diff options
Diffstat (limited to 'arch/x86/kernel')
59 files changed, 1527 insertions, 1745 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 11817ff85399..82f2912155a5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,24 +17,6 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif -# -# vsyscalls (which work on the user stack) should have -# no stack-protector checks: -# -nostackp := $(call cc-option, -fno-stack-protector) -CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp) -CFLAGS_hpet.o := $(nostackp) -CFLAGS_vread_tsc_64.o := $(nostackp) -CFLAGS_paravirt.o := $(nostackp) -GCOV_PROFILE_vsyscall_64.o := n -GCOV_PROFILE_hpet.o := n -GCOV_PROFILE_tsc.o := n -GCOV_PROFILE_vread_tsc_64.o := n -GCOV_PROFILE_paravirt.o := n - -# vread_tsc_64 is hot and should be fully optimized: -CFLAGS_REMOVE_vread_tsc_64.o = -pg -fno-optimize-sibling-calls - obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o @@ -43,7 +25,8 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o -obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o vread_tsc_64.o +obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o +obj-$(CONFIG_X86_64) += vsyscall_emu_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 5812404a0d4c..f50e7fb2a201 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -149,6 +149,29 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); +/* + * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, + * which can obviate IPI to trigger checking of need_resched. + * We execute MONITOR against need_resched and enter optimized wait state + * through MWAIT. Whenever someone changes need_resched, we would be woken + * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. + */ +void mwait_idle_with_hints(unsigned long ax, unsigned long cx) +{ + if (!need_resched()) { + if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) + clflush((void *)¤t_thread_info()->flags); + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + smp_mb(); + if (!need_resched()) + __mwait(ax, cx); + } +} + void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a81f2d52f869..c63822816249 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -14,7 +14,6 @@ #include <asm/pgtable.h> #include <asm/mce.h> #include <asm/nmi.h> -#include <asm/vsyscall.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/io.h> @@ -250,7 +249,6 @@ static void __init_or_module add_nops(void *insns, unsigned int len) extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; -extern char __vsyscall_0; void *text_poke_early(void *addr, const void *opcode, size_t len); /* Replace instructions with better alternatives for this CPU type. @@ -263,6 +261,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, struct alt_instr *end) { struct alt_instr *a; + u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; DPRINTK("%s: alt table %p -> %p\n", __func__, start, end); @@ -276,25 +275,23 @@ void __init_or_module apply_alternatives(struct alt_instr *start, * order. */ for (a = start; a < end; a++) { - u8 *instr = a->instr; + instr = (u8 *)&a->instr_offset + a->instr_offset; + replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->replacementlen > a->instrlen); BUG_ON(a->instrlen > sizeof(insnbuf)); BUG_ON(a->cpuid >= NCAPINTS*32); if (!boot_cpu_has(a->cpuid)) continue; -#ifdef CONFIG_X86_64 - /* vsyscall code is not mapped yet. resolve it manually. */ - if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) { - instr = __va(instr - (u8*)VSYSCALL_START + (u8*)__pa_symbol(&__vsyscall_0)); - DPRINTK("%s: vsyscall fixup: %p => %p\n", - __func__, a->instr, instr); - } -#endif - memcpy(insnbuf, a->replacement, a->replacementlen); + + memcpy(insnbuf, replacement, a->replacementlen); + + /* 0xe8 is a relative jump; fix the offset. */ if (*insnbuf == 0xe8 && a->replacementlen == 5) - *(s32 *)(insnbuf + 1) += a->replacement - a->instr; + *(s32 *)(insnbuf + 1) += replacement - instr; + add_nops(insnbuf + a->replacementlen, a->instrlen - a->replacementlen); + text_poke_early(instr, insnbuf, a->instrlen); } } diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index b117efd24f71..8a439d364b94 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -30,7 +30,7 @@ #include <linux/syscore_ops.h> #include <linux/io.h> #include <linux/gfp.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/mtrr.h> #include <asm/pgtable.h> #include <asm/proto.h> diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 289e92862fd9..afdc3f756dea 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -27,15 +27,12 @@ * timer, but by default APB timer has higher rating than local APIC timers. */ -#include <linux/clocksource.h> -#include <linux/clockchips.h> #include <linux/delay.h> +#include <linux/dw_apb_timer.h> #include <linux/errno.h> #include <linux/init.h> -#include <linux/sysdev.h> #include <linux/slab.h> #include <linux/pm.h> -#include <linux/pci.h> #include <linux/sfi.h> #include <linux/interrupt.h> #include <linux/cpu.h> @@ -44,76 +41,48 @@ #include <asm/fixmap.h> #include <asm/apb_timer.h> #include <asm/mrst.h> +#include <asm/time.h> -#define APBT_MASK CLOCKSOURCE_MASK(32) -#define APBT_SHIFT 22 #define APBT_CLOCKEVENT_RATING 110 #define APBT_CLOCKSOURCE_RATING 250 -#define APBT_MIN_DELTA_USEC 200 -#define EVT_TO_APBT_DEV(evt) container_of(evt, struct apbt_dev, evt) #define APBT_CLOCKEVENT0_NUM (0) -#define APBT_CLOCKEVENT1_NUM (1) #define APBT_CLOCKSOURCE_NUM (2) -static unsigned long apbt_address; +static phys_addr_t apbt_address; static int apb_timer_block_enabled; static void __iomem *apbt_virt_address; -static int phy_cs_timer_id; /* * Common DW APB timer info */ -static uint64_t apbt_freq; - -static void apbt_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt); -static int apbt_next_event(unsigned long delta, - struct clock_event_device *evt); -static cycle_t apbt_read_clocksource(struct clocksource *cs); -static void apbt_restart_clocksource(struct clocksource *cs); +static unsigned long apbt_freq; struct apbt_dev { - struct clock_event_device evt; - unsigned int num; - int cpu; - unsigned int irq; - unsigned int tick; - unsigned int count; - unsigned int flags; - char name[10]; + struct dw_apb_clock_event_device *timer; + unsigned int num; + int cpu; + unsigned int irq; + char name[10]; }; -static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); +static struct dw_apb_clocksource *clocksource_apbt; -#ifdef CONFIG_SMP -static unsigned int apbt_num_timers_used; -static struct apbt_dev *apbt_devs; -#endif - -static inline unsigned long apbt_readl_reg(unsigned long a) +static inline void __iomem *adev_virt_addr(struct apbt_dev *adev) { - return readl(apbt_virt_address + a); + return apbt_virt_address + adev->num * APBTMRS_REG_SIZE; } -static inline void apbt_writel_reg(unsigned long d, unsigned long a) -{ - writel(d, apbt_virt_address + a); -} - -static inline unsigned long apbt_readl(int n, unsigned long a) -{ - return readl(apbt_virt_address + a + n * APBTMRS_REG_SIZE); -} +static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); -static inline void apbt_writel(int n, unsigned long d, unsigned long a) -{ - writel(d, apbt_virt_address + a + n * APBTMRS_REG_SIZE); -} +#ifdef CONFIG_SMP +static unsigned int apbt_num_timers_used; +#endif static inline void apbt_set_mapping(void) { struct sfi_timer_table_entry *mtmr; + int phy_cs_timer_id = 0; if (apbt_virt_address) { pr_debug("APBT base already mapped\n"); @@ -125,21 +94,18 @@ static inline void apbt_set_mapping(void) APBT_CLOCKEVENT0_NUM); return; } - apbt_address = (unsigned long)mtmr->phys_addr; + apbt_address = (phys_addr_t)mtmr->phys_addr; if (!apbt_address) { printk(KERN_WARNING "No timer base from SFI, use default\n"); apbt_address = APBT_DEFAULT_BASE; } apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE); - if (apbt_virt_address) { - pr_debug("Mapped APBT physical addr %p at virtual addr %p\n",\ - (void *)apbt_address, (void *)apbt_virt_address); - } else { - pr_debug("Failed mapping APBT phy address at %p\n",\ - (void *)apbt_address); + if (!apbt_virt_address) { + pr_debug("Failed mapping APBT phy address at %lu\n",\ + (unsigned long)apbt_address); goto panic_noapbt; } - apbt_freq = mtmr->freq_hz / USEC_PER_SEC; + apbt_freq = mtmr->freq_hz; sfi_free_mtmr(mtmr); /* Now figure out the physical timer id for clocksource device */ @@ -148,9 +114,14 @@ static inline void apbt_set_mapping(void) goto panic_noapbt; /* Now figure out the physical timer id */ - phy_cs_timer_id = (unsigned int)(mtmr->phys_addr & 0xff) - / APBTMRS_REG_SIZE; - pr_debug("Use timer %d for clocksource\n", phy_cs_timer_id); + pr_debug("Use timer %d for clocksource\n", + (int)(mtmr->phys_addr & 0xff) / APBTMRS_REG_SIZE); + phy_cs_timer_id = (unsigned int)(mtmr->phys_addr & 0xff) / + APBTMRS_REG_SIZE; + + clocksource_apbt = dw_apb_clocksource_init(APBT_CLOCKSOURCE_RATING, + "apbt0", apbt_virt_address + phy_cs_timer_id * + APBTMRS_REG_SIZE, apbt_freq); return; panic_noapbt: @@ -172,82 +143,6 @@ static inline int is_apbt_capable(void) return apbt_virt_address ? 1 : 0; } -static struct clocksource clocksource_apbt = { - .name = "apbt", - .rating = APBT_CLOCKSOURCE_RATING, - .read = apbt_read_clocksource, - .mask = APBT_MASK, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .resume = apbt_restart_clocksource, -}; - -/* boot APB clock event device */ -static struct clock_event_device apbt_clockevent = { - .name = "apbt0", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = apbt_set_mode, - .set_next_event = apbt_next_event, - .shift = APBT_SHIFT, - .irq = 0, - .rating = APBT_CLOCKEVENT_RATING, -}; - -/* - * start count down from 0xffff_ffff. this is done by toggling the enable bit - * then load initial load count to ~0. - */ -static void apbt_start_counter(int n) -{ - unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL); - - ctrl &= ~APBTMR_CONTROL_ENABLE; - apbt_writel(n, ctrl, APBTMR_N_CONTROL); - apbt_writel(n, ~0, APBTMR_N_LOAD_COUNT); - /* enable, mask interrupt */ - ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC; - ctrl |= (APBTMR_CONTROL_ENABLE | APBTMR_CONTROL_INT); - apbt_writel(n, ctrl, APBTMR_N_CONTROL); - /* read it once to get cached counter value initialized */ - apbt_read_clocksource(&clocksource_apbt); -} - -static irqreturn_t apbt_interrupt_handler(int irq, void *data) -{ - struct apbt_dev *dev = (struct apbt_dev *)data; - struct clock_event_device *aevt = &dev->evt; - - if (!aevt->event_handler) { - printk(KERN_INFO "Spurious APBT timer interrupt on %d\n", - dev->num); - return IRQ_NONE; - } - aevt->event_handler(aevt); - return IRQ_HANDLED; -} - -static void apbt_restart_clocksource(struct clocksource *cs) -{ - apbt_start_counter(phy_cs_timer_id); -} - -static void apbt_enable_int(int n) -{ - unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL); - /* clear pending intr */ - apbt_readl(n, APBTMR_N_EOI); - ctrl &= ~APBTMR_CONTROL_INT; - apbt_writel(n, ctrl, APBTMR_N_CONTROL); -} - -static void apbt_disable_int(int n) -{ - unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL); - - ctrl |= APBTMR_CONTROL_INT; - apbt_writel(n, ctrl, APBTMR_N_CONTROL); -} - - static int __init apbt_clockevent_register(void) { struct sfi_timer_table_entry *mtmr; @@ -260,45 +155,21 @@ static int __init apbt_clockevent_register(void) return -ENODEV; } - /* - * We need to calculate the scaled math multiplication factor for - * nanosecond to apbt tick conversion. - * mult = (nsec/cycle)*2^APBT_SHIFT - */ - apbt_clockevent.mult = div_sc((unsigned long) mtmr->freq_hz - , NSEC_PER_SEC, APBT_SHIFT); - - /* Calculate the min / max delta */ - apbt_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, - &apbt_clockevent); - apbt_clockevent.min_delta_ns = clockevent_delta2ns( - APBT_MIN_DELTA_USEC*apbt_freq, - &apbt_clockevent); - /* - * Start apbt with the boot cpu mask and make it - * global if not used for per cpu timer. - */ - apbt_clockevent.cpumask = cpumask_of(smp_processor_id()); adev->num = smp_processor_id(); - memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); + adev->timer = dw_apb_clockevent_init(smp_processor_id(), "apbt0", + mrst_timer_options == MRST_TIMER_LAPIC_APBT ? + APBT_CLOCKEVENT_RATING - 100 : APBT_CLOCKEVENT_RATING, + adev_virt_addr(adev), 0, apbt_freq); + /* Firmware does EOI handling for us. */ + adev->timer->eoi = NULL; if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { - adev->evt.rating = APBT_CLOCKEVENT_RATING - 100; - global_clock_event = &adev->evt; + global_clock_event = &adev->timer->ced; printk(KERN_DEBUG "%s clockevent registered as global\n", global_clock_event->name); } - if (request_irq(apbt_clockevent.irq, apbt_interrupt_handler, - IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING, - apbt_clockevent.name, adev)) { - printk(KERN_ERR "Failed request IRQ for APBT%d\n", - apbt_clockevent.irq); - } - - clockevents_register_device(&adev->evt); - /* Start APBT 0 interrupts */ - apbt_enable_int(APBT_CLOCKEVENT0_NUM); + dw_apb_clockevent_register(adev->timer); sfi_free_mtmr(mtmr); return 0; @@ -316,52 +187,34 @@ static void apbt_setup_irq(struct apbt_dev *adev) irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); /* APB timer irqs are set up as mp_irqs, timer is edge type */ __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge"); - - if (system_state == SYSTEM_BOOTING) { - if (request_irq(adev->irq, apbt_interrupt_handler, - IRQF_TIMER | IRQF_DISABLED | - IRQF_NOBALANCING, - adev->name, adev)) { - printk(KERN_ERR "Failed request IRQ for APBT%d\n", - adev->num); - } - } else - enable_irq(adev->irq); } /* Should be called with per cpu */ void apbt_setup_secondary_clock(void) { struct apbt_dev *adev; - struct clock_event_device *aevt; int cpu; /* Don't register boot CPU clockevent */ cpu = smp_processor_id(); if (!cpu) return; - /* - * We need to calculate the scaled math multiplication factor for - * nanosecond to apbt tick conversion. - * mult = (nsec/cycle)*2^APBT_SHIFT - */ - printk(KERN_INFO "Init per CPU clockevent %d\n", cpu); - adev = &per_cpu(cpu_apbt_dev, cpu); - aevt = &adev->evt; - memcpy(aevt, &apbt_clockevent, sizeof(*aevt)); - aevt->cpumask = cpumask_of(cpu); - aevt->name = adev->name; - aevt->mode = CLOCK_EVT_MODE_UNUSED; + adev = &__get_cpu_var(cpu_apbt_dev); + if (!adev->timer) { + adev->timer = dw_apb_clockevent_init(cpu, adev->name, + APBT_CLOCKEVENT_RATING, adev_virt_addr(adev), + adev->irq, apbt_freq); + adev->timer->eoi = NULL; + } else { + dw_apb_clockevent_resume(adev->timer); + } - printk(KERN_INFO "Registering CPU %d clockevent device %s, mask %08x\n", - cpu, aevt->name, *(u32 *)aevt->cpumask); + printk(KERN_INFO "Registering CPU %d clockevent device %s, cpu %08x\n", + cpu, adev->name, adev->cpu); apbt_setup_irq(adev); - - clockevents_register_device(aevt); - - apbt_enable_int(cpu); + dw_apb_clockevent_register(adev->timer); return; } @@ -384,13 +237,12 @@ static int apbt_cpuhp_notify(struct notifier_block *n, switch (action & 0xf) { case CPU_DEAD: - disable_irq(adev->irq); - apbt_disable_int(cpu); + dw_apb_clockevent_pause(adev->timer); if (system_state == SYSTEM_RUNNING) { pr_debug("skipping APBT CPU %lu offline\n", cpu); } else if (adev) { pr_debug("APBT clockevent for cpu %lu offline\n", cpu); - free_irq(adev->irq, adev); + dw_apb_clockevent_stop(adev->timer); } break; default: @@ -415,116 +267,16 @@ void apbt_setup_secondary_clock(void) {} #endif /* CONFIG_SMP */ -static void apbt_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) -{ - unsigned long ctrl; - uint64_t delta; - int timer_num; - struct apbt_dev *adev = EVT_TO_APBT_DEV(evt); - - BUG_ON(!apbt_virt_address); - - timer_num = adev->num; - pr_debug("%s CPU %d timer %d mode=%d\n", - __func__, first_cpu(*evt->cpumask), timer_num, mode); - - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * apbt_clockevent.mult; - delta >>= apbt_clockevent.shift; - ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL); - ctrl |= APBTMR_CONTROL_MODE_PERIODIC; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - /* - * DW APB p. 46, have to disable timer before load counter, - * may cause sync problem. - */ - ctrl &= ~APBTMR_CONTROL_ENABLE; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - udelay(1); - pr_debug("Setting clock period %d for HZ %d\n", (int)delta, HZ); - apbt_writel(timer_num, delta, APBTMR_N_LOAD_COUNT); - ctrl |= APBTMR_CONTROL_ENABLE; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - break; - /* APB timer does not have one-shot mode, use free running mode */ - case CLOCK_EVT_MODE_ONESHOT: - ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL); - /* - * set free running mode, this mode will let timer reload max - * timeout which will give time (3min on 25MHz clock) to rearm - * the next event, therefore emulate the one-shot mode. - */ - ctrl &= ~APBTMR_CONTROL_ENABLE; - ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC; - - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - /* write again to set free running mode */ - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - - /* - * DW APB p. 46, load counter with all 1s before starting free - * running mode. - */ - apbt_writel(timer_num, ~0, APBTMR_N_LOAD_COUNT); - ctrl &= ~APBTMR_CONTROL_INT; - ctrl |= APBTMR_CONTROL_ENABLE; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - break; - - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - apbt_disable_int(timer_num); - ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL); - ctrl &= ~APBTMR_CONTROL_ENABLE; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - break; - - case CLOCK_EVT_MODE_RESUME: - apbt_enable_int(timer_num); - break; - } -} - -static int apbt_next_event(unsigned long delta, - struct clock_event_device *evt) -{ - unsigned long ctrl; - int timer_num; - - struct apbt_dev *adev = EVT_TO_APBT_DEV(evt); - - timer_num = adev->num; - /* Disable timer */ - ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL); - ctrl &= ~APBTMR_CONTROL_ENABLE; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - /* write new count */ - apbt_writel(timer_num, delta, APBTMR_N_LOAD_COUNT); - ctrl |= APBTMR_CONTROL_ENABLE; - apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL); - return 0; -} - -static cycle_t apbt_read_clocksource(struct clocksource *cs) -{ - unsigned long current_count; - - current_count = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE); - return (cycle_t)~current_count; -} - static int apbt_clocksource_register(void) { u64 start, now; cycle_t t1; /* Start the counter, use timer 2 as source, timer 0/1 for event */ - apbt_start_counter(phy_cs_timer_id); + dw_apb_clocksource_start(clocksource_apbt); /* Verify whether apbt counter works */ - t1 = apbt_read_clocksource(&clocksource_apbt); + t1 = dw_apb_clocksource_read(clocksource_apbt); rdtscll(start); /* @@ -539,10 +291,10 @@ static int apbt_clocksource_register(void) } while ((now - start) < 200000UL); /* APBT is the only always on clocksource, it has to work! */ - if (t1 == apbt_read_clocksource(&clocksource_apbt)) + if (t1 == dw_apb_clocksource_read(clocksource_apbt)) panic("APBT counter not counting. APBT disabled\n"); - clocksource_register_khz(&clocksource_apbt, (u32)apbt_freq*1000); + dw_apb_clocksource_register(clocksource_apbt); return 0; } @@ -566,10 +318,7 @@ void __init apbt_time_init(void) if (apb_timer_block_enabled) return; apbt_set_mapping(); - if (apbt_virt_address) { - pr_debug("Found APBT version 0x%lx\n",\ - apbt_readl_reg(APBTMRS_COMP_VERSION)); - } else + if (!apbt_virt_address) goto out_noapbt; /* * Read the frequency and check for a sane value, for ESL model @@ -577,7 +326,7 @@ void __init apbt_time_init(void) */ if (apbt_freq < APBT_MIN_FREQ || apbt_freq > APBT_MAX_FREQ) { - pr_debug("APBT has invalid freq 0x%llx\n", apbt_freq); + pr_debug("APBT has invalid freq 0x%lx\n", apbt_freq); goto out_noapbt; } if (apbt_clocksource_register()) { @@ -603,30 +352,20 @@ void __init apbt_time_init(void) } else { percpu_timer = 0; apbt_num_timers_used = 1; - adev = &per_cpu(cpu_apbt_dev, 0); - adev->flags &= ~APBT_DEV_USED; } pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used); /* here we set up per CPU timer data structure */ - apbt_devs = kzalloc(sizeof(struct apbt_dev) * apbt_num_timers_used, - GFP_KERNEL); - if (!apbt_devs) { - printk(KERN_ERR "Failed to allocate APB timer devices\n"); - return; - } for (i = 0; i < apbt_num_timers_used; i++) { adev = &per_cpu(cpu_apbt_dev, i); adev->num = i; adev->cpu = i; p_mtmr = sfi_get_mtmr(i); - if (p_mtmr) { - adev->tick = p_mtmr->freq_hz; + if (p_mtmr) adev->irq = p_mtmr->irq; - } else + else printk(KERN_ERR "Failed to get timer for cpu %d\n", i); - adev->count = 0; - sprintf(adev->name, "apbt%d", i); + snprintf(adev->name, sizeof(adev->name) - 1, "apbt%d", i); } #endif @@ -638,17 +377,8 @@ out_noapbt: panic("failed to enable APB timer\n"); } -static inline void apbt_disable(int n) -{ - if (is_apbt_capable()) { - unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL); - ctrl &= ~APBTMR_CONTROL_ENABLE; - apbt_writel(n, ctrl, APBTMR_N_CONTROL); - } -} - /* called before apb_timer_enable, use early map */ -unsigned long apbt_quick_calibrate() +unsigned long apbt_quick_calibrate(void) { int i, scale; u64 old, new; @@ -657,31 +387,31 @@ unsigned long apbt_quick_calibrate() u32 loop, shift; apbt_set_mapping(); - apbt_start_counter(phy_cs_timer_id); + dw_apb_clocksource_start(clocksource_apbt); /* check if the timer can count down, otherwise return */ - old = apbt_read_clocksource(&clocksource_apbt); + old = dw_apb_clocksource_read(clocksource_apbt); i = 10000; while (--i) { - if (old != apbt_read_clocksource(&clocksource_apbt)) + if (old != dw_apb_clocksource_read(clocksource_apbt)) break; } if (!i) goto failed; /* count 16 ms */ - loop = (apbt_freq * 1000) << 4; + loop = (apbt_freq / 1000) << 4; /* restart the timer to ensure it won't get to 0 in the calibration */ - apbt_start_counter(phy_cs_timer_id); + dw_apb_clocksource_start(clocksource_apbt); - old = apbt_read_clocksource(&clocksource_apbt); + old = dw_apb_clocksource_read(clocksource_apbt); old += loop; t1 = __native_read_tsc(); do { - new = apbt_read_clocksource(&clocksource_apbt); + new = dw_apb_clocksource_read(clocksource_apbt); } while (new < old); t2 = __native_read_tsc(); @@ -693,7 +423,7 @@ unsigned long apbt_quick_calibrate() return 0; } scale = (int)div_u64((t2 - t1), loop >> shift); - khz = (scale * apbt_freq * 1000) >> shift; + khz = (scale * (apbt_freq / 1000)) >> shift; printk(KERN_INFO "TSC freq calculated by APB timer is %lu khz\n", khz); return khz; failed: diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b9338b8cf420..52fa56399a50 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -27,6 +27,7 @@ #include <linux/syscore_ops.h> #include <linux/delay.h> #include <linux/timex.h> +#include <linux/i8253.h> #include <linux/dmar.h> #include <linux/init.h> #include <linux/cpu.h> @@ -37,9 +38,8 @@ #include <asm/perf_event.h> #include <asm/x86_init.h> #include <asm/pgalloc.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/mpspec.h> -#include <asm/i8253.h> #include <asm/i8259.h> #include <asm/proto.h> #include <asm/apic.h> @@ -48,6 +48,7 @@ #include <asm/hpet.h> #include <asm/idle.h> #include <asm/mtrr.h> +#include <asm/time.h> #include <asm/smp.h> #include <asm/mce.h> #include <asm/tsc.h> @@ -1429,7 +1430,7 @@ void enable_x2apic(void) rdmsr(MSR_IA32_APICBASE, msr, msr2); if (!(msr & X2APIC_ENABLE)) { printk_once(KERN_INFO "Enabling x2apic\n"); - wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0); + wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, msr2); } } #endif /* CONFIG_X86_X2APIC */ @@ -1943,10 +1944,28 @@ void disconnect_bsp_APIC(int virt_wire_setup) void __cpuinit generic_processor_info(int apicid, int version) { - int cpu; + int cpu, max = nr_cpu_ids; + bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, + phys_cpu_present_map); + + /* + * If boot cpu has not been detected yet, then only allow upto + * nr_cpu_ids - 1 processors and keep one slot free for boot cpu + */ + if (!boot_cpu_detected && num_processors >= nr_cpu_ids - 1 && + apicid != boot_cpu_physical_apicid) { + int thiscpu = max + disabled_cpus - 1; + + pr_warning( + "ACPI: NR_CPUS/possible_cpus limit of %i almost" + " reached. Keeping one slot for boot cpu." + " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); + + disabled_cpus++; + return; + } if (num_processors >= nr_cpu_ids) { - int max = nr_cpu_ids; int thiscpu = max + disabled_cpus; pr_warning( diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 9536b3fe43f8..5d513bc47b6b 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -48,7 +48,7 @@ #include <linux/io.h> #include <asm/apicdef.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/fixmap.h> #include <asm/mpspec.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e5293394b548..8eb863e27ea6 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1295,6 +1295,16 @@ static int setup_ioapic_entry(int apic_id, int irq, * irq handler will do the explicit EOI to the io-apic. */ ir_entry->vector = pin; + + apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: " + "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d " + "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X " + "Avail:%X Vector:%02X Dest:%08X " + "SID:%04X SQ:%X SVT:%X)\n", + apic_id, irte.present, irte.fpd, irte.dst_mode, + irte.redir_hint, irte.trigger_mode, irte.dlvry_mode, + irte.avail, irte.vector, irte.dest_id, + irte.sid, irte.sq, irte.svt); } else { entry->delivery_mode = apic->irq_delivery_mode; entry->dest_mode = apic->irq_dest_mode; @@ -1337,9 +1347,9 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq, apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " - "IRQ %d Mode:%i Active:%i)\n", + "IRQ %d Mode:%i Active:%i Dest:%d)\n", apic_id, mpc_ioapic_id(apic_id), pin, cfg->vector, - irq, trigger, polarity); + irq, trigger, polarity, dest); if (setup_ioapic_entry(mpc_ioapic_id(apic_id), irq, &entry, @@ -1522,10 +1532,12 @@ __apicdebuginit(void) print_IO_APIC(void) printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS); printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)®_01); - printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries); + printk(KERN_DEBUG "....... : max redirection entries: %02X\n", + reg_01.bits.entries); printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); - printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version); + printk(KERN_DEBUG "....... : IO APIC version: %02X\n", + reg_01.bits.version); /* * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02, @@ -1550,31 +1562,60 @@ __apicdebuginit(void) print_IO_APIC(void) printk(KERN_DEBUG ".... IRQ redirection table:\n"); - printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" - " Stat Dmod Deli Vect:\n"); + if (intr_remapping_enabled) { + printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR" + " Pol Stat Indx2 Zero Vect:\n"); + } else { + printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" + " Stat Dmod Deli Vect:\n"); + } for (i = 0; i <= reg_01.bits.entries; i++) { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(apic, i); - - printk(KERN_DEBUG " %02x %03X ", - i, - entry.dest - ); + if (intr_remapping_enabled) { + struct IO_APIC_route_entry entry; + struct IR_IO_APIC_route_entry *ir_entry; + + entry = ioapic_read_entry(apic, i); + ir_entry = (struct IR_IO_APIC_route_entry *) &entry; + printk(KERN_DEBUG " %02x %04X ", + i, + ir_entry->index + ); + printk("%1d %1d %1d %1d %1d " + "%1d %1d %X %02X\n", + ir_entry->format, + ir_entry->mask, + ir_entry->trigger, + ir_entry->irr, + ir_entry->polarity, + ir_entry->delivery_status, + ir_entry->index2, + ir_entry->zero, + ir_entry->vector + ); + } else { + struct IO_APIC_route_entry entry; - printk("%1d %1d %1d %1d %1d %1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); + entry = ioapic_read_entry(apic, i); + printk(KERN_DEBUG " %02x %02X ", + i, + entry.dest + ); + printk("%1d %1d %1d %1d %1d " + "%1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector + ); + } } } + printk(KERN_DEBUG "IRQ to pin mappings:\n"); for_each_active_irq(irq) { struct irq_pin_list *entry; @@ -1792,7 +1833,7 @@ __apicdebuginit(int) print_ICs(void) return 0; } -fs_initcall(print_ICs); +late_initcall(print_ICs); /* Where if anywhere is the i8259 connect in external int mode */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index adc66c3a1fef..34b18594e724 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -207,7 +207,6 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); - mdelay(10); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 965a7666c283..0371c484bb8a 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -229,11 +229,11 @@ #include <linux/jiffies.h> #include <linux/acpi.h> #include <linux/syscore_ops.h> +#include <linux/i8253.h> #include <asm/system.h> #include <asm/uaccess.h> #include <asm/desc.h> -#include <asm/i8253.h> #include <asm/olpc.h> #include <asm/paravirt.h> #include <asm/reboot.h> @@ -1220,11 +1220,11 @@ static void reinit_timer(void) raw_spin_lock_irqsave(&i8253_lock, flags); /* set the clock to HZ */ - outb_pit(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */ + outb_p(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */ udelay(10); - outb_pit(LATCH & 0xff, PIT_CH0); /* LSB */ + outb_p(LATCH & 0xff, PIT_CH0); /* LSB */ udelay(10); - outb_pit(LATCH >> 8, PIT_CH0); /* MSB */ + outb_p(LATCH >> 8, PIT_CH0); /* MSB */ udelay(10); raw_spin_unlock_irqrestore(&i8253_lock, flags); #endif diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 6042981d0309..1044fd787db8 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -28,6 +28,11 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +ifdef CONFIG_PERF_EVENTS +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +endif + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 525514cf33c3..46674fbb62ba 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -62,6 +62,8 @@ static void __init check_fpu(void) return; } + kernel_fpu_begin(); + /* * trap_init() enabled FXSR and company _before_ testing for FP * problems here. @@ -80,6 +82,8 @@ static void __init check_fpu(void) : "=m" (*&fdiv_bug) : "m" (*&x), "m" (*&y)); + kernel_fpu_end(); + boot_cpu_data.fdiv_bug = fdiv_bug; if (boot_cpu_data.fdiv_bug) printk(KERN_WARNING "Hmm, FPU with FDIV bug.\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 22a073d7fbff..62184390a601 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -21,7 +21,7 @@ #include <linux/topology.h> #include <linux/cpumask.h> #include <asm/pgtable.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/proto.h> #include <asm/setup.h> #include <asm/apic.h> diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 8095f8611f8a..755f64fb0743 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -32,11 +32,11 @@ */ static const __initconst struct hypervisor_x86 * const hypervisors[] = { - &x86_hyper_vmware, - &x86_hyper_ms_hyperv, #ifdef CONFIG_XEN_PVHVM &x86_hyper_xen_hvm, #endif + &x86_hyper_vmware, + &x86_hyper_ms_hyperv, }; const struct hypervisor_x86 *x86_hyper; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1edf5ba4fb2b..ed6086eedf1d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -456,6 +456,24 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_VMX)) detect_vmx_virtcap(c); + + /* + * Initialize MSR_IA32_ENERGY_PERF_BIAS if BIOS did not. + * x86_energy_perf_policy(8) is available to change it at run-time + */ + if (cpu_has(c, X86_FEATURE_EPB)) { + u64 epb; + + rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); + if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) { + printk_once(KERN_WARNING "ENERGY_PERF_BIAS:" + " Set to 'normal', was 'performance'\n" + "ENERGY_PERF_BIAS: View and update with" + " x86_energy_perf_policy(8)\n"); + epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; + wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); + } + } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 1e8d66c1336a..7395d5f4272d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -43,61 +43,105 @@ static struct severity { unsigned char covered; char *msg; } severities[] = { -#define KERNEL .context = IN_KERNEL -#define USER .context = IN_USER -#define SER .ser = SER_REQUIRED -#define NOSER .ser = NO_SER -#define SEV(s) .sev = MCE_ ## s ## _SEVERITY -#define BITCLR(x, s, m, r...) { .mask = x, .result = 0, SEV(s), .msg = m, ## r } -#define BITSET(x, s, m, r...) { .mask = x, .result = x, SEV(s), .msg = m, ## r } -#define MCGMASK(x, res, s, m, r...) \ - { .mcgmask = x, .mcgres = res, SEV(s), .msg = m, ## r } -#define MASK(x, y, s, m, r...) \ - { .mask = x, .result = y, SEV(s), .msg = m, ## r } +#define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c } +#define KERNEL .context = IN_KERNEL +#define USER .context = IN_USER +#define SER .ser = SER_REQUIRED +#define NOSER .ser = NO_SER +#define BITCLR(x) .mask = x, .result = 0 +#define BITSET(x) .mask = x, .result = x +#define MCGMASK(x, y) .mcgmask = x, .mcgres = y +#define MASK(x, y) .mask = x, .result = y #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) #define MCACOD 0xffff - BITCLR(MCI_STATUS_VAL, NO, "Invalid"), - BITCLR(MCI_STATUS_EN, NO, "Not enabled"), - BITSET(MCI_STATUS_PCC, PANIC, "Processor context corrupt"), + MCESEV( + NO, "Invalid", + BITCLR(MCI_STATUS_VAL) + ), + MCESEV( + NO, "Not enabled", + BITCLR(MCI_STATUS_EN) + ), + MCESEV( + PANIC, "Processor context corrupt", + BITSET(MCI_STATUS_PCC) + ), /* When MCIP is not set something is very confused */ - MCGMASK(MCG_STATUS_MCIP, 0, PANIC, "MCIP not set in MCA handler"), + MCESEV( + PANIC, "MCIP not set in MCA handler", + MCGMASK(MCG_STATUS_MCIP, 0) + ), /* Neither return not error IP -- no chance to recover -> PANIC */ - MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0, PANIC, - "Neither restart nor error IP"), - MCGMASK(MCG_STATUS_RIPV, 0, PANIC, "In kernel and no restart IP", - KERNEL), - BITCLR(MCI_STATUS_UC, KEEP, "Corrected error", NOSER), - MASK(MCI_STATUS_OVER|MCI_STATUS_UC|MCI_STATUS_EN, MCI_STATUS_UC, SOME, - "Spurious not enabled", SER), + MCESEV( + PANIC, "Neither restart nor error IP", + MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) + ), + MCESEV( + PANIC, "In kernel and no restart IP", + KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( + KEEP, "Corrected error", + NOSER, BITCLR(MCI_STATUS_UC) + ), /* ignore OVER for UCNA */ - MASK(MCI_UC_SAR, MCI_STATUS_UC, KEEP, - "Uncorrected no action required", SER), - MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_UC|MCI_STATUS_AR, PANIC, - "Illegal combination (UCNA with AR=1)", SER), - MASK(MCI_STATUS_S, 0, KEEP, "Non signalled machine check", SER), + MCESEV( + KEEP, "Uncorrected no action required", + SER, MASK(MCI_UC_SAR, MCI_STATUS_UC) + ), + MCESEV( + PANIC, "Illegal combination (UCNA with AR=1)", + SER, + MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_UC|MCI_STATUS_AR) + ), + MCESEV( + KEEP, "Non signalled machine check", + SER, BITCLR(MCI_STATUS_S) + ), /* AR add known MCACODs here */ - MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_OVER|MCI_UC_SAR, PANIC, - "Action required with lost events", SER), - MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_SAR, PANIC, - "Action required; unknown MCACOD", SER), + MCESEV( + PANIC, "Action required with lost events", + SER, BITSET(MCI_STATUS_OVER|MCI_UC_SAR) + ), + MCESEV( + PANIC, "Action required: unknown MCACOD", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR) + ), /* known AO MCACODs: */ - MASK(MCI_UC_SAR|MCI_STATUS_OVER|0xfff0, MCI_UC_S|0xc0, AO, - "Action optional: memory scrubbing error", SER), - MASK(MCI_UC_SAR|MCI_STATUS_OVER|MCACOD, MCI_UC_S|0x17a, AO, - "Action optional: last level cache writeback error", SER), - - MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S, SOME, - "Action optional unknown MCACOD", SER), - MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S|MCI_STATUS_OVER, SOME, - "Action optional with lost events", SER), - BITSET(MCI_STATUS_UC|MCI_STATUS_OVER, PANIC, "Overflowed uncorrected"), - BITSET(MCI_STATUS_UC, UC, "Uncorrected"), - BITSET(0, SOME, "No match") /* always matches. keep at end */ + MCESEV( + AO, "Action optional: memory scrubbing error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|0xfff0, MCI_UC_S|0x00c0) + ), + MCESEV( + AO, "Action optional: last level cache writeback error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|0x017a) + ), + MCESEV( + SOME, "Action optional: unknown MCACOD", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S) + ), + MCESEV( + SOME, "Action optional with lost events", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_OVER|MCI_UC_S) + ), + + MCESEV( + PANIC, "Overflowed uncorrected", + BITSET(MCI_STATUS_OVER|MCI_STATUS_UC) + ), + MCESEV( + UC, "Uncorrected", + BITSET(MCI_STATUS_UC) + ), + MCESEV( + SOME, "No match", + BITSET(0) + ) /* always matches. keep at end */ }; /* @@ -112,15 +156,15 @@ static int error_context(struct mce *m) return IN_KERNEL; } -int mce_severity(struct mce *a, int tolerant, char **msg) +int mce_severity(struct mce *m, int tolerant, char **msg) { - enum context ctx = error_context(a); + enum context ctx = error_context(m); struct severity *s; for (s = severities;; s++) { - if ((a->status & s->mask) != s->result) + if ((m->status & s->mask) != s->result) continue; - if ((a->mcgstatus & s->mcgmask) != s->mcgres) + if ((m->mcgstatus & s->mcgmask) != s->mcgres) continue; if (s->ser == SER_REQUIRED && !mce_ser) continue; @@ -197,15 +241,15 @@ static const struct file_operations severities_coverage_fops = { static int __init severities_debugfs_init(void) { - struct dentry *dmce = NULL, *fseverities_coverage = NULL; + struct dentry *dmce, *fsev; dmce = mce_get_debugfs_dir(); - if (dmce == NULL) + if (!dmce) goto err_out; - fseverities_coverage = debugfs_create_file("severities-coverage", - 0444, dmce, NULL, - &severities_coverage_fops); - if (fseverities_coverage == NULL) + + fsev = debugfs_create_file("severities-coverage", 0444, dmce, NULL, + &severities_coverage_fops); + if (!fsev) goto err_out; return 0; @@ -214,4 +258,4 @@ err_out: return -ENOMEM; } late_initcall(severities_debugfs_init); -#endif +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index ff1ae9b6464d..08363b042122 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -10,7 +10,6 @@ #include <linux/thread_info.h> #include <linux/capability.h> #include <linux/miscdevice.h> -#include <linux/interrupt.h> #include <linux/ratelimit.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> @@ -38,23 +37,20 @@ #include <linux/mm.h> #include <linux/debugfs.h> #include <linux/edac_mce.h> +#include <linux/irq_work.h> #include <asm/processor.h> -#include <asm/hw_irq.h> -#include <asm/apic.h> -#include <asm/idle.h> -#include <asm/ipi.h> #include <asm/mce.h> #include <asm/msr.h> #include "mce-internal.h" -static DEFINE_MUTEX(mce_read_mutex); +static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ rcu_dereference_index_check((p), \ rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_read_mutex)) + lockdep_is_held(&mce_chrdev_read_mutex)) #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -94,7 +90,8 @@ static unsigned long mce_need_notify; static char mce_helper[128]; static char *mce_helper_argv[2] = { mce_helper, NULL }; -static DECLARE_WAIT_QUEUE_HEAD(mce_wait); +static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); + static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; @@ -373,6 +370,31 @@ static void mce_wrmsrl(u32 msr, u64 v) } /* + * Collect all global (w.r.t. this processor) status about this machine + * check into our "mce" struct so that we can use it later to assess + * the severity of the problem as we read per-bank specific details. + */ +static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) +{ + mce_setup(m); + + m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (regs) { + /* + * Get the address of the instruction at the time of + * the machine check error. + */ + if (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) { + m->ip = regs->ip; + m->cs = regs->cs; + } + /* Use accurate RIP reporting if available. */ + if (rip_msr) + m->ip = mce_rdmsrl(rip_msr); + } +} + +/* * Simple lockless ring to communicate PFNs from the exception handler with the * process context work function. This is vastly simplified because there's * only a single reader and a single writer. @@ -443,40 +465,13 @@ static void mce_schedule_work(void) } } -/* - * Get the address of the instruction at the time of the machine check - * error. - */ -static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) -{ - - if (regs && (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV))) { - m->ip = regs->ip; - m->cs = regs->cs; - } else { - m->ip = 0; - m->cs = 0; - } - if (rip_msr) - m->ip = mce_rdmsrl(rip_msr); -} +DEFINE_PER_CPU(struct irq_work, mce_irq_work); -#ifdef CONFIG_X86_LOCAL_APIC -/* - * Called after interrupts have been reenabled again - * when a MCE happened during an interrupts off region - * in the kernel. - */ -asmlinkage void smp_mce_self_interrupt(struct pt_regs *regs) +static void mce_irq_work_cb(struct irq_work *entry) { - ack_APIC_irq(); - exit_idle(); - irq_enter(); mce_notify_irq(); mce_schedule_work(); - irq_exit(); } -#endif static void mce_report_event(struct pt_regs *regs) { @@ -492,29 +487,7 @@ static void mce_report_event(struct pt_regs *regs) return; } -#ifdef CONFIG_X86_LOCAL_APIC - /* - * Without APIC do not notify. The event will be picked - * up eventually. - */ - if (!cpu_has_apic) - return; - - /* - * When interrupts are disabled we cannot use - * kernel services safely. Trigger an self interrupt - * through the APIC to instead do the notification - * after interrupts are reenabled again. - */ - apic->send_IPI_self(MCE_SELF_VECTOR); - - /* - * Wait for idle afterwards again so that we don't leave the - * APIC in a non idle state because the normal APIC writes - * cannot exclude us. - */ - apic_wait_icr_idle(); -#endif + irq_work_queue(&__get_cpu_var(mce_irq_work)); } DEFINE_PER_CPU(unsigned, mce_poll_count); @@ -541,9 +514,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) percpu_inc(mce_poll_count); - mce_setup(&m); + mce_gather_info(&m, NULL); - m.mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); for (i = 0; i < banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) continue; @@ -879,9 +851,9 @@ static int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) return 0; - if ((m->misc & 0x3f) > PAGE_SHIFT) + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) return 0; - if (((m->misc >> 6) & 7) != MCM_ADDR_PHYS) + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) return 0; return 1; } @@ -942,9 +914,8 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (!banks) goto out; - mce_setup(&m); + mce_gather_info(&m, regs); - m.mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); final = &__get_cpu_var(mces_seen); *final = m; @@ -1028,7 +999,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) mce_ring_add(m.addr >> PAGE_SHIFT); - mce_get_rip(&m, regs); mce_log(&m); if (severity > worst) { @@ -1190,7 +1160,8 @@ int mce_notify_irq(void) clear_thread_flag(TIF_MCE_NOTIFY); if (test_and_clear_bit(0, &mce_need_notify)) { - wake_up_interruptible(&mce_wait); + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); /* * There is no risk of missing notifications because @@ -1363,18 +1334,23 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) return 0; } -static void __cpuinit __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) +static int __cpuinit __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) { if (c->x86 != 5) - return; + return 0; + switch (c->x86_vendor) { case X86_VENDOR_INTEL: intel_p5_mcheck_init(c); + return 1; break; case X86_VENDOR_CENTAUR: winchip_mcheck_init(c); + return 1; break; } + + return 0; } static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) @@ -1428,7 +1404,8 @@ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) if (mce_disabled) return; - __mcheck_cpu_ancient_init(c); + if (__mcheck_cpu_ancient_init(c)) + return; if (!mce_available(c)) return; @@ -1444,44 +1421,45 @@ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_timer(); INIT_WORK(&__get_cpu_var(mce_work), mce_process_work); - + init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb); } /* - * Character device to read and clear the MCE log. + * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log. */ -static DEFINE_SPINLOCK(mce_state_lock); -static int open_count; /* #times opened */ -static int open_exclu; /* already open exclusive? */ +static DEFINE_SPINLOCK(mce_chrdev_state_lock); +static int mce_chrdev_open_count; /* #times opened */ +static int mce_chrdev_open_exclu; /* already open exclusive? */ -static int mce_open(struct inode *inode, struct file *file) +static int mce_chrdev_open(struct inode *inode, struct file *file) { - spin_lock(&mce_state_lock); + spin_lock(&mce_chrdev_state_lock); - if (open_exclu || (open_count && (file->f_flags & O_EXCL))) { - spin_unlock(&mce_state_lock); + if (mce_chrdev_open_exclu || + (mce_chrdev_open_count && (file->f_flags & O_EXCL))) { + spin_unlock(&mce_chrdev_state_lock); return -EBUSY; } if (file->f_flags & O_EXCL) - open_exclu = 1; - open_count++; + mce_chrdev_open_exclu = 1; + mce_chrdev_open_count++; - spin_unlock(&mce_state_lock); + spin_unlock(&mce_chrdev_state_lock); return nonseekable_open(inode, file); } -static int mce_release(struct inode *inode, struct file *file) +static int mce_chrdev_release(struct inode *inode, struct file *file) { - spin_lock(&mce_state_lock); + spin_lock(&mce_chrdev_state_lock); - open_count--; - open_exclu = 0; + mce_chrdev_open_count--; + mce_chrdev_open_exclu = 0; - spin_unlock(&mce_state_lock); + spin_unlock(&mce_chrdev_state_lock); return 0; } @@ -1530,8 +1508,8 @@ static int __mce_read_apei(char __user **ubuf, size_t usize) return 0; } -static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, - loff_t *off) +static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, + size_t usize, loff_t *off) { char __user *buf = ubuf; unsigned long *cpu_tsc; @@ -1542,7 +1520,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, if (!cpu_tsc) return -ENOMEM; - mutex_lock(&mce_read_mutex); + mutex_lock(&mce_chrdev_read_mutex); if (!mce_apei_read_done) { err = __mce_read_apei(&buf, usize); @@ -1562,19 +1540,18 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, do { for (i = prev; i < next; i++) { unsigned long start = jiffies; + struct mce *m = &mcelog.entry[i]; - while (!mcelog.entry[i].finished) { + while (!m->finished) { if (time_after_eq(jiffies, start + 2)) { - memset(mcelog.entry + i, 0, - sizeof(struct mce)); + memset(m, 0, sizeof(*m)); goto timeout; } cpu_relax(); } smp_rmb(); - err |= copy_to_user(buf, mcelog.entry + i, - sizeof(struct mce)); - buf += sizeof(struct mce); + err |= copy_to_user(buf, m, sizeof(*m)); + buf += sizeof(*m); timeout: ; } @@ -1594,13 +1571,13 @@ timeout: on_each_cpu(collect_tscs, cpu_tsc, 1); for (i = next; i < MCE_LOG_LEN; i++) { - if (mcelog.entry[i].finished && - mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) { - err |= copy_to_user(buf, mcelog.entry+i, - sizeof(struct mce)); + struct mce *m = &mcelog.entry[i]; + + if (m->finished && m->tsc < cpu_tsc[m->cpu]) { + err |= copy_to_user(buf, m, sizeof(*m)); smp_rmb(); - buf += sizeof(struct mce); - memset(&mcelog.entry[i], 0, sizeof(struct mce)); + buf += sizeof(*m); + memset(m, 0, sizeof(*m)); } } @@ -1608,15 +1585,15 @@ timeout: err = -EFAULT; out: - mutex_unlock(&mce_read_mutex); + mutex_unlock(&mce_chrdev_read_mutex); kfree(cpu_tsc); return err ? err : buf - ubuf; } -static unsigned int mce_poll(struct file *file, poll_table *wait) +static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) { - poll_wait(file, &mce_wait, wait); + poll_wait(file, &mce_chrdev_wait, wait); if (rcu_access_index(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) @@ -1624,7 +1601,8 @@ static unsigned int mce_poll(struct file *file, poll_table *wait) return 0; } -static long mce_ioctl(struct file *f, unsigned int cmd, unsigned long arg) +static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, + unsigned long arg) { int __user *p = (int __user *)arg; @@ -1652,16 +1630,16 @@ static long mce_ioctl(struct file *f, unsigned int cmd, unsigned long arg) /* Modified in mce-inject.c, so not static or const */ struct file_operations mce_chrdev_ops = { - .open = mce_open, - .release = mce_release, - .read = mce_read, - .poll = mce_poll, - .unlocked_ioctl = mce_ioctl, - .llseek = no_llseek, + .open = mce_chrdev_open, + .release = mce_chrdev_release, + .read = mce_chrdev_read, + .poll = mce_chrdev_poll, + .unlocked_ioctl = mce_chrdev_ioctl, + .llseek = no_llseek, }; EXPORT_SYMBOL_GPL(mce_chrdev_ops); -static struct miscdevice mce_log_device = { +static struct miscdevice mce_chrdev_device = { MISC_MCELOG_MINOR, "mcelog", &mce_chrdev_ops, @@ -1719,7 +1697,7 @@ int __init mcheck_init(void) } /* - * Sysfs support + * mce_syscore: PM support */ /* @@ -1739,12 +1717,12 @@ static int mce_disable_error_reporting(void) return 0; } -static int mce_suspend(void) +static int mce_syscore_suspend(void) { return mce_disable_error_reporting(); } -static void mce_shutdown(void) +static void mce_syscore_shutdown(void) { mce_disable_error_reporting(); } @@ -1754,18 +1732,22 @@ static void mce_shutdown(void) * Only one CPU is active at this time, the others get re-added later using * CPU hotplug: */ -static void mce_resume(void) +static void mce_syscore_resume(void) { __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info)); } static struct syscore_ops mce_syscore_ops = { - .suspend = mce_suspend, - .shutdown = mce_shutdown, - .resume = mce_resume, + .suspend = mce_syscore_suspend, + .shutdown = mce_syscore_shutdown, + .resume = mce_syscore_resume, }; +/* + * mce_sysdev: Sysfs support + */ + static void mce_cpu_restart(void *data) { del_timer_sync(&__get_cpu_var(mce_timer)); @@ -1801,11 +1783,11 @@ static void mce_enable_ce(void *all) __mcheck_cpu_init_timer(); } -static struct sysdev_class mce_sysclass = { +static struct sysdev_class mce_sysdev_class = { .name = "machinecheck", }; -DEFINE_PER_CPU(struct sys_device, mce_dev); +DEFINE_PER_CPU(struct sys_device, mce_sysdev); __cpuinitdata void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); @@ -1934,7 +1916,7 @@ static struct sysdev_ext_attribute attr_cmci_disabled = { &mce_cmci_disabled }; -static struct sysdev_attribute *mce_attrs[] = { +static struct sysdev_attribute *mce_sysdev_attrs[] = { &attr_tolerant.attr, &attr_check_interval.attr, &attr_trigger, @@ -1945,66 +1927,67 @@ static struct sysdev_attribute *mce_attrs[] = { NULL }; -static cpumask_var_t mce_dev_initialized; +static cpumask_var_t mce_sysdev_initialized; /* Per cpu sysdev init. All of the cpus still share the same ctrl bank: */ -static __cpuinit int mce_create_device(unsigned int cpu) +static __cpuinit int mce_sysdev_create(unsigned int cpu) { + struct sys_device *sysdev = &per_cpu(mce_sysdev, cpu); int err; int i, j; if (!mce_available(&boot_cpu_data)) return -EIO; - memset(&per_cpu(mce_dev, cpu).kobj, 0, sizeof(struct kobject)); - per_cpu(mce_dev, cpu).id = cpu; - per_cpu(mce_dev, cpu).cls = &mce_sysclass; + memset(&sysdev->kobj, 0, sizeof(struct kobject)); + sysdev->id = cpu; + sysdev->cls = &mce_sysdev_class; - err = sysdev_register(&per_cpu(mce_dev, cpu)); + err = sysdev_register(sysdev); if (err) return err; - for (i = 0; mce_attrs[i]; i++) { - err = sysdev_create_file(&per_cpu(mce_dev, cpu), mce_attrs[i]); + for (i = 0; mce_sysdev_attrs[i]; i++) { + err = sysdev_create_file(sysdev, mce_sysdev_attrs[i]); if (err) goto error; } for (j = 0; j < banks; j++) { - err = sysdev_create_file(&per_cpu(mce_dev, cpu), - &mce_banks[j].attr); + err = sysdev_create_file(sysdev, &mce_banks[j].attr); if (err) goto error2; } - cpumask_set_cpu(cpu, mce_dev_initialized); + cpumask_set_cpu(cpu, mce_sysdev_initialized); return 0; error2: while (--j >= 0) - sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[j].attr); + sysdev_remove_file(sysdev, &mce_banks[j].attr); error: while (--i >= 0) - sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]); + sysdev_remove_file(sysdev, mce_sysdev_attrs[i]); - sysdev_unregister(&per_cpu(mce_dev, cpu)); + sysdev_unregister(sysdev); return err; } -static __cpuinit void mce_remove_device(unsigned int cpu) +static __cpuinit void mce_sysdev_remove(unsigned int cpu) { + struct sys_device *sysdev = &per_cpu(mce_sysdev, cpu); int i; - if (!cpumask_test_cpu(cpu, mce_dev_initialized)) + if (!cpumask_test_cpu(cpu, mce_sysdev_initialized)) return; - for (i = 0; mce_attrs[i]; i++) - sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]); + for (i = 0; mce_sysdev_attrs[i]; i++) + sysdev_remove_file(sysdev, mce_sysdev_attrs[i]); for (i = 0; i < banks; i++) - sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[i].attr); + sysdev_remove_file(sysdev, &mce_banks[i].attr); - sysdev_unregister(&per_cpu(mce_dev, cpu)); - cpumask_clear_cpu(cpu, mce_dev_initialized); + sysdev_unregister(sysdev); + cpumask_clear_cpu(cpu, mce_sysdev_initialized); } /* Make sure there are no machine checks on offlined CPUs. */ @@ -2054,7 +2037,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - mce_create_device(cpu); + mce_sysdev_create(cpu); if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); break; @@ -2062,7 +2045,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD_FROZEN: if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); - mce_remove_device(cpu); + mce_sysdev_remove(cpu); break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: @@ -2116,27 +2099,28 @@ static __init int mcheck_init_device(void) if (!mce_available(&boot_cpu_data)) return -EIO; - zalloc_cpumask_var(&mce_dev_initialized, GFP_KERNEL); + zalloc_cpumask_var(&mce_sysdev_initialized, GFP_KERNEL); mce_init_banks(); - err = sysdev_class_register(&mce_sysclass); + err = sysdev_class_register(&mce_sysdev_class); if (err) return err; for_each_online_cpu(i) { - err = mce_create_device(i); + err = mce_sysdev_create(i); if (err) return err; } register_syscore_ops(&mce_syscore_ops); register_hotcpu_notifier(&mce_cpu_notifier); - misc_register(&mce_log_device); + + /* register character device /dev/mcelog */ + misc_register(&mce_chrdev_device); return err; } - device_initcall(mcheck_init_device); /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index bb0adad35143..f5474218cffe 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -548,7 +548,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (!b) goto out; - err = sysfs_create_link(&per_cpu(mce_dev, cpu).kobj, + err = sysfs_create_link(&per_cpu(mce_sysdev, cpu).kobj, b->kobj, name); if (err) goto out; @@ -571,7 +571,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } - b->kobj = kobject_create_and_add(name, &per_cpu(mce_dev, cpu).kobj); + b->kobj = kobject_create_and_add(name, &per_cpu(mce_sysdev, cpu).kobj); if (!b->kobj) goto out_free; @@ -591,7 +591,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (i == cpu) continue; - err = sysfs_create_link(&per_cpu(mce_dev, i).kobj, + err = sysfs_create_link(&per_cpu(mce_sysdev, i).kobj, b->kobj, name); if (err) goto out; @@ -669,7 +669,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) #ifdef CONFIG_SMP /* sibling symlink */ if (shared_bank[bank] && b->blocks->cpu != cpu) { - sysfs_remove_link(&per_cpu(mce_dev, cpu).kobj, name); + sysfs_remove_link(&per_cpu(mce_sysdev, cpu).kobj, name); per_cpu(threshold_banks, cpu)[bank] = NULL; return; @@ -681,7 +681,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) if (i == cpu) continue; - sysfs_remove_link(&per_cpu(mce_dev, i).kobj, name); + sysfs_remove_link(&per_cpu(mce_sysdev, i).kobj, name); per_cpu(threshold_banks, i)[bank] = NULL; } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 929739a653d1..6b96110bb0c3 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -79,7 +79,6 @@ void set_mtrr_ops(const struct mtrr_ops *ops) static int have_wrcomb(void) { struct pci_dev *dev; - u8 rev; dev = pci_get_class(PCI_CLASS_BRIDGE_HOST << 8, NULL); if (dev != NULL) { @@ -89,13 +88,11 @@ static int have_wrcomb(void) * chipsets to be tagged */ if (dev->vendor == PCI_VENDOR_ID_SERVERWORKS && - dev->device == PCI_DEVICE_ID_SERVERWORKS_LE) { - pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev); - if (rev <= 5) { - pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n"); - pci_dev_put(dev); - return 0; - } + dev->device == PCI_DEVICE_ID_SERVERWORKS_LE && + dev->revision <= 5) { + pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n"); + pci_dev_put(dev); + return 0; } /* * Intel 450NX errata # 23. Non ascending cacheline evictions to @@ -137,56 +134,42 @@ static void __init init_table(void) } struct set_mtrr_data { - atomic_t count; - atomic_t gate; unsigned long smp_base; unsigned long smp_size; unsigned int smp_reg; mtrr_type smp_type; }; -static DEFINE_PER_CPU(struct cpu_stop_work, mtrr_work); - /** - * mtrr_work_handler - Synchronisation handler. Executed by "other" CPUs. + * mtrr_rendezvous_handler - Work done in the synchronization handler. Executed + * by all the CPUs. * @info: pointer to mtrr configuration data * * Returns nothing. */ -static int mtrr_work_handler(void *info) +static int mtrr_rendezvous_handler(void *info) { -#ifdef CONFIG_SMP struct set_mtrr_data *data = info; - unsigned long flags; - atomic_dec(&data->count); - while (!atomic_read(&data->gate)) - cpu_relax(); - - local_irq_save(flags); - - atomic_dec(&data->count); - while (atomic_read(&data->gate)) - cpu_relax(); - - /* The master has cleared me to execute */ + /* + * We use this same function to initialize the mtrrs during boot, + * resume, runtime cpu online and on an explicit request to set a + * specific MTRR. + * + * During boot or suspend, the state of the boot cpu's mtrrs has been + * saved, and we want to replicate that across all the cpus that come + * online (either at the end of boot or resume or during a runtime cpu + * online). If we're doing that, @reg is set to something special and on + * all the cpu's we do mtrr_if->set_all() (On the logical cpu that + * started the boot/resume sequence, this might be a duplicate + * set_all()). + */ if (data->smp_reg != ~0U) { mtrr_if->set(data->smp_reg, data->smp_base, data->smp_size, data->smp_type); - } else if (mtrr_aps_delayed_init) { - /* - * Initialize the MTRRs inaddition to the synchronisation. - */ + } else if (mtrr_aps_delayed_init || !cpu_online(smp_processor_id())) { mtrr_if->set_all(); } - - atomic_dec(&data->count); - while (!atomic_read(&data->gate)) - cpu_relax(); - - atomic_dec(&data->count); - local_irq_restore(flags); -#endif return 0; } @@ -223,20 +206,11 @@ static inline int types_compatible(mtrr_type type1, mtrr_type type2) * 14. Wait for buddies to catch up * 15. Enable interrupts. * - * What does that mean for us? Well, first we set data.count to the number - * of CPUs. As each CPU announces that it started the rendezvous handler by - * decrementing the count, We reset data.count and set the data.gate flag - * allowing all the cpu's to proceed with the work. As each cpu disables - * interrupts, it'll decrement data.count once. We wait until it hits 0 and - * proceed. We clear the data.gate flag and reset data.count. Meanwhile, they - * are waiting for that flag to be cleared. Once it's cleared, each - * CPU goes through the transition of updating MTRRs. - * The CPU vendors may each do it differently, - * so we call mtrr_if->set() callback and let them take care of it. - * When they're done, they again decrement data->count and wait for data.gate - * to be set. - * When we finish, we wait for data.count to hit 0 and toggle the data.gate flag - * Everyone then enables interrupts and we all continue on. + * What does that mean for us? Well, stop_machine() will ensure that + * the rendezvous handler is started on each CPU. And in lockstep they + * do the state transition of disabling interrupts, updating MTRR's + * (the CPU vendors may each do it differently, so we call mtrr_if->set() + * callback and let them take care of it.) and enabling interrupts. * * Note that the mechanism is the same for UP systems, too; all the SMP stuff * becomes nops. @@ -244,92 +218,26 @@ static inline int types_compatible(mtrr_type type1, mtrr_type type2) static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { - struct set_mtrr_data data; - unsigned long flags; - int cpu; + struct set_mtrr_data data = { .smp_reg = reg, + .smp_base = base, + .smp_size = size, + .smp_type = type + }; - preempt_disable(); - - data.smp_reg = reg; - data.smp_base = base; - data.smp_size = size; - data.smp_type = type; - atomic_set(&data.count, num_booting_cpus() - 1); - - /* Make sure data.count is visible before unleashing other CPUs */ - smp_wmb(); - atomic_set(&data.gate, 0); - - /* Start the ball rolling on other CPUs */ - for_each_online_cpu(cpu) { - struct cpu_stop_work *work = &per_cpu(mtrr_work, cpu); - - if (cpu == smp_processor_id()) - continue; - - stop_one_cpu_nowait(cpu, mtrr_work_handler, &data, work); - } - - - while (atomic_read(&data.count)) - cpu_relax(); - - /* Ok, reset count and toggle gate */ - atomic_set(&data.count, num_booting_cpus() - 1); - smp_wmb(); - atomic_set(&data.gate, 1); - - local_irq_save(flags); - - while (atomic_read(&data.count)) - cpu_relax(); - - /* Ok, reset count and toggle gate */ - atomic_set(&data.count, num_booting_cpus() - 1); - smp_wmb(); - atomic_set(&data.gate, 0); - - /* Do our MTRR business */ - - /* - * HACK! - * - * We use this same function to initialize the mtrrs during boot, - * resume, runtime cpu online and on an explicit request to set a - * specific MTRR. - * - * During boot or suspend, the state of the boot cpu's mtrrs has been - * saved, and we want to replicate that across all the cpus that come - * online (either at the end of boot or resume or during a runtime cpu - * online). If we're doing that, @reg is set to something special and on - * this cpu we still do mtrr_if->set_all(). During boot/resume, this - * is unnecessary if at this point we are still on the cpu that started - * the boot/resume sequence. But there is no guarantee that we are still - * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be - * sure that we are in sync with everyone else. - */ - if (reg != ~0U) - mtrr_if->set(reg, base, size, type); - else - mtrr_if->set_all(); - - /* Wait for the others */ - while (atomic_read(&data.count)) - cpu_relax(); - - atomic_set(&data.count, num_booting_cpus() - 1); - smp_wmb(); - atomic_set(&data.gate, 1); - - /* - * Wait here for everyone to have seen the gate change - * So we're the last ones to touch 'data' - */ - while (atomic_read(&data.count)) - cpu_relax(); + stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); +} - local_irq_restore(flags); - preempt_enable(); +static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base, + unsigned long size, mtrr_type type) +{ + struct set_mtrr_data data = { .smp_reg = reg, + .smp_base = base, + .smp_size = size, + .smp_type = type + }; + + stop_machine_from_inactive_cpu(mtrr_rendezvous_handler, &data, + cpu_callout_mask); } /** @@ -783,7 +691,7 @@ void mtrr_ap_init(void) * 2. cpu hotadd time. We let mtrr_add/del_page hold cpuhotplug * lock to prevent mtrr entry changes */ - set_mtrr(~0U, 0, 0, 0); + set_mtrr_from_inactive_cpu(~0U, 0, 0, 0); } /** diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4ee3abf20ed6..8ab89112f93c 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -32,6 +32,8 @@ #include <asm/smp.h> #include <asm/alternative.h> +#include "perf_event.h" + #if 0 #undef wrmsrl #define wrmsrl(msr, val) \ @@ -43,283 +45,17 @@ do { \ } while (0) #endif -/* - * | NHM/WSM | SNB | - * register ------------------------------- - * | HT | no HT | HT | no HT | - *----------------------------------------- - * offcore | core | core | cpu | core | - * lbr_sel | core | core | cpu | core | - * ld_lat | cpu | core | cpu | core | - *----------------------------------------- - * - * Given that there is a small number of shared regs, - * we can pre-allocate their slot in the per-cpu - * per-core reg tables. - */ -enum extra_reg_type { - EXTRA_REG_NONE = -1, /* not used */ - - EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ - EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ - - EXTRA_REG_MAX /* number of entries needed */ -}; - -struct event_constraint { - union { - unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - u64 idxmsk64; - }; - u64 code; - u64 cmask; - int weight; -}; - -struct amd_nb { - int nb_id; /* NorthBridge id */ - int refcnt; /* reference count */ - struct perf_event *owners[X86_PMC_IDX_MAX]; - struct event_constraint event_constraints[X86_PMC_IDX_MAX]; -}; - -struct intel_percore; - -#define MAX_LBR_ENTRIES 16 - -struct cpu_hw_events { - /* - * Generic x86 PMC bits - */ - struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ - unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - int enabled; - - int n_events; - int n_added; - int n_txn; - int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ - u64 tags[X86_PMC_IDX_MAX]; - struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ - - unsigned int group_flag; - - /* - * Intel DebugStore bits - */ - struct debug_store *ds; - u64 pebs_enabled; - - /* - * Intel LBR bits - */ - int lbr_users; - void *lbr_context; - struct perf_branch_stack lbr_stack; - struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; - - /* - * manage shared (per-core, per-cpu) registers - * used on Intel NHM/WSM/SNB - */ - struct intel_shared_regs *shared_regs; - - /* - * AMD specific bits - */ - struct amd_nb *amd_nb; -}; - -#define __EVENT_CONSTRAINT(c, n, m, w) {\ - { .idxmsk64 = (n) }, \ - .code = (c), \ - .cmask = (m), \ - .weight = (w), \ -} - -#define EVENT_CONSTRAINT(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) - -/* - * Constraint on the Event code. - */ -#define INTEL_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) - -/* - * Constraint on the Event code + UMask + fixed-mask - * - * filter mask to validate fixed counter events. - * the following filters disqualify for fixed counters: - * - inv - * - edge - * - cnt-mask - * The other filters are supported by fixed counters. - * The any-thread option is supported starting with v3. - */ -#define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) - -/* - * Constraint on the Event code + UMask - */ -#define INTEL_UEVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) - -#define EVENT_CONSTRAINT_END \ - EVENT_CONSTRAINT(0, 0, 0) - -#define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->weight; (e)++) - -/* - * Per register state. - */ -struct er_account { - raw_spinlock_t lock; /* per-core: protect structure */ - u64 config; /* extra MSR config */ - u64 reg; /* extra MSR number */ - atomic_t ref; /* reference count */ -}; - -/* - * Extra registers for specific events. - * - * Some events need large masks and require external MSRs. - * Those extra MSRs end up being shared for all events on - * a PMU and sometimes between PMU of sibling HT threads. - * In either case, the kernel needs to handle conflicting - * accesses to those extra, shared, regs. The data structure - * to manage those registers is stored in cpu_hw_event. - */ -struct extra_reg { - unsigned int event; - unsigned int msr; - u64 config_mask; - u64 valid_mask; - int idx; /* per_xxx->regs[] reg index */ -}; - -#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i \ - } - -#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ - EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) - -#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) - -union perf_capabilities { - struct { - u64 lbr_format : 6; - u64 pebs_trap : 1; - u64 pebs_arch_reg : 1; - u64 pebs_format : 4; - u64 smm_freeze : 1; - }; - u64 capabilities; -}; +struct x86_pmu x86_pmu __read_mostly; -/* - * struct x86_pmu - generic x86 pmu - */ -struct x86_pmu { - /* - * Generic x86 PMC bits - */ - const char *name; - int version; - int (*handle_irq)(struct pt_regs *); - void (*disable_all)(void); - void (*enable_all)(int added); - void (*enable)(struct perf_event *); - void (*disable)(struct perf_event *); - int (*hw_config)(struct perf_event *event); - int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); - unsigned eventsel; - unsigned perfctr; - u64 (*event_map)(int); - int max_events; - int num_counters; - int num_counters_fixed; - int cntval_bits; - u64 cntval_mask; - int apic; - u64 max_period; - struct event_constraint * - (*get_event_constraints)(struct cpu_hw_events *cpuc, - struct perf_event *event); - - void (*put_event_constraints)(struct cpu_hw_events *cpuc, - struct perf_event *event); - struct event_constraint *event_constraints; - void (*quirks)(void); - int perfctr_second_write; - - int (*cpu_prepare)(int cpu); - void (*cpu_starting)(int cpu); - void (*cpu_dying)(int cpu); - void (*cpu_dead)(int cpu); - - /* - * Intel Arch Perfmon v2+ - */ - u64 intel_ctrl; - union perf_capabilities intel_cap; - - /* - * Intel DebugStore bits - */ - int bts, pebs; - int bts_active, pebs_active; - int pebs_record_size; - void (*drain_pebs)(struct pt_regs *regs); - struct event_constraint *pebs_constraints; - - /* - * Intel LBR - */ - unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ - int lbr_nr; /* hardware stack size */ - - /* - * Extra registers for events - */ - struct extra_reg *extra_regs; - unsigned int er_flags; -}; - -#define ERF_NO_HT_SHARING 1 -#define ERF_HAS_RSP_1 2 - -static struct x86_pmu x86_pmu __read_mostly; - -static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { +DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; -static int x86_perf_event_set_period(struct perf_event *event); - -/* - * Generalized hw caching related hw_event table, filled - * in on a per model basis. A value of 0 means - * 'not supported', -1 means 'hw_event makes no sense on - * this CPU', any other value means the raw hw_event - * ID. - */ - -#define C(x) PERF_COUNT_HW_CACHE_##x - -static u64 __read_mostly hw_cache_event_ids +u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; -static u64 __read_mostly hw_cache_extra_regs +u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; @@ -329,8 +65,7 @@ static u64 __read_mostly hw_cache_extra_regs * Can only be executed on the CPU where the event is active. * Returns the delta events processed. */ -static u64 -x86_perf_event_update(struct perf_event *event) +u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.cntval_bits; @@ -373,30 +108,6 @@ again: return new_raw_count; } -static inline int x86_pmu_addr_offset(int index) -{ - int offset; - - /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ - alternative_io(ASM_NOP2, - "shll $1, %%eax", - X86_FEATURE_PERFCTR_CORE, - "=a" (offset), - "a" (index)); - - return offset; -} - -static inline unsigned int x86_pmu_config_addr(int index) -{ - return x86_pmu.eventsel + x86_pmu_addr_offset(index); -} - -static inline unsigned int x86_pmu_event_addr(int index) -{ - return x86_pmu.perfctr + x86_pmu_addr_offset(index); -} - /* * Find and validate any extra registers to set up. */ @@ -532,9 +243,6 @@ msr_fail: return false; } -static void reserve_ds_buffers(void); -static void release_ds_buffers(void); - static void hw_perf_event_destroy(struct perf_event *event) { if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { @@ -583,7 +291,7 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } -static int x86_setup_perfctr(struct perf_event *event) +int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -647,7 +355,7 @@ static int x86_setup_perfctr(struct perf_event *event) return 0; } -static int x86_pmu_hw_config(struct perf_event *event) +int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { int precise = 0; @@ -723,7 +431,7 @@ static int __x86_pmu_event_init(struct perf_event *event) return x86_pmu.hw_config(event); } -static void x86_pmu_disable_all(void) +void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; @@ -758,15 +466,7 @@ static void x86_pmu_disable(struct pmu *pmu) x86_pmu.disable_all(); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, - u64 enable_mask) -{ - if (hwc->extra_reg.reg) - wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); - wrmsrl(hwc->config_base, hwc->config | enable_mask); -} - -static void x86_pmu_enable_all(int added) +void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; @@ -788,7 +488,7 @@ static inline int is_x86_event(struct perf_event *event) return event->pmu == &pmu; } -static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) +int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c, *constraints[X86_PMC_IDX_MAX]; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; @@ -959,7 +659,6 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc, } static void x86_pmu_start(struct perf_event *event, int flags); -static void x86_pmu_stop(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { @@ -1031,21 +730,13 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu.enable_all(added); } -static inline void x86_pmu_disable_event(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - wrmsrl(hwc->config_base, hwc->config); -} - static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. * To be called with the event disabled in hw: */ -static int -x86_perf_event_set_period(struct perf_event *event) +int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); @@ -1105,7 +796,7 @@ x86_perf_event_set_period(struct perf_event *event) return ret; } -static void x86_pmu_enable_event(struct perf_event *event) +void x86_pmu_enable_event(struct perf_event *event) { if (__this_cpu_read(cpu_hw_events.enabled)) __x86_pmu_enable_event(&event->hw, @@ -1244,7 +935,7 @@ void perf_event_print_debug(void) local_irq_restore(flags); } -static void x86_pmu_stop(struct perf_event *event, int flags) +void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -1297,7 +988,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) perf_event_update_userpage(event); } -static int x86_pmu_handle_irq(struct pt_regs *regs) +int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; @@ -1437,39 +1128,19 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = { .priority = NMI_LOCAL_LOW_PRIOR, }; -static struct event_constraint unconstrained; -static struct event_constraint emptyconstraint; - -static struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) -{ - struct event_constraint *c; - - if (x86_pmu.event_constraints) { - for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) - return c; - } - } - - return &unconstrained; -} - -#include "perf_event_amd.c" -#include "perf_event_p6.c" -#include "perf_event_p4.c" -#include "perf_event_intel_lbr.c" -#include "perf_event_intel_ds.c" -#include "perf_event_intel.c" +struct event_constraint emptyconstraint; +struct event_constraint unconstrained; static int __cpuinit x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int ret = NOTIFY_OK; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: + cpuc->kfree_on_online = NULL; if (x86_pmu.cpu_prepare) ret = x86_pmu.cpu_prepare(cpu); break; @@ -1479,6 +1150,10 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) x86_pmu.cpu_starting(cpu); break; + case CPU_ONLINE: + kfree(cpuc->kfree_on_online); + break; + case CPU_DYING: if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); @@ -1900,6 +1575,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_store(entry, regs->ip); + if (!current->mm) + return; + if (perf_callchain_user32(regs, entry)) return; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h new file mode 100644 index 000000000000..fb330b0a816e --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event.h @@ -0,0 +1,493 @@ +/* + * Performance events x86 architecture header + * + * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2009 Jaswinder Singh Rajput + * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> + * Copyright (C) 2009 Google, Inc., Stephane Eranian + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/perf_event.h> + +/* + * | NHM/WSM | SNB | + * register ------------------------------- + * | HT | no HT | HT | no HT | + *----------------------------------------- + * offcore | core | core | cpu | core | + * lbr_sel | core | core | cpu | core | + * ld_lat | cpu | core | cpu | core | + *----------------------------------------- + * + * Given that there is a small number of shared regs, + * we can pre-allocate their slot in the per-cpu + * per-core reg tables. + */ +enum extra_reg_type { + EXTRA_REG_NONE = -1, /* not used */ + + EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ + EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + + EXTRA_REG_MAX /* number of entries needed */ +}; + +struct event_constraint { + union { + unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 idxmsk64; + }; + u64 code; + u64 cmask; + int weight; +}; + +struct amd_nb { + int nb_id; /* NorthBridge id */ + int refcnt; /* reference count */ + struct perf_event *owners[X86_PMC_IDX_MAX]; + struct event_constraint event_constraints[X86_PMC_IDX_MAX]; +}; + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 4 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +}; + +/* + * Per register state. + */ +struct er_account { + raw_spinlock_t lock; /* per-core: protect structure */ + u64 config; /* extra MSR config */ + u64 reg; /* extra MSR number */ + atomic_t ref; /* reference count */ +}; + +/* + * Per core/cpu state + * + * Used to coordinate shared registers between HT threads or + * among events on a single PMU. + */ +struct intel_shared_regs { + struct er_account regs[EXTRA_REG_MAX]; + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ +}; + +#define MAX_LBR_ENTRIES 16 + +struct cpu_hw_events { + /* + * Generic x86 PMC bits + */ + struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ + unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + int enabled; + + int n_events; + int n_added; + int n_txn; + int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ + u64 tags[X86_PMC_IDX_MAX]; + struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + + unsigned int group_flag; + + /* + * Intel DebugStore bits + */ + struct debug_store *ds; + u64 pebs_enabled; + + /* + * Intel LBR bits + */ + int lbr_users; + void *lbr_context; + struct perf_branch_stack lbr_stack; + struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + + /* + * manage shared (per-core, per-cpu) registers + * used on Intel NHM/WSM/SNB + */ + struct intel_shared_regs *shared_regs; + + /* + * AMD specific bits + */ + struct amd_nb *amd_nb; + + void *kfree_on_online; +}; + +#define __EVENT_CONSTRAINT(c, n, m, w) {\ + { .idxmsk64 = (n) }, \ + .code = (c), \ + .cmask = (m), \ + .weight = (w), \ +} + +#define EVENT_CONSTRAINT(c, n, m) \ + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) + +/* + * Constraint on the Event code. + */ +#define INTEL_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* + * Constraint on the Event code + UMask + fixed-mask + * + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ +#define FIXED_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + +/* + * Constraint on the Event code + UMask + */ +#define INTEL_UEVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) + +#define EVENT_CONSTRAINT_END \ + EVENT_CONSTRAINT(0, 0, 0) + +#define for_each_event_constraint(e, c) \ + for ((e) = (c); (e)->weight; (e)++) + +/* + * Extra registers for specific events. + * + * Some events need large masks and require external MSRs. + * Those extra MSRs end up being shared for all events on + * a PMU and sometimes between PMU of sibling HT threads. + * In either case, the kernel needs to handle conflicting + * accesses to those extra, shared, regs. The data structure + * to manage those registers is stored in cpu_hw_event. + */ +struct extra_reg { + unsigned int event; + unsigned int msr; + u64 config_mask; + u64 valid_mask; + int idx; /* per_xxx->regs[] reg index */ +}; + +#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i \ + } + +#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) + +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) + +union perf_capabilities { + struct { + u64 lbr_format:6; + u64 pebs_trap:1; + u64 pebs_arch_reg:1; + u64 pebs_format:4; + u64 smm_freeze:1; + }; + u64 capabilities; +}; + +/* + * struct x86_pmu - generic x86 pmu + */ +struct x86_pmu { + /* + * Generic x86 PMC bits + */ + const char *name; + int version; + int (*handle_irq)(struct pt_regs *); + void (*disable_all)(void); + void (*enable_all)(int added); + void (*enable)(struct perf_event *); + void (*disable)(struct perf_event *); + int (*hw_config)(struct perf_event *event); + int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); + unsigned eventsel; + unsigned perfctr; + u64 (*event_map)(int); + int max_events; + int num_counters; + int num_counters_fixed; + int cntval_bits; + u64 cntval_mask; + int apic; + u64 max_period; + struct event_constraint * + (*get_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + + void (*put_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + struct event_constraint *event_constraints; + void (*quirks)(void); + int perfctr_second_write; + + int (*cpu_prepare)(int cpu); + void (*cpu_starting)(int cpu); + void (*cpu_dying)(int cpu); + void (*cpu_dead)(int cpu); + + /* + * Intel Arch Perfmon v2+ + */ + u64 intel_ctrl; + union perf_capabilities intel_cap; + + /* + * Intel DebugStore bits + */ + int bts, pebs; + int bts_active, pebs_active; + int pebs_record_size; + void (*drain_pebs)(struct pt_regs *regs); + struct event_constraint *pebs_constraints; + + /* + * Intel LBR + */ + unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ + int lbr_nr; /* hardware stack size */ + + /* + * Extra registers for events + */ + struct extra_reg *extra_regs; + unsigned int er_flags; +}; + +#define ERF_NO_HT_SHARING 1 +#define ERF_HAS_RSP_1 2 + +extern struct x86_pmu x86_pmu __read_mostly; + +DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + +int x86_perf_event_set_period(struct perf_event *event); + +/* + * Generalized hw caching related hw_event table, filled + * in on a per model basis. A value of 0 means + * 'not supported', -1 means 'hw_event makes no sense on + * this CPU', any other value means the raw hw_event + * ID. + */ + +#define C(x) PERF_COUNT_HW_CACHE_##x + +extern u64 __read_mostly hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +extern u64 __read_mostly hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; + +u64 x86_perf_event_update(struct perf_event *event); + +static inline int x86_pmu_addr_offset(int index) +{ + int offset; + + /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ + alternative_io(ASM_NOP2, + "shll $1, %%eax", + X86_FEATURE_PERFCTR_CORE, + "=a" (offset), + "a" (index)); + + return offset; +} + +static inline unsigned int x86_pmu_config_addr(int index) +{ + return x86_pmu.eventsel + x86_pmu_addr_offset(index); +} + +static inline unsigned int x86_pmu_event_addr(int index) +{ + return x86_pmu.perfctr + x86_pmu_addr_offset(index); +} + +int x86_setup_perfctr(struct perf_event *event); + +int x86_pmu_hw_config(struct perf_event *event); + +void x86_pmu_disable_all(void); + +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, + u64 enable_mask) +{ + if (hwc->extra_reg.reg) + wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); + wrmsrl(hwc->config_base, hwc->config | enable_mask); +} + +void x86_pmu_enable_all(int added); + +int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); + +void x86_pmu_stop(struct perf_event *event, int flags); + +static inline void x86_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +void x86_pmu_enable_event(struct perf_event *event); + +int x86_pmu_handle_irq(struct pt_regs *regs); + +extern struct event_constraint emptyconstraint; + +extern struct event_constraint unconstrained; + +#ifdef CONFIG_CPU_SUP_AMD + +int amd_pmu_init(void); + +#else /* CONFIG_CPU_SUP_AMD */ + +static inline int amd_pmu_init(void) +{ + return 0; +} + +#endif /* CONFIG_CPU_SUP_AMD */ + +#ifdef CONFIG_CPU_SUP_INTEL + +int intel_pmu_save_and_restart(struct perf_event *event); + +struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event); + +struct intel_shared_regs *allocate_shared_regs(int cpu); + +int intel_pmu_init(void); + +void init_debug_store_on_cpu(int cpu); + +void fini_debug_store_on_cpu(int cpu); + +void release_ds_buffers(void); + +void reserve_ds_buffers(void); + +extern struct event_constraint bts_constraint; + +void intel_pmu_enable_bts(u64 config); + +void intel_pmu_disable_bts(void); + +int intel_pmu_drain_bts_buffer(void); + +extern struct event_constraint intel_core2_pebs_event_constraints[]; + +extern struct event_constraint intel_atom_pebs_event_constraints[]; + +extern struct event_constraint intel_nehalem_pebs_event_constraints[]; + +extern struct event_constraint intel_westmere_pebs_event_constraints[]; + +extern struct event_constraint intel_snb_pebs_event_constraints[]; + +struct event_constraint *intel_pebs_constraints(struct perf_event *event); + +void intel_pmu_pebs_enable(struct perf_event *event); + +void intel_pmu_pebs_disable(struct perf_event *event); + +void intel_pmu_pebs_enable_all(void); + +void intel_pmu_pebs_disable_all(void); + +void intel_ds_init(void); + +void intel_pmu_lbr_reset(void); + +void intel_pmu_lbr_enable(struct perf_event *event); + +void intel_pmu_lbr_disable(struct perf_event *event); + +void intel_pmu_lbr_enable_all(void); + +void intel_pmu_lbr_disable_all(void); + +void intel_pmu_lbr_read(void); + +void intel_pmu_lbr_init_core(void); + +void intel_pmu_lbr_init_nhm(void); + +void intel_pmu_lbr_init_atom(void); + +int p4_pmu_init(void); + +int p6_pmu_init(void); + +#else /* CONFIG_CPU_SUP_INTEL */ + +static inline void reserve_ds_buffers(void) +{ +} + +static inline void release_ds_buffers(void) +{ +} + +static inline int intel_pmu_init(void) +{ + return 0; +} + +static inline struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + return NULL; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 941caa2e449b..384450d67128 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,4 +1,10 @@ -#ifdef CONFIG_CPU_SUP_AMD +#include <linux/perf_event.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <asm/apicdef.h> + +#include "perf_event.h" static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -350,7 +356,7 @@ static void amd_pmu_cpu_starting(int cpu) continue; if (nb->nb_id == nb_id) { - kfree(cpuc->amd_nb); + cpuc->kfree_on_online = cpuc->amd_nb; cpuc->amd_nb = nb; break; } @@ -573,7 +579,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { #endif }; -static __init int amd_pmu_init(void) +__init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) @@ -602,12 +608,3 @@ static __init int amd_pmu_init(void) return 0; } - -#else /* CONFIG_CPU_SUP_AMD */ - -static int amd_pmu_init(void) -{ - return 0; -} - -#endif diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 45fbb8f7f549..61fa35750b98 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,16 +1,19 @@ -#ifdef CONFIG_CPU_SUP_INTEL - /* * Per core/cpu state * * Used to coordinate shared registers between HT threads or * among events on a single PMU. */ -struct intel_shared_regs { - struct er_account regs[EXTRA_REG_MAX]; - int refcnt; /* per-core: #HT threads */ - unsigned core_id; /* per-core: core id */ -}; + +#include <linux/stddef.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> + +#include <asm/hardirq.h> +#include <asm/apic.h> + +#include "perf_event.h" /* * Intel PerfMon, used on Core and later. @@ -945,7 +948,7 @@ static void intel_pmu_enable_event(struct perf_event *event) * Save and restart an expired event. Called by NMI contexts, * so it has to be careful about preempting normal event ops: */ -static int intel_pmu_save_and_restart(struct perf_event *event) +int intel_pmu_save_and_restart(struct perf_event *event) { x86_perf_event_update(event); return x86_perf_event_set_period(event); @@ -1197,6 +1200,21 @@ intel_shared_regs_constraints(struct cpu_hw_events *cpuc, return c; } +struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c; + + if (x86_pmu.event_constraints) { + for_each_event_constraint(c, x86_pmu.event_constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &unconstrained; +} + static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -1309,7 +1327,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, }; -static struct intel_shared_regs *allocate_shared_regs(int cpu) +struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; int i; @@ -1362,7 +1380,7 @@ static void intel_pmu_cpu_starting(int cpu) pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - kfree(cpuc->shared_regs); + cpuc->kfree_on_online = cpuc->shared_regs; cpuc->shared_regs = pc; break; } @@ -1441,7 +1459,7 @@ static void intel_clovertown_quirks(void) x86_pmu.pebs_constraints = NULL; } -static __init int intel_pmu_init(void) +__init int intel_pmu_init(void) { union cpuid10_edx edx; union cpuid10_eax eax; @@ -1590,13 +1608,14 @@ static __init int intel_pmu_init(void) break; case 42: /* SandyBridge */ + case 45: /* SandyBridge, "Romely-EP" */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_snb_event_constraints; - x86_pmu.pebs_constraints = intel_snb_pebs_events; + x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; @@ -1627,16 +1646,3 @@ static __init int intel_pmu_init(void) } return 0; } - -#else /* CONFIG_CPU_SUP_INTEL */ - -static int intel_pmu_init(void) -{ - return 0; -} - -static struct intel_shared_regs *allocate_shared_regs(int cpu) -{ - return NULL; -} -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 1b1ef3addcfd..c0d238f49db8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -1,7 +1,10 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/slab.h> -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +#include <asm/perf_event.h> + +#include "perf_event.h" /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -37,24 +40,7 @@ struct pebs_record_nhm { u64 status, dla, dse, lat; }; -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; - -static void init_debug_store_on_cpu(int cpu) +void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -66,7 +52,7 @@ static void init_debug_store_on_cpu(int cpu) (u32)((u64)(unsigned long)ds >> 32)); } -static void fini_debug_store_on_cpu(int cpu) +void fini_debug_store_on_cpu(int cpu) { if (!per_cpu(cpu_hw_events, cpu).ds) return; @@ -175,7 +161,7 @@ static void release_ds_buffer(int cpu) kfree(ds); } -static void release_ds_buffers(void) +void release_ds_buffers(void) { int cpu; @@ -194,7 +180,7 @@ static void release_ds_buffers(void) put_online_cpus(); } -static void reserve_ds_buffers(void) +void reserve_ds_buffers(void) { int bts_err = 0, pebs_err = 0; int cpu; @@ -260,10 +246,10 @@ static void reserve_ds_buffers(void) * BTS */ -static struct event_constraint bts_constraint = +struct event_constraint bts_constraint = EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); -static void intel_pmu_enable_bts(u64 config) +void intel_pmu_enable_bts(u64 config) { unsigned long debugctlmsr; @@ -282,7 +268,7 @@ static void intel_pmu_enable_bts(u64 config) update_debugctlmsr(debugctlmsr); } -static void intel_pmu_disable_bts(void) +void intel_pmu_disable_bts(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); unsigned long debugctlmsr; @@ -299,7 +285,7 @@ static void intel_pmu_disable_bts(void) update_debugctlmsr(debugctlmsr); } -static int intel_pmu_drain_bts_buffer(void) +int intel_pmu_drain_bts_buffer(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -361,7 +347,7 @@ static int intel_pmu_drain_bts_buffer(void) /* * PEBS */ -static struct event_constraint intel_core2_pebs_event_constraints[] = { +struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ @@ -370,14 +356,14 @@ static struct event_constraint intel_core2_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_atom_pebs_event_constraints[] = { +struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; -static struct event_constraint intel_nehalem_pebs_event_constraints[] = { +struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ @@ -392,7 +378,7 @@ static struct event_constraint intel_nehalem_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_westmere_pebs_event_constraints[] = { +struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ @@ -407,7 +393,7 @@ static struct event_constraint intel_westmere_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_snb_pebs_events[] = { +struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ @@ -428,8 +414,7 @@ static struct event_constraint intel_snb_pebs_events[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint * -intel_pebs_constraints(struct perf_event *event) +struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -446,7 +431,7 @@ intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } -static void intel_pmu_pebs_enable(struct perf_event *event) +void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -460,7 +445,7 @@ static void intel_pmu_pebs_enable(struct perf_event *event) intel_pmu_lbr_enable(event); } -static void intel_pmu_pebs_disable(struct perf_event *event) +void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -475,7 +460,7 @@ static void intel_pmu_pebs_disable(struct perf_event *event) intel_pmu_lbr_disable(event); } -static void intel_pmu_pebs_enable_all(void) +void intel_pmu_pebs_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -483,7 +468,7 @@ static void intel_pmu_pebs_enable_all(void) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); } -static void intel_pmu_pebs_disable_all(void) +void intel_pmu_pebs_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -576,8 +561,6 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static int intel_pmu_save_and_restart(struct perf_event *event); - static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { @@ -716,7 +699,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * BTS, PEBS probe and setup */ -static void intel_ds_init(void) +void intel_ds_init(void) { /* * No support for 32bit formats @@ -749,15 +732,3 @@ static void intel_ds_init(void) } } } - -#else /* CONFIG_CPU_SUP_INTEL */ - -static void reserve_ds_buffers(void) -{ -} - -static void release_ds_buffers(void) -{ -} - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d202c1bece1a..3fab3de3ce96 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -1,4 +1,10 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> +#include <linux/types.h> + +#include <asm/perf_event.h> +#include <asm/msr.h> + +#include "perf_event.h" enum { LBR_FORMAT_32 = 0x00, @@ -48,7 +54,7 @@ static void intel_pmu_lbr_reset_64(void) } } -static void intel_pmu_lbr_reset(void) +void intel_pmu_lbr_reset(void) { if (!x86_pmu.lbr_nr) return; @@ -59,7 +65,7 @@ static void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_64(); } -static void intel_pmu_lbr_enable(struct perf_event *event) +void intel_pmu_lbr_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -81,7 +87,7 @@ static void intel_pmu_lbr_enable(struct perf_event *event) cpuc->lbr_users++; } -static void intel_pmu_lbr_disable(struct perf_event *event) +void intel_pmu_lbr_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -95,7 +101,7 @@ static void intel_pmu_lbr_disable(struct perf_event *event) __intel_pmu_lbr_disable(); } -static void intel_pmu_lbr_enable_all(void) +void intel_pmu_lbr_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -103,7 +109,7 @@ static void intel_pmu_lbr_enable_all(void) __intel_pmu_lbr_enable(); } -static void intel_pmu_lbr_disable_all(void) +void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -178,7 +184,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_stack.nr = i; } -static void intel_pmu_lbr_read(void) +void intel_pmu_lbr_read(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -191,7 +197,7 @@ static void intel_pmu_lbr_read(void) intel_pmu_lbr_read_64(cpuc); } -static void intel_pmu_lbr_init_core(void) +void intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; x86_pmu.lbr_tos = 0x01c9; @@ -199,7 +205,7 @@ static void intel_pmu_lbr_init_core(void) x86_pmu.lbr_to = 0x60; } -static void intel_pmu_lbr_init_nhm(void) +void intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = 0x01c9; @@ -207,12 +213,10 @@ static void intel_pmu_lbr_init_nhm(void) x86_pmu.lbr_to = 0x6c0; } -static void intel_pmu_lbr_init_atom(void) +void intel_pmu_lbr_init_atom(void) { x86_pmu.lbr_nr = 8; x86_pmu.lbr_tos = 0x01c9; x86_pmu.lbr_from = 0x40; x86_pmu.lbr_to = 0x60; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 7809d2bcb209..492bf1358a7c 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -7,9 +7,13 @@ * For licencing details see kernel-base/COPYING */ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> #include <asm/perf_event_p4.h> +#include <asm/hardirq.h> +#include <asm/apic.h> + +#include "perf_event.h" #define P4_CNTR_LIMIT 3 /* @@ -1303,7 +1307,7 @@ static __initconst const struct x86_pmu p4_pmu = { .perfctr_second_write = 1, }; -static __init int p4_pmu_init(void) +__init int p4_pmu_init(void) { unsigned int low, high; @@ -1326,5 +1330,3 @@ static __init int p4_pmu_init(void) return 0; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 20c097e33860..c7181befecde 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -1,4 +1,7 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> +#include <linux/types.h> + +#include "perf_event.h" /* * Not sure about some of these @@ -114,7 +117,7 @@ static __initconst const struct x86_pmu p6_pmu = { .event_constraints = p6_event_constraints, }; -static __init int p6_pmu_init(void) +__init int p6_pmu_init(void) { switch (boot_cpu_data.x86_model) { case 1: @@ -138,5 +141,3 @@ static __init int p6_pmu_init(void) return 0; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 5c1a91974918..f3f6f5344001 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -54,6 +54,7 @@ #include <asm/ftrace.h> #include <asm/irq_vectors.h> #include <asm/cpufeature.h> +#include <asm/alternative-asm.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -873,12 +874,7 @@ ENTRY(simd_coprocessor_error) 661: pushl_cfi $do_general_protection 662: .section .altinstructions,"a" - .balign 4 - .long 661b - .long 663f - .word X86_FEATURE_XMM - .byte 662b-661b - .byte 664f-663f + altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f .previous .section .altinstr_replacement,"ax" 663: pushl $do_simd_coprocessor_error diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index d656f68371a4..6419bb05ecd5 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -9,6 +9,8 @@ /* * entry.S contains the system-call and fault low-level handling routines. * + * Some of this is documented in Documentation/x86/entry_64.txt + * * NOTE: This code handles signal-recognition, which happens every time * after an interrupt and after each system call. * @@ -467,7 +469,7 @@ ENTRY(system_call_after_swapgs) * and short: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,1 + SAVE_ARGS 8,0 movq %rax,ORIG_RAX-ARGOFFSET(%rsp) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET @@ -502,7 +504,7 @@ sysret_check: TRACE_IRQS_ON movq RIP-ARGOFFSET(%rsp),%rcx CFI_REGISTER rip,rcx - RESTORE_ARGS 0,-ARG_SKIP,1 + RESTORE_ARGS 1,-ARG_SKIP,0 /*CFI_REGISTER rflags,r11*/ movq PER_CPU_VAR(old_rsp), %rsp USERGS_SYSRET64 @@ -851,7 +853,7 @@ retint_restore_args: /* return to kernel space */ */ TRACE_IRQS_IRETQ restore_args: - RESTORE_ARGS 0,8,0 + RESTORE_ARGS 1,8,1 irq_return: INTERRUPT_RETURN @@ -984,11 +986,6 @@ apicinterrupt THRESHOLD_APIC_VECTOR \ apicinterrupt THERMAL_APIC_VECTOR \ thermal_interrupt smp_thermal_interrupt -#ifdef CONFIG_X86_MCE -apicinterrupt MCE_SELF_VECTOR \ - mce_self_interrupt smp_mce_self_interrupt -#endif - #ifdef CONFIG_SMP apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ call_function_single_interrupt smp_call_function_single_interrupt @@ -1115,6 +1112,7 @@ zeroentry coprocessor_error do_coprocessor_error errorentry alignment_check do_alignment_check zeroentry simd_coprocessor_error do_simd_coprocessor_error + /* Reload gs selector with exception handling */ /* edi: new selector */ ENTRY(native_load_gs_index) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 6781765b3a0d..4aecc54236a9 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -4,6 +4,7 @@ #include <linux/sysdev.h> #include <linux/delay.h> #include <linux/errno.h> +#include <linux/i8253.h> #include <linux/slab.h> #include <linux/hpet.h> #include <linux/init.h> @@ -12,8 +13,8 @@ #include <linux/io.h> #include <asm/fixmap.h> -#include <asm/i8253.h> #include <asm/hpet.h> +#include <asm/time.h> #define HPET_MASK CLOCKSOURCE_MASK(32) @@ -71,7 +72,7 @@ static inline void hpet_set_mapping(void) { hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); #ifdef CONFIG_X86_64 - __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE); + __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE); #endif } @@ -738,13 +739,6 @@ static cycle_t read_hpet(struct clocksource *cs) return (cycle_t)hpet_readl(HPET_COUNTER); } -#ifdef CONFIG_X86_64 -static cycle_t __vsyscall_fn vread_hpet(void) -{ - return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); -} -#endif - static struct clocksource clocksource_hpet = { .name = "hpet", .rating = 250, @@ -753,7 +747,7 @@ static struct clocksource clocksource_hpet = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = hpet_resume_counter, #ifdef CONFIG_X86_64 - .vread = vread_hpet, + .archdata = { .vclock_mode = VCLOCK_HPET }, #endif }; diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 12aff2537682..739d8598f789 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -321,7 +321,7 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd) return tmp; } -#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16); +#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) #define FP_EXP_TAG_VALID 0 #define FP_EXP_TAG_ZERO 1 #define FP_EXP_TAG_SPECIAL 2 diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index fb66dc9e36cb..f2b96de3c7c1 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -3,113 +3,24 @@ * */ #include <linux/clockchips.h> -#include <linux/interrupt.h> -#include <linux/spinlock.h> -#include <linux/jiffies.h> #include <linux/module.h> #include <linux/timex.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/io.h> +#include <linux/i8253.h> -#include <asm/i8253.h> #include <asm/hpet.h> +#include <asm/time.h> #include <asm/smp.h> -DEFINE_RAW_SPINLOCK(i8253_lock); -EXPORT_SYMBOL(i8253_lock); - /* * HPET replaces the PIT, when enabled. So we need to know, which of * the two timers is used */ struct clock_event_device *global_clock_event; -/* - * Initialize the PIT timer. - * - * This is also called after resume to bring the PIT into operation again. - */ -static void init_pit_timer(enum clock_event_mode mode, - struct clock_event_device *evt) -{ - raw_spin_lock(&i8253_lock); - - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* binary, mode 2, LSB/MSB, ch 0 */ - outb_pit(0x34, PIT_MODE); - outb_pit(LATCH & 0xff , PIT_CH0); /* LSB */ - outb_pit(LATCH >> 8 , PIT_CH0); /* MSB */ - break; - - case CLOCK_EVT_MODE_SHUTDOWN: - case CLOCK_EVT_MODE_UNUSED: - if (evt->mode == CLOCK_EVT_MODE_PERIODIC || - evt->mode == CLOCK_EVT_MODE_ONESHOT) { - outb_pit(0x30, PIT_MODE); - outb_pit(0, PIT_CH0); - outb_pit(0, PIT_CH0); - } - break; - - case CLOCK_EVT_MODE_ONESHOT: - /* One shot setup */ - outb_pit(0x38, PIT_MODE); - break; - - case CLOCK_EVT_MODE_RESUME: - /* Nothing to do here */ - break; - } - raw_spin_unlock(&i8253_lock); -} - -/* - * Program the next event in oneshot mode - * - * Delta is given in PIT ticks - */ -static int pit_next_event(unsigned long delta, struct clock_event_device *evt) -{ - raw_spin_lock(&i8253_lock); - outb_pit(delta & 0xff , PIT_CH0); /* LSB */ - outb_pit(delta >> 8 , PIT_CH0); /* MSB */ - raw_spin_unlock(&i8253_lock); - - return 0; -} - -/* - * On UP the PIT can serve all of the possible timer functions. On SMP systems - * it can be solely used for the global tick. - * - * The profiling and update capabilities are switched off once the local apic is - * registered. This mechanism replaces the previous #ifdef LOCAL_APIC - - * !using_apic_timer decisions in do_timer_interrupt_hook() - */ -static struct clock_event_device pit_ce = { - .name = "pit", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = init_pit_timer, - .set_next_event = pit_next_event, - .irq = 0, -}; - -/* - * Initialize the conversion factor and the min/max deltas of the clock event - * structure and register the clock event source with the framework. - */ void __init setup_pit_timer(void) { - /* - * Start pit with the boot cpu mask and make it global after the - * IO_APIC has been initialized. - */ - pit_ce.cpumask = cpumask_of(smp_processor_id()); - - clockevents_config_and_register(&pit_ce, CLOCK_TICK_RATE, 0xF, 0x7FFF); - global_clock_event = &pit_ce; + clockevent_i8253_init(true); + global_clock_event = &i8253_clockevent; } #ifndef CONFIG_X86_64 @@ -123,7 +34,7 @@ static int __init init_pit_clocksource(void) * - when local APIC timer is active (PIT is switched off) */ if (num_possible_cpus() > 1 || is_hpet_enabled() || - pit_ce.mode != CLOCK_EVT_MODE_PERIODIC) + i8253_clockevent.mode != CLOCK_EVT_MODE_PERIODIC) return 0; return clocksource_i8253_init(); diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 65b8f5c2eebf..610485223bdb 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -14,7 +14,7 @@ #include <linux/io.h> #include <linux/delay.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/system.h> #include <asm/timer.h> #include <asm/hw_irq.h> diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index f470e4ef993e..b3300e6bacef 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -15,7 +15,7 @@ #include <linux/io.h> #include <linux/delay.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/system.h> #include <asm/timer.h> #include <asm/hw_irq.h> @@ -272,9 +272,6 @@ static void __init apic_intr_init(void) #ifdef CONFIG_X86_MCE_THRESHOLD alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); #endif -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_LOCAL_APIC) - alloc_intr_gate(MCE_SELF_VECTOR, mce_self_interrupt); -#endif #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) /* self generated IPI for local APIC timer */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 33c07b0b122e..a9c2116001d6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -51,6 +51,15 @@ static int parse_no_kvmapf(char *arg) early_param("no-kvmapf", parse_no_kvmapf); +static int steal_acc = 1; +static int parse_no_stealacc(char *arg) +{ + steal_acc = 0; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); + struct kvm_para_state { u8 mmu_queue[MMU_QUEUE_SIZE]; int mmu_queue_len; @@ -58,6 +67,8 @@ struct kvm_para_state { static DEFINE_PER_CPU(struct kvm_para_state, para_state); static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); +static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); +static int has_steal_clock = 0; static struct kvm_para_state *kvm_para_state(void) { @@ -441,6 +452,21 @@ static void __init paravirt_ops_setup(void) #endif } +static void kvm_register_steal_time(void) +{ + int cpu = smp_processor_id(); + struct kvm_steal_time *st = &per_cpu(steal_time, cpu); + + if (!has_steal_clock) + return; + + memset(st, 0, sizeof(*st)); + + wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED)); + printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n", + cpu, __pa(st)); +} + void __cpuinit kvm_guest_cpu_init(void) { if (!kvm_para_available()) @@ -457,6 +483,9 @@ void __cpuinit kvm_guest_cpu_init(void) printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); } + + if (has_steal_clock) + kvm_register_steal_time(); } static void kvm_pv_disable_apf(void *unused) @@ -483,6 +512,31 @@ static struct notifier_block kvm_pv_reboot_nb = { .notifier_call = kvm_pv_reboot_notify, }; +static u64 kvm_steal_clock(int cpu) +{ + u64 steal; + struct kvm_steal_time *src; + int version; + + src = &per_cpu(steal_time, cpu); + do { + version = src->version; + rmb(); + steal = src->steal; + rmb(); + } while ((version & 1) || (version != src->version)); + + return steal; +} + +void kvm_disable_steal_time(void) +{ + if (!has_steal_clock) + return; + + wrmsr(MSR_KVM_STEAL_TIME, 0, 0); +} + #ifdef CONFIG_SMP static void __init kvm_smp_prepare_boot_cpu(void) { @@ -500,6 +554,7 @@ static void __cpuinit kvm_guest_cpu_online(void *dummy) static void kvm_guest_cpu_offline(void *dummy) { + kvm_disable_steal_time(); kvm_pv_disable_apf(NULL); apf_task_wake_all(); } @@ -548,6 +603,11 @@ void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) x86_init.irqs.trap_init = kvm_apf_trap_init; + if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + has_steal_clock = 1; + pv_time_ops.steal_clock = kvm_steal_clock; + } + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); @@ -555,3 +615,15 @@ void __init kvm_guest_init(void) kvm_guest_cpu_init(); #endif } + +static __init int activate_jump_labels(void) +{ + if (has_steal_clock) { + jump_label_inc(¶virt_steal_enabled); + if (steal_acc) + jump_label_inc(¶virt_steal_rq_enabled); + } + + return 0; +} +arch_initcall(activate_jump_labels); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 6389a6bca11b..c1a0188e29ae 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -160,6 +160,7 @@ static void __cpuinit kvm_setup_secondary_clock(void) static void kvm_crash_shutdown(struct pt_regs *regs) { native_write_msr(msr_kvm_system_time, 0, 0); + kvm_disable_steal_time(); native_machine_crash_shutdown(regs); } #endif @@ -167,6 +168,7 @@ static void kvm_crash_shutdown(struct pt_regs *regs) static void kvm_shutdown(void) { native_write_msr(msr_kvm_system_time, 0, 0); + kvm_disable_steal_time(); native_machine_shutdown(); } diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index c5610384ab16..591be0ee1934 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -66,8 +66,8 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define UCODE_CONTAINER_SECTION_HDR 8 -#define UCODE_CONTAINER_HEADER_SIZE 12 +#define SECTION_HDR_SIZE 8 +#define CONTAINER_HDR_SZ 12 static struct equiv_cpu_entry *equiv_cpu_table; @@ -157,7 +157,7 @@ static int apply_microcode_amd(int cpu) static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size) { struct cpuinfo_x86 *c = &cpu_data(cpu); - unsigned int max_size, actual_size; + u32 max_size, actual_size; #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 @@ -175,9 +175,9 @@ static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size) break; } - actual_size = buf[4] + (buf[5] << 8); + actual_size = *(u32 *)(buf + 4); - if (actual_size > size || actual_size > max_size) { + if (actual_size + SECTION_HDR_SIZE > size || actual_size > max_size) { pr_err("section size mismatch\n"); return 0; } @@ -191,7 +191,7 @@ get_next_ucode(int cpu, const u8 *buf, unsigned int size, unsigned int *mc_size) struct microcode_header_amd *mc = NULL; unsigned int actual_size = 0; - if (buf[0] != UCODE_UCODE_TYPE) { + if (*(u32 *)buf != UCODE_UCODE_TYPE) { pr_err("invalid type field in container file section header\n"); goto out; } @@ -204,8 +204,8 @@ get_next_ucode(int cpu, const u8 *buf, unsigned int size, unsigned int *mc_size) if (!mc) goto out; - get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, actual_size); - *mc_size = actual_size + UCODE_CONTAINER_SECTION_HDR; + get_ucode_data(mc, buf + SECTION_HDR_SIZE, actual_size); + *mc_size = actual_size + SECTION_HDR_SIZE; out: return mc; @@ -229,9 +229,10 @@ static int install_equiv_cpu_table(const u8 *buf) return -ENOMEM; } - get_ucode_data(equiv_cpu_table, buf + UCODE_CONTAINER_HEADER_SIZE, size); + get_ucode_data(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); - return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */ + /* add header length */ + return size + CONTAINER_HDR_SZ; } static void free_equiv_cpu_table(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 52f256f2cc81..925179f871de 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -45,21 +45,6 @@ void *module_alloc(unsigned long size) -1, __builtin_return_address(0)); } -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) -{ - vfree(module_region); -} - -/* We don't need anything special. */ -int module_frob_arch_sections(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - char *secstrings, - struct module *mod) -{ - return 0; -} - #ifdef CONFIG_X86_32 int apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, @@ -100,17 +85,6 @@ int apply_relocate(Elf32_Shdr *sechdrs, } return 0; } - -int apply_relocate_add(Elf32_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - printk(KERN_ERR "module %s: ADD RELOCATION unsupported\n", - me->name); - return -ENOEXEC; -} #else /*X86_64*/ int apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, @@ -181,17 +155,6 @@ overflow: me->name); return -ENOEXEC; } - -int apply_relocate(Elf_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - printk(KERN_ERR "non add relocation not supported\n"); - return -ENOSYS; -} - #endif int module_finalize(const Elf_Ehdr *hdr, diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 869e1aeeb71b..d90272e6bc40 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -202,6 +202,14 @@ static void native_flush_tlb_single(unsigned long addr) __native_flush_tlb_single(addr); } +struct jump_label_key paravirt_steal_enabled; +struct jump_label_key paravirt_steal_rq_enabled; + +static u64 native_steal_clock(int cpu) +{ + return 0; +} + /* These are in entry.S */ extern void native_iret(void); extern void native_irq_enable_sysexit(void); @@ -299,6 +307,10 @@ struct pv_info pv_info = { .paravirt_enabled = 0, .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ + +#ifdef CONFIG_X86_64 + .extra_user_64bit_cs = __USER_CS, +#endif }; struct pv_init_ops pv_init_ops = { @@ -307,6 +319,7 @@ struct pv_init_ops pv_init_ops = { struct pv_time_ops pv_time_ops = { .sched_clock = native_sched_clock, + .steal_clock = native_steal_clock, }; struct pv_irq_ops pv_irq_ops = { diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index e8c33a302006..726494b58345 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1553,7 +1553,7 @@ static void __init calgary_fixup_one_tce_space(struct pci_dev *dev) continue; /* cover the whole region */ - npages = (r->end - r->start) >> PAGE_SHIFT; + npages = resource_size(r) >> PAGE_SHIFT; npages++; iommu_range_reserve(tbl, r->start, npages); diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index ba0a4cce53be..63228035f9d7 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -234,7 +234,7 @@ void __init probe_roms(void) /* check for extension rom (ignore length byte!) */ rom = isa_bus_to_virt(extension_rom_resource.start); if (romsignature(rom)) { - length = extension_rom_resource.end - extension_rom_resource.start + 1; + length = resource_size(&extension_rom_resource); if (romchecksum(rom, length)) { request_resource(&iomem_resource, &extension_rom_resource); upper = extension_rom_resource.start; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e1ba8cb24e4e..e7e3b019c439 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -438,29 +438,6 @@ void cpu_idle_wait(void) } EXPORT_SYMBOL_GPL(cpu_idle_wait); -/* - * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, - * which can obviate IPI to trigger checking of need_resched. - * We execute MONITOR against need_resched and enter optimized wait state - * through MWAIT. Whenever someone changes need_resched, we would be woken - * up from MWAIT (without an IPI). - * - * New with Core Duo processors, MWAIT can take some hints based on CPU - * capability. - */ -void mwait_idle_with_hints(unsigned long ax, unsigned long cx) -{ - if (!need_resched()) { - if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) - clflush((void *)¤t_thread_info()->flags); - - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __mwait(ax, cx); - } -} - /* Default MONITOR/MWAIT with no hints, used for default C1 state */ static void mwait_idle(void) { diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a3d0dc59067b..7a3b65107a27 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -38,6 +38,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> +#include <linux/cpuidle.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -109,7 +110,8 @@ void cpu_idle(void) local_irq_disable(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + if (cpuidle_idle_call()) + pm_idle(); start_critical_timings(); } tick_nohz_restart_sched_tick(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ca6f7ab8df33..f693e44e1bf6 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/cpuidle.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -136,7 +137,8 @@ void cpu_idle(void) enter_idle(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + if (cpuidle_idle_call()) + pm_idle(); start_critical_timings(); /* In many cases the interrupt that ended idle diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 8bbe8c56916d..b78643d0f9a5 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -10,7 +10,7 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) { - u8 config, rev; + u8 config; u16 word; /* BIOS may enable hardware IRQ balancing for @@ -18,8 +18,7 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) * based platforms. * Disable SW irqbalance/affinity on those platforms. */ - pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev); - if (rev > 0x9) + if (dev->revision > 0x9) return; /* enable access to config space*/ diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 41235531b11c..36818f8ec2be 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -97,6 +97,8 @@ relocate_kernel: ret identity_mapped: + /* set return address to 0 if not preserving context */ + pushl $0 /* store the start address on the stack */ pushl %edx diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 4de8f5b3d476..7a6f3b3be3cf 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -100,6 +100,8 @@ relocate_kernel: ret identity_mapped: + /* set return address to 0 if not preserving context */ + pushq $0 /* store the start address on the stack */ pushq %rdx diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 40a24932a8a1..54ddaeb221c1 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -485,17 +485,18 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, asmlinkage int sys_sigsuspend(int history0, int history1, old_sigset_t mask) { - mask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, mask); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + mask &= _BLOCKABLE; + siginitset(&blocked, mask); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); - set_restore_sigmask(); + set_restore_sigmask(); return -ERESTARTNOHAND; } @@ -572,10 +573,7 @@ unsigned long sys_sigreturn(struct pt_regs *regs) goto badframe; sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); if (restore_sigcontext(regs, &frame->sc, &ax)) goto badframe; @@ -653,11 +651,15 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs *regs) + struct pt_regs *regs) { int usig = signr_convert(sig); + sigset_t *set = ¤t->blocked; int ret; + if (current_thread_info()->status & TS_RESTORE_SIGMASK) + set = ¤t->saved_sigmask; + /* Set up the stack frame */ if (is_ia32) { if (ka->sa.sa_flags & SA_SIGINFO) @@ -672,12 +674,13 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return -EFAULT; } + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; return ret; } static int handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, - sigset_t *oldset, struct pt_regs *regs) + struct pt_regs *regs) { sigset_t blocked; int ret; @@ -712,20 +715,11 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, likely(test_and_clear_thread_flag(TIF_FORCED_TF))) regs->flags &= ~X86_EFLAGS_TF; - ret = setup_rt_frame(sig, ka, info, oldset, regs); + ret = setup_rt_frame(sig, ka, info, regs); if (ret) return ret; -#ifdef CONFIG_X86_64 - /* - * This has nothing to do with segment registers, - * despite the name. This magic affects uaccess.h - * macros' behavior. Reset it to the normal setting. - */ - set_fs(USER_DS); -#endif - /* * Clear the direction flag as per the ABI for function entry. */ @@ -767,7 +761,6 @@ static void do_signal(struct pt_regs *regs) struct k_sigaction ka; siginfo_t info; int signr; - sigset_t *oldset; /* * We want the common case to go fast, which is why we may in certain @@ -779,23 +772,10 @@ static void do_signal(struct pt_regs *regs) if (!user_mode(regs)) return; - if (current_thread_info()->status & TS_RESTORE_SIGMASK) - oldset = ¤t->saved_sigmask; - else - oldset = ¤t->blocked; - signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { /* Whee! Actually deliver the signal. */ - if (handle_signal(signr, &info, &ka, oldset, regs) == 0) { - /* - * A signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TS_RESTORE_SIGMASK flag. - */ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - } + handle_signal(signr, &info, &ka, regs); return; } @@ -823,7 +803,7 @@ static void do_signal(struct pt_regs *regs) */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9fd3137230d4..9f548cb4a958 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -438,7 +438,7 @@ static void impress_friends(void) void __inquire_remote_apic(int apicid) { unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; - char *names[] = { "ID", "VERSION", "SPIV" }; + const char * const names[] = { "ID", "VERSION", "SPIV" }; int timeout; u32 status; diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 7977f0cfe339..c346d1161488 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -74,7 +74,7 @@ static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs) #ifdef CONFIG_X86_64 case 0x40 ... 0x4f: - if (regs->cs != __USER_CS) + if (!user_64bit_mode(regs)) /* 32-bit mode: register increment */ return 0; /* 64-bit mode: REX prefix */ diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index fbb0a045a1a2..bc19be332bc9 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -168,7 +168,7 @@ ENTRY(sys_call_table) .long ptregs_vm86 .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 00cbb272627f..5a64d057be57 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -11,13 +11,13 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> +#include <linux/i8253.h> #include <linux/time.h> #include <linux/mca.h> #include <asm/vsyscall.h> #include <asm/x86_init.h> #include <asm/i8259.h> -#include <asm/i8253.h> #include <asm/timer.h> #include <asm/hpet.h> #include <asm/time.h> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b9b67166f9de..6913369c234c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -49,7 +49,7 @@ #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/system.h> #include <asm/traps.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6cc6922262af..db483369f10b 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -5,7 +5,6 @@ #include <linux/timer.h> #include <linux/acpi_pmtmr.h> #include <linux/cpufreq.h> -#include <linux/dmi.h> #include <linux/delay.h> #include <linux/clocksource.h> #include <linux/percpu.h> @@ -777,7 +776,7 @@ static struct clocksource clocksource_tsc = { .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, #ifdef CONFIG_X86_64 - .vread = vread_tsc, + .archdata = { .vclock_mode = VCLOCK_TSC }, #endif }; @@ -800,27 +799,6 @@ void mark_tsc_unstable(char *reason) EXPORT_SYMBOL_GPL(mark_tsc_unstable); -static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d) -{ - printk(KERN_NOTICE "%s detected: marking TSC unstable.\n", - d->ident); - tsc_unstable = 1; - return 0; -} - -/* List of systems that have known TSC problems */ -static struct dmi_system_id __initdata bad_tsc_dmi_table[] = { - { - .callback = dmi_mark_tsc_unstable, - .ident = "IBM Thinkpad 380XD", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), - DMI_MATCH(DMI_BOARD_NAME, "2635FA0"), - }, - }, - {} -}; - static void __init check_system_tsc_reliable(void) { #ifdef CONFIG_MGEODE_LX @@ -1010,8 +988,6 @@ void __init tsc_init(void) lpj_fine = lpj; use_tsc_delay(); - /* Check and install the TSC clocksource */ - dmi_check_system(bad_tsc_dmi_table); if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 89aed99aafce..0f703f10901a 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -71,7 +71,6 @@ PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(6); /* RW_ */ #ifdef CONFIG_X86_64 - user PT_LOAD FLAGS(5); /* R_E */ #ifdef CONFIG_SMP percpu PT_LOAD FLAGS(6); /* RW_ */ #endif @@ -154,56 +153,25 @@ SECTIONS #ifdef CONFIG_X86_64 -#define VSYSCALL_ADDR (-10*1024*1024) - -#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET) -#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET) - -#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0) -#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) -#define EMIT_VVAR(x, offset) .vsyscall_var_ ## x \ - ADDR(.vsyscall_0) + offset \ - : AT(VLOAD(.vsyscall_var_ ## x)) { \ - *(.vsyscall_var_ ## x) \ - } \ - x = VVIRT(.vsyscall_var_ ## x); - - . = ALIGN(4096); - __vsyscall_0 = .; - - . = VSYSCALL_ADDR; - .vsyscall_0 : AT(VLOAD(.vsyscall_0)) { - *(.vsyscall_0) - } :user - - . = ALIGN(L1_CACHE_BYTES); - .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { - *(.vsyscall_fn) - } - - .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) { - *(.vsyscall_1) - } - .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) { - *(.vsyscall_2) - } + . = ALIGN(PAGE_SIZE); + __vvar_page = .; - .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) { - *(.vsyscall_3) - } + .vvar : AT(ADDR(.vvar) - LOAD_OFFSET) { + /* work around gold bug 13023 */ + __vvar_beginning_hack = .; + /* Place all vvars at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) \ + . = __vvar_beginning_hack + offset; \ + *(.vvar_ ## name) #define __VVAR_KERNEL_LDS #include <asm/vvar.h> #undef __VVAR_KERNEL_LDS +#undef EMIT_VVAR - . = __vsyscall_0 + PAGE_SIZE; + } :data -#undef VSYSCALL_ADDR -#undef VLOAD_OFFSET -#undef VLOAD -#undef VVIRT_OFFSET -#undef VVIRT -#undef EMIT_VVAR + . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE); #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/vread_tsc_64.c b/arch/x86/kernel/vread_tsc_64.c deleted file mode 100644 index a81aa9e9894c..000000000000 --- a/arch/x86/kernel/vread_tsc_64.c +++ /dev/null @@ -1,36 +0,0 @@ -/* This code runs in userspace. */ - -#define DISABLE_BRANCH_PROFILING -#include <asm/vgtod.h> - -notrace cycle_t __vsyscall_fn vread_tsc(void) -{ - cycle_t ret; - u64 last; - - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)vget_cycles(); - - last = VVAR(vsyscall_gtod_data).clock.cycle_last; - - if (likely(ret >= last)) - return ret; - - /* - * GCC likes to generate cmov here, but this branch is extremely - * predictable (it's just a funciton of time and the likely is - * very likely) and there's a data dependence, so force GCC - * to generate a branch instead. I don't barrier() because - * we don't actually need a barrier, and if this function - * ever gets inlined it will generate worse code. - */ - asm volatile (""); - return last; -} diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 3e682184d76c..18ae83dd1cd7 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -2,6 +2,8 @@ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * + * [ NOTE: this mechanism is now deprecated in favor of the vDSO. ] + * * Thanks to hpa@transmeta.com for some useful hint. * Special thanks to Ingo Molnar for his early experience with * a different vsyscall implementation for Linux/IA32 and for the name. @@ -11,15 +13,11 @@ * vsyscalls. One vsyscall can reserve more than 1 slot to avoid * jumping out of line if necessary. We cannot add more with this * mechanism because older kernels won't return -ENOSYS. - * If we want more than four we need a vDSO. * - * Note: the concept clashes with user mode linux. If you use UML and - * want per guest time just set the kernel.vsyscall64 sysctl to 0. + * Note: the concept clashes with user mode linux. UML users should + * use the vDSO. */ -/* Disable profiling for userspace code: */ -#define DISABLE_BRANCH_PROFILING - #include <linux/time.h> #include <linux/init.h> #include <linux/kernel.h> @@ -32,9 +30,12 @@ #include <linux/cpu.h> #include <linux/smp.h> #include <linux/notifier.h> +#include <linux/syscalls.h> +#include <linux/ratelimit.h> #include <asm/vsyscall.h> #include <asm/pgtable.h> +#include <asm/compat.h> #include <asm/page.h> #include <asm/unistd.h> #include <asm/fixmap.h> @@ -44,18 +45,38 @@ #include <asm/desc.h> #include <asm/topology.h> #include <asm/vgtod.h> +#include <asm/traps.h> -#define __vsyscall(nr) \ - __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace -#define __syscall_clobber "r11","cx","memory" +#define CREATE_TRACE_POINTS +#include "vsyscall_trace.h" DEFINE_VVAR(int, vgetcpu_mode); DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = { .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), - .sysctl_enabled = 1, }; +static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; + +static int __init vsyscall_setup(char *str) +{ + if (str) { + if (!strcmp("emulate", str)) + vsyscall_mode = EMULATE; + else if (!strcmp("native", str)) + vsyscall_mode = NATIVE; + else if (!strcmp("none", str)) + vsyscall_mode = NONE; + else + return -EINVAL; + + return 0; + } + + return -EINVAL; +} +early_param("vsyscall", vsyscall_setup); + void update_vsyscall_tz(void) { unsigned long flags; @@ -72,179 +93,140 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, unsigned long flags; write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); + /* copy vsyscall data */ - vsyscall_gtod_data.clock.vread = clock->vread; - vsyscall_gtod_data.clock.cycle_last = clock->cycle_last; - vsyscall_gtod_data.clock.mask = clock->mask; - vsyscall_gtod_data.clock.mult = mult; - vsyscall_gtod_data.clock.shift = clock->shift; - vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; - vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; - vsyscall_gtod_data.wall_to_monotonic = *wtm; - vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); + vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode; + vsyscall_gtod_data.clock.cycle_last = clock->cycle_last; + vsyscall_gtod_data.clock.mask = clock->mask; + vsyscall_gtod_data.clock.mult = mult; + vsyscall_gtod_data.clock.shift = clock->shift; + vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; + vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; + vsyscall_gtod_data.wall_to_monotonic = *wtm; + vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); + write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } -/* RED-PEN may want to readd seq locking, but then the variable should be - * write-once. - */ -static __always_inline void do_get_tz(struct timezone * tz) +static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, + const char *message) { - *tz = VVAR(vsyscall_gtod_data).sys_tz; -} + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); + struct task_struct *tsk; -static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) -{ - int ret; - asm volatile("syscall" - : "=a" (ret) - : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) - : __syscall_clobber ); - return ret; -} + if (!show_unhandled_signals || !__ratelimit(&rs)) + return; -static __always_inline long time_syscall(long *t) -{ - long secs; - asm volatile("syscall" - : "=a" (secs) - : "0" (__NR_time),"D" (t) : __syscall_clobber); - return secs; -} + tsk = current; -static __always_inline void do_vgettimeofday(struct timeval * tv) -{ - cycle_t now, base, mask, cycle_delta; - unsigned seq; - unsigned long mult, shift, nsec; - cycle_t (*vread)(void); - do { - seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock); - - vread = VVAR(vsyscall_gtod_data).clock.vread; - if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled || - !vread)) { - gettimeofday(tv,NULL); - return; - } - - now = vread(); - base = VVAR(vsyscall_gtod_data).clock.cycle_last; - mask = VVAR(vsyscall_gtod_data).clock.mask; - mult = VVAR(vsyscall_gtod_data).clock.mult; - shift = VVAR(vsyscall_gtod_data).clock.shift; - - tv->tv_sec = VVAR(vsyscall_gtod_data).wall_time_sec; - nsec = VVAR(vsyscall_gtod_data).wall_time_nsec; - } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq)); - - /* calculate interval: */ - cycle_delta = (now - base) & mask; - /* convert to nsecs: */ - nsec += (cycle_delta * mult) >> shift; - - while (nsec >= NSEC_PER_SEC) { - tv->tv_sec += 1; - nsec -= NSEC_PER_SEC; - } - tv->tv_usec = nsec / NSEC_PER_USEC; + printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, tsk->comm, task_pid_nr(tsk), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } -int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz) +static int addr_to_vsyscall_nr(unsigned long addr) { - if (tv) - do_vgettimeofday(tv); - if (tz) - do_get_tz(tz); - return 0; + int nr; + + if ((addr & ~0xC00UL) != VSYSCALL_START) + return -EINVAL; + + nr = (addr & 0xC00UL) >> 10; + if (nr >= 3) + return -EINVAL; + + return nr; } -/* This will break when the xtime seconds get inaccurate, but that is - * unlikely */ -time_t __vsyscall(1) vtime(time_t *t) +bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) { - unsigned seq; - time_t result; - if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled)) - return time_syscall(t); - - do { - seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock); + struct task_struct *tsk; + unsigned long caller; + int vsyscall_nr; + long ret; + + /* + * No point in checking CS -- the only way to get here is a user mode + * trap to a high address, which means that we're in 64-bit user code. + */ + + WARN_ON_ONCE(address != regs->ip); + + if (vsyscall_mode == NONE) { + warn_bad_vsyscall(KERN_INFO, regs, + "vsyscall attempted with vsyscall=none"); + return false; + } - result = VVAR(vsyscall_gtod_data).wall_time_sec; + vsyscall_nr = addr_to_vsyscall_nr(address); - } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq)); + trace_emulate_vsyscall(vsyscall_nr); - if (t) - *t = result; - return result; -} + if (vsyscall_nr < 0) { + warn_bad_vsyscall(KERN_WARNING, regs, + "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); + goto sigsegv; + } -/* Fast way to get current CPU and node. - This helps to do per node and per CPU caches in user space. - The result is not guaranteed without CPU affinity, but usually - works out because the scheduler tries to keep a thread on the same - CPU. + if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { + warn_bad_vsyscall(KERN_WARNING, regs, + "vsyscall with bad stack (exploit attempt?)"); + goto sigsegv; + } - tcache must point to a two element sized long array. - All arguments can be NULL. */ -long __vsyscall(2) -vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) -{ - unsigned int p; - unsigned long j = 0; - - /* Fast cache - only recompute value once per jiffies and avoid - relatively costly rdtscp/cpuid otherwise. - This works because the scheduler usually keeps the process - on the same CPU and this syscall doesn't guarantee its - results anyways. - We do this here because otherwise user space would do it on - its own in a likely inferior way (no access to jiffies). - If you don't like it pass NULL. */ - if (tcache && tcache->blob[0] == (j = VVAR(jiffies))) { - p = tcache->blob[1]; - } else if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { - /* Load per CPU data from RDTSCP */ - native_read_tscp(&p); - } else { - /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + tsk = current; + if (seccomp_mode(&tsk->seccomp)) + do_exit(SIGKILL); + + switch (vsyscall_nr) { + case 0: + ret = sys_gettimeofday( + (struct timeval __user *)regs->di, + (struct timezone __user *)regs->si); + break; + + case 1: + ret = sys_time((time_t __user *)regs->di); + break; + + case 2: + ret = sys_getcpu((unsigned __user *)regs->di, + (unsigned __user *)regs->si, + 0); + break; } - if (tcache) { - tcache->blob[0] = j; - tcache->blob[1] = p; + + if (ret == -EFAULT) { + /* + * Bad news -- userspace fed a bad pointer to a vsyscall. + * + * With a real vsyscall, that would have caused SIGSEGV. + * To make writing reliable exploits using the emulated + * vsyscalls harder, generate SIGSEGV here as well. + */ + warn_bad_vsyscall(KERN_INFO, regs, + "vsyscall fault (exploit attempt?)"); + goto sigsegv; } - if (cpu) - *cpu = p & 0xfff; - if (node) - *node = p >> 12; - return 0; -} -static long __vsyscall(3) venosys_1(void) -{ - return -ENOSYS; -} + regs->ax = ret; -#ifdef CONFIG_SYSCTL -static ctl_table kernel_table2[] = { - { .procname = "vsyscall64", - .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec }, - {} -}; + /* Emulate a ret instruction. */ + regs->ip = caller; + regs->sp += 8; -static ctl_table kernel_root_table2[] = { - { .procname = "kernel", .mode = 0555, - .child = kernel_table2 }, - {} -}; -#endif + return true; -/* Assume __initcall executes before all user space. Hopefully kmod - doesn't violate that. We'll find out if it does. */ +sigsegv: + force_sig(SIGSEGV, current); + return true; +} + +/* + * Assume __initcall executes before all user space. Hopefully kmod + * doesn't violate that. We'll find out if it does. + */ static void __cpuinit vsyscall_set_cpu(int cpu) { unsigned long d; @@ -255,13 +237,15 @@ static void __cpuinit vsyscall_set_cpu(int cpu) if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) write_rdtscp_aux((node << 12) | cpu); - /* Store cpu number in limit so that it can be loaded quickly - in user space in vgetcpu. - 12 bits for the CPU and 8 bits for the node. */ + /* + * Store cpu number in limit so that it can be loaded quickly + * in user space in vgetcpu. (12 bits for the CPU and 8 bits for the node) + */ d = 0x0f40000000000ULL; d |= cpu; d |= (node & 0xf) << 12; d |= (node >> 4) << 48; + write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); } @@ -275,34 +259,40 @@ static int __cpuinit cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg) { long cpu = (long)arg; + if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1); + return NOTIFY_DONE; } void __init map_vsyscall(void) { - extern char __vsyscall_0; - unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0); - - /* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */ - __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL); + extern char __vsyscall_page; + unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); + extern char __vvar_page; + unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page); + + __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall, + vsyscall_mode == NATIVE + ? PAGE_KERNEL_VSYSCALL + : PAGE_KERNEL_VVAR); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) != + (unsigned long)VSYSCALL_START); + + __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != + (unsigned long)VVAR_ADDRESS); } static int __init vsyscall_init(void) { - BUG_ON(((unsigned long) &vgettimeofday != - VSYSCALL_ADDR(__NR_vgettimeofday))); - BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime)); - BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE))); - BUG_ON((unsigned long) &vgetcpu != VSYSCALL_ADDR(__NR_vgetcpu)); -#ifdef CONFIG_SYSCTL - register_sysctl_table(kernel_root_table2); -#endif + BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE)); + on_each_cpu(cpu_vsyscall_init, NULL, 1); /* notifier priority > KVM */ hotcpu_notifier(cpu_vsyscall_notifier, 30); + return 0; } - __initcall(vsyscall_init); diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/kernel/vsyscall_emu_64.S new file mode 100644 index 000000000000..c9596a9af159 --- /dev/null +++ b/arch/x86/kernel/vsyscall_emu_64.S @@ -0,0 +1,37 @@ +/* + * vsyscall_emu_64.S: Vsyscall emulation page + * + * Copyright (c) 2011 Andy Lutomirski + * + * Subject to the GNU General Public License, version 2 + */ + +#include <linux/linkage.h> + +#include <asm/irq_vectors.h> +#include <asm/page_types.h> +#include <asm/unistd_64.h> + +__PAGE_ALIGNED_DATA + .globl __vsyscall_page + .balign PAGE_SIZE, 0xcc + .type __vsyscall_page, @object +__vsyscall_page: + + mov $__NR_gettimeofday, %rax + syscall + ret + + .balign 1024, 0xcc + mov $__NR_time, %rax + syscall + ret + + .balign 1024, 0xcc + mov $__NR_getcpu, %rax + syscall + ret + + .balign 4096, 0xcc + + .size __vsyscall_page, 4096 diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/kernel/vsyscall_trace.h new file mode 100644 index 000000000000..a8b2edec54fe --- /dev/null +++ b/arch/x86/kernel/vsyscall_trace.h @@ -0,0 +1,29 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vsyscall + +#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define __VSYSCALL_TRACE_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(emulate_vsyscall, + + TP_PROTO(int nr), + + TP_ARGS(nr), + + TP_STRUCT__entry(__field(int, nr)), + + TP_fast_assign( + __entry->nr = nr; + ), + + TP_printk("nr = %d", __entry->nr) +); + +#endif + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../../arch/x86/kernel +#define TRACE_INCLUDE_FILE vsyscall_trace +#include <trace/define_trace.h> |
