diff options
| author | H. Peter Anvin <hpa@linux.intel.com> | 2012-10-19 14:54:24 (GMT) |
|---|---|---|
| committer | H. Peter Anvin <hpa@linux.intel.com> | 2012-10-19 14:55:09 (GMT) |
| commit | 4533d86270d7986e00594495dde9a109d6be27ae (patch) | |
| tree | c2473cac653f7b98e5bd5e6475e63734be4b7644 /arch/x86/kernel | |
| parent | 21c5e50e15b1abd797e62f18fd7f90b9cc004cbd (diff) | |
| parent | 5bc66170dc486556a1e36fd384463536573f4b82 (diff) | |
| download | linux-fsl-qoriq-4533d86270d7986e00594495dde9a109d6be27ae.tar.xz | |
Merge commit '5bc66170dc486556a1e36fd384463536573f4b82' into x86/urgent
From Borislav Petkov <bp@amd64.org>:
Below is a RAS fix which reverts the addition of a sysfs attribute
which we agreed is not needed, post-factum. And this should go in now
because that sysfs attribute is going to end up in 3.7 otherwise and
thus exposed to userspace; removing it then would be a lot harder.
This is done as a merge rather than a simple patch/cherry-pick since
the baseline for this patch was not in the previous x86/urgent.
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'arch/x86/kernel')
56 files changed, 1827 insertions, 739 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e56..91ce48f 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -23,7 +23,7 @@ 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 @@ -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 b2297e5..e651f7a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -656,7 +656,7 @@ 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/alternative.c b/arch/x86/kernel/alternative.c index ced4534..ef5ccca 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 24deb30..b17416e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1934,7 +1934,7 @@ 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 bc552cf..a65829a 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -30,7 +30,7 @@ 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) { @@ -199,7 +199,7 @@ 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/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 68de2dc..2861082 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 d30a6a9..a0e067d 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 9d92e19..f7e98a2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -737,6 +737,72 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, } #endif +static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) +{ + if (!cpu_has_invlpg) + return; + + 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 +822,7 @@ 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/common.c b/arch/x86/kernel/cpu/common.c index fefd9b7..7505f7b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -489,7 +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], @@ -955,8 +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) @@ -1036,14 +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); } @@ -1130,8 +1131,6 @@ void syscall_init(void) 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. @@ -1312,8 +1311,6 @@ void __cpuinit cpu_init(void) fpu_init(); - raw_local_save_flags(kernel_eflags); - if (is_uv_system()) uv_cpu_init(); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0a4ce29..198e019 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -648,6 +648,10 @@ 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/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index fc4beb3..ddc72f8 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 ed44c8a..6a05c1d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -28,6 +28,18 @@ 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.c b/arch/x86/kernel/cpu/mcheck/mce.c index 292d025..46cbf86 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -83,6 +83,7 @@ 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; +int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; @@ -1266,6 +1267,14 @@ 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 +1285,7 @@ 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 +1293,38 @@ 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 */ @@ -1585,6 +1619,7 @@ 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 +1629,28 @@ 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 (mce_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) { @@ -1907,6 +1947,7 @@ 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) { @@ -1926,6 +1967,8 @@ static int __init mcheck_enable(char *str) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) mce_bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { get_option(&str, &tolerant); if (*str == ',') { @@ -2294,38 +2337,33 @@ 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; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 38e49bc..5f88abf 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. @@ -30,7 +32,22 @@ 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) { @@ -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 (!mce_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 (mce_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 (mce_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"); + } } /* @@ -156,7 +278,7 @@ 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)); } @@ -186,7 +308,7 @@ void cmci_rediscover(int dying) continue; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } set_cpus_allowed_ptr(current, old); @@ -200,7 +322,7 @@ 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 +333,7 @@ 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 c7b3fe2..091972e 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/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 6605a81..271d257 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[]; extern struct event_constraint intel_snb_pebs_event_constraints[]; +extern struct event_constraint intel_ivb_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); @@ -624,6 +626,8 @@ 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_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 7bfb5be..6336bcb 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 { @@ -209,6 +214,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config) return -EOPNOTSUPP; } +static const struct perf_event_attr ibs_notsupp = { + .exclude_user = 1, + .exclude_kernel = 1, + .exclude_hv = 1, + .exclude_idle = 1, + .exclude_host = 1, + .exclude_guest = 1, +}; + static int perf_ibs_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -229,6 +243,9 @@ static int perf_ibs_init(struct perf_event *event) if (event->pmu != &perf_ibs->pmu) return -ENOENT; + if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp)) + return -EINVAL; + if (config & ~perf_ibs->config_mask) return -EINVAL; @@ -434,6 +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, @@ -453,6 +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, }; @@ -476,6 +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, }; @@ -585,6 +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; @@ -596,13 +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 7f2739e..324bb52 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1906,6 +1906,8 @@ __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(); } @@ -2008,6 +2010,7 @@ __init int intel_pmu_init(void) break; case 28: /* Atom */ + case 54: /* Cedariew */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2047,7 +2050,6 @@ __init int intel_pmu_init(void) case 42: /* SandyBridge */ case 45: /* SandyBridge, "Romely-EP" */ x86_add_quirk(intel_sandybridge_quirk); - case 58: /* IvyBridge */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, @@ -2072,6 +2074,29 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; + case 58: /* IvyBridge */ + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.extra_regs = intel_snb_extra_regs; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); + + pr_cont("IvyBridge events, "); + break; + default: switch (x86_pmu.version) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index e38d97b..826054a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_ivb_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 520b426..da02e9c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void) * to have an operational LBR which can freeze * on PMU interrupt */ - if (boot_cpu_data.x86_mask < 10) { + if (boot_cpu_data.x86_model == 28 + && boot_cpu_data.x86_mask < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 0a55710..99d96a4 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + static struct attribute *snb_uncore_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = { .constraints = snb_uncore_cbox_constraints, .ops = &snb_uncore_msr_ops, .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, }; static struct intel_uncore_type *snb_msr_uncores[] = { @@ -1944,7 +1950,7 @@ 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) @@ -2341,6 +2347,27 @@ 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; @@ -2378,8 +2405,8 @@ 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) @@ -2431,9 +2458,10 @@ 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: diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 5b81c18..e68a455 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 0000000..7c46bfd --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -0,0 +1,248 @@ +/* Driver for Intel Xeon Phi "Knights Corner" PMU */ + +#include <linux/perf_event.h> +#include <linux/types.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 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; + + (void)wrmsrl_safe(hwc->config_base + hwc->idx, val); +} + +static void knc_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; + + (void)wrmsrl_safe(hwc->config_base + hwc->idx, val); +} + +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 = x86_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 << 31) - 1, + .version = 0, + .num_counters = 2, + /* in theory 40 bits, early silicon is buggy though */ + .cntval_bits = 32, + .cntval_mask = (1ULL << 32) - 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/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 966512b..2e8caf0 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 8022c66..fbd8955 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 39472dd..60c7891 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/devicetree.c b/arch/x86/kernel/devicetree.c index 3ae2ced..b158152 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/entry_32.S b/arch/x86/kernel/entry_32.S index 9ebbeca..a1193ae 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -299,6 +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 */ @@ -323,8 +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 @@ -616,6 +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 @@ -626,24 +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 @@ -732,7 +741,6 @@ ENDPROC(ptregs_##name) PTREGSCALL1(iopl) PTREGSCALL0(fork) PTREGSCALL0(vfork) -PTREGSCALL3(execve) PTREGSCALL2(sigaltstack) PTREGSCALL0(sigreturn) PTREGSCALL0(rt_sigreturn) @@ -1015,16 +1023,6 @@ 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. */ @@ -1130,17 +1128,21 @@ 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: @@ -1152,6 +1154,71 @@ 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) @@ -1192,9 +1259,6 @@ 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 diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index ce87e3d..0c58952 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,6 +56,7 @@ #include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> +#include <asm/rcu.h> #include <asm/smap.h> #include <linux/err.h> @@ -69,25 +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) @@ -98,8 +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 @@ -120,8 +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 @@ -129,20 +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 @@ -343,15 +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 @@ -385,7 +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 @@ -441,7 +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 @@ -451,7 +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 @@ -459,6 +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) @@ -567,7 +678,7 @@ sysret_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi jmp sysret_check @@ -680,7 +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 @@ -759,7 +870,6 @@ 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) @@ -809,8 +919,7 @@ 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 @@ -977,7 +1086,7 @@ 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) @@ -1215,52 +1324,6 @@ 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 @@ -1458,7 +1521,7 @@ 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 diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c3a7cb4..1d41402 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/i8259.c b/arch/x86/kernel/i8259.c index 36d1853..9a5c460 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 d44f782..e4595f1 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 3f61904..836f832 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 e2f751e..57916c0 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 c1d61ee..b3e5e51 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -354,6 +354,7 @@ 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 +397,7 @@ 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(); } diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 82746f9..7720ff5 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -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); @@ -118,95 +211,37 @@ 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 +273,7 @@ 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 +285,113 @@ 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 +402,7 @@ 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 +410,17 @@ 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 +436,17 @@ 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 +480,10 @@ 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 4873e62..3a04b22 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, if (do_microcode_update(buf, len) == 0) ret = (ssize_t)len; + if (ret > 0) + perf_check_microcode(); + mutex_unlock(µcode_mutex); put_online_cpus(); @@ -276,19 +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; } @@ -370,18 +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; @@ -392,7 +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); @@ -405,14 +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) @@ -428,7 +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; @@ -477,34 +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 0327e2b..3544aed 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 eb11369..a7c5661 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 0000000..e309cc5 --- /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/process.c b/arch/x86/kernel/process.c index dc3567e..b644e1c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -293,71 +293,6 @@ sys_clone(unsigned long clone_flags, unsigned long newsp, } /* - * 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 */ unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index b9ff83c..44e0bff 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. @@ -127,23 +128,39 @@ void release_thread(struct task_struct *dead_task) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long unused, + unsigned long arg, struct task_struct *p, struct pt_regs *regs) { - struct pt_regs *childregs; + struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; int err; - childregs = task_pt_regs(p); + p->thread.sp = (unsigned long) childregs; + p->thread.sp0 = (unsigned long) (childregs+1); + + if (unlikely(!regs)) { + /* 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 = *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; - task_user_gs(p) = get_user_gs(regs); p->fpu_counter = 0; @@ -190,6 +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; + /* + * force it to the iret return path by making it look as if there was + * some work pending. + */ + 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 8a6d20c..16c6365 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -146,29 +146,18 @@ 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, + unsigned long arg, struct task_struct *p, struct pt_regs *regs) { 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 +167,24 @@ 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(!regs)) { + /* 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 = *regs; + + childregs->ax = 0; + childregs->sp = sp; err = -ENOMEM; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 861a9d1..b00b33a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include <linux/signal.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -1460,6 +1461,8 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + rcu_user_exit(); + /* * If we stepped into a sysenter/syscall insn, it trapped in * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. @@ -1523,4 +1526,6 @@ 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); + + rcu_user_enter(); } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index af6db6e..4929c1b 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -225,7 +225,7 @@ 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 198e774..468e98d 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> @@ -970,13 +971,11 @@ 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 */ @@ -1047,6 +1046,8 @@ void __init setup_arch(char **cmdline_p) mcheck_init(); arch_init_ideal_nops(); + + register_refined_jiffies(CLOCK_TICK_RATE); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 036bddb..29ad351 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -816,6 +816,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { + rcu_user_exit(); + #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ if (thread_info_flags & _TIF_MCE_NOTIFY) @@ -838,9 +840,7 @@ 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 */ + rcu_user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c5a8c3..c80a33b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -665,7 +665,8 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long boot_error = 0; int timeout; - 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); @@ -1053,20 +1054,6 @@ 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(); @@ -1256,9 +1243,6 @@ 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); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index c346d11..cd3b243 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 0b0cb5f..0000000 --- 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/traps.c b/arch/x86/kernel/traps.c index 4f4aba0..8276dc6 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/rcu.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 @@ -630,6 +645,7 @@ 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 @@ -640,6 +656,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + exception_exit(regs); return; } #endif @@ -647,12 +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; @@ -660,10 +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/uprobes.c b/arch/x86/kernel/uprobes.c index 36fd420..9538f00 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: @@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) * Skip these instructions as per the currently known x86 ISA. * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 } */ -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; @@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) } 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; +} + +void arch_uprobe_enable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + struct pt_regs *regs = task_pt_regs(task); + + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) + set_task_blockstep(task, false); +} + +void arch_uprobe_disable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED); + struct pt_regs *regs = task_pt_regs(task); + /* + * The state of TIF_BLOCKSTEP was not saved so we can get an extra + * SIGTRAP if we do not clear TF. We need to examine the opcode to + * make it right. + */ + if (unlikely(trapped)) { + if (!autask->saved_tf) + regs->flags &= ~X86_EFLAGS_TF; + } else { + if (autask->saved_tf) + send_sig(SIGTRAP, task, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + } +} diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 54abcc0..5c9687b 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -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 8d141b3..3a3e8c9 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 6020f6f..1330dd1 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 9f3167e..7a3d075 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 = { |