diff options
Diffstat (limited to 'arch/x86/kernel')
79 files changed, 3668 insertions, 2028 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e5652d97..34e923a53762 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -9,7 +9,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_tsc.o = -pg -CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg @@ -23,7 +22,7 @@ obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(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_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o @@ -62,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o @@ -81,8 +81,7 @@ obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o -obj-$(CONFIG_KVM_GUEST) += kvm.o -obj-$(CONFIG_KVM_CLOCK) += kvmclock.o +obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o @@ -100,6 +99,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 6b75777c0a8d..bacf4b0d91f4 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -574,6 +574,12 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) return irq; } +EXPORT_SYMBOL_GPL(acpi_register_gsi); + +void acpi_unregister_gsi(u32 gsi) +{ +} +EXPORT_SYMBOL_GPL(acpi_unregister_gsi); void __init acpi_set_irq_model_pic(void) { @@ -656,7 +662,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) acpi_register_lapic(physid, ACPI_MADT_ENABLED); /* - * If mp_register_lapic successfully generates a new logical cpu + * If acpi_register_lapic successfully generates a new logical cpu * number, then the following will get us exactly what was mapped */ cpumask_andnot(new_map, cpu_present_mask, tmp_map); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 1b8e5a03d942..d5e0d717005a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -43,17 +43,22 @@ int acpi_suspend_lowlevel(void) header->video_mode = saved_video_mode; + header->pmode_behavior = 0; + #ifndef CONFIG_64BIT store_gdt((struct desc_ptr *)&header->pmode_gdt); - if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low, - &header->pmode_efer_high)) - header->pmode_efer_low = header->pmode_efer_high = 0; + if (!rdmsr_safe(MSR_EFER, + &header->pmode_efer_low, + &header->pmode_efer_high)) + header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER); #endif /* !CONFIG_64BIT */ header->pmode_cr0 = read_cr0(); - header->pmode_cr4 = read_cr4_safe(); - header->pmode_behavior = 0; + if (__this_cpu_read(cpu_info.cpuid_level) >= 0) { + header->pmode_cr4 = read_cr4(); + header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4); + } if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, &header->pmode_misc_en_low, &header->pmode_misc_en_high)) @@ -96,6 +101,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); + if (strncmp(str, "nonvs_s3", 8) == 0) + acpi_nvs_nosave_s3(); if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); str = strchr(str, ','); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ced4534baed5..ef5ccca79a6c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -23,19 +23,6 @@ #define MAX_PATCH_LEN (255-1) -#ifdef CONFIG_HOTPLUG_CPU -static int smp_alt_once; - -static int __init bootonly(char *str) -{ - smp_alt_once = 1; - return 1; -} -__setup("smp-alt-boot", bootonly); -#else -#define smp_alt_once 1 -#endif - static int __initdata_or_module debug_alternative; static int __init debug_alt(char *str) @@ -317,7 +304,7 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, /* turn DS segment override prefix into lock prefix */ if (*ptr == 0x3e) text_poke(ptr, ((unsigned char []){0xf0}), 1); - }; + } mutex_unlock(&text_mutex); } @@ -326,9 +313,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, { const s32 *poff; - if (noreplace_smp) - return; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -338,7 +322,7 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, /* turn lock prefix into DS segment override prefix */ if (*ptr == 0xf0) text_poke(ptr, ((unsigned char []){0x3E}), 1); - }; + } mutex_unlock(&text_mutex); } @@ -359,7 +343,7 @@ struct smp_alt_module { }; static LIST_HEAD(smp_alt_modules); static DEFINE_MUTEX(smp_alt); -static int smp_mode = 1; /* protected by smp_alt */ +static bool uniproc_patched = false; /* protected by smp_alt */ void __init_or_module alternatives_smp_module_add(struct module *mod, char *name, @@ -368,19 +352,18 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, { struct smp_alt_module *smp; - if (noreplace_smp) - return; + mutex_lock(&smp_alt); + if (!uniproc_patched) + goto unlock; - if (smp_alt_once) { - if (boot_cpu_has(X86_FEATURE_UP)) - alternatives_smp_unlock(locks, locks_end, - text, text_end); - return; - } + if (num_possible_cpus() == 1) + /* Don't bother remembering, we'll never have to undo it. */ + goto smp_unlock; smp = kzalloc(sizeof(*smp), GFP_KERNEL); if (NULL == smp) - return; /* we'll run the (safe but slow) SMP code then ... */ + /* we'll run the (safe but slow) SMP code then ... */ + goto unlock; smp->mod = mod; smp->name = name; @@ -392,11 +375,10 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, __func__, smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); - mutex_lock(&smp_alt); list_add_tail(&smp->next, &smp_alt_modules); - if (boot_cpu_has(X86_FEATURE_UP)) - alternatives_smp_unlock(smp->locks, smp->locks_end, - smp->text, smp->text_end); +smp_unlock: + alternatives_smp_unlock(locks, locks_end, text, text_end); +unlock: mutex_unlock(&smp_alt); } @@ -404,24 +386,18 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) { struct smp_alt_module *item; - if (smp_alt_once || noreplace_smp) - return; - mutex_lock(&smp_alt); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; list_del(&item->next); - mutex_unlock(&smp_alt); - DPRINTK("%s: %s\n", __func__, item->name); kfree(item); - return; + break; } mutex_unlock(&smp_alt); } -bool skip_smp_alternatives; -void alternatives_smp_switch(int smp) +void alternatives_enable_smp(void) { struct smp_alt_module *mod; @@ -436,34 +412,21 @@ void alternatives_smp_switch(int smp) pr_info("lockdep: fixing up alternatives\n"); #endif - if (noreplace_smp || smp_alt_once || skip_smp_alternatives) - return; - BUG_ON(!smp && (num_online_cpus() > 1)); + /* Why bother if there are no other CPUs? */ + BUG_ON(num_possible_cpus() == 1); mutex_lock(&smp_alt); - /* - * Avoid unnecessary switches because it forces JIT based VMs to - * throw away all cached translations, which can be quite costly. - */ - if (smp == smp_mode) { - /* nothing */ - } else if (smp) { + if (uniproc_patched) { pr_info("switching to SMP code\n"); + BUG_ON(num_online_cpus() != 1); clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_lock(mod->locks, mod->locks_end, mod->text, mod->text_end); - } else { - pr_info("switching to UP code\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); - set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); - list_for_each_entry(mod, &smp_alt_modules, next) - alternatives_smp_unlock(mod->locks, mod->locks_end, - mod->text, mod->text_end); + uniproc_patched = false; } - smp_mode = smp; mutex_unlock(&smp_alt); } @@ -540,40 +503,22 @@ void __init alternative_instructions(void) apply_alternatives(__alt_instructions, __alt_instructions_end); - /* switch to patch-once-at-boottime-only mode and free the - * tables in case we know the number of CPUs will never ever - * change */ -#ifdef CONFIG_HOTPLUG_CPU - if (num_possible_cpus() < 2) - smp_alt_once = 1; -#endif - #ifdef CONFIG_SMP - if (smp_alt_once) { - if (1 == num_possible_cpus()) { - pr_info("switching to UP code\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); - set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); - - alternatives_smp_unlock(__smp_locks, __smp_locks_end, - _text, _etext); - } - } else { + /* Patch to UP if other cpus not imminent. */ + if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { + uniproc_patched = true; alternatives_smp_module_add(NULL, "core kernel", __smp_locks, __smp_locks_end, _text, _etext); - - /* Only switch to UP mode if we don't immediately boot others */ - if (num_present_cpus() == 1 || setup_max_cpus <= 1) - alternatives_smp_switch(0); } -#endif - apply_paravirt(__parainstructions, __parainstructions_end); - if (smp_alt_once) + if (!uniproc_patched || num_possible_cpus() == 1) free_init_pages("SMP alternatives", (unsigned long)__smp_locks, (unsigned long)__smp_locks_end); +#endif + + apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 24deb3082328..b994cc84aa7e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -90,21 +90,6 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID); -/* - * Knob to control our willingness to enable the local APIC. - * - * +1=force-enable - */ -static int force_enable_local_apic __initdata; -/* - * APIC command line parameters - */ -static int __init parse_lapic(char *arg) -{ - force_enable_local_apic = 1; - return 0; -} -early_param("lapic", parse_lapic); /* Local APIC was disabled by the BIOS and enabled by the kernel */ static int enabled_via_apicbase; @@ -133,6 +118,25 @@ static inline void imcr_apic_to_pic(void) } #endif +/* + * Knob to control our willingness to enable the local APIC. + * + * +1=force-enable + */ +static int force_enable_local_apic __initdata; +/* + * APIC command line parameters + */ +static int __init parse_lapic(char *arg) +{ + if (config_enabled(CONFIG_X86_32) && !arg) + force_enable_local_apic = 1; + else if (!strncmp(arg, "notscdeadline", 13)) + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + return 0; +} +early_param("lapic", parse_lapic); + #ifdef CONFIG_X86_64 static int apic_calibrate_pmtmr __initdata; static __init int setup_apicpmtimer(char *s) @@ -315,6 +319,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 +#define TSC_DIVISOR 32 /* * This function sets up the local APIC timer, with a timeout of @@ -333,6 +338,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) lvtt_value = LOCAL_TIMER_VECTOR; if (!oneshot) lvtt_value |= APIC_LVT_TIMER_PERIODIC; + else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE; + if (!lapic_is_integrated()) lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV); @@ -341,6 +349,11 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) apic_write(APIC_LVTT, lvtt_value); + if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) { + printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); + return; + } + /* * Divide PICLK by 16 */ @@ -453,6 +466,16 @@ static int lapic_next_event(unsigned long delta, return 0; } +static int lapic_next_deadline(unsigned long delta, + struct clock_event_device *evt) +{ + u64 tsc; + + rdtscll(tsc); + wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); + return 0; +} + /* * Setup the lapic timer in periodic or oneshot mode */ @@ -533,7 +556,15 @@ static void __cpuinit setup_APIC_timer(void) memcpy(levt, &lapic_clockevent, sizeof(*levt)); levt->cpumask = cpumask_of(smp_processor_id()); - clockevents_register_device(levt); + if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_DUMMY); + levt->set_next_event = lapic_next_deadline; + clockevents_config_and_register(levt, + (tsc_khz / TSC_DIVISOR) * 1000, + 0xF, ~0UL); + } else + clockevents_register_device(levt); } /* @@ -661,7 +692,9 @@ static int __init calibrate_APIC_clock(void) * in the clockevent structure and return. */ - if (lapic_timer_frequency) { + if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + return 0; + } else if (lapic_timer_frequency) { apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", lapic_timer_frequency); lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, @@ -674,6 +707,9 @@ static int __init calibrate_APIC_clock(void) return 0; } + apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" + "calibrating APIC timer ...\n"); + local_irq_disable(); /* Replace the global interrupt handler */ @@ -811,9 +847,6 @@ void __init setup_boot_APIC_clock(void) return; } - apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" - "calibrating APIC timer ...\n"); - if (calibrate_APIC_clock()) { /* No broadcast on UP ! */ if (num_possible_cpus() > 1) @@ -1934,7 +1967,7 @@ void smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]); i++; v1 >>= 1; - }; + } apic_printk(APIC_DEBUG, KERN_CONT "\n"); diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index bc552cff2578..9c2aa89a11cb 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -22,6 +22,7 @@ #include <linux/hardirq.h> #include <linux/delay.h> +#include <asm/numachip/numachip.h> #include <asm/numachip/numachip_csr.h> #include <asm/smp.h> #include <asm/apic.h> @@ -30,7 +31,7 @@ static int numachip_system __read_mostly; -static struct apic apic_numachip __read_mostly; +static const struct apic apic_numachip __read_mostly; static unsigned int get_apic_id(unsigned long x) { @@ -179,6 +180,7 @@ static int __init numachip_system_init(void) return 0; x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; map_csrs(); @@ -199,7 +201,7 @@ static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static struct apic apic_numachip __refconst = { +static const struct apic apic_numachip __refconst = { .name = "NumaConnect system", .probe = numachip_probe, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c265593ec2cd..b739d398bb29 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -234,11 +234,11 @@ int __init arch_early_irq_init(void) zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node); /* * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0. + * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. */ if (i < legacy_pic->nr_legacy_irqs) { cfg[i].vector = IRQ0_VECTOR + i; - cpumask_set_cpu(0, cfg[i].domain); + cpumask_setall(cfg[i].domain); } } @@ -1141,7 +1141,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * allocation for the members that are not used anymore. */ cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = 1; + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); cpumask_and(cfg->domain, cfg->domain, tmp_mask); break; } @@ -1172,8 +1173,9 @@ next: current_vector = vector; current_offset = offset; if (cfg->vector) { - cfg->move_in_progress = 1; cpumask_copy(cfg->old_domain, cfg->domain); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); } for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; @@ -1241,12 +1243,6 @@ void __setup_vector_irq(int cpu) cfg = irq_get_chip_data(irq); if (!cfg) continue; - /* - * If it is a legacy IRQ handled by the legacy PIC, this cpu - * will be part of the irq_cfg's domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq)) - cpumask_set_cpu(cpu, cfg->domain); if (!cpumask_test_cpu(cpu, cfg->domain)) continue; @@ -1356,16 +1352,6 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; - /* - * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC - * can handle this irq and the apic driver is finialized at this point, - * update the cfg->domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && - cpumask_equal(cfg->domain, cpumask_of(0))) - apic->vector_allocation_domain(0, cfg->domain, - apic->target_cpus()); - if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; @@ -2199,9 +2185,11 @@ static int ioapic_retrigger_irq(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; unsigned long flags; + int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); + cpu = cpumask_first_and(cfg->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -2257,6 +2245,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) continue; cfg = irq_cfg(irq); + if (!cfg) + continue; + raw_spin_lock(&desc->lock); /* @@ -3314,8 +3305,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) int ret; if (irq_remapping_enabled) { - if (!setup_hpet_msi_remapped(irq, id)) - return -1; + ret = setup_hpet_msi_remapped(irq, id); + if (ret) + return ret; } ret = msi_compose_msg(NULL, irq, &msg, id); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 68de2dc962ec..28610822fb3c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -69,4 +69,7 @@ void common(void) { OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); OFFSET(BP_pref_address, boot_params, hdr.pref_address); OFFSET(BP_code32_start, boot_params, hdr.code32_start); + + BLANK(); + DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d30a6a9a0121..a0e067d3d96c 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -32,7 +32,7 @@ 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 +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o endif diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9d92e19039f0..15239fffd6fe 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -304,7 +304,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (cpu_has_topoext) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } + /* + * The way access filter has a performance penalty on some workloads. + * Disable it on the affected CPUs. + */ + if ((c->x86 == 0x15) && + (c->x86_model >= 0x02) && (c->x86_model < 0x20)) { + u64 val; + + if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) { + val |= 0x1E; + wrmsrl_safe(0xc0011021, val); + } + } + cpu_detect_cache_sizes(c); /* Multi core CPU? */ @@ -643,12 +657,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) detect_ht(c); #endif - if (c->extended_cpuid_level >= 0x80000006) { - if (cpuid_edx(0x80000006) & 0xf000) - num_cache_leaves = 4; - else - num_cache_leaves = 3; - } + init_amd_cacheinfo(c); if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); @@ -737,6 +746,69 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, } #endif +static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) +{ + tlb_flushall_shift = 5; + + if (c->x86 <= 0x11) + tlb_flushall_shift = 4; +} + +static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c) +{ + u32 ebx, eax, ecx, edx; + u16 mask = 0xfff; + + if (c->x86 < 0xf) + return; + + if (c->extended_cpuid_level < 0x80000006) + return; + + cpuid(0x80000006, &eax, &ebx, &ecx, &edx); + + tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask; + tlb_lli_4k[ENTRIES] = ebx & mask; + + /* + * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB + * characteristics from the CPUID function 0x80000005 instead. + */ + if (c->x86 == 0xf) { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + mask = 0xff; + } + + /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!((eax >> 16) & mask)) { + u32 a, b, c, d; + + cpuid(0x80000005, &a, &b, &c, &d); + tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff; + } else { + tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; + } + + /* a 4M entry uses two 2M entries */ + tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; + + /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!(eax & mask)) { + /* Erratum 658 */ + if (c->x86 == 0x15 && c->x86_model <= 0x1f) { + tlb_lli_2m[ENTRIES] = 1024; + } else { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + tlb_lli_2m[ENTRIES] = eax & 0xff; + } + } else + tlb_lli_2m[ENTRIES] = eax & mask; + + tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; + + cpu_set_tlb_flushall_shift(c); +} + static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, @@ -756,6 +828,7 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_size_cache = amd_size_cache, #endif .c_early_init = early_init_amd, + .c_detect_tlb = cpu_detect_tlb_amd, .c_bsp_init = bsp_init_amd, .c_init = init_amd, .c_x86_vendor = X86_VENDOR_AMD, diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c97bb7b5a9f8..92dfec986a48 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -107,53 +107,17 @@ static void __init check_hlt(void) } /* - * Most 386 processors have a bug where a POPAD can lock the - * machine even from user space. - */ - -static void __init check_popad(void) -{ -#ifndef CONFIG_X86_POPAD_OK - int res, inp = (int) &res; - - pr_info("Checking for popad bug... "); - __asm__ __volatile__( - "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " - : "=&a" (res) - : "d" (inp) - : "ecx", "edi"); - /* - * If this fails, it means that any user program may lock the - * CPU hard. Too bad. - */ - if (res != 12345678) - pr_cont("Buggy\n"); - else - pr_cont("OK\n"); -#endif -} - -/* * Check whether we are able to run this kernel safely on SMP. * - * - In order to run on a i386, we need to be compiled for i386 - * (for due to lack of "invlpg" and working WP on a i386) + * - i386 is no longer supported. * - In order to run on anything without a TSC, we need to be * compiled for a i486. */ static void __init check_config(void) { -/* - * We'd better not be a i386 if we're configured to use some - * i486+ only features! (WP works in supervisor mode and the - * new "invlpg" and "bswap" instructions) - */ -#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \ - defined(CONFIG_X86_BSWAP) - if (boot_cpu_data.x86 == 3) + if (boot_cpu_data.x86 < 4) panic("Kernel requires i486+ for 'invlpg' and other features"); -#endif } @@ -165,10 +129,14 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); #endif check_config(); - check_fpu(); check_hlt(); - check_popad(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); + + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + check_fpu(); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5fbc3c5fccc..9c3ab43a6954 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -259,23 +259,36 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) } #endif -static int disable_smep __cpuinitdata; static __init int setup_disable_smep(char *arg) { - disable_smep = 1; + setup_clear_cpu_cap(X86_FEATURE_SMEP); return 1; } __setup("nosmep", setup_disable_smep); -static __cpuinit void setup_smep(struct cpuinfo_x86 *c) +static __always_inline void setup_smep(struct cpuinfo_x86 *c) { - if (cpu_has(c, X86_FEATURE_SMEP)) { - if (unlikely(disable_smep)) { - setup_clear_cpu_cap(X86_FEATURE_SMEP); - clear_in_cr4(X86_CR4_SMEP); - } else - set_in_cr4(X86_CR4_SMEP); - } + if (cpu_has(c, X86_FEATURE_SMEP)) + set_in_cr4(X86_CR4_SMEP); +} + +static __init int setup_disable_smap(char *arg) +{ + setup_clear_cpu_cap(X86_FEATURE_SMAP); + return 1; +} +__setup("nosmap", setup_disable_smap); + +static __always_inline void setup_smap(struct cpuinfo_x86 *c) +{ + unsigned long eflags; + + /* This should have been cleared long ago */ + raw_local_save_flags(eflags); + BUG_ON(eflags & X86_EFLAGS_AC); + + if (cpu_has(c, X86_FEATURE_SMAP)) + set_in_cr4(X86_CR4_SMAP); } /* @@ -476,7 +489,7 @@ void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c) printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ - "tlb_flushall_shift is 0x%x\n", + "tlb_flushall_shift: %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], @@ -712,8 +725,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) c->cpu_index = 0; filter_cpuid_features(c, false); - setup_smep(c); - if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); } @@ -798,8 +809,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) c->phys_proc_id = c->initial_apicid; } - setup_smep(c); - get_model_name(c); /* Default name */ detect_nopl(c); @@ -864,6 +873,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); + /* Set up SMEP/SMAP */ + setup_smep(c); + setup_smap(c); + /* * The vendor-specific functions might have changed features. * Now we do "generic changes." @@ -942,8 +955,7 @@ void __init identify_boot_cpu(void) #else vgetcpu_set_mode(); #endif - if (boot_cpu_data.cpuid_level >= 2) - cpu_detect_tlb(&boot_cpu_data); + cpu_detect_tlb(&boot_cpu_data); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) @@ -1023,14 +1035,16 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", c->x86_model_id); + printk(KERN_CONT "%s", strim(c->x86_model_id)); else printk(KERN_CONT "%d86", c->x86); + printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model); + if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT " stepping %02x\n", c->x86_mask); + printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask); else - printk(KERN_CONT "\n"); + printk(KERN_CONT ")\n"); print_cpu_msr(c); } @@ -1113,11 +1127,10 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, - X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL); + X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| + X86_EFLAGS_IOPL|X86_EFLAGS_AC); } -unsigned long kernel_eflags; - /* * Copies of the original ist values from the tss are only accessed during * debugging, no special alignment required. @@ -1160,15 +1173,6 @@ DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif -/* Make sure %fs and %gs are initialized properly in idle threads */ -struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) -{ - memset(regs, 0, sizeof(struct pt_regs)); - regs->fs = __KERNEL_PERCPU; - regs->gs = __KERNEL_STACK_CANARY; - - return regs; -} #endif /* CONFIG_X86_64 */ /* @@ -1224,7 +1228,7 @@ void __cpuinit cpu_init(void) oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA - if (cpu != 0 && this_cpu_read(numa_node) == 0 && + if (this_cpu_read(numa_node) == 0 && early_cpu_to_node(cpu) != NUMA_NO_NODE) set_numa_node(early_cpu_to_node(cpu)); #endif @@ -1256,8 +1260,7 @@ void __cpuinit cpu_init(void) barrier(); x86_configure_nx(); - if (cpu != 0) - enable_x2apic(); + enable_x2apic(); /* * set up and load the per-CPU TSS @@ -1297,9 +1300,6 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); - xsave_init(); - - raw_local_save_flags(kernel_eflags); if (is_uv_system()) uv_cpu_init(); @@ -1352,6 +1352,5 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); - xsave_init(); } #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0a4ce2980a5a..fcaabd0432c5 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -612,10 +612,6 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc) static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) { - if (!cpu_has_invlpg) { - tlb_flushall_shift = -1; - return; - } switch ((c->x86 << 8) + c->x86_model) { case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ @@ -648,6 +644,10 @@ static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c) int i, j, n; unsigned int regs[4]; unsigned char *desc = (unsigned char *)regs; + + if (c->cpuid_level < 2) + return; + /* Number of times to iterate */ n = cpuid_eax(2) & 0xFF; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 9a7c90d80bc4..fe9edec6698a 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -538,7 +538,11 @@ __cpuinit cpuid4_cache_lookup_regs(int index, unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - amd_cpuid4(index, &eax, &ebx, &ecx); + if (cpu_has_topoext) + cpuid_count(0x8000001d, index, &eax.full, + &ebx.full, &ecx.full, &edx); + else + amd_cpuid4(index, &eax, &ebx, &ecx); amd_init_l3_cache(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); @@ -557,21 +561,39 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int __cpuinit find_num_cache_leaves(void) +static int __cpuinit find_num_cache_leaves(struct cpuinfo_x86 *c) { - unsigned int eax, ebx, ecx, edx; + unsigned int eax, ebx, ecx, edx, op; union _cpuid4_leaf_eax cache_eax; int i = -1; + if (c->x86_vendor == X86_VENDOR_AMD) + op = 0x8000001d; + else + op = 4; + do { ++i; - /* Do cpuid(4) loop to find out num_cache_leaves */ - cpuid_count(4, i, &eax, &ebx, &ecx, &edx); + /* Do cpuid(op) loop to find out num_cache_leaves */ + cpuid_count(op, i, &eax, &ebx, &ecx, &edx); cache_eax.full = eax; } while (cache_eax.split.type != CACHE_TYPE_NULL); return i; } +void __cpuinit init_amd_cacheinfo(struct cpuinfo_x86 *c) +{ + + if (cpu_has_topoext) { + num_cache_leaves = find_num_cache_leaves(c); + } else if (c->extended_cpuid_level >= 0x80000006) { + if (cpuid_edx(0x80000006) & 0xf000) + num_cache_leaves = 4; + else + num_cache_leaves = 3; + } +} + unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ @@ -588,7 +610,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) if (is_initialized == 0) { /* Init num_cache_leaves from boot CPU */ - num_cache_leaves = find_num_cache_leaves(); + num_cache_leaves = find_num_cache_leaves(c); is_initialized++; } @@ -728,37 +750,50 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf; - int ret, i, sibling; - struct cpuinfo_x86 *c = &cpu_data(cpu); + int i, sibling; - ret = 0; - if (index == 3) { - ret = 1; - for_each_cpu(i, cpu_llc_shared_mask(cpu)) { + if (cpu_has_topoext) { + unsigned int apicid, nshared, first, last; + + if (!per_cpu(ici_cpuid4_info, cpu)) + return 0; + + this_leaf = CPUID4_INFO_IDX(cpu, index); + nshared = this_leaf->base.eax.split.num_threads_sharing + 1; + apicid = cpu_data(cpu).apicid; + first = apicid - (apicid % nshared); + last = first + nshared - 1; + + for_each_online_cpu(i) { + apicid = cpu_data(i).apicid; + if ((apicid < first) || (apicid > last)) + continue; if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { - if (!cpu_online(sibling)) + + for_each_online_cpu(sibling) { + apicid = cpu_data(sibling).apicid; + if ((apicid < first) || (apicid > last)) continue; set_bit(sibling, this_leaf->shared_cpu_map); } } - } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) { - ret = 1; - for_each_cpu(i, cpu_sibling_mask(cpu)) { + } else if (index == 3) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { if (!cpu_online(sibling)) continue; set_bit(sibling, this_leaf->shared_cpu_map); } } - } + } else + return 0; - return ret; + return 1; } static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) @@ -991,7 +1026,7 @@ static struct attribute ** __cpuinit amd_l3_attrs(void) if (attrs) return attrs; - n = sizeof (default_attrs) / sizeof (struct attribute *); + n = ARRAY_SIZE(default_attrs); if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) n += 2; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index fc4beb393577..ddc72f839332 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -78,6 +78,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) } static cpumask_var_t mce_inject_cpumask; +static DEFINE_MUTEX(mce_inject_mutex); static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { @@ -194,7 +195,11 @@ static void raise_mce(struct mce *m) put_online_cpus(); } else #endif + { + preempt_disable(); raise_local(); + preempt_enable(); + } } /* Error injection interface */ @@ -225,7 +230,10 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, * so do it a jiffie or two later everywhere. */ schedule_timeout(2); + + mutex_lock(&mce_inject_mutex); raise_mce(&m); + mutex_unlock(&mce_inject_mutex); return usize; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index ed44c8a65858..5b7d4fa5d3b7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -24,10 +24,20 @@ struct mce_bank { int mce_severity(struct mce *a, int tolerant, char **msg); struct dentry *mce_get_debugfs_dir(void); -extern int mce_ser; - extern struct mce_bank *mce_banks; +#ifdef CONFIG_X86_MCE_INTEL +unsigned long mce_intel_adjust_timer(unsigned long interval); +void mce_intel_cmci_poll(void); +void mce_intel_hcpu_update(unsigned long cpu); +#else +# define mce_intel_adjust_timer mce_adjust_timer_default +static inline void mce_intel_cmci_poll(void) { } +static inline void mce_intel_hcpu_update(unsigned long cpu) { } +#endif + +void mce_timer_kick(unsigned long interval); + #ifdef CONFIG_ACPI_APEI int apei_write_mce(struct mce *m); ssize_t apei_read_mce(struct mce *m, u64 *record_id); diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 13017626f9a8..beb1f1689e52 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -193,9 +193,9 @@ int mce_severity(struct mce *m, int tolerant, char **msg) continue; if ((m->mcgstatus & s->mcgmask) != s->mcgres) continue; - if (s->ser == SER_REQUIRED && !mce_ser) + if (s->ser == SER_REQUIRED && !mca_cfg.ser) continue; - if (s->ser == NO_SER && mce_ser) + if (s->ser == NO_SER && mca_cfg.ser) continue; if (s->context && ctx != s->context) continue; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 292d0258311c..80dbda84f1c3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -58,33 +58,26 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define CREATE_TRACE_POINTS #include <trace/events/mce.h> -int mce_disabled __read_mostly; - #define SPINUNIT 100 /* 100ns */ atomic_t mce_entry; DEFINE_PER_CPU(unsigned, mce_exception_count); -/* - * Tolerant levels: - * 0: always panic on uncorrected errors, log corrected errors - * 1: panic or SIGBUS on uncorrected errors, log corrected errors - * 2: SIGBUS or log uncorrected errors (if possible), log corrected errors - * 3: never panic or SIGBUS, log all errors (for testing only) - */ -static int tolerant __read_mostly = 1; -static int banks __read_mostly; -static int rip_msr __read_mostly; -static int mce_bootlog __read_mostly = -1; -static int monarch_timeout __read_mostly = -1; -static int mce_panic_timeout __read_mostly; -static int mce_dont_log_ce __read_mostly; -int mce_cmci_disabled __read_mostly; -int mce_ignore_ce __read_mostly; -int mce_ser __read_mostly; - -struct mce_bank *mce_banks __read_mostly; +struct mce_bank *mce_banks __read_mostly; + +struct mca_config mca_cfg __read_mostly = { + .bootlog = -1, + /* + * Tolerant levels: + * 0: always panic on uncorrected errors, log corrected errors + * 1: panic or SIGBUS on uncorrected errors, log corrected errors + * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors + * 3: never panic or SIGBUS, log all errors (for testing only) + */ + .tolerant = 1, + .monarch_timeout = -1 +}; /* User mode helper program triggered by machine check event */ static unsigned long mce_need_notify; @@ -301,7 +294,7 @@ static void wait_for_panic(void) while (timeout-- > 0) udelay(1); if (panic_timeout == 0) - panic_timeout = mce_panic_timeout; + panic_timeout = mca_cfg.panic_timeout; panic("Panicing machine check CPU died"); } @@ -359,7 +352,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); if (!fake_panic) { if (panic_timeout == 0) - panic_timeout = mce_panic_timeout; + panic_timeout = mca_cfg.panic_timeout; panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -371,7 +364,7 @@ static int msr_to_offset(u32 msr) { unsigned bank = __this_cpu_read(injectm.bank); - if (msr == rip_msr) + if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); if (msr == MSR_IA32_MCx_STATUS(bank)) return offsetof(struct mce, status); @@ -450,8 +443,8 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) m->cs |= 3; } /* Use accurate RIP reporting if available. */ - if (rip_msr) - m->ip = mce_rdmsrl(rip_msr); + if (mca_cfg.rip_msr) + m->ip = mce_rdmsrl(mca_cfg.rip_msr); } } @@ -512,7 +505,7 @@ static int mce_ring_add(unsigned long pfn) int mce_available(struct cpuinfo_x86 *c) { - if (mce_disabled) + if (mca_cfg.disabled) return 0; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -564,7 +557,7 @@ static void mce_read_aux(struct mce *m, int i) /* * Mask the reported address by the reported granularity. */ - if (mce_ser && (m->status & MCI_STATUS_MISCV)) { + if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) { u8 shift = MCI_MISC_ADDR_LSB(m->misc); m->addr >>= shift; m->addr <<= shift; @@ -598,7 +591,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) continue; @@ -619,7 +612,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * TBD do the same check for MCI_STATUS_EN here? */ if (!(flags & MCP_UC) && - (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC))) + (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; mce_read_aux(&m, i); @@ -630,7 +623,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); /* @@ -657,14 +650,14 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, { int i, ret = 0; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY) + if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY) ret = 1; } return ret; @@ -695,11 +688,11 @@ static int mce_timed_out(u64 *t) rmb(); if (atomic_read(&mce_paniced)) wait_for_panic(); - if (!monarch_timeout) + if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { /* CHECKME: Make panic default for 1 too? */ - if (tolerant < 1) + if (mca_cfg.tolerant < 1) mce_panic("Timeout synchronizing machine check over CPUs", NULL, NULL); cpu_missing = 1; @@ -749,7 +742,8 @@ static void mce_reign(void) * Grade the severity of the errors of all the CPUs. */ for_each_possible_cpu(cpu) { - int severity = mce_severity(&per_cpu(mces_seen, cpu), tolerant, + int severity = mce_severity(&per_cpu(mces_seen, cpu), + mca_cfg.tolerant, &nmsg); if (severity > global_worst) { msg = nmsg; @@ -763,7 +757,7 @@ static void mce_reign(void) * This dumps all the mces in the log buffer and stops the * other CPUs. */ - if (m && global_worst >= MCE_PANIC_SEVERITY && tolerant < 3) + if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) mce_panic("Fatal Machine check", m, msg); /* @@ -776,7 +770,7 @@ static void mce_reign(void) * No machine check event found. Must be some external * source or one CPU is hung. Panic. */ - if (global_worst <= MCE_KEEP_SEVERITY && tolerant < 3) + if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) mce_panic("Machine check from unknown source", NULL, NULL); /* @@ -800,7 +794,7 @@ static int mce_start(int *no_way_out) { int order; int cpus = num_online_cpus(); - u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC; + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; if (!timeout) return -1; @@ -864,7 +858,7 @@ static int mce_start(int *no_way_out) static int mce_end(int order) { int ret = -1; - u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC; + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; if (!timeout) goto reset; @@ -945,7 +939,7 @@ static void mce_clear_state(unsigned long *toclear) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { if (test_bit(i, toclear)) mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); } @@ -1010,6 +1004,7 @@ static void mce_clear_info(struct mce_info *mi) */ void do_machine_check(struct pt_regs *regs, long error_code) { + struct mca_config *cfg = &mca_cfg; struct mce m, *final; int i; int worst = 0; @@ -1021,7 +1016,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) int order; /* * If no_way_out gets set, there is no safe way to recover from this - * MCE. If tolerant is cranked up, we'll try anyway. + * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; /* @@ -1037,7 +1032,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) this_cpu_inc(mce_exception_count); - if (!banks) + if (!cfg->banks) goto out; mce_gather_info(&m, regs); @@ -1064,7 +1059,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * because the first one to see it will clear it. */ order = mce_start(&no_way_out); - for (i = 0; i < banks; i++) { + for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) continue; @@ -1083,7 +1078,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * Non uncorrected or non signaled errors are handled by * machine_check_poll. Leave them alone, unless this panics. */ - if (!(m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && !no_way_out) continue; @@ -1092,7 +1087,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK); - severity = mce_severity(&m, tolerant, NULL); + severity = mce_severity(&m, cfg->tolerant, NULL); /* * When machine check was for corrected handler don't touch, @@ -1116,7 +1111,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * When the ring overflows we just ignore the AO error. * RED-PEN add some logging mechanism when * usable_address or mce_add_ring fails. - * RED-PEN don't ignore overflow for tolerant == 0 + * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0 */ if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) mce_ring_add(m.addr >> PAGE_SHIFT); @@ -1148,7 +1143,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * issues we try to recover, or limit damage to the current * process. */ - if (tolerant < 3) { + if (cfg->tolerant < 3) { if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); if (worst == MCE_AR_SEVERITY) { @@ -1266,6 +1261,14 @@ static unsigned long check_interval = 5 * 60; /* 5 minutes */ static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); +static unsigned long mce_adjust_timer_default(unsigned long interval) +{ + return interval; +} + +static unsigned long (*mce_adjust_timer)(unsigned long interval) = + mce_adjust_timer_default; + static void mce_timer_fn(unsigned long data) { struct timer_list *t = &__get_cpu_var(mce_timer); @@ -1276,6 +1279,7 @@ static void mce_timer_fn(unsigned long data) if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_poll_banks)); + mce_intel_cmci_poll(); } /* @@ -1283,14 +1287,38 @@ static void mce_timer_fn(unsigned long data) * polling interval, otherwise increase the polling interval. */ iv = __this_cpu_read(mce_next_interval); - if (mce_notify_irq()) + if (mce_notify_irq()) { iv = max(iv / 2, (unsigned long) HZ/100); - else + } else { iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); + iv = mce_adjust_timer(iv); + } __this_cpu_write(mce_next_interval, iv); + /* Might have become 0 after CMCI storm subsided */ + if (iv) { + t->expires = jiffies + iv; + add_timer_on(t, smp_processor_id()); + } +} - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); +/* + * Ensure that the timer is firing in @interval from now. + */ +void mce_timer_kick(unsigned long interval) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned long when = jiffies + interval; + unsigned long iv = __this_cpu_read(mce_next_interval); + + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); + } else { + t->expires = round_jiffies(when); + add_timer_on(t, smp_processor_id()); + } + if (interval < iv) + __this_cpu_write(mce_next_interval, interval); } /* Must not be called in IRQ context where del_timer_sync() can deadlock */ @@ -1343,11 +1371,13 @@ EXPORT_SYMBOL_GPL(mce_notify_irq); static int __cpuinit __mcheck_cpu_mce_banks_init(void) { int i; + u8 num_banks = mca_cfg.banks; - mce_banks = kzalloc(banks * sizeof(struct mce_bank), GFP_KERNEL); + mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL); if (!mce_banks) return -ENOMEM; - for (i = 0; i < banks; i++) { + + for (i = 0; i < num_banks; i++) { struct mce_bank *b = &mce_banks[i]; b->ctl = -1ULL; @@ -1367,7 +1397,7 @@ static int __cpuinit __mcheck_cpu_cap_init(void) rdmsrl(MSR_IA32_MCG_CAP, cap); b = cap & MCG_BANKCNT_MASK; - if (!banks) + if (!mca_cfg.banks) pr_info("CPU supports %d MCE banks\n", b); if (b > MAX_NR_BANKS) { @@ -1377,8 +1407,9 @@ static int __cpuinit __mcheck_cpu_cap_init(void) } /* Don't support asymmetric configurations today */ - WARN_ON(banks != 0 && b != banks); - banks = b; + WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks); + mca_cfg.banks = b; + if (!mce_banks) { int err = __mcheck_cpu_mce_banks_init(); @@ -1388,25 +1419,29 @@ static int __cpuinit __mcheck_cpu_cap_init(void) /* Use accurate RIP reporting if available. */ if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9) - rip_msr = MSR_IA32_MCG_EIP; + mca_cfg.rip_msr = MSR_IA32_MCG_EIP; if (cap & MCG_SER_P) - mce_ser = 1; + mca_cfg.ser = true; return 0; } static void __mcheck_cpu_init_generic(void) { + enum mcp_flags m_fl = 0; mce_banks_t all_banks; u64 cap; int i; + if (!mca_cfg.bootlog) + m_fl = MCP_DONTLOG; + /* * Log the machine checks left over from the previous reset. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks); + machine_check_poll(MCP_UC | m_fl, &all_banks); set_in_cr4(X86_CR4_MCE); @@ -1414,7 +1449,7 @@ static void __mcheck_cpu_init_generic(void) if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (!b->init) @@ -1455,6 +1490,8 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) /* Add per CPU specific workarounds here */ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { + struct mca_config *cfg = &mca_cfg; + if (c->x86_vendor == X86_VENDOR_UNKNOWN) { pr_info("unknown CPU type - not enabling MCE support\n"); return -EOPNOTSUPP; @@ -1462,7 +1499,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD) { - if (c->x86 == 15 && banks > 4) { + if (c->x86 == 15 && cfg->banks > 4) { /* * disable GART TBL walk error reporting, which * trips off incorrectly with the IOMMU & 3ware @@ -1470,18 +1507,18 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 <= 17 && mce_bootlog < 0) { + if (c->x86 <= 17 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: */ - mce_bootlog = 0; + cfg->bootlog = 0; } /* * Various K7s with broken bank 0 around. Always disable * by default. */ - if (c->x86 == 6 && banks > 0) + if (c->x86 == 6 && cfg->banks > 0) mce_banks[0].ctl = 0; /* @@ -1532,7 +1569,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * valid event later, merely don't write CTL0. */ - if (c->x86 == 6 && c->x86_model < 0x1A && banks > 0) + if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0) mce_banks[0].init = 0; /* @@ -1540,23 +1577,23 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * synchronization with a one second timeout. */ if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && - monarch_timeout < 0) - monarch_timeout = USEC_PER_SEC; + cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; /* * There are also broken BIOSes on some Pentium M and * earlier systems: */ - if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) - mce_bootlog = 0; + if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0) + cfg->bootlog = 0; if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; } - if (monarch_timeout < 0) - monarch_timeout = 0; - if (mce_bootlog != 0) - mce_panic_timeout = 30; + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = 0; + if (cfg->bootlog != 0) + cfg->panic_timeout = 30; return 0; } @@ -1585,6 +1622,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); + mce_adjust_timer = mce_intel_adjust_timer; break; case X86_VENDOR_AMD: mce_amd_feature_init(c); @@ -1594,23 +1632,28 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } -static void __mcheck_cpu_init_timer(void) +static void mce_start_timer(unsigned int cpu, struct timer_list *t) { - struct timer_list *t = &__get_cpu_var(mce_timer); - unsigned long iv = check_interval * HZ; + unsigned long iv = mce_adjust_timer(check_interval * HZ); - setup_timer(t, mce_timer_fn, smp_processor_id()); + __this_cpu_write(mce_next_interval, iv); - if (mce_ignore_ce) + if (mca_cfg.ignore_ce || !iv) return; - __this_cpu_write(mce_next_interval, iv); - if (!iv) - return; t->expires = round_jiffies(jiffies + iv); add_timer_on(t, smp_processor_id()); } +static void __mcheck_cpu_init_timer(void) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned int cpu = smp_processor_id(); + + setup_timer(t, mce_timer_fn, cpu); + mce_start_timer(cpu, t); +} + /* Handle unconfigured int18 (should never happen) */ static void unexpected_machine_check(struct pt_regs *regs, long error_code) { @@ -1628,7 +1671,7 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) = */ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) { - if (mce_disabled) + if (mca_cfg.disabled) return; if (__mcheck_cpu_ancient_init(c)) @@ -1638,7 +1681,7 @@ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) return; if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) { - mce_disabled = 1; + mca_cfg.disabled = true; return; } @@ -1907,9 +1950,12 @@ static struct miscdevice mce_chrdev_device = { * check, or 0 to not wait * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. * mce=nobootlog Don't log MCEs from before booting. + * mce=bios_cmci_threshold Don't program the CMCI threshold */ static int __init mcheck_enable(char *str) { + struct mca_config *cfg = &mca_cfg; + if (*str == 0) { enable_p5_mce(); return 1; @@ -1917,20 +1963,22 @@ static int __init mcheck_enable(char *str) if (*str == '=') str++; if (!strcmp(str, "off")) - mce_disabled = 1; + cfg->disabled = true; else if (!strcmp(str, "no_cmci")) - mce_cmci_disabled = 1; + cfg->cmci_disabled = true; else if (!strcmp(str, "dont_log_ce")) - mce_dont_log_ce = 1; + cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) - mce_ignore_ce = 1; + cfg->ignore_ce = true; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) - mce_bootlog = (str[0] == 'b'); + cfg->bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + cfg->bios_cmci_threshold = true; else if (isdigit(str[0])) { - get_option(&str, &tolerant); + get_option(&str, &(cfg->tolerant)); if (*str == ',') { ++str; - get_option(&str, &monarch_timeout); + get_option(&str, &(cfg->monarch_timeout)); } } else { pr_info("mce argument %s ignored. Please use /sys\n", str); @@ -1959,7 +2007,7 @@ static int mce_disable_error_reporting(void) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2099,15 +2147,15 @@ static ssize_t set_ignore_ce(struct device *s, if (strict_strtoull(buf, 0, &new) < 0) return -EINVAL; - if (mce_ignore_ce ^ !!new) { + if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ mce_timer_delete_all(); on_each_cpu(mce_disable_cmci, NULL, 1); - mce_ignore_ce = 1; + mca_cfg.ignore_ce = true; } else { /* enable ce features */ - mce_ignore_ce = 0; + mca_cfg.ignore_ce = false; on_each_cpu(mce_enable_ce, (void *)1, 1); } } @@ -2123,14 +2171,14 @@ static ssize_t set_cmci_disabled(struct device *s, if (strict_strtoull(buf, 0, &new) < 0) return -EINVAL; - if (mce_cmci_disabled ^ !!new) { + if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ on_each_cpu(mce_disable_cmci, NULL, 1); - mce_cmci_disabled = 1; + mca_cfg.cmci_disabled = true; } else { /* enable cmci */ - mce_cmci_disabled = 0; + mca_cfg.cmci_disabled = false; on_each_cpu(mce_enable_ce, NULL, 1); } } @@ -2147,9 +2195,9 @@ static ssize_t store_int_with_restart(struct device *s, } static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); -static DEVICE_INT_ATTR(tolerant, 0644, tolerant); -static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout); -static DEVICE_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce); +static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); +static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); +static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static struct dev_ext_attribute dev_attr_check_interval = { __ATTR(check_interval, 0644, device_show_int, store_int_with_restart), @@ -2157,13 +2205,13 @@ static struct dev_ext_attribute dev_attr_check_interval = { }; static struct dev_ext_attribute dev_attr_ignore_ce = { - __ATTR(ignore_ce, 0644, device_show_int, set_ignore_ce), - &mce_ignore_ce + __ATTR(ignore_ce, 0644, device_show_bool, set_ignore_ce), + &mca_cfg.ignore_ce }; static struct dev_ext_attribute dev_attr_cmci_disabled = { - __ATTR(cmci_disabled, 0644, device_show_int, set_cmci_disabled), - &mce_cmci_disabled + __ATTR(cmci_disabled, 0644, device_show_bool, set_cmci_disabled), + &mca_cfg.cmci_disabled }; static struct device_attribute *mce_device_attrs[] = { @@ -2210,7 +2258,7 @@ static __cpuinit int mce_device_create(unsigned int cpu) if (err) goto error; } - for (j = 0; j < banks; j++) { + for (j = 0; j < mca_cfg.banks; j++) { err = device_create_file(dev, &mce_banks[j].attr); if (err) goto error2; @@ -2242,7 +2290,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) for (i = 0; mce_device_attrs[i]; i++) device_remove_file(dev, mce_device_attrs[i]); - for (i = 0; i < banks; i++) + for (i = 0; i < mca_cfg.banks; i++) device_remove_file(dev, &mce_banks[i].attr); device_unregister(dev); @@ -2261,7 +2309,7 @@ static void __cpuinit mce_disable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2279,7 +2327,7 @@ static void __cpuinit mce_reenable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_reenable(); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2294,38 +2342,33 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) unsigned int cpu = (unsigned long)hcpu; struct timer_list *t = &per_cpu(mce_timer, cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: mce_device_create(cpu); if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); break; case CPU_DEAD: - case CPU_DEAD_FROZEN: if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); mce_device_remove(cpu); + mce_intel_hcpu_update(cpu); break; case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - del_timer_sync(t); smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + del_timer_sync(t); break; case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - if (!mce_ignore_ce && check_interval) { - t->expires = round_jiffies(jiffies + - per_cpu(mce_next_interval, cpu)); - add_timer_on(t, cpu); - } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + mce_start_timer(cpu, t); break; - case CPU_POST_DEAD: + } + + if (action == CPU_POST_DEAD) { /* intentionally ignoring frozen here */ cmci_rediscover(cpu); - break; } + return NOTIFY_OK; } @@ -2337,7 +2380,7 @@ static __init void mce_init_banks(void) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; struct device_attribute *a = &b->attr; @@ -2388,7 +2431,7 @@ device_initcall_sync(mcheck_init_device); */ static int __init mcheck_disable(char *str) { - mce_disabled = 1; + mca_cfg.disabled = true; return 1; } __setup("nomce", mcheck_disable); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index c4e916d77378..1ac581f38dfa 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -6,7 +6,7 @@ * * Written by Jacob Shin - AMD, Inc. * - * Support: borislav.petkov@amd.com + * Maintained by: Borislav Petkov <bp@alien8.de> * * April 2006 * - added support for AMD Family 0x10 processors @@ -576,12 +576,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) int err = 0; if (shared_bank[bank]) { - nb = node_to_amd_nb(amd_get_nb_id(cpu)); - WARN_ON(!nb); /* threshold descriptor already initialized on this node? */ - if (nb->bank4) { + if (nb && nb->bank4) { /* yes, use it */ b = nb->bank4; err = kobject_add(b->kobj, &dev->kobj, name); @@ -615,8 +613,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) atomic_set(&b->cpus, 1); /* nb is already initialized, see above */ - WARN_ON(nb->bank4); - nb->bank4 = b; + if (nb) { + WARN_ON(nb->bank4); + nb->bank4 = b; + } } err = allocate_threshold_blocks(cpu, bank, 0, diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 38e49bc95ffc..402c454fbff0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -15,6 +15,8 @@ #include <asm/msr.h> #include <asm/mce.h> +#include "mce-internal.h" + /* * Support for Intel Correct Machine Check Interrupts. This allows * the CPU to raise an interrupt when a corrected machine check happened. @@ -30,13 +32,28 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); */ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); -#define CMCI_THRESHOLD 1 +#define CMCI_THRESHOLD 1 +#define CMCI_POLL_INTERVAL (30 * HZ) +#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_THRESHOLD 15 + +static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); +static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); +static DEFINE_PER_CPU(unsigned int, cmci_storm_state); + +enum { + CMCI_STORM_NONE, + CMCI_STORM_ACTIVE, + CMCI_STORM_SUBSIDED, +}; + +static atomic_t cmci_storm_on_cpus; static int cmci_supported(int *banks) { u64 cap; - if (mce_cmci_disabled || mce_ignore_ce) + if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) return 0; /* @@ -53,6 +70,93 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +void mce_intel_cmci_poll(void) +{ + if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) + return; + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); +} + +void mce_intel_hcpu_update(unsigned long cpu) +{ + if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) + atomic_dec(&cmci_storm_on_cpus); + + per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +} + +unsigned long mce_intel_adjust_timer(unsigned long interval) +{ + int r; + + if (interval < CMCI_POLL_INTERVAL) + return interval; + + switch (__this_cpu_read(cmci_storm_state)) { + case CMCI_STORM_ACTIVE: + /* + * We switch back to interrupt mode once the poll timer has + * silenced itself. That means no events recorded and the + * timer interval is back to our poll interval. + */ + __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); + r = atomic_sub_return(1, &cmci_storm_on_cpus); + if (r == 0) + pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ + + case CMCI_STORM_SUBSIDED: + /* + * We wait for all cpus to go back to SUBSIDED + * state. When that happens we switch back to + * interrupt mode. + */ + if (!atomic_read(&cmci_storm_on_cpus)) { + __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); + cmci_reenable(); + cmci_recheck(); + } + return CMCI_POLL_INTERVAL; + default: + /* + * We have shiny weather. Let the poll do whatever it + * thinks. + */ + return interval; + } +} + +static bool cmci_storm_detect(void) +{ + unsigned int cnt = __this_cpu_read(cmci_storm_cnt); + unsigned long ts = __this_cpu_read(cmci_time_stamp); + unsigned long now = jiffies; + int r; + + if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) + return true; + + if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { + cnt++; + } else { + cnt = 1; + __this_cpu_write(cmci_time_stamp, now); + } + __this_cpu_write(cmci_storm_cnt, cnt); + + if (cnt <= CMCI_STORM_THRESHOLD) + return false; + + cmci_clear(); + __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); + r = atomic_add_return(1, &cmci_storm_on_cpus); + mce_timer_kick(CMCI_POLL_INTERVAL); + + if (r == 1) + pr_notice("CMCI storm detected: switching to poll mode\n"); + return true; +} + /* * The interrupt handler. This is called on every event. * Just call the poller directly to log any events. @@ -61,33 +165,28 @@ static int cmci_supported(int *banks) */ static void intel_threshold_interrupt(void) { + if (cmci_storm_detect()) + return; machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); mce_notify_irq(); } -static void print_update(char *type, int *hdr, int num) -{ - if (*hdr == 0) - printk(KERN_INFO "CPU %d MCA banks", smp_processor_id()); - *hdr = 1; - printk(KERN_CONT " %s:%d", type, num); -} - /* * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks * on this CPU. Use the algorithm recommended in the SDM to discover shared * banks. */ -static void cmci_discover(int banks, int boot) +static void cmci_discover(int banks) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); unsigned long flags; - int hdr = 0; int i; + int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; + int bios_zero_thresh = 0; if (test_bit(i, owned)) continue; @@ -96,29 +195,52 @@ static void cmci_discover(int banks, int boot) /* Already owned by someone else? */ if (val & MCI_CTL2_CMCI_EN) { - if (test_and_clear_bit(i, owned) && !boot) - print_update("SHD", &hdr, i); + clear_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); continue; } - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD; + if (!mca_cfg.bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { + /* + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. + */ + bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; + } + + val |= MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Did the enable bit stick? -- the bank supports CMCI */ if (val & MCI_CTL2_CMCI_EN) { - if (!test_and_set_bit(i, owned) && !boot) - print_update("CMCI", &hdr, i); + set_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + bios_wrong_thresh = 1; } else { WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); - if (hdr) - printk(KERN_CONT "\n"); + if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) { + pr_info_once( + "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); + pr_info_once( + "bios_cmci_threshold: Make sure your BIOS supports this boot option\n"); + } } /* @@ -156,41 +278,46 @@ void cmci_clear(void) continue; /* Disable CMCI */ rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK); + val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } +static long cmci_rediscover_work_func(void *arg) +{ + int banks; + + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks); + + return 0; +} + /* * After a CPU went down cycle through all the others and rediscover * Must run in process context. */ void cmci_rediscover(int dying) { - int banks; - int cpu; - cpumask_var_t old; + int cpu, banks; if (!cmci_supported(&banks)) return; - if (!alloc_cpumask_var(&old, GFP_KERNEL)) - return; - cpumask_copy(old, ¤t->cpus_allowed); for_each_online_cpu(cpu) { if (cpu == dying) continue; - if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) + + if (cpu == smp_processor_id()) { + cmci_rediscover_work_func(NULL); continue; - /* Recheck banks in case CPUs don't all have the same */ - if (cmci_supported(&banks)) - cmci_discover(banks, 0); - } + } - set_cpus_allowed_ptr(current, old); - free_cpumask_var(old); + work_on_cpu(cpu, cmci_rediscover_work_func, NULL); + } } /* @@ -200,7 +327,7 @@ void cmci_reenable(void) { int banks; if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } static void intel_init_cmci(void) @@ -211,7 +338,7 @@ static void intel_init_cmci(void) return; mce_threshold_vector = intel_threshold_interrupt; - cmci_discover(banks, 1); + cmci_discover(banks); /* * For CPU #0 this runs with still disabled APIC, but that's * ok because only the vector is set up. We still do another diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl index c7b3fe2d72e0..091972ef49de 100644 --- a/arch/x86/kernel/cpu/mkcapflags.pl +++ b/arch/x86/kernel/cpu/mkcapflags.pl @@ -8,7 +8,10 @@ open(IN, "< $in\0") or die "$0: cannot open: $in: $!\n"; open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n"; -print OUT "#include <asm/cpufeature.h>\n\n"; +print OUT "#ifndef _ASM_X86_CPUFEATURE_H\n"; +print OUT "#include <asm/cpufeature.h>\n"; +print OUT "#endif\n"; +print OUT "\n"; print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n"; %features = (); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6b96110bb0c3..726bf963c227 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -606,7 +606,7 @@ void __init mtrr_bp_init(void) /* * This is an AMD specific MSR, but we assume(hope?) that - * Intel will implement it to when they extend the address + * Intel will implement it too when they extend the address * bus of the Xeon. */ if (cpuid_eax(0x80000000) >= 0x80000008) { @@ -695,11 +695,16 @@ void mtrr_ap_init(void) } /** - * Save current fixed-range MTRR state of the BSP + * Save current fixed-range MTRR state of the first cpu in cpu_online_mask. */ void mtrr_save_state(void) { - smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1); + int first_cpu; + + get_online_cpus(); + first_cpu = cpumask_first(cpu_online_mask); + smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); + put_online_cpus(); } void set_mtrr_aps_delayed_init(void) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 915b876edd1e..4428fd178bce 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -208,12 +208,14 @@ static bool check_hw_exists(void) } /* - * Now write a value and read it back to see if it matches, - * this is needed to detect certain hardware emulators (qemu/kvm) - * that don't trap on the MSR access and always return 0s. + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ - val = 0xabcdUL; reg = x86_pmu_event_addr(0); + if (rdmsrl_safe(reg, &val)) + goto msr_fail; + val ^= 0xffffUL; ret = wrmsrl_safe(reg, val); ret |= rdmsrl_safe(reg, &val_new); if (ret || val != val_new) @@ -338,6 +340,9 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; + + if (!attr->exclude_guest) + return -EOPNOTSUPP; } hwc->config |= config; @@ -380,6 +385,9 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip) { int precise = 0; + if (!event->attr.exclude_guest) + return -EOPNOTSUPP; + /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; @@ -1308,6 +1316,121 @@ static struct attribute_group x86_pmu_format_group = { .attrs = NULL, }; +struct perf_pmu_events_attr { + struct device_attribute attr; + u64 id; +}; + +/* + * Remove all undefined events (x86_pmu.event_map(id) == 0) + * out of events_attr attributes. + */ +static void __init filter_events(struct attribute **attrs) +{ + int i, j; + + for (i = 0; attrs[i]; i++) { + if (x86_pmu.event_map(i)) + continue; + + for (j = i; attrs[j]; j++) + attrs[j] = attrs[j + 1]; + + /* Check the shifted attr. */ + i--; + } +} + +static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = \ + container_of(attr, struct perf_pmu_events_attr, attr); + + u64 config = x86_pmu.event_map(pmu_attr->id); + return x86_pmu.events_sysfs_show(page, config); +} + +#define EVENT_VAR(_id) event_attr_##_id +#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + +#define EVENT_ATTR(_name, _id) \ +static struct perf_pmu_events_attr EVENT_VAR(_id) = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = PERF_COUNT_HW_##_id, \ +}; + +EVENT_ATTR(cpu-cycles, CPU_CYCLES ); +EVENT_ATTR(instructions, INSTRUCTIONS ); +EVENT_ATTR(cache-references, CACHE_REFERENCES ); +EVENT_ATTR(cache-misses, CACHE_MISSES ); +EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS ); +EVENT_ATTR(branch-misses, BRANCH_MISSES ); +EVENT_ATTR(bus-cycles, BUS_CYCLES ); +EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND ); +EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND ); +EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); + +static struct attribute *empty_attrs; + +static struct attribute *events_attr[] = { + EVENT_PTR(CPU_CYCLES), + EVENT_PTR(INSTRUCTIONS), + EVENT_PTR(CACHE_REFERENCES), + EVENT_PTR(CACHE_MISSES), + EVENT_PTR(BRANCH_INSTRUCTIONS), + EVENT_PTR(BRANCH_MISSES), + EVENT_PTR(BUS_CYCLES), + EVENT_PTR(STALLED_CYCLES_FRONTEND), + EVENT_PTR(STALLED_CYCLES_BACKEND), + EVENT_PTR(REF_CPU_CYCLES), + NULL, +}; + +static struct attribute_group x86_pmu_events_group = { + .name = "events", + .attrs = events_attr, +}; + +ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) +{ + u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; + u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; + bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); + bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL); + bool any = (config & ARCH_PERFMON_EVENTSEL_ANY); + bool inv = (config & ARCH_PERFMON_EVENTSEL_INV); + ssize_t ret; + + /* + * We have whole page size to spend and just little data + * to write, so we can safely use sprintf. + */ + ret = sprintf(page, "event=0x%02llx", event); + + if (umask) + ret += sprintf(page + ret, ",umask=0x%02llx", umask); + + if (edge) + ret += sprintf(page + ret, ",edge"); + + if (pc) + ret += sprintf(page + ret, ",pc"); + + if (any) + ret += sprintf(page + ret, ",any"); + + if (inv) + ret += sprintf(page + ret, ",inv"); + + if (cmask) + ret += sprintf(page + ret, ",cmask=0x%02llx", cmask); + + ret += sprintf(page + ret, "\n"); + + return ret; +} + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1354,6 +1477,11 @@ static int __init init_hw_perf_events(void) x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (!x86_pmu.events_sysfs_show) + x86_pmu_events_group.attrs = &empty_attrs; + else + filter_events(x86_pmu_events_group.attrs); + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -1643,6 +1771,7 @@ static struct attribute_group x86_pmu_attr_group = { static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, + &x86_pmu_events_group, NULL, }; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 8b6defe7eefc..115c1ea97746 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -354,6 +354,8 @@ struct x86_pmu { int attr_rdpmc; struct attribute **format_attrs; + ssize_t (*events_sysfs_show)(char *page, u64 config); + /* * CPU Hotplug hooks */ @@ -536,6 +538,9 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } +ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); +ssize_t intel_event_sysfs_show(char *page, u64 config); + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -626,6 +631,8 @@ int p4_pmu_init(void); int p6_pmu_init(void); +int knc_pmu_init(void); + #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 4528ae7b6ec4..c93bc4e813a0 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -568,6 +568,14 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev } } +static ssize_t amd_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | + (config & AMD64_EVENTSEL_EVENT) >> 24; + + return x86_event_sysfs_show(page, config, event); +} + static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, @@ -591,6 +599,7 @@ static __initconst const struct x86_pmu amd_pmu = { .put_event_constraints = amd_put_event_constraints, .format_attrs = amd_format_attr, + .events_sysfs_show = amd_event_sysfs_show, .cpu_prepare = amd_pmu_cpu_prepare, .cpu_starting = amd_pmu_cpu_starting, diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index eebd5ffe1bba..6336bcbd0618 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -41,17 +41,22 @@ struct cpu_perf_ibs { }; struct perf_ibs { - struct pmu pmu; - unsigned int msr; - u64 config_mask; - u64 cnt_mask; - u64 enable_mask; - u64 valid_mask; - u64 max_period; - unsigned long offset_mask[1]; - int offset_max; - struct cpu_perf_ibs __percpu *pcpu; - u64 (*get_count)(u64 config); + struct pmu pmu; + unsigned int msr; + u64 config_mask; + u64 cnt_mask; + u64 enable_mask; + u64 valid_mask; + u64 max_period; + unsigned long offset_mask[1]; + int offset_max; + struct cpu_perf_ibs __percpu *pcpu; + + struct attribute **format_attrs; + struct attribute_group format_group; + const struct attribute_group *attr_groups[2]; + + u64 (*get_count)(u64 config); }; struct perf_ibs_data { @@ -446,6 +451,19 @@ static void perf_ibs_del(struct perf_event *event, int flags) static void perf_ibs_read(struct perf_event *event) { } +PMU_FORMAT_ATTR(rand_en, "config:57"); +PMU_FORMAT_ATTR(cnt_ctl, "config:19"); + +static struct attribute *ibs_fetch_format_attrs[] = { + &format_attr_rand_en.attr, + NULL, +}; + +static struct attribute *ibs_op_format_attrs[] = { + NULL, /* &format_attr_cnt_ctl.attr if IBS_CAPS_OPCNT */ + NULL, +}; + static struct perf_ibs perf_ibs_fetch = { .pmu = { .task_ctx_nr = perf_invalid_context, @@ -465,6 +483,7 @@ static struct perf_ibs perf_ibs_fetch = { .max_period = IBS_FETCH_MAX_CNT << 4, .offset_mask = { MSR_AMD64_IBSFETCH_REG_MASK }, .offset_max = MSR_AMD64_IBSFETCH_REG_COUNT, + .format_attrs = ibs_fetch_format_attrs, .get_count = get_ibs_fetch_count, }; @@ -488,6 +507,7 @@ static struct perf_ibs perf_ibs_op = { .max_period = IBS_OP_MAX_CNT << 4, .offset_mask = { MSR_AMD64_IBSOP_REG_MASK }, .offset_max = MSR_AMD64_IBSOP_REG_COUNT, + .format_attrs = ibs_op_format_attrs, .get_count = get_ibs_op_count, }; @@ -597,6 +617,17 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) perf_ibs->pcpu = pcpu; + /* register attributes */ + if (perf_ibs->format_attrs[0]) { + memset(&perf_ibs->format_group, 0, sizeof(perf_ibs->format_group)); + perf_ibs->format_group.name = "format"; + perf_ibs->format_group.attrs = perf_ibs->format_attrs; + + memset(&perf_ibs->attr_groups, 0, sizeof(perf_ibs->attr_groups)); + perf_ibs->attr_groups[0] = &perf_ibs->format_group; + perf_ibs->pmu.attr_groups = perf_ibs->attr_groups; + } + ret = perf_pmu_register(&perf_ibs->pmu, name, -1); if (ret) { perf_ibs->pcpu = NULL; @@ -608,13 +639,19 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) static __init int perf_event_ibs_init(void) { + struct attribute **attr = ibs_op_format_attrs; + if (!ibs_caps) return -ENODEV; /* ibs not supported by the cpu */ perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); - if (ibs_caps & IBS_CAPS_OPCNT) + + if (ibs_caps & IBS_CAPS_OPCNT) { perf_ibs_op.config_mask |= IBS_OP_CNT_CTL; + *attr++ = &format_attr_cnt_ctl.attr; + } perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); + register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 6bca492b8547..93b9e1181f83 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1603,6 +1603,13 @@ static struct attribute *intel_arch_formats_attr[] = { NULL, }; +ssize_t intel_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT); + + return x86_event_sysfs_show(page, config, event); +} + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -1628,6 +1635,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, .guest_get_msrs = core_guest_get_msrs, .format_attrs = intel_arch_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, }; struct intel_shared_regs *allocate_shared_regs(int cpu) @@ -1766,6 +1774,7 @@ static __initconst const struct x86_pmu intel_pmu = { .pebs_aliases = intel_pebs_aliases_core2, .format_attrs = intel_arch3_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, @@ -1906,6 +1915,8 @@ __init int intel_pmu_init(void) switch (boot_cpu_data.x86) { case 0x6: return p6_pmu_init(); + case 0xb: + return knc_pmu_init(); case 0xf: return p4_pmu_init(); } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 38e4894165b9..3cf3d97cce3a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -118,22 +118,24 @@ static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); - u32 config; + u32 config = 0; - pci_read_config_dword(pdev, box_ctl, &config); - config |= SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } } static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); - u32 config; + u32 config = 0; - pci_read_config_dword(pdev, box_ctl, &config); - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } } static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) @@ -156,7 +158,7 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; - u64 count; + u64 count = 0; pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); @@ -603,11 +605,12 @@ static struct pci_driver snbep_uncore_pci_driver = { /* * build pci bus to socket mapping */ -static void snbep_pci2phy_map_init(void) +static int snbep_pci2phy_map_init(void) { struct pci_dev *ubox_dev = NULL; int i, bus, nodeid; - u32 config; + int err = 0; + u32 config = 0; while (1) { /* find the UBOX device */ @@ -618,10 +621,14 @@ static void snbep_pci2phy_map_init(void) break; bus = ubox_dev->bus->number; /* get the Node ID of the local register */ - pci_read_config_dword(ubox_dev, 0x40, &config); + err = pci_read_config_dword(ubox_dev, 0x40, &config); + if (err) + break; nodeid = config; /* get the Node ID mapping */ - pci_read_config_dword(ubox_dev, 0x54, &config); + err = pci_read_config_dword(ubox_dev, 0x54, &config); + if (err) + break; /* * every three bits in the Node ID mapping register maps * to a particular node. @@ -633,7 +640,11 @@ static void snbep_pci2phy_map_init(void) } } }; - return; + + if (ubox_dev) + pci_dev_put(ubox_dev); + + return err ? pcibios_err_to_errno(err) : 0; } /* end of Sandy Bridge-EP uncore support */ @@ -1547,7 +1558,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int port; /* adjust the main event selector and extra register index */ if (reg1->idx % 2) { @@ -1559,7 +1569,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) } /* adjust extra register config */ - port = reg1->idx / 6 + box->pmu->pmu_idx * 4; switch (reg1->idx % 6) { case 2: /* shift the 8~15 bits to the 0~7 bits */ @@ -1950,7 +1959,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp static struct intel_uncore_box * uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - static struct intel_uncore_box *box; + struct intel_uncore_box *box; box = *per_cpu_ptr(pmu->box, cpu); if (box) @@ -2347,6 +2356,27 @@ int uncore_pmu_event_init(struct perf_event *event) return ret; } +static ssize_t uncore_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); + +static struct attribute *uncore_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group uncore_pmu_attr_group = { + .attrs = uncore_pmu_attrs, +}; + static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -2384,8 +2414,8 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) free_percpu(type->pmus[i].box); kfree(type->pmus); type->pmus = NULL; - kfree(type->attr_groups[1]); - type->attr_groups[1] = NULL; + kfree(type->events_group); + type->events_group = NULL; } static void __init uncore_types_exit(struct intel_uncore_type **types) @@ -2437,9 +2467,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type) for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->attr_groups[1] = events_group; + type->events_group = events_group; } + type->pmu_group = &uncore_pmu_attr_group; type->pmus = pmus; return 0; fail: @@ -2556,9 +2587,11 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ + ret = snbep_pci2phy_map_init(); + if (ret) + return ret; pci_uncores = snbep_pci_uncores; uncore_pci_driver = &snbep_uncore_pci_driver; - snbep_pci2phy_map_init(); break; default: return 0; @@ -2904,6 +2937,9 @@ static int __init intel_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return -ENODEV; + if (cpu_has_hypervisor) + return -ENODEV; + ret = uncore_pci_init(); if (ret) goto fail; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 5b81c1856aac..e68a4550e952 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -369,10 +369,12 @@ struct intel_uncore_type { struct intel_uncore_pmu *pmus; struct intel_uncore_ops *ops; struct uncore_event_desc *event_descs; - const struct attribute_group *attr_groups[3]; + const struct attribute_group *attr_groups[4]; }; -#define format_group attr_groups[0] +#define pmu_group attr_groups[0] +#define format_group attr_groups[1] +#define events_group attr_groups[2] struct intel_uncore_ops { void (*init_box)(struct intel_uncore_box *); diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c new file mode 100644 index 000000000000..4b7731bf23a8 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -0,0 +1,319 @@ +/* Driver for Intel Xeon Phi "Knights Corner" PMU */ + +#include <linux/perf_event.h> +#include <linux/types.h> + +#include <asm/hardirq.h> + +#include "perf_event.h" + +static const u64 knc_perfmon_event_map[] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x002a, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x0016, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0028, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0029, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x0012, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x002b, +}; + +static __initconst u64 knc_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + /* On Xeon Phi event "0" is a valid DATA_READ */ + /* (L1 Data Cache Reads) Instruction. */ + /* We code this as ARCH_PERFMON_EVENTSEL_INT as this */ + /* bit will always be set in x86_pmu_hw_config(). */ + [ C(RESULT_ACCESS) ] = ARCH_PERFMON_EVENTSEL_INT, + /* DATA_READ */ + [ C(RESULT_MISS) ] = 0x0003, /* DATA_READ_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0001, /* DATA_WRITE */ + [ C(RESULT_MISS) ] = 0x0004, /* DATA_WRITE_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0011, /* L1_DATA_PF1 */ + [ C(RESULT_MISS) ] = 0x001c, /* L1_DATA_PF1_MISS */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x000c, /* CODE_READ */ + [ C(RESULT_MISS) ] = 0x000e, /* CODE_CACHE_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x10cb, /* L2_READ_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x10cc, /* L2_WRITE_HIT */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x10fc, /* L2_DATA_PF2 */ + [ C(RESULT_MISS) ] = 0x10fe, /* L2_DATA_PF2_MISS */ + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = ARCH_PERFMON_EVENTSEL_INT, + /* DATA_READ */ + /* see note on L1 OP_READ */ + [ C(RESULT_MISS) ] = 0x0002, /* DATA_PAGE_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0001, /* DATA_WRITE */ + [ C(RESULT_MISS) ] = 0x0002, /* DATA_PAGE_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x000c, /* CODE_READ */ + [ C(RESULT_MISS) ] = 0x000d, /* CODE_PAGE_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0012, /* BRANCHES */ + [ C(RESULT_MISS) ] = 0x002b, /* BRANCHES_MISPREDICTED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + + +static u64 knc_pmu_event_map(int hw_event) +{ + return knc_perfmon_event_map[hw_event]; +} + +static struct event_constraint knc_event_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0xc3, 0x1), /* HWP_L2HIT */ + INTEL_EVENT_CONSTRAINT(0xc4, 0x1), /* HWP_L2MISS */ + INTEL_EVENT_CONSTRAINT(0xc8, 0x1), /* L2_READ_HIT_E */ + INTEL_EVENT_CONSTRAINT(0xc9, 0x1), /* L2_READ_HIT_M */ + INTEL_EVENT_CONSTRAINT(0xca, 0x1), /* L2_READ_HIT_S */ + INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* L2_READ_MISS */ + INTEL_EVENT_CONSTRAINT(0xcc, 0x1), /* L2_WRITE_HIT */ + INTEL_EVENT_CONSTRAINT(0xce, 0x1), /* L2_STRONGLY_ORDERED_STREAMING_VSTORES_MISS */ + INTEL_EVENT_CONSTRAINT(0xcf, 0x1), /* L2_WEAKLY_ORDERED_STREAMING_VSTORE_MISS */ + INTEL_EVENT_CONSTRAINT(0xd7, 0x1), /* L2_VICTIM_REQ_WITH_DATA */ + INTEL_EVENT_CONSTRAINT(0xe3, 0x1), /* SNP_HITM_BUNIT */ + INTEL_EVENT_CONSTRAINT(0xe6, 0x1), /* SNP_HIT_L2 */ + INTEL_EVENT_CONSTRAINT(0xe7, 0x1), /* SNP_HITM_L2 */ + INTEL_EVENT_CONSTRAINT(0xf1, 0x1), /* L2_DATA_READ_MISS_CACHE_FILL */ + INTEL_EVENT_CONSTRAINT(0xf2, 0x1), /* L2_DATA_WRITE_MISS_CACHE_FILL */ + INTEL_EVENT_CONSTRAINT(0xf6, 0x1), /* L2_DATA_READ_MISS_MEM_FILL */ + INTEL_EVENT_CONSTRAINT(0xf7, 0x1), /* L2_DATA_WRITE_MISS_MEM_FILL */ + INTEL_EVENT_CONSTRAINT(0xfc, 0x1), /* L2_DATA_PF2 */ + INTEL_EVENT_CONSTRAINT(0xfd, 0x1), /* L2_DATA_PF2_DROP */ + INTEL_EVENT_CONSTRAINT(0xfe, 0x1), /* L2_DATA_PF2_MISS */ + INTEL_EVENT_CONSTRAINT(0xff, 0x1), /* L2_DATA_HIT_INFLIGHT_PF2 */ + EVENT_CONSTRAINT_END +}; + +#define MSR_KNC_IA32_PERF_GLOBAL_STATUS 0x0000002d +#define MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL 0x0000002e +#define MSR_KNC_IA32_PERF_GLOBAL_CTRL 0x0000002f + +#define KNC_ENABLE_COUNTER0 0x00000001 +#define KNC_ENABLE_COUNTER1 0x00000002 + +static void knc_pmu_disable_all(void) +{ + u64 val; + + rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val); + val &= ~(KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1); + wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val); +} + +static void knc_pmu_enable_all(int added) +{ + u64 val; + + rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val); + val |= (KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1); + wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val); +} + +static inline void +knc_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 val; + + val = hwc->config; + val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; + + (void)wrmsrl_safe(hwc->config_base + hwc->idx, val); +} + +static void knc_pmu_enable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 val; + + val = hwc->config; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; + + (void)wrmsrl_safe(hwc->config_base + hwc->idx, val); +} + +static inline u64 knc_pmu_get_status(void) +{ + u64 status; + + rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status); + + return status; +} + +static inline void knc_pmu_ack_status(u64 ack) +{ + wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack); +} + +static int knc_pmu_handle_irq(struct pt_regs *regs) +{ + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + int handled = 0; + int bit, loops; + u64 status; + + cpuc = &__get_cpu_var(cpu_hw_events); + + knc_pmu_disable_all(); + + status = knc_pmu_get_status(); + if (!status) { + knc_pmu_enable_all(0); + return handled; + } + + loops = 0; +again: + knc_pmu_ack_status(status); + if (++loops > 100) { + WARN_ONCE(1, "perf: irq loop stuck!\n"); + perf_event_print_debug(); + goto done; + } + + inc_irq_stat(apic_perf_irqs); + + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { + struct perf_event *event = cpuc->events[bit]; + + handled++; + + if (!test_bit(bit, cpuc->active_mask)) + continue; + + if (!intel_pmu_save_and_restart(event)) + continue; + + perf_sample_data_init(&data, 0, event->hw.last_period); + + if (perf_event_overflow(event, &data, regs)) + x86_pmu_stop(event, 0); + } + + /* + * Repeat if there is more work to be done: + */ + status = knc_pmu_get_status(); + if (status) + goto again; + +done: + knc_pmu_enable_all(0); + + return handled; +} + + +PMU_FORMAT_ATTR(event, "config:0-7" ); +PMU_FORMAT_ATTR(umask, "config:8-15" ); +PMU_FORMAT_ATTR(edge, "config:18" ); +PMU_FORMAT_ATTR(inv, "config:23" ); +PMU_FORMAT_ATTR(cmask, "config:24-31" ); + +static struct attribute *intel_knc_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask.attr, + NULL, +}; + +static __initconst struct x86_pmu knc_pmu = { + .name = "knc", + .handle_irq = knc_pmu_handle_irq, + .disable_all = knc_pmu_disable_all, + .enable_all = knc_pmu_enable_all, + .enable = knc_pmu_enable_event, + .disable = knc_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, + .eventsel = MSR_KNC_EVNTSEL0, + .perfctr = MSR_KNC_PERFCTR0, + .event_map = knc_pmu_event_map, + .max_events = ARRAY_SIZE(knc_perfmon_event_map), + .apic = 1, + .max_period = (1ULL << 39) - 1, + .version = 0, + .num_counters = 2, + .cntval_bits = 40, + .cntval_mask = (1ULL << 40) - 1, + .get_event_constraints = x86_get_event_constraints, + .event_constraints = knc_event_constraints, + .format_attrs = intel_knc_formats_attr, +}; + +__init int knc_pmu_init(void) +{ + x86_pmu = knc_pmu; + + memcpy(hw_cache_event_ids, knc_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + return 0; +} diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index e4dd0f7a0453..f2af39f5dc3d 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -8,13 +8,106 @@ */ static const u64 p6_perfmon_event_map[] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, - [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, - [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, + [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, /* CPU_CLK_UNHALTED */ + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, /* INST_RETIRED */ + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, /* L2_RQSTS:M:E:S:I */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, /* L2_RQSTS:I */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, /* BR_INST_RETIRED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, /* BR_MISS_PRED_RETIRED */ + [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, /* BUS_DRDY_CLOCKS */ + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a2, /* RESOURCE_STALLS */ + +}; + +static __initconst u64 p6_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0043, /* DATA_MEM_REFS */ + [ C(RESULT_MISS) ] = 0x0045, /* DCU_LINES_IN */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0f29, /* L2_LD:M:E:S:I */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* IFU_IFETCH */ + [ C(RESULT_MISS) ] = 0x0f28, /* L2_IFETCH:M:E:S:I */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0025, /* L2_M_LINES_INM */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0043, /* DATA_MEM_REFS */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* IFU_IFETCH */ + [ C(RESULT_MISS) ] = 0x0085, /* ITLB_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED */ + [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISS_PRED_RETIRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, }; static u64 p6_pmu_event_map(int hw_event) @@ -34,7 +127,7 @@ static struct event_constraint p6_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ - INTEL_EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */ + INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ @@ -64,25 +157,25 @@ static void p6_pmu_enable_all(int added) static inline void p6_pmu_disable_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; u64 val = P6_NOP_EVENT; - if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)wrmsrl_safe(hwc->config_base, val); } static void p6_pmu_enable_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; u64 val; val = hwc->config; - if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL_ENABLE; + + /* + * p6 only has a global event enable, set on PerfEvtSel0 + * We "disable" events by programming P6_NOP_EVENT + * and we rely on p6_pmu_enable_all() being called + * to actually enable the events. + */ (void)wrmsrl_safe(hwc->config_base, val); } @@ -134,6 +227,8 @@ static __initconst const struct x86_pmu p6_pmu = { .event_constraints = p6_event_constraints, .format_attrs = intel_p6_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, + }; __init int p6_pmu_init(void) @@ -158,5 +253,9 @@ __init int p6_pmu_init(void) x86_pmu = p6_pmu; + memcpy(hw_cache_event_ids, p6_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + return 0; } diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 966512b2cacf..2e8caf03f593 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -56,6 +56,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) switch (boot_cpu_data.x86) { case 6: return msr - MSR_P6_PERFCTR0; + case 11: + return msr - MSR_KNC_PERFCTR0; case 15: return msr - MSR_P4_BPU_PERFCTR0; } @@ -82,6 +84,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) switch (boot_cpu_data.x86) { case 6: return msr - MSR_P6_EVNTSEL0; + case 11: + return msr - MSR_KNC_EVNTSEL0; case 15: return msr - MSR_P4_BSU_ESCR0; } diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 8022c6681485..fbd895562292 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -140,10 +140,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = cpumask_first(cpu_online_mask); - else - *pos = cpumask_next(*pos - 1, cpu_online_mask); + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return &cpu_data(*pos); return NULL; diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 39472dd2323f..60c78917190c 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -199,12 +199,14 @@ static int __init cpuid_init(void) goto out_chrdev; } cpuid_class->devnode = cpuid_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = cpuid_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -214,6 +216,7 @@ out_class: for_each_online_cpu(i) { cpuid_device_destroy(i); } + put_online_cpus(); class_destroy(cpuid_class); out_chrdev: __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); @@ -225,11 +228,13 @@ static void __exit cpuid_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); } module_init(cpuid_init); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 13ad89971d47..74467feb4dc5 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -16,6 +16,7 @@ #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/module.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -30,6 +31,27 @@ int in_crash_kexec; +/* + * This is used to VMCLEAR all VMCSs loaded on the + * processor. And when loading kvm_intel module, the + * callback function pointer will be assigned. + * + * protected by rcu. + */ +crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; +EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); + +static inline void cpu_crash_vmclear_loaded_vmcss(void) +{ + crash_vmclear_fn *do_vmclear_operation = NULL; + + rcu_read_lock(); + do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); + if (do_vmclear_operation) + do_vmclear_operation(); + rcu_read_unlock(); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) @@ -46,6 +68,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) #endif crash_save_cpu(regs, cpu); + /* + * VMCLEAR VMCSs loaded on all cpus if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Disable VMX or SVM if needed. * * We need to disable virtualization on all CPUs. @@ -88,6 +115,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) kdump_nmi_shootdown_cpus(); + /* + * VMCLEAR VMCSs loaded on this cpu if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Booting kdump kernel with VMX or SVM enabled won't work, * because (among other limitations) we can't disable paging * with the virt flags. diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 3ae2ced4a874..b1581527a236 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -342,6 +342,47 @@ const struct irq_domain_ops ioapic_irq_domain_ops = { .xlate = ioapic_xlate, }; +static void dt_add_ioapic_domain(unsigned int ioapic_num, + struct device_node *np) +{ + struct irq_domain *id; + struct mp_ioapic_gsi *gsi_cfg; + int ret; + int num; + + gsi_cfg = mp_ioapic_gsi_routing(ioapic_num); + num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; + + id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops, + (void *)ioapic_num); + BUG_ON(!id); + if (gsi_cfg->gsi_base == 0) { + /* + * The first NR_IRQS_LEGACY irq descs are allocated in + * early_irq_init() and need just a mapping. The + * remaining irqs need both. All of them are preallocated + * and assigned so we can keep the 1:1 mapping which the ioapic + * is having. + */ + ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY); + if (ret) + pr_err("Error mapping legacy IRQs: %d\n", ret); + + if (num > NR_IRQS_LEGACY) { + ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY, + NR_IRQS_LEGACY, num - NR_IRQS_LEGACY); + if (ret) + pr_err("Error creating mapping for the " + "remaining IRQs: %d\n", ret); + } + irq_set_default_host(id); + } else { + ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num); + if (ret) + pr_err("Error creating IRQ mapping: %d\n", ret); + } +} + static void __init ioapic_add_ofnode(struct device_node *np) { struct resource r; @@ -356,15 +397,7 @@ static void __init ioapic_add_ofnode(struct device_node *np) for (i = 0; i < nr_ioapics; i++) { if (r.start == mpc_ioapic_addr(i)) { - struct irq_domain *id; - struct mp_ioapic_gsi *gsi_cfg; - - gsi_cfg = mp_ioapic_gsi_routing(i); - - id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0, - &ioapic_irq_domain_ops, - (void*)i); - BUG_ON(!id); + dt_add_ioapic_domain(i, np); return; } } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ed858e9e9a74..df06ade26bef 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1077,6 +1077,9 @@ void __init memblock_x86_fill(void) memblock_add(ei->addr, ei->size); } + /* throw away partial pages */ + memblock_trim_memory(PAGE_SIZE); + memblock_dump_all(); } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 623f28837476..c763116c5359 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -57,6 +57,7 @@ #include <asm/cpufeature.h> #include <asm/alternative-asm.h> #include <asm/asm.h> +#include <asm/smap.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -298,6 +299,21 @@ ENTRY(ret_from_fork) CFI_ENDPROC END(ret_from_fork) +ENTRY(ret_from_kernel_thread) + CFI_STARTPROC + pushl_cfi %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl_cfi %eax + pushl_cfi $0x0202 # Reset kernel eflags + popfl_cfi + movl PT_EBP(%esp),%eax + call *PT_EBX(%esp) + movl $0,PT_EAX(%esp) + jmp syscall_exit + CFI_ENDPROC +ENDPROC(ret_from_kernel_thread) + /* * Interrupt exit functions should be protected against kprobes */ @@ -322,8 +338,7 @@ ret_from_intr: andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax #else /* - * We can be coming here from a syscall done in the kernel space, - * e.g. a failed kernel_execve(). + * We can be coming here from child spawned by kernel_thread(). */ movl PT_CS(%esp), %eax andl $SEGMENT_RPL_MASK, %eax @@ -407,7 +422,9 @@ sysenter_past_esp: */ cmpl $__PAGE_OFFSET-3,%ebp jae syscall_fault + ASM_STAC 1: movl (%ebp),%ebp + ASM_CLAC movl %ebp,PT_EBP(%esp) _ASM_EXTABLE(1b,syscall_fault) @@ -488,6 +505,7 @@ ENDPROC(ia32_sysenter_target) # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway + ASM_CLAC pushl_cfi %eax # save orig_eax SAVE_ALL GET_THREAD_INFO(%ebp) @@ -612,6 +630,10 @@ work_notifysig: # deal with pending signals and movl %esp, %eax jne work_notifysig_v86 # returning to kernel-space or # vm86-space +1: +#else + movl %esp, %eax +#endif TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) movb PT_CS(%esp), %bl @@ -622,24 +644,15 @@ work_notifysig: # deal with pending signals and call do_notify_resume jmp resume_userspace +#ifdef CONFIG_VM86 ALIGN work_notifysig_v86: pushl_cfi %ecx # save ti_flags for do_notify_resume call save_v86_state # %eax contains pt_regs pointer popl_cfi %ecx movl %eax, %esp -#else - movl %esp, %eax + jmp 1b #endif - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - movb PT_CS(%esp), %bl - andb $SEGMENT_RPL_MASK, %bl - cmpb $USER_RPL, %bl - jb resume_kernel - xorl %edx, %edx - call do_notify_resume - jmp resume_userspace END(work_pending) # perform syscall exit tracing @@ -670,6 +683,7 @@ END(syscall_exit_work) RING0_INT_FRAME # can't unwind into user space anyway syscall_fault: + ASM_CLAC GET_THREAD_INFO(%ebp) movl $-EFAULT,PT_EAX(%esp) jmp resume_userspace @@ -725,31 +739,12 @@ ENTRY(ptregs_##name) ; \ ENDPROC(ptregs_##name) PTREGSCALL1(iopl) -PTREGSCALL0(fork) -PTREGSCALL0(vfork) -PTREGSCALL3(execve) PTREGSCALL2(sigaltstack) PTREGSCALL0(sigreturn) PTREGSCALL0(rt_sigreturn) PTREGSCALL2(vm86) PTREGSCALL1(vm86old) -/* Clone is an oddball. The 4th arg is in %edi */ -ENTRY(ptregs_clone) - CFI_STARTPROC - leal 4(%esp),%eax - pushl_cfi %eax - pushl_cfi PT_EDI(%eax) - movl PT_EDX(%eax),%ecx - movl PT_ECX(%eax),%edx - movl PT_EBX(%eax),%eax - call sys_clone - addl $8,%esp - CFI_ADJUST_CFA_OFFSET -8 - ret - CFI_ENDPROC -ENDPROC(ptregs_clone) - .macro FIXUP_ESPFIX_STACK /* * Switch back for ESPFIX stack to the normal zerobased stack @@ -825,6 +820,7 @@ END(interrupt) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: + ASM_CLAC addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ SAVE_ALL TRACE_IRQS_OFF @@ -841,6 +837,7 @@ ENDPROC(common_interrupt) #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ + ASM_CLAC; \ pushl_cfi $~(nr); \ SAVE_ALL; \ TRACE_IRQS_OFF \ @@ -857,6 +854,7 @@ ENDPROC(name) ENTRY(coprocessor_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_coprocessor_error jmp error_code @@ -865,6 +863,7 @@ END(coprocessor_error) ENTRY(simd_coprocessor_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ @@ -886,6 +885,7 @@ END(simd_coprocessor_error) ENTRY(device_not_available) RING0_INT_FRAME + ASM_CLAC pushl_cfi $-1 # mark this as an int pushl_cfi $do_device_not_available jmp error_code @@ -906,6 +906,7 @@ END(native_irq_enable_sysexit) ENTRY(overflow) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_overflow jmp error_code @@ -914,6 +915,7 @@ END(overflow) ENTRY(bounds) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_bounds jmp error_code @@ -922,6 +924,7 @@ END(bounds) ENTRY(invalid_op) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_invalid_op jmp error_code @@ -930,6 +933,7 @@ END(invalid_op) ENTRY(coprocessor_segment_overrun) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_coprocessor_segment_overrun jmp error_code @@ -938,6 +942,7 @@ END(coprocessor_segment_overrun) ENTRY(invalid_TSS) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_invalid_TSS jmp error_code CFI_ENDPROC @@ -945,6 +950,7 @@ END(invalid_TSS) ENTRY(segment_not_present) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_segment_not_present jmp error_code CFI_ENDPROC @@ -952,6 +958,7 @@ END(segment_not_present) ENTRY(stack_segment) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_stack_segment jmp error_code CFI_ENDPROC @@ -959,6 +966,7 @@ END(stack_segment) ENTRY(alignment_check) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_alignment_check jmp error_code CFI_ENDPROC @@ -966,6 +974,7 @@ END(alignment_check) ENTRY(divide_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 # no error code pushl_cfi $do_divide_error jmp error_code @@ -975,6 +984,7 @@ END(divide_error) #ifdef CONFIG_X86_MCE ENTRY(machine_check) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi machine_check_vector jmp error_code @@ -984,6 +994,7 @@ END(machine_check) ENTRY(spurious_interrupt_bug) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_spurious_interrupt_bug jmp error_code @@ -994,16 +1005,6 @@ END(spurious_interrupt_bug) */ .popsection -ENTRY(kernel_thread_helper) - pushl $0 # fake return address for unwinder - CFI_STARTPROC - movl %edi,%eax - call *%esi - call do_exit - ud2 # padding for call trace - CFI_ENDPROC -ENDPROC(kernel_thread_helper) - #ifdef CONFIG_XEN /* Xen doesn't set %esp to be precisely what the normal sysenter entrypoint expects, so fix it up before using the normal path. */ @@ -1016,7 +1017,7 @@ ENTRY(xen_sysenter_target) ENTRY(xen_hypervisor_callback) CFI_STARTPROC - pushl_cfi $0 + pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL TRACE_IRQS_OFF @@ -1058,14 +1059,16 @@ ENTRY(xen_failsafe_callback) 2: mov 8(%esp),%es 3: mov 12(%esp),%fs 4: mov 16(%esp),%gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ testl %eax,%eax popl_cfi %eax lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f addl $16,%esp - jmp iret_exc # EAX != 0 => Category 2 (Bad IRET) -5: pushl_cfi $0 # EAX == 0 => Category 1 (Bad segment) + jmp iret_exc +5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp ret_from_exception CFI_ENDPROC @@ -1109,17 +1112,21 @@ ENTRY(ftrace_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %eax + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax movl 0x4(%ebp), %edx + leal function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call ftrace_call: call ftrace_stub + addl $4,%esp /* skip NULL pointer */ popl %edx popl %ecx popl %eax +ftrace_ret: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -1131,6 +1138,71 @@ ftrace_stub: ret END(ftrace_caller) +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS,13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + +ftrace_restore_flags: + popf + jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) @@ -1171,9 +1243,6 @@ END(mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx @@ -1207,6 +1276,7 @@ return_to_handler: ENTRY(page_fault) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_page_fault ALIGN error_code: @@ -1279,6 +1349,7 @@ END(page_fault) ENTRY(debug) RING0_INT_FRAME + ASM_CLAC cmpl $ia32_sysenter_target,(%esp) jne debug_stack_correct FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn @@ -1303,6 +1374,7 @@ END(debug) */ ENTRY(nmi) RING0_INT_FRAME + ASM_CLAC pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax @@ -1373,6 +1445,7 @@ END(nmi) ENTRY(int3) RING0_INT_FRAME + ASM_CLAC pushl_cfi $-1 # mark this as an int SAVE_ALL TRACE_IRQS_OFF @@ -1393,6 +1466,7 @@ END(general_protection) #ifdef CONFIG_KVM_GUEST ENTRY(async_page_fault) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_async_page_fault jmp error_code CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 69babd8c834f..70641aff0c25 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,6 +56,8 @@ #include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> +#include <asm/context_tracking.h> +#include <asm/smap.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -68,25 +70,51 @@ .section .entry.text, "ax" #ifdef CONFIG_FUNCTION_TRACER + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +#else +# define function_hook mcount +#endif + #ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(mcount) + +ENTRY(function_hook) retq -END(mcount) +END(function_hook) + +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + leaq function_trace_op, %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif +.endm ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ cmpl $0, function_trace_stop jne ftrace_stub - MCOUNT_SAVE_FRAME - - movq 0x38(%rsp), %rdi - movq 8(%rbp), %rsi - subq $MCOUNT_INSN_SIZE, %rdi + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx GLOBAL(ftrace_call) call ftrace_stub MCOUNT_RESTORE_FRAME +ftrace_return: #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -97,8 +125,78 @@ GLOBAL(ftrace_stub) retq END(ftrace_caller) +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, SS+8(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + #else /* ! CONFIG_DYNAMIC_FTRACE */ -ENTRY(mcount) + +ENTRY(function_hook) cmpl $0, function_trace_stop jne ftrace_stub @@ -119,8 +217,12 @@ GLOBAL(ftrace_stub) trace: MCOUNT_SAVE_FRAME - movq 0x38(%rsp), %rdi + movq RIP(%rsp), %rdi +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else movq 8(%rbp), %rsi +#endif subq $MCOUNT_INSN_SIZE, %rdi call *ftrace_trace_function @@ -128,20 +230,22 @@ trace: MCOUNT_RESTORE_FRAME jmp ftrace_stub -END(mcount) +END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - MCOUNT_SAVE_FRAME +#ifdef CC_USING_FENTRY + leaq SS+16(%rsp), %rdi + movq $0, %rdx /* No framepointers needed */ +#else leaq 8(%rbp), %rdi - movq 0x38(%rsp), %rsi movq (%rbp), %rdx +#endif + movq RIP(%rsp), %rsi subq $MCOUNT_INSN_SIZE, %rsi call prepare_ftrace_return @@ -342,15 +446,15 @@ ENDPROC(native_usergs_sysret64) .macro SAVE_ARGS_IRQ cld /* start from rbp in pt_regs and jump over */ - movq_cfi rdi, RDI-RBP - movq_cfi rsi, RSI-RBP - movq_cfi rdx, RDX-RBP - movq_cfi rcx, RCX-RBP - movq_cfi rax, RAX-RBP - movq_cfi r8, R8-RBP - movq_cfi r9, R9-RBP - movq_cfi r10, R10-RBP - movq_cfi r11, R11-RBP + movq_cfi rdi, (RDI-RBP) + movq_cfi rsi, (RSI-RBP) + movq_cfi rdx, (RDX-RBP) + movq_cfi rcx, (RCX-RBP) + movq_cfi rax, (RAX-RBP) + movq_cfi r8, (R8-RBP) + movq_cfi r9, (R9-RBP) + movq_cfi r10, (R10-RBP) + movq_cfi r11, (R11-RBP) /* Save rbp so that we can unwind from get_irq_regs() */ movq_cfi rbp, 0 @@ -384,7 +488,7 @@ ENDPROC(native_usergs_sysret64) .endm ENTRY(save_rest) - PARTIAL_FRAME 1 REST_SKIP+8 + PARTIAL_FRAME 1 (REST_SKIP+8) movq 5*8+16(%rsp), %r11 /* save return address */ movq_cfi rbx, RBX+16 movq_cfi rbp, RBP+16 @@ -440,7 +544,7 @@ ENTRY(ret_from_fork) LOCK ; btr $TIF_FORK,TI_flags(%r8) - pushq_cfi kernel_eflags(%rip) + pushq_cfi $0x0002 popfq_cfi # reset kernel eflags call schedule_tail # rdi: 'prev' task parameter @@ -450,7 +554,7 @@ ENTRY(ret_from_fork) RESTORE_REST testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? - jz retint_restore_args + jz 1f testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET jnz int_ret_from_sys_call @@ -458,6 +562,14 @@ ENTRY(ret_from_fork) RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET jmp ret_from_sys_call # go to the SYSRET fastpath +1: + subq $REST_SKIP, %rsp # leave space for volatiles + CFI_ADJUST_CFA_OFFSET REST_SKIP + movq %rbp, %rdi + call *%rbx + movl $0, RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call CFI_ENDPROC END(ret_from_fork) @@ -465,7 +577,8 @@ END(ret_from_fork) * System call entry. Up to 6 arguments in registers are supported. * * SYSCALL does not save anything on the stack and does not change the - * stack pointer. + * stack pointer. However, it does mask the flags register for us, so + * CLD and CLAC are not needed. */ /* @@ -565,7 +678,7 @@ sysret_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi jmp sysret_check @@ -678,7 +791,7 @@ int_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -732,9 +845,25 @@ ENTRY(\label) END(\label) .endm - PTREGSCALL stub_clone, sys_clone, %r8 - PTREGSCALL stub_fork, sys_fork, %rdi - PTREGSCALL stub_vfork, sys_vfork, %rdi + .macro FORK_LIKE func +ENTRY(stub_\func) + CFI_STARTPROC + popq %r11 /* save return address */ + PARTIAL_FRAME 0 + SAVE_REST + pushq %r11 /* put it back on stack */ + FIXUP_TOP_OF_STACK %r11, 8 + DEFAULT_FRAME 0 8 /* offset 8: return address */ + call sys_\func + RESTORE_TOP_OF_STACK %r11, 8 + ret $REST_SKIP /* pop extended registers */ + CFI_ENDPROC +END(stub_\func) + .endm + + FORK_LIKE clone + FORK_LIKE fork + FORK_LIKE vfork PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx PTREGSCALL stub_iopl, sys_iopl, %rsi @@ -757,7 +886,6 @@ ENTRY(stub_execve) PARTIAL_FRAME 0 SAVE_REST FIXUP_TOP_OF_STACK %r11 - movq %rsp, %rcx call sys_execve RESTORE_TOP_OF_STACK %r11 movq %rax,RAX(%rsp) @@ -807,8 +935,7 @@ ENTRY(stub_x32_execve) PARTIAL_FRAME 0 SAVE_REST FIXUP_TOP_OF_STACK %r11 - movq %rsp, %rcx - call sys32_execve + call compat_sys_execve RESTORE_TOP_OF_STACK %r11 movq %rax,RAX(%rsp) RESTORE_REST @@ -885,6 +1012,7 @@ END(interrupt) .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: XCPT_FRAME + ASM_CLAC addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ /* 0(%rsp): old_rsp-ARGOFFSET */ @@ -974,7 +1102,7 @@ retint_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) @@ -1024,6 +1152,7 @@ END(common_interrupt) .macro apicinterrupt num sym do_sym ENTRY(\sym) INTR_FRAME + ASM_CLAC pushq_cfi $~(\num) .Lcommon_\sym: interrupt \do_sym @@ -1078,6 +1207,7 @@ apicinterrupt IRQ_WORK_VECTOR \ .macro zeroentry sym do_sym ENTRY(\sym) INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1095,6 +1225,7 @@ END(\sym) .macro paranoidzeroentry sym do_sym ENTRY(\sym) INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1113,6 +1244,7 @@ END(\sym) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1132,6 +1264,7 @@ END(\sym) .macro errorentry sym do_sym ENTRY(\sym) XCPT_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 @@ -1150,6 +1283,7 @@ END(\sym) .macro paranoiderrorentry sym do_sym ENTRY(\sym) XCPT_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 @@ -1206,52 +1340,6 @@ bad_gs: jmp 2b .previous -ENTRY(kernel_thread_helper) - pushq $0 # fake return address - CFI_STARTPROC - /* - * Here we are in the child and the registers are set as they were - * at kernel_thread() invocation in the parent. - */ - call *%rsi - # exit - mov %eax, %edi - call do_exit - ud2 # padding for call trace - CFI_ENDPROC -END(kernel_thread_helper) - -/* - * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. - * - * C extern interface: - * extern long execve(const char *name, char **argv, char **envp) - * - * asm input arguments: - * rdi: name, rsi: argv, rdx: envp - * - * We want to fallback into: - * extern long sys_execve(const char *name, char **argv,char **envp, struct pt_regs *regs) - * - * do_sys_execve asm fallback arguments: - * rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack - */ -ENTRY(kernel_execve) - CFI_STARTPROC - FAKE_STACK_FRAME $0 - SAVE_ALL - movq %rsp,%rcx - call sys_execve - movq %rax, RAX(%rsp) - RESTORE_REST - testq %rax,%rax - je int_ret_from_sys_call - RESTORE_ARGS - UNFAKE_STACK_FRAME - ret - CFI_ENDPROC -END(kernel_execve) - /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(call_softirq) CFI_STARTPROC @@ -1363,7 +1451,7 @@ ENTRY(xen_failsafe_callback) CFI_RESTORE r11 addq $0x30,%rsp CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $0 + pushq_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp error_exit CFI_ENDPROC @@ -1449,7 +1537,7 @@ paranoid_userspace: paranoid_schedule: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) - call schedule + SCHEDULE_USER DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF jmp paranoid_userspace @@ -1627,9 +1715,10 @@ nested_nmi: 1: /* Set up the interrupted NMIs stack to jump to repeat_nmi */ - leaq -6*8(%rsp), %rdx + leaq -1*8(%rsp), %rdx movq %rdx, %rsp - CFI_ADJUST_CFA_OFFSET 6*8 + CFI_ADJUST_CFA_OFFSET 1*8 + leaq -10*8(%rsp), %rdx pushq_cfi $__KERNEL_DS pushq_cfi %rdx pushfq_cfi @@ -1637,8 +1726,8 @@ nested_nmi: pushq_cfi $repeat_nmi /* Put stack back */ - addq $(11*8), %rsp - CFI_ADJUST_CFA_OFFSET -11*8 + addq $(6*8), %rsp + CFI_ADJUST_CFA_OFFSET -6*8 nested_nmi_out: popq_cfi %rdx @@ -1664,18 +1753,18 @@ first_nmi: * +-------------------------+ * | NMI executing variable | * +-------------------------+ - * | Saved SS | - * | Saved Return RSP | - * | Saved RFLAGS | - * | Saved CS | - * | Saved RIP | - * +-------------------------+ * | copied SS | * | copied Return RSP | * | copied RFLAGS | * | copied CS | * | copied RIP | * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ * | pt_regs | * +-------------------------+ * @@ -1691,9 +1780,14 @@ first_nmi: /* Set the NMI executing variable on the stack. */ pushq_cfi $1 + /* + * Leave room for the "copied" frame + */ + subq $(5*8), %rsp + /* Copy the stack frame to the Saved frame */ .rept 5 - pushq_cfi 6*8(%rsp) + pushq_cfi 11*8(%rsp) .endr CFI_DEF_CFA_OFFSET SS+8-RIP @@ -1714,12 +1808,15 @@ repeat_nmi: * is benign for the non-repeat case, where 1 was pushed just above * to this very stack slot). */ - movq $1, 5*8(%rsp) + movq $1, 10*8(%rsp) /* Make another copy, this one may be modified by nested NMIs */ + addq $(10*8), %rsp + CFI_ADJUST_CFA_OFFSET -10*8 .rept 5 - pushq_cfi 4*8(%rsp) + pushq_cfi -6*8(%rsp) .endr + subq $(5*8), %rsp CFI_DEF_CFA_OFFSET SS+8-RIP end_repeat_nmi: @@ -1770,8 +1867,12 @@ nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + + /* Pop the extra iret frame */ + addq $(5*8), %rsp + /* Clear the NMI executing stack variable */ - movq $0, 10*8(%rsp) + movq $0, 5*8(%rsp) jmp irq_return CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c3a7cb4bf6e6..1d414029f1d8 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -206,6 +206,21 @@ static int ftrace_modify_code(unsigned long ip, unsigned const char *old_code, unsigned const char *new_code); +/* + * Should never be called: + * As it is only called by __ftrace_replace_code() which is called by + * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() + * which is called to turn mcount into nops or nops into function calls + * but not to convert a function from not using regs to one that uses + * regs, which ftrace_modify_call() is for. + */ +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + WARN_ON(1); + return -EINVAL; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); @@ -220,6 +235,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func) ret = ftrace_modify_code(ip, old, new); + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + } + atomic_dec(&modifying_ftrace_code); return ret; @@ -299,6 +322,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } +/* + * If the record has the FTRACE_FL_REGS set, that means that it + * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS + * is not not set, then it wants to convert to the normal callback. + */ +static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +/* + * The FTRACE_FL_REGS_EN is set when the record already points to + * a function that saves all the regs. Basically the '_EN' version + * represents the current state of the function. + */ +static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS_EN) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; @@ -306,7 +355,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -316,6 +365,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + ftrace_addr = get_ftrace_old_addr(rec); + /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -360,13 +413,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); + nop = ftrace_call_replace(ip, ftrace_addr); + + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) + goto update; + + /* Check both ftrace_addr and ftrace_old_addr */ + ftrace_addr = get_ftrace_old_addr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } + update: return probe_kernel_write((void *)ip, &nop[0], 1); } @@ -405,12 +466,14 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return add_update_call(rec, ftrace_addr); @@ -455,12 +518,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return finish_update_call(rec, ftrace_addr); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index d42ab17b7397..8e7f6556028f 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -266,6 +266,19 @@ num_subarch_entries = (. - subarch_entries) / 4 jmp default_entry #endif /* CONFIG_PARAVIRT */ +#ifdef CONFIG_HOTPLUG_CPU +/* + * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * up already except stack. We just set up stack here. Then call + * start_secondary(). + */ +ENTRY(start_cpu0) + movl stack_start, %ecx + movl %ecx, %esp + jmp *(initial_code) +ENDPROC(start_cpu0) +#endif + /* * Non-boot CPU entry point; entered from trampoline.S * We can't lgdt here, because lgdt itself uses a data segment, but @@ -287,27 +300,33 @@ ENTRY(startup_32_smp) leal -__PAGE_OFFSET(%ecx),%esp default_entry: - /* * New page tables may be in 4Mbyte page mode and may * be using the global pages. * * NOTE! If we are on a 486 we may have no cr4 at all! - * So we do not try to touch it unless we really have - * some bits in it to set. This won't work if the BSP - * implements cr4 but this AP does not -- very unlikely - * but be warned! The same applies to the pse feature - * if not equally supported. --macro - * - * NOTE! We have to correct for the fact that we're - * not yet offset PAGE_OFFSET.. + * Specifically, cr4 exists if and only if CPUID exists + * and has flags other than the FPU flag set. */ -#define cr4_bits pa(mmu_cr4_features) - movl cr4_bits,%edx - andl %edx,%edx - jz 6f - movl %cr4,%eax # Turn on paging options (PSE,PAE,..) - orl %edx,%eax + movl $X86_EFLAGS_ID,%ecx + pushl %ecx + popfl + pushfl + popl %eax + pushl $0 + popfl + pushfl + popl %edx + xorl %edx,%eax + testl %ecx,%eax + jz 6f # No ID flag = no CPUID = no CR4 + + movl $1,%eax + cpuid + andl $~1,%edx # Ignore CPUID.FPU + jz 6f # No flags or only CPUID.FPU = no CR4 + + movl pa(mmu_cr4_features),%eax movl %eax,%cr4 testb $X86_CR4_PAE, %al # check if PAE is enabled diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 94bf9cc2c7ee..980053c4b9cc 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -252,6 +252,22 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq +#ifdef CONFIG_HOTPLUG_CPU +/* + * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * up already except stack. We just set up stack here. Then call + * start_secondary(). + */ +ENTRY(start_cpu0) + movq stack_start(%rip),%rsp + movq initial_code(%rip),%rax + pushq $0 # fake return address to stop unwinder + pushq $__KERNEL_CS # set correct cs + pushq %rax # target address in negative space + lretq +ENDPROC(start_cpu0) +#endif + /* SMP bootup changes these two */ __REFDATA .align 8 diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 1460a5df92f7..e28670f9a589 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -434,7 +434,7 @@ void hpet_msi_unmask(struct irq_data *data) /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg |= HPET_TN_FSB; + cfg |= HPET_TN_ENABLE | HPET_TN_FSB; hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } @@ -445,7 +445,7 @@ void hpet_msi_mask(struct irq_data *data) /* mask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg &= ~HPET_TN_FSB; + cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB); hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index f250431fb505..245a71db401a 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -19,24 +19,17 @@ #include <asm/fpu-internal.h> #include <asm/user.h> -#ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> -# include <asm/user32.h> -#else -# define save_i387_xstate_ia32 save_i387_xstate -# define restore_i387_xstate_ia32 restore_i387_xstate -# define _fpstate_ia32 _fpstate -# define _xstate_ia32 _xstate -# define sig_xstate_ia32_size sig_xstate_size -# define fx_sw_reserved_ia32 fx_sw_reserved -# define user_i387_ia32_struct user_i387_struct -# define user32_fxsr_struct user_fxsr_struct -#endif - /* * Were we in an interrupt that interrupted kernel mode? * - * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * For now, with eagerfpu we will return interrupted kernel FPU + * state as not-idle. TBD: Ideally we can change the return value + * to something like __thread_has_fpu(current). But we need to + * be careful of doing __thread_clear_has_fpu() before saving + * the FPU etc for supporting nested uses etc. For now, take + * the simple route! + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that * pair does nothing at all: the thread must not have fpu (so * that we don't try to save the FPU state), and TS must * be set (so that the clts/stts pair does nothing that is @@ -44,6 +37,9 @@ */ static inline bool interrupted_kernel_fpu_idle(void) { + if (use_eager_fpu()) + return 0; + return !__thread_has_fpu(current) && (read_cr0() & X86_CR0_TS); } @@ -77,29 +73,29 @@ bool irq_fpu_usable(void) } EXPORT_SYMBOL(irq_fpu_usable); -void kernel_fpu_begin(void) +void __kernel_fpu_begin(void) { struct task_struct *me = current; - WARN_ON_ONCE(!irq_fpu_usable()); - preempt_disable(); if (__thread_has_fpu(me)) { __save_init_fpu(me); __thread_clear_has_fpu(me); - /* We do 'stts()' in kernel_fpu_end() */ - } else { + /* We do 'stts()' in __kernel_fpu_end() */ + } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task, NULL); clts(); } } -EXPORT_SYMBOL(kernel_fpu_begin); +EXPORT_SYMBOL(__kernel_fpu_begin); -void kernel_fpu_end(void) +void __kernel_fpu_end(void) { - stts(); - preempt_enable(); + if (use_eager_fpu()) + math_state_restore(); + else + stts(); } -EXPORT_SYMBOL(kernel_fpu_end); +EXPORT_SYMBOL(__kernel_fpu_end); void unlazy_fpu(struct task_struct *tsk) { @@ -113,23 +109,15 @@ void unlazy_fpu(struct task_struct *tsk) } EXPORT_SYMBOL(unlazy_fpu); -#ifdef CONFIG_MATH_EMULATION -# define HAVE_HWFP (boot_cpu_data.hard_math) -#else -# define HAVE_HWFP 1 -#endif - -static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; - clts(); if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); asm volatile("fxsave %0" : : "m" (fx_scratch)); @@ -138,7 +126,6 @@ static void __cpuinit mxcsr_feature_mask_init(void) mask = 0x0000ffbf; } mxcsr_feature_mask &= mask; - stts(); } static void __cpuinit init_thread_xstate(void) @@ -188,13 +175,16 @@ void __cpuinit fpu_init(void) cr0 |= X86_CR0_EM; write_cr0(cr0); - if (!smp_processor_id()) + /* + * init_thread_xstate is only called once to avoid overriding + * xstate_size during boot time or during CPU hotplug. + */ + if (xstate_size == 0) init_thread_xstate(); mxcsr_feature_mask_init(); - /* clean state in init */ - current_thread_info()->status = 0; - clear_used_math(); + xsave_init(); + eager_fpu_init(); } void fpu_finit(struct fpu *fpu) @@ -205,12 +195,7 @@ void fpu_finit(struct fpu *fpu) } if (cpu_has_fxsr) { - struct i387_fxsave_struct *fx = &fpu->state->fxsave; - - memset(fx, 0, xstate_size); - fx->cwd = 0x37f; - if (cpu_has_xmm) - fx->mxcsr = MXCSR_DEFAULT; + fx_finit(&fpu->state->fxsave); } else { struct i387_fsave_struct *fp = &fpu->state->fsave; memset(fp, 0, xstate_size); @@ -454,7 +439,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) * FXSR floating point environment conversions. */ -static void +void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; @@ -491,8 +476,8 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) memcpy(&to[i], &from[i], sizeof(to[0])); } -static void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) { struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; @@ -589,223 +574,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, } /* - * Signal frame handlers. - */ - -static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave; - - fp->status = fp->swd; - if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct))) - return -1; - return 1; -} - -static int save_i387_fxsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - struct user_i387_ia32_struct env; - int err = 0; - - convert_from_fxsr(&env, tsk); - if (__copy_to_user(buf, &env, sizeof(env))) - return -1; - - err |= __put_user(fx->swd, &buf->status); - err |= __put_user(X86_FXSR_MAGIC, &buf->magic); - if (err) - return -1; - - if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size)) - return -1; - return 1; -} - -static int save_i387_xsave(void __user *buf) -{ - struct task_struct *tsk = current; - struct _fpstate_ia32 __user *fx = buf; - int err = 0; - - - sanitize_i387_state(tsk); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. - * This will enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware applications can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - if (save_i387_fxsave(fx) < 0) - return -1; - - err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32, - sizeof(struct _fpx_sw_bytes)); - err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *) (buf + sig_xstate_ia32_size - - FP_XSTATE_MAGIC2_SIZE)); - if (err) - return -1; - - return 1; -} - -int save_i387_xstate_ia32(void __user *buf) -{ - struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf; - struct task_struct *tsk = current; - - if (!used_math()) - return 0; - - if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size)) - return -EACCES; - /* - * This will cause a "finit" to be triggered by the next - * attempted FPU operation by the 'current' process. - */ - clear_used_math(); - - if (!HAVE_HWFP) { - return fpregs_soft_get(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, fp) ? -1 : 1; - } - - unlazy_fpu(tsk); - - if (cpu_has_xsave) - return save_i387_xsave(fp); - if (cpu_has_fxsr) - return save_i387_fxsave(fp); - else - return save_i387_fsave(fp); -} - -static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - - return __copy_from_user(&tsk->thread.fpu.state->fsave, buf, - sizeof(struct i387_fsave_struct)); -} - -static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf, - unsigned int size) -{ - struct task_struct *tsk = current; - struct user_i387_ia32_struct env; - int err; - - err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0], - size); - /* mxcsr reserved bits must be masked to zero for security reasons */ - tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - if (err || __copy_from_user(&env, buf, sizeof(env))) - return 1; - convert_to_fxsr(tsk, &env); - - return 0; -} - -static int restore_i387_xsave(void __user *buf) -{ - struct _fpx_sw_bytes fx_sw_user; - struct _fpstate_ia32 __user *fx_user = - ((struct _fpstate_ia32 __user *) buf); - struct i387_fxsave_struct __user *fx = - (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0]; - struct xsave_hdr_struct *xsave_hdr = - ¤t->thread.fpu.state->xsave.xsave_hdr; - u64 mask; - int err; - - if (check_for_xstate(fx, buf, &fx_sw_user)) - goto fx_only; - - mask = fx_sw_user.xstate_bv; - - err = restore_i387_fxsave(buf, fx_sw_user.xstate_size); - - xsave_hdr->xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; - - /* - * Init the state that is not present in the memory layout - * and enabled by the OS. - */ - mask = ~(pcntxt_mask & ~mask); - xsave_hdr->xstate_bv &= mask; - - return err; -fx_only: - /* - * Couldn't find the extended state information in the memory - * layout. Restore the FP/SSE and init the other extended state - * enabled by the OS. - */ - xsave_hdr->xstate_bv = XSTATE_FPSSE; - return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct)); -} - -int restore_i387_xstate_ia32(void __user *buf) -{ - int err; - struct task_struct *tsk = current; - struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf; - - if (HAVE_HWFP) - clear_fpu(tsk); - - if (!buf) { - if (used_math()) { - clear_fpu(tsk); - clear_used_math(); - } - - return 0; - } else - if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size)) - return -EACCES; - - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } - - if (HAVE_HWFP) { - if (cpu_has_xsave) - err = restore_i387_xsave(buf); - else if (cpu_has_fxsr) - err = restore_i387_fxsave(fp, sizeof(struct - i387_fxsave_struct)); - else - err = restore_i387_fsave(fp); - } else { - err = fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, fp) != 0; - } - set_used_math(); - - return err; -} - -/* * FPU state for core dumps. * This is only used for a.out dumps now. * It is declared generically using elf_fpregset_t (which is diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 36d1853e91af..9a5c460404dc 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -263,7 +263,7 @@ static void i8259A_shutdown(void) * out of. */ outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ - outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ + outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ } static struct syscore_ops i8259_syscore_ops = { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index d44f7829968e..e4595f105910 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -92,7 +92,8 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - + irq_stats(j)->irq_tlb_count); seq_printf(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) @@ -147,7 +148,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; - sum += irq_stats(cpu)->irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR sum += irq_stats(cpu)->irq_thermal_count; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 3f61904365cf..836f8322960e 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -746,7 +746,9 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { int err; +#ifdef CONFIG_DEBUG_RODATA char opc[BREAK_INSTR_SIZE]; +#endif /* CONFIG_DEBUG_RODATA */ bpt->type = BP_BREAKPOINT; err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e2f751efb7b1..57916c0d3cf6 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -541,6 +541,23 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } +#ifdef KPROBES_CAN_USE_FTRACE +static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); +} +#endif + /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. @@ -599,6 +616,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } else if (kprobe_running()) { p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { +#ifdef KPROBES_CAN_USE_FTRACE + if (kprobe_ftrace(p)) { + skip_singlestep(p, regs, kcb); + return 1; + } +#endif setup_singlestep(p, regs, kcb, 0); return 1; } @@ -1052,6 +1075,50 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } +#ifdef KPROBES_CAN_USE_FTRACE +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} +#endif + int __init arch_init_kprobes(void) { return arch_init_optprobes(); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index c1d61ee4b4f1..08b973f64032 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -42,6 +42,7 @@ #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> +#include <asm/kvm_guest.h> static int kvmapf = 1; @@ -62,6 +63,15 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static int kvmclock_vsyscall = 1; +static int parse_no_kvmclock_vsyscall(char *arg) +{ + kvmclock_vsyscall = 0; + return 0; +} + +early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); + 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; @@ -110,11 +120,6 @@ void kvm_async_pf_task_wait(u32 token) struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node n, *e; DEFINE_WAIT(wait); - int cpu, idle; - - cpu = get_cpu(); - idle = idle_cpu(cpu); - put_cpu(); spin_lock(&b->lock); e = _find_apf_task(b, token); @@ -128,7 +133,7 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = idle || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1; init_waitqueue_head(&n.wq); hlist_add_head(&n.link, &b->list); spin_unlock(&b->lock); @@ -247,7 +252,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ + rcu_irq_enter(); + exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); + rcu_irq_exit(); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); @@ -354,6 +362,7 @@ static void kvm_pv_guest_cpu_reboot(void *unused) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) wrmsrl(MSR_KVM_PV_EOI_EN, 0); kvm_pv_disable_apf(); + kvm_disable_steal_time(); } static int kvm_pv_reboot_notify(struct notifier_block *nb, @@ -396,9 +405,7 @@ void kvm_disable_steal_time(void) #ifdef CONFIG_SMP static void __init kvm_smp_prepare_boot_cpu(void) { -#ifdef CONFIG_KVM_CLOCK WARN_ON(kvm_register_clock("primary cpu clock")); -#endif kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); } @@ -469,6 +476,9 @@ void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); + if (kvmclock_vsyscall) + kvm_setup_vsyscall_timeinfo(); + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index f1b42b3a186c..220a360010f8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -23,6 +23,7 @@ #include <asm/apic.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/memblock.h> #include <asm/x86_init.h> #include <asm/reboot.h> @@ -39,7 +40,7 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; /* @@ -52,15 +53,20 @@ static unsigned long kvm_get_wallclock(void) struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; int low, high; + int cpu; low = (int)__pa_symbol(&wall_clock); high = ((u64)__pa_symbol(&wall_clock) >> 32); native_write_msr(msr_kvm_wall_clock, low, high); - vcpu_time = &get_cpu_var(hv_clock); + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); - put_cpu_var(hv_clock); + + preempt_enable(); return ts.tv_sec; } @@ -74,9 +80,11 @@ static cycle_t kvm_clock_read(void) { struct pvclock_vcpu_time_info *src; cycle_t ret; + int cpu; preempt_disable_notrace(); - src = &__get_cpu_var(hv_clock); + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -99,8 +107,15 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs) static unsigned long kvm_get_tsc_khz(void) { struct pvclock_vcpu_time_info *src; - src = &per_cpu(hv_clock, 0); - return pvclock_tsc_khz(src); + int cpu; + unsigned long tsc_khz; + + preempt_disable(); + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; + tsc_khz = pvclock_tsc_khz(src); + preempt_enable(); + return tsc_khz; } static void kvm_get_preset_lpj(void) @@ -119,10 +134,14 @@ bool kvm_check_and_clear_guest_paused(void) { bool ret = false; struct pvclock_vcpu_time_info *src; + int cpu = smp_processor_id(); - src = &__get_cpu_var(hv_clock); + if (!hv_clock) + return ret; + + src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { - __this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED); + src->flags &= ~PVCLOCK_GUEST_STOPPED; ret = true; } @@ -141,9 +160,10 @@ int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high, ret; + struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti; - low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; - high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); + low = (int)__pa(src) | 1; + high = ((u64)__pa(src) >> 32); ret = native_write_msr_safe(msr_kvm_system_time, low, high); printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", cpu, high, low, txt); @@ -197,6 +217,8 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + unsigned long mem; + if (!kvm_para_available()) return; @@ -209,8 +231,18 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); - if (kvm_register_clock("boot clock")) + mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS, + PAGE_SIZE); + if (!mem) + return; + hv_clock = __va(mem); + + if (kvm_register_clock("boot clock")) { + hv_clock = NULL; + memblock_free(mem, + sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); return; + } pv_time_ops.sched_clock = kvm_clock_read; x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; @@ -233,3 +265,37 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); } + +int __init kvm_setup_vsyscall_timeinfo(void) +{ +#ifdef CONFIG_X86_64 + int cpu; + int ret; + u8 flags; + struct pvclock_vcpu_time_info *vcpu_time; + unsigned int size; + + size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS; + + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { + preempt_enable(); + return 1; + } + + if ((ret = pvclock_init_vsyscall(hv_clock, size))) { + preempt_enable(); + return ret; + } + + preempt_enable(); + + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; +#endif + return 0; +} diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 82746f942cd8..efdec7cd8e01 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -8,8 +8,8 @@ * Tigran Aivazian <tigran@aivazian.fsnet.co.uk> * * Maintainers: - * Andreas Herrmann <andreas.herrmann3@amd.com> - * Borislav Petkov <borislav.petkov@amd.com> + * Andreas Herrmann <herrmann.der.user@googlemail.com> + * Borislav Petkov <bp@alien8.de> * * This driver allows to upgrade microcode on F10h AMD * CPUs and later. @@ -75,20 +75,113 @@ struct microcode_amd { static struct equiv_cpu_entry *equiv_cpu_table; -/* page-sized ucode patch buffer */ -void *patch; +struct ucode_patch { + struct list_head plist; + void *data; + u32 patch_id; + u16 equiv_cpu; +}; + +static LIST_HEAD(pcache); + +static u16 find_equiv_id(unsigned int cpu) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + int i = 0; + + if (!equiv_cpu_table) + return 0; + + while (equiv_cpu_table[i].installed_cpu != 0) { + if (uci->cpu_sig.sig == equiv_cpu_table[i].installed_cpu) + return equiv_cpu_table[i].equiv_cpu; + + i++; + } + return 0; +} + +static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu) +{ + int i = 0; + + BUG_ON(!equiv_cpu_table); + + while (equiv_cpu_table[i].equiv_cpu != 0) { + if (equiv_cpu == equiv_cpu_table[i].equiv_cpu) + return equiv_cpu_table[i].installed_cpu; + i++; + } + return 0; +} + +/* + * a small, trivial cache of per-family ucode patches + */ +static struct ucode_patch *cache_find_patch(u16 equiv_cpu) +{ + struct ucode_patch *p; + + list_for_each_entry(p, &pcache, plist) + if (p->equiv_cpu == equiv_cpu) + return p; + return NULL; +} + +static void update_cache(struct ucode_patch *new_patch) +{ + struct ucode_patch *p; + + list_for_each_entry(p, &pcache, plist) { + if (p->equiv_cpu == new_patch->equiv_cpu) { + if (p->patch_id >= new_patch->patch_id) + /* we already have the latest patch */ + return; + + list_replace(&p->plist, &new_patch->plist); + kfree(p->data); + kfree(p); + return; + } + } + /* no patch found, add it */ + list_add_tail(&new_patch->plist, &pcache); +} + +static void free_cache(void) +{ + struct ucode_patch *p, *tmp; + + list_for_each_entry_safe(p, tmp, &pcache, plist) { + __list_del(p->plist.prev, p->plist.next); + kfree(p->data); + kfree(p); + } +} + +static struct ucode_patch *find_patch(unsigned int cpu) +{ + u16 equiv_id; + + equiv_id = find_equiv_id(cpu); + if (!equiv_id) + return NULL; + + return cache_find_patch(equiv_id); +} static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); + csig->sig = cpuid_eax(0x00000001); csig->rev = c->microcode; pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); return 0; } -static unsigned int verify_ucode_size(int cpu, u32 patch_size, +static unsigned int verify_patch_size(int cpu, u32 patch_size, unsigned int size) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -97,6 +190,7 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size, #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 #define F15H_MPB_MAX_SIZE 4096 +#define F16H_MPB_MAX_SIZE 3458 switch (c->x86) { case 0x14: @@ -105,6 +199,9 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size, case 0x15: max_size = F15H_MPB_MAX_SIZE; break; + case 0x16: + max_size = F16H_MPB_MAX_SIZE; + break; default: max_size = F1XH_MPB_MAX_SIZE; break; @@ -118,95 +215,37 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size, return patch_size; } -static u16 find_equiv_id(void) +static int apply_microcode_amd(int cpu) { - unsigned int current_cpu_id, i = 0; - - BUG_ON(equiv_cpu_table == NULL); - - current_cpu_id = cpuid_eax(0x00000001); - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (current_cpu_id == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } - return 0; -} + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_amd *mc_amd; + struct ucode_cpu_info *uci; + struct ucode_patch *p; + u32 rev, dummy; -/* - * we signal a good patch is found by returning its size > 0 - */ -static int get_matching_microcode(int cpu, const u8 *ucode_ptr, - unsigned int leftover_size, int rev, - unsigned int *current_size) -{ - struct microcode_header_amd *mc_hdr; - unsigned int actual_size, patch_size; - u16 equiv_cpu_id; + BUG_ON(raw_smp_processor_id() != cpu); - /* size of the current patch we're staring at */ - patch_size = *(u32 *)(ucode_ptr + 4); - *current_size = patch_size + SECTION_HDR_SIZE; + uci = ucode_cpu_info + cpu; - equiv_cpu_id = find_equiv_id(); - if (!equiv_cpu_id) + p = find_patch(cpu); + if (!p) return 0; - /* - * let's look at the patch header itself now - */ - mc_hdr = (struct microcode_header_amd *)(ucode_ptr + SECTION_HDR_SIZE); + mc_amd = p->data; + uci->mc = p->data; - if (mc_hdr->processor_rev_id != equiv_cpu_id) - return 0; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* ucode might be chipset specific -- currently we don't support this */ - if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { - pr_err("CPU%d: chipset specific code not yet supported\n", - cpu); + /* need to apply patch? */ + if (rev >= mc_amd->hdr.patch_id) { + c->microcode = rev; return 0; } - if (mc_hdr->patch_id <= rev) - return 0; - - /* - * now that the header looks sane, verify its size - */ - actual_size = verify_ucode_size(cpu, patch_size, leftover_size); - if (!actual_size) - return 0; - - /* clear the patch buffer */ - memset(patch, 0, PAGE_SIZE); - - /* all looks ok, get the binary patch */ - get_ucode_data(patch, ucode_ptr + SECTION_HDR_SIZE, actual_size); - - return actual_size; -} - -static int apply_microcode_amd(int cpu) -{ - u32 rev, dummy; - int cpu_num = raw_smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - struct microcode_amd *mc_amd = uci->mc; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - /* We should bind the task to the CPU */ - BUG_ON(cpu_num != cpu); - - if (mc_amd == NULL) - return 0; - wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); - /* get patch id after patching */ - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* check current patch id and patch's id for match */ + /* verify patch application was successful */ + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev != mc_amd->hdr.patch_id) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -238,7 +277,7 @@ static int install_equiv_cpu_table(const u8 *buf) return -ENOMEM; } - get_ucode_data(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); + memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); /* add header length */ return size + CONTAINER_HDR_SZ; @@ -250,61 +289,113 @@ static void free_equiv_cpu_table(void) equiv_cpu_table = NULL; } -static enum ucode_state -generic_load_microcode(int cpu, const u8 *data, size_t size) +static void cleanup(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct microcode_header_amd *mc_hdr = NULL; - unsigned int mc_size, leftover, current_size = 0; + free_equiv_cpu_table(); + free_cache(); +} + +/* + * We return the current size even if some of the checks failed so that + * we can skip over the next patch. If we return a negative value, we + * signal a grave error like a memory allocation has failed and the + * driver cannot continue functioning normally. In such cases, we tear + * down everything we've used up so far and exit. + */ +static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_header_amd *mc_hdr; + struct ucode_patch *patch; + unsigned int patch_size, crnt_size, ret; + u32 proc_fam; + u16 proc_id; + + patch_size = *(u32 *)(fw + 4); + crnt_size = patch_size + SECTION_HDR_SIZE; + mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE); + proc_id = mc_hdr->processor_rev_id; + + proc_fam = find_cpu_family_by_equiv_cpu(proc_id); + if (!proc_fam) { + pr_err("No patch family for equiv ID: 0x%04x\n", proc_id); + return crnt_size; + } + + /* check if patch is for the current family */ + proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff); + if (proc_fam != c->x86) + return crnt_size; + + if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { + pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", + mc_hdr->patch_id); + return crnt_size; + } + + ret = verify_patch_size(cpu, patch_size, leftover); + if (!ret) { + pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id); + return crnt_size; + } + + patch = kzalloc(sizeof(*patch), GFP_KERNEL); + if (!patch) { + pr_err("Patch allocation failure.\n"); + return -EINVAL; + } + + patch->data = kzalloc(patch_size, GFP_KERNEL); + if (!patch->data) { + pr_err("Patch data allocation failure.\n"); + kfree(patch); + return -EINVAL; + } + + /* All looks ok, copy patch... */ + memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size); + INIT_LIST_HEAD(&patch->plist); + patch->patch_id = mc_hdr->patch_id; + patch->equiv_cpu = proc_id; + + /* ... and add to cache. */ + update_cache(patch); + + return crnt_size; +} + +static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) +{ + enum ucode_state ret = UCODE_ERROR; + unsigned int leftover; + u8 *fw = (u8 *)data; + int crnt_size = 0; int offset; - const u8 *ucode_ptr = data; - void *new_mc = NULL; - unsigned int new_rev = uci->cpu_sig.rev; - enum ucode_state state = UCODE_ERROR; - offset = install_equiv_cpu_table(ucode_ptr); + offset = install_equiv_cpu_table(data); if (offset < 0) { pr_err("failed to create equivalent cpu table\n"); - goto out; + return ret; } - ucode_ptr += offset; + fw += offset; leftover = size - offset; - if (*(u32 *)ucode_ptr != UCODE_UCODE_TYPE) { + if (*(u32 *)fw != UCODE_UCODE_TYPE) { pr_err("invalid type field in container file section header\n"); - goto free_table; + free_equiv_cpu_table(); + return ret; } while (leftover) { - mc_size = get_matching_microcode(cpu, ucode_ptr, leftover, - new_rev, ¤t_size); - if (mc_size) { - mc_hdr = patch; - new_mc = patch; - new_rev = mc_hdr->patch_id; - goto out_ok; - } - - ucode_ptr += current_size; - leftover -= current_size; - } + crnt_size = verify_and_add_patch(cpu, fw, leftover); + if (crnt_size < 0) + return ret; - if (!new_mc) { - state = UCODE_NFOUND; - goto free_table; + fw += crnt_size; + leftover -= crnt_size; } -out_ok: - uci->mc = new_mc; - state = UCODE_OK; - pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n", - cpu, uci->cpu_sig.rev, new_rev); - -free_table: - free_equiv_cpu_table(); - -out: - return state; + return UCODE_OK; } /* @@ -315,7 +406,7 @@ out: * * This legacy file is always smaller than 2K in size. * - * Starting at family 15h they are in family specific firmware files: + * Beginning with family 15h, they are in family-specific firmware files: * * amd-ucode/microcode_amd_fam15h.bin * amd-ucode/microcode_amd_fam16h.bin @@ -323,12 +414,17 @@ out: * * These might be larger than 2K. */ -static enum ucode_state request_microcode_amd(int cpu, struct device *device) +static enum ucode_state request_microcode_amd(int cpu, struct device *device, + bool refresh_fw) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; - const struct firmware *fw; - enum ucode_state ret = UCODE_NFOUND; struct cpuinfo_x86 *c = &cpu_data(cpu); + enum ucode_state ret = UCODE_NFOUND; + const struct firmware *fw; + + /* reload ucode container only on the boot cpu */ + if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + return UCODE_OK; if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); @@ -344,12 +440,17 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) goto fw_release; } - ret = generic_load_microcode(cpu, fw->data, fw->size); + /* free old equiv table */ + free_equiv_cpu_table(); + + ret = load_microcode_amd(cpu, fw->data, fw->size); + if (ret != UCODE_OK) + cleanup(); -fw_release: + fw_release: release_firmware(fw); -out: + out: return ret; } @@ -383,14 +484,10 @@ struct microcode_ops * __init init_amd_microcode(void) return NULL; } - patch = (void *)get_zeroed_page(GFP_KERNEL); - if (!patch) - return NULL; - return µcode_amd_ops; } void __exit exit_amd_microcode(void) { - free_page((unsigned long)patch); + cleanup(); } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 9e5bcf1e2376..3a04b224d0c0 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -279,19 +279,18 @@ static struct platform_device *microcode_pdev; static int reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + enum ucode_state ustate; int err = 0; - if (uci->valid) { - enum ucode_state ustate; - - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - } + if (!uci->valid) + return err; + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); + if (ustate == UCODE_OK) + apply_microcode_on_target(cpu); + else + if (ustate == UCODE_ERROR) + err = -EINVAL; return err; } @@ -373,18 +372,15 @@ static void microcode_fini_cpu(int cpu) static enum ucode_state microcode_resume_cpu(int cpu) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - if (!uci->mc) - return UCODE_NFOUND; - pr_debug("CPU%d updated upon resume\n", cpu); - apply_microcode_on_target(cpu); + + if (apply_microcode_on_target(cpu)) + return UCODE_ERROR; return UCODE_OK; } -static enum ucode_state microcode_init_cpu(int cpu) +static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) { enum ucode_state ustate; @@ -395,7 +391,8 @@ static enum ucode_state microcode_init_cpu(int cpu) if (system_state != SYSTEM_RUNNING) return UCODE_NFOUND; - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, + refresh_fw); if (ustate == UCODE_OK) { pr_debug("CPU%d updated upon init\n", cpu); @@ -408,14 +405,11 @@ static enum ucode_state microcode_init_cpu(int cpu) static enum ucode_state microcode_update_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; if (uci->valid) - ustate = microcode_resume_cpu(cpu); - else - ustate = microcode_init_cpu(cpu); + return microcode_resume_cpu(cpu); - return ustate; + return microcode_init_cpu(cpu, false); } static int mc_device_add(struct device *dev, struct subsys_interface *sif) @@ -431,7 +425,7 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif) if (err) return err; - if (microcode_init_cpu(cpu) == UCODE_ERROR) + if (microcode_init_cpu(cpu, true) == UCODE_ERROR) return -EINVAL; return err; @@ -480,34 +474,41 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) struct device *dev; dev = get_cpu_device(cpu); - switch (action) { + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: microcode_update_cpu(cpu); - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: pr_debug("CPU%d added\n", cpu); + /* + * "break" is missing on purpose here because we want to fall + * through in order to create the sysfs group. + */ + + case CPU_DOWN_FAILED: if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); break; + case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&dev->kobj, &mc_attr_group); pr_debug("CPU%d removed\n", cpu); break; /* + * case CPU_DEAD: + * * When a CPU goes offline, don't free up or invalidate the copy of * the microcode in kernel memory, so that we can reuse it when the * CPU comes back online without unnecessarily requesting the userspace * for it again. */ - case CPU_UP_CANCELED_FROZEN: - /* The CPU refused to come up during a system resume */ - microcode_fini_cpu(cpu); - break; } + + /* The CPU refused to come up during a system resume */ + if (action == CPU_UP_CANCELED_FROZEN) + microcode_fini_cpu(cpu); + return NOTIFY_OK; } diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 0327e2b3c408..3544aed39338 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -405,7 +405,8 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } -static enum ucode_state request_microcode_fw(int cpu, struct device *device) +static enum ucode_state request_microcode_fw(int cpu, struct device *device, + bool refresh_fw) { char name[30]; struct cpuinfo_x86 *c = &cpu_data(cpu); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index eb113693f043..a7c5661f8496 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -257,12 +257,14 @@ static int __init msr_init(void) goto out_chrdev; } msr_class->devnode = msr_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = msr_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -271,6 +273,7 @@ out_class: i = 0; for_each_online_cpu(i) msr_device_destroy(i); + put_online_cpus(); class_destroy(msr_class); out_chrdev: __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); @@ -281,11 +284,13 @@ out: static void __exit msr_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) msr_device_destroy(cpu); class_destroy(msr_class); __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); } module_init(msr_init); diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c new file mode 100644 index 000000000000..e309cc5c276e --- /dev/null +++ b/arch/x86/kernel/perf_regs.c @@ -0,0 +1,105 @@ +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/perf_event.h> +#include <linux/bug.h> +#include <linux/stddef.h> +#include <asm/perf_regs.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_X86_32 +#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX +#else +#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX +#endif + +#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) + +static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { + PT_REGS_OFFSET(PERF_REG_X86_AX, ax), + PT_REGS_OFFSET(PERF_REG_X86_BX, bx), + PT_REGS_OFFSET(PERF_REG_X86_CX, cx), + PT_REGS_OFFSET(PERF_REG_X86_DX, dx), + PT_REGS_OFFSET(PERF_REG_X86_SI, si), + PT_REGS_OFFSET(PERF_REG_X86_DI, di), + PT_REGS_OFFSET(PERF_REG_X86_BP, bp), + PT_REGS_OFFSET(PERF_REG_X86_SP, sp), + PT_REGS_OFFSET(PERF_REG_X86_IP, ip), + PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags), + PT_REGS_OFFSET(PERF_REG_X86_CS, cs), + PT_REGS_OFFSET(PERF_REG_X86_SS, ss), +#ifdef CONFIG_X86_32 + PT_REGS_OFFSET(PERF_REG_X86_DS, ds), + PT_REGS_OFFSET(PERF_REG_X86_ES, es), + PT_REGS_OFFSET(PERF_REG_X86_FS, fs), + PT_REGS_OFFSET(PERF_REG_X86_GS, gs), +#else + /* + * The pt_regs struct does not store + * ds, es, fs, gs in 64 bit mode. + */ + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, +#endif +#ifdef CONFIG_X86_64 + PT_REGS_OFFSET(PERF_REG_X86_R8, r8), + PT_REGS_OFFSET(PERF_REG_X86_R9, r9), + PT_REGS_OFFSET(PERF_REG_X86_R10, r10), + PT_REGS_OFFSET(PERF_REG_X86_R11, r11), + PT_REGS_OFFSET(PERF_REG_X86_R12, r12), + PT_REGS_OFFSET(PERF_REG_X86_R13, r13), + PT_REGS_OFFSET(PERF_REG_X86_R14, r14), + PT_REGS_OFFSET(PERF_REG_X86_R15, r15), +#endif +}; + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) + return 0; + + return regs_get_register(regs, pt_regs_offset[idx]); +} + +#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) + +#ifdef CONFIG_X86_32 +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} +#else /* CONFIG_X86_64 */ +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ + (1ULL << PERF_REG_X86_ES) | \ + (1ULL << PERF_REG_X86_FS) | \ + (1ULL << PERF_REG_X86_GS)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + if (mask & REG_NOSUPPORT) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_IA32)) + return PERF_SAMPLE_REGS_ABI_32; + else + return PERF_SAMPLE_REGS_ABI_64; +} +#endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 0bc72e2069e3..d5f15c3f7b25 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -150,7 +150,7 @@ static struct resource *find_oprom(struct pci_dev *pdev) return oprom; } -void *pci_map_biosrom(struct pci_dev *pdev) +void __iomem *pci_map_biosrom(struct pci_dev *pdev) { struct resource *oprom = find_oprom(pdev); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ef6a8456f719..2ed787f15bf0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -66,15 +66,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { int ret; - unlazy_fpu(src); - *dst = *src; if (fpu_allocated(&src->thread.fpu)) { memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); ret = fpu_alloc(&dst->thread.fpu); if (ret) return ret; - fpu_copy(&dst->thread.fpu, &src->thread.fpu); + fpu_copy(dst, src); } return 0; } @@ -97,16 +95,6 @@ void arch_task_cache_init(void) SLAB_PANIC | SLAB_NOTRACK, NULL); } -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - /* * Free current thread data structures etc.. */ @@ -163,7 +151,13 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - drop_fpu(tsk); + drop_init_fpu(tsk); + /* + * Free the FPU state for non xsave platforms. They get reallocated + * lazily at the first use. + */ + if (!use_eager_fpu()) + free_thread_xstate(tsk); } static void hard_disable_TSC(void) @@ -268,101 +262,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, propagate_user_return_notify(prev_p, next_p); } -int sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -int sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, - NULL, NULL); -} - -long -sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) -{ - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - -/* - * This gets run with %si containing the - * function to call, and %di containing - * the "args". - */ -extern void kernel_thread_helper(void); - -/* - * Create a kernel thread - */ -int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) -{ - struct pt_regs regs; - - memset(®s, 0, sizeof(regs)); - - regs.si = (unsigned long) fn; - regs.di = (unsigned long) arg; - -#ifdef CONFIG_X86_32 - regs.ds = __USER_DS; - regs.es = __USER_DS; - regs.fs = __KERNEL_PERCPU; - regs.gs = __KERNEL_STACK_CANARY; -#else - regs.ss = __KERNEL_DS; -#endif - - regs.orig_ax = -1; - regs.ip = (unsigned long) kernel_thread_helper; - regs.cs = __KERNEL_CS | get_kernel_rpl(); - regs.flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; - - /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); -} -EXPORT_SYMBOL(kernel_thread); - -/* - * sys_execve() executes a new program. - */ -long sys_execve(const char __user *name, - const char __user *const __user *argv, - const char __user *const __user *envp, struct pt_regs *regs) -{ - long error; - char *filename; - - filename = getname(name); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - return error; - error = do_execve(filename, argv, envp, regs); - -#ifdef CONFIG_X86_32 - if (error == 0) { - /* Make sure we don't return using sysenter.. */ - set_thread_flag(TIF_IRET); - } -#endif - - putname(filename); - return error; -} - /* * Idle related variables and functions */ @@ -377,11 +276,6 @@ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); #endif -static inline int hlt_use_halt(void) -{ - return 1; -} - #ifndef CONFIG_SMP static inline void play_dead(void) { @@ -481,28 +375,22 @@ void cpu_idle(void) */ void default_idle(void) { - if (hlt_use_halt()) { - trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle_rcuidle(1, smp_processor_id()); - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); + trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we + * test NEED_RESCHED: + */ + smp_mb(); - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - trace_power_end_rcuidle(smp_processor_id()); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); - } else { + if (!need_resched()) + safe_halt(); /* enables interrupts racelessly */ + else local_irq_enable(); - /* loop is done by the caller */ - cpu_relax(); - } + current_thread_info()->status |= TS_POLLING; + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(default_idle); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 516fa186121b..b5a8905785e6 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -57,6 +57,7 @@ #include <asm/switch_to.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); +asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); /* * Return saved PC of a blocked thread. @@ -127,24 +128,40 @@ void release_thread(struct task_struct *dead_task) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long unused, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { - struct pt_regs *childregs; + struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; int err; - childregs = task_pt_regs(p); - *childregs = *regs; - childregs->ax = 0; - childregs->sp = sp; - p->thread.sp = (unsigned long) childregs; p->thread.sp0 = (unsigned long) (childregs+1); - p->thread.ip = (unsigned long) ret_from_fork; + if (unlikely(p->flags & PF_KTHREAD)) { + /* kernel thread */ + memset(childregs, 0, sizeof(struct pt_regs)); + p->thread.ip = (unsigned long) ret_from_kernel_thread; + task_user_gs(p) = __KERNEL_STACK_CANARY; + childregs->ds = __USER_DS; + childregs->es = __USER_DS; + childregs->fs = __KERNEL_PERCPU; + childregs->bx = sp; /* function */ + childregs->bp = arg; + childregs->orig_ax = -1; + childregs->cs = __KERNEL_CS | get_kernel_rpl(); + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + p->fpu_counter = 0; + p->thread.io_bitmap_ptr = NULL; + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); + return 0; + } + *childregs = *current_pt_regs(); + childregs->ax = 0; + if (sp) + childregs->sp = sp; - task_user_gs(p) = get_user_gs(regs); + p->thread.ip = (unsigned long) ret_from_fork; + task_user_gs(p) = get_user_gs(current_pt_regs()); p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; @@ -190,10 +207,12 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->cs = __USER_CS; regs->ip = new_ip; regs->sp = new_sp; + regs->flags = X86_EFLAGS_IF; /* - * Free the old FP and other extended state + * force it to the iret return path by making it look as if there was + * some work pending. */ - free_thread_xstate(current); + set_thread_flag(TIF_NOTIFY_RESUME); } EXPORT_SYMBOL_GPL(start_thread); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0a980c9d7cb8..6e68a6194965 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -146,29 +146,17 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long unused, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { int err; struct pt_regs *childregs; struct task_struct *me = current; - childregs = ((struct pt_regs *) - (THREAD_SIZE + task_stack_page(p))) - 1; - *childregs = *regs; - - childregs->ax = 0; - if (user_mode(regs)) - childregs->sp = sp; - else - childregs->sp = (unsigned long)childregs; - + p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; + childregs = task_pt_regs(p); p->thread.sp = (unsigned long) childregs; - p->thread.sp0 = (unsigned long) (childregs+1); p->thread.usersp = me->thread.usersp; - set_tsk_thread_flag(p, TIF_FORK); - p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; @@ -178,6 +166,25 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs; savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); + + if (unlikely(p->flags & PF_KTHREAD)) { + /* kernel thread */ + memset(childregs, 0, sizeof(struct pt_regs)); + childregs->sp = (unsigned long)childregs; + childregs->ss = __KERNEL_DS; + childregs->bx = sp; /* function */ + childregs->bp = arg; + childregs->orig_ax = -1; + childregs->cs = __KERNEL_CS | get_kernel_rpl(); + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + return 0; + } + *childregs = *current_pt_regs(); + + childregs->ax = 0; + if (sp) + childregs->sp = sp; err = -ENOMEM; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -232,10 +239,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - /* - * Free the old FP and other extended state - */ - free_thread_xstate(current); } void diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index c4c6a5c2bf0f..b629bbe0d9bd 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,9 @@ #include <linux/signal.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> +#include <linux/rcupdate.h> +#include <linux/module.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -165,6 +168,35 @@ static inline bool invalid_selector(u16 value) #define FLAG_MASK FLAG_MASK_32 +/* + * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode + * when it traps. The previous stack will be directly underneath the saved + * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. + * + * Now, if the stack is empty, '®s->sp' is out of range. In this + * case we try to take the previous stack. To always return a non-null + * stack pointer we fall back to regs as stack if no previous stack + * exists. + * + * This is valid only for kernel mode traps. + */ +unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1); + unsigned long sp = (unsigned long)®s->sp; + struct thread_info *tinfo; + + if (context == (sp & ~(THREAD_SIZE - 1))) + return sp; + + tinfo = (struct thread_info *)context; + if (tinfo->previous_esp) + return tinfo->previous_esp; + + return (unsigned long)regs; +} +EXPORT_SYMBOL_GPL(kernel_stack_pointer); + static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); @@ -1332,9 +1364,6 @@ static const struct user_regset_view user_x86_64_view = { #define genregs32_get genregs_get #define genregs32_set genregs_set -#define user_i387_ia32_struct user_i387_struct -#define user32_fxsr_struct user_fxsr_struct - #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION @@ -1463,6 +1492,8 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + user_exit(); + /* * If we stepped into a sysenter/syscall insn, it trapped in * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. @@ -1511,6 +1542,13 @@ void syscall_trace_leave(struct pt_regs *regs) { bool step; + /* + * We may come here right after calling schedule_user() + * or do_notify_resume(), in which case we can be in RCU + * user mode. + */ + user_exit(); + audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) @@ -1526,4 +1564,6 @@ void syscall_trace_leave(struct pt_regs *regs) !test_thread_flag(TIF_SYSCALL_EMU); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); + + user_enter(); } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 42eb3300dfc6..85c39590c1a4 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -17,23 +17,13 @@ #include <linux/kernel.h> #include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/sched.h> +#include <linux/gfp.h> +#include <linux/bootmem.h> +#include <asm/fixmap.h> #include <asm/pvclock.h> -/* - * These are perodically updated - * xen: magic shared_info page - * kvm: gpa registered via msr - * and then copied here. - */ -struct pvclock_shadow_time { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - int tsc_shift; - u32 version; - u8 flags; -}; - static u8 valid_flags __read_mostly = 0; void pvclock_set_flags(u8 flags) @@ -41,34 +31,6 @@ void pvclock_set_flags(u8 flags) valid_flags = flags; } -static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow) -{ - u64 delta = native_read_tsc() - shadow->tsc_timestamp; - return pvclock_scale_delta(delta, shadow->tsc_to_nsec_mul, - shadow->tsc_shift); -} - -/* - * Reads a consistent set of time-base values from hypervisor, - * into a shadow data area. - */ -static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, - struct pvclock_vcpu_time_info *src) -{ - do { - dst->version = src->version; - rmb(); /* fetch version before data */ - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - dst->flags = src->flags; - rmb(); /* test version after fetching data */ - } while ((src->version & 1) || (dst->version != src->version)); - - return dst->version; -} - unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) { u64 pv_tsc_khz = 1000000ULL << 32; @@ -88,23 +50,32 @@ void pvclock_resume(void) atomic64_set(&last_value, 0); } +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) +{ + unsigned version; + cycle_t ret; + u8 flags; + + do { + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); + + return flags & valid_flags; +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { - struct pvclock_shadow_time shadow; unsigned version; - cycle_t ret, offset; + cycle_t ret; u64 last; + u8 flags; do { - version = pvclock_get_time_values(&shadow, src); - barrier(); - offset = pvclock_get_nsec_offset(&shadow); - ret = shadow.system_timestamp + offset; - barrier(); - } while (version != src->version); + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && - (shadow.flags & PVCLOCK_TSC_STABLE_BIT)) + (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; /* @@ -156,3 +127,71 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } + +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + +#ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + +/* + * Initialize the generic pvclock vsyscall state. This will allocate + * a/some page(s) for the per-vcpu pvclock information, set up a + * fixmap mapping for the page(s) + */ + +int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, + int size) +{ + int idx; + + WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + + pvclock_vdso_info = i; + + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { + __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, + __pa_symbol(i) + (idx*PAGE_SIZE), + PAGE_KERNEL_VVAR); + } + + + register_task_migration_notifier(&pvclock_migrate); + + return 0; +} +#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 52190a938b4a..4e8ba39eaf0f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -358,14 +358,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), }, }, - { /* Handle problems with rebooting on CompuLab SBC-FITPC2 */ - .callback = set_bios_reboot, - .ident = "CompuLab SBC-FITPC2", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "CompuLab"), - DMI_MATCH(DMI_PRODUCT_NAME, "SBC-FITPC2"), - }, - }, { /* Handle problems with rebooting on ASUS P4S800 */ .callback = set_bios_reboot, .ident = "ASUS P4S800", diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index af6db6ec5b2a..801602b5d745 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -195,12 +195,6 @@ void read_persistent_clock(struct timespec *ts) ts->tv_nsec = 0; } -unsigned long long native_read_tsc(void) -{ - return __native_read_tsc(); -} -EXPORT_SYMBOL(native_read_tsc); - static struct resource rtc_resources[] = { [0] = { @@ -225,7 +219,7 @@ static struct platform_device rtc_device = { static __init int add_rtc_cmos(void) { #ifdef CONFIG_PNP - static const char *ids[] __initconst = + static const char * const const ids[] __initconst = { "PNP0b00", "PNP0b01", "PNP0b02", }; struct pnp_dev *dev; struct pnp_id *id; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bf82c1e05464..23ddd558fbd5 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -68,6 +68,7 @@ #include <linux/percpu.h> #include <linux/crash_dump.h> #include <linux/tboot.h> +#include <linux/jiffies.h> #include <video/edid.h> @@ -142,11 +143,7 @@ int default_check_phys_apicid_present(int phys_apicid) } #endif -#ifndef CONFIG_DEBUG_BOOT_PARAMS -struct boot_params __initdata boot_params; -#else struct boot_params boot_params; -#endif /* * Machine setup.. @@ -919,8 +916,22 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { - max_pfn_mapped = init_memory_mapping(1UL<<32, - max_pfn<<PAGE_SHIFT); + int i; + unsigned long start, end; + unsigned long start_pfn, end_pfn; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, + NULL) { + + end = PFN_PHYS(end_pfn); + if (end <= (1UL<<32)) + continue; + + start = PFN_PHYS(start_pfn); + max_pfn_mapped = init_memory_mapping( + max((1UL<<32), start), end); + } + /* can we preseve max_low_pfn ?*/ max_low_pfn = max_pfn; } @@ -961,13 +972,11 @@ void __init setup_arch(char **cmdline_p) initmem_init(); memblock_find_dma_reserve(); -#ifdef CONFIG_KVM_CLOCK +#ifdef CONFIG_KVM_GUEST kvmclock_init(); #endif - x86_init.paging.pagetable_setup_start(swapper_pg_dir); - paging_init(); - x86_init.paging.pagetable_setup_done(swapper_pg_dir); + x86_init.paging.pagetable_init(); if (boot_cpu_data.cpuid_level >= 0) { /* A CPU has %cr4 if and only if it has CPUID */ @@ -1038,6 +1047,20 @@ void __init setup_arch(char **cmdline_p) mcheck_init(); arch_init_ideal_nops(); + + register_refined_jiffies(CLOCK_TICK_RATE); + +#ifdef CONFIG_EFI + /* Once setup is done above, disable efi_enabled on mismatched + * firmware/kernel archtectures since there is no support for + * runtime services. + */ + if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) { + pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); + efi_unmap_memmap(); + efi_enabled = 0; + } +#endif } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b280908a376e..fbbb604313a2 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -22,6 +22,7 @@ #include <linux/uaccess.h> #include <linux/user-return-notifier.h> #include <linux/uprobes.h> +#include <linux/context_tracking.h> #include <asm/processor.h> #include <asm/ucontext.h> @@ -114,11 +115,12 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, regs->orig_ax = -1; /* disable syscall checks */ get_user_ex(buf, &sc->fpstate); - err |= restore_i387_xstate(buf); get_user_ex(*pax, &sc->ax); } get_user_catch(err); + err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + return err; } @@ -206,35 +208,32 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { /* Default to using normal stack */ + unsigned long math_size = 0; unsigned long sp = regs->sp; + unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); -#ifdef CONFIG_X86_64 /* redzone */ - sp -= 128; -#endif /* CONFIG_X86_64 */ + if (config_enabled(CONFIG_X86_64)) + sp -= 128; if (!onsigstack) { /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { if (current->sas_ss_size) sp = current->sas_ss_sp + current->sas_ss_size; - } else { -#ifdef CONFIG_X86_32 - /* This is the legacy signal stack switching. */ - if ((regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) + } else if (config_enabled(CONFIG_X86_32) && + (regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; -#endif /* CONFIG_X86_32 */ } } if (used_math()) { - sp -= sig_xstate_size; -#ifdef CONFIG_X86_64 - sp = round_down(sp, 64); -#endif /* CONFIG_X86_64 */ + sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -247,8 +246,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (onsigstack && !likely(on_sig_stack(sp))) return (void __user *)-1L; - /* save i387 state */ - if (used_math() && save_i387_xstate(*fpstate) < 0) + /* save i387 and extended state */ + if (used_math() && + save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -357,7 +357,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sig, &frame->sig); put_user_ex(&frame->info, &frame->pinfo); put_user_ex(&frame->uc, &frame->puc); - err |= copy_siginfo_to_user(&frame->info, info); /* Create the ucontext. */ if (cpu_has_xsave) @@ -369,9 +368,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sas_ss_flags(regs->sp), &frame->uc.uc_stack.ss_flags); put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -388,6 +384,11 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, */ put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode); } put_user_catch(err); + + err |= copy_siginfo_to_user(&frame->info, info); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) return -EFAULT; @@ -436,8 +437,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sas_ss_flags(regs->sp), &frame->uc.uc_stack.ss_flags); put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -450,6 +449,9 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } } put_user_catch(err); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) return -EFAULT; @@ -474,6 +476,75 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } #endif /* CONFIG_X86_32 */ +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs) +{ +#ifdef CONFIG_X86_X32_ABI + struct rt_sigframe_x32 __user *frame; + void __user *restorer; + int err = 0; + void __user *fpstate = NULL; + + frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + return -EFAULT; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, info)) + return -EFAULT; + } + + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + put_user_ex(0, &frame->uc.uc__pad0); + + if (ka->sa.sa_flags & SA_RESTORER) { + restorer = ka->sa.sa_restorer; + } else { + /* could use a vstub here */ + restorer = NULL; + err |= -EFAULT; + } + put_user_ex(restorer, &frame->pretcode); + } put_user_catch(err); + + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (err) + return -EFAULT; + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ka->sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; +#endif /* CONFIG_X86_X32_ABI */ + + return 0; +} + #ifdef CONFIG_X86_32 /* * Atomically swap in the new signal mask, and wait for a signal. @@ -612,55 +683,22 @@ static int signr_convert(int sig) return sig; } -#ifdef CONFIG_X86_32 - -#define is_ia32 1 -#define ia32_setup_frame __setup_frame -#define ia32_setup_rt_frame __setup_rt_frame - -#else /* !CONFIG_X86_32 */ - -#ifdef CONFIG_IA32_EMULATION -#define is_ia32 test_thread_flag(TIF_IA32) -#else /* !CONFIG_IA32_EMULATION */ -#define is_ia32 0 -#endif /* CONFIG_IA32_EMULATION */ - -#ifdef CONFIG_X86_X32_ABI -#define is_x32 test_thread_flag(TIF_X32) - -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, - struct pt_regs *regs); -#else /* !CONFIG_X86_X32_ABI */ -#define is_x32 0 -#endif /* CONFIG_X86_X32_ABI */ - -int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs *regs); - -#endif /* CONFIG_X86_32 */ - static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, struct pt_regs *regs) { int usig = signr_convert(sig); sigset_t *set = sigmask_to_save(); + compat_sigset_t *cset = (compat_sigset_t *) set; /* Set up the stack frame */ - if (is_ia32) { + if (is_ia32_frame()) { if (ka->sa.sa_flags & SA_SIGINFO) - return ia32_setup_rt_frame(usig, ka, info, set, regs); + return ia32_setup_rt_frame(usig, ka, info, cset, regs); else - return ia32_setup_frame(usig, ka, set, regs); -#ifdef CONFIG_X86_X32_ABI - } else if (is_x32) { - return x32_setup_rt_frame(usig, ka, info, - (compat_sigset_t *)set, regs); -#endif + return ia32_setup_frame(usig, ka, cset, regs); + } else if (is_x32_frame()) { + return x32_setup_rt_frame(usig, ka, info, cset, regs); } else { return __setup_rt_frame(sig, ka, info, set, regs); } @@ -779,16 +817,16 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { + user_exit(); + #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ if (thread_info_flags & _TIF_MCE_NOTIFY) mce_notify_process(); #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ - if (thread_info_flags & _TIF_UPROBE) { - clear_thread_flag(TIF_UPROBE); + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); - } /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) @@ -801,9 +839,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) fire_user_return_notifiers(); -#ifdef CONFIG_X86_32 - clear_thread_flag(TIF_IRET); -#endif /* CONFIG_X86_32 */ + user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) @@ -824,72 +860,6 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) } #ifdef CONFIG_X86_X32_ABI -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, - struct pt_regs *regs) -{ - struct rt_sigframe_x32 __user *frame; - void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - return -EFAULT; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user32(&frame->info, info)) - return -EFAULT; - } - - put_user_try { - /* Create the ucontext. */ - if (cpu_has_xsave) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - put_user_ex(0, &frame->uc.uc__pad0); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (ka->sa.sa_flags & SA_RESTORER) { - restorer = ka->sa.sa_restorer; - } else { - /* could use a vstub here */ - restorer = NULL; - err |= -EFAULT; - } - put_user_ex(restorer, &frame->pretcode); - } put_user_catch(err); - - if (err) - return -EFAULT; - - /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; - - /* We use the x32 calling convention here... */ - regs->di = sig; - regs->si = (unsigned long) &frame->info; - regs->dx = (unsigned long) &frame->uc; - - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); - - regs->cs = __USER_CS; - regs->ss = __USER_DS; - - return 0; -} - asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) { struct rt_sigframe_x32 __user *frame; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c5a8c314c02..ed0fe385289d 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -68,6 +68,8 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> +#include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -125,8 +127,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; /* - * Report back to the Boot Processor. - * Running on AP. + * Report back to the Boot Processor during boot time or to the caller processor + * during CPU online. */ static void __cpuinit smp_callin(void) { @@ -138,15 +140,17 @@ static void __cpuinit smp_callin(void) * we may get here before an INIT-deassert IPI reaches * our local APIC. We have to wait for the IPI or we'll * lock up on an APIC access. + * + * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. */ - if (apic->wait_for_init_deassert) + cpuid = smp_processor_id(); + if (apic->wait_for_init_deassert && cpuid != 0) apic->wait_for_init_deassert(&init_deasserted); /* * (This works even if the APIC is not enabled.) */ phys_id = read_apic_id(); - cpuid = smp_processor_id(); if (cpumask_test_cpu(cpuid, cpu_callin_mask)) { panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, phys_id, cpuid); @@ -228,6 +232,8 @@ static void __cpuinit smp_callin(void) cpumask_set_cpu(cpuid, cpu_callin_mask); } +static int cpu0_logical_apicid; +static int enable_start_cpu0; /* * Activate a secondary processor. */ @@ -243,6 +249,8 @@ notrace static void __cpuinit start_secondary(void *unused) preempt_disable(); smp_callin(); + enable_start_cpu0 = 0; + #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); @@ -279,19 +287,30 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } +void __init smp_store_boot_cpu_info(void) +{ + int id = 0; /* CPU 0 */ + struct cpuinfo_x86 *c = &cpu_data(id); + + *c = boot_cpu_data; + c->cpu_index = id; +} + /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU */ - void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); *c = boot_cpu_data; c->cpu_index = id; - if (id != 0) - identify_secondary_cpu(c); + /* + * During boot time, CPU0 has this setup already. Save the info when + * bringing up AP or offlined CPU0. + */ + identify_secondary_cpu(c); } static bool __cpuinit @@ -313,7 +332,7 @@ do { \ static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (cpu_has_topoext) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && @@ -481,7 +500,7 @@ void __inquire_remote_apic(int apicid) * won't ... remember to clear down the APIC, etc later. */ int __cpuinit -wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) +wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; int maxlvt; @@ -489,7 +508,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) /* Target chip */ /* Boot on the stack */ /* Kick the second */ - apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid); + apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -649,6 +668,63 @@ static void __cpuinit announce_cpu(int cpu, int apicid) node, cpu, apicid); } +static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs) +{ + int cpu; + + cpu = smp_processor_id(); + if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0) + return NMI_HANDLED; + + return NMI_DONE; +} + +/* + * Wake up AP by INIT, INIT, STARTUP sequence. + * + * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS + * boot-strap code which is not a desired behavior for waking up BSP. To + * void the boot-strap code, wake up CPU0 by NMI instead. + * + * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined + * (i.e. physically hot removed and then hot added), NMI won't wake it up. + * We'll change this code in the future to wake up hard offlined CPU0 if + * real platform and request are available. + */ +static int __cpuinit +wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, + int *cpu0_nmi_registered) +{ + int id; + int boot_error; + + /* + * Wake up AP by INIT, INIT, STARTUP sequence. + */ + if (cpu) + return wakeup_secondary_cpu_via_init(apicid, start_ip); + + /* + * Wake up BSP by nmi. + * + * Register a NMI handler to help wake up CPU0. + */ + boot_error = register_nmi_handler(NMI_LOCAL, + wakeup_cpu0_nmi, 0, "wake_cpu0"); + + if (!boot_error) { + enable_start_cpu0 = 1; + *cpu0_nmi_registered = 1; + if (apic->dest_logical == APIC_DEST_LOGICAL) + id = cpu0_logical_apicid; + else + id = apicid; + boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); + } + + return boot_error; +} + /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -664,8 +740,10 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long boot_error = 0; int timeout; + int cpu0_nmi_registered = 0; - alternatives_smp_switch(1); + /* Just in case we booted with a single CPU. */ + alternatives_enable_smp(); idle->thread.sp = (unsigned long) (((struct pt_regs *) (THREAD_SIZE + task_stack_page(idle))) - 1); @@ -710,13 +788,16 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) } /* - * Kick the secondary CPU. Use the method in the APIC driver - * if it's defined - or use an INIT boot APIC message otherwise: + * Wake up a CPU in difference cases: + * - Use the method in the APIC driver if it's defined + * Otherwise, + * - Use an INIT boot APIC message for APs or NMI for BSP. */ if (apic->wakeup_secondary_cpu) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else - boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); + boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, + &cpu0_nmi_registered); if (!boot_error) { /* @@ -781,6 +862,13 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + return boot_error; } @@ -794,7 +882,7 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); - if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || + if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) || !apic->apic_id_valid(apicid)) { pr_err("%s: bad cpu %d\n", __func__, cpu); @@ -817,6 +905,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* the FPU context is blank, nobody can own it */ + __cpu_disable_lazy_restore(cpu); + err = do_boot_cpu(apicid, cpu, tidle); if (err) { pr_debug("do_boot_cpu failed %d\n", err); @@ -989,7 +1080,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) /* * Setup boot CPU information */ - smp_store_cpu_info(0); /* Final full version of the data */ + smp_store_boot_cpu_info(); /* Final full version of the data */ cpumask_copy(cpu_callin_mask, cpumask_of(0)); mb(); @@ -1025,6 +1116,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) */ setup_local_APIC(); + if (x2apic_mode) + cpu0_logical_apicid = apic_read(APIC_LDR); + else + cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + /* * Enable IO APIC before setting up error vector */ @@ -1053,20 +1149,6 @@ out: preempt_enable(); } -void arch_disable_nonboot_cpus_begin(void) -{ - /* - * Avoid the smp alternatives switch during the disable_nonboot_cpus(). - * In the suspend path, we will be back in the SMP mode shortly anyways. - */ - skip_smp_alternatives = true; -} - -void arch_disable_nonboot_cpus_end(void) -{ - skip_smp_alternatives = false; -} - void arch_enable_nonboot_cpus_begin(void) { set_mtrr_aps_delayed_init(); @@ -1227,19 +1309,6 @@ void cpu_disable_common(void) int native_cpu_disable(void) { - int cpu = smp_processor_id(); - - /* - * Perhaps use cpufreq to drop frequency, but that could go - * into generic code. - * - * We won't take down the boot processor on i386 due to some - * interrupts only being able to be serviced by the BSP. - * Especially so if we're not using an IOAPIC -zwane - */ - if (cpu == 0) - return -EBUSY; - clear_local_APIC(); cpu_disable_common(); @@ -1256,9 +1325,6 @@ void native_cpu_die(unsigned int cpu) if (per_cpu(cpu_state, cpu) == CPU_DEAD) { if (system_state == SYSTEM_RUNNING) pr_info("CPU %u is now offline\n", cpu); - - if (1 == num_online_cpus()) - alternatives_smp_switch(0); return; } msleep(100); @@ -1282,6 +1348,14 @@ void play_dead_common(void) local_irq_disable(); } +static bool wakeup_cpu0(void) +{ + if (smp_processor_id() == 0 && enable_start_cpu0) + return true; + + return false; +} + /* * We need to flush the caches before going to sleep, lest we have * dirty data in our caches when we come back up. @@ -1345,6 +1419,11 @@ static inline void mwait_play_dead(void) __monitor(mwait_ptr, 0, 0); mb(); __mwait(eax, 0); + /* + * If NMI wants to wake up CPU0, start CPU0. + */ + if (wakeup_cpu0()) + start_cpu0(); } } @@ -1355,6 +1434,11 @@ static inline void hlt_play_dead(void) while (1) { native_halt(); + /* + * If NMI wants to wake up CPU0, start CPU0. + */ + if (wakeup_cpu0()) + start_cpu0(); } } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index c346d1161488..cd3b2438a980 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child) return 1; } +void set_task_blockstep(struct task_struct *task, bool on) +{ + unsigned long debugctl; + + /* + * Ensure irq/preemption can't change debugctl in between. + * Note also that both TIF_BLOCKSTEP and debugctl should + * be changed atomically wrt preemption. + * FIXME: this means that set/clear TIF_BLOCKSTEP is simply + * wrong if task != current, SIGKILL can wakeup the stopped + * tracee and set/clear can play with the running task, this + * can confuse the next __switch_to_xtra(). + */ + local_irq_disable(); + debugctl = get_debugctlmsr(); + if (on) { + debugctl |= DEBUGCTLMSR_BTF; + set_tsk_thread_flag(task, TIF_BLOCKSTEP); + } else { + debugctl &= ~DEBUGCTLMSR_BTF; + clear_tsk_thread_flag(task, TIF_BLOCKSTEP); + } + if (task == current) + update_debugctlmsr(debugctl); + local_irq_enable(); +} + /* * Enable single or block step. */ @@ -169,19 +196,10 @@ static void enable_step(struct task_struct *child, bool block) * So no one should try to use debugger block stepping in a program * that uses user-mode single stepping itself. */ - if (enable_single_step(child) && block) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - set_tsk_thread_flag(child, TIF_BLOCKSTEP); - } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (enable_single_step(child) && block) + set_task_blockstep(child, true); + else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); } void user_enable_single_step(struct task_struct *child) @@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c deleted file mode 100644 index 0b0cb5fede19..000000000000 --- a/arch/x86/kernel/sys_i386_32.c +++ /dev/null @@ -1,40 +0,0 @@ -/* - * This file contains various random system calls that - * have a non-standard calling sequence on the Linux/i386 - * platform. - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/fs.h> -#include <linux/smp.h> -#include <linux/sem.h> -#include <linux/msg.h> -#include <linux/shm.h> -#include <linux/stat.h> -#include <linux/syscalls.h> -#include <linux/mman.h> -#include <linux/file.h> -#include <linux/utsname.h> -#include <linux/ipc.h> - -#include <linux/uaccess.h> -#include <linux/unistd.h> - -#include <asm/syscalls.h> - -/* - * Do a system call from kernel instead of calling sys_execve so we - * end up with proper pt_regs. - */ -int kernel_execve(const char *filename, - const char *const argv[], - const char *const envp[]) -{ - long __res; - asm volatile ("int $0x80" - : "=a" (__res) - : "0" (__NR_execve), "b" (filename), "c" (argv), "d" (envp) : "memory"); - return __res; -} diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index b4d3c3927dd8..97ef74b88e0f 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -21,37 +21,23 @@ /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. - * - * @flags denotes the allocation direction - bottomup or topdown - - * or vDSO; see call sites below. */ -unsigned long align_addr(unsigned long addr, struct file *filp, - enum align_flags flags) +static unsigned long get_align_mask(void) { - unsigned long tmp_addr; - /* handle 32- and 64-bit case with a single conditional */ if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32()))) - return addr; + return 0; if (!(current->flags & PF_RANDOMIZE)) - return addr; - - if (!((flags & ALIGN_VDSO) || filp)) - return addr; - - tmp_addr = addr; - - /* - * We need an address which is <= than the original - * one only when in topdown direction. - */ - if (!(flags & ALIGN_TOPDOWN)) - tmp_addr += va_align.mask; + return 0; - tmp_addr &= ~va_align.mask; + return va_align.mask; +} - return tmp_addr; +unsigned long align_vdso_addr(unsigned long addr) +{ + unsigned long align_mask = get_align_mask(); + return (addr + align_mask) & ~align_mask; } static int __init control_va_addr_alignment(char *str) @@ -126,7 +112,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long start_addr; + struct vm_unmapped_area_info info; unsigned long begin, end; if (flags & MAP_FIXED) @@ -144,50 +130,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, (!vma || addr + len <= vma->vm_start)) return addr; } - if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) - && len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = begin; - } - addr = mm->free_area_cache; - if (addr < begin) - addr = begin; - start_addr = addr; - -full_search: - - addr = align_addr(addr, filp, 0); - - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (end - len < addr) { - /* - * Start a new search - just in case we missed - * some holes. - */ - if (start_addr != begin) { - start_addr = addr = begin; - mm->cached_hole_size = 0; - goto full_search; - } - return -ENOMEM; - } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - mm->free_area_cache = addr + len; - return addr; - } - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - addr = align_addr(addr, filp, 0); - } + info.flags = 0; + info.length = len; + info.low_limit = begin; + info.high_limit = end; + info.align_mask = filp ? get_align_mask() : 0; + info.align_offset = pgoff << PAGE_SHIFT; + return vm_unmapped_area(&info); } - unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, @@ -195,7 +147,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - unsigned long addr = addr0, start_addr; + unsigned long addr = addr0; + struct vm_unmapped_area_info info; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -217,51 +170,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; } - /* check if free_area_cache is useful for us */ - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - -try_again: - /* either no address requested or can't fit in requested address hole */ - start_addr = addr = mm->free_area_cache; - - if (addr < len) - goto fail; - - addr -= len; - do { - addr = align_addr(addr, filp, ALIGN_TOPDOWN); - - /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: - */ - vma = find_vma(mm, addr); - if (!vma || addr+len <= vma->vm_start) - /* remember the address as a hint for next time */ - return mm->free_area_cache = addr; - - /* remember the largest hole we saw so far */ - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start-len; - } while (len < vma->vm_start); - -fail: - /* - * if hint left us with no space for the requested - * mapping then try again: - */ - if (start_addr != mm->mmap_base) { - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = 0; - goto try_again; - } + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + info.align_mask = filp ? get_align_mask() : 0; + info.align_offset = pgoff << PAGE_SHIFT; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + return addr; + VM_BUG_ON(addr != -ENOMEM); bottomup: /* @@ -270,14 +188,5 @@ bottomup: * can happen with large stack limits and large mmap() * allocations. */ - mm->cached_hole_size = ~0UL; - mm->free_area_cache = TASK_UNMAPPED_BASE; - addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); - /* - * Restore the topdown base: - */ - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; - - return addr; + return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); } diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 76ee97709a00..6e60b5fe2244 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -30,23 +30,110 @@ #include <linux/mmzone.h> #include <linux/init.h> #include <linux/smp.h> +#include <linux/irq.h> #include <asm/cpu.h> static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU + +#ifdef CONFIG_BOOTPARAM_HOTPLUG_CPU0 +static int cpu0_hotpluggable = 1; +#else +static int cpu0_hotpluggable; +static int __init enable_cpu0_hotplug(char *str) +{ + cpu0_hotpluggable = 1; + return 1; +} + +__setup("cpu0_hotplug", enable_cpu0_hotplug); +#endif + +#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 +/* + * This function offlines a CPU as early as possible and allows userspace to + * boot up without the CPU. The CPU can be onlined back by user after boot. + * + * This is only called for debugging CPU offline/online feature. + */ +int __ref _debug_hotplug_cpu(int cpu, int action) +{ + struct device *dev = get_cpu_device(cpu); + int ret; + + if (!cpu_is_hotpluggable(cpu)) + return -EINVAL; + + cpu_hotplug_driver_lock(); + + switch (action) { + case 0: + ret = cpu_down(cpu); + if (!ret) { + pr_info("CPU %u is now offline\n", cpu); + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); + } else + pr_debug("Can't offline CPU%d.\n", cpu); + break; + case 1: + ret = cpu_up(cpu); + if (!ret) + kobject_uevent(&dev->kobj, KOBJ_ONLINE); + else + pr_debug("Can't online CPU%d.\n", cpu); + break; + default: + ret = -EINVAL; + } + + cpu_hotplug_driver_unlock(); + + return ret; +} + +static int __init debug_hotplug_cpu(void) +{ + _debug_hotplug_cpu(0, 0); + return 0; +} + +late_initcall_sync(debug_hotplug_cpu); +#endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */ + int __ref arch_register_cpu(int num) { + struct cpuinfo_x86 *c = &cpu_data(num); + + /* + * Currently CPU0 is only hotpluggable on Intel platforms. Other + * vendors can add hotplug support later. + */ + if (c->x86_vendor != X86_VENDOR_INTEL) + cpu0_hotpluggable = 0; + /* - * CPU0 cannot be offlined due to several - * restrictions and assumptions in kernel. This basically - * doesn't add a control file, one cannot attempt to offline - * BSP. + * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate + * depends on BSP. PIC interrupts depend on BSP. * - * Also certain PCI quirks require not to enable hotplug control - * for all CPU's. + * If the BSP depencies are under control, one can tell kernel to + * enable BSP hotplug. This basically adds a control file and + * one can attempt to offline BSP. */ - if (num) + if (num == 0 && cpu0_hotpluggable) { + unsigned int irq; + /* + * We won't take down the boot processor on i386 if some + * interrupts only are able to be serviced by the BSP in PIC. + */ + for_each_active_irq(irq) { + if (!IO_APIC_IRQ(irq) && irq_has_action(irq)) { + cpu0_hotpluggable = 0; + break; + } + } + } + if (num || cpu0_hotpluggable) per_cpu(cpu_devices, num).cpu.hotpluggable = 1; return register_cpu(&per_cpu(cpu_devices, num).cpu, num); diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c new file mode 100644 index 000000000000..25b993729f9b --- /dev/null +++ b/arch/x86/kernel/trace_clock.c @@ -0,0 +1,21 @@ +/* + * X86 trace clocks + */ +#include <asm/trace_clock.h> +#include <asm/barrier.h> +#include <asm/msr.h> + +/* + * trace_clock_x86_tsc(): A clock that is just the cycle counter. + * + * Unlike the other clocks, this is not in nanoseconds. + */ +u64 notrace trace_clock_x86_tsc(void) +{ + u64 ret; + + rdtsc_barrier(); + rdtscll(ret); + + return ret; +} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b481341c9369..eb8586693e0b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -55,6 +55,7 @@ #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/mce.h> +#include <asm/context_tracking.h> #include <asm/mach_traps.h> @@ -107,30 +108,45 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) dec_preempt_count(); } -static void __kprobes -do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, - long error_code, siginfo_t *info) +static int __kprobes +do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, + struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - #ifdef CONFIG_X86_32 if (regs->flags & X86_VM_MASK) { /* - * traps 0, 1, 3, 4, and 5 should be forwarded to vm86. + * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86. * On nmi (interrupt 2), do_trap should not be called. */ - if (trapnr < X86_TRAP_UD) - goto vm86_trap; - goto trap_signal; + if (trapnr < X86_TRAP_UD) { + if (!handle_vm86_trap((struct kernel_vm86_regs *) regs, + error_code, trapnr)) + return 0; + } + return -1; } #endif + if (!user_mode(regs)) { + if (!fixup_exception(regs)) { + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = trapnr; + die(str, regs, error_code); + } + return 0; + } - if (!user_mode(regs)) - goto kernel_trap; + return -1; +} -#ifdef CONFIG_X86_32 -trap_signal: -#endif +static void __kprobes +do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, + long error_code, siginfo_t *info) +{ + struct task_struct *tsk = current; + + + if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) + return; /* * We want error_code and trap_nr set for userspace faults and * kernelspace faults which result in die(), but not @@ -158,33 +174,20 @@ trap_signal: force_sig_info(signr, info, tsk); else force_sig(signr, tsk); - return; - -kernel_trap: - if (!fixup_exception(regs)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = trapnr; - die(str, regs, error_code); - } - return; - -#ifdef CONFIG_X86_32 -vm86_trap: - if (handle_vm86_trap((struct kernel_vm86_regs *) regs, - error_code, trapnr)) - goto trap_signal; - return; -#endif } #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ + exception_exit(regs); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ @@ -195,11 +198,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ + exception_exit(regs); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -222,12 +229,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { + exception_enter(regs); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) == NOTIFY_STOP) - return; - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); + X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { + preempt_conditional_sti(regs); + do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); + preempt_conditional_cli(regs); + } + exception_exit(regs); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -235,6 +244,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; + exception_enter(regs); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -255,16 +265,29 @@ do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + exception_enter(regs); conditional_sti(regs); #ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) - goto gp_in_vm86; + if (regs->flags & X86_VM_MASK) { + local_irq_enable(); + handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + goto exit; + } #endif tsk = current; - if (!user_mode(regs)) - goto gp_in_kernel; + if (!user_mode(regs)) { + if (fixup_exception(regs)) + goto exit; + + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = X86_TRAP_GP; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) + die("general protection fault", regs, error_code); + goto exit; + } tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -279,25 +302,8 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig(SIGSEGV, tsk); - return; - -#ifdef CONFIG_X86_32 -gp_in_vm86: - local_irq_enable(); - handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - return; -#endif - -gp_in_kernel: - if (fixup_exception(regs)) - return; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (notify_die(DIE_GPF, "general protection fault", regs, error_code, - X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); +exit: + exception_exit(regs); } /* May run on IST stack. */ @@ -312,15 +318,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + exception_enter(regs); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -331,6 +338,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); debug_stack_usage_dec(); +exit: + exception_exit(regs); } #ifdef CONFIG_X86_64 @@ -391,6 +400,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; + exception_enter(regs); + get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -406,7 +417,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Catch kmemcheck conditions first of all! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) - return; + goto exit; /* DR6 may or may not be cleared by the CPU */ set_debugreg(0, 6); @@ -421,7 +432,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -437,7 +448,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) X86_TRAP_DB); preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; + goto exit; } /* @@ -458,7 +469,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; +exit: + exception_exit(regs); } /* @@ -555,14 +567,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 ignore_fpu_irq = 1; #endif - + exception_enter(regs); math_error(regs, error_code, X86_TRAP_MF); + exception_exit(regs); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { + exception_enter(regs); math_error(regs, error_code, X86_TRAP_XF); + exception_exit(regs); } dotraplinkage void @@ -613,11 +628,12 @@ void math_state_restore(void) } __thread_fpu_begin(tsk); + /* * Paranoid restore. send a SIGSEGV if we fail to restore the state. */ if (unlikely(restore_fpu_checking(tsk))) { - __thread_fpu_end(tsk); + drop_init_fpu(tsk); force_sig(SIGSEGV, tsk); return; } @@ -629,6 +645,9 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { + exception_enter(regs); + BUG_ON(use_eager_fpu()); + #ifdef CONFIG_MATH_EMULATION if (read_cr0() & X86_CR0_EM) { struct math_emu_info info = { }; @@ -637,6 +656,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + exception_exit(regs); return; } #endif @@ -644,12 +664,15 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif + exception_exit(regs); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + + exception_enter(regs); local_irq_enable(); info.si_signo = SIGILL; @@ -657,10 +680,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) info.si_code = ILL_BADSTK; info.si_addr = NULL; if (notify_die(DIE_TRAP, "iret exception", regs, error_code, - X86_TRAP_IRET, SIGILL) == NOTIFY_STOP) - return; - do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, - &info); + X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + &info); + } + exception_exit(regs); } #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cfa5d4f7ca56..06ccb5073a3f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -77,6 +77,12 @@ unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); #endif +unsigned long long native_read_tsc(void) +{ + return __native_read_tsc(); +} +EXPORT_SYMBOL(native_read_tsc); + int check_tsc_unstable(void) { return tsc_unstable; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 36fd42091fa7..c71025b67462 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -41,6 +41,9 @@ /* Adjust the return address of a call insn */ #define UPROBE_FIX_CALL 0x2 +/* Instruction will modify TF, don't change it */ +#define UPROBE_FIX_SETF 0x4 + #define UPROBE_FIX_RIP_AX 0x8000 #define UPROBE_FIX_RIP_CX 0x4000 @@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) insn_get_opcode(insn); /* should be a nop */ switch (OPCODE1(insn)) { + case 0x9d: + /* popf */ + auprobe->fixups |= UPROBE_FIX_SETF; + break; case 0xc3: /* ret/lret */ case 0xcb: case 0xc2: @@ -471,6 +478,11 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) regs->ip = current->utask->xol_vaddr; pre_xol_rip_insn(auprobe, regs, autask); + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) + set_task_blockstep(current, false); + return 0; } @@ -596,6 +608,16 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) if (auprobe->fixups & UPROBE_FIX_CALL) result = adjust_ret_addr(regs->sp, correction); + /* + * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP + * so we can get an extra SIGTRAP if we do not clear TF. We need + * to examine the opcode to make it right. + */ + if (utask->autask.saved_tf) + send_sig(SIGTRAP, current, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + return result; } @@ -640,36 +662,36 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) current->thread.trap_nr = utask->autask.saved_trap_nr; handle_riprel_post_xol(auprobe, regs, NULL); instruction_pointer_set(regs, utask->vaddr); + + /* clear TF if it was set by us in arch_uprobe_pre_xol() */ + if (!utask->autask.saved_tf) + regs->flags &= ~X86_EFLAGS_TF; } /* * Skip these instructions as per the currently known x86 ISA. - * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 } + * rep=0x66*; nop=0x90 */ -bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { int i; for (i = 0; i < MAX_UINSN_BYTES; i++) { - if ((auprobe->insn[i] == 0x66)) + if (auprobe->insn[i] == 0x66) continue; if (auprobe->insn[i] == 0x90) return true; - if (i == (MAX_UINSN_BYTES - 1)) - break; - - if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x1f)) - return true; - - if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x19)) - return true; - - if ((auprobe->insn[i] == 0x87) && (auprobe->insn[i+1] == 0xc0)) - return true; - break; } return false; } + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + bool ret = __skip_sstep(auprobe, regs); + if (ret && (regs->flags & X86_EFLAGS_TF)) + send_sig(SIGTRAP, current, 0); + return ret; +} diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 54abcc0baf23..1dfe69cc78a8 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd(mm, pmd); + split_huge_page_pmd_mm(mm, 0xA0000, pmd); if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); @@ -561,9 +561,9 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) if ((trapno == 3) || (trapno == 1)) { KVM86->regs32->ax = VM86_TRAP + (trapno << 8); /* setting this flag forces the code in entry_32.S to - call save_v86_state() and change the stack pointer - to KVM86->regs32 */ - set_thread_flag(TIF_IRET); + the path where we call save_v86_state() and change + the stack pointer to KVM86->regs32 */ + set_thread_flag(TIF_NOTIFY_RESUME); return 0; } do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs)); diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8d141b309046..3a3e8c9e280d 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -28,7 +28,7 @@ #include <linux/jiffies.h> #include <linux/sysctl.h> #include <linux/topology.h> -#include <linux/clocksource.h> +#include <linux/timekeeper_internal.h> #include <linux/getcpu.h> #include <linux/cpu.h> #include <linux/smp.h> @@ -82,32 +82,41 @@ void update_vsyscall_tz(void) vsyscall_gtod_data.sys_tz = sys_tz; } -void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) +void update_vsyscall(struct timekeeper *tk) { - struct timespec monotonic; + struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; - write_seqcount_begin(&vsyscall_gtod_data.seq); + write_seqcount_begin(&vdata->seq); /* copy vsyscall data */ - 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; + vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->clock->cycle_last; + vdata->clock.mask = tk->clock->mask; + vdata->clock.mult = tk->mult; + vdata->clock.shift = tk->shift; + + vdata->wall_time_sec = tk->xtime_sec; + vdata->wall_time_snsec = tk->xtime_nsec; + + vdata->monotonic_time_sec = tk->xtime_sec + + tk->wall_to_monotonic.tv_sec; + vdata->monotonic_time_snsec = tk->xtime_nsec + + (tk->wall_to_monotonic.tv_nsec + << tk->shift); + while (vdata->monotonic_time_snsec >= + (((u64)NSEC_PER_SEC) << tk->shift)) { + vdata->monotonic_time_snsec -= + ((u64)NSEC_PER_SEC) << tk->shift; + vdata->monotonic_time_sec++; + } - monotonic = timespec_add(*wall_time, *wtm); - vsyscall_gtod_data.monotonic_time_sec = monotonic.tv_sec; - vsyscall_gtod_data.monotonic_time_nsec = monotonic.tv_nsec; + vdata->wall_time_coarse.tv_sec = tk->xtime_sec; + vdata->wall_time_coarse.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); - vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); - vsyscall_gtod_data.monotonic_time_coarse = - timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm); + vdata->monotonic_time_coarse = timespec_add(vdata->wall_time_coarse, + tk->wall_to_monotonic); - write_seqcount_end(&vsyscall_gtod_data.seq); + write_seqcount_end(&vdata->seq); } static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 6020f6f5927c..1330dd102950 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -13,9 +13,13 @@ #include <asm/ftrace.h> #ifdef CONFIG_FUNCTION_TRACER -/* mcount is defined in assembly */ +/* mcount and __fentry__ are defined in assembly */ +#ifdef CC_USING_FENTRY +EXPORT_SYMBOL(__fentry__); +#else EXPORT_SYMBOL(mcount); #endif +#endif EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 9f3167e891ef..7a3d075a814a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -26,7 +26,6 @@ void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } -void __init x86_init_pgd_noop(pgd_t *unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } @@ -68,8 +67,7 @@ struct x86_init_ops x86_init __initdata = { }, .paging = { - .pagetable_setup_start = native_pagetable_setup_start, - .pagetable_setup_done = native_pagetable_setup_done, + .pagetable_init = native_pagetable_init, }, .timers = { diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 3d3e20709119..ada87a329edc 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -10,9 +10,7 @@ #include <linux/compat.h> #include <asm/i387.h> #include <asm/fpu-internal.h> -#ifdef CONFIG_IA32_EMULATION -#include <asm/sigcontext32.h> -#endif +#include <asm/sigframe.h> #include <asm/xcr.h> /* @@ -23,13 +21,9 @@ u64 pcntxt_mask; /* * Represents init state for the supported extended state. */ -static struct xsave_struct *init_xstate_buf; - -struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -struct _fpx_sw_bytes fx_sw_reserved_ia32; -#endif +struct xsave_struct *init_xstate_buf; +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; /* @@ -44,9 +38,9 @@ static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; */ void __sanitize_i387_state(struct task_struct *tsk) { - u64 xstate_bv; - int feature_bit = 0x2; struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; + int feature_bit = 0x2; + u64 xstate_bv; if (!fx) return; @@ -104,213 +98,326 @@ void __sanitize_i387_state(struct task_struct *tsk) * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. */ -int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw_user) +static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) { int min_xstate_size = sizeof(struct i387_fxsave_struct) + sizeof(struct xsave_hdr_struct); unsigned int magic2; - int err; - err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0], - sizeof(struct _fpx_sw_bytes)); - if (err) - return -EFAULT; + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; - /* - * First Magic check failed. - */ - if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1) - return -EINVAL; + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; /* - * Check for error scenarios. - */ - if (fx_sw_user->xstate_size < min_xstate_size || - fx_sw_user->xstate_size > xstate_size || - fx_sw_user->xstate_size > fx_sw_user->extended_size) - return -EINVAL; - - err = __get_user(magic2, (__u32 *) (((void *)fpstate) + - fx_sw_user->extended_size - - FP_XSTATE_MAGIC2_SIZE)); - if (err) - return err; - /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ - if (magic2 != FP_XSTATE_MAGIC2) - return -EFAULT; + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; return 0; } -#ifdef CONFIG_X86_64 /* * Signal frame handlers. */ - -int save_i387_xstate(void __user *buf) +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) { - struct task_struct *tsk = current; - int err = 0; - - if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size)) - return -EACCES; + if (use_fxsr()) { + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct user_i387_ia32_struct env; + struct _fpstate_ia32 __user *fp = buf; - BUG_ON(sig_xstate_size < xstate_size); + convert_from_fxsr(&env, tsk); - if ((unsigned long)buf % 64) - pr_err("%s: bad fpstate %p\n", __func__, buf); - - if (!used_math()) - return 0; - - if (user_has_fpu()) { - if (use_xsave()) - err = xsave_user(buf); - else - err = fxsave_user(buf); - - if (err) - return err; - user_fpu_end(); + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, - xstate_size)) + struct i387_fsave_struct __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) return -1; } - clear_used_math(); /* trigger finit */ + return 0; +} - if (use_xsave()) { - struct _fpstate __user *fx = buf; - struct _xstate __user *x = buf; - u64 xstate_bv; +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xsave_struct __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xstate_bv; + int err; - err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved, - sizeof(struct _fpx_sw_bytes)); + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *) (buf + sig_xstate_size - - FP_XSTATE_MAGIC2_SIZE)); + if (!use_xsave()) + return err; - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers and - * set the FP/SSE bits. - */ - err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv); + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; + /* + * Read the xstate_bv which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv); + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xstate_bv in the xsave header. + * + * xsave aware apps can change the xstate_bv in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xstate_bv |= XSTATE_FPSSE; - if (err) - return err; - } + err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - return 1; + return err; +} + +static inline int save_user_xstate(struct xsave_struct __user *buf) +{ + int err; + + if (use_xsave()) + err = xsave_user(buf); + else if (use_fxsr()) + err = fxsave_user((struct i387_fxsave_struct __user *) buf); + else + err = fsave_user((struct i387_fsave_struct __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; } /* - * Restore the extended state if present. Otherwise, restore the FP/SSE - * state. + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. */ -static int restore_user_xstate(void __user *buf) +int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) { - struct _fpx_sw_bytes fx_sw_user; - u64 mask; - int err; + struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); - if (((unsigned long)buf % 64) || - check_for_xstate(buf, buf, &fx_sw_user)) - goto fx_only; + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); - mask = fx_sw_user.xstate_bv; + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; - /* - * restore the state passed by the user. - */ - err = xrestore_user(buf, mask); - if (err) - return err; + if (!HAVE_HWFP) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - /* - * init the state skipped by the user. - */ - mask = pcntxt_mask & ~mask; - if (unlikely(mask)) - xrstor_state(init_xstate_buf, mask); + if (user_has_fpu()) { + /* Save the live register state to the user directly. */ + if (save_user_xstate(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + fpu_fxsave(&tsk->thread.fpu); + } else { + sanitize_i387_state(tsk); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + drop_init_fpu(tsk); /* trigger finit */ return 0; +} -fx_only: - /* - * couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE); - return fxrstor_checking((__force struct i387_fxsave_struct *)buf); +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xstate_bv, int fx_only) +{ + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; + + if (use_xsave()) { + /* These bits must be zero. */ + xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + xsave_hdr->xstate_bv = XSTATE_FPSSE; + else + xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } } /* - * This restores directly out of user space. Exceptions are handled. + * Restore the extended state if present. Otherwise, restore the FP/SSE state. */ -int restore_i387_xstate(void __user *buf) +static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) { + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; + xrstor_state(init_xstate_buf, init_bv); + return fxrstor_user(buf); + } else { + u64 init_bv = pcntxt_mask & ~xbv; + if (unlikely(init_bv)) + xrstor_state(init_xstate_buf, init_bv); + return xrestore_user(buf, xbv); + } + } else if (use_fxsr()) { + return fxrstor_user(buf); + } else + return frstor_user(buf); +} + +int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); struct task_struct *tsk = current; - int err = 0; + int state_size = xstate_size; + u64 xstate_bv = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); if (!buf) { - if (used_math()) - goto clear; + drop_init_fpu(tsk); return 0; - } else - if (!access_ok(VERIFY_READ, buf, sig_xstate_size)) - return -EACCES; + } - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + if (!used_math() && init_fpu(tsk)) + return -1; + + if (!HAVE_HWFP) { + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; } - user_fpu_begin(); - if (use_xsave()) - err = restore_user_xstate(buf); - else - err = fxrstor_checking((__force struct i387_fxsave_struct *) - buf); - if (unlikely(err)) { + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct i387_fxsave_struct); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xstate_bv = fx_sw_user.xstate_bv; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears used_math(). This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * set_used_math() is again set. + */ + drop_fpu(tsk); + + if (__copy_from_user(xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); + set_used_math(); + } + + if (use_eager_fpu()) + math_state_restore(); + + return err; + } else { /* - * Encountered an error while doing the restore from the - * user buffer, clear the fpu state. + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). */ -clear: - clear_fpu(tsk); - clear_used_math(); + user_fpu_begin(); + if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { + drop_init_fpu(tsk); + return -1; + } } - return err; + + return 0; } -#endif /* * Prepare the SW reserved portion of the fxsave memory layout, indicating @@ -321,31 +428,22 @@ clear: */ static void prepare_fx_sw_frame(void) { - int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) + - FP_XSTATE_MAGIC2_SIZE; + int fsave_header_size = sizeof(struct i387_fsave_struct); + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - sig_xstate_size = sizeof(struct _fpstate) + size_extended; - -#ifdef CONFIG_IA32_EMULATION - sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended; -#endif - - memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved)); + if (config_enabled(CONFIG_X86_32)) + size += fsave_header_size; fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = sig_xstate_size; + fx_sw_reserved.extended_size = size; fx_sw_reserved.xstate_bv = pcntxt_mask; fx_sw_reserved.xstate_size = xstate_size; -#ifdef CONFIG_IA32_EMULATION - memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved, - sizeof(struct _fpx_sw_bytes)); - fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size; -#endif -} -#ifdef CONFIG_X86_64 -unsigned int sig_xstate_size = sizeof(struct _fpstate); -#endif + if (config_enabled(CONFIG_IA32_EMULATION)) { + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size += fsave_header_size; + } +} /* * Enable the extended processor state save/restore feature @@ -384,19 +482,21 @@ static void __init setup_xstate_features(void) /* * setup the xstate image representing the init state */ -static void __init setup_xstate_init(void) +static void __init setup_init_fpu_buf(void) { - setup_xstate_features(); - /* * Setup init_xstate_buf to represent the init state of * all the features managed by the xsave */ init_xstate_buf = alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); - init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; + fx_finit(&init_xstate_buf->i387); + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); - clts(); /* * Init all the features state with header_bv being 0x0 */ @@ -406,9 +506,21 @@ static void __init setup_xstate_init(void) * of any feature which is not represented by all zero's. */ xsave_state(init_xstate_buf, -1); - stts(); } +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + /* * Enable and initialize the xsave feature. */ @@ -445,8 +557,11 @@ static void __init xstate_enable_boot_cpu(void) update_regset_xstate_info(xstate_size, pcntxt_mask); prepare_fx_sw_frame(); + setup_init_fpu_buf(); - setup_xstate_init(); + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", pcntxt_mask, xstate_size); @@ -471,3 +586,43 @@ void __cpuinit xsave_init(void) next_func = xstate_enable; this_func(); } + +static inline void __init eager_fpu_init_bp(void) +{ + current->thread.fpu.state = + alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); + if (!init_xstate_buf) + setup_init_fpu_buf(); +} + +void __cpuinit eager_fpu_init(void) +{ + static __refdata void (*boot_func)(void) = eager_fpu_init_bp; + + clear_used_math(); + current_thread_info()->status = 0; + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + if (!cpu_has_eager_fpu) { + stts(); + return; + } + + if (boot_func) { + boot_func(); + boot_func = NULL; + } + + /* + * This is same as math_state_restore(). But use_xsave() is + * not yet patched to use math_state_restore(). + */ + init_fpu(current); + __thread_fpu_begin(current); + if (cpu_has_xsave) + xrstor_state(init_xstate_buf, -1); + else + fxrstor_checking(&init_xstate_buf->i387); +} |
