diff options
Diffstat (limited to 'arch')
79 files changed, 992 insertions, 723 deletions
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 60cde53d266..8bb936226de 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -51,7 +51,7 @@ config GENERIC_CMOS_UPDATE def_bool y config GENERIC_GPIO - def_bool y + bool config ZONE_DMA bool diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3269576dbfa..3146ed3f6ec 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1283,6 +1283,20 @@ config ARM_ERRATA_364296 processor into full low interrupt latency mode. ARM11MPCore is not affected. +config ARM_ERRATA_764369 + bool "ARM errata: Data cache line maintenance operation by MVA may not succeed" + depends on CPU_V7 && SMP + help + This option enables the workaround for erratum 764369 + affecting Cortex-A9 MPCore with two or more processors (all + current revisions). Under certain timing circumstances, a data + cache line maintenance operation by MVA targeting an Inner + Shareable memory region may fail to proceed up to either the + Point of Coherency or to the Point of Unification of the + system. This workaround adds a DSB instruction before the + relevant cache maintenance functions and sets a specific bit + in the diagnostic control register of the SCU. + endmenu source "arch/arm/common/Kconfig" diff --git a/arch/arm/boot/dts/tegra-harmony.dts b/arch/arm/boot/dts/tegra-harmony.dts index 4c053340ce3..e5818668d09 100644 --- a/arch/arm/boot/dts/tegra-harmony.dts +++ b/arch/arm/boot/dts/tegra-harmony.dts @@ -57,14 +57,14 @@ }; sdhci@c8000200 { - gpios = <&gpio 69 0>, /* cd, gpio PI5 */ - <&gpio 57 0>, /* wp, gpio PH1 */ - <&gpio 155 0>; /* power, gpio PT3 */ + cd-gpios = <&gpio 69 0>; /* gpio PI5 */ + wp-gpios = <&gpio 57 0>; /* gpio PH1 */ + power-gpios = <&gpio 155 0>; /* gpio PT3 */ }; sdhci@c8000600 { - gpios = <&gpio 58 0>, /* cd, gpio PH2 */ - <&gpio 59 0>, /* wp, gpio PH3 */ - <&gpio 70 0>; /* power, gpio PI6 */ + cd-gpios = <&gpio 58 0>; /* gpio PH2 */ + wp-gpios = <&gpio 59 0>; /* gpio PH3 */ + power-gpios = <&gpio 70 0>; /* gpio PI6 */ }; }; diff --git a/arch/arm/boot/dts/tegra-seaboard.dts b/arch/arm/boot/dts/tegra-seaboard.dts index 1940cae0074..64cedca6fc7 100644 --- a/arch/arm/boot/dts/tegra-seaboard.dts +++ b/arch/arm/boot/dts/tegra-seaboard.dts @@ -21,8 +21,8 @@ }; sdhci@c8000400 { - gpios = <&gpio 69 0>, /* cd, gpio PI5 */ - <&gpio 57 0>, /* wp, gpio PH1 */ - <&gpio 70 0>; /* power, gpio PI6 */ + cd-gpios = <&gpio 69 0>; /* gpio PI5 */ + wp-gpios = <&gpio 57 0>; /* gpio PH1 */ + power-gpios = <&gpio 70 0>; /* gpio PI6 */ }; }; diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index 8c73900da9e..253cc86318b 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -25,17 +25,17 @@ #ifdef CONFIG_SMP -#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ +#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ smp_mb(); \ __asm__ __volatile__( \ - "1: ldrex %1, [%2]\n" \ + "1: ldrex %1, [%3]\n" \ " " insn "\n" \ - "2: strex %1, %0, [%2]\n" \ - " teq %1, #0\n" \ + "2: strex %2, %0, [%3]\n" \ + " teq %2, #0\n" \ " bne 1b\n" \ " mov %0, #0\n" \ - __futex_atomic_ex_table("%4") \ - : "=&r" (ret), "=&r" (oldval) \ + __futex_atomic_ex_table("%5") \ + : "=&r" (ret), "=&r" (oldval), "=&r" (tmp) \ : "r" (uaddr), "r" (oparg), "Ir" (-EFAULT) \ : "cc", "memory") @@ -73,14 +73,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, #include <linux/preempt.h> #include <asm/domain.h> -#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ +#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ __asm__ __volatile__( \ - "1: " T(ldr) " %1, [%2]\n" \ + "1: " T(ldr) " %1, [%3]\n" \ " " insn "\n" \ - "2: " T(str) " %0, [%2]\n" \ + "2: " T(str) " %0, [%3]\n" \ " mov %0, #0\n" \ - __futex_atomic_ex_table("%4") \ - : "=&r" (ret), "=&r" (oldval) \ + __futex_atomic_ex_table("%5") \ + : "=&r" (ret), "=&r" (oldval), "=&r" (tmp) \ : "r" (uaddr), "r" (oparg), "Ir" (-EFAULT) \ : "cc", "memory") @@ -117,7 +117,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) int cmp = (encoded_op >> 24) & 15; int oparg = (encoded_op << 8) >> 20; int cmparg = (encoded_op << 20) >> 20; - int oldval = 0, ret; + int oldval = 0, ret, tmp; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; @@ -129,19 +129,19 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("mov %0, %4", ret, oldval, tmp, uaddr, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("add %0, %1, %4", ret, oldval, tmp, uaddr, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %0, %1, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("orr %0, %1, %4", ret, oldval, tmp, uaddr, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %0, %1, %3", ret, oldval, uaddr, ~oparg); + __futex_atomic_op("and %0, %1, %4", ret, oldval, tmp, uaddr, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %0, %1, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("eor %0, %1, %4", ret, oldval, tmp, uaddr, oparg); break; default: ret = -ENOSYS; diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 2c04ed5efeb..c60a2944f95 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -478,8 +478,8 @@ /* * Unimplemented (or alternatively implemented) syscalls */ -#define __IGNORE_fadvise64_64 1 -#define __IGNORE_migrate_pages 1 +#define __IGNORE_fadvise64_64 +#define __IGNORE_migrate_pages #endif /* __KERNEL__ */ #endif /* __ASM_ARM_UNISTD_H */ diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 79ed5e7f204..7fcddb75c87 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -13,6 +13,7 @@ #include <asm/smp_scu.h> #include <asm/cacheflush.h> +#include <asm/cputype.h> #define SCU_CTRL 0x00 #define SCU_CONFIG 0x04 @@ -37,6 +38,15 @@ void __init scu_enable(void __iomem *scu_base) { u32 scu_ctrl; +#ifdef CONFIG_ARM_ERRATA_764369 + /* Cortex-A9 only */ + if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) { + scu_ctrl = __raw_readl(scu_base + 0x30); + if (!(scu_ctrl & 1)) + __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); + } +#endif + scu_ctrl = __raw_readl(scu_base + SCU_CTRL); /* already enabled? */ if (scu_ctrl & 1) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index bf977f8514f..4e66f62b8d4 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -23,8 +23,10 @@ #if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK) #define ARM_EXIT_KEEP(x) x +#define ARM_EXIT_DISCARD(x) #else #define ARM_EXIT_KEEP(x) +#define ARM_EXIT_DISCARD(x) x #endif OUTPUT_ARCH(arm) @@ -39,6 +41,11 @@ jiffies = jiffies_64 + 4; SECTIONS { /* + * XXX: The linker does not define how output sections are + * assigned to input sections when there are multiple statements + * matching the same input section name. There is no documented + * order of matching. + * * unwind exit sections must be discarded before the rest of the * unwind sections get included. */ @@ -47,6 +54,9 @@ SECTIONS *(.ARM.extab.exit.text) ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text)) ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text)) + ARM_EXIT_DISCARD(EXIT_TEXT) + ARM_EXIT_DISCARD(EXIT_DATA) + EXIT_CALL #ifndef CONFIG_HOTPLUG *(.ARM.exidx.devexit.text) *(.ARM.extab.devexit.text) @@ -58,6 +68,8 @@ SECTIONS #ifndef CONFIG_SMP_ON_UP *(.alt.smp.init) #endif + *(.discard) + *(.discard.*) } #ifdef CONFIG_XIP_KERNEL @@ -279,9 +291,6 @@ SECTIONS STABS_DEBUG .comment 0 : { *(.comment) } - - /* Default discards */ - DISCARDS } /* diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c index 83dce859886..a9e0dae86a2 100644 --- a/arch/arm/mach-dove/common.c +++ b/arch/arm/mach-dove/common.c @@ -158,7 +158,7 @@ void __init dove_spi0_init(void) void __init dove_spi1_init(void) { - orion_spi_init(DOVE_SPI1_PHYS_BASE, get_tclk()); + orion_spi_1_init(DOVE_SPI1_PHYS_BASE, get_tclk()); } /***************************************************************************** diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c index 1561b036a9b..86964d2e9e1 100644 --- a/arch/arm/mach-exynos4/clock.c +++ b/arch/arm/mach-exynos4/clock.c @@ -899,8 +899,7 @@ static struct clksrc_clk clksrcs[] = { .reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 28, .size = 4 }, }, { .clk = { - .name = "sclk_cam", - .devname = "exynos4-fimc.0", + .name = "sclk_cam0", .enable = exynos4_clksrc_mask_cam_ctrl, .ctrlbit = (1 << 16), }, @@ -909,8 +908,7 @@ static struct clksrc_clk clksrcs[] = { .reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 16, .size = 4 }, }, { .clk = { - .name = "sclk_cam", - .devname = "exynos4-fimc.1", + .name = "sclk_cam1", .enable = exynos4_clksrc_mask_cam_ctrl, .ctrlbit = (1 << 20), }, @@ -1160,7 +1158,7 @@ void __init_or_cpufreq exynos4_setup_clocks(void) vpllsrc = clk_get_rate(&clk_vpllsrc.clk); vpll = s5p_get_pll46xx(vpllsrc, __raw_readl(S5P_VPLL_CON0), - __raw_readl(S5P_VPLL_CON1), pll_4650); + __raw_readl(S5P_VPLL_CON1), pll_4650c); clk_fout_apll.ops = &exynos4_fout_apll_ops; clk_fout_mpll.rate = mpll; diff --git a/arch/arm/mach-exynos4/mct.c b/arch/arm/mach-exynos4/mct.c index 1ae059b7ad7..ddd86864fb8 100644 --- a/arch/arm/mach-exynos4/mct.c +++ b/arch/arm/mach-exynos4/mct.c @@ -132,12 +132,18 @@ static cycle_t exynos4_frc_read(struct clocksource *cs) return ((cycle_t)hi << 32) | lo; } +static void exynos4_frc_resume(struct clocksource *cs) +{ + exynos4_mct_frc_start(0, 0); +} + struct clocksource mct_frc = { .name = "mct-frc", .rating = 400, .read = exynos4_frc_read, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .resume = exynos4_frc_resume, }; static void __init exynos4_clocksource_init(void) @@ -389,9 +395,11 @@ static void exynos4_mct_tick_init(struct clock_event_device *evt) } /* Setup the local clock events for a CPU */ -void __cpuinit local_timer_setup(struct clock_event_device *evt) +int __cpuinit local_timer_setup(struct clock_event_device *evt) { exynos4_mct_tick_init(evt); + + return 0; } int local_timer_ack(void) diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c index 7c2282c6ba8..df6ef1b2f98 100644 --- a/arch/arm/mach-exynos4/platsmp.c +++ b/arch/arm/mach-exynos4/platsmp.c @@ -106,6 +106,8 @@ void __cpuinit platform_secondary_init(unsigned int cpu) */ spin_lock(&boot_lock); spin_unlock(&boot_lock); + + set_cpu_online(cpu, true); } int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) diff --git a/arch/arm/mach-exynos4/setup-keypad.c b/arch/arm/mach-exynos4/setup-keypad.c index 1ee0ebff111..7862bfb5933 100644 --- a/arch/arm/mach-exynos4/setup-keypad.c +++ b/arch/arm/mach-exynos4/setup-keypad.c @@ -19,15 +19,16 @@ void samsung_keypad_cfg_gpio(unsigned int rows, unsigned int cols) if (rows > 8) { /* Set all the necessary GPX2 pins: KP_ROW[0~7] */ - s3c_gpio_cfgrange_nopull(EXYNOS4_GPX2(0), 8, S3C_GPIO_SFN(3)); + s3c_gpio_cfgall_range(EXYNOS4_GPX2(0), 8, S3C_GPIO_SFN(3), + S3C_GPIO_PULL_UP); /* Set all the necessary GPX3 pins: KP_ROW[8~] */ - s3c_gpio_cfgrange_nopull(EXYNOS4_GPX3(0), (rows - 8), - S3C_GPIO_SFN(3)); + s3c_gpio_cfgall_range(EXYNOS4_GPX3(0), (rows - 8), + S3C_GPIO_SFN(3), S3C_GPIO_PULL_UP); } else { /* Set all the necessary GPX2 pins: KP_ROW[x] */ - s3c_gpio_cfgrange_nopull(EXYNOS4_GPX2(0), rows, - S3C_GPIO_SFN(3)); + s3c_gpio_cfgall_range(EXYNOS4_GPX2(0), rows, S3C_GPIO_SFN(3), + S3C_GPIO_PULL_UP); } /* Set all the necessary GPX1 pins to special-function 3: KP_COL[x] */ diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index fcf0ae95651..8cdc730dcb3 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/mtd/physmap.h> +#include <video/vga.h> #include <mach/hardware.h> #include <mach/platform.h> @@ -154,6 +155,7 @@ static struct map_desc ap_io_desc[] __initdata = { static void __init ap_map_io(void) { iotable_init(ap_io_desc, ARRAY_SIZE(ap_io_desc)); + vga_base = PCI_MEMORY_VADDR; } #define INTEGRATOR_SC_VALID_INT 0x003fffff diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c index dd56bfb351e..11b86e5b71c 100644 --- a/arch/arm/mach-integrator/pci_v3.c +++ b/arch/arm/mach-integrator/pci_v3.c @@ -27,7 +27,6 @@ #include <linux/spinlock.h> #include <linux/init.h> #include <linux/io.h> -#include <video/vga.h> #include <mach/hardware.h> #include <mach/platform.h> @@ -505,7 +504,6 @@ void __init pci_v3_preinit(void) pcibios_min_io = 0x6000; pcibios_min_mem = 0x00100000; - vga_base = PCI_MEMORY_VADDR; /* * Hook in our fault handler for PCI errors diff --git a/arch/arm/mach-s3c2443/clock.c b/arch/arm/mach-s3c2443/clock.c index a1a7176675b..38058af4897 100644 --- a/arch/arm/mach-s3c2443/clock.c +++ b/arch/arm/mach-s3c2443/clock.c @@ -128,7 +128,7 @@ static int s3c2443_armclk_setrate(struct clk *clk, unsigned long rate) unsigned long clkcon0; clkcon0 = __raw_readl(S3C2443_CLKDIV0); - clkcon0 &= S3C2443_CLKDIV0_ARMDIV_MASK; + clkcon0 &= ~S3C2443_CLKDIV0_ARMDIV_MASK; clkcon0 |= val << S3C2443_CLKDIV0_ARMDIV_SHIFT; __raw_writel(clkcon0, S3C2443_CLKDIV0); } diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c index ecbea92bf83..a9f3183e029 100644 --- a/arch/arm/mach-s3c64xx/mach-smdk6410.c +++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c @@ -262,45 +262,6 @@ static struct samsung_keypad_platdata smdk6410_keypad_data __initdata = { .cols = 8, }; -static int smdk6410_backlight_init(struct device *dev) -{ - int ret; - - ret = gpio_request(S3C64XX_GPF(15), "Backlight"); - if (ret) { - printk(KERN_ERR "failed to request GPF for PWM-OUT1\n"); - return ret; - } - - /* Configure GPIO pin with S3C64XX_GPF15_PWM_TOUT1 */ - s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_SFN(2)); - - return 0; -} - -static void smdk6410_backlight_exit(struct device *dev) -{ - s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_OUTPUT); - gpio_free(S3C64XX_GPF(15)); -} - -static struct platform_pwm_backlight_data smdk6410_backlight_data = { - .pwm_id = 1, - .max_brightness = 255, - .dft_brightness = 255, - .pwm_period_ns = 78770, - .init = smdk6410_backlight_init, - .exit = smdk6410_backlight_exit, -}; - -static struct platform_device smdk6410_backlight_device = { - .name = "pwm-backlight", - .dev = { - .parent = &s3c_device_timer[1].dev, - .platform_data = &smdk6410_backlight_data, - }, -}; - static struct map_desc smdk6410_iodesc[] = {}; static struct platform_device *smdk6410_devices[] __initdata = { diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c index 52a8e607bcc..f5f8fa89679 100644 --- a/arch/arm/mach-s5pv210/clock.c +++ b/arch/arm/mach-s5pv210/clock.c @@ -815,8 +815,7 @@ static struct clksrc_clk clksrcs[] = { .reg_div = { .reg = S5P_CLK_DIV3, .shift = 20, .size = 4 }, }, { .clk = { - .name = "sclk_cam", - .devname = "s5pv210-fimc.0", + .name = "sclk_cam0", .enable = s5pv210_clk_mask0_ctrl, .ctrlbit = (1 << 3), }, @@ -825,8 +824,7 @@ static struct clksrc_clk clksrcs[] = { .reg_div = { .reg = S5P_CLK_DIV1, .shift = 12, .size = 4 }, }, { .clk = { - .name = "sclk_cam", - .devname = "s5pv210-fimc.1", + .name = "sclk_cam1", .enable = s5pv210_clk_mask0_ctrl, .ctrlbit = (1 << 4), }, diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 3b24bfa3b82..07c4bc8ea0a 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -174,6 +174,10 @@ ENTRY(v7_coherent_user_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r12, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: USER( mcr p15, 0, r12, c7, c11, 1 ) @ clean D line to the point of unification add r12, r12, r2 @@ -223,6 +227,10 @@ ENTRY(v7_flush_kern_dcache_area) add r1, r0, r1 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line / unified line add r0, r0, r2 @@ -247,6 +255,10 @@ v7_dma_inv_range: sub r3, r2, #1 tst r0, r3 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif mcrne p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line tst r1, r3 @@ -270,6 +282,10 @@ v7_dma_clean_range: dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c10, 1 @ clean D / U line add r0, r0, r2 @@ -288,6 +304,10 @@ ENTRY(v7_dma_flush_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line add r0, r0, r2 diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 0a0a1e7c20d..c3ff82f92d9 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -324,6 +324,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); + else + __dma_free_buffer(page, size); return addr; } diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c index f71078ef6bb..f88216d2399 100644 --- a/arch/arm/plat-s5p/irq-gpioint.c +++ b/arch/arm/plat-s5p/irq-gpioint.c @@ -114,17 +114,18 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip) { static int used_gpioint_groups = 0; int group = chip->group; - struct s5p_gpioint_bank *bank = NULL; + struct s5p_gpioint_bank *b, *bank = NULL; struct irq_chip_generic *gc; struct irq_chip_type *ct; if (used_gpioint_groups >= S5P_GPIOINT_GROUP_COUNT) return -ENOMEM; - list_for_each_entry(bank, &banks, list) { - if (group >= bank->start && - group < bank->start + bank->nr_groups) + list_for_each_entry(b, &banks, list) { + if (group >= b->start && group < b->start + b->nr_groups) { + bank = b; break; + } } if (!bank) return -EINVAL; diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c index 302c42670bd..3b4451979d1 100644 --- a/arch/arm/plat-samsung/clock.c +++ b/arch/arm/plat-samsung/clock.c @@ -64,6 +64,17 @@ static LIST_HEAD(clocks); */ DEFINE_SPINLOCK(clocks_lock); +/* Global watchdog clock used by arch_wtd_reset() callback */ +struct clk *s3c2410_wdtclk; +static int __init s3c_wdt_reset_init(void) +{ + s3c2410_wdtclk = clk_get(NULL, "watchdog"); + if (IS_ERR(s3c2410_wdtclk)) + printk(KERN_WARNING "%s: warning: cannot get watchdog clock\n", __func__); + return 0; +} +arch_initcall(s3c_wdt_reset_init); + /* enable and disable calls for use with the clk struct */ static int clk_null_enable(struct clk *clk, int enable) diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h index 87d5b38a86f..73c66d4d10f 100644 --- a/arch/arm/plat-samsung/include/plat/clock.h +++ b/arch/arm/plat-samsung/include/plat/clock.h @@ -9,6 +9,9 @@ * published by the Free Software Foundation. */ +#ifndef __ASM_PLAT_CLOCK_H +#define __ASM_PLAT_CLOCK_H __FILE__ + #include <linux/spinlock.h> #include <linux/clkdev.h> @@ -121,3 +124,8 @@ extern int s3c64xx_sclk_ctrl(struct clk *clk, int enable); extern void s3c_pwmclk_init(void); +/* Global watchdog clock used by arch_wtd_reset() callback */ + +extern struct clk *s3c2410_wdtclk; + +#endif /* __ASM_PLAT_CLOCK_H */ diff --git a/arch/arm/plat-samsung/include/plat/watchdog-reset.h b/arch/arm/plat-samsung/include/plat/watchdog-reset.h index 54b762acb5a..40dbb2b0ae2 100644 --- a/arch/arm/plat-samsung/include/plat/watchdog-reset.h +++ b/arch/arm/plat-samsung/include/plat/watchdog-reset.h @@ -10,6 +10,7 @@ * published by the Free Software Foundation. */ +#include <plat/clock.h> #include <plat/regs-watchdog.h> #include <mach/map.h> @@ -19,17 +20,12 @@ static inline void arch_wdt_reset(void) { - struct clk *wdtclk; - printk("arch_reset: attempting watchdog reset\n"); __raw_writel(0, S3C2410_WTCON); /* disable watchdog, to be safe */ - wdtclk = clk_get(NULL, "watchdog"); - if (!IS_ERR(wdtclk)) { - clk_enable(wdtclk); - } else - printk(KERN_WARNING "%s: warning: cannot get watchdog clock\n", __func__); + if (s3c2410_wdtclk) + clk_enable(s3c2410_wdtclk); /* put initial values into count and data */ __raw_writel(0x80, S3C2410_WTCNT); diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 5cc83851ad0..31a7d3a7ce2 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -561,6 +561,20 @@ static struct pci_ops u4_pcie_pci_ops = .write = u4_pcie_write_config, }; +static void __devinit pmac_pci_fixup_u4_of_node(struct pci_dev *dev) +{ + /* Apple's device-tree "hides" the root complex virtual P2P bridge + * on U4. However, Linux sees it, causing the PCI <-> OF matching + * code to fail to properly match devices below it. This works around + * it by setting the node of the bridge to point to the PHB node, + * which is not entirely correct but fixes the matching code and + * doesn't break anything else. It's also the simplest possible fix. + */ + if (dev->dev.of_node == NULL) + dev->dev.of_node = pcibios_get_phb_of_node(dev->bus); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_APPLE, 0x5b, pmac_pci_fixup_u4_of_node); + #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC32 diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 64b61bf72e9..547f1a6a35d 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -188,7 +188,8 @@ extern char elf_platform[]; #define SET_PERSONALITY(ex) \ do { \ if (personality(current->personality) != PER_LINUX32) \ - set_personality(PER_LINUX); \ + set_personality(PER_LINUX | \ + (current->personality & ~PER_MASK)); \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ set_thread_flag(TIF_31BIT); \ else \ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 519eb5f187e..c0cb794bb36 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -658,12 +658,14 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste) * struct gmap_struct - guest address space * @mm: pointer to the parent mm_struct * @table: pointer to the page directory + * @asce: address space control element for gmap page table * @crst_list: list of all crst tables used in the guest address space */ struct gmap { struct list_head list; struct mm_struct *mm; unsigned long *table; + unsigned long asce; struct list_head crst_list; }; diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 532fd432215..2b45591e158 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <asm/vdso.h> #include <asm/sigp.h> +#include <asm/pgtable.h> /* * Make sure that the compiler is new enough. We want a compiler that @@ -126,6 +127,7 @@ int main(void) DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack)); DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack)); DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack)); + DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce)); DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags)); @@ -151,6 +153,7 @@ int main(void) DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data)); DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap)); DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp)); + DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); #endif /* CONFIG_32BIT */ return 0; } diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 5f729d627ce..713da076053 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -1076,6 +1076,11 @@ sie_loop: lg %r14,__LC_THREAD_INFO # pointer thread_info struct tm __TI_flags+7(%r14),_TIF_EXIT_SIE jnz sie_exit + lg %r14,__LC_GMAP # get gmap pointer + ltgr %r14,%r14 + jz sie_gmap + lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce +sie_gmap: lg %r14,__SF_EMPTY(%r15) # get control block pointer SPP __SF_EMPTY(%r15) # set guest id sie 0(%r14) @@ -1083,6 +1088,7 @@ sie_done: SPP __LC_CMF_HPP # set host id lg %r14,__LC_THREAD_INFO # pointer thread_info struct sie_exit: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) lg %r14,__SF_EMPTY+8(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f17296e4fc8..dc2b580e27b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -123,6 +123,7 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_S390_PSW: + case KVM_CAP_S390_GMAP: r = 1; break; default: @@ -263,10 +264,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK; restore_fp_regs(&vcpu->arch.guest_fpregs); restore_access_regs(vcpu->arch.guest_acrs); + gmap_enable(vcpu->arch.gmap); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + gmap_disable(vcpu->arch.gmap); save_fp_regs(&vcpu->arch.guest_fpregs); save_access_regs(vcpu->arch.guest_acrs); restore_fp_regs(&vcpu->arch.host_fpregs); @@ -461,7 +464,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu) local_irq_disable(); kvm_guest_enter(); local_irq_enable(); - gmap_enable(vcpu->arch.gmap); VCPU_EVENT(vcpu, 6, "entering sie flags %x", atomic_read(&vcpu->arch.sie_block->cpuflags)); if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) { @@ -470,7 +472,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu) } VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); - gmap_disable(vcpu->arch.gmap); local_irq_disable(); kvm_guest_exit(); local_irq_enable(); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 4d1f2bce87b..5d56c2b95b1 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -160,6 +160,8 @@ struct gmap *gmap_alloc(struct mm_struct *mm) table = (unsigned long *) page_to_phys(page); crst_table_init(table, _REGION1_ENTRY_EMPTY); gmap->table = table; + gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | __pa(table); list_add(&gmap->list, &mm->context.gmap_list); return gmap; @@ -240,10 +242,6 @@ EXPORT_SYMBOL_GPL(gmap_free); */ void gmap_enable(struct gmap *gmap) { - /* Load primary space page table origin. */ - S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | __pa(gmap->table); - asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) ); S390_lowcore.gmap = (unsigned long) gmap; } EXPORT_SYMBOL_GPL(gmap_enable); @@ -254,10 +252,6 @@ EXPORT_SYMBOL_GPL(gmap_enable); */ void gmap_disable(struct gmap *gmap) { - /* Load primary space page table origin. */ - S390_lowcore.user_asce = - gmap->mm->context.asce_bits | __pa(gmap->mm->pgd); - asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) ); S390_lowcore.gmap = 0UL; } EXPORT_SYMBOL_GPL(gmap_disable); @@ -309,15 +303,15 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) /* Walk the guest addr space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); if (*table & _REGION_ENTRY_INV) - return 0; + goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 42) & 0x7ff); if (*table & _REGION_ENTRY_INV) - return 0; + goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 31) & 0x7ff); if (*table & _REGION_ENTRY_INV) - return 0; + goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 20) & 0x7ff); @@ -325,6 +319,7 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) flush |= gmap_unlink_segment(gmap, table); *table = _SEGMENT_ENTRY_INV; } +out: up_read(&gmap->mm->mmap_sem); if (flush) gmap_flush_tlb(gmap); diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 55a17c6efeb..d06a2660175 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -43,6 +43,8 @@ #define SUN4V_CHIP_NIAGARA1 0x01 #define SUN4V_CHIP_NIAGARA2 0x02 #define SUN4V_CHIP_NIAGARA3 0x03 +#define SUN4V_CHIP_NIAGARA4 0x04 +#define SUN4V_CHIP_NIAGARA5 0x05 #define SUN4V_CHIP_UNKNOWN 0xff #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h index 9ed6ff679ab..ee8edc68423 100644 --- a/arch/sparc/include/asm/xor_64.h +++ b/arch/sparc/include/asm/xor_64.h @@ -66,6 +66,8 @@ static struct xor_block_template xor_block_niagara = { ((tlb_type == hypervisor && \ (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \ sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \ - sun4v_chip_type == SUN4V_CHIP_NIAGARA3)) ? \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA5)) ? \ &xor_block_niagara : \ &xor_block_VIS) diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index 9810fd88105..ba9b1cec4e6 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -481,6 +481,18 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara3"; break; + case SUN4V_CHIP_NIAGARA4: + sparc_cpu_type = "UltraSparc T4 (Niagara4)"; + sparc_fpu_type = "UltraSparc T4 integrated FPU"; + sparc_pmu_type = "niagara4"; + break; + + case SUN4V_CHIP_NIAGARA5: + sparc_cpu_type = "UltraSparc T5 (Niagara5)"; + sparc_fpu_type = "UltraSparc T5 integrated FPU"; + sparc_pmu_type = "niagara5"; + break; + default: printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n", prom_cpu_compatible); diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index 4197e8d62d4..9323eafccb9 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -325,6 +325,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA1: case SUN4V_CHIP_NIAGARA2: case SUN4V_CHIP_NIAGARA3: + case SUN4V_CHIP_NIAGARA4: + case SUN4V_CHIP_NIAGARA5: rover_inc_table = niagara_iterate_method; break; default: diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 0eac1b2fc53..0d810c2f1d0 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -133,7 +133,7 @@ prom_sun4v_name: prom_niagara_prefix: .asciz "SUNW,UltraSPARC-T" prom_sparc_prefix: - .asciz "SPARC-T" + .asciz "SPARC-" .align 4 prom_root_compatible: .skip 64 @@ -396,7 +396,7 @@ sun4v_chip_type: or %g1, %lo(prom_cpu_compatible), %g1 sethi %hi(prom_sparc_prefix), %g7 or %g7, %lo(prom_sparc_prefix), %g7 - mov 7, %g3 + mov 6, %g3 90: ldub [%g7], %g2 ldub [%g1], %g4 cmp %g2, %g4 @@ -408,10 +408,23 @@ sun4v_chip_type: sethi %hi(prom_cpu_compatible), %g1 or %g1, %lo(prom_cpu_compatible), %g1 - ldub [%g1 + 7], %g2 + ldub [%g1 + 6], %g2 + cmp %g2, 'T' + be,pt %xcc, 70f + cmp %g2, 'M' + bne,pn %xcc, 4f + nop + +70: ldub [%g1 + 7], %g2 cmp %g2, '3' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA3, %g4 + cmp %g2, '4' + be,pt %xcc, 5f + mov SUN4V_CHIP_NIAGARA4, %g4 + cmp %g2, '5' + be,pt %xcc, 5f + mov SUN4V_CHIP_NIAGARA5, %g4 ba,pt %xcc, 4f nop @@ -545,6 +558,12 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_NIAGARA3 be,pt %xcc, niagara2_patch nop + cmp %g1, SUN4V_CHIP_NIAGARA4 + be,pt %xcc, niagara2_patch + nop + cmp %g1, SUN4V_CHIP_NIAGARA5 + be,pt %xcc, niagara2_patch + nop call generic_patch_copyops nop diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index c8cc461ff75..f793742eec2 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -380,8 +380,7 @@ void flush_thread(void) #endif } - /* Now, this task is no longer a kernel thread. */ - current->thread.current_ds = USER_DS; + /* This task is no longer a kernel thread. */ if (current->thread.flags & SPARC_FLAG_KTHREAD) { current->thread.flags &= ~SPARC_FLAG_KTHREAD; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index c158a95ec66..d959cd0a4aa 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -368,9 +368,6 @@ void flush_thread(void) /* Clear FPU register state. */ t->fpsaved[0] = 0; - - if (get_thread_current_ds() != ASI_AIUS) - set_fs(USER_DS); } /* It's a bit more tricky when 64-bit tasks are involved... */ diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index d26e1f6c717..3e3e2914c70 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -137,7 +137,7 @@ static void __init process_switch(char c) prom_halt(); break; case 'p': - /* Just ignore, this behavior is now the default. */ + prom_early_console.flags &= ~CON_BOOT; break; default: printk("Unknown boot switch (-%c)\n", c); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 3c5bb784214..c965595aa7e 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -106,7 +106,7 @@ static void __init process_switch(char c) prom_halt(); break; case 'p': - /* Just ignore, this behavior is now the default. */ + prom_early_console.flags &= ~CON_BOOT; break; case 'P': /* Force UltraSPARC-III P-Cache on. */ @@ -425,10 +425,14 @@ static void __init init_sparc64_elf_hwcap(void) else if (tlb_type == hypervisor) { if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA3) + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) cap |= HWCAP_SPARC_BLKINIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA3) + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) cap |= HWCAP_SPARC_N2; } @@ -452,11 +456,15 @@ static void __init init_sparc64_elf_hwcap(void) if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1) cap |= AV_SPARC_ASI_BLK_INIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA3) + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | AV_SPARC_ASI_BLK_INIT | AV_SPARC_POPC); - if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3) + if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | AV_SPARC_FMAF); } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 581531dbc8b..8e073d80213 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -511,6 +511,11 @@ static void __init read_obp_translations(void) for (i = 0; i < prom_trans_ents; i++) prom_trans[i].data &= ~0x0003fe0000000000UL; } + + /* Force execute bit on. */ + for (i = 0; i < prom_trans_ents; i++) + prom_trans[i].data |= (tlb_type == hypervisor ? + _PAGE_EXEC_4V : _PAGE_EXEC_4U); } static void __init hypervisor_tlb_lock(unsigned long vaddr, diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86 index d31ecf346b4..21bebe63df6 100644 --- a/arch/um/Kconfig.x86 +++ b/arch/um/Kconfig.x86 @@ -10,6 +10,10 @@ config CMPXCHG_LOCAL bool default n +config CMPXCHG_DOUBLE + bool + default n + source "arch/x86/Kconfig.cpu" endmenu diff --git a/arch/um/Makefile b/arch/um/Makefile index fab8121d2b3..c0f712cc7c5 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -41,7 +41,7 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH) KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\" \ $(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap \ -Din6addr_loopback=kernel_in6addr_loopback \ - -Din6addr_any=kernel_in6addr_any + -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr KBUILD_AFLAGS += $(ARCH_INCLUDE) diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index d51c404239a..364c8a15c4c 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -399,8 +399,8 @@ int line_setup_irq(int fd, int input, int output, struct line *line, void *data) * is done under a spinlock. Checking whether the device is in use is * line->tty->count > 1, also under the spinlock. * - * tty->count serves to decide whether the device should be enabled or - * disabled on the host. If it's equal to 1, then we are doing the + * line->count serves to decide whether the device should be enabled or + * disabled on the host. If it's equal to 0, then we are doing the * first open or last close. Otherwise, open and close just return. */ @@ -414,16 +414,16 @@ int line_open(struct line *lines, struct tty_struct *tty) goto out_unlock; err = 0; - if (tty->count > 1) + if (line->count++) goto out_unlock; - spin_unlock(&line->count_lock); - + BUG_ON(tty->driver_data); tty->driver_data = line; line->tty = tty; + spin_unlock(&line->count_lock); err = enable_chan(line); - if (err) + if (err) /* line_close() will be called by our caller */ return err; INIT_DELAYED_WORK(&line->task, line_timer_cb); @@ -436,7 +436,7 @@ int line_open(struct line *lines, struct tty_struct *tty) chan_window_size(&line->chan_list, &tty->winsize.ws_row, &tty->winsize.ws_col); - return err; + return 0; out_unlock: spin_unlock(&line->count_lock); @@ -460,17 +460,16 @@ void line_close(struct tty_struct *tty, struct file * filp) flush_buffer(line); spin_lock(&line->count_lock); - if (!line->valid) - goto out_unlock; + BUG_ON(!line->valid); - if (tty->count > 1) + if (--line->count) goto out_unlock; - spin_unlock(&line->count_lock); - line->tty = NULL; tty->driver_data = NULL; + spin_unlock(&line->count_lock); + if (line->sigio) { unregister_winch(tty); line->sigio = 0; @@ -498,7 +497,7 @@ static int setup_one_line(struct line *lines, int n, char *init, int init_prio, spin_lock(&line->count_lock); - if (line->tty != NULL) { + if (line->count) { *error_out = "Device is already open"; goto out; } @@ -722,41 +721,53 @@ struct winch { int pid; struct tty_struct *tty; unsigned long stack; + struct work_struct work; }; -static void free_winch(struct winch *winch, int free_irq_ok) +static void __free_winch(struct work_struct *work) { - if (free_irq_ok) - free_irq(WINCH_IRQ, winch); - - list_del(&winch->list); + struct winch *winch = container_of(work, struct winch, work); + free_irq(WINCH_IRQ, winch); if (winch->pid != -1) os_kill_process(winch->pid, 1); - if (winch->fd != -1) - os_close_file(winch->fd); if (winch->stack != 0) free_stack(winch->stack, 0); kfree(winch); } +static void free_winch(struct winch *winch) +{ + int fd = winch->fd; + winch->fd = -1; + if (fd != -1) + os_close_file(fd); + list_del(&winch->list); + __free_winch(&winch->work); +} + static irqreturn_t winch_interrupt(int irq, void *data) { struct winch *winch = data; struct tty_struct *tty; struct line *line; + int fd = winch->fd; int err; char c; - if (winch->fd != -1) { - err = generic_read(winch->fd, &c, NULL); + if (fd != -1) { + err = generic_read(fd, &c, NULL); if (err < 0) { if (err != -EAGAIN) { + winch->fd = -1; + list_del(&winch->list); + os_close_file(fd); printk(KERN_ERR "winch_interrupt : " "read failed, errno = %d\n", -err); printk(KERN_ERR "fd %d is losing SIGWINCH " "support\n", winch->tty_fd); - free_winch(winch, 0); + INIT_WORK(&winch->work, __free_winch); + schedule_work(&winch->work); return IRQ_HANDLED; } goto out; @@ -828,7 +839,7 @@ static void unregister_winch(struct tty_struct *tty) list_for_each_safe(ele, next, &winch_handlers) { winch = list_entry(ele, struct winch, list); if (winch->tty == tty) { - free_winch(winch, 1); + free_winch(winch); break; } } @@ -844,7 +855,7 @@ static void winch_cleanup(void) list_for_each_safe(ele, next, &winch_handlers) { winch = list_entry(ele, struct winch, list); - free_winch(winch, 1); + free_winch(winch); } spin_unlock(&winch_handler_lock); diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c index 8ac7146c237..2e1de572860 100644 --- a/arch/um/drivers/xterm.c +++ b/arch/um/drivers/xterm.c @@ -123,6 +123,7 @@ static int xterm_open(int input, int output, int primary, void *d, err = -errno; printk(UM_KERN_ERR "xterm_open : unlink failed, errno = %d\n", errno); + close(fd); return err; } close(fd); diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h index ae084ad1a3a..1a7d2757fe0 100644 --- a/arch/um/include/asm/ptrace-generic.h +++ b/arch/um/include/asm/ptrace-generic.h @@ -42,10 +42,6 @@ extern long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern unsigned long getreg(struct task_struct *child, int regno); extern int putreg(struct task_struct *child, int regno, unsigned long value); -extern int get_fpregs(struct user_i387_struct __user *buf, - struct task_struct *child); -extern int set_fpregs(struct user_i387_struct __user *buf, - struct task_struct *child); extern int arch_copy_tls(struct task_struct *new); extern void clear_flushed_tls(struct task_struct *task); diff --git a/arch/um/include/shared/line.h b/arch/um/include/shared/line.h index 72f4f25af24..63df3ca02ac 100644 --- a/arch/um/include/shared/line.h +++ b/arch/um/include/shared/line.h @@ -33,6 +33,7 @@ struct line_driver { struct line { struct tty_struct *tty; spinlock_t count_lock; + unsigned long count; int valid; char *init_str; diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h index b0b4589e0eb..f1e0aa56c52 100644 --- a/arch/um/include/shared/registers.h +++ b/arch/um/include/shared/registers.h @@ -16,7 +16,7 @@ extern int restore_fpx_registers(int pid, unsigned long *fp_regs); extern int save_registers(int pid, struct uml_pt_regs *regs); extern int restore_registers(int pid, struct uml_pt_regs *regs); extern int init_registers(int pid); -extern void get_safe_registers(unsigned long *regs); +extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs); extern unsigned long get_thread_reg(int reg, jmp_buf *buf); extern int get_fp_registers(int pid, unsigned long *regs); extern int put_fp_registers(int pid, unsigned long *regs); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index fab4371184f..21c1ae7c3d7 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -202,7 +202,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, arch_copy_thread(¤t->thread.arch, &p->thread.arch); } else { - get_safe_registers(p->thread.regs.regs.gp); + get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); p->thread.request.u.thread = current->thread.request.u.thread; handler = new_thread_handler; } diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c index 701b672c112..c9da32b0c70 100644 --- a/arch/um/kernel/ptrace.c +++ b/arch/um/kernel/ptrace.c @@ -50,23 +50,11 @@ long arch_ptrace(struct task_struct *child, long request, void __user *vp = p; switch (request) { - /* read word at location addr. */ - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - ret = generic_ptrace_peekdata(child, addr, data); - break; - /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: ret = peek_user(child, addr, data); break; - /* write the word at location addr. */ - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - ret = generic_ptrace_pokedata(child, addr, data); - break; - /* write the word at location addr in the USER area */ case PTRACE_POKEUSR: ret = poke_user(child, addr, data); @@ -107,16 +95,6 @@ long arch_ptrace(struct task_struct *child, long request, break; } #endif -#ifdef PTRACE_GETFPREGS - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - ret = get_fpregs(vp, child); - break; -#endif -#ifdef PTRACE_SETFPREGS - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - ret = set_fpregs(vp, child); - break; -#endif case PTRACE_GET_THREAD_AREA: ret = ptrace_get_thread_area(child, addr, vp); break; @@ -154,12 +132,6 @@ long arch_ptrace(struct task_struct *child, long request, break; } #endif -#ifdef PTRACE_ARCH_PRCTL - case PTRACE_ARCH_PRCTL: - /* XXX Calls ptrace on the host - needs some SMP thinking */ - ret = arch_prctl(child, data, (void __user *) addr); - break; -#endif default: ret = ptrace_request(child, request, addr, data); if (ret == -EIO) diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c index 830fe6a1518..b866b9e3bef 100644 --- a/arch/um/os-Linux/registers.c +++ b/arch/um/os-Linux/registers.c @@ -8,6 +8,8 @@ #include <string.h> #include <sys/ptrace.h> #include "sysdep/ptrace.h" +#include "sysdep/ptrace_user.h" +#include "registers.h" int save_registers(int pid, struct uml_pt_regs *regs) { @@ -32,6 +34,7 @@ int restore_registers(int pid, struct uml_pt_regs *regs) /* This is set once at boot time and not changed thereafter */ static unsigned long exec_regs[MAX_REG_NR]; +static unsigned long exec_fp_regs[FP_SIZE]; int init_registers(int pid) { @@ -42,10 +45,14 @@ int init_registers(int pid) return -errno; arch_init_registers(pid); + get_fp_registers(pid, exec_fp_regs); return 0; } -void get_safe_registers(unsigned long *regs) +void get_safe_registers(unsigned long *regs, unsigned long *fp_regs) { memcpy(regs, exec_regs, sizeof(exec_regs)); + + if (fp_regs) + memcpy(fp_regs, exec_fp_regs, sizeof(exec_fp_regs)); } diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index d261f170d12..e771398be5f 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -39,7 +39,7 @@ static unsigned long syscall_regs[MAX_REG_NR]; static int __init init_syscall_regs(void) { - get_safe_registers(syscall_regs); + get_safe_registers(syscall_regs, NULL); syscall_regs[REGS_IP_INDEX] = STUB_CODE + ((unsigned long) &batch_syscall_stub - (unsigned long) &__syscall_stub_start); diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index d6e0a2234b8..dee0e8cf8ad 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -373,6 +373,9 @@ void userspace(struct uml_pt_regs *regs) if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) fatal_sigsegv(); + if (put_fp_registers(pid, regs->fp)) + fatal_sigsegv(); + /* Now we set local_using_sysemu to be used for one loop */ local_using_sysemu = get_using_sysemu(); @@ -399,6 +402,12 @@ void userspace(struct uml_pt_regs *regs) fatal_sigsegv(); } + if (get_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "userspace - get_fp_registers failed, " + "errno = %d\n", errno); + fatal_sigsegv(); + } + UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */ if (WIFSTOPPED(status)) { @@ -457,10 +466,11 @@ void userspace(struct uml_pt_regs *regs) } static unsigned long thread_regs[MAX_REG_NR]; +static unsigned long thread_fp_regs[FP_SIZE]; static int __init init_thread_regs(void) { - get_safe_registers(thread_regs); + get_safe_registers(thread_regs, thread_fp_regs); /* Set parent's instruction pointer to start of clone-stub */ thread_regs[REGS_IP_INDEX] = STUB_CODE + (unsigned long) stub_clone_handler - @@ -503,6 +513,13 @@ int copy_context_skas0(unsigned long new_stack, int pid) return err; } + err = put_fp_registers(pid, thread_fp_regs); + if (err < 0) { + printk(UM_KERN_ERR "copy_context_skas0 : put_fp_registers " + "failed, pid = %d, err = %d\n", pid, err); + return err; + } + /* set a well known return code for detection of child write failure */ child_data->err = 12345678; diff --git a/arch/um/sys-i386/asm/ptrace.h b/arch/um/sys-i386/asm/ptrace.h index 0273e4d09af..5d2a5911253 100644 --- a/arch/um/sys-i386/asm/ptrace.h +++ b/arch/um/sys-i386/asm/ptrace.h @@ -42,11 +42,6 @@ */ struct user_desc; -extern int get_fpxregs(struct user_fxsr_struct __user *buf, - struct task_struct *child); -extern int set_fpxregs(struct user_fxsr_struct __user *buf, - struct task_struct *tsk); - extern int ptrace_get_thread_area(struct task_struct *child, int idx, struct user_desc __user *user_desc); diff --git a/arch/um/sys-i386/ptrace.c b/arch/um/sys-i386/ptrace.c index d23b2d3ea38..3375c271785 100644 --- a/arch/um/sys-i386/ptrace.c +++ b/arch/um/sys-i386/ptrace.c @@ -145,7 +145,7 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long __user *) data); } -int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_i387_struct fpregs; @@ -161,7 +161,7 @@ int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) return n; } -int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_i387_struct fpregs; @@ -174,7 +174,7 @@ int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) (unsigned long *) &fpregs); } -int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) +static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_fxsr_struct fpregs; @@ -190,7 +190,7 @@ int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) return n; } -int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) +static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_fxsr_struct fpregs; @@ -206,5 +206,23 @@ int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { - return -EIO; + int ret = -EIO; + void __user *datap = (void __user *) data; + switch (request) { + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + ret = get_fpregs(datap, child); + break; + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + ret = set_fpregs(datap, child); + break; + case PTRACE_GETFPXREGS: /* Get the child FPU state. */ + ret = get_fpxregs(datap, child); + break; + case PTRACE_SETFPXREGS: /* Set the child FPU state. */ + ret = set_fpxregs(datap, child); + break; + default: + ret = -EIO; + } + return ret; } diff --git a/arch/um/sys-i386/shared/sysdep/ptrace.h b/arch/um/sys-i386/shared/sysdep/ptrace.h index d50e62e0707..c398a507611 100644 --- a/arch/um/sys-i386/shared/sysdep/ptrace.h +++ b/arch/um/sys-i386/shared/sysdep/ptrace.h @@ -53,6 +53,7 @@ extern int sysemu_supported; struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; + unsigned long fp[HOST_FPX_SIZE]; struct faultinfo faultinfo; long syscall; int is_user; diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/um/sys-x86_64/ptrace.c index f43613643cd..4005506834f 100644 --- a/arch/um/sys-x86_64/ptrace.c +++ b/arch/um/sys-x86_64/ptrace.c @@ -145,7 +145,7 @@ int is_syscall(unsigned long addr) return instr == 0x050f; } -int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; long fpregs[HOST_FP_SIZE]; @@ -162,7 +162,7 @@ int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) return n; } -int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; long fpregs[HOST_FP_SIZE]; @@ -182,12 +182,16 @@ long subarch_ptrace(struct task_struct *child, long request, void __user *datap = (void __user *) data; switch (request) { - case PTRACE_GETFPXREGS: /* Get the child FPU state. */ + case PTRACE_GETFPREGS: /* Get the child FPU state. */ ret = get_fpregs(datap, child); break; - case PTRACE_SETFPXREGS: /* Set the child FPU state. */ + case PTRACE_SETFPREGS: /* Set the child FPU state. */ ret = set_fpregs(datap, child); break; + case PTRACE_ARCH_PRCTL: + /* XXX Calls ptrace on the host - needs some SMP thinking */ + ret = arch_prctl(child, data, (void __user *) addr); + break; } return ret; diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace.h b/arch/um/sys-x86_64/shared/sysdep/ptrace.h index fdba5457947..8ee8f8e12af 100644 --- a/arch/um/sys-x86_64/shared/sysdep/ptrace.h +++ b/arch/um/sys-x86_64/shared/sysdep/ptrace.h @@ -85,6 +85,7 @@ struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; + unsigned long fp[HOST_FP_SIZE]; struct faultinfo faultinfo; long syscall; int is_user; diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 4554cc6fb96..091508b533b 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -16,7 +16,6 @@ #endif .macro altinstruction_entry orig alt feature orig_len alt_len - .align 8 .long \orig - . .long \alt - . .word \feature diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 23fb6d79f20..37ad100a221 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -48,9 +48,6 @@ struct alt_instr { u16 cpuid; /* cpuid bit set for replacement */ u8 instrlen; /* length of original instruction */ u8 replacementlen; /* length of new instruction, <= instrlen */ -#ifdef CONFIG_X86_64 - u32 pad2; -#endif }; extern void alternative_instructions(void); @@ -83,7 +80,6 @@ static inline int alternatives_text_reserved(void *start, void *end) \ "661:\n\t" oldinstr "\n662:\n" \ ".section .altinstructions,\"a\"\n" \ - _ASM_ALIGN "\n" \ " .long 661b - .\n" /* label */ \ " .long 663f - .\n" /* new instruction */ \ " .word " __stringify(feature) "\n" /* feature bit */ \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 4258aac99a6..88b23a43f34 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -332,7 +332,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) asm goto("1: jmp %l[t_no]\n" "2:\n" ".section .altinstructions,\"a\"\n" - _ASM_ALIGN "\n" " .long 1b - .\n" " .long 0\n" /* no replacement */ " .word %P0\n" /* feature bit */ @@ -350,7 +349,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) asm volatile("1: movb $0,%0\n" "2:\n" ".section .altinstructions,\"a\"\n" - _ASM_ALIGN "\n" " .long 1b - .\n" " .long 3f - .\n" " .word %P1\n" /* feature bit */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 6042981d030..1044fd787db 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -28,6 +28,11 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +ifdef CONFIG_PERF_EVENTS +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +endif + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index cfa62ec090e..8ab89112f93 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -32,6 +32,8 @@ #include <asm/smp.h> #include <asm/alternative.h> +#include "perf_event.h" + #if 0 #undef wrmsrl #define wrmsrl(msr, val) \ @@ -43,283 +45,17 @@ do { \ } while (0) #endif -/* - * | NHM/WSM | SNB | - * register ------------------------------- - * | HT | no HT | HT | no HT | - *----------------------------------------- - * offcore | core | core | cpu | core | - * lbr_sel | core | core | cpu | core | - * ld_lat | cpu | core | cpu | core | - *----------------------------------------- - * - * Given that there is a small number of shared regs, - * we can pre-allocate their slot in the per-cpu - * per-core reg tables. - */ -enum extra_reg_type { - EXTRA_REG_NONE = -1, /* not used */ - - EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ - EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ - - EXTRA_REG_MAX /* number of entries needed */ -}; - -struct event_constraint { - union { - unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - u64 idxmsk64; - }; - u64 code; - u64 cmask; - int weight; -}; - -struct amd_nb { - int nb_id; /* NorthBridge id */ - int refcnt; /* reference count */ - struct perf_event *owners[X86_PMC_IDX_MAX]; - struct event_constraint event_constraints[X86_PMC_IDX_MAX]; -}; - -struct intel_percore; - -#define MAX_LBR_ENTRIES 16 - -struct cpu_hw_events { - /* - * Generic x86 PMC bits - */ - struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ - unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - int enabled; - - int n_events; - int n_added; - int n_txn; - int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ - u64 tags[X86_PMC_IDX_MAX]; - struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ - - unsigned int group_flag; - - /* - * Intel DebugStore bits - */ - struct debug_store *ds; - u64 pebs_enabled; - - /* - * Intel LBR bits - */ - int lbr_users; - void *lbr_context; - struct perf_branch_stack lbr_stack; - struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; - - /* - * manage shared (per-core, per-cpu) registers - * used on Intel NHM/WSM/SNB - */ - struct intel_shared_regs *shared_regs; - - /* - * AMD specific bits - */ - struct amd_nb *amd_nb; -}; - -#define __EVENT_CONSTRAINT(c, n, m, w) {\ - { .idxmsk64 = (n) }, \ - .code = (c), \ - .cmask = (m), \ - .weight = (w), \ -} - -#define EVENT_CONSTRAINT(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) - -/* - * Constraint on the Event code. - */ -#define INTEL_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) - -/* - * Constraint on the Event code + UMask + fixed-mask - * - * filter mask to validate fixed counter events. - * the following filters disqualify for fixed counters: - * - inv - * - edge - * - cnt-mask - * The other filters are supported by fixed counters. - * The any-thread option is supported starting with v3. - */ -#define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) - -/* - * Constraint on the Event code + UMask - */ -#define INTEL_UEVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) - -#define EVENT_CONSTRAINT_END \ - EVENT_CONSTRAINT(0, 0, 0) +struct x86_pmu x86_pmu __read_mostly; -#define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->weight; (e)++) - -/* - * Per register state. - */ -struct er_account { - raw_spinlock_t lock; /* per-core: protect structure */ - u64 config; /* extra MSR config */ - u64 reg; /* extra MSR number */ - atomic_t ref; /* reference count */ -}; - -/* - * Extra registers for specific events. - * - * Some events need large masks and require external MSRs. - * Those extra MSRs end up being shared for all events on - * a PMU and sometimes between PMU of sibling HT threads. - * In either case, the kernel needs to handle conflicting - * accesses to those extra, shared, regs. The data structure - * to manage those registers is stored in cpu_hw_event. - */ -struct extra_reg { - unsigned int event; - unsigned int msr; - u64 config_mask; - u64 valid_mask; - int idx; /* per_xxx->regs[] reg index */ -}; - -#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i \ - } - -#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ - EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) - -#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) - -union perf_capabilities { - struct { - u64 lbr_format : 6; - u64 pebs_trap : 1; - u64 pebs_arch_reg : 1; - u64 pebs_format : 4; - u64 smm_freeze : 1; - }; - u64 capabilities; -}; - -/* - * struct x86_pmu - generic x86 pmu - */ -struct x86_pmu { - /* - * Generic x86 PMC bits - */ - const char *name; - int version; - int (*handle_irq)(struct pt_regs *); - void (*disable_all)(void); - void (*enable_all)(int added); - void (*enable)(struct perf_event *); - void (*disable)(struct perf_event *); - int (*hw_config)(struct perf_event *event); - int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); - unsigned eventsel; - unsigned perfctr; - u64 (*event_map)(int); - int max_events; - int num_counters; - int num_counters_fixed; - int cntval_bits; - u64 cntval_mask; - int apic; - u64 max_period; - struct event_constraint * - (*get_event_constraints)(struct cpu_hw_events *cpuc, - struct perf_event *event); - - void (*put_event_constraints)(struct cpu_hw_events *cpuc, - struct perf_event *event); - struct event_constraint *event_constraints; - void (*quirks)(void); - int perfctr_second_write; - - int (*cpu_prepare)(int cpu); - void (*cpu_starting)(int cpu); - void (*cpu_dying)(int cpu); - void (*cpu_dead)(int cpu); - - /* - * Intel Arch Perfmon v2+ - */ - u64 intel_ctrl; - union perf_capabilities intel_cap; - - /* - * Intel DebugStore bits - */ - int bts, pebs; - int bts_active, pebs_active; - int pebs_record_size; - void (*drain_pebs)(struct pt_regs *regs); - struct event_constraint *pebs_constraints; - - /* - * Intel LBR - */ - unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ - int lbr_nr; /* hardware stack size */ - - /* - * Extra registers for events - */ - struct extra_reg *extra_regs; - unsigned int er_flags; -}; - -#define ERF_NO_HT_SHARING 1 -#define ERF_HAS_RSP_1 2 - -static struct x86_pmu x86_pmu __read_mostly; - -static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { +DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; -static int x86_perf_event_set_period(struct perf_event *event); - -/* - * Generalized hw caching related hw_event table, filled - * in on a per model basis. A value of 0 means - * 'not supported', -1 means 'hw_event makes no sense on - * this CPU', any other value means the raw hw_event - * ID. - */ - -#define C(x) PERF_COUNT_HW_CACHE_##x - -static u64 __read_mostly hw_cache_event_ids +u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; -static u64 __read_mostly hw_cache_extra_regs +u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; @@ -329,8 +65,7 @@ static u64 __read_mostly hw_cache_extra_regs * Can only be executed on the CPU where the event is active. * Returns the delta events processed. */ -static u64 -x86_perf_event_update(struct perf_event *event) +u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.cntval_bits; @@ -373,30 +108,6 @@ again: return new_raw_count; } -static inline int x86_pmu_addr_offset(int index) -{ - int offset; - - /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ - alternative_io(ASM_NOP2, - "shll $1, %%eax", - X86_FEATURE_PERFCTR_CORE, - "=a" (offset), - "a" (index)); - - return offset; -} - -static inline unsigned int x86_pmu_config_addr(int index) -{ - return x86_pmu.eventsel + x86_pmu_addr_offset(index); -} - -static inline unsigned int x86_pmu_event_addr(int index) -{ - return x86_pmu.perfctr + x86_pmu_addr_offset(index); -} - /* * Find and validate any extra registers to set up. */ @@ -532,9 +243,6 @@ msr_fail: return false; } -static void reserve_ds_buffers(void); -static void release_ds_buffers(void); - static void hw_perf_event_destroy(struct perf_event *event) { if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { @@ -583,7 +291,7 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } -static int x86_setup_perfctr(struct perf_event *event) +int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -647,7 +355,7 @@ static int x86_setup_perfctr(struct perf_event *event) return 0; } -static int x86_pmu_hw_config(struct perf_event *event) +int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { int precise = 0; @@ -723,7 +431,7 @@ static int __x86_pmu_event_init(struct perf_event *event) return x86_pmu.hw_config(event); } -static void x86_pmu_disable_all(void) +void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; @@ -758,15 +466,7 @@ static void x86_pmu_disable(struct pmu *pmu) x86_pmu.disable_all(); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, - u64 enable_mask) -{ - if (hwc->extra_reg.reg) - wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); - wrmsrl(hwc->config_base, hwc->config | enable_mask); -} - -static void x86_pmu_enable_all(int added) +void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; @@ -788,7 +488,7 @@ static inline int is_x86_event(struct perf_event *event) return event->pmu == &pmu; } -static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) +int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c, *constraints[X86_PMC_IDX_MAX]; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; @@ -959,7 +659,6 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc, } static void x86_pmu_start(struct perf_event *event, int flags); -static void x86_pmu_stop(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { @@ -1031,21 +730,13 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu.enable_all(added); } -static inline void x86_pmu_disable_event(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - wrmsrl(hwc->config_base, hwc->config); -} - static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. * To be called with the event disabled in hw: */ -static int -x86_perf_event_set_period(struct perf_event *event) +int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); @@ -1105,7 +796,7 @@ x86_perf_event_set_period(struct perf_event *event) return ret; } -static void x86_pmu_enable_event(struct perf_event *event) +void x86_pmu_enable_event(struct perf_event *event) { if (__this_cpu_read(cpu_hw_events.enabled)) __x86_pmu_enable_event(&event->hw, @@ -1244,7 +935,7 @@ void perf_event_print_debug(void) local_irq_restore(flags); } -static void x86_pmu_stop(struct perf_event *event, int flags) +void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -1297,7 +988,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) perf_event_update_userpage(event); } -static int x86_pmu_handle_irq(struct pt_regs *regs) +int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; @@ -1437,39 +1128,19 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = { .priority = NMI_LOCAL_LOW_PRIOR, }; -static struct event_constraint unconstrained; -static struct event_constraint emptyconstraint; - -static struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) -{ - struct event_constraint *c; - - if (x86_pmu.event_constraints) { - for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) - return c; - } - } - - return &unconstrained; -} - -#include "perf_event_amd.c" -#include "perf_event_p6.c" -#include "perf_event_p4.c" -#include "perf_event_intel_lbr.c" -#include "perf_event_intel_ds.c" -#include "perf_event_intel.c" +struct event_constraint emptyconstraint; +struct event_constraint unconstrained; static int __cpuinit x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int ret = NOTIFY_OK; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: + cpuc->kfree_on_online = NULL; if (x86_pmu.cpu_prepare) ret = x86_pmu.cpu_prepare(cpu); break; @@ -1479,6 +1150,10 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) x86_pmu.cpu_starting(cpu); break; + case CPU_ONLINE: + kfree(cpuc->kfree_on_online); + break; + case CPU_DYING: if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h new file mode 100644 index 00000000000..fb330b0a816 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event.h @@ -0,0 +1,493 @@ +/* + * Performance events x86 architecture header + * + * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2009 Jaswinder Singh Rajput + * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> + * Copyright (C) 2009 Google, Inc., Stephane Eranian + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/perf_event.h> + +/* + * | NHM/WSM | SNB | + * register ------------------------------- + * | HT | no HT | HT | no HT | + *----------------------------------------- + * offcore | core | core | cpu | core | + * lbr_sel | core | core | cpu | core | + * ld_lat | cpu | core | cpu | core | + *----------------------------------------- + * + * Given that there is a small number of shared regs, + * we can pre-allocate their slot in the per-cpu + * per-core reg tables. + */ +enum extra_reg_type { + EXTRA_REG_NONE = -1, /* not used */ + + EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ + EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + + EXTRA_REG_MAX /* number of entries needed */ +}; + +struct event_constraint { + union { + unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 idxmsk64; + }; + u64 code; + u64 cmask; + int weight; +}; + +struct amd_nb { + int nb_id; /* NorthBridge id */ + int refcnt; /* reference count */ + struct perf_event *owners[X86_PMC_IDX_MAX]; + struct event_constraint event_constraints[X86_PMC_IDX_MAX]; +}; + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 4 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +}; + +/* + * Per register state. + */ +struct er_account { + raw_spinlock_t lock; /* per-core: protect structure */ + u64 config; /* extra MSR config */ + u64 reg; /* extra MSR number */ + atomic_t ref; /* reference count */ +}; + +/* + * Per core/cpu state + * + * Used to coordinate shared registers between HT threads or + * among events on a single PMU. + */ +struct intel_shared_regs { + struct er_account regs[EXTRA_REG_MAX]; + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ +}; + +#define MAX_LBR_ENTRIES 16 + +struct cpu_hw_events { + /* + * Generic x86 PMC bits + */ + struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ + unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + int enabled; + + int n_events; + int n_added; + int n_txn; + int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ + u64 tags[X86_PMC_IDX_MAX]; + struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + + unsigned int group_flag; + + /* + * Intel DebugStore bits + */ + struct debug_store *ds; + u64 pebs_enabled; + + /* + * Intel LBR bits + */ + int lbr_users; + void *lbr_context; + struct perf_branch_stack lbr_stack; + struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + + /* + * manage shared (per-core, per-cpu) registers + * used on Intel NHM/WSM/SNB + */ + struct intel_shared_regs *shared_regs; + + /* + * AMD specific bits + */ + struct amd_nb *amd_nb; + + void *kfree_on_online; +}; + +#define __EVENT_CONSTRAINT(c, n, m, w) {\ + { .idxmsk64 = (n) }, \ + .code = (c), \ + .cmask = (m), \ + .weight = (w), \ +} + +#define EVENT_CONSTRAINT(c, n, m) \ + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) + +/* + * Constraint on the Event code. + */ +#define INTEL_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* + * Constraint on the Event code + UMask + fixed-mask + * + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ +#define FIXED_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + +/* + * Constraint on the Event code + UMask + */ +#define INTEL_UEVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) + +#define EVENT_CONSTRAINT_END \ + EVENT_CONSTRAINT(0, 0, 0) + +#define for_each_event_constraint(e, c) \ + for ((e) = (c); (e)->weight; (e)++) + +/* + * Extra registers for specific events. + * + * Some events need large masks and require external MSRs. + * Those extra MSRs end up being shared for all events on + * a PMU and sometimes between PMU of sibling HT threads. + * In either case, the kernel needs to handle conflicting + * accesses to those extra, shared, regs. The data structure + * to manage those registers is stored in cpu_hw_event. + */ +struct extra_reg { + unsigned int event; + unsigned int msr; + u64 config_mask; + u64 valid_mask; + int idx; /* per_xxx->regs[] reg index */ +}; + +#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i \ + } + +#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) + +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) + +union perf_capabilities { + struct { + u64 lbr_format:6; + u64 pebs_trap:1; + u64 pebs_arch_reg:1; + u64 pebs_format:4; + u64 smm_freeze:1; + }; + u64 capabilities; +}; + +/* + * struct x86_pmu - generic x86 pmu + */ +struct x86_pmu { + /* + * Generic x86 PMC bits + */ + const char *name; + int version; + int (*handle_irq)(struct pt_regs *); + void (*disable_all)(void); + void (*enable_all)(int added); + void (*enable)(struct perf_event *); + void (*disable)(struct perf_event *); + int (*hw_config)(struct perf_event *event); + int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); + unsigned eventsel; + unsigned perfctr; + u64 (*event_map)(int); + int max_events; + int num_counters; + int num_counters_fixed; + int cntval_bits; + u64 cntval_mask; + int apic; + u64 max_period; + struct event_constraint * + (*get_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + + void (*put_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + struct event_constraint *event_constraints; + void (*quirks)(void); + int perfctr_second_write; + + int (*cpu_prepare)(int cpu); + void (*cpu_starting)(int cpu); + void (*cpu_dying)(int cpu); + void (*cpu_dead)(int cpu); + + /* + * Intel Arch Perfmon v2+ + */ + u64 intel_ctrl; + union perf_capabilities intel_cap; + + /* + * Intel DebugStore bits + */ + int bts, pebs; + int bts_active, pebs_active; + int pebs_record_size; + void (*drain_pebs)(struct pt_regs *regs); + struct event_constraint *pebs_constraints; + + /* + * Intel LBR + */ + unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ + int lbr_nr; /* hardware stack size */ + + /* + * Extra registers for events + */ + struct extra_reg *extra_regs; + unsigned int er_flags; +}; + +#define ERF_NO_HT_SHARING 1 +#define ERF_HAS_RSP_1 2 + +extern struct x86_pmu x86_pmu __read_mostly; + +DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + +int x86_perf_event_set_period(struct perf_event *event); + +/* + * Generalized hw caching related hw_event table, filled + * in on a per model basis. A value of 0 means + * 'not supported', -1 means 'hw_event makes no sense on + * this CPU', any other value means the raw hw_event + * ID. + */ + +#define C(x) PERF_COUNT_HW_CACHE_##x + +extern u64 __read_mostly hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +extern u64 __read_mostly hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; + +u64 x86_perf_event_update(struct perf_event *event); + +static inline int x86_pmu_addr_offset(int index) +{ + int offset; + + /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ + alternative_io(ASM_NOP2, + "shll $1, %%eax", + X86_FEATURE_PERFCTR_CORE, + "=a" (offset), + "a" (index)); + + return offset; +} + +static inline unsigned int x86_pmu_config_addr(int index) +{ + return x86_pmu.eventsel + x86_pmu_addr_offset(index); +} + +static inline unsigned int x86_pmu_event_addr(int index) +{ + return x86_pmu.perfctr + x86_pmu_addr_offset(index); +} + +int x86_setup_perfctr(struct perf_event *event); + +int x86_pmu_hw_config(struct perf_event *event); + +void x86_pmu_disable_all(void); + +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, + u64 enable_mask) +{ + if (hwc->extra_reg.reg) + wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); + wrmsrl(hwc->config_base, hwc->config | enable_mask); +} + +void x86_pmu_enable_all(int added); + +int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); + +void x86_pmu_stop(struct perf_event *event, int flags); + +static inline void x86_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +void x86_pmu_enable_event(struct perf_event *event); + +int x86_pmu_handle_irq(struct pt_regs *regs); + +extern struct event_constraint emptyconstraint; + +extern struct event_constraint unconstrained; + +#ifdef CONFIG_CPU_SUP_AMD + +int amd_pmu_init(void); + +#else /* CONFIG_CPU_SUP_AMD */ + +static inline int amd_pmu_init(void) +{ + return 0; +} + +#endif /* CONFIG_CPU_SUP_AMD */ + +#ifdef CONFIG_CPU_SUP_INTEL + +int intel_pmu_save_and_restart(struct perf_event *event); + +struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event); + +struct intel_shared_regs *allocate_shared_regs(int cpu); + +int intel_pmu_init(void); + +void init_debug_store_on_cpu(int cpu); + +void fini_debug_store_on_cpu(int cpu); + +void release_ds_buffers(void); + +void reserve_ds_buffers(void); + +extern struct event_constraint bts_constraint; + +void intel_pmu_enable_bts(u64 config); + +void intel_pmu_disable_bts(void); + +int intel_pmu_drain_bts_buffer(void); + +extern struct event_constraint intel_core2_pebs_event_constraints[]; + +extern struct event_constraint intel_atom_pebs_event_constraints[]; + +extern struct event_constraint intel_nehalem_pebs_event_constraints[]; + +extern struct event_constraint intel_westmere_pebs_event_constraints[]; + +extern struct event_constraint intel_snb_pebs_event_constraints[]; + +struct event_constraint *intel_pebs_constraints(struct perf_event *event); + +void intel_pmu_pebs_enable(struct perf_event *event); + +void intel_pmu_pebs_disable(struct perf_event *event); + +void intel_pmu_pebs_enable_all(void); + +void intel_pmu_pebs_disable_all(void); + +void intel_ds_init(void); + +void intel_pmu_lbr_reset(void); + +void intel_pmu_lbr_enable(struct perf_event *event); + +void intel_pmu_lbr_disable(struct perf_event *event); + +void intel_pmu_lbr_enable_all(void); + +void intel_pmu_lbr_disable_all(void); + +void intel_pmu_lbr_read(void); + +void intel_pmu_lbr_init_core(void); + +void intel_pmu_lbr_init_nhm(void); + +void intel_pmu_lbr_init_atom(void); + +int p4_pmu_init(void); + +int p6_pmu_init(void); + +#else /* CONFIG_CPU_SUP_INTEL */ + +static inline void reserve_ds_buffers(void) +{ +} + +static inline void release_ds_buffers(void) +{ +} + +static inline int intel_pmu_init(void) +{ + return 0; +} + +static inline struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + return NULL; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 941caa2e449..384450d6712 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,4 +1,10 @@ -#ifdef CONFIG_CPU_SUP_AMD +#include <linux/perf_event.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <asm/apicdef.h> + +#include "perf_event.h" static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -350,7 +356,7 @@ static void amd_pmu_cpu_starting(int cpu) continue; if (nb->nb_id == nb_id) { - kfree(cpuc->amd_nb); + cpuc->kfree_on_online = cpuc->amd_nb; cpuc->amd_nb = nb; break; } @@ -573,7 +579,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { #endif }; -static __init int amd_pmu_init(void) +__init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) @@ -602,12 +608,3 @@ static __init int amd_pmu_init(void) return 0; } - -#else /* CONFIG_CPU_SUP_AMD */ - -static int amd_pmu_init(void) -{ - return 0; -} - -#endif diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f88af2c2a56..61fa35750b9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,16 +1,19 @@ -#ifdef CONFIG_CPU_SUP_INTEL - /* * Per core/cpu state * * Used to coordinate shared registers between HT threads or * among events on a single PMU. */ -struct intel_shared_regs { - struct er_account regs[EXTRA_REG_MAX]; - int refcnt; /* per-core: #HT threads */ - unsigned core_id; /* per-core: core id */ -}; + +#include <linux/stddef.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> + +#include <asm/hardirq.h> +#include <asm/apic.h> + +#include "perf_event.h" /* * Intel PerfMon, used on Core and later. @@ -945,7 +948,7 @@ static void intel_pmu_enable_event(struct perf_event *event) * Save and restart an expired event. Called by NMI contexts, * so it has to be careful about preempting normal event ops: */ -static int intel_pmu_save_and_restart(struct perf_event *event) +int intel_pmu_save_and_restart(struct perf_event *event) { x86_perf_event_update(event); return x86_perf_event_set_period(event); @@ -1197,6 +1200,21 @@ intel_shared_regs_constraints(struct cpu_hw_events *cpuc, return c; } +struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c; + + if (x86_pmu.event_constraints) { + for_each_event_constraint(c, x86_pmu.event_constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &unconstrained; +} + static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -1309,7 +1327,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, }; -static struct intel_shared_regs *allocate_shared_regs(int cpu) +struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; int i; @@ -1362,7 +1380,7 @@ static void intel_pmu_cpu_starting(int cpu) pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - kfree(cpuc->shared_regs); + cpuc->kfree_on_online = cpuc->shared_regs; cpuc->shared_regs = pc; break; } @@ -1441,7 +1459,7 @@ static void intel_clovertown_quirks(void) x86_pmu.pebs_constraints = NULL; } -static __init int intel_pmu_init(void) +__init int intel_pmu_init(void) { union cpuid10_edx edx; union cpuid10_eax eax; @@ -1597,7 +1615,7 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_snb_event_constraints; - x86_pmu.pebs_constraints = intel_snb_pebs_events; + x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; @@ -1628,16 +1646,3 @@ static __init int intel_pmu_init(void) } return 0; } - -#else /* CONFIG_CPU_SUP_INTEL */ - -static int intel_pmu_init(void) -{ - return 0; -} - -static struct intel_shared_regs *allocate_shared_regs(int cpu) -{ - return NULL; -} -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 1b1ef3addcf..c0d238f49db 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -1,7 +1,10 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/slab.h> -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +#include <asm/perf_event.h> + +#include "perf_event.h" /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -37,24 +40,7 @@ struct pebs_record_nhm { u64 status, dla, dse, lat; }; -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; - -static void init_debug_store_on_cpu(int cpu) +void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -66,7 +52,7 @@ static void init_debug_store_on_cpu(int cpu) (u32)((u64)(unsigned long)ds >> 32)); } -static void fini_debug_store_on_cpu(int cpu) +void fini_debug_store_on_cpu(int cpu) { if (!per_cpu(cpu_hw_events, cpu).ds) return; @@ -175,7 +161,7 @@ static void release_ds_buffer(int cpu) kfree(ds); } -static void release_ds_buffers(void) +void release_ds_buffers(void) { int cpu; @@ -194,7 +180,7 @@ static void release_ds_buffers(void) put_online_cpus(); } -static void reserve_ds_buffers(void) +void reserve_ds_buffers(void) { int bts_err = 0, pebs_err = 0; int cpu; @@ -260,10 +246,10 @@ static void reserve_ds_buffers(void) * BTS */ -static struct event_constraint bts_constraint = +struct event_constraint bts_constraint = EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); -static void intel_pmu_enable_bts(u64 config) +void intel_pmu_enable_bts(u64 config) { unsigned long debugctlmsr; @@ -282,7 +268,7 @@ static void intel_pmu_enable_bts(u64 config) update_debugctlmsr(debugctlmsr); } -static void intel_pmu_disable_bts(void) +void intel_pmu_disable_bts(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); unsigned long debugctlmsr; @@ -299,7 +285,7 @@ static void intel_pmu_disable_bts(void) update_debugctlmsr(debugctlmsr); } -static int intel_pmu_drain_bts_buffer(void) +int intel_pmu_drain_bts_buffer(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -361,7 +347,7 @@ static int intel_pmu_drain_bts_buffer(void) /* * PEBS */ -static struct event_constraint intel_core2_pebs_event_constraints[] = { +struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ @@ -370,14 +356,14 @@ static struct event_constraint intel_core2_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_atom_pebs_event_constraints[] = { +struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; -static struct event_constraint intel_nehalem_pebs_event_constraints[] = { +struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ @@ -392,7 +378,7 @@ static struct event_constraint intel_nehalem_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_westmere_pebs_event_constraints[] = { +struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ @@ -407,7 +393,7 @@ static struct event_constraint intel_westmere_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_snb_pebs_events[] = { +struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ @@ -428,8 +414,7 @@ static struct event_constraint intel_snb_pebs_events[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint * -intel_pebs_constraints(struct perf_event *event) +struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -446,7 +431,7 @@ intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } -static void intel_pmu_pebs_enable(struct perf_event *event) +void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -460,7 +445,7 @@ static void intel_pmu_pebs_enable(struct perf_event *event) intel_pmu_lbr_enable(event); } -static void intel_pmu_pebs_disable(struct perf_event *event) +void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -475,7 +460,7 @@ static void intel_pmu_pebs_disable(struct perf_event *event) intel_pmu_lbr_disable(event); } -static void intel_pmu_pebs_enable_all(void) +void intel_pmu_pebs_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -483,7 +468,7 @@ static void intel_pmu_pebs_enable_all(void) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); } -static void intel_pmu_pebs_disable_all(void) +void intel_pmu_pebs_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -576,8 +561,6 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static int intel_pmu_save_and_restart(struct perf_event *event); - static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { @@ -716,7 +699,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * BTS, PEBS probe and setup */ -static void intel_ds_init(void) +void intel_ds_init(void) { /* * No support for 32bit formats @@ -749,15 +732,3 @@ static void intel_ds_init(void) } } } - -#else /* CONFIG_CPU_SUP_INTEL */ - -static void reserve_ds_buffers(void) -{ -} - -static void release_ds_buffers(void) -{ -} - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d202c1bece1..3fab3de3ce9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -1,4 +1,10 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> +#include <linux/types.h> + +#include <asm/perf_event.h> +#include <asm/msr.h> + +#include "perf_event.h" enum { LBR_FORMAT_32 = 0x00, @@ -48,7 +54,7 @@ static void intel_pmu_lbr_reset_64(void) } } -static void intel_pmu_lbr_reset(void) +void intel_pmu_lbr_reset(void) { if (!x86_pmu.lbr_nr) return; @@ -59,7 +65,7 @@ static void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_64(); } -static void intel_pmu_lbr_enable(struct perf_event *event) +void intel_pmu_lbr_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -81,7 +87,7 @@ static void intel_pmu_lbr_enable(struct perf_event *event) cpuc->lbr_users++; } -static void intel_pmu_lbr_disable(struct perf_event *event) +void intel_pmu_lbr_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -95,7 +101,7 @@ static void intel_pmu_lbr_disable(struct perf_event *event) __intel_pmu_lbr_disable(); } -static void intel_pmu_lbr_enable_all(void) +void intel_pmu_lbr_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -103,7 +109,7 @@ static void intel_pmu_lbr_enable_all(void) __intel_pmu_lbr_enable(); } -static void intel_pmu_lbr_disable_all(void) +void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -178,7 +184,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_stack.nr = i; } -static void intel_pmu_lbr_read(void) +void intel_pmu_lbr_read(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -191,7 +197,7 @@ static void intel_pmu_lbr_read(void) intel_pmu_lbr_read_64(cpuc); } -static void intel_pmu_lbr_init_core(void) +void intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; x86_pmu.lbr_tos = 0x01c9; @@ -199,7 +205,7 @@ static void intel_pmu_lbr_init_core(void) x86_pmu.lbr_to = 0x60; } -static void intel_pmu_lbr_init_nhm(void) +void intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = 0x01c9; @@ -207,12 +213,10 @@ static void intel_pmu_lbr_init_nhm(void) x86_pmu.lbr_to = 0x6c0; } -static void intel_pmu_lbr_init_atom(void) +void intel_pmu_lbr_init_atom(void) { x86_pmu.lbr_nr = 8; x86_pmu.lbr_tos = 0x01c9; x86_pmu.lbr_from = 0x40; x86_pmu.lbr_to = 0x60; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 7809d2bcb20..492bf1358a7 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -7,9 +7,13 @@ * For licencing details see kernel-base/COPYING */ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> #include <asm/perf_event_p4.h> +#include <asm/hardirq.h> +#include <asm/apic.h> + +#include "perf_event.h" #define P4_CNTR_LIMIT 3 /* @@ -1303,7 +1307,7 @@ static __initconst const struct x86_pmu p4_pmu = { .perfctr_second_write = 1, }; -static __init int p4_pmu_init(void) +__init int p4_pmu_init(void) { unsigned int low, high; @@ -1326,5 +1330,3 @@ static __init int p4_pmu_init(void) return 0; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 20c097e3386..c7181befecd 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -1,4 +1,7 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> +#include <linux/types.h> + +#include "perf_event.h" /* * Not sure about some of these @@ -114,7 +117,7 @@ static __initconst const struct x86_pmu p6_pmu = { .event_constraints = p6_event_constraints, }; -static __init int p6_pmu_init(void) +__init int p6_pmu_init(void) { switch (boot_cpu_data.x86_model) { case 1: @@ -138,5 +141,3 @@ static __init int p6_pmu_init(void) return 0; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 3f2ad2640d8..ccdbc16b894 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -42,8 +42,11 @@ int mach_set_rtc_mmss(unsigned long nowtime) { int real_seconds, real_minutes, cmos_minutes; unsigned char save_control, save_freq_select; + unsigned long flags; int retval = 0; + spin_lock_irqsave(&rtc_lock, flags); + /* tell the clock it's being set */ save_control = CMOS_READ(RTC_CONTROL); CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); @@ -93,12 +96,17 @@ int mach_set_rtc_mmss(unsigned long nowtime) CMOS_WRITE(save_control, RTC_CONTROL); CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + spin_unlock_irqrestore(&rtc_lock, flags); + return retval; } unsigned long mach_get_cmos_time(void) { unsigned int status, year, mon, day, hour, min, sec, century = 0; + unsigned long flags; + + spin_lock_irqsave(&rtc_lock, flags); /* * If UIP is clear, then we have >= 244 microseconds before @@ -125,6 +133,8 @@ unsigned long mach_get_cmos_time(void) status = CMOS_READ(RTC_CONTROL); WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY)); + spin_unlock_irqrestore(&rtc_lock, flags); + if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) { sec = bcd2bin(sec); min = bcd2bin(min); @@ -169,24 +179,15 @@ EXPORT_SYMBOL(rtc_cmos_write); int update_persistent_clock(struct timespec now) { - unsigned long flags; - int retval; - - spin_lock_irqsave(&rtc_lock, flags); - retval = x86_platform.set_wallclock(now.tv_sec); - spin_unlock_irqrestore(&rtc_lock, flags); - - return retval; + return x86_platform.set_wallclock(now.tv_sec); } /* not static: needed by APM */ void read_persistent_clock(struct timespec *ts) { - unsigned long retval, flags; + unsigned long retval; - spin_lock_irqsave(&rtc_lock, flags); retval = x86_platform.get_wallclock(); - spin_unlock_irqrestore(&rtc_lock, flags); ts->tv_sec = retval; ts->tv_nsec = 0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 6f08bc940fa..8b4cc5f067d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3603,7 +3603,7 @@ done_prefixes: break; case Src2CL: ctxt->src2.bytes = 1; - ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0x8; + ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff; break; case Src2ImmByte: rc = decode_imm(ctxt, &ctxt->src2, 1, true); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 1c5b69373a0..8e8da7960db 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -400,7 +400,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) /* xchg acts as a barrier before the setting of the high bits */ orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low); - orig.spte_high = ssptep->spte_high = sspte.spte_high; + orig.spte_high = ssptep->spte_high; + ssptep->spte_high = sspte.spte_high; count_spte_clear(sptep, spte); return orig.spte; diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 94b745045e4..d90528ea541 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -28,7 +28,7 @@ static int counter_width = 32; #define MSR_PPRO_EVENTSEL_RESERVED ((0xFFFFFFFFULL<<32)|(1ULL<<21)) -static u64 *reset_value; +static u64 reset_value[OP_MAX_COUNTER]; static void ppro_shutdown(struct op_msrs const * const msrs) { @@ -40,10 +40,6 @@ static void ppro_shutdown(struct op_msrs const * const msrs) release_perfctr_nmi(MSR_P6_PERFCTR0 + i); release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); } - if (reset_value) { - kfree(reset_value); - reset_value = NULL; - } } static int ppro_fill_in_addresses(struct op_msrs * const msrs) @@ -79,13 +75,6 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, u64 val; int i; - if (!reset_value) { - reset_value = kzalloc(sizeof(reset_value[0]) * num_counters, - GFP_ATOMIC); - if (!reset_value) - return; - } - if (cpu_has_arch_perfmon) { union cpuid10_eax eax; eax.full = cpuid_eax(0xa); @@ -141,13 +130,6 @@ static int ppro_check_ctrs(struct pt_regs * const regs, u64 val; int i; - /* - * This can happen if perf counters are in use when - * we steal the die notifier NMI. - */ - if (unlikely(!reset_value)) - goto out; - for (i = 0; i < num_counters; ++i) { if (!reset_value[i]) continue; @@ -158,7 +140,6 @@ static int ppro_check_ctrs(struct pt_regs * const regs, wrmsrl(msrs->counters[i].addr, -reset_value[i]); } -out: /* Only P6 based Pentium M need to re-unmask the apic vector but it * doesn't hurt other P6 variant */ apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); @@ -179,8 +160,6 @@ static void ppro_start(struct op_msrs const * const msrs) u64 val; int i; - if (!reset_value) - return; for (i = 0; i < num_counters; ++i) { if (reset_value[i]) { rdmsrl(msrs->controls[i].addr, val); @@ -196,8 +175,6 @@ static void ppro_stop(struct op_msrs const * const msrs) u64 val; int i; - if (!reset_value) - return; for (i = 0; i < num_counters; ++i) { if (!reset_value[i]) continue; @@ -242,7 +219,7 @@ static void arch_perfmon_setup_counters(void) eax.split.bit_width = 40; } - num_counters = eax.split.num_counters; + num_counters = min((int)eax.split.num_counters, OP_MAX_COUNTER); op_arch_perfmon_spec.num_counters = num_counters; op_arch_perfmon_spec.num_controls = num_counters; diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c index 73d70d65e76..6d5dbcdd444 100644 --- a/arch/x86/platform/mrst/vrtc.c +++ b/arch/x86/platform/mrst/vrtc.c @@ -58,8 +58,11 @@ EXPORT_SYMBOL_GPL(vrtc_cmos_write); unsigned long vrtc_get_time(void) { u8 sec, min, hour, mday, mon; + unsigned long flags; u32 year; + spin_lock_irqsave(&rtc_lock, flags); + while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP)) cpu_relax(); @@ -70,6 +73,8 @@ unsigned long vrtc_get_time(void) mon = vrtc_cmos_read(RTC_MONTH); year = vrtc_cmos_read(RTC_YEAR); + spin_unlock_irqrestore(&rtc_lock, flags); + /* vRTC YEAR reg contains the offset to 1960 */ year += 1960; @@ -83,8 +88,10 @@ unsigned long vrtc_get_time(void) int vrtc_set_mmss(unsigned long nowtime) { int real_sec, real_min; + unsigned long flags; int vrtc_min; + spin_lock_irqsave(&rtc_lock, flags); vrtc_min = vrtc_cmos_read(RTC_MINUTES); real_sec = nowtime % 60; @@ -95,6 +102,8 @@ int vrtc_set_mmss(unsigned long nowtime) vrtc_cmos_write(real_sec, RTC_SECONDS); vrtc_cmos_write(real_min, RTC_MINUTES); + spin_unlock_irqrestore(&rtc_lock, flags); + return 0; } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 20a61427506..3dd53f997b1 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1721,10 +1721,8 @@ void __init xen_setup_machphys_mapping(void) machine_to_phys_nr = MACH2PHYS_NR_ENTRIES; } #ifdef CONFIG_X86_32 - if ((machine_to_phys_mapping + machine_to_phys_nr) - < machine_to_phys_mapping) - machine_to_phys_nr = (unsigned long *)NULL - - machine_to_phys_mapping; + WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1)) + < machine_to_phys_mapping); #endif } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index c3b8d440873..46d6d21dbdb 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -306,10 +306,12 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); extra_limit = xen_get_max_pages(); - if (extra_limit >= max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; + if (max_pfn + extra_pages > extra_limit) { + if (extra_limit > max_pfn) + extra_pages = extra_limit - max_pfn; + else + extra_pages = 0; + } extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d4fc6d454f8..041d4fe9dfe 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -532,7 +532,6 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) WARN_ON(xen_smp_intr_init(0)); xen_init_lock_cpu(0); - xen_init_spinlocks(); } static int __cpuinit xen_hvm_cpu_up(unsigned int cpu) diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 5158c505bef..163b4679556 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -168,9 +168,10 @@ cycle_t xen_clocksource_read(void) struct pvclock_vcpu_time_info *src; cycle_t ret; - src = &get_cpu_var(xen_vcpu)->time; + preempt_disable_notrace(); + src = &__get_cpu_var(xen_vcpu)->time; ret = pvclock_clocksource_read(src); - put_cpu_var(xen_vcpu); + preempt_enable_notrace(); return ret; } |