diff options
Diffstat (limited to 'arch')
41 files changed, 451 insertions, 239 deletions
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 99a57270250..f84dfe67724 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -266,6 +266,7 @@ void die(const char *str, struct pt_regs *regs, int err) { struct thread_info *thread = current_thread_info(); int ret; + enum bug_trap_type bug_type = BUG_TRAP_TYPE_NONE; oops_enter(); @@ -273,7 +274,9 @@ void die(const char *str, struct pt_regs *regs, int err) console_verbose(); bust_spinlocks(1); if (!user_mode(regs)) - report_bug(regs->ARM_pc, regs); + bug_type = report_bug(regs->ARM_pc, regs); + if (bug_type != BUG_TRAP_TYPE_NONE) + str = "Oops - BUG"; ret = __die(str, err, thread, regs); if (regs && kexec_should_crash(thread->task)) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 1e19691e040..43a31fb0631 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -10,6 +10,7 @@ #include <asm/page.h> #define PROC_INFO \ + . = ALIGN(4); \ VMLINUX_SYMBOL(__proc_info_begin) = .; \ *(.proc.info.init) \ VMLINUX_SYMBOL(__proc_info_end) = .; diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c index 21fc8764866..4e9071589bf 100644 --- a/arch/arm/mach-omap2/board-4430sdp.c +++ b/arch/arm/mach-omap2/board-4430sdp.c @@ -814,7 +814,7 @@ static struct omap_dss_board_info sdp4430_dss_data = { .default_device = &sdp4430_lcd_device, }; -static void omap_4430sdp_display_init(void) +static void __init omap_4430sdp_display_init(void) { int r; @@ -851,7 +851,7 @@ static struct omap_board_mux board_mux[] __initdata = { #define board_mux NULL #endif -static void omap4_sdp4430_wifi_mux_init(void) +static void __init omap4_sdp4430_wifi_mux_init(void) { omap_mux_init_gpio(GPIO_WIFI_IRQ, OMAP_PIN_INPUT | OMAP_PIN_OFF_WAKEUPENABLE); @@ -878,12 +878,17 @@ static struct wl12xx_platform_data omap4_sdp4430_wlan_data __initdata = { .board_tcxo_clock = WL12XX_TCXOCLOCK_26, }; -static void omap4_sdp4430_wifi_init(void) +static void __init omap4_sdp4430_wifi_init(void) { + int ret; + omap4_sdp4430_wifi_mux_init(); - if (wl12xx_set_platform_data(&omap4_sdp4430_wlan_data)) - pr_err("Error setting wl12xx data\n"); - platform_device_register(&omap_vwlan_device); + ret = wl12xx_set_platform_data(&omap4_sdp4430_wlan_data); + if (ret) + pr_err("Error setting wl12xx data: %d\n", ret); + ret = platform_device_register(&omap_vwlan_device); + if (ret) + pr_err("Error registering wl12xx device: %d\n", ret); } static void __init omap_4430sdp_init(void) diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c index 003fe34c934..c775bead149 100644 --- a/arch/arm/mach-omap2/board-omap3evm.c +++ b/arch/arm/mach-omap2/board-omap3evm.c @@ -617,6 +617,21 @@ static struct gpio omap3_evm_ehci_gpios[] __initdata = { { OMAP3_EVM_EHCI_SELECT, GPIOF_OUT_INIT_LOW, "select EHCI port" }, }; +static void __init omap3_evm_wl12xx_init(void) +{ +#ifdef CONFIG_WL12XX_PLATFORM_DATA + int ret; + + /* WL12xx WLAN Init */ + ret = wl12xx_set_platform_data(&omap3evm_wlan_data); + if (ret) + pr_err("error setting wl12xx data: %d\n", ret); + ret = platform_device_register(&omap3evm_wlan_regulator); + if (ret) + pr_err("error registering wl12xx device: %d\n", ret); +#endif +} + static void __init omap3_evm_init(void) { omap3_evm_get_revision(); @@ -665,13 +680,7 @@ static void __init omap3_evm_init(void) omap_ads7846_init(1, OMAP3_EVM_TS_GPIO, 310, NULL); omap3evm_init_smsc911x(); omap3_evm_display_init(); - -#ifdef CONFIG_WL12XX_PLATFORM_DATA - /* WL12xx WLAN Init */ - if (wl12xx_set_platform_data(&omap3evm_wlan_data)) - pr_err("error setting wl12xx data\n"); - platform_device_register(&omap3evm_wlan_regulator); -#endif + omap3_evm_wl12xx_init(); } MACHINE_START(OMAP3EVM, "OMAP3 EVM") diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c index b7779c206a9..28fc271f703 100644 --- a/arch/arm/mach-omap2/board-omap4panda.c +++ b/arch/arm/mach-omap2/board-omap4panda.c @@ -488,13 +488,15 @@ void omap4_panda_display_init(void) static void __init omap4_panda_init(void) { int package = OMAP_PACKAGE_CBS; + int ret; if (omap_rev() == OMAP4430_REV_ES1_0) package = OMAP_PACKAGE_CBL; omap4_mux_init(board_mux, NULL, package); - if (wl12xx_set_platform_data(&omap_panda_wlan_data)) - pr_err("error setting wl12xx data\n"); + ret = wl12xx_set_platform_data(&omap_panda_wlan_data); + if (ret) + pr_err("error setting wl12xx data: %d\n", ret); omap4_panda_i2c_init(); platform_add_devices(panda_devices, ARRAY_SIZE(panda_devices)); diff --git a/arch/arm/mach-omap2/board-zoom-peripherals.c b/arch/arm/mach-omap2/board-zoom-peripherals.c index 8d7ce11cfea..c126461836a 100644 --- a/arch/arm/mach-omap2/board-zoom-peripherals.c +++ b/arch/arm/mach-omap2/board-zoom-peripherals.c @@ -296,8 +296,10 @@ static void enable_board_wakeup_source(void) void __init zoom_peripherals_init(void) { - if (wl12xx_set_platform_data(&omap_zoom_wlan_data)) - pr_err("error setting wl12xx data\n"); + int ret = wl12xx_set_platform_data(&omap_zoom_wlan_data); + + if (ret) + pr_err("error setting wl12xx data: %d\n", ret); omap_i2c_init(); platform_device_register(&omap_vwlan_device); diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c index ad0adb5a1e0..b40c2889529 100644 --- a/arch/arm/mach-omap2/hsmmc.c +++ b/arch/arm/mach-omap2/hsmmc.c @@ -293,8 +293,8 @@ static inline void omap_hsmmc_mux(struct omap_mmc_platform_data *mmc_controller, } } -static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c, - struct omap_mmc_platform_data *mmc) +static int omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c, + struct omap_mmc_platform_data *mmc) { char *hc_name; @@ -430,7 +430,7 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c, #define MAX_OMAP_MMC_HWMOD_NAME_LEN 16 -void __init omap_init_hsmmc(struct omap2_hsmmc_info *hsmmcinfo, int ctrl_nr) +void omap_init_hsmmc(struct omap2_hsmmc_info *hsmmcinfo, int ctrl_nr) { struct omap_hwmod *oh; struct platform_device *pdev; @@ -487,7 +487,7 @@ done: kfree(mmc_data); } -void __init omap2_hsmmc_init(struct omap2_hsmmc_info *controllers) +void omap2_hsmmc_init(struct omap2_hsmmc_info *controllers) { u32 reg; diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c index e1cc75d1a57..fb8bc9fa43b 100644 --- a/arch/arm/mach-omap2/mux.c +++ b/arch/arm/mach-omap2/mux.c @@ -100,8 +100,8 @@ void omap_mux_write_array(struct omap_mux_partition *partition, static char *omap_mux_options; -static int __init _omap_mux_init_gpio(struct omap_mux_partition *partition, - int gpio, int val) +static int _omap_mux_init_gpio(struct omap_mux_partition *partition, + int gpio, int val) { struct omap_mux_entry *e; struct omap_mux *gpio_mux = NULL; @@ -145,7 +145,7 @@ static int __init _omap_mux_init_gpio(struct omap_mux_partition *partition, return 0; } -int __init omap_mux_init_gpio(int gpio, int val) +int omap_mux_init_gpio(int gpio, int val) { struct omap_mux_partition *partition; int ret; @@ -159,9 +159,9 @@ int __init omap_mux_init_gpio(int gpio, int val) return -ENODEV; } -static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition, - const char *muxname, - struct omap_mux **found_mux) +static int _omap_mux_get_by_name(struct omap_mux_partition *partition, + const char *muxname, + struct omap_mux **found_mux) { struct omap_mux *mux = NULL; struct omap_mux_entry *e; @@ -240,7 +240,7 @@ omap_mux_get_by_name(const char *muxname, return -ENODEV; } -int __init omap_mux_init_signal(const char *muxname, int val) +int omap_mux_init_signal(const char *muxname, int val) { struct omap_mux_partition *partition = NULL; struct omap_mux *mux = NULL; @@ -1094,8 +1094,8 @@ static void omap_mux_init_package(struct omap_mux *superset, omap_mux_package_init_balls(package_balls, superset); } -static void omap_mux_init_signals(struct omap_mux_partition *partition, - struct omap_board_mux *board_mux) +static void __init omap_mux_init_signals(struct omap_mux_partition *partition, + struct omap_board_mux *board_mux) { omap_mux_set_cmdline_signals(); omap_mux_write_array(partition, board_mux); @@ -1109,8 +1109,8 @@ static void omap_mux_init_package(struct omap_mux *superset, { } -static void omap_mux_init_signals(struct omap_mux_partition *partition, - struct omap_board_mux *board_mux) +static void __init omap_mux_init_signals(struct omap_mux_partition *partition, + struct omap_board_mux *board_mux) { } diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S index b13ef7ef5ef..503ac777a2b 100644 --- a/arch/arm/mach-omap2/omap-headsmp.S +++ b/arch/arm/mach-omap2/omap-headsmp.S @@ -18,6 +18,7 @@ #include <linux/linkage.h> #include <linux/init.h> + __CPUINIT /* * OMAP4 specific entry point for secondary CPU to jump from ROM * code. This routine also provides a holding flag into which diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 5192cabb40e..eba6cd3816f 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1517,8 +1517,8 @@ static int _enable(struct omap_hwmod *oh) if (oh->_state != _HWMOD_STATE_INITIALIZED && oh->_state != _HWMOD_STATE_IDLE && oh->_state != _HWMOD_STATE_DISABLED) { - WARN(1, "omap_hwmod: %s: enabled state can only be entered " - "from initialized, idle, or disabled state\n", oh->name); + WARN(1, "omap_hwmod: %s: enabled state can only be entered from initialized, idle, or disabled state\n", + oh->name); return -EINVAL; } @@ -1600,8 +1600,8 @@ static int _idle(struct omap_hwmod *oh) pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { - WARN(1, "omap_hwmod: %s: idle state can only be entered from " - "enabled state\n", oh->name); + WARN(1, "omap_hwmod: %s: idle state can only be entered from enabled state\n", + oh->name); return -EINVAL; } @@ -1682,8 +1682,8 @@ static int _shutdown(struct omap_hwmod *oh) if (oh->_state != _HWMOD_STATE_IDLE && oh->_state != _HWMOD_STATE_ENABLED) { - WARN(1, "omap_hwmod: %s: disabled state can only be entered " - "from idle, or enabled state\n", oh->name); + WARN(1, "omap_hwmod: %s: disabled state can only be entered from idle, or enabled state\n", + oh->name); return -EINVAL; } @@ -2240,8 +2240,8 @@ void omap_hwmod_ocp_barrier(struct omap_hwmod *oh) BUG_ON(!oh); if (!oh->class->sysc || !oh->class->sysc->sysc_flags) { - WARN(1, "omap_device: %s: OCP barrier impossible due to " - "device configuration\n", oh->name); + WARN(1, "omap_device: %s: OCP barrier impossible due to device configuration\n", + oh->name); return; } diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c index 33dd655e6aa..a1d6154dc12 100644 --- a/arch/arm/mach-omap2/prm44xx.c +++ b/arch/arm/mach-omap2/prm44xx.c @@ -19,6 +19,7 @@ #include "common.h" #include <plat/cpu.h> +#include <plat/irqs.h> #include <plat/prcm.h> #include "vp.h" diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c index 247d89478f2..f590afc1f67 100644 --- a/arch/arm/mach-omap2/serial.c +++ b/arch/arm/mach-omap2/serial.c @@ -107,18 +107,18 @@ static void omap_uart_set_noidle(struct platform_device *pdev) omap_hwmod_set_slave_idlemode(od->hwmods[0], HWMOD_IDLEMODE_NO); } -static void omap_uart_set_forceidle(struct platform_device *pdev) +static void omap_uart_set_smartidle(struct platform_device *pdev) { struct omap_device *od = to_omap_device(pdev); - omap_hwmod_set_slave_idlemode(od->hwmods[0], HWMOD_IDLEMODE_FORCE); + omap_hwmod_set_slave_idlemode(od->hwmods[0], HWMOD_IDLEMODE_SMART); } #else static void omap_uart_enable_wakeup(struct platform_device *pdev, bool enable) {} static void omap_uart_set_noidle(struct platform_device *pdev) {} -static void omap_uart_set_forceidle(struct platform_device *pdev) {} +static void omap_uart_set_smartidle(struct platform_device *pdev) {} #endif /* CONFIG_PM */ #ifdef CONFIG_OMAP_MUX @@ -349,7 +349,7 @@ void __init omap_serial_init_port(struct omap_board_data *bdata, omap_up.uartclk = OMAP24XX_BASE_BAUD * 16; omap_up.flags = UPF_BOOT_AUTOCONF; omap_up.get_context_loss_count = omap_pm_get_dev_context_loss_count; - omap_up.set_forceidle = omap_uart_set_forceidle; + omap_up.set_forceidle = omap_uart_set_smartidle; omap_up.set_noidle = omap_uart_set_noidle; omap_up.enable_wakeup = omap_uart_enable_wakeup; omap_up.dma_rx_buf_size = info->dma_rx_buf_size; diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c index 031d116fbf1..175b7d86d86 100644 --- a/arch/arm/mach-omap2/vc.c +++ b/arch/arm/mach-omap2/vc.c @@ -247,7 +247,7 @@ static void __init omap4_vc_init_channel(struct voltagedomain *voltdm) * omap_vc_i2c_init - initialize I2C interface to PMIC * @voltdm: voltage domain containing VC data * - * Use PMIC supplied seetings for I2C high-speed mode and + * Use PMIC supplied settings for I2C high-speed mode and * master code (if set) and program the VC I2C configuration * register. * @@ -265,8 +265,8 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm) if (initialized) { if (voltdm->pmic->i2c_high_speed != i2c_high_speed) - pr_warn("%s: I2C config for all channels must match.", - __func__); + pr_warn("%s: I2C config for vdd_%s does not match other channels (%u).", + __func__, voltdm->name, i2c_high_speed); return; } @@ -292,9 +292,7 @@ void __init omap_vc_init_channel(struct voltagedomain *voltdm) u32 val; if (!voltdm->pmic || !voltdm->pmic->uv_to_vsel) { - pr_err("%s: PMIC info requried to configure vc for" - "vdd_%s not populated.Hence cannot initialize vc\n", - __func__, voltdm->name); + pr_err("%s: No PMIC info for vdd_%s\n", __func__, voltdm->name); return; } diff --git a/arch/arm/mach-omap2/vp.c b/arch/arm/mach-omap2/vp.c index 807391d84a9..0df88820978 100644 --- a/arch/arm/mach-omap2/vp.c +++ b/arch/arm/mach-omap2/vp.c @@ -41,6 +41,11 @@ void __init omap_vp_init(struct voltagedomain *voltdm) u32 val, sys_clk_rate, timeout, waittime; u32 vddmin, vddmax, vstepmin, vstepmax; + if (!voltdm->pmic || !voltdm->pmic->uv_to_vsel) { + pr_err("%s: No PMIC info for vdd_%s\n", __func__, voltdm->name); + return; + } + if (!voltdm->read || !voltdm->write) { pr_err("%s: No read/write API for accessing vdd_%s regs\n", __func__, voltdm->name); diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 07c4bc8ea0a..7a24d39661f 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -54,9 +54,15 @@ loop1: and r1, r1, #7 @ mask of the bits for current cache only cmp r1, #2 @ see what cache we have at this level blt skip @ skip if no cache, or just i-cache +#ifdef CONFIG_PREEMPT + save_and_disable_irqs r9 @ make cssr&csidr read atomic +#endif mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr isb @ isb to sych the new cssr&csidr mrc p15, 1, r1, c0, c0, 0 @ read the new csidr +#ifdef CONFIG_PREEMPT + restore_irqs_notrace r9 +#endif and r2, r1, #7 @ extract the length of the cache lines add r2, r2, #4 @ add 4 (line length offset) ldr r4, =0x3ff diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 2156e077859..1acf6502677 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -24,10 +24,6 @@ CONFIG_PPC_SPLPAR=y CONFIG_SCANLOG=m CONFIG_PPC_SMLPAR=y CONFIG_DTL=y -CONFIG_PPC_ISERIES=y -CONFIG_VIODASD=y -CONFIG_VIOCD=m -CONFIG_VIOTAPE=m CONFIG_PPC_MAPLE=y CONFIG_PPC_PASEMI=y CONFIG_PPC_PASEMI_IOMMU=y @@ -259,7 +255,6 @@ CONFIG_PASEMI_MAC=y CONFIG_MLX4_EN=m CONFIG_QLGE=m CONFIG_BE2NET=m -CONFIG_ISERIES_VETH=m CONFIG_PPP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 43268f15004..6d422979eba 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -142,6 +142,11 @@ static inline const char *eeh_pci_name(struct pci_dev *pdev) return pdev ? pci_name(pdev) : "<null>"; } +static inline const char *eeh_driver_name(struct pci_dev *pdev) +{ + return (pdev && pdev->driver) ? pdev->driver->name : "<null>"; +} + #endif /* CONFIG_EEH */ #else /* CONFIG_PCI */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 78a205162fd..84cc7840cd1 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -83,8 +83,18 @@ struct pt_regs { #ifndef __ASSEMBLY__ -#define instruction_pointer(regs) ((regs)->nip) -#define user_stack_pointer(regs) ((regs)->gpr[1]) +#define GET_IP(regs) ((regs)->nip) +#define GET_USP(regs) ((regs)->gpr[1]) +#define GET_FP(regs) (0) +#define SET_FP(regs, val) + +#ifdef CONFIG_SMP +extern unsigned long profile_pc(struct pt_regs *regs); +#define profile_pc profile_pc +#endif + +#include <asm-generic/ptrace.h> + #define kernel_stack_pointer(regs) ((regs)->gpr[1]) static inline int is_syscall_success(struct pt_regs *regs) { @@ -99,12 +109,6 @@ static inline long regs_return_value(struct pt_regs *regs) return -regs->gpr[3]; } -#ifdef CONFIG_SMP -extern unsigned long profile_pc(struct pt_regs *regs); -#else -#define profile_pc(regs) instruction_pointer(regs) -#endif - #ifdef __powerpc64__ #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1) #else diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index d4be7bb3dbd..3844ca7c509 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -775,7 +775,7 @@ program_check_common: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl .save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS + DISABLE_INTS bl .program_check_exception b .ret_from_except diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 701d4aceb4f..01e2877e8e0 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -118,10 +118,14 @@ static inline notrace void set_soft_enabled(unsigned long enable) static inline notrace void decrementer_check_overflow(void) { u64 now = get_tb_or_rtc(); - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb; + + preempt_disable(); + next_tb = &__get_cpu_var(decrementers_next_tb); if (now >= *next_tb) set_dec(1); + preempt_enable(); } notrace void arch_local_irq_restore(unsigned long en) diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 10a140f82cb..64483fde95c 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -865,6 +865,7 @@ static void power_pmu_start(struct perf_event *event, int ef_flags) { unsigned long flags; s64 left; + unsigned long val; if (!event->hw.idx || !event->hw.sample_period) return; @@ -880,7 +881,12 @@ static void power_pmu_start(struct perf_event *event, int ef_flags) event->hw.state = 0; left = local64_read(&event->hw.period_left); - write_pmc(event->hw.idx, left); + + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + + write_pmc(event->hw.idx, val); perf_event_update_userpage(event); perf_pmu_enable(event->pmu); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ebe5766781a..d817ab01848 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -566,12 +566,12 @@ static void show_instructions(struct pt_regs *regs) */ if (!__kernel_text_address(pc) || __get_user(instr, (unsigned int __user *)pc)) { - printk("XXXXXXXX "); + printk(KERN_CONT "XXXXXXXX "); } else { if (regs->nip == pc) - printk("<%08x> ", instr); + printk(KERN_CONT "<%08x> ", instr); else - printk("%08x ", instr); + printk(KERN_CONT "%08x ", instr); } pc += sizeof(int); diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 517b1d8f455..9f843cdfee9 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -716,7 +716,6 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w int cpu; slb_set_size(SLB_MIN_SIZE); - stop_topology_update(); printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id()); while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) && @@ -732,7 +731,6 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w rc = atomic_read(&data->error); atomic_set(&data->error, rc); - start_topology_update(); pSeries_coalesce_init(); if (wake_when_done) { @@ -846,6 +844,7 @@ int rtas_ibm_suspend_me(struct rtas_args *args) atomic_set(&data.error, 0); data.token = rtas_token("ibm,suspend-me"); data.complete = &done; + stop_topology_update(); /* Call function on all CPUs. One of us will make the * rtas call @@ -858,6 +857,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args) if (atomic_read(&data.error) != 0) printk(KERN_ERR "Error doing global join\n"); + start_topology_update(); + return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index a70bc1e385e..f92b9ef7340 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -52,32 +52,38 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) static unsigned int pnv_get_one_msi(struct pnv_phb *phb) { - unsigned int id; + unsigned long flags; + unsigned int id, rc; + + spin_lock_irqsave(&phb->lock, flags); - spin_lock(&phb->lock); id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next); if (id >= phb->msi_count && phb->msi_next) id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0); if (id >= phb->msi_count) { - spin_unlock(&phb->lock); - return 0; + rc = 0; + goto out; } __set_bit(id, phb->msi_map); - spin_unlock(&phb->lock); - return id + phb->msi_base; + rc = id + phb->msi_base; +out: + spin_unlock_irqrestore(&phb->lock, flags); + return rc; } static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq) { + unsigned long flags; unsigned int id; if (WARN_ON(hwirq < phb->msi_base || hwirq >= (phb->msi_base + phb->msi_count))) return; id = hwirq - phb->msi_base; - spin_lock(&phb->lock); + + spin_lock_irqsave(&phb->lock, flags); __clear_bit(id, phb->msi_map); - spin_unlock(&phb->lock); + spin_unlock_irqrestore(&phb->lock, flags); } static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 565869022e3..c0b40af4ce4 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -551,9 +551,9 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) printk (KERN_ERR "EEH: %d reads ignored for recovering device at " "location=%s driver=%s pci addr=%s\n", pdn->eeh_check_count, location, - dev->driver->name, eeh_pci_name(dev)); + eeh_driver_name(dev), eeh_pci_name(dev)); printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n", - dev->driver->name); + eeh_driver_name(dev)); dump_stack(); } goto dn_unlock; diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index b84a8b2238d..47226e04126 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -24,6 +24,7 @@ #include <asm/machdep.h> #include <asm/mmu.h> #include <asm/rtas.h> +#include <asm/topology.h> static u64 stream_id; static struct device suspend_dev; @@ -138,8 +139,11 @@ static ssize_t store_hibernate(struct device *dev, ssleep(1); } while (rc == -EAGAIN); - if (!rc) + if (!rc) { + stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); + start_topology_update(); + } stream_id = 0; diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c index 57687439254..97fe82ee863 100644 --- a/arch/powerpc/platforms/wsp/ics.c +++ b/arch/powerpc/platforms/wsp/ics.c @@ -346,7 +346,7 @@ static int wsp_chip_set_affinity(struct irq_data *d, * For the moment only implement delivery to all cpus or one cpu. * Get current irq_server for the given irq */ - ret = cache_hwirq_map(ics, d->irq, cpumask); + ret = cache_hwirq_map(ics, hw_irq, cpumask); if (ret == -1) { char cpulist[128]; cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c index e0262cd0e2d..d24b3acf858 100644 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ b/arch/powerpc/platforms/wsp/wsp_pci.c @@ -468,15 +468,15 @@ static void __init wsp_pcie_configure_hw(struct pci_controller *hose) #define DUMP_REG(x) \ pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x)) -#ifdef CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS - /* WSP DD1 has a bogus class code by default in the PCI-E - * root complex's built-in P2P bridge */ + /* + * Some WSP variants has a bogus class code by default in the PCI-E + * root complex's built-in P2P bridge + */ val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1); pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val); out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1, (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8)); pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1)); -#endif /* CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS */ #ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS /* XXX Disable TCE caching, it doesn't work on DD1 */ diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 30eb17ecad4..6073288fed2 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -385,26 +385,36 @@ static void __init setup_pci_cmd(struct pci_controller *hose) void fsl_pcibios_fixup_bus(struct pci_bus *bus) { struct pci_controller *hose = pci_bus_to_host(bus); - int i; - - if ((bus->parent == hose->bus) && - ((fsl_pcie_bus_fixup && - early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) || - (hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK))) - { - for (i = 0; i < 4; ++i) { + int i, is_pcie = 0, no_link; + + /* The root complex bridge comes up with bogus resources, + * we copy the PHB ones in. + * + * With the current generic PCI code, the PHB bus no longer + * has bus->resource[0..4] set, so things are a bit more + * tricky. + */ + + if (fsl_pcie_bus_fixup) + is_pcie = early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP); + no_link = !!(hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK); + + if (bus->parent == hose->bus && (is_pcie || no_link)) { + for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; ++i) { struct resource *res = bus->resource[i]; - struct resource *par = bus->parent->resource[i]; - if (res) { - res->start = 0; - res->end = 0; - res->flags = 0; - } - if (res && par) { - res->start = par->start; - res->end = par->end; - res->flags = par->flags; - } + struct resource *par; + + if (!res) + continue; + if (i == 0) + par = &hose->io_resource; + else if (i < 4) + par = &hose->mem_resources[i-1]; + else par = NULL; + + res->start = par ? par->start : 0; + res->end = par ? par->end : 0; + res->flags = par ? par->flags : 0; } } } diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 6919e936345..a850b4d8d14 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -29,8 +29,8 @@ extern unsigned int sig_xstate_size; extern void fpu_init(void); extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); -extern asmlinkage void math_state_restore(void); -extern void __math_state_restore(void); +extern void __math_state_restore(struct task_struct *); +extern void math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern user_regset_active_fn fpregs_active, xfpregs_active; @@ -212,19 +212,11 @@ static inline void fpu_fxsave(struct fpu *fpu) #endif /* CONFIG_X86_64 */ -/* We need a safe address that is cheap to find and that is already - in L1 during context switch. The best choices are unfortunately - different for UP and SMP */ -#ifdef CONFIG_SMP -#define safe_address (__per_cpu_offset[0]) -#else -#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER]) -#endif - /* - * These must be called with preempt disabled + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact. */ -static inline void fpu_save_init(struct fpu *fpu) +static inline int fpu_save_init(struct fpu *fpu) { if (use_xsave()) { fpu_xsave(fpu); @@ -233,33 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu) * xsave header may indicate the init state of the FP. */ if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return; + return 1; } else if (use_fxsr()) { fpu_fxsave(fpu); } else { asm volatile("fnsave %[fx]; fwait" : [fx] "=m" (fpu->state->fsave)); - return; + return 0; } - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) + /* + * If exceptions are pending, we need to clear them so + * that we don't randomly get exceptions later. + * + * FIXME! Is this perhaps only true for the old-style + * irq13 case? Maybe we could leave the x87 state + * intact otherwise? + */ + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { asm volatile("fnclex"); - - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. safe_address is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (safe_address)); + return 0; + } + return 1; } -static inline void __save_init_fpu(struct task_struct *tsk) +static inline int __save_init_fpu(struct task_struct *tsk) { - fpu_save_init(&tsk->thread.fpu); - task_thread_info(tsk)->status &= ~TS_USEDFPU; + return fpu_save_init(&tsk->thread.fpu); } static inline int fpu_fxrstor_checking(struct fpu *fpu) @@ -281,39 +273,185 @@ static inline int restore_fpu_checking(struct task_struct *tsk) } /* - * Signal frame handlers... + * Software FPU state helpers. Careful: these need to + * be preemption protection *and* they need to be + * properly paired with the CR0.TS changes! */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); +static inline int __thread_has_fpu(struct task_struct *tsk) +{ + return tsk->thread.has_fpu; +} -static inline void __unlazy_fpu(struct task_struct *tsk) +/* Must be paired with an 'stts' after! */ +static inline void __thread_clear_has_fpu(struct task_struct *tsk) { - if (task_thread_info(tsk)->status & TS_USEDFPU) { - __save_init_fpu(tsk); - stts(); - } else - tsk->fpu_counter = 0; + tsk->thread.has_fpu = 0; +} + +/* Must be paired with a 'clts' before! */ +static inline void __thread_set_has_fpu(struct task_struct *tsk) +{ + tsk->thread.has_fpu = 1; } +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void __thread_fpu_end(struct task_struct *tsk) +{ + __thread_clear_has_fpu(tsk); + stts(); +} + +static inline void __thread_fpu_begin(struct task_struct *tsk) +{ + clts(); + __thread_set_has_fpu(tsk); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +/* + * FIXME! We could do a totally lazy restore, but we need to + * add a per-cpu "this was the task that last touched the FPU + * on this CPU" variable, and the task needs to have a "I last + * touched the FPU on this CPU" and check them. + * + * We don't do that yet, so "fpu_lazy_restore()" always returns + * false, but some day.. + */ +#define fpu_lazy_restore(tsk) (0) +#define fpu_lazy_state_intact(tsk) do { } while (0) + +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new) +{ + fpu_switch_t fpu; + + fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + if (__thread_has_fpu(old)) { + if (__save_init_fpu(old)) + fpu_lazy_state_intact(old); + __thread_clear_has_fpu(old); + old->fpu_counter++; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + __thread_set_has_fpu(new); + prefetch(new->thread.fpu.state); + } else + stts(); + } else { + old->fpu_counter = 0; + if (fpu.preload) { + if (fpu_lazy_restore(new)) + fpu.preload = 0; + else + prefetch(new->thread.fpu.state); + __thread_fpu_begin(new); + } + } + return fpu; +} + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) +{ + if (fpu.preload) + __math_state_restore(new); +} + +/* + * Signal frame handlers... + */ +extern int save_i387_xstate(void __user *buf); +extern int restore_i387_xstate(void __user *buf); + static inline void __clear_fpu(struct task_struct *tsk) { - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (__thread_has_fpu(tsk)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + __thread_fpu_end(tsk); } } +/* + * Were we in an interrupt that interrupted kernel mode? + * + * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + */ +static inline bool interrupted_kernel_fpu_idle(void) +{ + return !__thread_has_fpu(current) && + (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static inline bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode_vm(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +static inline bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} + static inline void kernel_fpu_begin(void) { - struct thread_info *me = current_thread_info(); + struct task_struct *me = current; + + WARN_ON_ONCE(!irq_fpu_usable()); preempt_disable(); - if (me->status & TS_USEDFPU) - __save_init_fpu(me->task); - else + if (__thread_has_fpu(me)) { + __save_init_fpu(me); + __thread_clear_has_fpu(me); + /* We do 'stts()' in kernel_fpu_end() */ + } else clts(); } @@ -323,14 +461,6 @@ static inline void kernel_fpu_end(void) preempt_enable(); } -static inline bool irq_fpu_usable(void) -{ - struct pt_regs *regs; - - return !in_interrupt() || !(regs = get_irq_regs()) || \ - user_mode(regs) || (read_cr0() & X86_CR0_TS); -} - /* * Some instructions like VIA's padlock instructions generate a spurious * DNA fault but don't modify SSE registers. And these instructions @@ -363,20 +493,64 @@ static inline void irq_ts_restore(int TS_state) } /* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + * + * The actual user_fpu_begin/end() functions + * need to be preemption-safe, though. + * + * NOTE! user_fpu_end() must be used only after you + * have saved the FP state, and user_fpu_begin() must + * be used only immediately before restoring it. + * These functions do not do any save/restore on + * their own. + */ +static inline int user_has_fpu(void) +{ + return __thread_has_fpu(current); +} + +static inline void user_fpu_end(void) +{ + preempt_disable(); + __thread_fpu_end(current); + preempt_enable(); +} + +static inline void user_fpu_begin(void) +{ + preempt_disable(); + if (!user_has_fpu()) + __thread_fpu_begin(current); + preempt_enable(); +} + +/* * These disable preemption on their own and are safe */ static inline void save_init_fpu(struct task_struct *tsk) { + WARN_ON_ONCE(!__thread_has_fpu(tsk)); preempt_disable(); __save_init_fpu(tsk); - stts(); + __thread_fpu_end(tsk); preempt_enable(); } static inline void unlazy_fpu(struct task_struct *tsk) { preempt_disable(); - __unlazy_fpu(tsk); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; preempt_enable(); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index aa9088c2693..f7c89e231c6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -454,6 +454,7 @@ struct thread_struct { unsigned long trap_no; unsigned long error_code; /* floating point and extended processor state */ + unsigned long has_fpu; struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index bc817cd8b44..cfd8144d552 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -247,8 +247,6 @@ static inline struct thread_info *current_thread_info(void) * ever touches our thread-synchronous status, so we don't * have to worry about atomic accesses. */ -#define TS_USEDFPU 0x0001 /* FPU was used by this task - this quantum (SMP) */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #define TS_POLLING 0x0004 /* idle task polling need_resched, skip sending interrupt */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 73da6b64f5b..d6bd49faa40 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -439,7 +439,6 @@ void intel_pmu_pebs_enable(struct perf_event *event) hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; cpuc->pebs_enabled |= 1ULL << hwc->idx; - WARN_ON_ONCE(cpuc->enabled); if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) intel_pmu_lbr_enable(event); diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 3fab3de3ce9..47a7e63bfe5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -72,8 +72,6 @@ void intel_pmu_lbr_enable(struct perf_event *event) if (!x86_pmu.lbr_nr) return; - WARN_ON_ONCE(cpuc->enabled); - /* * Reset the LBR stack if we changed task context to * avoid data leaks. diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 485204f58cd..80bfe1ab003 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -299,22 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); - bool preload_fpu; + fpu_switch_t fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - __unlazy_fpu(prev_p); - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p); /* * Reload esp0. @@ -354,11 +343,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); - /* If we're going to preload the fpu context, make sure clts - is run while we're batching the cpu state updates. */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -368,15 +352,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); - if (preload_fpu) - __math_state_restore(); - /* * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) lazy_load_gs(next->gs); + switch_fpu_finish(next_p, fpu); + percpu_write(current_task, next_p); return prev_p; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9b9fe4a85c8..1fd94bc4279 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -386,18 +386,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); unsigned fsindex, gsindex; - bool preload_fpu; + fpu_switch_t fpu; - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p); /* * Reload esp0, LDT and the page table pointer: @@ -427,13 +418,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) load_TLS(next, cpu); - /* Must be after DS reload */ - __unlazy_fpu(prev_p); - - /* Make sure cpu is ready for new context */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -474,6 +458,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; + switch_fpu_finish(next_p, fpu); + /* * Switch the PDA and FPU contexts. */ @@ -492,13 +478,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); - /* - * Preload the FPU context, now that we've determined that the - * task is likely to be using it. - */ - if (preload_fpu) - __math_state_restore(); - return prev_p; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 482ec3af206..77da5b475ad 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -571,25 +571,34 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void) } /* - * __math_state_restore assumes that cr0.TS is already clear and the - * fpu state is all ready for use. Used during context switch. + * This gets called with the process already owning the + * FPU state, and with CR0.TS cleared. It just needs to + * restore the FPU register state. */ -void __math_state_restore(void) +void __math_state_restore(struct task_struct *tsk) { - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; + /* We need a safe address that is cheap to find and that is already + in L1. We've just brought in "tsk->thread.has_fpu", so use that */ +#define safe_address (tsk->thread.has_fpu) + + /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception + is pending. Clear the x87 state here by setting it to fixed + values. safe_address is a random variable that should be in L1 */ + alternative_input( + ASM_NOP8 ASM_NOP2, + "emms\n\t" /* clear stack tags */ + "fildl %P[addr]", /* set F?P to defined value */ + X86_FEATURE_FXSAVE_LEAK, + [addr] "m" (safe_address)); /* * Paranoid restore. send a SIGSEGV if we fail to restore the state. */ if (unlikely(restore_fpu_checking(tsk))) { - stts(); + __thread_fpu_end(tsk); force_sig(SIGSEGV, tsk); return; } - - thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ - tsk->fpu_counter++; } /* @@ -599,13 +608,12 @@ void __math_state_restore(void) * Careful.. There are problems with IBM-designed IRQ13 behaviour. * Don't touch unless you *really* know how it works. * - * Must be called with kernel preemption disabled (in this case, - * local interrupts are disabled at the call-site in entry.S). + * Must be called with kernel preemption disabled (eg with local + * local interrupts as in the case of do_device_not_available). */ -asmlinkage void math_state_restore(void) +void math_state_restore(void) { - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; + struct task_struct *tsk = current; if (!tsk_used_math(tsk)) { local_irq_enable(); @@ -622,9 +630,10 @@ asmlinkage void math_state_restore(void) local_irq_disable(); } - clts(); /* Allow maths ops (or we recurse) */ + __thread_fpu_begin(tsk); + __math_state_restore(tsk); - __math_state_restore(); + tsk->fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a3911343976..71109111411 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk) if (!fx) return; - BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU); + BUG_ON(__thread_has_fpu(tsk)); xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; @@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf) if (!used_math()) return 0; - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (user_has_fpu()) { if (use_xsave()) err = xsave_user(buf); else @@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf) if (err) return err; - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + user_fpu_end(); } else { sanitize_i387_state(tsk); if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, @@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf) return err; } - if (!(task_thread_info(current)->status & TS_USEDFPU)) { - clts(); - task_thread_info(current)->status |= TS_USEDFPU; - } + user_fpu_begin(); if (use_xsave()) err = restore_user_xstate(buf); else diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d29216c462b..3b4c8d8ad90 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1457,7 +1457,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (current_thread_info()->status & TS_USEDFPU) + if (__thread_has_fpu(current)) clts(); load_gdt(&__get_cpu_var(host_gdt)); } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 492ade8c978..d99346ea8fd 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -374,7 +374,7 @@ int __init pci_xen_init(void) int __init pci_xen_hvm_init(void) { - if (!xen_feature(XENFEAT_hvm_pirqs)) + if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs)) return 0; #ifdef CONFIG_ACPI diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 041d4fe9dfe..501d4e0244b 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -409,6 +409,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL); cpu_bringup(); + /* + * Balance out the preempt calls - as we are running in cpu_idle + * loop which has been called at bootup from cpu_bringup_and_idle. + * The cpucpu_bringup_and_idle called cpu_bringup which made a + * preempt_disable() So this preempt_enable will balance it out. + */ + preempt_enable(); } #else /* !CONFIG_HOTPLUG_CPU */ |