diff options
Diffstat (limited to 'arch/x86/kernel')
40 files changed, 963 insertions, 694 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index a468f0fdc907..6bb680671088 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -180,10 +180,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) return -EINVAL; } + if (!enabled) { + ++disabled_cpus; + return -EINVAL; + } + if (boot_cpu_physical_apicid != -1U) ver = boot_cpu_apic_version; - cpu = __generic_processor_info(id, ver, enabled); + cpu = generic_processor_info(id, ver); if (cpu >= 0) early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid; @@ -711,7 +716,7 @@ static void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; @@ -1560,12 +1565,6 @@ int __init early_acpi_boot_init(void) return 0; } -static int __init acpi_parse_bgrt(struct acpi_table_header *table) -{ - efi_bgrt_init(table); - return 0; -} - int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4eca103a1e01..847650b14558 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -731,8 +731,10 @@ static int __init calibrate_APIC_clock(void) TICK_NSEC, lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); + lapic_clockevent.max_delta_ticks = 0x7FFFFF; lapic_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &lapic_clockevent); + lapic_clockevent.min_delta_ticks = 0xF; lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; return 0; } @@ -778,8 +780,10 @@ static int __init calibrate_APIC_clock(void) lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent); + lapic_clockevent.max_delta_ticks = 0x7FFFFFFF; lapic_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &lapic_clockevent); + lapic_clockevent.min_delta_ticks = 0xF; lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; @@ -1610,24 +1614,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } #endif /* !CONFIG_X86_X2APIC */ -static int __init try_to_enable_IR(void) -{ -#ifdef CONFIG_X86_IO_APIC - if (!x2apic_enabled() && skip_ioapic_setup) { - pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); - return -1; - } -#endif - return irq_remapping_enable(); -} - void __init enable_IR_x2apic(void) { unsigned long flags; int ret, ir_stat; - if (skip_ioapic_setup) + if (skip_ioapic_setup) { + pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); return; + } ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) @@ -1645,7 +1640,7 @@ void __init enable_IR_x2apic(void) /* If irq_remapping_prepare() succeeded, try to enable it */ if (ir_stat >= 0) - ir_stat = try_to_enable_IR(); + ir_stat = irq_remapping_enable(); /* ir_stat contains the remap mode or an error code */ try_to_enable_x2apic(ir_stat); @@ -2062,17 +2057,17 @@ static int allocate_logical_cpuid(int apicid) /* Allocate a new cpuid. */ if (nr_logical_cpuids >= nr_cpu_ids) { - WARN_ONCE(1, "Only %d processors supported." + WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. " "Processor %d/0x%x and the rest are ignored.\n", - nr_cpu_ids - 1, nr_logical_cpuids, apicid); - return -1; + nr_cpu_ids, nr_logical_cpuids, apicid); + return -EINVAL; } cpuid_to_apicid[nr_logical_cpuids] = apicid; return nr_logical_cpuids++; } -int __generic_processor_info(int apicid, int version, bool enabled) +int generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2130,11 +2125,9 @@ int __generic_processor_info(int apicid, int version, bool enabled) if (num_processors >= nr_cpu_ids) { int thiscpu = max + disabled_cpus; - if (enabled) { - pr_warning("APIC: NR_CPUS/possible_cpus limit of %i " - "reached. Processor %d/0x%x ignored.\n", - max, thiscpu, apicid); - } + pr_warning("APIC: NR_CPUS/possible_cpus limit of %i " + "reached. Processor %d/0x%x ignored.\n", + max, thiscpu, apicid); disabled_cpus++; return -EINVAL; @@ -2186,23 +2179,13 @@ int __generic_processor_info(int apicid, int version, bool enabled) apic->x86_32_early_logical_apicid(cpu); #endif set_cpu_possible(cpu, true); - - if (enabled) { - num_processors++; - physid_set(apicid, phys_cpu_present_map); - set_cpu_present(cpu, true); - } else { - disabled_cpus++; - } + physid_set(apicid, phys_cpu_present_map); + set_cpu_present(cpu, true); + num_processors++; return cpu; } -int generic_processor_info(int apicid, int version) -{ - return __generic_processor_info(apicid, version, true); -} - int hard_smp_processor_id(void) { return read_apic_id(); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 7f179f1c467c..b487b3a01615 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1106,7 +1106,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi) node_id.v = uv_read_local_mmr(UVH_NODE_ID); uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val); hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1; - hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val; + if (mn.m_val) + hi->gnode_upper = (u64)hi->gnode_extra << mn.m_val; if (uv_gp_table) { hi->global_mmr_base = uv_gp_table->mmr_base; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 35a5d5dca2fa..c36140d788fe 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (check_tsc_unstable()) - clear_sched_clock_stable(); - } else { - clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 106bd3318121..44207b71fee1 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif - - clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b11b38c3b0bd..58094a1f9e9d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif - clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -1077,8 +1076,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); - else - clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 0a3bc19de017..a70fd61095f8 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } - clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fe0a615a051b..dfa90a3a5145 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -90,16 +90,12 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) return; } - if (ring3mwait_disabled) { - msr_clear_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + if (ring3mwait_disabled) return; - } - - msr_set_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + this_cpu_or(msr_misc_features_shadow, + 1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT); if (c == &boot_cpu_data) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; @@ -162,10 +158,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (check_tsc_unstable()) - clear_sched_clock_stable(); - } else { - clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -492,6 +484,34 @@ static void intel_bsp_resume(struct cpuinfo_x86 *c) init_intel_energy_perf(c); } +static void init_cpuid_fault(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) { + if (msr & MSR_PLATFORM_INFO_CPUID_FAULT) + set_cpu_cap(c, X86_FEATURE_CPUID_FAULT); + } +} + +static void init_intel_misc_features(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr)) + return; + + /* Clear all MISC features */ + this_cpu_write(msr_misc_features_shadow, 0); + + /* Check features and update capabilities and shadow control bits */ + init_cpuid_fault(c); + probe_xeon_phi_r3mwait(c); + + msr = this_cpu_read(msr_misc_features_shadow); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msr); +} + static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -606,7 +626,7 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_energy_perf(c); - probe_xeon_phi_r3mwait(c); + init_intel_misc_features(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 0bbe0f3a039f..9ac2a5cdd9c2 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -28,7 +28,6 @@ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/slab.h> -#include <linux/cpu.h> #include <linux/task_work.h> #include <uapi/linux/magic.h> @@ -728,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { kernfs_unbreak_active_protection(kn); - kernfs_put(kn); + kernfs_put(rdtgrp->kn); kfree(rdtgrp); } else { kernfs_unbreak_active_protection(kn); diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c index f369cb8db0d5..badd2b31a560 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c @@ -200,11 +200,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } out: - rdtgroup_kn_unlock(of->kn); for_each_enabled_rdt_resource(r) { kfree(r->tmp_cbms); r->tmp_cbms = NULL; } + rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; } diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index a3311c886194..43051f0777d4 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -9,3 +9,5 @@ obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o obj-$(CONFIG_ACPI_APEI) += mce-apei.o + +obj-$(CONFIG_X86_MCELOG_LEGACY) += dev-mcelog.o diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c new file mode 100644 index 000000000000..9c632cb88546 --- /dev/null +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -0,0 +1,397 @@ +/* + * /dev/mcelog driver + * + * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. + * Rest from unknown author(s). + * 2004 Andi Kleen. Rewrote most of it. + * Copyright 2008 Intel Corporation + * Author: Andi Kleen + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/miscdevice.h> +#include <linux/slab.h> +#include <linux/kmod.h> +#include <linux/poll.h> + +#include "mce-internal.h" + +static DEFINE_MUTEX(mce_chrdev_read_mutex); + +static char mce_helper[128]; +static char *mce_helper_argv[2] = { mce_helper, NULL }; + +#define mce_log_get_idx_check(p) \ +({ \ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious mce_log_get_idx_check() usage"); \ + smp_load_acquire(&(p)); \ +}) + +/* + * Lockless MCE logging infrastructure. + * This avoids deadlocks on printk locks without having to break locks. Also + * separate MCEs from kernel messages to avoid bogus bug reports. + */ + +static struct mce_log_buffer mcelog = { + .signature = MCE_LOG_SIGNATURE, + .len = MCE_LOG_LEN, + .recordlen = sizeof(struct mce), +}; + +static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); + +/* User mode helper program triggered by machine check event */ +extern char mce_helper[128]; + +static int dev_mce_log(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + unsigned int next, entry; + + wmb(); + for (;;) { + entry = mce_log_get_idx_check(mcelog.next); + for (;;) { + + /* + * When the buffer fills up discard new entries. + * Assume that the earlier errors are the more + * interesting ones: + */ + if (entry >= MCE_LOG_LEN) { + set_bit(MCE_OVERFLOW, + (unsigned long *)&mcelog.flags); + return NOTIFY_OK; + } + /* Old left over entry. Skip: */ + if (mcelog.entry[entry].finished) { + entry++; + continue; + } + break; + } + smp_rmb(); + next = entry + 1; + if (cmpxchg(&mcelog.next, entry, next) == entry) + break; + } + memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); + wmb(); + mcelog.entry[entry].finished = 1; + wmb(); + + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); + + return NOTIFY_OK; +} + +static struct notifier_block dev_mcelog_nb = { + .notifier_call = dev_mce_log, + .priority = MCE_PRIO_MCELOG, +}; + +static void mce_do_trigger(struct work_struct *work) +{ + call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); +} + +static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + + +void mce_work_trigger(void) +{ + if (mce_helper[0]) + schedule_work(&mce_trigger_work); +} + +static ssize_t +show_trigger(struct device *s, struct device_attribute *attr, char *buf) +{ + strcpy(buf, mce_helper); + strcat(buf, "\n"); + return strlen(mce_helper) + 1; +} + +static ssize_t set_trigger(struct device *s, struct device_attribute *attr, + const char *buf, size_t siz) +{ + char *p; + + strncpy(mce_helper, buf, sizeof(mce_helper)); + mce_helper[sizeof(mce_helper)-1] = 0; + p = strchr(mce_helper, '\n'); + + if (p) + *p = 0; + + return strlen(mce_helper) + !!p; +} + +DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); + +/* + * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log. + */ + +static DEFINE_SPINLOCK(mce_chrdev_state_lock); +static int mce_chrdev_open_count; /* #times opened */ +static int mce_chrdev_open_exclu; /* already open exclusive? */ + +static int mce_chrdev_open(struct inode *inode, struct file *file) +{ + spin_lock(&mce_chrdev_state_lock); + + if (mce_chrdev_open_exclu || + (mce_chrdev_open_count && (file->f_flags & O_EXCL))) { + spin_unlock(&mce_chrdev_state_lock); + + return -EBUSY; + } + + if (file->f_flags & O_EXCL) + mce_chrdev_open_exclu = 1; + mce_chrdev_open_count++; + + spin_unlock(&mce_chrdev_state_lock); + + return nonseekable_open(inode, file); +} + +static int mce_chrdev_release(struct inode *inode, struct file *file) +{ + spin_lock(&mce_chrdev_state_lock); + + mce_chrdev_open_count--; + mce_chrdev_open_exclu = 0; + + spin_unlock(&mce_chrdev_state_lock); + + return 0; +} + +static void collect_tscs(void *data) +{ + unsigned long *cpu_tsc = (unsigned long *)data; + + cpu_tsc[smp_processor_id()] = rdtsc(); +} + +static int mce_apei_read_done; + +/* Collect MCE record of previous boot in persistent storage via APEI ERST. */ +static int __mce_read_apei(char __user **ubuf, size_t usize) +{ + int rc; + u64 record_id; + struct mce m; + + if (usize < sizeof(struct mce)) + return -EINVAL; + + rc = apei_read_mce(&m, &record_id); + /* Error or no more MCE record */ + if (rc <= 0) { + mce_apei_read_done = 1; + /* + * When ERST is disabled, mce_chrdev_read() should return + * "no record" instead of "no device." + */ + if (rc == -ENODEV) + return 0; + return rc; + } + rc = -EFAULT; + if (copy_to_user(*ubuf, &m, sizeof(struct mce))) + return rc; + /* + * In fact, we should have cleared the record after that has + * been flushed to the disk or sent to network in + * /sbin/mcelog, but we have no interface to support that now, + * so just clear it to avoid duplication. + */ + rc = apei_clear_mce(record_id); + if (rc) { + mce_apei_read_done = 1; + return rc; + } + *ubuf += sizeof(struct mce); + + return 0; +} + +static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, + size_t usize, loff_t *off) +{ + char __user *buf = ubuf; + unsigned long *cpu_tsc; + unsigned prev, next; + int i, err; + + cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); + if (!cpu_tsc) + return -ENOMEM; + + mutex_lock(&mce_chrdev_read_mutex); + + if (!mce_apei_read_done) { + err = __mce_read_apei(&buf, usize); + if (err || buf != ubuf) + goto out; + } + + next = mce_log_get_idx_check(mcelog.next); + + /* Only supports full reads right now */ + err = -EINVAL; + if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) + goto out; + + err = 0; + prev = 0; + do { + for (i = prev; i < next; i++) { + unsigned long start = jiffies; + struct mce *m = &mcelog.entry[i]; + + while (!m->finished) { + if (time_after_eq(jiffies, start + 2)) { + memset(m, 0, sizeof(*m)); + goto timeout; + } + cpu_relax(); + } + smp_rmb(); + err |= copy_to_user(buf, m, sizeof(*m)); + buf += sizeof(*m); +timeout: + ; + } + + memset(mcelog.entry + prev, 0, + (next - prev) * sizeof(struct mce)); + prev = next; + next = cmpxchg(&mcelog.next, prev, 0); + } while (next != prev); + + synchronize_sched(); + + /* + * Collect entries that were still getting written before the + * synchronize. + */ + on_each_cpu(collect_tscs, cpu_tsc, 1); + + for (i = next; i < MCE_LOG_LEN; i++) { + struct mce *m = &mcelog.entry[i]; + + if (m->finished && m->tsc < cpu_tsc[m->cpu]) { + err |= copy_to_user(buf, m, sizeof(*m)); + smp_rmb(); + buf += sizeof(*m); + memset(m, 0, sizeof(*m)); + } + } + + if (err) + err = -EFAULT; + +out: + mutex_unlock(&mce_chrdev_read_mutex); + kfree(cpu_tsc); + + return err ? err : buf - ubuf; +} + +static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) +{ + poll_wait(file, &mce_chrdev_wait, wait); + if (READ_ONCE(mcelog.next)) + return POLLIN | POLLRDNORM; + if (!mce_apei_read_done && apei_check_mce()) + return POLLIN | POLLRDNORM; + return 0; +} + +static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, + unsigned long arg) +{ + int __user *p = (int __user *)arg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (cmd) { + case MCE_GET_RECORD_LEN: + return put_user(sizeof(struct mce), p); + case MCE_GET_LOG_LEN: + return put_user(MCE_LOG_LEN, p); + case MCE_GETCLEAR_FLAGS: { + unsigned flags; + + do { + flags = mcelog.flags; + } while (cmpxchg(&mcelog.flags, flags, 0) != flags); + + return put_user(flags, p); + } + default: + return -ENOTTY; + } +} + +static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off); + +void register_mce_write_callback(ssize_t (*fn)(struct file *filp, + const char __user *ubuf, + size_t usize, loff_t *off)) +{ + mce_write = fn; +} +EXPORT_SYMBOL_GPL(register_mce_write_callback); + +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) +{ + if (mce_write) + return mce_write(filp, ubuf, usize, off); + else + return -EINVAL; +} + +static const struct file_operations mce_chrdev_ops = { + .open = mce_chrdev_open, + .release = mce_chrdev_release, + .read = mce_chrdev_read, + .write = mce_chrdev_write, + .poll = mce_chrdev_poll, + .unlocked_ioctl = mce_chrdev_ioctl, + .llseek = no_llseek, +}; + +static struct miscdevice mce_chrdev_device = { + MISC_MCELOG_MINOR, + "mcelog", + &mce_chrdev_ops, +}; + +static __init int dev_mcelog_init_device(void) +{ + int err; + + /* register character device /dev/mcelog */ + err = misc_register(&mce_chrdev_device); + if (err) { + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + return err; + } + mce_register_decode_chain(&dev_mcelog_nb); + return 0; +} +device_initcall_sync(dev_mcelog_init_device); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 1e5a50c11d3c..217cd4449bc9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused) head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 903043e6a62b..654ad0668d72 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,7 +13,7 @@ enum severity_level { MCE_PANIC_SEVERITY, }; -extern struct atomic_notifier_head x86_mce_decoder_chain; +extern struct blocking_notifier_head x86_mce_decoder_chain; #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ @@ -96,3 +96,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2) m1->addr != m2->addr || m1->misc != m2->misc; } + +extern struct device_attribute dev_attr_trigger; + +#ifdef CONFIG_X86_MCELOG_LEGACY +extern void mce_work_trigger(void); +#else +static inline void mce_work_trigger(void) { } +#endif diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8e9725c607ea..5abd4bf73d6e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -35,6 +35,7 @@ #include <linux/poll.h> #include <linux/nmi.h> #include <linux/cpu.h> +#include <linux/ras.h> #include <linux/smp.h> #include <linux/fs.h> #include <linux/mm.h> @@ -49,18 +50,11 @@ #include <asm/tlbflush.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/reboot.h> #include "mce-internal.h" -static DEFINE_MUTEX(mce_chrdev_read_mutex); - -#define mce_log_get_idx_check(p) \ -({ \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ - !lockdep_is_held(&mce_chrdev_read_mutex), \ - "suspicious mce_log_get_idx_check() usage"); \ - smp_load_acquire(&(p)); \ -}) +static DEFINE_MUTEX(mce_log_mutex); #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -85,15 +79,9 @@ struct mca_config mca_cfg __read_mostly = { .monarch_timeout = -1 }; -/* User mode helper program triggered by machine check event */ -static unsigned long mce_need_notify; -static char mce_helper[128]; -static char *mce_helper_argv[2] = { mce_helper, NULL }; - -static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); - static DEFINE_PER_CPU(struct mce, mces_seen); -static int cpu_missing; +static unsigned long mce_need_notify; +static int cpu_missing; /* * MCA banks polled by the period polling timer for corrected events. @@ -121,7 +109,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) @@ -143,82 +131,38 @@ void mce_setup(struct mce *m) DEFINE_PER_CPU(struct mce, injectm); EXPORT_PER_CPU_SYMBOL_GPL(injectm); -/* - * Lockless MCE logging infrastructure. - * This avoids deadlocks on printk locks without having to break locks. Also - * separate MCEs from kernel messages to avoid bogus bug reports. - */ - -static struct mce_log mcelog = { - .signature = MCE_LOG_SIGNATURE, - .len = MCE_LOG_LEN, - .recordlen = sizeof(struct mce), -}; - -void mce_log(struct mce *mce) +void mce_log(struct mce *m) { - unsigned next, entry; - - /* Emit the trace record: */ - trace_mce_record(mce); - - if (!mce_gen_pool_add(mce)) + if (!mce_gen_pool_add(m)) irq_work_queue(&mce_irq_work); - - wmb(); - for (;;) { - entry = mce_log_get_idx_check(mcelog.next); - for (;;) { - - /* - * When the buffer fills up discard new entries. - * Assume that the earlier errors are the more - * interesting ones: - */ - if (entry >= MCE_LOG_LEN) { - set_bit(MCE_OVERFLOW, - (unsigned long *)&mcelog.flags); - return; - } - /* Old left over entry. Skip: */ - if (mcelog.entry[entry].finished) { - entry++; - continue; - } - break; - } - smp_rmb(); - next = entry + 1; - if (cmpxchg(&mcelog.next, entry, next) == entry) - break; - } - memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); - wmb(); - mcelog.entry[entry].finished = 1; - wmb(); - - set_bit(0, &mce_need_notify); } void mce_inject_log(struct mce *m) { - mutex_lock(&mce_chrdev_read_mutex); + mutex_lock(&mce_log_mutex); mce_log(m); - mutex_unlock(&mce_chrdev_read_mutex); + mutex_unlock(&mce_log_mutex); } EXPORT_SYMBOL_GPL(mce_inject_log); static struct notifier_block mce_srao_nb; +/* + * We run the default notifier if we have only the SRAO, the first and the + * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS + * notifiers registered on the chain. + */ +#define NUM_DEFAULT_NOTIFIERS 3 static atomic_t num_notifiers; void mce_register_decode_chain(struct notifier_block *nb) { - atomic_inc(&num_notifiers); + if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC)) + return; - WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); + atomic_inc(&num_notifiers); - atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -226,7 +170,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb) { atomic_dec(&num_notifiers); - atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -319,18 +263,7 @@ static void __print_mce(struct mce *m) static void print_mce(struct mce *m) { - int ret = 0; - __print_mce(m); - - /* - * Print out human-readable details about the MCE error, - * (if the CPU has an implementation for that) - */ - ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - if (ret == NOTIFY_STOP) - return; - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } @@ -519,7 +452,6 @@ static void mce_schedule_work(void) static void mce_irq_work_cb(struct irq_work *entry) { - mce_notify_irq(); mce_schedule_work(); } @@ -548,20 +480,97 @@ static void mce_report_event(struct pt_regs *regs) */ static int mce_usable_address(struct mce *m) { - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + if (!(m->status & MCI_STATUS_ADDRV)) return 0; /* Checks after this one are Intel-specific: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 1; + if (!(m->status & MCI_STATUS_MISCV)) + return 0; + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) return 0; + return 1; } +static bool memory_error(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86_vendor == X86_VENDOR_AMD) { + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); + } else if (c->x86_vendor == X86_VENDOR_INTEL) { + /* + * Intel SDM Volume 3B - 15.9.2 Compound Error Codes + * + * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for + * indicating a memory error. Bit 8 is used for indicating a + * cache hierarchy error. The combination of bit 2 and bit 3 + * is used for indicating a `generic' cache hierarchy error + * But we can't just blindly check the above bits, because if + * bit 11 is set, then it is a bus/interconnect error - and + * either way the above bits just gives more detail on what + * bus/interconnect error happened. Note that bit 12 can be + * ignored, as it's the "filter" bit. + */ + return (m->status & 0xef80) == BIT(7) || + (m->status & 0xef00) == BIT(8) || + (m->status & 0xeffc) == 0xc; + } + + return false; +} + +static bool cec_add_mce(struct mce *m) +{ + if (!m) + return false; + + /* We eat only correctable DRAM errors with usable addresses. */ + if (memory_error(m) && + !(m->status & MCI_STATUS_UC) && + mce_usable_address(m)) + if (!cec_add_elem(m->addr >> PAGE_SHIFT)) + return true; + + return false; +} + +static int mce_first_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + if (cec_add_mce(m)) + return NOTIFY_STOP; + + /* Emit the trace record: */ + trace_mce_record(m); + + set_bit(0, &mce_need_notify); + + mce_notify_irq(); + + return NOTIFY_DONE; +} + +static struct notifier_block first_nb = { + .notifier_call = mce_first_notifier, + .priority = MCE_PRIO_FIRST, +}; + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -591,11 +600,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, if (!m) return NOTIFY_DONE; - /* - * Run the default notifier if we have only the SRAO - * notifier and us registered. - */ - if (atomic_read(&num_notifiers) > 2) + if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS) return NOTIFY_DONE; __print_mce(m); @@ -648,37 +653,6 @@ static void mce_read_aux(struct mce *m, int i) } } -static bool memory_error(struct mce *m) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - if (c->x86_vendor == X86_VENDOR_AMD) { - /* ErrCodeExt[20:16] */ - u8 xec = (m->status >> 16) & 0x1f; - - return (xec == 0x0 || xec == 0x8); - } else if (c->x86_vendor == X86_VENDOR_INTEL) { - /* - * Intel SDM Volume 3B - 15.9.2 Compound Error Codes - * - * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for - * indicating a memory error. Bit 8 is used for indicating a - * cache hierarchy error. The combination of bit 2 and bit 3 - * is used for indicating a `generic' cache hierarchy error - * But we can't just blindly check the above bits, because if - * bit 11 is set, then it is a bus/interconnect error - and - * either way the above bits just gives more detail on what - * bus/interconnect error happened. Note that bit 12 can be - * ignored, as it's the "filter" bit. - */ - return (m->status & 0xef80) == BIT(7) || - (m->status & 0xef00) == BIT(8) || - (m->status & 0xeffc) == 0xc; - } - - return false; -} - DEFINE_PER_CPU(unsigned, mce_poll_count); /* @@ -1127,9 +1101,22 @@ void do_machine_check(struct pt_regs *regs, long error_code) * on Intel. */ int lmce = 1; + int cpu = smp_processor_id(); - /* If this CPU is offline, just bail out. */ - if (cpu_is_offline(smp_processor_id())) { + /* + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. + * + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. + */ + if (cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); @@ -1399,13 +1386,6 @@ static void mce_timer_delete_all(void) del_timer_sync(&per_cpu(mce_timer, cpu)); } -static void mce_do_trigger(struct work_struct *work) -{ - call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); -} - -static DECLARE_WORK(mce_trigger_work, mce_do_trigger); - /* * Notify the user(s) about new machine check events. * Can be called from interrupt context, but not from machine check/NMI @@ -1417,11 +1397,7 @@ int mce_notify_irq(void) static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); if (test_and_clear_bit(0, &mce_need_notify)) { - /* wake processes polling /dev/mcelog */ - wake_up_interruptible(&mce_chrdev_wait); - - if (mce_helper[0]) - schedule_work(&mce_trigger_work); + mce_work_trigger(); if (__ratelimit(&ratelimit)) pr_info(HW_ERR "Machine check events logged\n"); @@ -1688,30 +1664,35 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) return 0; } -static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) +/* + * Init basic CPU features needed for early decoding of MCEs. + */ +static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) { - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - mce_intel_feature_init(c); - mce_adjust_timer = cmci_intel_adjust_timer; - break; - - case X86_VENDOR_AMD: { + if (c->x86_vendor == X86_VENDOR_AMD) { mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); - /* - * Install proper ops for Scalable MCA enabled processors - */ if (mce_flags.smca) { msr_ops.ctl = smca_ctl_reg; msr_ops.status = smca_status_reg; msr_ops.addr = smca_addr_reg; msr_ops.misc = smca_misc_reg; } - mce_amd_feature_init(c); + } +} + +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 = cmci_intel_adjust_timer; + break; + case X86_VENDOR_AMD: { + mce_amd_feature_init(c); break; } @@ -1798,6 +1779,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) machine_check_vector = do_machine_check; + __mcheck_cpu_init_early(c); __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_clear_banks(); @@ -1823,252 +1805,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c) } -/* - * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log. - */ - -static DEFINE_SPINLOCK(mce_chrdev_state_lock); -static int mce_chrdev_open_count; /* #times opened */ -static int mce_chrdev_open_exclu; /* already open exclusive? */ - -static int mce_chrdev_open(struct inode *inode, struct file *file) -{ - spin_lock(&mce_chrdev_state_lock); - - if (mce_chrdev_open_exclu || - (mce_chrdev_open_count && (file->f_flags & O_EXCL))) { - spin_unlock(&mce_chrdev_state_lock); - - return -EBUSY; - } - - if (file->f_flags & O_EXCL) - mce_chrdev_open_exclu = 1; - mce_chrdev_open_count++; - - spin_unlock(&mce_chrdev_state_lock); - - return nonseekable_open(inode, file); -} - -static int mce_chrdev_release(struct inode *inode, struct file *file) -{ - spin_lock(&mce_chrdev_state_lock); - - mce_chrdev_open_count--; - mce_chrdev_open_exclu = 0; - - spin_unlock(&mce_chrdev_state_lock); - - return 0; -} - -static void collect_tscs(void *data) -{ - unsigned long *cpu_tsc = (unsigned long *)data; - - cpu_tsc[smp_processor_id()] = rdtsc(); -} - -static int mce_apei_read_done; - -/* Collect MCE record of previous boot in persistent storage via APEI ERST. */ -static int __mce_read_apei(char __user **ubuf, size_t usize) -{ - int rc; - u64 record_id; - struct mce m; - - if (usize < sizeof(struct mce)) - return -EINVAL; - - rc = apei_read_mce(&m, &record_id); - /* Error or no more MCE record */ - if (rc <= 0) { - mce_apei_read_done = 1; - /* - * When ERST is disabled, mce_chrdev_read() should return - * "no record" instead of "no device." - */ - if (rc == -ENODEV) - return 0; - return rc; - } - rc = -EFAULT; - if (copy_to_user(*ubuf, &m, sizeof(struct mce))) - return rc; - /* - * In fact, we should have cleared the record after that has - * been flushed to the disk or sent to network in - * /sbin/mcelog, but we have no interface to support that now, - * so just clear it to avoid duplication. - */ - rc = apei_clear_mce(record_id); - if (rc) { - mce_apei_read_done = 1; - return rc; - } - *ubuf += sizeof(struct mce); - - return 0; -} - -static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, - size_t usize, loff_t *off) -{ - char __user *buf = ubuf; - unsigned long *cpu_tsc; - unsigned prev, next; - int i, err; - - cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); - if (!cpu_tsc) - return -ENOMEM; - - mutex_lock(&mce_chrdev_read_mutex); - - if (!mce_apei_read_done) { - err = __mce_read_apei(&buf, usize); - if (err || buf != ubuf) - goto out; - } - - next = mce_log_get_idx_check(mcelog.next); - - /* Only supports full reads right now */ - err = -EINVAL; - if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) - goto out; - - err = 0; - prev = 0; - do { - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - struct mce *m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2)) { - memset(m, 0, sizeof(*m)); - goto timeout; - } - cpu_relax(); - } - smp_rmb(); - err |= copy_to_user(buf, m, sizeof(*m)); - buf += sizeof(*m); -timeout: - ; - } - - memset(mcelog.entry + prev, 0, - (next - prev) * sizeof(struct mce)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); - - synchronize_sched(); - - /* - * Collect entries that were still getting written before the - * synchronize. - */ - on_each_cpu(collect_tscs, cpu_tsc, 1); - - for (i = next; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - - if (m->finished && m->tsc < cpu_tsc[m->cpu]) { - err |= copy_to_user(buf, m, sizeof(*m)); - smp_rmb(); - buf += sizeof(*m); - memset(m, 0, sizeof(*m)); - } - } - - if (err) - err = -EFAULT; - -out: - mutex_unlock(&mce_chrdev_read_mutex); - kfree(cpu_tsc); - - return err ? err : buf - ubuf; -} - -static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) -{ - poll_wait(file, &mce_chrdev_wait, wait); - if (READ_ONCE(mcelog.next)) - return POLLIN | POLLRDNORM; - if (!mce_apei_read_done && apei_check_mce()) - return POLLIN | POLLRDNORM; - return 0; -} - -static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, - unsigned long arg) -{ - int __user *p = (int __user *)arg; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - switch (cmd) { - case MCE_GET_RECORD_LEN: - return put_user(sizeof(struct mce), p); - case MCE_GET_LOG_LEN: - return put_user(MCE_LOG_LEN, p); - case MCE_GETCLEAR_FLAGS: { - unsigned flags; - - do { - flags = mcelog.flags; - } while (cmpxchg(&mcelog.flags, flags, 0) != flags); - - return put_user(flags, p); - } - default: - return -ENOTTY; - } -} - -static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off); - -void register_mce_write_callback(ssize_t (*fn)(struct file *filp, - const char __user *ubuf, - size_t usize, loff_t *off)) -{ - mce_write = fn; -} -EXPORT_SYMBOL_GPL(register_mce_write_callback); - -static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) -{ - if (mce_write) - return mce_write(filp, ubuf, usize, off); - else - return -EINVAL; -} - -static const struct file_operations mce_chrdev_ops = { - .open = mce_chrdev_open, - .release = mce_chrdev_release, - .read = mce_chrdev_read, - .write = mce_chrdev_write, - .poll = mce_chrdev_poll, - .unlocked_ioctl = mce_chrdev_ioctl, - .llseek = no_llseek, -}; - -static struct miscdevice mce_chrdev_device = { - MISC_MCELOG_MINOR, - "mcelog", - &mce_chrdev_ops, -}; - static void __mce_disable_bank(void *arg) { int bank = *((int *)arg); @@ -2142,6 +1878,7 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); + mce_register_decode_chain(&first_nb); mce_register_decode_chain(&mce_srao_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); @@ -2286,29 +2023,6 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return size; } -static ssize_t -show_trigger(struct device *s, struct device_attribute *attr, char *buf) -{ - strcpy(buf, mce_helper); - strcat(buf, "\n"); - return strlen(mce_helper) + 1; -} - -static ssize_t set_trigger(struct device *s, struct device_attribute *attr, - const char *buf, size_t siz) -{ - char *p; - - strncpy(mce_helper, buf, sizeof(mce_helper)); - mce_helper[sizeof(mce_helper)-1] = 0; - p = strchr(mce_helper, '\n'); - - if (p) - *p = 0; - - return strlen(mce_helper) + !!p; -} - static ssize_t set_ignore_ce(struct device *s, struct device_attribute *attr, const char *buf, size_t size) @@ -2365,7 +2079,6 @@ static ssize_t store_int_with_restart(struct device *s, return ret; } -static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); @@ -2388,7 +2101,9 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, +#ifdef CONFIG_X86_MCELOG_LEGACY &dev_attr_trigger, +#endif &dev_attr_monarch_timeout.attr, &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, @@ -2562,7 +2277,6 @@ static __init void mce_init_banks(void) static __init int mcheck_init_device(void) { - enum cpuhp_state hp_online; int err; if (!mce_available(&boot_cpu_data)) { @@ -2590,21 +2304,11 @@ static __init int mcheck_init_device(void) mce_cpu_online, mce_cpu_pre_down); if (err < 0) goto err_out_online; - hp_online = err; register_syscore_ops(&mce_syscore_ops); - /* register character device /dev/mcelog */ - err = misc_register(&mce_chrdev_device); - if (err) - goto err_register; - return 0; -err_register: - unregister_syscore_ops(&mce_syscore_ops); - cpuhp_remove_state(hp_online); - err_out_online: cpuhp_remove_state(CPUHP_X86_MCE_DEAD); @@ -2612,7 +2316,7 @@ err_out_mem: free_cpumask_var(mce_device_initialized); err_out: - pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + pr_err("Unable to init MCE device (rc: %d)\n", err); return err; } @@ -2691,6 +2395,7 @@ static int __init mcheck_late_init(void) static_branch_inc(&mcsafe_key); mcheck_debugfs_init(); + cec_init(); /* * Flush out everything that has been logged during early boot, now that diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 524cc5780a77..6e4a047e4b68 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -60,7 +60,7 @@ static const char * const th_names[] = { "load_store", "insn_fetch", "combined_unit", - "", + "decode_unit", "northbridge", "execution_unit", }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 190b3e6cef4d..e84db79ef272 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -481,6 +481,9 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) case INTEL_FAM6_BROADWELL_XEON_D: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: + if (rdmsrl_safe(MSR_PPIN_CTL, &val)) return; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 8457b4978668..d77d07ab310b 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } - - clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 891f4dad7b2c..22403a28caf5 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -30,7 +30,6 @@ #include <asm/hypervisor.h> #include <asm/timer.h> #include <asm/apic.h> -#include <asm/timer.h> #undef pr_fmt #define pr_fmt(fmt) "vmware: " fmt diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8639bb2ae058..5b7153540727 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -535,7 +535,7 @@ static void run_sync(void) { int enable_irqs = irqs_disabled(); - /* We may be called with interrupts disbled (on bootup). */ + /* We may be called with interrupts disabled (on bootup). */ if (enable_irqs) local_irq_enable(); on_each_cpu(do_sync_core, NULL, 1); @@ -983,6 +983,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long return_hooker = (unsigned long) &return_to_handler; + /* + * When resuming from suspend-to-ram, this function can be indirectly + * called from early CPU startup code while the CPU is in real mode, + * which would fail miserably. Make sure the stack pointer is a + * virtual address. + * + * This check isn't as accurate as virt_addr_valid(), but it should be + * good enough for this purpose, and it's fast. + */ + if (unlikely((long)__builtin_frame_address(0) >= 0)) + return; + if (unlikely(ftrace_graph_is_dead())) return; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index baa0e7b78d80..43b7002f44fb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -4,6 +4,7 @@ * Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE */ +#define DISABLE_BRANCH_PROFILING #include <linux/init.h> #include <linux/linkage.h> #include <linux/types.h> diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dc6ba5bda9fc..89ff7af2de50 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); - disable_irq(hdev->irq); + disable_hardirq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); } diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index bdb83e431d89..38b64587b31b 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void) struct dentry *dbp, *version, *data; int error = -ENOMEM; - dbp = debugfs_create_dir("boot_params", NULL); + dbp = debugfs_create_dir("boot_params", arch_debugfs_dir); if (!dbp) return -ENOMEM; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index c6ee63f927ab..db2182d63ed0 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -67,7 +67,7 @@ #endif /* Ensure if the instruction can be boostable */ -extern int can_boost(kprobe_opcode_t *instruction); +extern int can_boost(struct insn *insn, void *orig_addr); /* Recover instruction if given address is probed */ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr); @@ -75,7 +75,7 @@ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, * Copy an instruction and adjust the displacement if the instruction * uses the %rip-relative addressing mode. */ -extern int __copy_instruction(u8 *dest, u8 *src); +extern int __copy_instruction(u8 *dest, u8 *src, struct insn *insn); /* Generate a relative-jump/call instruction */ extern void synthesize_reljump(void *from, void *to); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6384eb754a58..19e1f2a6d7b0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -164,42 +164,38 @@ static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn) NOKPROBE_SYMBOL(skip_prefixes); /* - * Returns non-zero if opcode is boostable. + * Returns non-zero if INSN is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int can_boost(kprobe_opcode_t *opcodes) +int can_boost(struct insn *insn, void *addr) { kprobe_opcode_t opcode; - kprobe_opcode_t *orig_opcodes = opcodes; - if (search_exception_tables((unsigned long)opcodes)) + if (search_exception_tables((unsigned long)addr)) return 0; /* Page fault may occur on this address. */ -retry: - if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) - return 0; - opcode = *(opcodes++); - /* 2nd-byte opcode */ - if (opcode == 0x0f) { - if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) - return 0; - return test_bit(*opcodes, + if (insn->opcode.nbytes == 2) + return test_bit(insn->opcode.bytes[1], (unsigned long *)twobyte_is_boostable); - } + + if (insn->opcode.nbytes != 1) + return 0; + + /* Can't boost Address-size override prefix */ + if (unlikely(inat_is_address_size_prefix(insn->attr))) + return 0; + + opcode = insn->opcode.bytes[0]; switch (opcode & 0xf0) { -#ifdef CONFIG_X86_64 - case 0x40: - goto retry; /* REX prefix is boostable */ -#endif case 0x60: - if (0x63 < opcode && opcode < 0x67) - goto retry; /* prefixes */ - /* can't boost Address-size override and bound */ - return (opcode != 0x62 && opcode != 0x67); + /* can't boost "bound" */ + return (opcode != 0x62); case 0x70: return 0; /* can't boost conditional jump */ + case 0x90: + return opcode != 0x9a; /* can't boost call far */ case 0xc0: /* can't boost software-interruptions */ return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf; @@ -210,14 +206,9 @@ retry: /* can boost in/out and absolute jmps */ return ((opcode & 0x04) || opcode == 0xea); case 0xf0: - if ((opcode & 0x0c) == 0 && opcode != 0xf1) - goto retry; /* lock/rep(ne) prefix */ /* clear and set flags are boostable */ return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); default: - /* segment override prefixes are boostable */ - if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e) - goto retry; /* prefixes */ /* CS override prefix and call are not boostable */ return (opcode != 0x2e && opcode != 0x9a); } @@ -264,7 +255,10 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Fortunately, we know that the original code is the ideal 5-byte * long NOP. */ - memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (probe_kernel_read(buf, (void *)addr, + MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) + return 0UL; + if (faddr) memcpy(buf, ideal_nops[NOP_ATOMIC5], 5); else @@ -276,7 +270,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Recover the probed instruction at addr for further analysis. * Caller must lock kprobes by kprobe_mutex, or disable preemption * for preventing to release referencing kprobes. - * Returns zero if the instruction can not get recovered. + * Returns zero if the instruction can not get recovered (or access failed). */ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) { @@ -348,37 +342,36 @@ static int is_IF_modifier(kprobe_opcode_t *insn) } /* - * Copy an instruction and adjust the displacement if the instruction - * uses the %rip-relative addressing mode. - * If it does, Return the address of the 32-bit displacement word. - * If not, return null. - * Only applicable to 64-bit x86. + * Copy an instruction with recovering modified instruction by kprobes + * and adjust the displacement if the instruction uses the %rip-relative + * addressing mode. + * This returns the length of copied instruction, or 0 if it has an error. */ -int __copy_instruction(u8 *dest, u8 *src) +int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) { - struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; - int length; unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); - if (!recovered_insn) + if (!recovered_insn || !insn) + return 0; + + /* This can access kernel text if given address is not recovered */ + if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE)) return 0; - kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); - insn_get_length(&insn); - length = insn.length; + + kernel_insn_init(insn, dest, MAX_INSN_SIZE); + insn_get_length(insn); /* Another subsystem puts a breakpoint, failed to recover */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; - memcpy(dest, insn.kaddr, length); #ifdef CONFIG_X86_64 - if (insn_rip_relative(&insn)) { + /* Only x86_64 has RIP relative instructions */ + if (insn_rip_relative(insn)) { s64 newdisp; u8 *disp; - kernel_insn_init(&insn, dest, length); - insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing * mode. Adjust the displacement for the difference between @@ -391,36 +384,57 @@ int __copy_instruction(u8 *dest, u8 *src) * extension of the original signed 32-bit displacement would * have given. */ - newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; + newdisp = (u8 *) src + (s64) insn->displacement.value + - (u8 *) dest; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); - pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value); + pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", + src, dest, insn->displacement.value); return 0; } - disp = (u8 *) dest + insn_offset_displacement(&insn); + disp = (u8 *) dest + insn_offset_displacement(insn); *(s32 *) disp = (s32) newdisp; } #endif - return length; + return insn->length; +} + +/* Prepare reljump right after instruction to boost */ +static void prepare_boost(struct kprobe *p, struct insn *insn) +{ + if (can_boost(insn, p->addr) && + MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) { + /* + * These instructions can be executed directly if it + * jumps back to correct address. + */ + synthesize_reljump(p->ainsn.insn + insn->length, + p->addr + insn->length); + p->ainsn.boostable = true; + } else { + p->ainsn.boostable = false; + } } static int arch_copy_kprobe(struct kprobe *p) { - int ret; + struct insn insn; + int len; + + set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1); /* Copy an instruction with recovering if other optprobe modifies it.*/ - ret = __copy_instruction(p->ainsn.insn, p->addr); - if (!ret) + len = __copy_instruction(p->ainsn.insn, p->addr, &insn); + if (!len) return -EINVAL; /* * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - if (can_boost(p->ainsn.insn)) - p->ainsn.boostable = 0; - else - p->ainsn.boostable = -1; + prepare_boost(p, &insn); + + set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1); /* Check whether the instruction modifies Interrupt Flag or not */ p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); @@ -459,7 +473,7 @@ void arch_disarm_kprobe(struct kprobe *p) void arch_remove_kprobe(struct kprobe *p) { if (p->ainsn.insn) { - free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); + free_insn_slot(p->ainsn.insn, p->ainsn.boostable); p->ainsn.insn = NULL; } } @@ -531,7 +545,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, return; #if !defined(CONFIG_PREEMPT) - if (p->ainsn.boostable == 1 && !p->post_handler) { + if (p->ainsn.boostable && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ if (!reenter) reset_current_kprobe(); @@ -851,7 +865,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, case 0xcf: case 0xea: /* jmp absolute -- ip is correct */ /* ip is already adjusted, no more changes required */ - p->ainsn.boostable = 1; + p->ainsn.boostable = true; goto no_change; case 0xe8: /* call relative - Fix return addr */ *tos = orig_ip + (*tos - copy_ip); @@ -876,28 +890,13 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, * jmp near and far, absolute indirect * ip is correct. And this is boostable */ - p->ainsn.boostable = 1; + p->ainsn.boostable = true; goto no_change; } default: break; } - if (p->ainsn.boostable == 0) { - if ((regs->ip > copy_ip) && - (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) { - /* - * These instructions can be executed directly if it - * jumps back to correct address. - */ - synthesize_reljump((void *)regs->ip, - (void *)orig_ip + (regs->ip - copy_ip)); - p->ainsn.boostable = 1; - } else { - p->ainsn.boostable = -1; - } - } - regs->ip += orig_ip - copy_ip; no_change: diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 5f8f0b3cc674..041f7b6dfa0f 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -94,6 +94,6 @@ NOKPROBE_SYMBOL(kprobe_ftrace_handler); int arch_prepare_kprobe_ftrace(struct kprobe *p) { p->ainsn.insn = NULL; - p->ainsn.boostable = -1; + p->ainsn.boostable = false; return 0; } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3d1bee9d6a72..9aadff3d0902 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -65,7 +65,10 @@ found: * overwritten by jump destination address. In this case, original * bytes must be recovered from op->optinsn.copied_insn buffer. */ - memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (probe_kernel_read(buf, (void *)addr, + MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) + return 0UL; + if (addr == (unsigned long)kp->addr) { buf[0] = kp->opcode; memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); @@ -174,11 +177,12 @@ NOKPROBE_SYMBOL(optimized_callback); static int copy_optimized_instructions(u8 *dest, u8 *src) { + struct insn insn; int len = 0, ret; while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len); - if (!ret || !can_boost(dest + len)) + ret = __copy_instruction(dest + len, src + len, &insn); + if (!ret || !can_boost(&insn, src + len)) return -EINVAL; len += ret; } @@ -350,6 +354,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, } buf = (u8 *)op->optinsn.insn; + set_memory_rw((unsigned long)buf & PAGE_MASK, 1); /* Copy instructions into the out-of-line buffer */ ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); @@ -372,6 +377,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, (u8 *)op->kp.addr + op->optinsn.size); + set_memory_ro((unsigned long)buf & PAGE_MASK, 1); + flush_icache_range((unsigned long) buf, (unsigned long) buf + TMPL_END_IDX + op->optinsn.size + RELATIVEJUMP_SIZE); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 307b1f4543de..857cdbd02867 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image) /* Setup copying of backup region */ if (image->type == KEXEC_TYPE_CRASH) { - ret = kexec_purgatory_get_set_symbol(image, "backup_dest", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_dest", &image->arch.backup_load_addr, sizeof(image->arch.backup_load_addr), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_src", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_src", &image->arch.backup_src_start, sizeof(image->arch.backup_src_start), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_sz", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_sz", &image->arch.backup_src_sz, sizeof(image->arch.backup_src_sz), 0); if (ret) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index f088ea4c66e7..446c8aa09b9b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) spin_lock_irqsave(&desc->lock, flags); /* - * most handlers of type NMI_UNKNOWN never return because - * they just assume the NMI is theirs. Just a sanity check - * to manage expectations + * Indicate if there are multiple registrations on the + * internal NMI handler call chains (SERR and IO_CHECK). */ - WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head)); WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head)); WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head)); @@ -224,17 +222,6 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", reason, smp_processor_id()); - /* - * On some machines, PCI SERR line is used to report memory - * errors. EDAC makes use of it. - */ -#if defined(CONFIG_EDAC) - if (edac_handler_set()) { - edac_atomic_assert_error(); - return; - } -#endif - if (panic_on_unrecovered_nmi) nmi_panic(regs, "NMI: Not continuing"); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f67591561711..0bb88428cbf2 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -37,6 +37,7 @@ #include <asm/vm86.h> #include <asm/switch_to.h> #include <asm/desc.h> +#include <asm/prctl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -124,11 +125,6 @@ void flush_thread(void) fpu__clear(&tsk->thread.fpu); } -static void hard_disable_TSC(void) -{ - cr4_set_bits(X86_CR4_TSD); -} - void disable_TSC(void) { preempt_disable(); @@ -137,15 +133,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); } -static void hard_enable_TSC(void) -{ - cr4_clear_bits(X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -154,7 +145,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); } @@ -182,54 +173,129 @@ int set_tsc_mode(unsigned int val) return 0; } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; +DEFINE_PER_CPU(u64, msr_misc_features_shadow); - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); +static void set_cpuid_faulting(bool on) +{ + u64 msrval; - debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) - debugctl |= DEBUGCTLMSR_BTF; + msrval = this_cpu_read(msr_misc_features_shadow); + msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; + msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT); + this_cpu_write(msr_misc_features_shadow, msrval); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval); +} - update_debugctlmsr(debugctl); +static void disable_cpuid(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(true); } + preempt_enable(); +} - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); +static void enable_cpuid(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(false); } + preempt_enable(); +} + +static int get_cpuid_mode(void) +{ + return !test_thread_flag(TIF_NOCPUID); +} + +static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled) +{ + if (!static_cpu_has(X86_FEATURE_CPUID_FAULT)) + return -ENODEV; + + if (cpuid_enabled) + enable_cpuid(); + else + disable_cpuid(); + + return 0; +} + +/* + * Called immediately after a successful exec. + */ +void arch_setup_new_exec(void) +{ + /* If cpuid was previously disabled for this task, re-enable it. */ + if (test_thread_flag(TIF_NOCPUID)) + enable_cpuid(); +} - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { +static inline void switch_to_bitmap(struct tss_struct *tss, + struct thread_struct *prev, + struct thread_struct *next, + unsigned long tifp, unsigned long tifn) +{ + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. * Normally this is 128 bytes or less: */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); - /* * Make sure that the TSS limit is correct for the CPU * to notice the IO bitmap. */ refresh_tss_limit(); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + } else if (tifp & _TIF_IO_BITMAP) { /* * Clear any possible leftover bits: */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + unsigned long tifp, tifn; + + prev = &prev_p->thread; + next = &next_p->thread; + + tifn = READ_ONCE(task_thread_info(next_p)->flags); + tifp = READ_ONCE(task_thread_info(prev_p)->flags); + switch_to_bitmap(tss, prev, next, tifp, tifn); + propagate_user_return_notify(prev_p, next_p); + + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~DEBUGCTLMSR_BTF; + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_NOCPUID) + set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); } /* @@ -550,3 +616,16 @@ out: put_task_stack(p); return ret; } + +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled) +{ + switch (option) { + case ARCH_GET_CPUID: + return get_cpuid_mode(); + case ARCH_SET_CPUID: + return set_cpuid_mode(task, cpuid_enabled); + } + + return -EINVAL; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4c818f8bc135..ff40e74c9181 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/ldt.h> @@ -56,6 +57,7 @@ #include <asm/switch_to.h> #include <asm/vm86.h> #include <asm/intel_rdt.h> +#include <asm/proto.h> void __show_regs(struct pt_regs *regs, int all) { @@ -304,3 +306,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return do_arch_prctl_common(current, option, arg2); +} diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index d6b784a5520d..ea1a6180bf39 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -204,7 +205,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, tls); + err = do_arch_prctl_64(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -547,70 +548,72 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) } #endif -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; int doit = task == current; int cpu; - switch (code) { + switch (option) { case ARCH_SET_GS: - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.gsindex = 0; - task->thread.gsbase = addr; + task->thread.gsbase = arg2; if (doit) { load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2); } put_cpu(); break; case ARCH_SET_FS: /* Not strictly needed for fs, but do it for symmetry with gs */ - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.fsindex = 0; - task->thread.fsbase = addr; + task->thread.fsbase = arg2; if (doit) { /* set the selector to 0 to not confuse __switch_to */ loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); + ret = wrmsrl_safe(MSR_FS_BASE, arg2); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; + if (doit) rdmsrl(MSR_FS_BASE, base); else base = task->thread.fsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } case ARCH_GET_GS: { unsigned long base; + if (doit) rdmsrl(MSR_KERNEL_GS_BASE, base); else base = task->thread.gsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } #ifdef CONFIG_CHECKPOINT_RESTORE # ifdef CONFIG_X86_X32_ABI case ARCH_MAP_VDSO_X32: - return prctl_map_vdso(&vdso_image_x32, addr); + return prctl_map_vdso(&vdso_image_x32, arg2); # endif # if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION case ARCH_MAP_VDSO_32: - return prctl_map_vdso(&vdso_image_32, addr); + return prctl_map_vdso(&vdso_image_32, arg2); # endif case ARCH_MAP_VDSO_64: - return prctl_map_vdso(&vdso_image_64, addr); + return prctl_map_vdso(&vdso_image_64, arg2); #endif default: @@ -621,10 +624,23 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + long ret; + + ret = do_arch_prctl_64(current, option, arg2); + if (ret == -EINVAL) + ret = do_arch_prctl_common(current, option, arg2); + + return ret; +} + +#ifdef CONFIG_IA32_EMULATION +COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl(current, code, addr); + return do_arch_prctl_common(current, option, arg2); } +#endif unsigned long KSTK_ESP(struct task_struct *task) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2364b23ea3e5..f37d18124648 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -396,12 +396,12 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; /* - * When changing the segment base, use do_arch_prctl + * When changing the segment base, use do_arch_prctl_64 * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ if (child->thread.fsbase != value) - return do_arch_prctl(child, ARCH_SET_FS, value); + return do_arch_prctl_64(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): /* @@ -410,7 +410,7 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; if (child->thread.gsbase != value) - return do_arch_prctl(child, ARCH_SET_GS, value); + return do_arch_prctl_64(child, ARCH_SET_GS, value); return 0; #endif } @@ -869,7 +869,7 @@ long arch_ptrace(struct task_struct *child, long request, Works just like arch_prctl, except that the arguments are reversed. */ case PTRACE_ARCH_PRCTL: - ret = do_arch_prctl(child, data, addr); + ret = do_arch_prctl_64(child, data, addr); break; #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index e244c19a2451..2544700a2a87 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, + { /* Handle problems with rebooting on ASUS EeeBook X205TA */ + .callback = set_acpi_reboot, + .ident = "ASUS EeeBook X205TA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"), + }, + }, + { /* Handle problems with rebooting on ASUS EeeBook X205TAW */ + .callback = set_acpi_reboot, + .ident = "ASUS EeeBook X205TAW", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"), + }, + }, /* Certec */ { /* Handle problems with rebooting on Certec BPC600 */ @@ -749,10 +765,11 @@ void machine_crash_shutdown(struct pt_regs *regs) #endif +/* This is the CPU performing the emergency shutdown work. */ +int crashing_cpu = -1; + #if defined(CONFIG_SMP) -/* This keeps a track of which one is crashing cpu. */ -static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 396c042e9d0e..cc30a74e4adb 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -846,7 +846,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ec1f756f9dc9..71beb28600d4 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, if (from->si_signo == SIGSEGV) { if (from->si_code == SEGV_BNDERR) { - compat_uptr_t lower = (unsigned long)&to->si_lower; - compat_uptr_t upper = (unsigned long)&to->si_upper; + compat_uptr_t lower = (unsigned long)from->si_lower; + compat_uptr_t upper = (unsigned long)from->si_upper; put_user_ex(lower, &to->si_lower); put_user_ex(upper, &to->si_upper); } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 9d7223cad389..d798c0da451c 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -125,7 +125,7 @@ static bool smp_no_nmi_ipi = false; static void native_smp_send_reschedule(int cpu) { if (unlikely(cpu_is_offline(cpu))) { - WARN_ON(1); + WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu); return; } apic->send_IPI(cpu, RESCHEDULE_VECTOR); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 948443e115c1..4e496379a871 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -255,7 +255,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", tsk->comm, tsk->pid, str, regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } @@ -519,7 +519,7 @@ do_general_protection(struct pt_regs *regs, long error_code) pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx", tsk->comm, task_pid_nr(tsk), regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 46bcda4cb1c2..714dfba6a1e7 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -327,9 +327,16 @@ unsigned long long sched_clock(void) { return paravirt_sched_clock(); } + +bool using_native_sched_clock(void) +{ + return pv_time_ops.sched_clock == native_sched_clock; +} #else unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); + +bool using_native_sched_clock(void) { return true; } #endif int check_tsc_unstable(void) @@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) { if (tsc_unstable) return; + tsc_unstable = 1; - clear_sched_clock_stable(); + if (using_native_sched_clock()) + clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to clocksource watchdog\n"); } @@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = { void mark_tsc_unstable(char *reason) { - if (!tsc_unstable) { - tsc_unstable = 1; + if (tsc_unstable) + return; + + tsc_unstable = 1; + if (using_native_sched_clock()) clear_sched_clock_stable(); - disable_sched_clock_irqtime(); - pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) - clocksource_mark_unstable(&clocksource_tsc); - else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to %s\n", reason); + /* Change only the rating, when not registered */ + if (clocksource_tsc.mult) { + clocksource_mark_unstable(&clocksource_tsc); + } else { + clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; + clocksource_tsc.rating = 0; } } @@ -1322,6 +1333,8 @@ static int __init init_tsc_clocksource(void) * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { + if (boot_cpu_has(X86_FEATURE_ART)) + art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); return 0; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 478d15dbaee4..08339262b666 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -82,19 +82,43 @@ static size_t regs_size(struct pt_regs *regs) return sizeof(*regs); } +#ifdef CONFIG_X86_32 +#define GCC_REALIGN_WORDS 3 +#else +#define GCC_REALIGN_WORDS 1 +#endif + static bool is_last_task_frame(struct unwind_state *state) { - unsigned long bp = (unsigned long)state->bp; - unsigned long regs = (unsigned long)task_pt_regs(state->task); + unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2; + unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS; /* * We have to check for the last task frame at two different locations * because gcc can occasionally decide to realign the stack pointer and - * change the offset of the stack frame by a word in the prologue of a - * function called by head/entry code. + * change the offset of the stack frame in the prologue of a function + * called by head/entry code. Examples: + * + * <start_secondary>: + * push %edi + * lea 0x8(%esp),%edi + * and $0xfffffff8,%esp + * pushl -0x4(%edi) + * push %ebp + * mov %esp,%ebp + * + * <x86_64_start_kernel>: + * lea 0x8(%rsp),%r10 + * and $0xfffffffffffffff0,%rsp + * pushq -0x8(%r10) + * push %rbp + * mov %rsp,%rbp + * + * Note that after aligning the stack, it pushes a duplicate copy of + * the return address before pushing the frame pointer. */ - return bp == regs - FRAME_HEADER_SIZE || - bp == regs - FRAME_HEADER_SIZE - sizeof(long); + return (state->bp == last_bp || + (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1))); } /* |