summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAndi Kleen <andi@firstfloor.org>2009-05-27 21:56:55 +0200
committerH. Peter Anvin <hpa@zytor.com>2009-06-03 14:45:12 -0700
commitf94b61c2c9fdcc90773c49df9ccf9ede3ad0d7db (patch)
treee928c8a6b254b288076cd7f552cb7fb361b18d41
parentccc3c3192ae78dd56dcdf5353fd1a9ef5f9a3e2b (diff)
downloadop-kernel-dev-f94b61c2c9fdcc90773c49df9ccf9ede3ad0d7db.zip
op-kernel-dev-f94b61c2c9fdcc90773c49df9ccf9ede3ad0d7db.tar.gz
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>
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c22
1 files changed, 22 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 1217816..421020f 100644
--- 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 */
OpenPOWER on IntegriCloud