#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/percpu.h>
+#include <linux/poll.h>
+#include <linux/thread_info.h>
#include <linux/ctype.h>
#include <linux/kmod.h>
#include <linux/kdebug.h>
#include <asm/mce.h>
#include <asm/uaccess.h>
#include <asm/smp.h>
+#include <asm/idle.h>
#define MISC_MCELOG_MINOR 227
#define NR_BANKS 6
static int tolerant = 1;
static int banks;
static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
-static unsigned long console_logged;
-static int notify_user;
+static unsigned long notify_user;
static int rip_msr;
static int mce_bootlog = 1;
static atomic_t mce_events;
static char trigger[128];
static char *trigger_argv[2] = { trigger, NULL };
+static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
+
/*
* Lockless MCE logging infrastructure.
* This avoids deadlocks on printk locks without having to break locks. Also
mcelog.entry[entry].finished = 1;
wmb();
- if (!test_and_set_bit(0, &console_logged))
- notify_user = 1;
+ set_bit(0, ¬ify_user);
}
static void print_mce(struct mce *m)
static void mce_panic(char *msg, struct mce *backup, unsigned long start)
{
int i;
+
+ if (tolerant >= 3)
+ return;
+
oops_begin();
for (i = 0; i < MCE_LOG_LEN; i++) {
unsigned long tsc = mcelog.entry[i].tsc;
}
if (backup)
print_mce(backup);
- if (tolerant >= 3)
- printk("Fake panic: %s\n", msg);
- else
- panic(msg);
+ panic(msg);
}
static int mce_available(struct cpuinfo_x86 *c)
}
}
-static void do_mce_trigger(void)
-{
- static atomic_t mce_logged;
- int events = atomic_read(&mce_events);
- if (events != atomic_read(&mce_logged) && trigger[0]) {
- /* Small race window, but should be harmless. */
- atomic_set(&mce_logged, events);
- call_usermodehelper(trigger, trigger_argv, NULL, UMH_NO_WAIT);
- }
-}
-
/*
* The actual machine check handler
*/
}
/* Never do anything final in the polling timer */
- if (!regs) {
- /* Normal interrupt context here. Call trigger for any new
- events. */
- do_mce_trigger();
+ if (!regs)
goto out;
- }
/* If we didn't find an uncorrectable error, pick
the last one (shouldn't happen, just being safe). */
do_exit(SIGBUS);
}
+ /* notify userspace ASAP */
+ set_thread_flag(TIF_MCE_NOTIFY);
+
out:
/* Last thing done in the machine check exception to clear state. */
wrmsrl(MSR_IA32_MCG_STATUS, 0);
on_each_cpu(mcheck_check_cpu, NULL, 1, 1);
/*
- * It's ok to read stale data here for notify_user and
- * console_logged as we'll simply get the updated versions
- * on the next mcheck_timer execution and atomic operations
- * on console_logged act as synchronization for notify_user
- * writes.
+ * Alert userspace if needed. If we logged an MCE, reduce the
+ * polling interval, otherwise increase the polling interval.
*/
- if (notify_user && console_logged) {
+ if (mce_notify_user()) {
+ next_interval = max(next_interval/2, HZ/100);
+ } else {
+ next_interval = min(next_interval*2, check_interval*HZ);
+ }
+
+ schedule_delayed_work(&mcheck_work, next_interval);
+}
+
+/*
+ * This is only called from process context. This is where we do
+ * anything we need to alert userspace about new MCEs. This is called
+ * directly from the poller and also from entry.S and idle, thanks to
+ * TIF_MCE_NOTIFY.
+ */
+int mce_notify_user(void)
+{
+ clear_thread_flag(TIF_MCE_NOTIFY);
+ if (test_and_clear_bit(0, ¬ify_user)) {
static unsigned long last_print;
unsigned long now = jiffies;
- /* if we logged an MCE, reduce the polling interval */
- next_interval = max(next_interval/2, HZ/100);
- notify_user = 0;
- clear_bit(0, &console_logged);
+ wake_up_interruptible(&mce_wait);
+ if (trigger[0])
+ call_usermodehelper(trigger, trigger_argv, NULL,
+ UMH_NO_WAIT);
+
if (time_after_eq(now, last_print + (check_interval*HZ))) {
last_print = now;
printk(KERN_INFO "Machine check events logged\n");
}
- } else {
- next_interval = min(next_interval*2, check_interval*HZ);
+
+ return 1;
}
+ return 0;
+}
- schedule_delayed_work(&mcheck_work, next_interval);
+/* see if the idle task needs to notify userspace */
+static int
+mce_idle_callback(struct notifier_block *nfb, unsigned long action, void *junk)
+{
+ /* IDLE_END should be safe - interrupts are back on */
+ if (action == IDLE_END && test_thread_flag(TIF_MCE_NOTIFY))
+ mce_notify_user();
+
+ return NOTIFY_OK;
}
+static struct notifier_block mce_idle_notifier = {
+ .notifier_call = mce_idle_callback,
+};
static __init int periodic_mcheck_init(void)
{
next_interval = check_interval * HZ;
if (next_interval)
schedule_delayed_work(&mcheck_work, next_interval);
+ idle_notifier_register(&mce_idle_notifier);
return 0;
}
__initcall(periodic_mcheck_init);
return err ? -EFAULT : buf - ubuf;
}
+static unsigned int mce_poll(struct file *file, poll_table *wait)
+{
+ poll_wait(file, &mce_wait, wait);
+ if (rcu_dereference(mcelog.next))
+ return POLLIN | POLLRDNORM;
+ return 0;
+}
+
static int mce_ioctl(struct inode *i, struct file *f,unsigned int cmd, unsigned long arg)
{
int __user *p = (int __user *)arg;
.open = mce_open,
.release = mce_release,
.read = mce_read,
+ .poll = mce_poll,
.ioctl = mce_ioctl,
};
projects / openwrt / staging / blogic.git / commitdiff