struct mce m;
int i;
- percpu_inc(mce_poll_count);
+ this_cpu_inc(mce_poll_count);
mce_gather_info(&m, NULL);
atomic_t inuse;
struct task_struct *t;
__u64 paddr;
+ int restartable;
} mce_info[MCE_INFO_MAX];
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
{
struct mce_info *mi;
if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
mi->t = current;
mi->paddr = addr;
+ mi->restartable = c;
return;
}
}
atomic_inc(&mce_entry);
- percpu_inc(mce_exception_count);
+ this_cpu_inc(mce_exception_count);
if (!banks)
goto out;
mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst == MCE_AR_SEVERITY) {
/* schedule action before return to userland */
- mce_save_info(m.addr);
+ mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
set_thread_flag(TIF_MCE_NOTIFY);
} else if (kill_it) {
force_sig(SIGBUS, current);
pr_err("Uncorrected hardware memory error in user-access at %llx",
mi->paddr);
- if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+ /*
+ * 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.
+ */
+ if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+ mi->restartable == 0) {
pr_err("Memory error not recovered");
force_sig(SIGBUS, current);
}
* poller finds an MCE, poll 2x faster. When the poller finds no more
* errors, poll 2x slower (up to check_interval seconds).
*/
- static int check_interval = 5 * 60; /* 5 minutes */
+ static unsigned long check_interval = 5 * 60; /* 5 minutes */
- static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
+ static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
- static void mce_start_timer(unsigned long data)
+ static void mce_timer_fn(unsigned long data)
{
- struct timer_list *t = &per_cpu(mce_timer, data);
- int *n;
+ struct timer_list *t = &__get_cpu_var(mce_timer);
+ unsigned long iv;
WARN_ON(smp_processor_id() != data);
* Alert userspace if needed. If we logged an MCE, reduce the
* polling interval, otherwise increase the polling interval.
*/
- n = &__get_cpu_var(mce_next_interval);
+ iv = __this_cpu_read(mce_next_interval);
if (mce_notify_irq())
- *n = max(*n/2, HZ/100);
+ iv = max(iv, (unsigned long) HZ/100);
else
- *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
+ iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
+ __this_cpu_write(mce_next_interval, iv);
- t->expires = jiffies + *n;
+ t->expires = jiffies + iv;
add_timer_on(t, smp_processor_id());
}
*/
if (c->x86 == 6 && banks > 0)
mce_banks[0].ctl = 0;
+
+ /*
+ * Turn off MC4_MISC thresholding banks on those models since
+ * they're not supported there.
+ */
+ if (c->x86 == 0x15 &&
+ (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) {
+ int i;
+ u64 val, hwcr;
+ bool need_toggle;
+ u32 msrs[] = {
+ 0x00000413, /* MC4_MISC0 */
+ 0xc0000408, /* MC4_MISC1 */
+ };
+
+ rdmsrl(MSR_K7_HWCR, hwcr);
+
+ /* McStatusWrEn has to be set */
+ need_toggle = !(hwcr & BIT(18));
+
+ if (need_toggle)
+ wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
+
+ for (i = 0; i < ARRAY_SIZE(msrs); i++) {
+ rdmsrl(msrs[i], val);
+
+ /* CntP bit set? */
+ if (val & BIT_64(62)) {
+ val &= ~BIT_64(62);
+ wrmsrl(msrs[i], val);
+ }
+ }
+
+ /* restore old settings */
+ if (need_toggle)
+ wrmsrl(MSR_K7_HWCR, hwcr);
+ }
}
if (c->x86_vendor == X86_VENDOR_INTEL) {
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- int *n = &__get_cpu_var(mce_next_interval);
+ unsigned long iv = __this_cpu_read(mce_next_interval);
- setup_timer(t, mce_start_timer, smp_processor_id());
+ setup_timer(t, mce_timer_fn, smp_processor_id());
if (mce_ignore_ce)
return;
- *n = check_interval * HZ;
- if (!*n)
+ __this_cpu_write(mce_next_interval, iv);
+ if (!iv)
return;
- t->expires = round_jiffies(jiffies + *n);
+ t->expires = round_jiffies(jiffies + iv);
add_timer_on(t, smp_processor_id());
}
case CPU_DOWN_FAILED_FROZEN:
if (!mce_ignore_ce && check_interval) {
t->expires = round_jiffies(jiffies +
- __get_cpu_var(mce_next_interval));
+ per_cpu(mce_next_interval, cpu));
add_timer_on(t, cpu);
}
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);