#include <linux/sched.h>
#include <linux/sysfs.h>
#include <linux/types.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/poll.h>
#include "mce-internal.h"
+static DEFINE_MUTEX(mce_read_mutex);
+
+#define rcu_dereference_check_mce(p) \
+ rcu_dereference_check((p), \
+ rcu_read_lock_sched_held() || \
+ lockdep_is_held(&mce_read_mutex))
+
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
mce->finished = 0;
wmb();
for (;;) {
- entry = rcu_dereference(mcelog.next);
+ entry = rcu_dereference_check_mce(mcelog.next);
for (;;) {
/*
* When the buffer fills up discard new entries.
static void mce_panic(char *msg, struct mce *final, char *exp)
{
- int i;
+ int i, apei_err = 0;
if (!fake_panic) {
/*
struct mce *m = &mcelog.entry[i];
if (!(m->status & MCI_STATUS_VAL))
continue;
- if (!(m->status & MCI_STATUS_UC))
+ if (!(m->status & MCI_STATUS_UC)) {
print_mce(m);
+ if (!apei_err)
+ apei_err = apei_write_mce(m);
+ }
}
/* Now print uncorrected but with the final one last */
for (i = 0; i < MCE_LOG_LEN; i++) {
continue;
if (!(m->status & MCI_STATUS_UC))
continue;
- if (!final || memcmp(m, final, sizeof(struct mce)))
+ if (!final || memcmp(m, final, sizeof(struct mce))) {
print_mce(m);
+ if (!apei_err)
+ apei_err = apei_write_mce(m);
+ }
}
- if (final)
+ if (final) {
print_mce(final);
+ if (!apei_err)
+ apei_err = apei_write_mce(final);
+ }
if (cpu_missing)
printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n");
print_mce_tail();
struct mce m;
int i;
- __get_cpu_var(mce_poll_count)++;
+ percpu_inc(mce_poll_count);
mce_setup(&m);
atomic_inc(&mce_entry);
- __get_cpu_var(mce_exception_count)++;
+ percpu_inc(mce_exception_count);
if (notify_die(DIE_NMI, "machine check", regs, error_code,
18, SIGKILL) == NOTIFY_STOP)
}
EXPORT_SYMBOL_GPL(mce_notify_irq);
-static int mce_banks_init(void)
+static int __cpuinit __mcheck_cpu_mce_banks_init(void)
{
int i;
WARN_ON(banks != 0 && b != banks);
banks = b;
if (!mce_banks) {
- int err = mce_banks_init();
+ int err = __mcheck_cpu_mce_banks_init();
if (err)
return err;
struct timer_list *t = &__get_cpu_var(mce_timer);
int *n = &__get_cpu_var(mce_next_interval);
+ setup_timer(t, mce_start_timer, smp_processor_id());
+
if (mce_ignore_ce)
return;
*n = check_interval * HZ;
if (!*n)
return;
- setup_timer(t, mce_start_timer, smp_processor_id());
t->expires = round_jiffies(jiffies + *n);
add_timer_on(t, smp_processor_id());
}
rdtscll(cpu_tsc[smp_processor_id()]);
}
-static DEFINE_MUTEX(mce_read_mutex);
+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;
+ 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_read(struct file *filp, char __user *ubuf, size_t usize,
loff_t *off)
return -ENOMEM;
mutex_lock(&mce_read_mutex);
- next = rcu_dereference(mcelog.next);
-
- /* Only supports full reads right now */
- if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
- mutex_unlock(&mce_read_mutex);
- kfree(cpu_tsc);
- return -EINVAL;
+ if (!mce_apei_read_done) {
+ err = __mce_read_apei(&buf, usize);
+ if (err || buf != ubuf)
+ goto out;
}
+ next = rcu_dereference_check_mce(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 {
memset(&mcelog.entry[i], 0, sizeof(struct mce));
}
}
+
+ if (err)
+ err = -EFAULT;
+
+out:
mutex_unlock(&mce_read_mutex);
kfree(cpu_tsc);
- return err ? -EFAULT : buf - ubuf;
+ return err ? err : buf - ubuf;
}
static unsigned int mce_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_wait, wait);
- if (rcu_dereference(mcelog.next))
+ if (rcu_dereference_check_mce(mcelog.next))
+ return POLLIN | POLLRDNORM;
+ if (!mce_apei_read_done && apei_check_mce())
return POLLIN | POLLRDNORM;
return 0;
}
sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[j].attr);
error:
while (--i >= 0)
- sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[i].attr);
+ sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]);
sysdev_unregister(&per_cpu(mce_dev, cpu));
}
/* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void __cpuinit mce_disable_cpu(void *h)
{
unsigned long action = *(unsigned long *)h;
int i;
if (!mce_available(¤t_cpu_data))
return;
+
if (!(action & CPU_TASKS_FROZEN))
cmci_clear();
for (i = 0; i < banks; i++) {
}
}
-static void mce_reenable_cpu(void *h)
+static void __cpuinit mce_reenable_cpu(void *h)
{
unsigned long action = *(unsigned long *)h;
int i;
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- t->expires = round_jiffies(jiffies +
+ if (!mce_ignore_ce && check_interval) {
+ t->expires = round_jiffies(jiffies +
__get_cpu_var(mce_next_interval));
- add_timer_on(t, cpu);
+ add_timer_on(t, cpu);
+ }
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break;
case CPU_POST_DEAD:
struct mce_bank *b = &mce_banks[i];
struct sysdev_attribute *a = &b->attr;
+ sysfs_attr_init(&a->attr);
a->attr.name = b->attrname;
snprintf(b->attrname, ATTR_LEN, "bank%d", i);