if (!mce_gen_pool_add(mce))
irq_work_queue(&mce_irq_work);
- mce->finished = 0;
wmb();
for (;;) {
entry = mce_log_get_idx_check(mcelog.next);
mcelog.entry[entry].finished = 1;
wmb();
- mce->finished = 1;
set_bit(0, &mce_need_notify);
}
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
+static inline u32 ctl_reg(int bank)
+{
+ return MSR_IA32_MCx_CTL(bank);
+}
+
+static inline u32 status_reg(int bank)
+{
+ return MSR_IA32_MCx_STATUS(bank);
+}
+
+static inline u32 addr_reg(int bank)
+{
+ return MSR_IA32_MCx_ADDR(bank);
+}
+
+static inline u32 misc_reg(int bank)
+{
+ return MSR_IA32_MCx_MISC(bank);
+}
+
+static inline u32 smca_ctl_reg(int bank)
+{
+ return MSR_AMD64_SMCA_MCx_CTL(bank);
+}
+
+static inline u32 smca_status_reg(int bank)
+{
+ return MSR_AMD64_SMCA_MCx_STATUS(bank);
+}
+
+static inline u32 smca_addr_reg(int bank)
+{
+ return MSR_AMD64_SMCA_MCx_ADDR(bank);
+}
+
+static inline u32 smca_misc_reg(int bank)
+{
+ return MSR_AMD64_SMCA_MCx_MISC(bank);
+}
+
+struct mca_msr_regs msr_ops = {
+ .ctl = ctl_reg,
+ .status = status_reg,
+ .addr = addr_reg,
+ .misc = misc_reg
+};
+
static void print_mce(struct mce *m)
{
int ret = 0;
static void mce_panic(const char *msg, struct mce *final, char *exp)
{
- int i, apei_err = 0;
+ int apei_err = 0;
+ struct llist_node *pending;
+ struct mce_evt_llist *l;
if (!fake_panic) {
/*
if (atomic_inc_return(&mce_fake_panicked) > 1)
return;
}
+ pending = mce_gen_pool_prepare_records();
/* First print corrected ones that are still unlogged */
- for (i = 0; i < MCE_LOG_LEN; i++) {
- struct mce *m = &mcelog.entry[i];
- if (!(m->status & MCI_STATUS_VAL))
- continue;
+ llist_for_each_entry(l, pending, llnode) {
+ struct mce *m = &l->mce;
if (!(m->status & MCI_STATUS_UC)) {
print_mce(m);
if (!apei_err)
}
}
/* Now print uncorrected but with the final one last */
- for (i = 0; i < MCE_LOG_LEN; i++) {
- struct mce *m = &mcelog.entry[i];
- if (!(m->status & MCI_STATUS_VAL))
- continue;
+ llist_for_each_entry(l, pending, llnode) {
+ struct mce *m = &l->mce;
if (!(m->status & MCI_STATUS_UC))
continue;
- if (!final || memcmp(m, final, sizeof(struct mce))) {
+ if (!final || mce_cmp(m, final)) {
print_mce(m);
if (!apei_err)
apei_err = apei_write_mce(m);
if (msr == mca_cfg.rip_msr)
return offsetof(struct mce, ip);
- if (msr == MSR_IA32_MCx_STATUS(bank))
+ if (msr == msr_ops.status(bank))
return offsetof(struct mce, status);
- if (msr == MSR_IA32_MCx_ADDR(bank))
+ if (msr == msr_ops.addr(bank))
return offsetof(struct mce, addr);
- if (msr == MSR_IA32_MCx_MISC(bank))
+ if (msr == msr_ops.misc(bank))
return offsetof(struct mce, misc);
if (msr == MSR_IA32_MCG_STATUS)
return offsetof(struct mce, mcgstatus);
static void mce_read_aux(struct mce *m, int i)
{
if (m->status & MCI_STATUS_MISCV)
- m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
+ m->misc = mce_rdmsrl(msr_ops.misc(i));
if (m->status & MCI_STATUS_ADDRV) {
- m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+ m->addr = mce_rdmsrl(msr_ops.addr(i));
/*
* Mask the reported address by the reported granularity.
m.tsc = 0;
barrier();
- m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+ m.status = mce_rdmsrl(msr_ops.status(i));
if (!(m.status & MCI_STATUS_VAL))
continue;
/*
* Clear state for this bank.
*/
- mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+ mce_wrmsrl(msr_ops.status(i), 0);
}
/*
char *tmp;
for (i = 0; i < mca_cfg.banks; i++) {
- m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+ m->status = mce_rdmsrl(msr_ops.status(i));
if (m->status & MCI_STATUS_VAL) {
__set_bit(i, validp);
if (quirk_no_way_out)
atomic_add(*no_way_out, &global_nwo);
/*
- * global_nwo should be updated before mce_callin
+ * Rely on the implied barrier below, such that global_nwo
+ * is updated before mce_callin.
*/
- smp_wmb();
order = atomic_inc_return(&mce_callin);
/*
for (i = 0; i < mca_cfg.banks; i++) {
if (test_bit(i, toclear))
- mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+ mce_wrmsrl(msr_ops.status(i), 0);
}
}
+static int do_memory_failure(struct mce *m)
+{
+ int flags = MF_ACTION_REQUIRED;
+ int ret;
+
+ pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
+ if (!(m->mcgstatus & MCG_STATUS_RIPV))
+ flags |= MF_MUST_KILL;
+ ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
+ if (ret)
+ pr_err("Memory error not recovered");
+ return ret;
+}
+
/*
* The actual machine check handler. This only handles real
* exceptions when something got corrupted coming in through int 18.
int i;
int worst = 0;
int severity;
+
/*
* Establish sequential order between the CPUs entering the machine
* check handler.
*/
- int order;
+ int order = -1;
/*
* If no_way_out gets set, there is no safe way to recover from this
* MCE. If mca_cfg.tolerant is cranked up, we'll try anyway.
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
char *msg = "Unknown";
- u64 recover_paddr = ~0ull;
- int flags = MF_ACTION_REQUIRED;
- int lmce = 0;
+
+ /*
+ * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
+ * on Intel.
+ */
+ int lmce = 1;
/* If this CPU is offline, just bail out. */
if (cpu_is_offline(smp_processor_id())) {
kill_it = 1;
/*
- * Check if this MCE is signaled to only this logical processor
+ * Check if this MCE is signaled to only this logical processor,
+ * on Intel only.
*/
- if (m.mcgstatus & MCG_STATUS_LMCES)
- lmce = 1;
- else {
- /*
- * Go through all the banks in exclusion of the other CPUs.
- * This way we don't report duplicated events on shared banks
- * because the first one to see it will clear it.
- * If this is a Local MCE, then no need to perform rendezvous.
- */
+ if (m.cpuvendor == X86_VENDOR_INTEL)
+ lmce = m.mcgstatus & MCG_STATUS_LMCES;
+
+ /*
+ * Go through all banks in exclusion of the other CPUs. This way we
+ * don't report duplicated events on shared banks because the first one
+ * to see it will clear it. If this is a Local MCE, then no need to
+ * perform rendezvous.
+ */
+ if (!lmce)
order = mce_start(&no_way_out);
- }
for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
m.addr = 0;
m.bank = i;
- m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+ m.status = mce_rdmsrl(msr_ops.status(i));
if ((m.status & MCI_STATUS_VAL) == 0)
continue;
}
/*
- * At insane "tolerant" levels we take no action. Otherwise
- * we only die if we have no other choice. For less serious
- * issues we try to recover, or limit damage to the current
- * process.
+ * If tolerant is at an insane level we drop requests to kill
+ * processes and continue even when there is no way out.
*/
- if (cfg->tolerant < 3) {
- if (no_way_out)
- mce_panic("Fatal machine check on current CPU", &m, msg);
- if (worst == MCE_AR_SEVERITY) {
- recover_paddr = m.addr;
- if (!(m.mcgstatus & MCG_STATUS_RIPV))
- flags |= MF_MUST_KILL;
- } else if (kill_it) {
- force_sig(SIGBUS, current);
- }
- }
+ if (cfg->tolerant == 3)
+ kill_it = 0;
+ else if (no_way_out)
+ mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst > 0)
mce_report_event(regs);
out:
sync_core();
- if (recover_paddr == ~0ull)
- goto done;
+ if (worst != MCE_AR_SEVERITY && !kill_it)
+ goto out_ist;
- pr_err("Uncorrected hardware memory error in user-access at %llx",
- recover_paddr);
- /*
- * We must call memory_failure() here even if the current process is
- * doomed. We still need to mark the page as poisoned and alert any
- * other users of the page.
- */
- ist_begin_non_atomic(regs);
- local_irq_enable();
- if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) {
- pr_err("Memory error not recovered");
- force_sig(SIGBUS, current);
+ /* Fault was in user mode and we need to take some action */
+ if ((m.cs & 3) == 3) {
+ ist_begin_non_atomic(regs);
+ local_irq_enable();
+
+ if (kill_it || do_memory_failure(&m))
+ force_sig(SIGBUS, current);
+ local_irq_disable();
+ ist_end_non_atomic();
+ } else {
+ if (!fixup_exception(regs, X86_TRAP_MC))
+ mce_panic("Failed kernel mode recovery", &m, NULL);
}
- local_irq_disable();
- ist_end_non_atomic();
-done:
+
+out_ist:
ist_exit(regs);
}
EXPORT_SYMBOL_GPL(do_machine_check);
enum mcp_flags m_fl = 0;
mce_banks_t all_banks;
u64 cap;
- int i;
if (!mca_cfg.bootlog)
m_fl = MCP_DONTLOG;
rdmsrl(MSR_IA32_MCG_CAP, cap);
if (cap & MCG_CTL_P)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+}
+
+static void __mcheck_cpu_init_clear_banks(void)
+{
+ int i;
for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
if (!b->init)
continue;
- wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
- wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+ wrmsrl(msr_ops.ctl(i), b->ctl);
+ wrmsrl(msr_ops.status(i), 0);
}
}
*/
clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
}
- if (c->x86 <= 17 && cfg->bootlog < 0) {
+ if (c->x86 < 17 && cfg->bootlog < 0) {
/*
* Lots of broken BIOS around that don't clear them
* by default and leave crap in there. Don't log:
if (c->x86 == 6 && c->x86_model == 45)
quirk_no_way_out = quirk_sandybridge_ifu;
+ /*
+ * MCG_CAP.MCG_SER_P is necessary but not sufficient to know
+ * whether this processor will actually generate recoverable
+ * machine checks. Check to see if this is an E7 model Xeon.
+ * We can't do a model number check because E5 and E7 use the
+ * same model number. E5 doesn't support recovery, E7 does.
+ */
+ if (mca_cfg.recovery || (mca_cfg.ser &&
+ !strncmp(c->x86_model_id,
+ "Intel(R) Xeon(R) CPU E7-", 24)))
+ set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY);
}
if (cfg->monarch_timeout < 0)
cfg->monarch_timeout = 0;
break;
case X86_VENDOR_AMD: {
- u32 ebx = cpuid_ebx(0x80000007);
+ 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);
- mce_flags.overflow_recov = !!(ebx & BIT(0));
- mce_flags.succor = !!(ebx & BIT(1));
- mce_flags.smca = !!(ebx & BIT(3));
break;
}
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
+ __mcheck_cpu_init_clear_banks();
__mcheck_cpu_init_timer();
}
cfg->bootlog = (str[0] == 'b');
else if (!strcmp(str, "bios_cmci_threshold"))
cfg->bios_cmci_threshold = true;
+ else if (!strcmp(str, "recovery"))
+ cfg->recovery = true;
else if (isdigit(str[0])) {
if (get_option(&str, &cfg->tolerant) == 2)
get_option(&str, &(cfg->monarch_timeout));
struct mce_bank *b = &mce_banks[i];
if (b->init)
- wrmsrl(MSR_IA32_MCx_CTL(i), 0);
+ wrmsrl(msr_ops.ctl(i), 0);
}
return;
}
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
+ __mcheck_cpu_init_clear_banks();
}
static struct syscore_ops mce_syscore_ops = {
if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
+ __mcheck_cpu_init_clear_banks();
__mcheck_cpu_init_timer();
}
struct mce_bank *b = &mce_banks[i];
if (b->init)
- wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
+ wrmsrl(msr_ops.ctl(i), b->ctl);
}
}