diff options
author | Scott Wood <scottwood@freescale.com> | 2015-02-13 22:12:06 (GMT) |
---|---|---|
committer | Scott Wood <scottwood@freescale.com> | 2015-02-13 22:19:22 (GMT) |
commit | 6faa2909871d8937cb2f79a10e1b21ffe193fac1 (patch) | |
tree | f558a94f1553814cc122ab8d9e04c0ebad5262a5 /arch/x86/kernel | |
parent | fcb2fb84301c673ee15ca04e7a2fc965712d49a0 (diff) | |
download | linux-fsl-qoriq-6faa2909871d8937cb2f79a10e1b21ffe193fac1.tar.xz |
Reset to 3.12.37
Diffstat (limited to 'arch/x86/kernel')
38 files changed, 761 insertions, 311 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a5408b9..32f1140 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a7eb82d..7170f17 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1282,7 +1282,7 @@ void setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1379,7 +1379,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5816e6a..e63a5bd 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2396,8 +2396,7 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) { /* If we are moving the irq we need to mask it */ - if (unlikely(irqd_is_setaffinity_pending(data) && - !irqd_irq_inprogress(data))) { + if (unlikely(irqd_is_setaffinity_pending(data))) { mask_ioapic(cfg); return true; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index a36d9cf..2861082 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -33,7 +33,6 @@ void common(void) { OFFSET(TI_status, thread_info, status); OFFSET(TI_addr_limit, thread_info, addr_limit); OFFSET(TI_preempt_count, thread_info, preempt_count); - OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count); BLANK(); OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 28233b9..ee51e67 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -509,6 +509,13 @@ static void early_init_amd(struct cpuinfo_x86 *c) } #endif + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + /* F16h erratum 793, CVE-2013-6885 */ if (c->x86 == 0x16 && c->x86_model <= 0xf) { u64 val; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3533e2c..00cc6f7 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { + if (strlen(s)) + return 0; setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); setup_clear_cpu_cap(X86_FEATURE_AVX); @@ -1135,7 +1137,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 87c0be5..f4a9985 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -154,6 +154,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -369,6 +384,13 @@ static void init_intel(struct cpuinfo_x86 *c) detect_extended_topology(c); l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -483,6 +505,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -688,7 +717,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .vendor = X86_VENDOR_INTEL, .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3a7ab0b..b3218cd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -18,7 +18,6 @@ #include <linux/rcupdate.h> #include <linux/kobject.h> #include <linux/uaccess.h> -#include <linux/kthread.h> #include <linux/kdebug.h> #include <linux/kernel.h> #include <linux/percpu.h> @@ -42,7 +41,6 @@ #include <linux/debugfs.h> #include <linux/irq_work.h> #include <linux/export.h> -#include <linux/jiffies.h> #include <asm/processor.h> #include <asm/mce.h> @@ -1270,7 +1268,7 @@ void mce_log_therm_throt_event(__u64 status) 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 hrtimer, mce_timer); +static DEFINE_PER_CPU(struct timer_list, mce_timer); static unsigned long mce_adjust_timer_default(unsigned long interval) { @@ -1280,10 +1278,13 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) +static void mce_timer_fn(unsigned long data) { + struct timer_list *t = &__get_cpu_var(mce_timer); unsigned long iv; + WARN_ON(smp_processor_id() != data); + if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_poll_banks)); @@ -1304,11 +1305,9 @@ static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) __this_cpu_write(mce_next_interval, iv); /* Might have become 0 after CMCI storm subsided */ if (iv) { - hrtimer_forward_now(timer, ns_to_ktime( - jiffies_to_usecs(iv) * 1000ULL)); - return HRTIMER_RESTART; + t->expires = jiffies + iv; + add_timer_on(t, smp_processor_id()); } - return HRTIMER_NORESTART; } /* @@ -1316,37 +1315,28 @@ static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) */ void mce_timer_kick(unsigned long interval) { - struct hrtimer *t = &__get_cpu_var(mce_timer); + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned long when = jiffies + interval; unsigned long iv = __this_cpu_read(mce_next_interval); - if (hrtimer_active(t)) { - s64 exp; - s64 intv_us; - - intv_us = jiffies_to_usecs(interval); - exp = ktime_to_us(hrtimer_expires_remaining(t)); - if (intv_us < exp) { - hrtimer_cancel(t); - hrtimer_start_range_ns(t, - ns_to_ktime(intv_us * 1000), - 0, HRTIMER_MODE_REL_PINNED); - } + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); } else { - hrtimer_start_range_ns(t, - ns_to_ktime(jiffies_to_usecs(interval) * 1000ULL), - 0, HRTIMER_MODE_REL_PINNED); + 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 hrtimer_cancel() can deadlock */ +/* Must not be called in IRQ context where del_timer_sync() can deadlock */ static void mce_timer_delete_all(void) { int cpu; for_each_online_cpu(cpu) - hrtimer_cancel(&per_cpu(mce_timer, cpu)); + del_timer_sync(&per_cpu(mce_timer, cpu)); } static void mce_do_trigger(struct work_struct *work) @@ -1356,63 +1346,6 @@ static void mce_do_trigger(struct work_struct *work) static DECLARE_WORK(mce_trigger_work, mce_do_trigger); -static void __mce_notify_work(void) -{ - /* Not more than two messages every minute */ - static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); - - /* wake processes polling /dev/mcelog */ - wake_up_interruptible(&mce_chrdev_wait); - - /* - * There is no risk of missing notifications because - * work_pending is always cleared before the function is - * executed. - */ - if (mce_helper[0] && !work_pending(&mce_trigger_work)) - schedule_work(&mce_trigger_work); - - if (__ratelimit(&ratelimit)) - pr_info(HW_ERR "Machine check events logged\n"); -} - -#ifdef CONFIG_PREEMPT_RT_FULL -struct task_struct *mce_notify_helper; - -static int mce_notify_helper_thread(void *unused) -{ - while (1) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - if (kthread_should_stop()) - break; - __mce_notify_work(); - } - return 0; -} - -static int mce_notify_work_init(void) -{ - mce_notify_helper = kthread_run(mce_notify_helper_thread, NULL, - "mce-notify"); - if (!mce_notify_helper) - return -ENOMEM; - - return 0; -} - -static void mce_notify_work(void) -{ - wake_up_process(mce_notify_helper); -} -#else -static void mce_notify_work(void) -{ - __mce_notify_work(); -} -static inline int mce_notify_work_init(void) { return 0; } -#endif - /* * Notify the user(s) about new machine check events. * Can be called from interrupt context, but not from machine check/NMI @@ -1420,8 +1353,19 @@ static inline int mce_notify_work_init(void) { return 0; } */ int mce_notify_irq(void) { + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + if (test_and_clear_bit(0, &mce_need_notify)) { - mce_notify_work(); + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); + + if (mce_helper[0]) + schedule_work(&mce_trigger_work); + + if (__ratelimit(&ratelimit)) + pr_info(HW_ERR "Machine check events logged\n"); + return 1; } return 0; @@ -1692,7 +1636,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct hrtimer *t) +static void mce_start_timer(unsigned int cpu, struct timer_list *t) { unsigned long iv = mce_adjust_timer(check_interval * HZ); @@ -1701,17 +1645,16 @@ static void mce_start_timer(unsigned int cpu, struct hrtimer *t) if (mca_cfg.ignore_ce || !iv) return; - hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL), - 0, HRTIMER_MODE_REL_PINNED); + t->expires = round_jiffies(jiffies + iv); + add_timer_on(t, smp_processor_id()); } static void __mcheck_cpu_init_timer(void) { - struct hrtimer *t = &__get_cpu_var(mce_timer); + struct timer_list *t = &__get_cpu_var(mce_timer); unsigned int cpu = smp_processor_id(); - hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - t->function = mce_timer_fn; + setup_timer(t, mce_timer_fn, cpu); mce_start_timer(cpu, t); } @@ -2386,8 +2329,6 @@ static void mce_disable_cpu(void *h) if (!mce_available(__this_cpu_ptr(&cpu_info))) return; - hrtimer_cancel(&__get_cpu_var(mce_timer)); - if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); for (i = 0; i < mca_cfg.banks; i++) { @@ -2414,7 +2355,6 @@ static void mce_reenable_cpu(void *h) if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); } - __mcheck_cpu_init_timer(); } /* Get notified when a cpu comes on/off. Be hotplug friendly. */ @@ -2422,6 +2362,7 @@ static int 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 & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: @@ -2437,9 +2378,11 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_DOWN_PREPARE: smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + del_timer_sync(t); break; case CPU_DOWN_FAILED: smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + mce_start_timer(cpu, t); break; } @@ -2501,8 +2444,6 @@ static __init int mcheck_init_device(void) /* register character device /dev/mcelog */ misc_register(&mce_chrdev_device); - err = mce_notify_work_init(); - return err; } device_initcall_sync(mcheck_init_device); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 71a39f3..6474807 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -63,6 +63,7 @@ static struct clocksource hyperv_cs = { .rating = 400, /* use this when running on Hyperv*/ .read = read_hv_clock, .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ce2d0a2..0e25a1b 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) } /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Save MTRR state */ @@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Intel (P6) standard MTRRs */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5edd3c0..c7106f1 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; + /* Check if the extra msrs can be safely accessed*/ + if (!er->extra_msr_access) + return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index cc16faa..53bd272 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -279,14 +279,16 @@ struct extra_reg { u64 config_mask; u64 valid_mask; int idx; /* per_xxx->regs[] reg index */ + bool extra_msr_access; }; #define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i, \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i, \ + .extra_msr_access = true, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f31a165..b400d0b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1365,6 +1365,15 @@ again: intel_pmu_lbr_read(); /* + * CondChgd bit 63 doesn't mean any overflow status. Ignore + * and clear the bit. + */ + if (__test_and_clear_bit(63, (unsigned long *)&status)) { + if (!status) + goto done; + } + + /* * PEBS overflow sets bit 62 in the global status register */ if (__test_and_clear_bit(62, (unsigned long *)&status)) { @@ -2135,6 +2144,41 @@ static void intel_snb_check_microcode(void) } } +/* + * Under certain circumstances, access certain MSR may cause #GP. + * The function tests if the input MSR can be safely accessed. + */ +static bool check_msr(unsigned long msr, u64 mask) +{ + u64 val_old, val_new, val_tmp; + + /* + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. + */ + if (rdmsrl_safe(msr, &val_old)) + return false; + + /* + * Only change the bits which can be updated by wrmsrl. + */ + val_tmp = val_old ^ mask; + if (wrmsrl_safe(msr, val_tmp) || + rdmsrl_safe(msr, &val_new)) + return false; + + if (val_new != val_tmp) + return false; + + /* Here it's sure that the MSR can be safely accessed. + * Restore the old value and return. + */ + wrmsrl(msr, val_old); + + return true; +} + static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; @@ -2198,7 +2242,8 @@ __init int intel_pmu_init(void) union cpuid10_ebx ebx; struct event_constraint *c; unsigned int unused; - int version; + struct extra_reg *er; + int version, i; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -2243,10 +2288,7 @@ __init int intel_pmu_init(void) if (version > 1) x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); - /* - * v2 and above have a perf capabilities MSR - */ - if (version > 1) { + if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); @@ -2404,6 +2446,9 @@ __init int intel_pmu_init(void) case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + /* dTLB-load-misses on IVB is different than SNB */ + hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */ + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -2503,6 +2548,34 @@ __init int intel_pmu_init(void) } } + /* + * Access LBR MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support LBR MSR + * Check all LBT MSR here. + * Disable LBR access if any LBR MSRs can not be accessed. + */ + if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL)) + x86_pmu.lbr_nr = 0; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) && + check_msr(x86_pmu.lbr_to + i, 0xffffUL))) + x86_pmu.lbr_nr = 0; + } + + /* + * Access extra MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support offcore event + * Check all extra_regs here. + */ + if (x86_pmu.extra_regs) { + for (er = x86_pmu.extra_regs; er->msr; er++) { + er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + /* Disable LBR select mapping */ + if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) + x86_pmu.lbr_sel_map = NULL; + } + } + /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { x86_pmu.max_period = x86_pmu.cntval_mask; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 4118f9f..3e1cfbb 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2764,6 +2764,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } +/* + * Using uncore_pmu_event_init pmu event_init callback + * as a detection point for uncore events. + */ +static int uncore_pmu_event_init(struct perf_event *event); + +static bool is_uncore_event(struct perf_event *event) +{ + return event->pmu->event_init == uncore_pmu_event_init; +} + static int uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { @@ -2778,13 +2789,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b return -EINVAL; n = box->n_events; - box->event_list[n] = leader; - n++; + + if (is_uncore_event(leader)) { + box->event_list[n] = leader; + n++; + } + if (!dogrp) return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (event->state <= PERF_EVENT_STATE_OFF) + if (!is_uncore_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207..66e274a 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = { [ DEBUG_STACK-1 ] = "#DB", [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ STACKFAULT_STACK-1 ] = "#SS", [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index e491bfd..1f1c33d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -364,22 +364,14 @@ ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? jnz restore_all +need_resched: movl TI_flags(%ebp), %ecx # need_resched set ? testb $_TIF_NEED_RESCHED, %cl - jnz 1f - - cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? - jnz restore_all - testl $_TIF_NEED_RESCHED_LAZY, %ecx jz restore_all - -1: testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq - movl TI_flags(%ebp), %ecx # need_resched set ? - testl $_TIF_NEED_RESCHED_MASK, %ecx - jnz 1b - jmp restore_all + jmp need_resched END(resume_kernel) #endif CFI_ENDPROC @@ -442,8 +434,9 @@ sysenter_past_esp: jnz sysenter_audit sysenter_do_call: cmpl $(NR_syscalls), %eax - jae syscall_badsys + jae sysenter_badsys call *sys_call_table(,%eax,4) +sysenter_after_call: movl %eax,PT_EAX(%esp) LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) @@ -524,6 +517,7 @@ ENTRY(system_call) jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) +syscall_after_call: movl %eax,PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT @@ -538,6 +532,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -548,6 +543,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -560,13 +556,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -608,6 +600,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -615,7 +608,7 @@ ENDPROC(system_call) ALIGN RING0_PTREGS_FRAME # can't unwind into user space anyway work_pending: - testl $_TIF_NEED_RESCHED_MASK, %ecx + testb $_TIF_NEED_RESCHED, %cl jz work_notifysig work_resched: call schedule @@ -628,7 +621,7 @@ work_resched: andl $_TIF_WORK_MASK, %ecx # is there any work to be done other # than syscall tracing? jz restore_all - testl $_TIF_NEED_RESCHED_MASK, %ecx + testb $_TIF_NEED_RESCHED, %cl jnz work_resched work_notifysig: # deal with pending signals and @@ -698,8 +691,13 @@ syscall_fault: END(syscall_fault) syscall_badsys: - movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + movl $-ENOSYS,%eax + jmp syscall_after_call +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,%eax + jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC /* @@ -715,6 +713,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -724,8 +723,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -736,6 +737,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1356,11 +1358,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1400,6 +1404,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1421,6 +1426,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index abca4f4..e965606 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -58,6 +58,7 @@ #include <asm/asm.h> #include <asm/context_tracking.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -658,8 +659,8 @@ sysret_check: /* Handle reschedules */ /* edx: work, edi: workmask */ sysret_careful: - testl $_TIF_NEED_RESCHED_MASK,%edx - jz sysret_signal + bt $TIF_NEED_RESCHED,%edx + jnc sysret_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -771,8 +772,8 @@ GLOBAL(int_with_check) /* First do a reschedule test. */ /* edx: work, edi: workmask */ int_careful: - testl $_TIF_NEED_RESCHED_MASK,%edx - jz int_very_careful + bt $TIF_NEED_RESCHED,%edx + jnc int_very_careful TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -1041,38 +1042,58 @@ restore_args: irq_return: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) -#ifdef CONFIG_PARAVIRT ENTRY(native_iret) - iretq - _ASM_EXTABLE(native_iret, bad_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt #endif - .section .fixup,"ax" -bad_iret: +.global native_irq_return_iret +native_irq_return_iret: /* - * The iret traps when the %cs or %ss being restored is bogus. - * We've lost the original trap vector and error code. - * #GPF is the most likely one to get for an invalid selector. - * So pretend we completed the iret and took the #GPF in user mode. - * - * We are now running with the kernel GS after exception recovery. - * But error_entry expects us to have user GS to match the user %cs, - * so swap back. + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. */ - pushq $0 + iretq +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi SWAPGS - jmp general_protection - - .previous + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp native_irq_return_iret +#endif /* edi: workmask, edx: work */ retint_careful: CFI_RESTORE_STATE - testl $_TIF_NEED_RESCHED_MASK,%edx - jz retint_signal + bt $TIF_NEED_RESCHED,%edx + jnc retint_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -1105,22 +1126,16 @@ retint_signal: ENTRY(retint_kernel) cmpl $0,TI_preempt_count(%rcx) jnz retint_restore_args - bt $TIF_NEED_RESCHED,TI_flags(%rcx) - jc 1f - - cmpl $0,TI_preempt_lazy_count(%rcx) - jnz retint_restore_args - bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) + bt $TIF_NEED_RESCHED,TI_flags(%rcx) jnc retint_restore_args - -1: bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ + bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + /* * End of kprobes section */ @@ -1347,7 +1362,6 @@ bad_gs: jmp 2b .previous -#ifndef CONFIG_PREEMPT_RT_FULL /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(call_softirq) CFI_STARTPROC @@ -1367,7 +1381,6 @@ ENTRY(call_softirq) ret CFI_ENDPROC END(call_softirq) -#endif #ifdef CONFIG_XEN zeroentry xen_hypervisor_callback xen_do_hypervisor_callback @@ -1483,7 +1496,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ paranoidzeroentry_ist debug do_debug DEBUG_STACK paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +errorentry stack_segment do_stack_segment #ifdef CONFIG_XEN zeroentry xen_debug do_debug zeroentry xen_int3 do_int3 @@ -1537,7 +1550,7 @@ paranoid_userspace: movq %rsp,%rdi /* &pt_regs */ call sync_regs movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED_MASK,%ebx + testl $_TIF_NEED_RESCHED,%ebx jnz paranoid_schedule movl %ebx,%edx /* arg3: thread flags */ TRACE_IRQS_ON @@ -1593,16 +1606,15 @@ error_sti: /* * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. The exception handlers after iret run with - * kernel gs again, so don't set the user space flag. B stepping K8s - * sometimes report an truncated RIP for IRET exceptions returning to - * compat mode. Check for these here too. + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) - je error_swapgs + je error_bad_iret movl %ecx,%eax /* zero extend */ cmpq %rax,RIP+8(%rsp) je bstep_iret @@ -1613,7 +1625,15 @@ error_kernelspace: bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) - jmp error_swapgs + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti CFI_ENDPROC END(error_entry) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 0000000..94d857f --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,208 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/random.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/setup.h> +#include <asm/espfix.h> + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index e625319..f8ab203 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -297,16 +297,7 @@ int ftrace_int3_handler(struct pt_regs *regs) static int ftrace_write(unsigned long ip, const char *val, int size) { - /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); + ip = text_ip_addr(ip); return probe_kernel_write((void *)ip, val, size); } @@ -659,8 +650,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code, ret = -EPERM; goto out; } - run_sync(); out: + run_sync(); return ret; fail_update: diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 22d0687..3910078 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -262,6 +262,83 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU + +/* These two declarations are only used in check_irq_vectors_for_cpu_disable() + * below, which is protected by stop_machine(). Putting them on the stack + * results in a stack frame overflow. Dynamically allocating could result in a + * failure so declare these two cpumasks as global. + */ +static struct cpumask affinity_new, online_new; + +/* + * This cpu is going to be removed and its vectors migrated to the remaining + * online cpus. Check to see if there are enough vectors in the remaining cpus. + * This function is protected by stop_machine(). + */ +int check_irq_vectors_for_cpu_disable(void) +{ + int irq, cpu; + unsigned int this_cpu, vector, this_count, count; + struct irq_desc *desc; + struct irq_data *data; + + this_cpu = smp_processor_id(); + cpumask_copy(&online_new, cpu_online_mask); + cpu_clear(this_cpu, online_new); + + this_count = 0; + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { + irq = __this_cpu_read(vector_irq[vector]); + if (irq >= 0) { + desc = irq_to_desc(irq); + data = irq_desc_get_irq_data(desc); + cpumask_copy(&affinity_new, data->affinity); + cpu_clear(this_cpu, affinity_new); + + /* Do not count inactive or per-cpu irqs. */ + if (!irq_has_action(irq) || irqd_is_per_cpu(data)) + continue; + + /* + * A single irq may be mapped to multiple + * cpu's vector_irq[] (for example IOAPIC cluster + * mode). In this case we have two + * possibilities: + * + * 1) the resulting affinity mask is empty; that is + * this the down'd cpu is the last cpu in the irq's + * affinity mask, or + * + * 2) the resulting affinity mask is no longer + * a subset of the online cpus but the affinity + * mask is not zero; that is the down'd cpu is the + * last online cpu in a user set affinity mask. + */ + if (cpumask_empty(&affinity_new) || + !cpumask_subset(&affinity_new, &online_new)) + this_count++; + } + } + + count = 0; + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; + vector++) { + if (per_cpu(vector_irq, cpu)[vector] < 0) + count++; + } + } + + if (count < this_count) { + pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n", + this_cpu, this_count, count); + return -ERANGE; + } + return 0; +} + /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 9da1bc7..4186755 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -149,7 +149,6 @@ void irq_ctx_init(int cpu) cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); } -#ifndef CONFIG_PREEMPT_RT_FULL asmlinkage void do_softirq(void) { unsigned long flags; @@ -180,7 +179,6 @@ asmlinkage void do_softirq(void) local_irq_restore(flags); } -#endif bool handle_irq(unsigned irq, struct pt_regs *regs) { diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 831f247..d04d3ec 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -88,7 +88,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) return true; } -#ifndef CONFIG_PREEMPT_RT_FULL + extern void call_softirq(void); asmlinkage void do_softirq(void) @@ -108,4 +108,3 @@ asmlinkage void do_softirq(void) } local_irq_restore(flags); } -#endif diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 3d21f7b..1de84e3 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -38,7 +38,6 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) exiting_irq(); } -#ifndef CONFIG_PREEMPT_RT_FULL void arch_irq_work_raise(void) { #ifdef CONFIG_X86_LOCAL_APIC @@ -49,4 +48,3 @@ void arch_irq_work_raise(void) apic_wait_icr_idle(); #endif } -#endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 79a3f96..a1f5b18 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1017,6 +1017,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } @@ -1042,24 +1051,25 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index f022c54..e725933 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -280,7 +280,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - pv_info.paravirt_enabled = 1; + + /* + * KVM isn't paravirt in the sense of paravirt_enabled. A KVM + * guest kernel works like a bare metal kernel with additional + * features, and paravirt_enabled is about features that are + * missing. + */ + pv_info.paravirt_enabled = 0; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1570e07..23457e5 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -262,7 +262,6 @@ void __init kvmclock_init(void) #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); - pv_info.paravirt_enabled = 1; pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ebc9873..c37886d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out_unlock; + } + fill_ldt(&ldt, &ldt_info); if (oldmode) ldt.avl = 0; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34..a1da673 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_cpu_ops, iret, "iretq"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); @@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, iret); PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 6ce0537..884f98f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -36,7 +36,6 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> -#include <linux/highmem.h> #include <asm/pgtable.h> #include <asm/ldt.h> @@ -220,35 +219,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); -#ifdef CONFIG_PREEMPT_RT_FULL -static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) -{ - int i; - - /* - * Clear @prev's kmap_atomic mappings - */ - for (i = 0; i < prev_p->kmap_idx; i++) { - int idx = i + KM_TYPE_NR * smp_processor_id(); - pte_t *ptep = kmap_pte - idx; - - kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); - } - /* - * Restore @next_p's kmap_atomic mappings - */ - for (i = 0; i < next_p->kmap_idx; i++) { - int idx = i + KM_TYPE_NR * smp_processor_id(); - - if (!pte_none(next_p->kmap_pte[i])) - set_pte(kmap_pte - idx, next_p->kmap_pte[i]); - } -} -#else -static inline void -switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } -#endif - /* * switch_to(x,y) should switch tasks from x to y. @@ -328,8 +298,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); - switch_kmaps(prev_p, next_p); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7461f50..0686fe3 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,15 +1441,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 -#endif - /* * We must return the syscall number to actually look up in the table. * This can be -1L to skip running any syscall at all. @@ -1487,7 +1478,7 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) + if (is_ia32_task()) audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax, regs->bx, regs->cx, diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 2a26819..80eab01 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail) void arch_remove_reservations(struct resource *avail) { - /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + /* + * Trim out BIOS area (high 2MB) and E820 regions. We do not remove + * the low 1MB unconditionally, as this area is needed for some ISA + * cards requiring a memory range, e.g. the i82365 PCMCIA controller. + */ if (avail->flags & IORESOURCE_MEM) { - if (avail->start < BIOS_END) - avail->start = BIOS_END; resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); remove_e820_regions(avail); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index ecfe089..b88fc86 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } @@ -739,14 +744,6 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) mce_notify_process(); #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ -#ifdef ARCH_RT_DELAYS_SIGNAL_SEND - if (unlikely(current->forced_info.si_signo)) { - struct task_struct *t = current; - force_sig_info(t->forced_info.si_signo, &t->forced_info, t); - t->forced_info.si_signo = 0; - } -#endif - if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6cacab6..9ccb7ef 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -265,6 +265,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -1278,6 +1285,9 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_sibling_mask(cpu)) cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(cpu_sibling_mask(cpu)); cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; @@ -1310,6 +1320,12 @@ void cpu_disable_common(void) int native_cpu_disable(void) { + int ret; + + ret = check_irq_vectors_for_cpu_disable(); + if (ret) + return ret; + clear_local_APIC(); cpu_disable_common(); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09..7fc5e84 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,58 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + /* + * For historical reasons (i.e. no one ever documented how any + * of the segmentation APIs work), user programs can and do + * assume that a struct user_desc that's all zeros except for + * entry_number means "no segment at all". This never actually + * worked. In fact, up to Linux 3.19, a struct user_desc like + * this would create a 16-bit read-write segment with base and + * limit both equal to zero. + * + * That was close enough to "no segment at all" until we + * hardened this function to disallow 16-bit TLS segments. Fix + * it up by interpreting these zeroed segments the way that they + * were almost certainly intended to be interpreted. + * + * The correct way to ask for "no segment at all" is to specify + * a user_desc that satisfies LDT_empty. To keep everything + * working, we accept both. + * + * Note that there's a similar kludge in modify_ldt -- look at + * the distinction between modes 1 and 0x11. + */ + if (LDT_empty(info) || LDT_zero(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -40,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info)) + if (LDT_empty(info) || LDT_zero(info)) desc->a = desc->b = 0; else fill_ldt(desc, info); @@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 6663bb5..88f3d3b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -86,21 +86,9 @@ static inline void conditional_sti(struct pt_regs *regs) local_irq_enable(); } -static inline void conditional_sti_ist(struct pt_regs *regs) +static inline void preempt_conditional_sti(struct pt_regs *regs) { -#ifdef CONFIG_X86_64 - /* - * X86_64 uses a per CPU stack on the IST for certain traps - * like int3. The task can not be preempted when using one - * of these stacks, thus preemption must be disabled, otherwise - * the stack can be corrupted if the task is scheduled out, - * and another task comes in and uses this stack. - * - * On x86_32 the task keeps its own stack and it is OK if the - * task schedules out. - */ inc_preempt_count(); -#endif if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } @@ -111,13 +99,11 @@ static inline void conditional_cli(struct pt_regs *regs) local_irq_disable(); } -static inline void conditional_cli_ist(struct pt_regs *regs) +static inline void preempt_conditional_cli(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); -#ifdef CONFIG_X86_64 dec_preempt_count(); -#endif } static int __kprobes @@ -235,33 +221,41 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) -#ifdef CONFIG_X86_32 DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) -#endif DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - enum ctx_state prev_state; - - prev_state = exception_enter(); - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - conditional_sti_ist(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - conditional_cli_ist(regs); - } - exception_exit(prev_state); -} - dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_X86_ESPFIX64 + extern unsigned char native_irq_return_iret[]; + + /* + * If IRET takes a non-IST fault on the espfix64 stack, then we + * end up promoting it to a doublefault. In that case, modify + * the stack to make it look like we just entered the #GP + * handler from user space, similar to bad_iret. + */ + if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + regs->cs == __KERNEL_CS && + regs->ip == (unsigned long)native_irq_return_iret) + { + struct pt_regs *normal_regs = task_pt_regs(current); + + /* Fake a #GP(0) from userspace. */ + memmove(&normal_regs->ip, (void *)regs->sp, 5*8); + normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + regs->ip = (unsigned long)general_protection; + regs->sp = (unsigned long)&normal_regs->orig_ax; + return; + } +#endif + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -361,9 +355,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - conditional_sti_ist(regs); + preempt_conditional_sti(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); - conditional_cli_ist(regs); + preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: exception_exit(prev_state); @@ -375,7 +369,7 @@ exit: * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage notrace __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -394,6 +388,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } + +struct bad_iret_stack { + void *error_entry_ret; + struct pt_regs regs; +}; + +asmlinkage __visible notrace __kprobes +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +{ + /* + * This is called from entry_64.S early in handling a fault + * caused by a bad iret to user mode. To handle the fault + * correctly, we want move our stack frame to task_pt_regs + * and we want to pretend that the exception came from the + * iret target. + */ + struct bad_iret_stack *new_stack = + container_of(task_pt_regs(current), + struct bad_iret_stack, regs); + + /* Copy the IRET target to the new stack. */ + memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + + /* Copy the remainder of the stack from the current stack. */ + memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + + BUG_ON(!user_mode_vm(&new_stack->regs)); + return new_stack; +} #endif /* @@ -469,12 +492,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - conditional_sti_ist(regs); + preempt_conditional_sti(regs); if (regs->flags & X86_VM_MASK) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); - conditional_cli_ist(regs); + preempt_conditional_cli(regs); debug_stack_usage_dec(); goto exit; } @@ -494,7 +517,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) si_code = get_si_code(tsk->thread.debugreg6); if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); - conditional_cli_ist(regs); + preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: @@ -766,7 +789,7 @@ void __init trap_init(void) set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); set_intr_gate(X86_TRAP_TS, &invalid_TSS); set_intr_gate(X86_TRAP_NP, &segment_not_present); - set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_SS, stack_segment); set_intr_gate(X86_TRAP_GP, &general_protection); set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); set_intr_gate(X86_TRAP_MF, &coprocessor_error); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 930e5d4..cefe57c 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -386,7 +386,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - pr_err("Fast TSC calibration failed\n"); + pr_info("Fast TSC calibration failed\n"); return 0; success: @@ -974,14 +974,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 1f96f93..09ce23a 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 422fd82..f5869fc 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -399,8 +397,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) set_used_math(); } - if (use_eager_fpu()) + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { |