16],
+ enum blk_unique_id id_type);
struct module *owner;
const struct pr_ops *pr_ops;
@@ -1869,60 +1236,6 @@ 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 *);
-#ifdef CONFIG_BLK_DEV_ZONED
-bool blk_req_needs_zone_write_lock(struct request *rq);
-bool blk_req_zone_write_trylock(struct request *rq);
-void __blk_req_zone_write_lock(struct request *rq);
-void __blk_req_zone_write_unlock(struct request *rq);
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
- if (blk_req_needs_zone_write_lock(rq))
- __blk_req_zone_write_lock(rq);
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
- if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
- __blk_req_zone_write_unlock(rq);
-}
-
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
- return rq->q->seq_zones_wlock &&
- test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
- if (!blk_req_needs_zone_write_lock(rq))
- return true;
- return !blk_req_zone_is_write_locked(rq);
-}
-#else
-static inline bool blk_req_needs_zone_write_lock(struct request *rq)
-{
- return false;
-}
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-}
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
- return false;
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
- return true;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
static inline void blk_wake_io_task(struct task_struct *waiter)
{
/*
@@ -1991,6 +1304,8 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
#ifdef CONFIG_BLOCK
void invalidate_bdev(struct block_device *bdev);
int sync_blockdev(struct block_device *bdev);
+int sync_blockdev_nowait(struct block_device *bdev);
+void sync_bdevs(bool wait);
#else
static inline void invalidate_bdev(struct block_device *bdev)
{
@@ -1999,10 +1314,54 @@ static inline int sync_blockdev(struct block_device *bdev)
{
return 0;
}
+static inline int sync_blockdev_nowait(struct block_device *bdev)
+{
+ return 0;
+}
+static inline void sync_bdevs(bool wait)
+{
+}
#endif
int fsync_bdev(struct block_device *bdev);
int freeze_bdev(struct block_device *bdev);
int thaw_bdev(struct block_device *bdev);
+struct io_comp_batch {
+ struct request *req_list;
+ bool need_ts;
+ void (*complete)(struct io_comp_batch *);
+};
+
+#define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { }
+
+#define rq_list_add(listptr, rq) do { \
+ (rq)->rq_next = *(listptr); \
+ *(listptr) = rq; \
+} while (0)
+
+#define rq_list_pop(listptr) \
+({ \
+ struct request *__req = NULL; \
+ if ((listptr) && *(listptr)) { \
+ __req = *(listptr); \
+ *(listptr) = __req->rq_next; \
+ } \
+ __req; \
+})
+
+#define rq_list_peek(listptr) \
+({ \
+ struct request *__req = NULL; \
+ if ((listptr) && *(listptr)) \
+ __req = *(listptr); \
+ __req; \
+})
+
+#define rq_list_for_each(listptr, pos) \
+ for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \
+
+#define rq_list_next(rq) (rq)->rq_next
+#define rq_list_empty(list) ((list) == (struct request *) NULL)
+
#endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index a083e15df608..22501a293fa5 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -2,7 +2,7 @@
#ifndef BLKTRACE_H
#define BLKTRACE_H
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
#include <linux/relay.h>
#include <linux/compat.h>
#include <uapi/linux/blktrace_api.h>
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 020a7d5bf470..3db6f6c95489 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -929,8 +929,11 @@ struct bpf_array_aux {
* stored in the map to make sure that all callers and callees have
* the same prog type and JITed flag.
*/
- enum bpf_prog_type type;
- bool jited;
+ struct {
+ spinlock_t lock;
+ enum bpf_prog_type type;
+ bool jited;
+ } owner;
/* Programs with direct jumps into programs part of this array. */
struct list_head poke_progs;
struct bpf_map *map;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9c81724e4b98..bbe1eefa4c8a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -101,14 +101,14 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
-#ifdef CONFIG_NET
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
#ifdef CONFIG_BPF_LSM
BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
+#ifdef CONFIG_NET
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 0e9bdd42dafb..35c25dff651a 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -44,7 +44,7 @@ struct bvec_iter {
unsigned int bi_bvec_done; /* number of bytes completed in
current bvec */
-};
+} __packed;
struct bvec_iter_all {
struct bio_vec bv;
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index c4fef00abdf3..0a89f111e00e 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -64,6 +64,7 @@ struct cdrom_device_info {
int for_data;
int (*exit)(struct cdrom_device_info *);
int mrw_mode_page;
+ __s64 last_media_change_ms;
};
struct cdrom_device_ops {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 114553b487ef..a7df155ea49b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -576,9 +576,9 @@ struct dm_table *dm_swap_table(struct mapped_device *md,
struct dm_table *t);
/*
- * Table keyslot manager functions
+ * Table blk_crypto_profile functions
*/
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm);
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile);
/*-----------------------------------------------------------------
* Macros.
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4a93c12543ee..ef03ff34234d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1051,6 +1051,7 @@ extern int bpf_jit_enable;
extern int bpf_jit_harden;
extern int bpf_jit_kallsyms;
extern long bpf_jit_limit;
+extern long bpf_jit_limit_max;
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h
index c12df59d3f5f..3e378b1fb0bc 100644
--- a/include/linux/flex_proportions.h
+++ b/include/linux/flex_proportions.h
@@ -83,9 +83,10 @@ struct fprop_local_percpu {
int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp);
void fprop_local_destroy_percpu(struct fprop_local_percpu *pl);
-void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl);
-void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl,
- int max_frac);
+void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl,
+ long nr);
+void __fprop_add_percpu_max(struct fprop_global *p,
+ struct fprop_local_percpu *pl, int max_frac, long nr);
void fprop_fraction_percpu(struct fprop_global *p,
struct fprop_local_percpu *pl, unsigned long *numerator,
unsigned long *denominator);
@@ -96,7 +97,7 @@ void fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
unsigned long flags;
local_irq_save(flags);
- __fprop_inc_percpu(p, pl);
+ __fprop_add_percpu(p, pl, 1);
local_irq_restore(flags);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 56eba723477e..f3cfca5edc9a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -48,6 +48,7 @@
struct backing_dev_info;
struct bdi_writeback;
struct bio;
+struct io_comp_batch;
struct export_operations;
struct fiemap_extent_info;
struct hd_geometry;
@@ -329,16 +330,12 @@ struct kiocb {
randomized_struct_fields_start
loff_t ki_pos;
- void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
+ void (*ki_complete)(struct kiocb *iocb, long ret);
void *private;
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
- union {
- unsigned int ki_cookie; /* for ->iopoll */
- struct wait_page_queue *ki_waitq; /* for async buffered IO */
- };
-
+ struct wait_page_queue *ki_waitq; /* for async buffered IO */
randomized_struct_fields_end
};
@@ -2075,7 +2072,8 @@ struct file_operations {
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
- int (*iopoll)(struct kiocb *kiocb, bool spin);
+ int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
+ unsigned int flags);
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index e912ed9141d9..91ea9477e9bd 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -118,9 +118,6 @@ struct fscrypt_operations {
*/
bool (*empty_dir)(struct inode *inode);
- /* The filesystem's maximum ciphertext filename length, in bytes */
- unsigned int max_namelen;
-
/*
* Check whether the filesystem's inode numbers and UUID are stable,
* meaning that they will never be changed even by offline operations
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 0f5315c2b5a3..59eabbc3a36b 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -12,12 +12,10 @@
#include <linux/types.h>
#include <linux/kdev_t.h>
-#include <linux/rcupdate.h>
-#include <linux/slab.h>
-#include <linux/percpu-refcount.h>
#include <linux/uuid.h>
#include <linux/blk_types.h>
-#include <asm/local.h>
+#include <linux/device.h>
+#include <linux/xarray.h>
extern const struct device_type disk_type;
extern struct device_type part_type;
@@ -26,14 +24,6 @@ extern struct class block_class;
#define DISK_MAX_PARTS 256
#define DISK_NAME_LEN 32
-#include <linux/major.h>
-#include <linux/device.h>
-#include <linux/smp.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/workqueue.h>
-#include <linux/xarray.h>
-
#define PARTITION_META_INFO_VOLNAMELTH 64
/*
* Enough for the string representation of any kind of UUID plus NULL.
@@ -223,6 +213,8 @@ static inline int add_disk(struct gendisk *disk)
}
extern void del_gendisk(struct gendisk *gp);
+void invalidate_disk(struct gendisk *disk);
+
void set_disk_ro(struct gendisk *disk, bool read_only);
static inline int get_disk_ro(struct gendisk *disk)
@@ -231,6 +223,11 @@ static inline int get_disk_ro(struct gendisk *disk)
test_bit(GD_READ_ONLY, &disk->state);
}
+static inline int bdev_read_only(struct block_device *bdev)
+{
+ return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
+}
+
extern void disk_block_events(struct gendisk *disk);
extern void disk_unblock_events(struct gendisk *disk);
extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
@@ -248,7 +245,12 @@ static inline sector_t get_start_sect(struct block_device *bdev)
static inline sector_t bdev_nr_sectors(struct block_device *bdev)
{
- return i_size_read(bdev->bd_inode) >> 9;
+ return bdev->bd_nr_sectors;
+}
+
+static inline loff_t bdev_nr_bytes(struct block_device *bdev)
+{
+ return bdev_nr_sectors(bdev) << SECTOR_SHIFT;
}
static inline sector_t get_capacity(struct gendisk *disk)
@@ -256,6 +258,12 @@ static inline sector_t get_capacity(struct gendisk *disk)
return bdev_nr_sectors(disk->part0);
}
+static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
+{
+ return bdev_nr_sectors(sb->s_bdev) >>
+ (sb->s_blocksize_bits - SECTOR_SHIFT);
+}
+
int bdev_disk_changed(struct gendisk *disk, bool invalidate);
void blk_drop_partitions(struct gendisk *disk);
@@ -291,10 +299,6 @@ bool bdev_check_media_change(struct block_device *bdev);
int __invalidate_device(struct block_device *bdev, bool kill_dirty);
void set_capacity(struct gendisk *disk, sector_t size);
-/* for drivers/char/raw.c: */
-int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
-long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-
#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 55b2ec1f965a..3745efd21cf6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -520,15 +520,11 @@ static inline void arch_free_page(struct page *page, int order) { }
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif
-#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
-static inline int arch_make_page_accessible(struct page *page)
-{
- return 0;
-}
-#endif
struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
nodemask_t *nodemask);
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+ nodemask_t *nodemask);
unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
nodemask_t *nodemask, int nr_pages,
@@ -570,6 +566,15 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
return __alloc_pages(gfp_mask, order, nid, NULL);
}
+static inline
+struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
+{
+ VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+ VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));
+
+ return __folio_alloc(gfp, order, nid, NULL);
+}
+
/*
* Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
* prefer the current CPU's closest node. Otherwise node must be valid and
@@ -586,6 +591,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
#ifdef CONFIG_NUMA
struct page *alloc_pages(gfp_t gfp, unsigned int order);
+struct folio *folio_alloc(gfp_t gfp, unsigned order);
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
struct vm_area_struct *vma, unsigned long addr,
int node, bool hugepage);
@@ -596,6 +602,10 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
{
return alloc_pages_node(numa_node_id(), gfp_mask, order);
}
+static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
+{
+ return __folio_alloc_node(gfp, order, numa_node_id());
+}
#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
alloc_pages(gfp_mask, order)
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 4aa1031d3e4c..0a0b2b09b1b8 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -73,6 +73,12 @@ static inline void *kmap_local_page(struct page *page)
return __kmap_local_page_prot(page, kmap_prot);
}
+static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+{
+ struct page *page = folio_page(folio, offset / PAGE_SIZE);
+ return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE;
+}
+
static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
{
return __kmap_local_page_prot(page, prot);
@@ -171,6 +177,11 @@ static inline void *kmap_local_page(struct page *page)
return page_address(page);
}
+static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+{
+ return page_address(&folio->page) + offset;
+}
+
static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
{
return kmap_local_page(page);
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index b4c49f9cc379..27cdd715c5f9 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -97,6 +97,43 @@ static inline void kmap_flush_unused(void);
static inline void *kmap_local_page(struct page *page);
/**
+ * kmap_local_folio - Map a page in this folio for temporary usage
+ * @folio: The folio containing the page.
+ * @offset: The byte offset within the folio which identifies the page.
+ *
+ * Requires careful handling when nesting multiple mappings because the map
+ * management is stack based. The unmap has to be in the reverse order of
+ * the map operation::
+ *
+ * addr1 = kmap_local_folio(folio1, offset1);
+ * addr2 = kmap_local_folio(folio2, offset2);
+ * ...
+ * kunmap_local(addr2);
+ * kunmap_local(addr1);
+ *
+ * Unmapping addr1 before addr2 is invalid and causes malfunction.
+ *
+ * Contrary to kmap() mappings the mapping is only valid in the context of
+ * the caller and cannot be handed to other contexts.
+ *
+ * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
+ * virtual address of the direct mapping. Only real highmem pages are
+ * temporarily mapped.
+ *
+ * While it is significantly faster than kmap() for the higmem case it
+ * comes with restrictions about the pointer validity. Only use when really
+ * necessary.
+ *
+ * On HIGHMEM enabled systems mapping a highmem page has the side effect of
+ * disabling migration in order to keep the virtual address stable across
+ * preemption. No caller of kmap_local_folio() can rely on this side effect.
+ *
+ * Context: Can be invoked from any context.
+ * Return: The virtual address of @offset.
+ */
+static inline void *kmap_local_folio(struct folio *folio, size_t offset);
+
+/**
* kmap_atomic - Atomically map a page for temporary usage - Deprecated!
* @page: Pointer to the page to be mapped
*
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f123e15d966e..f280f33ff223 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -251,15 +251,6 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
}
/**
- * thp_head - Head page of a transparent huge page.
- * @page: Any page (tail, head or regular) found in the page cache.
- */
-static inline struct page *thp_head(struct page *page)
-{
- return compound_head(page);
-}
-
-/**
* thp_order - Order of a transparent huge page.
* @page: Head page of a transparent huge page.
*/
@@ -336,12 +327,6 @@ static inline struct list_head *page_deferred_list(struct page *page)
#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
-static inline struct page *thp_head(struct page *page)
-{
- VM_BUG_ON_PGFLAGS(PageTail(page), page);
- return page;
-}
-
static inline unsigned int thp_order(struct page *page)
{
VM_BUG_ON_PGFLAGS(PageTail(page), page);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 24f8489583ca..63f4ea4dac9b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -313,8 +313,8 @@ int iomap_writepages(struct address_space *mapping,
struct iomap_dio_ops {
int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
unsigned flags);
- blk_qc_t (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
- loff_t file_offset);
+ void (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
+ loff_t file_offset);
};
/*
@@ -337,7 +337,6 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
unsigned int dio_flags);
ssize_t iomap_dio_complete(struct iomap_dio *dio);
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
#ifdef CONFIG_SWAP
struct file;
diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h
deleted file mode 100644
index a27605e2f826..000000000000
--- a/include/linux/keyslot-manager.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright 2019 Google LLC
- */
-
-#ifndef __LINUX_KEYSLOT_MANAGER_H
-#define __LINUX_KEYSLOT_MANAGER_H
-
-#include <linux/bio.h>
-#include <linux/blk-crypto.h>
-
-struct blk_keyslot_manager;
-
-/**
- * struct blk_ksm_ll_ops - functions to manage keyslots in hardware
- * @keyslot_program: Program the specified key into the specified slot in the
- * inline encryption hardware.
- * @keyslot_evict: Evict key from the specified keyslot in the hardware.
- * The key is provided so that e.g. dm layers can evict
- * keys from the devices that they map over.
- * Returns 0 on success, -errno otherwise.
- *
- * This structure should be provided by storage device drivers when they set up
- * a keyslot manager - this structure holds the function ptrs that the keyslot
- * manager will use to manipulate keyslots in the hardware.
- */
-struct blk_ksm_ll_ops {
- int (*keyslot_program)(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot);
- int (*keyslot_evict)(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot);
-};
-
-struct blk_keyslot_manager {
- /*
- * The struct blk_ksm_ll_ops that this keyslot manager will use
- * to perform operations like programming and evicting keys on the
- * device
- */
- struct blk_ksm_ll_ops ksm_ll_ops;
-
- /*
- * The maximum number of bytes supported for specifying the data unit
- * number.
- */
- unsigned int max_dun_bytes_supported;
-
- /*
- * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents
- * whether a crypto mode and data unit size are supported. The i'th
- * bit of crypto_mode_supported[crypto_mode] is set iff a data unit
- * size of (1 << i) is supported. We only support data unit sizes
- * that are powers of 2.
- */
- unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX];
-
- /* Device for runtime power management (NULL if none) */
- struct device *dev;
-
- /* Here onwards are *private* fields for internal keyslot manager use */
-
- unsigned int num_slots;
-
- /* Protects programming and evicting keys from the device */
- struct rw_semaphore lock;
-
- /* List of idle slots, with least recently used slot at front */
- wait_queue_head_t idle_slots_wait_queue;
- struct list_head idle_slots;
- spinlock_t idle_slots_lock;
-
- /*
- * Hash table which maps struct *blk_crypto_key to keyslots, so that we
- * can find a key's keyslot in O(1) time rather than O(num_slots).
- * Protected by 'lock'.
- */
- struct hlist_head *slot_hashtable;
- unsigned int log_slot_ht_size;
-
- /* Per-keyslot data */
- struct blk_ksm_keyslot *slots;
-};
-
-int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots);
-
-int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm,
- unsigned int num_slots);
-
-blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- struct blk_ksm_keyslot **slot_ptr);
-
-unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot);
-
-void blk_ksm_put_slot(struct blk_ksm_keyslot *slot);
-
-bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_config *cfg);
-
-int blk_ksm_evict_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key);
-
-void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm);
-
-void blk_ksm_destroy(struct blk_keyslot_manager *ksm);
-
-void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent,
- const struct blk_keyslot_manager *child);
-
-void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm);
-
-bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset,
- struct blk_keyslot_manager *ksm_subset);
-
-void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm,
- struct blk_keyslot_manager *reference_ksm);
-
-#endif /* __LINUX_KEYSLOT_MANAGER_H */
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 161e8164abcf..a38a5bca1ba5 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -52,7 +52,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
struct vm_area_struct *vma, unsigned long address);
void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
-void ksm_migrate_page(struct page *newpage, struct page *oldpage);
+void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
#else /* !CONFIG_KSM */
@@ -83,7 +83,7 @@ static inline void rmap_walk_ksm(struct page *page,
{
}
-static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old)
{
}
#endif /* CONFIG_MMU */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c0c64f03e107..236ec689056a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -676,6 +676,18 @@ struct ata_ering {
struct ata_ering_entry ring[ATA_ERING_SIZE];
};
+struct ata_cpr {
+ u8 num;
+ u8 num_storage_elements;
+ u64 start_lba;
+ u64 num_lbas;
+};
+
+struct ata_cpr_log {
+ u8 nr_cpr;
+ struct ata_cpr cpr[];
+};
+
struct ata_device {
struct ata_link *link;
unsigned int devno; /* 0 or 1 */
@@ -735,6 +747,9 @@ struct ata_device {
u32 zac_zones_optimal_nonseq;
u32 zac_zones_max_open;
+ /* Concurrent positioning ranges */
+ struct ata_cpr_log *cpr_log;
+
/* error history */
int spdn_cnt;
/* ering is CLEAR_END, read comment above CLEAR_END */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3096c9a0ee01..e34bf0cbdf55 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -369,7 +369,7 @@ enum page_memcg_data_flags {
#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
-static inline bool PageMemcgKmem(struct page *page);
+static inline bool folio_memcg_kmem(struct folio *folio);
/*
* After the initialization objcg->memcg is always pointing at
@@ -384,89 +384,95 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
}
/*
- * __page_memcg - get the memory cgroup associated with a non-kmem page
- * @page: a pointer to the page struct
+ * __folio_memcg - Get the memory cgroup associated with a non-kmem folio
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * Returns a pointer to the memory cgroup associated with the folio,
+ * or NULL. This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages or
- * kmem pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios or
+ * kmem folios.
*/
-static inline struct mem_cgroup *__page_memcg(struct page *page)
+static inline struct mem_cgroup *__folio_memcg(struct folio *folio)
{
- unsigned long memcg_data = page->memcg_data;
+ unsigned long memcg_data = folio->memcg_data;
- VM_BUG_ON_PAGE(PageSlab(page), page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
+ VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
- * __page_objcg - get the object cgroup associated with a kmem page
- * @page: a pointer to the page struct
+ * __folio_objcg - get the object cgroup associated with a kmem folio.
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the object cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * Returns a pointer to the object cgroup associated with the folio,
+ * or NULL. This function assumes that the folio is known to have a
* proper object cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages or
- * LRU pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios or
+ * LRU folios.
*/
-static inline struct obj_cgroup *__page_objcg(struct page *page)
+static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
{
- unsigned long memcg_data = page->memcg_data;
+ unsigned long memcg_data = folio->memcg_data;
- VM_BUG_ON_PAGE(PageSlab(page), page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
- VM_BUG_ON_PAGE(!(memcg_data & MEMCG_DATA_KMEM), page);
+ VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);
return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
- * page_memcg - get the memory cgroup associated with a page
- * @page: a pointer to the page struct
+ * folio_memcg - Get the memory cgroup associated with a folio.
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * Returns a pointer to the memory cgroup associated with the folio,
+ * or NULL. This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios.
*
- * For a non-kmem page any of the following ensures page and memcg binding
+ * For a non-kmem folio any of the following ensures folio and memcg binding
* stability:
*
- * - the page lock
+ * - the folio lock
* - LRU isolation
* - lock_page_memcg()
* - exclusive reference
*
- * For a kmem page a caller should hold an rcu read lock to protect memcg
- * associated with a kmem page from being released.
+ * For a kmem folio a caller should hold an rcu read lock to protect memcg
+ * associated with a kmem folio from being released.
*/
+static inline struct mem_cgroup *folio_memcg(struct folio *folio)
+{
+ if (folio_memcg_kmem(folio))
+ return obj_cgroup_memcg(__folio_objcg(folio));
+ return __folio_memcg(folio);
+}
+
static inline struct mem_cgroup *page_memcg(struct page *page)
{
- if (PageMemcgKmem(page))
- return obj_cgroup_memcg(__page_objcg(page));
- else
- return __page_memcg(page);
+ return folio_memcg(page_folio(page));
}
-/*
- * page_memcg_rcu - locklessly get the memory cgroup associated with a page
- * @page: a pointer to the page struct
+/**
+ * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio.
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios.
+ *
+ * Return: A pointer to the memory cgroup associated with the folio,
+ * or NULL.
*/
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
{
- unsigned long memcg_data = READ_ONCE(page->memcg_data);
+ unsigned long memcg_data = READ_ONCE(folio->memcg_data);
- VM_BUG_ON_PAGE(PageSlab(page), page);
+ VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
WARN_ON_ONCE(!rcu_read_lock_held());
if (memcg_data & MEMCG_DATA_KMEM) {
@@ -523,17 +529,18 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
#ifdef CONFIG_MEMCG_KMEM
/*
- * PageMemcgKmem - check if the page has MemcgKmem flag set
- * @page: a pointer to the page struct
+ * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
+ * @folio: Pointer to the folio.
*
- * Checks if the page has MemcgKmem flag set. The caller must ensure that
- * the page has an associated memory cgroup. It's not safe to call this function
- * against some types of pages, e.g. slab pages.
+ * Checks if the folio has MemcgKmem flag set. The caller must ensure
+ * that the folio has an associated memory cgroup. It's not safe to call
+ * this function against some types of folios, e.g. slab folios.
*/
-static inline bool PageMemcgKmem(struct page *page)
+static inline bool folio_memcg_kmem(struct folio *folio)
{
- VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page);
- return page->memcg_data & MEMCG_DATA_KMEM;
+ VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page);
+ VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio);
+ return folio->memcg_data & MEMCG_DATA_KMEM;
}
/*
@@ -577,7 +584,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
}
#else
-static inline bool PageMemcgKmem(struct page *page)
+static inline bool folio_memcg_kmem(struct folio *folio)
{
return false;
}
@@ -593,6 +600,11 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
}
#endif
+static inline bool PageMemcgKmem(struct page *page)
+{
+ return folio_memcg_kmem(page_folio(page));
+}
+
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
return (memcg == root_mem_cgroup);
@@ -684,26 +696,47 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
page_counter_read(&memcg->memory);
}
-int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask);
-static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp);
+
+/**
+ * mem_cgroup_charge - Charge a newly allocated folio to a cgroup.
+ * @folio: Folio to charge.
+ * @mm: mm context of the allocating task.
+ * @gfp: Reclaim mode.
+ *
+ * Try to charge @folio to the memcg that @mm belongs to, reclaiming
+ * pages according to @gfp if necessary. If @mm is NULL, try to
+ * charge to the active memcg.
+ *
+ * Do not use this for folios allocated for swapin.
+ *
+ * Return: 0 on success. Otherwise, an error code is returned.
+ */
+static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
+ gfp_t gfp)
{
if (mem_cgroup_disabled())
return 0;
- return __mem_cgroup_charge(page, mm, gfp_mask);
+ return __mem_cgroup_charge(folio, mm, gfp);
}
int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry);
void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
-void __mem_cgroup_uncharge(struct page *page);
-static inline void mem_cgroup_uncharge(struct page *page)
+void __mem_cgroup_uncharge(struct folio *folio);
+
+/**
+ * mem_cgroup_uncharge - Uncharge a folio.
+ * @folio: Folio to uncharge.
+ *
+ * Uncharge a folio previously charged with mem_cgroup_charge().
+ */
+static inline void mem_cgroup_uncharge(struct folio *folio)
{
if (mem_cgroup_disabled())
return;
- __mem_cgroup_uncharge(page);
+ __mem_cgroup_uncharge(folio);
}
void __mem_cgroup_uncharge_list(struct list_head *page_list);
@@ -714,7 +747,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
__mem_cgroup_uncharge_list(page_list);
}
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
+void mem_cgroup_migrate(struct folio *old, struct folio *new);
/**
* mem_cgroup_lruvec - get the lru list vector for a memcg & node
@@ -753,33 +786,33 @@ out:
}
/**
- * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
- * @page: the page
+ * folio_lruvec - return lruvec for isolating/putting an LRU folio
+ * @folio: Pointer to the folio.
*
- * This function relies on page->mem_cgroup being stable.
+ * This function relies on folio->mem_cgroup being stable.
*/
-static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page)
+static inline struct lruvec *folio_lruvec(struct folio *folio)
{
- pg_data_t *pgdat = page_pgdat(page);
- struct mem_cgroup *memcg = page_memcg(page);
+ struct mem_cgroup *memcg = folio_memcg(folio);
- VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
- return mem_cgroup_lruvec(memcg, pgdat);
+ VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio);
+ return mem_cgroup_lruvec(memcg, folio_pgdat(folio));
}
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
-struct lruvec *lock_page_lruvec(struct page *page);
-struct lruvec *lock_page_lruvec_irq(struct page *page);
-struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+struct lruvec *folio_lruvec_lock(struct folio *folio);
+struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
+struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flags);
#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page);
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio);
#else
-static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+static inline
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
}
#endif
@@ -947,6 +980,8 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
extern bool cgroup_memory_noswap;
#endif
+void folio_memcg_lock(struct folio *folio);
+void folio_memcg_unlock(struct folio *folio);
void lock_page_memcg(struct page *page);
void unlock_page_memcg(struct page *page);
@@ -1115,12 +1150,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
#define MEM_CGROUP_ID_SHIFT 0
#define MEM_CGROUP_ID_MAX 0
+static inline struct mem_cgroup *folio_memcg(struct folio *folio)
+{
+ return NULL;
+}
+
static inline struct mem_cgroup *page_memcg(struct page *page)
{
return NULL;
}
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
{
WARN_ON_ONCE(!rcu_read_lock_held());
return NULL;
@@ -1131,6 +1171,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
return NULL;
}
+static inline bool folio_memcg_kmem(struct folio *folio)
+{
+ return false;
+}
+
static inline bool PageMemcgKmem(struct page *page)
{
return false;
@@ -1179,8 +1224,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
return false;
}
-static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+static inline int mem_cgroup_charge(struct folio *folio,
+ struct mm_struct *mm, gfp_t gfp)
{
return 0;
}
@@ -1195,7 +1240,7 @@ static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
{
}
-static inline void mem_cgroup_uncharge(struct page *page)
+static inline void mem_cgroup_uncharge(struct folio *folio)
{
}
@@ -1203,7 +1248,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
{
}
-static inline void mem_cgroup_migrate(struct page *old, struct page *new)
+static inline void mem_cgroup_migrate(struct folio *old, struct folio *new)
{
}
@@ -1213,14 +1258,14 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
return &pgdat->__lruvec;
}
-static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page)
+static inline struct lruvec *folio_lruvec(struct folio *folio)
{
- pg_data_t *pgdat = page_pgdat(page);
-
+ struct pglist_data *pgdat = folio_pgdat(folio);
return &pgdat->__lruvec;
}
-static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+static inline
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
}
@@ -1250,26 +1295,26 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg)
{
}
-static inline struct lruvec *lock_page_lruvec(struct page *page)
+static inline struct lruvec *folio_lruvec_lock(struct folio *folio)
{
- struct pglist_data *pgdat = page_pgdat(page);
+ struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock(&pgdat->__lruvec.lru_lock);
return &pgdat->__lruvec;
}
-static inline struct lruvec *lock_page_lruvec_irq(struct page *page)
+static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
- struct pglist_data *pgdat = page_pgdat(page);
+ struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock_irq(&pgdat->__lruvec.lru_lock);
return &pgdat->__lruvec;
}
-static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flagsp)
{
- struct pglist_data *pgdat = page_pgdat(page);
+ struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
return &pgdat->__lruvec;
@@ -1356,6 +1401,14 @@ static inline void unlock_page_memcg(struct page *page)
{
}
+static inline void folio_memcg_lock(struct folio *folio)
+{
+}
+
+static inline void folio_memcg_unlock(struct folio *folio)
+{
+}
+
static inline void mem_cgroup_handle_over_high(void)
{
}
@@ -1517,38 +1570,39 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
}
/* Test requires a stable page->memcg binding, see page_memcg() */
-static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec)
+static inline bool folio_matches_lruvec(struct folio *folio,
+ struct lruvec *lruvec)
{
- return lruvec_pgdat(lruvec) == page_pgdat(page) &&
- lruvec_memcg(lruvec) == page_memcg(page);
+ return lruvec_pgdat(lruvec) == folio_pgdat(folio) &&
+ lruvec_memcg(lruvec) == folio_memcg(folio);
}
/* Don't lock again iff page's lruvec locked */
-static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
+static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio,
struct lruvec *locked_lruvec)
{
if (locked_lruvec) {
- if (page_matches_lruvec(page, locked_lruvec))
+ if (folio_matches_lruvec(folio, locked_lruvec))
return locked_lruvec;
unlock_page_lruvec_irq(locked_lruvec);
}
- return lock_page_lruvec_irq(page);
+ return folio_lruvec_lock_irq(folio);
}
/* Don't lock again iff page's lruvec locked */
-static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
+static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio,
struct lruvec *locked_lruvec, unsigned long *flags)
{
if (locked_lruvec) {
- if (page_matches_lruvec(page, locked_lruvec))
+ if (folio_matches_lruvec(folio, locked_lruvec))
return locked_lruvec;
unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
}
- return lock_page_lruvec_irqsave(page, flags);
+ return folio_lruvec_lock_irqsave(folio, flags);
}
#ifdef CONFIG_CGROUP_WRITEBACK
@@ -1558,17 +1612,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback);
-void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
struct bdi_writeback *wb);
-static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
if (mem_cgroup_disabled())
return;
- if (unlikely(&page_memcg(page)->css != wb->memcg_css))
- mem_cgroup_track_foreign_dirty_slowpath(page, wb);
+ if (unlikely(&folio_memcg(folio)->css != wb->memcg_css))
+ mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
}
void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
@@ -1588,7 +1642,7 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
{
}
-static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
}
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index c8077e936691..0d2aeb9b0f66 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -57,6 +57,10 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page, int extra_count);
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
+void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
+int folio_migrate_mapping(struct address_space *mapping,
+ struct folio *newfolio, struct folio *folio, int extra_count);
#else
static inline void putback_movable_pages(struct list_head *l) {}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 73a52aba448f..40ff114aaf9e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -36,10 +36,7 @@
struct mempolicy;
struct anon_vma;
struct anon_vma_chain;
-struct file_ra_state;
struct user_struct;
-struct writeback_control;
-struct bdi_writeback;
struct pt_regs;
extern int sysctl_page_lock_unfairness;
@@ -216,13 +213,6 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
loff_t *);
int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
loff_t *);
-/*
- * Any attempt to mark this function as static leads to build failure
- * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked()
- * is referred to by BPF code. This must be visible for error injection.
- */
-int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t index, gfp_t gfp, void **shadowp);
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
@@ -748,13 +738,18 @@ static inline int put_page_testzero(struct page *page)
return page_ref_dec_and_test(page);
}
+static inline int folio_put_testzero(struct folio *folio)
+{
+ return put_page_testzero(&folio->page);
+}
+
/*
* Try to grab a ref unless the page has a refcount of zero, return false if
* that is the case.
* This can be called when MMU is off so it must not access
* any of the virtual mappings.
*/
-static inline int get_page_unless_zero(struct page *page)
+static inline bool get_page_unless_zero(struct page *page)
{
return page_ref_add_unless(page, 1, 0);
}
@@ -907,7 +902,7 @@ void __put_page(struct page *page);
void put_pages_list(struct list_head *pages);
void split_page(struct page *page, unsigned int order);
-void copy_huge_page(struct page *dst, struct page *src);
+void folio_copy(struct folio *dst, struct folio *src);
/*
* Compound pages have a destructor function. Provide a
@@ -950,6 +945,20 @@ static inline unsigned int compound_order(struct page *page)
return page[1].compound_order;
}
+/**
+ * folio_order - The allocation order of a folio.
+ * @folio: The folio.
+ *
+ * A folio is composed of 2^order pages. See get_order() for the definition
+ * of order.
+ *
+ * Return: The order of the folio.
+ */
+static inline unsigned int folio_order(struct folio *folio)
+{
+ return compound_order(&folio->page);
+}
+
static inline bool hpage_pincount_available(struct page *page)
{
/*
@@ -1131,6 +1140,11 @@ static inline enum zone_type page_zonenum(const struct page *page)
return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
+static inline enum zone_type folio_zonenum(const struct folio *folio)
+{
+ return page_zonenum(&folio->page);
+}
+
#ifdef CONFIG_ZONE_DEVICE
static inline bool is_zone_device_page(const struct page *page)
{
@@ -1200,18 +1214,26 @@ static inline bool is_pci_p2pdma_page(const struct page *page)
}
/* 127: arbitrary random number, small enough to assemble well */
-#define page_ref_zero_or_close_to_overflow(page) \
- ((unsigned int) page_ref_count(page) + 127u <= 127u)
+#define folio_ref_zero_or_close_to_overflow(folio) \
+ ((unsigned int) folio_ref_count(folio) + 127u <= 127u)
+
+/**
+ * folio_get - Increment the reference count on a folio.
+ * @folio: The folio.
+ *
+ * Context: May be called in any context, as long as you know that
+ * you have a refcount on the folio. If you do not already have one,
+ * folio_try_get() may be the right interface for you to use.
+ */
+static inline void folio_get(struct folio *folio)
+{
+ VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio);
+ folio_ref_inc(folio);
+}
static inline void get_page(struct page *page)
{
- page = compound_head(page);
- /*
- * Getting a normal page or the head of a compound page
- * requires to already have an elevated page->_refcount.
- */
- VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page);
- page_ref_inc(page);
+ folio_get(page_folio(page));
}
bool __must_check try_grab_page(struct page *page, unsigned int flags);
@@ -1228,9 +1250,28 @@ static inline __must_check bool try_get_page(struct page *page)
return true;
}
+/**
+ * folio_put - Decrement the reference count on a folio.
+ * @folio: The folio.
+ *
+ * If the folio's reference count reaches zero, the memory will be
+ * released back to the page allocator and may be used by another
+ * allocation immediately. Do not access the memory or the struct folio
+ * after calling folio_put() unless you can be sure that it wasn't the
+ * last reference.
+ *
+ * Context: May be called in process or interrupt context, but not in NMI
+ * context. May be called while holding a spinlock.
+ */
+static inline void folio_put(struct folio *folio)
+{
+ if (folio_put_testzero(folio))
+ __put_page(&folio->page);
+}
+
static inline void put_page(struct page *page)
{
- page = compound_head(page);
+ struct folio *folio = page_folio(page);
/*
* For devmap managed pages we need to catch refcount transition from
@@ -1238,13 +1279,12 @@ static inline void put_page(struct page *page)
* need to inform the device driver through callback. See
* include/linux/memremap.h and HMM for details.
*/
- if (page_is_devmap_managed(page)) {
- put_devmap_managed_page(page);
+ if (page_is_devmap_managed(&folio->page)) {
+ put_devmap_managed_page(&folio->page);
return;
}
- if (put_page_testzero(page))
- __put_page(page);
+ folio_put(folio);
}
/*
@@ -1379,6 +1419,11 @@ static inline int page_to_nid(const struct page *page)
}
#endif
+static inline int folio_nid(const struct folio *folio)
+{
+ return page_to_nid(&folio->page);
+}
+
#ifdef CONFIG_NUMA_BALANCING
static inline int cpu_pid_to_cpupid(int cpu, int pid)
{
@@ -1546,6 +1591,16 @@ static inline pg_data_t *page_pgdat(const struct page *page)
return NODE_DATA(page_to_nid(page));
}
+static inline struct zone *folio_zone(const struct folio *folio)
+{
+ return page_zone(&folio->page);
+}
+
+static inline pg_data_t *folio_pgdat(const struct folio *folio)
+{
+ return page_pgdat(&folio->page);
+}
+
#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
@@ -1559,6 +1614,20 @@ static inline unsigned long page_to_section(const struct page *page)
}
#endif
+/**
+ * folio_pfn - Return the Page Frame Number of a folio.
+ * @folio: The folio.
+ *
+ * A folio may contain multiple pages. The pages have consecutive
+ * Page Frame Numbers.
+ *
+ * Return: The Page Frame Number of the first page in the folio.
+ */
+static inline unsigned long folio_pfn(struct folio *folio)
+{
+ return page_to_pfn(&folio->page);
+}
+
/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
#ifdef CONFIG_MIGRATION
static inline bool is_pinnable_page(struct page *page)
@@ -1595,6 +1664,89 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
#endif
}
+/**
+ * folio_nr_pages - The number of pages in the folio.
+ * @folio: The folio.
+ *
+ * Return: A positive power of two.
+ */
+static inline long folio_nr_pages(struct folio *folio)
+{
+ return compound_nr(&folio->page);
+}
+
+/**
+ * folio_next - Move to the next physical folio.
+ * @folio: The folio we're currently operating on.
+ *
+ * If you have physically contiguous memory which may span more than
+ * one folio (eg a &struct bio_vec), use this function to move from one
+ * folio to the next. Do not use it if the memory is only virtually
+ * contiguous as the folios are almost certainly not adjacent to each
+ * other. This is the folio equivalent to writing ``page++``.
+ *
+ * Context: We assume that the folios are refcounted and/or locked at a
+ * higher level and do not adjust the reference counts.
+ * Return: The next struct folio.
+ */
+static inline struct folio *folio_next(struct folio *folio)
+{
+ return (struct folio *)folio_page(folio, folio_nr_pages(folio));
+}
+
+/**
+ * folio_shift - The size of the memory described by this folio.
+ * @folio: The folio.
+ *
+ * A folio represents a number of bytes which is a power-of-two in size.
+ * This function tells you which power-of-two the folio is. See also
+ * folio_size() and folio_order().
+ *
+ * Context: The caller should have a reference on the folio to prevent
+ * it from being split. It is not necessary for the folio to be locked.
+ * Return: The base-2 logarithm of the size of this folio.
+ */
+static inline unsigned int folio_shift(struct folio *folio)
+{
+ return PAGE_SHIFT + folio_order(folio);
+}
+
+/**
+ * folio_size - The number of bytes in a folio.
+ * @folio: The folio.
+ *
+ * Context: The caller should have a reference on the folio to prevent
+ * it from being split. It is not necessary for the folio to be locked.
+ * Return: The number of bytes in this folio.
+ */
+static inline size_t folio_size(struct folio *folio)
+{
+ return PAGE_SIZE << folio_order(folio);
+}
+
+#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
+static inline int arch_make_page_accessible(struct page *page)
+{
+ return 0;
+}
+#endif
+
+#ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
+static inline int arch_make_folio_accessible(struct folio *folio)
+{
+ int ret;
+ long i, nr = folio_nr_pages(folio);
+
+ for (i = 0; i < nr; i++) {
+ ret = arch_make_page_accessible(folio_page(folio, i));
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+#endif
+
/*
* Some inline functions in vmstat.h depend on page_zone()
*/
@@ -1635,19 +1787,6 @@ void page_address_init(void);
extern void *page_rmapping(struct page *page);
extern struct anon_vma *page_anon_vma(struct page *page);
-extern struct address_space *page_mapping(struct page *page);
-
-extern struct address_space *__page_file_mapping(struct page *);
-
-static inline
-struct address_space *page_file_mapping(struct page *page)
-{
- if (unlikely(PageSwapCache(page)))
- return __page_file_mapping(page);
-
- return page->mapping;
-}
-
extern pgoff_t __page_file_index(struct page *page);
/*
@@ -1662,7 +1801,7 @@ static inline pgoff_t page_index(struct page *page)
}
bool page_mapped(struct page *page);
-struct address_space *page_mapping(struct page *page);
+bool folio_mapped(struct folio *folio);
/*
* Return true only if the page has been allocated with
@@ -1700,6 +1839,7 @@ extern void pagefault_out_of_memory(void);
#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1))
+#define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1))
/*
* Flags passed to show_mem() and show_free_areas() to suppress output in
@@ -1854,20 +1994,9 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
-int redirty_page_for_writepage(struct writeback_control *wbc,
- struct page *page);
-void account_page_cleaned(struct page *page, struct address_space *mapping,
- struct bdi_writeback *wb);
-int set_page_dirty(struct page *page);
+bool folio_mark_dirty(struct folio *folio);
+bool set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
-void __cancel_dirty_page(struct page *page);
-static inline void cancel_dirty_page(struct page *page)
-{
- /* Avoid atomic ops, locking, etc. when not actually needed. */
- if (PageDirty(page))
- __cancel_dirty_page(page);
-}
-int clear_page_dirty_for_io(struct page *page);
int get_cmdline(struct task_struct *task, char *buffer, int buflen);
@@ -2659,10 +2788,6 @@ extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
-/* mm/page-writeback.c */
-int __must_check write_one_page(struct page *page);
-void task_dirty_inc(struct task_struct *tsk);
-
extern unsigned long stack_guard_gap;
/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 355ea1ee32bd..e2ec68b0515c 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -6,27 +6,33 @@
#include <linux/swap.h>
/**
- * page_is_file_lru - should the page be on a file LRU or anon LRU?
- * @page: the page to test
- *
- * Returns 1 if @page is a regular filesystem backed page cache page or a lazily
- * freed anonymous page (e.g. via MADV_FREE). Returns 0 if @page is a normal
- * anonymous page, a tmpfs page or otherwise ram or swap backed page. Used by
- * functions that manipulate the LRU lists, to sort a page onto the right LRU
- * list.
+ * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
+ * @folio: The folio to test.
*
* We would like to get this info without a page flag, but the state
- * needs to survive until the page is last deleted from the LRU, which
+ * needs to survive until the folio is last deleted from the LRU, which
* could be as far down as __page_cache_release.
+ *
+ * Return: An integer (not a boolean!) used to sort a folio onto the
+ * right LRU list and to account folios correctly.
+ * 1 if @folio is a regular filesystem backed page cache folio
+ * or a lazily freed anonymous folio (e.g. via MADV_FREE).
+ * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise
+ * ram or swap backed folio.
*/
+static inline int folio_is_file_lru(struct folio *folio)
+{
+ return !folio_test_swapbacked(folio);
+}
+
static inline int page_is_file_lru(struct page *page)
{
- return !PageSwapBacked(page);
+ return folio_is_file_lru(page_folio(page));
}
static __always_inline void update_lru_size(struct lruvec *lruvec,
enum lru_list lru, enum zone_type zid,
- int nr_pages)
+ long nr_pages)
{
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -39,69 +45,94 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
}
/**
- * __clear_page_lru_flags - clear page lru flags before releasing a page
- * @page: the page that was on lru and now has a zero reference
+ * __folio_clear_lru_flags - Clear page lru flags before releasing a page.
+ * @folio: The folio that was on lru and now has a zero reference.
*/
-static __always_inline void __clear_page_lru_flags(struct page *page)
+static __always_inline void __folio_clear_lru_flags(struct folio *folio)
{
- VM_BUG_ON_PAGE(!PageLRU(page), page);
+ VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio);
- __ClearPageLRU(page);
+ __folio_clear_lru(folio);
/* this shouldn't happen, so leave the flags to bad_page() */
- if (PageActive(page) && PageUnevictable(page))
+ if (folio_test_active(folio) && folio_test_unevictable(folio))
return;
- __ClearPageActive(page);
- __ClearPageUnevictable(page);
+ __folio_clear_active(folio);
+ __folio_clear_unevictable(folio);
+}
+
+static __always_inline void __clear_page_lru_flags(struct page *page)
+{
+ __folio_clear_lru_flags(page_folio(page));
}
/**
- * page_lru - which LRU list should a page be on?
- * @page: the page to test
+ * folio_lru_list - Which LRU list should a folio be on?
+ * @folio: The folio to test.
*
- * Returns the LRU list a page should be on, as an index
+ * Return: The LRU list a folio should be on, as an index
* into the array of LRU lists.
*/
-static __always_inline enum lru_list page_lru(struct page *page)
+static __always_inline enum lru_list folio_lru_list(struct folio *folio)
{
enum lru_list lru;
- VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
+ VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);
- if (PageUnevictable(page))
+ if (folio_test_unevictable(folio))
return LRU_UNEVICTABLE;
- lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
- if (PageActive(page))
+ lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
+ if (folio_test_active(folio))
lru += LRU_ACTIVE;
return lru;
}
+static __always_inline
+void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
+{
+ enum lru_list lru = folio_lru_list(folio);
+
+ update_lru_size(lruvec, lru, folio_zonenum(folio),
+ folio_nr_pages(folio));
+ list_add(&folio->lru, &lruvec->lists[lru]);
+}
+
static __always_inline void add_page_to_lru_list(struct page *page,
struct lruvec *lruvec)
{
- enum lru_list lru = page_lru(page);
+ lruvec_add_folio(lruvec, page_folio(page));
+}
- update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
- list_add(&page->lru, &lruvec->lists[lru]);
+static __always_inline
+void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
+{
+ enum lru_list lru = folio_lru_list(folio);
+
+ update_lru_size(lruvec, lru, folio_zonenum(folio),
+ folio_nr_pages(folio));
+ list_add_tail(&folio->lru, &lruvec->lists[lru]);
}
static __always_inline void add_page_to_lru_list_tail(struct page *page,
struct lruvec *lruvec)
{
- enum lru_list lru = page_lru(page);
+ lruvec_add_folio_tail(lruvec, page_folio(page));
+}
- update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
- list_add_tail(&page->lru, &lruvec->lists[lru]);
+static __always_inline
+void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
+{
+ list_del(&folio->lru);
+ update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio),
+ -folio_nr_pages(folio));
}
static __always_inline void del_page_from_lru_list(struct page *page,
struct lruvec *lruvec)
{
- list_del(&page->lru);
- update_lru_size(lruvec, page_lru(page), page_zonenum(page),
- -thp_nr_pages(page));
+ lruvec_del_folio(lruvec, page_folio(page));
}
#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7f8ee09c711f..82dab23205c3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -239,6 +239,72 @@ struct page {
#endif
} _struct_page_alignment;
+/**
+ * struct folio - Represents a contiguous set of bytes.
+ * @flags: Identical to the page flags.
+ * @lru: Least Recently Used list; tracks how recently this folio was used.
+ * @mapping: The file this page belongs to, or refers to the anon_vma for
+ * anonymous memory.
+ * @index: Offset within the file, in units of pages. For anonymous memory,
+ * this is the index from the beginning of the mmap.
+ * @private: Filesystem per-folio data (see folio_attach_private()).
+ * Used for swp_entry_t if folio_test_swapcache().
+ * @_mapcount: Do not access this member directly. Use folio_mapcount() to
+ * find out how many times this folio is mapped by userspace.
+ * @_refcount: Do not access this member directly. Use folio_ref_count()
+ * to find how many references there are to this folio.
+ * @memcg_data: Memory Control Group data.
+ *
+ * A folio is a physically, virtually and logically contiguous set
+ * of bytes. It is a power-of-two in size, and it is aligned to that
+ * same power-of-two. It is at least as large as %PAGE_SIZE. If it is
+ * in the page cache, it is at a file offset which is a multiple of that
+ * power-of-two. It may be mapped into userspace at an address which is
+ * at an arbitrary page offset, but its kernel virtual address is aligned
+ * to its size.
+ */
+struct folio {
+ /* private: don't document the anon union */
+ union {
+ struct {
+ /* public: */
+ unsigned long flags;
+ struct list_head lru;
+ struct address_space *mapping;
+ pgoff_t index;
+ void *private;
+ atomic_t _mapcount;
+ atomic_t _refcount;
+#ifdef CONFIG_MEMCG
+ unsigned long memcg_data;
+#endif
+ /* private: the union with struct page is transitional */
+ };
+ struct page page;
+ };
+};
+
+static_assert(sizeof(struct page) == sizeof(struct folio));
+#define FOLIO_MATCH(pg, fl) \
+ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl))
+FOLIO_MATCH(flags, flags);
+FOLIO_MATCH(lru, lru);
+FOLIO_MATCH(compound_head, lru);
+FOLIO_MATCH(index, index);
+FOLIO_MATCH(private, private);
+FOLIO_MATCH(_mapcount, _mapcount);
+FOLIO_MATCH(_refcount, _refcount);
+#ifdef CONFIG_MEMCG
+FOLIO_MATCH(memcg_data, memcg_data);
+#endif
+#undef FOLIO_MATCH
+
+static inline atomic_t *folio_mapcount_ptr(struct folio *folio)
+{
+ struct page *tail = &folio->page + 1;
+ return &tail->compound_mapcount;
+}
+
static inline atomic_t *compound_mapcount_ptr(struct page *page)
{
return &page[1].compound_mapcount;
@@ -257,6 +323,12 @@ static inline atomic_t *compound_pincount_ptr(struct page *page)
#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK)
#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE)
+/*
+ * page_private can be used on tail pages. However, PagePrivate is only
+ * checked by the VM on the head page. So page_private on the tail pages
+ * should be used for data that's ancillary to the head page (eg attaching
+ * buffer heads to tail pages after attaching buffer heads to the head page)
+ */
#define page_private(page) ((page)->private)
static inline void set_page_private(struct page *page, unsigned long private)
@@ -264,6 +336,11 @@ static inline void set_page_private(struct page *page, unsigned long private)
page->private = private;
}
+static inline void *folio_get_private(struct folio *folio)
+{
+ return folio->private;
+}
+
struct page_frag_cache {
void * va;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 0c0c9a0fdf57..52eae8c45b8d 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -15,7 +15,7 @@
#include <linux/mmc/card.h>
#include <linux/mmc/pm.h>
#include <linux/dma-direction.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
struct mmc_ios {
unsigned int clock; /* clock rate */
@@ -492,7 +492,7 @@ struct mmc_host {
/* Inline encryption support */
#ifdef CONFIG_MMC_CRYPTO
- struct blk_keyslot_manager ksm;
+ struct blk_crypto_profile crypto_profile;
#endif
/* Host Software Queue support */
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 1935d4c72d10..d7285f8148a3 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -22,6 +22,13 @@ void dump_mm(const struct mm_struct *mm);
BUG(); \
} \
} while (0)
+#define VM_BUG_ON_FOLIO(cond, folio) \
+ do { \
+ if (unlikely(cond)) { \
+ dump_page(&folio->page, "VM_BUG_ON_FOLIO(" __stringify(cond)")");\
+ BUG(); \
+ } \
+ } while (0)
#define VM_BUG_ON_VMA(cond, vma) \
do { \
if (unlikely(cond)) { \
@@ -47,6 +54,17 @@ void dump_mm(const struct mm_struct *mm);
} \
unlikely(__ret_warn_once); \
})
+#define VM_WARN_ON_ONCE_FOLIO(cond, folio) ({ \
+ static bool __section(".data.once") __warned; \
+ int __ret_warn_once = !!(cond); \
+ \
+ if (unlikely(__ret_warn_once && !__warned)) { \
+ dump_page(&folio->page, "VM_WARN_ON_ONCE_FOLIO(" __stringify(cond)")");\
+ __warned = true; \
+ WARN_ON(1); \
+ } \
+ unlikely(__ret_warn_once); \
+})
#define VM_WARN_ON(cond) (void)WARN_ON(cond)
#define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
@@ -55,11 +73,13 @@ void dump_mm(const struct mm_struct *mm);
#else
#define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
#define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
+#define VM_BUG_ON_FOLIO(cond, folio) VM_BUG_ON(cond)
#define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond)
#define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
#define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
#endif
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 5d6a4158a9a6..12c4177f7703 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -22,6 +22,7 @@
* Overload PG_private_2 to give us PG_fscache - this is used to indicate that
* a page is currently backed by a local disk cache
*/
+#define folio_test_fscache(folio) folio_test_private_2(folio)
#define PageFsCache(page) PagePrivate2((page))
#define SetPageFsCache(page) SetPagePrivate2((page))
#define ClearPageFsCache(page) ClearPagePrivate2((page))
@@ -29,60 +30,80 @@
#define TestClearPageFsCache(page) TestClearPagePrivate2((page))
/**
- * set_page_fscache - Set PG_fscache on a page and take a ref
- * @page: The page.
+ * folio_start_fscache - Start an fscache write on a folio.
+ * @folio: The folio.
*
- * Set the PG_fscache (PG_private_2) flag on a page and take the reference
- * needed for the VM to handle its lifetime correctly. This sets the flag and
- * takes the reference unconditionally, so care must be taken not to set the
- * flag again if it's already set.
+ * Call this function before writing a folio to a local cache. Starting a
+ * second write before the first one finishes is not allowed.
*/
-static inline void set_page_fscache(struct page *page)
+static inline void folio_start_fscache(struct folio *folio)
{
- set_page_private_2(page);
+ VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio);
+ folio_get(folio);
+ folio_set_private_2(folio);
}
/**
- * end_page_fscache - Clear PG_fscache and release any waiters
- * @page: The page
- *
- * Clear the PG_fscache (PG_private_2) bit on a page and wake up any sleepers
- * waiting for this. The page ref held for PG_private_2 being set is released.
+ * folio_end_fscache - End an fscache write on a folio.
+ * @folio: The folio.
*
- * This is, for example, used when a netfs page is being written to a local
- * disk cache, thereby allowing writes to the cache for the same page to be
- * serialised.
+ * Call this function after the folio has been written to the local cache.
+ * This will wake any sleepers waiting on this folio.
*/
-static inline void end_page_fscache(struct page *page)
+static inline void folio_end_fscache(struct folio *folio)
{
- end_page_private_2(page);
+ folio_end_private_2(folio);
}
/**
- * wait_on_page_fscache - Wait for PG_fscache to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_fscache - Wait for an fscache write on this folio to end.
+ * @folio: The folio.
*
- * Wait for PG_fscache (aka PG_private_2) to be cleared on a page.
+ * If this folio is currently being written to a local cache, wait for
+ * the write to finish. Another write may start after this one finishes,
+ * unless the caller holds the folio lock.
*/
-static inline void wait_on_page_fscache(struct page *page)
+static inline void folio_wait_fscache(struct folio *folio)
{
- wait_on_page_private_2(page);
+ folio_wait_private_2(folio);
}
/**
- * wait_on_page_fscache_killable - Wait for PG_fscache to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_fscache_killable - Wait for an fscache write on this folio to end.
+ * @folio: The folio.
*
- * Wait for PG_fscache (aka PG_private_2) to be cleared on a page or until a
- * fatal signal is received by the calling task.
+ * If this folio is currently being written to a local cache, wait
+ * for the write to finish or for a fatal signal to be received.
+ * Another write may start after this one finishes, unless the caller
+ * holds the folio lock.
*
* Return:
* - 0 if successful.
* - -EINTR if a fatal signal was encountered.
*/
+static inline int folio_wait_fscache_killable(struct folio *folio)
+{
+ return folio_wait_private_2_killable(folio);
+}
+
+static inline void set_page_fscache(struct page *page)
+{
+ folio_start_fscache(page_folio(page));
+}
+
+static inline void end_page_fscache(struct page *page)
+{
+ folio_end_private_2(page_folio(page));
+}
+
+static inline void wait_on_page_fscache(struct page *page)
+{
+ folio_wait_private_2(page_folio(page));
+}
+
static inline int wait_on_page_fscache_killable(struct page *page)
{
- return wait_on_page_private_2_killable(page);
+ return folio_wait_private_2_killable(page_folio(page));
}
enum netfs_read_source {
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 2a38f2b477a5..cb909edb76c4 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -7,6 +7,7 @@
#define _NVME_FC_DRIVER_H 1
#include <linux/scatterlist.h>
+#include <linux/blk-mq.h>
/*
@@ -497,6 +498,8 @@ struct nvme_fc_port_template {
int (*xmt_ls_rsp)(struct nvme_fc_local_port *localport,
struct nvme_fc_remote_port *rport,
struct nvmefc_ls_rsp *ls_rsp);
+ void (*map_queues)(struct nvme_fc_local_port *localport,
+ struct blk_mq_queue_map *map);
u32 max_hw_queues;
u16 max_sgl_segments;
@@ -779,6 +782,10 @@ struct nvmet_fc_target_port {
* LS received.
* Entrypoint is Mandatory.
*
+ * @map_queues: This functions lets the driver expose the queue mapping
+ * to the block layer.
+ * Entrypoint is Optional.
+ *
* @fcp_op: Called to perform a data transfer or transmit a response.
* The nvmefc_tgt_fcp_req structure is the same LLDD-supplied
* exchange structure specified in the nvmet_fc_rcv_fcp_req() call
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 3ec8e50efa16..4dd7e6fe92fb 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,6 +6,8 @@
#ifndef _LINUX_NVME_RDMA_H
#define _LINUX_NVME_RDMA_H
+#define NVME_RDMA_MAX_QUEUE_SIZE 128
+
enum nvme_rdma_cm_fmt {
NVME_RDMA_CM_FMT_1_0 = 0x0,
};
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index b7c4c4130b65..855dd9b3e84b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -27,8 +27,20 @@
#define NVME_NSID_ALL 0xffffffff
enum nvme_subsys_type {
- NVME_NQN_DISC = 1, /* Discovery type target subsystem */
- NVME_NQN_NVME = 2, /* NVME type target subsystem */
+ /* Referral to another discovery type target subsystem */
+ NVME_NQN_DISC = 1,
+
+ /* NVME type target subsystem */
+ NVME_NQN_NVME = 2,
+
+ /* Current discovery type target subsystem */
+ NVME_NQN_CURR = 3,
+};
+
+enum nvme_ctrl_type {
+ NVME_CTRL_IO = 1, /* I/O controller */
+ NVME_CTRL_DISC = 2, /* Discovery controller */
+ NVME_CTRL_ADMIN = 3, /* Administrative controller */
};
/* Address Family codes for Discovery Log Page entry ADRFAM field */
@@ -244,7 +256,9 @@ struct nvme_id_ctrl {
__le32 rtd3e;
__le32 oaes;
__le32 ctratt;
- __u8 rsvd100[28];
+ __u8 rsvd100[11];
+ __u8 cntrltype;
+ __u8 fguid[16];
__le16 crdt1;
__le16 crdt2;
__le16 crdt3;
@@ -312,6 +326,7 @@ struct nvme_id_ctrl {
};
enum {
+ NVME_CTRL_CMIC_MULTI_PORT = 1 << 0,
NVME_CTRL_CMIC_MULTI_CTRL = 1 << 1,
NVME_CTRL_CMIC_ANA = 1 << 3,
NVME_CTRL_ONCS_COMPARE = 1 << 0,
@@ -1303,6 +1318,12 @@ struct nvmf_common_command {
#define MAX_DISC_LOGS 255
+/* Discovery log page entry flags (EFLAGS): */
+enum {
+ NVME_DISC_EFLAGS_EPCSD = (1 << 1),
+ NVME_DISC_EFLAGS_DUPRETINFO = (1 << 0),
+};
+
/* Discovery log page entry */
struct nvmf_disc_rsp_page_entry {
__u8 trtype;
@@ -1312,7 +1333,8 @@ struct nvmf_disc_rsp_page_entry {
__le16 portid;
__le16 cntlid;
__le16 asqsz;
- __u8 resv8[22];
+ __le16 eflags;
+ __u8 resv10[20];
char trsvcid[NVMF_TRSVCID_SIZE];
__u8 resv64[192];
char subnqn[NVMF_NQN_FIELD_LEN];
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a558d67ee86f..d8623d6e1141 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -143,6 +143,8 @@ enum pageflags {
#endif
__NR_PAGEFLAGS,
+ PG_readahead = PG_reclaim,
+
/* Filesystems */
PG_checked = PG_owner_priv_1,
@@ -171,6 +173,15 @@ enum pageflags {
/* Compound pages. Stored in first tail page's flags */
PG_double_map = PG_workingset,
+#ifdef CONFIG_MEMORY_FAILURE
+ /*
+ * Compound pages. Stored in first tail page's flags.
+ * Indicates that at least one subpage is hwpoisoned in the
+ * THP.
+ */
+ PG_has_hwpoisoned = PG_mappedtodisk,
+#endif
+
/* non-lru isolated movable page */
PG_isolated = PG_reclaim,
@@ -193,6 +204,34 @@ static inline unsigned long _compound_head(const struct page *page)
#define compound_head(page) ((typeof(page))_compound_head(page))
+/**
+ * page_folio - Converts from page to folio.
+ * @p: The page.
+ *
+ * Every page is part of a folio. This function cannot be called on a
+ * NULL pointer.
+ *
+ * Context: No reference, nor lock is required on @page. If the caller
+ * does not hold a reference, this call may race with a folio split, so
+ * it should re-check the folio still contains this page after gaining
+ * a reference on the folio.
+ * Return: The folio which contains this page.
+ */
+#define page_folio(p) (_Generic((p), \
+ const struct page *: (const struct folio *)_compound_head(p), \
+ struct page *: (struct folio *)_compound_head(p)))
+
+/**
+ * folio_page - Return a page from a folio.
+ * @folio: The folio.
+ * @n: The page number to return.
+ *
+ * @n is relative to the start of the folio. This function does not
+ * check that the page number lies within @folio; the caller is presumed
+ * to have a reference to the page.
+ */
+#define folio_page(folio, n) nth_page(&(folio)->page, n)
+
static __always_inline int PageTail(struct page *page)
{
return READ_ONCE(page->compound_head) & 1;
@@ -217,6 +256,15 @@ static inline void page_init_poison(struct page *page, size_t size)
}
#endif
+static unsigned long *folio_flags(struct folio *folio, unsigned n)
+{
+ struct page *page = &folio->page;
+
+ VM_BUG_ON_PGFLAGS(PageTail(page), page);
+ VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
+ return &page[n].flags;
+}
+
/*
* Page flags policies wrt compound pages
*
@@ -261,36 +309,64 @@ static inline void page_init_poison(struct page *page, size_t size)
VM_BUG_ON_PGFLAGS(!PageHead(page), page); \
PF_POISONED_CHECK(&page[1]); })
+/* Which page is the flag stored in */
+#define FOLIO_PF_ANY 0
+#define FOLIO_PF_HEAD 0
+#define FOLIO_PF_ONLY_HEAD 0
+#define FOLIO_PF_NO_TAIL 0
+#define FOLIO_PF_NO_COMPOUND 0
+#define FOLIO_PF_SECOND 1
+
/*
* Macros to create function definitions for page flags
*/
#define TESTPAGEFLAG(uname, lname, policy) \
+static __always_inline bool folio_test_##lname(struct folio *folio) \
+{ return test_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline int Page##uname(struct page *page) \
- { return test_bit(PG_##lname, &policy(page, 0)->flags); }
+{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
#define SETPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void folio_set_##lname(struct folio *folio) \
+{ set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void SetPage##uname(struct page *page) \
- { set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ set_bit(PG_##lname, &policy(page, 1)->flags); }
#define CLEARPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void folio_clear_##lname(struct folio *folio) \
+{ clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void ClearPage##uname(struct page *page) \
- { clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define __SETPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void __folio_set_##lname(struct folio *folio) \
+{ __set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void __SetPage##uname(struct page *page) \
- { __set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
#define __CLEARPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void __folio_clear_##lname(struct folio *folio) \
+{ __clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void __ClearPage##uname(struct page *page) \
- { __clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define TESTSETFLAG(uname, lname, policy) \
+static __always_inline \
+bool folio_test_set_##lname(struct folio *folio) \
+{ return test_and_set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline int TestSetPage##uname(struct page *page) \
- { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
#define TESTCLEARFLAG(uname, lname, policy) \
+static __always_inline \
+bool folio_test_clear_##lname(struct folio *folio) \
+{ return test_and_clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline int TestClearPage##uname(struct page *page) \
- { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define PAGEFLAG(uname, lname, policy) \
TESTPAGEFLAG(uname, lname, policy) \
@@ -306,29 +382,37 @@ static __always_inline int TestClearPage##uname(struct page *page) \
TESTSETFLAG(uname, lname, policy) \
TESTCLEARFLAG(uname, lname, policy)
-#define TESTPAGEFLAG_FALSE(uname) \
+#define TESTPAGEFLAG_FALSE(uname, lname) \
+static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \
static inline int Page##uname(const struct page *page) { return 0; }
-#define SETPAGEFLAG_NOOP(uname) \
+#define SETPAGEFLAG_NOOP(uname, lname) \
+static inline void folio_set_##lname(struct folio *folio) { } \
static inline void SetPage##uname(struct page *page) { }
-#define CLEARPAGEFLAG_NOOP(uname) \
+#define CLEARPAGEFLAG_NOOP(uname, lname) \
+static inline void folio_clear_##lname(struct folio *folio) { } \
static inline void ClearPage##uname(struct page *page) { }
-#define __CLEARPAGEFLAG_NOOP(uname) \
+#define __CLEARPAGEFLAG_NOOP(uname, lname) \
+static inline void __folio_clear_##lname(struct folio *folio) { } \
static inline void __ClearPage##uname(struct page *page) { }
-#define TESTSETFLAG_FALSE(uname) \
+#define TESTSETFLAG_FALSE(uname, lname) \
+static inline bool folio_test_set_##lname(struct folio *folio) \
+{ return 0; } \
static inline int TestSetPage##uname(struct page *page) { return 0; }
-#define TESTCLEARFLAG_FALSE(uname) \
+#define TESTCLEARFLAG_FALSE(uname, lname) \
+static inline bool folio_test_clear_##lname(struct folio *folio) \
+{ return 0; } \
static inline int TestClearPage##uname(struct page *page) { return 0; }
-#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \
- SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname)
+#define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \
+ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname)
-#define TESTSCFLAG_FALSE(uname) \
- TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
+#define TESTSCFLAG_FALSE(uname, lname) \
+ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname)
__PAGEFLAG(Locked, locked, PF_NO_TAIL)
PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
@@ -384,8 +468,8 @@ PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL)
/* PG_readahead is only used for reads; PG_reclaim is only for writes */
PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL)
-PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
- TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND)
+PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND)
+ TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND)
#ifdef CONFIG_HIGHMEM
/*
@@ -394,22 +478,25 @@ PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
*/
#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p))
#else
-PAGEFLAG_FALSE(HighMem)
+PAGEFLAG_FALSE(HighMem, highmem)
#endif
#ifdef CONFIG_SWAP
-static __always_inline int PageSwapCache(struct page *page)
+static __always_inline bool folio_test_swapcache(struct folio *folio)
{
-#ifdef CONFIG_THP_SWAP
- page = compound_head(page);
-#endif
- return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
+ return folio_test_swapbacked(folio) &&
+ test_bit(PG_swapcache, folio_flags(folio, 0));
+}
+static __always_inline bool PageSwapCache(struct page *page)
+{
+ return folio_test_swapcache(page_folio(page));
}
+
SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
#else
-PAGEFLAG_FALSE(SwapCache)
+PAGEFLAG_FALSE(SwapCache, swapcache)
#endif
PAGEFLAG(Unevictable, unevictable, PF_HEAD)
@@ -421,14 +508,14 @@ PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
__CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
#else
-PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
- TESTSCFLAG_FALSE(Mlocked)
+PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked)
+ TESTSCFLAG_FALSE(Mlocked, mlocked)
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
#else
-PAGEFLAG_FALSE(Uncached)
+PAGEFLAG_FALSE(Uncached, uncached)
#endif
#ifdef CONFIG_MEMORY_FAILURE
@@ -437,7 +524,7 @@ TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
#define __PG_HWPOISON (1UL << PG_hwpoison)
extern bool take_page_off_buddy(struct page *page);
#else
-PAGEFLAG_FALSE(HWPoison)
+PAGEFLAG_FALSE(HWPoison, hwpoison)
#define __PG_HWPOISON 0
#endif
@@ -451,7 +538,7 @@ PAGEFLAG(Idle, idle, PF_ANY)
#ifdef CONFIG_KASAN_HW_TAGS
PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD)
#else
-PAGEFLAG_FALSE(SkipKASanPoison)
+PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison)
#endif
/*
@@ -489,10 +576,14 @@ static __always_inline int PageMappingFlags(struct page *page)
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
}
-static __always_inline int PageAnon(struct page *page)
+static __always_inline bool folio_test_anon(struct folio *folio)
+{
+ return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
+}
+
+static __always_inline bool PageAnon(struct page *page)
{
- page = compound_head(page);
- return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
+ return folio_test_anon(page_folio(page));
}
static __always_inline int __PageMovable(struct page *page)
@@ -508,30 +599,32 @@ static __always_inline int __PageMovable(struct page *page)
* is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any
* anon_vma, but to that page's node of the stable tree.
*/
-static __always_inline int PageKsm(struct page *page)
+static __always_inline bool folio_test_ksm(struct folio *folio)
{
- page = compound_head(page);
- return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
+ return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
PAGE_MAPPING_KSM;
}
+
+static __always_inline bool PageKsm(struct page *page)
+{
+ return folio_test_ksm(page_folio(page));
+}
#else
-TESTPAGEFLAG_FALSE(Ksm)
+TESTPAGEFLAG_FALSE(Ksm, ksm)
#endif
u64 stable_page_flags(struct page *page);
-static inline int PageUptodate(struct page *page)
+static inline bool folio_test_uptodate(struct folio *folio)
{
- int ret;
- page = compound_head(page);
- ret = test_bit(PG_uptodate, &(page)->flags);
+ bool ret = test_bit(PG_uptodate, folio_flags(folio, 0));
/*
- * Must ensure that the data we read out of the page is loaded
- * _after_ we've loaded page->flags to check for PageUptodate.
- * We can skip the barrier if the page is not uptodate, because
+ * Must ensure that the data we read out of the folio is loaded
+ * _after_ we've loaded folio->flags to check the uptodate bit.
+ * We can skip the barrier if the folio is not uptodate, because
* we wouldn't be reading anything from it.
*
- * See SetPageUptodate() for the other side of the story.
+ * See folio_mark_uptodate() for the other side of the story.
*/
if (ret)
smp_rmb();
@@ -539,47 +632,71 @@ static inline int PageUptodate(struct page *page)
return ret;
}
-static __always_inline void __SetPageUptodate(struct page *page)
+static inline int PageUptodate(struct page *page)
+{
+ return folio_test_uptodate(page_folio(page));
+}
+
+static __always_inline void __folio_mark_uptodate(struct folio *folio)
{
- VM_BUG_ON_PAGE(PageTail(page), page);
smp_wmb();
- __set_bit(PG_uptodate, &page->flags);
+ __set_bit(PG_uptodate, folio_flags(folio, 0));
}
-static __always_inline void SetPageUptodate(struct page *page)
+static __always_inline void folio_mark_uptodate(struct folio *folio)
{
- VM_BUG_ON_PAGE(PageTail(page), page);
/*
* Memory barrier must be issued before setting the PG_uptodate bit,
- * so that all previous stores issued in order to bring the page
- * uptodate are actually visible before PageUptodate becomes true.
+ * so that all previous stores issued in order to bring the folio
+ * uptodate are actually visible before folio_test_uptodate becomes true.
*/
smp_wmb();
- set_bit(PG_uptodate, &page->flags);
+ set_bit(PG_uptodate, folio_flags(folio, 0));
+}
+
+static __always_inline void __SetPageUptodate(struct page *page)
+{
+ __folio_mark_uptodate((struct folio *)page);
+}
+
+static __always_inline void SetPageUptodate(struct page *page)
+{
+ folio_mark_uptodate((struct folio *)page);
}
CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
-int test_clear_page_writeback(struct page *page);
-int __test_set_page_writeback(struct page *page, bool keep_write);
+bool __folio_start_writeback(struct folio *folio, bool keep_write);
+bool set_page_writeback(struct page *page);
-#define test_set_page_writeback(page) \
- __test_set_page_writeback(page, false)
-#define test_set_page_writeback_keepwrite(page) \
- __test_set_page_writeback(page, true)
+#define folio_start_writeback(folio) \
+ __folio_start_writeback(folio, false)
+#define folio_start_writeback_keepwrite(folio) \
+ __folio_start_writeback(folio, true)
-static inline void set_page_writeback(struct page *page)
+static inline void set_page_writeback_keepwrite(struct page *page)
{
- test_set_page_writeback(page);
+ folio_start_writeback_keepwrite(page_folio(page));
}
-static inline void set_page_writeback_keepwrite(struct page *page)
+static inline bool test_set_page_writeback(struct page *page)
{
- test_set_page_writeback_keepwrite(page);
+ return set_page_writeback(page);
}
__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
+/* Whether there are one or multiple pages in a folio */
+static inline bool folio_test_single(struct folio *folio)
+{
+ return !folio_test_head(folio);
+}
+
+static inline bool folio_test_multi(struct folio *folio)
+{
+ return folio_test_head(folio);
+}
+
static __always_inline void set_compound_head(struct page *page, struct page *head)
{
WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
@@ -603,12 +720,15 @@ static inline void ClearPageCompound(struct page *page)
#ifdef CONFIG_HUGETLB_PAGE
int PageHuge(struct page *page);
int PageHeadHuge(struct page *page);
+static inline bool folio_test_hugetlb(struct folio *folio)
+{
+ return PageHeadHuge(&folio->page);
+}
#else
-TESTPAGEFLAG_FALSE(Huge)
-TESTPAGEFLAG_FALSE(HeadHuge)
+TESTPAGEFLAG_FALSE(Huge, hugetlb)
+TESTPAGEFLAG_FALSE(HeadHuge, headhuge)
#endif
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* PageHuge() only returns true for hugetlbfs pages, but not for
@@ -624,6 +744,11 @@ static inline int PageTransHuge(struct page *page)
return PageHead(page);
}
+static inline bool folio_test_transhuge(struct folio *folio)
+{
+ return folio_test_head(folio);
+}
+
/*
* PageTransCompound returns true for both transparent huge pages
* and hugetlbfs pages, so it should only be called when it's known
@@ -660,12 +785,26 @@ static inline int PageTransTail(struct page *page)
PAGEFLAG(DoubleMap, double_map, PF_SECOND)
TESTSCFLAG(DoubleMap, double_map, PF_SECOND)
#else
-TESTPAGEFLAG_FALSE(TransHuge)
-TESTPAGEFLAG_FALSE(TransCompound)
-TESTPAGEFLAG_FALSE(TransCompoundMap)
-TESTPAGEFLAG_FALSE(TransTail)
-PAGEFLAG_FALSE(DoubleMap)
- TESTSCFLAG_FALSE(DoubleMap)
+TESTPAGEFLAG_FALSE(TransHuge, transhuge)
+TESTPAGEFLAG_FALSE(TransCompound, transcompound)
+TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap)
+TESTPAGEFLAG_FALSE(TransTail, transtail)
+PAGEFLAG_FALSE(DoubleMap, double_map)
+ TESTSCFLAG_FALSE(DoubleMap, double_map)
+#endif
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+/*
+ * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the
+ * compound page.
+ *
+ * This flag is set by hwpoison handler. Cleared by THP split or free page.
+ */
+PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+ TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+#else
+PAGEFLAG_FALSE(HasHWPoisoned)
+ TESTSCFLAG_FALSE(HasHWPoisoned)
#endif
/*
@@ -849,6 +988,11 @@ static inline int page_has_private(struct page *page)
return !!(page->flags & PAGE_FLAGS_PRIVATE);
}
+static inline bool folio_has_private(struct folio *folio)
+{
+ return page_has_private(&folio->page);
+}
+
#undef PF_ANY
#undef PF_HEAD
#undef PF_ONLY_HEAD
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index d8a6aecf99cb..83abf95e9fa7 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -8,46 +8,16 @@
#ifdef CONFIG_PAGE_IDLE_FLAG
-#ifdef CONFIG_64BIT
-static inline bool page_is_young(struct page *page)
-{
- return PageYoung(page);
-}
-
-static inline void set_page_young(struct page *page)
-{
- SetPageYoung(page);
-}
-
-static inline bool test_and_clear_page_young(struct page *page)
-{
- return TestClearPageYoung(page);
-}
-
-static inline bool page_is_idle(struct page *page)
-{
- return PageIdle(page);
-}
-
-static inline void set_page_idle(struct page *page)
-{
- SetPageIdle(page);
-}
-
-static inline void clear_page_idle(struct page *page)
-{
- ClearPageIdle(page);
-}
-#else /* !CONFIG_64BIT */
+#ifndef CONFIG_64BIT
/*
* If there is not enough space to store Idle and Young bits in page flags, use
* page ext flags instead.
*/
extern struct page_ext_operations page_idle_ops;
-static inline bool page_is_young(struct page *page)
+static inline bool folio_test_young(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return false;
@@ -55,9 +25,9 @@ static inline bool page_is_young(struct page *page)
return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
-static inline void set_page_young(struct page *page)
+static inline void folio_set_young(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return;
@@ -65,9 +35,9 @@ static inline void set_page_young(struct page *page)
set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
-static inline bool test_and_clear_page_young(struct page *page)
+static inline bool folio_test_clear_young(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return false;
@@ -75,9 +45,9 @@ static inline bool test_and_clear_page_young(struct page *page)
return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
-static inline bool page_is_idle(struct page *page)
+static inline bool folio_test_idle(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return false;
@@ -85,9 +55,9 @@ static inline bool page_is_idle(struct page *page)
return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
-static inline void set_page_idle(struct page *page)
+static inline void folio_set_idle(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return;
@@ -95,46 +65,75 @@ static inline void set_page_idle(struct page *page)
set_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
-static inline void clear_page_idle(struct page *page)
+static inline void folio_clear_idle(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return;
clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
-#endif /* CONFIG_64BIT */
+#endif /* !CONFIG_64BIT */
#else /* !CONFIG_PAGE_IDLE_FLAG */
-static inline bool page_is_young(struct page *page)
+static inline bool folio_test_young(struct folio *folio)
{
return false;
}
-static inline void set_page_young(struct page *page)
+static inline void folio_set_young(struct folio *folio)
{
}
-static inline bool test_and_clear_page_young(struct page *page)
+static inline bool folio_test_clear_young(struct folio *folio)
{
return false;
}
-static inline bool page_is_idle(struct page *page)
+static inline bool folio_test_idle(struct folio *folio)
{
return false;
}
-static inline void set_page_idle(struct page *page)
+static inline void folio_set_idle(struct folio *folio)
{
}
-static inline void clear_page_idle(struct page *page)
+static inline void folio_clear_idle(struct folio *folio)
{
}
#endif /* CONFIG_PAGE_IDLE_FLAG */
+static inline bool page_is_young(struct page *page)
+{
+ return folio_test_young(page_folio(page));
+}
+
+static inline void set_page_young(struct page *page)
+{
+ folio_set_young(page_folio(page));
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+ return folio_test_clear_young(page_folio(page));
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+ return folio_test_idle(page_folio(page));
+}
+
+static inline void set_page_idle(struct page *page)
+{
+ folio_set_idle(page_folio(page));
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+ folio_clear_idle(page_folio(page));
+}
#endif /* _LINUX_MM_PAGE_IDLE_H */
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 719bfe5108c5..43c638c51c1f 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -12,7 +12,7 @@ extern void __reset_page_owner(struct page *page, unsigned int order);
extern void __set_page_owner(struct page *page,
unsigned int order, gfp_t gfp_mask);
extern void __split_page_owner(struct page *page, unsigned int nr);
-extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
+extern void __folio_copy_owner(struct folio *newfolio, struct folio *old);
extern void __set_page_owner_migrate_reason(struct page *page, int reason);
extern void __dump_page_owner(const struct page *page);
extern void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -36,10 +36,10 @@ static inline void split_page_owner(struct page *page, unsigned int nr)
if (static_branch_unlikely(&page_owner_inited))
__split_page_owner(page, nr);
}
-static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+static inline void folio_copy_owner(struct folio *newfolio, struct folio *old)
{
if (static_branch_unlikely(&page_owner_inited))
- __copy_page_owner(oldpage, newpage);
+ __folio_copy_owner(newfolio, old);
}
static inline void set_page_owner_migrate_reason(struct page *page, int reason)
{
@@ -63,7 +63,7 @@ static inline void split_page_owner(struct page *page,
unsigned int order)
{
}
-static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio)
{
}
static inline void set_page_owner_migrate_reason(struct page *page, int reason)
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 7ad46f45df39..2e677e6ad09f 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -67,9 +67,31 @@ static inline int page_ref_count(const struct page *page)
return atomic_read(&page->_refcount);
}
+/**
+ * folio_ref_count - The reference count on this folio.
+ * @folio: The folio.
+ *
+ * The refcount is usually incremented by calls to folio_get() and
+ * decremented by calls to folio_put(). Some typical users of the
+ * folio refcount:
+ *
+ * - Each reference from a page table
+ * - The page cache
+ * - Filesystem private data
+ * - The LRU list
+ * - Pipes
+ * - Direct IO which references this page in the process address space
+ *
+ * Return: The number of references to this folio.
+ */
+static inline int folio_ref_count(const struct folio *folio)
+{
+ return page_ref_count(&folio->page);
+}
+
static inline int page_count(const struct page *page)
{
- return atomic_read(&compound_head(page)->_refcount);
+ return folio_ref_count(page_folio(page));
}
static inline void set_page_count(struct page *page, int v)
@@ -79,6 +101,11 @@ static inline void set_page_count(struct page *page, int v)
__page_ref_set(page, v);
}
+static inline void folio_set_count(struct folio *folio, int v)
+{
+ set_page_count(&folio->page, v);
+}
+
/*
* Setup the page count before being freed into the page allocator for
* the first time (boot or memory hotplug)
@@ -95,6 +122,11 @@ static inline void page_ref_add(struct page *page, int nr)
__page_ref_mod(page, nr);
}
+static inline void folio_ref_add(struct folio *folio, int nr)
+{
+ page_ref_add(&folio->page, nr);
+}
+
static inline void page_ref_sub(struct page *page, int nr)
{
atomic_sub(nr, &page->_refcount);
@@ -102,6 +134,11 @@ static inline void page_ref_sub(struct page *page, int nr)
__page_ref_mod(page, -nr);
}
+static inline void folio_ref_sub(struct folio *folio, int nr)
+{
+ page_ref_sub(&folio->page, nr);
+}
+
static inline int page_ref_sub_return(struct page *page, int nr)
{
int ret = atomic_sub_return(nr, &page->_refcount);
@@ -111,6 +148,11 @@ static inline int page_ref_sub_return(struct page *page, int nr)
return ret;
}
+static inline int folio_ref_sub_return(struct folio *folio, int nr)
+{
+ return page_ref_sub_return(&folio->page, nr);
+}
+
static inline void page_ref_inc(struct page *page)
{
atomic_inc(&page->_refcount);
@@ -118,6 +160,11 @@ static inline void page_ref_inc(struct page *page)
__page_ref_mod(page, 1);
}
+static inline void folio_ref_inc(struct folio *folio)
+{
+ page_ref_inc(&folio->page);
+}
+
static inline void page_ref_dec(struct page *page)
{
atomic_dec(&page->_refcount);
@@ -125,6 +172,11 @@ static inline void page_ref_dec(struct page *page)
__page_ref_mod(page, -1);
}
+static inline void folio_ref_dec(struct folio *folio)
+{
+ page_ref_dec(&folio->page);
+}
+
static inline int page_ref_sub_and_test(struct page *page, int nr)
{
int ret = atomic_sub_and_test(nr, &page->_refcount);
@@ -134,6 +186,11 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
return ret;
}
+static inline int folio_ref_sub_and_test(struct folio *folio, int nr)
+{
+ return page_ref_sub_and_test(&folio->page, nr);
+}
+
static inline int page_ref_inc_return(struct page *page)
{
int ret = atomic_inc_return(&page->_refcount);
@@ -143,6 +200,11 @@ static inline int page_ref_inc_return(struct page *page)
return ret;
}
+static inline int folio_ref_inc_return(struct folio *folio)
+{
+ return page_ref_inc_return(&folio->page);
+}
+
static inline int page_ref_dec_and_test(struct page *page)
{
int ret = atomic_dec_and_test(&page->_refcount);
@@ -152,6 +214,11 @@ static inline int page_ref_dec_and_test(struct page *page)
return ret;
}
+static inline int folio_ref_dec_and_test(struct folio *folio)
+{
+ return page_ref_dec_and_test(&folio->page);
+}
+
static inline int page_ref_dec_return(struct page *page)
{
int ret = atomic_dec_return(&page->_refcount);
@@ -161,15 +228,91 @@ static inline int page_ref_dec_return(struct page *page)
return ret;
}
-static inline int page_ref_add_unless(struct page *page, int nr, int u)
+static inline int folio_ref_dec_return(struct folio *folio)
+{
+ return page_ref_dec_return(&folio->page);
+}
+
+static inline bool page_ref_add_unless(struct page *page, int nr, int u)
{
- int ret = atomic_add_unless(&page->_refcount, nr, u);
+ bool ret = atomic_add_unless(&page->_refcount, nr, u);
if (page_ref_tracepoint_active(page_ref_mod_unless))
__page_ref_mod_unless(page, nr, ret);
return ret;
}
+static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u)
+{
+ return page_ref_add_unless(&folio->page, nr, u);
+}
+
+/**
+ * folio_try_get - Attempt to increase the refcount on a folio.
+ * @folio: The folio.
+ *
+ * If you do not already have a reference to a folio, you can attempt to
+ * get one using this function. It may fail if, for example, the folio
+ * has been freed since you found a pointer to it, or it is frozen for
+ * the purposes of splitting or migration.
+ *
+ * Return: True if the reference count was successfully incremented.
+ */
+static inline bool folio_try_get(struct folio *folio)
+{
+ return folio_ref_add_unless(folio, 1, 0);
+}
+
+static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
+{
+#ifdef CONFIG_TINY_RCU
+ /*
+ * The caller guarantees the folio will not be freed from interrupt
+ * context, so (on !SMP) we only need preemption to be disabled
+ * and TINY_RCU does that for us.
+ */
+# ifdef CONFIG_PREEMPT_COUNT
+ VM_BUG_ON(!in_atomic() && !irqs_disabled());
+# endif
+ VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
+ folio_ref_add(folio, count);
+#else
+ if (unlikely(!folio_ref_add_unless(folio, count, 0))) {
+ /* Either the folio has been freed, or will be freed. */
+ return false;
+ }
+#endif
+ return true;
+}
+
+/**
+ * folio_try_get_rcu - Attempt to increase the refcount on a folio.
+ * @folio: The folio.
+ *
+ * This is a version of folio_try_get() optimised for non-SMP kernels.
+ * If you are still holding the rcu_read_lock() after looking up the
+ * page and know that the page cannot have its refcount decreased to
+ * zero in interrupt context, you can use this instead of folio_try_get().
+ *
+ * Example users include get_user_pages_fast() (as pages are not unmapped
+ * from interrupt context) and the page cache lookups (as pages are not
+ * truncated from interrupt context). We also know that pages are not
+ * frozen in interrupt context for the purposes of splitting or migration.
+ *
+ * You can also use this function if you're holding a lock that prevents
+ * pages being frozen & removed; eg the i_pages lock for the page cache
+ * or the mmap_sem or page table lock for page tables. In this case,
+ * it will always succeed, and you could have used a plain folio_get(),
+ * but it's sometimes more convenient to have a common function called
+ * from both locked and RCU-protected contexts.
+ *
+ * Return: True if the reference count was successfully incremented.
+ */
+static inline bool folio_try_get_rcu(struct folio *folio)
+{
+ return folio_ref_try_add_rcu(folio, 1);
+}
+
static inline int page_ref_freeze(struct page *page, int count)
{
int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
@@ -179,6 +322,11 @@ static inline int page_ref_freeze(struct page *page, int count)
return ret;
}
+static inline int folio_ref_freeze(struct folio *folio, int count)
+{
+ return page_ref_freeze(&folio->page, count);
+}
+
static inline void page_ref_unfreeze(struct page *page, int count)
{
VM_BUG_ON_PAGE(page_count(page) != 0, page);
@@ -189,4 +337,8 @@ static inline void page_ref_unfreeze(struct page *page, int count)
__page_ref_unfreeze(page, count);
}
+static inline void folio_ref_unfreeze(struct folio *folio, int count)
+{
+ page_ref_unfreeze(&folio->page, count);
+}
#endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 62db6b0176b9..013cdc90f5fd 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -162,149 +162,119 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping)
void release_pages(struct page **pages, int nr);
-/*
- * For file cache pages, return the address_space, otherwise return NULL
+struct address_space *page_mapping(struct page *);
+struct address_space *folio_mapping(struct folio *);
+struct address_space *swapcache_mapping(struct folio *);
+
+/**
+ * folio_file_mapping - Find the mapping this folio belongs to.
+ * @folio: The folio.
+ *
+ * For folios which are in the page cache, return the mapping that this
+ * page belongs to. Folios in the swap cache return the mapping of the
+ * swap file or swap device where the data is stored. This is different
+ * from the mapping returned by folio_mapping(). The only reason to
+ * use it is if, like NFS, you return 0 from ->activate_swapfile.
+ *
+ * Do not call this for folios which aren't in the page cache or swap cache.
*/
-static inline struct address_space *page_mapping_file(struct page *page)
+static inline struct address_space *folio_file_mapping(struct folio *folio)
{
- if (unlikely(PageSwapCache(page)))
- return NULL;
- return page_mapping(page);
+ if (unlikely(folio_test_swapcache(folio)))
+ return swapcache_mapping(folio);
+
+ return folio->mapping;
+}
+
+static inline struct address_space *page_file_mapping(struct page *page)
+{
+ return folio_file_mapping(page_folio(page));
}
/*
- * speculatively take a reference to a page.
- * If the page is free (_refcount == 0), then _refcount is untouched, and 0
- * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned.
- *
- * This function must be called inside the same rcu_read_lock() section as has
- * been used to lookup the page in the pagecache radix-tree (or page table):
- * this allows allocators to use a synchronize_rcu() to stabilize _refcount.
- *
- * Unless an RCU grace period has passed, the count of all pages coming out
- * of the allocator must be considered unstable. page_count may return higher
- * than expected, and put_page must be able to do the right thing when the
- * page has been finished with, no matter what it is subsequently allocated
- * for (because put_page is what is used here to drop an invalid speculative
- * reference).
- *
- * This is the interesting part of the lockless pagecache (and lockless
- * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
- * has the following pattern:
- * 1. find page in radix tree
- * 2. conditionally increment refcount
- * 3. check the page is still in pagecache (if no, goto 1)
- *
- * Remove-side that cares about stability of _refcount (eg. reclaim) has the
- * following (with the i_pages lock held):
- * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
- * B. remove page from pagecache
- * C. free the page
- *
- * There are 2 critical interleavings that matter:
- * - 2 runs before A: in this case, A sees elevated refcount and bails out
- * - A runs before 2: in this case, 2 sees zero refcount and retries;
- * subsequently, B will complete and 1 will find no page, causing the
- * lookup to return NULL.
- *
- * It is possible that between 1 and 2, the page is removed then the exact same
- * page is inserted into the same position in pagecache. That's OK: the
- * old find_get_page using a lock could equally have run before or after
- * such a re-insertion, depending on order that locks are granted.
- *
- * Lookups racing against pagecache insertion isn't a big problem: either 1
- * will find the page or it will not. Likewise, the old find_get_page could run
- * either before the insertion or afterwards, depending on timing.
+ * For file cache pages, return the address_space, otherwise return NULL
*/
-static inline int __page_cache_add_speculative(struct page *page, int count)
+static inline struct address_space *page_mapping_file(struct page *page)
{
-#ifdef CONFIG_TINY_RCU
-# ifdef CONFIG_PREEMPT_COUNT
- VM_BUG_ON(!in_atomic() && !irqs_disabled());
-# endif
- /*
- * Preempt must be disabled here - we rely on rcu_read_lock doing
- * this for us.
- *
- * Pagecache won't be truncated from interrupt context, so if we have
- * found a page in the radix tree here, we have pinned its refcount by
- * disabling preempt, and hence no need for the "speculative get" that
- * SMP requires.
- */
- VM_BUG_ON_PAGE(page_count(page) == 0, page);
- page_ref_add(page, count);
+ struct folio *folio = page_folio(page);
-#else
- if (unlikely(!page_ref_add_unless(page, count, 0))) {
- /*
- * Either the page has been freed, or will be freed.
- * In either case, retry here and the caller should
- * do the right thing (see comments above).
- */
- return 0;
- }
-#endif
- VM_BUG_ON_PAGE(PageTail(page), page);
-
- return 1;
+ if (unlikely(folio_test_swapcache(folio)))
+ return NULL;
+ return folio_mapping(folio);
}
-static inline int page_cache_get_speculative(struct page *page)
+static inline bool page_cache_add_speculative(struct page *page, int count)
{
- return __page_cache_add_speculative(page, 1);
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ return folio_ref_try_add_rcu((struct folio *)page, count);
}
-static inline int page_cache_add_speculative(struct page *page, int count)
+static inline bool page_cache_get_speculative(struct page *page)
{
- return __page_cache_add_speculative(page, count);
+ return page_cache_add_speculative(page, 1);
}
/**
- * attach_page_private - Attach private data to a page.
- * @page: Page to attach data to.
- * @data: Data to attach to page.
+ * folio_attach_private - Attach private data to a folio.
+ * @folio: Folio to attach data to.
+ * @data: Data to attach to folio.
*
- * Attaching private data to a page increments the page's reference count.
- * The data must be detached before the page will be freed.
+ * Attaching private data to a folio increments the page's reference count.
+ * The data must be detached before the folio will be freed.
*/
-static inline void attach_page_private(struct page *page, void *data)
+static inline void folio_attach_private(struct folio *folio, void *data)
{
- get_page(page);
- set_page_private(page, (unsigned long)data);
- SetPagePrivate(page);
+ folio_get(folio);
+ folio->private = data;
+ folio_set_private(folio);
}
/**
- * detach_page_private - Detach private data from a page.
- * @page: Page to detach data from.
+ * folio_detach_private - Detach private data from a folio.
+ * @folio: Folio to detach data from.
*
- * Removes the data that was previously attached to the page and decrements
+ * Removes the data that was previously attached to the folio and decrements
* the refcount on the page.
*
- * Return: Data that was attached to the page.
+ * Return: Data that was attached to the folio.
*/
-static inline void *detach_page_private(struct page *page)
+static inline void *folio_detach_private(struct folio *folio)
{
- void *data = (void *)page_private(page);
+ void *data = folio_get_private(folio);
- if (!PagePrivate(page))
+ if (!folio_test_private(folio))
return NULL;
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
+ folio_clear_private(folio);
+ folio->private = NULL;
+ folio_put(folio);
return data;
}
+static inline void attach_page_private(struct page *page, void *data)
+{
+ folio_attach_private(page_folio(page), data);
+}
+
+static inline void *detach_page_private(struct page *page)
+{
+ return folio_detach_private(page_folio(page));
+}
+
#ifdef CONFIG_NUMA
-extern struct page *__page_cache_alloc(gfp_t gfp);
+struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
#else
-static inline struct page *__page_cache_alloc(gfp_t gfp)
+static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
{
- return alloc_pages(gfp, 0);
+ return folio_alloc(gfp, order);
}
#endif
+static inline struct page *__page_cache_alloc(gfp_t gfp)
+{
+ return &filemap_alloc_folio(gfp, 0)->page;
+}
+
static inline struct page *page_cache_alloc(struct address_space *x)
{
return __page_cache_alloc(mapping_gfp_mask(x));
@@ -331,9 +301,28 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
#define FGP_FOR_MMAP 0x00000040
#define FGP_HEAD 0x00000080
#define FGP_ENTRY 0x00000100
+#define FGP_STABLE 0x00000200
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
- int fgp_flags, gfp_t cache_gfp_mask);
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp);
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp);
+
+/**
+ * filemap_get_folio - Find and get a folio.
+ * @mapping: The address_space to search.
+ * @index: The page index.
+ *
+ * Looks up the page cache entry at @mapping & @index. If a folio is
+ * present, it is returned with an increased refcount.
+ *
+ * Otherwise, %NULL is returned.
+ */
+static inline struct folio *filemap_get_folio(struct address_space *mapping,
+ pgoff_t index)
+{
+ return __filemap_get_folio(mapping, index, 0, 0);
+}
/**
* find_get_page - find and get a page reference
@@ -377,25 +366,6 @@ static inline struct page *find_lock_page(struct address_space *mapping,
}
/**
- * find_lock_head - Locate, pin and lock a pagecache page.
- * @mapping: The address_space to search.
- * @index: The page index.
- *
- * Looks up the page cache entry at @mapping & @index. If there is a
- * page cache page, its head page is returned locked and with an increased
- * refcount.
- *
- * Context: May sleep.
- * Return: A struct page which is !PageTail, or %NULL if there is no page
- * in the cache for this index.
- */
-static inline struct page *find_lock_head(struct address_space *mapping,
- pgoff_t index)
-{
- return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0);
-}
-
-/**
* find_or_create_page - locate or add a pagecache page
* @mapping: the page's address_space
* @index: the page's index into the mapping
@@ -452,6 +422,73 @@ static inline bool thp_contains(struct page *head, pgoff_t index)
return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL));
}
+#define swapcache_index(folio) __page_file_index(&(folio)->page)
+
+/**
+ * folio_index - File index of a folio.
+ * @folio: The folio.
+ *
+ * For a folio which is either in the page cache or the swap cache,
+ * return its index within the address_space it belongs to. If you know
+ * the page is definitely in the page cache, you can look at the folio's
+ * index directly.
+ *
+ * Return: The index (offset in units of pages) of a folio in its file.
+ */
+static inline pgoff_t folio_index(struct folio *folio)
+{
+ if (unlikely(folio_test_swapcache(folio)))
+ return swapcache_index(folio);
+ return folio->index;
+}
+
+/**
+ * folio_next_index - Get the index of the next folio.
+ * @folio: The current folio.
+ *
+ * Return: The index of the folio which follows this folio in the file.
+ */
+static inline pgoff_t folio_next_index(struct folio *folio)
+{
+ return folio->index + folio_nr_pages(folio);
+}
+
+/**
+ * folio_file_page - The page for a particular index.
+ * @folio: The folio which contains this index.
+ * @index: The index we want to look up.
+ *
+ * Sometimes after looking up a folio in the page cache, we need to
+ * obtain the specific page for an index (eg a page fault).
+ *
+ * Return: The page containing the file data for this index.
+ */
+static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
+{
+ /* HugeTLBfs indexes the page cache in units of hpage_size */
+ if (folio_test_hugetlb(folio))
+ return &folio->page;
+ return folio_page(folio, index & (folio_nr_pages(folio) - 1));
+}
+
+/**
+ * folio_contains - Does this folio contain this index?
+ * @folio: The folio.
+ * @index: The page index within the file.
+ *
+ * Context: The caller should have the page locked in order to prevent
+ * (eg) shmem from moving the page between the page cache and swap cache
+ * and changing its index in the middle of the operation.
+ * Return: true or false.
+ */
+static inline bool folio_contains(struct folio *folio, pgoff_t index)
+{
+ /* HugeTLBfs indexes the page cache in units of hpage_size */
+ if (folio_test_hugetlb(folio))
+ return folio->index == index;
+ return index - folio_index(folio) < folio_nr_pages(folio);
+}
+
/*
* Given the page we found in the page cache, return the page corresponding
* to this index in the file
@@ -560,6 +597,27 @@ static inline loff_t page_file_offset(struct page *page)
return ((loff_t)page_index(page)) << PAGE_SHIFT;
}
+/**
+ * folio_pos - Returns the byte position of this folio in its file.
+ * @folio: The folio.
+ */
+static inline loff_t folio_pos(struct folio *folio)
+{
+ return page_offset(&folio->page);
+}
+
+/**
+ * folio_file_pos - Returns the byte position of this folio in its file.
+ * @folio: The folio.
+ *
+ * This differs from folio_pos() for folios which belong to a swap file.
+ * NFS is the only filesystem today which needs to use folio_file_pos().
+ */
+static inline loff_t folio_file_pos(struct folio *folio)
+{
+ return page_file_offset(&folio->page);
+}
+
extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
unsigned long address);
@@ -575,13 +633,13 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
}
struct wait_page_key {
- struct page *page;
+ struct folio *folio;
int bit_nr;
int page_match;
};
struct wait_page_queue {
- struct page *page;
+ struct folio *folio;
int bit_nr;
wait_queue_entry_t wait;
};
@@ -589,7 +647,7 @@ struct wait_page_queue {
static inline bool wake_page_match(struct wait_page_queue *wait_page,
struct wait_page_key *key)
{
- if (wait_page->page != key->page)
+ if (wait_page->folio != key->folio)
return false;
key->page_match = 1;
@@ -599,20 +657,31 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page,
return true;
}
-extern void __lock_page(struct page *page);
-extern int __lock_page_killable(struct page *page);
-extern int __lock_page_async(struct page *page, struct wait_page_queue *wait);
-extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+void __folio_lock(struct folio *folio);
+int __folio_lock_killable(struct folio *folio);
+bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
unsigned int flags);
-extern void unlock_page(struct page *page);
+void unlock_page(struct page *page);
+void folio_unlock(struct folio *folio);
+
+static inline bool folio_trylock(struct folio *folio)
+{
+ return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0)));
+}
/*
* Return true if the page was successfully locked
*/
static inline int trylock_page(struct page *page)
{
- page = compound_head(page);
- return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
+ return folio_trylock(page_folio(page));
+}
+
+static inline void folio_lock(struct folio *folio)
+{
+ might_sleep();
+ if (!folio_trylock(folio))
+ __folio_lock(folio);
}
/*
@@ -620,38 +689,30 @@ static inline int trylock_page(struct page *page)
*/
static inline void lock_page(struct page *page)
{
+ struct folio *folio;
might_sleep();
- if (!trylock_page(page))
- __lock_page(page);
+
+ folio = page_folio(page);
+ if (!folio_trylock(folio))
+ __folio_lock(folio);
}
-/*
- * lock_page_killable is like lock_page but can be interrupted by fatal
- * signals. It returns 0 if it locked the page and -EINTR if it was
- * killed while waiting.
- */
-static inline int lock_page_killable(struct page *page)
+static inline int folio_lock_killable(struct folio *folio)
{
might_sleep();
- if (!trylock_page(page))
- return __lock_page_killable(page);
+ if (!folio_trylock(folio))
+ return __folio_lock_killable(folio);
return 0;
}
/*
- * lock_page_async - Lock the page, unless this would block. If the page
- * is already locked, then queue a callback when the page becomes unlocked.
- * This callback can then retry the operation.
- *
- * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page
- * was already locked and the callback defined in 'wait' was queued.
+ * lock_page_killable is like lock_page but can be interrupted by fatal
+ * signals. It returns 0 if it locked the page and -EINTR if it was
+ * killed while waiting.
*/
-static inline int lock_page_async(struct page *page,
- struct wait_page_queue *wait)
+static inline int lock_page_killable(struct page *page)
{
- if (!trylock_page(page))
- return __lock_page_async(page, wait);
- return 0;
+ return folio_lock_killable(page_folio(page));
}
/*
@@ -659,78 +720,108 @@ static inline int lock_page_async(struct page *page,
* caller indicated that it can handle a retry.
*
* Return value and mmap_lock implications depend on flags; see
- * __lock_page_or_retry().
+ * __folio_lock_or_retry().
*/
-static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
+static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
+ struct folio *folio;
might_sleep();
- return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
+
+ folio = page_folio(page);
+ return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags);
}
/*
- * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc.,
+ * This is exported only for folio_wait_locked/folio_wait_writeback, etc.,
* and should not be used directly.
*/
-extern void wait_on_page_bit(struct page *page, int bit_nr);
-extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
+void folio_wait_bit(struct folio *folio, int bit_nr);
+int folio_wait_bit_killable(struct folio *folio, int bit_nr);
/*
- * Wait for a page to be unlocked.
+ * Wait for a folio to be unlocked.
*
- * This must be called with the caller "holding" the page,
- * ie with increased "page->count" so that the page won't
+ * This must be called with the caller "holding" the folio,
+ * ie with increased "page->count" so that the folio won't
* go away during the wait..
*/
+static inline void folio_wait_locked(struct folio *folio)
+{
+ if (folio_test_locked(folio))
+ folio_wait_bit(folio, PG_locked);
+}
+
+static inline int folio_wait_locked_killable(struct folio *folio)
+{
+ if (!folio_test_locked(folio))
+ return 0;
+ return folio_wait_bit_killable(folio, PG_locked);
+}
+
static inline void wait_on_page_locked(struct page *page)
{
- if (PageLocked(page))
- wait_on_page_bit(compound_head(page), PG_locked);
+ folio_wait_locked(page_folio(page));
}
static inline int wait_on_page_locked_killable(struct page *page)
{
- if (!PageLocked(page))
- return 0;
- return wait_on_page_bit_killable(compound_head(page), PG_locked);
+ return folio_wait_locked_killable(page_folio(page));
}
int put_and_wait_on_page_locked(struct page *page, int state);
void wait_on_page_writeback(struct page *page);
-int wait_on_page_writeback_killable(struct page *page);
-extern void end_page_writeback(struct page *page);
+void folio_wait_writeback(struct folio *folio);
+int folio_wait_writeback_killable(struct folio *folio);
+void end_page_writeback(struct page *page);
+void folio_end_writeback(struct folio *folio);
void wait_for_stable_page(struct page *page);
+void folio_wait_stable(struct folio *folio);
+void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn);
+static inline void __set_page_dirty(struct page *page,
+ struct address_space *mapping, int warn)
+{
+ __folio_mark_dirty(page_folio(page), mapping, warn);
+}
+void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
+ struct bdi_writeback *wb);
+static inline void account_page_cleaned(struct page *page,
+ struct address_space *mapping, struct bdi_writeback *wb)
+{
+ return folio_account_cleaned(page_folio(page), mapping, wb);
+}
+void __folio_cancel_dirty(struct folio *folio);
+static inline void folio_cancel_dirty(struct folio *folio)
+{
+ /* Avoid atomic ops, locking, etc. when not actually needed. */
+ if (folio_test_dirty(folio))
+ __folio_cancel_dirty(folio);
+}
+static inline void cancel_dirty_page(struct page *page)
+{
+ folio_cancel_dirty(page_folio(page));
+}
+bool folio_clear_dirty_for_io(struct folio *folio);
+bool clear_page_dirty_for_io(struct page *page);
+int __must_check folio_write_one(struct folio *folio);
+static inline int __must_check write_one_page(struct page *page)
+{
+ return folio_write_one(page_folio(page));
+}
-void __set_page_dirty(struct page *, struct address_space *, int warn);
int __set_page_dirty_nobuffers(struct page *page);
int __set_page_dirty_no_writeback(struct page *page);
void page_endio(struct page *page, bool is_write, int err);
-/**
- * set_page_private_2 - Set PG_private_2 on a page and take a ref
- * @page: The page.
- *
- * Set the PG_private_2 flag on a page and take the reference needed for the VM
- * to handle its lifetime correctly. This sets the flag and takes the
- * reference unconditionally, so care must be taken not to set the flag again
- * if it's already set.
- */
-static inline void set_page_private_2(struct page *page)
-{
- page = compound_head(page);
- get_page(page);
- SetPagePrivate2(page);
-}
-
-void end_page_private_2(struct page *page);
-void wait_on_page_private_2(struct page *page);
-int wait_on_page_private_2_killable(struct page *page);
+void folio_end_private_2(struct folio *folio);
+void folio_wait_private_2(struct folio *folio);
+int folio_wait_private_2_killable(struct folio *folio);
/*
* Add an arbitrary waiter to a page's wait queue
*/
-extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
+void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
/*
* Fault everything in given userspace address range in.
@@ -790,9 +881,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, size_t size)
}
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t index, gfp_t gfp_mask);
+ pgoff_t index, gfp_t gfp);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t index, gfp_t gfp_mask);
+ pgoff_t index, gfp_t gfp);
+int filemap_add_folio(struct address_space *mapping, struct folio *folio,
+ pgoff_t index, gfp_t gfp);
extern void delete_from_page_cache(struct page *page);
extern void __delete_from_page_cache(struct page *page, void *shadow);
void replace_page_cache_page(struct page *old, struct page *new);
@@ -817,6 +910,10 @@ static inline int add_to_page_cache(struct page *page,
return error;
}
+/* Must be non-static for BPF error injection */
+int __filemap_add_folio(struct address_space *mapping, struct folio *folio,
+ pgoff_t index, gfp_t gfp, void **shadowp);
+
/**
* struct readahead_control - Describes a readahead request.
*
@@ -906,33 +1003,57 @@ void page_cache_async_readahead(struct address_space *mapping,
page_cache_async_ra(&ractl, page, req_count);
}
+static inline struct folio *__readahead_folio(struct readahead_control *ractl)
+{
+ struct folio *folio;
+
+ BUG_ON(ractl->_batch_count > ractl->_nr_pages);
+ ractl->_nr_pages -= ractl->_batch_count;
+ ractl->_index += ractl->_batch_count;
+
+ if (!ractl->_nr_pages) {
+ ractl->_batch_count = 0;
+ return NULL;
+ }
+
+ folio = xa_load(&ractl->mapping->i_pages, ractl->_index);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ ractl->_batch_count = folio_nr_pages(folio);
+
+ return folio;
+}
+
/**
* readahead_page - Get the next page to read.
- * @rac: The current readahead request.
+ * @ractl: The current readahead request.
*
* Context: The page is locked and has an elevated refcount. The caller
* should decreases the refcount once the page has been submitted for I/O
* and unlock the page once all I/O to that page has completed.
* Return: A pointer to the next page, or %NULL if we are done.
*/
-static inline struct page *readahead_page(struct readahead_control *rac)
+static inline struct page *readahead_page(struct readahead_control *ractl)
{
- struct page *page;
-
- BUG_ON(rac->_batch_count > rac->_nr_pages);
- rac->_nr_pages -= rac->_batch_count;
- rac->_index += rac->_batch_count;
+ struct folio *folio = __readahead_folio(ractl);
- if (!rac->_nr_pages) {
- rac->_batch_count = 0;
- return NULL;
- }
+ return &folio->page;
+}
- page = xa_load(&rac->mapping->i_pages, rac->_index);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- rac->_batch_count = thp_nr_pages(page);
+/**
+ * readahead_folio - Get the next folio to read.
+ * @ractl: The current readahead request.
+ *
+ * Context: The folio is locked. The caller should unlock the folio once
+ * all I/O to that folio has completed.
+ * Return: A pointer to the next folio, or %NULL if we are done.
+ */
+static inline struct folio *readahead_folio(struct readahead_control *ractl)
+{
+ struct folio *folio = __readahead_folio(ractl);
- return page;
+ if (folio)
+ folio_put(folio);
+ return folio;
}
static inline unsigned int __readahead_batch(struct readahead_control *rac,
@@ -1040,6 +1161,34 @@ static inline unsigned long dir_pages(struct inode *inode)
}
/**
+ * folio_mkwrite_check_truncate - check if folio was truncated
+ * @folio: the folio to check
+ * @inode: the inode to check the folio against
+ *
+ * Return: the number of bytes in the folio up to EOF,
+ * or -EFAULT if the folio was truncated.
+ */
+static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio,
+ struct inode *inode)
+{
+ loff_t size = i_size_read(inode);
+ pgoff_t index = size >> PAGE_SHIFT;
+ size_t offset = offset_in_folio(folio, size);
+
+ if (!folio->mapping)
+ return -EFAULT;
+
+ /* folio is wholly inside EOF */
+ if (folio_next_index(folio) - 1 < index)
+ return folio_size(folio);
+ /* folio is wholly past EOF */
+ if (folio->index > index || !offset)
+ return -EFAULT;
+ /* folio is partially inside EOF */
+ return offset;
+}
+
+/**
* page_mkwrite_check_truncate - check if page was truncated
* @page: the page to check
* @inode: the inode to check the page against
@@ -1068,19 +1217,25 @@ static inline int page_mkwrite_check_truncate(struct page *page,
}
/**
- * i_blocks_per_page - How many blocks fit in this page.
+ * i_blocks_per_folio - How many blocks fit in this folio.
* @inode: The inode which contains the blocks.
- * @page: The page (head page if the page is a THP).
+ * @folio: The folio.
*
- * If the block size is larger than the size of this page, return zero.
+ * If the block size is larger than the size of this folio, return zero.
*
- * Context: The caller should hold a refcount on the page to prevent it
+ * Context: The caller should hold a refcount on the folio to prevent it
* from being split.
- * Return: The number of filesystem blocks covered by this page.
+ * Return: The number of filesystem blocks covered by this folio.
*/
static inline
+unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio)
+{
+ return folio_size(folio) >> inode->i_blkbits;
+}
+
+static inline
unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
{
- return thp_size(page) >> inode->i_blkbits;
+ return i_blocks_per_folio(inode, page_folio(page));
}
#endif /* _LINUX_PAGEMAP_H */
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index d2558121d48c..6f7949b2fd8d 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -3,6 +3,7 @@
#define _LINUX_PART_STAT_H
#include <linux/genhd.h>
+#include <asm/local.h>
struct disk_stats {
u64 nsecs[NR_STAT_GROUPS];
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index ae16a9856305..b31d3f3312ce 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -267,6 +267,28 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
}
/**
+ * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the
+ * caller is responsible for taking RCU.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref)
+{
+ unsigned long __percpu *percpu_count;
+ bool ret = false;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ if (likely(__ref_is_percpu(ref, &percpu_count))) {
+ this_cpu_inc(*percpu_count);
+ ret = true;
+ } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
+ ret = atomic_long_inc_not_zero(&ref->data->count);
+ }
+ return ret;
+}
+
+/**
* percpu_ref_tryget_live - try to increment a live percpu refcount
* @ref: percpu_ref to try-get
*
@@ -283,20 +305,11 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
*/
static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
{
- unsigned long __percpu *percpu_count;
bool ret = false;
rcu_read_lock();
-
- if (__ref_is_percpu(ref, &percpu_count)) {
- this_cpu_inc(*percpu_count);
- ret = true;
- } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
- ret = atomic_long_inc_not_zero(&ref->data->count);
- }
-
+ ret = percpu_ref_tryget_live_rcu(ref);
rcu_read_unlock();
-
return ret;
}
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c976cc6de257..e704b1a4c06c 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -235,7 +235,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
*
* returns the number of cleaned PTEs.
*/
-int page_mkclean(struct page *);
+int folio_mkclean(struct folio *);
/*
* called in munlock()/munmap() path to check for other vmas holding
@@ -295,12 +295,14 @@ static inline void try_to_unmap(struct page *page, enum ttu_flags flags)
{
}
-static inline int page_mkclean(struct page *page)
+static inline int folio_mkclean(struct folio *folio)
{
return 0;
}
-
-
#endif /* CONFIG_MMU */
+static inline int page_mkclean(struct page *page)
+{
+ return folio_mkclean(page_folio(page));
+}
#endif /* _LINUX_RMAP_H */
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 2713e689ad66..4a6ff274335a 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -427,6 +427,19 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
int __sbitmap_queue_get(struct sbitmap_queue *sbq);
/**
+ * __sbitmap_queue_get_batch() - Try to allocate a batch of free bits
+ * @sbq: Bitmap queue to allocate from.
+ * @nr_tags: number of tags requested
+ * @offset: offset to add to returned bits
+ *
+ * Return: Mask of allocated tags, 0 if none are found. Each tag allocated is
+ * a bit in the mask returned, and the caller must add @offset to the value to
+ * get the absolute tag value.
+ */
+unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
+ unsigned int *offset);
+
+/**
* __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
* sbitmap_queue, limiting the depth used from each word, with preemption
* already disabled.
@@ -515,6 +528,17 @@ void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
unsigned int cpu);
+/**
+ * sbitmap_queue_clear_batch() - Free a batch of allocated bits
+ * &struct sbitmap_queue.
+ * @sbq: Bitmap to free from.
+ * @offset: offset for each tag in array
+ * @tags: array of tags
+ * @nr_tags: number of tags in array
+ */
+void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
+ int *tags, int nr_tags);
+
static inline int sbq_index_inc(int index)
{
return (index + 1) & (SBQ_WAIT_QUEUES - 1);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c1a927ddec64..e0454e60fe8f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1160,10 +1160,8 @@ struct task_struct {
/* Stacked block device info: */
struct bio_list *bio_list;
-#ifdef CONFIG_BLOCK
/* Stack plugging: */
struct blk_plug *plug;
-#endif
/* VM state: */
struct reclaim_state *reclaim_state;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 14ab0c0bc924..1ce9a9eb223b 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -128,6 +128,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags);
+bool sk_msg_is_readable(struct sock *sk);
static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
{
diff --git a/include/linux/swap.h b/include/linux/swap.h
index ba52f3a3478e..cdf0957a88a4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -320,11 +320,17 @@ struct vma_swap_readahead {
#endif
};
+static inline swp_entry_t folio_swap_entry(struct folio *folio)
+{
+ swp_entry_t entry = { .val = page_private(&folio->page) };
+ return entry;
+}
+
/* linux/mm/workingset.c */
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg);
-void workingset_refault(struct page *page, void *shadow);
-void workingset_activation(struct page *page);
+void workingset_refault(struct folio *folio, void *shadow);
+void workingset_activation(struct folio *folio);
/* Only track the nodes of mappings with shadow entries */
void workingset_update_node(struct xa_node *node);
@@ -344,9 +350,11 @@ extern unsigned long nr_free_buffer_pages(void);
/* linux/mm/swap.c */
extern void lru_note_cost(struct lruvec *lruvec, bool file,
unsigned int nr_pages);
-extern void lru_note_cost_page(struct page *);
+extern void lru_note_cost_folio(struct folio *);
+extern void folio_add_lru(struct folio *);
extern void lru_cache_add(struct page *);
-extern void mark_page_accessed(struct page *);
+void mark_page_accessed(struct page *);
+void folio_mark_accessed(struct folio *);
extern atomic_t lru_disable_count;
@@ -365,7 +373,6 @@ extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_cpu_zone(struct zone *zone);
extern void lru_add_drain_all(void);
-extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
extern void deactivate_page(struct page *page);
extern void mark_page_lazyfree(struct page *page);
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index 96305a64a5a7..c635c2e014e3 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -3,7 +3,7 @@
#define _LINUX_T10_PI_H
#include <linux/types.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
/*
* A T10 PI-capable target device can be formatted with different
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index aa11fe323c56..12d827734686 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -269,6 +269,7 @@ enum tpm2_cc_attrs {
#define TPM_VID_INTEL 0x8086
#define TPM_VID_WINBOND 0x1050
#define TPM_VID_STM 0x104A
+#define TPM_VID_ATML 0x1114
enum tpm_chip_flags {
TPM_CHIP_FLAG_TPM2 = BIT(1),
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d6a6cf53b127..bfe38869498d 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -415,6 +415,78 @@ static inline void drain_zonestat(struct zone *zone,
struct per_cpu_zonestat *pzstats) { }
#endif /* CONFIG_SMP */
+static inline void __zone_stat_mod_folio(struct folio *folio,
+ enum zone_stat_item item, long nr)
+{
+ __mod_zone_page_state(folio_zone(folio), item, nr);
+}
+
+static inline void __zone_stat_add_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio));
+}
+
+static inline void __zone_stat_sub_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void zone_stat_mod_folio(struct folio *folio,
+ enum zone_stat_item item, long nr)
+{
+ mod_zone_page_state(folio_zone(folio), item, nr);
+}
+
+static inline void zone_stat_add_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio));
+}
+
+static inline void zone_stat_sub_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void __node_stat_mod_folio(struct folio *folio,
+ enum node_stat_item item, long nr)
+{
+ __mod_node_page_state(folio_pgdat(folio), item, nr);
+}
+
+static inline void __node_stat_add_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio));
+}
+
+static inline void __node_stat_sub_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void node_stat_mod_folio(struct folio *folio,
+ enum node_stat_item item, long nr)
+{
+ mod_node_page_state(folio_pgdat(folio), item, nr);
+}
+
+static inline void node_stat_add_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio));
+}
+
+static inline void node_stat_sub_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio));
+}
+
static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
int migratetype)
{
@@ -525,12 +597,6 @@ static inline void mod_lruvec_page_state(struct page *page,
#endif /* CONFIG_MEMCG */
-static inline void inc_lruvec_state(struct lruvec *lruvec,
- enum node_stat_item idx)
-{
- mod_lruvec_state(lruvec, idx, 1);
-}
-
static inline void __inc_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
@@ -543,6 +609,24 @@ static inline void __dec_lruvec_page_state(struct page *page,
__mod_lruvec_page_state(page, idx, -1);
}
+static inline void __lruvec_stat_mod_folio(struct folio *folio,
+ enum node_stat_item idx, int val)
+{
+ __mod_lruvec_page_state(&folio->page, idx, val);
+}
+
+static inline void __lruvec_stat_add_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio));
+}
+
+static inline void __lruvec_stat_sub_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
+}
+
static inline void inc_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
@@ -555,4 +639,21 @@ static inline void dec_lruvec_page_state(struct page *page,
mod_lruvec_page_state(page, idx, -1);
}
+static inline void lruvec_stat_mod_folio(struct folio *folio,
+ enum node_stat_item idx, int val)
+{
+ mod_lruvec_page_state(&folio->page, idx, val);
+}
+
+static inline void lruvec_stat_add_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio));
+}
+
+static inline void lruvec_stat_sub_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
+}
#endif /* _LINUX_VMSTAT_H */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index d1f65adf6a26..3bfd487d1dd2 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -11,7 +11,6 @@
#include <linux/flex_proportions.h>
#include <linux/backing-dev-defs.h>
#include <linux/blk_types.h>
-#include <linux/blk-cgroup.h>
struct bio;
@@ -109,15 +108,12 @@ static inline int wbc_to_write_flags(struct writeback_control *wbc)
return flags;
}
-static inline struct cgroup_subsys_state *
-wbc_blkcg_css(struct writeback_control *wbc)
-{
#ifdef CONFIG_CGROUP_WRITEBACK
- if (wbc->wb)
- return wbc->wb->blkcg_css;
-#endif
- return blkcg_root_css;
-}
+#define wbc_blkcg_css(wbc) \
+ ((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css)
+#else
+#define wbc_blkcg_css(wbc) (blkcg_root_css)
+#endif /* CONFIG_CGROUP_WRITEBACK */
/*
* A wb_domain represents a domain that wb's (bdi_writeback's) belong to
@@ -393,7 +389,14 @@ void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
-void account_page_redirty(struct page *page);
+bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio);
+void folio_account_redirty(struct folio *folio);
+static inline void account_page_redirty(struct page *page)
+{
+ folio_account_redirty(page_folio(page));
+}
+bool folio_redirty_for_writepage(struct writeback_control *, struct folio *);
+bool redirty_page_for_writepage(struct writeback_control *, struct page *);
void sb_mark_inode_writeback(struct inode *inode);
void sb_clear_inode_writeback(struct inode *inode);
diff --git a/include/linux/xz.h b/include/linux/xz.h
index 9884c8440188..7285ca5d56e9 100644
--- a/include/linux/xz.h
+++ b/include/linux/xz.h
@@ -234,6 +234,112 @@ XZ_EXTERN void xz_dec_reset(struct xz_dec *s);
XZ_EXTERN void xz_dec_end(struct xz_dec *s);
/*
+ * Decompressor for MicroLZMA, an LZMA variant with a very minimal header.
+ * See xz_dec_microlzma_alloc() below for details.
+ *
+ * These functions aren't used or available in preboot code and thus aren't
+ * marked with XZ_EXTERN. This avoids warnings about static functions that
+ * are never defined.
+ */
+/**
+ * struct xz_dec_microlzma - Opaque type to hold the MicroLZMA decoder state
+ */
+struct xz_dec_microlzma;
+
+/**
+ * xz_dec_microlzma_alloc() - Allocate memory for the MicroLZMA decoder
+ * @mode XZ_SINGLE or XZ_PREALLOC
+ * @dict_size LZMA dictionary size. This must be at least 4 KiB and
+ * at most 3 GiB.
+ *
+ * In contrast to xz_dec_init(), this function only allocates the memory
+ * and remembers the dictionary size. xz_dec_microlzma_reset() must be used
+ * before calling xz_dec_microlzma_run().
+ *
+ * The amount of allocated memory is a little less than 30 KiB with XZ_SINGLE.
+ * With XZ_PREALLOC also a dictionary buffer of dict_size bytes is allocated.
+ *
+ * On success, xz_dec_microlzma_alloc() returns a pointer to
+ * struct xz_dec_microlzma. If memory allocation fails or
+ * dict_size is invalid, NULL is returned.
+ *
+ * The compressed format supported by this decoder is a raw LZMA stream
+ * whose first byte (always 0x00) has been replaced with bitwise-negation
+ * of the LZMA properties (lc/lp/pb) byte. For example, if lc/lp/pb is
+ * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00.
+ * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream
+ * marker must not be used. The unused values are reserved for future use.
+ * This MicroLZMA header format was created for use in EROFS but may be used
+ * by others too.
+ */
+extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode,
+ uint32_t dict_size);
+
+/**
+ * xz_dec_microlzma_reset() - Reset the MicroLZMA decoder state
+ * @s Decoder state allocated using xz_dec_microlzma_alloc()
+ * @comp_size Compressed size of the input stream
+ * @uncomp_size Uncompressed size of the input stream. A value smaller
+ * than the real uncompressed size of the input stream can
+ * be specified if uncomp_size_is_exact is set to false.
+ * uncomp_size can never be set to a value larger than the
+ * expected real uncompressed size because it would eventually
+ * result in XZ_DATA_ERROR.
+ * @uncomp_size_is_exact This is an int instead of bool to avoid
+ * requiring stdbool.h. This should normally be set to true.
+ * When this is set to false, error detection is weaker.
+ */
+extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s,
+ uint32_t comp_size, uint32_t uncomp_size,
+ int uncomp_size_is_exact);
+
+/**
+ * xz_dec_microlzma_run() - Run the MicroLZMA decoder
+ * @s Decoder state initialized using xz_dec_microlzma_reset()
+ * @b: Input and output buffers
+ *
+ * This works similarly to xz_dec_run() with a few important differences.
+ * Only the differences are documented here.
+ *
+ * The only possible return values are XZ_OK, XZ_STREAM_END, and
+ * XZ_DATA_ERROR. This function cannot return XZ_BUF_ERROR: if no progress
+ * is possible due to lack of input data or output space, this function will
+ * keep returning XZ_OK. Thus, the calling code must be written so that it
+ * will eventually provide input and output space matching (or exceeding)
+ * comp_size and uncomp_size arguments given to xz_dec_microlzma_reset().
+ * If the caller cannot do this (for example, if the input file is truncated
+ * or otherwise corrupt), the caller must detect this error by itself to
+ * avoid an infinite loop.
+ *
+ * If the compressed data seems to be corrupt, XZ_DATA_ERROR is returned.
+ * This can happen also when incorrect dictionary, uncompressed, or
+ * compressed sizes have been specified.
+ *
+ * With XZ_PREALLOC only: As an extra feature, b->out may be NULL to skip over
+ * uncompressed data. This way the caller doesn't need to provide a temporary
+ * output buffer for the bytes that will be ignored.
+ *
+ * With XZ_SINGLE only: In contrast to xz_dec_run(), the return value XZ_OK
+ * is also possible and thus XZ_SINGLE is actually a limited multi-call mode.
+ * After XZ_OK the bytes decoded so far may be read from the output buffer.
+ * It is possible to continue decoding but the variables b->out and b->out_pos
+ * MUST NOT be changed by the caller. Increasing the value of b->out_size is
+ * allowed to make more output space available; one doesn't need to provide
+ * space for the whole uncompressed data on the first call. The input buffer
+ * may be changed normally like with XZ_PREALLOC. This way input data can be
+ * provided from non-contiguous memory.
+ */
+extern enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s,
+ struct xz_buf *b);
+
+/**
+ * xz_dec_microlzma_end() - Free the memory allocated for the decoder state
+ * @s: Decoder state allocated using xz_dec_microlzma_alloc().
+ * If s is NULL, this function does nothing.
+ */
+extern void xz_dec_microlzma_end(struct xz_dec_microlzma *s);
+
+/*
* Standalone build (userspace build or in-kernel build for boot time use)
* needs a CRC32 implementation. For normal in-kernel use, kernel's own
* CRC32 module is used instead, and users of this module don't need to
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 62dd8422e0dc..27336fc70467 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5376,7 +5376,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy)
* netdev and may otherwise be used by driver read-only, will be update
* by cfg80211 on change_interface
* @mgmt_registrations: list of registrations for management frames
- * @mgmt_registrations_lock: lock for the list
* @mgmt_registrations_need_update: mgmt registrations were updated,
* need to propagate the update to the driver
* @mtx: mutex used to lock data in this struct, may be used by drivers
@@ -5423,7 +5422,6 @@ struct wireless_dev {
u32 identifier;
struct list_head mgmt_registrations;
- spinlock_t mgmt_registrations_lock;
u8 mgmt_registrations_need_update:1;
struct mutex mtx;
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 6026bbefbffd..3214848402ec 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -69,6 +69,10 @@ struct mptcp_out_options {
struct {
u64 sndr_key;
u64 rcvr_key;
+ u64 data_seq;
+ u32 subflow_seq;
+ u16 data_len;
+ __sum16 csum;
};
struct {
struct mptcp_addr_info addr;
diff --git a/include/net/sock.h b/include/net/sock.h
index ea6fbc88c8f9..463f390d90b3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1208,7 +1208,7 @@ struct proto {
#endif
bool (*stream_memory_free)(const struct sock *sk, int wake);
- bool (*stream_memory_read)(const struct sock *sk);
+ bool (*sock_is_readable)(struct sock *sk);
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
void (*leave_memory_pressure)(struct sock *sk);
@@ -2820,4 +2820,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs);
int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
+static inline bool sk_is_readable(struct sock *sk)
+{
+ if (sk->sk_prot->sock_is_readable)
+ return sk->sk_prot->sock_is_readable(sk);
+ return false;
+}
#endif /* _SOCK_H */
diff --git a/include/net/tls.h b/include/net/tls.h
index be4b3e1cac46..1fffb206f09f 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -358,6 +358,7 @@ int tls_sk_query(struct sock *sk, int optname, char __user *optval,
int __user *optlen);
int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
+void tls_err_abort(struct sock *sk, int err);
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
@@ -375,7 +376,7 @@ void tls_sw_release_resources_rx(struct sock *sk);
void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
-bool tls_sw_stream_read(const struct sock *sk);
+bool tls_sw_sock_is_readable(struct sock *sk);
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
@@ -466,12 +467,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
#endif
}
-static inline void tls_err_abort(struct sock *sk, int err)
-{
- sk->sk_err = err;
- sk_error_report(sk);
-}
-
static inline bool tls_bigint_increment(unsigned char *seq, int len)
{
int i;
@@ -512,7 +507,7 @@ static inline void tls_advance_record_sn(struct sock *sk,
struct cipher_context *ctx)
{
if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size))
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (prot->version != TLS_1_3_VERSION &&
prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
diff --git a/include/net/udp.h b/include/net/udp.h
index 360df454356c..909ecf447e0f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -494,8 +494,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
* CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
* packets in udp_gro_complete_segment. As does UDP GSO, verified by
* udp_send_skb. But when those packets are looped in dev_loopback_xmit
- * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
- * specific case, where PARTIAL is both correct and required.
+ * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
+ * Reset in this specific case, where PARTIAL is both correct and
+ * required.
*/
if (skb->pkt_type == PACKET_LOOPBACK)
skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index eaf04c9a1dfc..31078063afac 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -396,4 +396,7 @@ static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd)
extern void scsi_build_sense(struct scsi_cmnd *scmd, int desc,
u8 key, u8 asc, u8 ascq);
+struct request *scsi_alloc_request(struct request_queue *q,
+ unsigned int op, blk_mq_req_flags_t flags);
+
#endif /* _SCSI_SCSI_CMND_H */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index b97e142a7ca9..430b73bd02ac 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -5,7 +5,7 @@
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
#include <scsi/scsi.h>
#include <linux/atomic.h>
#include <linux/sbitmap.h>
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index cc5ab96a7471..a95daa4d4caa 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -114,7 +114,7 @@ TRACE_EVENT(block_rq_requeue,
*/
TRACE_EVENT(block_rq_complete,
- TP_PROTO(struct request *rq, int error, unsigned int nr_bytes),
+ TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
TP_ARGS(rq, error, nr_bytes),
@@ -122,7 +122,7 @@ TRACE_EVENT(block_rq_complete,
__field( dev_t, dev )
__field( sector_t, sector )
__field( unsigned int, nr_sector )
- __field( int, error )
+ __field( int , error )
__array( char, rwbs, RWBS_LEN )
__dynamic_array( char, cmd, 1 )
),
@@ -131,7 +131,7 @@ TRACE_EVENT(block_rq_complete,
__entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
__entry->sector = blk_rq_pos(rq);
__entry->nr_sector = nr_bytes >> 9;
- __entry->error = error;
+ __entry->error = blk_status_to_errno(error);
blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
__get_str(cmd)[0] = '\0';
diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h
index db4f2cec8360..16ae7b666810 100644
--- a/include/trace/events/erofs.h
+++ b/include/trace/events/erofs.h
@@ -24,7 +24,7 @@ struct erofs_map_blocks;
#define show_mflags(flags) __print_flags(flags, "", \
{ EROFS_MAP_MAPPED, "M" }, \
{ EROFS_MAP_META, "I" }, \
- { EROFS_MAP_ZIPPED, "Z" })
+ { EROFS_MAP_ENCODED, "E" })
TRACE_EVENT(erofs_lookup,
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 0dd30de00e5b..7346f0164cf4 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -6,6 +6,7 @@
#define _TRACE_IO_URING_H
#include <linux/tracepoint.h>
+#include <uapi/linux/io_uring.h>
struct io_wq_work;
@@ -497,6 +498,66 @@ TRACE_EVENT(io_uring_task_run,
(unsigned long long) __entry->user_data)
);
+/*
+ * io_uring_req_failed - called when an sqe is errored dring submission
+ *
+ * @sqe: pointer to the io_uring_sqe that failed
+ * @error: error it failed with
+ *
+ * Allows easier diagnosing of malformed requests in production systems.
+ */
+TRACE_EVENT(io_uring_req_failed,
+
+ TP_PROTO(const struct io_uring_sqe *sqe, int error),
+
+ TP_ARGS(sqe, error),
+
+ TP_STRUCT__entry (
+ __field( u8, opcode )
+ __field( u8, flags )
+ __field( u8, ioprio )
+ __field( u64, off )
+ __field( u64, addr )
+ __field( u32, len )
+ __field( u32, op_flags )
+ __field( u64, user_data )
+ __field( u16, buf_index )
+ __field( u16, personality )
+ __field( u32, file_index )
+ __field( u64, pad1 )
+ __field( u64, pad2 )
+ __field( int, error )
+ ),
+
+ TP_fast_assign(
+ __entry->opcode = sqe->opcode;
+ __entry->flags = sqe->flags;
+ __entry->ioprio = sqe->ioprio;
+ __entry->off = sqe->off;
+ __entry->addr = sqe->addr;
+ __entry->len = sqe->len;
+ __entry->op_flags = sqe->rw_flags;
+ __entry->user_data = sqe->user_data;
+ __entry->buf_index = sqe->buf_index;
+ __entry->personality = sqe->personality;
+ __entry->file_index = sqe->file_index;
+ __entry->pad1 = sqe->__pad2[0];
+ __entry->pad2 = sqe->__pad2[1];
+ __entry->error = error;
+ ),
+
+ TP_printk("op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, "
+ "len=%u, rw_flags=0x%x, user_data=0x%llx, buf_index=%d, "
+ "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d",
+ __entry->opcode, __entry->flags, __entry->ioprio,
+ (unsigned long long)__entry->off,
+ (unsigned long long) __entry->addr, __entry->len,
+ __entry->op_flags, (unsigned long long) __entry->user_data,
+ __entry->buf_index, __entry->personality, __entry->file_index,
+ (unsigned long long) __entry->pad1,
+ (unsigned long long) __entry->pad2, __entry->error)
+);
+
#endif /* _TRACE_IO_URING_H */
/* This part must be outside protection */
diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 1d28431e85bd..171524d3526d 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -16,38 +16,38 @@
#define PAGEMAP_MAPPEDDISK 0x0020u
#define PAGEMAP_BUFFERS 0x0040u
-#define trace_pagemap_flags(page) ( \
- (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \
- (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \
- (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \
- (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \
- (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \
- (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \
+#define trace_pagemap_flags(folio) ( \
+ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \
+ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \
+ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \
+ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \
+ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \
+ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \
)
TRACE_EVENT(mm_lru_insertion,
- TP_PROTO(struct page *page),
+ TP_PROTO(struct folio *folio),
- TP_ARGS(page),
+ TP_ARGS(folio),
TP_STRUCT__entry(
- __field(struct page *, page )
+ __field(struct folio *, folio )
__field(unsigned long, pfn )
__field(enum lru_list, lru )
__field(unsigned long, flags )
),
TP_fast_assign(
- __entry->page = page;
- __entry->pfn = page_to_pfn(page);
- __entry->lru = page_lru(page);
- __entry->flags = trace_pagemap_flags(page);
+ __entry->folio = folio;
+ __entry->pfn = folio_pfn(folio);
+ __entry->lru = folio_lru_list(folio);
+ __entry->flags = trace_pagemap_flags(folio);
),
/* Flag format is based on page-types.c formatting for pagemap */
- TP_printk("page=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s",
- __entry->page,
+ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s",
+ __entry->folio,
__entry->pfn,
__entry->lru,
__entry->flags & PAGEMAP_MAPPED ? "M" : " ",
@@ -60,23 +60,21 @@ TRACE_EVENT(mm_lru_insertion,
TRACE_EVENT(mm_lru_activate,
- TP_PROTO(struct page *page),
+ TP_PROTO(struct folio *folio),
- TP_ARGS(page),
+ TP_ARGS(folio),
TP_STRUCT__entry(
- __field(struct page *, page )
+ __field(struct folio *, folio )
__field(unsigned long, pfn )
),
TP_fast_assign(
- __entry->page = page;
- __entry->pfn = page_to_pfn(page);
+ __entry->folio = folio;
+ __entry->pfn = folio_pfn(folio);
),
- /* Flag format is based on page-types.c formatting for pagemap */
- TP_printk("page=%p pfn=0x%lx", __entry->page, __entry->pfn)
-
+ TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn)
);
#endif /* _TRACE_PAGEMAP_H */
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 840d1ba84cf5..7dccb66474f7 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -52,11 +52,11 @@ WB_WORK_REASON
struct wb_writeback_work;
-DECLARE_EVENT_CLASS(writeback_page_template,
+DECLARE_EVENT_CLASS(writeback_folio_template,
- TP_PROTO(struct page *page, struct address_space *mapping),
+ TP_PROTO(struct folio *folio, struct address_space *mapping),
- TP_ARGS(page, mapping),
+ TP_ARGS(folio, mapping),
TP_STRUCT__entry (
__array(char, name, 32)
@@ -69,7 +69,7 @@ DECLARE_EVENT_CLASS(writeback_page_template,
bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
NULL), 32);
__entry->ino = mapping ? mapping->host->i_ino : 0;
- __entry->index = page->index;
+ __entry->index = folio->index;
),
TP_printk("bdi %s: ino=%lu index=%lu",
@@ -79,18 +79,18 @@ DECLARE_EVENT_CLASS(writeback_page_template,
)
);
-DEFINE_EVENT(writeback_page_template, writeback_dirty_page,
+DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio,
- TP_PROTO(struct page *page, struct address_space *mapping),
+ TP_PROTO(struct folio *folio, struct address_space *mapping),
- TP_ARGS(page, mapping)
+ TP_ARGS(folio, mapping)
);
-DEFINE_EVENT(writeback_page_template, wait_on_page_writeback,
+DEFINE_EVENT(writeback_folio_template, folio_wait_writeback,
- TP_PROTO(struct page *page, struct address_space *mapping),
+ TP_PROTO(struct folio *folio, struct address_space *mapping),
- TP_ARGS(page, mapping)
+ TP_ARGS(folio, mapping)
);
DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
@@ -236,9 +236,9 @@ TRACE_EVENT(inode_switch_wbs,
TRACE_EVENT(track_foreign_dirty,
- TP_PROTO(struct page *page, struct bdi_writeback *wb),
+ TP_PROTO(struct folio *folio, struct bdi_writeback *wb),
- TP_ARGS(page, wb),
+ TP_ARGS(folio, wb),
TP_STRUCT__entry(
__array(char, name, 32)
@@ -250,7 +250,7 @@ TRACE_EVENT(track_foreign_dirty,
),
TP_fast_assign(
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio_mapping(folio);
struct inode *inode = mapping ? mapping->host : NULL;
strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
@@ -258,7 +258,7 @@ TRACE_EVENT(track_foreign_dirty,
__entry->ino = inode ? inode->i_ino : 0;
__entry->memcg_id = wb->memcg_css->id;
__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup);
+ __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup);
),
TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu",
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 9dc0bf0c5a6e..ecd0f5bdfc1d 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -181,6 +181,10 @@ struct f_owner_ex {
blocking */
#define LOCK_UN 8 /* remove lock */
+/*
+ * LOCK_MAND support has been removed from the kernel. We leave the symbols
+ * here to not break legacy builds, but these should not be used in new code.
+ */
#define LOCK_MAND 32 /* This is a mandatory flock ... */
#define LOCK_READ 64 /* which allows concurrent read operations */
#define LOCK_WRITE 128 /* which allows concurrent write operations */
diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h
index 6c34f6e2f1f7..804ff8d98f71 100644
--- a/include/uapi/linux/cdrom.h
+++ b/include/uapi/linux/cdrom.h
@@ -147,6 +147,8 @@
#define CDROM_NEXT_WRITABLE 0x5394 /* get next writable block */
#define CDROM_LAST_WRITTEN 0x5395 /* get last block written on disc */
+#define CDROM_TIMED_MEDIA_CHANGE 0x5396 /* get the timestamp of the last media change */
+
/*******************************************************
* CDROM IOCTL structures
*******************************************************/
@@ -295,6 +297,23 @@ struct cdrom_generic_command
};
};
+/* This struct is used by CDROM_TIMED_MEDIA_CHANGE */
+struct cdrom_timed_media_change_info {
+ __s64 last_media_change; /* Timestamp of the last detected media
+ * change in ms. May be set by caller,
+ * updated upon successful return of
+ * ioctl.
+ */
+ __u64 media_flags; /* Flags returned by ioctl to indicate
+ * media status.
+ */
+};
+#define MEDIA_CHANGED_FLAG 0x1 /* Last detected media change was more
+ * recent than last_media_change set by
+ * caller.
+ */
+/* other bits of media_flags available for future use */
+
/*
* A CD-ROM physical sector size is 2048, 2052, 2056, 2324, 2332, 2336,
* 2340, or 2352 bytes long.
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index b270a07b285e..c45b5e9a9387 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -158,6 +158,7 @@ enum {
#define IORING_TIMEOUT_BOOTTIME (1U << 2)
#define IORING_TIMEOUT_REALTIME (1U << 3)
#define IORING_LINK_TIMEOUT_UPDATE (1U << 4)
+#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5)
#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
/*
diff --git a/init/main.c b/init/main.c
index 3c4054a95545..4162d7f3179f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -83,7 +83,6 @@
#include <linux/ptrace.h>
#include <linux/pti.h>
#include <linux/blkdev.h>
-#include <linux/elevator.h>
#include <linux/sched/clock.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
diff --git a/kernel/acct.c b/kernel/acct.c
index 23a7ab8e6cbc..3df53cf1dcd5 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -60,7 +60,6 @@
#include <linux/sched/cputime.h>
#include <asm/div64.h>
-#include <linux/blkdev.h> /* sector_div */
#include <linux/pid_namespace.h>
#include <linux/fs_pin.h>
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cebd4fb06d19..447def540544 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1072,6 +1072,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
INIT_WORK(&aux->work, prog_array_map_clear_deferred);
INIT_LIST_HEAD(&aux->poke_progs);
mutex_init(&aux->poke_mutex);
+ spin_lock_init(&aux->owner.lock);
map = array_map_alloc(attr);
if (IS_ERR(map)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6b7dfdd8066..6e3ae90ad107 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -524,6 +524,7 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
long bpf_jit_limit __read_mostly;
+long bpf_jit_limit_max __read_mostly;
static void
bpf_prog_ksym_set_addr(struct bpf_prog *prog)
@@ -817,7 +818,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void)
static int __init bpf_jit_charge_init(void)
{
/* Only used as heuristic here to derive limit. */
- bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+ bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
PAGE_SIZE), LONG_MAX);
return 0;
}
@@ -1821,20 +1823,26 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
+ bool ret;
+
if (fp->kprobe_override)
return false;
- if (!array->aux->type) {
+ spin_lock(&array->aux->owner.lock);
+
+ if (!array->aux->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
- array->aux->type = fp->type;
- array->aux->jited = fp->jited;
- return true;
+ array->aux->owner.type = fp->type;
+ array->aux->owner.jited = fp->jited;
+ ret = true;
+ } else {
+ ret = array->aux->owner.type == fp->type &&
+ array->aux->owner.jited == fp->jited;
}
-
- return array->aux->type == fp->type &&
- array->aux->jited == fp->jited;
+ spin_unlock(&array->aux->owner.lock);
+ return ret;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4e50c0bfdb7d..1cad6979a0d0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -543,8 +543,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
array = container_of(map, struct bpf_array, map);
- type = array->aux->type;
- jited = array->aux->jited;
+ spin_lock(&array->aux->owner.lock);
+ type = array->aux->owner.type;
+ jited = array->aux->owner.jited;
+ spin_unlock(&array->aux->owner.lock);
}
seq_printf(m,
@@ -1337,12 +1339,11 @@ int generic_map_update_batch(struct bpf_map *map,
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
u32 value_size, cp, max_count;
- int ufd = attr->map_fd;
+ int ufd = attr->batch.map_fd;
void *key, *value;
struct fd f;
int err = 0;
- f = fdget(ufd);
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
@@ -1367,6 +1368,7 @@ int generic_map_update_batch(struct bpf_map *map,
return -ENOMEM;
}
+ f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
@@ -1386,6 +1388,7 @@ int generic_map_update_batch(struct bpf_map *map,
kvfree(value);
kvfree(key);
+ fdput(f);
return err;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e76b55917905..de006552be8a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13319,7 +13319,7 @@ BTF_SET_START(btf_non_sleepable_error_inject)
/* Three functions below can be called from sleepable and non-sleepable context.
* Assume non-sleepable from bpf safety point of view.
*/
-BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, __filemap_add_folio)
BTF_ID(func, should_fail_alloc_page)
BTF_ID(func, should_failslab)
BTF_SET_END(btf_non_sleepable_error_inject)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 570b0c97392a..ea08f01d0111 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2187,8 +2187,10 @@ static void cgroup_kill_sb(struct super_block *sb)
* And don't kill the default root.
*/
if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
- !percpu_ref_is_dying(&root->cgrp.self.refcnt))
+ !percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+ cgroup_bpf_offline(&root->cgrp);
percpu_ref_kill(&root->cgrp.self.refcnt);
+ }
cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index af24dc3febbe..6357c3580d07 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -167,7 +167,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
addr + PAGE_SIZE);
if (new_page) {
- err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL);
+ err = mem_cgroup_charge(page_folio(new_page), vma->vm_mm,
+ GFP_KERNEL);
if (err)
return err;
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 91a43e57a32e..a53863dafb3d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -48,7 +48,6 @@
#include <linux/pipe_fs_i.h>
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
-#include <linux/blkdev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/tracehook.h>
#include <linux/fs_struct.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 38681ad44c76..67679e3933f2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -76,7 +76,6 @@
#include <linux/taskstats_kern.h>
#include <linux/random.h>
#include <linux/tty.h>
-#include <linux/blkdev.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
#include <linux/perf_event.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f21714ea3db8..59bea523c84b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -13,7 +13,7 @@
#include "sched.h"
#include <linux/nospec.h>
-
+#include <linux/blkdev.h>
#include <linux/kcov.h>
#include <linux/scs.h>
@@ -6343,7 +6343,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
* make sure to submit it to avoid deadlocks.
*/
if (blk_needs_flush_plug(tsk))
- blk_schedule_flush_plug(tsk);
+ blk_flush_plug(tsk->plug, true);
}
static void sched_update_worker(struct task_struct *tsk)
@@ -8354,7 +8354,8 @@ int io_schedule_prepare(void)
int old_iowait = current->in_iowait;
current->in_iowait = 1;
- blk_schedule_flush_plug(current);
+ if (current->plug)
+ blk_flush_plug(current->plug, true);
return old_iowait;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3d3e5793e117..66128dfc05fb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -37,7 +37,6 @@
#include <linux/binfmts.h>
#include <linux/bitops.h>
-#include <linux/blkdev.h>
#include <linux/compat.h>
#include <linux/context_tracking.h>
#include <linux/cpufreq.h>
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index fa91f398f28b..1183c88634aa 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -816,7 +816,7 @@ blk_trace_request_get_cgid(struct request *rq)
* Records an action against a request. Will log the bio offset + size.
*
**/
-static void blk_add_trace_rq(struct request *rq, int error,
+static void blk_add_trace_rq(struct request *rq, blk_status_t error,
unsigned int nr_bytes, u32 what, u64 cgid)
{
struct blk_trace *bt;
@@ -834,7 +834,8 @@ static void blk_add_trace_rq(struct request *rq, int error,
what |= BLK_TC_ACT(BLK_TC_FS);
__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
- rq->cmd_flags, what, error, 0, NULL, cgid);
+ rq->cmd_flags, what, blk_status_to_errno(error), 0,
+ NULL, cgid);
rcu_read_unlock();
}
@@ -863,7 +864,7 @@ static void blk_add_trace_rq_requeue(void *ignore, struct request *rq)
}
static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
- int error, unsigned int nr_bytes)
+ blk_status_t error, unsigned int nr_bytes)
{
blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
blk_trace_request_get_cgid(rq));
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 635fbdc9d589..feebf57c6458 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2208,7 +2208,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
}
/**
- * ftrace_update_record, set a record that now is tracing or not
+ * ftrace_update_record - set a record that now is tracing or not
* @rec: the record to update
* @enable: set to true if the record is tracing, false to force disable
*
@@ -2221,7 +2221,7 @@ int ftrace_update_record(struct dyn_ftrace *rec, bool enable)
}
/**
- * ftrace_test_record, check if the record has been enabled or not
+ * ftrace_test_record - check if the record has been enabled or not
* @rec: the record to test
* @enable: set to true to check if enabled, false if it is disabled
*
@@ -2574,7 +2574,7 @@ struct ftrace_rec_iter {
};
/**
- * ftrace_rec_iter_start, start up iterating over traced functions
+ * ftrace_rec_iter_start - start up iterating over traced functions
*
* Returns an iterator handle that is used to iterate over all
* the records that represent address locations where functions
@@ -2605,7 +2605,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void)
}
/**
- * ftrace_rec_iter_next, get the next record to process.
+ * ftrace_rec_iter_next - get the next record to process.
* @iter: The handle to the iterator.
*
* Returns the next iterator after the given iterator @iter.
@@ -2630,7 +2630,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter)
}
/**
- * ftrace_rec_iter_record, get the record at the iterator location
+ * ftrace_rec_iter_record - get the record at the iterator location
* @iter: The current iterator location
*
* Returns the record that the current @iter is at.
@@ -2733,7 +2733,7 @@ static int __ftrace_modify_code(void *data)
}
/**
- * ftrace_run_stop_machine, go back to the stop machine method
+ * ftrace_run_stop_machine - go back to the stop machine method
* @command: The command to tell ftrace what to do
*
* If an arch needs to fall back to the stop machine method, the
@@ -2745,7 +2745,7 @@ void ftrace_run_stop_machine(int command)
}
/**
- * arch_ftrace_update_code, modify the code to trace or not trace
+ * arch_ftrace_update_code - modify the code to trace or not trace
* @command: The command that needs to be done
*
* Archs can override this function if it does not need to
@@ -7525,7 +7525,9 @@ void ftrace_kill(void)
}
/**
- * Test if ftrace is dead or not.
+ * ftrace_is_dead - Test if ftrace is dead or not.
+ *
+ * Returns 1 if ftrace is "dead", zero otherwise.
*/
int ftrace_is_dead(void)
{
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index c4a15aef36af..928867f527e7 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -904,8 +904,8 @@ static int __trace_eprobe_create(int argc, const char *argv[])
if (IS_ERR(ep)) {
ret = PTR_ERR(ep);
- /* This must return -ENOMEM, else there is a bug */
- WARN_ON_ONCE(ret != -ENOMEM);
+ /* This must return -ENOMEM or missing event, else there is a bug */
+ WARN_ON_ONCE(ret != -ENOMEM && ret != -ENODEV);
ep = NULL;
goto error;
}
diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c
index a2f38e23004a..9f4262ee33a5 100644
--- a/lib/decompress_unxz.c
+++ b/lib/decompress_unxz.c
@@ -20,8 +20,8 @@
*
* The worst case for in-place decompression is that the beginning of
* the file is compressed extremely well, and the rest of the file is
- * uncompressible. Thus, we must look for worst-case expansion when the
- * compressor is encoding uncompressible data.
+ * incompressible. Thus, we must look for worst-case expansion when the
+ * compressor is encoding incompressible data.
*
* The structure of the .xz file in case of a compressed kernel is as follows.
* Sizes (as bytes) of the fields are in parenthesis.
@@ -58,7 +58,7 @@
* uncompressed size of the payload is in practice never less than the
* payload size itself. The LZMA2 format would allow uncompressed size
* to be less than the payload size, but no sane compressor creates such
- * files. LZMA2 supports storing uncompressible data in uncompressed form,
+ * files. LZMA2 supports storing incompressible data in uncompressed form,
* so there's never a need to create payloads whose uncompressed size is
* smaller than the compressed size.
*
@@ -167,8 +167,8 @@
* memeq and memzero are not used much and any remotely sane implementation
* is fast enough. memcpy/memmove speed matters in multi-call mode, but
* the kernel image is decompressed in single-call mode, in which only
- * memcpy speed can matter and only if there is a lot of uncompressible data
- * (LZMA2 stores uncompressible chunks in uncompressed form). Thus, the
+ * memmove speed can matter and only if there is a lot of incompressible data
+ * (LZMA2 stores incompressible chunks in uncompressed form). Thus, the
* functions below should just be kept small; it's probably not worth
* optimizing for speed.
*/
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index 451543937524..53e7eb1dd76c 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -217,11 +217,12 @@ static void fprop_reflect_period_percpu(struct fprop_global *p,
}
/* Event of type pl happened */
-void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
+void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl,
+ long nr)
{
fprop_reflect_period_percpu(p, pl);
- percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
- percpu_counter_add(&p->events, 1);
+ percpu_counter_add_batch(&pl->events, nr, PROP_BATCH);
+ percpu_counter_add(&p->events, nr);
}
void fprop_fraction_percpu(struct fprop_global *p,
@@ -253,20 +254,29 @@ void fprop_fraction_percpu(struct fprop_global *p,
}
/*
- * Like __fprop_inc_percpu() except that event is counted only if the given
+ * Like __fprop_add_percpu() except that event is counted only if the given
* type has fraction smaller than @max_frac/FPROP_FRAC_BASE
*/
-void __fprop_inc_percpu_max(struct fprop_global *p,
- struct fprop_local_percpu *pl, int max_frac)
+void __fprop_add_percpu_max(struct fprop_global *p,
+ struct fprop_local_percpu *pl, int max_frac, long nr)
{
if (unlikely(max_frac < FPROP_FRAC_BASE)) {
unsigned long numerator, denominator;
+ s64 tmp;
fprop_fraction_percpu(p, pl, &numerator, &denominator);
- if (numerator >
- (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
+ /* Adding 'nr' to fraction exceeds max_frac/FPROP_FRAC_BASE? */
+ tmp = (u64)denominator * max_frac -
+ ((u64)numerator << FPROP_FRAC_SHIFT);
+ if (tmp < 0) {
+ /* Maximum fraction already exceeded? */
return;
+ } else if (tmp < nr * (FPROP_FRAC_BASE - max_frac)) {
+ /* Add just enough for the fraction to saturate */
+ nr = div_u64(tmp + FPROP_FRAC_BASE - max_frac - 1,
+ FPROP_FRAC_BASE - max_frac);
+ }
}
- __fprop_inc_percpu(p, pl);
+ __fprop_add_percpu(p, pl, nr);
}
diff --git a/lib/random32.c b/lib/random32.c
index 4d0e05e471d7..a57a0e18819d 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -39,6 +39,7 @@
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/bitops.h>
+#include <linux/slab.h>
#include <asm/unaligned.h>
#include <trace/events/random.h>
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index b25db9be938a..2709ab825499 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -489,6 +489,57 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq)
}
EXPORT_SYMBOL_GPL(__sbitmap_queue_get);
+unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
+ unsigned int *offset)
+{
+ struct sbitmap *sb = &sbq->sb;
+ unsigned int hint, depth;
+ unsigned long index, nr;
+ int i;
+
+ if (unlikely(sb->round_robin))
+ return 0;
+
+ depth = READ_ONCE(sb->depth);
+ hint = update_alloc_hint_before_get(sb, depth);
+
+ index = SB_NR_TO_INDEX(sb, hint);
+
+ for (i = 0; i < sb->map_nr; i++) {
+ struct sbitmap_word *map = &sb->map[index];
+ unsigned long get_mask;
+
+ sbitmap_deferred_clear(map);
+ if (map->word == (1UL << (map->depth - 1)) - 1)
+ continue;
+
+ nr = find_first_zero_bit(&map->word, map->depth);
+ if (nr + nr_tags <= map->depth) {
+ atomic_long_t *ptr = (atomic_long_t *) &map->word;
+ int map_tags = min_t(int, nr_tags, map->depth);
+ unsigned long val, ret;
+
+ get_mask = ((1UL << map_tags) - 1) << nr;
+ do {
+ val = READ_ONCE(map->word);
+ ret = atomic_long_cmpxchg(ptr, val, get_mask | val);
+ } while (ret != val);
+ get_mask = (get_mask & ~ret) >> nr;
+ if (get_mask) {
+ *offset = nr + (index << sb->shift);
+ update_alloc_hint_after_get(sb, depth, hint,
+ *offset + map_tags - 1);
+ return get_mask;
+ }
+ }
+ /* Jump to next index. */
+ if (++index >= sb->map_nr)
+ index = 0;
+ }
+
+ return 0;
+}
+
int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
unsigned int shallow_depth)
{
@@ -577,6 +628,46 @@ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq)
}
EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
+static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag)
+{
+ if (likely(!sb->round_robin && tag < sb->depth))
+ data_race(*per_cpu_ptr(sb->alloc_hint, cpu) = tag);
+}
+
+void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
+ int *tags, int nr_tags)
+{
+ struct sbitmap *sb = &sbq->sb;
+ unsigned long *addr = NULL;
+ unsigned long mask = 0;
+ int i;
+
+ smp_mb__before_atomic();
+ for (i = 0; i < nr_tags; i++) {
+ const int tag = tags[i] - offset;
+ unsigned long *this_addr;
+
+ /* since we're clearing a batch, skip the deferred map */
+ this_addr = &sb->map[SB_NR_TO_INDEX(sb, tag)].word;
+ if (!addr) {
+ addr = this_addr;
+ } else if (addr != this_addr) {
+ atomic_long_andnot(mask, (atomic_long_t *) addr);
+ mask = 0;
+ addr = this_addr;
+ }
+ mask |= (1UL << SB_NR_TO_BIT(sb, tag));
+ }
+
+ if (mask)
+ atomic_long_andnot(mask, (atomic_long_t *) addr);
+
+ smp_mb__after_atomic();
+ sbitmap_queue_wake_up(sbq);
+ sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(),
+ tags[nr_tags - 1] - offset);
+}
+
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
unsigned int cpu)
{
@@ -601,9 +692,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
*/
smp_mb__after_atomic();
sbitmap_queue_wake_up(sbq);
-
- if (likely(!sbq->sb.round_robin && nr < sbq->sb.depth))
- *per_cpu_ptr(sbq->sb.alloc_hint, cpu) = nr;
+ sbitmap_update_cpu_hint(&sbq->sb, cpu, nr);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_clear);
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 5cb50245a878..adce22ac18d6 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -39,6 +39,19 @@ config XZ_DEC_SPARC
default y
select XZ_DEC_BCJ
+config XZ_DEC_MICROLZMA
+ bool "MicroLZMA decoder"
+ default n
+ help
+ MicroLZMA is a header format variant where the first byte
+ of a raw LZMA stream (without the end of stream marker) has
+ been replaced with a bitwise-negation of the lc/lp/pb
+ properties byte. MicroLZMA was created to be used in EROFS
+ but can be used by other things too where wasting minimal
+ amount of space for headers is important.
+
+ Unless you know that you need this, say N.
+
endif
config XZ_DEC_BCJ
diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c
index 7a6781e3f47b..27ce34520e78 100644
--- a/lib/xz/xz_dec_lzma2.c
+++ b/lib/xz/xz_dec_lzma2.c
@@ -248,6 +248,10 @@ struct lzma2_dec {
* before the first LZMA chunk.
*/
bool need_props;
+
+#ifdef XZ_DEC_MICROLZMA
+ bool pedantic_microlzma;
+#endif
};
struct xz_dec_lzma2 {
@@ -387,7 +391,14 @@ static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
*left -= copy_size;
- memcpy(dict->buf + dict->pos, b->in + b->in_pos, copy_size);
+ /*
+ * If doing in-place decompression in single-call mode and the
+ * uncompressed size of the file is larger than the caller
+ * thought (i.e. it is invalid input!), the buffers below may
+ * overlap and cause undefined behavior with memcpy().
+ * With valid inputs memcpy() would be fine here.
+ */
+ memmove(dict->buf + dict->pos, b->in + b->in_pos, copy_size);
dict->pos += copy_size;
if (dict->full < dict->pos)
@@ -397,7 +408,11 @@ static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
if (dict->pos == dict->end)
dict->pos = 0;
- memcpy(b->out + b->out_pos, b->in + b->in_pos,
+ /*
+ * Like above but for multi-call mode: use memmove()
+ * to avoid undefined behavior with invalid input.
+ */
+ memmove(b->out + b->out_pos, b->in + b->in_pos,
copy_size);
}
@@ -408,6 +423,12 @@ static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
}
}
+#ifdef XZ_DEC_MICROLZMA
+# define DICT_FLUSH_SUPPORTS_SKIPPING true
+#else
+# define DICT_FLUSH_SUPPORTS_SKIPPING false
+#endif
+
/*
* Flush pending data from dictionary to b->out. It is assumed that there is
* enough space in b->out. This is guaranteed because caller uses dict_limit()
@@ -421,8 +442,19 @@ static uint32_t dict_flush(struct dictionary *dict, struct xz_buf *b)
if (dict->pos == dict->end)
dict->pos = 0;
- memcpy(b->out + b->out_pos, dict->buf + dict->start,
- copy_size);
+ /*
+ * These buffers cannot overlap even if doing in-place
+ * decompression because in multi-call mode dict->buf
+ * has been allocated by us in this file; it's not
+ * provided by the caller like in single-call mode.
+ *
+ * With MicroLZMA, b->out can be NULL to skip bytes that
+ * the caller doesn't need. This cannot be done with XZ
+ * because it would break BCJ filters.
+ */
+ if (!DICT_FLUSH_SUPPORTS_SKIPPING || b->out != NULL)
+ memcpy(b->out + b->out_pos, dict->buf + dict->start,
+ copy_size);
}
dict->start = dict->pos;
@@ -488,7 +520,7 @@ static __always_inline void rc_normalize(struct rc_dec *rc)
* functions so that the compiler is supposed to be able to more easily avoid
* an extra branch. In this particular version of the LZMA decoder, this
* doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3
- * on x86). Using a non-splitted version results in nicer looking code too.
+ * on x86). Using a non-split version results in nicer looking code too.
*
* NOTE: This must return an int. Do not make it return a bool or the speed
* of the code generated by GCC 3.x decreases 10-15 %. (GCC 4.3 doesn't care,
@@ -774,6 +806,7 @@ static void lzma_reset(struct xz_dec_lzma2 *s)
s->lzma.rep1 = 0;
s->lzma.rep2 = 0;
s->lzma.rep3 = 0;
+ s->lzma.len = 0;
/*
* All probabilities are initialized to the same value. This hack
@@ -1157,8 +1190,6 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props)
}
}
- s->lzma.len = 0;
-
s->lzma2.sequence = SEQ_CONTROL;
s->lzma2.need_dict_reset = true;
@@ -1174,3 +1205,140 @@ XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s)
kfree(s);
}
+
+#ifdef XZ_DEC_MICROLZMA
+/* This is a wrapper struct to have a nice struct name in the public API. */
+struct xz_dec_microlzma {
+ struct xz_dec_lzma2 s;
+};
+
+enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s_ptr,
+ struct xz_buf *b)
+{
+ struct xz_dec_lzma2 *s = &s_ptr->s;
+
+ /*
+ * sequence is SEQ_PROPERTIES before the first input byte,
+ * SEQ_LZMA_PREPARE until a total of five bytes have been read,
+ * and SEQ_LZMA_RUN for the rest of the input stream.
+ */
+ if (s->lzma2.sequence != SEQ_LZMA_RUN) {
+ if (s->lzma2.sequence == SEQ_PROPERTIES) {
+ /* One byte is needed for the props. */
+ if (b->in_pos >= b->in_size)
+ return XZ_OK;
+
+ /*
+ * Don't increment b->in_pos here. The same byte is
+ * also passed to rc_read_init() which will ignore it.
+ */
+ if (!lzma_props(s, ~b->in[b->in_pos]))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.sequence = SEQ_LZMA_PREPARE;
+ }
+
+ /*
+ * xz_dec_microlzma_reset() doesn't validate the compressed
+ * size so we do it here. We have to limit the maximum size
+ * to avoid integer overflows in lzma2_lzma(). 3 GiB is a nice
+ * round number and much more than users of this code should
+ * ever need.
+ */
+ if (s->lzma2.compressed < RC_INIT_BYTES
+ || s->lzma2.compressed > (3U << 30))
+ return XZ_DATA_ERROR;
+
+ if (!rc_read_init(&s->rc, b))
+ return XZ_OK;
+
+ s->lzma2.compressed -= RC_INIT_BYTES;
+ s->lzma2.sequence = SEQ_LZMA_RUN;
+
+ dict_reset(&s->dict, b);
+ }
+
+ /* This is to allow increasing b->out_size between calls. */
+ if (DEC_IS_SINGLE(s->dict.mode))
+ s->dict.end = b->out_size - b->out_pos;
+
+ while (true) {
+ dict_limit(&s->dict, min_t(size_t, b->out_size - b->out_pos,
+ s->lzma2.uncompressed));
+
+ if (!lzma2_lzma(s, b))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.uncompressed -= dict_flush(&s->dict, b);
+
+ if (s->lzma2.uncompressed == 0) {
+ if (s->lzma2.pedantic_microlzma) {
+ if (s->lzma2.compressed > 0 || s->lzma.len > 0
+ || !rc_is_finished(&s->rc))
+ return XZ_DATA_ERROR;
+ }
+
+ return XZ_STREAM_END;
+ }
+
+ if (b->out_pos == b->out_size)
+ return XZ_OK;
+
+ if (b->in_pos == b->in_size
+ && s->temp.size < s->lzma2.compressed)
+ return XZ_OK;
+ }
+}
+
+struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode,
+ uint32_t dict_size)
+{
+ struct xz_dec_microlzma *s;
+
+ /* Restrict dict_size to the same range as in the LZMA2 code. */
+ if (dict_size < 4096 || dict_size > (3U << 30))
+ return NULL;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s == NULL)
+ return NULL;
+
+ s->s.dict.mode = mode;
+ s->s.dict.size = dict_size;
+
+ if (DEC_IS_MULTI(mode)) {
+ s->s.dict.end = dict_size;
+
+ s->s.dict.buf = vmalloc(dict_size);
+ if (s->s.dict.buf == NULL) {
+ kfree(s);
+ return NULL;
+ }
+ }
+
+ return s;
+}
+
+void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, uint32_t comp_size,
+ uint32_t uncomp_size, int uncomp_size_is_exact)
+{
+ /*
+ * comp_size is validated in xz_dec_microlzma_run().
+ * uncomp_size can safely be anything.
+ */
+ s->s.lzma2.compressed = comp_size;
+ s->s.lzma2.uncompressed = uncomp_size;
+ s->s.lzma2.pedantic_microlzma = uncomp_size_is_exact;
+
+ s->s.lzma2.sequence = SEQ_PROPERTIES;
+ s->s.temp.size = 0;
+}
+
+void xz_dec_microlzma_end(struct xz_dec_microlzma *s)
+{
+ if (DEC_IS_MULTI(s->s.dict.mode))
+ vfree(s->s.dict.buf);
+
+ kfree(s);
+}
+#endif
diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c
index fea86deaaa01..683570b93a8c 100644
--- a/lib/xz/xz_dec_stream.c
+++ b/lib/xz/xz_dec_stream.c
@@ -402,12 +402,12 @@ static enum xz_ret dec_stream_header(struct xz_dec *s)
* we will accept other check types too, but then the check won't
* be verified and a warning (XZ_UNSUPPORTED_CHECK) will be given.
*/
+ if (s->temp.buf[HEADER_MAGIC_SIZE + 1] > XZ_CHECK_MAX)
+ return XZ_OPTIONS_ERROR;
+
s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1];
#ifdef XZ_DEC_ANY_CHECK
- if (s->check_type > XZ_CHECK_MAX)
- return XZ_OPTIONS_ERROR;
-
if (s->check_type > XZ_CHECK_CRC32)
return XZ_UNSUPPORTED_CHECK;
#else
diff --git a/lib/xz/xz_dec_syms.c b/lib/xz/xz_dec_syms.c
index 32eb3c03aede..61098c67a413 100644
--- a/lib/xz/xz_dec_syms.c
+++ b/lib/xz/xz_dec_syms.c
@@ -15,8 +15,15 @@ EXPORT_SYMBOL(xz_dec_reset);
EXPORT_SYMBOL(xz_dec_run);
EXPORT_SYMBOL(xz_dec_end);
+#ifdef CONFIG_XZ_DEC_MICROLZMA
+EXPORT_SYMBOL(xz_dec_microlzma_alloc);
+EXPORT_SYMBOL(xz_dec_microlzma_reset);
+EXPORT_SYMBOL(xz_dec_microlzma_run);
+EXPORT_SYMBOL(xz_dec_microlzma_end);
+#endif
+
MODULE_DESCRIPTION("XZ decompressor");
-MODULE_VERSION("1.0");
+MODULE_VERSION("1.1");
MODULE_AUTHOR("Lasse Collin <lasse.collin@tukaani.org> and Igor Pavlov");
/*
diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h
index 09360ebb510e..bf1e94ec7873 100644
--- a/lib/xz/xz_private.h
+++ b/lib/xz/xz_private.h
@@ -37,6 +37,9 @@
# ifdef CONFIG_XZ_DEC_SPARC
# define XZ_DEC_SPARC
# endif
+# ifdef CONFIG_XZ_DEC_MICROLZMA
+# define XZ_DEC_MICROLZMA
+# endif
# define memeq(a, b, size) (memcmp(a, b, size) == 0)
# define memzero(buf, size) memset(buf, 0, size)
# endif
diff --git a/mm/Makefile b/mm/Makefile
index fc60a40ce954..d6c0042e3aa0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -46,7 +46,7 @@ mmu-$(CONFIG_MMU) += process_vm_access.o
endif
obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
- maccess.o page-writeback.o \
+ maccess.o page-writeback.o folio-compat.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o percpu.o slab_common.o \
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 4a9d4e27d0d9..c878d995af06 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -2,8 +2,9 @@
#include <linux/wait.h>
#include <linux/rbtree.h>
-#include <linux/backing-dev.h>
#include <linux/kthread.h>
+#include <linux/backing-dev.h>
+#include <linux/blk-cgroup.h>
#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
@@ -977,6 +978,22 @@ void bdi_put(struct backing_dev_info *bdi)
}
EXPORT_SYMBOL(bdi_put);
+struct backing_dev_info *inode_to_bdi(struct inode *inode)
+{
+ struct super_block *sb;
+
+ if (!inode)
+ return &noop_backing_dev_info;
+
+ sb = inode->i_sb;
+#ifdef CONFIG_BLOCK
+ if (sb_is_blkdev_sb(sb))
+ return I_BDEV(inode)->bd_disk->bdi;
+#endif
+ return sb->s_bdi;
+}
+EXPORT_SYMBOL(inode_to_bdi);
+
const char *bdi_dev_name(struct backing_dev_info *bdi)
{
if (!bdi || !bdi->dev)
diff --git a/mm/compaction.c b/mm/compaction.c
index bfc93da1c2c7..fbc60f964c38 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1022,7 +1022,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
if (!TestClearPageLRU(page))
goto isolate_fail_put;
- lruvec = mem_cgroup_page_lruvec(page);
+ lruvec = folio_lruvec(page_folio(page));
/* If we already hold the lock, we can skip some rechecking */
if (lruvec != locked) {
@@ -1032,7 +1032,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
locked = lruvec;
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, page_folio(page));
/* Try get exclusive access under lock */
if (!skip_updated) {
diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h
index c938a9c34e6c..7008c3735e99 100644
--- a/mm/damon/core-test.h
+++ b/mm/damon/core-test.h
@@ -219,14 +219,14 @@ static void damon_test_split_regions_of(struct kunit *test)
r = damon_new_region(0, 22);
damon_add_region(r, t);
damon_split_regions_of(c, t, 2);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 2u);
+ KUNIT_EXPECT_LE(test, damon_nr_regions(t), 2u);
damon_free_target(t);
t = damon_new_target(42);
r = damon_new_region(0, 220);
damon_add_region(r, t);
damon_split_regions_of(c, t, 4);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 4u);
+ KUNIT_EXPECT_LE(test, damon_nr_regions(t), 4u);
damon_free_target(t);
damon_destroy_ctx(c);
}
diff --git a/mm/filemap.c b/mm/filemap.c
index dae481293b5d..5e206a429b57 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -30,7 +30,6 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/cpuset.h>
#include <linux/hugetlb.h>
@@ -835,6 +834,8 @@ EXPORT_SYMBOL(file_write_and_wait_range);
*/
void replace_page_cache_page(struct page *old, struct page *new)
{
+ struct folio *fold = page_folio(old);
+ struct folio *fnew = page_folio(new);
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *) = mapping->a_ops->freepage;
pgoff_t offset = old->index;
@@ -848,7 +849,7 @@ void replace_page_cache_page(struct page *old, struct page *new)
new->mapping = mapping;
new->index = offset;
- mem_cgroup_migrate(old, new);
+ mem_cgroup_migrate(fold, fnew);
xas_lock_irq(&xas);
xas_store(&xas, new);
@@ -870,26 +871,25 @@ void replace_page_cache_page(struct page *old, struct page *new)
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
-noinline int __add_to_page_cache_locked(struct page *page,
- struct address_space *mapping,
- pgoff_t offset, gfp_t gfp,
- void **shadowp)
+noinline int __filemap_add_folio(struct address_space *mapping,
+ struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp)
{
- XA_STATE(xas, &mapping->i_pages, offset);
- int huge = PageHuge(page);
+ XA_STATE(xas, &mapping->i_pages, index);
+ int huge = folio_test_hugetlb(folio);
int error;
bool charged = false;
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(PageSwapBacked(page), page);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
mapping_set_update(&xas, mapping);
- get_page(page);
- page->mapping = mapping;
- page->index = offset;
+ folio_get(folio);
+ folio->mapping = mapping;
+ folio->index = index;
if (!huge) {
- error = mem_cgroup_charge(page, NULL, gfp);
+ error = mem_cgroup_charge(folio, NULL, gfp);
+ VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
if (error)
goto error;
charged = true;
@@ -901,7 +901,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
unsigned int order = xa_get_order(xas.xa, xas.xa_index);
void *entry, *old = NULL;
- if (order > thp_order(page))
+ if (order > folio_order(folio))
xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
order, gfp);
xas_lock_irq(&xas);
@@ -918,13 +918,13 @@ noinline int __add_to_page_cache_locked(struct page *page,
*shadowp = old;
/* entry may have been split before we acquired lock */
order = xa_get_order(xas.xa, xas.xa_index);
- if (order > thp_order(page)) {
+ if (order > folio_order(folio)) {
xas_split(&xas, old, order);
xas_reset(&xas);
}
}
- xas_store(&xas, page);
+ xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
@@ -932,7 +932,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
/* hugetlb pages do not participate in page cache accounting */
if (!huge)
- __inc_lruvec_page_state(page, NR_FILE_PAGES);
+ __lruvec_stat_add_folio(folio, NR_FILE_PAGES);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
@@ -940,19 +940,19 @@ unlock:
if (xas_error(&xas)) {
error = xas_error(&xas);
if (charged)
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(folio);
goto error;
}
- trace_mm_filemap_add_to_page_cache(page);
+ trace_mm_filemap_add_to_page_cache(&folio->page);
return 0;
error:
- page->mapping = NULL;
+ folio->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
- put_page(page);
+ folio_put(folio);
return error;
}
-ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
+ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
/**
* add_to_page_cache_locked - add a locked page to the pagecache
@@ -969,59 +969,58 @@ ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
- return __add_to_page_cache_locked(page, mapping, offset,
+ return __filemap_add_folio(mapping, page_folio(page), offset,
gfp_mask, NULL);
}
EXPORT_SYMBOL(add_to_page_cache_locked);
-int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
+int filemap_add_folio(struct address_space *mapping, struct folio *folio,
+ pgoff_t index, gfp_t gfp)
{
void *shadow = NULL;
int ret;
- __SetPageLocked(page);
- ret = __add_to_page_cache_locked(page, mapping, offset,
- gfp_mask, &shadow);
+ __folio_set_locked(folio);
+ ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow);
if (unlikely(ret))
- __ClearPageLocked(page);
+ __folio_clear_locked(folio);
else {
/*
- * The page might have been evicted from cache only
+ * The folio might have been evicted from cache only
* recently, in which case it should be activated like
- * any other repeatedly accessed page.
- * The exception is pages getting rewritten; evicting other
+ * any other repeatedly accessed folio.
+ * The exception is folios getting rewritten; evicting other
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
*/
- WARN_ON_ONCE(PageActive(page));
- if (!(gfp_mask & __GFP_WRITE) && shadow)
- workingset_refault(page, shadow);
- lru_cache_add(page);
+ WARN_ON_ONCE(folio_test_active(folio));
+ if (!(gfp & __GFP_WRITE) && shadow)
+ workingset_refault(folio, shadow);
+ folio_add_lru(folio);
}
return ret;
}
-EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
+EXPORT_SYMBOL_GPL(filemap_add_folio);
#ifdef CONFIG_NUMA
-struct page *__page_cache_alloc(gfp_t gfp)
+struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
{
int n;
- struct page *page;
+ struct folio *folio;
if (cpuset_do_page_mem_spread()) {
unsigned int cpuset_mems_cookie;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
n = cpuset_mem_spread_node();
- page = __alloc_pages_node(n, gfp, 0);
- } while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
+ folio = __folio_alloc_node(gfp, order, n);
+ } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie));
- return page;
+ return folio;
}
- return alloc_pages(gfp, 0);
+ return folio_alloc(gfp, order);
}
-EXPORT_SYMBOL(__page_cache_alloc);
+EXPORT_SYMBOL(filemap_alloc_folio);
#endif
/*
@@ -1074,11 +1073,11 @@ EXPORT_SYMBOL(filemap_invalidate_unlock_two);
*/
#define PAGE_WAIT_TABLE_BITS 8
#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
-static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
-static wait_queue_head_t *page_waitqueue(struct page *page)
+static wait_queue_head_t *folio_waitqueue(struct folio *folio)
{
- return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
+ return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)];
}
void __init pagecache_init(void)
@@ -1086,7 +1085,7 @@ void __init pagecache_init(void)
int i;
for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
- init_waitqueue_head(&page_wait_table[i]);
+ init_waitqueue_head(&folio_wait_table[i]);
page_writeback_init();
}
@@ -1141,10 +1140,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
*/
flags = wait->flags;
if (flags & WQ_FLAG_EXCLUSIVE) {
- if (test_bit(key->bit_nr, &key->page->flags))
+ if (test_bit(key->bit_nr, &key->folio->flags))
return -1;
if (flags & WQ_FLAG_CUSTOM) {
- if (test_and_set_bit(key->bit_nr, &key->page->flags))
+ if (test_and_set_bit(key->bit_nr, &key->folio->flags))
return -1;
flags |= WQ_FLAG_DONE;
}
@@ -1157,7 +1156,7 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
*
* So update the flags atomically, and wake up the waiter
* afterwards to avoid any races. This store-release pairs
- * with the load-acquire in wait_on_page_bit_common().
+ * with the load-acquire in folio_wait_bit_common().
*/
smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
wake_up_state(wait->private, mode);
@@ -1176,14 +1175,14 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
return (flags & WQ_FLAG_EXCLUSIVE) != 0;
}
-static void wake_up_page_bit(struct page *page, int bit_nr)
+static void folio_wake_bit(struct folio *folio, int bit_nr)
{
- wait_queue_head_t *q = page_waitqueue(page);
+ wait_queue_head_t *q = folio_waitqueue(folio);
struct wait_page_key key;
unsigned long flags;
wait_queue_entry_t bookmark;
- key.page = page;
+ key.folio = folio;
key.bit_nr = bit_nr;
key.page_match = 0;
@@ -1218,7 +1217,7 @@ static void wake_up_page_bit(struct page *page, int bit_nr)
* page waiters.
*/
if (!waitqueue_active(q) || !key.page_match) {
- ClearPageWaiters(page);
+ folio_clear_waiters(folio);
/*
* It's possible to miss clearing Waiters here, when we woke
* our page waiters, but the hashed waitqueue has waiters for
@@ -1230,19 +1229,19 @@ static void wake_up_page_bit(struct page *page, int bit_nr)
spin_unlock_irqrestore(&q->lock, flags);
}
-static void wake_up_page(struct page *page, int bit)
+static void folio_wake(struct folio *folio, int bit)
{
- if (!PageWaiters(page))
+ if (!folio_test_waiters(folio))
return;
- wake_up_page_bit(page, bit);
+ folio_wake_bit(folio, bit);
}
/*
- * A choice of three behaviors for wait_on_page_bit_common():
+ * A choice of three behaviors for folio_wait_bit_common():
*/
enum behavior {
EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
- * __lock_page() waiting on then setting PG_locked.
+ * __folio_lock() waiting on then setting PG_locked.
*/
SHARED, /* Hold ref to page and check the bit when woken, like
* wait_on_page_writeback() waiting on PG_writeback.
@@ -1253,16 +1252,16 @@ enum behavior {
};
/*
- * Attempt to check (or get) the page bit, and mark us done
+ * Attempt to check (or get) the folio flag, and mark us done
* if successful.
*/
-static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
+static inline bool folio_trylock_flag(struct folio *folio, int bit_nr,
struct wait_queue_entry *wait)
{
if (wait->flags & WQ_FLAG_EXCLUSIVE) {
- if (test_and_set_bit(bit_nr, &page->flags))
+ if (test_and_set_bit(bit_nr, &folio->flags))
return false;
- } else if (test_bit(bit_nr, &page->flags))
+ } else if (test_bit(bit_nr, &folio->flags))
return false;
wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
@@ -1272,9 +1271,10 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
/* How many times do we accept lock stealing from under a waiter? */
int sysctl_page_lock_unfairness = 5;
-static inline int wait_on_page_bit_common(wait_queue_head_t *q,
- struct page *page, int bit_nr, int state, enum behavior behavior)
+static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
+ int state, enum behavior behavior)
{
+ wait_queue_head_t *q = folio_waitqueue(folio);
int unfairness = sysctl_page_lock_unfairness;
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
@@ -1283,8 +1283,8 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
unsigned long pflags;
if (bit_nr == PG_locked &&
- !PageUptodate(page) && PageWorkingset(page)) {
- if (!PageSwapBacked(page)) {
+ !folio_test_uptodate(folio) && folio_test_workingset(folio)) {
+ if (!folio_test_swapbacked(folio)) {
delayacct_thrashing_start();
delayacct = true;
}
@@ -1294,7 +1294,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
init_wait(wait);
wait->func = wake_page_function;
- wait_page.page = page;
+ wait_page.folio = folio;
wait_page.bit_nr = bit_nr;
repeat:
@@ -1309,7 +1309,7 @@ repeat:
* Do one last check whether we can get the
* page bit synchronously.
*
- * Do the SetPageWaiters() marking before that
+ * Do the folio_set_waiters() marking before that
* to let any waker we _just_ missed know they
* need to wake us up (otherwise they'll never
* even go to the slow case that looks at the
@@ -1320,8 +1320,8 @@ repeat:
* lock to avoid races.
*/
spin_lock_irq(&q->lock);
- SetPageWaiters(page);
- if (!trylock_page_bit_common(page, bit_nr, wait))
+ folio_set_waiters(folio);
+ if (!folio_trylock_flag(folio, bit_nr, wait))
__add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
@@ -1331,10 +1331,10 @@ repeat:
* see whether the page bit testing has already
* been done by the wake function.
*
- * We can drop our reference to the page.
+ * We can drop our reference to the folio.
*/
if (behavior == DROP)
- put_page(page);
+ folio_put(folio);
/*
* Note that until the "finish_wait()", or until
@@ -1371,7 +1371,7 @@ repeat:
*
* And if that fails, we'll have to retry this all.
*/
- if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
+ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0))))
goto repeat;
wait->flags |= WQ_FLAG_DONE;
@@ -1380,7 +1380,7 @@ repeat:
/*
* If a signal happened, this 'finish_wait()' may remove the last
- * waiter from the wait-queues, but the PageWaiters bit will remain
+ * waiter from the wait-queues, but the folio waiters bit will remain
* set. That's ok. The next wakeup will take care of it, and trying
* to do it here would be difficult and prone to races.
*/
@@ -1411,19 +1411,17 @@ repeat:
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
-void wait_on_page_bit(struct page *page, int bit_nr)
+void folio_wait_bit(struct folio *folio, int bit_nr)
{
- wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
+ folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
-EXPORT_SYMBOL(wait_on_page_bit);
+EXPORT_SYMBOL(folio_wait_bit);
-int wait_on_page_bit_killable(struct page *page, int bit_nr)
+int folio_wait_bit_killable(struct folio *folio, int bit_nr)
{
- wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
+ return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED);
}
-EXPORT_SYMBOL(wait_on_page_bit_killable);
+EXPORT_SYMBOL(folio_wait_bit_killable);
/**
* put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
@@ -1440,31 +1438,28 @@ EXPORT_SYMBOL(wait_on_page_bit_killable);
*/
int put_and_wait_on_page_locked(struct page *page, int state)
{
- wait_queue_head_t *q;
-
- page = compound_head(page);
- q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, PG_locked, state, DROP);
+ return folio_wait_bit_common(page_folio(page), PG_locked, state,
+ DROP);
}
/**
- * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
- * @page: Page defining the wait queue of interest
+ * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue
+ * @folio: Folio defining the wait queue of interest
* @waiter: Waiter to add to the queue
*
- * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ * Add an arbitrary @waiter to the wait queue for the nominated @folio.
*/
-void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
+void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter)
{
- wait_queue_head_t *q = page_waitqueue(page);
+ wait_queue_head_t *q = folio_waitqueue(folio);
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__add_wait_queue_entry_tail(q, waiter);
- SetPageWaiters(page);
+ folio_set_waiters(folio);
spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL_GPL(add_page_wait_queue);
+EXPORT_SYMBOL_GPL(folio_add_wait_queue);
#ifndef clear_bit_unlock_is_negative_byte
@@ -1490,124 +1485,116 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem
#endif
/**
- * unlock_page - unlock a locked page
- * @page: the page
+ * folio_unlock - Unlock a locked folio.
+ * @folio: The folio.
*
- * Unlocks the page and wakes up sleepers in wait_on_page_locked().
- * Also wakes sleepers in wait_on_page_writeback() because the wakeup
- * mechanism between PageLocked pages and PageWriteback pages is shared.
- * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
+ * Unlocks the folio and wakes up any thread sleeping on the page lock.
*
- * Note that this depends on PG_waiters being the sign bit in the byte
- * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
- * clear the PG_locked bit and test PG_waiters at the same time fairly
- * portably (architectures that do LL/SC can test any bit, while x86 can
- * test the sign bit).
+ * Context: May be called from interrupt or process context. May not be
+ * called from NMI context.
*/
-void unlock_page(struct page *page)
+void folio_unlock(struct folio *folio)
{
+ /* Bit 7 allows x86 to check the byte's sign bit */
BUILD_BUG_ON(PG_waiters != 7);
- page = compound_head(page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
- wake_up_page_bit(page, PG_locked);
+ BUILD_BUG_ON(PG_locked > 7);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0)))
+ folio_wake_bit(folio, PG_locked);
}
-EXPORT_SYMBOL(unlock_page);
+EXPORT_SYMBOL(folio_unlock);
/**
- * end_page_private_2 - Clear PG_private_2 and release any waiters
- * @page: The page
+ * folio_end_private_2 - Clear PG_private_2 and wake any waiters.
+ * @folio: The folio.
*
- * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for
- * this. The page ref held for PG_private_2 being set is released.
+ * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for
+ * it. The folio reference held for PG_private_2 being set is released.
*
- * This is, for example, used when a netfs page is being written to a local
- * disk cache, thereby allowing writes to the cache for the same page to be
+ * This is, for example, used when a netfs folio is being written to a local
+ * disk cache, thereby allowing writes to the cache for the same folio to be
* serialised.
*/
-void end_page_private_2(struct page *page)
+void folio_end_private_2(struct folio *folio)
{
- page = compound_head(page);
- VM_BUG_ON_PAGE(!PagePrivate2(page), page);
- clear_bit_unlock(PG_private_2, &page->flags);
- wake_up_page_bit(page, PG_private_2);
- put_page(page);
+ VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio);
+ clear_bit_unlock(PG_private_2, folio_flags(folio, 0));
+ folio_wake_bit(folio, PG_private_2);
+ folio_put(folio);
}
-EXPORT_SYMBOL(end_page_private_2);
+EXPORT_SYMBOL(folio_end_private_2);
/**
- * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio.
+ * @folio: The folio to wait on.
*
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page.
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio.
*/
-void wait_on_page_private_2(struct page *page)
+void folio_wait_private_2(struct folio *folio)
{
- page = compound_head(page);
- while (PagePrivate2(page))
- wait_on_page_bit(page, PG_private_2);
+ while (folio_test_private_2(folio))
+ folio_wait_bit(folio, PG_private_2);
}
-EXPORT_SYMBOL(wait_on_page_private_2);
+EXPORT_SYMBOL(folio_wait_private_2);
/**
- * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio.
+ * @folio: The folio to wait on.
*
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a
* fatal signal is received by the calling task.
*
* Return:
* - 0 if successful.
* - -EINTR if a fatal signal was encountered.
*/
-int wait_on_page_private_2_killable(struct page *page)
+int folio_wait_private_2_killable(struct folio *folio)
{
int ret = 0;
- page = compound_head(page);
- while (PagePrivate2(page)) {
- ret = wait_on_page_bit_killable(page, PG_private_2);
+ while (folio_test_private_2(folio)) {
+ ret = folio_wait_bit_killable(folio, PG_private_2);
if (ret < 0)
break;
}
return ret;
}
-EXPORT_SYMBOL(wait_on_page_private_2_killable);
+EXPORT_SYMBOL(folio_wait_private_2_killable);
/**
- * end_page_writeback - end writeback against a page
- * @page: the page
+ * folio_end_writeback - End writeback against a folio.
+ * @folio: The folio.
*/
-void end_page_writeback(struct page *page)
+void folio_end_writeback(struct folio *folio)
{
/*
- * TestClearPageReclaim could be used here but it is an atomic
- * operation and overkill in this particular case. Failing to
- * shuffle a page marked for immediate reclaim is too mild to
- * justify taking an atomic operation penalty at the end of
- * ever page writeback.
+ * folio_test_clear_reclaim() could be used here but it is an
+ * atomic operation and overkill in this particular case. Failing
+ * to shuffle a folio marked for immediate reclaim is too mild
+ * a gain to justify taking an atomic operation penalty at the
+ * end of every folio writeback.
*/
- if (PageReclaim(page)) {
- ClearPageReclaim(page);
- rotate_reclaimable_page(page);
+ if (folio_test_reclaim(folio)) {
+ folio_clear_reclaim(folio);
+ folio_rotate_reclaimable(folio);
}
/*
- * Writeback does not hold a page reference of its own, relying
+ * Writeback does not hold a folio reference of its own, relying
* on truncation to wait for the clearing of PG_writeback.
- * But here we must make sure that the page is not freed and
- * reused before the wake_up_page().
+ * But here we must make sure that the folio is not freed and
+ * reused before the folio_wake().
*/
- get_page(page);
- if (!test_clear_page_writeback(page))
+ folio_get(folio);
+ if (!__folio_end_writeback(folio))
BUG();
smp_mb__after_atomic();
- wake_up_page(page, PG_writeback);
- put_page(page);
+ folio_wake(folio, PG_writeback);
+ folio_put(folio);
}
-EXPORT_SYMBOL(end_page_writeback);
+EXPORT_SYMBOL(folio_end_writeback);
/*
* After completing I/O on a page, call this routine to update the page
@@ -1638,39 +1625,35 @@ void page_endio(struct page *page, bool is_write, int err)
EXPORT_SYMBOL_GPL(page_endio);
/**
- * __lock_page - get a lock on the page, assuming we need to sleep to get it
- * @__page: the page to lock
+ * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it.
+ * @folio: The folio to lock
*/
-void __lock_page(struct page *__page)
+void __folio_lock(struct folio *folio)
{
- struct page *page = compound_head(__page);
- wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
+ folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE,
EXCLUSIVE);
}
-EXPORT_SYMBOL(__lock_page);
+EXPORT_SYMBOL(__folio_lock);
-int __lock_page_killable(struct page *__page)
+int __folio_lock_killable(struct folio *folio)
{
- struct page *page = compound_head(__page);
- wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
+ return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE,
EXCLUSIVE);
}
-EXPORT_SYMBOL_GPL(__lock_page_killable);
+EXPORT_SYMBOL_GPL(__folio_lock_killable);
-int __lock_page_async(struct page *page, struct wait_page_queue *wait)
+static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait)
{
- struct wait_queue_head *q = page_waitqueue(page);
+ struct wait_queue_head *q = folio_waitqueue(folio);
int ret = 0;
- wait->page = page;
+ wait->folio = folio;
wait->bit_nr = PG_locked;
spin_lock_irq(&q->lock);
__add_wait_queue_entry_tail(q, &wait->wait);
- SetPageWaiters(page);
- ret = !trylock_page(page);
+ folio_set_waiters(folio);
+ ret = !folio_trylock(folio);
/*
* If we were successful now, we know we're still on the
* waitqueue as we're still under the lock. This means it's
@@ -1687,16 +1670,16 @@ int __lock_page_async(struct page *page, struct wait_page_queue *wait)
/*
* Return values:
- * 1 - page is locked; mmap_lock is still held.
- * 0 - page is not locked.
+ * true - folio is locked; mmap_lock is still held.
+ * false - folio is not locked.
* mmap_lock has been released (mmap_read_unlock(), unless flags had both
* FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
* which case mmap_lock is still held.
*
- * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
- * with the page locked and the mmap_lock unperturbed.
+ * If neither ALLOW_RETRY nor KILLABLE are set, will always return true
+ * with the folio locked and the mmap_lock unperturbed.
*/
-int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
unsigned int flags)
{
if (fault_flag_allow_retry_first(flags)) {
@@ -1705,28 +1688,28 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
* even though return 0.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
- return 0;
+ return false;
mmap_read_unlock(mm);
if (flags & FAULT_FLAG_KILLABLE)
- wait_on_page_locked_killable(page);
+ folio_wait_locked_killable(folio);
else
- wait_on_page_locked(page);
- return 0;
+ folio_wait_locked(folio);
+ return false;
}
if (flags & FAULT_FLAG_KILLABLE) {
- int ret;
+ bool ret;
- ret = __lock_page_killable(page);
+ ret = __folio_lock_killable(folio);
if (ret) {
mmap_read_unlock(mm);
- return 0;
+ return false;
}
} else {
- __lock_page(page);
+ __folio_lock(folio);
}
- return 1;
+ return true;
}
/**
@@ -1802,143 +1785,155 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
EXPORT_SYMBOL(page_cache_prev_miss);
/*
+ * Lockless page cache protocol:
+ * On the lookup side:
+ * 1. Load the folio from i_pages
+ * 2. Increment the refcount if it's not zero
+ * 3. If the folio is not found by xas_reload(), put the refcount and retry
+ *
+ * On the removal side:
+ * A. Freeze the page (by zeroing the refcount if nobody else has a reference)
+ * B. Remove the page from i_pages
+ * C. Return the page to the page allocator
+ *
+ * This means that any page may have its reference count temporarily
+ * increased by a speculative page cache (or fast GUP) lookup as it can
+ * be allocated by another user before the RCU grace period expires.
+ * Because the refcount temporarily acquired here may end up being the
+ * last refcount on the page, any page allocation must be freeable by
+ * folio_put().
+ */
+
+/*
* mapping_get_entry - Get a page cache entry.
* @mapping: the address_space to search
* @index: The page cache index.
*
- * Looks up the page cache slot at @mapping & @index. If there is a
- * page cache page, the head page is returned with an increased refcount.
+ * Looks up the page cache entry at @mapping & @index. If it is a folio,
+ * it is returned with an increased refcount. If it is a shadow entry
+ * of a previously evicted folio, or a swap entry from shmem/tmpfs,
+ * it is returned without further action.
*
- * If the slot holds a shadow entry of a previously evicted page, or a
- * swap entry from shmem/tmpfs, it is returned.
- *
- * Return: The head page or shadow entry, %NULL if nothing is found.
+ * Return: The folio, swap or shadow entry, %NULL if nothing is found.
*/
-static struct page *mapping_get_entry(struct address_space *mapping,
- pgoff_t index)
+static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
{
XA_STATE(xas, &mapping->i_pages, index);
- struct page *page;
+ struct folio *folio;
rcu_read_lock();
repeat:
xas_reset(&xas);
- page = xas_load(&xas);
- if (xas_retry(&xas, page))
+ folio = xas_load(&xas);
+ if (xas_retry(&xas, folio))
goto repeat;
/*
* A shadow entry of a recently evicted page, or a swap entry from
* shmem/tmpfs. Return it without attempting to raise page count.
*/
- if (!page || xa_is_value(page))
+ if (!folio || xa_is_value(folio))
goto out;
- if (!page_cache_get_speculative(page))
+ if (!folio_try_get_rcu(folio))
goto repeat;
- /*
- * Has the page moved or been split?
- * This is part of the lockless pagecache protocol. See
- * include/linux/pagemap.h for details.
- */
- if (unlikely(page != xas_reload(&xas))) {
- put_page(page);
+ if (unlikely(folio != xas_reload(&xas))) {
+ folio_put(folio);
goto repeat;
}
out:
rcu_read_unlock();
- return page;
+ return folio;
}
/**
- * pagecache_get_page - Find and get a reference to a page.
+ * __filemap_get_folio - Find and get a reference to a folio.
* @mapping: The address_space to search.
* @index: The page index.
- * @fgp_flags: %FGP flags modify how the page is returned.
- * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified.
+ * @fgp_flags: %FGP flags modify how the folio is returned.
+ * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
*
* Looks up the page cache entry at @mapping & @index.
*
* @fgp_flags can be zero or more of these flags:
*
- * * %FGP_ACCESSED - The page will be marked accessed.
- * * %FGP_LOCK - The page is returned locked.
- * * %FGP_HEAD - If the page is present and a THP, return the head page
- * rather than the exact page specified by the index.
+ * * %FGP_ACCESSED - The folio will be marked accessed.
+ * * %FGP_LOCK - The folio is returned locked.
* * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it
- * instead of allocating a new page to replace it.
+ * instead of allocating a new folio to replace it.
* * %FGP_CREAT - If no page is present then a new page is allocated using
- * @gfp_mask and added to the page cache and the VM's LRU list.
+ * @gfp and added to the page cache and the VM's LRU list.
* The page is returned locked and with an increased refcount.
* * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
* page is already in cache. If the page was allocated, unlock it before
* returning so the caller can do the same dance.
- * * %FGP_WRITE - The page will be written
- * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask
- * * %FGP_NOWAIT - Don't get blocked by page lock
+ * * %FGP_WRITE - The page will be written to by the caller.
+ * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
+ * * %FGP_NOWAIT - Don't get blocked by page lock.
+ * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
*
* If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
* if the %GFP flags specified for %FGP_CREAT are atomic.
*
* If there is a page cache page, it is returned with an increased refcount.
*
- * Return: The found page or %NULL otherwise.
+ * Return: The found folio or %NULL otherwise.
*/
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp_mask)
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp)
{
- struct page *page;
+ struct folio *folio;
repeat:
- page = mapping_get_entry(mapping, index);
- if (xa_is_value(page)) {
+ folio = mapping_get_entry(mapping, index);
+ if (xa_is_value(folio)) {
if (fgp_flags & FGP_ENTRY)
- return page;
- page = NULL;
+ return folio;
+ folio = NULL;
}
- if (!page)
+ if (!folio)
goto no_page;
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
- if (!trylock_page(page)) {
- put_page(page);
+ if (!folio_trylock(folio)) {
+ folio_put(folio);
return NULL;
}
} else {
- lock_page(page);
+ folio_lock(folio);
}
/* Has the page been truncated? */
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- put_page(page);
+ if (unlikely(folio->mapping != mapping)) {
+ folio_unlock(folio);
+ folio_put(folio);
goto repeat;
}
- VM_BUG_ON_PAGE(!thp_contains(page, index), page);
+ VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
}
if (fgp_flags & FGP_ACCESSED)
- mark_page_accessed(page);
+ folio_mark_accessed(folio);
else if (fgp_flags & FGP_WRITE) {
/* Clear idle flag for buffer write */
- if (page_is_idle(page))
- clear_page_idle(page);
+ if (folio_test_idle(folio))
+ folio_clear_idle(folio);
}
- if (!(fgp_flags & FGP_HEAD))
- page = find_subpage(page, index);
+ if (fgp_flags & FGP_STABLE)
+ folio_wait_stable(folio);
no_page:
- if (!page && (fgp_flags & FGP_CREAT)) {
+ if (!folio && (fgp_flags & FGP_CREAT)) {
int err;
if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
- gfp_mask |= __GFP_WRITE;
+ gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
- gfp_mask &= ~__GFP_FS;
+ gfp &= ~__GFP_FS;
- page = __page_cache_alloc(gfp_mask);
- if (!page)
+ folio = filemap_alloc_folio(gfp, 0);
+ if (!folio)
return NULL;
if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
@@ -1946,27 +1941,27 @@ no_page:
/* Init accessed so avoid atomic mark_page_accessed later */
if (fgp_flags & FGP_ACCESSED)
- __SetPageReferenced(page);
+ __folio_set_referenced(folio);
- err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
+ err = filemap_add_folio(mapping, folio, index, gfp);
if (unlikely(err)) {
- put_page(page);
- page = NULL;
+ folio_put(folio);
+ folio = NULL;
if (err == -EEXIST)
goto repeat;
}
/*
- * add_to_page_cache_lru locks the page, and for mmap we expect
- * an unlocked page.
+ * filemap_add_folio locks the page, and for mmap
+ * we expect an unlocked page.
*/
- if (page && (fgp_flags & FGP_FOR_MMAP))
- unlock_page(page);
+ if (folio && (fgp_flags & FGP_FOR_MMAP))
+ folio_unlock(folio);
}
- return page;
+ return folio;
}
-EXPORT_SYMBOL(pagecache_get_page);
+EXPORT_SYMBOL(__filemap_get_folio);
static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max,
xa_mark_t mark)
@@ -2421,6 +2416,7 @@ static int filemap_update_page(struct kiocb *iocb,
struct address_space *mapping, struct iov_iter *iter,
struct page *page)
{
+ struct folio *folio = page_folio(page);
int error;
if (iocb->ki_flags & IOCB_NOWAIT) {
@@ -2430,40 +2426,40 @@ static int filemap_update_page(struct kiocb *iocb,
filemap_invalidate_lock_shared(mapping);
}
- if (!trylock_page(page)) {
+ if (!folio_trylock(folio)) {
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
goto unlock_mapping;
if (!(iocb->ki_flags & IOCB_WAITQ)) {
filemap_invalidate_unlock_shared(mapping);
- put_and_wait_on_page_locked(page, TASK_KILLABLE);
+ put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE);
return AOP_TRUNCATED_PAGE;
}
- error = __lock_page_async(page, iocb->ki_waitq);
+ error = __folio_lock_async(folio, iocb->ki_waitq);
if (error)
goto unlock_mapping;
}
error = AOP_TRUNCATED_PAGE;
- if (!page->mapping)
+ if (!folio->mapping)
goto unlock;
error = 0;
- if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
+ if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, &folio->page))
goto unlock;
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
- error = filemap_read_page(iocb->ki_filp, mapping, page);
+ error = filemap_read_page(iocb->ki_filp, mapping, &folio->page);
goto unlock_mapping;
unlock:
- unlock_page(page);
+ folio_unlock(folio);
unlock_mapping:
filemap_invalidate_unlock_shared(mapping);
if (error == AOP_TRUNCATED_PAGE)
- put_page(page);
+ folio_put(folio);
return error;
}
@@ -2900,7 +2896,9 @@ unlock:
static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
struct file **fpin)
{
- if (trylock_page(page))
+ struct folio *folio = page_folio(page);
+
+ if (folio_trylock(folio))
return 1;
/*
@@ -2913,7 +2911,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_KILLABLE) {
- if (__lock_page_killable(page)) {
+ if (__folio_lock_killable(folio)) {
/*
* We didn't have the right flags to drop the mmap_lock,
* but all fault_handlers only check for fatal signals
@@ -2925,11 +2923,11 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
return 0;
}
} else
- __lock_page(page);
+ __folio_lock(folio);
+
return 1;
}
-
/*
* Synchronous readahead happens when we don't even find a page in the page
* cache at all. We don't want to perform IO under the mmap sem, so if we have
@@ -3708,28 +3706,6 @@ out:
}
EXPORT_SYMBOL(generic_file_direct_write);
-/*
- * Find or create a page at the given pagecache position. Return the locked
- * page. This function is specifically for buffered writes.
- */
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
- pgoff_t index, unsigned flags)
-{
- struct page *page;
- int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
-
- if (flags & AOP_FLAG_NOFS)
- fgp_flags |= FGP_NOFS;
-
- page = pagecache_get_page(mapping, index, fgp_flags,
- mapping_gfp_mask(mapping));
- if (page)
- wait_for_stable_page(page);
-
- return page;
-}
-EXPORT_SYMBOL(grab_cache_page_write_begin);
-
ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
new file mode 100644
index 000000000000..5b6ae1da314e
--- /dev/null
+++ b/mm/folio-compat.c
@@ -0,0 +1,142 @@
+/*
+ * Compatibility functions which bloat the callers too much to make inline.
+ * All of the callers of these functions should be converted to use folios
+ * eventually.
+ */
+
+#include <linux/migrate.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+struct address_space *page_mapping(struct page *page)
+{
+ return folio_mapping(page_folio(page));
+}
+EXPORT_SYMBOL(page_mapping);
+
+void unlock_page(struct page *page)
+{
+ return folio_unlock(page_folio(page));
+}
+EXPORT_SYMBOL(unlock_page);
+
+void end_page_writeback(struct page *page)
+{
+ return folio_end_writeback(page_folio(page));
+}
+EXPORT_SYMBOL(end_page_writeback);
+
+void wait_on_page_writeback(struct page *page)
+{
+ return folio_wait_writeback(page_folio(page));
+}
+EXPORT_SYMBOL_GPL(wait_on_page_writeback);
+
+void wait_for_stable_page(struct page *page)
+{
+ return folio_wait_stable(page_folio(page));
+}
+EXPORT_SYMBOL_GPL(wait_for_stable_page);
+
+bool page_mapped(struct page *page)
+{
+ return folio_mapped(page_folio(page));
+}
+EXPORT_SYMBOL(page_mapped);
+
+void mark_page_accessed(struct page *page)
+{
+ folio_mark_accessed(page_folio(page));
+}
+EXPORT_SYMBOL(mark_page_accessed);
+
+#ifdef CONFIG_MIGRATION
+int migrate_page_move_mapping(struct address_space *mapping,
+ struct page *newpage, struct page *page, int extra_count)
+{
+ return folio_migrate_mapping(mapping, page_folio(newpage),
+ page_folio(page), extra_count);
+}
+EXPORT_SYMBOL(migrate_page_move_mapping);
+
+void migrate_page_states(struct page *newpage, struct page *page)
+{
+ folio_migrate_flags(page_folio(newpage), page_folio(page));
+}
+EXPORT_SYMBOL(migrate_page_states);
+
+void migrate_page_copy(struct page *newpage, struct page *page)
+{
+ folio_migrate_copy(page_folio(newpage), page_folio(page));
+}
+EXPORT_SYMBOL(migrate_page_copy);
+#endif
+
+bool set_page_writeback(struct page *page)
+{
+ return folio_start_writeback(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_writeback);
+
+bool set_page_dirty(struct page *page)
+{
+ return folio_mark_dirty(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_dirty);
+
+int __set_page_dirty_nobuffers(struct page *page)
+{
+ return filemap_dirty_folio(page_mapping(page), page_folio(page));
+}
+EXPORT_SYMBOL(__set_page_dirty_nobuffers);
+
+bool clear_page_dirty_for_io(struct page *page)
+{
+ return folio_clear_dirty_for_io(page_folio(page));
+}
+EXPORT_SYMBOL(clear_page_dirty_for_io);
+
+bool redirty_page_for_writepage(struct writeback_control *wbc,
+ struct page *page)
+{
+ return folio_redirty_for_writepage(wbc, page_folio(page));
+}
+EXPORT_SYMBOL(redirty_page_for_writepage);
+
+void lru_cache_add(struct page *page)
+{
+ folio_add_lru(page_folio(page));
+}
+EXPORT_SYMBOL(lru_cache_add);
+
+int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
+ pgoff_t index, gfp_t gfp)
+{
+ return filemap_add_folio(mapping, page_folio(page), index, gfp);
+}
+EXPORT_SYMBOL(add_to_page_cache_lru);
+
+noinline
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp)
+{
+ struct folio *folio;
+
+ folio = __filemap_get_folio(mapping, index, fgp_flags, gfp);
+ if ((fgp_flags & FGP_HEAD) || !folio || xa_is_value(folio))
+ return &folio->page;
+ return folio_file_page(folio, index);
+}
+EXPORT_SYMBOL(pagecache_get_page);
+
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags)
+{
+ unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
+
+ if (flags & AOP_FLAG_NOFS)
+ fgp_flags |= FGP_NOFS;
+ return pagecache_get_page(mapping, index, fgp_flags,
+ mapping_gfp_mask(mapping));
+}
+EXPORT_SYMBOL(grab_cache_page_write_begin);
diff --git a/mm/highmem.c b/mm/highmem.c
index 4212ad0e4a19..471d9779a7f4 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -23,7 +23,6 @@
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
-#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 92192cb086c7..e5483347291c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -603,7 +603,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
VM_BUG_ON_PAGE(!PageCompound(page), page);
- if (mem_cgroup_charge(page, vma->vm_mm, gfp)) {
+ if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) {
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
count_vm_event(THP_FAULT_FALLBACK_CHARGE);
@@ -2405,7 +2405,8 @@ static void __split_huge_page_tail(struct page *head, int tail,
static void __split_huge_page(struct page *page, struct list_head *list,
pgoff_t end)
{
- struct page *head = compound_head(page);
+ struct folio *folio = page_folio(page);
+ struct page *head = &folio->page;
struct lruvec *lruvec;
struct address_space *swap_cache = NULL;
unsigned long offset = 0;
@@ -2424,7 +2425,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
}
/* lock lru list/PageCompound, ref frozen by page_ref_freeze */
- lruvec = lock_page_lruvec(head);
+ lruvec = folio_lruvec_lock(folio);
+
+ ClearPageHasHWPoisoned(head);
for (i = nr - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 95dc7b83381f..6378c1066459 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5302,7 +5302,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
*pagep = NULL;
goto out;
}
- copy_huge_page(page, *pagep);
+ folio_copy(page_folio(page), page_folio(*pagep));
put_page(*pagep);
*pagep = NULL;
}
diff --git a/mm/internal.h b/mm/internal.h
index cf3cb933eba3..b1001ebeb286 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -34,7 +34,16 @@
void page_writeback_init(void);
+static inline void *folio_raw_mapping(struct folio *folio)
+{
+ unsigned long mapping = (unsigned long)folio->mapping;
+
+ return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
+}
+
vm_fault_t do_swap_page(struct vm_fault *vmf);
+void folio_rotate_reclaimable(struct folio *folio);
+bool __folio_end_writeback(struct folio *folio);
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
@@ -63,17 +72,28 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
/**
- * page_evictable - test whether a page is evictable
- * @page: the page to test
+ * folio_evictable - Test whether a folio is evictable.
+ * @folio: The folio to test.
*
- * Test whether page is evictable--i.e., should be placed on active/inactive
- * lists vs unevictable list.
- *
- * Reasons page might not be evictable:
- * (1) page's mapping marked unevictable
- * (2) page is part of an mlocked VMA
+ * Test whether @folio is evictable -- i.e., should be placed on
+ * active/inactive lists vs unevictable list.
*
+ * Reasons folio might not be evictable:
+ * 1. folio's mapping marked unevictable
+ * 2. One of the pages in the folio is part of an mlocked VMA
*/
+static inline bool folio_evictable(struct folio *folio)
+{
+ bool ret;
+
+ /* Prevent address_space of inode and swap cache from being freed */
+ rcu_read_lock();
+ ret = !mapping_unevictable(folio_mapping(folio)) &&
+ !folio_test_mlocked(folio);
+ rcu_read_unlock();
+ return ret;
+}
+
static inline bool page_evictable(struct page *page)
{
bool ret;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 045cc579f724..5f02fda6f265 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -445,22 +445,25 @@ static bool hugepage_vma_check(struct vm_area_struct *vma,
if (!transhuge_vma_enabled(vma, vm_flags))
return false;
+ if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) -
+ vma->vm_pgoff, HPAGE_PMD_NR))
+ return false;
+
/* Enabled via shmem mount options or sysfs settings. */
- if (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) {
- return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
- HPAGE_PMD_NR);
- }
+ if (shmem_file(vma->vm_file))
+ return shmem_huge_enabled(vma);
/* THP settings require madvise. */
if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always())
return false;
- /* Read-only file mappings need to be aligned for THP to work. */
+ /* Only regular file is valid */
if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file &&
- !inode_is_open_for_write(vma->vm_file->f_inode) &&
(vm_flags & VM_EXEC)) {
- return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
- HPAGE_PMD_NR);
+ struct inode *inode = vma->vm_file->f_inode;
+
+ return !inode_is_open_for_write(inode) &&
+ S_ISREG(inode->i_mode);
}
if (!vma->anon_vma || vma->vm_ops)
@@ -1087,7 +1090,7 @@ static void collapse_huge_page(struct mm_struct *mm,
goto out_nolock;
}
- if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) {
+ if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out_nolock;
}
@@ -1211,7 +1214,7 @@ out_up_write:
mmap_write_unlock(mm);
out_nolock:
if (!IS_ERR_OR_NULL(*hpage))
- mem_cgroup_uncharge(*hpage);
+ mem_cgroup_uncharge(page_folio(*hpage));
trace_mm_collapse_huge_page(mm, isolated, result);
return;
}
@@ -1658,7 +1661,7 @@ static void collapse_file(struct mm_struct *mm,
goto out;
}
- if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) {
+ if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out;
}
@@ -1763,6 +1766,10 @@ static void collapse_file(struct mm_struct *mm,
filemap_flush(mapping);
result = SCAN_FAIL;
goto xa_unlocked;
+ } else if (PageWriteback(page)) {
+ xas_unlock_irq(&xas);
+ result = SCAN_FAIL;
+ goto xa_unlocked;
} else if (trylock_page(page)) {
get_page(page);
xas_unlock_irq(&xas);
@@ -1798,7 +1805,8 @@ static void collapse_file(struct mm_struct *mm,
goto out_unlock;
}
- if (!is_shmem && PageDirty(page)) {
+ if (!is_shmem && (PageDirty(page) ||
+ PageWriteback(page))) {
/*
* khugepaged only works on read-only fd, so this
* page is dirty because it hasn't been flushed
@@ -1975,7 +1983,7 @@ xa_unlocked:
out:
VM_BUG_ON(!list_empty(&pagelist));
if (!IS_ERR_OR_NULL(*hpage))
- mem_cgroup_uncharge(*hpage);
+ mem_cgroup_uncharge(page_folio(*hpage));
/* TODO: tracepoints */
}
diff --git a/mm/ksm.c b/mm/ksm.c
index a5716fdec1aa..0662093237e4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -751,7 +751,7 @@ stale:
/*
* We come here from above when page->mapping or !PageSwapCache
* suggests that the node is stale; but it might be under migration.
- * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
+ * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(),
* before checking whether node->kpfn has been changed.
*/
smp_rmb();
@@ -852,9 +852,14 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
return err;
}
+static inline struct stable_node *folio_stable_node(struct folio *folio)
+{
+ return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL;
+}
+
static inline struct stable_node *page_stable_node(struct page *page)
{
- return PageKsm(page) ? page_rmapping(page) : NULL;
+ return folio_stable_node(page_folio(page));
}
static inline void set_page_stable_node(struct page *page,
@@ -2578,7 +2583,8 @@ struct page *ksm_might_need_to_copy(struct page *page,
return page; /* let do_swap_page report the error */
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
- if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) {
+ if (new_page &&
+ mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) {
put_page(new_page);
new_page = NULL;
}
@@ -2658,26 +2664,26 @@ again:
}
#ifdef CONFIG_MIGRATION
-void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+void folio_migrate_ksm(struct folio *newfolio, struct folio *folio)
{
struct stable_node *stable_node;
- VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
- VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
- VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio);
+ VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio);
- stable_node = page_stable_node(newpage);
+ stable_node = folio_stable_node(folio);
if (stable_node) {
- VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage);
- stable_node->kpfn = page_to_pfn(newpage);
+ VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio);
+ stable_node->kpfn = folio_pfn(newfolio);
/*
- * newpage->mapping was set in advance; now we need smp_wmb()
+ * newfolio->mapping was set in advance; now we need smp_wmb()
* to make sure that the new stable_node->kpfn is visible
- * to get_ksm_page() before it can see that oldpage->mapping
- * has gone stale (or that PageSwapCache has been cleared).
+ * to get_ksm_page() before it can see that folio->mapping
+ * has gone stale (or that folio_test_swapcache has been cleared).
*/
smp_wmb();
- set_page_stable_node(oldpage, NULL);
+ set_page_stable_node(&folio->page, NULL);
}
}
#endif /* CONFIG_MIGRATION */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6da5020a8656..8dab23a71fc4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -456,28 +456,6 @@ ino_t page_cgroup_ino(struct page *page)
return ino;
}
-static struct mem_cgroup_per_node *
-mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
-{
- int nid = page_to_nid(page);
-
- return memcg->nodeinfo[nid];
-}
-
-static struct mem_cgroup_tree_per_node *
-soft_limit_tree_node(int nid)
-{
- return soft_limit_tree.rb_tree_per_node[nid];
-}
-
-static struct mem_cgroup_tree_per_node *
-soft_limit_tree_from_page(struct page *page)
-{
- int nid = page_to_nid(page);
-
- return soft_limit_tree.rb_tree_per_node[nid];
-}
-
static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
struct mem_cgroup_tree_per_node *mctz,
unsigned long new_usage_in_excess)
@@ -548,13 +526,13 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
return excess;
}
-static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
+static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
{
unsigned long excess;
struct mem_cgroup_per_node *mz;
struct mem_cgroup_tree_per_node *mctz;
- mctz = soft_limit_tree_from_page(page);
+ mctz = soft_limit_tree.rb_tree_per_node[nid];
if (!mctz)
return;
/*
@@ -562,7 +540,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
* because their event counter is not touched.
*/
for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- mz = mem_cgroup_page_nodeinfo(memcg, page);
+ mz = memcg->nodeinfo[nid];
excess = soft_limit_excess(memcg);
/*
* We have to update the tree if mz is on RB-tree or
@@ -593,7 +571,7 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
for_each_node(nid) {
mz = memcg->nodeinfo[nid];
- mctz = soft_limit_tree_node(nid);
+ mctz = soft_limit_tree.rb_tree_per_node[nid];
if (mctz)
mem_cgroup_remove_exceeded(mz, mctz);
}
@@ -799,7 +777,6 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
- struct page *page,
int nr_pages)
{
/* pagein of a big page is an event. So, ignore page size */
@@ -842,7 +819,7 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
* Check events in order.
*
*/
-static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
+static void memcg_check_events(struct mem_cgroup *memcg, int nid)
{
/* threshold event is triggered in finer grain than soft limit */
if (unlikely(mem_cgroup_event_ratelimit(memcg,
@@ -853,7 +830,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
MEM_CGROUP_TARGET_SOFTLIMIT);
mem_cgroup_threshold(memcg);
if (unlikely(do_softlimit))
- mem_cgroup_update_tree(memcg, page);
+ mem_cgroup_update_tree(memcg, nid);
}
}
@@ -1149,64 +1126,88 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
}
#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
- memcg = page_memcg(page);
+ memcg = folio_memcg(folio);
if (!memcg)
- VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page);
+ VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio);
else
- VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page);
+ VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
}
#endif
/**
- * lock_page_lruvec - lock and return lruvec for a given page.
- * @page: the page
+ * folio_lruvec_lock - Lock the lruvec for a folio.
+ * @folio: Pointer to the folio.
*
* These functions are safe to use under any of the following conditions:
- * - page locked
- * - PageLRU cleared
- * - lock_page_memcg()
- * - page->_refcount is zero
+ * - folio locked
+ * - folio_test_lru false
+ * - folio_memcg_lock()
+ * - folio frozen (refcount of 0)
+ *
+ * Return: The lruvec this folio is on with its lock held.
*/
-struct lruvec *lock_page_lruvec(struct page *page)
+struct lruvec *folio_lruvec_lock(struct folio *folio)
{
- struct lruvec *lruvec;
+ struct lruvec *lruvec = folio_lruvec(folio);
- lruvec = mem_cgroup_page_lruvec(page);
spin_lock(&lruvec->lru_lock);
-
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
-struct lruvec *lock_page_lruvec_irq(struct page *page)
+/**
+ * folio_lruvec_lock_irq - Lock the lruvec for a folio.
+ * @folio: Pointer to the folio.
+ *
+ * These functions are safe to use under any of the following conditions:
+ * - folio locked
+ * - folio_test_lru false
+ * - folio_memcg_lock()
+ * - folio frozen (refcount of 0)
+ *
+ * Return: The lruvec this folio is on with its lock held and interrupts
+ * disabled.
+ */
+struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
- struct lruvec *lruvec;
+ struct lruvec *lruvec = folio_lruvec(folio);
- lruvec = mem_cgroup_page_lruvec(page);
spin_lock_irq(&lruvec->lru_lock);
-
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
-struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags)
+/**
+ * folio_lruvec_lock_irqsave - Lock the lruvec for a folio.
+ * @folio: Pointer to the folio.
+ * @flags: Pointer to irqsave flags.
+ *
+ * These functions are safe to use under any of the following conditions:
+ * - folio locked
+ * - folio_test_lru false
+ * - folio_memcg_lock()
+ * - folio frozen (refcount of 0)
+ *
+ * Return: The lruvec this folio is on with its lock held and interrupts
+ * disabled.
+ */
+struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
+ unsigned long *flags)
{
- struct lruvec *lruvec;
+ struct lruvec *lruvec = folio_lruvec(folio);
- lruvec = mem_cgroup_page_lruvec(page);
spin_lock_irqsave(&lruvec->lru_lock, *flags);
-
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
@@ -1956,18 +1957,17 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
}
/**
- * lock_page_memcg - lock a page and memcg binding
- * @page: the page
+ * folio_memcg_lock - Bind a folio to its memcg.
+ * @folio: The folio.
*
- * This function protects unlocked LRU pages from being moved to
+ * This function prevents unlocked LRU folios from being moved to
* another cgroup.
*
- * It ensures lifetime of the locked memcg. Caller is responsible
- * for the lifetime of the page.
+ * It ensures lifetime of the bound memcg. The caller is responsible
+ * for the lifetime of the folio.
*/
-void lock_page_memcg(struct page *page)
+void folio_memcg_lock(struct folio *folio)
{
- struct page *head = compound_head(page); /* rmap on tail pages */
struct mem_cgroup *memcg;
unsigned long flags;
@@ -1981,7 +1981,7 @@ void lock_page_memcg(struct page *page)
if (mem_cgroup_disabled())
return;
again:
- memcg = page_memcg(head);
+ memcg = folio_memcg(folio);
if (unlikely(!memcg))
return;
@@ -1995,7 +1995,7 @@ again:
return;
spin_lock_irqsave(&memcg->move_lock, flags);
- if (memcg != page_memcg(head)) {
+ if (memcg != folio_memcg(folio)) {
spin_unlock_irqrestore(&memcg->move_lock, flags);
goto again;
}
@@ -2009,9 +2009,15 @@ again:
memcg->move_lock_task = current;
memcg->move_lock_flags = flags;
}
+EXPORT_SYMBOL(folio_memcg_lock);
+
+void lock_page_memcg(struct page *page)
+{
+ folio_memcg_lock(page_folio(page));
+}
EXPORT_SYMBOL(lock_page_memcg);
-static void __unlock_page_memcg(struct mem_cgroup *memcg)
+static void __folio_memcg_unlock(struct mem_cgroup *memcg)
{
if (memcg && memcg->move_lock_task == current) {
unsigned long flags = memcg->move_lock_flags;
@@ -2026,14 +2032,22 @@ static void __unlock_page_memcg(struct mem_cgroup *memcg)
}
/**
- * unlock_page_memcg - unlock a page and memcg binding
- * @page: the page
+ * folio_memcg_unlock - Release the binding between a folio and its memcg.
+ * @folio: The folio.
+ *
+ * This releases the binding created by folio_memcg_lock(). This does
+ * not change the accounting of this folio to its memcg, but it does
+ * permit others to change it.
*/
-void unlock_page_memcg(struct page *page)
+void folio_memcg_unlock(struct folio *folio)
{
- struct page *head = compound_head(page);
+ __folio_memcg_unlock(folio_memcg(folio));
+}
+EXPORT_SYMBOL(folio_memcg_unlock);
- __unlock_page_memcg(page_memcg(head));
+void unlock_page_memcg(struct page *page)
+{
+ folio_memcg_unlock(page_folio(page));
}
EXPORT_SYMBOL(unlock_page_memcg);
@@ -2734,9 +2748,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
}
#endif
-static void commit_charge(struct page *page, struct mem_cgroup *memcg)
+static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
- VM_BUG_ON_PAGE(page_memcg(page), page);
+ VM_BUG_ON_FOLIO(folio_memcg(folio), folio);
/*
* Any of the following ensures page's memcg stability:
*
@@ -2745,7 +2759,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
* - lock_page_memcg()
* - exclusive reference
*/
- page->memcg_data = (unsigned long)memcg;
+ folio->memcg_data = (unsigned long)memcg;
}
static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
@@ -3015,15 +3029,16 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
*/
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
+ struct folio *folio = page_folio(page);
struct obj_cgroup *objcg;
unsigned int nr_pages = 1 << order;
- if (!PageMemcgKmem(page))
+ if (!folio_memcg_kmem(folio))
return;
- objcg = __page_objcg(page);
+ objcg = __folio_objcg(folio);
obj_cgroup_uncharge_pages(objcg, nr_pages);
- page->memcg_data = 0;
+ folio->memcg_data = 0;
obj_cgroup_put(objcg);
}
@@ -3257,17 +3272,18 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
*/
void split_page_memcg(struct page *head, unsigned int nr)
{
- struct mem_cgroup *memcg = page_memcg(head);
+ struct folio *folio = page_folio(head);
+ struct mem_cgroup *memcg = folio_memcg(folio);
int i;
if (mem_cgroup_disabled() || !memcg)
return;
for (i = 1; i < nr; i++)
- head[i].memcg_data = head->memcg_data;
+ folio_page(folio, i)->memcg_data = folio->memcg_data;
- if (PageMemcgKmem(head))
- obj_cgroup_get_many(__page_objcg(head), nr - 1);
+ if (folio_memcg_kmem(folio))
+ obj_cgroup_get_many(__folio_objcg(folio), nr - 1);
else
css_get_many(&memcg->css, nr - 1);
}
@@ -3381,7 +3397,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
if (order > 0)
return 0;
- mctz = soft_limit_tree_node(pgdat->node_id);
+ mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id];
/*
* Do not even bother to check the largest node if the root
@@ -4537,17 +4553,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
* As being wrong occasionally doesn't matter, updates and accesses to the
* records are lockless and racy.
*/
-void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
struct bdi_writeback *wb)
{
- struct mem_cgroup *memcg = page_memcg(page);
+ struct mem_cgroup *memcg = folio_memcg(folio);
struct memcg_cgwb_frn *frn;
u64 now = get_jiffies_64();
u64 oldest_at = now;
int oldest = -1;
int i;
- trace_track_foreign_dirty(page, wb);
+ trace_track_foreign_dirty(folio, wb);
/*
* Pick the slot to use. If there is already a slot for @wb, keep
@@ -5575,38 +5591,39 @@ static int mem_cgroup_move_account(struct page *page,
struct mem_cgroup *from,
struct mem_cgroup *to)
{
+ struct folio *folio = page_folio(page);
struct lruvec *from_vec, *to_vec;
struct pglist_data *pgdat;
- unsigned int nr_pages = compound ? thp_nr_pages(page) : 1;
- int ret;
+ unsigned int nr_pages = compound ? folio_nr_pages(folio) : 1;
+ int nid, ret;
VM_BUG_ON(from == to);
- VM_BUG_ON_PAGE(PageLRU(page), page);
- VM_BUG_ON(compound && !PageTransHuge(page));
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
+ VM_BUG_ON(compound && !folio_test_multi(folio));
/*
* Prevent mem_cgroup_migrate() from looking at
* page's memory cgroup of its source page while we change it.
*/
ret = -EBUSY;
- if (!trylock_page(page))
+ if (!folio_trylock(folio))
goto out;
ret = -EINVAL;
- if (page_memcg(page) != from)
+ if (folio_memcg(folio) != from)
goto out_unlock;
- pgdat = page_pgdat(page);
+ pgdat = folio_pgdat(folio);
from_vec = mem_cgroup_lruvec(from, pgdat);
to_vec = mem_cgroup_lruvec(to, pgdat);
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
- if (PageAnon(page)) {
- if (page_mapped(page)) {
+ if (folio_test_anon(folio)) {
+ if (folio_mapped(folio)) {
__mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages);
__mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages);
- if (PageTransHuge(page)) {
+ if (folio_test_transhuge(folio)) {
__mod_lruvec_state(from_vec, NR_ANON_THPS,
-nr_pages);
__mod_lruvec_state(to_vec, NR_ANON_THPS,
@@ -5617,18 +5634,18 @@ static int mem_cgroup_move_account(struct page *page,
__mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages);
__mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages);
- if (PageSwapBacked(page)) {
+ if (folio_test_swapbacked(folio)) {
__mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages);
__mod_lruvec_state(to_vec, NR_SHMEM, nr_pages);
}
- if (page_mapped(page)) {
+ if (folio_mapped(folio)) {
__mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages);
__mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages);
}
- if (PageDirty(page)) {
- struct address_space *mapping = page_mapping(page);
+ if (folio_test_dirty(folio)) {
+ struct address_space *mapping = folio_mapping(folio);
if (mapping_can_writeback(mapping)) {
__mod_lruvec_state(from_vec, NR_FILE_DIRTY,
@@ -5639,7 +5656,7 @@ static int mem_cgroup_move_account(struct page *page,
}
}
- if (PageWriteback(page)) {
+ if (folio_test_writeback(folio)) {
__mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages);
__mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
}
@@ -5662,20 +5679,21 @@ static int mem_cgroup_move_account(struct page *page,
css_get(&to->css);
css_put(&from->css);
- page->memcg_data = (unsigned long)to;
+ folio->memcg_data = (unsigned long)to;
- __unlock_page_memcg(from);
+ __folio_memcg_unlock(from);
ret = 0;
+ nid = folio_nid(folio);
local_irq_disable();
- mem_cgroup_charge_statistics(to, page, nr_pages);
- memcg_check_events(to, page);
- mem_cgroup_charge_statistics(from, page, -nr_pages);
- memcg_check_events(from, page);
+ mem_cgroup_charge_statistics(to, nr_pages);
+ memcg_check_events(to, nid);
+ mem_cgroup_charge_statistics(from, -nr_pages);
+ memcg_check_events(from, nid);
local_irq_enable();
out_unlock:
- unlock_page(page);
+ folio_unlock(folio);
out:
return ret;
}
@@ -6680,9 +6698,10 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root,
atomic_long_read(&parent->memory.children_low_usage)));
}
-static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
+static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
+ gfp_t gfp)
{
- unsigned int nr_pages = thp_nr_pages(page);
+ long nr_pages = folio_nr_pages(folio);
int ret;
ret = try_charge(memcg, gfp, nr_pages);
@@ -6690,38 +6709,23 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
goto out;
css_get(&memcg->css);
- commit_charge(page, memcg);
+ commit_charge(folio, memcg);
local_irq_disable();
- mem_cgroup_charge_statistics(memcg, page, nr_pages);
- memcg_check_events(memcg, page);
+ mem_cgroup_charge_statistics(memcg, nr_pages);
+ memcg_check_events(memcg, folio_nid(folio));
local_irq_enable();
out:
return ret;
}
-/**
- * __mem_cgroup_charge - charge a newly allocated page to a cgroup
- * @page: page to charge
- * @mm: mm context of the victim
- * @gfp_mask: reclaim mode
- *
- * Try to charge @page to the memcg that @mm belongs to, reclaiming
- * pages according to @gfp_mask if necessary. if @mm is NULL, try to
- * charge to the active memcg.
- *
- * Do not use this for pages allocated for swapin.
- *
- * Returns 0 on success. Otherwise, an error code is returned.
- */
-int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
{
struct mem_cgroup *memcg;
int ret;
memcg = get_mem_cgroup_from_mm(mm);
- ret = charge_memcg(page, memcg, gfp_mask);
+ ret = charge_memcg(folio, memcg, gfp);
css_put(&memcg->css);
return ret;
@@ -6742,6 +6746,7 @@ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry)
{
+ struct folio *folio = page_folio(page);
struct mem_cgroup *memcg;
unsigned short id;
int ret;
@@ -6756,7 +6761,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
memcg = get_mem_cgroup_from_mm(mm);
rcu_read_unlock();
- ret = charge_memcg(page, memcg, gfp);
+ ret = charge_memcg(folio, memcg, gfp);
css_put(&memcg->css);
return ret;
@@ -6800,7 +6805,7 @@ struct uncharge_gather {
unsigned long nr_memory;
unsigned long pgpgout;
unsigned long nr_kmem;
- struct page *dummy_page;
+ int nid;
};
static inline void uncharge_gather_clear(struct uncharge_gather *ug)
@@ -6824,36 +6829,36 @@ static void uncharge_batch(const struct uncharge_gather *ug)
local_irq_save(flags);
__count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory);
- memcg_check_events(ug->memcg, ug->dummy_page);
+ memcg_check_events(ug->memcg, ug->nid);
local_irq_restore(flags);
- /* drop reference from uncharge_page */
+ /* drop reference from uncharge_folio */
css_put(&ug->memcg->css);
}
-static void uncharge_page(struct page *page, struct uncharge_gather *ug)
+static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
{
- unsigned long nr_pages;
+ long nr_pages;
struct mem_cgroup *memcg;
struct obj_cgroup *objcg;
- bool use_objcg = PageMemcgKmem(page);
+ bool use_objcg = folio_memcg_kmem(folio);
- VM_BUG_ON_PAGE(PageLRU(page), page);
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
/*
* Nobody should be changing or seriously looking at
- * page memcg or objcg at this point, we have fully
- * exclusive access to the page.
+ * folio memcg or objcg at this point, we have fully
+ * exclusive access to the folio.
*/
if (use_objcg) {
- objcg = __page_objcg(page);
+ objcg = __folio_objcg(folio);
/*
* This get matches the put at the end of the function and
* kmem pages do not hold memcg references anymore.
*/
memcg = get_mem_cgroup_from_objcg(objcg);
} else {
- memcg = __page_memcg(page);
+ memcg = __folio_memcg(folio);
}
if (!memcg)
@@ -6865,19 +6870,19 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
uncharge_gather_clear(ug);
}
ug->memcg = memcg;
- ug->dummy_page = page;
+ ug->nid = folio_nid(folio);
/* pairs with css_put in uncharge_batch */
css_get(&memcg->css);
}
- nr_pages = compound_nr(page);
+ nr_pages = folio_nr_pages(folio);
if (use_objcg) {
ug->nr_memory += nr_pages;
ug->nr_kmem += nr_pages;
- page->memcg_data = 0;
+ folio->memcg_data = 0;
obj_cgroup_put(objcg);
} else {
/* LRU pages aren't accounted at the root level */
@@ -6885,28 +6890,22 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
ug->nr_memory += nr_pages;
ug->pgpgout++;
- page->memcg_data = 0;
+ folio->memcg_data = 0;
}
css_put(&memcg->css);
}
-/**
- * __mem_cgroup_uncharge - uncharge a page
- * @page: page to uncharge
- *
- * Uncharge a page previously charged with __mem_cgroup_charge().
- */
-void __mem_cgroup_uncharge(struct page *page)
+void __mem_cgroup_uncharge(struct folio *folio)
{
struct uncharge_gather ug;
- /* Don't touch page->lru of any random page, pre-check: */
- if (!page_memcg(page))
+ /* Don't touch folio->lru of any random page, pre-check: */
+ if (!folio_memcg(folio))
return;
uncharge_gather_clear(&ug);
- uncharge_page(page, &ug);
+ uncharge_folio(folio, &ug);
uncharge_batch(&ug);
}
@@ -6920,52 +6919,49 @@ void __mem_cgroup_uncharge(struct page *page)
void __mem_cgroup_uncharge_list(struct list_head *page_list)
{
struct uncharge_gather ug;
- struct page *page;
+ struct folio *folio;
uncharge_gather_clear(&ug);
- list_for_each_entry(page, page_list, lru)
- uncharge_page(page, &ug);
+ list_for_each_entry(folio, page_list, lru)
+ uncharge_folio(folio, &ug);
if (ug.memcg)
uncharge_batch(&ug);
}
/**
- * mem_cgroup_migrate - charge a page's replacement
- * @oldpage: currently circulating page
- * @newpage: replacement page
+ * mem_cgroup_migrate - Charge a folio's replacement.
+ * @old: Currently circulating folio.
+ * @new: Replacement folio.
*
- * Charge @newpage as a replacement page for @oldpage. @oldpage will
+ * Charge @new as a replacement folio for @old. @old will
* be uncharged upon free.
*
- * Both pages must be locked, @newpage->mapping must be set up.
+ * Both folios must be locked, @new->mapping must be set up.
*/
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
+void mem_cgroup_migrate(struct folio *old, struct folio *new)
{
struct mem_cgroup *memcg;
- unsigned int nr_pages;
+ long nr_pages = folio_nr_pages(new);
unsigned long flags;
- VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
- VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
- VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
- VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage),
- newpage);
+ VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
+ VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
+ VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new);
+ VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new);
if (mem_cgroup_disabled())
return;
- /* Page cache replacement: new page already charged? */
- if (page_memcg(newpage))
+ /* Page cache replacement: new folio already charged? */
+ if (folio_memcg(new))
return;
- memcg = page_memcg(oldpage);
- VM_WARN_ON_ONCE_PAGE(!memcg, oldpage);
+ memcg = folio_memcg(old);
+ VM_WARN_ON_ONCE_FOLIO(!memcg, old);
if (!memcg)
return;
/* Force-charge the new page. The old one will be freed soon */
- nr_pages = thp_nr_pages(newpage);
-
if (!mem_cgroup_is_root(memcg)) {
page_counter_charge(&memcg->memory, nr_pages);
if (do_memsw_account())
@@ -6973,11 +6969,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
}
css_get(&memcg->css);
- commit_charge(newpage, memcg);
+ commit_charge(new, memcg);
local_irq_save(flags);
- mem_cgroup_charge_statistics(memcg, newpage, nr_pages);
- memcg_check_events(memcg, newpage);
+ mem_cgroup_charge_statistics(memcg, nr_pages);
+ memcg_check_events(memcg, folio_nid(new));
local_irq_restore(flags);
}
@@ -7204,8 +7200,8 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
* only synchronisation we have for updating the per-CPU variables.
*/
VM_BUG_ON(!irqs_disabled());
- mem_cgroup_charge_statistics(memcg, page, -nr_entries);
- memcg_check_events(memcg, page);
+ mem_cgroup_charge_statistics(memcg, -nr_entries);
+ memcg_check_events(memcg, page_to_nid(page));
css_put(&memcg->css);
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 3e6449f2102a..93078a2859a7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -762,7 +762,7 @@ static int delete_from_lru_cache(struct page *p)
* Poisoned page might never drop its ref count to 0 so we have
* to uncharge it manually from its memcg.
*/
- mem_cgroup_uncharge(p);
+ mem_cgroup_uncharge(page_folio(p));
/*
* drop the page count elevated by isolate_lru_page()
@@ -1147,20 +1147,6 @@ static int __get_hwpoison_page(struct page *page)
if (!HWPoisonHandlable(head))
return -EBUSY;
- if (PageTransHuge(head)) {
- /*
- * Non anonymous thp exists only in allocation/free time. We
- * can't handle such a case correctly, so let's give it up.
- * This should be better than triggering BUG_ON when kernel
- * tries to touch the "partially handled" page.
- */
- if (!PageAnon(head)) {
- pr_err("Memory failure: %#lx: non anonymous thp\n",
- page_to_pfn(page));
- return 0;
- }
- }
-
if (get_page_unless_zero(head)) {
if (head == compound_head(page))
return 1;
@@ -1708,6 +1694,20 @@ try_again:
}
if (PageTransHuge(hpage)) {
+ /*
+ * The flag must be set after the refcount is bumped
+ * otherwise it may race with THP split.
+ * And the flag can't be set in get_hwpoison_page() since
+ * it is called by soft offline too and it is just called
+ * for !MF_COUNT_INCREASE. So here seems to be the best
+ * place.
+ *
+ * Don't need care about the above error handling paths for
+ * get_hwpoison_page() since they handle either free page
+ * or unhandlable page. The refcount is bumped iff the
+ * page is a valid handlable page.
+ */
+ SetPageHasHWPoisoned(hpage);
if (try_to_split_thp_page(p, "Memory Failure") < 0) {
action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
res = -EBUSY;
diff --git a/mm/memory.c b/mm/memory.c
index adf9b9ef8277..4b1de80c2a9c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -990,7 +990,7 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
if (!new_page)
return NULL;
- if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) {
+ if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) {
put_page(new_page);
return NULL;
}
@@ -3019,7 +3019,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
}
}
- if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL))
goto oom_free_new;
cgroup_throttle_swaprate(new_page, GFP_KERNEL);
@@ -3539,7 +3539,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
- workingset_refault(page, shadow);
+ workingset_refault(page_folio(page),
+ shadow);
lru_cache_add(page);
@@ -3769,7 +3770,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
if (!page)
goto oom;
- if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
goto oom_free_page;
cgroup_throttle_swaprate(page, GFP_KERNEL);
@@ -3907,6 +3908,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
return ret;
/*
+ * Just backoff if any subpage of a THP is corrupted otherwise
+ * the corrupted page may mapped by PMD silently to escape the
+ * check. This kind of THP just can be PTE mapped. Access to
+ * the corrupted subpage should trigger SIGBUS as expected.
+ */
+ if (unlikely(PageHasHWPoisoned(page)))
+ return ret;
+
+ /*
* Archs like ppc64 need additional space to store information
* related to pte entry. Use the preallocated table for that.
*/
@@ -4193,7 +4203,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
if (!vmf->cow_page)
return VM_FAULT_OOM;
- if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) {
+ if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm,
+ GFP_KERNEL)) {
put_page(vmf->cow_page);
return VM_FAULT_OOM;
}
@@ -4258,7 +4269,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults).
* The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
+ * return value. See filemap_fault() and __folio_lock_or_retry().
* If mmap_lock is released, vma may become invalid (for example
* by other thread calling munmap()).
*/
@@ -4499,7 +4510,7 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
* concurrent faults).
*
* The mmap_lock may have been released depending on flags and our return value.
- * See filemap_fault() and __lock_page_or_retry().
+ * See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
{
@@ -4603,7 +4614,7 @@ unlock:
* By the time we get here, we already hold the mm semaphore
*
* The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
+ * return value. See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
@@ -4759,7 +4770,7 @@ static inline void mm_account_fault(struct pt_regs *regs,
* By the time we get here, we already hold the mm semaphore
*
* The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
+ * return value. See filemap_fault() and __folio_lock_or_retry().
*/
vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
unsigned int flags, struct pt_regs *regs)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d12e0608fced..f4b4be7af4d3 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2196,6 +2196,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
}
EXPORT_SYMBOL(alloc_pages);
+struct folio *folio_alloc(gfp_t gfp, unsigned order)
+{
+ struct page *page = alloc_pages(gfp | __GFP_COMP, order);
+
+ if (page && order > 1)
+ prep_transhuge_page(page);
+ return (struct folio *)page;
+}
+EXPORT_SYMBOL(folio_alloc);
+
int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
struct mempolicy *pol = mpol_dup(vma_policy(src));
diff --git a/mm/mempool.c b/mm/mempool.c
index 0b8afbec3e35..b933d0fc21b8 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -17,7 +17,6 @@
#include <linux/kmemleak.h>
#include <linux/export.h>
#include <linux/mempool.h>
-#include <linux/blkdev.h>
#include <linux/writeback.h>
#include "slab.h"
diff --git a/mm/memremap.c b/mm/memremap.c
index ed593bf87109..5a66a71ab591 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -505,7 +505,7 @@ void free_devmap_managed_page(struct page *page)
__ClearPageWaiters(page);
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
/*
* When a device_private page is freed, the page->mapping field
diff --git a/mm/migrate.c b/mm/migrate.c
index 1852d787e6ab..efa9941ebe03 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -364,7 +364,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
*/
expected_count += is_device_private_page(page);
if (mapping)
- expected_count += thp_nr_pages(page) + page_has_private(page);
+ expected_count += compound_nr(page) + page_has_private(page);
return expected_count;
}
@@ -377,74 +377,75 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
* 2 for pages with a mapping
* 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
*/
-int migrate_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page, int extra_count)
+int folio_migrate_mapping(struct address_space *mapping,
+ struct folio *newfolio, struct folio *folio, int extra_count)
{
- XA_STATE(xas, &mapping->i_pages, page_index(page));
+ XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct zone *oldzone, *newzone;
int dirty;
- int expected_count = expected_page_refs(mapping, page) + extra_count;
- int nr = thp_nr_pages(page);
+ int expected_count = expected_page_refs(mapping, &folio->page) + extra_count;
+ long nr = folio_nr_pages(folio);
if (!mapping) {
/* Anonymous page without mapping */
- if (page_count(page) != expected_count)
+ if (folio_ref_count(folio) != expected_count)
return -EAGAIN;
/* No turning back from here */
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- if (PageSwapBacked(page))
- __SetPageSwapBacked(newpage);
+ newfolio->index = folio->index;
+ newfolio->mapping = folio->mapping;
+ if (folio_test_swapbacked(folio))
+ __folio_set_swapbacked(newfolio);
return MIGRATEPAGE_SUCCESS;
}
- oldzone = page_zone(page);
- newzone = page_zone(newpage);
+ oldzone = folio_zone(folio);
+ newzone = folio_zone(newfolio);
xas_lock_irq(&xas);
- if (page_count(page) != expected_count || xas_load(&xas) != page) {
+ if (folio_ref_count(folio) != expected_count ||
+ xas_load(&xas) != folio) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
- if (!page_ref_freeze(page, expected_count)) {
+ if (!folio_ref_freeze(folio, expected_count)) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
/*
- * Now we know that no one else is looking at the page:
+ * Now we know that no one else is looking at the folio:
* no turning back from here.
*/
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- page_ref_add(newpage, nr); /* add cache reference */
- if (PageSwapBacked(page)) {
- __SetPageSwapBacked(newpage);
- if (PageSwapCache(page)) {
- SetPageSwapCache(newpage);
- set_page_private(newpage, page_private(page));
+ newfolio->index = folio->index;
+ newfolio->mapping = folio->mapping;
+ folio_ref_add(newfolio, nr); /* add cache reference */
+ if (folio_test_swapbacked(folio)) {
+ __folio_set_swapbacked(newfolio);
+ if (folio_test_swapcache(folio)) {
+ folio_set_swapcache(newfolio);
+ newfolio->private = folio_get_private(folio);
}
} else {
- VM_BUG_ON_PAGE(PageSwapCache(page), page);
+ VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
}
/* Move dirty while page refs frozen and newpage not yet exposed */
- dirty = PageDirty(page);
+ dirty = folio_test_dirty(folio);
if (dirty) {
- ClearPageDirty(page);
- SetPageDirty(newpage);
+ folio_clear_dirty(folio);
+ folio_set_dirty(newfolio);
}
- xas_store(&xas, newpage);
- if (PageTransHuge(page)) {
+ xas_store(&xas, newfolio);
+ if (nr > 1) {
int i;
for (i = 1; i < nr; i++) {
xas_next(&xas);
- xas_store(&xas, newpage);
+ xas_store(&xas, newfolio);
}
}
@@ -453,7 +454,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
* to one less reference.
* We know this isn't the last reference.
*/
- page_ref_unfreeze(page, expected_count - nr);
+ folio_ref_unfreeze(folio, expected_count - nr);
xas_unlock(&xas);
/* Leave irq disabled to prevent preemption while updating stats */
@@ -472,18 +473,18 @@ int migrate_page_move_mapping(struct address_space *mapping,
struct lruvec *old_lruvec, *new_lruvec;
struct mem_cgroup *memcg;
- memcg = page_memcg(page);
+ memcg = folio_memcg(folio);
old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);
__mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
__mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
- if (PageSwapBacked(page) && !PageSwapCache(page)) {
+ if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) {
__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
}
#ifdef CONFIG_SWAP
- if (PageSwapCache(page)) {
+ if (folio_test_swapcache(folio)) {
__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
}
@@ -499,11 +500,11 @@ int migrate_page_move_mapping(struct address_space *mapping,
return MIGRATEPAGE_SUCCESS;
}
-EXPORT_SYMBOL(migrate_page_move_mapping);
+EXPORT_SYMBOL(folio_migrate_mapping);
/*
* The expected number of remaining references is the same as that
- * of migrate_page_move_mapping().
+ * of folio_migrate_mapping().
*/
int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page)
@@ -538,91 +539,87 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
}
/*
- * Copy the page to its new location
+ * Copy the flags and some other ancillary information
*/
-void migrate_page_states(struct page *newpage, struct page *page)
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
{
int cpupid;
- if (PageError(page))
- SetPageError(newpage);
- if (PageReferenced(page))
- SetPageReferenced(newpage);
- if (PageUptodate(page))
- SetPageUptodate(newpage);
- if (TestClearPageActive(page)) {
- VM_BUG_ON_PAGE(PageUnevictable(page), page);
- SetPageActive(newpage);
- } else if (TestClearPageUnevictable(page))
- SetPageUnevictable(newpage);
- if (PageWorkingset(page))
- SetPageWorkingset(newpage);
- if (PageChecked(page))
- SetPageChecked(newpage);
- if (PageMappedToDisk(page))
- SetPageMappedToDisk(newpage);
-
- /* Move dirty on pages not done by migrate_page_move_mapping() */
- if (PageDirty(page))
- SetPageDirty(newpage);
-
- if (page_is_young(page))
- set_page_young(newpage);
- if (page_is_idle(page))
- set_page_idle(newpage);
+ if (folio_test_error(folio))
+ folio_set_error(newfolio);
+ if (folio_test_referenced(folio))
+ folio_set_referenced(newfolio);
+ if (folio_test_uptodate(folio))
+ folio_mark_uptodate(newfolio);
+ if (folio_test_clear_active(folio)) {
+ VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio);
+ folio_set_active(newfolio);
+ } else if (folio_test_clear_unevictable(folio))
+ folio_set_unevictable(newfolio);
+ if (folio_test_workingset(folio))
+ folio_set_workingset(newfolio);
+ if (folio_test_checked(folio))
+ folio_set_checked(newfolio);
+ if (folio_test_mappedtodisk(folio))
+ folio_set_mappedtodisk(newfolio);
+
+ /* Move dirty on pages not done by folio_migrate_mapping() */
+ if (folio_test_dirty(folio))
+ folio_set_dirty(newfolio);
+
+ if (folio_test_young(folio))
+ folio_set_young(newfolio);
+ if (folio_test_idle(folio))
+ folio_set_idle(newfolio);
/*
* Copy NUMA information to the new page, to prevent over-eager
* future migrations of this same page.
*/
- cpupid = page_cpupid_xchg_last(page, -1);
- page_cpupid_xchg_last(newpage, cpupid);
+ cpupid = page_cpupid_xchg_last(&folio->page, -1);
+ page_cpupid_xchg_last(&newfolio->page, cpupid);
- ksm_migrate_page(newpage, page);
+ folio_migrate_ksm(newfolio, folio);
/*
* Please do not reorder this without considering how mm/ksm.c's
* get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
*/
- if (PageSwapCache(page))
- ClearPageSwapCache(page);
- ClearPagePrivate(page);
+ if (folio_test_swapcache(folio))
+ folio_clear_swapcache(folio);
+ folio_clear_private(folio);
/* page->private contains hugetlb specific flags */
- if (!PageHuge(page))
- set_page_private(page, 0);
+ if (!folio_test_hugetlb(folio))
+ folio->private = NULL;
/*
* If any waiters have accumulated on the new page then
* wake them up.
*/
- if (PageWriteback(newpage))
- end_page_writeback(newpage);
+ if (folio_test_writeback(newfolio))
+ folio_end_writeback(newfolio);
/*
* PG_readahead shares the same bit with PG_reclaim. The above
* end_page_writeback() may clear PG_readahead mistakenly, so set the
* bit after that.
*/
- if (PageReadahead(page))
- SetPageReadahead(newpage);
+ if (folio_test_readahead(folio))
+ folio_set_readahead(newfolio);
- copy_page_owner(page, newpage);
+ folio_copy_owner(newfolio, folio);
- if (!PageHuge(page))
- mem_cgroup_migrate(page, newpage);
+ if (!folio_test_hugetlb(folio))
+ mem_cgroup_migrate(folio, newfolio);
}
-EXPORT_SYMBOL(migrate_page_states);
+EXPORT_SYMBOL(folio_migrate_flags);
-void migrate_page_copy(struct page *newpage, struct page *page)
+void folio_migrate_copy(struct folio *newfolio, struct folio *folio)
{
- if (PageHuge(page) || PageTransHuge(page))
- copy_huge_page(newpage, page);
- else
- copy_highpage(newpage, page);
-
- migrate_page_states(newpage, page);
+ folio_copy(newfolio, folio);
+ folio_migrate_flags(newfolio, folio);
}
-EXPORT_SYMBOL(migrate_page_copy);
+EXPORT_SYMBOL(folio_migrate_copy);
/************************************************************
* Migration functions
@@ -638,19 +635,21 @@ int migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
+ struct folio *newfolio = page_folio(newpage);
+ struct folio *folio = page_folio(page);
int rc;
- BUG_ON(PageWriteback(page)); /* Writeback must be complete */
+ BUG_ON(folio_test_writeback(folio)); /* Writeback must be complete */
- rc = migrate_page_move_mapping(mapping, newpage, page, 0);
+ rc = folio_migrate_mapping(mapping, newfolio, folio, 0);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
+ folio_migrate_copy(newfolio, folio);
else
- migrate_page_states(newpage, page);
+ folio_migrate_flags(newfolio, folio);
return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(migrate_page);
@@ -2468,7 +2467,7 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
* @page: struct page to check
*
* Pinned pages cannot be migrated. This is the same test as in
- * migrate_page_move_mapping(), except that here we allow migration of a
+ * folio_migrate_mapping(), except that here we allow migration of a
* ZONE_DEVICE page.
*/
static bool migrate_vma_check_page(struct page *page)
@@ -2846,7 +2845,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
if (unlikely(anon_vma_prepare(vma)))
goto abort;
- if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
goto abort;
/*
diff --git a/mm/mlock.c b/mm/mlock.c
index 16d2ee160d43..e263d62ae2d0 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -271,6 +271,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
/* Phase 1: page isolation */
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(page);
if (TestClearPageMlocked(page)) {
/*
@@ -278,7 +279,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
* so we can spare the get_page() here.
*/
if (TestClearPageLRU(page)) {
- lruvec = relock_page_lruvec_irq(page, lruvec);
+ lruvec = folio_lruvec_relock_irq(folio, lruvec);
del_page_from_lru_list(page, lruvec);
continue;
} else
diff --git a/mm/nommu.c b/mm/nommu.c
index 02d2427b8f9e..41ef204e7482 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -27,7 +27,6 @@
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
-#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/compiler.h>
#include <linux/mount.h>
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 831340e7ad8b..989f35a2bbb1 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -1150,7 +1150,7 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
struct task_struct *task;
struct task_struct *p;
unsigned int f_flags;
- bool reap = true;
+ bool reap = false;
struct pid *pid;
long ret = 0;
@@ -1177,15 +1177,15 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
goto put_task;
}
- mm = p->mm;
- mmgrab(mm);
-
- /* If the work has been done already, just exit with success */
- if (test_bit(MMF_OOM_SKIP, &mm->flags))
- reap = false;
- else if (!task_will_free_mem(p)) {
- reap = false;
- ret = -EINVAL;
+ if (mmget_not_zero(p->mm)) {
+ mm = p->mm;
+ if (task_will_free_mem(p))
+ reap = true;
+ else {
+ /* Error only if the work has not been done already */
+ if (!test_bit(MMF_OOM_SKIP, &mm->flags))
+ ret = -EINVAL;
+ }
}
task_unlock(p);
@@ -1201,7 +1201,8 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
mmap_read_unlock(mm);
drop_mm:
- mmdrop(mm);
+ if (mm)
+ mmput(mm);
put_task:
put_task_struct(task);
put_pid:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4812a17b288c..9c64490171e0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -562,12 +562,12 @@ static unsigned long wp_next_time(unsigned long cur_time)
return cur_time;
}
-static void wb_domain_writeout_inc(struct wb_domain *dom,
+static void wb_domain_writeout_add(struct wb_domain *dom,
struct fprop_local_percpu *completions,
- unsigned int max_prop_frac)
+ unsigned int max_prop_frac, long nr)
{
- __fprop_inc_percpu_max(&dom->completions, completions,
- max_prop_frac);
+ __fprop_add_percpu_max(&dom->completions, completions,
+ max_prop_frac, nr);
/* First event after period switching was turned off? */
if (unlikely(!dom->period_time)) {
/*
@@ -583,20 +583,20 @@ static void wb_domain_writeout_inc(struct wb_domain *dom,
/*
* Increment @wb's writeout completion count and the global writeout
- * completion count. Called from test_clear_page_writeback().
+ * completion count. Called from __folio_end_writeback().
*/
-static inline void __wb_writeout_inc(struct bdi_writeback *wb)
+static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr)
{
struct wb_domain *cgdom;
- inc_wb_stat(wb, WB_WRITTEN);
- wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
- wb->bdi->max_prop_frac);
+ wb_stat_mod(wb, WB_WRITTEN, nr);
+ wb_domain_writeout_add(&global_wb_domain, &wb->completions,
+ wb->bdi->max_prop_frac, nr);
cgdom = mem_cgroup_wb_domain(wb);
if (cgdom)
- wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb),
- wb->bdi->max_prop_frac);
+ wb_domain_writeout_add(cgdom, wb_memcg_completions(wb),
+ wb->bdi->max_prop_frac, nr);
}
void wb_writeout_inc(struct bdi_writeback *wb)
@@ -604,7 +604,7 @@ void wb_writeout_inc(struct bdi_writeback *wb)
unsigned long flags;
local_irq_save(flags);
- __wb_writeout_inc(wb);
+ __wb_writeout_add(wb, 1);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(wb_writeout_inc);
@@ -1084,7 +1084,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb,
* write_bandwidth = ---------------------------------------------------
* period
*
- * @written may have decreased due to account_page_redirty().
+ * @written may have decreased due to folio_account_redirty().
* Avoid underflowing @bw calculation.
*/
bw = written - min(written, wb->written_stamp);
@@ -2381,44 +2381,44 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
}
/**
- * write_one_page - write out a single page and wait on I/O
- * @page: the page to write
+ * folio_write_one - write out a single folio and wait on I/O.
+ * @folio: The folio to write.
*
- * The page must be locked by the caller and will be unlocked upon return.
+ * The folio must be locked by the caller and will be unlocked upon return.
*
* Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this
* function returns.
*
* Return: %0 on success, negative error code otherwise
*/
-int write_one_page(struct page *page)
+int folio_write_one(struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
- .nr_to_write = 1,
+ .nr_to_write = folio_nr_pages(folio),
};
- BUG_ON(!PageLocked(page));
+ BUG_ON(!folio_test_locked(folio));
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
- if (clear_page_dirty_for_io(page)) {
- get_page(page);
- ret = mapping->a_ops->writepage(page, &wbc);
+ if (folio_clear_dirty_for_io(folio)) {
+ folio_get(folio);
+ ret = mapping->a_ops->writepage(&folio->page, &wbc);
if (ret == 0)
- wait_on_page_writeback(page);
- put_page(page);
+ folio_wait_writeback(folio);
+ folio_put(folio);
} else {
- unlock_page(page);
+ folio_unlock(folio);
}
if (!ret)
ret = filemap_check_errors(mapping);
return ret;
}
-EXPORT_SYMBOL(write_one_page);
+EXPORT_SYMBOL(folio_write_one);
/*
* For address_spaces which do not use buffers nor write back.
@@ -2438,29 +2438,30 @@ EXPORT_SYMBOL(__set_page_dirty_no_writeback);
*
* NOTE: This relies on being atomic wrt interrupts.
*/
-static void account_page_dirtied(struct page *page,
+static void folio_account_dirtied(struct folio *folio,
struct address_space *mapping)
{
struct inode *inode = mapping->host;
- trace_writeback_dirty_page(page, mapping);
+ trace_writeback_dirty_folio(folio, mapping);
if (mapping_can_writeback(mapping)) {
struct bdi_writeback *wb;
+ long nr = folio_nr_pages(folio);
- inode_attach_wb(inode, page);
+ inode_attach_wb(inode, &folio->page);
wb = inode_to_wb(inode);
- __inc_lruvec_page_state(page, NR_FILE_DIRTY);
- __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- __inc_node_page_state(page, NR_DIRTIED);
- inc_wb_stat(wb, WB_RECLAIMABLE);
- inc_wb_stat(wb, WB_DIRTIED);
- task_io_account_write(PAGE_SIZE);
- current->nr_dirtied++;
- __this_cpu_inc(bdp_ratelimits);
+ __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr);
+ __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
+ __node_stat_mod_folio(folio, NR_DIRTIED, nr);
+ wb_stat_mod(wb, WB_RECLAIMABLE, nr);
+ wb_stat_mod(wb, WB_DIRTIED, nr);
+ task_io_account_write(nr * PAGE_SIZE);
+ current->nr_dirtied += nr;
+ __this_cpu_add(bdp_ratelimits, nr);
- mem_cgroup_track_foreign_dirty(page, wb);
+ mem_cgroup_track_foreign_dirty(folio, wb);
}
}
@@ -2469,130 +2470,152 @@ static void account_page_dirtied(struct page *page,
*
* Caller must hold lock_page_memcg().
*/
-void account_page_cleaned(struct page *page, struct address_space *mapping,
+void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
struct bdi_writeback *wb)
{
if (mapping_can_writeback(mapping)) {
- dec_lruvec_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- dec_wb_stat(wb, WB_RECLAIMABLE);
- task_io_account_cancelled_write(PAGE_SIZE);
+ long nr = folio_nr_pages(folio);
+ lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+ wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
+ task_io_account_cancelled_write(nr * PAGE_SIZE);
}
}
/*
- * Mark the page dirty, and set it dirty in the page cache, and mark the inode
- * dirty.
+ * Mark the folio dirty, and set it dirty in the page cache, and mark
+ * the inode dirty.
*
- * If warn is true, then emit a warning if the page is not uptodate and has
+ * If warn is true, then emit a warning if the folio is not uptodate and has
* not been truncated.
*
* The caller must hold lock_page_memcg().
*/
-void __set_page_dirty(struct page *page, struct address_space *mapping,
+void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
int warn)
{
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
- if (page->mapping) { /* Race with truncate? */
- WARN_ON_ONCE(warn && !PageUptodate(page));
- account_page_dirtied(page, mapping);
- __xa_set_mark(&mapping->i_pages, page_index(page),
+ if (folio->mapping) { /* Race with truncate? */
+ WARN_ON_ONCE(warn && !folio_test_uptodate(folio));
+ folio_account_dirtied(folio, mapping);
+ __xa_set_mark(&mapping->i_pages, folio_index(folio),
PAGECACHE_TAG_DIRTY);
}
xa_unlock_irqrestore(&mapping->i_pages, flags);
}
-/*
- * For address_spaces which do not use buffers. Just tag the page as dirty in
- * the xarray.
+/**
+ * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads.
+ * @mapping: Address space this folio belongs to.
+ * @folio: Folio to be marked as dirty.
+ *
+ * Filesystems which do not use buffer heads should call this function
+ * from their set_page_dirty address space operation. It ignores the
+ * contents of folio_get_private(), so if the filesystem marks individual
+ * blocks as dirty, the filesystem should handle that itself.
*
- * This is also used when a single buffer is being dirtied: we want to set the
- * page dirty in that case, but not all the buffers. This is a "bottom-up"
- * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
+ * This is also sometimes used by filesystems which use buffer_heads when
+ * a single buffer is being dirtied: we want to set the folio dirty in
+ * that case, but not all the buffers. This is a "bottom-up" dirtying,
+ * whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
- * The caller must ensure this doesn't race with truncation. Most will simply
- * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
- * the pte lock held, which also locks out truncation.
+ * The caller must ensure this doesn't race with truncation. Most will
+ * simply hold the folio lock, but e.g. zap_pte_range() calls with the
+ * folio mapped and the pte lock held, which also locks out truncation.
*/
-int __set_page_dirty_nobuffers(struct page *page)
+bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
{
- lock_page_memcg(page);
- if (!TestSetPageDirty(page)) {
- struct address_space *mapping = page_mapping(page);
+ folio_memcg_lock(folio);
+ if (folio_test_set_dirty(folio)) {
+ folio_memcg_unlock(folio);
+ return false;
+ }
- if (!mapping) {
- unlock_page_memcg(page);
- return 1;
- }
- __set_page_dirty(page, mapping, !PagePrivate(page));
- unlock_page_memcg(page);
+ __folio_mark_dirty(folio, mapping, !folio_test_private(folio));
+ folio_memcg_unlock(folio);
- if (mapping->host) {
- /* !PageAnon && !swapper_space */
- __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- }
- return 1;
+ if (mapping->host) {
+ /* !PageAnon && !swapper_space */
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
- unlock_page_memcg(page);
- return 0;
+ return true;
}
-EXPORT_SYMBOL(__set_page_dirty_nobuffers);
+EXPORT_SYMBOL(filemap_dirty_folio);
-/*
- * Call this whenever redirtying a page, to de-account the dirty counters
- * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written
- * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to
- * systematic errors in balanced_dirty_ratelimit and the dirty pages position
- * control.
+/**
+ * folio_account_redirty - Manually account for redirtying a page.
+ * @folio: The folio which is being redirtied.
+ *
+ * Most filesystems should call folio_redirty_for_writepage() instead
+ * of this fuction. If your filesystem is doing writeback outside the
+ * context of a writeback_control(), it can call this when redirtying
+ * a folio, to de-account the dirty counters (NR_DIRTIED, WB_DIRTIED,
+ * tsk->nr_dirtied), so that they match the written counters (NR_WRITTEN,
+ * WB_WRITTEN) in long term. The mismatches will lead to systematic errors
+ * in balanced_dirty_ratelimit and the dirty pages position control.
*/
-void account_page_redirty(struct page *page)
+void folio_account_redirty(struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
if (mapping && mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
+ long nr = folio_nr_pages(folio);
wb = unlocked_inode_to_wb_begin(inode, &cookie);
- current->nr_dirtied--;
- dec_node_page_state(page, NR_DIRTIED);
- dec_wb_stat(wb, WB_DIRTIED);
+ current->nr_dirtied -= nr;
+ node_stat_mod_folio(folio, NR_DIRTIED, -nr);
+ wb_stat_mod(wb, WB_DIRTIED, -nr);
unlocked_inode_to_wb_end(inode, &cookie);
}
}
-EXPORT_SYMBOL(account_page_redirty);
+EXPORT_SYMBOL(folio_account_redirty);
-/*
- * When a writepage implementation decides that it doesn't want to write this
- * page for some reason, it should redirty the locked page via
- * redirty_page_for_writepage() and it should then unlock the page and return 0
+/**
+ * folio_redirty_for_writepage - Decline to write a dirty folio.
+ * @wbc: The writeback control.
+ * @folio: The folio.
+ *
+ * When a writepage implementation decides that it doesn't want to write
+ * @folio for some reason, it should call this function, unlock @folio and
+ * return 0.
+ *
+ * Return: True if we redirtied the folio. False if someone else dirtied
+ * it first.
*/
-int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
+bool folio_redirty_for_writepage(struct writeback_control *wbc,
+ struct folio *folio)
{
- int ret;
+ bool ret;
+ long nr = folio_nr_pages(folio);
+
+ wbc->pages_skipped += nr;
+ ret = filemap_dirty_folio(folio->mapping, folio);
+ folio_account_redirty(folio);
- wbc->pages_skipped++;
- ret = __set_page_dirty_nobuffers(page);
- account_page_redirty(page);
return ret;
}
-EXPORT_SYMBOL(redirty_page_for_writepage);
+EXPORT_SYMBOL(folio_redirty_for_writepage);
-/*
- * Dirty a page.
+/**
+ * folio_mark_dirty - Mark a folio as being modified.
+ * @folio: The folio.
*
- * For pages with a mapping this should be done under the page lock for the
- * benefit of asynchronous memory errors who prefer a consistent dirty state.
- * This rule can be broken in some special cases, but should be better not to.
+ * For folios with a mapping this should be done under the page lock
+ * for the benefit of asynchronous memory errors who prefer a consistent
+ * dirty state. This rule can be broken in some special cases,
+ * but should be better not to.
+ *
+ * Return: True if the folio was newly dirtied, false if it was already dirty.
*/
-int set_page_dirty(struct page *page)
+bool folio_mark_dirty(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio_mapping(folio);
- page = compound_head(page);
if (likely(mapping)) {
/*
* readahead/lru_deactivate_page could remain
@@ -2604,17 +2627,17 @@ int set_page_dirty(struct page *page)
* it will confuse readahead and make it restart the size rampup
* process. But it's a trivial problem.
*/
- if (PageReclaim(page))
- ClearPageReclaim(page);
- return mapping->a_ops->set_page_dirty(page);
+ if (folio_test_reclaim(folio))
+ folio_clear_reclaim(folio);
+ return mapping->a_ops->set_page_dirty(&folio->page);
}
- if (!PageDirty(page)) {
- if (!TestSetPageDirty(page))
- return 1;
+ if (!folio_test_dirty(folio)) {
+ if (!folio_test_set_dirty(folio))
+ return true;
}
- return 0;
+ return false;
}
-EXPORT_SYMBOL(set_page_dirty);
+EXPORT_SYMBOL(folio_mark_dirty);
/*
* set_page_dirty() is racy if the caller has no reference against
@@ -2650,49 +2673,49 @@ EXPORT_SYMBOL(set_page_dirty_lock);
* page without actually doing it through the VM. Can you say "ext3 is
* horribly ugly"? Thought you could.
*/
-void __cancel_dirty_page(struct page *page)
+void __folio_cancel_dirty(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio_mapping(folio);
if (mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
wb = unlocked_inode_to_wb_begin(inode, &cookie);
- if (TestClearPageDirty(page))
- account_page_cleaned(page, mapping, wb);
+ if (folio_test_clear_dirty(folio))
+ folio_account_cleaned(folio, mapping, wb);
unlocked_inode_to_wb_end(inode, &cookie);
- unlock_page_memcg(page);
+ folio_memcg_unlock(folio);
} else {
- ClearPageDirty(page);
+ folio_clear_dirty(folio);
}
}
-EXPORT_SYMBOL(__cancel_dirty_page);
+EXPORT_SYMBOL(__folio_cancel_dirty);
/*
- * Clear a page's dirty flag, while caring for dirty memory accounting.
- * Returns true if the page was previously dirty.
- *
- * This is for preparing to put the page under writeout. We leave the page
- * tagged as dirty in the xarray so that a concurrent write-for-sync
- * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
- * implementation will run either set_page_writeback() or set_page_dirty(),
- * at which stage we bring the page's dirty flag and xarray dirty tag
- * back into sync.
- *
- * This incoherency between the page's dirty flag and xarray tag is
- * unfortunate, but it only exists while the page is locked.
+ * Clear a folio's dirty flag, while caring for dirty memory accounting.
+ * Returns true if the folio was previously dirty.
+ *
+ * This is for preparing to put the folio under writeout. We leave
+ * the folio tagged as dirty in the xarray so that a concurrent
+ * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk.
+ * The ->writepage implementation will run either folio_start_writeback()
+ * or folio_mark_dirty(), at which stage we bring the folio's dirty flag
+ * and xarray dirty tag back into sync.
+ *
+ * This incoherency between the folio's dirty flag and xarray tag is
+ * unfortunate, but it only exists while the folio is locked.
*/
-int clear_page_dirty_for_io(struct page *page)
+bool folio_clear_dirty_for_io(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
- int ret = 0;
+ struct address_space *mapping = folio_mapping(folio);
+ bool ret = false;
- VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (mapping && mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
@@ -2705,48 +2728,49 @@ int clear_page_dirty_for_io(struct page *page)
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
- * mark the whole page dirty if it was
+ * mark the whole folio dirty if it was
* dirty in a pagetable. Only to then
- * (c) clean the page again and return 1 to
+ * (c) clean the folio again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
- * Note! Normally the "set_page_dirty(page)"
+ * Note! Normally the "folio_mark_dirty(folio)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
- * We basically use the page "master dirty bit"
+ * We basically use the folio "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
- if (page_mkclean(page))
- set_page_dirty(page);
+ if (folio_mkclean(folio))
+ folio_mark_dirty(folio);
/*
* We carefully synchronise fault handlers against
- * installing a dirty pte and marking the page dirty
+ * installing a dirty pte and marking the folio dirty
* at this point. We do this by having them hold the
- * page lock while dirtying the page, and pages are
+ * page lock while dirtying the folio, and folios are
* always locked coming in here, so we get the desired
* exclusion.
*/
wb = unlocked_inode_to_wb_begin(inode, &cookie);
- if (TestClearPageDirty(page)) {
- dec_lruvec_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- dec_wb_stat(wb, WB_RECLAIMABLE);
- ret = 1;
+ if (folio_test_clear_dirty(folio)) {
+ long nr = folio_nr_pages(folio);
+ lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+ wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
+ ret = true;
}
unlocked_inode_to_wb_end(inode, &cookie);
return ret;
}
- return TestClearPageDirty(page);
+ return folio_test_clear_dirty(folio);
}
-EXPORT_SYMBOL(clear_page_dirty_for_io);
+EXPORT_SYMBOL(folio_clear_dirty_for_io);
static void wb_inode_writeback_start(struct bdi_writeback *wb)
{
@@ -2766,27 +2790,28 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb)
queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
}
-int test_clear_page_writeback(struct page *page)
+bool __folio_end_writeback(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
- int ret;
+ long nr = folio_nr_pages(folio);
+ struct address_space *mapping = folio_mapping(folio);
+ bool ret;
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
if (mapping && mapping_use_writeback_tags(mapping)) {
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
- ret = TestClearPageWriteback(page);
+ ret = folio_test_clear_writeback(folio);
if (ret) {
- __xa_clear_mark(&mapping->i_pages, page_index(page),
+ __xa_clear_mark(&mapping->i_pages, folio_index(folio),
PAGECACHE_TAG_WRITEBACK);
if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
struct bdi_writeback *wb = inode_to_wb(inode);
- dec_wb_stat(wb, WB_WRITEBACK);
- __wb_writeout_inc(wb);
+ wb_stat_mod(wb, WB_WRITEBACK, -nr);
+ __wb_writeout_add(wb, nr);
if (!mapping_tagged(mapping,
PAGECACHE_TAG_WRITEBACK))
wb_inode_writeback_end(wb);
@@ -2799,32 +2824,34 @@ int test_clear_page_writeback(struct page *page)
xa_unlock_irqrestore(&mapping->i_pages, flags);
} else {
- ret = TestClearPageWriteback(page);
+ ret = folio_test_clear_writeback(folio);
}
if (ret) {
- dec_lruvec_page_state(page, NR_WRITEBACK);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- inc_node_page_state(page, NR_WRITTEN);
+ lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+ node_stat_mod_folio(folio, NR_WRITTEN, nr);
}
- unlock_page_memcg(page);
+ folio_memcg_unlock(folio);
return ret;
}
-int __test_set_page_writeback(struct page *page, bool keep_write)
+bool __folio_start_writeback(struct folio *folio, bool keep_write)
{
- struct address_space *mapping = page_mapping(page);
- int ret, access_ret;
+ long nr = folio_nr_pages(folio);
+ struct address_space *mapping = folio_mapping(folio);
+ bool ret;
+ int access_ret;
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
if (mapping && mapping_use_writeback_tags(mapping)) {
- XA_STATE(xas, &mapping->i_pages, page_index(page));
+ XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
xas_lock_irqsave(&xas, flags);
xas_load(&xas);
- ret = TestSetPageWriteback(page);
+ ret = folio_test_set_writeback(folio);
if (!ret) {
bool on_wblist;
@@ -2835,84 +2862,105 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
struct bdi_writeback *wb = inode_to_wb(inode);
- inc_wb_stat(wb, WB_WRITEBACK);
+ wb_stat_mod(wb, WB_WRITEBACK, nr);
if (!on_wblist)
wb_inode_writeback_start(wb);
}
/*
- * We can come through here when swapping anonymous
- * pages, so we don't necessarily have an inode to track
- * for sync.
+ * We can come through here when swapping
+ * anonymous folios, so we don't necessarily
+ * have an inode to track for sync.
*/
if (mapping->host && !on_wblist)
sb_mark_inode_writeback(mapping->host);
}
- if (!PageDirty(page))
+ if (!folio_test_dirty(folio))
xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
if (!keep_write)
xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
xas_unlock_irqrestore(&xas, flags);
} else {
- ret = TestSetPageWriteback(page);
+ ret = folio_test_set_writeback(folio);
}
if (!ret) {
- inc_lruvec_page_state(page, NR_WRITEBACK);
- inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
+ lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
}
- unlock_page_memcg(page);
- access_ret = arch_make_page_accessible(page);
+ folio_memcg_unlock(folio);
+ access_ret = arch_make_folio_accessible(folio);
/*
* If writeback has been triggered on a page that cannot be made
* accessible, it is too late to recover here.
*/
- VM_BUG_ON_PAGE(access_ret != 0, page);
+ VM_BUG_ON_FOLIO(access_ret != 0, folio);
return ret;
-
}
-EXPORT_SYMBOL(__test_set_page_writeback);
+EXPORT_SYMBOL(__folio_start_writeback);
-/*
- * Wait for a page to complete writeback
+/**
+ * folio_wait_writeback - Wait for a folio to finish writeback.
+ * @folio: The folio to wait for.
+ *
+ * If the folio is currently being written back to storage, wait for the
+ * I/O to complete.
+ *
+ * Context: Sleeps. Must be called in process context and with
+ * no spinlocks held. Caller should hold a reference on the folio.
+ * If the folio is not locked, writeback may start again after writeback
+ * has finished.
*/
-void wait_on_page_writeback(struct page *page)
+void folio_wait_writeback(struct folio *folio)
{
- while (PageWriteback(page)) {
- trace_wait_on_page_writeback(page, page_mapping(page));
- wait_on_page_bit(page, PG_writeback);
+ while (folio_test_writeback(folio)) {
+ trace_folio_wait_writeback(folio, folio_mapping(folio));
+ folio_wait_bit(folio, PG_writeback);
}
}
-EXPORT_SYMBOL_GPL(wait_on_page_writeback);
+EXPORT_SYMBOL_GPL(folio_wait_writeback);
-/*
- * Wait for a page to complete writeback. Returns -EINTR if we get a
- * fatal signal while waiting.
+/**
+ * folio_wait_writeback_killable - Wait for a folio to finish writeback.
+ * @folio: The folio to wait for.
+ *
+ * If the folio is currently being written back to storage, wait for the
+ * I/O to complete or a fatal signal to arrive.
+ *
+ * Context: Sleeps. Must be called in process context and with
+ * no spinlocks held. Caller should hold a reference on the folio.
+ * If the folio is not locked, writeback may start again after writeback
+ * has finished.
+ * Return: 0 on success, -EINTR if we get a fatal signal while waiting.
*/
-int wait_on_page_writeback_killable(struct page *page)
+int folio_wait_writeback_killable(struct folio *folio)
{
- while (PageWriteback(page)) {
- trace_wait_on_page_writeback(page, page_mapping(page));
- if (wait_on_page_bit_killable(page, PG_writeback))
+ while (folio_test_writeback(folio)) {
+ trace_folio_wait_writeback(folio, folio_mapping(folio));
+ if (folio_wait_bit_killable(folio, PG_writeback))
return -EINTR;
}
return 0;
}
-EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable);
+EXPORT_SYMBOL_GPL(folio_wait_writeback_killable);
/**
- * wait_for_stable_page() - wait for writeback to finish, if necessary.
- * @page: The page to wait on.
+ * folio_wait_stable() - wait for writeback to finish, if necessary.
+ * @folio: The folio to wait on.
+ *
+ * This function determines if the given folio is related to a backing
+ * device that requires folio contents to be held stable during writeback.
+ * If so, then it will wait for any pending writeback to complete.
*
- * This function determines if the given page is related to a backing device
- * that requires page contents to be held stable during writeback. If so, then
- * it will wait for any pending writeback to complete.
+ * Context: Sleeps. Must be called in process context and with
+ * no spinlocks held. Caller should hold a reference on the folio.
+ * If the folio is not locked, writeback may start again after writeback
+ * has finished.
*/
-void wait_for_stable_page(struct page *page)
+void folio_wait_stable(struct folio *folio)
{
- page = thp_head(page);
- if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
- wait_on_page_writeback(page);
+ if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
+ folio_wait_writeback(folio);
}
-EXPORT_SYMBOL_GPL(wait_for_stable_page);
+EXPORT_SYMBOL_GPL(folio_wait_stable);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b37435c274cf..fee18ada46a2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -724,7 +724,7 @@ static inline void free_the_page(struct page *page, unsigned int order)
void free_compound_page(struct page *page)
{
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
free_the_page(page, compound_order(page));
}
@@ -1312,8 +1312,10 @@ static __always_inline bool free_pages_prepare(struct page *page,
VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
- if (compound)
+ if (compound) {
ClearPageDoubleMap(page);
+ ClearPageHasHWPoisoned(page);
+ }
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
@@ -5223,6 +5225,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
if (unlikely(page_array && nr_pages - nr_populated == 0))
goto out;
+ /* Bulk allocator does not support memcg accounting. */
+ if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT))
+ goto failed;
+
/* Use the single page allocator for one page. */
if (nr_pages - nr_populated == 1)
goto failed;
@@ -5400,6 +5406,18 @@ out:
}
EXPORT_SYMBOL(__alloc_pages);
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+ nodemask_t *nodemask)
+{
+ struct page *page = __alloc_pages(gfp | __GFP_COMP, order,
+ preferred_nid, nodemask);
+
+ if (page && order > 1)
+ prep_transhuge_page(page);
+ return (struct folio *)page;
+}
+EXPORT_SYMBOL(__folio_alloc);
+
/*
* Common helper functions. Never use with __GFP_HIGHMEM because the returned
* address cannot represent highmem pages. Use alloc_pages and then kmap if
diff --git a/mm/page_io.c b/mm/page_io.c
index c493ce9ebcf5..9725c7e1eeea 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -38,7 +38,7 @@ void end_swap_bio_write(struct bio *bio)
* Also print a dire warning that things will go BAD (tm)
* very quickly.
*
- * Also clear PG_reclaim to avoid rotate_reclaimable_page()
+ * Also clear PG_reclaim to avoid folio_rotate_reclaimable()
*/
set_page_dirty(page);
pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
@@ -317,7 +317,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
* temporary failure if the system has limited
* memory for allocating transmit buffers.
* Mark the page dirty and avoid
- * rotate_reclaimable_page but rate-limit the
+ * folio_rotate_reclaimable but rate-limit the
* messages but do not flag PageError like
* the normal direct-to-bio case as it could
* be temporary.
@@ -358,8 +358,6 @@ int swap_readpage(struct page *page, bool synchronous)
struct bio *bio;
int ret = 0;
struct swap_info_struct *sis = page_swap_info(page);
- blk_qc_t qc;
- struct gendisk *disk;
unsigned long pflags;
VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
@@ -409,26 +407,24 @@ int swap_readpage(struct page *page, bool synchronous)
bio->bi_iter.bi_sector = swap_page_sector(page);
bio->bi_end_io = end_swap_bio_read;
bio_add_page(bio, page, thp_size(page), 0);
-
- disk = bio->bi_bdev->bd_disk;
/*
* Keep this task valid during swap readpage because the oom killer may
* attempt to access it in the page fault retry time check.
*/
if (synchronous) {
- bio->bi_opf |= REQ_HIPRI;
+ bio->bi_opf |= REQ_POLLED;
get_task_struct(current);
bio->bi_private = current;
}
count_vm_event(PSWPIN);
bio_get(bio);
- qc = submit_bio(bio);
+ submit_bio(bio);
while (synchronous) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio->bi_private))
break;
- if (!blk_poll(disk->queue, qc, true))
+ if (!bio_poll(bio, NULL, 0))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 62402d22539b..d24ed221357c 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -210,10 +210,10 @@ void __split_page_owner(struct page *page, unsigned int nr)
}
}
-void __copy_page_owner(struct page *oldpage, struct page *newpage)
+void __folio_copy_owner(struct folio *newfolio, struct folio *old)
{
- struct page_ext *old_ext = lookup_page_ext(oldpage);
- struct page_ext *new_ext = lookup_page_ext(newpage);
+ struct page_ext *old_ext = lookup_page_ext(&old->page);
+ struct page_ext *new_ext = lookup_page_ext(&newfolio->page);
struct page_owner *old_page_owner, *new_page_owner;
if (unlikely(!old_ext || !new_ext))
@@ -231,11 +231,11 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
/*
- * We don't clear the bit on the oldpage as it's going to be freed
+ * We don't clear the bit on the old folio as it's going to be freed
* after migration. Until then, the info can be useful in case of
* a bug, and the overall stats will be off a bit only temporarily.
* Also, migrate_misplaced_transhuge_page() can still fail the
- * migration and then we want the oldpage to retain the info. But
+ * migration and then we want the old folio to retain the info. But
* in that case we also don't need to explicitly clear the info from
* the new page, which will be freed.
*/
diff --git a/mm/readahead.c b/mm/readahead.c
index 41b75d76d36e..e71e719e36c9 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -12,7 +12,6 @@
#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/export.h>
-#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/pagevec.h>
diff --git a/mm/rmap.c b/mm/rmap.c
index 6aebd1747251..3a1059c284c3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -34,7 +34,7 @@
* mapping->private_lock (in __set_page_dirty_buffers)
* lock_page_memcg move_lock (in __set_page_dirty_buffers)
* i_pages lock (widely used)
- * lruvec->lru_lock (in lock_page_lruvec_irq)
+ * lruvec->lru_lock (in folio_lruvec_lock_irq)
* inode->i_lock (in set_page_dirty's __mark_inode_dirty)
* bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
* sb_lock (within inode_lock in fs/fs-writeback.c)
@@ -981,7 +981,7 @@ static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
return true;
}
-int page_mkclean(struct page *page)
+int folio_mkclean(struct folio *folio)
{
int cleaned = 0;
struct address_space *mapping;
@@ -991,20 +991,20 @@ int page_mkclean(struct page *page)
.invalid_vma = invalid_mkclean_vma,
};
- BUG_ON(!PageLocked(page));
+ BUG_ON(!folio_test_locked(folio));
- if (!page_mapped(page))
+ if (!folio_mapped(folio))
return 0;
- mapping = page_mapping(page);
+ mapping = folio_mapping(folio);
if (!mapping)
return 0;
- rmap_walk(page, &rwc);
+ rmap_walk(&folio->page, &rwc);
return cleaned;
}
-EXPORT_SYMBOL_GPL(page_mkclean);
+EXPORT_SYMBOL_GPL(folio_mkclean);
/**
* page_move_anon_rmap - move a page to our anon_vma
diff --git a/mm/secretmem.c b/mm/secretmem.c
index c2dda408bb36..22b310adb53d 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -218,8 +218,8 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags)
file->f_flags |= O_LARGEFILE;
- fd_install(fd, file);
atomic_inc(&secretmem_users);
+ fd_install(fd, file);
return fd;
err_put_fd:
diff --git a/mm/shmem.c b/mm/shmem.c
index b5860f4a2738..17e344e26e73 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -59,7 +59,6 @@ static struct vfsmount *shm_mnt;
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
#include <linux/writeback.h>
-#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/percpu_counter.h>
#include <linux/falloc.h>
@@ -710,7 +709,7 @@ static int shmem_add_to_page_cache(struct page *page,
page->index = index;
if (!PageSwapCache(page)) {
- error = mem_cgroup_charge(page, charge_mm, gfp);
+ error = mem_cgroup_charge(page_folio(page), charge_mm, gfp);
if (error) {
if (PageTransHuge(page)) {
count_vm_event(THP_FILE_FALLBACK);
@@ -1637,6 +1636,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct page *oldpage, *newpage;
+ struct folio *old, *new;
struct address_space *swap_mapping;
swp_entry_t entry;
pgoff_t swap_index;
@@ -1673,7 +1673,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
xa_lock_irq(&swap_mapping->i_pages);
error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage);
if (!error) {
- mem_cgroup_migrate(oldpage, newpage);
+ old = page_folio(oldpage);
+ new = page_folio(newpage);
+ mem_cgroup_migrate(old, new);
__inc_lruvec_page_state(newpage, NR_FILE_PAGES);
__dec_lruvec_page_state(oldpage, NR_FILE_PAGES);
}
diff --git a/mm/swap.c b/mm/swap.c
index af3cad4e5378..8ff9ba7cf2de 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -80,10 +80,11 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
static void __page_cache_release(struct page *page)
{
if (PageLRU(page)) {
+ struct folio *folio = page_folio(page);
struct lruvec *lruvec;
unsigned long flags;
- lruvec = lock_page_lruvec_irqsave(page, &flags);
+ lruvec = folio_lruvec_lock_irqsave(folio, &flags);
del_page_from_lru_list(page, lruvec);
__clear_page_lru_flags(page);
unlock_page_lruvec_irqrestore(lruvec, flags);
@@ -94,7 +95,7 @@ static void __page_cache_release(struct page *page)
static void __put_single_page(struct page *page)
{
__page_cache_release(page);
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
free_unref_page(page, 0);
}
@@ -188,12 +189,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(page);
/* block memcg migration during page moving between lru */
if (!TestClearPageLRU(page))
continue;
- lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
+ lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags);
(*move_fn)(page, lruvec);
SetPageLRU(page);
@@ -206,11 +208,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
{
- if (!PageUnevictable(page)) {
- del_page_from_lru_list(page, lruvec);
- ClearPageActive(page);
- add_page_to_lru_list_tail(page, lruvec);
- __count_vm_events(PGROTATED, thp_nr_pages(page));
+ struct folio *folio = page_folio(page);
+
+ if (!folio_test_unevictable(folio)) {
+ lruvec_del_folio(lruvec, folio);
+ folio_clear_active(folio);
+ lruvec_add_folio_tail(lruvec, folio);
+ __count_vm_events(PGROTATED, folio_nr_pages(folio));
}
}
@@ -227,23 +231,23 @@ static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page)
}
/*
- * Writeback is about to end against a page which has been marked for immediate
- * reclaim. If it still appears to be reclaimable, move it to the tail of the
- * inactive list.
+ * Writeback is about to end against a folio which has been marked for
+ * immediate reclaim. If it still appears to be reclaimable, move it
+ * to the tail of the inactive list.
*
- * rotate_reclaimable_page() must disable IRQs, to prevent nasty races.
+ * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races.
*/
-void rotate_reclaimable_page(struct page *page)
+void folio_rotate_reclaimable(struct folio *folio)
{
- if (!PageLocked(page) && !PageDirty(page) &&
- !PageUnevictable(page) && PageLRU(page)) {
+ if (!folio_test_locked(folio) && !folio_test_dirty(folio) &&
+ !folio_test_unevictable(folio) && folio_test_lru(folio)) {
struct pagevec *pvec;
unsigned long flags;
- get_page(page);
+ folio_get(folio);
local_lock_irqsave(&lru_rotate.lock, flags);
pvec = this_cpu_ptr(&lru_rotate.pvec);
- if (pagevec_add_and_need_flush(pvec, page))
+ if (pagevec_add_and_need_flush(pvec, &folio->page))
pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
local_unlock_irqrestore(&lru_rotate.lock, flags);
}
@@ -289,21 +293,21 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
} while ((lruvec = parent_lruvec(lruvec)));
}
-void lru_note_cost_page(struct page *page)
+void lru_note_cost_folio(struct folio *folio)
{
- lru_note_cost(mem_cgroup_page_lruvec(page),
- page_is_file_lru(page), thp_nr_pages(page));
+ lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
+ folio_nr_pages(folio));
}
-static void __activate_page(struct page *page, struct lruvec *lruvec)
+static void __folio_activate(struct folio *folio, struct lruvec *lruvec)
{
- if (!PageActive(page) && !PageUnevictable(page)) {
- int nr_pages = thp_nr_pages(page);
+ if (!folio_test_active(folio) && !folio_test_unevictable(folio)) {
+ long nr_pages = folio_nr_pages(folio);
- del_page_from_lru_list(page, lruvec);
- SetPageActive(page);
- add_page_to_lru_list(page, lruvec);
- trace_mm_lru_activate(page);
+ lruvec_del_folio(lruvec, folio);
+ folio_set_active(folio);
+ lruvec_add_folio(lruvec, folio);
+ trace_mm_lru_activate(folio);
__count_vm_events(PGACTIVATE, nr_pages);
__count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE,
@@ -312,6 +316,11 @@ static void __activate_page(struct page *page, struct lruvec *lruvec)
}
#ifdef CONFIG_SMP
+static void __activate_page(struct page *page, struct lruvec *lruvec)
+{
+ return __folio_activate(page_folio(page), lruvec);
+}
+
static void activate_page_drain(int cpu)
{
struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
@@ -325,16 +334,16 @@ static bool need_activate_page_drain(int cpu)
return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
}
-static void activate_page(struct page *page)
+static void folio_activate(struct folio *folio)
{
- page = compound_head(page);
- if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+ if (folio_test_lru(folio) && !folio_test_active(folio) &&
+ !folio_test_unevictable(folio)) {
struct pagevec *pvec;
+ folio_get(folio);
local_lock(&lru_pvecs.lock);
pvec = this_cpu_ptr(&lru_pvecs.activate_page);
- get_page(page);
- if (pagevec_add_and_need_flush(pvec, page))
+ if (pagevec_add_and_need_flush(pvec, &folio->page))
pagevec_lru_move_fn(pvec, __activate_page);
local_unlock(&lru_pvecs.lock);
}
@@ -345,21 +354,20 @@ static inline void activate_page_drain(int cpu)
{
}
-static void activate_page(struct page *page)
+static void folio_activate(struct folio *folio)
{
struct lruvec *lruvec;
- page = compound_head(page);
- if (TestClearPageLRU(page)) {
- lruvec = lock_page_lruvec_irq(page);
- __activate_page(page, lruvec);
+ if (folio_test_clear_lru(folio)) {
+ lruvec = folio_lruvec_lock_irq(folio);
+ __folio_activate(folio, lruvec);
unlock_page_lruvec_irq(lruvec);
- SetPageLRU(page);
+ folio_set_lru(folio);
}
}
#endif
-static void __lru_cache_activate_page(struct page *page)
+static void __lru_cache_activate_folio(struct folio *folio)
{
struct pagevec *pvec;
int i;
@@ -380,8 +388,8 @@ static void __lru_cache_activate_page(struct page *page)
for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
struct page *pagevec_page = pvec->pages[i];
- if (pagevec_page == page) {
- SetPageActive(page);
+ if (pagevec_page == &folio->page) {
+ folio_set_active(folio);
break;
}
}
@@ -399,61 +407,59 @@ static void __lru_cache_activate_page(struct page *page)
* When a newly allocated page is not yet visible, so safe for non-atomic ops,
* __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
*/
-void mark_page_accessed(struct page *page)
+void folio_mark_accessed(struct folio *folio)
{
- page = compound_head(page);
-
- if (!PageReferenced(page)) {
- SetPageReferenced(page);
- } else if (PageUnevictable(page)) {
+ if (!folio_test_referenced(folio)) {
+ folio_set_referenced(folio);
+ } else if (folio_test_unevictable(folio)) {
/*
* Unevictable pages are on the "LRU_UNEVICTABLE" list. But,
* this list is never rotated or maintained, so marking an
* evictable page accessed has no effect.
*/
- } else if (!PageActive(page)) {
+ } else if (!folio_test_active(folio)) {
/*
* If the page is on the LRU, queue it for activation via
* lru_pvecs.activate_page. Otherwise, assume the page is on a
* pagevec, mark it active and it'll be moved to the active
* LRU on the next drain.
*/
- if (PageLRU(page))
- activate_page(page);
+ if (folio_test_lru(folio))
+ folio_activate(folio);
else
- __lru_cache_activate_page(page);
- ClearPageReferenced(page);
- workingset_activation(page);
+ __lru_cache_activate_folio(folio);
+ folio_clear_referenced(folio);
+ workingset_activation(folio);
}
- if (page_is_idle(page))
- clear_page_idle(page);
+ if (folio_test_idle(folio))
+ folio_clear_idle(folio);
}
-EXPORT_SYMBOL(mark_page_accessed);
+EXPORT_SYMBOL(folio_mark_accessed);
/**
- * lru_cache_add - add a page to a page list
- * @page: the page to be added to the LRU.
+ * folio_add_lru - Add a folio to an LRU list.
+ * @folio: The folio to be added to the LRU.
*
- * Queue the page for addition to the LRU via pagevec. The decision on whether
+ * Queue the folio for addition to the LRU. The decision on whether
* to add the page to the [in]active [file|anon] list is deferred until the
- * pagevec is drained. This gives a chance for the caller of lru_cache_add()
- * have the page added to the active list using mark_page_accessed().
+ * pagevec is drained. This gives a chance for the caller of folio_add_lru()
+ * have the folio added to the active list using folio_mark_accessed().
*/
-void lru_cache_add(struct page *page)
+void folio_add_lru(struct folio *folio)
{
struct pagevec *pvec;
- VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
- VM_BUG_ON_PAGE(PageLRU(page), page);
+ VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
- get_page(page);
+ folio_get(folio);
local_lock(&lru_pvecs.lock);
pvec = this_cpu_ptr(&lru_pvecs.lru_add);
- if (pagevec_add_and_need_flush(pvec, page))
+ if (pagevec_add_and_need_flush(pvec, &folio->page))
__pagevec_lru_add(pvec);
local_unlock(&lru_pvecs.lock);
}
-EXPORT_SYMBOL(lru_cache_add);
+EXPORT_SYMBOL(folio_add_lru);
/**
* lru_cache_add_inactive_or_unevictable
@@ -888,11 +894,12 @@ void release_pages(struct page **pages, int nr)
int i;
LIST_HEAD(pages_to_free);
struct lruvec *lruvec = NULL;
- unsigned long flags;
+ unsigned long flags = 0;
unsigned int lock_batch;
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
+ struct folio *folio = page_folio(page);
/*
* Make sure the IRQ-safe lock-holding time does not get
@@ -904,7 +911,7 @@ void release_pages(struct page **pages, int nr)
lruvec = NULL;
}
- page = compound_head(page);
+ page = &folio->page;
if (is_huge_zero_page(page))
continue;
@@ -943,7 +950,7 @@ void release_pages(struct page **pages, int nr)
if (PageLRU(page)) {
struct lruvec *prev_lruvec = lruvec;
- lruvec = relock_page_lruvec_irqsave(page, lruvec,
+ lruvec = folio_lruvec_relock_irqsave(folio, lruvec,
&flags);
if (prev_lruvec != lruvec)
lock_batch = 0;
@@ -985,17 +992,18 @@ void __pagevec_release(struct pagevec *pvec)
}
EXPORT_SYMBOL(__pagevec_release);
-static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
+static void __pagevec_lru_add_fn(struct folio *folio, struct lruvec *lruvec)
{
- int was_unevictable = TestClearPageUnevictable(page);
- int nr_pages = thp_nr_pages(page);
+ int was_unevictable = folio_test_clear_unevictable(folio);
+ long nr_pages = folio_nr_pages(folio);
- VM_BUG_ON_PAGE(PageLRU(page), page);
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
/*
- * Page becomes evictable in two ways:
+ * A folio becomes evictable in two ways:
* 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()].
- * 2) Before acquiring LRU lock to put the page to correct LRU and then
+ * 2) Before acquiring LRU lock to put the folio on the correct LRU
+ * and then
* a) do PageLRU check with lock [check_move_unevictable_pages]
* b) do PageLRU check before lock [clear_page_mlock]
*
@@ -1004,35 +1012,36 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
*
* #0: __pagevec_lru_add_fn #1: clear_page_mlock
*
- * SetPageLRU() TestClearPageMlocked()
+ * folio_set_lru() folio_test_clear_mlocked()
* smp_mb() // explicit ordering // above provides strict
* // ordering
- * PageMlocked() PageLRU()
+ * folio_test_mlocked() folio_test_lru()
*
*
- * if '#1' does not observe setting of PG_lru by '#0' and fails
- * isolation, the explicit barrier will make sure that page_evictable
- * check will put the page in correct LRU. Without smp_mb(), SetPageLRU
- * can be reordered after PageMlocked check and can make '#1' to fail
- * the isolation of the page whose Mlocked bit is cleared (#0 is also
- * looking at the same page) and the evictable page will be stranded
- * in an unevictable LRU.
+ * if '#1' does not observe setting of PG_lru by '#0' and
+ * fails isolation, the explicit barrier will make sure that
+ * folio_evictable check will put the folio on the correct
+ * LRU. Without smp_mb(), folio_set_lru() can be reordered
+ * after folio_test_mlocked() check and can make '#1' fail the
+ * isolation of the folio whose mlocked bit is cleared (#0 is
+ * also looking at the same folio) and the evictable folio will
+ * be stranded on an unevictable LRU.
*/
- SetPageLRU(page);
+ folio_set_lru(folio);
smp_mb__after_atomic();
- if (page_evictable(page)) {
+ if (folio_evictable(folio)) {
if (was_unevictable)
__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
} else {
- ClearPageActive(page);
- SetPageUnevictable(page);
+ folio_clear_active(folio);
+ folio_set_unevictable(folio);
if (!was_unevictable)
__count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
}
- add_page_to_lru_list(page, lruvec);
- trace_mm_lru_insertion(page);
+ lruvec_add_folio(lruvec, folio);
+ trace_mm_lru_insertion(folio);
}
/*
@@ -1046,10 +1055,10 @@ void __pagevec_lru_add(struct pagevec *pvec)
unsigned long flags = 0;
for (i = 0; i < pagevec_count(pvec); i++) {
- struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(pvec->pages[i]);
- lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
- __pagevec_lru_add_fn(page, lruvec);
+ lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags);
+ __pagevec_lru_add_fn(folio, lruvec);
}
if (lruvec)
unlock_page_lruvec_irqrestore(lruvec, flags);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index bc7cee6b2ec5..8d4104242100 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -498,7 +498,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
mem_cgroup_swapin_uncharge_swap(entry);
if (shadow)
- workingset_refault(page, shadow);
+ workingset_refault(page_folio(page), shadow);
/* Caller will initiate read into locked page */
lru_cache_add(page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 22d10f713848..41c9e92f1f00 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -18,7 +18,7 @@
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shmem_fs.h>
-#include <linux/blkdev.h>
+#include <linux/blk-cgroup.h>
#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
@@ -3534,13 +3534,13 @@ struct swap_info_struct *page_swap_info(struct page *page)
}
/*
- * out-of-line __page_file_ methods to avoid include hell.
+ * out-of-line methods to avoid include hell.
*/
-struct address_space *__page_file_mapping(struct page *page)
+struct address_space *swapcache_mapping(struct folio *folio)
{
- return page_swap_info(page)->swap_file->f_mapping;
+ return page_swap_info(&folio->page)->swap_file->f_mapping;
}
-EXPORT_SYMBOL_GPL(__page_file_mapping);
+EXPORT_SYMBOL_GPL(swapcache_mapping);
pgoff_t __page_file_index(struct page *page)
{
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 7a9008415534..36e5f6ab976f 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -164,7 +164,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
__SetPageUptodate(page);
ret = -ENOMEM;
- if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL))
goto out_release;
ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
diff --git a/mm/util.c b/mm/util.c
index bacabe446906..e58151a61255 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -654,81 +654,78 @@ void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
}
EXPORT_SYMBOL(kvrealloc);
-static inline void *__page_rmapping(struct page *page)
-{
- unsigned long mapping;
-
- mapping = (unsigned long)page->mapping;
- mapping &= ~PAGE_MAPPING_FLAGS;
-
- return (void *)mapping;
-}
-
/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
- page = compound_head(page);
- return __page_rmapping(page);
+ return folio_raw_mapping(page_folio(page));
}
-/*
- * Return true if this page is mapped into pagetables.
- * For compound page it returns true if any subpage of compound page is mapped.
+/**
+ * folio_mapped - Is this folio mapped into userspace?
+ * @folio: The folio.
+ *
+ * Return: True if any page in this folio is referenced by user page tables.
*/
-bool page_mapped(struct page *page)
+bool folio_mapped(struct folio *folio)
{
- int i;
+ long i, nr;
- if (likely(!PageCompound(page)))
- return atomic_read(&page->_mapcount) >= 0;
- page = compound_head(page);
- if (atomic_read(compound_mapcount_ptr(page)) >= 0)
+ if (folio_test_single(folio))
+ return atomic_read(&folio->_mapcount) >= 0;
+ if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
return true;
- if (PageHuge(page))
+ if (folio_test_hugetlb(folio))
return false;
- for (i = 0; i < compound_nr(page); i++) {
- if (atomic_read(&page[i]._mapcount) >= 0)
+
+ nr = folio_nr_pages(folio);
+ for (i = 0; i < nr; i++) {
+ if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0)
return true;
}
return false;
}
-EXPORT_SYMBOL(page_mapped);
+EXPORT_SYMBOL(folio_mapped);
struct anon_vma *page_anon_vma(struct page *page)
{
- unsigned long mapping;
+ struct folio *folio = page_folio(page);
+ unsigned long mapping = (unsigned long)folio->mapping;
- page = compound_head(page);
- mapping = (unsigned long)page->mapping;
if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
return NULL;
- return __page_rmapping(page);
+ return (void *)(mapping - PAGE_MAPPING_ANON);
}
-struct address_space *page_mapping(struct page *page)
+/**
+ * folio_mapping - Find the mapping where this folio is stored.
+ * @folio: The folio.
+ *
+ * For folios which are in the page cache, return the mapping that this
+ * page belongs to. Folios in the swap cache return the swap mapping
+ * this page is stored in (which is different from the mapping for the
+ * swap file or swap device where the data is stored).
+ *
+ * You can call this for folios which aren't in the swap cache or page
+ * cache and it will return NULL.
+ */
+struct address_space *folio_mapping(struct folio *folio)
{
struct address_space *mapping;
- page = compound_head(page);
-
/* This happens if someone calls flush_dcache_page on slab page */
- if (unlikely(PageSlab(page)))
+ if (unlikely(folio_test_slab(folio)))
return NULL;
- if (unlikely(PageSwapCache(page))) {
- swp_entry_t entry;
+ if (unlikely(folio_test_swapcache(folio)))
+ return swap_address_space(folio_swap_entry(folio));
- entry.val = page_private(page);
- return swap_address_space(entry);
- }
-
- mapping = page->mapping;
+ mapping = folio->mapping;
if ((unsigned long)mapping & PAGE_MAPPING_ANON)
return NULL;
return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS);
}
-EXPORT_SYMBOL(page_mapping);
+EXPORT_SYMBOL(folio_mapping);
/* Slow path of page_mapcount() for compound pages */
int __page_mapcount(struct page *page)
@@ -750,13 +747,26 @@ int __page_mapcount(struct page *page)
}
EXPORT_SYMBOL_GPL(__page_mapcount);
-void copy_huge_page(struct page *dst, struct page *src)
+/**
+ * folio_copy - Copy the contents of one folio to another.
+ * @dst: Folio to copy to.
+ * @src: Folio to copy from.
+ *
+ * The bytes in the folio represented by @src are copied to @dst.
+ * Assumes the caller has validated that @dst is at least as large as @src.
+ * Can be called in atomic context for order-0 folios, but if the folio is
+ * larger, it may sleep.
+ */
+void folio_copy(struct folio *dst, struct folio *src)
{
- unsigned i, nr = compound_nr(src);
+ long i = 0;
+ long nr = folio_nr_pages(src);
- for (i = 0; i < nr; i++) {
+ for (;;) {
+ copy_highpage(folio_page(dst, i), folio_page(src, i));
+ if (++i == nr)
+ break;
cond_resched();
- copy_highpage(nth_page(dst, i), nth_page(src, i));
}
}
@@ -1079,3 +1089,14 @@ void page_offline_end(void)
up_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_end);
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio)
+{
+ long i, nr = folio_nr_pages(folio);
+
+ for (i = 0; i < nr; i++)
+ flush_dcache_page(folio_page(folio, i));
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+#endif
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d77830ff604c..e8a807c78110 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2816,6 +2816,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
unsigned int order, unsigned int nr_pages, struct page **pages)
{
unsigned int nr_allocated = 0;
+ struct page *page;
+ int i;
/*
* For order-0 pages we make use of bulk allocator, if
@@ -2823,7 +2825,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
* to fails, fallback to a single page allocator that is
* more permissive.
*/
- if (!order) {
+ if (!order && nid != NUMA_NO_NODE) {
while (nr_allocated < nr_pages) {
unsigned int nr, nr_pages_request;
@@ -2848,7 +2850,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
if (nr != nr_pages_request)
break;
}
- } else
+ } else if (order)
/*
* Compound pages required for remap_vmalloc_page if
* high-order pages.
@@ -2856,11 +2858,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
gfp |= __GFP_COMP;
/* High-order pages or fallback path if "bulk" fails. */
- while (nr_allocated < nr_pages) {
- struct page *page;
- int i;
- page = alloc_pages_node(nid, gfp, order);
+ while (nr_allocated < nr_pages) {
+ if (nid == NUMA_NO_NODE)
+ page = alloc_pages(gfp, order);
+ else
+ page = alloc_pages_node(nid, gfp, order);
if (unlikely(!page))
break;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 74296c2d1fed..306229c4313f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2090,6 +2090,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
*/
int isolate_lru_page(struct page *page)
{
+ struct folio *folio = page_folio(page);
int ret = -EBUSY;
VM_BUG_ON_PAGE(!page_count(page), page);
@@ -2099,7 +2100,7 @@ int isolate_lru_page(struct page *page)
struct lruvec *lruvec;
get_page(page);
- lruvec = lock_page_lruvec_irq(page);
+ lruvec = folio_lruvec_lock_irq(folio);
del_page_from_lru_list(page, lruvec);
unlock_page_lruvec_irq(lruvec);
ret = 0;
@@ -2199,7 +2200,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
* All pages were isolated from the same lruvec (and isolation
* inhibits memcg migration).
*/
- VM_BUG_ON_PAGE(!page_matches_lruvec(page, lruvec), page);
+ VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page);
add_page_to_lru_list(page, lruvec);
nr_pages = thp_nr_pages(page);
nr_moved += nr_pages;
@@ -4665,6 +4666,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
for (i = 0; i < pvec->nr; i++) {
struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(page);
int nr_pages;
if (PageTransTail(page))
@@ -4677,7 +4679,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
if (!TestClearPageLRU(page))
continue;
- lruvec = relock_page_lruvec_irq(page, lruvec);
+ lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (page_evictable(page) && PageUnevictable(page)) {
del_page_from_lru_list(page, lruvec);
ClearPageUnevictable(page);
diff --git a/mm/workingset.c b/mm/workingset.c
index d5b81e4f4cbe..109ab978251a 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -273,17 +273,17 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
}
/**
- * workingset_refault - evaluate the refault of a previously evicted page
- * @page: the freshly allocated replacement page
- * @shadow: shadow entry of the evicted page
+ * workingset_refault - Evaluate the refault of a previously evicted folio.
+ * @folio: The freshly allocated replacement folio.
+ * @shadow: Shadow entry of the evicted folio.
*
* Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the node and the memcg whose memory
+ * evicted folio in the context of the node and the memcg whose memory
* pressure caused the eviction.
*/
-void workingset_refault(struct page *page, void *shadow)
+void workingset_refault(struct folio *folio, void *shadow)
{
- bool file = page_is_file_lru(page);
+ bool file = folio_is_file_lru(folio);
struct mem_cgroup *eviction_memcg;
struct lruvec *eviction_lruvec;
unsigned long refault_distance;
@@ -295,16 +295,17 @@ void workingset_refault(struct page *page, void *shadow)
unsigned long refault;
bool workingset;
int memcgid;
+ long nr;
unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
rcu_read_lock();
/*
* Look up the memcg associated with the stored ID. It might
- * have been deleted since the page's eviction.
+ * have been deleted since the folio's eviction.
*
* Note that in rare events the ID could have been recycled
- * for a new cgroup that refaults a shared page. This is
+ * for a new cgroup that refaults a shared folio. This is
* impossible to tell from the available data. However, this
* should be a rare and limited disturbance, and activations
* are always speculative anyway. Ultimately, it's the aging
@@ -340,17 +341,18 @@ void workingset_refault(struct page *page, void *shadow)
refault_distance = (refault - eviction) & EVICTION_MASK;
/*
- * The activation decision for this page is made at the level
+ * The activation decision for this folio is made at the level
* where the eviction occurred, as that is where the LRU order
- * during page reclaim is being determined.
+ * during folio reclaim is being determined.
*
- * However, the cgroup that will own the page is the one that
+ * However, the cgroup that will own the folio is the one that
* is actually experiencing the refault event.
*/
- memcg = page_memcg(page);
+ nr = folio_nr_pages(folio);
+ memcg = folio_memcg(folio);
lruvec = mem_cgroup_lruvec(memcg, pgdat);
- inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
+ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
mem_cgroup_flush_stats();
/*
@@ -376,16 +378,16 @@ void workingset_refault(struct page *page, void *shadow)
if (refault_distance > workingset_size)
goto out;
- SetPageActive(page);
- workingset_age_nonresident(lruvec, thp_nr_pages(page));
- inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
+ folio_set_active(folio);
+ workingset_age_nonresident(lruvec, nr);
+ mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr);
- /* Page was active prior to eviction */
+ /* Folio was active prior to eviction */
if (workingset) {
- SetPageWorkingset(page);
+ folio_set_workingset(folio);
/* XXX: Move to lru_cache_add() when it supports new vs putback */
- lru_note_cost_page(page);
- inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
+ lru_note_cost_folio(folio);
+ mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
}
out:
rcu_read_unlock();
@@ -393,12 +395,11 @@ out:
/**
* workingset_activation - note a page activation
- * @page: page that is being activated
+ * @folio: Folio that is being activated.
*/
-void workingset_activation(struct page *page)
+void workingset_activation(struct folio *folio)
{
struct mem_cgroup *memcg;
- struct lruvec *lruvec;
rcu_read_lock();
/*
@@ -408,11 +409,10 @@ void workingset_activation(struct page *page)
* XXX: See workingset_refault() - this should return
* root_mem_cgroup even for !CONFIG_MEMCG.
*/
- memcg = page_memcg_rcu(page);
+ memcg = folio_memcg_rcu(folio);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_page_lruvec(page);
- workingset_age_nonresident(lruvec, thp_nr_pages(page));
+ workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio));
out:
rcu_read_unlock();
}
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 1669744304c5..17687848daec 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1560,10 +1560,14 @@ int batadv_bla_init(struct batadv_priv *bat_priv)
return 0;
bat_priv->bla.claim_hash = batadv_hash_new(128);
- bat_priv->bla.backbone_hash = batadv_hash_new(32);
+ if (!bat_priv->bla.claim_hash)
+ return -ENOMEM;
- if (!bat_priv->bla.claim_hash || !bat_priv->bla.backbone_hash)
+ bat_priv->bla.backbone_hash = batadv_hash_new(32);
+ if (!bat_priv->bla.backbone_hash) {
+ batadv_hash_destroy(bat_priv->bla.claim_hash);
return -ENOMEM;
+ }
batadv_hash_set_lock_class(bat_priv->bla.claim_hash,
&batadv_claim_hash_lock_class_key);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 3ddd66e4c29e..5207cd8d6ad8 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -190,29 +190,41 @@ int batadv_mesh_init(struct net_device *soft_iface)
bat_priv->gw.generation = 0;
- ret = batadv_v_mesh_init(bat_priv);
- if (ret < 0)
- goto err;
-
ret = batadv_originator_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_orig;
+ }
ret = batadv_tt_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_tt;
+ }
+
+ ret = batadv_v_mesh_init(bat_priv);
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_v;
+ }
ret = batadv_bla_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_bla;
+ }
ret = batadv_dat_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_dat;
+ }
ret = batadv_nc_mesh_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_nc;
+ }
batadv_gw_init(bat_priv);
batadv_mcast_init(bat_priv);
@@ -222,8 +234,20 @@ int batadv_mesh_init(struct net_device *soft_iface)
return 0;
-err:
- batadv_mesh_free(soft_iface);
+err_nc:
+ batadv_dat_free(bat_priv);
+err_dat:
+ batadv_bla_free(bat_priv);
+err_bla:
+ batadv_v_mesh_free(bat_priv);
+err_v:
+ batadv_tt_free(bat_priv);
+err_tt:
+ batadv_originator_free(bat_priv);
+err_orig:
+ batadv_purge_outstanding_packets(bat_priv, NULL);
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE);
+
return ret;
}
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 9f06132e007d..0a7f1d36a6a8 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -152,8 +152,10 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
&batadv_nc_coding_hash_lock_class_key);
bat_priv->nc.decoding_hash = batadv_hash_new(128);
- if (!bat_priv->nc.decoding_hash)
+ if (!bat_priv->nc.decoding_hash) {
+ batadv_hash_destroy(bat_priv->nc.coding_hash);
goto err;
+ }
batadv_hash_set_lock_class(bat_priv->nc.decoding_hash,
&batadv_nc_decoding_hash_lock_class_key);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index e0b3dace2020..4b7ad6684bc4 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -4162,8 +4162,10 @@ int batadv_tt_init(struct batadv_priv *bat_priv)
return ret;
ret = batadv_tt_global_init(bat_priv);
- if (ret < 0)
+ if (ret < 0) {
+ batadv_tt_local_table_free(bat_priv);
return ret;
+ }
batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1,
batadv_tt_tvlv_unicast_handler_v1,
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ee9fecd3aff..eb3a366bf212 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3163,6 +3163,12 @@ static u16 skb_tx_hash(const struct net_device *dev,
qoffset = sb_dev->tc_to_txq[tc].offset;
qcount = sb_dev->tc_to_txq[tc].count;
+ if (unlikely(!qcount)) {
+ net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n",
+ sb_dev->name, qoffset, tc);
+ qoffset = 0;
+ qcount = dev->real_num_tx_queues;
+ }
}
if (skb_rx_queue_recorded(skb)) {
@@ -3906,7 +3912,8 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
skb->pkt_type = PACKET_LOOPBACK;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (skb->ip_summed == CHECKSUM_NONE)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(skb));
skb_dst_force(skb);
netif_rx_ni(skb);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f6197774048b..b2e49eb7001d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1973,9 +1973,9 @@ int netdev_register_kobject(struct net_device *ndev)
int netdev_change_owner(struct net_device *ndev, const struct net *net_old,
const struct net *net_new)
{
+ kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID;
+ kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID;
struct device *dev = &ndev->dev;
- kuid_t old_uid, new_uid;
- kgid_t old_gid, new_gid;
int error;
net_ns_get_ownership(net_old, &old_uid, &old_gid);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2170bea2c7de..fe9358437380 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -80,6 +80,7 @@
#include <linux/indirect_call_wrapper.h>
#include "datagram.h"
+#include "sock_destructor.h"
struct kmem_cache *skbuff_head_cache __ro_after_init;
static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
@@ -1804,30 +1805,39 @@ EXPORT_SYMBOL(skb_realloc_headroom);
struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
{
int delta = headroom - skb_headroom(skb);
+ int osize = skb_end_offset(skb);
+ struct sock *sk = skb->sk;
if (WARN_ONCE(delta <= 0,
"%s is expecting an increase in the headroom", __func__))
return skb;
- /* pskb_expand_head() might crash, if skb is shared */
- if (skb_shared(skb)) {
+ delta = SKB_DATA_ALIGN(delta);
+ /* pskb_expand_head() might crash, if skb is shared. */
+ if (skb_shared(skb) || !is_skb_wmem(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
- if (likely(nskb)) {
- if (skb->sk)
- skb_set_owner_w(nskb, skb->sk);
- consume_skb(skb);
- } else {
- kfree_skb(skb);
- }
+ if (unlikely(!nskb))
+ goto fail;
+
+ if (sk)
+ skb_set_owner_w(nskb, sk);
+ consume_skb(skb);
skb = nskb;
}
- if (skb &&
- pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
- kfree_skb(skb);
- skb = NULL;
+ if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
+ goto fail;
+
+ if (sk && is_skb_wmem(skb)) {
+ delta = skb_end_offset(skb) - osize;
+ refcount_add(delta, &sk->sk_wmem_alloc);
+ skb->truesize += delta;
}
return skb;
+
+fail:
+ kfree_skb(skb);
+ return NULL;
}
EXPORT_SYMBOL(skb_expand_head);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b28928..a86ef7e844f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
+bool sk_msg_is_readable(struct sock *sk)
+{
+ struct sk_psock *psock;
+ bool empty = true;
+
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (likely(psock))
+ empty = list_empty(&psock->ingress_msg);
+ rcu_read_unlock();
+ return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
struct sk_buff *skb)
{
diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h
new file mode 100644
index 000000000000..2f396e6bfba5
--- /dev/null
+++ b/net/core/sock_destructor.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _NET_CORE_SOCK_DESTRUCTOR_H
+#define _NET_CORE_SOCK_DESTRUCTOR_H
+#include <net/tcp.h>
+
+static inline bool is_skb_wmem(const struct sk_buff *skb)
+{
+ return skb->destructor == sock_wfree ||
+ skb->destructor == __sock_wfree ||
+ (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree);
+}
+#endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c8496c1142c9..5f88526ad61c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -419,7 +419,7 @@ static struct ctl_table net_core_table[] = {
.mode = 0600,
.proc_handler = proc_dolongvec_minmax_bpf_restricted,
.extra1 = &long_one,
- .extra2 = &long_max,
+ .extra2 = &bpf_jit_limit_max,
},
#endif
{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8b48df73c85..f5c336f8b0c8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -486,10 +486,7 @@ static bool tcp_stream_is_readable(struct sock *sk, int target)
{
if (tcp_epollin_ready(sk, target))
return true;
-
- if (sk->sk_prot->stream_memory_read)
- return sk->sk_prot->stream_memory_read(sk);
- return false;
+ return sk_is_readable(sk);
}
/*
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386b493e..5f4d6f45d87f 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -150,19 +150,6 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
#ifdef CONFIG_BPF_SYSCALL
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
- struct sk_psock *psock;
- bool empty = true;
-
- rcu_read_lock();
- psock = sk_psock(sk);
- if (likely(psock))
- empty = list_empty(&psock->ingress_msg);
- rcu_read_unlock();
- return !empty;
-}
-
static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
long timeo)
{
@@ -232,6 +219,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
bool cork = false, enospc = sk_msg_full(msg);
struct sock *sk_redir;
u32 tosend, delta = 0;
+ u32 eval = __SK_NONE;
int ret;
more_data:
@@ -275,13 +263,24 @@ more_data:
case __SK_REDIRECT:
sk_redir = psock->sk_redir;
sk_msg_apply_bytes(psock, tosend);
+ if (!psock->apply_bytes) {
+ /* Clean up before releasing the sock lock. */
+ eval = psock->eval;
+ psock->eval = __SK_NONE;
+ psock->sk_redir = NULL;
+ }
if (psock->cork) {
cork = true;
psock->cork = NULL;
}
sk_msg_return(sk, msg, tosend);
release_sock(sk);
+
ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+ if (eval == __SK_REDIRECT)
+ sock_put(sk_redir);
+
lock_sock(sk);
if (unlikely(ret < 0)) {
int free = sk_msg_free_nocharge(sk, msg);
@@ -479,7 +478,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
prot[TCP_BPF_BASE].unhash = sock_map_unhash;
prot[TCP_BPF_BASE].close = sock_map_close;
prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg;
- prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read;
+ prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable;
prot[TCP_BPF_TX] = prot[TCP_BPF_BASE];
prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8536b2a7210b..2fffcf2b54f3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2867,6 +2867,9 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
+ /* psock ingress_msg queue should not contain any bad checksum frames */
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a1d5f473878..bbe6569c9ad3 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -114,6 +114,7 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = udp_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 97095b7c9c64..5dcfd53a4ab6 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -672,7 +672,7 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
u8 *ie, u8 ie_len)
{
struct ieee80211_supported_band *sband;
- const u8 *cap;
+ const struct element *cap;
const struct ieee80211_he_operation *he_oper = NULL;
sband = ieee80211_get_sband(sdata);
@@ -687,9 +687,10 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
sdata->vif.bss_conf.he_support = true;
- cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
- if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3]))
- he_oper = (void *)(cap + 3);
+ cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
+ if (cap && cap->datalen >= 1 + sizeof(*he_oper) &&
+ cap->datalen >= 1 + ieee80211_he_oper_size(cap->data + 1))
+ he_oper = (void *)(cap->data + 1);
if (he_oper)
sdata->vif.bss_conf.he_oper.params =
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c41273cefc51..f0f22eb4fd5f 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -485,11 +485,11 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
mpext = mptcp_get_ext(skb);
data_len = mpext ? mpext->data_len : 0;
- /* we will check ext_copy.data_len in mptcp_write_options() to
+ /* we will check ops->data_len in mptcp_write_options() to
* discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
* TCPOLEN_MPTCP_MPC_ACK
*/
- opts->ext_copy.data_len = data_len;
+ opts->data_len = data_len;
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
@@ -505,9 +505,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd) {
/* we need to propagate more info to csum the pseudo hdr */
- opts->ext_copy.data_seq = mpext->data_seq;
- opts->ext_copy.subflow_seq = mpext->subflow_seq;
- opts->ext_copy.csum = mpext->csum;
+ opts->data_seq = mpext->data_seq;
+ opts->subflow_seq = mpext->subflow_seq;
+ opts->csum = mpext->csum;
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
}
*size = ALIGN(len, 4);
@@ -1227,7 +1227,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp)
WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
-static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+static u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __sum16 sum)
{
struct csum_pseudo_header header;
__wsum csum;
@@ -1237,15 +1237,21 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
* always the 64-bit value, irrespective of what length is used in the
* DSS option itself.
*/
- header.data_seq = cpu_to_be64(mpext->data_seq);
- header.subflow_seq = htonl(mpext->subflow_seq);
- header.data_len = htons(mpext->data_len);
+ header.data_seq = cpu_to_be64(data_seq);
+ header.subflow_seq = htonl(subflow_seq);
+ header.data_len = htons(data_len);
header.csum = 0;
- csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum));
+ csum = csum_partial(&header, sizeof(header), ~csum_unfold(sum));
return (__force u16)csum_fold(csum);
}
+static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+{
+ return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len,
+ mpext->csum);
+}
+
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
@@ -1337,7 +1343,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
len = TCPOLEN_MPTCP_MPC_SYN;
} else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) {
len = TCPOLEN_MPTCP_MPC_SYNACK;
- } else if (opts->ext_copy.data_len) {
+ } else if (opts->data_len) {
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd)
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
@@ -1366,14 +1372,17 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
put_unaligned_be64(opts->rcvr_key, ptr);
ptr += 2;
- if (!opts->ext_copy.data_len)
+ if (!opts->data_len)
goto mp_capable_done;
if (opts->csum_reqd) {
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
- mptcp_make_csum(&opts->ext_copy), ptr);
+ put_unaligned_be32(opts->data_len << 16 |
+ __mptcp_make_csum(opts->data_seq,
+ opts->subflow_seq,
+ opts->data_len,
+ opts->csum), ptr);
} else {
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
+ put_unaligned_be32(opts->data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
ptr += 1;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 32df65f68c12..fb3da4d8f4a3 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -156,6 +156,12 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort(
void *arg,
struct sctp_cmd_seq *commands);
+static enum sctp_disposition
+__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands);
+
/* Small helper function that checks if the chunk length
* is of the appropriate length. The 'required_length' argument
* is set to be the size of a specific chunk we are testing.
@@ -337,6 +343,14 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
if (!chunk->singleton)
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ /* Make sure that the INIT chunk has a valid length.
+ * Normally, this would cause an ABORT with a Protocol Violation
+ * error, but since we don't have an association, we'll
+ * just discard the packet.
+ */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* If the packet is an OOTB packet which is temporarily on the
* control endpoint, respond with an ABORT.
*/
@@ -351,14 +365,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
if (chunk->sctp_hdr->vtag != 0)
return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
- /* Make sure that the INIT chunk has a valid length.
- * Normally, this would cause an ABORT with a Protocol Violation
- * error, but since we don't have an association, we'll
- * just discard the packet.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-
/* If the INIT is coming toward a closing socket, we'll send back
* and ABORT. Essentially, this catches the race of INIT being
* backloged to the socket at the same time as the user issues close().
@@ -704,6 +710,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
struct sock *sk;
int error = 0;
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* If the packet is an OOTB packet which is temporarily on the
* control endpoint, respond with an ABORT.
*/
@@ -718,7 +727,8 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
* in sctp_unpack_cookie().
*/
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
/* If the endpoint is not listening or if the number of associations
* on the TCP-style socket exceed the max backlog, respond with an
@@ -1524,20 +1534,16 @@ static enum sctp_disposition sctp_sf_do_unexpected_init(
if (!chunk->singleton)
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ /* Make sure that the INIT chunk has a valid length. */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* 3.1 A packet containing an INIT chunk MUST have a zero Verification
* Tag.
*/
if (chunk->sctp_hdr->vtag != 0)
return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
- /* Make sure that the INIT chunk has a valid length.
- * In this case, we generate a protocol violation since we have
- * an association established.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
-
if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port)
return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands);
@@ -1882,9 +1888,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
* its peer.
*/
if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) {
- disposition = sctp_sf_do_9_2_reshutack(net, ep, asoc,
- SCTP_ST_CHUNK(chunk->chunk_hdr->type),
- chunk, commands);
+ disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc,
+ SCTP_ST_CHUNK(chunk->chunk_hdr->type),
+ chunk, commands);
if (SCTP_DISPOSITION_NOMEM == disposition)
goto nomem;
@@ -2202,9 +2208,11 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
* enough for the chunk header. Cookie length verification is
* done later.
*/
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) {
+ if (!sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands);
+ }
/* "Decode" the chunk. We have no optional parameters so we
* are in good shape.
@@ -2341,7 +2349,7 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort(
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2387,7 +2395,7 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort(
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2657,7 +2665,7 @@ enum sctp_disposition sctp_sf_do_9_1_abort(
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2970,13 +2978,11 @@ enum sctp_disposition sctp_sf_do_9_2_shut_ctsn(
* that belong to this association, it should discard the INIT chunk and
* retransmit the SHUTDOWN ACK chunk.
*/
-enum sctp_disposition sctp_sf_do_9_2_reshutack(
- struct net *net,
- const struct sctp_endpoint *ep,
- const struct sctp_association *asoc,
- const union sctp_subtype type,
- void *arg,
- struct sctp_cmd_seq *commands)
+static enum sctp_disposition
+__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands)
{
struct sctp_chunk *chunk = arg;
struct sctp_chunk *reply;
@@ -3010,6 +3016,26 @@ nomem:
return SCTP_DISPOSITION_NOMEM;
}
+enum sctp_disposition
+sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_chunk *chunk = arg;
+
+ if (!chunk->singleton)
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
+ if (chunk->sctp_hdr->vtag != 0)
+ return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
+
+ return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands);
+}
+
/*
* sctp_sf_do_ecn_cwr
*
@@ -3662,6 +3688,9 @@ enum sctp_disposition sctp_sf_ootb(struct net *net,
SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES);
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+
ch = (struct sctp_chunkhdr *)chunk->chunk_hdr;
do {
/* Report violation if the chunk is less then minimal */
@@ -3777,12 +3806,6 @@ static enum sctp_disposition sctp_sf_shut_8_4_5(
SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
- /* If the chunk length is invalid, we don't want to process
- * the reset of the packet.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-
/* We need to discard the rest of the packet to prevent
* potential boomming attacks from additional bundled chunks.
* This is documented in SCTP Threats ID.
@@ -3810,6 +3833,9 @@ enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net,
{
struct sctp_chunk *chunk = arg;
+ if (!sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+
/* Make sure that the SHUTDOWN_ACK chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
@@ -3845,6 +3871,11 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
+ /* Make sure that the ASCONF ADDIP chunk has a valid length. */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk)))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* ADD-IP: Section 4.1.1
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
@@ -3853,13 +3884,7 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
*/
if (!asoc->peer.asconf_capable ||
(!net->sctp.addip_noauth && !chunk->auth))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg,
- commands);
-
- /* Make sure that the ASCONF ADDIP chunk has a valid length. */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
hdr = (struct sctp_addiphdr *)chunk->skb->data;
serial = ntohl(hdr->serial);
@@ -3988,6 +4013,12 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
+ /* Make sure that the ADDIP chunk has a valid length. */
+ if (!sctp_chunk_length_valid(asconf_ack,
+ sizeof(struct sctp_addip_chunk)))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* ADD-IP, Section 4.1.2:
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
@@ -3996,14 +4027,7 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
*/
if (!asoc->peer.asconf_capable ||
(!net->sctp.addip_noauth && !asconf_ack->auth))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg,
- commands);
-
- /* Make sure that the ADDIP chunk has a valid length. */
- if (!sctp_chunk_length_valid(asconf_ack,
- sizeof(struct sctp_addip_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data;
rcvd_serial = ntohl(addip_hdr->serial);
@@ -4575,6 +4599,9 @@ enum sctp_disposition sctp_sf_discard_chunk(struct net *net,
{
struct sctp_chunk *chunk = arg;
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Make sure that the chunk has a valid length.
* Since we don't know the chunk type, we use a general
* chunkhdr structure to make a comparison.
@@ -4642,6 +4669,9 @@ enum sctp_disposition sctp_sf_violation(struct net *net,
{
struct sctp_chunk *chunk = arg;
+ if (!sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Make sure that the chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
@@ -6348,6 +6378,7 @@ static struct sctp_packet *sctp_ootb_pkt_new(
* yet.
*/
switch (chunk->chunk_hdr->type) {
+ case SCTP_CID_INIT:
case SCTP_CID_INIT_ACK:
{
struct sctp_initack_chunk *initack;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c038efc23ce3..78b663dbfa1f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1057,7 +1057,7 @@ static void smc_connect_work(struct work_struct *work)
if (smc->clcsock->sk->sk_err) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
} else if ((1 << smc->clcsock->sk->sk_state) &
- (TCPF_SYN_SENT | TCP_SYN_RECV)) {
+ (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo);
if ((rc == -EPIPE) &&
((1 << smc->clcsock->sk->sk_state) &
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 72f4b72eb175..f1d323439a2a 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1822,7 +1822,7 @@ void smc_llc_link_active(struct smc_link *link)
link->smcibdev->ibdev->name, link->ibport);
link->state = SMC_LNK_ACTIVE;
if (link->lgr->llc_testlink_time) {
- link->llc_testlink_time = link->lgr->llc_testlink_time * HZ;
+ link->llc_testlink_time = link->lgr->llc_testlink_time;
schedule_delayed_work(&link->llc_testlink_wrk,
link->llc_testlink_time);
}
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c9391d38de85..dc60c32bb70d 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -2285,43 +2285,53 @@ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr)
u16 key_gen = msg_key_gen(hdr);
u16 size = msg_data_sz(hdr);
u8 *data = msg_data(hdr);
+ unsigned int keylen;
+
+ /* Verify whether the size can exist in the packet */
+ if (unlikely(size < sizeof(struct tipc_aead_key) + TIPC_AEAD_KEYLEN_MIN)) {
+ pr_debug("%s: message data size is too small\n", rx->name);
+ goto exit;
+ }
+
+ keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+
+ /* Verify the supplied size values */
+ if (unlikely(size != keylen + sizeof(struct tipc_aead_key) ||
+ keylen > TIPC_AEAD_KEY_SIZE_MAX)) {
+ pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name);
+ goto exit;
+ }
spin_lock(&rx->lock);
if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) {
pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name,
rx->skey, key_gen, rx->key_gen);
- goto exit;
+ goto exit_unlock;
}
/* Allocate memory for the key */
skey = kmalloc(size, GFP_ATOMIC);
if (unlikely(!skey)) {
pr_err("%s: unable to allocate memory for skey\n", rx->name);
- goto exit;
+ goto exit_unlock;
}
/* Copy key from msg data */
- skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+ skey->keylen = keylen;
memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME);
memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32),
skey->keylen);
- /* Sanity check */
- if (unlikely(size != tipc_aead_key_size(skey))) {
- kfree(skey);
- skey = NULL;
- goto exit;
- }
-
rx->key_gen = key_gen;
rx->skey_mode = msg_key_mode(hdr);
rx->skey = skey;
rx->nokey = 0;
mb(); /* for nokey flag */
-exit:
+exit_unlock:
spin_unlock(&rx->lock);
+exit:
/* Schedule the key attaching on this crypto */
if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0)))
return true;
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index fde56ff49163..9ab81db8a654 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -681,12 +681,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg;
- prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read;
+ prot[TLS_BASE][TLS_SW].sock_is_readable = tls_sw_sock_is_readable;
prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close;
prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg;
- prot[TLS_SW][TLS_SW].stream_memory_read = tls_sw_stream_read;
+ prot[TLS_SW][TLS_SW].sock_is_readable = tls_sw_sock_is_readable;
prot[TLS_SW][TLS_SW].close = tls_sk_proto_close;
#ifdef CONFIG_TLS_DEVICE
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4feb95e34b64..1b08b877a890 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -35,6 +35,7 @@
* SOFTWARE.
*/
+#include <linux/bug.h>
#include <linux/sched/signal.h>
#include <linux/module.h>
#include <linux/splice.h>
@@ -43,6 +44,14 @@
#include <net/strparser.h>
#include <net/tls.h>
+noinline void tls_err_abort(struct sock *sk, int err)
+{
+ WARN_ON_ONCE(err >= 0);
+ /* sk->sk_err should contain a positive error code. */
+ sk->sk_err = -err;
+ sk_error_report(sk);
+}
+
static int __skb_nsg(struct sk_buff *skb, int offset, int len,
unsigned int recursion_level)
{
@@ -419,7 +428,7 @@ int tls_tx_records(struct sock *sk, int flags)
tx_err:
if (rc < 0 && rc != -EAGAIN)
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
return rc;
}
@@ -450,7 +459,7 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
/* If err is already set on socket, return the same code */
if (sk->sk_err) {
- ctx->async_wait.err = sk->sk_err;
+ ctx->async_wait.err = -sk->sk_err;
} else {
ctx->async_wait.err = err;
tls_err_abort(sk, err);
@@ -763,7 +772,7 @@ static int tls_push_record(struct sock *sk, int flags,
msg_pl->sg.size + prot->tail_size, i);
if (rc < 0) {
if (rc != -EINPROGRESS) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (split) {
tls_ctx->pending_open_record_frags = true;
tls_merge_open_record(sk, rec, tmp, orig_end);
@@ -1827,7 +1836,7 @@ int tls_sw_recvmsg(struct sock *sk,
err = decrypt_skb_update(sk, skb, &msg->msg_iter,
&chunk, &zc, async_capable);
if (err < 0 && err != -EINPROGRESS) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
goto recv_end;
}
@@ -2007,7 +2016,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
}
if (err < 0) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
goto splice_read_end;
}
ctx->decrypted = 1;
@@ -2026,7 +2035,7 @@ splice_read_end:
return copied ? : err;
}
-bool tls_sw_stream_read(const struct sock *sk)
+bool tls_sw_sock_is_readable(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 89f9e85ae970..78e08e82c08c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3052,6 +3052,8 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
@@ -3091,6 +3093,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (sk->sk_type == SOCK_SEQPACKET) {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b927e2baae50..452376c6f419 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -102,6 +102,7 @@ static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void unix_stream_bpf_rebuild_protos(struct proto *prot,
@@ -110,6 +111,7 @@ static void unix_stream_bpf_rebuild_protos(struct proto *prot,
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
prot->unhash = sock_map_unhash;
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 03323121ca50..aaba847d79eb 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -524,6 +524,7 @@ use_default_name:
INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk);
INIT_WORK(&rdev->mgmt_registrations_update_wk,
cfg80211_mgmt_registrations_update_wk);
+ spin_lock_init(&rdev->mgmt_registrations_lock);
#ifdef CONFIG_CFG80211_DEFAULT_PS
rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -1279,7 +1280,6 @@ void cfg80211_init_wdev(struct wireless_dev *wdev)
INIT_LIST_HEAD(&wdev->event_list);
spin_lock_init(&wdev->event_lock);
INIT_LIST_HEAD(&wdev->mgmt_registrations);
- spin_lock_init(&wdev->mgmt_registrations_lock);
INIT_LIST_HEAD(&wdev->pmsr_list);
spin_lock_init(&wdev->pmsr_lock);
INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index b35d0db12f1d..1720abf36f92 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -100,6 +100,8 @@ struct cfg80211_registered_device {
struct work_struct propagate_cac_done_wk;
struct work_struct mgmt_registrations_update_wk;
+ /* lock for all wdev lists */
+ spinlock_t mgmt_registrations_lock;
/* must be last because of the way we do wiphy_priv(),
* and it should at least be aligned to NETDEV_ALIGN */
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 3aa69b375a10..783acd2c4211 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -452,9 +452,9 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev)
lockdep_assert_held(&rdev->wiphy.mtx);
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
if (!wdev->mgmt_registrations_need_update) {
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
return;
}
@@ -479,7 +479,7 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev)
rcu_read_unlock();
wdev->mgmt_registrations_need_update = 0;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
rdev_update_mgmt_frame_registrations(rdev, wdev, &upd);
}
@@ -503,6 +503,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
int match_len, bool multicast_rx,
struct netlink_ext_ack *extack)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_mgmt_registration *reg, *nreg;
int err = 0;
u16 mgmt_type;
@@ -548,7 +549,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
if (!nreg)
return -ENOMEM;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry(reg, &wdev->mgmt_registrations, list) {
int mlen = min(match_len, reg->match_len);
@@ -583,7 +584,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
list_add(&nreg->list, &wdev->mgmt_registrations);
}
wdev->mgmt_registrations_need_update = 1;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
cfg80211_mgmt_registrations_update(wdev);
@@ -591,7 +592,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
out:
kfree(nreg);
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
return err;
}
@@ -602,7 +603,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
struct cfg80211_mgmt_registration *reg, *tmp;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) {
if (reg->nlportid != nlportid)
@@ -615,7 +616,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
schedule_work(&rdev->mgmt_registrations_update_wk);
}
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
if (nlportid && rdev->crit_proto_nlportid == nlportid) {
rdev->crit_proto_nlportid = 0;
@@ -628,15 +629,16 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_mgmt_registration *reg, *tmp;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) {
list_del(&reg->list);
kfree(reg);
}
wdev->mgmt_registrations_need_update = 1;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
cfg80211_mgmt_registrations_update(wdev);
}
@@ -784,7 +786,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm,
data = buf + ieee80211_hdrlen(mgmt->frame_control);
data_len = len - ieee80211_hdrlen(mgmt->frame_control);
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry(reg, &wdev->mgmt_registrations, list) {
if (reg->frame_type != ftype)
@@ -808,7 +810,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm,
break;
}
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
trace_cfg80211_return_bool(result);
return result;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 11c68b159324..adc0d14cfd86 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -418,14 +418,17 @@ cfg80211_add_nontrans_list(struct cfg80211_bss *trans_bss,
}
ssid_len = ssid[1];
ssid = ssid + 2;
- rcu_read_unlock();
/* check if nontrans_bss is in the list */
list_for_each_entry(bss, &trans_bss->nontrans_list, nontrans_list) {
- if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len))
+ if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) {
+ rcu_read_unlock();
return 0;
+ }
}
+ rcu_read_unlock();
+
/* add to the list */
list_add_tail(&nontrans_bss->nontrans_list, &trans_bss->nontrans_list);
return 0;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 18dba3d7c638..a1a99a574984 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1028,14 +1028,14 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
!(rdev->wiphy.interface_modes & (1 << ntype)))
return -EOPNOTSUPP;
- /* if it's part of a bridge, reject changing type to station/ibss */
- if (netif_is_bridge_port(dev) &&
- (ntype == NL80211_IFTYPE_ADHOC ||
- ntype == NL80211_IFTYPE_STATION ||
- ntype == NL80211_IFTYPE_P2P_CLIENT))
- return -EBUSY;
-
if (ntype != otype) {
+ /* if it's part of a bridge, reject changing type to station/ibss */
+ if (netif_is_bridge_port(dev) &&
+ (ntype == NL80211_IFTYPE_ADHOC ||
+ ntype == NL80211_IFTYPE_STATION ||
+ ntype == NL80211_IFTYPE_P2P_CLIENT))
+ return -EBUSY;
+
dev->ieee80211_ptr->use_4addr = false;
dev->ieee80211_ptr->mesh_id_up_len = 0;
wdev_lock(dev->ieee80211_ptr);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5cd702062a04..b856afa6eb52 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h
$(Q)$(MKDIR) -p $(OUTPUT)dlfilters
$(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $<
+.SECONDARY: $(DLFILTERS:.so=.o)
+
$(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o
$(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $<
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3018a054526a..20cd6244863b 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = {
*/
static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
{
- Dwarf_Op ops_mem[2];
+ Dwarf_Op ops_mem[3];
Dwarf_Op dummy;
Dwarf_Op *ops = &dummy;
size_t nops;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6211d0b84b7a..c32c2eb16d7d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -459,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
return -EINVAL;
if (PRINT_FIELD(WEIGHT) &&
- evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT))
+ evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT))
return -EINVAL;
if (PRINT_FIELD(SYM) &&
@@ -4039,11 +4039,15 @@ script_found:
goto out_delete;
uname(&uts);
- if (data.is_pipe || /* assume pipe_mode indicates native_arch */
- !strcmp(uts.machine, session->header.env.arch) ||
- (!strcmp(uts.machine, "x86_64") &&
- !strcmp(session->header.env.arch, "i386")))
+ if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */
native_arch = true;
+ } else if (session->header.env.arch) {
+ if (!strcmp(uts.machine, session->header.env.arch))
+ native_arch = true;
+ else if (!strcmp(uts.machine, "x86_64") &&
+ !strcmp(session->header.env.arch, "i386"))
+ native_arch = true;
+ }
script.session = session;
script__setup_sample_type(&script);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 5c5979046523..d88bb65b74cc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
int err, n;
u32 key;
char b;
- int retries = 100;
zero_verdict_count(verd_mapfd);
@@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
goto close_peer1;
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_peer1:
xclose(p1);
@@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
int sfd[2];
u32 key;
@@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close:
xclose(c1);
@@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
u32 key;
char b;
@@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_cli1:
xclose(c1);
@@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
int sfd[2];
u32 key;
@@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_cli1:
xclose(c1);
@@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
int sfd[2];
u32 key;
char b;
- int retries = 100;
zero_verdict_count(verd_mapfd);
@@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close:
xclose(c1);
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 8e67a252b672..3313566ce906 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -445,10 +445,13 @@ cleanup()
ip -netns ${NSA} link set dev ${NSA_DEV} down
ip -netns ${NSA} link del dev ${NSA_DEV}
+ ip netns pids ${NSA} | xargs kill 2>/dev/null
ip netns del ${NSA}
fi
+ ip netns pids ${NSB} | xargs kill 2>/dev/null
ip netns del ${NSB}
+ ip netns pids ${NSC} | xargs kill 2>/dev/null
ip netns del ${NSC} >/dev/null 2>&1
}
diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
index 1af16d2c2a0a..52497b7b9f1d 100644
--- a/tools/testing/selftests/vm/split_huge_page_test.c
+++ b/tools/testing/selftests/vm/split_huge_page_test.c
@@ -341,7 +341,7 @@ void split_file_backed_thp(void)
}
/* write something to the file, so a file-backed THP can be allocated */
- num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc));
+ num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1);
close(fd);
if (num_written < 1) {