diff options
Diffstat (limited to 'arch')
56 files changed, 395 insertions, 277 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2c3bdce15134..13b739469c51 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -49,7 +49,6 @@ config ARM select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 - select VIRT_TO_BUS select KTIME_SCALAR select PERF_USE_VMALLOC select RTC_LIB @@ -743,6 +742,7 @@ config ARCH_RPC select NEED_MACH_IO_H select NEED_MACH_MEMORY_H select NO_IOPORT + select VIRT_TO_BUS help On the Acorn Risc-PC, Linux can support the internal IDE disk and CD-ROM interface, serial and parallel port, and the floppy drive. @@ -878,6 +878,7 @@ config ARCH_SHARK select ISA_DMA select NEED_MACH_MEMORY_H select PCI + select VIRT_TO_BUS select ZONE_DMA help Support for the StrongARM based Digital DNARD machine, also known @@ -1005,12 +1006,12 @@ config ARCH_MULTI_V4_V5 bool config ARCH_MULTI_V6 - bool "ARMv6 based platforms (ARM11, Scorpion, ...)" + bool "ARMv6 based platforms (ARM11)" select ARCH_MULTI_V6_V7 select CPU_V6 config ARCH_MULTI_V7 - bool "ARMv7 based platforms (Cortex-A, PJ4, Krait)" + bool "ARMv7 based platforms (Cortex-A, PJ4, Scorpion, Krait)" default y select ARCH_MULTI_V6_V7 select ARCH_VEXPRESS @@ -1461,10 +1462,6 @@ config ISA_DMA bool select ISA_DMA_API -config ARCH_NO_VIRT_TO_BUS - def_bool y - depends on !ARCH_RPC && !ARCH_NETWINDER && !ARCH_SHARK - # Select ISA DMA interface config ISA_DMA_API bool diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index aa98e641931f..a98c0d50fbbe 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -238,8 +238,32 @@ nand { pinctrl_nand: nand-0 { atmel,pins = - <3 4 0x0 0x1 /* PD5 gpio RDY pin pull_up */ - 3 5 0x0 0x1>; /* PD4 gpio enable pin pull_up */ + <3 0 0x1 0x0 /* PD0 periph A Read Enable */ + 3 1 0x1 0x0 /* PD1 periph A Write Enable */ + 3 2 0x1 0x0 /* PD2 periph A Address Latch Enable */ + 3 3 0x1 0x0 /* PD3 periph A Command Latch Enable */ + 3 4 0x0 0x1 /* PD4 gpio Chip Enable pin pull_up */ + 3 5 0x0 0x1 /* PD5 gpio RDY/BUSY pin pull_up */ + 3 6 0x1 0x0 /* PD6 periph A Data bit 0 */ + 3 7 0x1 0x0 /* PD7 periph A Data bit 1 */ + 3 8 0x1 0x0 /* PD8 periph A Data bit 2 */ + 3 9 0x1 0x0 /* PD9 periph A Data bit 3 */ + 3 10 0x1 0x0 /* PD10 periph A Data bit 4 */ + 3 11 0x1 0x0 /* PD11 periph A Data bit 5 */ + 3 12 0x1 0x0 /* PD12 periph A Data bit 6 */ + 3 13 0x1 0x0>; /* PD13 periph A Data bit 7 */ + }; + + pinctrl_nand_16bits: nand_16bits-0 { + atmel,pins = + <3 14 0x1 0x0 /* PD14 periph A Data bit 8 */ + 3 15 0x1 0x0 /* PD15 periph A Data bit 9 */ + 3 16 0x1 0x0 /* PD16 periph A Data bit 10 */ + 3 17 0x1 0x0 /* PD17 periph A Data bit 11 */ + 3 18 0x1 0x0 /* PD18 periph A Data bit 12 */ + 3 19 0x1 0x0 /* PD19 periph A Data bit 13 */ + 3 20 0x1 0x0 /* PD20 periph A Data bit 14 */ + 3 21 0x1 0x0>; /* PD21 periph A Data bit 15 */ }; }; diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi index e1347fceb5bc..1a62bcf18aa3 100644 --- a/arch/arm/boot/dts/exynos4.dtsi +++ b/arch/arm/boot/dts/exynos4.dtsi @@ -275,18 +275,27 @@ compatible = "arm,pl330", "arm,primecell"; reg = <0x12680000 0x1000>; interrupts = <0 35 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; pdma1: pdma@12690000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x12690000 0x1000>; interrupts = <0 36 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; mdma1: mdma@12850000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x12850000 0x1000>; interrupts = <0 34 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <1>; }; }; }; diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi index 5f3562ad6746..9a99755920c0 100644 --- a/arch/arm/boot/dts/exynos5440.dtsi +++ b/arch/arm/boot/dts/exynos5440.dtsi @@ -142,12 +142,18 @@ compatible = "arm,pl330", "arm,primecell"; reg = <0x120000 0x1000>; interrupts = <0 34 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; pdma1: pdma@121B0000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x121000 0x1000>; interrupts = <0 35 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; }; diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 31644f1978d5..79078edbb9bc 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -480,7 +480,7 @@ static void __cpuinit broadcast_timer_setup(struct clock_event_device *evt) evt->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_DUMMY; - evt->rating = 400; + evt->rating = 100; evt->mult = 1; evt->set_mode = broadcast_timer_set_mode; diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index d912e7397ecc..94b0650ea98f 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -14,31 +14,15 @@ .text .align 5 - .word 0 - -1: subs r2, r2, #4 @ 1 do we have enough - blt 5f @ 1 bytes to align with? - cmp r3, #2 @ 1 - strltb r1, [ip], #1 @ 1 - strleb r1, [ip], #1 @ 1 - strb r1, [ip], #1 @ 1 - add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) -/* - * The pointer is now aligned and the length is adjusted. Try doing the - * memset again. - */ ENTRY(memset) -/* - * Preserve the contents of r0 for the return value. - */ - mov ip, r0 - ands r3, ip, #3 @ 1 unaligned? - bne 1b @ 1 + ands r3, r0, #3 @ 1 unaligned? + mov ip, r0 @ preserve r0 as return value + bne 6f @ 1 /* * we know that the pointer in ip is aligned to a word boundary. */ - orr r1, r1, r1, lsl #8 +1: orr r1, r1, r1, lsl #8 orr r1, r1, r1, lsl #16 mov r3, r1 cmp r2, #16 @@ -127,4 +111,13 @@ ENTRY(memset) tst r2, #1 strneb r1, [ip], #1 mov pc, lr + +6: subs r2, r2, #4 @ 1 do we have enough + blt 5b @ 1 bytes to align with? + cmp r3, #2 @ 1 + strltb r1, [ip], #1 @ 1 + strleb r1, [ip], #1 @ 1 + strb r1, [ip], #1 @ 1 + add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) + b 1b ENDPROC(memset) diff --git a/arch/arm/mach-at91/include/mach/gpio.h b/arch/arm/mach-at91/include/mach/gpio.h index eed465ab0dd7..5fc23771c154 100644 --- a/arch/arm/mach-at91/include/mach/gpio.h +++ b/arch/arm/mach-at91/include/mach/gpio.h @@ -209,6 +209,14 @@ extern int at91_get_gpio_value(unsigned pin); extern void at91_gpio_suspend(void); extern void at91_gpio_resume(void); +#ifdef CONFIG_PINCTRL_AT91 +extern void at91_pinctrl_gpio_suspend(void); +extern void at91_pinctrl_gpio_resume(void); +#else +static inline void at91_pinctrl_gpio_suspend(void) {} +static inline void at91_pinctrl_gpio_resume(void) {} +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm/mach-at91/irq.c b/arch/arm/mach-at91/irq.c index 8e210262aeee..e0ca59171022 100644 --- a/arch/arm/mach-at91/irq.c +++ b/arch/arm/mach-at91/irq.c @@ -92,23 +92,21 @@ static int at91_aic_set_wake(struct irq_data *d, unsigned value) void at91_irq_suspend(void) { - int i = 0, bit; + int bit = -1; if (has_aic5()) { /* disable enabled irqs */ - while ((bit = find_next_bit(backups, n_irqs, i)) < n_irqs) { + while ((bit = find_next_bit(backups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IDCR, 1); - i = bit; } /* enable wakeup irqs */ - i = 0; - while ((bit = find_next_bit(wakeups, n_irqs, i)) < n_irqs) { + bit = -1; + while ((bit = find_next_bit(wakeups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IECR, 1); - i = bit; } } else { at91_aic_write(AT91_AIC_IDCR, *backups); @@ -118,23 +116,21 @@ void at91_irq_suspend(void) void at91_irq_resume(void) { - int i = 0, bit; + int bit = -1; if (has_aic5()) { /* disable wakeup irqs */ - while ((bit = find_next_bit(wakeups, n_irqs, i)) < n_irqs) { + while ((bit = find_next_bit(wakeups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IDCR, 1); - i = bit; } /* enable irqs disabled for suspend */ - i = 0; - while ((bit = find_next_bit(backups, n_irqs, i)) < n_irqs) { + bit = -1; + while ((bit = find_next_bit(backups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IECR, 1); - i = bit; } } else { at91_aic_write(AT91_AIC_IDCR, *wakeups); diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index adb6db888a1f..73f1f250403a 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -201,7 +201,10 @@ extern u32 at91_slow_clock_sz; static int at91_pm_enter(suspend_state_t state) { - at91_gpio_suspend(); + if (of_have_populated_dt()) + at91_pinctrl_gpio_suspend(); + else + at91_gpio_suspend(); at91_irq_suspend(); pr_debug("AT91: PM - wake mask %08x, pm state %d\n", @@ -286,7 +289,10 @@ static int at91_pm_enter(suspend_state_t state) error: target_state = PM_SUSPEND_ON; at91_irq_resume(); - at91_gpio_resume(); + if (of_have_populated_dt()) + at91_pinctrl_gpio_resume(); + else + at91_gpio_resume(); return 0; } diff --git a/arch/arm/mach-davinci/dma.c b/arch/arm/mach-davinci/dma.c index a685e9706b7b..45b7c71d9cc1 100644 --- a/arch/arm/mach-davinci/dma.c +++ b/arch/arm/mach-davinci/dma.c @@ -743,6 +743,9 @@ EXPORT_SYMBOL(edma_free_channel); */ int edma_alloc_slot(unsigned ctlr, int slot) { + if (!edma_cc[ctlr]) + return -EINVAL; + if (slot >= 0) slot = EDMA_CHAN_SLOT(slot); diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index abda5a18a664..0f2111a11315 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -67,6 +67,7 @@ config ARCH_NETWINDER select ISA select ISA_DMA select PCI + select VIRT_TO_BUS help Say Y here if you intend to run this kernel on the Rebel.COM NetWinder. Information about this machine can be found at: diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index 74e3a34d78b8..e13a8fa5e62c 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -264,6 +264,7 @@ int __init mx35_clocks_init(void) clk_prepare_enable(clk[gpio3_gate]); clk_prepare_enable(clk[iim_gate]); clk_prepare_enable(clk[emi_gate]); + clk_prepare_enable(clk[max_gate]); /* * SCC is needed to boot via mmc after a watchdog reset. The clock code diff --git a/arch/arm/mach-imx/imx25-dt.c b/arch/arm/mach-imx/imx25-dt.c index 03b65e5ea541..82348391582a 100644 --- a/arch/arm/mach-imx/imx25-dt.c +++ b/arch/arm/mach-imx/imx25-dt.c @@ -27,6 +27,11 @@ static const char * const imx25_dt_board_compat[] __initconst = { NULL }; +static void __init imx25_timer_init(void) +{ + mx25_clocks_init_dt(); +} + DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)") .map_io = mx25_map_io, .init_early = imx25_init_early, diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c index d1e2d595e79c..f62b68d926f4 100644 --- a/arch/arm/mach-mmp/gplugd.c +++ b/arch/arm/mach-mmp/gplugd.c @@ -9,6 +9,7 @@ */ #include <linux/init.h> +#include <linux/platform_device.h> #include <linux/gpio.h> #include <asm/mach/arch.h> diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c index fcdf52dbcc49..f051f53e35b7 100644 --- a/arch/arm/mach-s5pv210/clock.c +++ b/arch/arm/mach-s5pv210/clock.c @@ -214,11 +214,6 @@ static struct clk clk_pcmcdclk2 = { .name = "pcmcdclk", }; -static struct clk dummy_apb_pclk = { - .name = "apb_pclk", - .id = -1, -}; - static struct clk *clkset_vpllsrc_list[] = { [0] = &clk_fin_vpll, [1] = &clk_sclk_hdmi27m, @@ -305,18 +300,6 @@ static struct clk_ops clk_fout_apll_ops = { static struct clk init_clocks_off[] = { { - .name = "dma", - .devname = "dma-pl330.0", - .parent = &clk_hclk_psys.clk, - .enable = s5pv210_clk_ip0_ctrl, - .ctrlbit = (1 << 3), - }, { - .name = "dma", - .devname = "dma-pl330.1", - .parent = &clk_hclk_psys.clk, - .enable = s5pv210_clk_ip0_ctrl, - .ctrlbit = (1 << 4), - }, { .name = "rot", .parent = &clk_hclk_dsys.clk, .enable = s5pv210_clk_ip0_ctrl, @@ -573,6 +556,20 @@ static struct clk clk_hsmmc3 = { .ctrlbit = (1<<19), }; +static struct clk clk_pdma0 = { + .name = "pdma0", + .parent = &clk_hclk_psys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 3), +}; + +static struct clk clk_pdma1 = { + .name = "pdma1", + .parent = &clk_hclk_psys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 4), +}; + static struct clk *clkset_uart_list[] = { [6] = &clk_mout_mpll.clk, [7] = &clk_mout_epll.clk, @@ -1075,6 +1072,8 @@ static struct clk *clk_cdev[] = { &clk_hsmmc1, &clk_hsmmc2, &clk_hsmmc3, + &clk_pdma0, + &clk_pdma1, }; /* Clock initialisation code */ @@ -1333,6 +1332,8 @@ static struct clk_lookup s5pv210_clk_lookup[] = { CLKDEV_INIT(NULL, "spi_busclk0", &clk_p), CLKDEV_INIT("s5pv210-spi.0", "spi_busclk1", &clk_sclk_spi0.clk), CLKDEV_INIT("s5pv210-spi.1", "spi_busclk1", &clk_sclk_spi1.clk), + CLKDEV_INIT("dma-pl330.0", "apb_pclk", &clk_pdma0), + CLKDEV_INIT("dma-pl330.1", "apb_pclk", &clk_pdma1), }; void __init s5pv210_register_clocks(void) @@ -1361,6 +1362,5 @@ void __init s5pv210_register_clocks(void) for (ptr = 0; ptr < ARRAY_SIZE(clk_cdev); ptr++) s3c_disable_clocks(clk_cdev[ptr], 1); - s3c24xx_register_clock(&dummy_apb_pclk); s3c_pwmclk_init(); } diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c index 3a38f7b34b94..e373de44a8b6 100644 --- a/arch/arm/mach-s5pv210/mach-goni.c +++ b/arch/arm/mach-s5pv210/mach-goni.c @@ -845,7 +845,7 @@ static struct fimc_source_info goni_camera_sensors[] = { .mux_id = 0, .flags = V4L2_MBUS_PCLK_SAMPLE_FALLING | V4L2_MBUS_VSYNC_ACTIVE_LOW, - .bus_type = FIMC_BUS_TYPE_ITU_601, + .fimc_bus_type = FIMC_BUS_TYPE_ITU_601, .board_info = &noon010pc30_board_info, .i2c_bus_num = 0, .clk_frequency = 16000000UL, diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c index cdcb799e802f..fec49ebc359a 100644 --- a/arch/arm/mach-shmobile/board-marzen.c +++ b/arch/arm/mach-shmobile/board-marzen.c @@ -32,6 +32,7 @@ #include <linux/smsc911x.h> #include <linux/spi/spi.h> #include <linux/spi/sh_hspi.h> +#include <linux/mmc/host.h> #include <linux/mmc/sh_mobile_sdhi.h> #include <linux/mfd/tmio.h> #include <linux/usb/otg.h> diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 6828ef6ce80e..a0bd8a755bdf 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -576,7 +576,7 @@ load_ind: /* x = ((*(frame + k)) & 0xf) << 2; */ ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL; /* the interpreter should deal with the negative K */ - if (k < 0) + if ((int)k < 0) return -1; /* offset in r1: we might have to take the slow path */ emit_mov_i(r_off, k, ctx); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fd70a68387eb..9b6d19f74078 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -9,7 +9,6 @@ config ARM64 select CLONE_BACKWARDS select COMMON_CLK select GENERIC_CLOCKEVENTS - select GENERIC_HARDIRQS_NO_DEPRECATED select GENERIC_IOMAP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 51493430f142..1a6bfe954d49 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -6,17 +6,6 @@ config FRAME_POINTER bool default y -config DEBUG_ERRORS - bool "Verbose kernel error messages" - depends on DEBUG_KERNEL - help - This option controls verbose debugging information which can be - printed when the kernel detects an internal error. This debugging - information is useful to kernel hackers when tracking down problems, - but mostly meaningless to other people. It's safe to say Y unless - you are concerned with the code size or don't want to see these - messages. - config DEBUG_STACK_USAGE bool "Enable stack utilization instrumentation" depends on DEBUG_KERNEL diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 9212c7880da7..09bef29f3a09 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -82,4 +82,3 @@ CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_INFO=y # CONFIG_FTRACE is not set CONFIG_ATOMIC64_SELFTEST=y -CONFIG_DEBUG_ERRORS=y diff --git a/arch/arm64/include/asm/ucontext.h b/arch/arm64/include/asm/ucontext.h index bde960720892..42e04c877428 100644 --- a/arch/arm64/include/asm/ucontext.h +++ b/arch/arm64/include/asm/ucontext.h @@ -22,7 +22,7 @@ struct ucontext { stack_t uc_stack; sigset_t uc_sigmask; /* glibc uses a 1024-bit sigset_t */ - __u8 __unused[(1024 - sizeof(sigset_t)) / 8]; + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; /* last for future expansion */ struct sigcontext uc_mcontext; }; diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index cef3925eaf60..aa3e948f7885 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -40,7 +40,9 @@ EXPORT_SYMBOL(__copy_to_user); EXPORT_SYMBOL(__clear_user); /* bitops */ +#ifdef CONFIG_SMP EXPORT_SYMBOL(__atomic_hash); +#endif /* physical memory */ EXPORT_SYMBOL(memstart_addr); diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 7f4f3673f2bc..e393174fe859 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -549,7 +549,6 @@ int compat_setup_rt_frame(int usig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { struct compat_rt_sigframe __user *frame; - compat_stack_t stack; int err = 0; frame = compat_get_sigframe(ka, regs, sizeof(*frame)); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 80821512e9cc..ea5bb045983a 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -90,6 +90,7 @@ config GENERIC_GPIO config PPC bool default y + select BINFMT_ELF select OF select OF_EARLY_FLATTREE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 2fdb47a19efd..b59e06f507ea 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -343,17 +343,16 @@ extern void slb_set_size(u16 size); /* * VSID allocation (256MB segment) * - * We first generate a 38-bit "proto-VSID". For kernel addresses this - * is equal to the ESID | 1 << 37, for user addresses it is: - * (context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1) + * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated + * from mmu context id and effective segment id of the address. * - * This splits the proto-VSID into the below range - * 0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range - * 2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range - * - * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1 - * That is, we assign half of the space to user processes and half - * to the kernel. + * For user processes max context id is limited to ((1ul << 19) - 5) + * for kernel space, we use the top 4 context ids to map address as below + * NOTE: each context only support 64TB now. + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] * * The proto-VSIDs are then scrambled into real VSIDs with the * multiplicative hash: @@ -363,41 +362,49 @@ extern void slb_set_size(u16 size); * VSID_MULTIPLIER is prime, so in particular it is * co-prime to VSID_MODULUS, making this a 1:1 scrambling function. * Because the modulus is 2^n-1 we can compute it efficiently without - * a divide or extra multiply (see below). - * - * This scheme has several advantages over older methods: - * - * - We have VSIDs allocated for every kernel address - * (i.e. everything above 0xC000000000000000), except the very top - * segment, which simplifies several things. + * a divide or extra multiply (see below). The scramble function gives + * robust scattering in the hash table (at least based on some initial + * results). * - * - We allow for USER_ESID_BITS significant bits of ESID and - * CONTEXT_BITS bits of context for user addresses. - * i.e. 64T (46 bits) of address space for up to half a million contexts. + * We also consider VSID 0 special. We use VSID 0 for slb entries mapping + * bad address. This enables us to consolidate bad address handling in + * hash_page. * - * - The scramble function gives robust scattering in the hash - * table (at least based on some initial results). The previous - * method was more susceptible to pathological cases giving excessive - * hash collisions. + * We also need to avoid the last segment of the last context, because that + * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 + * because of the modulo operation in vsid scramble. But the vmemmap + * (which is what uses region 0xf) will never be close to 64TB in size + * (it's 56 bytes per page of system memory). */ +#define CONTEXT_BITS 19 +#define ESID_BITS 18 +#define ESID_BITS_1T 6 + +/* + * 256MB segment + * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments + * available for user + kernel mapping. The top 4 contexts are used for + * kernel mapping. Each segment contains 2^28 bytes. Each + * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts + * (19 == 37 + 28 - 46). + */ +#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 5) + /* * This should be computed such that protovosid * vsid_mulitplier * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus */ #define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_256M 38 +#define VSID_BITS_256M (CONTEXT_BITS + ESID_BITS) #define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1) #define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_1T 26 +#define VSID_BITS_1T (CONTEXT_BITS + ESID_BITS_1T) #define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1) -#define CONTEXT_BITS 19 -#define USER_ESID_BITS 18 -#define USER_ESID_BITS_1T 6 -#define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT)) +#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT)) /* * This macro generates asm code to compute the VSID scramble @@ -421,7 +428,8 @@ extern void slb_set_size(u16 size); srdi rx,rt,VSID_BITS_##size; \ clrldi rt,rt,(64-VSID_BITS_##size); \ add rt,rt,rx; /* add high and low bits */ \ - /* Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ + /* NOTE: explanation based on VSID_BITS_##size = 36 \ + * Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ * 2^36-1+2^28-1. That in particular means that if r3 >= \ * 2^36-1, then r3+1 has the 2^36 bit set. So, if r3+1 has \ * the bit clear, r3 already has the answer we want, if it \ @@ -513,34 +521,6 @@ typedef struct { }) #endif /* 1 */ -/* - * This is only valid for addresses >= PAGE_OFFSET - * The proto-VSID space is divided into two class - * User: 0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1 - * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1 - * - * With KERNEL_START at 0xc000000000000000, the proto vsid for - * the kernel ends up with 0xc00000000 (36 bits). With 64TB - * support we need to have kernel proto-VSID in the - * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS. - */ -static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) -{ - unsigned long proto_vsid; - /* - * We need to make sure proto_vsid for the kernel is - * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T]) - */ - if (ssize == MMU_SEGSIZE_256M) { - proto_vsid = ea >> SID_SHIFT; - proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS)); - return vsid_scramble(proto_vsid, 256M); - } - proto_vsid = ea >> SID_SHIFT_1T; - proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T)); - return vsid_scramble(proto_vsid, 1T); -} - /* Returns the segment size indicator for a user address */ static inline int user_segment_size(unsigned long addr) { @@ -550,17 +530,41 @@ static inline int user_segment_size(unsigned long addr) return MMU_SEGSIZE_256M; } -/* This is only valid for user addresses (which are below 2^44) */ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, int ssize) { + /* + * Bad address. We return VSID 0 for that + */ + if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) + return 0; + if (ssize == MMU_SEGSIZE_256M) - return vsid_scramble((context << USER_ESID_BITS) + return vsid_scramble((context << ESID_BITS) | (ea >> SID_SHIFT), 256M); - return vsid_scramble((context << USER_ESID_BITS_1T) + return vsid_scramble((context << ESID_BITS_1T) | (ea >> SID_SHIFT_1T), 1T); } +/* + * This is only valid for addresses >= PAGE_OFFSET + * + * For kernel space, we use the top 4 context ids to map address as below + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] + */ +static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) +{ + unsigned long context; + + /* + * kernel take the top 4 context from the available range + */ + context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1; + return get_vsid(context, ea, ssize); +} #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_MMU_HASH64_H_ */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 75a3d71b895d..19599ef352bc 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -275,7 +275,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 87ef8f5ee5bc..200afa5bcfb7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1452,20 +1452,36 @@ do_ste_alloc: _GLOBAL(do_stab_bolted) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ + mfspr r11,SPRN_DAR /* ea */ + /* + * check for bad kernel/user address + * (ea & ~REGION_MASK) >= PGTABLE_RANGE + */ + rldicr. r9,r11,4,(63 - 46 - 4) + li r9,0 /* VSID = 0 for bad address */ + bne- 0f + + /* + * Calculate VSID: + * This is the kernel vsid, we take the top for context from + * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * Here we know that (ea >> 60) == 0xc + */ + lis r9,(MAX_USER_CONTEXT + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT + 1)@l + + srdi r10,r11,SID_SHIFT + rldimi r10,r9,ESID_BITS,0 /* proto vsid */ + ASM_VSID_SCRAMBLE(r10, r9, 256M) + rldic r9,r10,12,16 /* r9 = vsid << 12 */ + +0: /* Hash to the primary group */ ld r10,PACASTABVIRT(r13) - mfspr r11,SPRN_DAR - srdi r11,r11,28 + srdi r11,r11,SID_SHIFT rldimi r10,r11,7,52 /* r10 = first ste of the group */ - /* Calculate VSID */ - /* This is a kernel address, so protovsid = ESID | 1 << 37 */ - li r9,0x1 - rldimi r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0 - ASM_VSID_SCRAMBLE(r11, r9, 256M) - rldic r9,r11,12,16 /* r9 = vsid << 12 */ - /* Search the primary group for a free entry */ 1: ld r11,0(r10) /* Test valid bit of the current ste */ andi. r11,r11,0x80 diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 7f7fb7fd991b..13f8d168b3f1 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2832,11 +2832,13 @@ static void unreloc_toc(void) { } #else -static void __reloc_toc(void *tocstart, unsigned long offset, - unsigned long nr_entries) +static void __reloc_toc(unsigned long offset, unsigned long nr_entries) { unsigned long i; - unsigned long *toc_entry = (unsigned long *)tocstart; + unsigned long *toc_entry; + + /* Get the start of the TOC by using r2 directly. */ + asm volatile("addi %0,2,-0x8000" : "=b" (toc_entry)); for (i = 0; i < nr_entries; i++) { *toc_entry = *toc_entry + offset; @@ -2850,8 +2852,7 @@ static void reloc_toc(void) unsigned long nr_entries = (__prom_init_toc_end - __prom_init_toc_start) / sizeof(long); - /* Need to add offset to get at __prom_init_toc_start */ - __reloc_toc(__prom_init_toc_start + offset, offset, nr_entries); + __reloc_toc(offset, nr_entries); mb(); } @@ -2864,8 +2865,7 @@ static void unreloc_toc(void) mb(); - /* __prom_init_toc_start has been relocated, no need to add offset */ - __reloc_toc(__prom_init_toc_start, -offset, nr_entries); + __reloc_toc(-offset, nr_entries); } #endif #endif diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 245c1b6a0858..f9b30c68ba47 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1428,6 +1428,7 @@ static long ppc_set_hwdebug(struct task_struct *child, brk.address = bp_info->addr & ~7UL; brk.type = HW_BRK_TYPE_TRANSLATE; + brk.len = 8; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index ead58e317294..5d7d29a313eb 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -326,8 +326,8 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu) vcpu3s->context_id[0] = err; vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1) - << USER_ESID_BITS) - 1; - vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS; + << ESID_BITS) - 1; + vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << ESID_BITS; vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first; kvmppc_mmu_hpte_init(vcpu); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 1b6e1271719f..f410c3e12c1e 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -195,6 +195,11 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, unsigned long vpn = hpt_vpn(vaddr, vsid, ssize); unsigned long tprot = prot; + /* + * If we hit a bad address return error. + */ + if (!vsid) + return -1; /* Make kernel text executable */ if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; @@ -759,6 +764,8 @@ void __init early_init_mmu(void) /* Initialize stab / SLB management */ if (mmu_has_feature(MMU_FTR_SLB)) slb_initialize(); + else + stab_initialize(get_paca()->stab_real); } #ifdef CONFIG_SMP @@ -922,11 +929,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n", ea, access, trap); - if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) { - DBG_LOW(" out of pgtable range !\n"); - return 1; - } - /* Get region & vsid */ switch (REGION_ID(ea)) { case USER_REGION_ID: @@ -957,6 +959,11 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) } DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid); + /* Bad address. */ + if (!vsid) { + DBG_LOW("Bad address!\n"); + return 1; + } /* Get pgdir */ pgdir = mm->pgd; if (pgdir == NULL) @@ -1126,6 +1133,8 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, /* Get VSID */ ssize = user_segment_size(ea); vsid = get_vsid(mm->context.id, ea, ssize); + if (!vsid) + return; /* Hash doesn't like irqs */ local_irq_save(flags); @@ -1233,6 +1242,9 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); + /* Don't create HPTE entries for bad address */ + if (!vsid) + return; ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr), mode, HPTE_V_BOLTED, mmu_linear_psize, mmu_kernel_ssize); diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index 40bc5b0ace54..d1d1b92c5b99 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -29,15 +29,6 @@ static DEFINE_SPINLOCK(mmu_context_lock); static DEFINE_IDA(mmu_context_ida); -/* - * 256MB segment - * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments - * available for user mappings. Each segment contains 2^28 bytes. Each - * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts - * (19 == 37 + 28 - 46). - */ -#define MAX_CONTEXT ((1UL << CONTEXT_BITS) - 1) - int __init_new_context(void) { int index; @@ -56,7 +47,7 @@ again: else if (err) return err; - if (index > MAX_CONTEXT) { + if (index > MAX_USER_CONTEXT) { spin_lock(&mmu_context_lock); ida_remove(&mmu_context_ida, index); spin_unlock(&mmu_context_lock); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e212a271c7a4..654258f165ae 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -61,7 +61,7 @@ #endif #ifdef CONFIG_PPC_STD_MMU_64 -#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT)) +#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT)) #error TASK_SIZE_USER64 exceeds user VSID range #endif #endif diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 1a16ca227757..17aa6dfceb34 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -31,10 +31,15 @@ * No other registers are examined or changed. */ _GLOBAL(slb_allocate_realmode) - /* r3 = faulting address */ + /* + * check for bad kernel/user address + * (ea & ~REGION_MASK) >= PGTABLE_RANGE + */ + rldicr. r9,r3,4,(63 - 46 - 4) + bne- 8f srdi r9,r3,60 /* get region */ - srdi r10,r3,28 /* get esid */ + srdi r10,r3,SID_SHIFT /* get esid */ cmpldi cr7,r9,0xc /* cmp PAGE_OFFSET for later use */ /* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */ @@ -56,12 +61,14 @@ _GLOBAL(slb_allocate_realmode) */ _GLOBAL(slb_miss_kernel_load_linear) li r11,0 - li r9,0x1 /* - * for 1T we shift 12 bits more. slb_finish_load_1T will do - * the necessary adjustment + * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * r9 = region id. */ - rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 + addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l + + BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) @@ -91,24 +98,19 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) _GLOBAL(slb_miss_kernel_load_io) li r11,0 6: - li r9,0x1 /* - * for 1T we shift 12 bits more. slb_finish_load_1T will do - * the necessary adjustment + * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * r9 = region id. */ - rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 + addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l + BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T -0: /* user address: proto-VSID = context << 15 | ESID. First check - * if the address is within the boundaries of the user region - */ - srdi. r9,r10,USER_ESID_BITS - bne- 8f /* invalid ea bits set */ - - +0: /* when using slices, we extract the psize off the slice bitmaps * and then we need to get the sllp encoding off the mmu_psize_defs * array. @@ -164,15 +166,13 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) ld r9,PACACONTEXTID(r13) BEGIN_FTR_SECTION cmpldi r10,0x1000 -END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) - rldimi r10,r9,USER_ESID_BITS,0 -BEGIN_FTR_SECTION bge slb_finish_load_1T END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load 8: /* invalid EA */ li r10,0 /* BAD_VSID */ + li r9,0 /* BAD_VSID */ li r11,SLB_VSID_USER /* flags don't much matter */ b slb_finish_load @@ -221,8 +221,6 @@ _GLOBAL(slb_allocate_user) /* get context to calculate proto-VSID */ ld r9,PACACONTEXTID(r13) - rldimi r10,r9,USER_ESID_BITS,0 - /* fall through slb_finish_load */ #endif /* __DISABLED__ */ @@ -231,9 +229,10 @@ _GLOBAL(slb_allocate_user) /* * Finish loading of an SLB entry and return * - * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET + * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET */ slb_finish_load: + rldimi r10,r9,ESID_BITS,0 ASM_VSID_SCRAMBLE(r10,r9,256M) /* * bits above VSID_BITS_256M need to be ignored from r10 @@ -298,10 +297,11 @@ _GLOBAL(slb_compare_rr_to_size) /* * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return. * - * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9 + * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9 */ slb_finish_load_1T: - srdi r10,r10,40-28 /* get 1T ESID */ + srdi r10,r10,(SID_SHIFT_1T - SID_SHIFT) /* get 1T ESID */ + rldimi r10,r9,ESID_BITS_1T,0 ASM_VSID_SCRAMBLE(r10,r9,1T) /* * bits above VSID_BITS_1T need to be ignored from r10 diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 0d82ef50dc3f..023ec8a13f38 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -82,11 +82,11 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, if (!is_kernel_addr(addr)) { ssize = user_segment_size(addr); vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); } else { vsid = get_kernel_vsid(addr, mmu_kernel_ssize); ssize = mmu_kernel_ssize; } + WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); rpte = __real_pte(__pte(pte), ptep); diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index b554879bd31e..3c475d6267c7 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -420,7 +420,20 @@ static struct attribute_group power7_pmu_events_group = { .attrs = power7_events_attr, }; +PMU_FORMAT_ATTR(event, "config:0-19"); + +static struct attribute *power7_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +struct attribute_group power7_pmu_format_group = { + .name = "format", + .attrs = power7_pmu_format_attr, +}; + static const struct attribute_group *power7_pmu_attr_groups[] = { + &power7_pmu_format_group, &power7_pmu_events_group, NULL, }; diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c index 611e92f291c4..7179726ba5c5 100644 --- a/arch/powerpc/platforms/85xx/sgy_cts1000.c +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -69,7 +69,7 @@ static irqreturn_t gpio_halt_irq(int irq, void *__data) return IRQ_HANDLED; }; -static int __devinit gpio_halt_probe(struct platform_device *pdev) +static int gpio_halt_probe(struct platform_device *pdev) { enum of_gpio_flags flags; struct device_node *node = pdev->dev.of_node; @@ -128,7 +128,7 @@ static int __devinit gpio_halt_probe(struct platform_device *pdev) return 0; } -static int __devexit gpio_halt_remove(struct platform_device *pdev) +static int gpio_halt_remove(struct platform_device *pdev) { if (halt_node) { int gpio = of_get_gpio(halt_node, 0); @@ -165,7 +165,7 @@ static struct platform_driver gpio_halt_driver = { .of_match_table = gpio_halt_match, }, .probe = gpio_halt_probe, - .remove = __devexit_p(gpio_halt_remove), + .remove = gpio_halt_remove, }; module_platform_driver(gpio_halt_driver); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index cea2f09c4241..18e3b76c78d7 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -124,9 +124,8 @@ config 6xx select PPC_HAVE_PMU_SUPPORT config POWER3 - bool depends on PPC64 && PPC_BOOK3S - default y if !POWER4_ONLY + def_bool y config POWER4 depends on PPC64 && PPC_BOOK3S @@ -145,8 +144,7 @@ config TUNE_CELL but somewhat slower on other machines. This option only changes the scheduling of instructions, not the selection of instructions itself, so the resulting kernel will keep running on all other - machines. When building a kernel that is supposed to run only - on Cell, you should also select the POWER4_ONLY option. + machines. # this is temp to handle compat with arch=ppc config 8xx diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index 8d4847191ecc..dc9200ca32ed 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -34,6 +34,8 @@ struct arsb { u32 reserved[4]; } __packed; +#define EQC_WR_PROHIBIT 22 + struct msb { u8 fmt:4; u8 oc:4; @@ -96,11 +98,13 @@ struct scm_device { #define OP_STATE_TEMP_ERR 2 #define OP_STATE_PERM_ERR 3 +enum scm_event {SCM_CHANGE, SCM_AVAIL}; + struct scm_driver { struct device_driver drv; int (*probe) (struct scm_device *scmdev); int (*remove) (struct scm_device *scmdev); - void (*notify) (struct scm_device *scmdev); + void (*notify) (struct scm_device *scmdev, enum scm_event event); void (*handler) (struct scm_device *scmdev, void *data, int error); }; diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 1d8fe2b17ef6..6b32af30878c 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -74,8 +74,6 @@ static inline void __tlb_flush_idte(unsigned long asce) static inline void __tlb_flush_mm(struct mm_struct * mm) { - if (unlikely(cpumask_empty(mm_cpumask(mm)))) - return; /* * If the machine has IDTE we prefer to do a per mm flush * on all cpus instead of doing a local flush if the mm diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 550228523267..94feff7d6132 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -636,7 +636,8 @@ ENTRY(mcck_int_handler) UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER mcck_skip: SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT - mvc __PT_R0(64,%r11),__LC_GPREGS_SAVE_AREA + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32 stm %r8,%r9,__PT_PSW(%r11) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) l %r1,BASED(.Ldo_machine_check) diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 9c837c101297..2e6d60c55f90 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -678,8 +678,9 @@ ENTRY(mcck_int_handler) UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER LAST_BREAK %r14 mcck_skip: - lghi %r14,__LC_GPREGS_SAVE_AREA - mvc __PT_R0(128,%r11),0(%r14) + lghi %r14,__LC_GPREGS_SAVE_AREA+64 + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),0(%r14) stmg %r8,%r9,__PT_PSW(%r11) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a5360de85ec7..29268859d8ee 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -571,6 +571,8 @@ static void __init setup_memory_end(void) /* Split remaining virtual space between 1:1 mapping & vmemmap array */ tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page)); + /* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */ + tmp = SECTION_ALIGN_UP(tmp); tmp = VMALLOC_START - tmp * sizeof(struct page); tmp &= ~((vmax >> 11) - 1); /* align to page table level */ tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 289127d5241c..3d361f236308 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -84,12 +84,6 @@ config ARCH_DEFCONFIG default "arch/sparc/configs/sparc32_defconfig" if SPARC32 default "arch/sparc/configs/sparc64_defconfig" if SPARC64 -# CONFIG_BITS can be used at source level to get 32/64 bits -config BITS - int - default 32 if SPARC32 - default 64 if SPARC64 - config IOMMU_HELPER bool default y if SPARC64 @@ -197,7 +191,7 @@ config RWSEM_XCHGADD_ALGORITHM config GENERIC_HWEIGHT bool - default y if !ULTRA_HAS_POPULATION_COUNT + default y config GENERIC_CALIBRATE_DELAY bool diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index d06a26601753..6b67e50fb9b4 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -45,6 +45,7 @@ #define SUN4V_CHIP_NIAGARA3 0x03 #define SUN4V_CHIP_NIAGARA4 0x04 #define SUN4V_CHIP_NIAGARA5 0x05 +#define SUN4V_CHIP_SPARC64X 0x8a #define SUN4V_CHIP_UNKNOWN 0xff #ifndef __ASSEMBLY__ diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index a6c94a2bf9d4..5c5125895db8 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -493,6 +493,12 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara5"; break; + case SUN4V_CHIP_SPARC64X: + sparc_cpu_type = "SPARC64-X"; + sparc_fpu_type = "SPARC64-X integrated FPU"; + sparc_pmu_type = "sparc64-x"; + break; + default: printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n", prom_cpu_compatible); diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 2feb15c35d9e..26b706a1867d 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -134,6 +134,8 @@ prom_niagara_prefix: .asciz "SUNW,UltraSPARC-T" prom_sparc_prefix: .asciz "SPARC-" +prom_sparc64x_prefix: + .asciz "SPARC64-X" .align 4 prom_root_compatible: .skip 64 @@ -412,7 +414,7 @@ sun4v_chip_type: cmp %g2, 'T' be,pt %xcc, 70f cmp %g2, 'M' - bne,pn %xcc, 4f + bne,pn %xcc, 49f nop 70: ldub [%g1 + 7], %g2 @@ -425,7 +427,7 @@ sun4v_chip_type: cmp %g2, '5' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA5, %g4 - ba,pt %xcc, 4f + ba,pt %xcc, 49f nop 91: sethi %hi(prom_cpu_compatible), %g1 @@ -439,6 +441,25 @@ sun4v_chip_type: mov SUN4V_CHIP_NIAGARA2, %g4 4: + /* Athena */ + sethi %hi(prom_cpu_compatible), %g1 + or %g1, %lo(prom_cpu_compatible), %g1 + sethi %hi(prom_sparc64x_prefix), %g7 + or %g7, %lo(prom_sparc64x_prefix), %g7 + mov 9, %g3 +41: ldub [%g7], %g2 + ldub [%g1], %g4 + cmp %g2, %g4 + bne,pn %icc, 49f + add %g7, 1, %g7 + subcc %g3, 1, %g3 + bne,pt %xcc, 41b + add %g1, 1, %g1 + mov SUN4V_CHIP_SPARC64X, %g4 + ba,pt %xcc, 5f + nop + +49: mov SUN4V_CHIP_UNKNOWN, %g4 5: sethi %hi(sun4v_chip_type), %g2 or %g2, %lo(sun4v_chip_type), %g2 diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index fc4320886a3a..4d1487138d26 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -186,6 +186,8 @@ struct grpci2_cap_first { #define CAP9_IOMAP_OFS 0x20 #define CAP9_BARSIZE_OFS 0x24 +#define TGT 256 + struct grpci2_priv { struct leon_pci_info info; /* must be on top of this structure */ struct grpci2_regs *regs; @@ -237,8 +239,12 @@ static int grpci2_cfg_r32(struct grpci2_priv *priv, unsigned int bus, if (where & 0x3) return -EINVAL; - if (bus == 0 && PCI_SLOT(devfn) != 0) - devfn += (0x8 * 6); + if (bus == 0) { + devfn += (0x8 * 6); /* start at AD16=Device0 */ + } else if (bus == TGT) { + bus = 0; + devfn = 0; /* special case: bridge controller itself */ + } /* Select bus */ spin_lock_irqsave(&grpci2_dev_lock, flags); @@ -303,8 +309,12 @@ static int grpci2_cfg_w32(struct grpci2_priv *priv, unsigned int bus, if (where & 0x3) return -EINVAL; - if (bus == 0 && PCI_SLOT(devfn) != 0) - devfn += (0x8 * 6); + if (bus == 0) { + devfn += (0x8 * 6); /* start at AD16=Device0 */ + } else if (bus == TGT) { + bus = 0; + devfn = 0; /* special case: bridge controller itself */ + } /* Select bus */ spin_lock_irqsave(&grpci2_dev_lock, flags); @@ -368,7 +378,7 @@ static int grpci2_read_config(struct pci_bus *bus, unsigned int devfn, unsigned int busno = bus->number; int ret; - if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0)) { + if (PCI_SLOT(devfn) > 15 || busno > 255) { *val = ~0; return 0; } @@ -406,7 +416,7 @@ static int grpci2_write_config(struct pci_bus *bus, unsigned int devfn, struct grpci2_priv *priv = grpci2priv; unsigned int busno = bus->number; - if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0)) + if (PCI_SLOT(devfn) > 15 || busno > 255) return 0; #ifdef GRPCI2_DEBUG_CFGACCESS @@ -578,15 +588,15 @@ void grpci2_hw_init(struct grpci2_priv *priv) REGSTORE(regs->ahbmst_map[i], priv->pci_area); /* Get the GRPCI2 Host PCI ID */ - grpci2_cfg_r32(priv, 0, 0, PCI_VENDOR_ID, &priv->pciid); + grpci2_cfg_r32(priv, TGT, 0, PCI_VENDOR_ID, &priv->pciid); /* Get address to first (always defined) capability structure */ - grpci2_cfg_r8(priv, 0, 0, PCI_CAPABILITY_LIST, &capptr); + grpci2_cfg_r8(priv, TGT, 0, PCI_CAPABILITY_LIST, &capptr); /* Enable/Disable Byte twisting */ - grpci2_cfg_r32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, &io_map); + grpci2_cfg_r32(priv, TGT, 0, capptr+CAP9_IOMAP_OFS, &io_map); io_map = (io_map & ~0x1) | (priv->bt_enabled ? 1 : 0); - grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, io_map); + grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_IOMAP_OFS, io_map); /* Setup the Host's PCI Target BARs for other peripherals to access, * and do DMA to the host's memory. The target BARs can be sized and @@ -617,17 +627,18 @@ void grpci2_hw_init(struct grpci2_priv *priv) pciadr = 0; } } - grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BARSIZE_OFS+i*4, bar_sz); - grpci2_cfg_w32(priv, 0, 0, PCI_BASE_ADDRESS_0+i*4, pciadr); - grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr); + grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_BARSIZE_OFS+i*4, + bar_sz); + grpci2_cfg_w32(priv, TGT, 0, PCI_BASE_ADDRESS_0+i*4, pciadr); + grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr); printk(KERN_INFO " TGT BAR[%d]: 0x%08x (PCI)-> 0x%08x\n", i, pciadr, ahbadr); } /* set as bus master and enable pci memory responses */ - grpci2_cfg_r32(priv, 0, 0, PCI_COMMAND, &data); + grpci2_cfg_r32(priv, TGT, 0, PCI_COMMAND, &data); data |= (PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); - grpci2_cfg_w32(priv, 0, 0, PCI_COMMAND, data); + grpci2_cfg_w32(priv, TGT, 0, PCI_COMMAND, data); /* Enable Error respone (CPU-TRAP) on illegal memory access. */ REGSTORE(regs->ctrl, CTRL_ER | CTRL_PE); diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 8c5eff6d6df5..47684815e5c8 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -330,7 +330,6 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MULTICORE_RAID456=y CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index e7a3dfcbcda7..dd2b8f0c631f 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -324,7 +324,6 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MULTICORE_RAID456=y CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index d3ddd17405d0..5a6d2873f80e 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -77,6 +77,7 @@ struct arch_specific_insn { * a post_handler or break_handler). */ int boostable; + bool if_modifier; }; struct arch_optimized_insn { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 635a74d22409..4979778cc7fb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -414,8 +414,8 @@ struct kvm_vcpu_arch { gpa_t time; struct pvclock_vcpu_time_info hv_clock; unsigned int hw_tsc_khz; - unsigned int time_offset; - struct page *time_page; + struct gfn_to_hva_cache pv_time; + bool pv_time_enabled; /* set guest stopped flag in pvclock flags field */ bool pvclock_set_guest_stopped_request; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 529c8931fc02..dab7580c47ae 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -101,6 +101,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ + INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3f06e6149981..7bfe318d3d8a 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -375,6 +375,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) else p->ainsn.boostable = -1; + /* Check whether the instruction modifies Interrupt Flag or not */ + p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); + /* Also, displacement change doesn't affect the first byte */ p->opcode = p->ainsn.insn[0]; } @@ -434,7 +437,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_flags = kcb->kprobe_old_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - if (is_IF_modifier(p->ainsn.insn)) + if (p->ainsn.if_modifier) kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f71500af1f81..f19ac0aca60d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1406,25 +1406,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) unsigned long flags, this_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; - void *shared_kaddr; s64 kernel_ns, max_kernel_ns; u64 tsc_timestamp, host_tsc; - struct pvclock_vcpu_time_info *guest_hv_clock; + struct pvclock_vcpu_time_info guest_hv_clock; u8 pvclock_flags; bool use_master_clock; kernel_ns = 0; host_tsc = 0; - /* Keep irq disabled to prevent changes to the clock */ - local_irq_save(flags); - this_tsc_khz = __get_cpu_var(cpu_tsc_khz); - if (unlikely(this_tsc_khz == 0)) { - local_irq_restore(flags); - kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); - return 1; - } - /* * If the host uses TSC clock, then passthrough TSC as stable * to the guest. @@ -1436,6 +1426,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kernel_ns = ka->master_kernel_ns; } spin_unlock(&ka->pvclock_gtod_sync_lock); + + /* Keep irq disabled to prevent changes to the clock */ + local_irq_save(flags); + this_tsc_khz = __get_cpu_var(cpu_tsc_khz); + if (unlikely(this_tsc_khz == 0)) { + local_irq_restore(flags); + kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); + return 1; + } if (!use_master_clock) { host_tsc = native_read_tsc(); kernel_ns = get_kernel_ns(); @@ -1463,7 +1462,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_restore(flags); - if (!vcpu->time_page) + if (!vcpu->pv_time_enabled) return 0; /* @@ -1525,12 +1524,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) */ vcpu->hv_clock.version += 2; - shared_kaddr = kmap_atomic(vcpu->time_page); - - guest_hv_clock = shared_kaddr + vcpu->time_offset; + if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + &guest_hv_clock, sizeof(guest_hv_clock)))) + return 0; /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ - pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); + pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); if (vcpu->pvclock_set_guest_stopped_request) { pvclock_flags |= PVCLOCK_GUEST_STOPPED; @@ -1543,12 +1542,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; - memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); - - kunmap_atomic(shared_kaddr); - - mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); return 0; } @@ -1837,10 +1833,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - if (vcpu->arch.time_page) { - kvm_release_page_dirty(vcpu->arch.time_page); - vcpu->arch.time_page = NULL; - } + vcpu->arch.pv_time_enabled = false; } static void accumulate_steal_time(struct kvm_vcpu *vcpu) @@ -1947,6 +1940,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { + u64 gpa_offset; kvmclock_reset(vcpu); vcpu->arch.time = data; @@ -1956,14 +1950,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & 1)) break; - /* ...but clean it before doing the actual write */ - vcpu->arch.time_offset = data & ~(PAGE_MASK | 1); + gpa_offset = data & ~(PAGE_MASK | 1); - vcpu->arch.time_page = - gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT); + /* Check that the address is 32-byte aligned. */ + if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1)) + break; - if (is_error_page(vcpu->arch.time_page)) - vcpu->arch.time_page = NULL; + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.pv_time, data & ~1ULL)) + vcpu->arch.pv_time_enabled = false; + else + vcpu->arch.pv_time_enabled = true; break; } @@ -2967,7 +2964,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, */ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) { - if (!vcpu->arch.time_page) + if (!vcpu->arch.pv_time_enabled) return -EINVAL; vcpu->arch.pvclock_set_guest_stopped_request = true; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -6718,6 +6715,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_wbinvd_dirty_mask; vcpu->arch.ia32_tsc_adjust_msr = 0x0; + vcpu->arch.pv_time_enabled = false; kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); |