diff options
317 files changed, 5361 insertions, 3635 deletions
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index f7b12c071d53..e6bd1e6512a5 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -25,7 +25,7 @@ callback, so cpufreq core can't request a transition to a specific frequency. The driver provides minimum and maximum frequency limits and callbacks to set a policy. The policy in cpufreq sysfs is referred to as the "scaling governor". The cpufreq core can request the driver to operate in any of the two policies: -"performance: and "powersave". The driver decides which frequency to use based +"performance" and "powersave". The driver decides which frequency to use based on the above policy selection considering minimum and maximum frequency limits. The Intel P-State driver falls under the latter category, which implements the diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt index a2bd593881ca..66422d663184 100644 --- a/Documentation/devicetree/bindings/arm/omap/omap.txt +++ b/Documentation/devicetree/bindings/arm/omap/omap.txt @@ -23,6 +23,7 @@ Optional properties: during suspend. - ti,no-reset-on-init: When present, the module should not be reset at init - ti,no-idle-on-init: When present, the module should not be idled at init +- ti,no-idle: When present, the module is never allowed to idle. Example: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9a53c929f017..64b5431904c3 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -193,6 +193,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. (e.g. thinkpad_acpi, sony_acpi, etc.) instead of the ACPI video.ko driver. + acpi_force_32bit_fadt_addr + force FADT to use 32 bit addresses rather than the + 64 bit X_* addresses. Some firmware have broken 64 + bit addresses for force ACPI ignore these and use + the older legacy 32 bit addresses. + acpica_no_return_repair [HW, ACPI] Disable AML predefined validation mechanism This mechanism can repair the evaluation result to make diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index daf9c0f742d2..c81731096a43 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -358,7 +358,8 @@ In the first case there are two additional complications: - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and - spte.nx=gpte.nx back. + spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when + shadow paging is in use. - if CR4.SMAP is disabled: since the page has been changed to a kernel page, it can not be reused when CR4.SMAP is enabled. We set CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, diff --git a/MAINTAINERS b/MAINTAINERS index f5e6a535bc34..6ee06ea47be4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4554,6 +4554,15 @@ S: Maintained F: drivers/net/ethernet/freescale/fs_enet/ F: include/linux/fs_enet_pd.h +FREESCALE IMX / MXC FEC DRIVER +M: Fugang Duan <fugang.duan@nxp.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/fec_main.c +F: drivers/net/ethernet/freescale/fec_ptp.c +F: drivers/net/ethernet/freescale/fec.h +F: Documentation/devicetree/bindings/net/fsl-fec.txt + FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan @@ -6770,6 +6779,7 @@ S: Maintained F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h F: net/mac80211/ +F: drivers/net/wireless/mac80211_hwsim.[ch] MACVLAN DRIVER M: Patrick McHardy <kaber@trash.net> @@ -7389,6 +7399,17 @@ W: https://www.myricom.com/support/downloads/myri10ge.html S: Supported F: drivers/net/ethernet/myricom/myri10ge/ +NAND FLASH SUBSYSTEM +M: Boris Brezillon <boris.brezillon@free-electrons.com> +R: Richard Weinberger <richard@nod.at> +L: linux-mtd@lists.infradead.org +W: http://www.linux-mtd.infradead.org/ +Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ +T: git git://github.com/linux-nand/linux.git +S: Maintained +F: drivers/mtd/nand/ +F: include/linux/mtd/nand*.h + NATSEMI ETHERNET DRIVER (DP8381x) S: Orphan F: drivers/net/ethernet/natsemi/natsemi.c @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts index 23fc670c0427..5c21b236721f 100644 --- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts +++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f774101416a5..ebe1d267406d 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -76,8 +76,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 4878d7353069..5730b875c4f5 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -95,8 +95,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index fb9e1bbf2338..8af463f26ea1 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -65,8 +65,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 6e9820e141f8..b89e6cf1271a 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 6ab33837a2b6..6522b04f4a8e 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -68,8 +68,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; internal-regs { serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index 62175a8848bc..d19f44c70925 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -64,8 +64,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index a5db17782e08..853bd392a4fe 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -65,9 +65,9 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000 + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts index 2391b11dc546..d17dab0a6f51 100644 --- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts +++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts @@ -78,8 +78,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index c4d9175b90dc..f82aa44c3cee 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1500,6 +1500,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index cfc696b972f3..fd8720532471 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -374,8 +374,13 @@ static struct pu_domain imx6q_pu_domain = { .name = "PU", .power_off = imx6q_pm_pu_power_off, .power_on = imx6q_pm_pu_power_on, - .power_off_latency_ns = 25000, - .power_on_latency_ns = 2000000, + .states = { + [0] = { + .power_off_latency_ns = 25000, + .power_on_latency_ns = 2000000, + }, + }, + .state_count = 1, }, }; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index e9f65fec55c0..b6d62e4cdfdd 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 76bce11c85a4..7c7a31169475 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm { * or idled. * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) #define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index f50608674580..819aff5d593f 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -40,7 +40,7 @@ * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ -#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE) +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) #ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) @@ -52,7 +52,8 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define VMEMMAP_START (VMALLOC_END + SZ_64K) -#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index e33fe33876ab..fd10eb663868 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -145,6 +145,10 @@ ENTRY(cpu_resume_mmu) ENDPROC(cpu_resume_mmu) .popsection cpu_resume_after_mmu: +#ifdef CONFIG_KASAN + mov x0, sp + bl kasan_unpoison_remaining_stack +#endif mov x0, #0 // return zero on success ldp x19, x20, [sp, #16] ldp x21, x22, [sp, #32] diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 82d607c3614e..da30529bb1f6 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -306,10 +306,6 @@ static __init int setup_hugepagesz(char *opt) hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); - } else if (ps == (PAGE_SIZE * CONT_PTES)) { - hugetlb_add_hstate(CONT_PTE_SHIFT); - } else if (ps == (PMD_SIZE * CONT_PMDS)) { - hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); return 0; @@ -317,13 +313,3 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); - -#ifdef CONFIG_ARM64_64K_PAGES -static __init int add_default_hugepagesz(void) -{ - if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) - hugetlb_add_hstate(CONT_PMD_SHIFT); - return 0; -} -arch_initcall(add_default_hugepagesz); -#endif diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 74a3db92da1b..d3da79dda629 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2169,7 +2169,7 @@ config MIPS_MT_SMP select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select MIPS_MT select SMP select SMP_UP @@ -2267,7 +2267,7 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2287,7 +2287,7 @@ config MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2306,6 +2306,7 @@ config MIPS_CPS_PM bool config MIPS_GIC_IPI + depends on MIPS_GIC bool config MIPS_CM diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c index 408799a839b4..f7521142deda 100644 --- a/arch/mips/boot/compressed/uart-16550.c +++ b/arch/mips/boot/compressed/uart-16550.c @@ -17,7 +17,7 @@ #define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset)) #endif -#ifdef CONFIG_MACH_JZ4740 +#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780) #include <asm/mach-jz4740/base.h> #define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset)) #endif diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a8e6e8..2b521e07b860 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -121,6 +121,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 6ee26de9a1de..25ae2c9913c3 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93ea3e3f..e485817f7b1a 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,25 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + if (mm->context.asce_limit == 0) { + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_bits = _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + mm->context.asce_limit = STACK_TOP_MAX; + } else if (mm->context.asce_limit == (1UL << 31)) { + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f158b4..d7cc79fb6191 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index c5febe84eba6..03c2b469c472 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ __HEAD ENTRY(startup_continue) - tm __LC_STFLE_FAC_LIST+6,0x80 # LPP available ? + tm __LC_STFLE_FAC_LIST+5,0x80 # LPP available ? jz 0f xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid mvi __LC_LPP,0x80 # and set LPP_MAGIC diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4af21c771f9b..03dfe9c667f4 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2381,7 +2381,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) /* manually convert vector registers if necessary */ if (MACHINE_HAS_VX) { - convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, fprs, 128); } else { diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index af30fdeb140d..f23cd8c80b1c 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -20,16 +20,15 @@ /* Supported features which support lazy state saving */ #define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ - XFEATURE_MASK_SSE) - -/* Supported features which require eager state saving */ -#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \ - XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM) +/* Supported features which require eager state saving */ +#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR) + /* All currently supported features */ #define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d25097c3fc1d..d5804adfa6da 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -409,8 +409,10 @@ static inline void copy_init_fpstate_to_fpregs(void) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, -1); - else + else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); + else + copy_kernel_to_fregs(&init_fpstate.fsave); } /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 6d9f0a7ef4c8..bd08fb77073d 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -78,13 +78,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + } #ifndef CONFIG_MATH_EMULATION if (!cpu_has_fpu) { @@ -132,7 +134,7 @@ static void __init fpu__init_system_generic(void) * Set up the legacy init FPU context. (xstate init might overwrite this * with a more modern format, if the CPU supports it.) */ - fpstate_init_fxstate(&init_fpstate.fxsave); + fpstate_init(&init_fpstate); fpu__init_system_mxcsr(); } @@ -300,12 +302,6 @@ u64 __init fpu__get_supported_xfeatures_mask(void) static void __init fpu__clear_eager_fpu_features(void) { setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); } /* diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 95a955de5964..1e7a49bfc94f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3721,13 +3721,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0ff453749a90..9bd8f44baded 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1813,6 +1813,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1850,26 +1857,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1880,16 +1892,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index e912b2f6d36e..2f07c291dcc8 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -102,7 +102,7 @@ static void delay_mwaitx(unsigned long __loops) * Use cpu_tss as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(this_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 2d66db8f80f9..ed30e79347e8 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -131,6 +131,27 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) EXPORT_SYMBOL_GPL(efi_query_variable_store); /* + * Helper function for efi_reserve_boot_services() to figure out if we + * can free regions in efi_free_boot_services(). + * + * Use this function to ensure we do not free regions owned by somebody + * else. We must only reserve (and then free) regions: + * + * - Not within any part of the kernel + * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc) + */ +static bool can_free_region(u64 start, u64 size) +{ + if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) + return false; + + if (!e820_all_mapped(start, start+size, E820_RAM)) + return false; + + return true; +} + +/* * The UEFI specification makes it clear that the operating system is free to do * whatever it wants with boot services code after ExitBootServices() has been * called. Ignoring this recommendation a significant bunch of EFI implementations @@ -147,26 +168,50 @@ void __init efi_reserve_boot_services(void) efi_memory_desc_t *md = p; u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; + bool already_reserved; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Only reserve where possible: - * - Not within any already allocated areas - * - Not over any memory area (really needed, if above?) - * - Not within any part of the kernel - * - Not the bios reserved area - */ - if ((start + size > __pa_symbol(_text) - && start <= __pa_symbol(_end)) || - !e820_all_mapped(start, start+size, E820_RAM) || - memblock_is_region_reserved(start, size)) { - /* Could not reserve, skip it */ - md->num_pages = 0; - memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", - start, start+size-1); - } else + + already_reserved = memblock_is_region_reserved(start, size); + + /* + * Because the following memblock_reserve() is paired + * with free_bootmem_late() for this region in + * efi_free_boot_services(), we must be extremely + * careful not to reserve, and subsequently free, + * critical regions of memory (like the kernel image) or + * those regions that somebody else has already + * reserved. + * + * A good example of a critical region that must not be + * freed is page zero (first 4Kb of memory), which may + * contain boot services code/data but is marked + * E820_RESERVED by trim_bios_range(). + */ + if (!already_reserved) { memblock_reserve(start, size); + + /* + * If we are the first to reserve the region, no + * one else cares about it. We own it and can + * free it later. + */ + if (can_free_region(start, size)) + continue; + } + + /* + * We don't own the region. We must not free it. + * + * Setting this bit for a boot services region really + * doesn't make sense as far as the firmware is + * concerned, but it does provide us with a way to tag + * those regions that must not be paired with + * free_bootmem_late(). + */ + md->attribute |= EFI_MEMORY_RUNTIME; } } @@ -183,8 +228,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Could not reserve boot area */ - if (!size) + /* Do not free, someone else owns it: */ + if (md->attribute & EFI_MEMORY_RUNTIME) continue; free_bootmem_late(start, size); diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index cb648a49543a..edeb2d1d99be 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -43,6 +43,7 @@ acpi-y += pci_root.o pci_link.o pci_irq.o acpi-y += acpi_lpss.o acpi_apd.o acpi-y += acpi_platform.o acpi-y += acpi_pnp.o +acpi-$(CONFIG_ARM_AMBA) += acpi_amba.o acpi-y += int340x_thermal.o acpi-y += power.o acpi-y += event.o diff --git a/drivers/acpi/acpi_amba.c b/drivers/acpi/acpi_amba.c new file mode 100644 index 000000000000..2a61b54ab968 --- /dev/null +++ b/drivers/acpi/acpi_amba.c @@ -0,0 +1,122 @@ + +/* + * ACPI support for platform bus type. + * + * Copyright (C) 2015, Linaro Ltd + * Author: Graeme Gregory <graeme.gregory@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/acpi.h> +#include <linux/amba/bus.h> +#include <linux/clkdev.h> +#include <linux/clk-provider.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/ioport.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#include "internal.h" + +static const struct acpi_device_id amba_id_list[] = { + {"ARMH0061", 0}, /* PL061 GPIO Device */ + {"", 0}, +}; + +static void amba_register_dummy_clk(void) +{ + static struct clk *amba_dummy_clk; + + /* If clock already registered */ + if (amba_dummy_clk) + return; + + amba_dummy_clk = clk_register_fixed_rate(NULL, "apb_pclk", NULL, + CLK_IS_ROOT, 0); + clk_register_clkdev(amba_dummy_clk, "apb_pclk", NULL); +} + +static int amba_handler_attach(struct acpi_device *adev, + const struct acpi_device_id *id) +{ + struct amba_device *dev; + struct resource_entry *rentry; + struct list_head resource_list; + bool address_found = false; + int irq_no = 0; + int ret; + + /* If the ACPI node already has a physical device attached, skip it. */ + if (adev->physical_node_count) + return 0; + + dev = amba_device_alloc(dev_name(&adev->dev), 0, 0); + if (!dev) { + dev_err(&adev->dev, "%s(): amba_device_alloc() failed\n", + __func__); + return -ENOMEM; + } + + INIT_LIST_HEAD(&resource_list); + ret = acpi_dev_get_resources(adev, &resource_list, NULL, NULL); + if (ret < 0) + goto err_free; + + list_for_each_entry(rentry, &resource_list, node) { + switch (resource_type(rentry->res)) { + case IORESOURCE_MEM: + if (!address_found) { + dev->res = *rentry->res; + address_found = true; + } + break; + case IORESOURCE_IRQ: + if (irq_no < AMBA_NR_IRQS) + dev->irq[irq_no++] = rentry->res->start; + break; + default: + dev_warn(&adev->dev, "Invalid resource\n"); + break; + } + } + + acpi_dev_free_resource_list(&resource_list); + + /* + * If the ACPI node has a parent and that parent has a physical device + * attached to it, that physical device should be the parent of + * the amba device we are about to create. + */ + if (adev->parent) + dev->dev.parent = acpi_get_first_physical_node(adev->parent); + + ACPI_COMPANION_SET(&dev->dev, adev); + + ret = amba_device_add(dev, &iomem_resource); + if (ret) { + dev_err(&adev->dev, "%s(): amba_device_add() failed (%d)\n", + __func__, ret); + goto err_free; + } + + return 1; + +err_free: + amba_device_put(dev); + return ret; +} + +static struct acpi_scan_handler amba_handler = { + .ids = amba_id_list, + .attach = amba_handler_attach, +}; + +void __init acpi_amba_init(void) +{ + amba_register_dummy_clk(); + acpi_scan_add_handler(&amba_handler); +} diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index d507cf6deda0..d0aad06b3872 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -143,6 +143,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = { /* Generic apd devices */ #ifdef CONFIG_X86_AMD_PLATFORM_DEVICE { "AMD0010", APD_ADDR(cz_i2c_desc) }, + { "AMDI0010", APD_ADDR(cz_i2c_desc) }, { "AMD0020", APD_ADDR(cz_uart_desc) }, { "AMD0030", }, #endif diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 296b7a14893a..c3af1088bf6b 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -43,7 +43,6 @@ static const struct acpi_device_id forbidden_id_list[] = { struct platform_device *acpi_create_platform_device(struct acpi_device *adev) { struct platform_device *pdev = NULL; - struct acpi_device *acpi_parent; struct platform_device_info pdevinfo; struct resource_entry *rentry; struct list_head resource_list; @@ -82,22 +81,8 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) * attached to it, that physical device should be the parent of the * platform device we are about to create. */ - pdevinfo.parent = NULL; - acpi_parent = adev->parent; - if (acpi_parent) { - struct acpi_device_physical_node *entry; - struct list_head *list; - - mutex_lock(&acpi_parent->physical_node_lock); - list = &acpi_parent->physical_node_list; - if (!list_empty(list)) { - entry = list_first_entry(list, - struct acpi_device_physical_node, - node); - pdevinfo.parent = entry->dev; - } - mutex_unlock(&acpi_parent->physical_node_lock); - } + pdevinfo.parent = adev->parent ? + acpi_get_first_physical_node(adev->parent) : NULL; pdevinfo.name = dev_name(&adev->dev); pdevinfo.id = -1; pdevinfo.res = resources; diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 6979186dbd4b..b5e54f2da53d 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -514,7 +514,24 @@ static struct acpi_scan_handler processor_handler = { }, }; +static int acpi_processor_container_attach(struct acpi_device *dev, + const struct acpi_device_id *id) +{ + return 1; +} + +static const struct acpi_device_id processor_container_ids[] = { + { ACPI_PROCESSOR_CONTAINER_HID, }, + { } +}; + +static struct acpi_scan_handler processor_container_handler = { + .ids = processor_container_ids, + .attach = acpi_processor_container_attach, +}; + void __init acpi_processor_init(void) { acpi_scan_add_handler_with_hotplug(&processor_handler, "processor"); + acpi_scan_add_handler(&processor_container_handler); } diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index a76f8be1bfe7..4361bc98ef4c 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -218,13 +218,6 @@ struct acpi_video_device { struct thermal_cooling_device *cooling_dev; }; -static const char device_decode[][30] = { - "motherboard VGA device", - "PCI VGA device", - "AGP VGA device", - "UNKNOWN", -}; - static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data); static void acpi_video_device_rebind(struct acpi_video_bus *video); static void acpi_video_device_bind(struct acpi_video_bus *video, diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 55c8197036f3..51b073b68f16 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -165,7 +165,7 @@ ACPI_GLOBAL(u8, acpi_gbl_next_owner_id_offset); /* Initialization sequencing */ -ACPI_INIT_GLOBAL(u8, acpi_gbl_reg_methods_enabled, FALSE); +ACPI_INIT_GLOBAL(u8, acpi_gbl_namespace_initialized, FALSE); /* Misc */ diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index e4977fac9c1d..9562a10a1a18 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -85,7 +85,7 @@ union acpi_parse_object; #define ACPI_MTX_MEMORY 5 /* Debug memory tracking lists */ #define ACPI_MAX_MUTEX 5 -#define ACPI_NUM_MUTEX ACPI_MAX_MUTEX+1 +#define ACPI_NUM_MUTEX (ACPI_MAX_MUTEX+1) /* Lock structure for reader/writer interfaces */ @@ -103,11 +103,11 @@ struct acpi_rw_lock { #define ACPI_LOCK_HARDWARE 1 #define ACPI_MAX_LOCK 1 -#define ACPI_NUM_LOCK ACPI_MAX_LOCK+1 +#define ACPI_NUM_LOCK (ACPI_MAX_LOCK+1) /* This Thread ID means that the mutex is not in use (unlocked) */ -#define ACPI_MUTEX_NOT_ACQUIRED (acpi_thread_id) 0 +#define ACPI_MUTEX_NOT_ACQUIRED ((acpi_thread_id) 0) /* This Thread ID means an invalid thread ID */ diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index 9684ed61284d..022d69cb345a 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -88,7 +88,7 @@ */ acpi_status acpi_ns_initialize_objects(void); -acpi_status acpi_ns_initialize_devices(void); +acpi_status acpi_ns_initialize_devices(u32 flags); /* * nsload - Namespace loading diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index 52f6bee52d47..5faeab41e302 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -1125,7 +1125,7 @@ const union acpi_predefined_info acpi_gbl_resource_names[] = { PACKAGE_INFO(0, 0, 0, 0, 0, 0) /* Table terminator */ }; -static const union acpi_predefined_info acpi_gbl_scope_names[] = { +const union acpi_predefined_info acpi_gbl_scope_names[] = { {{"_GPE", 0, 0}}, {{"_PR_", 0, 0}}, {{"_SB_", 0, 0}}, diff --git a/drivers/acpi/acpica/dbcmds.c b/drivers/acpi/acpica/dbcmds.c index 7ec62c461280..772178c96ccf 100644 --- a/drivers/acpi/acpica/dbcmds.c +++ b/drivers/acpi/acpica/dbcmds.c @@ -348,7 +348,7 @@ void acpi_db_display_table_info(char *table_arg) } else { /* If the pointer is null, the table has been unloaded */ - ACPI_INFO((AE_INFO, "%4.4s - Table has been unloaded", + ACPI_INFO(("%4.4s - Table has been unloaded", table_desc->signature.ascii)); } } diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c index 9fee88f1c654..68f4e0f4b095 100644 --- a/drivers/acpi/acpica/dbconvert.c +++ b/drivers/acpi/acpica/dbconvert.c @@ -408,7 +408,7 @@ void acpi_db_dump_pld_buffer(union acpi_object *obj_desc) new_buffer = acpi_db_encode_pld_buffer(pld_info); if (!new_buffer) { - return; + goto exit; } /* The two bit-packed buffers should match */ @@ -479,6 +479,7 @@ void acpi_db_dump_pld_buffer(union acpi_object *obj_desc) pld_info->horizontal_offset); } - ACPI_FREE(pld_info); ACPI_FREE(new_buffer); +exit: + ACPI_FREE(pld_info); } diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index 6a72047aae1c..1982310e6d83 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -809,8 +809,7 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc, if (method_desc->method. info_flags & ACPI_METHOD_SERIALIZED_PENDING) { if (walk_state) { - ACPI_INFO((AE_INFO, - "Marking method %4.4s as Serialized " + ACPI_INFO(("Marking method %4.4s as Serialized " "because of AE_ALREADY_EXISTS error", walk_state->method_node->name. ascii)); diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c index c303e9d9266f..a91de2b4603c 100644 --- a/drivers/acpi/acpica/dsobject.c +++ b/drivers/acpi/acpica/dsobject.c @@ -524,8 +524,7 @@ acpi_ds_build_internal_package_obj(struct acpi_walk_state *walk_state, arg = arg->common.next; } - ACPI_INFO((AE_INFO, - "Actual Package length (%u) is larger than " + ACPI_INFO(("Actual Package length (%u) is larger than " "NumElements field (%u), truncated", i, element_count)); } else if (i < element_count) { diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c index 9275e626ed8d..447fa1cac64f 100644 --- a/drivers/acpi/acpica/evgpeblk.c +++ b/drivers/acpi/acpica/evgpeblk.c @@ -499,8 +499,7 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info, } if (gpe_enabled_count) { - ACPI_INFO((AE_INFO, - "Enabled %u GPEs in block %02X to %02X", + ACPI_INFO(("Enabled %u GPEs in block %02X to %02X", gpe_enabled_count, (u32)gpe_block->block_base_number, (u32)(gpe_block->block_base_number + (gpe_block->gpe_count - 1)))); diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c index 9fdd8d09141b..7dc75474c897 100644 --- a/drivers/acpi/acpica/evgpeinit.c +++ b/drivers/acpi/acpica/evgpeinit.c @@ -281,7 +281,7 @@ void acpi_ev_update_gpes(acpi_owner_id table_owner_id) } if (walk_info.count) { - ACPI_INFO((AE_INFO, "Enabled %u new GPEs", walk_info.count)); + ACPI_INFO(("Enabled %u new GPEs", walk_info.count)); } (void)acpi_ut_release_mutex(ACPI_MTX_EVENTS); diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 47092b4d633c..63924d1c737a 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -600,7 +600,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function) if (region_obj2->extra.method_REG == NULL || region_obj->region.handler == NULL || - !acpi_gbl_reg_methods_enabled) { + !acpi_gbl_namespace_initialized) { return_ACPI_STATUS(AE_OK); } diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 011df210b7b2..f74161301037 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -252,7 +252,7 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state, status = acpi_get_table_by_index(table_index, &table); if (ACPI_SUCCESS(status)) { - ACPI_INFO((AE_INFO, "Dynamic OEM Table Load:")); + ACPI_INFO(("Dynamic OEM Table Load:")); acpi_tb_print_table_header(0, table); } @@ -472,7 +472,7 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc, /* Install the new table into the local data structures */ - ACPI_INFO((AE_INFO, "Dynamic OEM Table Load:")); + ACPI_INFO(("Dynamic OEM Table Load:")); (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); status = acpi_tb_install_standard_table(ACPI_PTR_TO_PHYSADDR(table), diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c index 28eb861c44eb..5aa21c4eda1d 100644 --- a/drivers/acpi/acpica/exoparg3.c +++ b/drivers/acpi/acpica/exoparg3.c @@ -123,8 +123,10 @@ acpi_status acpi_ex_opcode_3A_0T_0R(struct acpi_walk_state *walk_state) * op is intended for use by disassemblers in order to properly * disassemble control method invocations. The opcode or group of * opcodes should be surrounded by an "if (0)" clause to ensure that - * AML interpreters never see the opcode. + * AML interpreters never see the opcode. Thus, something is + * wrong if an external opcode ever gets here. */ + ACPI_ERROR((AE_INFO, "Executed External Op")); status = AE_OK; goto cleanup; diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c index 65d58bea4320..5d59cfcef6f4 100644 --- a/drivers/acpi/acpica/nseval.c +++ b/drivers/acpi/acpica/nseval.c @@ -378,8 +378,7 @@ void acpi_ns_exec_module_code_list(void) acpi_ut_remove_reference(prev); } - ACPI_INFO((AE_INFO, - "Executed %u blocks of module-level executable AML code", + ACPI_INFO(("Executed %u blocks of module-level executable AML code", method_count)); ACPI_FREE(info); diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index bd75d46234a4..d4aa8b696ee9 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -46,6 +46,7 @@ #include "acnamesp.h" #include "acdispat.h" #include "acinterp.h" +#include "acevents.h" #define _COMPONENT ACPI_NAMESPACE ACPI_MODULE_NAME("nsinit") @@ -83,6 +84,8 @@ acpi_status acpi_ns_initialize_objects(void) ACPI_FUNCTION_TRACE(ns_initialize_objects); + ACPI_DEBUG_PRINT((ACPI_DB_EXEC, + "[Init] Completing Initialization of ACPI Objects\n")); ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "**** Starting initialization of namespace objects ****\n")); ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT, @@ -133,82 +136,108 @@ acpi_status acpi_ns_initialize_objects(void) * ******************************************************************************/ -acpi_status acpi_ns_initialize_devices(void) +acpi_status acpi_ns_initialize_devices(u32 flags) { - acpi_status status; + acpi_status status = AE_OK; struct acpi_device_walk_info info; ACPI_FUNCTION_TRACE(ns_initialize_devices); - /* Init counters */ + if (!(flags & ACPI_NO_DEVICE_INIT)) { + ACPI_DEBUG_PRINT((ACPI_DB_EXEC, + "[Init] Initializing ACPI Devices\n")); - info.device_count = 0; - info.num_STA = 0; - info.num_INI = 0; + /* Init counters */ - ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT, - "Initializing Device/Processor/Thermal objects " - "and executing _INI/_STA methods:\n")); + info.device_count = 0; + info.num_STA = 0; + info.num_INI = 0; - /* Tree analysis: find all subtrees that contain _INI methods */ + ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT, + "Initializing Device/Processor/Thermal objects " + "and executing _INI/_STA methods:\n")); - status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, FALSE, - acpi_ns_find_ini_methods, NULL, &info, - NULL); - if (ACPI_FAILURE(status)) { - goto error_exit; - } + /* Tree analysis: find all subtrees that contain _INI methods */ + + status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, FALSE, + acpi_ns_find_ini_methods, NULL, + &info, NULL); + if (ACPI_FAILURE(status)) { + goto error_exit; + } + + /* Allocate the evaluation information block */ - /* Allocate the evaluation information block */ + info.evaluate_info = + ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_evaluate_info)); + if (!info.evaluate_info) { + status = AE_NO_MEMORY; + goto error_exit; + } - info.evaluate_info = - ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_evaluate_info)); - if (!info.evaluate_info) { - status = AE_NO_MEMORY; - goto error_exit; + /* + * Execute the "global" _INI method that may appear at the root. + * This support is provided for Windows compatibility (Vista+) and + * is not part of the ACPI specification. + */ + info.evaluate_info->prefix_node = acpi_gbl_root_node; + info.evaluate_info->relative_pathname = METHOD_NAME__INI; + info.evaluate_info->parameters = NULL; + info.evaluate_info->flags = ACPI_IGNORE_RETURN_VALUE; + + status = acpi_ns_evaluate(info.evaluate_info); + if (ACPI_SUCCESS(status)) { + info.num_INI++; + } } /* - * Execute the "global" _INI method that may appear at the root. This - * support is provided for Windows compatibility (Vista+) and is not - * part of the ACPI specification. + * Run all _REG methods + * + * Note: Any objects accessed by the _REG methods will be automatically + * initialized, even if they contain executable AML (see the call to + * acpi_ns_initialize_objects below). */ - info.evaluate_info->prefix_node = acpi_gbl_root_node; - info.evaluate_info->relative_pathname = METHOD_NAME__INI; - info.evaluate_info->parameters = NULL; - info.evaluate_info->flags = ACPI_IGNORE_RETURN_VALUE; + if (!(flags & ACPI_NO_ADDRESS_SPACE_INIT)) { + ACPI_DEBUG_PRINT((ACPI_DB_EXEC, + "[Init] Executing _REG OpRegion methods\n")); - status = acpi_ns_evaluate(info.evaluate_info); - if (ACPI_SUCCESS(status)) { - info.num_INI++; + status = acpi_ev_initialize_op_regions(); + if (ACPI_FAILURE(status)) { + goto error_exit; + } } - /* Walk namespace to execute all _INIs on present devices */ + if (!(flags & ACPI_NO_DEVICE_INIT)) { - status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, FALSE, - acpi_ns_init_one_device, NULL, &info, - NULL); + /* Walk namespace to execute all _INIs on present devices */ - /* - * Any _OSI requests should be completed by now. If the BIOS has - * requested any Windows OSI strings, we will always truncate - * I/O addresses to 16 bits -- for Windows compatibility. - */ - if (acpi_gbl_osi_data >= ACPI_OSI_WIN_2000) { - acpi_gbl_truncate_io_addresses = TRUE; - } + status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, FALSE, + acpi_ns_init_one_device, NULL, + &info, NULL); - ACPI_FREE(info.evaluate_info); - if (ACPI_FAILURE(status)) { - goto error_exit; - } + /* + * Any _OSI requests should be completed by now. If the BIOS has + * requested any Windows OSI strings, we will always truncate + * I/O addresses to 16 bits -- for Windows compatibility. + */ + if (acpi_gbl_osi_data >= ACPI_OSI_WIN_2000) { + acpi_gbl_truncate_io_addresses = TRUE; + } - ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT, - " Executed %u _INI methods requiring %u _STA executions " - "(examined %u objects)\n", - info.num_INI, info.num_STA, info.device_count)); + ACPI_FREE(info.evaluate_info); + if (ACPI_FAILURE(status)) { + goto error_exit; + } + + ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT, + " Executed %u _INI methods requiring %u _STA executions " + "(examined %u objects)\n", + info.num_INI, info.num_STA, + info.device_count)); + } return_ACPI_STATUS(status); diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index b661a1e013fb..4dc6108de4ff 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -267,8 +267,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, if (!reload && acpi_gbl_disable_ssdt_table_install && ACPI_COMPARE_NAME(&new_table_desc.signature, ACPI_SIG_SSDT)) { - ACPI_INFO((AE_INFO, - "Ignoring installation of %4.4s at %8.8X%8.8X", + ACPI_INFO(("Ignoring installation of %4.4s at %8.8X%8.8X", new_table_desc.signature.ascii, ACPI_FORMAT_UINT64(address))); goto release_and_exit; @@ -432,7 +431,7 @@ finish_override: return; } - ACPI_INFO((AE_INFO, "%4.4s 0x%8.8X%8.8X" + ACPI_INFO(("%4.4s 0x%8.8X%8.8X" " %s table override, new table: 0x%8.8X%8.8X", old_table_desc->signature.ascii, ACPI_FORMAT_UINT64(old_table_desc->address), diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index fd4146d4ff49..26d61dbace0a 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -132,7 +132,7 @@ acpi_tb_print_table_header(acpi_physical_address address, /* FACS only has signature and length fields */ - ACPI_INFO((AE_INFO, "%-4.4s 0x%8.8X%8.8X %06X", + ACPI_INFO(("%-4.4s 0x%8.8X%8.8X %06X", header->signature, ACPI_FORMAT_UINT64(address), header->length)); } else if (ACPI_VALIDATE_RSDP_SIG(header->signature)) { @@ -144,7 +144,7 @@ acpi_tb_print_table_header(acpi_physical_address address, ACPI_OEM_ID_SIZE); acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE); - ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)", + ACPI_INFO(("RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)", ACPI_FORMAT_UINT64(address), (ACPI_CAST_PTR(struct acpi_table_rsdp, header)-> revision > @@ -158,8 +158,7 @@ acpi_tb_print_table_header(acpi_physical_address address, acpi_tb_cleanup_table_header(&local_header, header); - ACPI_INFO((AE_INFO, - "%-4.4s 0x%8.8X%8.8X" + ACPI_INFO(("%-4.4s 0x%8.8X%8.8X" " %06X (v%.2d %-6.6s %-8.8s %08X %-4.4s %08X)", local_header.signature, ACPI_FORMAT_UINT64(address), local_header.length, local_header.revision, diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 3269bef371d7..9240c76d2823 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -174,9 +174,7 @@ struct acpi_table_header *acpi_tb_copy_dsdt(u32 table_index) ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL, new_table); - ACPI_INFO((AE_INFO, - "Forced DSDT copy: length 0x%05X copied locally, original unmapped", - new_table->length)); + ACPI_INFO(("Forced DSDT copy: length 0x%05X copied locally, original unmapped", new_table->length)); return (new_table); } diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index 278666e39563..3151968c10d1 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -47,6 +47,7 @@ #include "accommon.h" #include "acnamesp.h" #include "actables.h" +#include "acevents.h" #define _COMPONENT ACPI_TABLES ACPI_MODULE_NAME("tbxfload") @@ -68,6 +69,25 @@ acpi_status __init acpi_load_tables(void) ACPI_FUNCTION_TRACE(acpi_load_tables); + /* + * Install the default operation region handlers. These are the + * handlers that are defined by the ACPI specification to be + * "always accessible" -- namely, system_memory, system_IO, and + * PCI_Config. This also means that no _REG methods need to be + * run for these address spaces. We need to have these handlers + * installed before any AML code can be executed, especially any + * module-level code (11/2015). + * Note that we allow OSPMs to install their own region handlers + * between acpi_initialize_subsystem() and acpi_load_tables() to use + * their customized default region handlers. + */ + status = acpi_ev_install_region_handlers(); + if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) { + ACPI_EXCEPTION((AE_INFO, status, + "During Region initialization")); + return_ACPI_STATUS(status); + } + /* Load the namespace from the tables */ status = acpi_tb_load_namespace(); @@ -83,6 +103,20 @@ acpi_status __init acpi_load_tables(void) "While loading namespace from ACPI tables")); } + if (!acpi_gbl_group_module_level_code) { + /* + * Initialize the objects that remain uninitialized. This + * runs the executable AML that may be part of the + * declaration of these objects: + * operation_regions, buffer_fields, Buffers, and Packages. + */ + status = acpi_ns_initialize_objects(); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + } + + acpi_gbl_namespace_initialized = TRUE; return_ACPI_STATUS(status); } @@ -206,9 +240,7 @@ acpi_status acpi_tb_load_namespace(void) } if (!tables_failed) { - ACPI_INFO((AE_INFO, - "%u ACPI AML tables successfully acquired and loaded\n", - tables_loaded)); + ACPI_INFO(("%u ACPI AML tables successfully acquired and loaded\n", tables_loaded)); } else { ACPI_ERROR((AE_INFO, "%u table load failures, %u successful", @@ -301,7 +333,7 @@ acpi_status acpi_load_table(struct acpi_table_header *table) /* Install the table and load it into the namespace */ - ACPI_INFO((AE_INFO, "Host-directed Dynamic ACPI Table Load:")); + ACPI_INFO(("Host-directed Dynamic ACPI Table Load:")); (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); status = acpi_tb_install_standard_table(ACPI_PTR_TO_PHYSADDR(table), diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c index c9a720f2274a..f8e9978888e1 100644 --- a/drivers/acpi/acpica/utcache.c +++ b/drivers/acpi/acpica/utcache.c @@ -245,7 +245,7 @@ void *acpi_os_acquire_object(struct acpi_memory_list *cache) acpi_status status; void *object; - ACPI_FUNCTION_NAME(os_acquire_object); + ACPI_FUNCTION_TRACE(os_acquire_object); if (!cache) { return_PTR(NULL); diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c index c427a5cda465..d5c3adf19bd0 100644 --- a/drivers/acpi/acpica/utnonansi.c +++ b/drivers/acpi/acpica/utnonansi.c @@ -140,6 +140,67 @@ int acpi_ut_stricmp(char *string1, char *string2) return (c1 - c2); } +#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION) +/******************************************************************************* + * + * FUNCTION: acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat + * + * PARAMETERS: Adds a "DestSize" parameter to each of the standard string + * functions. This is the size of the Destination buffer. + * + * RETURN: TRUE if the operation would overflow the destination buffer. + * + * DESCRIPTION: Safe versions of standard Clib string functions. Ensure that + * the result of the operation will not overflow the output string + * buffer. + * + * NOTE: These functions are typically only helpful for processing + * user input and command lines. For most ACPICA code, the + * required buffer length is precisely calculated before buffer + * allocation, so the use of these functions is unnecessary. + * + ******************************************************************************/ + +u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source) +{ + + if (strlen(source) >= dest_size) { + return (TRUE); + } + + strcpy(dest, source); + return (FALSE); +} + +u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source) +{ + + if ((strlen(dest) + strlen(source)) >= dest_size) { + return (TRUE); + } + + strcat(dest, source); + return (FALSE); +} + +u8 +acpi_ut_safe_strncat(char *dest, + acpi_size dest_size, + char *source, acpi_size max_transfer_length) +{ + acpi_size actual_transfer_length; + + actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source)); + + if ((strlen(dest) + actual_transfer_length) >= dest_size) { + return (TRUE); + } + + strncat(dest, source, max_transfer_length); + return (FALSE); +} +#endif + /******************************************************************************* * * FUNCTION: acpi_ut_strtoul64 @@ -155,7 +216,15 @@ int acpi_ut_stricmp(char *string1, char *string2) * 32-bit or 64-bit conversion, depending on the current mode * of the interpreter. * - * NOTE: Does not support Octal strings, not needed. + * NOTES: acpi_gbl_integer_byte_width should be set to the proper width. + * For the core ACPICA code, this width depends on the DSDT + * version. For iASL, the default byte width is always 8. + * + * Does not support Octal strings, not needed at this time. + * + * There is an earlier version of the function after this one, + * below. It is slightly different than this one, and the two + * may eventually may need to be merged. (01/2016). * ******************************************************************************/ @@ -171,7 +240,7 @@ acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer) u8 sign_of0x = 0; u8 term = 0; - ACPI_FUNCTION_TRACE_STR(ut_stroul64, string); + ACPI_FUNCTION_TRACE_STR(ut_strtoul64, string); switch (base) { case ACPI_ANY_BASE: @@ -318,63 +387,162 @@ error_exit: } } -#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION) +#ifdef _OBSOLETE_FUNCTIONS +/* TBD: use version in ACPICA main code base? */ +/* DONE: 01/2016 */ + /******************************************************************************* * - * FUNCTION: acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat + * FUNCTION: strtoul64 * - * PARAMETERS: Adds a "DestSize" parameter to each of the standard string - * functions. This is the size of the Destination buffer. + * PARAMETERS: string - Null terminated string + * terminater - Where a pointer to the terminating byte + * is returned + * base - Radix of the string * - * RETURN: TRUE if the operation would overflow the destination buffer. + * RETURN: Converted value * - * DESCRIPTION: Safe versions of standard Clib string functions. Ensure that - * the result of the operation will not overflow the output string - * buffer. - * - * NOTE: These functions are typically only helpful for processing - * user input and command lines. For most ACPICA code, the - * required buffer length is precisely calculated before buffer - * allocation, so the use of these functions is unnecessary. + * DESCRIPTION: Convert a string into an unsigned value. * ******************************************************************************/ -u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source) +acpi_status strtoul64(char *string, u32 base, u64 *ret_integer) { + u32 index; + u32 sign; + u64 return_value = 0; + acpi_status status = AE_OK; - if (strlen(source) >= dest_size) { - return (TRUE); + *ret_integer = 0; + + switch (base) { + case 0: + case 8: + case 10: + case 16: + + break; + + default: + /* + * The specified Base parameter is not in the domain of + * this function: + */ + return (AE_BAD_PARAMETER); } - strcpy(dest, source); - return (FALSE); -} + /* Skip over any white space in the buffer: */ -u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source) -{ + while (isspace((int)*string) || *string == '\t') { + ++string; + } - if ((strlen(dest) + strlen(source)) >= dest_size) { - return (TRUE); + /* + * The buffer may contain an optional plus or minus sign. + * If it does, then skip over it but remember what is was: + */ + if (*string == '-') { + sign = ACPI_SIGN_NEGATIVE; + ++string; + } else if (*string == '+') { + ++string; + sign = ACPI_SIGN_POSITIVE; + } else { + sign = ACPI_SIGN_POSITIVE; } - strcat(dest, source); - return (FALSE); -} + /* + * If the input parameter Base is zero, then we need to + * determine if it is octal, decimal, or hexadecimal: + */ + if (base == 0) { + if (*string == '0') { + if (tolower((int)*(++string)) == 'x') { + base = 16; + ++string; + } else { + base = 8; + } + } else { + base = 10; + } + } -u8 -acpi_ut_safe_strncat(char *dest, - acpi_size dest_size, - char *source, acpi_size max_transfer_length) -{ - acpi_size actual_transfer_length; + /* + * For octal and hexadecimal bases, skip over the leading + * 0 or 0x, if they are present. + */ + if (base == 8 && *string == '0') { + string++; + } - actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source)); + if (base == 16 && *string == '0' && tolower((int)*(++string)) == 'x') { + string++; + } - if ((strlen(dest) + actual_transfer_length) >= dest_size) { - return (TRUE); + /* Main loop: convert the string to an unsigned long */ + + while (*string) { + if (isdigit((int)*string)) { + index = ((u8)*string) - '0'; + } else { + index = (u8)toupper((int)*string); + if (isupper((int)index)) { + index = index - 'A' + 10; + } else { + goto error_exit; + } + } + + if (index >= base) { + goto error_exit; + } + + /* Check to see if value is out of range: */ + + if (return_value > ((ACPI_UINT64_MAX - (u64)index) / (u64)base)) { + goto error_exit; + } else { + return_value *= base; + return_value += index; + } + + ++string; } - strncat(dest, source, max_transfer_length); - return (FALSE); + /* If a minus sign was present, then "the conversion is negated": */ + + if (sign == ACPI_SIGN_NEGATIVE) { + return_value = (ACPI_UINT32_MAX - return_value) + 1; + } + + *ret_integer = return_value; + return (status); + +error_exit: + switch (base) { + case 8: + + status = AE_BAD_OCTAL_CONSTANT; + break; + + case 10: + + status = AE_BAD_DECIMAL_CONSTANT; + break; + + case 16: + + status = AE_BAD_HEX_CONSTANT; + break; + + default: + + /* Base validated above */ + + break; + } + + return (status); } #endif diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c index c7c2bb8f3559..60c406a8efcb 100644 --- a/drivers/acpi/acpica/uttrack.c +++ b/drivers/acpi/acpica/uttrack.c @@ -712,7 +712,7 @@ void acpi_ut_dump_allocations(u32 component, const char *module) /* Print summary */ if (!num_outstanding) { - ACPI_INFO((AE_INFO, "No outstanding allocations")); + ACPI_INFO(("No outstanding allocations")); } else { ACPI_ERROR((AE_INFO, "%u(0x%X) Outstanding allocations", num_outstanding, num_outstanding)); diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c index 6fe59597b599..d9f15cbcd8a0 100644 --- a/drivers/acpi/acpica/utxferror.c +++ b/drivers/acpi/acpica/utxferror.c @@ -175,8 +175,7 @@ ACPI_EXPORT_SYMBOL(acpi_warning) * TBD: module_name and line_number args are not needed, should be removed. * ******************************************************************************/ -void ACPI_INTERNAL_VAR_XFACE -acpi_info(const char *module_name, u32 line_number, const char *format, ...) +void ACPI_INTERNAL_VAR_XFACE acpi_info(const char *format, ...) { va_list arg_list; diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index 721b87cce908..75b5f27da267 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -154,21 +154,6 @@ acpi_status __init acpi_enable_subsystem(u32 flags) */ acpi_gbl_early_initialization = FALSE; - /* - * Install the default operation region handlers. These are the - * handlers that are defined by the ACPI specification to be - * "always accessible" -- namely, system_memory, system_IO, and - * PCI_Config. This also means that no _REG methods need to be - * run for these address spaces. We need to have these handlers - * installed before any AML code can be executed, especially any - * module-level code (11/2015). - */ - status = acpi_ev_install_region_handlers(); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "During Region initialization")); - return_ACPI_STATUS(status); - } #if (!ACPI_REDUCED_HARDWARE) /* Enable ACPI mode */ @@ -260,23 +245,6 @@ acpi_status __init acpi_initialize_objects(u32 flags) ACPI_FUNCTION_TRACE(acpi_initialize_objects); - /* - * Run all _REG methods - * - * Note: Any objects accessed by the _REG methods will be automatically - * initialized, even if they contain executable AML (see the call to - * acpi_ns_initialize_objects below). - */ - acpi_gbl_reg_methods_enabled = TRUE; - if (!(flags & ACPI_NO_ADDRESS_SPACE_INIT)) { - ACPI_DEBUG_PRINT((ACPI_DB_EXEC, - "[Init] Executing _REG OpRegion methods\n")); - - status = acpi_ev_initialize_op_regions(); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); - } - } #ifdef ACPI_EXEC_APP /* * This call implements the "initialization file" option for acpi_exec. @@ -299,32 +267,27 @@ acpi_status __init acpi_initialize_objects(u32 flags) */ if (acpi_gbl_group_module_level_code) { acpi_ns_exec_module_code_list(); - } - - /* - * Initialize the objects that remain uninitialized. This runs the - * executable AML that may be part of the declaration of these objects: - * operation_regions, buffer_fields, Buffers, and Packages. - */ - if (!(flags & ACPI_NO_OBJECT_INIT)) { - ACPI_DEBUG_PRINT((ACPI_DB_EXEC, - "[Init] Completing Initialization of ACPI Objects\n")); - status = acpi_ns_initialize_objects(); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); + /* + * Initialize the objects that remain uninitialized. This + * runs the executable AML that may be part of the + * declaration of these objects: + * operation_regions, buffer_fields, Buffers, and Packages. + */ + if (!(flags & ACPI_NO_OBJECT_INIT)) { + status = acpi_ns_initialize_objects(); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } } } /* - * Initialize all device objects in the namespace. This runs the device - * _STA and _INI methods. + * Initialize all device/region objects in the namespace. This runs + * the device _STA and _INI methods and region _REG methods. */ - if (!(flags & ACPI_NO_DEVICE_INIT)) { - ACPI_DEBUG_PRINT((ACPI_DB_EXEC, - "[Init] Initializing ACPI Devices\n")); - - status = acpi_ns_initialize_devices(); + if (!(flags & (ACPI_NO_DEVICE_INIT | ACPI_NO_ADDRESS_SPACE_INIT))) { + status = acpi_ns_initialize_devices(flags); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index a2c8d7adb6eb..da370e1d31f4 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -536,7 +536,8 @@ int apei_resources_request(struct apei_resources *resources, goto err_unmap_ioport; } - return 0; + goto arch_res_fini; + err_unmap_ioport: list_for_each_entry(res, &resources->ioport, list) { if (res == res_bak) @@ -551,7 +552,8 @@ err_unmap_iomem: release_mem_region(res->start, res->end - res->start); } arch_res_fini: - apei_resources_fini(&arch_res); + if (arch_apei_filter_addr) + apei_resources_fini(&arch_res); nvs_res_fini: apei_resources_fini(&nvs_resources); return rc; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 6e6bc1059301..006c3894c6ea 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -1207,6 +1207,9 @@ static int __init erst_init(void) "Failed to allocate %lld bytes for persistent store error log.\n", erst_erange.size); + /* Cleanup ERST Resources */ + apei_resources_fini(&erst_resources); + return 0; err_release_erange: diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 3dd9c462d22a..60746ef904e4 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -26,7 +26,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/init.h> #include <linux/acpi.h> #include <linux/io.h> @@ -79,6 +79,11 @@ ((struct acpi_hest_generic_status *) \ ((struct ghes_estatus_node *)(estatus_node) + 1)) +/* + * This driver isn't really modular, however for the time being, + * continuing to use module_param is the easiest way to remain + * compatible with existing boot arg use cases. + */ bool ghes_disable; module_param_named(disable, ghes_disable, bool, 0); @@ -1148,18 +1153,4 @@ err_ioremap_exit: err: return rc; } - -static void __exit ghes_exit(void) -{ - platform_driver_unregister(&ghes_platform_driver); - ghes_estatus_pool_exit(); - ghes_ioremap_exit(); -} - -module_init(ghes_init); -module_exit(ghes_exit); - -MODULE_AUTHOR("Huang Ying"); -MODULE_DESCRIPTION("APEI Generic Hardware Error Source support"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:GHES"); +device_initcall(ghes_init); diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c index a83e3c62c5a9..75f128e766a9 100644 --- a/drivers/acpi/bgrt.c +++ b/drivers/acpi/bgrt.c @@ -1,4 +1,6 @@ /* + * BGRT boot graphic support + * Authors: Matthew Garrett, Josh Triplett <josh@joshtriplett.org> * Copyright 2012 Red Hat, Inc <mjg@redhat.com> * Copyright 2012 Intel Corporation * @@ -8,7 +10,6 @@ */ #include <linux/kernel.h> -#include <linux/module.h> #include <linux/init.h> #include <linux/device.h> #include <linux/sysfs.h> @@ -103,9 +104,4 @@ out_kobject: kobject_put(bgrt_kobj); return ret; } - -module_init(bgrt_init); - -MODULE_AUTHOR("Matthew Garrett, Josh Triplett <josh@joshtriplett.org>"); -MODULE_DESCRIPTION("BGRT boot graphic support"); -MODULE_LICENSE("GPL"); +device_initcall(bgrt_init); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 891c42d1cd65..0e8567846f1a 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -479,24 +479,38 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device) Device Matching -------------------------------------------------------------------------- */ -static struct acpi_device *acpi_primary_dev_companion(struct acpi_device *adev, - const struct device *dev) +/** + * acpi_get_first_physical_node - Get first physical node of an ACPI device + * @adev: ACPI device in question + * + * Return: First physical node of ACPI device @adev + */ +struct device *acpi_get_first_physical_node(struct acpi_device *adev) { struct mutex *physical_node_lock = &adev->physical_node_lock; + struct device *phys_dev; mutex_lock(physical_node_lock); if (list_empty(&adev->physical_node_list)) { - adev = NULL; + phys_dev = NULL; } else { const struct acpi_device_physical_node *node; node = list_first_entry(&adev->physical_node_list, struct acpi_device_physical_node, node); - if (node->dev != dev) - adev = NULL; + + phys_dev = node->dev; } mutex_unlock(physical_node_lock); - return adev; + return phys_dev; +} + +static struct acpi_device *acpi_primary_dev_companion(struct acpi_device *adev, + const struct device *dev) +{ + const struct device *phys_dev = acpi_get_first_physical_node(adev); + + return phys_dev && phys_dev == dev ? adev : NULL; } /** diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 6730f965b379..8adac69dba3d 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -39,6 +39,7 @@ #include <linux/cpufreq.h> #include <linux/delay.h> +#include <linux/ktime.h> #include <acpi/cppc_acpi.h> /* @@ -63,58 +64,140 @@ static struct mbox_chan *pcc_channel; static void __iomem *pcc_comm_addr; static u64 comm_base_addr; static int pcc_subspace_idx = -1; -static u16 pcc_cmd_delay; static bool pcc_channel_acquired; +static ktime_t deadline; +static unsigned int pcc_mpar, pcc_mrtt; + +/* pcc mapped address + header size + offset within PCC subspace */ +#define GET_PCC_VADDR(offs) (pcc_comm_addr + 0x8 + (offs)) /* * Arbitrary Retries in case the remote processor is slow to respond - * to PCC commands. + * to PCC commands. Keeping it high enough to cover emulators where + * the processors run painfully slow. */ #define NUM_RETRIES 500 +static int check_pcc_chan(void) +{ + int ret = -EIO; + struct acpi_pcct_shared_memory __iomem *generic_comm_base = pcc_comm_addr; + ktime_t next_deadline = ktime_add(ktime_get(), deadline); + + /* Retry in case the remote processor was too slow to catch up. */ + while (!ktime_after(ktime_get(), next_deadline)) { + /* + * Per spec, prior to boot the PCC space wil be initialized by + * platform and should have set the command completion bit when + * PCC can be used by OSPM + */ + if (readw_relaxed(&generic_comm_base->status) & PCC_CMD_COMPLETE) { + ret = 0; + break; + } + /* + * Reducing the bus traffic in case this loop takes longer than + * a few retries. + */ + udelay(3); + } + + return ret; +} + static int send_pcc_cmd(u16 cmd) { - int retries, result = -EIO; - struct acpi_pcct_hw_reduced *pcct_ss = pcc_channel->con_priv; + int ret = -EIO; struct acpi_pcct_shared_memory *generic_comm_base = (struct acpi_pcct_shared_memory *) pcc_comm_addr; - u32 cmd_latency = pcct_ss->latency; + static ktime_t last_cmd_cmpl_time, last_mpar_reset; + static int mpar_count; + unsigned int time_delta; - /* Min time OS should wait before sending next command. */ - udelay(pcc_cmd_delay); + /* + * For CMD_WRITE we know for a fact the caller should have checked + * the channel before writing to PCC space + */ + if (cmd == CMD_READ) { + ret = check_pcc_chan(); + if (ret) + return ret; + } + + /* + * Handle the Minimum Request Turnaround Time(MRTT) + * "The minimum amount of time that OSPM must wait after the completion + * of a command before issuing the next command, in microseconds" + */ + if (pcc_mrtt) { + time_delta = ktime_us_delta(ktime_get(), last_cmd_cmpl_time); + if (pcc_mrtt > time_delta) + udelay(pcc_mrtt - time_delta); + } + + /* + * Handle the non-zero Maximum Periodic Access Rate(MPAR) + * "The maximum number of periodic requests that the subspace channel can + * support, reported in commands per minute. 0 indicates no limitation." + * + * This parameter should be ideally zero or large enough so that it can + * handle maximum number of requests that all the cores in the system can + * collectively generate. If it is not, we will follow the spec and just + * not send the request to the platform after hitting the MPAR limit in + * any 60s window + */ + if (pcc_mpar) { + if (mpar_count == 0) { + time_delta = ktime_ms_delta(ktime_get(), last_mpar_reset); + if (time_delta < 60 * MSEC_PER_SEC) { + pr_debug("PCC cmd not sent due to MPAR limit"); + return -EIO; + } + last_mpar_reset = ktime_get(); + mpar_count = pcc_mpar; + } + mpar_count--; + } /* Write to the shared comm region. */ - writew(cmd, &generic_comm_base->command); + writew_relaxed(cmd, &generic_comm_base->command); /* Flip CMD COMPLETE bit */ - writew(0, &generic_comm_base->status); + writew_relaxed(0, &generic_comm_base->status); /* Ring doorbell */ - result = mbox_send_message(pcc_channel, &cmd); - if (result < 0) { + ret = mbox_send_message(pcc_channel, &cmd); + if (ret < 0) { pr_err("Err sending PCC mbox message. cmd:%d, ret:%d\n", - cmd, result); - return result; + cmd, ret); + return ret; } - /* Wait for a nominal time to let platform process command. */ - udelay(cmd_latency); - - /* Retry in case the remote processor was too slow to catch up. */ - for (retries = NUM_RETRIES; retries > 0; retries--) { - if (readw_relaxed(&generic_comm_base->status) & PCC_CMD_COMPLETE) { - result = 0; - break; - } + /* + * For READs we need to ensure the cmd completed to ensure + * the ensuing read()s can proceed. For WRITEs we dont care + * because the actual write()s are done before coming here + * and the next READ or WRITE will check if the channel + * is busy/free at the entry of this call. + * + * If Minimum Request Turnaround Time is non-zero, we need + * to record the completion time of both READ and WRITE + * command for proper handling of MRTT, so we need to check + * for pcc_mrtt in addition to CMD_READ + */ + if (cmd == CMD_READ || pcc_mrtt) { + ret = check_pcc_chan(); + if (pcc_mrtt) + last_cmd_cmpl_time = ktime_get(); } - mbox_client_txdone(pcc_channel, result); - return result; + mbox_client_txdone(pcc_channel, ret); + return ret; } static void cppc_chan_tx_done(struct mbox_client *cl, void *msg, int ret) { - if (ret) + if (ret < 0) pr_debug("TX did not complete: CMD sent:%x, ret:%d\n", *(u16 *)msg, ret); else @@ -306,6 +389,7 @@ static int register_pcc_channel(int pcc_subspace_idx) { struct acpi_pcct_hw_reduced *cppc_ss; unsigned int len; + u64 usecs_lat; if (pcc_subspace_idx >= 0) { pcc_channel = pcc_mbox_request_channel(&cppc_mbox_cl, @@ -335,7 +419,16 @@ static int register_pcc_channel(int pcc_subspace_idx) */ comm_base_addr = cppc_ss->base_address; len = cppc_ss->length; - pcc_cmd_delay = cppc_ss->min_turnaround_time; + + /* + * cppc_ss->latency is just a Nominal value. In reality + * the remote processor could be much slower to reply. + * So add an arbitrary amount of wait on top of Nominal. + */ + usecs_lat = NUM_RETRIES * cppc_ss->latency; + deadline = ns_to_ktime(usecs_lat * NSEC_PER_USEC); + pcc_mrtt = cppc_ss->min_turnaround_time; + pcc_mpar = cppc_ss->max_access_rate; pcc_comm_addr = acpi_os_ioremap(comm_base_addr, len); if (!pcc_comm_addr) { @@ -546,29 +639,74 @@ void acpi_cppc_processor_exit(struct acpi_processor *pr) } EXPORT_SYMBOL_GPL(acpi_cppc_processor_exit); -static u64 get_phys_addr(struct cpc_reg *reg) -{ - /* PCC communication addr space begins at byte offset 0x8. */ - if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) - return (u64)comm_base_addr + 0x8 + reg->address; - else - return reg->address; -} +/* + * Since cpc_read and cpc_write are called while holding pcc_lock, it should be + * as fast as possible. We have already mapped the PCC subspace during init, so + * we can directly write to it. + */ -static void cpc_read(struct cpc_reg *reg, u64 *val) +static int cpc_read(struct cpc_reg *reg, u64 *val) { - u64 addr = get_phys_addr(reg); + int ret_val = 0; - acpi_os_read_memory((acpi_physical_address)addr, - val, reg->bit_width); + *val = 0; + if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + void __iomem *vaddr = GET_PCC_VADDR(reg->address); + + switch (reg->bit_width) { + case 8: + *val = readb_relaxed(vaddr); + break; + case 16: + *val = readw_relaxed(vaddr); + break; + case 32: + *val = readl_relaxed(vaddr); + break; + case 64: + *val = readq_relaxed(vaddr); + break; + default: + pr_debug("Error: Cannot read %u bit width from PCC\n", + reg->bit_width); + ret_val = -EFAULT; + } + } else + ret_val = acpi_os_read_memory((acpi_physical_address)reg->address, + val, reg->bit_width); + return ret_val; } -static void cpc_write(struct cpc_reg *reg, u64 val) +static int cpc_write(struct cpc_reg *reg, u64 val) { - u64 addr = get_phys_addr(reg); + int ret_val = 0; - acpi_os_write_memory((acpi_physical_address)addr, - val, reg->bit_width); + if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + void __iomem *vaddr = GET_PCC_VADDR(reg->address); + + switch (reg->bit_width) { + case 8: + writeb_relaxed(val, vaddr); + break; + case 16: + writew_relaxed(val, vaddr); + break; + case 32: + writel_relaxed(val, vaddr); + break; + case 64: + writeq_relaxed(val, vaddr); + break; + default: + pr_debug("Error: Cannot write %u bit width to PCC\n", + reg->bit_width); + ret_val = -EFAULT; + break; + } + } else + ret_val = acpi_os_write_memory((acpi_physical_address)reg->address, + val, reg->bit_width); + return ret_val; } /** @@ -604,7 +742,7 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) (ref_perf->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) || (nom_perf->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM)) { /* Ring doorbell once to update PCC subspace */ - if (send_pcc_cmd(CMD_READ)) { + if (send_pcc_cmd(CMD_READ) < 0) { ret = -EIO; goto out_err; } @@ -662,7 +800,7 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs) if ((delivered_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) || (reference_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM)) { /* Ring doorbell once to update PCC subspace */ - if (send_pcc_cmd(CMD_READ)) { + if (send_pcc_cmd(CMD_READ) < 0) { ret = -EIO; goto out_err; } @@ -713,6 +851,13 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) spin_lock(&pcc_lock); + /* If this is PCC reg, check if channel is free before writing */ + if (desired_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + ret = check_pcc_chan(); + if (ret) + goto busy_channel; + } + /* * Skip writing MIN/MAX until Linux knows how to come up with * useful values. @@ -722,10 +867,10 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) /* Is this a PCC reg ?*/ if (desired_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { /* Ring doorbell so Remote can get our perf request. */ - if (send_pcc_cmd(CMD_WRITE)) + if (send_pcc_cmd(CMD_WRITE) < 0) ret = -EIO; } - +busy_channel: spin_unlock(&pcc_lock); return ret; diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c index bea8e425a8de..6c7dd7af789e 100644 --- a/drivers/acpi/ec_sys.c +++ b/drivers/acpi/ec_sys.c @@ -73,6 +73,9 @@ static ssize_t acpi_ec_write_io(struct file *f, const char __user *buf, loff_t init_off = *off; int err = 0; + if (!write_support) + return -EINVAL; + if (*off >= EC_SPACE_SIZE) return 0; if (*off + count >= EC_SPACE_SIZE) { diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 6322db64b4a4..384cfc3083e1 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -46,7 +46,7 @@ MODULE_DEVICE_TABLE(acpi, fan_device_ids); #ifdef CONFIG_PM_SLEEP static int acpi_fan_suspend(struct device *dev); static int acpi_fan_resume(struct device *dev); -static struct dev_pm_ops acpi_fan_pm = { +static const struct dev_pm_ops acpi_fan_pm = { .resume = acpi_fan_resume, .freeze = acpi_fan_suspend, .thaw = acpi_fan_resume, diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 1e6833a5cd44..a37508ef66c1 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -20,6 +20,7 @@ #define PREFIX "ACPI: " +void acpi_initrd_initialize_tables(void); acpi_status acpi_os_initialize1(void); void init_acpi_device_notify(void); int acpi_scan_init(void); @@ -29,6 +30,11 @@ void acpi_processor_init(void); void acpi_platform_init(void); void acpi_pnp_init(void); void acpi_int340x_thermal_init(void); +#ifdef CONFIG_ARM_AMBA +void acpi_amba_init(void); +#else +static inline void acpi_amba_init(void) {} +#endif int acpi_sysfs_init(void); void acpi_container_init(void); void acpi_memory_hotplug_init(void); @@ -106,6 +112,7 @@ bool acpi_device_is_present(struct acpi_device *adev); bool acpi_device_is_battery(struct acpi_device *adev); bool acpi_device_is_first_physical_node(struct acpi_device *adev, const struct device *dev); +struct device *acpi_get_first_physical_node(struct acpi_device *adev); /* -------------------------------------------------------------------------- Device Matching and Notification diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 67da6fb72274..814d5f83b75e 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -602,6 +602,14 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val, return AE_OK; } +static void acpi_table_taint(struct acpi_table_header *table) +{ + pr_warn(PREFIX + "Override [%4.4s-%8.8s], this is unsafe: tainting kernel\n", + table->signature, table->oem_table_id); + add_taint(TAINT_OVERRIDDEN_ACPI_TABLE, LOCKDEP_NOW_UNRELIABLE); +} + #ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE #include <linux/earlycpio.h> #include <linux/memblock.h> @@ -636,6 +644,7 @@ static const char * const table_sigs[] = { #define ACPI_OVERRIDE_TABLES 64 static struct cpio_data __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES]; +static DECLARE_BITMAP(acpi_initrd_installed, ACPI_OVERRIDE_TABLES); #define MAP_CHUNK_SIZE (NR_FIX_BTMAPS << PAGE_SHIFT) @@ -746,96 +755,125 @@ void __init acpi_initrd_override(void *data, size_t size) } } } -#endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */ -static void acpi_table_taint(struct acpi_table_header *table) +acpi_status +acpi_os_physical_table_override(struct acpi_table_header *existing_table, + acpi_physical_address *address, u32 *length) { - pr_warn(PREFIX - "Override [%4.4s-%8.8s], this is unsafe: tainting kernel\n", - table->signature, table->oem_table_id); - add_taint(TAINT_OVERRIDDEN_ACPI_TABLE, LOCKDEP_NOW_UNRELIABLE); -} + int table_offset = 0; + int table_index = 0; + struct acpi_table_header *table; + u32 table_length; + *length = 0; + *address = 0; + if (!acpi_tables_addr) + return AE_OK; -acpi_status -acpi_os_table_override(struct acpi_table_header * existing_table, - struct acpi_table_header ** new_table) -{ - if (!existing_table || !new_table) - return AE_BAD_PARAMETER; + while (table_offset + ACPI_HEADER_SIZE <= all_tables_size) { + table = acpi_os_map_memory(acpi_tables_addr + table_offset, + ACPI_HEADER_SIZE); + if (table_offset + table->length > all_tables_size) { + acpi_os_unmap_memory(table, ACPI_HEADER_SIZE); + WARN_ON(1); + return AE_OK; + } - *new_table = NULL; + table_length = table->length; -#ifdef CONFIG_ACPI_CUSTOM_DSDT - if (strncmp(existing_table->signature, "DSDT", 4) == 0) - *new_table = (struct acpi_table_header *)AmlCode; -#endif - if (*new_table != NULL) + /* Only override tables matched */ + if (test_bit(table_index, acpi_initrd_installed) || + memcmp(existing_table->signature, table->signature, 4) || + memcmp(table->oem_table_id, existing_table->oem_table_id, + ACPI_OEM_TABLE_ID_SIZE)) { + acpi_os_unmap_memory(table, ACPI_HEADER_SIZE); + goto next_table; + } + + *length = table_length; + *address = acpi_tables_addr + table_offset; acpi_table_taint(existing_table); + acpi_os_unmap_memory(table, ACPI_HEADER_SIZE); + set_bit(table_index, acpi_initrd_installed); + break; + +next_table: + table_offset += table_length; + table_index++; + } return AE_OK; } -acpi_status -acpi_os_physical_table_override(struct acpi_table_header *existing_table, - acpi_physical_address *address, - u32 *table_length) +void __init acpi_initrd_initialize_tables(void) { -#ifndef CONFIG_ACPI_INITRD_TABLE_OVERRIDE - *table_length = 0; - *address = 0; - return AE_OK; -#else int table_offset = 0; + int table_index = 0; + u32 table_length; struct acpi_table_header *table; - *table_length = 0; - *address = 0; - if (!acpi_tables_addr) - return AE_OK; - - do { - if (table_offset + ACPI_HEADER_SIZE > all_tables_size) { - WARN_ON(1); - return AE_OK; - } + return; + while (table_offset + ACPI_HEADER_SIZE <= all_tables_size) { table = acpi_os_map_memory(acpi_tables_addr + table_offset, ACPI_HEADER_SIZE); - if (table_offset + table->length > all_tables_size) { acpi_os_unmap_memory(table, ACPI_HEADER_SIZE); WARN_ON(1); - return AE_OK; + return; } - table_offset += table->length; + table_length = table->length; - if (memcmp(existing_table->signature, table->signature, 4)) { - acpi_os_unmap_memory(table, - ACPI_HEADER_SIZE); - continue; - } - - /* Only override tables with matching oem id */ - if (memcmp(table->oem_table_id, existing_table->oem_table_id, - ACPI_OEM_TABLE_ID_SIZE)) { - acpi_os_unmap_memory(table, - ACPI_HEADER_SIZE); - continue; + /* Skip RSDT/XSDT which should only be used for override */ + if (test_bit(table_index, acpi_initrd_installed) || + ACPI_COMPARE_NAME(table->signature, ACPI_SIG_RSDT) || + ACPI_COMPARE_NAME(table->signature, ACPI_SIG_XSDT)) { + acpi_os_unmap_memory(table, ACPI_HEADER_SIZE); + goto next_table; } - table_offset -= table->length; - *table_length = table->length; + acpi_table_taint(table); acpi_os_unmap_memory(table, ACPI_HEADER_SIZE); - *address = acpi_tables_addr + table_offset; - break; - } while (table_offset + ACPI_HEADER_SIZE < all_tables_size); + acpi_install_table(acpi_tables_addr + table_offset, TRUE); + set_bit(table_index, acpi_initrd_installed); +next_table: + table_offset += table_length; + table_index++; + } +} +#else +acpi_status +acpi_os_physical_table_override(struct acpi_table_header *existing_table, + acpi_physical_address *address, + u32 *table_length) +{ + *table_length = 0; + *address = 0; + return AE_OK; +} + +void __init acpi_initrd_initialize_tables(void) +{ +} +#endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */ - if (*address != 0) +acpi_status +acpi_os_table_override(struct acpi_table_header *existing_table, + struct acpi_table_header **new_table) +{ + if (!existing_table || !new_table) + return AE_BAD_PARAMETER; + + *new_table = NULL; + +#ifdef CONFIG_ACPI_CUSTOM_DSDT + if (strncmp(existing_table->signature, "DSDT", 4) == 0) + *new_table = (struct acpi_table_header *)AmlCode; +#endif + if (*new_table != NULL) acpi_table_taint(existing_table); return AE_OK; -#endif } static irqreturn_t acpi_irq(int irq, void *dev_id) diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index c8e169e46673..2c45dd3acc17 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -33,6 +33,7 @@ #include <linux/pci.h> #include <linux/acpi.h> #include <linux/slab.h> +#include <linux/interrupt.h> #define PREFIX "ACPI: " @@ -387,6 +388,23 @@ static inline int acpi_isa_register_gsi(struct pci_dev *dev) } #endif +static inline bool acpi_pci_irq_valid(struct pci_dev *dev, u8 pin) +{ +#ifdef CONFIG_X86 + /* + * On x86 irq line 0xff means "unknown" or "no connection" + * (PCI 3.0, Section 6.2.4, footnote on page 223). + */ + if (dev->irq == 0xff) { + dev->irq = IRQ_NOTCONNECTED; + dev_warn(&dev->dev, "PCI INT %c: not connected\n", + pin_name(pin)); + return false; + } +#endif + return true; +} + int acpi_pci_irq_enable(struct pci_dev *dev) { struct acpi_prt_entry *entry; @@ -431,11 +449,14 @@ int acpi_pci_irq_enable(struct pci_dev *dev) } else gsi = -1; - /* - * No IRQ known to the ACPI subsystem - maybe the BIOS / - * driver reported one, then use it. Exit in any case. - */ if (gsi < 0) { + /* + * No IRQ known to the ACPI subsystem - maybe the BIOS / + * driver reported one, then use it. Exit in any case. + */ + if (!acpi_pci_irq_valid(dev, pin)) + return 0; + if (acpi_isa_register_gsi(dev)) dev_warn(&dev->dev, "PCI INT %c: no GSI\n", pin_name(pin)); diff --git a/drivers/acpi/pmic/intel_pmic_crc.c b/drivers/acpi/pmic/intel_pmic_crc.c index 42df46a86c25..fcd1852dcdee 100644 --- a/drivers/acpi/pmic/intel_pmic_crc.c +++ b/drivers/acpi/pmic/intel_pmic_crc.c @@ -13,7 +13,7 @@ * GNU General Public License for more details. */ -#include <linux/module.h> +#include <linux/init.h> #include <linux/acpi.h> #include <linux/mfd/intel_soc_pmic.h> #include <linux/regmap.h> @@ -205,7 +205,4 @@ static int __init intel_crc_pmic_opregion_driver_init(void) { return platform_driver_register(&intel_crc_pmic_opregion_driver); } -module_init(intel_crc_pmic_opregion_driver_init); - -MODULE_DESCRIPTION("CrystalCove ACPI operation region driver"); -MODULE_LICENSE("GPL"); +device_initcall(intel_crc_pmic_opregion_driver_init); diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index 11154a330f07..d2fa8cb82d2b 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -314,7 +314,6 @@ static int __init acpi_processor_driver_init(void) if (result < 0) return result; - acpi_processor_syscore_init(); register_hotcpu_notifier(&acpi_cpu_notifier); acpi_thermal_cpufreq_init(); acpi_processor_ppc_init(); @@ -330,7 +329,6 @@ static void __exit acpi_processor_driver_exit(void) acpi_processor_ppc_exit(); acpi_thermal_cpufreq_exit(); unregister_hotcpu_notifier(&acpi_cpu_notifier); - acpi_processor_syscore_exit(); driver_unregister(&acpi_processor_driver); } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 175c86bee3a9..fadce354d2b7 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -23,6 +23,7 @@ * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ +#define pr_fmt(fmt) "ACPI: " fmt #include <linux/module.h> #include <linux/acpi.h> @@ -30,7 +31,6 @@ #include <linux/sched.h> /* need_resched() */ #include <linux/tick.h> #include <linux/cpuidle.h> -#include <linux/syscore_ops.h> #include <acpi/processor.h> /* @@ -43,8 +43,6 @@ #include <asm/apic.h> #endif -#define PREFIX "ACPI: " - #define ACPI_PROCESSOR_CLASS "processor" #define _COMPONENT ACPI_PROCESSOR_COMPONENT ACPI_MODULE_NAME("processor_idle"); @@ -81,9 +79,9 @@ static int set_max_cstate(const struct dmi_system_id *id) if (max_cstate > ACPI_PROCESSOR_MAX_POWER) return 0; - printk(KERN_NOTICE PREFIX "%s detected - limiting to C%ld max_cstate." - " Override with \"processor.max_cstate=%d\"\n", id->ident, - (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1); + pr_notice("%s detected - limiting to C%ld max_cstate." + " Override with \"processor.max_cstate=%d\"\n", id->ident, + (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1); max_cstate = (long)id->driver_data; @@ -194,42 +192,6 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr, #endif -#ifdef CONFIG_PM_SLEEP -static u32 saved_bm_rld; - -static int acpi_processor_suspend(void) -{ - acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld); - return 0; -} - -static void acpi_processor_resume(void) -{ - u32 resumed_bm_rld = 0; - - acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld); - if (resumed_bm_rld == saved_bm_rld) - return; - - acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld); -} - -static struct syscore_ops acpi_processor_syscore_ops = { - .suspend = acpi_processor_suspend, - .resume = acpi_processor_resume, -}; - -void acpi_processor_syscore_init(void) -{ - register_syscore_ops(&acpi_processor_syscore_ops); -} - -void acpi_processor_syscore_exit(void) -{ - unregister_syscore_ops(&acpi_processor_syscore_ops); -} -#endif /* CONFIG_PM_SLEEP */ - #if defined(CONFIG_X86) static void tsc_check_state(int state) { @@ -351,7 +313,7 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr) /* There must be at least 2 elements */ if (!cst || (cst->type != ACPI_TYPE_PACKAGE) || cst->package.count < 2) { - printk(KERN_ERR PREFIX "not enough elements in _CST\n"); + pr_err("not enough elements in _CST\n"); ret = -EFAULT; goto end; } @@ -360,7 +322,7 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr) /* Validate number of power states. */ if (count < 1 || count != cst->package.count - 1) { - printk(KERN_ERR PREFIX "count given by _CST is not valid\n"); + pr_err("count given by _CST is not valid\n"); ret = -EFAULT; goto end; } @@ -469,11 +431,9 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr) * (From 1 through ACPI_PROCESSOR_MAX_POWER - 1) */ if (current_count >= (ACPI_PROCESSOR_MAX_POWER - 1)) { - printk(KERN_WARNING - "Limiting number of power states to max (%d)\n", - ACPI_PROCESSOR_MAX_POWER); - printk(KERN_WARNING - "Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n"); + pr_warn("Limiting number of power states to max (%d)\n", + ACPI_PROCESSOR_MAX_POWER); + pr_warn("Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n"); break; } } @@ -1097,8 +1057,8 @@ int acpi_processor_power_init(struct acpi_processor *pr) retval = cpuidle_register_driver(&acpi_idle_driver); if (retval) return retval; - printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n", - acpi_idle_driver.name); + pr_debug("%s registered with cpuidle\n", + acpi_idle_driver.name); } dev = kzalloc(sizeof(*dev), GFP_KERNEL); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 407a3760e8de..5f28cf778349 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1930,6 +1930,7 @@ int __init acpi_scan_init(void) acpi_memory_hotplug_init(); acpi_pnp_init(); acpi_int340x_thermal_init(); + acpi_amba_init(); acpi_scan_add_handler(&generic_device_handler); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 9cb975200cac..fbfcce3b5227 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -19,6 +19,7 @@ #include <linux/reboot.h> #include <linux/acpi.h> #include <linux/module.h> +#include <linux/syscore_ops.h> #include <asm/io.h> #include <trace/events/power.h> @@ -677,6 +678,39 @@ static void acpi_sleep_suspend_setup(void) static inline void acpi_sleep_suspend_setup(void) {} #endif /* !CONFIG_SUSPEND */ +#ifdef CONFIG_PM_SLEEP +static u32 saved_bm_rld; + +static int acpi_save_bm_rld(void) +{ + acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld); + return 0; +} + +static void acpi_restore_bm_rld(void) +{ + u32 resumed_bm_rld = 0; + + acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld); + if (resumed_bm_rld == saved_bm_rld) + return; + + acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld); +} + +static struct syscore_ops acpi_sleep_syscore_ops = { + .suspend = acpi_save_bm_rld, + .resume = acpi_restore_bm_rld, +}; + +void acpi_sleep_syscore_init(void) +{ + register_syscore_ops(&acpi_sleep_syscore_ops); +} +#else +static inline void acpi_sleep_syscore_init(void) {} +#endif /* CONFIG_PM_SLEEP */ + #ifdef CONFIG_HIBERNATION static unsigned long s4_hardware_signature; static struct acpi_table_facs *facs; @@ -839,6 +873,7 @@ int __init acpi_sleep_init(void) sleep_states[ACPI_STATE_S0] = 1; + acpi_sleep_syscore_init(); acpi_sleep_suspend_setup(); acpi_sleep_hibernate_setup(); diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 6c0f0794aa82..f49c02442d65 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -32,6 +32,7 @@ #include <linux/errno.h> #include <linux/acpi.h> #include <linux/bootmem.h> +#include "internal.h" #define ACPI_MAX_TABLES 128 @@ -456,6 +457,7 @@ int __init acpi_table_init(void) status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0); if (ACPI_FAILURE(status)) return -EINVAL; + acpi_initrd_initialize_tables(); check_multiple_madt(); return 0; @@ -484,3 +486,13 @@ static int __init acpi_force_table_verification_setup(char *s) } early_param("acpi_force_table_verification", acpi_force_table_verification_setup); + +static int __init acpi_force_32bit_fadt_addr(char *s) +{ + pr_info("Forcing 32 Bit FADT addresses\n"); + acpi_gbl_use32_bit_fadt_addresses = TRUE; + + return 0; +} + +early_param("acpi_force_32bit_fadt_addr", acpi_force_32bit_fadt_addr); diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index f2f9873bb5c3..f12a72428aac 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -201,10 +201,6 @@ acpi_extract_package(union acpi_object *package, u8 **pointer = NULL; union acpi_object *element = &(package->package.elements[i]); - if (!element) { - return AE_BAD_DATA; - } - switch (element->type) { case ACPI_TYPE_INTEGER: diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 301b785f9f56..56705b52758e 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -104,6 +104,7 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd) static int genpd_power_on(struct generic_pm_domain *genpd, bool timed) { + unsigned int state_idx = genpd->state_idx; ktime_t time_start; s64 elapsed_ns; int ret; @@ -120,10 +121,10 @@ static int genpd_power_on(struct generic_pm_domain *genpd, bool timed) return ret; elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns <= genpd->power_on_latency_ns) + if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns) return ret; - genpd->power_on_latency_ns = elapsed_ns; + genpd->states[state_idx].power_on_latency_ns = elapsed_ns; genpd->max_off_time_changed = true; pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n", genpd->name, "on", elapsed_ns); @@ -133,6 +134,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, bool timed) static int genpd_power_off(struct generic_pm_domain *genpd, bool timed) { + unsigned int state_idx = genpd->state_idx; ktime_t time_start; s64 elapsed_ns; int ret; @@ -149,10 +151,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed) return ret; elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns <= genpd->power_off_latency_ns) + if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns) return ret; - genpd->power_off_latency_ns = elapsed_ns; + genpd->states[state_idx].power_off_latency_ns = elapsed_ns; genpd->max_off_time_changed = true; pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n", genpd->name, "off", elapsed_ns); @@ -485,8 +487,13 @@ static int pm_genpd_runtime_resume(struct device *dev) if (timed && runtime_pm) time_start = ktime_get(); - genpd_start_dev(genpd, dev); - genpd_restore_dev(genpd, dev); + ret = genpd_start_dev(genpd, dev); + if (ret) + goto err_poweroff; + + ret = genpd_restore_dev(genpd, dev); + if (ret) + goto err_stop; /* Update resume latency value if the measured time exceeds it. */ if (timed && runtime_pm) { @@ -501,6 +508,17 @@ static int pm_genpd_runtime_resume(struct device *dev) } return 0; + +err_stop: + genpd_stop_dev(genpd, dev); +err_poweroff: + if (!dev->power.irq_safe) { + mutex_lock(&genpd->lock); + genpd_poweroff(genpd, 0); + mutex_unlock(&genpd->lock); + } + + return ret; } static bool pd_ignore_unused; @@ -585,6 +603,8 @@ static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd, || atomic_read(&genpd->sd_count) > 0) return; + /* Choose the deepest state when suspending */ + genpd->state_idx = genpd->state_count - 1; genpd_power_off(genpd, timed); genpd->status = GPD_STATE_POWER_OFF; @@ -1378,7 +1398,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, mutex_lock(&subdomain->lock); mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); - if (!list_empty(&subdomain->slave_links) || subdomain->device_count) { + if (!list_empty(&subdomain->master_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, subdomain->name); ret = -EBUSY; @@ -1508,6 +1528,20 @@ void pm_genpd_init(struct generic_pm_domain *genpd, genpd->dev_ops.start = pm_clk_resume; } + if (genpd->state_idx >= GENPD_MAX_NUM_STATES) { + pr_warn("Initial state index out of bounds.\n"); + genpd->state_idx = GENPD_MAX_NUM_STATES - 1; + } + + if (genpd->state_count > GENPD_MAX_NUM_STATES) { + pr_warn("Limiting states to %d\n", GENPD_MAX_NUM_STATES); + genpd->state_count = GENPD_MAX_NUM_STATES; + } + + /* Use only one "off" state if there were no states declared */ + if (genpd->state_count == 0) + genpd->state_count = 1; + mutex_lock(&gpd_list_lock); list_add(&genpd->gpd_list_node, &gpd_list); mutex_unlock(&gpd_list_lock); @@ -1668,6 +1702,9 @@ struct generic_pm_domain *of_genpd_get_from_provider( struct generic_pm_domain *genpd = ERR_PTR(-ENOENT); struct of_genpd_provider *provider; + if (!genpdspec) + return ERR_PTR(-EINVAL); + mutex_lock(&of_genpd_mutex); /* Check if we have such a provider in our array */ @@ -1864,6 +1901,7 @@ static int pm_genpd_summary_one(struct seq_file *s, struct pm_domain_data *pm_data; const char *kobj_path; struct gpd_link *link; + char state[16]; int ret; ret = mutex_lock_interruptible(&genpd->lock); @@ -1872,7 +1910,13 @@ static int pm_genpd_summary_one(struct seq_file *s, if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup))) goto exit; - seq_printf(s, "%-30s %-15s ", genpd->name, status_lookup[genpd->status]); + if (genpd->status == GPD_STATE_POWER_OFF) + snprintf(state, sizeof(state), "%s-%u", + status_lookup[genpd->status], genpd->state_idx); + else + snprintf(state, sizeof(state), "%s", + status_lookup[genpd->status]); + seq_printf(s, "%-30s %-15s ", genpd->name, state); /* * Modifications on the list require holding locks on both diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 1e937ac5f456..00a5436dd44b 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -98,7 +98,8 @@ static bool default_stop_ok(struct device *dev) * * This routine must be executed under the PM domain's lock. */ -static bool default_power_down_ok(struct dev_pm_domain *pd) +static bool __default_power_down_ok(struct dev_pm_domain *pd, + unsigned int state) { struct generic_pm_domain *genpd = pd_to_genpd(pd); struct gpd_link *link; @@ -106,27 +107,9 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) s64 min_off_time_ns; s64 off_on_time_ns; - if (genpd->max_off_time_changed) { - struct gpd_link *link; - - /* - * We have to invalidate the cached results for the masters, so - * use the observation that default_power_down_ok() is not - * going to be called for any master until this instance - * returns. - */ - list_for_each_entry(link, &genpd->slave_links, slave_node) - link->master->max_off_time_changed = true; - - genpd->max_off_time_changed = false; - genpd->cached_power_down_ok = false; - genpd->max_off_time_ns = -1; - } else { - return genpd->cached_power_down_ok; - } + off_on_time_ns = genpd->states[state].power_off_latency_ns + + genpd->states[state].power_on_latency_ns; - off_on_time_ns = genpd->power_off_latency_ns + - genpd->power_on_latency_ns; min_off_time_ns = -1; /* @@ -186,8 +169,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) min_off_time_ns = constraint_ns; } - genpd->cached_power_down_ok = true; - /* * If the computed minimum device off time is negative, there are no * latency constraints, so the domain can spend arbitrary time in the @@ -201,10 +182,45 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) * time and the time needed to turn the domain on is the maximum * theoretical time this domain can spend in the "off" state. */ - genpd->max_off_time_ns = min_off_time_ns - genpd->power_on_latency_ns; + genpd->max_off_time_ns = min_off_time_ns - + genpd->states[state].power_on_latency_ns; return true; } +static bool default_power_down_ok(struct dev_pm_domain *pd) +{ + struct generic_pm_domain *genpd = pd_to_genpd(pd); + struct gpd_link *link; + + if (!genpd->max_off_time_changed) + return genpd->cached_power_down_ok; + + /* + * We have to invalidate the cached results for the masters, so + * use the observation that default_power_down_ok() is not + * going to be called for any master until this instance + * returns. + */ + list_for_each_entry(link, &genpd->slave_links, slave_node) + link->master->max_off_time_changed = true; + + genpd->max_off_time_ns = -1; + genpd->max_off_time_changed = false; + genpd->cached_power_down_ok = true; + genpd->state_idx = genpd->state_count - 1; + + /* Find a state to power down to, starting from the deepest. */ + while (!__default_power_down_ok(pd, genpd->state_idx)) { + if (genpd->state_idx == 0) { + genpd->cached_power_down_ok = false; + break; + } + genpd->state_idx--; + } + + return genpd->cached_power_down_ok; +} + static bool always_on_power_down_ok(struct dev_pm_domain *domain) { return false; diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index cf351d3dab1c..433b60092972 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -13,50 +13,52 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/clk.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/device.h> #include <linux/of.h> #include <linux/export.h> +#include <linux/regulator/consumer.h> #include "opp.h" /* - * The root of the list of all devices. All device_opp structures branch off - * from here, with each device_opp containing the list of opp it supports in + * The root of the list of all opp-tables. All opp_table structures branch off + * from here, with each opp_table containing the list of opps it supports in * various states of availability. */ -static LIST_HEAD(dev_opp_list); +static LIST_HEAD(opp_tables); /* Lock to allow exclusive modification to the device and opp lists */ -DEFINE_MUTEX(dev_opp_list_lock); +DEFINE_MUTEX(opp_table_lock); #define opp_rcu_lockdep_assert() \ do { \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ - !lockdep_is_held(&dev_opp_list_lock), \ - "Missing rcu_read_lock() or " \ - "dev_opp_list_lock protection"); \ + !lockdep_is_held(&opp_table_lock), \ + "Missing rcu_read_lock() or " \ + "opp_table_lock protection"); \ } while (0) -static struct device_list_opp *_find_list_dev(const struct device *dev, - struct device_opp *dev_opp) +static struct opp_device *_find_opp_dev(const struct device *dev, + struct opp_table *opp_table) { - struct device_list_opp *list_dev; + struct opp_device *opp_dev; - list_for_each_entry(list_dev, &dev_opp->dev_list, node) - if (list_dev->dev == dev) - return list_dev; + list_for_each_entry(opp_dev, &opp_table->dev_list, node) + if (opp_dev->dev == dev) + return opp_dev; return NULL; } -static struct device_opp *_managed_opp(const struct device_node *np) +static struct opp_table *_managed_opp(const struct device_node *np) { - struct device_opp *dev_opp; + struct opp_table *opp_table; - list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) { - if (dev_opp->np == np) { + list_for_each_entry_rcu(opp_table, &opp_tables, node) { + if (opp_table->np == np) { /* * Multiple devices can point to the same OPP table and * so will have same node-pointer, np. @@ -64,7 +66,7 @@ static struct device_opp *_managed_opp(const struct device_node *np) * But the OPPs will be considered as shared only if the * OPP table contains a "opp-shared" property. */ - return dev_opp->shared_opp ? dev_opp : NULL; + return opp_table->shared_opp ? opp_table : NULL; } } @@ -72,24 +74,24 @@ static struct device_opp *_managed_opp(const struct device_node *np) } /** - * _find_device_opp() - find device_opp struct using device pointer - * @dev: device pointer used to lookup device OPPs + * _find_opp_table() - find opp_table struct using device pointer + * @dev: device pointer used to lookup OPP table * - * Search list of device OPPs for one containing matching device. Does a RCU - * reader operation to grab the pointer needed. + * Search OPP table for one containing matching device. Does a RCU reader + * operation to grab the pointer needed. * - * Return: pointer to 'struct device_opp' if found, otherwise -ENODEV or + * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or * -EINVAL based on type of error. * * Locking: For readers, this function must be called under rcu_read_lock(). - * device_opp is a RCU protected pointer, which means that device_opp is valid + * opp_table is a RCU protected pointer, which means that opp_table is valid * as long as we are under RCU lock. * - * For Writers, this function must be called with dev_opp_list_lock held. + * For Writers, this function must be called with opp_table_lock held. */ -struct device_opp *_find_device_opp(struct device *dev) +struct opp_table *_find_opp_table(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; opp_rcu_lockdep_assert(); @@ -98,9 +100,9 @@ struct device_opp *_find_device_opp(struct device *dev) return ERR_PTR(-EINVAL); } - list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) - if (_find_list_dev(dev, dev_opp)) - return dev_opp; + list_for_each_entry_rcu(opp_table, &opp_tables, node) + if (_find_opp_dev(dev, opp_table)) + return opp_table; return ERR_PTR(-ENODEV); } @@ -213,16 +215,16 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo); */ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; unsigned long clock_latency_ns; rcu_read_lock(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) clock_latency_ns = 0; else - clock_latency_ns = dev_opp->clock_latency_ns_max; + clock_latency_ns = opp_table->clock_latency_ns_max; rcu_read_unlock(); return clock_latency_ns; @@ -230,6 +232,82 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); /** + * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds + * @dev: device for which we do this operation + * + * Return: This function returns the max voltage latency in nanoseconds. + * + * Locking: This function takes rcu_read_lock(). + */ +unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) +{ + struct opp_table *opp_table; + struct dev_pm_opp *opp; + struct regulator *reg; + unsigned long latency_ns = 0; + unsigned long min_uV = ~0, max_uV = 0; + int ret; + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + rcu_read_unlock(); + return 0; + } + + reg = opp_table->regulator; + if (IS_ERR(reg)) { + /* Regulator may not be required for device */ + if (reg) + dev_err(dev, "%s: Invalid regulator (%ld)\n", __func__, + PTR_ERR(reg)); + rcu_read_unlock(); + return 0; + } + + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { + if (!opp->available) + continue; + + if (opp->u_volt_min < min_uV) + min_uV = opp->u_volt_min; + if (opp->u_volt_max > max_uV) + max_uV = opp->u_volt_max; + } + + rcu_read_unlock(); + + /* + * The caller needs to ensure that opp_table (and hence the regulator) + * isn't freed, while we are executing this routine. + */ + ret = regulator_set_voltage_time(reg, min_uV, max_uV); + if (ret > 0) + latency_ns = ret * 1000; + + return latency_ns; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_volt_latency); + +/** + * dev_pm_opp_get_max_transition_latency() - Get max transition latency in + * nanoseconds + * @dev: device for which we do this operation + * + * Return: This function returns the max transition latency, in nanoseconds, to + * switch from one OPP to other. + * + * Locking: This function takes rcu_read_lock(). + */ +unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev) +{ + return dev_pm_opp_get_max_volt_latency(dev) + + dev_pm_opp_get_max_clock_latency(dev); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency); + +/** * dev_pm_opp_get_suspend_opp() - Get suspend opp * @dev: device for which we do this operation * @@ -244,21 +322,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); */ struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; opp_rcu_lockdep_assert(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp) || !dev_opp->suspend_opp || - !dev_opp->suspend_opp->available) + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table) || !opp_table->suspend_opp || + !opp_table->suspend_opp->available) return NULL; - return dev_opp->suspend_opp; + return opp_table->suspend_opp; } EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp); /** - * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list + * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table * @dev: device for which we do this operation * * Return: This function returns the number of available opps if there are any, @@ -268,21 +346,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp); */ int dev_pm_opp_get_opp_count(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp; int count = 0; rcu_read_lock(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - count = PTR_ERR(dev_opp); - dev_err(dev, "%s: device OPP not found (%d)\n", + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + count = PTR_ERR(opp_table); + dev_err(dev, "%s: OPP table not found (%d)\n", __func__, count); goto out_unlock; } - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available) count++; } @@ -299,7 +377,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count); * @freq: frequency to search for * @available: true/false - match for available opp * - * Return: Searches for exact match in the opp list and returns pointer to the + * Return: Searches for exact match in the opp table and returns pointer to the * matching opp if found, else returns ERR_PTR in case of error and should * be handled using IS_ERR. Error return values can be: * EINVAL: for bad pointer @@ -323,19 +401,20 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); opp_rcu_lockdep_assert(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - int r = PTR_ERR(dev_opp); - dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + int r = PTR_ERR(opp_table); + + dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r); return ERR_PTR(r); } - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available == available && temp_opp->rate == freq) { opp = temp_opp; @@ -371,7 +450,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact); struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); opp_rcu_lockdep_assert(); @@ -381,11 +460,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-EINVAL); } - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) - return ERR_CAST(dev_opp); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available && temp_opp->rate >= *freq) { opp = temp_opp; *freq = opp->rate; @@ -421,7 +500,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil); struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); opp_rcu_lockdep_assert(); @@ -431,11 +510,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, return ERR_PTR(-EINVAL); } - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) - return ERR_CAST(dev_opp); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available) { /* go to the next node, before choosing prev */ if (temp_opp->rate > *freq) @@ -451,130 +530,343 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor); -/* List-dev Helpers */ -static void _kfree_list_dev_rcu(struct rcu_head *head) +/* + * The caller needs to ensure that opp_table (and hence the clk) isn't freed, + * while clk returned here is used. + */ +static struct clk *_get_opp_clk(struct device *dev) +{ + struct opp_table *opp_table; + struct clk *clk; + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "%s: device opp doesn't exist\n", __func__); + clk = ERR_CAST(opp_table); + goto unlock; + } + + clk = opp_table->clk; + if (IS_ERR(clk)) + dev_err(dev, "%s: No clock available for the device\n", + __func__); + +unlock: + rcu_read_unlock(); + return clk; +} + +static int _set_opp_voltage(struct device *dev, struct regulator *reg, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) +{ + int ret; + + /* Regulator not available for device */ + if (IS_ERR(reg)) { + dev_dbg(dev, "%s: regulator not available: %ld\n", __func__, + PTR_ERR(reg)); + return 0; + } + + dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, u_volt_min, + u_volt, u_volt_max); + + ret = regulator_set_voltage_triplet(reg, u_volt_min, u_volt, + u_volt_max); + if (ret) + dev_err(dev, "%s: failed to set voltage (%lu %lu %lu mV): %d\n", + __func__, u_volt_min, u_volt, u_volt_max, ret); + + return ret; +} + +/** + * dev_pm_opp_set_rate() - Configure new OPP based on frequency + * @dev: device for which we do this operation + * @target_freq: frequency to achieve + * + * This configures the power-supplies and clock source to the levels specified + * by the OPP corresponding to the target_freq. + * + * Locking: This function takes rcu_read_lock(). + */ +int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) +{ + struct opp_table *opp_table; + struct dev_pm_opp *old_opp, *opp; + struct regulator *reg; + struct clk *clk; + unsigned long freq, old_freq; + unsigned long u_volt, u_volt_min, u_volt_max; + unsigned long ou_volt, ou_volt_min, ou_volt_max; + int ret; + + if (unlikely(!target_freq)) { + dev_err(dev, "%s: Invalid target frequency %lu\n", __func__, + target_freq); + return -EINVAL; + } + + clk = _get_opp_clk(dev); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + freq = clk_round_rate(clk, target_freq); + if ((long)freq <= 0) + freq = target_freq; + + old_freq = clk_get_rate(clk); + + /* Return early if nothing to do */ + if (old_freq == freq) { + dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", + __func__, freq); + return 0; + } + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "%s: device opp doesn't exist\n", __func__); + rcu_read_unlock(); + return PTR_ERR(opp_table); + } + + old_opp = dev_pm_opp_find_freq_ceil(dev, &old_freq); + if (!IS_ERR(old_opp)) { + ou_volt = old_opp->u_volt; + ou_volt_min = old_opp->u_volt_min; + ou_volt_max = old_opp->u_volt_max; + } else { + dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n", + __func__, old_freq, PTR_ERR(old_opp)); + } + + opp = dev_pm_opp_find_freq_ceil(dev, &freq); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); + dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n", + __func__, freq, ret); + rcu_read_unlock(); + return ret; + } + + u_volt = opp->u_volt; + u_volt_min = opp->u_volt_min; + u_volt_max = opp->u_volt_max; + + reg = opp_table->regulator; + + rcu_read_unlock(); + + /* Scaling up? Scale voltage before frequency */ + if (freq > old_freq) { + ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, + u_volt_max); + if (ret) + goto restore_voltage; + } + + /* Change frequency */ + + dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", + __func__, old_freq, freq); + + ret = clk_set_rate(clk, freq); + if (ret) { + dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, + ret); + goto restore_voltage; + } + + /* Scaling down? Scale voltage after frequency */ + if (freq < old_freq) { + ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, + u_volt_max); + if (ret) + goto restore_freq; + } + + return 0; + +restore_freq: + if (clk_set_rate(clk, old_freq)) + dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", + __func__, old_freq); +restore_voltage: + /* This shouldn't harm even if the voltages weren't updated earlier */ + if (!IS_ERR(old_opp)) + _set_opp_voltage(dev, reg, ou_volt, ou_volt_min, ou_volt_max); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); + +/* OPP-dev Helpers */ +static void _kfree_opp_dev_rcu(struct rcu_head *head) { - struct device_list_opp *list_dev; + struct opp_device *opp_dev; - list_dev = container_of(head, struct device_list_opp, rcu_head); - kfree_rcu(list_dev, rcu_head); + opp_dev = container_of(head, struct opp_device, rcu_head); + kfree_rcu(opp_dev, rcu_head); } -static void _remove_list_dev(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static void _remove_opp_dev(struct opp_device *opp_dev, + struct opp_table *opp_table) { - opp_debug_unregister(list_dev, dev_opp); - list_del(&list_dev->node); - call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head, - _kfree_list_dev_rcu); + opp_debug_unregister(opp_dev, opp_table); + list_del(&opp_dev->node); + call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head, + _kfree_opp_dev_rcu); } -struct device_list_opp *_add_list_dev(const struct device *dev, - struct device_opp *dev_opp) +struct opp_device *_add_opp_dev(const struct device *dev, + struct opp_table *opp_table) { - struct device_list_opp *list_dev; + struct opp_device *opp_dev; int ret; - list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL); - if (!list_dev) + opp_dev = kzalloc(sizeof(*opp_dev), GFP_KERNEL); + if (!opp_dev) return NULL; - /* Initialize list-dev */ - list_dev->dev = dev; - list_add_rcu(&list_dev->node, &dev_opp->dev_list); + /* Initialize opp-dev */ + opp_dev->dev = dev; + list_add_rcu(&opp_dev->node, &opp_table->dev_list); - /* Create debugfs entries for the dev_opp */ - ret = opp_debug_register(list_dev, dev_opp); + /* Create debugfs entries for the opp_table */ + ret = opp_debug_register(opp_dev, opp_table); if (ret) dev_err(dev, "%s: Failed to register opp debugfs (%d)\n", __func__, ret); - return list_dev; + return opp_dev; } /** - * _add_device_opp() - Find device OPP table or allocate a new one + * _add_opp_table() - Find OPP table or allocate a new one * @dev: device for which we do this operation * * It tries to find an existing table first, if it couldn't find one, it * allocates a new OPP table and returns that. * - * Return: valid device_opp pointer if success, else NULL. + * Return: valid opp_table pointer if success, else NULL. */ -static struct device_opp *_add_device_opp(struct device *dev) +static struct opp_table *_add_opp_table(struct device *dev) { - struct device_opp *dev_opp; - struct device_list_opp *list_dev; + struct opp_table *opp_table; + struct opp_device *opp_dev; + struct device_node *np; + int ret; - /* Check for existing list for 'dev' first */ - dev_opp = _find_device_opp(dev); - if (!IS_ERR(dev_opp)) - return dev_opp; + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (!IS_ERR(opp_table)) + return opp_table; /* - * Allocate a new device OPP table. In the infrequent case where a new + * Allocate a new OPP table. In the infrequent case where a new * device is needed to be added, we pay this penalty. */ - dev_opp = kzalloc(sizeof(*dev_opp), GFP_KERNEL); - if (!dev_opp) + opp_table = kzalloc(sizeof(*opp_table), GFP_KERNEL); + if (!opp_table) return NULL; - INIT_LIST_HEAD(&dev_opp->dev_list); + INIT_LIST_HEAD(&opp_table->dev_list); - list_dev = _add_list_dev(dev, dev_opp); - if (!list_dev) { - kfree(dev_opp); + opp_dev = _add_opp_dev(dev, opp_table); + if (!opp_dev) { + kfree(opp_table); return NULL; } - srcu_init_notifier_head(&dev_opp->srcu_head); - INIT_LIST_HEAD(&dev_opp->opp_list); + /* + * Only required for backward compatibility with v1 bindings, but isn't + * harmful for other cases. And so we do it unconditionally. + */ + np = of_node_get(dev->of_node); + if (np) { + u32 val; + + if (!of_property_read_u32(np, "clock-latency", &val)) + opp_table->clock_latency_ns_max = val; + of_property_read_u32(np, "voltage-tolerance", + &opp_table->voltage_tolerance_v1); + of_node_put(np); + } + + /* Set regulator to a non-NULL error value */ + opp_table->regulator = ERR_PTR(-ENXIO); + + /* Find clk for the device */ + opp_table->clk = clk_get(dev, NULL); + if (IS_ERR(opp_table->clk)) { + ret = PTR_ERR(opp_table->clk); + if (ret != -EPROBE_DEFER) + dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, + ret); + } - /* Secure the device list modification */ - list_add_rcu(&dev_opp->node, &dev_opp_list); - return dev_opp; + srcu_init_notifier_head(&opp_table->srcu_head); + INIT_LIST_HEAD(&opp_table->opp_list); + + /* Secure the device table modification */ + list_add_rcu(&opp_table->node, &opp_tables); + return opp_table; } /** - * _kfree_device_rcu() - Free device_opp RCU handler + * _kfree_device_rcu() - Free opp_table RCU handler * @head: RCU head */ static void _kfree_device_rcu(struct rcu_head *head) { - struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head); + struct opp_table *opp_table = container_of(head, struct opp_table, + rcu_head); - kfree_rcu(device_opp, rcu_head); + kfree_rcu(opp_table, rcu_head); } /** - * _remove_device_opp() - Removes a device OPP table - * @dev_opp: device OPP table to be removed. + * _remove_opp_table() - Removes a OPP table + * @opp_table: OPP table to be removed. * - * Removes/frees device OPP table it it doesn't contain any OPPs. + * Removes/frees OPP table if it doesn't contain any OPPs. */ -static void _remove_device_opp(struct device_opp *dev_opp) +static void _remove_opp_table(struct opp_table *opp_table) { - struct device_list_opp *list_dev; + struct opp_device *opp_dev; + + if (!list_empty(&opp_table->opp_list)) + return; - if (!list_empty(&dev_opp->opp_list)) + if (opp_table->supported_hw) return; - if (dev_opp->supported_hw) + if (opp_table->prop_name) return; - if (dev_opp->prop_name) + if (!IS_ERR(opp_table->regulator)) return; - list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp, - node); + /* Release clk */ + if (!IS_ERR(opp_table->clk)) + clk_put(opp_table->clk); - _remove_list_dev(list_dev, dev_opp); + opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device, + node); + + _remove_opp_dev(opp_dev, opp_table); /* dev_list must be empty now */ - WARN_ON(!list_empty(&dev_opp->dev_list)); + WARN_ON(!list_empty(&opp_table->dev_list)); - list_del_rcu(&dev_opp->node); - call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head, + list_del_rcu(&opp_table->node); + call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head, _kfree_device_rcu); } @@ -591,17 +883,17 @@ static void _kfree_opp_rcu(struct rcu_head *head) /** * _opp_remove() - Remove an OPP from a table definition - * @dev_opp: points back to the device_opp struct this opp belongs to + * @opp_table: points back to the opp_table struct this opp belongs to * @opp: pointer to the OPP to remove * @notify: OPP_EVENT_REMOVE notification should be sent or not * - * This function removes an opp definition from the opp list. + * This function removes an opp definition from the opp table. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * It is assumed that the caller holds required mutex for an RCU updater * strategy. */ -static void _opp_remove(struct device_opp *dev_opp, +static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify) { /* @@ -609,22 +901,23 @@ static void _opp_remove(struct device_opp *dev_opp, * frequency/voltage list. */ if (notify) - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp); + srcu_notifier_call_chain(&opp_table->srcu_head, + OPP_EVENT_REMOVE, opp); opp_debug_remove_one(opp); list_del_rcu(&opp->node); - call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); + call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); - _remove_device_opp(dev_opp); + _remove_opp_table(opp_table); } /** - * dev_pm_opp_remove() - Remove an OPP from OPP list + * dev_pm_opp_remove() - Remove an OPP from OPP table * @dev: device for which we do this operation * @freq: OPP to remove with matching 'freq' * - * This function removes an opp from the opp list. + * This function removes an opp from the opp table. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -633,17 +926,17 @@ static void _opp_remove(struct device_opp *dev_opp, void dev_pm_opp_remove(struct device *dev, unsigned long freq) { struct dev_pm_opp *opp; - struct device_opp *dev_opp; + struct opp_table *opp_table; bool found = false; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) goto unlock; - list_for_each_entry(opp, &dev_opp->opp_list, node) { + list_for_each_entry(opp, &opp_table->opp_list, node) { if (opp->rate == freq) { found = true; break; @@ -656,14 +949,14 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) goto unlock; } - _opp_remove(dev_opp, opp, true); + _opp_remove(opp_table, opp, true); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_remove); static struct dev_pm_opp *_allocate_opp(struct device *dev, - struct device_opp **dev_opp) + struct opp_table **opp_table) { struct dev_pm_opp *opp; @@ -674,8 +967,8 @@ static struct dev_pm_opp *_allocate_opp(struct device *dev, INIT_LIST_HEAD(&opp->node); - *dev_opp = _add_device_opp(dev); - if (!*dev_opp) { + *opp_table = _add_opp_table(dev); + if (!*opp_table) { kfree(opp); return NULL; } @@ -683,22 +976,38 @@ static struct dev_pm_opp *_allocate_opp(struct device *dev, return opp; } +static bool _opp_supported_by_regulators(struct dev_pm_opp *opp, + struct opp_table *opp_table) +{ + struct regulator *reg = opp_table->regulator; + + if (!IS_ERR(reg) && + !regulator_is_supported_voltage(reg, opp->u_volt_min, + opp->u_volt_max)) { + pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n", + __func__, opp->u_volt_min, opp->u_volt_max); + return false; + } + + return true; +} + static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, - struct device_opp *dev_opp) + struct opp_table *opp_table) { struct dev_pm_opp *opp; - struct list_head *head = &dev_opp->opp_list; + struct list_head *head = &opp_table->opp_list; int ret; /* * Insert new OPP in order of increasing frequency and discard if * already present. * - * Need to use &dev_opp->opp_list in the condition part of the 'for' + * Need to use &opp_table->opp_list in the condition part of the 'for' * loop, don't replace it with head otherwise it will become an infinite * loop. */ - list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { if (new_opp->rate > opp->rate) { head = &opp->node; continue; @@ -716,14 +1025,20 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, 0 : -EEXIST; } - new_opp->dev_opp = dev_opp; + new_opp->opp_table = opp_table; list_add_rcu(&new_opp->node, head); - ret = opp_debug_create_one(new_opp, dev_opp); + ret = opp_debug_create_one(new_opp, opp_table); if (ret) dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n", __func__, ret); + if (!_opp_supported_by_regulators(new_opp, opp_table)) { + new_opp->available = false; + dev_warn(dev, "%s: OPP not supported by regulators (%lu)\n", + __func__, new_opp->rate); + } + return 0; } @@ -734,14 +1049,14 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, * @u_volt: Voltage in uVolts for this OPP * @dynamic: Dynamically added OPPs. * - * This function adds an opp definition to the opp list and returns status. + * This function adds an opp definition to the opp table and returns status. * The opp is made available by default and it can be controlled using * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove. * * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table * and freed by dev_pm_opp_of_remove_table. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -757,14 +1072,15 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *new_opp; + unsigned long tol; int ret; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - new_opp = _allocate_opp(dev, &dev_opp); + new_opp = _allocate_opp(dev, &opp_table); if (!new_opp) { ret = -ENOMEM; goto unlock; @@ -772,33 +1088,36 @@ static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, /* populate the opp table */ new_opp->rate = freq; + tol = u_volt * opp_table->voltage_tolerance_v1 / 100; new_opp->u_volt = u_volt; + new_opp->u_volt_min = u_volt - tol; + new_opp->u_volt_max = u_volt + tol; new_opp->available = true; new_opp->dynamic = dynamic; - ret = _opp_add(dev, new_opp, dev_opp); + ret = _opp_add(dev, new_opp, opp_table); if (ret) goto free_opp; - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); /* * Notify the changes in the availability of the operable * frequency/voltage list. */ - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp); return 0; free_opp: - _opp_remove(dev_opp, new_opp, false); + _opp_remove(opp_table, new_opp, false); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } /* TODO: Support multiple regulators */ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, - struct device_opp *dev_opp) + struct opp_table *opp_table) { u32 microvolt[3] = {0}; u32 val; @@ -807,9 +1126,9 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, char name[NAME_MAX]; /* Search for "opp-microvolt-<name>" */ - if (dev_opp->prop_name) { + if (opp_table->prop_name) { snprintf(name, sizeof(name), "opp-microvolt-%s", - dev_opp->prop_name); + opp_table->prop_name); prop = of_find_property(opp->np, name, NULL); } @@ -844,14 +1163,20 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, } opp->u_volt = microvolt[0]; - opp->u_volt_min = microvolt[1]; - opp->u_volt_max = microvolt[2]; + + if (count == 1) { + opp->u_volt_min = opp->u_volt; + opp->u_volt_max = opp->u_volt; + } else { + opp->u_volt_min = microvolt[1]; + opp->u_volt_max = microvolt[2]; + } /* Search for "opp-microamp-<name>" */ prop = NULL; - if (dev_opp->prop_name) { + if (opp_table->prop_name) { snprintf(name, sizeof(name), "opp-microamp-%s", - dev_opp->prop_name); + opp_table->prop_name); prop = of_find_property(opp->np, name, NULL); } @@ -878,7 +1203,7 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, * OPPs, which are available for those versions, based on its 'opp-supported-hw' * property. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -887,44 +1212,44 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count) { - struct device_opp *dev_opp; + struct opp_table *opp_table; int ret = 0; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - dev_opp = _add_device_opp(dev); - if (!dev_opp) { + opp_table = _add_opp_table(dev); + if (!opp_table) { ret = -ENOMEM; goto unlock; } - /* Make sure there are no concurrent readers while updating dev_opp */ - WARN_ON(!list_empty(&dev_opp->opp_list)); + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); - /* Do we already have a version hierarchy associated with dev_opp? */ - if (dev_opp->supported_hw) { + /* Do we already have a version hierarchy associated with opp_table? */ + if (opp_table->supported_hw) { dev_err(dev, "%s: Already have supported hardware list\n", __func__); ret = -EBUSY; goto err; } - dev_opp->supported_hw = kmemdup(versions, count * sizeof(*versions), + opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions), GFP_KERNEL); - if (!dev_opp->supported_hw) { + if (!opp_table->supported_hw) { ret = -ENOMEM; goto err; } - dev_opp->supported_hw_count = count; - mutex_unlock(&dev_opp_list_lock); + opp_table->supported_hw_count = count; + mutex_unlock(&opp_table_lock); return 0; err: - _remove_device_opp(dev_opp); + _remove_opp_table(opp_table); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } @@ -932,13 +1257,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw); /** * dev_pm_opp_put_supported_hw() - Releases resources blocked for supported hw - * @dev: Device for which supported-hw has to be set. + * @dev: Device for which supported-hw has to be put. * * This is required only for the V2 bindings, and is called for a matching - * dev_pm_opp_set_supported_hw(). Until this is called, the device_opp structure + * dev_pm_opp_set_supported_hw(). Until this is called, the opp_table structure * will not be freed. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -946,42 +1271,43 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw); */ void dev_pm_opp_put_supported_hw(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - /* Check for existing list for 'dev' first */ - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - dev_err(dev, "Failed to find dev_opp: %ld\n", PTR_ERR(dev_opp)); + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "Failed to find opp_table: %ld\n", + PTR_ERR(opp_table)); goto unlock; } - /* Make sure there are no concurrent readers while updating dev_opp */ - WARN_ON(!list_empty(&dev_opp->opp_list)); + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); - if (!dev_opp->supported_hw) { + if (!opp_table->supported_hw) { dev_err(dev, "%s: Doesn't have supported hardware list\n", __func__); goto unlock; } - kfree(dev_opp->supported_hw); - dev_opp->supported_hw = NULL; - dev_opp->supported_hw_count = 0; + kfree(opp_table->supported_hw); + opp_table->supported_hw = NULL; + opp_table->supported_hw_count = 0; - /* Try freeing device_opp if this was the last blocking resource */ - _remove_device_opp(dev_opp); + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw); /** * dev_pm_opp_set_prop_name() - Set prop-extn name - * @dev: Device for which the regulator has to be set. + * @dev: Device for which the prop-name has to be set. * @name: name to postfix to properties. * * This is required only for the V2 bindings, and it enables a platform to @@ -989,7 +1315,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw); * which the extension will apply are opp-microvolt and opp-microamp. OPP core * should postfix the property name with -<name> while looking for them. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -997,42 +1323,42 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw); */ int dev_pm_opp_set_prop_name(struct device *dev, const char *name) { - struct device_opp *dev_opp; + struct opp_table *opp_table; int ret = 0; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - dev_opp = _add_device_opp(dev); - if (!dev_opp) { + opp_table = _add_opp_table(dev); + if (!opp_table) { ret = -ENOMEM; goto unlock; } - /* Make sure there are no concurrent readers while updating dev_opp */ - WARN_ON(!list_empty(&dev_opp->opp_list)); + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); - /* Do we already have a prop-name associated with dev_opp? */ - if (dev_opp->prop_name) { + /* Do we already have a prop-name associated with opp_table? */ + if (opp_table->prop_name) { dev_err(dev, "%s: Already have prop-name %s\n", __func__, - dev_opp->prop_name); + opp_table->prop_name); ret = -EBUSY; goto err; } - dev_opp->prop_name = kstrdup(name, GFP_KERNEL); - if (!dev_opp->prop_name) { + opp_table->prop_name = kstrdup(name, GFP_KERNEL); + if (!opp_table->prop_name) { ret = -ENOMEM; goto err; } - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return 0; err: - _remove_device_opp(dev_opp); + _remove_opp_table(opp_table); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } @@ -1040,13 +1366,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name); /** * dev_pm_opp_put_prop_name() - Releases resources blocked for prop-name - * @dev: Device for which the regulator has to be set. + * @dev: Device for which the prop-name has to be put. * * This is required only for the V2 bindings, and is called for a matching - * dev_pm_opp_set_prop_name(). Until this is called, the device_opp structure + * dev_pm_opp_set_prop_name(). Until this is called, the opp_table structure * will not be freed. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -1054,45 +1380,154 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name); */ void dev_pm_opp_put_prop_name(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - /* Check for existing list for 'dev' first */ - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - dev_err(dev, "Failed to find dev_opp: %ld\n", PTR_ERR(dev_opp)); + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "Failed to find opp_table: %ld\n", + PTR_ERR(opp_table)); goto unlock; } - /* Make sure there are no concurrent readers while updating dev_opp */ - WARN_ON(!list_empty(&dev_opp->opp_list)); + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); - if (!dev_opp->prop_name) { + if (!opp_table->prop_name) { dev_err(dev, "%s: Doesn't have a prop-name\n", __func__); goto unlock; } - kfree(dev_opp->prop_name); - dev_opp->prop_name = NULL; + kfree(opp_table->prop_name); + opp_table->prop_name = NULL; - /* Try freeing device_opp if this was the last blocking resource */ - _remove_device_opp(dev_opp); + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); -static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp, +/** + * dev_pm_opp_set_regulator() - Set regulator name for the device + * @dev: Device for which regulator name is being set. + * @name: Name of the regulator. + * + * In order to support OPP switching, OPP layer needs to know the name of the + * device's regulator, as the core would be required to switch voltages as well. + * + * This must be called before any OPPs are initialized for the device. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +int dev_pm_opp_set_regulator(struct device *dev, const char *name) +{ + struct opp_table *opp_table; + struct regulator *reg; + int ret; + + mutex_lock(&opp_table_lock); + + opp_table = _add_opp_table(dev); + if (!opp_table) { + ret = -ENOMEM; + goto unlock; + } + + /* This should be called before OPPs are initialized */ + if (WARN_ON(!list_empty(&opp_table->opp_list))) { + ret = -EBUSY; + goto err; + } + + /* Already have a regulator set */ + if (WARN_ON(!IS_ERR(opp_table->regulator))) { + ret = -EBUSY; + goto err; + } + /* Allocate the regulator */ + reg = regulator_get_optional(dev, name); + if (IS_ERR(reg)) { + ret = PTR_ERR(reg); + if (ret != -EPROBE_DEFER) + dev_err(dev, "%s: no regulator (%s) found: %d\n", + __func__, name, ret); + goto err; + } + + opp_table->regulator = reg; + + mutex_unlock(&opp_table_lock); + return 0; + +err: + _remove_opp_table(opp_table); +unlock: + mutex_unlock(&opp_table_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator); + +/** + * dev_pm_opp_put_regulator() - Releases resources blocked for regulator + * @dev: Device for which regulator was set. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +void dev_pm_opp_put_regulator(struct device *dev) +{ + struct opp_table *opp_table; + + mutex_lock(&opp_table_lock); + + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "Failed to find opp_table: %ld\n", + PTR_ERR(opp_table)); + goto unlock; + } + + if (IS_ERR(opp_table->regulator)) { + dev_err(dev, "%s: Doesn't have regulator set\n", __func__); + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + regulator_put(opp_table->regulator); + opp_table->regulator = ERR_PTR(-ENXIO); + + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); + +unlock: + mutex_unlock(&opp_table_lock); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator); + +static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table, struct device_node *np) { - unsigned int count = dev_opp->supported_hw_count; + unsigned int count = opp_table->supported_hw_count; u32 version; int ret; - if (!dev_opp->supported_hw) + if (!opp_table->supported_hw) return true; while (count--) { @@ -1105,7 +1540,7 @@ static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp, } /* Both of these are bitwise masks of the versions */ - if (!(version & dev_opp->supported_hw[count])) + if (!(version & opp_table->supported_hw[count])) return false; } @@ -1117,11 +1552,11 @@ static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp, * @dev: device for which we do this operation * @np: device node * - * This function adds an opp definition to the opp list and returns status. The + * This function adds an opp definition to the opp table and returns status. The * opp can be controlled using dev_pm_opp_enable/disable functions and may be * removed by dev_pm_opp_remove. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -1137,16 +1572,16 @@ static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp, */ static int _opp_add_static_v2(struct device *dev, struct device_node *np) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *new_opp; u64 rate; u32 val; int ret; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - new_opp = _allocate_opp(dev, &dev_opp); + new_opp = _allocate_opp(dev, &opp_table); if (!new_opp) { ret = -ENOMEM; goto unlock; @@ -1159,7 +1594,7 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) } /* Check if the OPP supports hardware's hierarchy of versions or not */ - if (!_opp_is_supported(dev, dev_opp, np)) { + if (!_opp_is_supported(dev, opp_table, np)) { dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate); goto free_opp; } @@ -1179,30 +1614,30 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) if (!of_property_read_u32(np, "clock-latency-ns", &val)) new_opp->clock_latency_ns = val; - ret = opp_parse_supplies(new_opp, dev, dev_opp); + ret = opp_parse_supplies(new_opp, dev, opp_table); if (ret) goto free_opp; - ret = _opp_add(dev, new_opp, dev_opp); + ret = _opp_add(dev, new_opp, opp_table); if (ret) goto free_opp; /* OPP to select on device suspend */ if (of_property_read_bool(np, "opp-suspend")) { - if (dev_opp->suspend_opp) { + if (opp_table->suspend_opp) { dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n", - __func__, dev_opp->suspend_opp->rate, + __func__, opp_table->suspend_opp->rate, new_opp->rate); } else { new_opp->suspend = true; - dev_opp->suspend_opp = new_opp; + opp_table->suspend_opp = new_opp; } } - if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max) - dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns; + if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max) + opp_table->clock_latency_ns_max = new_opp->clock_latency_ns; - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n", __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt, @@ -1213,13 +1648,13 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) * Notify the changes in the availability of the operable * frequency/voltage list. */ - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp); return 0; free_opp: - _opp_remove(dev_opp, new_opp, false); + _opp_remove(opp_table, new_opp, false); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } @@ -1229,11 +1664,11 @@ unlock: * @freq: Frequency in Hz for this OPP * @u_volt: Voltage in uVolts for this OPP * - * This function adds an opp definition to the opp list and returns status. + * This function adds an opp definition to the opp table and returns status. * The opp is made available by default and it can be controlled using * dev_pm_opp_enable/disable functions. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -1265,7 +1700,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add); * copy operation, returns 0 if no modification was done OR modification was * successful. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks to * keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -1274,7 +1709,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add); static int _opp_set_availability(struct device *dev, unsigned long freq, bool availability_req) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV); int r = 0; @@ -1283,18 +1718,18 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, if (!new_opp) return -ENOMEM; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - /* Find the device_opp */ - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - r = PTR_ERR(dev_opp); + /* Find the opp_table */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + r = PTR_ERR(opp_table); dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); goto unlock; } /* Do we have the frequency? */ - list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) { + list_for_each_entry(tmp_opp, &opp_table->opp_list, node) { if (tmp_opp->rate == freq) { opp = tmp_opp; break; @@ -1315,21 +1750,21 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, new_opp->available = availability_req; list_replace_rcu(&opp->node, &new_opp->node); - mutex_unlock(&dev_opp_list_lock); - call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); + mutex_unlock(&opp_table_lock); + call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); /* Notify the change of the OPP availability */ if (availability_req) - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ENABLE, - new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, + OPP_EVENT_ENABLE, new_opp); else - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_DISABLE, - new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, + OPP_EVENT_DISABLE, new_opp); return 0; unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); kfree(new_opp); return r; } @@ -1343,7 +1778,7 @@ unlock: * corresponding error value. It is meant to be used for users an OPP available * after being temporarily made unavailable with dev_pm_opp_disable. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU and mutex locks to keep the * integrity of the internal data structures. Callers should ensure that * this function is *NOT* called under RCU protection or in contexts where @@ -1369,7 +1804,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable); * control by users to make this OPP not available until the circumstances are * right to make it available again (with a call to dev_pm_opp_enable). * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU and mutex locks to keep the * integrity of the internal data structures. Callers should ensure that * this function is *NOT* called under RCU protection or in contexts where @@ -1387,26 +1822,26 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_disable); /** * dev_pm_opp_get_notifier() - find notifier_head of the device with opp - * @dev: device pointer used to lookup device OPPs. + * @dev: device pointer used to lookup OPP table. * * Return: pointer to notifier head if found, otherwise -ENODEV or * -EINVAL based on type of error casted as pointer. value must be checked * with IS_ERR to determine valid pointer or error result. * - * Locking: This function must be called under rcu_read_lock(). dev_opp is a RCU - * protected pointer. The reason for the same is that the opp pointer which is - * returned will remain valid for use with opp_get_{voltage, freq} only while + * Locking: This function must be called under rcu_read_lock(). opp_table is a + * RCU protected pointer. The reason for the same is that the opp pointer which + * is returned will remain valid for use with opp_get_{voltage, freq} only while * under the locked area. The pointer returned must be used prior to unlocking * with rcu_read_unlock() to maintain the integrity of the pointer. */ struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev) { - struct device_opp *dev_opp = _find_device_opp(dev); + struct opp_table *opp_table = _find_opp_table(dev); - if (IS_ERR(dev_opp)) - return ERR_CAST(dev_opp); /* matching type */ + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); /* matching type */ - return &dev_opp->srcu_head; + return &opp_table->srcu_head; } EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); @@ -1414,11 +1849,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); /** * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT * entries - * @dev: device pointer used to lookup device OPPs. + * @dev: device pointer used to lookup OPP table. * * Free OPPs created using static entries present in DT. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -1426,38 +1861,38 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); */ void dev_pm_opp_of_remove_table(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *opp, *tmp; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - /* Check for existing list for 'dev' */ - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - int error = PTR_ERR(dev_opp); + /* Check for existing table for 'dev' */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + int error = PTR_ERR(opp_table); if (error != -ENODEV) - WARN(1, "%s: dev_opp: %d\n", + WARN(1, "%s: opp_table: %d\n", IS_ERR_OR_NULL(dev) ? "Invalid device" : dev_name(dev), error); goto unlock; } - /* Find if dev_opp manages a single device */ - if (list_is_singular(&dev_opp->dev_list)) { + /* Find if opp_table manages a single device */ + if (list_is_singular(&opp_table->dev_list)) { /* Free static OPPs */ - list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) { + list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { if (!opp->dynamic) - _opp_remove(dev_opp, opp, true); + _opp_remove(opp_table, opp, true); } } else { - _remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp); + _remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table); } unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table); @@ -1478,22 +1913,22 @@ struct device_node *_of_get_opp_desc_node(struct device *dev) static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) { struct device_node *np; - struct device_opp *dev_opp; + struct opp_table *opp_table; int ret = 0, count = 0; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - dev_opp = _managed_opp(opp_np); - if (dev_opp) { + opp_table = _managed_opp(opp_np); + if (opp_table) { /* OPPs are already managed */ - if (!_add_list_dev(dev, dev_opp)) + if (!_add_opp_dev(dev, opp_table)) ret = -ENOMEM; - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); - /* We have opp-list node now, iterate over it and add OPPs */ + /* We have opp-table node now, iterate over it and add OPPs */ for_each_available_child_of_node(opp_np, np) { count++; @@ -1509,19 +1944,19 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) if (WARN_ON(!count)) return -ENOENT; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - dev_opp = _find_device_opp(dev); - if (WARN_ON(IS_ERR(dev_opp))) { - ret = PTR_ERR(dev_opp); - mutex_unlock(&dev_opp_list_lock); + opp_table = _find_opp_table(dev); + if (WARN_ON(IS_ERR(opp_table))) { + ret = PTR_ERR(opp_table); + mutex_unlock(&opp_table_lock); goto free_table; } - dev_opp->np = opp_np; - dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared"); + opp_table->np = opp_np; + opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared"); - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return 0; @@ -1550,7 +1985,7 @@ static int _of_add_opp_table_v1(struct device *dev) */ nr = prop->length / sizeof(u32); if (nr % 2) { - dev_err(dev, "%s: Invalid OPP list\n", __func__); + dev_err(dev, "%s: Invalid OPP table\n", __func__); return -EINVAL; } @@ -1570,11 +2005,11 @@ static int _of_add_opp_table_v1(struct device *dev) /** * dev_pm_opp_of_add_table() - Initialize opp table from device tree - * @dev: device pointer used to lookup device OPPs. + * @dev: device pointer used to lookup OPP table. * * Register the initial OPP table with the OPP library for given device. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c index 9f0c15570f64..ba2bdbd932ef 100644 --- a/drivers/base/power/opp/cpu.c +++ b/drivers/base/power/opp/cpu.c @@ -31,7 +31,7 @@ * @table: Cpufreq table returned back to caller * * Generate a cpufreq table for a provided device- this assumes that the - * opp list is already initialized and ready for usage. + * opp table is already initialized and ready for usage. * * This function allocates required memory for the cpufreq table. It is * expected that the caller does the required maintenance such as freeing @@ -44,7 +44,7 @@ * WARNING: It is important for the callers to ensure refreshing their copy of * the table if any of the mentioned functions have been invoked in the interim. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Since we just use the regular accessor functions to access the internal data * structures, we use RCU read lock inside this function. As a result, users of * this function DONOT need to use explicit locks for invoking. @@ -122,15 +122,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table); /* Required only for V1 bindings, as v2 can manage it from DT itself */ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) { - struct device_list_opp *list_dev; - struct device_opp *dev_opp; + struct opp_device *opp_dev; + struct opp_table *opp_table; struct device *dev; int cpu, ret = 0; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - dev_opp = _find_device_opp(cpu_dev); - if (IS_ERR(dev_opp)) { + opp_table = _find_opp_table(cpu_dev); + if (IS_ERR(opp_table)) { ret = -EINVAL; goto unlock; } @@ -146,15 +146,15 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) continue; } - list_dev = _add_list_dev(dev, dev_opp); - if (!list_dev) { - dev_err(dev, "%s: failed to add list-dev for cpu%d device\n", + opp_dev = _add_opp_dev(dev, opp_table); + if (!opp_dev) { + dev_err(dev, "%s: failed to add opp-dev for cpu%d device\n", __func__, cpu); continue; } } unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c index ddfe4773e922..ef1ae6b52042 100644 --- a/drivers/base/power/opp/debugfs.c +++ b/drivers/base/power/opp/debugfs.c @@ -34,9 +34,9 @@ void opp_debug_remove_one(struct dev_pm_opp *opp) debugfs_remove_recursive(opp->dentry); } -int opp_debug_create_one(struct dev_pm_opp *opp, struct device_opp *dev_opp) +int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) { - struct dentry *pdentry = dev_opp->dentry; + struct dentry *pdentry = opp_table->dentry; struct dentry *d; char name[25]; /* 20 chars for 64 bit value + 5 (opp:\0) */ @@ -83,52 +83,52 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct device_opp *dev_opp) return 0; } -static int device_opp_debug_create_dir(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static int opp_list_debug_create_dir(struct opp_device *opp_dev, + struct opp_table *opp_table) { - const struct device *dev = list_dev->dev; + const struct device *dev = opp_dev->dev; struct dentry *d; - opp_set_dev_name(dev, dev_opp->dentry_name); + opp_set_dev_name(dev, opp_table->dentry_name); /* Create device specific directory */ - d = debugfs_create_dir(dev_opp->dentry_name, rootdir); + d = debugfs_create_dir(opp_table->dentry_name, rootdir); if (!d) { dev_err(dev, "%s: Failed to create debugfs dir\n", __func__); return -ENOMEM; } - list_dev->dentry = d; - dev_opp->dentry = d; + opp_dev->dentry = d; + opp_table->dentry = d; return 0; } -static int device_opp_debug_create_link(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static int opp_list_debug_create_link(struct opp_device *opp_dev, + struct opp_table *opp_table) { - const struct device *dev = list_dev->dev; + const struct device *dev = opp_dev->dev; char name[NAME_MAX]; struct dentry *d; - opp_set_dev_name(list_dev->dev, name); + opp_set_dev_name(opp_dev->dev, name); /* Create device specific directory link */ - d = debugfs_create_symlink(name, rootdir, dev_opp->dentry_name); + d = debugfs_create_symlink(name, rootdir, opp_table->dentry_name); if (!d) { dev_err(dev, "%s: Failed to create link\n", __func__); return -ENOMEM; } - list_dev->dentry = d; + opp_dev->dentry = d; return 0; } /** * opp_debug_register - add a device opp node to the debugfs 'opp' directory - * @list_dev: list-dev pointer for device - * @dev_opp: the device-opp being added + * @opp_dev: opp-dev pointer for device + * @opp_table: the device-opp being added * * Dynamically adds device specific directory in debugfs 'opp' directory. If the * device-opp is shared with other devices, then links will be created for all @@ -136,73 +136,72 @@ static int device_opp_debug_create_link(struct device_list_opp *list_dev, * * Return: 0 on success, otherwise negative error. */ -int opp_debug_register(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table) { if (!rootdir) { pr_debug("%s: Uninitialized rootdir\n", __func__); return -EINVAL; } - if (dev_opp->dentry) - return device_opp_debug_create_link(list_dev, dev_opp); + if (opp_table->dentry) + return opp_list_debug_create_link(opp_dev, opp_table); - return device_opp_debug_create_dir(list_dev, dev_opp); + return opp_list_debug_create_dir(opp_dev, opp_table); } -static void opp_migrate_dentry(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static void opp_migrate_dentry(struct opp_device *opp_dev, + struct opp_table *opp_table) { - struct device_list_opp *new_dev; + struct opp_device *new_dev; const struct device *dev; struct dentry *dentry; - /* Look for next list-dev */ - list_for_each_entry(new_dev, &dev_opp->dev_list, node) - if (new_dev != list_dev) + /* Look for next opp-dev */ + list_for_each_entry(new_dev, &opp_table->dev_list, node) + if (new_dev != opp_dev) break; /* new_dev is guaranteed to be valid here */ dev = new_dev->dev; debugfs_remove_recursive(new_dev->dentry); - opp_set_dev_name(dev, dev_opp->dentry_name); + opp_set_dev_name(dev, opp_table->dentry_name); - dentry = debugfs_rename(rootdir, list_dev->dentry, rootdir, - dev_opp->dentry_name); + dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir, + opp_table->dentry_name); if (!dentry) { dev_err(dev, "%s: Failed to rename link from: %s to %s\n", - __func__, dev_name(list_dev->dev), dev_name(dev)); + __func__, dev_name(opp_dev->dev), dev_name(dev)); return; } new_dev->dentry = dentry; - dev_opp->dentry = dentry; + opp_table->dentry = dentry; } /** * opp_debug_unregister - remove a device opp node from debugfs opp directory - * @list_dev: list-dev pointer for device - * @dev_opp: the device-opp being removed + * @opp_dev: opp-dev pointer for device + * @opp_table: the device-opp being removed * * Dynamically removes device specific directory from debugfs 'opp' directory. */ -void opp_debug_unregister(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +void opp_debug_unregister(struct opp_device *opp_dev, + struct opp_table *opp_table) { - if (list_dev->dentry == dev_opp->dentry) { + if (opp_dev->dentry == opp_table->dentry) { /* Move the real dentry object under another device */ - if (!list_is_singular(&dev_opp->dev_list)) { - opp_migrate_dentry(list_dev, dev_opp); + if (!list_is_singular(&opp_table->dev_list)) { + opp_migrate_dentry(opp_dev, opp_table); goto out; } - dev_opp->dentry = NULL; + opp_table->dentry = NULL; } - debugfs_remove_recursive(list_dev->dentry); + debugfs_remove_recursive(opp_dev->dentry); out: - list_dev->dentry = NULL; + opp_dev->dentry = NULL; } static int __init opp_debug_init(void) diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index 690638ef36ee..f67f806fcf3a 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -22,13 +22,16 @@ #include <linux/rculist.h> #include <linux/rcupdate.h> +struct clk; +struct regulator; + /* Lock to allow exclusive modification to the device and opp lists */ -extern struct mutex dev_opp_list_lock; +extern struct mutex opp_table_lock; /* * Internal data structure organization with the OPP layer library is as * follows: - * dev_opp_list (root) + * opp_tables (root) * |- device 1 (represents voltage domain 1) * | |- opp 1 (availability, freq, voltage) * | |- opp 2 .. @@ -37,18 +40,18 @@ extern struct mutex dev_opp_list_lock; * |- device 2 (represents the next voltage domain) * ... * `- device m (represents mth voltage domain) - * device 1, 2.. are represented by dev_opp structure while each opp + * device 1, 2.. are represented by opp_table structure while each opp * is represented by the opp structure. */ /** * struct dev_pm_opp - Generic OPP description structure - * @node: opp list node. The nodes are maintained throughout the lifetime + * @node: opp table node. The nodes are maintained throughout the lifetime * of boot. It is expected only an optimal set of OPPs are * added to the library by the SoC framework. - * RCU usage: opp list is traversed with RCU locks. node + * RCU usage: opp table is traversed with RCU locks. node * modification is possible realtime, hence the modifications - * are protected by the dev_opp_list_lock for integrity. + * are protected by the opp_table_lock for integrity. * IMPORTANT: the opp nodes should be maintained in increasing * order. * @available: true/false - marks if this OPP as available or not @@ -62,7 +65,7 @@ extern struct mutex dev_opp_list_lock; * @u_amp: Maximum current drawn by the device in microamperes * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's * frequency from any other OPP's frequency. - * @dev_opp: points back to the device_opp struct this opp belongs to + * @opp_table: points back to the opp_table struct this opp belongs to * @rcu_head: RCU callback head used for deferred freeing * @np: OPP's device node. * @dentry: debugfs dentry pointer (per opp) @@ -84,7 +87,7 @@ struct dev_pm_opp { unsigned long u_amp; unsigned long clock_latency_ns; - struct device_opp *dev_opp; + struct opp_table *opp_table; struct rcu_head rcu_head; struct device_node *np; @@ -95,16 +98,16 @@ struct dev_pm_opp { }; /** - * struct device_list_opp - devices managed by 'struct device_opp' + * struct opp_device - devices managed by 'struct opp_table' * @node: list node * @dev: device to which the struct object belongs * @rcu_head: RCU callback head used for deferred freeing * @dentry: debugfs dentry pointer (per device) * - * This is an internal data structure maintaining the list of devices that are - * managed by 'struct device_opp'. + * This is an internal data structure maintaining the devices that are managed + * by 'struct opp_table'. */ -struct device_list_opp { +struct opp_device { struct list_head node; const struct device *dev; struct rcu_head rcu_head; @@ -115,16 +118,16 @@ struct device_list_opp { }; /** - * struct device_opp - Device opp structure - * @node: list node - contains the devices with OPPs that + * struct opp_table - Device opp structure + * @node: table node - contains the devices with OPPs that * have been registered. Nodes once added are not modified in this - * list. - * RCU usage: nodes are not modified in the list of device_opp, - * however addition is possible and is secured by dev_opp_list_lock + * table. + * RCU usage: nodes are not modified in the table of opp_table, + * however addition is possible and is secured by opp_table_lock * @srcu_head: notifier head to notify the OPP availability changes. * @rcu_head: RCU callback head used for deferred freeing * @dev_list: list of devices that share these OPPs - * @opp_list: list of opps + * @opp_list: table of opps * @np: struct device_node pointer for opp's DT node. * @clock_latency_ns_max: Max clock latency in nanoseconds. * @shared_opp: OPP is shared between multiple devices. @@ -132,9 +135,13 @@ struct device_list_opp { * @supported_hw: Array of version number to support. * @supported_hw_count: Number of elements in supported_hw array. * @prop_name: A name to postfix to many DT properties, while parsing them. + * @clk: Device's clock handle + * @regulator: Supply regulator * @dentry: debugfs dentry pointer of the real device directory (not links). * @dentry_name: Name of the real dentry. * + * @voltage_tolerance_v1: In percentage, for v1 bindings only. + * * This is an internal data structure maintaining the link to opps attached to * a device. This structure is not meant to be shared to users as it is * meant for book keeping and private to OPP library. @@ -143,7 +150,7 @@ struct device_list_opp { * need to wait for the grace period of both of them before freeing any * resources. And so we have used kfree_rcu() from within call_srcu() handlers. */ -struct device_opp { +struct opp_table { struct list_head node; struct srcu_notifier_head srcu_head; @@ -153,12 +160,18 @@ struct device_opp { struct device_node *np; unsigned long clock_latency_ns_max; + + /* For backward compatibility with v1 bindings */ + unsigned int voltage_tolerance_v1; + bool shared_opp; struct dev_pm_opp *suspend_opp; unsigned int *supported_hw; unsigned int supported_hw_count; const char *prop_name; + struct clk *clk; + struct regulator *regulator; #ifdef CONFIG_DEBUG_FS struct dentry *dentry; @@ -167,30 +180,27 @@ struct device_opp { }; /* Routines internal to opp core */ -struct device_opp *_find_device_opp(struct device *dev); -struct device_list_opp *_add_list_dev(const struct device *dev, - struct device_opp *dev_opp); +struct opp_table *_find_opp_table(struct device *dev); +struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table); struct device_node *_of_get_opp_desc_node(struct device *dev); #ifdef CONFIG_DEBUG_FS void opp_debug_remove_one(struct dev_pm_opp *opp); -int opp_debug_create_one(struct dev_pm_opp *opp, struct device_opp *dev_opp); -int opp_debug_register(struct device_list_opp *list_dev, - struct device_opp *dev_opp); -void opp_debug_unregister(struct device_list_opp *list_dev, - struct device_opp *dev_opp); +int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table); +int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table); +void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table); #else static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {} static inline int opp_debug_create_one(struct dev_pm_opp *opp, - struct device_opp *dev_opp) + struct opp_table *opp_table) { return 0; } -static inline int opp_debug_register(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static inline int opp_debug_register(struct opp_device *opp_dev, + struct opp_table *opp_table) { return 0; } -static inline void opp_debug_unregister(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static inline void opp_debug_unregister(struct opp_device *opp_dev, + struct opp_table *opp_table) { } #endif /* DEBUG_FS */ diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index a311cfa4c5bd..a6975795e7f3 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -166,14 +166,14 @@ void generate_pm_trace(const void *tracedata, unsigned int user) } EXPORT_SYMBOL(generate_pm_trace); -extern char __tracedata_start, __tracedata_end; +extern char __tracedata_start[], __tracedata_end[]; static int show_file_hash(unsigned int value) { int match; char *tracedata; match = 0; - for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ; + for (tracedata = __tracedata_start ; tracedata < __tracedata_end ; tracedata += 2 + sizeof(unsigned long)) { unsigned short lineno = *(unsigned short *)tracedata; const char *file = *(const char **)(tracedata + 2); diff --git a/drivers/base/property.c b/drivers/base/property.c index a163f2c59aa3..76628a7b45f1 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -218,7 +218,8 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname) bool ret; ret = __fwnode_property_present(fwnode, propname); - if (ret == false && fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) + if (ret == false && !IS_ERR_OR_NULL(fwnode) && + !IS_ERR_OR_NULL(fwnode->secondary)) ret = __fwnode_property_present(fwnode->secondary, propname); return ret; } @@ -423,7 +424,8 @@ EXPORT_SYMBOL_GPL(device_property_match_string); int _ret_; \ _ret_ = FWNODE_PROP_READ(_fwnode_, _propname_, _type_, _proptype_, \ _val_, _nval_); \ - if (_ret_ == -EINVAL && _fwnode_ && !IS_ERR_OR_NULL(_fwnode_->secondary)) \ + if (_ret_ == -EINVAL && !IS_ERR_OR_NULL(_fwnode_) && \ + !IS_ERR_OR_NULL(_fwnode_->secondary)) \ _ret_ = FWNODE_PROP_READ(_fwnode_->secondary, _propname_, _type_, \ _proptype_, _val_, _nval_); \ _ret_; \ @@ -593,7 +595,8 @@ int fwnode_property_read_string_array(struct fwnode_handle *fwnode, int ret; ret = __fwnode_property_read_string_array(fwnode, propname, val, nval); - if (ret == -EINVAL && fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) + if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) && + !IS_ERR_OR_NULL(fwnode->secondary)) ret = __fwnode_property_read_string_array(fwnode->secondary, propname, val, nval); return ret; @@ -621,7 +624,8 @@ int fwnode_property_read_string(struct fwnode_handle *fwnode, int ret; ret = __fwnode_property_read_string(fwnode, propname, val); - if (ret == -EINVAL && fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) + if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) && + !IS_ERR_OR_NULL(fwnode->secondary)) ret = __fwnode_property_read_string(fwnode->secondary, propname, val); return ret; @@ -820,11 +824,16 @@ void device_remove_property_set(struct device *dev) * the pset. If there is no real firmware node (ACPI/DT) primary * will hold the pset. */ - if (!is_pset_node(fwnode)) - fwnode = fwnode->secondary; - if (!IS_ERR(fwnode) && is_pset_node(fwnode)) + if (is_pset_node(fwnode)) { + set_primary_fwnode(dev, NULL); pset_free_set(to_pset_node(fwnode)); - set_secondary_fwnode(dev, NULL); + } else { + fwnode = fwnode->secondary; + if (!IS_ERR(fwnode) && is_pset_node(fwnode)) { + set_secondary_fwnode(dev, NULL); + pset_free_set(to_pset_node(fwnode)); + } + } } EXPORT_SYMBOL_GPL(device_remove_property_set); diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index f93511031177..a7f45853c103 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -19,6 +19,7 @@ config CPU_FREQ if CPU_FREQ config CPU_FREQ_GOV_COMMON + select IRQ_WORK bool config CPU_FREQ_BOOST_SW diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 51eef87bbc37..59a7b380fbe2 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -70,6 +70,8 @@ struct acpi_cpufreq_data { unsigned int cpu_feature; unsigned int acpi_perf_cpu; cpumask_var_t freqdomain_cpus; + void (*cpu_freq_write)(struct acpi_pct_register *reg, u32 val); + u32 (*cpu_freq_read)(struct acpi_pct_register *reg); }; /* acpi_perf_data is a pointer to percpu data. */ @@ -243,125 +245,119 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data) } } -struct msr_addr { - u32 reg; -}; +u32 cpu_freq_read_intel(struct acpi_pct_register *not_used) +{ + u32 val, dummy; -struct io_addr { - u16 port; - u8 bit_width; -}; + rdmsr(MSR_IA32_PERF_CTL, val, dummy); + return val; +} + +void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val) +{ + u32 lo, hi; + + rdmsr(MSR_IA32_PERF_CTL, lo, hi); + lo = (lo & ~INTEL_MSR_RANGE) | (val & INTEL_MSR_RANGE); + wrmsr(MSR_IA32_PERF_CTL, lo, hi); +} + +u32 cpu_freq_read_amd(struct acpi_pct_register *not_used) +{ + u32 val, dummy; + + rdmsr(MSR_AMD_PERF_CTL, val, dummy); + return val; +} + +void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val) +{ + wrmsr(MSR_AMD_PERF_CTL, val, 0); +} + +u32 cpu_freq_read_io(struct acpi_pct_register *reg) +{ + u32 val; + + acpi_os_read_port(reg->address, &val, reg->bit_width); + return val; +} + +void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val) +{ + acpi_os_write_port(reg->address, val, reg->bit_width); +} struct drv_cmd { - unsigned int type; - const struct cpumask *mask; - union { - struct msr_addr msr; - struct io_addr io; - } addr; + struct acpi_pct_register *reg; u32 val; + union { + void (*write)(struct acpi_pct_register *reg, u32 val); + u32 (*read)(struct acpi_pct_register *reg); + } func; }; /* Called via smp_call_function_single(), on the target CPU */ static void do_drv_read(void *_cmd) { struct drv_cmd *cmd = _cmd; - u32 h; - switch (cmd->type) { - case SYSTEM_INTEL_MSR_CAPABLE: - case SYSTEM_AMD_MSR_CAPABLE: - rdmsr(cmd->addr.msr.reg, cmd->val, h); - break; - case SYSTEM_IO_CAPABLE: - acpi_os_read_port((acpi_io_address)cmd->addr.io.port, - &cmd->val, - (u32)cmd->addr.io.bit_width); - break; - default: - break; - } + cmd->val = cmd->func.read(cmd->reg); } -/* Called via smp_call_function_many(), on the target CPUs */ -static void do_drv_write(void *_cmd) +static u32 drv_read(struct acpi_cpufreq_data *data, const struct cpumask *mask) { - struct drv_cmd *cmd = _cmd; - u32 lo, hi; + struct acpi_processor_performance *perf = to_perf_data(data); + struct drv_cmd cmd = { + .reg = &perf->control_register, + .func.read = data->cpu_freq_read, + }; + int err; - switch (cmd->type) { - case SYSTEM_INTEL_MSR_CAPABLE: - rdmsr(cmd->addr.msr.reg, lo, hi); - lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE); - wrmsr(cmd->addr.msr.reg, lo, hi); - break; - case SYSTEM_AMD_MSR_CAPABLE: - wrmsr(cmd->addr.msr.reg, cmd->val, 0); - break; - case SYSTEM_IO_CAPABLE: - acpi_os_write_port((acpi_io_address)cmd->addr.io.port, - cmd->val, - (u32)cmd->addr.io.bit_width); - break; - default: - break; - } + err = smp_call_function_any(mask, do_drv_read, &cmd, 1); + WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */ + return cmd.val; } -static void drv_read(struct drv_cmd *cmd) +/* Called via smp_call_function_many(), on the target CPUs */ +static void do_drv_write(void *_cmd) { - int err; - cmd->val = 0; + struct drv_cmd *cmd = _cmd; - err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1); - WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */ + cmd->func.write(cmd->reg, cmd->val); } -static void drv_write(struct drv_cmd *cmd) +static void drv_write(struct acpi_cpufreq_data *data, + const struct cpumask *mask, u32 val) { + struct acpi_processor_performance *perf = to_perf_data(data); + struct drv_cmd cmd = { + .reg = &perf->control_register, + .val = val, + .func.write = data->cpu_freq_write, + }; int this_cpu; this_cpu = get_cpu(); - if (cpumask_test_cpu(this_cpu, cmd->mask)) - do_drv_write(cmd); - smp_call_function_many(cmd->mask, do_drv_write, cmd, 1); + if (cpumask_test_cpu(this_cpu, mask)) + do_drv_write(&cmd); + + smp_call_function_many(mask, do_drv_write, &cmd, 1); put_cpu(); } -static u32 -get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data) +static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data) { - struct acpi_processor_performance *perf; - struct drv_cmd cmd; + u32 val; if (unlikely(cpumask_empty(mask))) return 0; - switch (data->cpu_feature) { - case SYSTEM_INTEL_MSR_CAPABLE: - cmd.type = SYSTEM_INTEL_MSR_CAPABLE; - cmd.addr.msr.reg = MSR_IA32_PERF_CTL; - break; - case SYSTEM_AMD_MSR_CAPABLE: - cmd.type = SYSTEM_AMD_MSR_CAPABLE; - cmd.addr.msr.reg = MSR_AMD_PERF_CTL; - break; - case SYSTEM_IO_CAPABLE: - cmd.type = SYSTEM_IO_CAPABLE; - perf = to_perf_data(data); - cmd.addr.io.port = perf->control_register.address; - cmd.addr.io.bit_width = perf->control_register.bit_width; - break; - default: - return 0; - } - - cmd.mask = mask; - drv_read(&cmd); + val = drv_read(data, mask); - pr_debug("get_cur_val = %u\n", cmd.val); + pr_debug("get_cur_val = %u\n", val); - return cmd.val; + return val; } static unsigned int get_cur_freq_on_cpu(unsigned int cpu) @@ -416,7 +412,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, { struct acpi_cpufreq_data *data = policy->driver_data; struct acpi_processor_performance *perf; - struct drv_cmd cmd; + const struct cpumask *mask; unsigned int next_perf_state = 0; /* Index into perf table */ int result = 0; @@ -434,42 +430,21 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } else { pr_debug("Already at target state (P%d)\n", next_perf_state); - goto out; + return 0; } } - switch (data->cpu_feature) { - case SYSTEM_INTEL_MSR_CAPABLE: - cmd.type = SYSTEM_INTEL_MSR_CAPABLE; - cmd.addr.msr.reg = MSR_IA32_PERF_CTL; - cmd.val = (u32) perf->states[next_perf_state].control; - break; - case SYSTEM_AMD_MSR_CAPABLE: - cmd.type = SYSTEM_AMD_MSR_CAPABLE; - cmd.addr.msr.reg = MSR_AMD_PERF_CTL; - cmd.val = (u32) perf->states[next_perf_state].control; - break; - case SYSTEM_IO_CAPABLE: - cmd.type = SYSTEM_IO_CAPABLE; - cmd.addr.io.port = perf->control_register.address; - cmd.addr.io.bit_width = perf->control_register.bit_width; - cmd.val = (u32) perf->states[next_perf_state].control; - break; - default: - result = -ENODEV; - goto out; - } - - /* cpufreq holds the hotplug lock, so we are safe from here on */ - if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY) - cmd.mask = policy->cpus; - else - cmd.mask = cpumask_of(policy->cpu); + /* + * The core won't allow CPUs to go away until the governor has been + * stopped, so we can rely on the stability of policy->cpus. + */ + mask = policy->shared_type == CPUFREQ_SHARED_TYPE_ANY ? + cpumask_of(policy->cpu) : policy->cpus; - drv_write(&cmd); + drv_write(data, mask, perf->states[next_perf_state].control); if (acpi_pstate_strict) { - if (!check_freqs(cmd.mask, data->freq_table[index].frequency, + if (!check_freqs(mask, data->freq_table[index].frequency, data)) { pr_debug("acpi_cpufreq_target failed (%d)\n", policy->cpu); @@ -480,7 +455,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, if (!result) perf->state = next_perf_state; -out: return result; } @@ -740,15 +714,21 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) } pr_debug("SYSTEM IO addr space\n"); data->cpu_feature = SYSTEM_IO_CAPABLE; + data->cpu_freq_read = cpu_freq_read_io; + data->cpu_freq_write = cpu_freq_write_io; break; case ACPI_ADR_SPACE_FIXED_HARDWARE: pr_debug("HARDWARE addr space\n"); if (check_est_cpu(cpu)) { data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; + data->cpu_freq_read = cpu_freq_read_intel; + data->cpu_freq_write = cpu_freq_write_intel; break; } if (check_amd_hwpstate_cpu(cpu)) { data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE; + data->cpu_freq_read = cpu_freq_read_amd; + data->cpu_freq_write = cpu_freq_write_amd; break; } result = -ENODEV; diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c index f6b79ab0070b..404360cad25c 100644 --- a/drivers/cpufreq/amd_freq_sensitivity.c +++ b/drivers/cpufreq/amd_freq_sensitivity.c @@ -21,7 +21,7 @@ #include <asm/msr.h> #include <asm/cpufeature.h> -#include "cpufreq_governor.h" +#include "cpufreq_ondemand.h" #define MSR_AMD64_FREQ_SENSITIVITY_ACTUAL 0xc0010080 #define MSR_AMD64_FREQ_SENSITIVITY_REFERENCE 0xc0010081 @@ -45,10 +45,10 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy, long d_actual, d_reference; struct msr actual, reference; struct cpu_data_t *data = &per_cpu(cpu_data, policy->cpu); - struct dbs_data *od_data = policy->governor_data; + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *od_data = policy_dbs->dbs_data; struct od_dbs_tuners *od_tuners = od_data->tuners; - struct od_cpu_dbs_info_s *od_info = - od_data->cdata->get_cpu_dbs_info_s(policy->cpu); + struct od_policy_dbs_info *od_info = to_dbs_info(policy_dbs); if (!od_info->freq_table) return freq_next; diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 0ca74d070058..f951f911786e 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -31,9 +31,8 @@ struct private_data { struct device *cpu_dev; - struct regulator *cpu_reg; struct thermal_cooling_device *cdev; - unsigned int voltage_tolerance; /* in percentage */ + const char *reg_name; }; static struct freq_attr *cpufreq_dt_attr[] = { @@ -44,175 +43,128 @@ static struct freq_attr *cpufreq_dt_attr[] = { static int set_target(struct cpufreq_policy *policy, unsigned int index) { - struct dev_pm_opp *opp; - struct cpufreq_frequency_table *freq_table = policy->freq_table; - struct clk *cpu_clk = policy->clk; struct private_data *priv = policy->driver_data; - struct device *cpu_dev = priv->cpu_dev; - struct regulator *cpu_reg = priv->cpu_reg; - unsigned long volt = 0, tol = 0; - int volt_old = 0; - unsigned int old_freq, new_freq; - long freq_Hz, freq_exact; - int ret; - - freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000); - if (freq_Hz <= 0) - freq_Hz = freq_table[index].frequency * 1000; - freq_exact = freq_Hz; - new_freq = freq_Hz / 1000; - old_freq = clk_get_rate(cpu_clk) / 1000; + return dev_pm_opp_set_rate(priv->cpu_dev, + policy->freq_table[index].frequency * 1000); +} - if (!IS_ERR(cpu_reg)) { - unsigned long opp_freq; +/* + * An earlier version of opp-v1 bindings used to name the regulator + * "cpu0-supply", we still need to handle that for backwards compatibility. + */ +static const char *find_supply_name(struct device *dev) +{ + struct device_node *np; + struct property *pp; + int cpu = dev->id; + const char *name = NULL; - rcu_read_lock(); - opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz); - if (IS_ERR(opp)) { - rcu_read_unlock(); - dev_err(cpu_dev, "failed to find OPP for %ld\n", - freq_Hz); - return PTR_ERR(opp); - } - volt = dev_pm_opp_get_voltage(opp); - opp_freq = dev_pm_opp_get_freq(opp); - rcu_read_unlock(); - tol = volt * priv->voltage_tolerance / 100; - volt_old = regulator_get_voltage(cpu_reg); - dev_dbg(cpu_dev, "Found OPP: %ld kHz, %ld uV\n", - opp_freq / 1000, volt); - } + np = of_node_get(dev->of_node); - dev_dbg(cpu_dev, "%u MHz, %d mV --> %u MHz, %ld mV\n", - old_freq / 1000, (volt_old > 0) ? volt_old / 1000 : -1, - new_freq / 1000, volt ? volt / 1000 : -1); + /* This must be valid for sure */ + if (WARN_ON(!np)) + return NULL; - /* scaling up? scale voltage before frequency */ - if (!IS_ERR(cpu_reg) && new_freq > old_freq) { - ret = regulator_set_voltage_tol(cpu_reg, volt, tol); - if (ret) { - dev_err(cpu_dev, "failed to scale voltage up: %d\n", - ret); - return ret; + /* Try "cpu0" for older DTs */ + if (!cpu) { + pp = of_find_property(np, "cpu0-supply", NULL); + if (pp) { + name = "cpu0"; + goto node_put; } } - ret = clk_set_rate(cpu_clk, freq_exact); - if (ret) { - dev_err(cpu_dev, "failed to set clock rate: %d\n", ret); - if (!IS_ERR(cpu_reg) && volt_old > 0) - regulator_set_voltage_tol(cpu_reg, volt_old, tol); - return ret; + pp = of_find_property(np, "cpu-supply", NULL); + if (pp) { + name = "cpu"; + goto node_put; } - /* scaling down? scale voltage after frequency */ - if (!IS_ERR(cpu_reg) && new_freq < old_freq) { - ret = regulator_set_voltage_tol(cpu_reg, volt, tol); - if (ret) { - dev_err(cpu_dev, "failed to scale voltage down: %d\n", - ret); - clk_set_rate(cpu_clk, old_freq * 1000); - } - } - - return ret; + dev_dbg(dev, "no regulator for cpu%d\n", cpu); +node_put: + of_node_put(np); + return name; } -static int allocate_resources(int cpu, struct device **cdev, - struct regulator **creg, struct clk **cclk) +static int resources_available(void) { struct device *cpu_dev; struct regulator *cpu_reg; struct clk *cpu_clk; int ret = 0; - char *reg_cpu0 = "cpu0", *reg_cpu = "cpu", *reg; + const char *name; - cpu_dev = get_cpu_device(cpu); + cpu_dev = get_cpu_device(0); if (!cpu_dev) { - pr_err("failed to get cpu%d device\n", cpu); + pr_err("failed to get cpu0 device\n"); return -ENODEV; } - /* Try "cpu0" for older DTs */ - if (!cpu) - reg = reg_cpu0; - else - reg = reg_cpu; - -try_again: - cpu_reg = regulator_get_optional(cpu_dev, reg); - ret = PTR_ERR_OR_ZERO(cpu_reg); + cpu_clk = clk_get(cpu_dev, NULL); + ret = PTR_ERR_OR_ZERO(cpu_clk); if (ret) { /* - * If cpu's regulator supply node is present, but regulator is - * not yet registered, we should try defering probe. + * If cpu's clk node is present, but clock is not yet + * registered, we should try defering probe. */ - if (ret == -EPROBE_DEFER) { - dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n", - cpu); - return ret; - } - - /* Try with "cpu-supply" */ - if (reg == reg_cpu0) { - reg = reg_cpu; - goto try_again; - } + if (ret == -EPROBE_DEFER) + dev_dbg(cpu_dev, "clock not ready, retry\n"); + else + dev_err(cpu_dev, "failed to get clock: %d\n", ret); - dev_dbg(cpu_dev, "no regulator for cpu%d: %d\n", cpu, ret); + return ret; } - cpu_clk = clk_get(cpu_dev, NULL); - ret = PTR_ERR_OR_ZERO(cpu_clk); - if (ret) { - /* put regulator */ - if (!IS_ERR(cpu_reg)) - regulator_put(cpu_reg); + clk_put(cpu_clk); + name = find_supply_name(cpu_dev); + /* Platform doesn't require regulator */ + if (!name) + return 0; + + cpu_reg = regulator_get_optional(cpu_dev, name); + ret = PTR_ERR_OR_ZERO(cpu_reg); + if (ret) { /* - * If cpu's clk node is present, but clock is not yet - * registered, we should try defering probe. + * If cpu's regulator supply node is present, but regulator is + * not yet registered, we should try defering probe. */ if (ret == -EPROBE_DEFER) - dev_dbg(cpu_dev, "cpu%d clock not ready, retry\n", cpu); + dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n"); else - dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", cpu, - ret); - } else { - *cdev = cpu_dev; - *creg = cpu_reg; - *cclk = cpu_clk; + dev_dbg(cpu_dev, "no regulator for cpu0: %d\n", ret); + + return ret; } - return ret; + regulator_put(cpu_reg); + return 0; } static int cpufreq_init(struct cpufreq_policy *policy) { struct cpufreq_frequency_table *freq_table; - struct device_node *np; struct private_data *priv; struct device *cpu_dev; - struct regulator *cpu_reg; struct clk *cpu_clk; struct dev_pm_opp *suspend_opp; - unsigned long min_uV = ~0, max_uV = 0; unsigned int transition_latency; - bool need_update = false; + bool opp_v1 = false; + const char *name; int ret; - ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk); - if (ret) { - pr_err("%s: Failed to allocate resources: %d\n", __func__, ret); - return ret; + cpu_dev = get_cpu_device(policy->cpu); + if (!cpu_dev) { + pr_err("failed to get cpu%d device\n", policy->cpu); + return -ENODEV; } - np = of_node_get(cpu_dev->of_node); - if (!np) { - dev_err(cpu_dev, "failed to find cpu%d node\n", policy->cpu); - ret = -ENOENT; - goto out_put_reg_clk; + cpu_clk = clk_get(cpu_dev, NULL); + if (IS_ERR(cpu_clk)) { + ret = PTR_ERR(cpu_clk); + dev_err(cpu_dev, "%s: failed to get clk: %d\n", __func__, ret); + return ret; } /* Get OPP-sharing information from "operating-points-v2" bindings */ @@ -223,9 +175,23 @@ static int cpufreq_init(struct cpufreq_policy *policy) * finding shared-OPPs for backward compatibility. */ if (ret == -ENOENT) - need_update = true; + opp_v1 = true; else - goto out_node_put; + goto out_put_clk; + } + + /* + * OPP layer will be taking care of regulators now, but it needs to know + * the name of the regulator first. + */ + name = find_supply_name(cpu_dev); + if (name) { + ret = dev_pm_opp_set_regulator(cpu_dev, name); + if (ret) { + dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n", + policy->cpu, ret); + goto out_put_clk; + } } /* @@ -246,12 +212,12 @@ static int cpufreq_init(struct cpufreq_policy *policy) */ ret = dev_pm_opp_get_opp_count(cpu_dev); if (ret <= 0) { - pr_debug("OPP table is not ready, deferring probe\n"); + dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n"); ret = -EPROBE_DEFER; goto out_free_opp; } - if (need_update) { + if (opp_v1) { struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data(); if (!pd || !pd->independent_clocks) @@ -265,10 +231,6 @@ static int cpufreq_init(struct cpufreq_policy *policy) if (ret) dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n", __func__, ret); - - of_property_read_u32(np, "clock-latency", &transition_latency); - } else { - transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev); } priv = kzalloc(sizeof(*priv), GFP_KERNEL); @@ -277,62 +239,16 @@ static int cpufreq_init(struct cpufreq_policy *policy) goto out_free_opp; } - of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance); - - if (!transition_latency) - transition_latency = CPUFREQ_ETERNAL; - - if (!IS_ERR(cpu_reg)) { - unsigned long opp_freq = 0; - - /* - * Disable any OPPs where the connected regulator isn't able to - * provide the specified voltage and record minimum and maximum - * voltage levels. - */ - while (1) { - struct dev_pm_opp *opp; - unsigned long opp_uV, tol_uV; - - rcu_read_lock(); - opp = dev_pm_opp_find_freq_ceil(cpu_dev, &opp_freq); - if (IS_ERR(opp)) { - rcu_read_unlock(); - break; - } - opp_uV = dev_pm_opp_get_voltage(opp); - rcu_read_unlock(); - - tol_uV = opp_uV * priv->voltage_tolerance / 100; - if (regulator_is_supported_voltage(cpu_reg, - opp_uV - tol_uV, - opp_uV + tol_uV)) { - if (opp_uV < min_uV) - min_uV = opp_uV; - if (opp_uV > max_uV) - max_uV = opp_uV; - } else { - dev_pm_opp_disable(cpu_dev, opp_freq); - } - - opp_freq++; - } - - ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV); - if (ret > 0) - transition_latency += ret * 1000; - } + priv->reg_name = name; ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { - pr_err("failed to init cpufreq table: %d\n", ret); + dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret); goto out_free_priv; } priv->cpu_dev = cpu_dev; - priv->cpu_reg = cpu_reg; policy->driver_data = priv; - policy->clk = cpu_clk; rcu_read_lock(); @@ -357,9 +273,11 @@ static int cpufreq_init(struct cpufreq_policy *policy) cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs; } - policy->cpuinfo.transition_latency = transition_latency; + transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev); + if (!transition_latency) + transition_latency = CPUFREQ_ETERNAL; - of_node_put(np); + policy->cpuinfo.transition_latency = transition_latency; return 0; @@ -369,12 +287,10 @@ out_free_priv: kfree(priv); out_free_opp: dev_pm_opp_of_cpumask_remove_table(policy->cpus); -out_node_put: - of_node_put(np); -out_put_reg_clk: + if (name) + dev_pm_opp_put_regulator(cpu_dev); +out_put_clk: clk_put(cpu_clk); - if (!IS_ERR(cpu_reg)) - regulator_put(cpu_reg); return ret; } @@ -386,9 +302,10 @@ static int cpufreq_exit(struct cpufreq_policy *policy) cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); + if (priv->reg_name) + dev_pm_opp_put_regulator(priv->cpu_dev); + clk_put(policy->clk); - if (!IS_ERR(priv->cpu_reg)) - regulator_put(priv->cpu_reg); kfree(priv); return 0; @@ -441,9 +358,6 @@ static struct cpufreq_driver dt_cpufreq_driver = { static int dt_cpufreq_probe(struct platform_device *pdev) { - struct device *cpu_dev; - struct regulator *cpu_reg; - struct clk *cpu_clk; int ret; /* @@ -453,19 +367,15 @@ static int dt_cpufreq_probe(struct platform_device *pdev) * * FIXME: Is checking this only for CPU0 sufficient ? */ - ret = allocate_resources(0, &cpu_dev, &cpu_reg, &cpu_clk); + ret = resources_available(); if (ret) return ret; - clk_put(cpu_clk); - if (!IS_ERR(cpu_reg)) - regulator_put(cpu_reg); - dt_cpufreq_driver.driver_data = dev_get_platdata(&pdev->dev); ret = cpufreq_register_driver(&dt_cpufreq_driver); if (ret) - dev_err(cpu_dev, "failed register driver: %d\n", ret); + dev_err(&pdev->dev, "failed register driver: %d\n", ret); return ret; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e979ec78b695..4c7825856eab 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -38,48 +38,10 @@ static inline bool policy_is_inactive(struct cpufreq_policy *policy) return cpumask_empty(policy->cpus); } -static bool suitable_policy(struct cpufreq_policy *policy, bool active) -{ - return active == !policy_is_inactive(policy); -} - -/* Finds Next Acive/Inactive policy */ -static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy, - bool active) -{ - do { - /* No more policies in the list */ - if (list_is_last(&policy->policy_list, &cpufreq_policy_list)) - return NULL; - - policy = list_next_entry(policy, policy_list); - } while (!suitable_policy(policy, active)); - - return policy; -} - -static struct cpufreq_policy *first_policy(bool active) -{ - struct cpufreq_policy *policy; - - /* No policies in the list */ - if (list_empty(&cpufreq_policy_list)) - return NULL; - - policy = list_first_entry(&cpufreq_policy_list, typeof(*policy), - policy_list); - - if (!suitable_policy(policy, active)) - policy = next_policy(policy, active); - - return policy; -} - /* Macros to iterate over CPU policies */ -#define for_each_suitable_policy(__policy, __active) \ - for (__policy = first_policy(__active); \ - __policy; \ - __policy = next_policy(__policy, __active)) +#define for_each_suitable_policy(__policy, __active) \ + list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \ + if ((__active) == !policy_is_inactive(__policy)) #define for_each_active_policy(__policy) \ for_each_suitable_policy(__policy, true) @@ -102,7 +64,6 @@ static LIST_HEAD(cpufreq_governor_list); static struct cpufreq_driver *cpufreq_driver; static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); static DEFINE_RWLOCK(cpufreq_driver_lock); -DEFINE_MUTEX(cpufreq_governor_lock); /* Flag to suspend/resume CPUFreq governors */ static bool cpufreq_suspended; @@ -113,10 +74,8 @@ static inline bool has_target(void) } /* internal prototypes */ -static int __cpufreq_governor(struct cpufreq_policy *policy, - unsigned int event); +static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event); static unsigned int __cpufreq_get(struct cpufreq_policy *policy); -static void handle_update(struct work_struct *work); /** * Two notifier lists: the "policy" list is involved in the @@ -818,12 +777,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) ssize_t ret; down_read(&policy->rwsem); - - if (fattr->show) - ret = fattr->show(policy, buf); - else - ret = -EIO; - + ret = fattr->show(policy, buf); up_read(&policy->rwsem); return ret; @@ -838,18 +792,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, get_online_cpus(); - if (!cpu_online(policy->cpu)) - goto unlock; - - down_write(&policy->rwsem); - - if (fattr->store) + if (cpu_online(policy->cpu)) { + down_write(&policy->rwsem); ret = fattr->store(policy, buf, count); - else - ret = -EIO; + up_write(&policy->rwsem); + } - up_write(&policy->rwsem); -unlock: put_online_cpus(); return ret; @@ -959,6 +907,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) return cpufreq_add_dev_symlink(policy); } +__weak struct cpufreq_governor *cpufreq_default_governor(void) +{ + return NULL; +} + static int cpufreq_init_policy(struct cpufreq_policy *policy) { struct cpufreq_governor *gov = NULL; @@ -968,11 +921,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy) /* Update governor of new_policy to the governor used before hotplug */ gov = find_governor(policy->last_governor); - if (gov) + if (gov) { pr_debug("Restoring governor %s for cpu %d\n", policy->governor->name, policy->cpu); - else - gov = CPUFREQ_DEFAULT_GOVERNOR; + } else { + gov = cpufreq_default_governor(); + if (!gov) + return -ENODATA; + } new_policy.governor = gov; @@ -996,36 +952,45 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp if (cpumask_test_cpu(cpu, policy->cpus)) return 0; + down_write(&policy->rwsem); if (has_target()) { - ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); if (ret) { pr_err("%s: Failed to stop governor\n", __func__); - return ret; + goto unlock; } } - down_write(&policy->rwsem); cpumask_set_cpu(cpu, policy->cpus); - up_write(&policy->rwsem); if (has_target()) { - ret = __cpufreq_governor(policy, CPUFREQ_GOV_START); + ret = cpufreq_governor(policy, CPUFREQ_GOV_START); if (!ret) - ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); - if (ret) { + if (ret) pr_err("%s: Failed to start governor\n", __func__); - return ret; - } } - return 0; +unlock: + up_write(&policy->rwsem); + return ret; +} + +static void handle_update(struct work_struct *work) +{ + struct cpufreq_policy *policy = + container_of(work, struct cpufreq_policy, update); + unsigned int cpu = policy->cpu; + pr_debug("handle_update for cpu %u called\n", cpu); + cpufreq_update_policy(cpu); } static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); struct cpufreq_policy *policy; + int ret; if (WARN_ON(!dev)) return NULL; @@ -1043,7 +1008,13 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) goto err_free_rcpumask; - kobject_init(&policy->kobj, &ktype_cpufreq); + ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, + cpufreq_global_kobject, "policy%u", cpu); + if (ret) { + pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret); + goto err_free_real_cpus; + } + INIT_LIST_HEAD(&policy->policy_list); init_rwsem(&policy->rwsem); spin_lock_init(&policy->transition_lock); @@ -1054,6 +1025,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) policy->cpu = cpu; return policy; +err_free_real_cpus: + free_cpumask_var(policy->real_cpus); err_free_rcpumask: free_cpumask_var(policy->related_cpus); err_free_cpumask: @@ -1158,16 +1131,6 @@ static int cpufreq_online(unsigned int cpu) cpumask_copy(policy->related_cpus, policy->cpus); /* Remember CPUs present at the policy creation time. */ cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask); - - /* Name and add the kobject */ - ret = kobject_add(&policy->kobj, cpufreq_global_kobject, - "policy%u", - cpumask_first(policy->related_cpus)); - if (ret) { - pr_err("%s: failed to add policy->kobj: %d\n", __func__, - ret); - goto out_exit_policy; - } } /* @@ -1309,9 +1272,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) return ret; } -static void cpufreq_offline_prepare(unsigned int cpu) +static void cpufreq_offline(unsigned int cpu) { struct cpufreq_policy *policy; + int ret; pr_debug("%s: unregistering CPU %u\n", __func__, cpu); @@ -1321,13 +1285,13 @@ static void cpufreq_offline_prepare(unsigned int cpu) return; } + down_write(&policy->rwsem); if (has_target()) { - int ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); if (ret) pr_err("%s: Failed to stop governor\n", __func__); } - down_write(&policy->rwsem); cpumask_clear_cpu(cpu, policy->cpus); if (policy_is_inactive(policy)) { @@ -1340,39 +1304,27 @@ static void cpufreq_offline_prepare(unsigned int cpu) /* Nominate new CPU */ policy->cpu = cpumask_any(policy->cpus); } - up_write(&policy->rwsem); /* Start governor again for active policy */ if (!policy_is_inactive(policy)) { if (has_target()) { - int ret = __cpufreq_governor(policy, CPUFREQ_GOV_START); + ret = cpufreq_governor(policy, CPUFREQ_GOV_START); if (!ret) - ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); if (ret) pr_err("%s: Failed to start governor\n", __func__); } - } else if (cpufreq_driver->stop_cpu) { - cpufreq_driver->stop_cpu(policy); - } -} -static void cpufreq_offline_finish(unsigned int cpu) -{ - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); - - if (!policy) { - pr_debug("%s: No cpu_data found\n", __func__); - return; + goto unlock; } - /* Only proceed for inactive policies */ - if (!policy_is_inactive(policy)) - return; + if (cpufreq_driver->stop_cpu) + cpufreq_driver->stop_cpu(policy); /* If cpu is last user of policy, free policy */ if (has_target()) { - int ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); + ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); if (ret) pr_err("%s: Failed to exit governor\n", __func__); } @@ -1386,6 +1338,9 @@ static void cpufreq_offline_finish(unsigned int cpu) cpufreq_driver->exit(policy); policy->freq_table = NULL; } + +unlock: + up_write(&policy->rwsem); } /** @@ -1401,10 +1356,8 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) if (!policy) return; - if (cpu_online(cpu)) { - cpufreq_offline_prepare(cpu); - cpufreq_offline_finish(cpu); - } + if (cpu_online(cpu)) + cpufreq_offline(cpu); cpumask_clear_cpu(cpu, policy->real_cpus); remove_cpu_dev_symlink(policy, cpu); @@ -1413,15 +1366,6 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) cpufreq_policy_free(policy, true); } -static void handle_update(struct work_struct *work) -{ - struct cpufreq_policy *policy = - container_of(work, struct cpufreq_policy, update); - unsigned int cpu = policy->cpu; - pr_debug("handle_update for cpu %u called\n", cpu); - cpufreq_update_policy(cpu); -} - /** * cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're * in deep trouble. @@ -1584,6 +1528,7 @@ EXPORT_SYMBOL(cpufreq_generic_suspend); void cpufreq_suspend(void) { struct cpufreq_policy *policy; + int ret; if (!cpufreq_driver) return; @@ -1594,7 +1539,11 @@ void cpufreq_suspend(void) pr_debug("%s: Suspending Governors\n", __func__); for_each_active_policy(policy) { - if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP)) + down_write(&policy->rwsem); + ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); + up_write(&policy->rwsem); + + if (ret) pr_err("%s: Failed to stop governor for policy: %p\n", __func__, policy); else if (cpufreq_driver->suspend @@ -1616,6 +1565,7 @@ suspend: void cpufreq_resume(void) { struct cpufreq_policy *policy; + int ret; if (!cpufreq_driver) return; @@ -1628,13 +1578,20 @@ void cpufreq_resume(void) pr_debug("%s: Resuming Governors\n", __func__); for_each_active_policy(policy) { - if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) + if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) { pr_err("%s: Failed to resume driver: %p\n", __func__, policy); - else if (__cpufreq_governor(policy, CPUFREQ_GOV_START) - || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS)) - pr_err("%s: Failed to start governor for policy: %p\n", - __func__, policy); + } else { + down_write(&policy->rwsem); + ret = cpufreq_governor(policy, CPUFREQ_GOV_START); + if (!ret) + cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + up_write(&policy->rwsem); + + if (ret) + pr_err("%s: Failed to start governor for policy: %p\n", + __func__, policy); + } } /* @@ -1846,7 +1803,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation) { unsigned int old_target_freq = target_freq; - int retval = -EINVAL; + struct cpufreq_frequency_table *freq_table; + int index, retval; if (cpufreq_disabled()) return -ENODEV; @@ -1873,34 +1831,28 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, policy->restore_freq = policy->cur; if (cpufreq_driver->target) - retval = cpufreq_driver->target(policy, target_freq, relation); - else if (cpufreq_driver->target_index) { - struct cpufreq_frequency_table *freq_table; - int index; - - freq_table = cpufreq_frequency_get_table(policy->cpu); - if (unlikely(!freq_table)) { - pr_err("%s: Unable to find freq_table\n", __func__); - goto out; - } + return cpufreq_driver->target(policy, target_freq, relation); - retval = cpufreq_frequency_table_target(policy, freq_table, - target_freq, relation, &index); - if (unlikely(retval)) { - pr_err("%s: Unable to find matching freq\n", __func__); - goto out; - } + if (!cpufreq_driver->target_index) + return -EINVAL; - if (freq_table[index].frequency == policy->cur) { - retval = 0; - goto out; - } + freq_table = cpufreq_frequency_get_table(policy->cpu); + if (unlikely(!freq_table)) { + pr_err("%s: Unable to find freq_table\n", __func__); + return -EINVAL; + } - retval = __target_index(policy, freq_table, index); + retval = cpufreq_frequency_table_target(policy, freq_table, target_freq, + relation, &index); + if (unlikely(retval)) { + pr_err("%s: Unable to find matching freq\n", __func__); + return retval; } -out: - return retval; + if (freq_table[index].frequency == policy->cur) + return 0; + + return __target_index(policy, freq_table, index); } EXPORT_SYMBOL_GPL(__cpufreq_driver_target); @@ -1920,20 +1872,14 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, } EXPORT_SYMBOL_GPL(cpufreq_driver_target); -static int __cpufreq_governor(struct cpufreq_policy *policy, - unsigned int event) +__weak struct cpufreq_governor *cpufreq_fallback_governor(void) { - int ret; + return NULL; +} - /* Only must be defined when default governor is known to have latency - restrictions, like e.g. conservative or ondemand. - That this is the case is already ensured in Kconfig - */ -#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE - struct cpufreq_governor *gov = &cpufreq_gov_performance; -#else - struct cpufreq_governor *gov = NULL; -#endif +static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event) +{ + int ret; /* Don't start any governor operations if we are entering suspend */ if (cpufreq_suspended) @@ -1948,12 +1894,14 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, if (policy->governor->max_transition_latency && policy->cpuinfo.transition_latency > policy->governor->max_transition_latency) { - if (!gov) - return -EINVAL; - else { + struct cpufreq_governor *gov = cpufreq_fallback_governor(); + + if (gov) { pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n", policy->governor->name, gov->name); policy->governor = gov; + } else { + return -EINVAL; } } @@ -1963,21 +1911,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event); - mutex_lock(&cpufreq_governor_lock); - if ((policy->governor_enabled && event == CPUFREQ_GOV_START) - || (!policy->governor_enabled - && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) { - mutex_unlock(&cpufreq_governor_lock); - return -EBUSY; - } - - if (event == CPUFREQ_GOV_STOP) - policy->governor_enabled = false; - else if (event == CPUFREQ_GOV_START) - policy->governor_enabled = true; - - mutex_unlock(&cpufreq_governor_lock); - ret = policy->governor->governor(policy, event); if (!ret) { @@ -1985,14 +1918,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, policy->governor->initialized++; else if (event == CPUFREQ_GOV_POLICY_EXIT) policy->governor->initialized--; - } else { - /* Restore original values */ - mutex_lock(&cpufreq_governor_lock); - if (event == CPUFREQ_GOV_STOP) - policy->governor_enabled = true; - else if (event == CPUFREQ_GOV_START) - policy->governor_enabled = false; - mutex_unlock(&cpufreq_governor_lock); } if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) || @@ -2147,7 +2072,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, old_gov = policy->governor; /* end old governor */ if (old_gov) { - ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); if (ret) { /* This can happen due to race with other operations */ pr_debug("%s: Failed to Stop Governor: %s (%d)\n", @@ -2155,10 +2080,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, return ret; } - up_write(&policy->rwsem); - ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - down_write(&policy->rwsem); - + ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); if (ret) { pr_err("%s: Failed to Exit Governor: %s (%d)\n", __func__, old_gov->name, ret); @@ -2168,32 +2090,30 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, /* start new governor */ policy->governor = new_policy->governor; - ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT); + ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT); if (!ret) { - ret = __cpufreq_governor(policy, CPUFREQ_GOV_START); + ret = cpufreq_governor(policy, CPUFREQ_GOV_START); if (!ret) goto out; - up_write(&policy->rwsem); - __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - down_write(&policy->rwsem); + cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); } /* new governor failed, so re-start old one */ pr_debug("starting governor %s failed\n", policy->governor->name); if (old_gov) { policy->governor = old_gov; - if (__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) + if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) policy->governor = NULL; else - __cpufreq_governor(policy, CPUFREQ_GOV_START); + cpufreq_governor(policy, CPUFREQ_GOV_START); } return ret; out: pr_debug("governor: change or update limits\n"); - return __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); } /** @@ -2260,11 +2180,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb, break; case CPU_DOWN_PREPARE: - cpufreq_offline_prepare(cpu); - break; - - case CPU_POST_DEAD: - cpufreq_offline_finish(cpu); + cpufreq_offline(cpu); break; case CPU_DOWN_FAILED: @@ -2297,8 +2213,11 @@ static int cpufreq_boost_set_sw(int state) __func__); break; } + + down_write(&policy->rwsem); policy->user_policy.max = policy->max; - __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + up_write(&policy->rwsem); } } @@ -2384,7 +2303,7 @@ EXPORT_SYMBOL_GPL(cpufreq_boost_enabled); * submitted by the CPU Frequency driver. * * Registers a CPU Frequency driver to this core code. This code - * returns zero on success, -EBUSY when another driver got here first + * returns zero on success, -EEXIST when another driver got here first * (and isn't unregistered in the meantime). * */ diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 606ad74abe6e..bf4913f6453b 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -14,6 +14,22 @@ #include <linux/slab.h> #include "cpufreq_governor.h" +struct cs_policy_dbs_info { + struct policy_dbs_info policy_dbs; + unsigned int down_skip; + unsigned int requested_freq; +}; + +static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs) +{ + return container_of(policy_dbs, struct cs_policy_dbs_info, policy_dbs); +} + +struct cs_dbs_tuners { + unsigned int down_threshold; + unsigned int freq_step; +}; + /* Conservative governor macros */ #define DEF_FREQUENCY_UP_THRESHOLD (80) #define DEF_FREQUENCY_DOWN_THRESHOLD (20) @@ -21,21 +37,6 @@ #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (10) -static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info); - -static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy, - unsigned int event); - -#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE -static -#endif -struct cpufreq_governor cpufreq_gov_conservative = { - .name = "conservative", - .governor = cs_cpufreq_governor_dbs, - .max_transition_latency = TRANSITION_LATENCY_LIMIT, - .owner = THIS_MODULE, -}; - static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners, struct cpufreq_policy *policy) { @@ -57,27 +58,28 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners, * Any frequency increase takes it to the maximum frequency. Frequency reduction * happens at minimum steps of 5% (default) of maximum frequency */ -static void cs_check_cpu(int cpu, unsigned int load) +static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) { - struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu); - struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy; - struct dbs_data *dbs_data = policy->governor_data; + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs); + struct dbs_data *dbs_data = policy_dbs->dbs_data; struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; + unsigned int load = dbs_update(policy); /* * break out if we 'cannot' reduce the speed as the user might * want freq_step to be zero */ if (cs_tuners->freq_step == 0) - return; + goto out; /* Check for frequency increase */ - if (load > cs_tuners->up_threshold) { + if (load > dbs_data->up_threshold) { dbs_info->down_skip = 0; /* if we are already at full speed then break out early */ if (dbs_info->requested_freq == policy->max) - return; + goto out; dbs_info->requested_freq += get_freq_target(cs_tuners, policy); @@ -86,12 +88,12 @@ static void cs_check_cpu(int cpu, unsigned int load) __cpufreq_driver_target(policy, dbs_info->requested_freq, CPUFREQ_RELATION_H); - return; + goto out; } /* if sampling_down_factor is active break out early */ - if (++dbs_info->down_skip < cs_tuners->sampling_down_factor) - return; + if (++dbs_info->down_skip < dbs_data->sampling_down_factor) + goto out; dbs_info->down_skip = 0; /* Check for frequency decrease */ @@ -101,7 +103,7 @@ static void cs_check_cpu(int cpu, unsigned int load) * if we cannot reduce the frequency anymore, break out early */ if (policy->cur == policy->min) - return; + goto out; freq_target = get_freq_target(cs_tuners, policy); if (dbs_info->requested_freq > freq_target) @@ -111,58 +113,25 @@ static void cs_check_cpu(int cpu, unsigned int load) __cpufreq_driver_target(policy, dbs_info->requested_freq, CPUFREQ_RELATION_L); - return; } -} - -static unsigned int cs_dbs_timer(struct cpufreq_policy *policy, bool modify_all) -{ - struct dbs_data *dbs_data = policy->governor_data; - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - - if (modify_all) - dbs_check_cpu(dbs_data, policy->cpu); - return delay_for_sampling_rate(cs_tuners->sampling_rate); + out: + return dbs_data->sampling_rate; } static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val, - void *data) -{ - struct cpufreq_freqs *freq = data; - struct cs_cpu_dbs_info_s *dbs_info = - &per_cpu(cs_cpu_dbs_info, freq->cpu); - struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu); - - if (!policy) - return 0; - - /* policy isn't governed by conservative governor */ - if (policy->governor != &cpufreq_gov_conservative) - return 0; - - /* - * we only care if our internally tracked freq moves outside the 'valid' - * ranges of frequency available to us otherwise we do not change it - */ - if (dbs_info->requested_freq > policy->max - || dbs_info->requested_freq < policy->min) - dbs_info->requested_freq = freq->new; - - return 0; -} + void *data); static struct notifier_block cs_cpufreq_notifier_block = { .notifier_call = dbs_cpufreq_notifier, }; /************************** sysfs interface ************************/ -static struct common_dbs_data cs_dbs_cdata; +static struct dbs_governor cs_dbs_gov; static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data, const char *buf, size_t count) { - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; unsigned int input; int ret; ret = sscanf(buf, "%u", &input); @@ -170,22 +139,7 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data, if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1) return -EINVAL; - cs_tuners->sampling_down_factor = input; - return count; -} - -static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf, - size_t count) -{ - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - unsigned int input; - int ret; - ret = sscanf(buf, "%u", &input); - - if (ret != 1) - return -EINVAL; - - cs_tuners->sampling_rate = max(input, dbs_data->min_sampling_rate); + dbs_data->sampling_down_factor = input; return count; } @@ -200,7 +154,7 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf, if (ret != 1 || input > 100 || input <= cs_tuners->down_threshold) return -EINVAL; - cs_tuners->up_threshold = input; + dbs_data->up_threshold = input; return count; } @@ -214,7 +168,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf, /* cannot be lower than 11 otherwise freq will not fall */ if (ret != 1 || input < 11 || input > 100 || - input >= cs_tuners->up_threshold) + input >= dbs_data->up_threshold) return -EINVAL; cs_tuners->down_threshold = input; @@ -224,8 +178,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf, static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data, const char *buf, size_t count) { - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - unsigned int input, j; + unsigned int input; int ret; ret = sscanf(buf, "%u", &input); @@ -235,21 +188,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data, if (input > 1) input = 1; - if (input == cs_tuners->ignore_nice_load) /* nothing to do */ + if (input == dbs_data->ignore_nice_load) /* nothing to do */ return count; - cs_tuners->ignore_nice_load = input; + dbs_data->ignore_nice_load = input; /* we need to re-evaluate prev_cpu_idle */ - for_each_online_cpu(j) { - struct cs_cpu_dbs_info_s *dbs_info; - dbs_info = &per_cpu(cs_cpu_dbs_info, j); - dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j, - &dbs_info->cdbs.prev_cpu_wall, 0); - if (cs_tuners->ignore_nice_load) - dbs_info->cdbs.prev_cpu_nice = - kcpustat_cpu(j).cpustat[CPUTIME_NICE]; - } + gov_update_cpu_data(dbs_data); + return count; } @@ -275,55 +221,47 @@ static ssize_t store_freq_step(struct dbs_data *dbs_data, const char *buf, return count; } -show_store_one(cs, sampling_rate); -show_store_one(cs, sampling_down_factor); -show_store_one(cs, up_threshold); -show_store_one(cs, down_threshold); -show_store_one(cs, ignore_nice_load); -show_store_one(cs, freq_step); -declare_show_sampling_rate_min(cs); - -gov_sys_pol_attr_rw(sampling_rate); -gov_sys_pol_attr_rw(sampling_down_factor); -gov_sys_pol_attr_rw(up_threshold); -gov_sys_pol_attr_rw(down_threshold); -gov_sys_pol_attr_rw(ignore_nice_load); -gov_sys_pol_attr_rw(freq_step); -gov_sys_pol_attr_ro(sampling_rate_min); - -static struct attribute *dbs_attributes_gov_sys[] = { - &sampling_rate_min_gov_sys.attr, - &sampling_rate_gov_sys.attr, - &sampling_down_factor_gov_sys.attr, - &up_threshold_gov_sys.attr, - &down_threshold_gov_sys.attr, - &ignore_nice_load_gov_sys.attr, - &freq_step_gov_sys.attr, +gov_show_one_common(sampling_rate); +gov_show_one_common(sampling_down_factor); +gov_show_one_common(up_threshold); +gov_show_one_common(ignore_nice_load); +gov_show_one_common(min_sampling_rate); +gov_show_one(cs, down_threshold); +gov_show_one(cs, freq_step); + +gov_attr_rw(sampling_rate); +gov_attr_rw(sampling_down_factor); +gov_attr_rw(up_threshold); +gov_attr_rw(ignore_nice_load); +gov_attr_ro(min_sampling_rate); +gov_attr_rw(down_threshold); +gov_attr_rw(freq_step); + +static struct attribute *cs_attributes[] = { + &min_sampling_rate.attr, + &sampling_rate.attr, + &sampling_down_factor.attr, + &up_threshold.attr, + &down_threshold.attr, + &ignore_nice_load.attr, + &freq_step.attr, NULL }; -static struct attribute_group cs_attr_group_gov_sys = { - .attrs = dbs_attributes_gov_sys, - .name = "conservative", -}; +/************************** sysfs end ************************/ -static struct attribute *dbs_attributes_gov_pol[] = { - &sampling_rate_min_gov_pol.attr, - &sampling_rate_gov_pol.attr, - &sampling_down_factor_gov_pol.attr, - &up_threshold_gov_pol.attr, - &down_threshold_gov_pol.attr, - &ignore_nice_load_gov_pol.attr, - &freq_step_gov_pol.attr, - NULL -}; +static struct policy_dbs_info *cs_alloc(void) +{ + struct cs_policy_dbs_info *dbs_info; -static struct attribute_group cs_attr_group_gov_pol = { - .attrs = dbs_attributes_gov_pol, - .name = "conservative", -}; + dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL); + return dbs_info ? &dbs_info->policy_dbs : NULL; +} -/************************** sysfs end ************************/ +static void cs_free(struct policy_dbs_info *policy_dbs) +{ + kfree(to_dbs_info(policy_dbs)); +} static int cs_init(struct dbs_data *dbs_data, bool notify) { @@ -335,11 +273,11 @@ static int cs_init(struct dbs_data *dbs_data, bool notify) return -ENOMEM; } - tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD; tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD; - tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR; - tuners->ignore_nice_load = 0; tuners->freq_step = DEF_FREQUENCY_STEP; + dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD; + dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR; + dbs_data->ignore_nice_load = 0; dbs_data->tuners = tuners; dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO * @@ -361,35 +299,66 @@ static void cs_exit(struct dbs_data *dbs_data, bool notify) kfree(dbs_data->tuners); } -define_get_cpu_dbs_routines(cs_cpu_dbs_info); +static void cs_start(struct cpufreq_policy *policy) +{ + struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data); + + dbs_info->down_skip = 0; + dbs_info->requested_freq = policy->cur; +} -static struct common_dbs_data cs_dbs_cdata = { - .governor = GOV_CONSERVATIVE, - .attr_group_gov_sys = &cs_attr_group_gov_sys, - .attr_group_gov_pol = &cs_attr_group_gov_pol, - .get_cpu_cdbs = get_cpu_cdbs, - .get_cpu_dbs_info_s = get_cpu_dbs_info_s, +static struct dbs_governor cs_dbs_gov = { + .gov = { + .name = "conservative", + .governor = cpufreq_governor_dbs, + .max_transition_latency = TRANSITION_LATENCY_LIMIT, + .owner = THIS_MODULE, + }, + .kobj_type = { .default_attrs = cs_attributes }, .gov_dbs_timer = cs_dbs_timer, - .gov_check_cpu = cs_check_cpu, + .alloc = cs_alloc, + .free = cs_free, .init = cs_init, .exit = cs_exit, - .mutex = __MUTEX_INITIALIZER(cs_dbs_cdata.mutex), + .start = cs_start, }; -static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy, - unsigned int event) +#define CPU_FREQ_GOV_CONSERVATIVE (&cs_dbs_gov.gov) + +static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val, + void *data) { - return cpufreq_governor_dbs(policy, &cs_dbs_cdata, event); + struct cpufreq_freqs *freq = data; + struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu); + struct cs_policy_dbs_info *dbs_info; + + if (!policy) + return 0; + + /* policy isn't governed by conservative governor */ + if (policy->governor != CPU_FREQ_GOV_CONSERVATIVE) + return 0; + + dbs_info = to_dbs_info(policy->governor_data); + /* + * we only care if our internally tracked freq moves outside the 'valid' + * ranges of frequency available to us otherwise we do not change it + */ + if (dbs_info->requested_freq > policy->max + || dbs_info->requested_freq < policy->min) + dbs_info->requested_freq = freq->new; + + return 0; } static int __init cpufreq_gov_dbs_init(void) { - return cpufreq_register_governor(&cpufreq_gov_conservative); + return cpufreq_register_governor(CPU_FREQ_GOV_CONSERVATIVE); } static void __exit cpufreq_gov_dbs_exit(void) { - cpufreq_unregister_governor(&cpufreq_gov_conservative); + cpufreq_unregister_governor(CPU_FREQ_GOV_CONSERVATIVE); } MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>"); @@ -399,6 +368,11 @@ MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for " MODULE_LICENSE("GPL"); #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE +struct cpufreq_governor *cpufreq_default_governor(void) +{ + return CPU_FREQ_GOV_CONSERVATIVE; +} + fs_initcall(cpufreq_gov_dbs_init); #else module_init(cpufreq_gov_dbs_init); diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index e0d111024d48..1c25ef405616 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -18,95 +18,193 @@ #include <linux/export.h> #include <linux/kernel_stat.h> +#include <linux/sched.h> #include <linux/slab.h> #include "cpufreq_governor.h" -static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data) -{ - if (have_governor_per_policy()) - return dbs_data->cdata->attr_group_gov_pol; - else - return dbs_data->cdata->attr_group_gov_sys; -} +static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs); + +static DEFINE_MUTEX(gov_dbs_data_mutex); -void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) +/* Common sysfs tunables */ +/** + * store_sampling_rate - update sampling rate effective immediately if needed. + * + * If new rate is smaller than the old, simply updating + * dbs.sampling_rate might not be appropriate. For example, if the + * original sampling_rate was 1 second and the requested new sampling rate is 10 + * ms because the user needs immediate reaction from ondemand governor, but not + * sure if higher frequency will be required or not, then, the governor may + * change the sampling rate too late; up to 1 second later. Thus, if we are + * reducing the sampling rate, we need to make the new value effective + * immediately. + * + * This must be called with dbs_data->mutex held, otherwise traversing + * policy_dbs_list isn't safe. + */ +ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf, + size_t count) { - struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu); - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - struct cpufreq_policy *policy = cdbs->shared->policy; - unsigned int sampling_rate; - unsigned int max_load = 0; - unsigned int ignore_nice; - unsigned int j; + struct policy_dbs_info *policy_dbs; + unsigned int rate; + int ret; + ret = sscanf(buf, "%u", &rate); + if (ret != 1) + return -EINVAL; - if (dbs_data->cdata->governor == GOV_ONDEMAND) { - struct od_cpu_dbs_info_s *od_dbs_info = - dbs_data->cdata->get_cpu_dbs_info_s(cpu); + dbs_data->sampling_rate = max(rate, dbs_data->min_sampling_rate); + /* + * We are operating under dbs_data->mutex and so the list and its + * entries can't be freed concurrently. + */ + list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) { + mutex_lock(&policy_dbs->timer_mutex); /* - * Sometimes, the ondemand governor uses an additional - * multiplier to give long delays. So apply this multiplier to - * the 'sampling_rate', so as to keep the wake-up-from-idle - * detection logic a bit conservative. + * On 32-bit architectures this may race with the + * sample_delay_ns read in dbs_update_util_handler(), but that + * really doesn't matter. If the read returns a value that's + * too big, the sample will be skipped, but the next invocation + * of dbs_update_util_handler() (when the update has been + * completed) will take a sample. + * + * If this runs in parallel with dbs_work_handler(), we may end + * up overwriting the sample_delay_ns value that it has just + * written, but it will be corrected next time a sample is + * taken, so it shouldn't be significant. */ - sampling_rate = od_tuners->sampling_rate; - sampling_rate *= od_dbs_info->rate_mult; + gov_update_sample_delay(policy_dbs, 0); + mutex_unlock(&policy_dbs->timer_mutex); + } - ignore_nice = od_tuners->ignore_nice_load; - } else { - sampling_rate = cs_tuners->sampling_rate; - ignore_nice = cs_tuners->ignore_nice_load; + return count; +} +EXPORT_SYMBOL_GPL(store_sampling_rate); + +/** + * gov_update_cpu_data - Update CPU load data. + * @dbs_data: Top-level governor data pointer. + * + * Update CPU load data for all CPUs in the domain governed by @dbs_data + * (that may be a single policy or a bunch of them if governor tunables are + * system-wide). + * + * Call under the @dbs_data mutex. + */ +void gov_update_cpu_data(struct dbs_data *dbs_data) +{ + struct policy_dbs_info *policy_dbs; + + list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) { + unsigned int j; + + for_each_cpu(j, policy_dbs->policy->cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + + j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, + dbs_data->io_is_busy); + if (dbs_data->ignore_nice_load) + j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; + } } +} +EXPORT_SYMBOL_GPL(gov_update_cpu_data); + +static inline struct dbs_data *to_dbs_data(struct kobject *kobj) +{ + return container_of(kobj, struct dbs_data, kobj); +} + +static inline struct governor_attr *to_gov_attr(struct attribute *attr) +{ + return container_of(attr, struct governor_attr, attr); +} + +static ssize_t governor_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct dbs_data *dbs_data = to_dbs_data(kobj); + struct governor_attr *gattr = to_gov_attr(attr); + + return gattr->show(dbs_data, buf); +} + +static ssize_t governor_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct dbs_data *dbs_data = to_dbs_data(kobj); + struct governor_attr *gattr = to_gov_attr(attr); + int ret = -EBUSY; + + mutex_lock(&dbs_data->mutex); + + if (dbs_data->usage_count) + ret = gattr->store(dbs_data, buf, count); + + mutex_unlock(&dbs_data->mutex); + + return ret; +} + +/* + * Sysfs Ops for accessing governor attributes. + * + * All show/store invocations for governor specific sysfs attributes, will first + * call the below show/store callbacks and the attribute specific callback will + * be called from within it. + */ +static const struct sysfs_ops governor_sysfs_ops = { + .show = governor_show, + .store = governor_store, +}; + +unsigned int dbs_update(struct cpufreq_policy *policy) +{ + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + unsigned int ignore_nice = dbs_data->ignore_nice_load; + unsigned int max_load = 0; + unsigned int sampling_rate, io_busy, j; + + /* + * Sometimes governors may use an additional multiplier to increase + * sample delays temporarily. Apply that multiplier to sampling_rate + * so as to keep the wake-up-from-idle detection logic a bit + * conservative. + */ + sampling_rate = dbs_data->sampling_rate * policy_dbs->rate_mult; + /* + * For the purpose of ondemand, waiting for disk IO is an indication + * that you're performance critical, and not that the system is actually + * idle, so do not add the iowait time to the CPU idle time then. + */ + io_busy = dbs_data->io_is_busy; /* Get Absolute Load */ for_each_cpu(j, policy->cpus) { - struct cpu_dbs_info *j_cdbs; + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); u64 cur_wall_time, cur_idle_time; unsigned int idle_time, wall_time; unsigned int load; - int io_busy = 0; - - j_cdbs = dbs_data->cdata->get_cpu_cdbs(j); - /* - * For the purpose of ondemand, waiting for disk IO is - * an indication that you're performance critical, and - * not that the system is actually idle. So do not add - * the iowait time to the cpu idle time. - */ - if (dbs_data->cdata->governor == GOV_ONDEMAND) - io_busy = od_tuners->io_is_busy; cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy); - wall_time = (unsigned int) - (cur_wall_time - j_cdbs->prev_cpu_wall); + wall_time = cur_wall_time - j_cdbs->prev_cpu_wall; j_cdbs->prev_cpu_wall = cur_wall_time; - if (cur_idle_time < j_cdbs->prev_cpu_idle) - cur_idle_time = j_cdbs->prev_cpu_idle; - - idle_time = (unsigned int) - (cur_idle_time - j_cdbs->prev_cpu_idle); - j_cdbs->prev_cpu_idle = cur_idle_time; + if (cur_idle_time <= j_cdbs->prev_cpu_idle) { + idle_time = 0; + } else { + idle_time = cur_idle_time - j_cdbs->prev_cpu_idle; + j_cdbs->prev_cpu_idle = cur_idle_time; + } if (ignore_nice) { - u64 cur_nice; - unsigned long cur_nice_jiffies; - - cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] - - cdbs->prev_cpu_nice; - /* - * Assumption: nice time between sampling periods will - * be less than 2^32 jiffies for 32 bit sys - */ - cur_nice_jiffies = (unsigned long) - cputime64_to_jiffies64(cur_nice); + u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; - cdbs->prev_cpu_nice = - kcpustat_cpu(j).cpustat[CPUTIME_NICE]; - idle_time += jiffies_to_usecs(cur_nice_jiffies); + idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice); + j_cdbs->prev_cpu_nice = cur_nice; } if (unlikely(!wall_time || wall_time < idle_time)) @@ -128,10 +226,10 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) * dropped down. So we perform the copy only once, upon the * first wake-up from idle.) * - * Detecting this situation is easy: the governor's deferrable - * timer would not have fired during CPU-idle periods. Hence - * an unusually large 'wall_time' (as compared to the sampling - * rate) indicates this scenario. + * Detecting this situation is easy: the governor's utilization + * update handler would not have run during CPU-idle periods. + * Hence, an unusually large 'wall_time' (as compared to the + * sampling rate) indicates this scenario. * * prev_load can be zero in two cases and we must recalculate it * for both cases: @@ -156,222 +254,224 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) if (load > max_load) max_load = load; } - - dbs_data->cdata->gov_check_cpu(cpu, max_load); + return max_load; } -EXPORT_SYMBOL_GPL(dbs_check_cpu); +EXPORT_SYMBOL_GPL(dbs_update); -void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay) +static void gov_set_update_util(struct policy_dbs_info *policy_dbs, + unsigned int delay_us) { - struct dbs_data *dbs_data = policy->governor_data; - struct cpu_dbs_info *cdbs; + struct cpufreq_policy *policy = policy_dbs->policy; int cpu; + gov_update_sample_delay(policy_dbs, delay_us); + policy_dbs->last_sample_time = 0; + for_each_cpu(cpu, policy->cpus) { - cdbs = dbs_data->cdata->get_cpu_cdbs(cpu); - cdbs->timer.expires = jiffies + delay; - add_timer_on(&cdbs->timer, cpu); + struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu); + + cpufreq_set_update_util_data(cpu, &cdbs->update_util); } } -EXPORT_SYMBOL_GPL(gov_add_timers); -static inline void gov_cancel_timers(struct cpufreq_policy *policy) +static inline void gov_clear_update_util(struct cpufreq_policy *policy) { - struct dbs_data *dbs_data = policy->governor_data; - struct cpu_dbs_info *cdbs; int i; - for_each_cpu(i, policy->cpus) { - cdbs = dbs_data->cdata->get_cpu_cdbs(i); - del_timer_sync(&cdbs->timer); - } -} + for_each_cpu(i, policy->cpus) + cpufreq_set_update_util_data(i, NULL); -void gov_cancel_work(struct cpu_common_dbs_info *shared) -{ - /* Tell dbs_timer_handler() to skip queuing up work items. */ - atomic_inc(&shared->skip_work); - /* - * If dbs_timer_handler() is already running, it may not notice the - * incremented skip_work, so wait for it to complete to prevent its work - * item from being queued up after the cancel_work_sync() below. - */ - gov_cancel_timers(shared->policy); - /* - * In case dbs_timer_handler() managed to run and spawn a work item - * before the timers have been canceled, wait for that work item to - * complete and then cancel all of the timers set up by it. If - * dbs_timer_handler() runs again at that point, it will see the - * positive value of skip_work and won't spawn any more work items. - */ - cancel_work_sync(&shared->work); - gov_cancel_timers(shared->policy); - atomic_set(&shared->skip_work, 0); + synchronize_sched(); } -EXPORT_SYMBOL_GPL(gov_cancel_work); -/* Will return if we need to evaluate cpu load again or not */ -static bool need_load_eval(struct cpu_common_dbs_info *shared, - unsigned int sampling_rate) +static void gov_cancel_work(struct cpufreq_policy *policy) { - if (policy_is_shared(shared->policy)) { - ktime_t time_now = ktime_get(); - s64 delta_us = ktime_us_delta(time_now, shared->time_stamp); - - /* Do nothing if we recently have sampled */ - if (delta_us < (s64)(sampling_rate / 2)) - return false; - else - shared->time_stamp = time_now; - } + struct policy_dbs_info *policy_dbs = policy->governor_data; - return true; + gov_clear_update_util(policy_dbs->policy); + irq_work_sync(&policy_dbs->irq_work); + cancel_work_sync(&policy_dbs->work); + atomic_set(&policy_dbs->work_count, 0); + policy_dbs->work_in_progress = false; } static void dbs_work_handler(struct work_struct *work) { - struct cpu_common_dbs_info *shared = container_of(work, struct - cpu_common_dbs_info, work); + struct policy_dbs_info *policy_dbs; struct cpufreq_policy *policy; - struct dbs_data *dbs_data; - unsigned int sampling_rate, delay; - bool eval_load; - - policy = shared->policy; - dbs_data = policy->governor_data; + struct dbs_governor *gov; - /* Kill all timers */ - gov_cancel_timers(policy); + policy_dbs = container_of(work, struct policy_dbs_info, work); + policy = policy_dbs->policy; + gov = dbs_governor_of(policy); - if (dbs_data->cdata->governor == GOV_CONSERVATIVE) { - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - - sampling_rate = cs_tuners->sampling_rate; - } else { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - - sampling_rate = od_tuners->sampling_rate; - } - - eval_load = need_load_eval(shared, sampling_rate); + /* + * Make sure cpufreq_governor_limits() isn't evaluating load or the + * ondemand governor isn't updating the sampling rate in parallel. + */ + mutex_lock(&policy_dbs->timer_mutex); + gov_update_sample_delay(policy_dbs, gov->gov_dbs_timer(policy)); + mutex_unlock(&policy_dbs->timer_mutex); + /* Allow the utilization update handler to queue up more work. */ + atomic_set(&policy_dbs->work_count, 0); /* - * Make sure cpufreq_governor_limits() isn't evaluating load in - * parallel. + * If the update below is reordered with respect to the sample delay + * modification, the utilization update handler may end up using a stale + * sample delay value. */ - mutex_lock(&shared->timer_mutex); - delay = dbs_data->cdata->gov_dbs_timer(policy, eval_load); - mutex_unlock(&shared->timer_mutex); + smp_wmb(); + policy_dbs->work_in_progress = false; +} - atomic_dec(&shared->skip_work); +static void dbs_irq_work(struct irq_work *irq_work) +{ + struct policy_dbs_info *policy_dbs; - gov_add_timers(policy, delay); + policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work); + schedule_work(&policy_dbs->work); } -static void dbs_timer_handler(unsigned long data) +static void dbs_update_util_handler(struct update_util_data *data, u64 time, + unsigned long util, unsigned long max) { - struct cpu_dbs_info *cdbs = (struct cpu_dbs_info *)data; - struct cpu_common_dbs_info *shared = cdbs->shared; + struct cpu_dbs_info *cdbs = container_of(data, struct cpu_dbs_info, update_util); + struct policy_dbs_info *policy_dbs = cdbs->policy_dbs; + u64 delta_ns, lst; /* - * Timer handler may not be allowed to queue the work at the moment, - * because: - * - Another timer handler has done that - * - We are stopping the governor - * - Or we are updating the sampling rate of the ondemand governor + * The work may not be allowed to be queued up right now. + * Possible reasons: + * - Work has already been queued up or is in progress. + * - It is too early (too little time from the previous sample). */ - if (atomic_inc_return(&shared->skip_work) > 1) - atomic_dec(&shared->skip_work); - else - queue_work(system_wq, &shared->work); -} + if (policy_dbs->work_in_progress) + return; -static void set_sampling_rate(struct dbs_data *dbs_data, - unsigned int sampling_rate) -{ - if (dbs_data->cdata->governor == GOV_CONSERVATIVE) { - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - cs_tuners->sampling_rate = sampling_rate; - } else { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - od_tuners->sampling_rate = sampling_rate; + /* + * If the reads below are reordered before the check above, the value + * of sample_delay_ns used in the computation may be stale. + */ + smp_rmb(); + lst = READ_ONCE(policy_dbs->last_sample_time); + delta_ns = time - lst; + if ((s64)delta_ns < policy_dbs->sample_delay_ns) + return; + + /* + * If the policy is not shared, the irq_work may be queued up right away + * at this point. Otherwise, we need to ensure that only one of the + * CPUs sharing the policy will do that. + */ + if (policy_dbs->is_shared) { + if (!atomic_add_unless(&policy_dbs->work_count, 1, 1)) + return; + + /* + * If another CPU updated last_sample_time in the meantime, we + * shouldn't be here, so clear the work counter and bail out. + */ + if (unlikely(lst != READ_ONCE(policy_dbs->last_sample_time))) { + atomic_set(&policy_dbs->work_count, 0); + return; + } } + + policy_dbs->last_sample_time = time; + policy_dbs->work_in_progress = true; + irq_work_queue(&policy_dbs->irq_work); } -static int alloc_common_dbs_info(struct cpufreq_policy *policy, - struct common_dbs_data *cdata) +static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy, + struct dbs_governor *gov) { - struct cpu_common_dbs_info *shared; + struct policy_dbs_info *policy_dbs; int j; - /* Allocate memory for the common information for policy->cpus */ - shared = kzalloc(sizeof(*shared), GFP_KERNEL); - if (!shared) - return -ENOMEM; + /* Allocate memory for per-policy governor data. */ + policy_dbs = gov->alloc(); + if (!policy_dbs) + return NULL; - /* Set shared for all CPUs, online+offline */ - for_each_cpu(j, policy->related_cpus) - cdata->get_cpu_cdbs(j)->shared = shared; + policy_dbs->policy = policy; + mutex_init(&policy_dbs->timer_mutex); + atomic_set(&policy_dbs->work_count, 0); + init_irq_work(&policy_dbs->irq_work, dbs_irq_work); + INIT_WORK(&policy_dbs->work, dbs_work_handler); - mutex_init(&shared->timer_mutex); - atomic_set(&shared->skip_work, 0); - INIT_WORK(&shared->work, dbs_work_handler); - return 0; + /* Set policy_dbs for all CPUs, online+offline */ + for_each_cpu(j, policy->related_cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + + j_cdbs->policy_dbs = policy_dbs; + j_cdbs->update_util.func = dbs_update_util_handler; + } + return policy_dbs; } -static void free_common_dbs_info(struct cpufreq_policy *policy, - struct common_dbs_data *cdata) +static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs, + struct dbs_governor *gov) { - struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu); - struct cpu_common_dbs_info *shared = cdbs->shared; int j; - mutex_destroy(&shared->timer_mutex); + mutex_destroy(&policy_dbs->timer_mutex); - for_each_cpu(j, policy->cpus) - cdata->get_cpu_cdbs(j)->shared = NULL; + for_each_cpu(j, policy_dbs->policy->related_cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); - kfree(shared); + j_cdbs->policy_dbs = NULL; + j_cdbs->update_util.func = NULL; + } + gov->free(policy_dbs); } -static int cpufreq_governor_init(struct cpufreq_policy *policy, - struct dbs_data *dbs_data, - struct common_dbs_data *cdata) +static int cpufreq_governor_init(struct cpufreq_policy *policy) { + struct dbs_governor *gov = dbs_governor_of(policy); + struct dbs_data *dbs_data; + struct policy_dbs_info *policy_dbs; unsigned int latency; - int ret; + int ret = 0; /* State should be equivalent to EXIT */ if (policy->governor_data) return -EBUSY; - if (dbs_data) { - if (WARN_ON(have_governor_per_policy())) - return -EINVAL; + policy_dbs = alloc_policy_dbs_info(policy, gov); + if (!policy_dbs) + return -ENOMEM; - ret = alloc_common_dbs_info(policy, cdata); - if (ret) - return ret; + /* Protect gov->gdbs_data against concurrent updates. */ + mutex_lock(&gov_dbs_data_mutex); + dbs_data = gov->gdbs_data; + if (dbs_data) { + if (WARN_ON(have_governor_per_policy())) { + ret = -EINVAL; + goto free_policy_dbs_info; + } + policy_dbs->dbs_data = dbs_data; + policy->governor_data = policy_dbs; + + mutex_lock(&dbs_data->mutex); dbs_data->usage_count++; - policy->governor_data = dbs_data; - return 0; + list_add(&policy_dbs->list, &dbs_data->policy_dbs_list); + mutex_unlock(&dbs_data->mutex); + goto out; } dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL); - if (!dbs_data) - return -ENOMEM; - - ret = alloc_common_dbs_info(policy, cdata); - if (ret) - goto free_dbs_data; + if (!dbs_data) { + ret = -ENOMEM; + goto free_policy_dbs_info; + } - dbs_data->cdata = cdata; - dbs_data->usage_count = 1; + INIT_LIST_HEAD(&dbs_data->policy_dbs_list); + mutex_init(&dbs_data->mutex); - ret = cdata->init(dbs_data, !policy->governor->initialized); + ret = gov->init(dbs_data, !policy->governor->initialized); if (ret) - goto free_common_dbs_info; + goto free_policy_dbs_info; /* policy latency is in ns. Convert it to us first */ latency = policy->cpuinfo.transition_latency / 1000; @@ -381,216 +481,156 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy, /* Bring kernel and HW constraints together */ dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate, MIN_LATENCY_MULTIPLIER * latency); - set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate, - latency * LATENCY_MULTIPLIER)); + dbs_data->sampling_rate = max(dbs_data->min_sampling_rate, + LATENCY_MULTIPLIER * latency); if (!have_governor_per_policy()) - cdata->gdbs_data = dbs_data; + gov->gdbs_data = dbs_data; - policy->governor_data = dbs_data; + policy->governor_data = policy_dbs; - ret = sysfs_create_group(get_governor_parent_kobj(policy), - get_sysfs_attr(dbs_data)); - if (ret) - goto reset_gdbs_data; + policy_dbs->dbs_data = dbs_data; + dbs_data->usage_count = 1; + list_add(&policy_dbs->list, &dbs_data->policy_dbs_list); - return 0; + gov->kobj_type.sysfs_ops = &governor_sysfs_ops; + ret = kobject_init_and_add(&dbs_data->kobj, &gov->kobj_type, + get_governor_parent_kobj(policy), + "%s", gov->gov.name); + if (!ret) + goto out; + + /* Failure, so roll back. */ + pr_err("cpufreq: Governor initialization failed (dbs_data kobject init error %d)\n", ret); -reset_gdbs_data: policy->governor_data = NULL; if (!have_governor_per_policy()) - cdata->gdbs_data = NULL; - cdata->exit(dbs_data, !policy->governor->initialized); -free_common_dbs_info: - free_common_dbs_info(policy, cdata); -free_dbs_data: + gov->gdbs_data = NULL; + gov->exit(dbs_data, !policy->governor->initialized); kfree(dbs_data); + +free_policy_dbs_info: + free_policy_dbs_info(policy_dbs, gov); + +out: + mutex_unlock(&gov_dbs_data_mutex); return ret; } -static int cpufreq_governor_exit(struct cpufreq_policy *policy, - struct dbs_data *dbs_data) +static int cpufreq_governor_exit(struct cpufreq_policy *policy) { - struct common_dbs_data *cdata = dbs_data->cdata; - struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu); + struct dbs_governor *gov = dbs_governor_of(policy); + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + int count; - /* State should be equivalent to INIT */ - if (!cdbs->shared || cdbs->shared->policy) - return -EBUSY; + /* Protect gov->gdbs_data against concurrent updates. */ + mutex_lock(&gov_dbs_data_mutex); + + mutex_lock(&dbs_data->mutex); + list_del(&policy_dbs->list); + count = --dbs_data->usage_count; + mutex_unlock(&dbs_data->mutex); - if (!--dbs_data->usage_count) { - sysfs_remove_group(get_governor_parent_kobj(policy), - get_sysfs_attr(dbs_data)); + if (!count) { + kobject_put(&dbs_data->kobj); policy->governor_data = NULL; if (!have_governor_per_policy()) - cdata->gdbs_data = NULL; + gov->gdbs_data = NULL; - cdata->exit(dbs_data, policy->governor->initialized == 1); + gov->exit(dbs_data, policy->governor->initialized == 1); + mutex_destroy(&dbs_data->mutex); kfree(dbs_data); } else { policy->governor_data = NULL; } - free_common_dbs_info(policy, cdata); + free_policy_dbs_info(policy_dbs, gov); + + mutex_unlock(&gov_dbs_data_mutex); return 0; } -static int cpufreq_governor_start(struct cpufreq_policy *policy, - struct dbs_data *dbs_data) +static int cpufreq_governor_start(struct cpufreq_policy *policy) { - struct common_dbs_data *cdata = dbs_data->cdata; - unsigned int sampling_rate, ignore_nice, j, cpu = policy->cpu; - struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu); - struct cpu_common_dbs_info *shared = cdbs->shared; - int io_busy = 0; + struct dbs_governor *gov = dbs_governor_of(policy); + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + unsigned int sampling_rate, ignore_nice, j; + unsigned int io_busy; if (!policy->cur) return -EINVAL; - /* State should be equivalent to INIT */ - if (!shared || shared->policy) - return -EBUSY; + policy_dbs->is_shared = policy_is_shared(policy); + policy_dbs->rate_mult = 1; - if (cdata->governor == GOV_CONSERVATIVE) { - struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; - - sampling_rate = cs_tuners->sampling_rate; - ignore_nice = cs_tuners->ignore_nice_load; - } else { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - - sampling_rate = od_tuners->sampling_rate; - ignore_nice = od_tuners->ignore_nice_load; - io_busy = od_tuners->io_is_busy; - } - - shared->policy = policy; - shared->time_stamp = ktime_get(); + sampling_rate = dbs_data->sampling_rate; + ignore_nice = dbs_data->ignore_nice_load; + io_busy = dbs_data->io_is_busy; for_each_cpu(j, policy->cpus) { - struct cpu_dbs_info *j_cdbs = cdata->get_cpu_cdbs(j); + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); unsigned int prev_load; - j_cdbs->prev_cpu_idle = - get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy); + j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy); - prev_load = (unsigned int)(j_cdbs->prev_cpu_wall - - j_cdbs->prev_cpu_idle); - j_cdbs->prev_load = 100 * prev_load / - (unsigned int)j_cdbs->prev_cpu_wall; + prev_load = j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle; + j_cdbs->prev_load = 100 * prev_load / (unsigned int)j_cdbs->prev_cpu_wall; if (ignore_nice) j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; - - __setup_timer(&j_cdbs->timer, dbs_timer_handler, - (unsigned long)j_cdbs, - TIMER_DEFERRABLE | TIMER_IRQSAFE); } - if (cdata->governor == GOV_CONSERVATIVE) { - struct cs_cpu_dbs_info_s *cs_dbs_info = - cdata->get_cpu_dbs_info_s(cpu); - - cs_dbs_info->down_skip = 0; - cs_dbs_info->requested_freq = policy->cur; - } else { - struct od_ops *od_ops = cdata->gov_ops; - struct od_cpu_dbs_info_s *od_dbs_info = cdata->get_cpu_dbs_info_s(cpu); - - od_dbs_info->rate_mult = 1; - od_dbs_info->sample_type = OD_NORMAL_SAMPLE; - od_ops->powersave_bias_init_cpu(cpu); - } + gov->start(policy); - gov_add_timers(policy, delay_for_sampling_rate(sampling_rate)); + gov_set_update_util(policy_dbs, sampling_rate); return 0; } -static int cpufreq_governor_stop(struct cpufreq_policy *policy, - struct dbs_data *dbs_data) +static int cpufreq_governor_stop(struct cpufreq_policy *policy) { - struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(policy->cpu); - struct cpu_common_dbs_info *shared = cdbs->shared; - - /* State should be equivalent to START */ - if (!shared || !shared->policy) - return -EBUSY; - - gov_cancel_work(shared); - shared->policy = NULL; - + gov_cancel_work(policy); return 0; } -static int cpufreq_governor_limits(struct cpufreq_policy *policy, - struct dbs_data *dbs_data) +static int cpufreq_governor_limits(struct cpufreq_policy *policy) { - struct common_dbs_data *cdata = dbs_data->cdata; - unsigned int cpu = policy->cpu; - struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu); + struct policy_dbs_info *policy_dbs = policy->governor_data; - /* State should be equivalent to START */ - if (!cdbs->shared || !cdbs->shared->policy) - return -EBUSY; + mutex_lock(&policy_dbs->timer_mutex); + + if (policy->max < policy->cur) + __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); + else if (policy->min > policy->cur) + __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); + + gov_update_sample_delay(policy_dbs, 0); - mutex_lock(&cdbs->shared->timer_mutex); - if (policy->max < cdbs->shared->policy->cur) - __cpufreq_driver_target(cdbs->shared->policy, policy->max, - CPUFREQ_RELATION_H); - else if (policy->min > cdbs->shared->policy->cur) - __cpufreq_driver_target(cdbs->shared->policy, policy->min, - CPUFREQ_RELATION_L); - dbs_check_cpu(dbs_data, cpu); - mutex_unlock(&cdbs->shared->timer_mutex); + mutex_unlock(&policy_dbs->timer_mutex); return 0; } -int cpufreq_governor_dbs(struct cpufreq_policy *policy, - struct common_dbs_data *cdata, unsigned int event) +int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event) { - struct dbs_data *dbs_data; - int ret; - - /* Lock governor to block concurrent initialization of governor */ - mutex_lock(&cdata->mutex); - - if (have_governor_per_policy()) - dbs_data = policy->governor_data; - else - dbs_data = cdata->gdbs_data; - - if (!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT)) { - ret = -EINVAL; - goto unlock; - } - - switch (event) { - case CPUFREQ_GOV_POLICY_INIT: - ret = cpufreq_governor_init(policy, dbs_data, cdata); - break; - case CPUFREQ_GOV_POLICY_EXIT: - ret = cpufreq_governor_exit(policy, dbs_data); - break; - case CPUFREQ_GOV_START: - ret = cpufreq_governor_start(policy, dbs_data); - break; - case CPUFREQ_GOV_STOP: - ret = cpufreq_governor_stop(policy, dbs_data); - break; - case CPUFREQ_GOV_LIMITS: - ret = cpufreq_governor_limits(policy, dbs_data); - break; - default: - ret = -EINVAL; + if (event == CPUFREQ_GOV_POLICY_INIT) { + return cpufreq_governor_init(policy); + } else if (policy->governor_data) { + switch (event) { + case CPUFREQ_GOV_POLICY_EXIT: + return cpufreq_governor_exit(policy); + case CPUFREQ_GOV_START: + return cpufreq_governor_start(policy); + case CPUFREQ_GOV_STOP: + return cpufreq_governor_stop(policy); + case CPUFREQ_GOV_LIMITS: + return cpufreq_governor_limits(policy); + } } - -unlock: - mutex_unlock(&cdata->mutex); - - return ret; + return -EINVAL; } EXPORT_SYMBOL_GPL(cpufreq_governor_dbs); diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index 91e767a058a7..61ff82fe0613 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -18,6 +18,7 @@ #define _CPUFREQ_GOVERNOR_H #include <linux/atomic.h> +#include <linux/irq_work.h> #include <linux/cpufreq.h> #include <linux/kernel_stat.h> #include <linux/module.h> @@ -41,96 +42,68 @@ enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE}; /* - * Macro for creating governors sysfs routines - * - * - gov_sys: One governor instance per whole system - * - gov_pol: One governor instance per policy + * Abbreviations: + * dbs: used as a shortform for demand based switching It helps to keep variable + * names smaller, simpler + * cdbs: common dbs + * od_*: On-demand governor + * cs_*: Conservative governor */ -/* Create attributes */ -#define gov_sys_attr_ro(_name) \ -static struct global_attr _name##_gov_sys = \ -__ATTR(_name, 0444, show_##_name##_gov_sys, NULL) - -#define gov_sys_attr_rw(_name) \ -static struct global_attr _name##_gov_sys = \ -__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys) - -#define gov_pol_attr_ro(_name) \ -static struct freq_attr _name##_gov_pol = \ -__ATTR(_name, 0444, show_##_name##_gov_pol, NULL) - -#define gov_pol_attr_rw(_name) \ -static struct freq_attr _name##_gov_pol = \ -__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol) +/* Governor demand based switching data (per-policy or global). */ +struct dbs_data { + int usage_count; + void *tuners; + unsigned int min_sampling_rate; + unsigned int ignore_nice_load; + unsigned int sampling_rate; + unsigned int sampling_down_factor; + unsigned int up_threshold; + unsigned int io_is_busy; -#define gov_sys_pol_attr_rw(_name) \ - gov_sys_attr_rw(_name); \ - gov_pol_attr_rw(_name) + struct kobject kobj; + struct list_head policy_dbs_list; + /* + * Protect concurrent updates to governor tunables from sysfs, + * policy_dbs_list and usage_count. + */ + struct mutex mutex; +}; -#define gov_sys_pol_attr_ro(_name) \ - gov_sys_attr_ro(_name); \ - gov_pol_attr_ro(_name) +/* Governor's specific attributes */ +struct dbs_data; +struct governor_attr { + struct attribute attr; + ssize_t (*show)(struct dbs_data *dbs_data, char *buf); + ssize_t (*store)(struct dbs_data *dbs_data, const char *buf, + size_t count); +}; -/* Create show/store routines */ -#define show_one(_gov, file_name) \ -static ssize_t show_##file_name##_gov_sys \ -(struct kobject *kobj, struct attribute *attr, char *buf) \ +#define gov_show_one(_gov, file_name) \ +static ssize_t show_##file_name \ +(struct dbs_data *dbs_data, char *buf) \ { \ - struct _gov##_dbs_tuners *tuners = _gov##_dbs_cdata.gdbs_data->tuners; \ - return sprintf(buf, "%u\n", tuners->file_name); \ -} \ - \ -static ssize_t show_##file_name##_gov_pol \ -(struct cpufreq_policy *policy, char *buf) \ -{ \ - struct dbs_data *dbs_data = policy->governor_data; \ struct _gov##_dbs_tuners *tuners = dbs_data->tuners; \ return sprintf(buf, "%u\n", tuners->file_name); \ } -#define store_one(_gov, file_name) \ -static ssize_t store_##file_name##_gov_sys \ -(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) \ -{ \ - struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data; \ - return store_##file_name(dbs_data, buf, count); \ -} \ - \ -static ssize_t store_##file_name##_gov_pol \ -(struct cpufreq_policy *policy, const char *buf, size_t count) \ +#define gov_show_one_common(file_name) \ +static ssize_t show_##file_name \ +(struct dbs_data *dbs_data, char *buf) \ { \ - struct dbs_data *dbs_data = policy->governor_data; \ - return store_##file_name(dbs_data, buf, count); \ + return sprintf(buf, "%u\n", dbs_data->file_name); \ } -#define show_store_one(_gov, file_name) \ -show_one(_gov, file_name); \ -store_one(_gov, file_name) +#define gov_attr_ro(_name) \ +static struct governor_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) -/* create helper routines */ -#define define_get_cpu_dbs_routines(_dbs_info) \ -static struct cpu_dbs_info *get_cpu_cdbs(int cpu) \ -{ \ - return &per_cpu(_dbs_info, cpu).cdbs; \ -} \ - \ -static void *get_cpu_dbs_info_s(int cpu) \ -{ \ - return &per_cpu(_dbs_info, cpu); \ -} - -/* - * Abbreviations: - * dbs: used as a shortform for demand based switching It helps to keep variable - * names smaller, simpler - * cdbs: common dbs - * od_*: On-demand governor - * cs_*: Conservative governor - */ +#define gov_attr_rw(_name) \ +static struct governor_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) /* Common to all CPUs of a policy */ -struct cpu_common_dbs_info { +struct policy_dbs_info { struct cpufreq_policy *policy; /* * Per policy mutex that serializes load evaluation from limit-change @@ -138,11 +111,27 @@ struct cpu_common_dbs_info { */ struct mutex timer_mutex; - ktime_t time_stamp; - atomic_t skip_work; + u64 last_sample_time; + s64 sample_delay_ns; + atomic_t work_count; + struct irq_work irq_work; struct work_struct work; + /* dbs_data may be shared between multiple policy objects */ + struct dbs_data *dbs_data; + struct list_head list; + /* Multiplier for increasing sample delay temporarily. */ + unsigned int rate_mult; + /* Status indicators */ + bool is_shared; /* This object is used by multiple CPUs */ + bool work_in_progress; /* Work is being queued up or in progress */ }; +static inline void gov_update_sample_delay(struct policy_dbs_info *policy_dbs, + unsigned int delay_us) +{ + policy_dbs->sample_delay_ns = delay_us * NSEC_PER_USEC; +} + /* Per cpu structures */ struct cpu_dbs_info { u64 prev_cpu_idle; @@ -155,54 +144,14 @@ struct cpu_dbs_info { * wake-up from idle. */ unsigned int prev_load; - struct timer_list timer; - struct cpu_common_dbs_info *shared; -}; - -struct od_cpu_dbs_info_s { - struct cpu_dbs_info cdbs; - struct cpufreq_frequency_table *freq_table; - unsigned int freq_lo; - unsigned int freq_lo_jiffies; - unsigned int freq_hi_jiffies; - unsigned int rate_mult; - unsigned int sample_type:1; -}; - -struct cs_cpu_dbs_info_s { - struct cpu_dbs_info cdbs; - unsigned int down_skip; - unsigned int requested_freq; -}; - -/* Per policy Governors sysfs tunables */ -struct od_dbs_tuners { - unsigned int ignore_nice_load; - unsigned int sampling_rate; - unsigned int sampling_down_factor; - unsigned int up_threshold; - unsigned int powersave_bias; - unsigned int io_is_busy; -}; - -struct cs_dbs_tuners { - unsigned int ignore_nice_load; - unsigned int sampling_rate; - unsigned int sampling_down_factor; - unsigned int up_threshold; - unsigned int down_threshold; - unsigned int freq_step; + struct update_util_data update_util; + struct policy_dbs_info *policy_dbs; }; /* Common Governor data across policies */ -struct dbs_data; -struct common_dbs_data { - /* Common across governors */ - #define GOV_ONDEMAND 0 - #define GOV_CONSERVATIVE 1 - int governor; - struct attribute_group *attr_group_gov_sys; /* one governor - system */ - struct attribute_group *attr_group_gov_pol; /* one governor - policy */ +struct dbs_governor { + struct cpufreq_governor gov; + struct kobj_type kobj_type; /* * Common data for platforms that don't set @@ -210,74 +159,32 @@ struct common_dbs_data { */ struct dbs_data *gdbs_data; - struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu); - void *(*get_cpu_dbs_info_s)(int cpu); - unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy, - bool modify_all); - void (*gov_check_cpu)(int cpu, unsigned int load); + unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy); + struct policy_dbs_info *(*alloc)(void); + void (*free)(struct policy_dbs_info *policy_dbs); int (*init)(struct dbs_data *dbs_data, bool notify); void (*exit)(struct dbs_data *dbs_data, bool notify); - - /* Governor specific ops, see below */ - void *gov_ops; - - /* - * Protects governor's data (struct dbs_data and struct common_dbs_data) - */ - struct mutex mutex; + void (*start)(struct cpufreq_policy *policy); }; -/* Governor Per policy data */ -struct dbs_data { - struct common_dbs_data *cdata; - unsigned int min_sampling_rate; - int usage_count; - void *tuners; -}; +static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy) +{ + return container_of(policy->governor, struct dbs_governor, gov); +} -/* Governor specific ops, will be passed to dbs_data->gov_ops */ +/* Governor specific operations */ struct od_ops { - void (*powersave_bias_init_cpu)(int cpu); unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy, unsigned int freq_next, unsigned int relation); - void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq); }; -static inline int delay_for_sampling_rate(unsigned int sampling_rate) -{ - int delay = usecs_to_jiffies(sampling_rate); - - /* We want all CPUs to do sampling nearly on same jiffy */ - if (num_online_cpus() > 1) - delay -= jiffies % delay; - - return delay; -} - -#define declare_show_sampling_rate_min(_gov) \ -static ssize_t show_sampling_rate_min_gov_sys \ -(struct kobject *kobj, struct attribute *attr, char *buf) \ -{ \ - struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data; \ - return sprintf(buf, "%u\n", dbs_data->min_sampling_rate); \ -} \ - \ -static ssize_t show_sampling_rate_min_gov_pol \ -(struct cpufreq_policy *policy, char *buf) \ -{ \ - struct dbs_data *dbs_data = policy->governor_data; \ - return sprintf(buf, "%u\n", dbs_data->min_sampling_rate); \ -} - -extern struct mutex cpufreq_governor_lock; - -void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay); -void gov_cancel_work(struct cpu_common_dbs_info *shared); -void dbs_check_cpu(struct dbs_data *dbs_data, int cpu); -int cpufreq_governor_dbs(struct cpufreq_policy *policy, - struct common_dbs_data *cdata, unsigned int event); +unsigned int dbs_update(struct cpufreq_policy *policy); +int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event); void od_register_powersave_bias_handler(unsigned int (*f) (struct cpufreq_policy *, unsigned int, unsigned int), unsigned int powersave_bias); void od_unregister_powersave_bias_handler(void); +ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf, + size_t count); +void gov_update_cpu_data(struct dbs_data *dbs_data); #endif /* _CPUFREQ_GOVERNOR_H */ diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index eae51070c034..acd80272ded6 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -16,7 +16,8 @@ #include <linux/percpu-defs.h> #include <linux/slab.h> #include <linux/tick.h> -#include "cpufreq_governor.h" + +#include "cpufreq_ondemand.h" /* On-demand governor macros */ #define DEF_FREQUENCY_UP_THRESHOLD (80) @@ -27,24 +28,10 @@ #define MIN_FREQUENCY_UP_THRESHOLD (11) #define MAX_FREQUENCY_UP_THRESHOLD (100) -static DEFINE_PER_CPU(struct od_cpu_dbs_info_s, od_cpu_dbs_info); - static struct od_ops od_ops; -#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND -static struct cpufreq_governor cpufreq_gov_ondemand; -#endif - static unsigned int default_powersave_bias; -static void ondemand_powersave_bias_init_cpu(int cpu) -{ - struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu); - - dbs_info->freq_table = cpufreq_frequency_get_table(cpu); - dbs_info->freq_lo = 0; -} - /* * Not all CPUs want IO time to be accounted as busy; this depends on how * efficient idling at a higher frequency/voltage is. @@ -70,8 +57,8 @@ static int should_io_be_busy(void) /* * Find right freq to be set now with powersave_bias on. - * Returns the freq_hi to be used right now and will set freq_hi_jiffies, - * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs. + * Returns the freq_hi to be used right now and will set freq_hi_delay_us, + * freq_lo, and freq_lo_delay_us in percpu area for averaging freqs. */ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy, unsigned int freq_next, unsigned int relation) @@ -79,15 +66,15 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy, unsigned int freq_req, freq_reduc, freq_avg; unsigned int freq_hi, freq_lo; unsigned int index = 0; - unsigned int jiffies_total, jiffies_hi, jiffies_lo; - struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, - policy->cpu); - struct dbs_data *dbs_data = policy->governor_data; + unsigned int delay_hi_us; + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs); + struct dbs_data *dbs_data = policy_dbs->dbs_data; struct od_dbs_tuners *od_tuners = dbs_data->tuners; if (!dbs_info->freq_table) { dbs_info->freq_lo = 0; - dbs_info->freq_lo_jiffies = 0; + dbs_info->freq_lo_delay_us = 0; return freq_next; } @@ -110,31 +97,30 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy, /* Find out how long we have to be in hi and lo freqs */ if (freq_hi == freq_lo) { dbs_info->freq_lo = 0; - dbs_info->freq_lo_jiffies = 0; + dbs_info->freq_lo_delay_us = 0; return freq_lo; } - jiffies_total = usecs_to_jiffies(od_tuners->sampling_rate); - jiffies_hi = (freq_avg - freq_lo) * jiffies_total; - jiffies_hi += ((freq_hi - freq_lo) / 2); - jiffies_hi /= (freq_hi - freq_lo); - jiffies_lo = jiffies_total - jiffies_hi; + delay_hi_us = (freq_avg - freq_lo) * dbs_data->sampling_rate; + delay_hi_us += (freq_hi - freq_lo) / 2; + delay_hi_us /= freq_hi - freq_lo; + dbs_info->freq_hi_delay_us = delay_hi_us; dbs_info->freq_lo = freq_lo; - dbs_info->freq_lo_jiffies = jiffies_lo; - dbs_info->freq_hi_jiffies = jiffies_hi; + dbs_info->freq_lo_delay_us = dbs_data->sampling_rate - delay_hi_us; return freq_hi; } -static void ondemand_powersave_bias_init(void) +static void ondemand_powersave_bias_init(struct cpufreq_policy *policy) { - int i; - for_each_online_cpu(i) { - ondemand_powersave_bias_init_cpu(i); - } + struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data); + + dbs_info->freq_table = cpufreq_frequency_get_table(policy->cpu); + dbs_info->freq_lo = 0; } static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq) { - struct dbs_data *dbs_data = policy->governor_data; + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; struct od_dbs_tuners *od_tuners = dbs_data->tuners; if (od_tuners->powersave_bias) @@ -152,21 +138,21 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq) * (default), then we try to increase frequency. Else, we adjust the frequency * proportional to load. */ -static void od_check_cpu(int cpu, unsigned int load) +static void od_update(struct cpufreq_policy *policy) { - struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu); - struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy; - struct dbs_data *dbs_data = policy->governor_data; + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs); + struct dbs_data *dbs_data = policy_dbs->dbs_data; struct od_dbs_tuners *od_tuners = dbs_data->tuners; + unsigned int load = dbs_update(policy); dbs_info->freq_lo = 0; /* Check for frequency increase */ - if (load > od_tuners->up_threshold) { + if (load > dbs_data->up_threshold) { /* If switching to max speed, apply sampling_down_factor */ if (policy->cur < policy->max) - dbs_info->rate_mult = - od_tuners->sampling_down_factor; + policy_dbs->rate_mult = dbs_data->sampling_down_factor; dbs_freq_increase(policy, policy->max); } else { /* Calculate the next frequency proportional to load */ @@ -177,177 +163,70 @@ static void od_check_cpu(int cpu, unsigned int load) freq_next = min_f + load * (max_f - min_f) / 100; /* No longer fully busy, reset rate_mult */ - dbs_info->rate_mult = 1; + policy_dbs->rate_mult = 1; - if (!od_tuners->powersave_bias) { - __cpufreq_driver_target(policy, freq_next, - CPUFREQ_RELATION_C); - return; - } + if (od_tuners->powersave_bias) + freq_next = od_ops.powersave_bias_target(policy, + freq_next, + CPUFREQ_RELATION_L); - freq_next = od_ops.powersave_bias_target(policy, freq_next, - CPUFREQ_RELATION_L); __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_C); } } -static unsigned int od_dbs_timer(struct cpufreq_policy *policy, bool modify_all) +static unsigned int od_dbs_timer(struct cpufreq_policy *policy) { - struct dbs_data *dbs_data = policy->governor_data; - unsigned int cpu = policy->cpu; - struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, - cpu); - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - int delay = 0, sample_type = dbs_info->sample_type; - - if (!modify_all) - goto max_delay; + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs); + int sample_type = dbs_info->sample_type; /* Common NORMAL_SAMPLE setup */ dbs_info->sample_type = OD_NORMAL_SAMPLE; - if (sample_type == OD_SUB_SAMPLE) { - delay = dbs_info->freq_lo_jiffies; + /* + * OD_SUB_SAMPLE doesn't make sense if sample_delay_ns is 0, so ignore + * it then. + */ + if (sample_type == OD_SUB_SAMPLE && policy_dbs->sample_delay_ns > 0) { __cpufreq_driver_target(policy, dbs_info->freq_lo, CPUFREQ_RELATION_H); - } else { - dbs_check_cpu(dbs_data, cpu); - if (dbs_info->freq_lo) { - /* Setup timer for SUB_SAMPLE */ - dbs_info->sample_type = OD_SUB_SAMPLE; - delay = dbs_info->freq_hi_jiffies; - } + return dbs_info->freq_lo_delay_us; } -max_delay: - if (!delay) - delay = delay_for_sampling_rate(od_tuners->sampling_rate - * dbs_info->rate_mult); - - return delay; -} - -/************************** sysfs interface ************************/ -static struct common_dbs_data od_dbs_cdata; - -/** - * update_sampling_rate - update sampling rate effective immediately if needed. - * @new_rate: new sampling rate - * - * If new rate is smaller than the old, simply updating - * dbs_tuners_int.sampling_rate might not be appropriate. For example, if the - * original sampling_rate was 1 second and the requested new sampling rate is 10 - * ms because the user needs immediate reaction from ondemand governor, but not - * sure if higher frequency will be required or not, then, the governor may - * change the sampling rate too late; up to 1 second later. Thus, if we are - * reducing the sampling rate, we need to make the new value effective - * immediately. - */ -static void update_sampling_rate(struct dbs_data *dbs_data, - unsigned int new_rate) -{ - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - struct cpumask cpumask; - int cpu; - - od_tuners->sampling_rate = new_rate = max(new_rate, - dbs_data->min_sampling_rate); - - /* - * Lock governor so that governor start/stop can't execute in parallel. - */ - mutex_lock(&od_dbs_cdata.mutex); - - cpumask_copy(&cpumask, cpu_online_mask); - - for_each_cpu(cpu, &cpumask) { - struct cpufreq_policy *policy; - struct od_cpu_dbs_info_s *dbs_info; - struct cpu_dbs_info *cdbs; - struct cpu_common_dbs_info *shared; - unsigned long next_sampling, appointed_at; - - dbs_info = &per_cpu(od_cpu_dbs_info, cpu); - cdbs = &dbs_info->cdbs; - shared = cdbs->shared; - - /* - * A valid shared and shared->policy means governor hasn't - * stopped or exited yet. - */ - if (!shared || !shared->policy) - continue; - - policy = shared->policy; - - /* clear all CPUs of this policy */ - cpumask_andnot(&cpumask, &cpumask, policy->cpus); + od_update(policy); - /* - * Update sampling rate for CPUs whose policy is governed by - * dbs_data. In case of governor_per_policy, only a single - * policy will be governed by dbs_data, otherwise there can be - * multiple policies that are governed by the same dbs_data. - */ - if (dbs_data != policy->governor_data) - continue; - - /* - * Checking this for any CPU should be fine, timers for all of - * them are scheduled together. - */ - next_sampling = jiffies + usecs_to_jiffies(new_rate); - appointed_at = dbs_info->cdbs.timer.expires; - - if (time_before(next_sampling, appointed_at)) { - gov_cancel_work(shared); - gov_add_timers(policy, usecs_to_jiffies(new_rate)); - - } + if (dbs_info->freq_lo) { + /* Setup timer for SUB_SAMPLE */ + dbs_info->sample_type = OD_SUB_SAMPLE; + return dbs_info->freq_hi_delay_us; } - mutex_unlock(&od_dbs_cdata.mutex); + return dbs_data->sampling_rate * policy_dbs->rate_mult; } -static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf, - size_t count) -{ - unsigned int input; - int ret; - ret = sscanf(buf, "%u", &input); - if (ret != 1) - return -EINVAL; - - update_sampling_rate(dbs_data, input); - return count; -} +/************************** sysfs interface ************************/ +static struct dbs_governor od_dbs_gov; static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf, size_t count) { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; unsigned int input; int ret; - unsigned int j; ret = sscanf(buf, "%u", &input); if (ret != 1) return -EINVAL; - od_tuners->io_is_busy = !!input; + dbs_data->io_is_busy = !!input; /* we need to re-evaluate prev_cpu_idle */ - for_each_online_cpu(j) { - struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, - j); - dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j, - &dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy); - } + gov_update_cpu_data(dbs_data); + return count; } static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf, size_t count) { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; unsigned int input; int ret; ret = sscanf(buf, "%u", &input); @@ -357,40 +236,43 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf, return -EINVAL; } - od_tuners->up_threshold = input; + dbs_data->up_threshold = input; return count; } static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data, const char *buf, size_t count) { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; - unsigned int input, j; + struct policy_dbs_info *policy_dbs; + unsigned int input; int ret; ret = sscanf(buf, "%u", &input); if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1) return -EINVAL; - od_tuners->sampling_down_factor = input; + + dbs_data->sampling_down_factor = input; /* Reset down sampling multiplier in case it was active */ - for_each_online_cpu(j) { - struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, - j); - dbs_info->rate_mult = 1; + list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) { + /* + * Doing this without locking might lead to using different + * rate_mult values in od_update() and od_dbs_timer(). + */ + mutex_lock(&policy_dbs->timer_mutex); + policy_dbs->rate_mult = 1; + mutex_unlock(&policy_dbs->timer_mutex); } + return count; } static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data, const char *buf, size_t count) { - struct od_dbs_tuners *od_tuners = dbs_data->tuners; unsigned int input; int ret; - unsigned int j; - ret = sscanf(buf, "%u", &input); if (ret != 1) return -EINVAL; @@ -398,22 +280,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data, if (input > 1) input = 1; - if (input == od_tuners->ignore_nice_load) { /* nothing to do */ + if (input == dbs_data->ignore_nice_load) { /* nothing to do */ return count; } - od_tuners->ignore_nice_load = input; + dbs_data->ignore_nice_load = input; /* we need to re-evaluate prev_cpu_idle */ - for_each_online_cpu(j) { - struct od_cpu_dbs_info_s *dbs_info; - dbs_info = &per_cpu(od_cpu_dbs_info, j); - dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j, - &dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy); - if (od_tuners->ignore_nice_load) - dbs_info->cdbs.prev_cpu_nice = - kcpustat_cpu(j).cpustat[CPUTIME_NICE]; + gov_update_cpu_data(dbs_data); - } return count; } @@ -421,6 +295,7 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf, size_t count) { struct od_dbs_tuners *od_tuners = dbs_data->tuners; + struct policy_dbs_info *policy_dbs; unsigned int input; int ret; ret = sscanf(buf, "%u", &input); @@ -432,59 +307,54 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf, input = 1000; od_tuners->powersave_bias = input; - ondemand_powersave_bias_init(); + + list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) + ondemand_powersave_bias_init(policy_dbs->policy); + return count; } -show_store_one(od, sampling_rate); -show_store_one(od, io_is_busy); -show_store_one(od, up_threshold); -show_store_one(od, sampling_down_factor); -show_store_one(od, ignore_nice_load); -show_store_one(od, powersave_bias); -declare_show_sampling_rate_min(od); - -gov_sys_pol_attr_rw(sampling_rate); -gov_sys_pol_attr_rw(io_is_busy); -gov_sys_pol_attr_rw(up_threshold); -gov_sys_pol_attr_rw(sampling_down_factor); -gov_sys_pol_attr_rw(ignore_nice_load); -gov_sys_pol_attr_rw(powersave_bias); -gov_sys_pol_attr_ro(sampling_rate_min); - -static struct attribute *dbs_attributes_gov_sys[] = { - &sampling_rate_min_gov_sys.attr, - &sampling_rate_gov_sys.attr, - &up_threshold_gov_sys.attr, - &sampling_down_factor_gov_sys.attr, - &ignore_nice_load_gov_sys.attr, - &powersave_bias_gov_sys.attr, - &io_is_busy_gov_sys.attr, +gov_show_one_common(sampling_rate); +gov_show_one_common(up_threshold); +gov_show_one_common(sampling_down_factor); +gov_show_one_common(ignore_nice_load); +gov_show_one_common(min_sampling_rate); +gov_show_one_common(io_is_busy); +gov_show_one(od, powersave_bias); + +gov_attr_rw(sampling_rate); +gov_attr_rw(io_is_busy); +gov_attr_rw(up_threshold); +gov_attr_rw(sampling_down_factor); +gov_attr_rw(ignore_nice_load); +gov_attr_rw(powersave_bias); +gov_attr_ro(min_sampling_rate); + +static struct attribute *od_attributes[] = { + &min_sampling_rate.attr, + &sampling_rate.attr, + &up_threshold.attr, + &sampling_down_factor.attr, + &ignore_nice_load.attr, + &powersave_bias.attr, + &io_is_busy.attr, NULL }; -static struct attribute_group od_attr_group_gov_sys = { - .attrs = dbs_attributes_gov_sys, - .name = "ondemand", -}; +/************************** sysfs end ************************/ -static struct attribute *dbs_attributes_gov_pol[] = { - &sampling_rate_min_gov_pol.attr, - &sampling_rate_gov_pol.attr, - &up_threshold_gov_pol.attr, - &sampling_down_factor_gov_pol.attr, - &ignore_nice_load_gov_pol.attr, - &powersave_bias_gov_pol.attr, - &io_is_busy_gov_pol.attr, - NULL -}; +static struct policy_dbs_info *od_alloc(void) +{ + struct od_policy_dbs_info *dbs_info; -static struct attribute_group od_attr_group_gov_pol = { - .attrs = dbs_attributes_gov_pol, - .name = "ondemand", -}; + dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL); + return dbs_info ? &dbs_info->policy_dbs : NULL; +} -/************************** sysfs end ************************/ +static void od_free(struct policy_dbs_info *policy_dbs) +{ + kfree(to_dbs_info(policy_dbs)); +} static int od_init(struct dbs_data *dbs_data, bool notify) { @@ -503,7 +373,7 @@ static int od_init(struct dbs_data *dbs_data, bool notify) put_cpu(); if (idle_time != -1ULL) { /* Idle micro accounting is supported. Use finer thresholds */ - tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD; + dbs_data->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD; /* * In nohz/micro accounting case we set the minimum frequency * not depending on HZ, but fixed (very low). The deferred @@ -511,17 +381,17 @@ static int od_init(struct dbs_data *dbs_data, bool notify) */ dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE; } else { - tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD; + dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD; /* For correct statistics, we need 10 ticks for each measure */ dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10); } - tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR; - tuners->ignore_nice_load = 0; + dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR; + dbs_data->ignore_nice_load = 0; tuners->powersave_bias = default_powersave_bias; - tuners->io_is_busy = should_io_be_busy(); + dbs_data->io_is_busy = should_io_be_busy(); dbs_data->tuners = tuners; return 0; @@ -532,33 +402,38 @@ static void od_exit(struct dbs_data *dbs_data, bool notify) kfree(dbs_data->tuners); } -define_get_cpu_dbs_routines(od_cpu_dbs_info); +static void od_start(struct cpufreq_policy *policy) +{ + struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data); + + dbs_info->sample_type = OD_NORMAL_SAMPLE; + ondemand_powersave_bias_init(policy); +} static struct od_ops od_ops = { - .powersave_bias_init_cpu = ondemand_powersave_bias_init_cpu, .powersave_bias_target = generic_powersave_bias_target, - .freq_increase = dbs_freq_increase, }; -static struct common_dbs_data od_dbs_cdata = { - .governor = GOV_ONDEMAND, - .attr_group_gov_sys = &od_attr_group_gov_sys, - .attr_group_gov_pol = &od_attr_group_gov_pol, - .get_cpu_cdbs = get_cpu_cdbs, - .get_cpu_dbs_info_s = get_cpu_dbs_info_s, +static struct dbs_governor od_dbs_gov = { + .gov = { + .name = "ondemand", + .governor = cpufreq_governor_dbs, + .max_transition_latency = TRANSITION_LATENCY_LIMIT, + .owner = THIS_MODULE, + }, + .kobj_type = { .default_attrs = od_attributes }, .gov_dbs_timer = od_dbs_timer, - .gov_check_cpu = od_check_cpu, - .gov_ops = &od_ops, + .alloc = od_alloc, + .free = od_free, .init = od_init, .exit = od_exit, - .mutex = __MUTEX_INITIALIZER(od_dbs_cdata.mutex), + .start = od_start, }; +#define CPU_FREQ_GOV_ONDEMAND (&od_dbs_gov.gov) + static void od_set_powersave_bias(unsigned int powersave_bias) { - struct cpufreq_policy *policy; - struct dbs_data *dbs_data; - struct od_dbs_tuners *od_tuners; unsigned int cpu; cpumask_t done; @@ -567,22 +442,25 @@ static void od_set_powersave_bias(unsigned int powersave_bias) get_online_cpus(); for_each_online_cpu(cpu) { - struct cpu_common_dbs_info *shared; + struct cpufreq_policy *policy; + struct policy_dbs_info *policy_dbs; + struct dbs_data *dbs_data; + struct od_dbs_tuners *od_tuners; if (cpumask_test_cpu(cpu, &done)) continue; - shared = per_cpu(od_cpu_dbs_info, cpu).cdbs.shared; - if (!shared) + policy = cpufreq_cpu_get_raw(cpu); + if (!policy || policy->governor != CPU_FREQ_GOV_ONDEMAND) continue; - policy = shared->policy; - cpumask_or(&done, &done, policy->cpus); - - if (policy->governor != &cpufreq_gov_ondemand) + policy_dbs = policy->governor_data; + if (!policy_dbs) continue; - dbs_data = policy->governor_data; + cpumask_or(&done, &done, policy->cpus); + + dbs_data = policy_dbs->dbs_data; od_tuners = dbs_data->tuners; od_tuners->powersave_bias = default_powersave_bias; } @@ -605,30 +483,14 @@ void od_unregister_powersave_bias_handler(void) } EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler); -static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy, - unsigned int event) -{ - return cpufreq_governor_dbs(policy, &od_dbs_cdata, event); -} - -#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND -static -#endif -struct cpufreq_governor cpufreq_gov_ondemand = { - .name = "ondemand", - .governor = od_cpufreq_governor_dbs, - .max_transition_latency = TRANSITION_LATENCY_LIMIT, - .owner = THIS_MODULE, -}; - static int __init cpufreq_gov_dbs_init(void) { - return cpufreq_register_governor(&cpufreq_gov_ondemand); + return cpufreq_register_governor(CPU_FREQ_GOV_ONDEMAND); } static void __exit cpufreq_gov_dbs_exit(void) { - cpufreq_unregister_governor(&cpufreq_gov_ondemand); + cpufreq_unregister_governor(CPU_FREQ_GOV_ONDEMAND); } MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>"); @@ -638,6 +500,11 @@ MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for " MODULE_LICENSE("GPL"); #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND +struct cpufreq_governor *cpufreq_default_governor(void) +{ + return CPU_FREQ_GOV_ONDEMAND; +} + fs_initcall(cpufreq_gov_dbs_init); #else module_init(cpufreq_gov_dbs_init); diff --git a/drivers/cpufreq/cpufreq_ondemand.h b/drivers/cpufreq/cpufreq_ondemand.h new file mode 100644 index 000000000000..f0121db3cd9e --- /dev/null +++ b/drivers/cpufreq/cpufreq_ondemand.h @@ -0,0 +1,30 @@ +/* + * Header file for CPUFreq ondemand governor and related code. + * + * Copyright (C) 2016, Intel Corporation + * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "cpufreq_governor.h" + +struct od_policy_dbs_info { + struct policy_dbs_info policy_dbs; + struct cpufreq_frequency_table *freq_table; + unsigned int freq_lo; + unsigned int freq_lo_delay_us; + unsigned int freq_hi_delay_us; + unsigned int sample_type:1; +}; + +static inline struct od_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs) +{ + return container_of(policy_dbs, struct od_policy_dbs_info, policy_dbs); +} + +struct od_dbs_tuners { + unsigned int powersave_bias; +}; diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index cf117deb39b1..af9f4b96f5a8 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -33,10 +33,7 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy, return 0; } -#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE -static -#endif -struct cpufreq_governor cpufreq_gov_performance = { +static struct cpufreq_governor cpufreq_gov_performance = { .name = "performance", .governor = cpufreq_governor_performance, .owner = THIS_MODULE, @@ -52,6 +49,19 @@ static void __exit cpufreq_gov_performance_exit(void) cpufreq_unregister_governor(&cpufreq_gov_performance); } +#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE +struct cpufreq_governor *cpufreq_default_governor(void) +{ + return &cpufreq_gov_performance; +} +#endif +#ifndef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE +struct cpufreq_governor *cpufreq_fallback_governor(void) +{ + return &cpufreq_gov_performance; +} +#endif + MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); MODULE_DESCRIPTION("CPUfreq policy governor 'performance'"); MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index e3b874c235ea..b8b400232a74 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -33,10 +33,7 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy, return 0; } -#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE -static -#endif -struct cpufreq_governor cpufreq_gov_powersave = { +static struct cpufreq_governor cpufreq_gov_powersave = { .name = "powersave", .governor = cpufreq_governor_powersave, .owner = THIS_MODULE, @@ -57,6 +54,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'"); MODULE_LICENSE("GPL"); #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE +struct cpufreq_governor *cpufreq_default_governor(void) +{ + return &cpufreq_gov_powersave; +} + fs_initcall(cpufreq_gov_powersave_init); #else module_init(cpufreq_gov_powersave_init); diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c index 4dbf1db16aca..4d16f45ee1da 100644 --- a/drivers/cpufreq/cpufreq_userspace.c +++ b/drivers/cpufreq/cpufreq_userspace.c @@ -89,10 +89,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, return rc; } -#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE -static -#endif -struct cpufreq_governor cpufreq_gov_userspace = { +static struct cpufreq_governor cpufreq_gov_userspace = { .name = "userspace", .governor = cpufreq_governor_userspace, .store_setspeed = cpufreq_set, @@ -116,6 +113,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'userspace'"); MODULE_LICENSE("GPL"); #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE +struct cpufreq_governor *cpufreq_default_governor(void) +{ + return &cpufreq_gov_userspace; +} + fs_initcall(cpufreq_gov_userspace_init); #else module_init(cpufreq_gov_userspace_init); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index cd83d477e32d..cb5607495816 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -71,7 +71,7 @@ struct sample { u64 mperf; u64 tsc; int freq; - ktime_t time; + u64 time; }; struct pstate_data { @@ -103,13 +103,13 @@ struct _pid { struct cpudata { int cpu; - struct timer_list timer; + struct update_util_data update_util; struct pstate_data pstate; struct vid_data vid; struct _pid pid; - ktime_t last_sample_time; + u64 last_sample_time; u64 prev_aperf; u64 prev_mperf; u64 prev_tsc; @@ -120,6 +120,7 @@ struct cpudata { static struct cpudata **all_cpu_data; struct pstate_adjust_policy { int sample_rate_ms; + s64 sample_rate_ns; int deadband; int setpoint; int p_gain_pct; @@ -197,8 +198,8 @@ static struct perf_limits *limits = &powersave_limits; static inline void pid_reset(struct _pid *pid, int setpoint, int busy, int deadband, int integral) { - pid->setpoint = setpoint; - pid->deadband = deadband; + pid->setpoint = int_tofp(setpoint); + pid->deadband = int_tofp(deadband); pid->integral = int_tofp(integral); pid->last_err = int_tofp(setpoint) - int_tofp(busy); } @@ -224,9 +225,9 @@ static signed int pid_calc(struct _pid *pid, int32_t busy) int32_t pterm, dterm, fp_error; int32_t integral_limit; - fp_error = int_tofp(pid->setpoint) - busy; + fp_error = pid->setpoint - busy; - if (abs(fp_error) <= int_tofp(pid->deadband)) + if (abs(fp_error) <= pid->deadband) return 0; pterm = mul_fp(pid->p_gain, fp_error); @@ -286,7 +287,7 @@ static inline void update_turbo_state(void) cpu->pstate.max_pstate == cpu->pstate.turbo_pstate); } -static void intel_pstate_hwp_set(void) +static void intel_pstate_hwp_set(const struct cpumask *cpumask) { int min, hw_min, max, hw_max, cpu, range, adj_range; u64 value, cap; @@ -296,9 +297,7 @@ static void intel_pstate_hwp_set(void) hw_max = HWP_HIGHEST_PERF(cap); range = hw_max - hw_min; - get_online_cpus(); - - for_each_online_cpu(cpu) { + for_each_cpu(cpu, cpumask) { rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); adj_range = limits->min_perf_pct * range / 100; min = hw_min + adj_range; @@ -317,7 +316,12 @@ static void intel_pstate_hwp_set(void) value |= HWP_MAX_PERF(max); wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } +} +static void intel_pstate_hwp_set_online_cpus(void) +{ + get_online_cpus(); + intel_pstate_hwp_set(cpu_online_mask); put_online_cpus(); } @@ -439,7 +443,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, limits->no_turbo = clamp_t(int, input, 0, 1); if (hwp_active) - intel_pstate_hwp_set(); + intel_pstate_hwp_set_online_cpus(); return count; } @@ -465,7 +469,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, int_tofp(100)); if (hwp_active) - intel_pstate_hwp_set(); + intel_pstate_hwp_set_online_cpus(); return count; } @@ -490,7 +494,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, int_tofp(100)); if (hwp_active) - intel_pstate_hwp_set(); + intel_pstate_hwp_set_online_cpus(); return count; } @@ -531,6 +535,9 @@ static void __init intel_pstate_sysfs_expose_params(void) static void intel_pstate_hwp_enable(struct cpudata *cpudata) { + /* First disable HWP notification interrupt as we don't process them */ + wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); + wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); } @@ -712,7 +719,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate) if (limits->no_turbo && !limits->turbo_disabled) val |= (u64)1 << 32; - wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val); + wrmsrl(MSR_IA32_PERF_CTL, val); } static int knl_get_turbo_pstate(void) @@ -824,11 +831,11 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) * policy, or by cpu specific default values determined through * experimentation. */ - max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf)); + max_perf_adj = fp_toint(max_perf * limits->max_perf); *max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); - min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf)); + min_perf = fp_toint(max_perf * limits->min_perf); *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf); } @@ -874,16 +881,10 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu) core_pct = int_tofp(sample->aperf) * int_tofp(100); core_pct = div64_u64(core_pct, int_tofp(sample->mperf)); - sample->freq = fp_toint( - mul_fp(int_tofp( - cpu->pstate.max_pstate_physical * - cpu->pstate.scaling / 100), - core_pct)); - sample->core_pct_busy = (int32_t)core_pct; } -static inline void intel_pstate_sample(struct cpudata *cpu) +static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time) { u64 aperf, mperf; unsigned long flags; @@ -893,14 +894,14 @@ static inline void intel_pstate_sample(struct cpudata *cpu) rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); tsc = rdtsc(); - if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) { + if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) { local_irq_restore(flags); - return; + return false; } local_irq_restore(flags); cpu->last_sample_time = cpu->sample.time; - cpu->sample.time = ktime_get(); + cpu->sample.time = time; cpu->sample.aperf = aperf; cpu->sample.mperf = mperf; cpu->sample.tsc = tsc; @@ -908,27 +909,16 @@ static inline void intel_pstate_sample(struct cpudata *cpu) cpu->sample.mperf -= cpu->prev_mperf; cpu->sample.tsc -= cpu->prev_tsc; - intel_pstate_calc_busy(cpu); - cpu->prev_aperf = aperf; cpu->prev_mperf = mperf; cpu->prev_tsc = tsc; + return true; } -static inline void intel_hwp_set_sample_time(struct cpudata *cpu) -{ - int delay; - - delay = msecs_to_jiffies(50); - mod_timer_pinned(&cpu->timer, jiffies + delay); -} - -static inline void intel_pstate_set_sample_time(struct cpudata *cpu) +static inline int32_t get_avg_frequency(struct cpudata *cpu) { - int delay; - - delay = msecs_to_jiffies(pid_params.sample_rate_ms); - mod_timer_pinned(&cpu->timer, jiffies + delay); + return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf * + cpu->pstate.scaling, cpu->sample.mperf); } static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) @@ -954,7 +944,6 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) mperf = cpu->sample.mperf + delta_iowait_mperf; cpu->prev_cummulative_iowait = cummulative_iowait; - /* * The load can be estimated as the ratio of the mperf counter * running at a constant frequency during active periods @@ -970,8 +959,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) { int32_t core_busy, max_pstate, current_pstate, sample_ratio; - s64 duration_us; - u32 sample_time; + u64 duration_ns; + + intel_pstate_calc_busy(cpu); /* * core_busy is the ratio of actual performance to max @@ -990,18 +980,16 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); /* - * Since we have a deferred timer, it will not fire unless - * we are in C0. So, determine if the actual elapsed time - * is significantly greater (3x) than our sample interval. If it - * is, then we were idle for a long enough period of time - * to adjust our busyness. + * Since our utilization update callback will not run unless we are + * in C0, check if the actual elapsed time is significantly greater (3x) + * than our sample interval. If it is, then we were idle for a long + * enough period of time to adjust our busyness. */ - sample_time = pid_params.sample_rate_ms * USEC_PER_MSEC; - duration_us = ktime_us_delta(cpu->sample.time, - cpu->last_sample_time); - if (duration_us > sample_time * 3) { - sample_ratio = div_fp(int_tofp(sample_time), - int_tofp(duration_us)); + duration_ns = cpu->sample.time - cpu->last_sample_time; + if ((s64)duration_ns > pid_params.sample_rate_ns * 3 + && cpu->last_sample_time > 0) { + sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns), + int_tofp(duration_ns)); core_busy = mul_fp(core_busy, sample_ratio); } @@ -1028,26 +1016,21 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) sample->mperf, sample->aperf, sample->tsc, - sample->freq); + get_avg_frequency(cpu)); } -static void intel_hwp_timer_func(unsigned long __data) +static void intel_pstate_update_util(struct update_util_data *data, u64 time, + unsigned long util, unsigned long max) { - struct cpudata *cpu = (struct cpudata *) __data; + struct cpudata *cpu = container_of(data, struct cpudata, update_util); + u64 delta_ns = time - cpu->sample.time; - intel_pstate_sample(cpu); - intel_hwp_set_sample_time(cpu); -} + if ((s64)delta_ns >= pid_params.sample_rate_ns) { + bool sample_taken = intel_pstate_sample(cpu, time); -static void intel_pstate_timer_func(unsigned long __data) -{ - struct cpudata *cpu = (struct cpudata *) __data; - - intel_pstate_sample(cpu); - - intel_pstate_adjust_busy_pstate(cpu); - - intel_pstate_set_sample_time(cpu); + if (sample_taken && !hwp_active) + intel_pstate_adjust_busy_pstate(cpu); + } } #define ICPU(model, policy) \ @@ -1095,24 +1078,19 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu->cpu = cpunum; - if (hwp_active) + if (hwp_active) { intel_pstate_hwp_enable(cpu); + pid_params.sample_rate_ms = 50; + pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC; + } intel_pstate_get_cpu_pstates(cpu); - init_timer_deferrable(&cpu->timer); - cpu->timer.data = (unsigned long)cpu; - cpu->timer.expires = jiffies + HZ/100; - - if (!hwp_active) - cpu->timer.function = intel_pstate_timer_func; - else - cpu->timer.function = intel_hwp_timer_func; - intel_pstate_busy_pid_reset(cpu); - intel_pstate_sample(cpu); + intel_pstate_sample(cpu, 0); - add_timer_on(&cpu->timer, cpunum); + cpu->update_util.func = intel_pstate_update_util; + cpufreq_set_update_util_data(cpunum, &cpu->update_util); pr_debug("intel_pstate: controlling: cpu %d\n", cpunum); @@ -1128,7 +1106,7 @@ static unsigned int intel_pstate_get(unsigned int cpu_num) if (!cpu) return 0; sample = &cpu->sample; - return sample->freq; + return get_avg_frequency(cpu); } static int intel_pstate_set_policy(struct cpufreq_policy *policy) @@ -1141,7 +1119,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) pr_debug("intel_pstate: set performance\n"); limits = &performance_limits; if (hwp_active) - intel_pstate_hwp_set(); + intel_pstate_hwp_set(policy->cpus); return 0; } @@ -1173,7 +1151,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) int_tofp(100)); if (hwp_active) - intel_pstate_hwp_set(); + intel_pstate_hwp_set(policy->cpus); return 0; } @@ -1196,7 +1174,9 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) pr_debug("intel_pstate: CPU %d exiting\n", cpu_num); - del_timer_sync(&all_cpu_data[cpu_num]->timer); + cpufreq_set_update_util_data(cpu_num, NULL); + synchronize_sched(); + if (hwp_active) return; @@ -1260,6 +1240,7 @@ static int intel_pstate_msrs_not_valid(void) static void copy_pid_params(struct pstate_adjust_policy *policy) { pid_params.sample_rate_ms = policy->sample_rate_ms; + pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC; pid_params.p_gain_pct = policy->p_gain_pct; pid_params.i_gain_pct = policy->i_gain_pct; pid_params.d_gain_pct = policy->d_gain_pct; @@ -1397,6 +1378,11 @@ static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; } static inline bool intel_pstate_has_acpi_ppc(void) { return false; } #endif /* CONFIG_ACPI */ +static const struct x86_cpu_id hwp_support_ids[] __initconst = { + { X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP }, + {} +}; + static int __init intel_pstate_init(void) { int cpu, rc = 0; @@ -1406,17 +1392,16 @@ static int __init intel_pstate_init(void) if (no_load) return -ENODEV; + if (x86_match_cpu(hwp_support_ids) && !no_hwp) { + copy_cpu_funcs(&core_params.funcs); + hwp_active++; + goto hwp_cpu_matched; + } + id = x86_match_cpu(intel_pstate_cpu_ids); if (!id) return -ENODEV; - /* - * The Intel pstate driver will be ignored if the platform - * firmware has its own power management modes. - */ - if (intel_pstate_platform_pwr_mgmt_exists()) - return -ENODEV; - cpu_def = (struct cpu_defaults *)id->driver_data; copy_pid_params(&cpu_def->pid_policy); @@ -1425,17 +1410,20 @@ static int __init intel_pstate_init(void) if (intel_pstate_msrs_not_valid()) return -ENODEV; +hwp_cpu_matched: + /* + * The Intel pstate driver will be ignored if the platform + * firmware has its own power management modes. + */ + if (intel_pstate_platform_pwr_mgmt_exists()) + return -ENODEV; + pr_info("Intel P-state driver initializing.\n"); all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus()); if (!all_cpu_data) return -ENOMEM; - if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) { - pr_info("intel_pstate: HWP enabled\n"); - hwp_active++; - } - if (!hwp_active && hwp_only) goto out; @@ -1446,12 +1434,16 @@ static int __init intel_pstate_init(void) intel_pstate_debug_expose_params(); intel_pstate_sysfs_expose_params(); + if (hwp_active) + pr_info("intel_pstate: HWP enabled\n"); + return rc; out: get_online_cpus(); for_each_online_cpu(cpu) { if (all_cpu_data[cpu]) { - del_timer_sync(&all_cpu_data[cpu]->timer); + cpufreq_set_update_util_data(cpu, NULL); + synchronize_sched(); kfree(all_cpu_data[cpu]); } } diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 547890fd9572..50bf12033bbc 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -28,6 +28,8 @@ #include <linux/of.h> #include <linux/reboot.h> #include <linux/slab.h> +#include <linux/cpu.h> +#include <trace/events/power.h> #include <asm/cputhreads.h> #include <asm/firmware.h> @@ -42,13 +44,24 @@ static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1]; static bool rebooting, throttled, occ_reset; +static unsigned int *core_to_chip_map; + +static const char * const throttle_reason[] = { + "No throttling", + "Power Cap", + "Processor Over Temperature", + "Power Supply Failure", + "Over Current", + "OCC Reset" +}; static struct chip { unsigned int id; bool throttled; + bool restore; + u8 throttle_reason; cpumask_t mask; struct work_struct throttle; - bool restore; } *chips; static int nr_chips; @@ -312,13 +325,14 @@ static inline unsigned int get_nominal_index(void) static void powernv_cpufreq_throttle_check(void *data) { unsigned int cpu = smp_processor_id(); + unsigned int chip_id = core_to_chip_map[cpu_core_index_of_thread(cpu)]; unsigned long pmsr; int pmsr_pmax, i; pmsr = get_pmspr(SPRN_PMSR); for (i = 0; i < nr_chips; i++) - if (chips[i].id == cpu_to_chip_id(cpu)) + if (chips[i].id == chip_id) break; /* Check for Pmax Capping */ @@ -328,17 +342,17 @@ static void powernv_cpufreq_throttle_check(void *data) goto next; chips[i].throttled = true; if (pmsr_pmax < powernv_pstate_info.nominal) - pr_crit("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n", - cpu, chips[i].id, pmsr_pmax, - powernv_pstate_info.nominal); - else - pr_info("CPU %d on Chip %u has Pmax reduced below turbo frequency (%d < %d)\n", - cpu, chips[i].id, pmsr_pmax, - powernv_pstate_info.max); + pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n", + cpu, chips[i].id, pmsr_pmax, + powernv_pstate_info.nominal); + trace_powernv_throttle(chips[i].id, + throttle_reason[chips[i].throttle_reason], + pmsr_pmax); } else if (chips[i].throttled) { chips[i].throttled = false; - pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu, - chips[i].id, pmsr_pmax); + trace_powernv_throttle(chips[i].id, + throttle_reason[chips[i].throttle_reason], + pmsr_pmax); } /* Check if Psafe_mode_active is set in PMSR. */ @@ -356,7 +370,7 @@ next: if (throttled) { pr_info("PMSR = %16lx\n", pmsr); - pr_crit("CPU Frequency could be throttled\n"); + pr_warn("CPU Frequency could be throttled\n"); } } @@ -423,18 +437,19 @@ void powernv_cpufreq_work_fn(struct work_struct *work) { struct chip *chip = container_of(work, struct chip, throttle); unsigned int cpu; - cpumask_var_t mask; + cpumask_t mask; - smp_call_function_any(&chip->mask, + get_online_cpus(); + cpumask_and(&mask, &chip->mask, cpu_online_mask); + smp_call_function_any(&mask, powernv_cpufreq_throttle_check, NULL, 0); if (!chip->restore) - return; + goto out; chip->restore = false; - cpumask_copy(mask, &chip->mask); - for_each_cpu_and(cpu, mask, cpu_online_mask) { - int index, tcpu; + for_each_cpu(cpu, &mask) { + int index; struct cpufreq_policy policy; cpufreq_get_policy(&policy, cpu); @@ -442,20 +457,12 @@ void powernv_cpufreq_work_fn(struct work_struct *work) policy.cur, CPUFREQ_RELATION_C, &index); powernv_cpufreq_target_index(&policy, index); - for_each_cpu(tcpu, policy.cpus) - cpumask_clear_cpu(tcpu, mask); + cpumask_andnot(&mask, &mask, policy.cpus); } +out: + put_online_cpus(); } -static char throttle_reason[][30] = { - "No throttling", - "Power Cap", - "Processor Over Temperature", - "Power Supply Failure", - "Over Current", - "OCC Reset" - }; - static int powernv_cpufreq_occ_msg(struct notifier_block *nb, unsigned long msg_type, void *_msg) { @@ -481,7 +488,7 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb, */ if (!throttled) { throttled = true; - pr_crit("CPU frequency is throttled for duration\n"); + pr_warn("CPU frequency is throttled for duration\n"); } break; @@ -505,23 +512,18 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb, return 0; } - if (omsg.throttle_status && + for (i = 0; i < nr_chips; i++) + if (chips[i].id == omsg.chip) + break; + + if (omsg.throttle_status >= 0 && omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS) - pr_info("OCC: Chip %u Pmax reduced due to %s\n", - (unsigned int)omsg.chip, - throttle_reason[omsg.throttle_status]); - else if (!omsg.throttle_status) - pr_info("OCC: Chip %u %s\n", (unsigned int)omsg.chip, - throttle_reason[omsg.throttle_status]); - else - return 0; + chips[i].throttle_reason = omsg.throttle_status; - for (i = 0; i < nr_chips; i++) - if (chips[i].id == omsg.chip) { - if (!omsg.throttle_status) - chips[i].restore = true; - schedule_work(&chips[i].throttle); - } + if (!omsg.throttle_status) + chips[i].restore = true; + + schedule_work(&chips[i].throttle); } return 0; } @@ -556,29 +558,54 @@ static int init_chip_info(void) unsigned int chip[256]; unsigned int cpu, i; unsigned int prev_chip_id = UINT_MAX; + cpumask_t cpu_mask; + int ret = -ENOMEM; + + core_to_chip_map = kcalloc(cpu_nr_cores(), sizeof(unsigned int), + GFP_KERNEL); + if (!core_to_chip_map) + goto out; - for_each_possible_cpu(cpu) { + cpumask_copy(&cpu_mask, cpu_possible_mask); + for_each_cpu(cpu, &cpu_mask) { unsigned int id = cpu_to_chip_id(cpu); if (prev_chip_id != id) { prev_chip_id = id; chip[nr_chips++] = id; } + core_to_chip_map[cpu_core_index_of_thread(cpu)] = id; + cpumask_andnot(&cpu_mask, &cpu_mask, cpu_sibling_mask(cpu)); } - chips = kmalloc_array(nr_chips, sizeof(struct chip), GFP_KERNEL); + chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL); if (!chips) - return -ENOMEM; + goto free_chip_map; for (i = 0; i < nr_chips; i++) { chips[i].id = chip[i]; - chips[i].throttled = false; cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i])); INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn); - chips[i].restore = false; } return 0; +free_chip_map: + kfree(core_to_chip_map); +out: + return ret; +} + +static inline void clean_chip_info(void) +{ + kfree(chips); + kfree(core_to_chip_map); +} + +static inline void unregister_all_notifiers(void) +{ + opal_message_notifier_unregister(OPAL_MSG_OCC, + &powernv_cpufreq_opal_nb); + unregister_reboot_notifier(&powernv_cpufreq_reboot_nb); } static int __init powernv_cpufreq_init(void) @@ -591,28 +618,35 @@ static int __init powernv_cpufreq_init(void) /* Discover pstates from device tree and init */ rc = init_powernv_pstates(); - if (rc) { - pr_info("powernv-cpufreq disabled. System does not support PState control\n"); - return rc; - } + if (rc) + goto out; /* Populate chip info */ rc = init_chip_info(); if (rc) - return rc; + goto out; register_reboot_notifier(&powernv_cpufreq_reboot_nb); opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb); - return cpufreq_register_driver(&powernv_cpufreq_driver); + + rc = cpufreq_register_driver(&powernv_cpufreq_driver); + if (!rc) + return 0; + + pr_info("Failed to register the cpufreq driver (%d)\n", rc); + unregister_all_notifiers(); + clean_chip_info(); +out: + pr_info("Platform driver disabled. System does not support PState control\n"); + return rc; } module_init(powernv_cpufreq_init); static void __exit powernv_cpufreq_exit(void) { - unregister_reboot_notifier(&powernv_cpufreq_reboot_nb); - opal_message_notifier_unregister(OPAL_MSG_OCC, - &powernv_cpufreq_opal_nb); cpufreq_unregister_driver(&powernv_cpufreq_driver); + unregister_all_notifiers(); + clean_chip_info(); } module_exit(powernv_cpufreq_exit); diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 0742b3296673..27fc733cb5b9 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -199,8 +199,8 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); static void get_typical_interval(struct menu_device *data) { int i, divisor; - unsigned int max, thresh; - uint64_t avg, stddev; + unsigned int max, thresh, avg; + uint64_t sum, variance; thresh = UINT_MAX; /* Discard outliers above this value */ @@ -208,52 +208,51 @@ again: /* First calculate the average of past intervals */ max = 0; - avg = 0; + sum = 0; divisor = 0; for (i = 0; i < INTERVALS; i++) { unsigned int value = data->intervals[i]; if (value <= thresh) { - avg += value; + sum += value; divisor++; if (value > max) max = value; } } if (divisor == INTERVALS) - avg >>= INTERVAL_SHIFT; + avg = sum >> INTERVAL_SHIFT; else - do_div(avg, divisor); + avg = div_u64(sum, divisor); - /* Then try to determine standard deviation */ - stddev = 0; + /* Then try to determine variance */ + variance = 0; for (i = 0; i < INTERVALS; i++) { unsigned int value = data->intervals[i]; if (value <= thresh) { - int64_t diff = value - avg; - stddev += diff * diff; + int64_t diff = (int64_t)value - avg; + variance += diff * diff; } } if (divisor == INTERVALS) - stddev >>= INTERVAL_SHIFT; + variance >>= INTERVAL_SHIFT; else - do_div(stddev, divisor); + do_div(variance, divisor); /* - * The typical interval is obtained when standard deviation is small - * or standard deviation is small compared to the average interval. - * - * int_sqrt() formal parameter type is unsigned long. When the - * greatest difference to an outlier exceeds ~65 ms * sqrt(divisor) - * the resulting squared standard deviation exceeds the input domain - * of int_sqrt on platforms where unsigned long is 32 bits in size. - * In such case reject the candidate average. + * The typical interval is obtained when standard deviation is + * small (stddev <= 20 us, variance <= 400 us^2) or standard + * deviation is small compared to the average interval (avg > + * 6*stddev, avg^2 > 36*variance). The average is smaller than + * UINT_MAX aka U32_MAX, so computing its square does not + * overflow a u64. We simply reject this candidate average if + * the standard deviation is greater than 715 s (which is + * rather unlikely). * * Use this result only if there is no timer to wake us up sooner. */ - if (likely(stddev <= ULONG_MAX)) { - stddev = int_sqrt(stddev); - if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3)) - || stddev <= 20) { + if (likely(variance <= U64_MAX/36)) { + if ((((u64)avg*avg > variance*36) && (divisor * 4 >= INTERVALS * 3)) + || variance <= 400) { if (data->next_timer_us > avg) data->predicted_us = avg; return; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 64f5d1bdbb48..8e304b1befc5 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -176,6 +176,7 @@ #define AT_XDMAC_MAX_CHAN 0x20 #define AT_XDMAC_MAX_CSIZE 16 /* 16 data */ #define AT_XDMAC_MAX_DWIDTH 8 /* 64 bits */ +#define AT_XDMAC_RESIDUE_MAX_RETRIES 5 #define AT_XDMAC_DMA_BUSWIDTHS\ (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\ @@ -1395,8 +1396,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, struct at_xdmac_desc *desc, *_desc; struct list_head *descs_list; enum dma_status ret; - int residue; - u32 cur_nda, mask, value; + int residue, retry; + u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; @@ -1433,7 +1434,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, cpu_relax(); } + /* + * When processing the residue, we need to read two registers but we + * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where + * we stand in the descriptor list and AT_XDMAC_CUBC is used + * to know how many data are remaining for the current descriptor. + * Since the dma channel is not paused to not loose data, between the + * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of + * descriptor. + * For that reason, after reading AT_XDMAC_CUBC, we check if we are + * still using the same descriptor by reading a second time + * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to + * read again AT_XDMAC_CUBC. + * Memory barriers are used to ensure the read order of the registers. + * A max number of retries is set because unlikely it can never ends if + * we are transferring a lot of data with small buffers. + */ cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { + rmb(); + check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + + if (likely(cur_nda == check_nda)) + break; + + cur_nda = check_nda; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + } + + if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { + ret = DMA_ERROR; + goto spin_unlock; + } + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current @@ -1446,7 +1482,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) break; } - residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth; + residue += cur_ubc << dwidth; dma_set_residue(txstate, residue); diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 2209f75fdf05..aac85c30c2cf 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -522,6 +522,8 @@ static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan, chan_dbg(chan, "LD %p callback\n", desc); txd->callback(txd->callback_param); } + + dma_descriptor_unmap(txd); } /* Run any dependencies */ diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index e438ee5b433f..f5c6b97c8958 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -1574,7 +1574,7 @@ static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes) for (cha = 0; cha < KNL_MAX_CHAS; cha++) { if (knl_get_mc_route(target, mc_route_reg[cha]) == channel - && participants[channel]) { + && !participants[channel]) { participant_count++; participants[channel] = 1; break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 8297bc319369..1846d65b7285 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - while (amdgpuCrtc->enabled && repcnt--) { + while (amdgpuCrtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -112,13 +112,13 @@ static void amdgpu_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); if (min_udelay > vblank->framedur_ns / 2000) { /* Don't wait ridiculously long - something is wrong */ repcnt = 0; break; } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c index 21aacc1f45c1..bf731e9f643e 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c @@ -265,15 +265,27 @@ static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector unsigned max_lane_num = drm_dp_max_lane_count(dpcd); unsigned lane_num, i, max_pix_clock; - for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { - for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { - max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector) == + ENCODER_OBJECT_ID_NUTMEG) { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + max_pix_clock = (lane_num * 270000 * 8) / bpp; if (max_pix_clock >= pix_clock) { *dp_lanes = lane_num; - *dp_rate = link_rates[i]; + *dp_rate = 270000; return 0; } } + } else { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (max_pix_clock >= pix_clock) { + *dp_lanes = lane_num; + *dp_rate = link_rates[i]; + return 0; + } + } + } } return -EINVAL; diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 34e38749a817..f8ee740c0e26 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1382,8 +1382,16 @@ static void tda998x_connector_destroy(struct drm_connector *connector) drm_connector_cleanup(connector); } +static int tda998x_connector_dpms(struct drm_connector *connector, int mode) +{ + if (drm_core_check_feature(connector->dev, DRIVER_ATOMIC)) + return drm_atomic_helper_connector_dpms(connector, mode); + else + return drm_helper_connector_dpms(connector, mode); +} + static const struct drm_connector_funcs tda998x_connector_funcs = { - .dpms = drm_atomic_helper_connector_dpms, + .dpms = tda998x_connector_dpms, .reset = drm_atomic_helper_connector_reset, .fill_modes = drm_helper_probe_single_connector_modes, .detect = tda998x_connector_detect, diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 31f6d212fb1b..30f921421b0c 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -527,6 +527,8 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) mutex_lock(&dev_priv->av_mutex); intel_dig_port->audio_connector = connector; + /* referred in audio callbacks */ + dev_priv->dig_port_map[port] = intel_encoder; mutex_unlock(&dev_priv->av_mutex); if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) @@ -554,6 +556,7 @@ void intel_audio_codec_disable(struct intel_encoder *intel_encoder) mutex_lock(&dev_priv->av_mutex); intel_dig_port->audio_connector = NULL; + dev_priv->dig_port_map[port] = NULL; mutex_unlock(&dev_priv->av_mutex); if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 0f3df2c39f7c..084d5586585d 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -3358,7 +3358,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->get_config = intel_ddi_get_config; intel_dig_port->port = port; - dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & (DDI_BUF_PORT_REVERSAL | DDI_A_4_LANES); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 1d8de43bed56..cdc2c15873dc 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -6045,7 +6045,6 @@ intel_dp_init(struct drm_device *dev, } intel_dig_port->port = port; - dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->dp.output_reg = output_reg; intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index cb5d1b15755c..616108c4bc3e 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -2154,7 +2154,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, void intel_hdmi_init(struct drm_device *dev, i915_reg_t hdmi_reg, enum port port) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_digital_port *intel_dig_port; struct intel_encoder *intel_encoder; struct intel_connector *intel_connector; @@ -2223,7 +2222,6 @@ void intel_hdmi_init(struct drm_device *dev, intel_encoder->cloneable |= 1 << INTEL_OUTPUT_HDMI; intel_dig_port->port = port; - dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->hdmi.hdmi_reg = hdmi_reg; intel_dig_port->dp.output_reg = INVALID_MMIO_REG; diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index deb8282c26d8..52fbe530fc9e 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -664,6 +664,12 @@ int intel_setup_gmbus(struct drm_device *dev) bus->adapter.algo = &gmbus_algorithm; + /* + * We wish to retry with bit banging + * after a timed out GMBUS attempt. + */ + bus->adapter.retries = 1; + /* By default use a conservative clock rate */ bus->reg0 = pin | GMBUS_RATE_100KHZ; diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 30a57185bdb4..287226311413 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -64,6 +64,7 @@ static void ipu_fb_enable(struct ipu_crtc *ipu_crtc) /* Start DC channel and DI after IDMAC */ ipu_dc_enable_channel(ipu_crtc->dc); ipu_di_enable(ipu_crtc->di); + drm_crtc_vblank_on(&ipu_crtc->base); ipu_crtc->enabled = 1; } @@ -80,6 +81,7 @@ static void ipu_fb_disable(struct ipu_crtc *ipu_crtc) ipu_di_disable(ipu_crtc->di); ipu_plane_disable(ipu_crtc->plane[0]); ipu_dc_disable(ipu); + drm_crtc_vblank_off(&ipu_crtc->base); ipu_crtc->enabled = 0; } diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 591ba2f1ae03..26bb1b626fe3 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -42,6 +42,7 @@ static const uint32_t ipu_plane_formats[] = { DRM_FORMAT_YVYU, DRM_FORMAT_YUV420, DRM_FORMAT_YVU420, + DRM_FORMAT_RGB565, }; int ipu_plane_irq(struct ipu_plane *ipu_plane) diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 44ee72e04df9..6af832545bc5 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -315,15 +315,27 @@ int radeon_dp_get_dp_link_config(struct drm_connector *connector, unsigned max_lane_num = drm_dp_max_lane_count(dpcd); unsigned lane_num, i, max_pix_clock; - for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { - for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { - max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) == + ENCODER_OBJECT_ID_NUTMEG) { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + max_pix_clock = (lane_num * 270000 * 8) / bpp; if (max_pix_clock >= pix_clock) { *dp_lanes = lane_num; - *dp_rate = link_rates[i]; + *dp_rate = 270000; return 0; } } + } else { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (max_pix_clock >= pix_clock) { + *dp_lanes = lane_num; + *dp_rate = link_rates[i]; + return 0; + } + } + } } return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 902b59cebac5..4197ca1bb1e4 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1744,7 +1744,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); - drm_helper_hpd_irq_event(dev); /* set the power state here in case we are a PX system or headless */ if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 2b9ba03a7c1a..2d9196a447fd 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -455,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - while (radeon_crtc->enabled && repcnt--) { + while (radeon_crtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -471,13 +471,13 @@ static void radeon_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); if (min_udelay > vblank->framedur_ns / 2000) { /* Don't wait ridiculously long - something is wrong */ repcnt = 0; break; } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 0f14d897baf9..7a98823bacd1 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1079,6 +1079,8 @@ force: /* update display watermarks based on new power state */ radeon_bandwidth_update(rdev); + /* update displays */ + radeon_dpm_display_configuration_changed(rdev); /* wait for the rings to drain */ for (i = 0; i < RADEON_NUM_RINGS; i++) { @@ -1095,9 +1097,6 @@ force: radeon_dpm_post_set_power_state(rdev); - /* update displays */ - radeon_dpm_display_configuration_changed(rdev); - rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; rdev->pm.dpm.single_display = single_display; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index db082bea8daf..c5a1a08b0449 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -563,6 +563,8 @@ static void vmw_sou_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_sou_connector_funcs = { .dpms = vmw_du_connector_dpms, + .detect = vmw_du_connector_detect, + .fill_modes = vmw_du_connector_fill_modes, .set_property = vmw_du_connector_set_property, .destroy = vmw_sou_connector_destroy, }; diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index f2e13eb8339f..e00db3f510dd 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1050,6 +1050,17 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) for (i = 0; i < ARRAY_SIZE(client_reg); i++) { const struct ipu_platform_reg *reg = &client_reg[i]; struct platform_device *pdev; + struct device_node *of_node; + + /* Associate subdevice with the corresponding port node */ + of_node = of_graph_get_port_by_id(dev->of_node, i); + if (!of_node) { + dev_info(dev, + "no port@%d node in %s, not using %s%d\n", + i, dev->of_node->full_name, + (i / 2) ? "DI" : "CSI", i % 2); + continue; + } pdev = platform_device_alloc(reg->name, id++); if (!pdev) { @@ -1057,17 +1068,9 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) goto err_register; } + pdev->dev.of_node = of_node; pdev->dev.parent = dev; - /* Associate subdevice with the corresponding port node */ - pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i); - if (!pdev->dev.of_node) { - dev_err(dev, "missing port@%d node in %s\n", i, - dev->of_node->full_name); - ret = -ENODEV; - goto err_register; - } - ret = platform_device_add_data(pdev, ®->pdata, sizeof(reg->pdata)); if (!ret) @@ -1289,10 +1292,6 @@ static int ipu_probe(struct platform_device *pdev) ipu->irq_sync = irq_sync; ipu->irq_err = irq_err; - ret = ipu_irq_init(ipu); - if (ret) - goto out_failed_irq; - ret = device_reset(&pdev->dev); if (ret) { dev_err(&pdev->dev, "failed to reset: %d\n", ret); @@ -1302,6 +1301,10 @@ static int ipu_probe(struct platform_device *pdev) if (ret) goto out_failed_reset; + ret = ipu_irq_init(ipu); + if (ret) + goto out_failed_irq; + /* Set MCU_T to divide MCU access window into 2 */ ipu_cm_write(ipu, 0x00400000L | (IPU_MCU_T_DEFAULT << 18), IPU_DISP_GEN); @@ -1324,9 +1327,9 @@ static int ipu_probe(struct platform_device *pdev) failed_add_clients: ipu_submodules_exit(ipu); failed_submodules_init: -out_failed_reset: ipu_irq_exit(ipu); out_failed_irq: +out_failed_reset: clk_disable_unprepare(ipu->clk); return ret; } diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 438f1b4964c0..d656657b805c 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -123,6 +123,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = { { "80860F41", 0 }, { "808622C1", 0 }, { "AMD0010", ACCESS_INTR_MASK }, + { "AMDI0010", ACCESS_INTR_MASK }, { "AMDI0510", 0 }, { "APMC0D0F", 0 }, { } diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 8f779a1ec99c..0ddf638d60f3 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -63,6 +63,7 @@ #include <linux/platform_device.h> #include <linux/mailbox_controller.h> #include <linux/mailbox_client.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include "mailbox.h" @@ -70,6 +71,9 @@ static struct mbox_chan *pcc_mbox_channels; +/* Array of cached virtual address for doorbell registers */ +static void __iomem **pcc_doorbell_vaddr; + static struct mbox_controller pcc_mbox_ctrl = {}; /** * get_pcc_channel - Given a PCC subspace idx, get @@ -160,6 +164,66 @@ void pcc_mbox_free_channel(struct mbox_chan *chan) } EXPORT_SYMBOL_GPL(pcc_mbox_free_channel); +/* + * PCC can be used with perf critical drivers such as CPPC + * So it makes sense to locally cache the virtual address and + * use it to read/write to PCC registers such as doorbell register + * + * The below read_register and write_registers are used to read and + * write from perf critical registers such as PCC doorbell register + */ +static int read_register(void __iomem *vaddr, u64 *val, unsigned int bit_width) +{ + int ret_val = 0; + + switch (bit_width) { + case 8: + *val = readb(vaddr); + break; + case 16: + *val = readw(vaddr); + break; + case 32: + *val = readl(vaddr); + break; + case 64: + *val = readq(vaddr); + break; + default: + pr_debug("Error: Cannot read register of %u bit width", + bit_width); + ret_val = -EFAULT; + break; + } + return ret_val; +} + +static int write_register(void __iomem *vaddr, u64 val, unsigned int bit_width) +{ + int ret_val = 0; + + switch (bit_width) { + case 8: + writeb(val, vaddr); + break; + case 16: + writew(val, vaddr); + break; + case 32: + writel(val, vaddr); + break; + case 64: + writeq(val, vaddr); + break; + default: + pr_debug("Error: Cannot write register of %u bit width", + bit_width); + ret_val = -EFAULT; + break; + } + return ret_val; +} + /** * pcc_send_data - Called from Mailbox Controller code. Used * here only to ring the channel doorbell. The PCC client @@ -175,21 +239,39 @@ EXPORT_SYMBOL_GPL(pcc_mbox_free_channel); static int pcc_send_data(struct mbox_chan *chan, void *data) { struct acpi_pcct_hw_reduced *pcct_ss = chan->con_priv; - struct acpi_generic_address doorbell; + struct acpi_generic_address *doorbell; u64 doorbell_preserve; u64 doorbell_val; u64 doorbell_write; + u32 id = chan - pcc_mbox_channels; + int ret = 0; + + if (id >= pcc_mbox_ctrl.num_chans) { + pr_debug("pcc_send_data: Invalid mbox_chan passed\n"); + return -ENOENT; + } - doorbell = pcct_ss->doorbell_register; + doorbell = &pcct_ss->doorbell_register; doorbell_preserve = pcct_ss->preserve_mask; doorbell_write = pcct_ss->write_mask; /* Sync notification from OS to Platform. */ - acpi_read(&doorbell_val, &doorbell); - acpi_write((doorbell_val & doorbell_preserve) | doorbell_write, - &doorbell); - - return 0; + if (pcc_doorbell_vaddr[id]) { + ret = read_register(pcc_doorbell_vaddr[id], &doorbell_val, + doorbell->bit_width); + if (ret) + return ret; + ret = write_register(pcc_doorbell_vaddr[id], + (doorbell_val & doorbell_preserve) | doorbell_write, + doorbell->bit_width); + } else { + ret = acpi_read(&doorbell_val, doorbell); + if (ret) + return ret; + ret = acpi_write((doorbell_val & doorbell_preserve) | doorbell_write, + doorbell); + } + return ret; } static const struct mbox_chan_ops pcc_chan_ops = { @@ -265,14 +347,29 @@ static int __init acpi_pcc_probe(void) return -ENOMEM; } + pcc_doorbell_vaddr = kcalloc(count, sizeof(void *), GFP_KERNEL); + if (!pcc_doorbell_vaddr) { + kfree(pcc_mbox_channels); + return -ENOMEM; + } + /* Point to the first PCC subspace entry */ pcct_entry = (struct acpi_subtable_header *) ( (unsigned long) pcct_tbl + sizeof(struct acpi_table_pcct)); for (i = 0; i < count; i++) { + struct acpi_generic_address *db_reg; + struct acpi_pcct_hw_reduced *pcct_ss; pcc_mbox_channels[i].con_priv = pcct_entry; pcct_entry = (struct acpi_subtable_header *) ((unsigned long) pcct_entry + pcct_entry->length); + + /* If doorbell is in system memory cache the virt address */ + pcct_ss = (struct acpi_pcct_hw_reduced *)pcct_entry; + db_reg = &pcct_ss->doorbell_register; + if (db_reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + pcc_doorbell_vaddr[i] = acpi_os_ioremap(db_reg->address, + db_reg->bit_width/8); } pcc_mbox_ctrl.num_chans = count; diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 7dae0ac0f3ae..e9219f528d7e 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -20,6 +20,9 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +/* We need to access legacy defines from linux/media.h */ +#define __NEED_MEDIA_LEGACY_API + #include <linux/compat.h> #include <linux/export.h> #include <linux/idr.h> @@ -115,6 +118,26 @@ static long media_device_enum_entities(struct media_device *mdev, u_ent.group_id = 0; /* Unused */ u_ent.pads = ent->num_pads; u_ent.links = ent->num_links - ent->num_backlinks; + + /* + * Workaround for a bug at media-ctl <= v1.10 that makes it to + * do the wrong thing if the entity function doesn't belong to + * either MEDIA_ENT_F_OLD_BASE or MEDIA_ENT_F_OLD_SUBDEV_BASE + * Ranges. + * + * Non-subdevices are expected to be at the MEDIA_ENT_F_OLD_BASE, + * or, otherwise, will be silently ignored by media-ctl when + * printing the graphviz diagram. So, map them into the devnode + * old range. + */ + if (ent->function < MEDIA_ENT_F_OLD_BASE || + ent->function > MEDIA_ENT_T_DEVNODE_UNKNOWN) { + if (is_media_entity_v4l2_subdev(ent)) + u_ent.type = MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN; + else if (ent->function != MEDIA_ENT_F_IO_V4L) + u_ent.type = MEDIA_ENT_T_DEVNODE_UNKNOWN; + } + memcpy(&u_ent.raw, &ent->info, sizeof(ent->info)); if (copy_to_user(uent, &u_ent, sizeof(u_ent))) return -EFAULT; diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c index 79316159eec6..88b6c81cebbe 100644 --- a/drivers/mtd/tests/mtd_nandecctest.c +++ b/drivers/mtd/tests/mtd_nandecctest.c @@ -187,7 +187,7 @@ static int double_bit_error_detect(void *error_data, void *error_ecc, __nand_calculate_ecc(error_data, size, calc_ecc); ret = __nand_correct_data(error_data, error_ecc, calc_ecc, size); - return (ret == -1) ? 0 : -EINVAL; + return (ret == -EBADMSG) ? 0 : -EINVAL; } static const struct nand_ecc_test nand_ecc_test[] = { diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 575790e8a75a..74a7dfecee27 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -843,7 +843,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) if (clear_intf) mcp251x_write_bits(spi, CANINTF, clear_intf, 0x00); - if (eflag) + if (eflag & (EFLG_RX0OVR | EFLG_RX1OVR)) mcp251x_write_bits(spi, EFLG, eflag, 0x00); /* Update can state */ diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5eee62badf45..cbc99d5649af 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface static void gs_destroy_candev(struct gs_can *dev) { unregister_candev(dev->netdev); - free_candev(dev->netdev); usb_kill_anchored_urbs(&dev->tx_submitted); - kfree(dev); + free_candev(dev->netdev); } static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id * for (i = 0; i < icount; i++) { dev->canch[i] = gs_make_candev(i, intf); if (IS_ERR_OR_NULL(dev->canch[i])) { + /* save error code to return later */ + rc = PTR_ERR(dev->canch[i]); + /* on failure destroy previously created candevs */ icount = i; - for (i = 0; i < icount; i++) { + for (i = 0; i < icount; i++) gs_destroy_candev(dev->canch[i]); - dev->canch[i] = NULL; - } + + usb_kill_anchored_urbs(&dev->rx_submitted); kfree(dev); return rc; } @@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf) return; } - for (i = 0; i < GS_MAX_INTF; i++) { - struct gs_can *can = dev->canch[i]; - - if (!can) - continue; - - gs_destroy_candev(can); - } + for (i = 0; i < GS_MAX_INTF; i++) + if (dev->canch[i]) + gs_destroy_candev(dev->canch[i]); usb_kill_anchored_urbs(&dev->rx_submitted); + kfree(dev); } static const struct usb_device_id gs_usb_table[] = { diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 79e1a0282163..17b2126075e0 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2461,7 +2461,7 @@ boomerang_interrupt(int irq, void *dev_id) int i; pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[entry].frag[0].addr), - le32_to_cpu(vp->tx_ring[entry].frag[0].length), + le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF, PCI_DMA_TODEVICE); for (i=1; i<=skb_shinfo(skb)->nr_frags; i++) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 17472851674f..f749e4d389eb 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -193,7 +193,6 @@ static void altera_tse_mdio_destroy(struct net_device *dev) priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); priv->mdio = NULL; } diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index f71ab2647a3b..08a23e6b60e9 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1460,7 +1460,19 @@ static int nb8800_probe(struct platform_device *pdev) goto err_disable_clk; } - priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + if (of_phy_is_fixed_link(pdev->dev.of_node)) { + ret = of_phy_register_fixed_link(pdev->dev.of_node); + if (ret < 0) { + dev_err(&pdev->dev, "bad fixed-link spec\n"); + goto err_free_bus; + } + priv->phy_node = of_node_get(pdev->dev.of_node); + } + + if (!priv->phy_node) + priv->phy_node = of_parse_phandle(pdev->dev.of_node, + "phy-handle", 0); + if (!priv->phy_node) { dev_err(&pdev->dev, "no PHY specified\n"); ret = -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 27aa0802d87d..91874d24fd56 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -4896,9 +4896,9 @@ struct c2s_pri_trans_table_entry { * cfc delete event data */ struct cfc_del_event_data { - u32 cid; - u32 reserved0; - u32 reserved1; + __le32 cid; + __le32 reserved0; + __le32 reserved1; }; @@ -5114,15 +5114,9 @@ struct vf_pf_channel_zone_trigger { * zone that triggers the in-bound interrupt */ struct trigger_vf_zone { -#if defined(__BIG_ENDIAN) - u16 reserved1; - u8 reserved0; - struct vf_pf_channel_zone_trigger vf_pf_channel; -#elif defined(__LITTLE_ENDIAN) struct vf_pf_channel_zone_trigger vf_pf_channel; u8 reserved0; u16 reserved1; -#endif u32 reserved2; }; @@ -5207,9 +5201,9 @@ struct e2_integ_data { * set mac event data */ struct eth_event_data { - u32 echo; - u32 reserved0; - u32 reserved1; + __le32 echo; + __le32 reserved0; + __le32 reserved1; }; @@ -5219,9 +5213,9 @@ struct eth_event_data { struct vf_pf_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 msg_addr_lo; - u32 msg_addr_hi; + __le16 reserved1; + __le32 msg_addr_lo; + __le32 msg_addr_hi; }; /* @@ -5230,9 +5224,9 @@ struct vf_pf_event_data { struct vf_flr_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* @@ -5241,9 +5235,9 @@ struct vf_flr_event_data { struct malicious_vf_event_data { u8 vf_id; u8 err_id; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 6c4e3a69976f..2bf9c871144f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5280,14 +5280,14 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; - u32 cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); + u32 cid = echo & BNX2X_SWCID_MASK; struct bnx2x_vlan_mac_obj *vlan_mac_obj; /* Always push next commands out, don't wait here */ __set_bit(RAMROD_CONT, &ramrod_flags); - switch (le32_to_cpu((__force __le32)elem->message.data.eth_event.echo) - >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n"); if (CNIC_LOADED(bp) && (cid == BNX2X_ISCSI_ETH_CID(bp))) @@ -5308,8 +5308,7 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, bnx2x_handle_mcast_eqe(bp); return; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } @@ -5478,9 +5477,6 @@ static void bnx2x_eq_int(struct bnx2x *bp) goto next_spqe; } - /* elem CID originates from FW; actually LE */ - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); opcode = elem->message.opcode; /* handle eq element */ @@ -5503,6 +5499,10 @@ static void bnx2x_eq_int(struct bnx2x *bp) * we may want to verify here that the bp state is * HALTING */ + + /* elem CID originates from FW; actually LE */ + cid = SW_CID(elem->message.data.cfc_del_event.cid); + DP(BNX2X_MSG_SP, "got delete ramrod for MULTI[%d]\n", cid); @@ -5596,10 +5596,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) BNX2X_STATE_OPENING_WAIT4_PORT): case (EVENT_RING_OPCODE_RSS_UPDATE_RULES | BNX2X_STATE_CLOSING_WAIT4_HALT): - cid = elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK; DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n", - cid); + SW_CID(elem->message.data.eth_event.echo)); rss_raw->clear_pending(rss_raw); break; @@ -5684,7 +5682,7 @@ static void bnx2x_sp_task(struct work_struct *work) if (status & BNX2X_DEF_SB_IDX) { struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp); - if (FCOE_INIT(bp) && + if (FCOE_INIT(bp) && (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) { /* Prevent local bottom-halves from running as * we are going to change the local NAPI list. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 9d027348cd09..632daff117d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1672,11 +1672,12 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); /* Always push next commands out, don't wait here */ set_bit(RAMROD_CONT, &ramrod_flags); - switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem, &ramrod_flags); @@ -1686,8 +1687,7 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, &ramrod_flags); break; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } if (rc < 0) @@ -1747,16 +1747,14 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem) switch (opcode) { case EVENT_RING_OPCODE_CFC_DEL: - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); + cid = SW_CID(elem->message.data.cfc_del_event.cid); DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_CLASSIFICATION_RULES: case EVENT_RING_OPCODE_MULTICAST_RULES: case EVENT_RING_OPCODE_FILTERS_RULES: case EVENT_RING_OPCODE_RSS_UPDATE_RULES: - cid = (elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK); + cid = SW_CID(elem->message.data.eth_event.echo); DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_VF_FLR: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 1374e5394a79..bfae300cf25f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2187,8 +2187,10 @@ void bnx2x_vf_mbx_schedule(struct bnx2x *bp, /* Update VFDB with current message and schedule its handling */ mutex_lock(&BP_VFDB(bp)->event_mutex); - BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi; - BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo; + BP_VF_MBX(bp, vf_idx)->vf_addr_hi = + le32_to_cpu(vfpf_event->msg_addr_hi); + BP_VF_MBX(bp, vf_idx)->vf_addr_lo = + le32_to_cpu(vfpf_event->msg_addr_lo); BP_VFDB(bp)->event_occur |= (1ULL << vf_idx); mutex_unlock(&BP_VFDB(bp)->event_mutex); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8ab000dd52d9..82f191382989 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -248,7 +248,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action); - end = PTR_ALIGN(pdata + length + 1, 8) - 1; + end = pdata + length; + end = PTR_ALIGN(end, 8) - 1; *end = 0; skb_copy_from_linear_data(skb, pdata, len); diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index 04b0d16b210e..95bc470ae441 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -987,7 +987,7 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf) if (!list_empty(&rxf->ucast_pending_add_q)) { mac = list_first_entry(&rxf->ucast_pending_add_q, struct bna_mac, qe); - list_add_tail(&mac->qe, &rxf->ucast_active_q); + list_move_tail(&mac->qe, &rxf->ucast_active_q); bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ); return 1; } diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 688828865c48..34e9acea8747 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -116,6 +116,15 @@ #define NIC_PF_INTR_ID_MBOX0 8 #define NIC_PF_INTR_ID_MBOX1 9 +/* Minimum FIFO level before all packets for the CQ are dropped + * + * This value ensures that once a packet has been "accepted" + * for reception it will not get dropped due to non-availability + * of CQ descriptor. An errata in HW mandates this value to be + * atleast 0x100. + */ +#define NICPF_CQM_MIN_DROP_LEVEL 0x100 + /* Global timer for CQ timer thresh interrupts * Calculated for SCLK of 700Mhz * value written should be a 1/16th of what is expected diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 4dded90076c8..95f17f8cadac 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -304,6 +304,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) static void nic_init_hw(struct nicpf *nic) { int i; + u64 cqm_cfg; /* Enable NIC HW block */ nic_reg_write(nic, NIC_PF_CFG, 0x3); @@ -340,6 +341,11 @@ static void nic_init_hw(struct nicpf *nic) /* Enable VLAN ethertype matching and stripping */ nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7, (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q); + + /* Check if HW expected value is higher (could be in future chips) */ + cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG); + if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL) + nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL); } /* Channel parse index configuration */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index dd536be20193..afb10e326b4f 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -21,7 +21,7 @@ #define NIC_PF_TCP_TIMER (0x0060) #define NIC_PF_BP_CFG (0x0080) #define NIC_PF_RRM_CFG (0x0088) -#define NIC_PF_CQM_CF (0x00A0) +#define NIC_PF_CQM_CFG (0x00A0) #define NIC_PF_CNM_CF (0x00A8) #define NIC_PF_CNM_STATUS (0x00B0) #define NIC_PF_CQ_AVG_CFG (0x00C0) diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index cf837831304b..f9751294ece7 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -531,6 +531,7 @@ struct be_adapter { struct delayed_work be_err_detection_work; u8 err_flags; + bool pcicfg_mapped; /* pcicfg obtained via pci_iomap() */ u32 flags; u32 cmd_privileges; /* Ethtool knobs and info */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 241819b36ca7..6d9a8d78e8ad 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -622,10 +622,13 @@ enum be_if_flags { BE_IF_FLAGS_VLAN_PROMISCUOUS |\ BE_IF_FLAGS_MCAST_PROMISCUOUS) -#define BE_IF_EN_FLAGS (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\ - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED) +#define BE_IF_FILT_FLAGS_BASIC (BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS | \ + BE_IF_FLAGS_UNTAGGED) -#define BE_IF_ALL_FILT_FLAGS (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS) +#define BE_IF_ALL_FILT_FLAGS (BE_IF_FILT_FLAGS_BASIC | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_ALL_PROMISCUOUS) /* An RX interface is an object with one or more MAC addresses and * filtering capabilities. */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index f99de3657ce3..d1cf1274fc2f 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -125,6 +125,11 @@ static const char * const ue_status_hi_desc[] = { "Unknown" }; +#define BE_VF_IF_EN_FLAGS (BE_IF_FLAGS_UNTAGGED | \ + BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS) + static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q) { struct be_dma_mem *mem = &q->dma_mem; @@ -3537,7 +3542,7 @@ static int be_enable_if_filters(struct be_adapter *adapter) { int status; - status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON); + status = be_cmd_rx_filter(adapter, BE_IF_FILT_FLAGS_BASIC, ON); if (status) return status; @@ -3857,8 +3862,7 @@ static int be_vfs_if_create(struct be_adapter *adapter) int status; /* If a FW profile exists, then cap_flags are updated */ - cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS; + cap_flags = BE_VF_IF_EN_FLAGS; for_all_vfs(adapter, vf_cfg, vf) { if (!BE3_chip(adapter)) { @@ -3874,10 +3878,8 @@ static int be_vfs_if_create(struct be_adapter *adapter) } } - en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | - BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | - BE_IF_FLAGS_PASS_L3L4_ERRORS); + /* PF should enable IF flags during proxy if_create call */ + en_flags = cap_flags & BE_VF_IF_EN_FLAGS; status = be_cmd_if_create(adapter, cap_flags, en_flags, &vf_cfg->if_handle, vf + 1); if (status) @@ -4968,6 +4970,8 @@ static void be_unmap_pci_bars(struct be_adapter *adapter) pci_iounmap(adapter->pdev, adapter->csr); if (adapter->db) pci_iounmap(adapter->pdev, adapter->db); + if (adapter->pcicfg && adapter->pcicfg_mapped) + pci_iounmap(adapter->pdev, adapter->pcicfg); } static int db_bar(struct be_adapter *adapter) @@ -5019,8 +5023,10 @@ static int be_map_pci_bars(struct be_adapter *adapter) if (!addr) goto pci_map_err; adapter->pcicfg = addr; + adapter->pcicfg_mapped = true; } else { adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET; + adapter->pcicfg_mapped = false; } } diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 62fa136554ac..41b010645100 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1265,7 +1265,6 @@ static int ethoc_remove(struct platform_device *pdev) if (priv->mdio) { mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } if (priv->clk) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 623aa1c8ebc6..79a210aaf0bb 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2791,6 +2791,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_free; } + fman->dev = &of_dev->dev; + return fman; fman_node_put: @@ -2845,8 +2847,6 @@ static int fman_probe(struct platform_device *of_dev) dev_set_drvdata(dev, fman); - fman->dev = dev; - dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id); return 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 2aa7b401cc3b..b9ecf197ad11 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1111,8 +1111,10 @@ static void __gfar_detect_errata_85xx(struct gfar_private *priv) if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20)) priv->errata |= GFAR_ERRATA_12; + /* P2020/P1010 Rev 1; MPC8548 Rev 2 */ if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) || - ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20))) + ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)) || + ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) < 0x31))) priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */ } #endif diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 74beb1867230..4ccc032633c4 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -25,6 +25,7 @@ config HIX5HD2_GMAC config HIP04_ETH tristate "HISILICON P04 Ethernet support" + depends on HAS_IOMEM # For MFD_SYSCON select MARVELL_PHY select MFD_SYSCON select HNS_MDIO diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index a0070d0e740d..d4f92ed322d6 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -675,8 +675,12 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, { int ret; struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); switch (loop) { + case MAC_INTERNALLOOP_PHY: + ret = 0; + break; case MAC_INTERNALLOOP_SERDES: ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en); break; @@ -686,6 +690,10 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, default: ret = -EINVAL; } + + if (!ret) + hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en); + return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 9439f04962e1..38fc5be3870c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -230,6 +230,30 @@ static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev) } } +static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev) +{ + u16 max_q_per_vf, max_vfn; + u32 q_id, q_num_per_port; + u32 mac_id; + + if (AE_IS_VER1(dsaf_dev->dsaf_ver)) + return; + + hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode, + HNS_DSAF_COMM_SERVICE_NW_IDX, + &max_vfn, &max_q_per_vf); + q_num_per_port = max_vfn * max_q_per_vf; + + for (mac_id = 0, q_id = 0; mac_id < DSAF_SERVICE_NW_NUM; mac_id++) { + dsaf_set_dev_field(dsaf_dev, + DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_QID_M, + DSAFV2_SERDES_LBK_QID_S, + q_id); + q_id += q_num_per_port; + } +} + /** * hns_dsaf_sw_port_type_cfg - cfg sw type * @dsaf_id: dsa fabric id @@ -691,6 +715,16 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en) dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en); } +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en) +{ + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + dsaf_dev->mac_cb[mac_id].mac_type == HNAE_PORT_DEBUG) + return; + + dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_EN_B, !!en); +} + /** * hns_dsaf_tbl_stat_en - tbl * @dsaf_id: dsa fabric id @@ -1022,6 +1056,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) /* set promisc def queue id */ hns_dsaf_mix_def_qid_cfg(dsaf_dev); + /* set inner loopback queue id */ + hns_dsaf_inner_qid_cfg(dsaf_dev); + /* in non switch mode, set all port to access mode */ hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 40205b910f80..5fea226efaf3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -417,5 +417,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port); void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); int hns_dsaf_get_regs_count(void); void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en); +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index f0c4f9b09d5b..60d695daa471 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -134,6 +134,7 @@ #define DSAF_XGE_INT_STS_0_REG 0x1C0 #define DSAF_PPE_INT_STS_0_REG 0x1E0 #define DSAF_ROCEE_INT_STS_0_REG 0x200 +#define DSAFV2_SERDES_LBK_0_REG 0x220 #define DSAF_PPE_QID_CFG_0_REG 0x300 #define DSAF_SW_PORT_TYPE_0_REG 0x320 #define DSAF_STP_PORT_TYPE_0_REG 0x340 @@ -857,6 +858,10 @@ #define PPEV2_CFG_RSS_TBL_4N3_S 24 #define PPEV2_CFG_RSS_TBL_4N3_M (((1UL << 5) - 1) << PPEV2_CFG_RSS_TBL_4N3_S) +#define DSAFV2_SERDES_LBK_EN_B 8 +#define DSAFV2_SERDES_LBK_QID_S 0 +#define DSAFV2_SERDES_LBK_QID_M (((1UL << 8) - 1) << DSAFV2_SERDES_LBK_QID_S) + #define PPE_CNT_CLR_CE_B 0 #define PPE_CNT_CLR_SNAP_EN_B 1 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 3df22840fcd1..3c4a3bc31a89 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -295,8 +295,10 @@ static int __lb_setup(struct net_device *ndev, switch (loop) { case MAC_INTERNALLOOP_PHY: - if ((phy_dev) && (!phy_dev->is_c45)) + if ((phy_dev) && (!phy_dev->is_c45)) { ret = hns_nic_config_phy_loopback(phy_dev, 0x1); + ret |= h->dev->ops->set_loopback(h, loop, 0x1); + } break; case MAC_INTERNALLOOP_MAC: if ((h->dev->ops->set_loopback) && @@ -376,6 +378,7 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, struct sk_buff *skb) { struct net_device *ndev; + struct hns_nic_priv *priv; struct hnae_ring *ring; struct netdev_queue *dev_queue; struct sk_buff *new_skb; @@ -385,8 +388,17 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, char buff[33]; /* 32B data and the last character '\0' */ if (!ring_data) { /* Just for doing create frame*/ + ndev = skb->dev; + priv = netdev_priv(ndev); + frame_size = skb->len; memset(skb->data, 0xFF, frame_size); + if ((!AE_IS_VER1(priv->enet_ver)) && + (priv->ae_handle->port_type == HNAE_PORT_SERVICE)) { + memcpy(skb->data, ndev->dev_addr, 6); + skb->data[5] += 0x1f; + } + frame_size &= ~1ul; memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); memset(&skb->data[frame_size / 2 + 10], 0xBE, @@ -486,6 +498,7 @@ static int __lb_run_test(struct net_device *ndev, /* place data into test skb */ (void)skb_put(skb, size); + skb->dev = ndev; __lb_other_process(NULL, skb); skb->queue_mapping = NIC_LB_TEST_RING_ID; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 335417b4756b..ebe60719e489 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1166,7 +1166,10 @@ map_failed: if (!firmware_has_feature(FW_FEATURE_CMO)) netdev_err(netdev, "tx: unable to map xmit buffer\n"); adapter->tx_map_failed++; - skb_linearize(skb); + if (skb_linearize(skb)) { + netdev->stats.tx_dropped++; + goto out; + } force_bounce = 1; goto retry_bounce; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7d6570843723..6e9e16eee5d0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1348,44 +1348,44 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) crq.request_capability.cmd = REQUEST_CAPABILITY; crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_tx_entries_per_subcrq); + cpu_to_be64(adapter->req_tx_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_rx_add_entries_per_subcrq); + cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_MTU); - crq.request_capability.number = cpu_to_be32(adapter->req_mtu); + crq.request_capability.number = cpu_to_be64(adapter->req_mtu); ibmvnic_send_crq(adapter, &crq); if (adapter->netdev->flags & IFF_PROMISC) { if (adapter->promisc_supported) { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(1); + crq.request_capability.number = cpu_to_be64(1); ibmvnic_send_crq(adapter, &crq); } } else { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(0); + crq.request_capability.number = cpu_to_be64(0); ibmvnic_send_crq(adapter, &crq); } @@ -2312,93 +2312,93 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, switch (be16_to_cpu(crq->query_capability.capability)) { case MIN_TX_QUEUES: adapter->min_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_queues = %lld\n", adapter->min_tx_queues); break; case MIN_RX_QUEUES: adapter->min_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_queues = %lld\n", adapter->min_rx_queues); break; case MIN_RX_ADD_QUEUES: adapter->min_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_queues = %lld\n", adapter->min_rx_add_queues); break; case MAX_TX_QUEUES: adapter->max_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_queues = %lld\n", adapter->max_tx_queues); break; case MAX_RX_QUEUES: adapter->max_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_queues = %lld\n", adapter->max_rx_queues); break; case MAX_RX_ADD_QUEUES: adapter->max_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_queues = %lld\n", adapter->max_rx_add_queues); break; case MIN_TX_ENTRIES_PER_SUBCRQ: adapter->min_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n", adapter->min_tx_entries_per_subcrq); break; case MIN_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->min_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n", adapter->min_rx_add_entries_per_subcrq); break; case MAX_TX_ENTRIES_PER_SUBCRQ: adapter->max_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n", adapter->max_tx_entries_per_subcrq); break; case MAX_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->max_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n", adapter->max_rx_add_entries_per_subcrq); break; case TCP_IP_OFFLOAD: adapter->tcp_ip_offload = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "tcp_ip_offload = %lld\n", adapter->tcp_ip_offload); break; case PROMISC_SUPPORTED: adapter->promisc_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "promisc_supported = %lld\n", adapter->promisc_supported); break; case MIN_MTU: - adapter->min_mtu = be32_to_cpu(crq->query_capability.number); + adapter->min_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); break; case MAX_MTU: - adapter->max_mtu = be32_to_cpu(crq->query_capability.number); + adapter->max_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); break; case MAX_MULTICAST_FILTERS: adapter->max_multicast_filters = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_multicast_filters = %lld\n", adapter->max_multicast_filters); break; case VLAN_HEADER_INSERTION: adapter->vlan_header_insertion = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); if (adapter->vlan_header_insertion) netdev->features |= NETIF_F_HW_VLAN_STAG_TX; netdev_dbg(netdev, "vlan_header_insertion = %lld\n", @@ -2406,43 +2406,43 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, break; case MAX_TX_SG_ENTRIES: adapter->max_tx_sg_entries = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_sg_entries = %lld\n", adapter->max_tx_sg_entries); break; case RX_SG_SUPPORTED: adapter->rx_sg_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "rx_sg_supported = %lld\n", adapter->rx_sg_supported); break; case OPT_TX_COMP_SUB_QUEUES: adapter->opt_tx_comp_sub_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n", adapter->opt_tx_comp_sub_queues); break; case OPT_RX_COMP_QUEUES: adapter->opt_rx_comp_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n", adapter->opt_rx_comp_queues); break; case OPT_RX_BUFADD_Q_PER_RX_COMP_Q: adapter->opt_rx_bufadd_q_per_rx_comp_q = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n", adapter->opt_rx_bufadd_q_per_rx_comp_q); break; case OPT_TX_ENTRIES_PER_SUBCRQ: adapter->opt_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n", adapter->opt_tx_entries_per_subcrq); break; case OPT_RXBA_ENTRIES_PER_SUBCRQ: adapter->opt_rxba_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n", adapter->opt_rxba_entries_per_subcrq); break; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 1242925ad34c..1a9993cc79b5 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -319,10 +319,8 @@ struct ibmvnic_capability { u8 first; u8 cmd; __be16 capability; /* one of ibmvnic_capabilities */ + __be64 number; struct ibmvnic_rc rc; - __be32 number; /*FIX: should be __be64, but I'm getting the least - * significant word first - */ } __packed __aligned(8); struct ibmvnic_login { diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b1de7afd4116..3ddf657bc10b 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme) } static inline void -jme_clear_pm(struct jme_adapter *jme) +jme_clear_pm_enable_wol(struct jme_adapter *jme) { jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs); } +static inline void +jme_clear_pm_disable_wol(struct jme_adapter *jme) +{ + jwrite32(jme, JME_PMCS, PMCS_STMASK); +} + static int jme_reload_eeprom(struct jme_adapter *jme) { @@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev) struct jme_adapter *jme = netdev_priv(netdev); int rc; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); JME_NAPI_ENABLE(jme); tasklet_init(&jme->linkch_task, jme_link_change_tasklet, @@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme) static void jme_powersave_phy(struct jme_adapter *jme) { - if (jme->reg_pmcs) { + if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) { jme_set_100m_half(jme); if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN)) jme_wait_link(jme); - jme_clear_pm(jme); + jme_clear_pm_enable_wol(jme); } else { jme_phy_off(jme); } @@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev, if (wol->wolopts & WAKE_MAGIC) jme->reg_pmcs |= PMCS_MFEN; - jwrite32(jme, JME_PMCS, jme->reg_pmcs); - device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs)); - return 0; } @@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_read = jme_mdio_read; jme->mii_if.mdio_write = jme_mdio_write; - jme_clear_pm(jme); - device_set_wakeup_enable(&pdev->dev, true); + jme_clear_pm_disable_wol(jme); + device_init_wakeup(&pdev->dev, true); jme_set_phyfifo_5level(jme); jme->pcirev = pdev->revision; @@ -3304,7 +3307,7 @@ jme_resume(struct device *dev) if (!netif_running(netdev)) return 0; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); jme_phy_on(jme); if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); @@ -3312,13 +3315,14 @@ jme_resume(struct device *dev) jme_reset_phy_processor(jme); jme_phy_calibration(jme); jme_phy_setEA(jme); - jme_start_irq(jme); netif_device_attach(netdev); atomic_inc(&jme->link_changing); jme_reset_link(jme); + jme_start_irq(jme); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index f191a1612589..21e2c0960271 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2245,7 +2245,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) struct mlx4_en_dev *mdev = en_priv->mdev; u64 mac_u64 = mlx4_mac_to_u64(mac); - if (!is_valid_ether_addr(mac)) + if (is_multicast_ether_addr(mac)) return -EINVAL; return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2cc3c626c3fe..f8674ae62752 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1256,6 +1256,7 @@ err_set_port: static int mlx4_mf_bond(struct mlx4_dev *dev) { int err = 0; + int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); @@ -1272,11 +1273,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) return -EINVAL; } + /* number of virtual functions is number of total functions minus one + * physical function for each port. + */ + nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + + bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2; + /* limit on maximum allowed VFs */ - if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + - bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) > - MAX_MF_BOND_ALLOWED_SLAVES) + if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) { + mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n", + nvfs, MAX_MF_BOND_ALLOWED_SLAVES); return -EINVAL; + } if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) { mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n"); diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 787b7bb54d52..211c65087997 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index aac071a7e830..5b1753233c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -223,6 +223,7 @@ struct mlx5e_pport_stats { static const char rq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "csum_none", "csum_sw", "lro_packets", @@ -232,16 +233,18 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_rq_stats { u64 packets; + u64 bytes; u64 csum_none; u64 csum_sw; u64 lro_packets; u64 lro_bytes; u64 wqe_err; -#define NUM_RQ_STATS 6 +#define NUM_RQ_STATS 7 }; static const char sq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "tso_packets", "tso_bytes", "csum_offload_none", @@ -253,6 +256,7 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_sq_stats { u64 packets; + u64 bytes; u64 tso_packets; u64 tso_bytes; u64 csum_offload_none; @@ -260,7 +264,7 @@ struct mlx5e_sq_stats { u64 wake; u64 dropped; u64 nop; -#define NUM_SQ_STATS 8 +#define NUM_SQ_STATS 9 }; struct mlx5e_stats { @@ -304,14 +308,9 @@ enum { MLX5E_RQ_STATE_POST_WQES_ENABLE, }; -enum cq_flags { - MLX5E_CQ_HAS_CQES = 1, -}; - struct mlx5e_cq { /* data path - accessed per cqe */ struct mlx5_cqwq wq; - unsigned long flags; /* data path - accessed per napi poll */ struct napi_struct *napi; @@ -452,6 +451,8 @@ enum mlx5e_traffic_types { MLX5E_NUM_TT, }; +#define IS_HASHING_TT(tt) (tt != MLX5E_TT_ANY) + enum mlx5e_rqt_ix { MLX5E_INDIRECTION_RQT, MLX5E_SINGLE_RQ_RQT, @@ -618,9 +619,12 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix); +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels); static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, struct mlx5e_tx_wqe *wqe, int bf_sz) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index be6543570b2b..2018eebe1531 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -62,10 +62,11 @@ static void mlx5e_timestamp_overflow(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, overflow_work); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period); } @@ -136,10 +137,11 @@ static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns = timespec64_to_ns(ts); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -150,10 +152,11 @@ static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns; + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); ns = timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); *ts = ns_to_timespec64(ns); @@ -164,10 +167,11 @@ static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_adjtime(&tstamp->clock, delta); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -176,6 +180,7 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) { u64 adj; u32 diff; + unsigned long flags; int neg_adj = 0; struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); @@ -189,11 +194,11 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : tstamp->nominal_c_mult + diff; - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 65624ac65b4c..5abeb00fceb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -385,6 +385,8 @@ static int mlx5e_set_channels(struct net_device *dev, mlx5e_close_locked(dev); priv->params.num_channels = count; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); if (was_opened) err = mlx5e_open_locked(dev); @@ -703,18 +705,36 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return 0; } +static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen) +{ + struct mlx5_core_dev *mdev = priv->mdev; + void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); + int i; + + MLX5_SET(modify_tir_in, in, bitmask.hash, 1); + mlx5e_build_tir_ctx_hash(tirc, priv); + + for (i = 0; i < MLX5E_NUM_TT; i++) + if (IS_HASHING_TT(i)) + mlx5_core_modify_tir(mdev, priv->tirn[i], in, inlen); +} + static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) { struct mlx5e_priv *priv = netdev_priv(dev); - bool close_open; - int err = 0; + int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + void *in; if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_XOR) && (hfunc != ETH_RSS_HASH_TOP)) return -EINVAL; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + mutex_lock(&priv->state_lock); if (indir) { @@ -723,11 +743,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, mlx5e_redirect_rqt(priv, MLX5E_INDIRECTION_RQT); } - close_open = (key || (hfunc != ETH_RSS_HASH_NO_CHANGE)) && - test_bit(MLX5E_STATE_OPENED, &priv->state); - if (close_open) - mlx5e_close_locked(dev); - if (key) memcpy(priv->params.toeplitz_hash_key, key, sizeof(priv->params.toeplitz_hash_key)); @@ -735,12 +750,13 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE) priv->params.rss_hfunc = hfunc; - if (close_open) - err = mlx5e_open_locked(priv->netdev); + mlx5e_modify_tirs_hash(priv, in, inlen); mutex_unlock(&priv->state_lock); - return err; + kvfree(in); + + return 0; } static int mlx5e_get_rxnfc(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d4e1c3045200..402994bf7e16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -141,6 +141,10 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) return; /* Collect firts the SW counters and then HW for consistency */ + s->rx_packets = 0; + s->rx_bytes = 0; + s->tx_packets = 0; + s->tx_bytes = 0; s->tso_packets = 0; s->tso_bytes = 0; s->tx_queue_stopped = 0; @@ -155,6 +159,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (i = 0; i < priv->params.num_channels; i++) { rq_stats = &priv->channel[i]->rq.stats; + s->rx_packets += rq_stats->packets; + s->rx_bytes += rq_stats->bytes; s->lro_packets += rq_stats->lro_packets; s->lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; @@ -164,6 +170,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (j = 0; j < priv->params.num_tc; j++) { sq_stats = &priv->channel[i]->sq[j].stats; + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; s->tso_packets += sq_stats->tso_packets; s->tso_bytes += sq_stats->tso_bytes; s->tx_queue_stopped += sq_stats->stopped; @@ -225,23 +233,6 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) s->tx_broadcast_bytes = MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); - s->rx_packets = - s->rx_unicast_packets + - s->rx_multicast_packets + - s->rx_broadcast_packets; - s->rx_bytes = - s->rx_unicast_bytes + - s->rx_multicast_bytes + - s->rx_broadcast_bytes; - s->tx_packets = - s->tx_unicast_packets + - s->tx_multicast_packets + - s->tx_broadcast_packets; - s->tx_bytes = - s->tx_unicast_bytes + - s->tx_multicast_bytes + - s->tx_broadcast_bytes; - /* Update calculated offload counters */ s->tx_csum_offload = s->tx_packets - tx_offload_none; s->rx_csum_good = s->rx_packets - s->rx_csum_none - @@ -1199,7 +1190,6 @@ static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc) ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE); ix = priv->params.indirection_rqt[ix]; - ix = ix % priv->params.num_channels; MLX5_SET(rqtc, rqtc, rq_num[i], test_bit(MLX5E_STATE_OPENED, &priv->state) ? priv->channel[ix]->rq.rqn : @@ -1317,7 +1307,22 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) lro_timer_supported_periods[2])); } -static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) +{ + MLX5_SET(tirc, tirc, rx_hash_fn, + mlx5e_rx_hash_fn(priv->params.rss_hfunc)); + if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { + void *rss_key = MLX5_ADDR_OF(tirc, tirc, + rx_hash_toeplitz_key); + size_t len = MLX5_FLD_SZ_BYTES(tirc, + rx_hash_toeplitz_key); + + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + memcpy(rss_key, priv->params.toeplitz_hash_key, len); + } +} + +static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -1325,6 +1330,7 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) void *tirc; int inlen; int err; + int tt; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = mlx5_vzalloc(inlen); @@ -1336,7 +1342,11 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) mlx5e_build_tir_ctx_lro(tirc, priv); - err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + for (tt = 0; tt < MLX5E_NUM_TT; tt++) { + err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + if (err) + break; + } kvfree(in); @@ -1672,17 +1682,7 @@ static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt) default: MLX5_SET(tirc, tirc, indirect_table, priv->rqtn[MLX5E_INDIRECTION_RQT]); - MLX5_SET(tirc, tirc, rx_hash_fn, - mlx5e_rx_hash_fn(priv->params.rss_hfunc)); - if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { - void *rss_key = MLX5_ADDR_OF(tirc, tirc, - rx_hash_toeplitz_key); - size_t len = MLX5_FLD_SZ_BYTES(tirc, - rx_hash_toeplitz_key); - - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); - memcpy(rss_key, priv->params.toeplitz_hash_key, len); - } + mlx5e_build_tir_ctx_hash(tirc, priv); break; } @@ -1885,8 +1885,10 @@ static int mlx5e_set_features(struct net_device *netdev, mlx5e_close_locked(priv->netdev); priv->params.lro_en = !!(features & NETIF_F_LRO); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV4_TCP); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV6_TCP); + err = mlx5e_modify_tirs_lro(priv); + if (err) + mlx5_core_warn(priv->mdev, "lro modify failed, %d\n", + err); if (was_opened) err = mlx5e_open_locked(priv->netdev); @@ -2089,12 +2091,20 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev) 2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/; } +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels) +{ + int i; + + for (i = 0; i < len; i++) + indirection_rqt[i] = i % num_channels; +} + static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, struct net_device *netdev, int num_channels) { struct mlx5e_priv *priv = netdev_priv(netdev); - int i; priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; @@ -2118,8 +2128,8 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, netdev_rss_key_fill(priv->params.toeplitz_hash_key, sizeof(priv->params.toeplitz_hash_key)); - for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) - priv->params.indirection_rqt[i] = i % num_channels; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, num_channels); priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index dd959d929aad..59658b9d05d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -230,10 +230,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return 0; - for (work_done = 0; work_done < budget; work_done++) { struct mlx5e_rx_wqe *wqe; struct mlx5_cqe64 *cqe; @@ -267,6 +263,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5e_build_rx_skb(cqe, rq, skb); rq->stats.packets++; + rq->stats.bytes += be32_to_cpu(cqe->byte_cnt); napi_gro_receive(cq->napi, skb); wq_ll_pop: @@ -279,8 +276,5 @@ wq_ll_pop: /* ensure cq space is freed before enabling more cqes */ wmb(); - if (work_done == budget) - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2c3fba0fff54..bb4eeeb007de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -179,6 +179,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) unsigned int skb_len = skb->len; u8 opcode = MLX5_OPCODE_SEND; dma_addr_t dma_addr = 0; + unsigned int num_bytes; bool bf = false; u16 headlen; u16 ds_cnt; @@ -204,8 +205,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) opcode = MLX5_OPCODE_LSO; ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); payload_len = skb->len - ihs; - wi->num_bytes = skb->len + - (skb_shinfo(skb)->gso_segs - 1) * ihs; + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; sq->stats.tso_packets++; sq->stats.tso_bytes += payload_len; } else { @@ -213,9 +213,11 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) !skb->xmit_more && !skb_shinfo(skb)->nr_frags; ihs = mlx5e_get_inline_hdr_size(sq, skb, bf); - wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } + wi->num_bytes = num_bytes; + if (skb_vlan_tag_present(skb)) { mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data, &skb_len); @@ -307,6 +309,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->bf_budget = bf ? sq->bf_budget - 1 : 0; sq->stats.packets++; + sq->stats.bytes += num_bytes; return NETDEV_TX_OK; dma_unmap_wqe_err: @@ -335,10 +338,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) u16 sqcc; int i; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return false; - sq = container_of(cq, struct mlx5e_sq, cq); npkts = 0; @@ -422,10 +421,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) netif_tx_wake_queue(sq->txq); sq->stats.wake++; } - if (i == MLX5E_TX_CQ_POLL_BUDGET) { - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return true; - } - return false; + return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 4ac8d716dbdd..66d51a77609e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -88,7 +88,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq) { struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags); barrier(); napi_schedule(cq->napi); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c071077aafbd..7992c553c1f5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -215,7 +215,7 @@ mlxsw_pci_queue_elem_info_producer_get(struct mlxsw_pci_queue *q) { int index = q->producer_counter & (q->count - 1); - if ((q->producer_counter - q->consumer_counter) == q->count) + if ((u16) (q->producer_counter - q->consumer_counter) == q->count) return NULL; return mlxsw_pci_queue_elem_info_get(q, index); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 09ce451c283b..a94daa8c346c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2358,9 +2358,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (mlxsw_sp_port->bridged) { mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); - - if (lag->ref_count == 1) - mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); } if (lag->ref_count == 1) { diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 00cfd95ca59d..3e67f451f2ab 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -474,9 +474,9 @@ static int moxart_mac_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ndev->base_addr = res->start; priv->base = devm_ioremap_resource(p_dev, res); - ret = IS_ERR(priv->base); - if (ret) { + if (IS_ERR(priv->base)) { dev_err(p_dev, "devm_ioremap_resource failed\n"); + ret = PTR_ERR(priv->base); goto init_fail; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 689a4a5c8dcf..1ef03939d25f 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev) dev->netdev_ops = &qcaspi_netdev_ops; qcaspi_set_ethtool_ops(dev); dev->watchdog_timeo = QCASPI_TX_TIMEOUT; - dev->flags = IFF_MULTICAST; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->tx_queue_len = 100; qca = netdev_priv(dev); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 537974cfd427..dd2cf3738b73 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4933,8 +4933,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40: - RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: @@ -4943,8 +4941,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: @@ -7730,10 +7726,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; + struct pci_dev *pdev = tp->pci_dev; struct rtl8169_counters *counters = tp->counters; unsigned int start; - if (netif_running(dev)) + pm_runtime_get_noresume(&pdev->dev); + + if (netif_running(dev) && pm_runtime_active(&pdev->dev)) rtl8169_rx_missed(dev, ioaddr); do { @@ -7761,7 +7760,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) * Fetch additonal counter values missing in stats collected by driver * from tally counters. */ - rtl8169_update_counters(dev); + if (pm_runtime_active(&pdev->dev)) + rtl8169_update_counters(dev); /* * Subtract values fetched during initalization. @@ -7774,6 +7774,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) - le16_to_cpu(tp->tc_offset.tx_aborted); + pm_runtime_put_noidle(&pdev->dev); + return stats; } @@ -7853,6 +7855,10 @@ static int rtl8169_runtime_suspend(struct device *device) rtl8169_net_suspend(dev); + /* Update counters before going runtime suspend */ + rtl8169_rx_missed(dev, tp->mmio_addr); + rtl8169_update_counters(dev); + return 0; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 744d7806a9ee..86449c357168 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1722,7 +1722,6 @@ static int ravb_set_gti(struct net_device *ndev) static int ravb_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct of_device_id *match; struct ravb_private *priv; enum ravb_chip_id chip_id; struct net_device *ndev; @@ -1754,8 +1753,7 @@ static int ravb_probe(struct platform_device *pdev) ndev->base_addr = res->start; ndev->dma = -1; - match = of_match_device(of_match_ptr(ravb_match_table), &pdev->dev); - chip_id = (enum ravb_chip_id)match->data; + chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev); if (chip_id == RCAR_GEN3) irq = platform_get_irq_byname(pdev, "ch22"); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index dfa9e59c9442..738449992876 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3061,15 +3061,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp->ether_link_active_low = pd->ether_link_active_low; /* set cpu data */ - if (id) { + if (id) mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; - } else { - const struct of_device_id *match; + else + mdp->cd = (struct sh_eth_cpu_data *)of_device_get_match_data(&pdev->dev); - match = of_match_device(of_match_ptr(sh_eth_match_table), - &pdev->dev); - mdp->cd = (struct sh_eth_cpu_data *)match->data; - } mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type); if (!mdp->reg_offset) { dev_err(&pdev->dev, "Unknown register type (%d)\n", diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 0faf16336035..efb54f356a67 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -199,21 +199,12 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; int addr, found; - struct device_node *mdio_node = NULL; - struct device_node *child_node = NULL; + struct device_node *mdio_node = priv->plat->mdio_node; if (!mdio_bus_data) return 0; if (IS_ENABLED(CONFIG_OF)) { - for_each_child_of_node(priv->device->of_node, child_node) { - if (of_device_is_compatible(child_node, - "snps,dwmac-mdio")) { - mdio_node = child_node; - break; - } - } - if (mdio_node) { netdev_dbg(ndev, "FOUND MDIO subnode\n"); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6a52fa18cbf2..4514ba73d961 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -110,6 +110,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + struct device_node *child_node = NULL; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -140,13 +141,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->phy_node = of_node_get(np); } + for_each_child_of_node(np, child_node) + if (of_device_is_compatible(child_node, "snps,dwmac-mdio")) { + plat->mdio_node = child_node; + break; + } + /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) + if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index fc8bbff2d7e3..af11ed1e0bcc 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -426,7 +426,7 @@ #define DWC_MMC_RXOCTETCOUNT_GB 0x0784 #define DWC_MMC_RXPACKETCOUNT_GB 0x0780 -static int debug = 3; +static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "DWC_eth_qos debug level (0=none,...,16=all)"); @@ -650,6 +650,11 @@ struct net_local { u32 mmc_tx_counters_mask; struct dwceqos_flowcontrol flowcontrol; + + /* Tracks the intermediate state of phy started but hardware + * init not finished yet. + */ + bool phy_defer; }; static void dwceqos_read_mmc_counters(struct net_local *lp, u32 rx_mask, @@ -901,6 +906,9 @@ static void dwceqos_adjust_link(struct net_device *ndev) struct phy_device *phydev = lp->phy_dev; int status_change = 0; + if (lp->phy_defer) + return; + if (phydev->link) { if ((lp->speed != phydev->speed) || (lp->duplex != phydev->duplex)) { @@ -1113,7 +1121,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) /* Allocate DMA descriptors */ size = DWCEQOS_RX_DCNT * sizeof(struct dwceqos_dma_desc); lp->rx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->rx_descs_addr, 0); + &lp->rx_descs_addr, GFP_KERNEL); if (!lp->rx_descs) goto err_out; lp->rx_descs_tail_addr = lp->rx_descs_addr + @@ -1121,7 +1129,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) size = DWCEQOS_TX_DCNT * sizeof(struct dwceqos_dma_desc); lp->tx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->tx_descs_addr, 0); + &lp->tx_descs_addr, GFP_KERNEL); if (!lp->tx_descs) goto err_out; lp->tx_descs_tail_addr = lp->tx_descs_addr + @@ -1635,6 +1643,12 @@ static void dwceqos_init_hw(struct net_local *lp) regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG); dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE); + + lp->phy_defer = false; + mutex_lock(&lp->phy_dev->lock); + phy_read_status(lp->phy_dev); + dwceqos_adjust_link(lp->ndev); + mutex_unlock(&lp->phy_dev->lock); } static void dwceqos_tx_reclaim(unsigned long data) @@ -1880,9 +1894,13 @@ static int dwceqos_open(struct net_device *ndev) } netdev_reset_queue(ndev); + /* The dwceqos reset state machine requires all phy clocks to complete, + * hence the unusual init order with phy_start first. + */ + lp->phy_defer = true; + phy_start(lp->phy_dev); dwceqos_init_hw(lp); napi_enable(&lp->napi); - phy_start(lp->phy_dev); netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); @@ -1915,18 +1933,19 @@ static int dwceqos_stop(struct net_device *ndev) { struct net_local *lp = netdev_priv(ndev); - phy_stop(lp->phy_dev); - tasklet_disable(&lp->tx_bdreclaim_tasklet); - netif_stop_queue(ndev); napi_disable(&lp->napi); - dwceqos_drain_dma(lp); + /* Stop all tx before we drain the tx dma. */ + netif_tx_lock_bh(lp->ndev); + netif_stop_queue(ndev); + netif_tx_unlock_bh(lp->ndev); - netif_tx_lock(lp->ndev); + dwceqos_drain_dma(lp); dwceqos_reset_hw(lp); + phy_stop(lp->phy_dev); + dwceqos_descriptor_free(lp); - netif_tx_unlock(lp->ndev); return 0; } @@ -2178,12 +2197,10 @@ static int dwceqos_start_xmit(struct sk_buff *skb, struct net_device *ndev) ((trans.initial_descriptor + trans.nr_descriptors) % DWCEQOS_TX_DCNT)); - dwceqos_tx_finalize(skb, lp, &trans); - - netdev_sent_queue(ndev, skb->len); - spin_lock_bh(&lp->tx_lock); lp->tx_free -= trans.nr_descriptors; + dwceqos_tx_finalize(skb, lp, &trans); + netdev_sent_queue(ndev, skb->len); spin_unlock_bh(&lp->tx_lock); ndev->trans_start = jiffies; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 03833dbfca67..dc85f7095e51 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -297,6 +297,17 @@ static int kszphy_config_init(struct phy_device *phydev) if (priv->led_mode >= 0) kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode); + if (phy_interrupt_is_valid(phydev)) { + int ctl = phy_read(phydev, MII_BMCR); + + if (ctl < 0) + return ctl; + + ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE); + if (ret < 0) + return ret; + } + return 0; } @@ -635,6 +646,21 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static int kszphy_resume(struct phy_device *phydev) +{ + int value; + + mutex_lock(&phydev->lock); + + value = phy_read(phydev, MII_BMCR); + phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); + + kszphy_config_intr(phydev); + mutex_unlock(&phydev->lock); + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -844,7 +870,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8061, .name = "Micrel KSZ8061", diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index fc8ad001bc94..d61da9ece3ba 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -443,9 +443,14 @@ static ssize_t ppp_read(struct file *file, char __user *buf, * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && - (ppp->flags & SC_LOOP_TRAFFIC) == 0) + (ppp->flags & SC_LOOP_TRAFFIC) == 0) { + ppp_recv_unlock(ppp); break; + } + ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) @@ -532,9 +537,12 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait) else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= POLLIN | POLLRDNORM; + ppp_recv_unlock(ppp); } return mask; @@ -2808,6 +2816,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, out2: mutex_unlock(&pn->all_ppp_mutex); + rtnl_unlock(); free_netdev(dev); out1: *retp = ret; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 224e7d82de6d..cf77f2dffa69 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -134,7 +134,6 @@ static void ax88172a_remove_mdio(struct usbnet *dev) netdev_info(dev->net, "deregistering mdio bus %s\n", priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index dc0212c3cc28..86ba30ba35e8 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -837,7 +837,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; - /* reset data interface */ + /* Reset data interface. Some devices will not reset properly + * unless they are configured first. Toggle the altsetting to + * force a reset + */ + usb_set_interface(dev->udev, iface_no, data_altsetting); temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); @@ -984,8 +988,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting); static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) { - int ret; - /* MBIM backwards compatible function? */ if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM) return -ENODEV; @@ -994,16 +996,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) * Additionally, generic NCM devices are assumed to accept arbitrarily * placed NDP. */ - ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); - - /* - * We should get an event when network connection is "connected" or - * "disconnected". Set network connection in "disconnected" state - * (carrier is OFF) during attach, so the IP network stack does not - * start IPv6 negotiation and more. - */ - usbnet_link_change(dev, 0, 0); - return ret; + return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); } static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max) @@ -1586,7 +1579,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", - .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET, + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_LINK_INTR, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1599,7 +1593,7 @@ static const struct driver_info cdc_ncm_info = { static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN, + | FLAG_LINK_INTR | FLAG_WWAN, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1612,7 +1606,7 @@ static const struct driver_info wwan_info = { static const struct driver_info wwan_noarp_info = { .description = "Mobile Broadband Network Device (NO ARP)", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN | FLAG_NOARP, + | FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 570deef53f74..a3a4ccf7cf52 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -861,8 +861,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ @@ -885,6 +887,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_FIXED_INTF(0x1e0e, 0x9001, 5)}, /* SIMCom 7230E */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 0b0ba7ef14e4..10798128c03f 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1769,6 +1769,13 @@ out3: if (info->unbind) info->unbind (dev, udev); out1: + /* subdrivers must undo all they did in bind() if they + * fail it, but we may fail later and a deferred kevent + * may trigger an error resubmitting itself and, worse, + * schedule a timer. So we kill it all just in case. + */ + cancel_work_sync(&dev->kevent); + del_timer_sync(&dev->delay); free_netdev(net); out: return status; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 0cbf520cea77..fc895d0e85d9 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -814,7 +814,7 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) /* - * parse and copy relevant protocol headers: + * parse relevant protocol headers: * For a tso pkt, relevant headers are L2/3/4 including options * For a pkt requesting csum offloading, they are L2/3 and may include L4 * if it's a TCP/UDP pkt @@ -827,15 +827,14 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) * Other effects: * 1. related *ctx fields are updated. * 2. ctx->copy_size is # of bytes copied - * 3. the portion copied is guaranteed to be in the linear part + * 3. the portion to be copied is guaranteed to be in the linear part * */ static int -vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, - struct vmxnet3_tx_ctx *ctx, - struct vmxnet3_adapter *adapter) +vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) { - struct Vmxnet3_TxDataDesc *tdd; u8 protocol = 0; if (ctx->mss) { /* TSO */ @@ -892,16 +891,34 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, return 0; } + return 1; +err: + return -1; +} + +/* + * copy relevant protocol headers to the transmit ring: + * For a tso pkt, relevant headers are L2/3/4 including options + * For a pkt requesting csum offloading, they are L2/3 and may include L4 + * if it's a TCP/UDP pkt + * + * + * Note that this requires that vmxnet3_parse_hdr be called first to set the + * appropriate bits in ctx first + */ +static void +vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_TxDataDesc *tdd; + tdd = tq->data_ring.base + tq->tx_ring.next2fill; memcpy(tdd->data, skb->data, ctx->copy_size); netdev_dbg(adapter->netdev, "copy %u bytes to dataRing[%u]\n", ctx->copy_size, tq->tx_ring.next2fill); - return 1; - -err: - return -1; } @@ -998,22 +1015,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } - spin_lock_irqsave(&tq->tx_lock, flags); - - if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { - tq->stats.tx_ring_full++; - netdev_dbg(adapter->netdev, - "tx queue stopped on %s, next2comp %u" - " next2fill %u\n", adapter->netdev->name, - tq->tx_ring.next2comp, tq->tx_ring.next2fill); - - vmxnet3_tq_stop(tq, adapter); - spin_unlock_irqrestore(&tq->tx_lock, flags); - return NETDEV_TX_BUSY; - } - - - ret = vmxnet3_parse_and_copy_hdr(skb, tq, &ctx, adapter); + ret = vmxnet3_parse_hdr(skb, tq, &ctx, adapter); if (ret >= 0) { BUG_ON(ret <= 0 && ctx.copy_size != 0); /* hdrs parsed, check against other limits */ @@ -1033,9 +1035,26 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } else { tq->stats.drop_hdr_inspect_err++; - goto unlock_drop_pkt; + goto drop_pkt; } + spin_lock_irqsave(&tq->tx_lock, flags); + + if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { + tq->stats.tx_ring_full++; + netdev_dbg(adapter->netdev, + "tx queue stopped on %s, next2comp %u" + " next2fill %u\n", adapter->netdev->name, + tq->tx_ring.next2comp, tq->tx_ring.next2fill); + + vmxnet3_tq_stop(tq, adapter); + spin_unlock_irqrestore(&tq->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + + vmxnet3_copy_hdr(skb, tq, &ctx, adapter); + /* fill tx descs related to addr & len */ if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter)) goto unlock_drop_pkt; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 66addb7a7911..bdcf617a9d52 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -104,20 +104,23 @@ static struct dst_ops vrf_dst_ops = { #if IS_ENABLED(CONFIG_IPV6) static bool check_ipv6_frame(const struct sk_buff *skb) { - const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data; - size_t hlen = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h; + struct ipv6hdr _ipv6h; bool rc = true; - if (skb->len < hlen) + ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h); + if (!ipv6h) goto out; if (ipv6h->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; + struct icmp6hdr _icmph; - if (skb->len < hlen + sizeof(*icmph)) + icmph = skb_header_pointer(skb, sizeof(_ipv6h), + sizeof(_icmph), &_icmph); + if (!icmph) goto out; - icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h)); switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e6944b29588e..1c32bd104797 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -931,8 +931,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + cb->args[1] = err; goto out; + } skip: ++idx; } @@ -1306,8 +1308,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) gbp = (struct vxlanhdr_gbp *)vxh; md->gbp = ntohs(gbp->policy_id); - if (tun_dst) + if (tun_dst) { tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + tun_dst->u.tun_info.options_len = sizeof(*md); + } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 4ed5180c547b..0ccc697fef76 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -107,7 +107,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant) sizeof(tx_ant_cmd), &tx_ant_cmd); } -static void iwl_free_fw_paging(struct iwl_mvm *mvm) +void iwl_free_fw_paging(struct iwl_mvm *mvm) { int i; @@ -127,6 +127,8 @@ static void iwl_free_fw_paging(struct iwl_mvm *mvm) get_order(mvm->fw_paging_db[i].fw_paging_size)); } kfree(mvm->trans->paging_download_buf); + mvm->trans->paging_download_buf = NULL; + memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db)); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 5f3ac8cccf49..ff7c6df9f941 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1225,6 +1225,9 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm, void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); +/* Paging */ +void iwl_free_fw_paging(struct iwl_mvm *mvm); + /* MVM debugfs */ #ifdef CONFIG_IWLWIFI_DEBUGFS int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 89ea70deeb84..e80be9a59520 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -684,6 +684,8 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) for (i = 0; i < NVM_MAX_NUM_SECTIONS; i++) kfree(mvm->nvm_sections[i].data); + iwl_free_fw_paging(mvm); + iwl_mvm_tof_clean(mvm); ieee80211_free_hw(mvm->hw); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 0914ec2fd574..a040edc55057 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -423,6 +423,15 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return -1; } + /* + * Increase the pending frames counter, so that later when a reply comes + * in and the counter is decreased - we don't start getting negative + * values. + * Note that we don't need to make sure it isn't agg'd, since we're + * TXing non-sta + */ + atomic_inc(&mvm->pending_frames[sta_id]); + return 0; } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 39c4be41ef83..365dc7e83ab4 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -305,6 +305,7 @@ EXPORT_SYMBOL(of_phy_find_device); * @dev: pointer to net_device claiming the phy * @phy_np: Pointer to device tree node for the PHY * @hndlr: Link state callback for the network device + * @flags: flags to pass to the PHY * @iface: PHY data interface type * * If successful, returns a pointer to the phy_device with the embedded diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 602eb4223510..f89db3af0607 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4772,8 +4772,10 @@ int pci_get_new_domain_nr(void) void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent) { static int use_dt_domains = -1; - int domain = of_get_pci_domain_nr(parent->of_node); + int domain = -1; + if (parent) + domain = of_get_pci_domain_nr(parent->of_node); /* * Check DT domain and use_dt_domains values. * diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 05796495be0e..4b717c699313 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -252,6 +252,10 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, case ACPI_RESOURCE_TYPE_GENERIC_REGISTER: break; + case ACPI_RESOURCE_TYPE_SERIAL_BUS: + /* serial bus connections (I2C/SPI/UART) are not pnp */ + break; + default: dev_warn(&dev->dev, "unknown resource type %d in _CRS\n", res->type); diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 6c592dc71aee..cdfd01f0adb8 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -133,6 +133,12 @@ struct rapl_domain_data { unsigned long timestamp; }; +struct msrl_action { + u32 msr_no; + u64 clear_mask; + u64 set_mask; + int err; +}; #define DOMAIN_STATE_INACTIVE BIT(0) #define DOMAIN_STATE_POWER_LIMIT_SET BIT(1) @@ -149,6 +155,7 @@ struct rapl_power_limit { static const char pl1_name[] = "long_term"; static const char pl2_name[] = "short_term"; +struct rapl_package; struct rapl_domain { const char *name; enum rapl_domain_type id; @@ -159,7 +166,7 @@ struct rapl_domain { u64 attr_map; /* track capabilities */ unsigned int state; unsigned int domain_energy_unit; - int package_id; + struct rapl_package *rp; }; #define power_zone_to_rapl_domain(_zone) \ container_of(_zone, struct rapl_domain, power_zone) @@ -184,6 +191,7 @@ struct rapl_package { * notify interrupt enable status. */ struct list_head plist; + int lead_cpu; /* one active cpu per package for access */ }; struct rapl_defaults { @@ -231,10 +239,10 @@ static int rapl_read_data_raw(struct rapl_domain *rd, static int rapl_write_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, unsigned long long value); -static u64 rapl_unit_xlate(struct rapl_domain *rd, int package, +static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type, u64 value, int to_raw); -static void package_power_limit_irq_save(int package_id); +static void package_power_limit_irq_save(struct rapl_package *rp); static LIST_HEAD(rapl_packages); /* guarded by CPU hotplug lock */ @@ -260,20 +268,6 @@ static struct rapl_package *find_package_by_id(int id) return NULL; } -/* caller to ensure CPU hotplug lock is held */ -static int find_active_cpu_on_package(int package_id) -{ - int i; - - for_each_online_cpu(i) { - if (topology_physical_package_id(i) == package_id) - return i; - } - /* all CPUs on this package are offline */ - - return -ENODEV; -} - /* caller must hold cpu hotplug lock */ static void rapl_cleanup_data(void) { @@ -312,25 +306,19 @@ static int get_max_energy_counter(struct powercap_zone *pcd_dev, u64 *energy) { struct rapl_domain *rd = power_zone_to_rapl_domain(pcd_dev); - *energy = rapl_unit_xlate(rd, 0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0); + *energy = rapl_unit_xlate(rd, ENERGY_UNIT, ENERGY_STATUS_MASK, 0); return 0; } static int release_zone(struct powercap_zone *power_zone) { struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone); - struct rapl_package *rp; + struct rapl_package *rp = rd->rp; /* package zone is the last zone of a package, we can free * memory here since all children has been unregistered. */ if (rd->id == RAPL_DOMAIN_PACKAGE) { - rp = find_package_by_id(rd->package_id); - if (!rp) { - dev_warn(&power_zone->dev, "no package id %s\n", - rd->name); - return -ENODEV; - } kfree(rd); rp->domains = NULL; } @@ -432,11 +420,7 @@ static int set_power_limit(struct powercap_zone *power_zone, int id, get_online_cpus(); rd = power_zone_to_rapl_domain(power_zone); - rp = find_package_by_id(rd->package_id); - if (!rp) { - ret = -ENODEV; - goto set_exit; - } + rp = rd->rp; if (rd->state & DOMAIN_STATE_BIOS_LOCKED) { dev_warn(&power_zone->dev, "%s locked by BIOS, monitoring only\n", @@ -456,7 +440,7 @@ static int set_power_limit(struct powercap_zone *power_zone, int id, ret = -EINVAL; } if (!ret) - package_power_limit_irq_save(rd->package_id); + package_power_limit_irq_save(rp); set_exit: put_online_cpus(); return ret; @@ -655,24 +639,19 @@ static void rapl_init_domains(struct rapl_package *rp) break; } if (mask) { - rd->package_id = rp->id; + rd->rp = rp; rd++; } } } -static u64 rapl_unit_xlate(struct rapl_domain *rd, int package, - enum unit_type type, u64 value, - int to_raw) +static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type, + u64 value, int to_raw) { u64 units = 1; - struct rapl_package *rp; + struct rapl_package *rp = rd->rp; u64 scale = 1; - rp = find_package_by_id(package); - if (!rp) - return value; - switch (type) { case POWER_UNIT: units = rp->power_unit; @@ -769,10 +748,8 @@ static int rapl_read_data_raw(struct rapl_domain *rd, msr = rd->msrs[rp->id]; if (!msr) return -EINVAL; - /* use physical package id to look up active cpus */ - cpu = find_active_cpu_on_package(rd->package_id); - if (cpu < 0) - return cpu; + + cpu = rd->rp->lead_cpu; /* special-case package domain, which uses a different bit*/ if (prim == FW_LOCK && rd->id == RAPL_DOMAIN_PACKAGE) { @@ -793,42 +770,66 @@ static int rapl_read_data_raw(struct rapl_domain *rd, final = value & rp->mask; final = final >> rp->shift; if (xlate) - *data = rapl_unit_xlate(rd, rd->package_id, rp->unit, final, 0); + *data = rapl_unit_xlate(rd, rp->unit, final, 0); else *data = final; return 0; } + +static int msrl_update_safe(u32 msr_no, u64 clear_mask, u64 set_mask) +{ + int err; + u64 val; + + err = rdmsrl_safe(msr_no, &val); + if (err) + goto out; + + val &= ~clear_mask; + val |= set_mask; + + err = wrmsrl_safe(msr_no, val); + +out: + return err; +} + +static void msrl_update_func(void *info) +{ + struct msrl_action *ma = info; + + ma->err = msrl_update_safe(ma->msr_no, ma->clear_mask, ma->set_mask); +} + /* Similar use of primitive info in the read counterpart */ static int rapl_write_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, unsigned long long value) { - u64 msr_val; - u32 msr; struct rapl_primitive_info *rp = &rpi[prim]; int cpu; + u64 bits; + struct msrl_action ma; + int ret; - cpu = find_active_cpu_on_package(rd->package_id); - if (cpu < 0) - return cpu; - msr = rd->msrs[rp->id]; - if (rdmsrl_safe_on_cpu(cpu, msr, &msr_val)) { - dev_dbg(&rd->power_zone.dev, - "failed to read msr 0x%x on cpu %d\n", msr, cpu); - return -EIO; - } - value = rapl_unit_xlate(rd, rd->package_id, rp->unit, value, 1); - msr_val &= ~rp->mask; - msr_val |= value << rp->shift; - if (wrmsrl_safe_on_cpu(cpu, msr, msr_val)) { - dev_dbg(&rd->power_zone.dev, - "failed to write msr 0x%x on cpu %d\n", msr, cpu); - return -EIO; - } + cpu = rd->rp->lead_cpu; + bits = rapl_unit_xlate(rd, rp->unit, value, 1); + bits |= bits << rp->shift; + memset(&ma, 0, sizeof(ma)); - return 0; + ma.msr_no = rd->msrs[rp->id]; + ma.clear_mask = rp->mask; + ma.set_mask = bits; + + ret = smp_call_function_single(cpu, msrl_update_func, &ma, 1); + if (ret) + WARN_ON_ONCE(ret); + else + ret = ma.err; + + return ret; } /* @@ -893,6 +894,21 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu) return 0; } +static void power_limit_irq_save_cpu(void *info) +{ + u32 l, h = 0; + struct rapl_package *rp = (struct rapl_package *)info; + + /* save the state of PLN irq mask bit before disabling it */ + rdmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h); + if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) { + rp->power_limit_irq = l & PACKAGE_THERM_INT_PLN_ENABLE; + rp->power_limit_irq |= PACKAGE_PLN_INT_SAVED; + } + l &= ~PACKAGE_THERM_INT_PLN_ENABLE; + wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); +} + /* REVISIT: * When package power limit is set artificially low by RAPL, LVT @@ -904,61 +920,40 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu) * to do by adding an atomic notifier. */ -static void package_power_limit_irq_save(int package_id) +static void package_power_limit_irq_save(struct rapl_package *rp) { - u32 l, h = 0; - int cpu; - struct rapl_package *rp; - - rp = find_package_by_id(package_id); - if (!rp) - return; - if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN)) return; - cpu = find_active_cpu_on_package(package_id); - if (cpu < 0) - return; - /* save the state of PLN irq mask bit before disabling it */ - rdmsr_safe_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h); - if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) { - rp->power_limit_irq = l & PACKAGE_THERM_INT_PLN_ENABLE; - rp->power_limit_irq |= PACKAGE_PLN_INT_SAVED; - } - l &= ~PACKAGE_THERM_INT_PLN_ENABLE; - wrmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); + smp_call_function_single(rp->lead_cpu, power_limit_irq_save_cpu, rp, 1); } -/* restore per package power limit interrupt enable state */ -static void package_power_limit_irq_restore(int package_id) +static void power_limit_irq_restore_cpu(void *info) { - u32 l, h; - int cpu; - struct rapl_package *rp; + u32 l, h = 0; + struct rapl_package *rp = (struct rapl_package *)info; - rp = find_package_by_id(package_id); - if (!rp) - return; + rdmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h); - if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN)) - return; + if (rp->power_limit_irq & PACKAGE_THERM_INT_PLN_ENABLE) + l |= PACKAGE_THERM_INT_PLN_ENABLE; + else + l &= ~PACKAGE_THERM_INT_PLN_ENABLE; + + wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); +} - cpu = find_active_cpu_on_package(package_id); - if (cpu < 0) +/* restore per package power limit interrupt enable state */ +static void package_power_limit_irq_restore(struct rapl_package *rp) +{ + if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN)) return; /* irq enable state not saved, nothing to restore */ if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) return; - rdmsr_safe_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h); - - if (rp->power_limit_irq & PACKAGE_THERM_INT_PLN_ENABLE) - l |= PACKAGE_THERM_INT_PLN_ENABLE; - else - l &= ~PACKAGE_THERM_INT_PLN_ENABLE; - wrmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); + smp_call_function_single(rp->lead_cpu, power_limit_irq_restore_cpu, rp, 1); } static void set_floor_freq_default(struct rapl_domain *rd, bool mode) @@ -1141,7 +1136,7 @@ static int rapl_unregister_powercap(void) * hotplug lock held */ list_for_each_entry(rp, &rapl_packages, plist) { - package_power_limit_irq_restore(rp->id); + package_power_limit_irq_restore(rp); for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { @@ -1392,7 +1387,8 @@ static int rapl_detect_topology(void) /* add the new package to the list */ new_package->id = phy_package_id; new_package->nr_cpus = 1; - + /* use the first active cpu of the package to access */ + new_package->lead_cpu = i; /* check if the package contains valid domains */ if (rapl_detect_domains(new_package, i) || rapl_defaults->check_unit(new_package, i)) { @@ -1448,6 +1444,8 @@ static int rapl_add_package(int cpu) /* add the new package to the list */ rp->id = phy_package_id; rp->nr_cpus = 1; + rp->lead_cpu = cpu; + /* check if the package contains valid domains */ if (rapl_detect_domains(rp, cpu) || rapl_defaults->check_unit(rp, cpu)) { @@ -1480,6 +1478,7 @@ static int rapl_cpu_callback(struct notifier_block *nfb, unsigned long cpu = (unsigned long)hcpu; int phy_package_id; struct rapl_package *rp; + int lead_cpu; phy_package_id = topology_physical_package_id(cpu); switch (action) { @@ -1500,6 +1499,15 @@ static int rapl_cpu_callback(struct notifier_block *nfb, break; if (--rp->nr_cpus == 0) rapl_remove_package(rp); + else if (cpu == rp->lead_cpu) { + /* choose another active cpu in the package */ + lead_cpu = cpumask_any_but(topology_core_cpumask(cpu), cpu); + if (lead_cpu < nr_cpu_ids) + rp->lead_cpu = lead_cpu; + else /* should never go here */ + pr_err("no active cpu available for package %d\n", + phy_package_id); + } } return NOTIFY_OK; diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index cb61f300f8b5..277b5c8c825c 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -67,7 +67,7 @@ static const u8 DASD_DIAG_CMS1[] = { 0xc3, 0xd4, 0xe2, 0xf1 };/* EBCDIC CMS1 */ * and function code cmd. * In case of an exception return 3. Otherwise return result of bitwise OR of * resulting condition code and DIAG return code. */ -static inline int dia250(void *iob, int cmd) +static inline int __dia250(void *iob, int cmd) { register unsigned long reg2 asm ("2") = (unsigned long) iob; typedef union { @@ -77,7 +77,6 @@ static inline int dia250(void *iob, int cmd) int rc; rc = 3; - diag_stat_inc(DIAG_STAT_X250); asm volatile( " diag 2,%2,0x250\n" "0: ipm %0\n" @@ -91,6 +90,12 @@ static inline int dia250(void *iob, int cmd) return rc; } +static inline int dia250(void *iob, int cmd) +{ + diag_stat_inc(DIAG_STAT_X250); + return __dia250(iob, cmd); +} + /* Initialize block I/O to DIAG device using the specified blocksize and * block offset. On success, return zero and set end_block to contain the * number of blocks on the device minus the specified offset. Return non-zero diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 6a4ff27f4357..c688efa95e29 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -204,8 +204,8 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, { struct spi_imx_data *spi_imx = spi_master_get_devdata(master); - if (spi_imx->dma_is_inited && - transfer->len > spi_imx->wml * sizeof(u32)) + if (spi_imx->dma_is_inited && transfer->len >= spi_imx->wml && + (transfer->len % spi_imx->wml) == 0) return true; return false; } @@ -919,8 +919,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL; int ret; unsigned long timeout; - u32 dma; - int left; struct spi_master *master = spi_imx->bitbang.master; struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg; @@ -954,13 +952,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, /* Trigger the cspi module. */ spi_imx->dma_finished = 0; - dma = readl(spi_imx->base + MX51_ECSPI_DMA); - dma = dma & (~MX51_ECSPI_DMA_RXT_WML_MASK); - /* Change RX_DMA_LENGTH trigger dma fetch tail data */ - left = transfer->len % spi_imx->wml; - if (left) - writel(dma | (left << MX51_ECSPI_DMA_RXT_WML_OFFSET), - spi_imx->base + MX51_ECSPI_DMA); /* * Set these order to avoid potential RX overflow. The overflow may * happen if we enable SPI HW before starting RX DMA due to rescheduling @@ -992,10 +983,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, spi_imx->devtype_data->reset(spi_imx); dmaengine_terminate_all(master->dma_rx); } - dma &= ~MX51_ECSPI_DMA_RXT_WML_MASK; - writel(dma | - spi_imx->wml << MX51_ECSPI_DMA_RXT_WML_OFFSET, - spi_imx->base + MX51_ECSPI_DMA); } spi_imx->dma_finished = 1; diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 79a8bc4f6cec..7cb1b2d710c1 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -749,6 +749,7 @@ static int rockchip_spi_probe(struct platform_device *pdev) return 0; err_register_master: + pm_runtime_disable(&pdev->dev); if (rs->dma_tx.ch) dma_release_channel(rs->dma_tx.ch); if (rs->dma_rx.ch) @@ -778,6 +779,8 @@ static int rockchip_spi_remove(struct platform_device *pdev) if (rs->dma_rx.ch) dma_release_channel(rs->dma_rx.ch); + spi_master_put(master); + return 0; } diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig index 0c675861623f..d8e4219c2324 100644 --- a/drivers/ssb/Kconfig +++ b/drivers/ssb/Kconfig @@ -83,6 +83,7 @@ config SSB_SDIOHOST config SSB_HOST_SOC bool "Support for SSB bus on SoC" depends on SSB && BCM47XX_NVRAM + select SSB_SPROM help Host interface for a SSB directly mapped into memory. This is for some Broadcom SoCs from the BCM47xx and BCM53xx lines. diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 82a663ba9800..4f229e711e1c 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -177,7 +177,6 @@ void core_tmr_abort_task( if (!__target_check_io_state(se_cmd, se_sess, 0)) { spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - target_put_sess_cmd(se_cmd); goto out; } list_del_init(&se_cmd->se_cmd_list); @@ -1056,6 +1056,7 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault); int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct file *file = vma->vm_file; + int error; /* * We pass NO_SECTOR to dax_radix_entry() because we expect that a @@ -1065,7 +1066,13 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) * saves us from having to make a call to get_block() here to look * up the sector. */ - dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, true); + error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, + true); + + if (error == -ENOMEM) + return VM_FAULT_OOM; + if (error) + return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index e032a0423e35..4098acc701c3 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -390,6 +390,7 @@ data_copy: *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); if (*err < 0) break; + bh = bh->b_this_page; } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index d211b8e18566..30c4c9ebb693 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n", __func__, ret); - /* Might as well let the VFS know */ - d_instantiate(new_dentry, d_inode(old_dentry)); - ihold(d_inode(old_dentry)); + /* + * We can't keep the target in dcache after that. + * For one thing, we can't afford dentry aliases for directories. + * For another, if there was a victim, we _can't_ set new inode + * for that sucker and we have to trigger mount eviction - the + * caller won't do it on its own since we are returning an error. + */ + d_invalidate(new_dentry); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 26c2de2de13f..b7f8eaeea5d8 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx, d_rehash(newdent); } else { spin_lock(&dentry->d_lock); - NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE; + NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE; spin_unlock(&dentry->d_lock); } } else { diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 9581d190f6e1..77ebc2bc1cca 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -147,6 +147,10 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else + ret = VM_FAULT_SIGBUS; goto out; } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index ed95272d57a6..52f6de5d40a9 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) * sole user of this dentry. Too tricky... Just unhash for * now. */ - d_drop(dentry); + if (!err) + d_drop(dentry); inode_unlock(dir); return err; @@ -903,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, if (!overwrite && new_is_dir && !old_opaque && new_opaque) ovl_remove_opaque(newdentry); + /* + * Old dentry now lives in different location. Dentries in + * lowerstack are stale. We cannot drop them here because + * access to them is lockless. This could be only pure upper + * or opaque directory - numlower is zero. Or upper non-dir + * entry - its pureness is tracked by flag opaque. + */ if (old_opaque != new_opaque) { ovl_dentry_set_opaque(old, new_opaque); if (!overwrite) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 49e204560655..a4ff5d0d7db9 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -65,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) inode_lock(upperdentry->d_inode); err = notify_change(upperdentry, attr, NULL); + if (!err) + ovl_copyattr(upperdentry->d_inode, dentry->d_inode); inode_unlock(upperdentry->d_inode); } ovl_drop_write(dentry); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 8d826bd56b26..619ad4b016d2 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) if (oe->__upperdentry) { type = __OVL_PATH_UPPER; - if (oe->numlower) { - if (S_ISDIR(dentry->d_inode->i_mode)) - type |= __OVL_PATH_MERGE; - } else if (!oe->opaque) { + /* + * Non-dir dentry can hold lower dentry from previous + * location. Its purity depends only on opaque flag. + */ + if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + else if (!oe->opaque) type |= __OVL_PATH_PURE; - } } else { if (oe->numlower > 1) type |= __OVL_PATH_MERGE; @@ -341,6 +343,7 @@ static const struct dentry_operations ovl_dentry_operations = { static const struct dentry_operations ovl_reval_dentry_operations = { .d_release = ovl_dentry_release, + .d_select_inode = ovl_d_select_inode, .d_revalidate = ovl_dentry_revalidate, .d_weak_revalidate = ovl_dentry_weak_revalidate, }; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 594f7e63b432..be5568839442 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1109,27 +1109,10 @@ xlog_verify_head( bool tmp_wrapped; /* - * Search backwards through the log looking for the log record header - * block. This wraps all the way back around to the head so something is - * seriously wrong if we can't find it. - */ - found = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, rhead_blk, - rhead, wrapped); - if (found < 0) - return found; - if (!found) { - xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); - return -EIO; - } - - *tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn)); - - /* - * Now that we have a tail block, check the head of the log for torn - * writes. Search again until we hit the tail or the maximum number of - * log record I/Os that could have been in flight at one time. Use a - * temporary buffer so we don't trash the rhead/bp pointer from the - * call above. + * Check the head of the log for torn writes. Search backwards from the + * head until we hit the tail or the maximum number of log record I/Os + * that could have been in flight at one time. Use a temporary buffer so + * we don't trash the rhead/bp pointers from the caller. */ tmp_bp = xlog_get_bp(log, 1); if (!tmp_bp) @@ -1216,6 +1199,115 @@ xlog_verify_head( } /* + * Check whether the head of the log points to an unmount record. In other + * words, determine whether the log is clean. If so, update the in-core state + * appropriately. + */ +static int +xlog_check_unmount_rec( + struct xlog *log, + xfs_daddr_t *head_blk, + xfs_daddr_t *tail_blk, + struct xlog_rec_header *rhead, + xfs_daddr_t rhead_blk, + struct xfs_buf *bp, + bool *clean) +{ + struct xlog_op_header *op_head; + xfs_daddr_t umount_data_blk; + xfs_daddr_t after_umount_blk; + int hblks; + int error; + char *offset; + + *clean = false; + + /* + * Look for unmount record. If we find it, then we know there was a + * clean unmount. Since 'i' could be the last block in the physical + * log, we convert to a log block before comparing to the head_blk. + * + * Save the current tail lsn to use to pass to xlog_clear_stale_blocks() + * below. We won't want to clear the unmount record if there is one, so + * we pass the lsn of the unmount record rather than the block after it. + */ + if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { + int h_size = be32_to_cpu(rhead->h_size); + int h_version = be32_to_cpu(rhead->h_version); + + if ((h_version & XLOG_VERSION_2) && + (h_size > XLOG_HEADER_CYCLE_SIZE)) { + hblks = h_size / XLOG_HEADER_CYCLE_SIZE; + if (h_size % XLOG_HEADER_CYCLE_SIZE) + hblks++; + } else { + hblks = 1; + } + } else { + hblks = 1; + } + after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); + after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); + if (*head_blk == after_umount_blk && + be32_to_cpu(rhead->h_num_logops) == 1) { + umount_data_blk = rhead_blk + hblks; + umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); + error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + if (error) + return error; + + op_head = (struct xlog_op_header *)offset; + if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) { + /* + * Set tail and last sync so that newly written log + * records will point recovery to after the current + * unmount record. + */ + xlog_assign_atomic_lsn(&log->l_tail_lsn, + log->l_curr_cycle, after_umount_blk); + xlog_assign_atomic_lsn(&log->l_last_sync_lsn, + log->l_curr_cycle, after_umount_blk); + *tail_blk = after_umount_blk; + + *clean = true; + } + } + + return 0; +} + +static void +xlog_set_state( + struct xlog *log, + xfs_daddr_t head_blk, + struct xlog_rec_header *rhead, + xfs_daddr_t rhead_blk, + bool bump_cycle) +{ + /* + * Reset log values according to the state of the log when we + * crashed. In the case where head_blk == 0, we bump curr_cycle + * one because the next write starts a new cycle rather than + * continuing the cycle of the last good log record. At this + * point we have guaranteed that all partial log records have been + * accounted for. Therefore, we know that the last good log record + * written was complete and ended exactly on the end boundary + * of the physical log. + */ + log->l_prev_block = rhead_blk; + log->l_curr_block = (int)head_blk; + log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); + if (bump_cycle) + log->l_curr_cycle++; + atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); + atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); + xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle, + BBTOB(log->l_curr_block)); + xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle, + BBTOB(log->l_curr_block)); +} + +/* * Find the sync block number or the tail of the log. * * This will be the block number of the last record to have its @@ -1238,22 +1330,20 @@ xlog_find_tail( xfs_daddr_t *tail_blk) { xlog_rec_header_t *rhead; - xlog_op_header_t *op_head; char *offset = NULL; xfs_buf_t *bp; int error; - xfs_daddr_t umount_data_blk; - xfs_daddr_t after_umount_blk; xfs_daddr_t rhead_blk; xfs_lsn_t tail_lsn; - int hblks; bool wrapped = false; + bool clean = false; /* * Find previous log record */ if ((error = xlog_find_head(log, head_blk))) return error; + ASSERT(*head_blk < INT_MAX); bp = xlog_get_bp(log, 1); if (!bp) @@ -1271,100 +1361,75 @@ xlog_find_tail( } /* - * Trim the head block back to skip over torn records. We can have - * multiple log I/Os in flight at any time, so we assume CRC failures - * back through the previous several records are torn writes and skip - * them. + * Search backwards through the log looking for the log record header + * block. This wraps all the way back around to the head so something is + * seriously wrong if we can't find it. */ - ASSERT(*head_blk < INT_MAX); - error = xlog_verify_head(log, head_blk, tail_blk, bp, &rhead_blk, - &rhead, &wrapped); - if (error) - goto done; + error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, + &rhead_blk, &rhead, &wrapped); + if (error < 0) + return error; + if (!error) { + xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); + return -EIO; + } + *tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn)); /* - * Reset log values according to the state of the log when we - * crashed. In the case where head_blk == 0, we bump curr_cycle - * one because the next write starts a new cycle rather than - * continuing the cycle of the last good log record. At this - * point we have guaranteed that all partial log records have been - * accounted for. Therefore, we know that the last good log record - * written was complete and ended exactly on the end boundary - * of the physical log. + * Set the log state based on the current head record. */ - log->l_prev_block = rhead_blk; - log->l_curr_block = (int)*head_blk; - log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); - if (wrapped) - log->l_curr_cycle++; - atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); - atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); - xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle, - BBTOB(log->l_curr_block)); - xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle, - BBTOB(log->l_curr_block)); + xlog_set_state(log, *head_blk, rhead, rhead_blk, wrapped); + tail_lsn = atomic64_read(&log->l_tail_lsn); /* - * Look for unmount record. If we find it, then we know there - * was a clean unmount. Since 'i' could be the last block in - * the physical log, we convert to a log block before comparing - * to the head_blk. + * Look for an unmount record at the head of the log. This sets the log + * state to determine whether recovery is necessary. + */ + error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead, + rhead_blk, bp, &clean); + if (error) + goto done; + + /* + * Verify the log head if the log is not clean (e.g., we have anything + * but an unmount record at the head). This uses CRC verification to + * detect and trim torn writes. If discovered, CRC failures are + * considered torn writes and the log head is trimmed accordingly. * - * Save the current tail lsn to use to pass to - * xlog_clear_stale_blocks() below. We won't want to clear the - * unmount record if there is one, so we pass the lsn of the - * unmount record rather than the block after it. + * Note that we can only run CRC verification when the log is dirty + * because there's no guarantee that the log data behind an unmount + * record is compatible with the current architecture. */ - if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { - int h_size = be32_to_cpu(rhead->h_size); - int h_version = be32_to_cpu(rhead->h_version); + if (!clean) { + xfs_daddr_t orig_head = *head_blk; - if ((h_version & XLOG_VERSION_2) && - (h_size > XLOG_HEADER_CYCLE_SIZE)) { - hblks = h_size / XLOG_HEADER_CYCLE_SIZE; - if (h_size % XLOG_HEADER_CYCLE_SIZE) - hblks++; - } else { - hblks = 1; - } - } else { - hblks = 1; - } - after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); - after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); - tail_lsn = atomic64_read(&log->l_tail_lsn); - if (*head_blk == after_umount_blk && - be32_to_cpu(rhead->h_num_logops) == 1) { - umount_data_blk = rhead_blk + hblks; - umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); - error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + error = xlog_verify_head(log, head_blk, tail_blk, bp, + &rhead_blk, &rhead, &wrapped); if (error) goto done; - op_head = (xlog_op_header_t *)offset; - if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) { - /* - * Set tail and last sync so that newly written - * log records will point recovery to after the - * current unmount record. - */ - xlog_assign_atomic_lsn(&log->l_tail_lsn, - log->l_curr_cycle, after_umount_blk); - xlog_assign_atomic_lsn(&log->l_last_sync_lsn, - log->l_curr_cycle, after_umount_blk); - *tail_blk = after_umount_blk; - - /* - * Note that the unmount was clean. If the unmount - * was not clean, we need to know this to rebuild the - * superblock counters from the perag headers if we - * have a filesystem using non-persistent counters. - */ - log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN; + /* update in-core state again if the head changed */ + if (*head_blk != orig_head) { + xlog_set_state(log, *head_blk, rhead, rhead_blk, + wrapped); + tail_lsn = atomic64_read(&log->l_tail_lsn); + error = xlog_check_unmount_rec(log, head_blk, tail_blk, + rhead, rhead_blk, bp, + &clean); + if (error) + goto done; } } /* + * Note that the unmount was clean. If the unmount was not clean, we + * need to know this to rebuild the superblock counters from the perag + * headers if we have a filesystem using non-persistent counters. + */ + if (clean) + log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN; + + /* * Make sure that there are no blocks in front of the head * with the same cycle number as the head. This can happen * because we allow multiple outstanding log writes concurrently, diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 5bfc61943f88..34f601e7b88d 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -262,7 +262,7 @@ #define ACPI_GET_FUNCTION_NAME _acpi_function_name /* - * The Name parameter should be the procedure name as a quoted string. + * The Name parameter should be the procedure name as a non-quoted string. * The function name is also used by the function exit macros below. * Note: (const char) is used to be compatible with the debug interfaces * and macros such as __func__. diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index c96621e87c19..17556979dc79 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -897,11 +897,9 @@ ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3) acpi_warning(const char *module_name, u32 line_number, const char *format, ...)) -ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3) +ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(1) void ACPI_INTERNAL_VAR_XFACE - acpi_info(const char *module_name, - u32 line_number, - const char *format, ...)) + acpi_info(const char *format, ...)) ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3) void ACPI_INTERNAL_VAR_XFACE acpi_bios_error(const char *module_name, diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 07fb100bcc68..6f1805dd5d3c 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -9,6 +9,7 @@ #define ACPI_PROCESSOR_CLASS "processor" #define ACPI_PROCESSOR_DEVICE_NAME "Processor" #define ACPI_PROCESSOR_DEVICE_HID "ACPI0007" +#define ACPI_PROCESSOR_CONTAINER_HID "ACPI0010" #define ACPI_PROCESSOR_BUSY_METRIC 10 @@ -394,14 +395,6 @@ static inline int acpi_processor_hotplug(struct acpi_processor *pr) } #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ -#if defined(CONFIG_PM_SLEEP) & defined(CONFIG_ACPI_PROCESSOR_IDLE) -void acpi_processor_syscore_init(void); -void acpi_processor_syscore_exit(void); -#else -static inline void acpi_processor_syscore_init(void) {} -static inline void acpi_processor_syscore_exit(void) {} -#endif - /* in processor_thermal.c */ int acpi_processor_get_limit_info(struct acpi_processor *pr); extern const struct thermal_cooling_device_ops processor_cooling_ops; diff --git a/include/linux/bio.h b/include/linux/bio.h index cb6888824108..88bc64f00bb5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -320,11 +320,6 @@ static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) struct bvec_iter iter = bio->bi_iter; int idx; - if (!bio_flagged(bio, BIO_CLONED)) { - *bv = bio->bi_io_vec[bio->bi_vcnt - 1]; - return; - } - if (unlikely(!bio_multiple_segments(bio))) { *bv = bio_iovec(bio); return; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 88a4215125bc..718e8725de8a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -80,7 +80,6 @@ struct cpufreq_policy { unsigned int last_policy; /* policy before unplug */ struct cpufreq_governor *governor; /* see below */ void *governor_data; - bool governor_enabled; /* governor start/stop flag */ char last_governor[CPUFREQ_NAME_LEN]; /* last governor used */ struct work_struct update; /* if update_policy() needs to be @@ -100,10 +99,6 @@ struct cpufreq_policy { * - Any routine that will write to the policy structure and/or may take away * the policy altogether (eg. CPU hotplug), will hold this lock in write * mode before doing so. - * - * Additional rules: - * - Lock should not be held across - * __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT); */ struct rw_semaphore rwsem; @@ -464,29 +459,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); -/* CPUFREQ DEFAULT GOVERNOR */ -/* - * Performance governor is fallback governor if any other gov failed to auto - * load due latency restrictions - */ -#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE -extern struct cpufreq_governor cpufreq_gov_performance; -#endif -#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_performance) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE) -extern struct cpufreq_governor cpufreq_gov_powersave; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_powersave) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE) -extern struct cpufreq_governor cpufreq_gov_userspace; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_userspace) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND) -extern struct cpufreq_governor cpufreq_gov_ondemand; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_ondemand) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE) -extern struct cpufreq_governor cpufreq_gov_conservative; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative) -#endif +struct cpufreq_governor *cpufreq_default_governor(void); +struct cpufreq_governor *cpufreq_fallback_governor(void); /********************************************************************* * FREQUENCY TABLE HELPERS * @@ -525,16 +499,6 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, } #endif -static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos) -{ - while ((*pos)->frequency != CPUFREQ_TABLE_END) - if ((*pos)->frequency != CPUFREQ_ENTRY_INVALID) - return true; - else - (*pos)++; - return false; -} - /* * cpufreq_for_each_entry - iterate over a cpufreq_frequency_table * @pos: the cpufreq_frequency_table * to use as a loop cursor. @@ -551,8 +515,11 @@ static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos) * @table: the cpufreq_frequency_table * to iterate over. */ -#define cpufreq_for_each_valid_entry(pos, table) \ - for (pos = table; cpufreq_next_valid(&pos); pos++) +#define cpufreq_for_each_valid_entry(pos, table) \ + for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++) \ + if (pos->frequency == CPUFREQ_ENTRY_INVALID) \ + continue; \ + else int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 75857cda38e9..728ef074602a 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -386,7 +386,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size, if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) return; - if (!ops->free) + if (!ops->free || !cpu_addr) return; debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0e95fcc75b2a..358076eda364 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -125,6 +125,16 @@ struct irqaction { extern irqreturn_t no_action(int cpl, void *dev_id); +/* + * If a (PCI) device interrupt is not connected we set dev->irq to + * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we + * can distingiush that case from other error returns. + * + * 0x80000000 is guaranteed to be outside the available range of interrupts + * and easy to distinguish from other possible incorrect values. + */ +#define IRQ_NOTCONNECTED (1U << 31) + extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4b9f85c963d0..0fdc798e3ff7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -1,6 +1,7 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H +#include <linux/sched.h> #include <linux/types.h> struct kmem_cache; @@ -13,7 +14,6 @@ struct vm_struct; #include <asm/kasan.h> #include <asm/pgtable.h> -#include <linux/sched.h> extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; @@ -43,6 +43,8 @@ static inline void kasan_disable_current(void) void kasan_unpoison_shadow(const void *address, size_t size); +void kasan_unpoison_task_stack(struct task_struct *task); + void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); @@ -66,6 +68,8 @@ void kasan_free_shadow(const struct vm_struct *vm); static inline void kasan_unpoison_shadow(const void *address, size_t size) {} +static inline void kasan_unpoison_task_stack(struct task_struct *task) {} + static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} diff --git a/include/linux/list.h b/include/linux/list.h index 30cf4200ab40..5356f4d661a7 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -113,17 +113,6 @@ extern void __list_del_entry(struct list_head *entry); extern void list_del(struct list_head *entry); #endif -#ifdef CONFIG_DEBUG_LIST -/* - * See devm_memremap_pages() which wants DEBUG_LIST=y to assert if one - * of the pages it allocates is ever passed to list_add() - */ -extern void list_force_poison(struct list_head *entry); -#else -/* fallback to the less strict LIST_POISON* definitions */ -#define list_force_poison list_del -#endif - /** * list_replace - replace old entry by new one * @old : the element to be replaced diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..58eef02edc7e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4245,7 +4245,9 @@ struct mlx5_ifc_modify_tir_bitmask_bits { u8 reserved_at_20[0x1b]; u8 self_lb_en[0x1]; - u8 reserved_at_3c[0x3]; + u8 reserved_at_3c[0x1]; + u8 hash[0x1]; + u8 reserved_at_3e[0x1]; u8 lro[0x1]; }; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index db21d3995f7e..49cd8890b873 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -19,6 +19,8 @@ /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ +#define GENPD_MAX_NUM_STATES 8 /* Number of possible low power states */ + enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ GPD_STATE_POWER_OFF, /* PM domain is off */ @@ -37,6 +39,11 @@ struct gpd_dev_ops { bool (*active_wakeup)(struct device *dev); }; +struct genpd_power_state { + s64 power_off_latency_ns; + s64 power_on_latency_ns; +}; + struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ @@ -54,9 +61,7 @@ struct generic_pm_domain { unsigned int prepared_count; /* Suspend counter of prepared devices */ bool suspend_power_off; /* Power status before system suspend */ int (*power_off)(struct generic_pm_domain *domain); - s64 power_off_latency_ns; int (*power_on)(struct generic_pm_domain *domain); - s64 power_on_latency_ns; struct gpd_dev_ops dev_ops; s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ bool max_off_time_changed; @@ -66,6 +71,10 @@ struct generic_pm_domain { void (*detach_dev)(struct generic_pm_domain *domain, struct device *dev); unsigned int flags; /* Bit field of configs for genpd */ + struct genpd_power_state states[GENPD_MAX_NUM_STATES]; + unsigned int state_count; /* number of states */ + unsigned int state_idx; /* state that genpd will go to when off */ + }; static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 95403d2ccaf5..cccaf4a29e9f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -34,6 +34,8 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev); struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, @@ -60,6 +62,9 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, void dev_pm_opp_put_supported_hw(struct device *dev); int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); +int dev_pm_opp_set_regulator(struct device *dev, const char *name); +void dev_pm_opp_put_regulator(struct device *dev); +int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -86,6 +91,16 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) return 0; } +static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) +{ + return 0; +} + +static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev) +{ + return 0; +} + static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) { return NULL; @@ -151,6 +166,18 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) static inline void dev_pm_opp_put_prop_name(struct device *dev) {} +static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_regulator(struct device *dev) {} + +static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) +{ + return -EINVAL; +} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) diff --git a/include/linux/sched.h b/include/linux/sched.h index a10494a94cc3..913e755ef7b8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3207,4 +3207,13 @@ static inline unsigned long rlimit_max(unsigned int limit) return task_rlimit_max(current, limit); } +#ifdef CONFIG_CPU_FREQ +struct update_util_data { + void (*func)(struct update_util_data *data, + u64 time, unsigned long util, unsigned long max); +}; + +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); +#endif /* CONFIG_CPU_FREQ */ + #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4ce9ff7086f4..d3fcd4591ce4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1985,6 +1985,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +/** + * skb_tailroom_reserve - adjust reserved_tailroom + * @skb: buffer to alter + * @mtu: maximum amount of headlen permitted + * @needed_tailroom: minimum amount of reserved_tailroom + * + * Set reserved_tailroom so that headlen can be as large as possible but + * not larger than mtu and tailroom cannot be smaller than + * needed_tailroom. + * The required headroom should already have been reserved before using + * this function. + */ +static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, + unsigned int needed_tailroom) +{ + SKB_LINEAR_ASSERT(skb); + if (mtu < skb_tailroom(skb) - needed_tailroom) + /* use at most mtu */ + skb->reserved_tailroom = skb_tailroom(skb) - mtu; + else + /* use up to all available space */ + skb->reserved_tailroom = needed_tailroom; +} + #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index eead8ab93c0a..881a79d52467 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -100,6 +100,7 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index acfdbf353a0b..be586c632a0c 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -134,9 +134,6 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ - if (!cpu_online(raw_smp_processor_id())) \ - return; \ - \ if (!(cond)) \ return; \ prercu; \ @@ -343,15 +340,19 @@ extern void syscall_unregfunc(void); * "void *__data, proto" as the callback prototype. */ #define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , 1, void *__data, __data) + __DECLARE_TRACE(name, void, , \ + cpu_online(raw_smp_processor_id()), \ + void *__data, __data) #define DECLARE_TRACE(name, proto, args) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) #define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc38fc..e0f4109e64c6 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h index 317a1ed2f4ac..9130dd5a184a 100644 --- a/include/trace/events/asoc.h +++ b/include/trace/events/asoc.h @@ -231,13 +231,13 @@ TRACE_EVENT(snd_soc_jack_report, TP_ARGS(jack, mask, val), TP_STRUCT__entry( - __string( name, jack->jack->name ) + __string( name, jack->jack->id ) __field( int, mask ) __field( int, val ) ), TP_fast_assign( - __assign_str(name, jack->jack->name); + __assign_str(name, jack->jack->id); __entry->mask = mask; __entry->val = val; ), @@ -253,12 +253,12 @@ TRACE_EVENT(snd_soc_jack_notify, TP_ARGS(jack, val), TP_STRUCT__entry( - __string( name, jack->jack->name ) + __string( name, jack->jack->id ) __field( int, val ) ), TP_fast_assign( - __assign_str(name, jack->jack->name); + __assign_str(name, jack->jack->id); __entry->val = val; ), diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 284244ebfe8d..19e50300ce7d 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -38,6 +38,28 @@ DEFINE_EVENT(cpu, cpu_idle, TP_ARGS(state, cpu_id) ); +TRACE_EVENT(powernv_throttle, + + TP_PROTO(int chip_id, const char *reason, int pmax), + + TP_ARGS(chip_id, reason, pmax), + + TP_STRUCT__entry( + __field(int, chip_id) + __string(reason, reason) + __field(int, pmax) + ), + + TP_fast_assign( + __entry->chip_id = chip_id; + __assign_str(reason, reason); + __entry->pmax = pmax; + ), + + TP_printk("Chip %d Pmax %d %s", __entry->chip_id, + __entry->pmax, __get_str(reason)) +); + TRACE_EVENT(pstate_sample, TP_PROTO(u32 core_busy, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aa6f8571de13..5df4881dea7b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -292,6 +292,9 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 625b38f65764..a8e3a8c0d85a 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -120,7 +120,7 @@ struct media_device_info { #define MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN MEDIA_ENT_F_OLD_SUBDEV_BASE -#ifndef __KERNEL__ +#if !defined(__KERNEL__) || defined(__NEED_MEDIA_LEGACY_API) /* * Legacy symbols used to avoid userspace compilation breakages @@ -133,6 +133,10 @@ struct media_device_info { #define MEDIA_ENT_TYPE_MASK 0x00ff0000 #define MEDIA_ENT_SUBTYPE_MASK 0x0000ffff +/* End of the old subdev reserved numberspace */ +#define MEDIA_ENT_T_DEVNODE_UNKNOWN (MEDIA_ENT_T_DEVNODE | \ + MEDIA_ENT_SUBTYPE_MASK) + #define MEDIA_ENT_T_DEVNODE MEDIA_ENT_F_OLD_BASE #define MEDIA_ENT_T_DEVNODE_V4L MEDIA_ENT_F_IO_V4L #define MEDIA_ENT_T_DEVNODE_FB (MEDIA_ENT_T_DEVNODE + 2) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 841187239adc..e79e60f50bce 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1609,6 +1609,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, struct irq_desc *desc; int retval; + if (irq == IRQ_NOTCONNECTED) + return -ENOTCONN; + /* * Sanity-check: shared interrupts must pass in a real dev-ID, * otherwise we'll have trouble later trying to figure out @@ -1699,9 +1702,13 @@ EXPORT_SYMBOL(request_threaded_irq); int request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id) { - struct irq_desc *desc = irq_to_desc(irq); + struct irq_desc *desc; int ret; + if (irq == IRQ_NOTCONNECTED) + return -ENOTCONN; + + desc = irq_to_desc(irq); if (!desc) return -EINVAL; diff --git a/kernel/memremap.c b/kernel/memremap.c index b981a7b023f0..6cf54615a9c4 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -29,10 +29,10 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) static void *try_ram_remap(resource_size_t offset, size_t size) { - struct page *page = pfn_to_page(offset >> PAGE_SHIFT); + unsigned long pfn = PHYS_PFN(offset); /* In the simple case just return the existing linear address */ - if (!PageHighMem(page)) + if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn))) return __va(offset); return NULL; /* fallback to ioremap_cache */ } @@ -270,13 +270,16 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { - int is_ram = region_intersects(res->start, resource_size(res), - "System RAM"); resource_size_t key, align_start, align_size, align_end; struct dev_pagemap *pgmap; struct page_map *page_map; + int error, nid, is_ram; unsigned long pfn; - int error, nid; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) + - align_start; + is_ram = region_intersects(align_start, align_size, "System RAM"); if (is_ram == REGION_MIXED) { WARN_ONCE(1, "%s attempted on mixed region %pr\n", @@ -314,8 +317,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); align_end = align_start + align_size - 1; for (key = align_start; key <= align_end; key += SECTION_SIZE) { struct dev_pagemap *dup; @@ -351,8 +352,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, for_each_device_pfn(pfn, page_map) { struct page *page = pfn_to_page(pfn); - /* ZONE_DEVICE pages must never appear on a slab lru */ - list_force_poison(&page->lru); + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back + * pointer. It is a bug if a ZONE_DEVICE page is ever + * freed or placed on a driver-private list. Seed the + * storage with LIST_POISON* values. + */ + list_del(&page->lru); page->pgmap = pgmap; } devres_add(dev, page_map); diff --git a/kernel/power/process.c b/kernel/power/process.c index 564f786df470..df058bed53ce 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -30,13 +30,12 @@ static int try_to_freeze_tasks(bool user_only) unsigned long end_time; unsigned int todo; bool wq_busy = false; - struct timeval start, end; - u64 elapsed_msecs64; + ktime_t start, end, elapsed; unsigned int elapsed_msecs; bool wakeup = false; int sleep_usecs = USEC_PER_MSEC; - do_gettimeofday(&start); + start = ktime_get_boottime(); end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs); @@ -78,10 +77,9 @@ static int try_to_freeze_tasks(bool user_only) sleep_usecs *= 2; } - do_gettimeofday(&end); - elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start); - do_div(elapsed_msecs64, NSEC_PER_MSEC); - elapsed_msecs = elapsed_msecs64; + end = ktime_get_boottime(); + elapsed = ktime_sub(end, start); + elapsed_msecs = ktime_to_ms(elapsed); if (todo) { pr_cont("\n"); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f9fe133c13e2..230a77225e2e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -248,7 +248,7 @@ static int suspend_test(int level) { #ifdef CONFIG_PM_DEBUG if (pm_test_level == level) { - printk(KERN_INFO "suspend debug: Waiting for %d second(s).\n", + pr_info("suspend debug: Waiting for %d second(s).\n", pm_test_delay); mdelay(pm_test_delay * 1000); return 1; @@ -320,7 +320,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) error = dpm_suspend_late(PMSG_SUSPEND); if (error) { - printk(KERN_ERR "PM: late suspend of devices failed\n"); + pr_err("PM: late suspend of devices failed\n"); goto Platform_finish; } error = platform_suspend_prepare_late(state); @@ -329,7 +329,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) error = dpm_suspend_noirq(PMSG_SUSPEND); if (error) { - printk(KERN_ERR "PM: noirq suspend of devices failed\n"); + pr_err("PM: noirq suspend of devices failed\n"); goto Platform_early_resume; } error = platform_suspend_prepare_noirq(state); diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 67687973ce80..9507522164ac 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o +obj-$(CONFIG_CPU_FREQ) += cpufreq.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9503d590e5ef..41f6b2215aa8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,6 +26,7 @@ * Thomas Gleixner, Mike Kravetz */ +#include <linux/kasan.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nmi.h> @@ -5096,6 +5097,8 @@ void init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); + kasan_unpoison_task_stack(idle); + #ifdef CONFIG_SMP /* * Its possible that init_idle() gets called multiple times on a task, diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c new file mode 100644 index 000000000000..928c4ba32f68 --- /dev/null +++ b/kernel/sched/cpufreq.c @@ -0,0 +1,37 @@ +/* + * Scheduler code and data structures related to cpufreq. + * + * Copyright (C) 2016, Intel Corporation + * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "sched.h" + +DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer. + * @cpu: The CPU to set the pointer for. + * @data: New pointer value. + * + * Set and publish the update_util_data pointer for the given CPU. That pointer + * points to a struct update_util_data object containing a callback function + * to call from cpufreq_update_util(). That function will be called from an RCU + * read-side critical section, so it must not sleep. + * + * Callers must use RCU-sched callbacks to free any memory that might be + * accessed via the old update_util_data pointer or invoke synchronize_sched() + * right after this function to avoid use-after-free. + */ +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data) +{ + if (WARN_ON(data && !data->func)) + return; + + rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data); +} +EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 57b939c81bce..2037cf432a45 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -726,6 +726,10 @@ static void update_curr_dl(struct rq *rq) if (!dl_task(curr) || !on_dl_rq(dl_se)) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + /* * Consumed budget is computed considering the time as * observed by schedulable tasks (excluding time spent diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56b7d4b83947..e2987a7e489d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2824,7 +2824,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) { struct cfs_rq *cfs_rq = cfs_rq_of(se); u64 now = cfs_rq_clock_task(cfs_rq); - int cpu = cpu_of(rq_of(cfs_rq)); + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); /* * Track task load average for carrying it to new CPU after migrated, and @@ -2836,6 +2837,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg) update_tg_load_avg(cfs_rq, 0); + + if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) { + unsigned long max = rq->cpu_capacity_orig; + + /* + * There are a few boundary cases this might miss but it should + * get called often enough that that should (hopefully) not be + * a real problem -- added to that it only calls on the local + * CPU, so if we enqueue remotely we'll miss an update, but + * the next tick/schedule should update. + * + * It will not get called when we go idle, because the idle + * thread is a different class (!fair), nor will the utilization + * number include things like RT tasks. + * + * As is, the util number is not freq-invariant (we'd have to + * implement arch_scale_freq_capacity() for that). + * + * See cpu_util(). + */ + cpufreq_update_util(rq_clock(rq), + min(cfs_rq->avg.util_avg, max), max); + } } static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86abe0ea1..27f5b03cbdbe 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -945,6 +945,10 @@ static void update_curr_rt(struct rq *rq) if (curr->sched_class != &rt_sched_class) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + delta_exec = rq_clock_task(rq) - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 10f16374df7f..faf7e2758dd0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1738,3 +1738,51 @@ static inline u64 irq_time_read(int cpu) } #endif /* CONFIG_64BIT */ #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_CPU_FREQ +DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_update_util - Take a note about CPU utilization changes. + * @time: Current time. + * @util: Current utilization. + * @max: Utilization ceiling. + * + * This function is called by the scheduler on every invocation of + * update_load_avg() on the CPU whose utilization is being updated. + * + * It can only be called from RCU-sched read-side critical sections. + */ +static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) +{ + struct update_util_data *data; + + data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + if (data) + data->func(data, time, util, max); +} + +/** + * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. + * @time: Current time. + * + * The way cpufreq is currently arranged requires it to evaluate the CPU + * performance state (frequency/voltage) on a regular basis to prevent it from + * being stuck in a completely inadequate performance level for too long. + * That is not guaranteed to happen if the updates are only triggered from CFS, + * though, because they may not be coming in if RT or deadline tasks are active + * all the time (or there are RT and DL tasks only). + * + * As a workaround for that issue, this function is called by the RT and DL + * sched classes to trigger extra cpufreq updates to prevent it from stalling, + * but that really is a band-aid. Going forward it should be replaced with + * solutions targeted more specifically at RT and DL tasks. + */ +static inline void cpufreq_trigger_update(u64 time) +{ + cpufreq_update_util(time, ULONG_MAX, 0); +} +#else +static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {} +static inline void cpufreq_trigger_update(u64 time) {} +#endif /* CONFIG_CPU_FREQ */ diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c index eb4220a132ec..81b87451c0ea 100644 --- a/kernel/trace/power-traces.c +++ b/kernel/trace/power-traces.c @@ -15,4 +15,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume); EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle); +EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle); diff --git a/lib/cpumask.c b/lib/cpumask.c index 5a70f6196f57..81dedaab36cc 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -41,6 +41,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) break; return i; } +EXPORT_SYMBOL(cpumask_any_but); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK diff --git a/lib/list_debug.c b/lib/list_debug.c index 3345a089ef7b..3859bf63561c 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -12,13 +12,6 @@ #include <linux/kernel.h> #include <linux/rculist.h> -static struct list_head force_poison; -void list_force_poison(struct list_head *entry) -{ - entry->next = &force_poison; - entry->prev = &force_poison; -} - /* * Insert a new entry between two known consecutive entries. * @@ -30,8 +23,6 @@ void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { - WARN(new->next == &force_poison || new->prev == &force_poison, - "list_add attempted on force-poisoned entry\n"); WARN(next->prev != prev, "list_add corruption. next->prev should be " "prev (%p), but was %p. (next=%p).\n", diff --git a/mm/filemap.c b/mm/filemap.c index 3461d97ecb30..da7a35d83de7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -195,6 +195,30 @@ void __delete_from_page_cache(struct page *page, void *shadow, else cleancache_invalidate_page(mapping, page); + VM_BUG_ON_PAGE(page_mapped(page), page); + if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { + int mapcount; + + pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", + current->comm, page_to_pfn(page)); + dump_page(page, "still mapped when deleted"); + dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + + mapcount = page_mapcount(page); + if (mapping_exiting(mapping) && + page_count(page) >= mapcount + 2) { + /* + * All vmas have already been torn down, so it's + * a good bet that actually the page is unmapped, + * and we'd prefer not to leak it: if we're wrong, + * some other bad page check should catch it later. + */ + page_mapcount_reset(page); + atomic_sub(mapcount, &page->_count); + } + } + page_cache_tree_delete(mapping, page, shadow); page->mapping = NULL; @@ -205,7 +229,6 @@ void __delete_from_page_cache(struct page *page, void *shadow, __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); - VM_BUG_ON_PAGE(page_mapped(page), page); /* * At this point page must be either written or cleaned by truncate. diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 01f2b48c8618..aefba5a9cc47 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2751,7 +2751,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, int ret; if (!hugepages_supported()) - return -ENOTSUPP; + return -EOPNOTSUPP; table->data = &tmp; table->maxlen = sizeof(unsigned long); @@ -2792,7 +2792,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, int ret; if (!hugepages_supported()) - return -ENOTSUPP; + return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; @@ -3502,7 +3502,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, * COW. Warn that such a situation has occurred as it may not be obvious */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { - pr_warning("PID %d killed due to inadequate hugepage pool\n", + pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); return ret; } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index bc0a8d8b8f42..1ad20ade8c91 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> +#include <linux/linkage.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/mm.h> @@ -60,6 +61,25 @@ void kasan_unpoison_shadow(const void *address, size_t size) } } +static void __kasan_unpoison_stack(struct task_struct *task, void *sp) +{ + void *base = task_stack_page(task); + size_t size = sp - base; + + kasan_unpoison_shadow(base, size); +} + +/* Unpoison the entire stack for a task. */ +void kasan_unpoison_task_stack(struct task_struct *task) +{ + __kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE); +} + +/* Unpoison the stack for the current task beyond a watermark sp value. */ +asmlinkage void kasan_unpoison_remaining_stack(void *sp) +{ + __kasan_unpoison_stack(current, sp); +} /* * All functions below always inlined so compiler could diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4c4187c0e1de..9a3f6b90e628 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -532,7 +532,7 @@ retry: nid = page_to_nid(page); if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT)) continue; - if (PageTail(page) && PageAnon(page)) { + if (PageTransCompound(page) && PageAnon(page)) { get_page(page); pte_unmap_unlock(pte, ptl); lock_page(page); diff --git a/mm/mempool.c b/mm/mempool.c index 004d42b1dfaf..7924f4f58a6d 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -135,8 +135,8 @@ static void *remove_element(mempool_t *pool) void *element = pool->elements[--pool->curr_nr]; BUG_ON(pool->curr_nr < 0); - check_element(pool, element); kasan_unpoison_element(pool, element); + check_element(pool, element); return element; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 82e3e9705017..dcea4f4c62b3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -723,6 +723,8 @@ int br_fdb_dump(struct sk_buff *skb, struct net_bridge_fdb_entry *f; hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { + int err; + if (idx < cb->args[0]) goto skip; @@ -741,12 +743,15 @@ int br_fdb_dump(struct sk_buff *skb, if (!filter_dev && f->dst) goto skip; - if (fdb_fill_info(skb, br, f, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - NLM_F_MULTI) < 0) + err = fdb_fill_info(skb, br, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI); + if (err < 0) { + cb->args[1] = err; break; + } skip: ++idx; } diff --git a/net/core/filter.c b/net/core/filter.c index 94d26201080d..bba502f7cd57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1752,7 +1752,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; - if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6))) + if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { @@ -1776,7 +1776,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM; info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; @@ -1787,6 +1787,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) sizeof(from->remote_ipv6)); } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + if (flags & BPF_F_ZERO_CSUM_TX) + info->key.tun_flags &= ~TUNNEL_CSUM; } return 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d735e854f916..8261d95dd846 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2911,6 +2911,7 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); out: netif_addr_unlock_bh(dev); + cb->args[1] = err; return idx; } EXPORT_SYMBOL(ndo_dflt_fdb_dump); @@ -2944,6 +2945,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } + cb->args[1] = 0; for_each_netdev(net, dev) { if (brport_idx && (dev->ifindex != brport_idx)) continue; @@ -2971,12 +2973,16 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, idx); } + if (cb->args[1] == -EMSGSIZE) + break; if (dev->netdev_ops->ndo_fdb_dump) idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, idx); else idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (cb->args[1] == -EMSGSIZE) + break; cops = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5bf88f58bee7..8616d1147c93 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2948,6 +2948,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + +/** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled @@ -4084,9 +4102,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14162..b3086cf27027 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 64878efa045c..565bf64b2b7d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1236,13 +1236,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 89e8861e05fc..336e6892a93c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -661,6 +661,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -758,7 +760,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c8cbc2b4b792..a726d7853ce5 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -550,7 +550,7 @@ reset: */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75632a925824..9b02af2139d3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -455,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -815,6 +815,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 0ec08814f37d..96599d1a1318 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -89,6 +89,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 5c5d23e59da5..9508a20fbf61 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, *fragoff = _frag_off; return hp->nexthdr; } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a69aad1e29d1..c0d4dc1c5ea4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -777,6 +777,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 137fca42aaa6..6c5dfec7a377 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ee56d0a8699..d64ee7e83664 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 22e28a44e3c8..422dd014aa2c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -962,11 +962,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 10ad4ac1fa0b..367784be5df2 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -291,7 +291,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } /* prepare A-MPDU MLME for Rx aggregation */ - tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); + tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL); if (!tid_agg_rx) goto end; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b84f6aa32c08..f006f4a44c0e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -92,7 +92,7 @@ struct ieee80211_fragment_entry { u16 extra_len; u16 last_frag; u8 rx_queue; - bool ccmp; /* Whether fragments were encrypted with CCMP */ + bool check_sequential_pn; /* needed for CCMP/GCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3ece7d1034c8..b54f398cda5d 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta) * computing cur_tp */ tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10; tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; return tmp_cur_tp; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 3928dbd24e25..370d677b547b 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -414,15 +414,16 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) (max_tp_group != MINSTREL_CCK_GROUP)) return; + max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; + max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; + if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_ewma); if (cur_tp_avg > tmp_tp_avg) mi->max_prob_rate = index; - max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; - max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; - max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, max_gpr_prob); @@ -431,7 +432,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) } else { if (mrs->prob_ewma > tmp_prob) mi->max_prob_rate = index; - if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma) + if (mrs->prob_ewma > max_gpr_prob) mg->max_group_prob_rate = index; } } @@ -691,7 +692,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (likely(sta->ampdu_mlme.tid_tx[tid])) return; - ieee80211_start_tx_ba_session(pubsta, tid, 5000); + ieee80211_start_tx_ba_session(pubsta, tid, 0); } static void @@ -871,7 +872,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ - if (offset > 0 && + if (offset > 0 || (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; @@ -1334,7 +1335,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) prob = mi->groups[i].rates[j].prob_ewma; /* convert tp_avg from pkt per second in kbps */ - tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; + tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bc081850ac0e..60d093f40f1d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1753,7 +1753,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, entry->seq = seq; entry->rx_queue = rx_queue; entry->last_frag = frag; - entry->ccmp = 0; + entry->check_sequential_pn = false; entry->extra_len = 0; return entry; @@ -1849,15 +1849,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->seqno_idx, &(rx->skb)); if (rx->key && (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; - /* Store CCMP PN so that we can verify that the next - * fragment has a sequential PN value. */ - entry->ccmp = 1; + + /* Store CCMP/GCMP PN so that we can verify that the + * next fragment has a sequential PN value. + */ + entry->check_sequential_pn = true; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); + BUILD_BUG_ON(offsetof(struct ieee80211_key, + u.ccmp.rx_pn) != + offsetof(struct ieee80211_key, + u.gcmp.rx_pn)); + BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) != + sizeof(rx->key->u.gcmp.rx_pn[queue])); + BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != + IEEE80211_GCMP_PN_LEN); } return RX_QUEUED; } @@ -1872,15 +1884,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* Verify that MPDUs within one MSDU have sequential PN values. - * (IEEE 802.11i, 8.3.3.4.5) */ - if (entry->ccmp) { + /* "The receiver shall discard MSDUs and MMPDUs whose constituent + * MPDU PN values are not incrementing in steps of 1." + * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP) + * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP) + */ + if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; + if (!rx->key || (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { @@ -3366,6 +3384,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return false; /* ignore action frames to TDLS-peers */ if (ieee80211_is_action(hdr->frame_control) && + !is_broadcast_ether_addr(bssid) && !ether_addr_equal(bssid, hdr->addr1)) return false; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d05869646515..6b70399ab781 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -62,6 +62,7 @@ static void ipt_destroy_target(struct xt_entry_target *t) struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, + .family = NFPROTO_IPV4, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -195,6 +196,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, par.hooknum = ipt->tcfi_hook; par.target = ipt->tcfi_t->u.kernel.target; par.targinfo = ipt->tcfi_t->data; + par.family = NFPROTO_IPV4; ret = par.target->target(skb, &par); switch (ret) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ec529121f38a..ce46f1c7f133 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ diff --git a/net/sctp/proc.c b/net/sctp/proc.c index ded7d931a6a5..963dffcc2618 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -482,7 +482,7 @@ static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v) static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) { struct sctp_association *assoc; - struct sctp_transport *tsp; + struct sctp_transport *transport, *tsp; if (v == SEQ_START_TOKEN) { seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " @@ -490,10 +490,10 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) return 0; } - tsp = (struct sctp_transport *)v; - if (!sctp_transport_hold(tsp)) + transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) return 0; - assoc = tsp->asoc; + assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { @@ -546,7 +546,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } - sctp_transport_put(tsp); + sctp_transport_put(transport); return 0; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 47f7da58a7f0..8b5833c1ff2e 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1093,8 +1093,11 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .cb = cb, .idx = idx, }; + int err; - switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb); + err = switchdev_port_obj_dump(dev, &dump.fdb.obj, + switchdev_port_fdb_dump_cb); + cb->args[1] = err; return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 69c29050f14a..4d420bb27396 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -673,7 +673,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct iov_iter save = msg->msg_iter; uint mtu; int rc; @@ -687,14 +687,16 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, msg_set_nameupper(mhdr, seq->upper); msg_set_hdr_sz(mhdr, MCAST_H_SIZE); + skb_queue_head_init(&pktchain); + new_mtu: mtu = tipc_bcast_get_mtu(net); - rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bcast_xmit(net, pktchain); + rc = tipc_bcast_xmit(net, &pktchain); if (likely(!rc)) return dsz; @@ -704,7 +706,7 @@ new_mtu: if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; @@ -863,7 +865,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct sk_buff *skb; struct tipc_name_seq *seq; struct iov_iter save; @@ -924,17 +926,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) msg_set_hdr_sz(mhdr, BASIC_H_SIZE); } + skb_queue_head_init(&pktchain); save = m->msg_iter; new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); - rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain); if (rc < 0) return rc; do { - skb = skb_peek(pktchain); + skb = skb_peek(&pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid); if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -946,7 +949,7 @@ new_mtu: if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; @@ -1016,7 +1019,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); u32 portid = tsk->portid; int rc = -EINVAL; @@ -1044,17 +1047,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); dnode = tsk_peer_node(tsk); + skb_queue_head_init(&pktchain); next: save = m->msg_iter; mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); - rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain); if (unlikely(rc < 0)) return rc; + do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_node_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, &pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1063,7 +1068,7 @@ next: goto next; } if (rc == -EMSGSIZE) { - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1077,7 +1082,7 @@ next: rc = tipc_wait_for_sndpkt(sock, &timeo); } while (!rc); - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); return sent ? sent : rc; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 69ee2eeef968..f9ff73a8d815 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -296,7 +296,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) return tipc_conn_terminate(tn->topsrv, subscrb->conid); - tipc_nametbl_subscribe(sub); + if (sub) + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ diff --git a/net/wireless/core.c b/net/wireless/core.c index b0915515640e..8f0bac7e03c4 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1147,6 +1147,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } + wireless_nlevent_flush(); + return NOTIFY_OK; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d4786f2802aa..711cb7ad6ae0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7547,7 +7547,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) && no_ht) { - kfree(connkeys); + kzfree(connkeys); return -EINVAL; } } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8020b5b094d4..d49ed7666d4c 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -917,6 +917,12 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); + /* stop critical protocol if supported */ + if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { + rdev->crit_proto_nlportid = 0; + rdev_crit_proto_stop(rdev, wdev); + } + /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c8717c1d082e..b50ee5d622e1 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,6 +342,40 @@ static const int compat_event_type_size[] = { /* IW event code */ +void wireless_nlevent_flush(void) +{ + struct sk_buff *skb; + struct net *net; + + ASSERT_RTNL(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } +} +EXPORT_SYMBOL_GPL(wireless_nlevent_flush); + +static int wext_netdev_notifier_call(struct notifier_block *nb, + unsigned long state, void *ptr) +{ + /* + * When a netdev changes state in any way, flush all pending messages + * to avoid them going out in a strange order, e.g. RTM_NEWLINK after + * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() + * or similar - all of which could otherwise happen due to delays from + * schedule_work(). + */ + wireless_nlevent_flush(); + + return NOTIFY_OK; +} + +static struct notifier_block wext_netdev_notifier = { + .notifier_call = wext_netdev_notifier_call, +}; + static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); @@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = { static int __init wireless_nlevent_init(void) { - return register_pernet_subsys(&wext_pernet_ops); + int err = register_pernet_subsys(&wext_pernet_ops); + + if (err) + return err; + + return register_netdevice_notifier(&wext_netdev_notifier); } subsys_initcall(wireless_nlevent_init); @@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { - struct sk_buff *skb; - struct net *net; - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - + wireless_nlevent_flush(); rtnl_unlock(); } diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh index d154f0877fd8..7bfe9fa1c8dc 100755 --- a/scripts/ld-version.sh +++ b/scripts/ld-version.sh @@ -1,7 +1,7 @@ #!/usr/bin/awk -f # extract linker version number from stdin and turn into single number { - gsub(".*)", ""); + gsub(".*\\)", ""); gsub(".*version ", ""); gsub("-.*", ""); split($1,a, "."); diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c index affb192238a4..faae6936bae4 100644 --- a/sound/soc/codecs/ab8500-codec.c +++ b/sound/soc/codecs/ab8500-codec.c @@ -1130,7 +1130,7 @@ static int sid_status_control_get(struct snd_kcontrol *kcontrol, struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev); mutex_lock(&drvdata->ctrl_lock); - ucontrol->value.integer.value[0] = drvdata->sid_status; + ucontrol->value.enumerated.item[0] = drvdata->sid_status; mutex_unlock(&drvdata->ctrl_lock); return 0; @@ -1147,7 +1147,7 @@ static int sid_status_control_put(struct snd_kcontrol *kcontrol, dev_dbg(codec->dev, "%s: Enter\n", __func__); - if (ucontrol->value.integer.value[0] != SID_APPLY_FIR) { + if (ucontrol->value.enumerated.item[0] != SID_APPLY_FIR) { dev_err(codec->dev, "%s: ERROR: This control supports '%s' only!\n", __func__, enum_sid_state[SID_APPLY_FIR]); @@ -1199,7 +1199,7 @@ static int anc_status_control_get(struct snd_kcontrol *kcontrol, struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev); mutex_lock(&drvdata->ctrl_lock); - ucontrol->value.integer.value[0] = drvdata->anc_status; + ucontrol->value.enumerated.item[0] = drvdata->anc_status; mutex_unlock(&drvdata->ctrl_lock); return 0; @@ -1220,7 +1220,7 @@ static int anc_status_control_put(struct snd_kcontrol *kcontrol, mutex_lock(&drvdata->ctrl_lock); - req = ucontrol->value.integer.value[0]; + req = ucontrol->value.enumerated.item[0]; if (req >= ARRAY_SIZE(enum_anc_state)) { status = -EINVAL; goto cleanup; diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h index e13583e6ff56..5ae87a084d97 100644 --- a/sound/soc/codecs/adau17x1.h +++ b/sound/soc/codecs/adau17x1.h @@ -103,9 +103,9 @@ bool adau17x1_has_dsp(struct adau *adau); #define ADAU17X1_CLOCK_CONTROL_CORECLK_SRC_PLL BIT(3) #define ADAU17X1_CLOCK_CONTROL_SYSCLK_EN BIT(0) -#define ADAU17X1_SERIAL_PORT1_BCLK32 (0x0 << 5) -#define ADAU17X1_SERIAL_PORT1_BCLK48 (0x1 << 5) -#define ADAU17X1_SERIAL_PORT1_BCLK64 (0x2 << 5) +#define ADAU17X1_SERIAL_PORT1_BCLK64 (0x0 << 5) +#define ADAU17X1_SERIAL_PORT1_BCLK32 (0x1 << 5) +#define ADAU17X1_SERIAL_PORT1_BCLK48 (0x2 << 5) #define ADAU17X1_SERIAL_PORT1_BCLK128 (0x3 << 5) #define ADAU17X1_SERIAL_PORT1_BCLK256 (0x4 << 5) #define ADAU17X1_SERIAL_PORT1_BCLK_MASK (0x7 << 5) diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index b3951524339f..35488f14e237 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -60,15 +60,15 @@ static int cs42l51_get_chan_mix(struct snd_kcontrol *kcontrol, switch (value) { default: case 0: - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; break; /* same value : (L+R)/2 and (R+L)/2 */ case 1: case 2: - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; break; case 3: - ucontrol->value.integer.value[0] = 2; + ucontrol->value.enumerated.item[0] = 2; break; } @@ -85,7 +85,7 @@ static int cs42l51_set_chan_mix(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); unsigned char val; - switch (ucontrol->value.integer.value[0]) { + switch (ucontrol->value.enumerated.item[0]) { default: case 0: val = CHAN_MIX_NORMAL; diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c index 1d5a89c5164b..461506a4ca6a 100644 --- a/sound/soc/codecs/da732x.c +++ b/sound/soc/codecs/da732x.c @@ -334,7 +334,7 @@ static int da732x_hpf_set(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct soc_enum *enum_ctrl = (struct soc_enum *)kcontrol->private_value; unsigned int reg = enum_ctrl->reg; - unsigned int sel = ucontrol->value.integer.value[0]; + unsigned int sel = ucontrol->value.enumerated.item[0]; unsigned int bits; switch (sel) { @@ -368,13 +368,13 @@ static int da732x_hpf_get(struct snd_kcontrol *kcontrol, switch (val) { case DA732X_HPF_VOICE_EN: - ucontrol->value.integer.value[0] = DA732X_HPF_VOICE; + ucontrol->value.enumerated.item[0] = DA732X_HPF_VOICE; break; case DA732X_HPF_MUSIC_EN: - ucontrol->value.integer.value[0] = DA732X_HPF_MUSIC; + ucontrol->value.enumerated.item[0] = DA732X_HPF_MUSIC; break; default: - ucontrol->value.integer.value[0] = DA732X_HPF_DISABLED; + ucontrol->value.enumerated.item[0] = DA732X_HPF_DISABLED; break; } diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c index 20dcc496d39c..fc22804cabc5 100644 --- a/sound/soc/codecs/max98088.c +++ b/sound/soc/codecs/max98088.c @@ -1496,7 +1496,7 @@ static int max98088_put_eq_enum(struct snd_kcontrol *kcontrol, struct max98088_pdata *pdata = max98088->pdata; int channel = max98088_get_channel(codec, kcontrol->id.name); struct max98088_cdata *cdata; - int sel = ucontrol->value.integer.value[0]; + int sel = ucontrol->value.enumerated.item[0]; if (channel < 0) return channel; diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c index 1fedac50355e..3577003f39cf 100644 --- a/sound/soc/codecs/max98095.c +++ b/sound/soc/codecs/max98095.c @@ -1499,7 +1499,7 @@ static int max98095_put_eq_enum(struct snd_kcontrol *kcontrol, struct max98095_pdata *pdata = max98095->pdata; int channel = max98095_get_eq_channel(kcontrol->id.name); struct max98095_cdata *cdata; - unsigned int sel = ucontrol->value.integer.value[0]; + unsigned int sel = ucontrol->value.enumerated.item[0]; struct max98095_eq_cfg *coef_set; int fs, best, best_val, i; int regmask, regsave; @@ -1653,7 +1653,7 @@ static int max98095_put_bq_enum(struct snd_kcontrol *kcontrol, struct max98095_pdata *pdata = max98095->pdata; int channel = max98095_get_bq_channel(codec, kcontrol->id.name); struct max98095_cdata *cdata; - unsigned int sel = ucontrol->value.integer.value[0]; + unsigned int sel = ucontrol->value.enumerated.item[0]; struct max98095_biquad_cfg *coef_set; int fs, best, best_val, i; int regmask, regsave; diff --git a/sound/soc/codecs/tlv320dac33.c b/sound/soc/codecs/tlv320dac33.c index 781398fb2841..f7a6ce7e5fb1 100644 --- a/sound/soc/codecs/tlv320dac33.c +++ b/sound/soc/codecs/tlv320dac33.c @@ -446,7 +446,7 @@ static int dac33_get_fifo_mode(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct tlv320dac33_priv *dac33 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = dac33->fifo_mode; + ucontrol->value.enumerated.item[0] = dac33->fifo_mode; return 0; } @@ -458,17 +458,16 @@ static int dac33_set_fifo_mode(struct snd_kcontrol *kcontrol, struct tlv320dac33_priv *dac33 = snd_soc_codec_get_drvdata(codec); int ret = 0; - if (dac33->fifo_mode == ucontrol->value.integer.value[0]) + if (dac33->fifo_mode == ucontrol->value.enumerated.item[0]) return 0; /* Do not allow changes while stream is running*/ if (snd_soc_codec_is_active(codec)) return -EPERM; - if (ucontrol->value.integer.value[0] < 0 || - ucontrol->value.integer.value[0] >= DAC33_FIFO_LAST_MODE) + if (ucontrol->value.enumerated.item[0] >= DAC33_FIFO_LAST_MODE) ret = -EINVAL; else - dac33->fifo_mode = ucontrol->value.integer.value[0]; + dac33->fifo_mode = ucontrol->value.enumerated.item[0]; return ret; } diff --git a/sound/soc/codecs/wl1273.c b/sound/soc/codecs/wl1273.c index 7693c1129bab..1b79778098d2 100644 --- a/sound/soc/codecs/wl1273.c +++ b/sound/soc/codecs/wl1273.c @@ -175,7 +175,7 @@ static int snd_wl1273_get_audio_route(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wl1273_priv *wl1273 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = wl1273->mode; + ucontrol->value.enumerated.item[0] = wl1273->mode; return 0; } @@ -193,18 +193,17 @@ static int snd_wl1273_set_audio_route(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wl1273_priv *wl1273 = snd_soc_codec_get_drvdata(codec); - if (wl1273->mode == ucontrol->value.integer.value[0]) + if (wl1273->mode == ucontrol->value.enumerated.item[0]) return 0; /* Do not allow changes while stream is running */ if (snd_soc_codec_is_active(codec)) return -EPERM; - if (ucontrol->value.integer.value[0] < 0 || - ucontrol->value.integer.value[0] >= ARRAY_SIZE(wl1273_audio_route)) + if (ucontrol->value.enumerated.item[0] >= ARRAY_SIZE(wl1273_audio_route)) return -EINVAL; - wl1273->mode = ucontrol->value.integer.value[0]; + wl1273->mode = ucontrol->value.enumerated.item[0]; return 1; } @@ -219,7 +218,7 @@ static int snd_wl1273_fm_audio_get(struct snd_kcontrol *kcontrol, dev_dbg(codec->dev, "%s: enter.\n", __func__); - ucontrol->value.integer.value[0] = wl1273->core->audio_mode; + ucontrol->value.enumerated.item[0] = wl1273->core->audio_mode; return 0; } @@ -233,7 +232,7 @@ static int snd_wl1273_fm_audio_put(struct snd_kcontrol *kcontrol, dev_dbg(codec->dev, "%s: enter.\n", __func__); - val = ucontrol->value.integer.value[0]; + val = ucontrol->value.enumerated.item[0]; if (wl1273->core->audio_mode == val) return 0; diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c index 61299ca372ff..6f1024f48b19 100644 --- a/sound/soc/codecs/wm8753.c +++ b/sound/soc/codecs/wm8753.c @@ -233,7 +233,7 @@ static int wm8753_get_dai(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = wm8753->dai_func; + ucontrol->value.enumerated.item[0] = wm8753->dai_func; return 0; } @@ -244,7 +244,7 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol, struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec); u16 ioctl; - if (wm8753->dai_func == ucontrol->value.integer.value[0]) + if (wm8753->dai_func == ucontrol->value.enumerated.item[0]) return 0; if (snd_soc_codec_is_active(codec)) @@ -252,7 +252,7 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol, ioctl = snd_soc_read(codec, WM8753_IOCTL); - wm8753->dai_func = ucontrol->value.integer.value[0]; + wm8753->dai_func = ucontrol->value.enumerated.item[0]; if (((ioctl >> 2) & 0x3) == wm8753->dai_func) return 1; diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 8172e499e6ed..edd7a7709194 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -396,7 +396,7 @@ static int wm8904_put_drc_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); struct wm8904_pdata *pdata = wm8904->pdata; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (value >= pdata->num_drc_cfgs) return -EINVAL; @@ -467,7 +467,7 @@ static int wm8904_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); struct wm8904_pdata *pdata = wm8904->pdata; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (value >= pdata->num_retune_mobile_cfgs) return -EINVAL; diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index c799cca5abeb..6b864c0fc2b6 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -459,7 +459,7 @@ static int wm8958_put_mbc_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -549,7 +549,7 @@ static int wm8958_put_vss_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -582,7 +582,7 @@ static int wm8958_put_vss_hpf_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -749,7 +749,7 @@ static int wm8958_put_enh_eq_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ diff --git a/sound/soc/codecs/wm8983.c b/sound/soc/codecs/wm8983.c index 7350ff654bbf..0c002a5712cb 100644 --- a/sound/soc/codecs/wm8983.c +++ b/sound/soc/codecs/wm8983.c @@ -497,9 +497,9 @@ static int eqmode_get(struct snd_kcontrol *kcontrol, reg = snd_soc_read(codec, WM8983_EQ1_LOW_SHELF); if (reg & WM8983_EQ3DMODE) - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; return 0; } @@ -511,18 +511,18 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, unsigned int regpwr2, regpwr3; unsigned int reg_eq; - if (ucontrol->value.integer.value[0] != 0 - && ucontrol->value.integer.value[0] != 1) + if (ucontrol->value.enumerated.item[0] != 0 + && ucontrol->value.enumerated.item[0] != 1) return -EINVAL; reg_eq = snd_soc_read(codec, WM8983_EQ1_LOW_SHELF); switch ((reg_eq & WM8983_EQ3DMODE) >> WM8983_EQ3DMODE_SHIFT) { case 0: - if (!ucontrol->value.integer.value[0]) + if (!ucontrol->value.enumerated.item[0]) return 0; break; case 1: - if (ucontrol->value.integer.value[0]) + if (ucontrol->value.enumerated.item[0]) return 0; break; } @@ -537,7 +537,7 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, /* set the desired eqmode */ snd_soc_update_bits(codec, WM8983_EQ1_LOW_SHELF, WM8983_EQ3DMODE_MASK, - ucontrol->value.integer.value[0] + ucontrol->value.enumerated.item[0] << WM8983_EQ3DMODE_SHIFT); /* restore DAC/ADC configuration */ snd_soc_write(codec, WM8983_POWER_MANAGEMENT_2, regpwr2); diff --git a/sound/soc/codecs/wm8985.c b/sound/soc/codecs/wm8985.c index 9918152a03c7..6ac76fe116b0 100644 --- a/sound/soc/codecs/wm8985.c +++ b/sound/soc/codecs/wm8985.c @@ -531,9 +531,9 @@ static int eqmode_get(struct snd_kcontrol *kcontrol, reg = snd_soc_read(codec, WM8985_EQ1_LOW_SHELF); if (reg & WM8985_EQ3DMODE) - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; return 0; } @@ -545,18 +545,18 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, unsigned int regpwr2, regpwr3; unsigned int reg_eq; - if (ucontrol->value.integer.value[0] != 0 - && ucontrol->value.integer.value[0] != 1) + if (ucontrol->value.enumerated.item[0] != 0 + && ucontrol->value.enumerated.item[0] != 1) return -EINVAL; reg_eq = snd_soc_read(codec, WM8985_EQ1_LOW_SHELF); switch ((reg_eq & WM8985_EQ3DMODE) >> WM8985_EQ3DMODE_SHIFT) { case 0: - if (!ucontrol->value.integer.value[0]) + if (!ucontrol->value.enumerated.item[0]) return 0; break; case 1: - if (ucontrol->value.integer.value[0]) + if (ucontrol->value.enumerated.item[0]) return 0; break; } @@ -573,7 +573,7 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, /* set the desired eqmode */ snd_soc_update_bits(codec, WM8985_EQ1_LOW_SHELF, WM8985_EQ3DMODE_MASK, - ucontrol->value.integer.value[0] + ucontrol->value.enumerated.item[0] << WM8985_EQ3DMODE_SHIFT); /* restore DAC/ADC configuration */ snd_soc_write(codec, WM8985_POWER_MANAGEMENT_2, regpwr2); diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 2ccbb322df77..a18aecb49935 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -362,7 +362,7 @@ static int wm8994_put_drc_enum(struct snd_kcontrol *kcontrol, struct wm8994 *control = wm8994->wm8994; struct wm8994_pdata *pdata = &control->pdata; int drc = wm8994_get_drc(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (drc < 0) return drc; @@ -469,7 +469,7 @@ static int wm8994_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct wm8994 *control = wm8994->wm8994; struct wm8994_pdata *pdata = &control->pdata; int block = wm8994_get_retune_mobile_block(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (block < 0) return block; diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c index 8d7d6c01a2f7..f99b34f7647b 100644 --- a/sound/soc/codecs/wm8996.c +++ b/sound/soc/codecs/wm8996.c @@ -416,7 +416,7 @@ static int wm8996_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct wm8996_priv *wm8996 = snd_soc_codec_get_drvdata(codec); struct wm8996_pdata *pdata = &wm8996->pdata; int block = wm8996_get_retune_mobile_block(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (block < 0) return block; diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c index ccb3b15139ad..363b3b667616 100644 --- a/sound/soc/codecs/wm9081.c +++ b/sound/soc/codecs/wm9081.c @@ -344,9 +344,9 @@ static int speaker_mode_get(struct snd_kcontrol *kcontrol, reg = snd_soc_read(codec, WM9081_ANALOGUE_SPEAKER_2); if (reg & WM9081_SPK_MODE) - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; return 0; } @@ -365,7 +365,7 @@ static int speaker_mode_put(struct snd_kcontrol *kcontrol, unsigned int reg2 = snd_soc_read(codec, WM9081_ANALOGUE_SPEAKER_2); /* Are we changing anything? */ - if (ucontrol->value.integer.value[0] == + if (ucontrol->value.enumerated.item[0] == ((reg2 & WM9081_SPK_MODE) != 0)) return 0; @@ -373,7 +373,7 @@ static int speaker_mode_put(struct snd_kcontrol *kcontrol, if (reg_pwr & WM9081_SPK_ENA) return -EINVAL; - if (ucontrol->value.integer.value[0]) { + if (ucontrol->value.enumerated.item[0]) { /* Class AB */ reg2 &= ~(WM9081_SPK_INV_MUTE | WM9081_OUT_SPK_CTRL); reg2 |= WM9081_SPK_MODE; diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c index 79e143625ac3..9849643ef809 100644 --- a/sound/soc/codecs/wm9713.c +++ b/sound/soc/codecs/wm9713.c @@ -1212,7 +1212,7 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec) if (IS_ERR(wm9713->ac97)) return PTR_ERR(wm9713->ac97); - regmap = devm_regmap_init_ac97(wm9713->ac97, &wm9713_regmap_config); + regmap = regmap_init_ac97(wm9713->ac97, &wm9713_regmap_config); if (IS_ERR(regmap)) { snd_soc_free_ac97_codec(wm9713->ac97); return PTR_ERR(regmap); diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 33806d487b8a..b9195b9c2b05 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -586,7 +586,7 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; struct wm_adsp *dsp = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = dsp[e->shift_l].fw; + ucontrol->value.enumerated.item[0] = dsp[e->shift_l].fw; return 0; } @@ -599,10 +599,10 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol, struct wm_adsp *dsp = snd_soc_codec_get_drvdata(codec); int ret = 0; - if (ucontrol->value.integer.value[0] == dsp[e->shift_l].fw) + if (ucontrol->value.enumerated.item[0] == dsp[e->shift_l].fw) return 0; - if (ucontrol->value.integer.value[0] >= WM_ADSP_NUM_FW) + if (ucontrol->value.enumerated.item[0] >= WM_ADSP_NUM_FW) return -EINVAL; mutex_lock(&dsp[e->shift_l].pwr_lock); @@ -610,7 +610,7 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol, if (dsp[e->shift_l].running || dsp[e->shift_l].compr) ret = -EBUSY; else - dsp[e->shift_l].fw = ucontrol->value.integer.value[0]; + dsp[e->shift_l].fw = ucontrol->value.enumerated.item[0]; mutex_unlock(&dsp[e->shift_l].pwr_lock); diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index ed8de1035cda..40dfd8a36484 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -112,6 +112,20 @@ struct fsl_ssi_rxtx_reg_val { struct fsl_ssi_reg_val tx; }; +static const struct reg_default fsl_ssi_reg_defaults[] = { + {CCSR_SSI_SCR, 0x00000000}, + {CCSR_SSI_SIER, 0x00003003}, + {CCSR_SSI_STCR, 0x00000200}, + {CCSR_SSI_SRCR, 0x00000200}, + {CCSR_SSI_STCCR, 0x00040000}, + {CCSR_SSI_SRCCR, 0x00040000}, + {CCSR_SSI_SACNT, 0x00000000}, + {CCSR_SSI_STMSK, 0x00000000}, + {CCSR_SSI_SRMSK, 0x00000000}, + {CCSR_SSI_SACCEN, 0x00000000}, + {CCSR_SSI_SACCDIS, 0x00000000}, +}; + static bool fsl_ssi_readable_reg(struct device *dev, unsigned int reg) { switch (reg) { @@ -176,7 +190,8 @@ static const struct regmap_config fsl_ssi_regconfig = { .val_bits = 32, .reg_stride = 4, .val_format_endian = REGMAP_ENDIAN_NATIVE, - .num_reg_defaults_raw = CCSR_SSI_SACCDIS / sizeof(uint32_t) + 1, + .reg_defaults = fsl_ssi_reg_defaults, + .num_reg_defaults = ARRAY_SIZE(fsl_ssi_reg_defaults), .readable_reg = fsl_ssi_readable_reg, .volatile_reg = fsl_ssi_volatile_reg, .precious_reg = fsl_ssi_precious_reg, @@ -186,7 +201,6 @@ static const struct regmap_config fsl_ssi_regconfig = { struct fsl_ssi_soc_data { bool imx; - bool imx21regs; /* imx21-class SSI - no SACC{ST,EN,DIS} regs */ bool offline_config; u32 sisr_write_mask; }; @@ -289,7 +303,6 @@ static struct fsl_ssi_soc_data fsl_ssi_mpc8610 = { static struct fsl_ssi_soc_data fsl_ssi_imx21 = { .imx = true, - .imx21regs = true, .offline_config = true, .sisr_write_mask = 0, }; @@ -573,12 +586,8 @@ static void fsl_ssi_setup_ac97(struct fsl_ssi_private *ssi_private) */ regmap_write(regs, CCSR_SSI_SACNT, CCSR_SSI_SACNT_AC97EN | CCSR_SSI_SACNT_FV); - - /* no SACC{ST,EN,DIS} regs on imx21-class SSI */ - if (!ssi_private->soc->imx21regs) { - regmap_write(regs, CCSR_SSI_SACCDIS, 0xff); - regmap_write(regs, CCSR_SSI_SACCEN, 0x300); - } + regmap_write(regs, CCSR_SSI_SACCDIS, 0xff); + regmap_write(regs, CCSR_SSI_SACCEN, 0x300); /* * Enable SSI, Transmit and Receive. AC97 has to communicate with the @@ -1388,7 +1397,6 @@ static int fsl_ssi_probe(struct platform_device *pdev) struct resource *res; void __iomem *iomem; char name[64]; - struct regmap_config regconfig = fsl_ssi_regconfig; of_id = of_match_device(fsl_ssi_ids, &pdev->dev); if (!of_id || !of_id->data) @@ -1436,25 +1444,15 @@ static int fsl_ssi_probe(struct platform_device *pdev) return PTR_ERR(iomem); ssi_private->ssi_phys = res->start; - if (ssi_private->soc->imx21regs) { - /* - * According to datasheet imx21-class SSI - * don't have SACC{ST,EN,DIS} regs. - */ - regconfig.max_register = CCSR_SSI_SRMSK; - regconfig.num_reg_defaults_raw = - CCSR_SSI_SRMSK / sizeof(uint32_t) + 1; - } - ret = of_property_match_string(np, "clock-names", "ipg"); if (ret < 0) { ssi_private->has_ipg_clk_name = false; ssi_private->regs = devm_regmap_init_mmio(&pdev->dev, iomem, - ®config); + &fsl_ssi_regconfig); } else { ssi_private->has_ipg_clk_name = true; ssi_private->regs = devm_regmap_init_mmio_clk(&pdev->dev, - "ipg", iomem, ®config); + "ipg", iomem, &fsl_ssi_regconfig); } if (IS_ERR(ssi_private->regs)) { dev_err(&pdev->dev, "Failed to init register map\n"); diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c index 2d3afddb0a2e..a7b96a9a4e0e 100644 --- a/sound/soc/intel/boards/cht_bsw_rt5645.c +++ b/sound/soc/intel/boards/cht_bsw_rt5645.c @@ -367,8 +367,12 @@ static int snd_cht_mc_probe(struct platform_device *pdev) } card->dev = &pdev->dev; sprintf(codec_name, "i2c-%s:00", drv->acpi_card->codec_id); + /* set correct codec name */ - strcpy((char *)card->dai_link[2].codec_name, codec_name); + for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) + if (!strcmp(card->dai_link[i].codec_name, "i2c-10EC5645:00")) + card->dai_link[i].codec_name = kstrdup(codec_name, GFP_KERNEL); + snd_soc_card_set_drvdata(card, drv); ret_val = devm_snd_soc_register_card(&pdev->dev, card); if (ret_val) { diff --git a/sound/soc/intel/boards/mfld_machine.c b/sound/soc/intel/boards/mfld_machine.c index 49c09a0add79..34f46c72a0e2 100644 --- a/sound/soc/intel/boards/mfld_machine.c +++ b/sound/soc/intel/boards/mfld_machine.c @@ -94,7 +94,7 @@ static const struct soc_enum lo_enum = static int headset_get_switch(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = hs_switch; + ucontrol->value.enumerated.item[0] = hs_switch; return 0; } @@ -104,12 +104,12 @@ static int headset_set_switch(struct snd_kcontrol *kcontrol, struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); struct snd_soc_dapm_context *dapm = &card->dapm; - if (ucontrol->value.integer.value[0] == hs_switch) + if (ucontrol->value.enumerated.item[0] == hs_switch) return 0; snd_soc_dapm_mutex_lock(dapm); - if (ucontrol->value.integer.value[0]) { + if (ucontrol->value.enumerated.item[0]) { pr_debug("hs_set HS path\n"); snd_soc_dapm_enable_pin_unlocked(dapm, "Headphones"); snd_soc_dapm_disable_pin_unlocked(dapm, "EPOUT"); @@ -123,7 +123,7 @@ static int headset_set_switch(struct snd_kcontrol *kcontrol, snd_soc_dapm_mutex_unlock(dapm); - hs_switch = ucontrol->value.integer.value[0]; + hs_switch = ucontrol->value.enumerated.item[0]; return 0; } @@ -148,7 +148,7 @@ static void lo_enable_out_pins(struct snd_soc_dapm_context *dapm) static int lo_get_switch(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = lo_dac; + ucontrol->value.enumerated.item[0] = lo_dac; return 0; } @@ -158,7 +158,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol, struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); struct snd_soc_dapm_context *dapm = &card->dapm; - if (ucontrol->value.integer.value[0] == lo_dac) + if (ucontrol->value.enumerated.item[0] == lo_dac) return 0; snd_soc_dapm_mutex_lock(dapm); @@ -168,7 +168,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol, */ lo_enable_out_pins(dapm); - switch (ucontrol->value.integer.value[0]) { + switch (ucontrol->value.enumerated.item[0]) { case 0: pr_debug("set vibra path\n"); snd_soc_dapm_disable_pin_unlocked(dapm, "VIB1OUT"); @@ -202,7 +202,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol, snd_soc_dapm_mutex_unlock(dapm); - lo_dac = ucontrol->value.integer.value[0]; + lo_dac = ucontrol->value.enumerated.item[0]; return 0; } diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index a294fee431f0..5a4837dcfce3 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -978,7 +978,7 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol, return -EFAULT; } else { if (copy_from_user(ac->params, - data + 2 * sizeof(u32), size)) + data + 2, size)) return -EFAULT; } diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c index 190f868e78b2..fdecb7043174 100644 --- a/sound/soc/omap/n810.c +++ b/sound/soc/omap/n810.c @@ -133,7 +133,7 @@ static struct snd_soc_ops n810_ops = { static int n810_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = n810_spk_func; + ucontrol->value.enumerated.item[0] = n810_spk_func; return 0; } @@ -143,10 +143,10 @@ static int n810_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (n810_spk_func == ucontrol->value.integer.value[0]) + if (n810_spk_func == ucontrol->value.enumerated.item[0]) return 0; - n810_spk_func = ucontrol->value.integer.value[0]; + n810_spk_func = ucontrol->value.enumerated.item[0]; n810_ext_control(&card->dapm); return 1; @@ -155,7 +155,7 @@ static int n810_set_spk(struct snd_kcontrol *kcontrol, static int n810_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = n810_jack_func; + ucontrol->value.enumerated.item[0] = n810_jack_func; return 0; } @@ -165,10 +165,10 @@ static int n810_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (n810_jack_func == ucontrol->value.integer.value[0]) + if (n810_jack_func == ucontrol->value.enumerated.item[0]) return 0; - n810_jack_func = ucontrol->value.integer.value[0]; + n810_jack_func = ucontrol->value.enumerated.item[0]; n810_ext_control(&card->dapm); return 1; @@ -177,7 +177,7 @@ static int n810_set_jack(struct snd_kcontrol *kcontrol, static int n810_get_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = n810_dmic_func; + ucontrol->value.enumerated.item[0] = n810_dmic_func; return 0; } @@ -187,10 +187,10 @@ static int n810_set_input(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (n810_dmic_func == ucontrol->value.integer.value[0]) + if (n810_dmic_func == ucontrol->value.enumerated.item[0]) return 0; - n810_dmic_func = ucontrol->value.integer.value[0]; + n810_dmic_func = ucontrol->value.enumerated.item[0]; n810_ext_control(&card->dapm); return 1; diff --git a/sound/soc/omap/rx51.c b/sound/soc/omap/rx51.c index 5e21f08579d8..54949242bc70 100644 --- a/sound/soc/omap/rx51.c +++ b/sound/soc/omap/rx51.c @@ -132,7 +132,7 @@ static struct snd_soc_ops rx51_ops = { static int rx51_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = rx51_spk_func; + ucontrol->value.enumerated.item[0] = rx51_spk_func; return 0; } @@ -142,10 +142,10 @@ static int rx51_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (rx51_spk_func == ucontrol->value.integer.value[0]) + if (rx51_spk_func == ucontrol->value.enumerated.item[0]) return 0; - rx51_spk_func = ucontrol->value.integer.value[0]; + rx51_spk_func = ucontrol->value.enumerated.item[0]; rx51_ext_control(&card->dapm); return 1; @@ -180,7 +180,7 @@ static int rx51_hp_event(struct snd_soc_dapm_widget *w, static int rx51_get_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = rx51_dmic_func; + ucontrol->value.enumerated.item[0] = rx51_dmic_func; return 0; } @@ -190,10 +190,10 @@ static int rx51_set_input(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (rx51_dmic_func == ucontrol->value.integer.value[0]) + if (rx51_dmic_func == ucontrol->value.enumerated.item[0]) return 0; - rx51_dmic_func = ucontrol->value.integer.value[0]; + rx51_dmic_func = ucontrol->value.enumerated.item[0]; rx51_ext_control(&card->dapm); return 1; @@ -202,7 +202,7 @@ static int rx51_set_input(struct snd_kcontrol *kcontrol, static int rx51_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = rx51_jack_func; + ucontrol->value.enumerated.item[0] = rx51_jack_func; return 0; } @@ -212,10 +212,10 @@ static int rx51_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (rx51_jack_func == ucontrol->value.integer.value[0]) + if (rx51_jack_func == ucontrol->value.enumerated.item[0]) return 0; - rx51_jack_func = ucontrol->value.integer.value[0]; + rx51_jack_func = ucontrol->value.enumerated.item[0]; rx51_ext_control(&card->dapm); return 1; diff --git a/sound/soc/pxa/corgi.c b/sound/soc/pxa/corgi.c index c97dc13d3608..dcbb7aa9830c 100644 --- a/sound/soc/pxa/corgi.c +++ b/sound/soc/pxa/corgi.c @@ -163,7 +163,7 @@ static struct snd_soc_ops corgi_ops = { static int corgi_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = corgi_jack_func; + ucontrol->value.enumerated.item[0] = corgi_jack_func; return 0; } @@ -172,10 +172,10 @@ static int corgi_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (corgi_jack_func == ucontrol->value.integer.value[0]) + if (corgi_jack_func == ucontrol->value.enumerated.item[0]) return 0; - corgi_jack_func = ucontrol->value.integer.value[0]; + corgi_jack_func = ucontrol->value.enumerated.item[0]; corgi_ext_control(&card->dapm); return 1; } @@ -183,7 +183,7 @@ static int corgi_set_jack(struct snd_kcontrol *kcontrol, static int corgi_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = corgi_spk_func; + ucontrol->value.enumerated.item[0] = corgi_spk_func; return 0; } @@ -192,10 +192,10 @@ static int corgi_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (corgi_spk_func == ucontrol->value.integer.value[0]) + if (corgi_spk_func == ucontrol->value.enumerated.item[0]) return 0; - corgi_spk_func = ucontrol->value.integer.value[0]; + corgi_spk_func = ucontrol->value.enumerated.item[0]; corgi_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/pxa/magician.c b/sound/soc/pxa/magician.c index 241d0be42d7a..62b8377a9d2b 100644 --- a/sound/soc/pxa/magician.c +++ b/sound/soc/pxa/magician.c @@ -308,17 +308,17 @@ static int magician_set_spk(struct snd_kcontrol *kcontrol, static int magician_get_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = magician_in_sel; + ucontrol->value.enumerated.item[0] = magician_in_sel; return 0; } static int magician_set_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - if (magician_in_sel == ucontrol->value.integer.value[0]) + if (magician_in_sel == ucontrol->value.enumerated.item[0]) return 0; - magician_in_sel = ucontrol->value.integer.value[0]; + magician_in_sel = ucontrol->value.enumerated.item[0]; switch (magician_in_sel) { case MAGICIAN_MIC: diff --git a/sound/soc/pxa/poodle.c b/sound/soc/pxa/poodle.c index 84d0e2e50808..4b3b714f5ee7 100644 --- a/sound/soc/pxa/poodle.c +++ b/sound/soc/pxa/poodle.c @@ -138,7 +138,7 @@ static struct snd_soc_ops poodle_ops = { static int poodle_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = poodle_jack_func; + ucontrol->value.enumerated.item[0] = poodle_jack_func; return 0; } @@ -147,10 +147,10 @@ static int poodle_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (poodle_jack_func == ucontrol->value.integer.value[0]) + if (poodle_jack_func == ucontrol->value.enumerated.item[0]) return 0; - poodle_jack_func = ucontrol->value.integer.value[0]; + poodle_jack_func = ucontrol->value.enumerated.item[0]; poodle_ext_control(&card->dapm); return 1; } @@ -158,7 +158,7 @@ static int poodle_set_jack(struct snd_kcontrol *kcontrol, static int poodle_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = poodle_spk_func; + ucontrol->value.enumerated.item[0] = poodle_spk_func; return 0; } @@ -167,10 +167,10 @@ static int poodle_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (poodle_spk_func == ucontrol->value.integer.value[0]) + if (poodle_spk_func == ucontrol->value.enumerated.item[0]) return 0; - poodle_spk_func = ucontrol->value.integer.value[0]; + poodle_spk_func = ucontrol->value.enumerated.item[0]; poodle_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/pxa/spitz.c b/sound/soc/pxa/spitz.c index b00222620fd0..0e02634c8b7f 100644 --- a/sound/soc/pxa/spitz.c +++ b/sound/soc/pxa/spitz.c @@ -164,7 +164,7 @@ static struct snd_soc_ops spitz_ops = { static int spitz_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = spitz_jack_func; + ucontrol->value.enumerated.item[0] = spitz_jack_func; return 0; } @@ -173,10 +173,10 @@ static int spitz_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (spitz_jack_func == ucontrol->value.integer.value[0]) + if (spitz_jack_func == ucontrol->value.enumerated.item[0]) return 0; - spitz_jack_func = ucontrol->value.integer.value[0]; + spitz_jack_func = ucontrol->value.enumerated.item[0]; spitz_ext_control(&card->dapm); return 1; } @@ -184,7 +184,7 @@ static int spitz_set_jack(struct snd_kcontrol *kcontrol, static int spitz_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = spitz_spk_func; + ucontrol->value.enumerated.item[0] = spitz_spk_func; return 0; } @@ -193,10 +193,10 @@ static int spitz_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (spitz_spk_func == ucontrol->value.integer.value[0]) + if (spitz_spk_func == ucontrol->value.enumerated.item[0]) return 0; - spitz_spk_func = ucontrol->value.integer.value[0]; + spitz_spk_func = ucontrol->value.enumerated.item[0]; spitz_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/pxa/tosa.c b/sound/soc/pxa/tosa.c index 49518dd642aa..c508f024ecfb 100644 --- a/sound/soc/pxa/tosa.c +++ b/sound/soc/pxa/tosa.c @@ -95,7 +95,7 @@ static struct snd_soc_ops tosa_ops = { static int tosa_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = tosa_jack_func; + ucontrol->value.enumerated.item[0] = tosa_jack_func; return 0; } @@ -104,10 +104,10 @@ static int tosa_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (tosa_jack_func == ucontrol->value.integer.value[0]) + if (tosa_jack_func == ucontrol->value.enumerated.item[0]) return 0; - tosa_jack_func = ucontrol->value.integer.value[0]; + tosa_jack_func = ucontrol->value.enumerated.item[0]; tosa_ext_control(&card->dapm); return 1; } @@ -115,7 +115,7 @@ static int tosa_set_jack(struct snd_kcontrol *kcontrol, static int tosa_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = tosa_spk_func; + ucontrol->value.enumerated.item[0] = tosa_spk_func; return 0; } @@ -124,10 +124,10 @@ static int tosa_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (tosa_spk_func == ucontrol->value.integer.value[0]) + if (tosa_spk_func == ucontrol->value.enumerated.item[0]) return 0; - tosa_spk_func = ucontrol->value.integer.value[0]; + tosa_spk_func = ucontrol->value.enumerated.item[0]; tosa_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 00b6c9d039cf..e5101e0d2d37 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -355,7 +355,6 @@ static struct regmap_config lpass_cpu_regmap_config = { .readable_reg = lpass_cpu_regmap_readable, .volatile_reg = lpass_cpu_regmap_volatile, .cache_type = REGCACHE_FLAT, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index 84d9e77c0fbe..70a2559b63f9 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -481,10 +481,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, unsigned int cdcon_mask = 1 << i2s_regs->cdclkcon_off; unsigned int rsrc_mask = 1 << i2s_regs->rclksrc_off; u32 mod, mask, val = 0; + unsigned long flags; - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); switch (clk_id) { case SAMSUNG_I2S_OPCLK: @@ -575,11 +576,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); mod = (mod & ~mask) | val; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); return 0; } @@ -590,6 +591,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, struct i2s_dai *i2s = to_info(dai); int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave; u32 mod, tmp = 0; + unsigned long flags; lrp_shift = i2s->variant_regs->lrp_off; sdf_shift = i2s->variant_regs->sdf_off; @@ -649,7 +651,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); /* * Don't change the I2S mode if any controller is active on this @@ -657,7 +659,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, */ if (any_active(i2s) && ((mod & (sdf_mask | lrp_rlow | mod_slave)) != tmp)) { - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); dev_err(&i2s->pdev->dev, "%s:%d Other DAI busy\n", __func__, __LINE__); return -EAGAIN; @@ -666,7 +668,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, mod &= ~(sdf_mask | lrp_rlow | mod_slave); mod |= tmp; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); return 0; } @@ -676,6 +678,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, { struct i2s_dai *i2s = to_info(dai); u32 mod, mask = 0, val = 0; + unsigned long flags; if (!is_secondary(i2s)) mask |= (MOD_DC2_EN | MOD_DC1_EN); @@ -744,11 +747,11 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); mod = (mod & ~mask) | val; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); samsung_asoc_init_dma_data(dai, &i2s->dma_playback, &i2s->dma_capture); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 0d3707987900..581175a51ecf 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3573,7 +3573,7 @@ static int snd_soc_dapm_dai_link_get(struct snd_kcontrol *kcontrol, { struct snd_soc_dapm_widget *w = snd_kcontrol_chip(kcontrol); - ucontrol->value.integer.value[0] = w->params_select; + ucontrol->value.enumerated.item[0] = w->params_select; return 0; } @@ -3587,13 +3587,13 @@ static int snd_soc_dapm_dai_link_put(struct snd_kcontrol *kcontrol, if (w->power) return -EBUSY; - if (ucontrol->value.integer.value[0] == w->params_select) + if (ucontrol->value.enumerated.item[0] == w->params_select) return 0; - if (ucontrol->value.integer.value[0] >= w->num_params) + if (ucontrol->value.enumerated.item[0] >= w->num_params) return -EINVAL; - w->params_select = ucontrol->value.integer.value[0]; + w->params_select = ucontrol->value.enumerated.item[0]; return 0; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a11cfd20a6a0..9102ae172d2a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1952,6 +1952,9 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) else val *= halt_poll_ns_grow; + if (val > halt_poll_ns) + val = halt_poll_ns; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } |