diff options
56 files changed, 646 insertions, 264 deletions
diff --git a/Documentation/prctl/no_new_privs.txt b/Documentation/prctl/no_new_privs.txt new file mode 100644 index 000000000000..cb705ec69abe --- /dev/null +++ b/Documentation/prctl/no_new_privs.txt @@ -0,0 +1,50 @@ +The execve system call can grant a newly-started program privileges that +its parent did not have. The most obvious examples are setuid/setgid +programs and file capabilities. To prevent the parent program from +gaining these privileges as well, the kernel and user code must be +careful to prevent the parent from doing anything that could subvert the +child. For example: + + - The dynamic loader handles LD_* environment variables differently if + a program is setuid. + + - chroot is disallowed to unprivileged processes, since it would allow + /etc/passwd to be replaced from the point of view of a process that + inherited chroot. + + - The exec code has special handling for ptrace. + +These are all ad-hoc fixes. The no_new_privs bit (since Linux 3.5) is a +new, generic mechanism to make it safe for a process to modify its +execution environment in a manner that persists across execve. Any task +can set no_new_privs. Once the bit is set, it is inherited across fork, +clone, and execve and cannot be unset. With no_new_privs set, execve +promises not to grant the privilege to do anything that could not have +been done without the execve call. For example, the setuid and setgid +bits will no longer change the uid or gid; file capabilities will not +add to the permitted set, and LSMs will not relax constraints after +execve. + +Note that no_new_privs does not prevent privilege changes that do not +involve execve. An appropriately privileged task can still call +setuid(2) and receive SCM_RIGHTS datagrams. + +There are two main use cases for no_new_privs so far: + + - Filters installed for the seccomp mode 2 sandbox persist across + execve and can change the behavior of newly-executed programs. + Unprivileged users are therefore only allowed to install such filters + if no_new_privs is set. + + - By itself, no_new_privs can be used to reduce the attack surface + available to an unprivileged user. If everything running with a + given uid has no_new_privs set, then that uid will be unable to + escalate its privileges by directly attacking setuid, setgid, and + fcap-using binaries; it will need to compromise something without the + no_new_privs bit set first. + +In the future, other potentially dangerous kernel features could become +available to unprivileged tasks if no_new_privs is set. In principle, +several options to unshare(2) and clone(2) would be safe when +no_new_privs is set, and no_new_privs + chroot is considerable less +dangerous than chroot by itself. diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt index f0ab5cf28fca..4a7b54bd37e8 100644 --- a/Documentation/stable_kernel_rules.txt +++ b/Documentation/stable_kernel_rules.txt @@ -12,6 +12,12 @@ Rules on what kind of patches are accepted, and which ones are not, into the marked CONFIG_BROKEN), an oops, a hang, data corruption, a real security issue, or some "oh, that's not good" issue. In short, something critical. + - Serious issues as reported by a user of a distribution kernel may also + be considered if they fix a notable performance or interactivity issue. + As these fixes are not as obvious and have a higher risk of a subtle + regression they should only be submitted by a distribution kernel + maintainer and include an addendum linking to a bugzilla entry if it + exists and additional information on the user-visible impact. - New device IDs and quirks are also accepted. - No "theoretical race condition" issues, unless an explanation of how the race can be exploited is also provided. @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Saber-toothed Squirrel # *DOCUMENTATION* diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 43a31fb06318..36ff15bbfdd4 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -183,7 +183,9 @@ SECTIONS } #endif +#ifdef CONFIG_SMP PERCPU_SECTION(L1_CACHE_BYTES) +#endif #ifdef CONFIG_XIP_KERNEL __data_loc = ALIGN(4); /* location in binary */ diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 573be57d3d28..6f6d13f91e4c 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -212,7 +212,7 @@ config MACH_SMDKV310 select EXYNOS_DEV_SYSMMU select EXYNOS4_DEV_AHCI select SAMSUNG_DEV_KEYPAD - select EXYNOS4_DEV_DMA + select EXYNOS_DEV_DMA select SAMSUNG_DEV_PWM select EXYNOS4_DEV_USB_OHCI select EXYNOS4_SETUP_FIMD0 @@ -264,7 +264,7 @@ config MACH_UNIVERSAL_C210 select S5P_DEV_ONENAND select S5P_DEV_TV select EXYNOS_DEV_SYSMMU - select EXYNOS4_DEV_DMA + select EXYNOS_DEV_DMA select EXYNOS_DEV_DRM select EXYNOS4_SETUP_FIMD0 select EXYNOS4_SETUP_I2C1 @@ -303,7 +303,7 @@ config MACH_NURI select S5P_DEV_MFC select S5P_DEV_USB_EHCI select S5P_SETUP_MIPIPHY - select EXYNOS4_DEV_DMA + select EXYNOS_DEV_DMA select EXYNOS_DEV_DRM select EXYNOS4_SETUP_FIMC select EXYNOS4_SETUP_FIMD0 @@ -341,7 +341,7 @@ config MACH_ORIGEN select SAMSUNG_DEV_PWM select EXYNOS_DEV_DRM select EXYNOS_DEV_SYSMMU - select EXYNOS4_DEV_DMA + select EXYNOS_DEV_DMA select EXYNOS4_DEV_USB_OHCI select EXYNOS4_SETUP_FIMD0 select EXYNOS4_SETUP_SDHCI diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 17dc66a085a5..e1a17ac7b3b4 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -152,13 +152,14 @@ enum mx6q_clks { ssi2, ssi3, uart_ipg, uart_serial, usboh3, usdhc1, usdhc2, usdhc3, usdhc4, vdo_axi, vpu_axi, cko1, pll1_sys, pll2_bus, pll3_usb_otg, pll4_audio, pll5_video, pll6_mlb, pll7_usb_host, pll8_enet, ssi1_ipg, - ssi2_ipg, ssi3_ipg, clk_max + ssi2_ipg, ssi3_ipg, rom, + clk_max }; static struct clk *clk[clk_max]; static enum mx6q_clks const clks_init_on[] __initconst = { - mmdc_ch0_axi, mmdc_ch1_axi, + mmdc_ch0_axi, rom, }; int __init mx6q_clocks_init(void) @@ -364,6 +365,7 @@ int __init mx6q_clocks_init(void) clk[gpmi_bch] = imx_clk_gate2("gpmi_bch", "usdhc4", base + 0x78, 26); clk[gpmi_io] = imx_clk_gate2("gpmi_io", "enfc", base + 0x78, 28); clk[gpmi_apb] = imx_clk_gate2("gpmi_apb", "usdhc3", base + 0x78, 30); + clk[rom] = imx_clk_gate2("rom", "ahb", base + 0x7c, 0); clk[sata] = imx_clk_gate2("sata", "ipg", base + 0x7c, 4); clk[sdma] = imx_clk_gate2("sdma", "ahb", base + 0x7c, 6); clk[spba] = imx_clk_gate2("spba", "ipg", base + 0x7c, 12); diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c index 70a81f900bb5..53c39d239d6e 100644 --- a/arch/arm/mach-omap2/board-flash.c +++ b/arch/arm/mach-omap2/board-flash.c @@ -97,11 +97,6 @@ __init board_onenand_init(struct mtd_partition *onenand_parts, gpmc_onenand_init(&board_onenand_data); } -#else -void -__init board_onenand_init(struct mtd_partition *nor_parts, u8 nr_parts, u8 cs) -{ -} #endif /* CONFIG_MTD_ONENAND_OMAP2 || CONFIG_MTD_ONENAND_OMAP2_MODULE */ #if defined(CONFIG_MTD_NAND_OMAP2) || \ diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c index e2b701e164f6..ba6f9a0a43e9 100644 --- a/arch/arm/mach-omap2/clock44xx_data.c +++ b/arch/arm/mach-omap2/clock44xx_data.c @@ -3417,9 +3417,12 @@ int __init omap4xxx_clk_init(void) if (cpu_is_omap443x()) { cpu_mask = RATE_IN_4430; cpu_clkflg = CK_443X; - } else if (cpu_is_omap446x()) { + } else if (cpu_is_omap446x() || cpu_is_omap447x()) { cpu_mask = RATE_IN_4460 | RATE_IN_4430; cpu_clkflg = CK_446X | CK_443X; + + if (cpu_is_omap447x()) + pr_warn("WARNING: OMAP4470 clock data incomplete!\n"); } else { return 0; } diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index 9e37026ef9dd..9bd135531d76 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -779,6 +779,7 @@ DT_MACHINE_START(ARMADILLO800EVA_DT, "armadillo800eva") .init_irq = r8a7740_init_irq, .handle_irq = shmobile_handle_irq_intc, .init_machine = eva_init, + .init_late = shmobile_init_late, .timer = &shmobile_timer, .dt_compat = eva_boards_compat_dt, MACHINE_END diff --git a/arch/arm/mach-shmobile/board-kzm9d.c b/arch/arm/mach-shmobile/board-kzm9d.c index 7bc5e7d39f9b..6a33cf393428 100644 --- a/arch/arm/mach-shmobile/board-kzm9d.c +++ b/arch/arm/mach-shmobile/board-kzm9d.c @@ -80,6 +80,7 @@ DT_MACHINE_START(KZM9D_DT, "kzm9d") .init_irq = emev2_init_irq, .handle_irq = gic_handle_irq, .init_machine = kzm9d_add_standard_devices, + .init_late = shmobile_init_late, .timer = &shmobile_timer, .dt_compat = kzm9d_boards_compat_dt, MACHINE_END diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index d8e33b682832..c0ae815e7beb 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -455,6 +455,7 @@ DT_MACHINE_START(KZM9G_DT, "kzm9g") .init_irq = sh73a0_init_irq, .handle_irq = gic_handle_irq, .init_machine = kzm_init, + .init_late = shmobile_init_late, .timer = &shmobile_timer, .dt_compat = kzm9g_boards_compat_dt, MACHINE_END diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index b577f7c44678..150122a44630 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -1512,6 +1512,9 @@ static void __init mackerel_init(void) gpio_request(GPIO_FN_SDHID0_1, NULL); gpio_request(GPIO_FN_SDHID0_0, NULL); + /* SDHI0 PORT172 card-detect IRQ26 */ + gpio_request(GPIO_FN_IRQ26_172, NULL); + #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE) /* enable SDHI1 */ gpio_request(GPIO_FN_SDHICMD1, NULL); diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c index 472d1f5361e5..3946c4ba2aa8 100644 --- a/arch/arm/mach-shmobile/clock-sh73a0.c +++ b/arch/arm/mach-shmobile/clock-sh73a0.c @@ -475,9 +475,9 @@ static struct clk *late_main_clks[] = { enum { MSTP001, MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP100, - MSTP219, + MSTP219, MSTP218, MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200, - MSTP331, MSTP329, MSTP325, MSTP323, MSTP318, + MSTP331, MSTP329, MSTP325, MSTP323, MSTP314, MSTP313, MSTP312, MSTP311, MSTP303, MSTP302, MSTP301, MSTP300, MSTP411, MSTP410, MSTP403, @@ -497,6 +497,7 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP116] = MSTP(&div4_clks[DIV4_HP], SMSTPCR1, 16, 0), /* IIC0 */ [MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */ [MSTP219] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 19, 0), /* SCIFA7 */ + [MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* SY-DMAC */ [MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */ [MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */ [MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */ @@ -508,7 +509,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */ [MSTP325] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 25, 0), /* IrDA */ [MSTP323] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 23, 0), /* IIC1 */ - [MSTP318] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 18, 0), /* SY-DMAC */ [MSTP314] = MSTP(&div6_clks[DIV6_SDHI0], SMSTPCR3, 14, 0), /* SDHI0 */ [MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */ [MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */ @@ -552,6 +552,7 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* I2C0 */ CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */ CLKDEV_DEV_ID("sh-sci.7", &mstp_clks[MSTP219]), /* SCIFA7 */ + CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* SY-DMAC */ CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */ CLKDEV_DEV_ID("sh-sci.8", &mstp_clks[MSTP206]), /* SCIFB */ CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */ @@ -563,7 +564,6 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */ CLKDEV_DEV_ID("sh_irda.0", &mstp_clks[MSTP325]), /* IrDA */ CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* I2C1 */ - CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP318]), /* SY-DMAC */ CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */ CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */ CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */ diff --git a/arch/arm/mach-shmobile/intc-r8a7779.c b/arch/arm/mach-shmobile/intc-r8a7779.c index 550b23df4fd4..f04fad4ec4fb 100644 --- a/arch/arm/mach-shmobile/intc-r8a7779.c +++ b/arch/arm/mach-shmobile/intc-r8a7779.c @@ -35,6 +35,9 @@ #define INT2SMSKCR3 0xfe7822ac #define INT2SMSKCR4 0xfe7822b0 +#define INT2NTSR0 0xfe700060 +#define INT2NTSR1 0xfe700064 + static int r8a7779_set_wake(struct irq_data *data, unsigned int on) { return 0; /* always allow wakeup */ @@ -49,6 +52,10 @@ void __init r8a7779_init_irq(void) gic_init(0, 29, gic_dist_base, gic_cpu_base); gic_arch_extn.irq_set_wake = r8a7779_set_wake; + /* route all interrupts to ARM */ + __raw_writel(0xffffffff, INT2NTSR0); + __raw_writel(0x3fffffff, INT2NTSR1); + /* unmask all known interrupts in INTCS2 */ __raw_writel(0xfffffff0, INT2SMSKCR0); __raw_writel(0xfff7ffff, INT2SMSKCR1); diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index bacdd667e3b1..e859fcdb3d58 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -25,7 +25,12 @@ #define is_sh73a0() (machine_is_ag5evm() || machine_is_kota2() || \ of_machine_is_compatible("renesas,sh73a0")) #define is_r8a7779() machine_is_marzen() + +#ifdef CONFIG_ARCH_EMEV2 #define is_emev2() of_machine_is_compatible("renesas,emev2") +#else +#define is_emev2() (0) +#endif static unsigned int __init shmobile_smp_get_core_count(void) { diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c index 6a4bd582c028..fafce9ce8218 100644 --- a/arch/arm/mach-shmobile/setup-sh7372.c +++ b/arch/arm/mach-shmobile/setup-sh7372.c @@ -484,7 +484,7 @@ static const struct sh_dmae_slave_config sh7372_dmae_slaves[] = { }, }; -#define SH7372_CHCLR 0x220 +#define SH7372_CHCLR (0x220 - 0x20) static const struct sh_dmae_channel sh7372_dmae_channels[] = { { diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e5dad60b558b..cf4528d51774 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -791,6 +791,79 @@ void __init iotable_init(struct map_desc *io_desc, int nr) } } +#ifndef CONFIG_ARM_LPAE + +/* + * The Linux PMD is made of two consecutive section entries covering 2MB + * (see definition in include/asm/pgtable-2level.h). However a call to + * create_mapping() may optimize static mappings by using individual + * 1MB section mappings. This leaves the actual PMD potentially half + * initialized if the top or bottom section entry isn't used, leaving it + * open to problems if a subsequent ioremap() or vmalloc() tries to use + * the virtual space left free by that unused section entry. + * + * Let's avoid the issue by inserting dummy vm entries covering the unused + * PMD halves once the static mappings are in place. + */ + +static void __init pmd_empty_section_gap(unsigned long addr) +{ + struct vm_struct *vm; + + vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm)); + vm->addr = (void *)addr; + vm->size = SECTION_SIZE; + vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; + vm->caller = pmd_empty_section_gap; + vm_area_add_early(vm); +} + +static void __init fill_pmd_gaps(void) +{ + struct vm_struct *vm; + unsigned long addr, next = 0; + pmd_t *pmd; + + /* we're still single threaded hence no lock needed here */ + for (vm = vmlist; vm; vm = vm->next) { + if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + continue; + addr = (unsigned long)vm->addr; + if (addr < next) + continue; + + /* + * Check if this vm starts on an odd section boundary. + * If so and the first section entry for this PMD is free + * then we block the corresponding virtual address. + */ + if ((addr & ~PMD_MASK) == SECTION_SIZE) { + pmd = pmd_off_k(addr); + if (pmd_none(*pmd)) + pmd_empty_section_gap(addr & PMD_MASK); + } + + /* + * Then check if this vm ends on an odd section boundary. + * If so and the second section entry for this PMD is empty + * then we block the corresponding virtual address. + */ + addr += vm->size; + if ((addr & ~PMD_MASK) == SECTION_SIZE) { + pmd = pmd_off_k(addr) + 1; + if (pmd_none(*pmd)) + pmd_empty_section_gap(addr); + } + + /* no need to look at any vm entry until we hit the next PMD */ + next = (addr + PMD_SIZE - 1) & PMD_MASK; + } +} + +#else +#define fill_pmd_gaps() do { } while (0) +#endif + static void * __initdata vmalloc_min = (void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET); @@ -1072,6 +1145,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) */ if (mdesc->map_io) mdesc->map_io(); + fill_pmd_gaps(); /* * Finally flush the caches and tlb to ensure that we're in a diff --git a/arch/arm/plat-samsung/include/plat/map-s3c.h b/arch/arm/plat-samsung/include/plat/map-s3c.h index 7d048759b772..c0c70a895ca8 100644 --- a/arch/arm/plat-samsung/include/plat/map-s3c.h +++ b/arch/arm/plat-samsung/include/plat/map-s3c.h @@ -22,7 +22,7 @@ #define S3C24XX_VA_WATCHDOG S3C_VA_WATCHDOG #define S3C2412_VA_SSMC S3C_ADDR_CPU(0x00000000) -#define S3C2412_VA_EBI S3C_ADDR_CPU(0x00010000) +#define S3C2412_VA_EBI S3C_ADDR_CPU(0x00100000) #define S3C2410_PA_UART (0x50000000) #define S3C24XX_PA_UART S3C2410_PA_UART diff --git a/arch/arm/plat-samsung/include/plat/watchdog-reset.h b/arch/arm/plat-samsung/include/plat/watchdog-reset.h index f19aff19205c..bc4db9b04e36 100644 --- a/arch/arm/plat-samsung/include/plat/watchdog-reset.h +++ b/arch/arm/plat-samsung/include/plat/watchdog-reset.h @@ -25,7 +25,7 @@ static inline void arch_wdt_reset(void) __raw_writel(0, S3C2410_WTCON); /* disable watchdog, to be safe */ - if (s3c2410_wdtclk) + if (!IS_ERR(s3c2410_wdtclk)) clk_enable(s3c2410_wdtclk); /* put initial values into count and data */ diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 32b394f3b854..6eb75b80488c 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -103,6 +103,11 @@ static inline void hard_irq_disable(void) /* include/linux/interrupt.h needs hard_irq_disable to be a macro */ #define hard_irq_disable hard_irq_disable +static inline bool lazy_irq_pending(void) +{ + return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS); +} + /* * This is called by asynchronous interrupts to conditionally * re-enable hard interrupts when soft-disabled after having diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index ed1718feb9d9..5971c85df136 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -558,27 +558,54 @@ _GLOBAL(ret_from_except_lite) mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ -#ifdef CONFIG_PREEMPT clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */ - li r0,_TIF_NEED_RESCHED /* bits to check */ ld r3,_MSR(r1) ld r4,TI_FLAGS(r9) - /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */ - rlwimi r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING - and. r0,r4,r0 /* check NEED_RESCHED and maybe SIGPENDING */ - bne do_work - -#else /* !CONFIG_PREEMPT */ - ld r3,_MSR(r1) /* Returning to user mode? */ andi. r3,r3,MSR_PR - beq restore /* if not, just restore regs and return */ + beq resume_kernel /* Check current_thread_info()->flags */ + andi. r0,r4,_TIF_USER_WORK_MASK + beq restore + + andi. r0,r4,_TIF_NEED_RESCHED + beq 1f + bl .restore_interrupts + bl .schedule + b .ret_from_except_lite + +1: bl .save_nvgprs + bl .restore_interrupts + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_notify_resume + b .ret_from_except + +resume_kernel: +#ifdef CONFIG_PREEMPT + /* Check if we need to preempt */ + andi. r0,r4,_TIF_NEED_RESCHED + beq+ restore + /* Check that preempt_count() == 0 and interrupts are enabled */ + lwz r8,TI_PREEMPT(r9) + cmpwi cr1,r8,0 + ld r0,SOFTE(r1) + cmpdi r0,0 + crandc eq,cr1*4+eq,eq + bne restore + + /* + * Here we are preempting the current task. We want to make + * sure we are soft-disabled first + */ + SOFT_DISABLE_INTS(r3,r4) +1: bl .preempt_schedule_irq + + /* Re-test flags and eventually loop */ clrrdi r9,r1,THREAD_SHIFT ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_USER_WORK_MASK - bne do_work -#endif /* !CONFIG_PREEMPT */ + andi. r0,r4,_TIF_NEED_RESCHED + bne 1b +#endif /* CONFIG_PREEMPT */ .globl fast_exc_return_irq fast_exc_return_irq: @@ -759,50 +786,6 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ 1: b .ret_from_except /* What else to do here ? */ - - -3: -do_work: -#ifdef CONFIG_PREEMPT - andi. r0,r3,MSR_PR /* Returning to user mode? */ - bne user_work - /* Check that preempt_count() == 0 and interrupts are enabled */ - lwz r8,TI_PREEMPT(r9) - cmpwi cr1,r8,0 - ld r0,SOFTE(r1) - cmpdi r0,0 - crandc eq,cr1*4+eq,eq - bne restore - - /* - * Here we are preempting the current task. We want to make - * sure we are soft-disabled first - */ - SOFT_DISABLE_INTS(r3,r4) -1: bl .preempt_schedule_irq - - /* Re-test flags and eventually loop */ - clrrdi r9,r1,THREAD_SHIFT - ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_NEED_RESCHED - bne 1b - b restore - -user_work: -#endif /* CONFIG_PREEMPT */ - - andi. r0,r4,_TIF_NEED_RESCHED - beq 1f - bl .restore_interrupts - bl .schedule - b .ret_from_except_lite - -1: bl .save_nvgprs - bl .restore_interrupts - addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_notify_resume - b .ret_from_except - unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD bl .unrecoverable_exception diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 7835a5e1ea5f..1b415027ec0e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -277,7 +277,7 @@ EXPORT_SYMBOL(arch_local_irq_restore); * NOTE: This is called with interrupts hard disabled but not marked * as such in paca->irq_happened, so we need to resync this. */ -void restore_interrupts(void) +void notrace restore_interrupts(void) { if (irqs_disabled()) { local_paca->irq_happened |= PACA_IRQ_HARD_DIS; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 1b488e5305c5..0794a3017b1b 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1312,7 +1312,7 @@ static struct opal_secondary_data { extern char opal_secondary_entry; -static void prom_query_opal(void) +static void __init prom_query_opal(void) { long rc; @@ -1436,7 +1436,7 @@ static void __init prom_opal_hold_cpus(void) prom_debug("prom_opal_hold_cpus: end...\n"); } -static void prom_opal_takeover(void) +static void __init prom_opal_takeover(void) { struct opal_secondary_data *data = &RELOC(opal_secondary_data); struct opal_takeover_args *args = &data->args; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index a84aafce2a12..a1044f43becd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -810,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) lwz r3,VCORE_NAPPING_THREADS(r5) lwz r4,VCPU_PTID(r9) li r0,1 - sldi r0,r0,r4 + sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ beq 43f mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b6edbb3b4a54..6e8f677f5646 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -635,7 +635,7 @@ static inline int __init read_usm_ranges(const u32 **usm) */ static void __init parse_drconf_memory(struct device_node *memory) { - const u32 *dm, *usm; + const u32 *uninitialized_var(dm), *usm; unsigned int n, rc, ranges, is_kexec_kdump = 0; unsigned long lmb_size, base, size, sz; int nid; diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S index 55ba3855a97f..7d3a3b5619a2 100644 --- a/arch/powerpc/net/bpf_jit_64.S +++ b/arch/powerpc/net/bpf_jit_64.S @@ -105,6 +105,7 @@ sk_load_byte_msh_positive_offset: mr r4, r_addr; \ li r6, SIZE; \ bl skb_copy_bits; \ + nop; \ /* R3 = 0 on success */ \ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ ld r0, 16(r1); \ @@ -156,6 +157,7 @@ bpf_slow_path_byte_msh: mr r4, r_addr; \ li r5, SIZE; \ bl bpf_internal_load_pointer_neg_helper; \ + nop; \ /* R3 != 0 on success */ \ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ ld r0, 16(r1); \ diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0915b1ad66ce..2d311c0caf8e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -106,7 +106,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, tcep++; } - if (tbl->it_type == TCE_PCI_SWINV_CREATE) + if (tbl->it_type & TCE_PCI_SWINV_CREATE) tce_invalidate_pSeries_sw(tbl, tces, tcep - 1); return 0; } @@ -121,7 +121,7 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) while (npages--) *(tcep++) = 0; - if (tbl->it_type == TCE_PCI_SWINV_FREE) + if (tbl->it_type & TCE_PCI_SWINV_FREE) tce_invalidate_pSeries_sw(tbl, tces, tcep - 1); } diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index 41a34bc4a9a2..e61483e8e960 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -106,7 +106,7 @@ static void check_and_cede_processor(void) * we first hard disable then check. */ hard_irq_disable(); - if (get_paca()->irq_happened == 0) + if (!lazy_irq_pending()) cede_processor(); } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0f3ab06d2222..eab3492a45c5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -971,7 +971,7 @@ static int cpu_cmd(void) /* print cpus waiting or in xmon */ printf("cpus stopped:"); count = 0; - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_cpu(cpu) { if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index daeca56211e3..673ac9b63d6b 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -38,7 +38,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { int err = 0; - bool ia32 = is_ia32_task(); + bool ia32 = test_thread_flag(TIF_IA32); if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) return -EFAULT; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 340ee49961a6..f91e80f4f180 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -176,7 +176,7 @@ #define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ #define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ #define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */ +#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */ #define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */ /* Virtualization flags: Linux defined, word 8 */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8afb69319815..b2297e58c6ed 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -422,12 +422,14 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, return 0; } - if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (intsrc->source_irq == 0) { if (acpi_skip_timer_override) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + printk(PREFIX "BIOS IRQ0 override ignored.\n"); return 0; } - if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + + if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity + && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); } @@ -1334,17 +1336,12 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d) } /* - * Force ignoring BIOS IRQ0 pin2 override + * Force ignoring BIOS IRQ0 override */ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) { - /* - * The ati_ixp4x0_rev() early PCI quirk should have set - * the acpi_skip_timer_override flag already: - */ if (!acpi_skip_timer_override) { - WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n"); - pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", + pr_notice("%s detected: Ignoring BIOS IRQ0 override\n", d->ident); acpi_skip_timer_override = 1; } @@ -1438,7 +1435,7 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { * is enabled. This input is incorrectly designated the * ISA IRQ 0 via an interrupt source override even though * it is wired to the output of the master 8259A and INTIN0 - * is not connected at all. Force ignoring BIOS IRQ0 pin2 + * is not connected at all. Force ignoring BIOS IRQ0 * override in that cases. */ { @@ -1473,6 +1470,14 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq 6715b"), }, }, + { + .callback = dmi_ignore_irq0_timer_override, + .ident = "FUJITSU SIEMENS", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), + }, + }, {} }; diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl index dfea390e1608..c7b3fe2d72e0 100644 --- a/arch/x86/kernel/cpu/mkcapflags.pl +++ b/arch/x86/kernel/cpu/mkcapflags.pl @@ -1,4 +1,4 @@ -#!/usr/bin/perl +#!/usr/bin/perl -w # # Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h # @@ -11,22 +11,35 @@ open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n"; print OUT "#include <asm/cpufeature.h>\n\n"; print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n"; +%features = (); +$err = 0; + while (defined($line = <IN>)) { if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) { $macro = $1; - $feature = $2; + $feature = "\L$2"; $tail = $3; if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) { - $feature = $1; + $feature = "\L$1"; } - if ($feature ne '') { - printf OUT "\t%-32s = \"%s\",\n", - "[$macro]", "\L$feature"; + next if ($feature eq ''); + + if ($features{$feature}++) { + print STDERR "$in: duplicate feature name: $feature\n"; + $err++; } + printf OUT "\t%-32s = \"%s\",\n", "[$macro]", $feature; } } print OUT "};\n"; close(IN); close(OUT); + +if ($err) { + unlink($out); + exit(1); +} + +exit(0); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index addf9e82a7f2..ee8e9abc859f 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,7 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { - { X86_FEATURE_DTS, CR_EAX, 0, 0x00000006, 0 }, + { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 8bfb6146f753..3f61904365cf 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -444,12 +444,12 @@ void kgdb_roundup_cpus(unsigned long flags) /** * kgdb_arch_handle_exception - Handle architecture specific GDB packets. - * @vector: The error vector of the exception that happened. + * @e_vector: The error vector of the exception that happened. * @signo: The signal number of the exception that happened. * @err_code: The error code of the exception that happened. - * @remcom_in_buffer: The buffer of the packet we have read. - * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into. - * @regs: The &struct pt_regs of the current process. + * @remcomInBuffer: The buffer of the packet we have read. + * @remcomOutBuffer: The buffer of %BUFMAX bytes to write a packet into. + * @linux_regs: The &struct pt_regs of the current process. * * This function MUST handle the 'c' and 's' command packets, * as well packets to set / remove a hardware breakpoint, if used. diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 25b48edb847c..5de92f1abd76 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -451,6 +451,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), }, }, + { /* Handle problems with rebooting on the Precision M6600. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), + }, + }, { } }; diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 459b58a8a15c..25b7ae8d058a 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL(csum_partial_copy_to_user); * @src: source address * @dst: destination address * @len: number of bytes to be copied. - * @isum: initial sum that is added into the result (32bit unfolded) + * @sum: initial sum that is added into the result (32bit unfolded) * * Returns an 32bit unfolded checksum of the buffer. */ diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index a43fa1a57d57..1502c50273b5 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -36,6 +36,7 @@ #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator" #define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80 static DEFINE_MUTEX(isolated_cpus_lock); +static DEFINE_MUTEX(round_robin_lock); static unsigned long power_saving_mwait_eax; @@ -107,7 +108,7 @@ static void round_robin_cpu(unsigned int tsk_index) if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) return; - mutex_lock(&isolated_cpus_lock); + mutex_lock(&round_robin_lock); cpumask_clear(tmp); for_each_cpu(cpu, pad_busy_cpus) cpumask_or(tmp, tmp, topology_thread_cpumask(cpu)); @@ -116,7 +117,7 @@ static void round_robin_cpu(unsigned int tsk_index) if (cpumask_empty(tmp)) cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus); if (cpumask_empty(tmp)) { - mutex_unlock(&isolated_cpus_lock); + mutex_unlock(&round_robin_lock); return; } for_each_cpu(cpu, tmp) { @@ -131,7 +132,7 @@ static void round_robin_cpu(unsigned int tsk_index) tsk_in_cpu[tsk_index] = preferred_cpu; cpumask_set_cpu(preferred_cpu, pad_busy_cpus); cpu_weight[preferred_cpu]++; - mutex_unlock(&isolated_cpus_lock); + mutex_unlock(&round_robin_lock); set_cpus_allowed_ptr(current, cpumask_of(preferred_cpu)); } diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 5577762daee1..6686b1eaf13e 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -243,7 +243,7 @@ static int pre_map_gar_callback(struct apei_exec_context *ctx, u8 ins = entry->instruction; if (ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER) - return acpi_os_map_generic_address(&entry->register_region); + return apei_map_generic_address(&entry->register_region); return 0; } @@ -276,7 +276,7 @@ static int post_unmap_gar_callback(struct apei_exec_context *ctx, u8 ins = entry->instruction; if (ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER) - acpi_os_unmap_generic_address(&entry->register_region); + apei_unmap_generic_address(&entry->register_region); return 0; } @@ -606,6 +606,19 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr, return 0; } +int apei_map_generic_address(struct acpi_generic_address *reg) +{ + int rc; + u32 access_bit_width; + u64 address; + + rc = apei_check_gar(reg, &address, &access_bit_width); + if (rc) + return rc; + return acpi_os_map_generic_address(reg); +} +EXPORT_SYMBOL_GPL(apei_map_generic_address); + /* read GAR in interrupt (including NMI) or process context */ int apei_read(u64 *val, struct acpi_generic_address *reg) { diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index cca240a33038..f220d642136e 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -7,6 +7,8 @@ #define APEI_INTERNAL_H #include <linux/cper.h> +#include <linux/acpi.h> +#include <linux/acpi_io.h> struct apei_exec_context; @@ -68,6 +70,13 @@ static inline int apei_exec_run_optional(struct apei_exec_context *ctx, u8 actio /* IP has been set in instruction function */ #define APEI_EXEC_SET_IP 1 +int apei_map_generic_address(struct acpi_generic_address *reg); + +static inline void apei_unmap_generic_address(struct acpi_generic_address *reg) +{ + acpi_os_unmap_generic_address(reg); +} + int apei_read(u64 *val, struct acpi_generic_address *reg); int apei_write(u64 val, struct acpi_generic_address *reg); diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 9b3cac0abecc..1599566ed1fe 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -301,7 +301,7 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic) if (!ghes) return ERR_PTR(-ENOMEM); ghes->generic = generic; - rc = acpi_os_map_generic_address(&generic->error_status_address); + rc = apei_map_generic_address(&generic->error_status_address); if (rc) goto err_free; error_block_length = generic->error_block_length; @@ -321,7 +321,7 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic) return ghes; err_unmap: - acpi_os_unmap_generic_address(&generic->error_status_address); + apei_unmap_generic_address(&generic->error_status_address); err_free: kfree(ghes); return ERR_PTR(rc); @@ -330,7 +330,7 @@ err_free: static void ghes_fini(struct ghes *ghes) { kfree(ghes->estatus); - acpi_os_unmap_generic_address(&ghes->generic->error_status_address); + apei_unmap_generic_address(&ghes->generic->error_status_address); } enum { diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index f3decb30223f..47a8caa89dbe 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -224,6 +224,7 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr, /* * Suspend / resume control */ +static int acpi_idle_suspend; static u32 saved_bm_rld; static void acpi_idle_bm_rld_save(void) @@ -242,13 +243,21 @@ static void acpi_idle_bm_rld_restore(void) int acpi_processor_suspend(struct acpi_device * device, pm_message_t state) { + if (acpi_idle_suspend == 1) + return 0; + acpi_idle_bm_rld_save(); + acpi_idle_suspend = 1; return 0; } int acpi_processor_resume(struct acpi_device * device) { + if (acpi_idle_suspend == 0) + return 0; + acpi_idle_bm_rld_restore(); + acpi_idle_suspend = 0; return 0; } @@ -754,6 +763,12 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, local_irq_disable(); + if (acpi_idle_suspend) { + local_irq_enable(); + cpu_relax(); + return -EBUSY; + } + lapic_timer_state_broadcast(pr, cx, 1); kt1 = ktime_get_real(); acpi_idle_do_entry(cx); @@ -823,6 +838,12 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, local_irq_disable(); + if (acpi_idle_suspend) { + local_irq_enable(); + cpu_relax(); + return -EBUSY; + } + if (cx->entry_method != ACPI_CSTATE_FFH) { current_thread_info()->status &= ~TS_POLLING; /* @@ -907,14 +928,21 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, drv, drv->safe_state_index); } else { local_irq_disable(); - acpi_safe_halt(); + if (!acpi_idle_suspend) + acpi_safe_halt(); local_irq_enable(); - return -EINVAL; + return -EBUSY; } } local_irq_disable(); + if (acpi_idle_suspend) { + local_irq_enable(); + cpu_relax(); + return -EBUSY; + } + if (cx->entry_method != ACPI_CSTATE_FFH) { current_thread_info()->status &= ~TS_POLLING; /* diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 9f66181c814e..240a24400976 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -173,7 +173,7 @@ static int param_set_trace_state(const char *val, struct kernel_param *kp) { int result = 0; - if (!strncmp(val, "enable", strlen("enable") - 1)) { + if (!strncmp(val, "enable", strlen("enable"))) { result = acpi_debug_trace(trace_method_name, trace_debug_level, trace_debug_layer, 0); if (result) @@ -181,7 +181,7 @@ static int param_set_trace_state(const char *val, struct kernel_param *kp) goto exit; } - if (!strncmp(val, "disable", strlen("disable") - 1)) { + if (!strncmp(val, "disable", strlen("disable"))) { int name = 0; result = acpi_debug_trace((char *)&name, trace_debug_level, trace_debug_layer, 0); diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index a576575617d7..1e0a9e17c31d 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -558,6 +558,8 @@ acpi_video_bus_DOS(struct acpi_video_bus *video, int bios_flag, int lcd_flag) union acpi_object arg0 = { ACPI_TYPE_INTEGER }; struct acpi_object_list args = { 1, &arg0 }; + if (!video->cap._DOS) + return 0; if (bios_flag < 0 || bios_flag > 3 || lcd_flag < 0 || lcd_flag > 1) return -EINVAL; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index e0fb5b0435a3..9cb845e49334 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1031,7 +1031,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_wait_for_children(dev, async); if (async_error) - return 0; + goto Complete; pm_runtime_get_noresume(dev); if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) @@ -1040,7 +1040,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) if (pm_wakeup_pending()) { pm_runtime_put_sync(dev); async_error = -EBUSY; - return 0; + goto Complete; } device_lock(dev); @@ -1097,6 +1097,8 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) } device_unlock(dev); + + Complete: complete_all(&dev->power.completion); if (error) { diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 7f1feb2f467a..637c51c11b44 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -693,7 +693,7 @@ static void __cpuinit get_core_online(unsigned int cpu) * sensors. We check this bit only, all the early CPUs * without thermal sensors will be filtered out. */ - if (!cpu_has(c, X86_FEATURE_DTS)) + if (!cpu_has(c, X86_FEATURE_DTHERM)) return; if (!pdev) { @@ -794,7 +794,7 @@ static struct notifier_block coretemp_cpu_notifier __refdata = { }; static const struct x86_cpu_id coretemp_ids[] = { - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTS }, + { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTHERM }, {} }; MODULE_DEVICE_TABLE(x86cpu, coretemp_ids); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1c2f9048e1ae..a4c219e3c859 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5784,8 +5784,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) super_types[mddev->major_version]. validate_super(mddev, rdev); if ((info->state & (1<<MD_DISK_SYNC)) && - (!test_bit(In_sync, &rdev->flags) || - rdev->raid_disk != info->raid_disk)) { + rdev->raid_disk != info->raid_disk) { /* This was a hot-add request, but events doesn't * match, so reject it. */ @@ -6751,7 +6750,7 @@ struct md_thread *md_register_thread(void (*run) (struct mddev *), struct mddev thread->tsk = kthread_run(md_thread, thread, "%s_%s", mdname(thread->mddev), - name ?: mddev->pers->name); + name); if (IS_ERR(thread->tsk)) { kfree(thread); return NULL; @@ -7298,6 +7297,7 @@ void md_do_sync(struct mddev *mddev) int skipped = 0; struct md_rdev *rdev; char *desc; + struct blk_plug plug; /* just incase thread restarts... */ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) @@ -7447,6 +7447,7 @@ void md_do_sync(struct mddev *mddev) } mddev->curr_resync_completed = j; + blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; @@ -7552,6 +7553,7 @@ void md_do_sync(struct mddev *mddev) * this also signals 'finished resyncing' to md_stop */ out: + blk_finish_plug(&plug); wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 9339e67fcc79..61a1833ebaf3 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -474,7 +474,8 @@ static int multipath_run (struct mddev *mddev) } { - mddev->thread = md_register_thread(multipathd, mddev, NULL); + mddev->thread = md_register_thread(multipathd, mddev, + "multipath"); if (!mddev->thread) { printk(KERN_ERR "multipath: couldn't allocate thread" " for %s\n", mdname(mddev)); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a9c7981ddd24..8c2754f835ef 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -517,8 +517,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect int bad_sectors; int disk = start_disk + i; - if (disk >= conf->raid_disks) - disk -= conf->raid_disks; + if (disk >= conf->raid_disks * 2) + disk -= conf->raid_disks * 2; rdev = rcu_dereference(conf->mirrors[disk].rdev); if (r1_bio->bios[disk] == IO_BLOCKED @@ -883,7 +883,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); struct md_rdev *blocked_rdev; - int plugged; int first_clone; int sectors_handled; int max_sectors; @@ -1034,7 +1033,6 @@ read_again: * the bad blocks. Each set of writes gets it's own r1bio * with a set of bios attached. */ - plugged = mddev_check_plugged(mddev); disks = conf->raid_disks * 2; retry_write: @@ -1191,6 +1189,8 @@ read_again: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Mustn't call r1_bio_write_done before this next test, * as it could result in the bio being freed. @@ -1213,9 +1213,6 @@ read_again: /* In case raid1d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -2621,7 +2618,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) goto abort; } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, NULL); + conf->thread = md_register_thread(raid1d, mddev, "raid1"); if (!conf->thread) { printk(KERN_ERR "md/raid1:%s: couldn't allocate thread\n", diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 99ae6068e456..acf5a828c7e1 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1039,7 +1039,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_fua = (bio->bi_rw & REQ_FUA); unsigned long flags; struct md_rdev *blocked_rdev; - int plugged; int sectors_handled; int max_sectors; int sectors; @@ -1239,7 +1238,6 @@ read_again: * of r10_bios is recored in bio->bi_phys_segments just as with * the read case. */ - plugged = mddev_check_plugged(mddev); r10_bio->read_slot = -1; /* make sure repl_bio gets freed */ raid10_find_phys(conf, r10_bio); @@ -1396,6 +1394,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev, 0, 0)) + md_wakeup_thread(mddev->thread); if (!r10_bio->devs[i].repl_bio) continue; @@ -1423,6 +1423,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Don't remove the bias on 'remaining' (one_write_done) until @@ -1448,9 +1450,6 @@ retry_write: /* In case raid10d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !mddev->bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -2310,7 +2309,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 if (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s<<9, conf->tmppage, WRITE) + s, conf->tmppage, WRITE) == 0) { /* Well, this device is dead */ printk(KERN_NOTICE @@ -2349,7 +2348,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 switch (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s<<9, conf->tmppage, + s, conf->tmppage, READ)) { case 0: /* Well, this device is dead */ @@ -2512,7 +2511,7 @@ read_more: slot = r10_bio->read_slot; printk_ratelimited( KERN_ERR - "md/raid10:%s: %s: redirecting" + "md/raid10:%s: %s: redirecting " "sector %llu to another mirror\n", mdname(mddev), bdevname(rdev->bdev, b), @@ -2661,7 +2660,8 @@ static void raid10d(struct mddev *mddev) blk_start_plug(&plug); for (;;) { - flush_pending_writes(conf); + if (atomic_read(&mddev->plug_cnt) == 0) + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { @@ -2890,6 +2890,12 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, /* want to reconstruct this device */ rb2 = r10_bio; sect = raid10_find_virt(conf, sector_nr, i); + if (sect >= mddev->resync_max_sectors) { + /* last stripe is not complete - don't + * try to recover this sector. + */ + continue; + } /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -3421,7 +3427,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) spin_lock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); - conf->thread = md_register_thread(raid10d, mddev, NULL); + conf->thread = md_register_thread(raid10d, mddev, "raid10"); if (!conf->thread) goto out; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d26767246d26..04348d76bb30 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -196,12 +196,14 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) BUG_ON(!list_empty(&sh->lru)); BUG_ON(atomic_read(&conf->active_stripes)==0); if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) + if (test_bit(STRIPE_DELAYED, &sh->state) && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) list_add_tail(&sh->lru, &conf->delayed_list); else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && sh->bm_seq - conf->seq_write > 0) list_add_tail(&sh->lru, &conf->bitmap_list); else { + clear_bit(STRIPE_DELAYED, &sh->state); clear_bit(STRIPE_BIT_DELAY, &sh->state); list_add_tail(&sh->lru, &conf->handle_list); } @@ -606,6 +608,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) * a chance*/ md_check_recovery(conf->mddev); } + /* + * Because md_wait_for_blocked_rdev + * will dec nr_pending, we must + * increment it first. + */ + atomic_inc(&rdev->nr_pending); md_wait_for_blocked_rdev(rdev, conf->mddev); } else { /* Acknowledged bad block - skip the write */ @@ -1737,6 +1745,7 @@ static void raid5_end_read_request(struct bio * bi, int error) } else { const char *bdn = bdevname(rdev->bdev, b); int retry = 0; + int set_bad = 0; clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); @@ -1748,7 +1757,8 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (conf->mddev->degraded >= conf->max_degraded) + else if (conf->mddev->degraded >= conf->max_degraded) { + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error not correctable " @@ -1756,8 +1766,9 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) + } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) { /* Oh, no!!! */ + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error NOT corrected!! " @@ -1765,7 +1776,7 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (atomic_read(&rdev->read_errors) + } else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING "md/raid:%s: Too many read errors, failing device %s.\n", @@ -1777,7 +1788,11 @@ static void raid5_end_read_request(struct bio * bi, int error) else { clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); - md_error(conf->mddev, rdev); + if (!(set_bad + && test_bit(In_sync, &rdev->flags) + && rdev_set_badblocks( + rdev, sh->sector, STRIPE_SECTORS, 0))) + md_error(conf->mddev, rdev); } } rdev_dec_pending(rdev, conf->mddev); @@ -3582,8 +3597,18 @@ static void handle_stripe(struct stripe_head *sh) finish: /* wait for this device to become unblocked */ - if (conf->mddev->external && unlikely(s.blocked_rdev)) - md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev); + if (unlikely(s.blocked_rdev)) { + if (conf->mddev->external) + md_wait_for_blocked_rdev(s.blocked_rdev, + conf->mddev); + else + /* Internal metadata will immediately + * be written by raid5d, so we don't + * need to wait here. + */ + rdev_dec_pending(s.blocked_rdev, + conf->mddev); + } if (s.handle_bad_blocks) for (i = disks; i--; ) { @@ -3881,8 +3906,6 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) raid_bio->bi_next = (void*)rdev; align_bi->bi_bdev = rdev->bdev; align_bi->bi_flags &= ~(1 << BIO_SEG_VALID); - /* No reshape active, so we can trust rdev->data_offset */ - align_bi->bi_sector += rdev->data_offset; if (!bio_fits_rdev(align_bi) || is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9, @@ -3893,6 +3916,9 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) return 0; } + /* No reshape active, so we can trust rdev->data_offset */ + align_bi->bi_sector += rdev->data_offset; + spin_lock_irq(&conf->device_lock); wait_event_lock_irq(conf->wait_for_stripe, conf->quiesce == 0, @@ -3971,7 +3997,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) struct stripe_head *sh; const int rw = bio_data_dir(bi); int remaining; - int plugged; if (unlikely(bi->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bi); @@ -3990,7 +4015,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) bi->bi_next = NULL; bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ - plugged = mddev_check_plugged(mddev); for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int previous; @@ -4092,6 +4116,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) if ((bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); + mddev_check_plugged(mddev); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -4099,10 +4124,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); break; } - } - if (!plugged) - md_wakeup_thread(mddev->thread); spin_lock_irq(&conf->device_lock); remaining = raid5_dec_bi_phys_segments(bi); @@ -4823,6 +4845,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) int raid_disk, memory, max_disks; struct md_rdev *rdev; struct disk_info *disk; + char pers_name[6]; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -4946,7 +4969,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) printk(KERN_INFO "md/raid:%s: allocated %dkB\n", mdname(mddev), memory); - conf->thread = md_register_thread(raid5d, mddev, NULL); + sprintf(pers_name, "raid%d", mddev->new_level); + conf->thread = md_register_thread(raid5d, mddev, pers_name); if (!conf->thread) { printk(KERN_ERR "md/raid:%s: couldn't allocate thread.\n", @@ -5465,10 +5489,9 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk >= 0 && rdev->saved_raid_disk >= first && conf->disks[rdev->saved_raid_disk].rdev == NULL) - disk = rdev->saved_raid_disk; - else - disk = first; - for ( ; disk <= last ; disk++) { + first = rdev->saved_raid_disk; + + for (disk = first; disk <= last; disk++) { p = conf->disks + disk; if (p->rdev == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5477,8 +5500,11 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk != disk) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); - break; + goto out; } + } + for (disk = first; disk <= last; disk++) { + p = conf->disks + disk; if (test_bit(WantReplacement, &p->rdev->flags) && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5490,6 +5516,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } +out: print_raid5_conf(conf); return err; } diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c index da14432806c6..efc4b7f308cf 100644 --- a/drivers/oprofile/oprofile_perf.c +++ b/drivers/oprofile/oprofile_perf.c @@ -25,7 +25,7 @@ static int oprofile_perf_enabled; static DEFINE_MUTEX(oprofile_perf_mutex); static struct op_counter_config *counter_config; -static struct perf_event **perf_events[nr_cpumask_bits]; +static struct perf_event **perf_events[NR_CPUS]; static int num_counters; /* diff --git a/include/linux/irq.h b/include/linux/irq.h index 61f5cec031e0..a5261e3d2e3c 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -301,8 +301,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_pm_shutdown: function called from core code on shutdown once per chip * @irq_print_chip: optional to print special chip info in show_interrupts * @flags: chip specific flags - * - * @release: release function solely used by UML */ struct irq_chip { const char *name; diff --git a/kernel/printk.c b/kernel/printk.c index a2276b916769..dba18211685e 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -193,12 +193,19 @@ static int console_may_schedule; * separated by ',', and find the message after the ';' character. */ +enum log_flags { + LOG_DEFAULT = 0, + LOG_NOCONS = 1, /* already flushed, do not print to console */ +}; + struct log { u64 ts_nsec; /* timestamp in nanoseconds */ u16 len; /* length of entire record */ u16 text_len; /* length of text buffer */ u16 dict_len; /* length of dictionary buffer */ - u16 level; /* syslog level + facility */ + u8 facility; /* syslog facility */ + u8 flags:5; /* internal record flags */ + u8 level:3; /* syslog level */ }; /* @@ -286,6 +293,7 @@ static u32 log_next(u32 idx) /* insert record into the buffer, discard old ones, update heads */ static void log_store(int facility, int level, + enum log_flags flags, u64 ts_nsec, const char *dict, u16 dict_len, const char *text, u16 text_len) { @@ -329,8 +337,13 @@ static void log_store(int facility, int level, msg->text_len = text_len; memcpy(log_dict(msg), dict, dict_len); msg->dict_len = dict_len; - msg->level = (facility << 3) | (level & 7); - msg->ts_nsec = local_clock(); + msg->facility = facility; + msg->level = level & 7; + msg->flags = flags & 0x1f; + if (ts_nsec > 0) + msg->ts_nsec = ts_nsec; + else + msg->ts_nsec = local_clock(); memset(log_dict(msg) + dict_len, 0, pad_len); msg->len = sizeof(struct log) + text_len + dict_len + pad_len; @@ -446,7 +459,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, ts_usec = msg->ts_nsec; do_div(ts_usec, 1000); len = sprintf(user->buf, "%u,%llu,%llu;", - msg->level, user->seq, ts_usec); + (msg->facility << 3) | msg->level, user->seq, ts_usec); /* escape non-printable characters */ for (i = 0; i < msg->text_len; i++) { @@ -787,6 +800,21 @@ static bool printk_time; #endif module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); +static size_t print_time(u64 ts, char *buf) +{ + unsigned long rem_nsec; + + if (!printk_time) + return 0; + + if (!buf) + return 15; + + rem_nsec = do_div(ts, 1000000000); + return sprintf(buf, "[%5lu.%06lu] ", + (unsigned long)ts, rem_nsec / 1000); +} + static size_t print_prefix(const struct log *msg, bool syslog, char *buf) { size_t len = 0; @@ -803,18 +831,7 @@ static size_t print_prefix(const struct log *msg, bool syslog, char *buf) } } - if (printk_time) { - if (buf) { - unsigned long long ts = msg->ts_nsec; - unsigned long rem_nsec = do_div(ts, 1000000000); - - len += sprintf(buf + len, "[%5lu.%06lu] ", - (unsigned long) ts, rem_nsec / 1000); - } else { - len += 15; - } - } - + len += print_time(msg->ts_nsec, buf ? buf + len : NULL); return len; } @@ -862,28 +879,49 @@ static int syslog_print(char __user *buf, int size) { char *text; struct log *msg; - int len; + int len = 0; text = kmalloc(LOG_LINE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; - raw_spin_lock_irq(&logbuf_lock); - if (syslog_seq < log_first_seq) { - /* messages are gone, move to first one */ - syslog_seq = log_first_seq; - syslog_idx = log_first_idx; - } - msg = log_from_idx(syslog_idx); - len = msg_print_text(msg, true, text, LOG_LINE_MAX); - syslog_idx = log_next(syslog_idx); - syslog_seq++; - raw_spin_unlock_irq(&logbuf_lock); + while (size > 0) { + size_t n; - if (len > size) - len = -EINVAL; - else if (len > 0 && copy_to_user(buf, text, len)) - len = -EFAULT; + raw_spin_lock_irq(&logbuf_lock); + if (syslog_seq < log_first_seq) { + /* messages are gone, move to first one */ + syslog_seq = log_first_seq; + syslog_idx = log_first_idx; + } + if (syslog_seq == log_next_seq) { + raw_spin_unlock_irq(&logbuf_lock); + break; + } + msg = log_from_idx(syslog_idx); + n = msg_print_text(msg, true, text, LOG_LINE_MAX); + if (n <= size) { + syslog_idx = log_next(syslog_idx); + syslog_seq++; + } else + n = 0; + raw_spin_unlock_irq(&logbuf_lock); + + if (!n) + break; + + len += n; + size -= n; + buf += n; + n = copy_to_user(buf - n, text, n); + + if (n) { + len -= n; + if (!len) + len = -EFAULT; + break; + } + } kfree(text); return len; @@ -1040,6 +1078,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_print_all(NULL, 0, true); + break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == -1) @@ -1272,15 +1311,92 @@ static inline void printk_delay(void) } } +/* + * Continuation lines are buffered, and not committed to the record buffer + * until the line is complete, or a race forces it. The line fragments + * though, are printed immediately to the consoles to ensure everything has + * reached the console in case of a kernel crash. + */ +static struct cont { + char buf[LOG_LINE_MAX]; + size_t len; /* length == 0 means unused buffer */ + size_t cons; /* bytes written to console */ + struct task_struct *owner; /* task of first print*/ + u64 ts_nsec; /* time of first print */ + u8 level; /* log level of first message */ + u8 facility; /* log level of first message */ + bool flushed:1; /* buffer sealed and committed */ +} cont; + +static void cont_flush(void) +{ + if (cont.flushed) + return; + if (cont.len == 0) + return; + + log_store(cont.facility, cont.level, LOG_NOCONS, cont.ts_nsec, + NULL, 0, cont.buf, cont.len); + + cont.flushed = true; +} + +static bool cont_add(int facility, int level, const char *text, size_t len) +{ + if (cont.len && cont.flushed) + return false; + + if (cont.len + len > sizeof(cont.buf)) { + cont_flush(); + return false; + } + + if (!cont.len) { + cont.facility = facility; + cont.level = level; + cont.owner = current; + cont.ts_nsec = local_clock(); + cont.cons = 0; + cont.flushed = false; + } + + memcpy(cont.buf + cont.len, text, len); + cont.len += len; + return true; +} + +static size_t cont_print_text(char *text, size_t size) +{ + size_t textlen = 0; + size_t len; + + if (cont.cons == 0) { + textlen += print_time(cont.ts_nsec, text); + size -= textlen; + } + + len = cont.len - cont.cons; + if (len > 0) { + if (len+1 > size) + len = size-1; + memcpy(text + textlen, cont.buf + cont.cons, len); + textlen += len; + cont.cons = cont.len; + } + + if (cont.flushed) { + text[textlen++] = '\n'; + /* got everything, release buffer */ + cont.len = 0; + } + return textlen; +} + asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) { static int recursion_bug; - static char cont_buf[LOG_LINE_MAX]; - static size_t cont_len; - static int cont_level; - static struct task_struct *cont_task; static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len; @@ -1326,7 +1442,8 @@ asmlinkage int vprintk_emit(int facility, int level, recursion_bug = 0; printed_len += strlen(recursion_msg); /* emit KERN_CRIT message */ - log_store(0, 2, NULL, 0, recursion_msg, printed_len); + log_store(0, 2, LOG_DEFAULT, 0, + NULL, 0, recursion_msg, printed_len); } /* @@ -1364,55 +1481,37 @@ asmlinkage int vprintk_emit(int facility, int level, } if (!newline) { - if (cont_len && (prefix || cont_task != current)) { - /* - * Flush earlier buffer, which is either from a - * different thread, or when we got a new prefix. - */ - log_store(facility, cont_level, NULL, 0, cont_buf, cont_len); - cont_len = 0; - } - - if (!cont_len) { - cont_level = level; - cont_task = current; - } + /* + * Flush the conflicting buffer. An earlier newline was missing, + * or another task also prints continuation lines. + */ + if (cont.len && (prefix || cont.owner != current)) + cont_flush(); - /* buffer or append to earlier buffer from the same thread */ - if (cont_len + text_len > sizeof(cont_buf)) - text_len = sizeof(cont_buf) - cont_len; - memcpy(cont_buf + cont_len, text, text_len); - cont_len += text_len; + /* buffer line if possible, otherwise store it right away */ + if (!cont_add(facility, level, text, text_len)) + log_store(facility, level, LOG_DEFAULT, 0, + dict, dictlen, text, text_len); } else { - if (cont_len && cont_task == current) { - if (prefix) { - /* - * New prefix from the same thread; flush. We - * either got no earlier newline, or we race - * with an interrupt. - */ - log_store(facility, cont_level, - NULL, 0, cont_buf, cont_len); - cont_len = 0; - } + bool stored = false; - /* append to the earlier buffer and flush */ - if (cont_len + text_len > sizeof(cont_buf)) - text_len = sizeof(cont_buf) - cont_len; - memcpy(cont_buf + cont_len, text, text_len); - cont_len += text_len; - log_store(facility, cont_level, - NULL, 0, cont_buf, cont_len); - cont_len = 0; - cont_task = NULL; - printed_len = cont_len; - } else { - /* ordinary single and terminated line */ - log_store(facility, level, - dict, dictlen, text, text_len); - printed_len = text_len; + /* + * If an earlier newline was missing and it was the same task, + * either merge it with the current buffer and flush, or if + * there was a race with interrupts (prefix == true) then just + * flush it out and store this line separately. + */ + if (cont.len && cont.owner == current) { + if (!prefix) + stored = cont_add(facility, level, text, text_len); + cont_flush(); } + + if (!stored) + log_store(facility, level, LOG_DEFAULT, 0, + dict, dictlen, text, text_len); } + printed_len += text_len; /* * Try to acquire and then immediately release the console semaphore. @@ -1499,11 +1598,18 @@ EXPORT_SYMBOL(printk); #else #define LOG_LINE_MAX 0 +static struct cont { + size_t len; + size_t cons; + u8 level; + bool flushed:1; +} cont; static struct log *log_from_idx(u32 idx) { return NULL; } static u32 log_next(u32 idx) { return 0; } static void call_console_drivers(int level, const char *text, size_t len) {} static size_t msg_print_text(const struct log *msg, bool syslog, char *buf, size_t size) { return 0; } +static size_t cont_print_text(char *text, size_t size) { return 0; } #endif /* CONFIG_PRINTK */ @@ -1795,6 +1901,7 @@ static u32 console_idx; */ void console_unlock(void) { + static char text[LOG_LINE_MAX]; static u64 seen_seq; unsigned long flags; bool wake_klogd = false; @@ -1807,10 +1914,23 @@ void console_unlock(void) console_may_schedule = 0; + /* flush buffered message fragment immediately to console */ + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (cont.len && (cont.cons < cont.len || cont.flushed)) { + size_t len; + + len = cont_print_text(text, sizeof(text)); + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, text, len); + start_critical_timings(); + local_irq_restore(flags); + } else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + again: for (;;) { struct log *msg; - static char text[LOG_LINE_MAX]; size_t len; int level; @@ -1825,13 +1945,22 @@ again: console_seq = log_first_seq; console_idx = log_first_idx; } - +skip: if (console_seq == log_next_seq) break; msg = log_from_idx(console_idx); - level = msg->level & 7; + if (msg->flags & LOG_NOCONS) { + /* + * Skip record we have buffered and already printed + * directly to the console when we received it. + */ + console_idx = log_next(console_idx); + console_seq++; + goto skip; + } + level = msg->level; len = msg_print_text(msg, false, text, sizeof(text)); console_idx = log_next(console_idx); @@ -2409,7 +2538,7 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_line); * kmsg_dump_get_buffer - copy kmsg log lines * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes - * @line: buffer to copy the line to + * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 3b0f1337f75b..38ecdda3f55f 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1530,7 +1530,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; struct rcu_head *next, *list, **tail; - int bl, count, count_lazy; + int bl, count, count_lazy, i; /* If no callbacks are ready, just return.*/ if (!cpu_has_callbacks_ready_to_invoke(rdp)) { @@ -1553,9 +1553,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; *rdp->nxttail[RCU_DONE_TAIL] = NULL; tail = rdp->nxttail[RCU_DONE_TAIL]; - for (count = RCU_NEXT_SIZE - 1; count >= 0; count--) - if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL]) - rdp->nxttail[count] = &rdp->nxtlist; + for (i = RCU_NEXT_SIZE - 1; i >= 0; i--) + if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL]) + rdp->nxttail[i] = &rdp->nxtlist; local_irq_restore(flags); /* Invoke callbacks. */ @@ -1583,9 +1583,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) if (list != NULL) { *tail = rdp->nxtlist; rdp->nxtlist = list; - for (count = 0; count < RCU_NEXT_SIZE; count++) - if (&rdp->nxtlist == rdp->nxttail[count]) - rdp->nxttail[count] = tail; + for (i = 0; i < RCU_NEXT_SIZE; i++) + if (&rdp->nxtlist == rdp->nxttail[i]) + rdp->nxttail[i] = tail; else break; } diff --git a/security/security.c b/security/security.c index 3efc9b12aef4..860aeb349cb3 100644 --- a/security/security.c +++ b/security/security.c @@ -23,6 +23,7 @@ #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> +#include <linux/backing-dev.h> #include <net/flow.h> #define MAX_LSM_EVM_XATTR 2 |