x86, mce: implement panic synchronization

In some circumstances multiple CPUs can enter mce_panic() in parallel.
This gives quite confused output because they will all dump the same
machine check buffer.

The other problem is that they would all panic in parallel, but not
process each other's shutdown IPIs because interrupts are disabled.

Detect this situation early on in mce_panic(). On the first CPU
entering will do the panic, the others will just wait to be killed.

For paranoia reasons in case the other CPU dies during the MCE I added
a 5 seconds timeout. If it expires each CPU will panic on its own again.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 1217816278584ef06e5aab3787b5a5c1f6448be2..421020f1d7db34b9fd4688a402cb5ebc292cb9a3 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -196,10 +196,32 @@ static void print_mce(struct mce *m)
               "and contact your hardware vendor\n");
 }
 
+#define PANIC_TIMEOUT 5 /* 5 seconds */
+
+static atomic_t mce_paniced;
+
+/* Panic in progress. Enable interrupts and wait for final IPI */
+static void wait_for_panic(void)
+{
+       long timeout = PANIC_TIMEOUT*USEC_PER_SEC;
+       preempt_disable();
+       local_irq_enable();
+       while (timeout-- > 0)
+               udelay(1);
+       panic("Panicing machine check CPU died");
+}
+
 static void mce_panic(char *msg, struct mce *final, char *exp)
 {
        int i;
 
+       /*
+        * Make sure only one CPU runs in machine check panic
+        */
+       if (atomic_add_return(1, &mce_paniced) > 1)
+               wait_for_panic();
+       barrier();
+
        bust_spinlocks(1);
        console_verbose();
        /* First print corrected ones that are still unlogged */