[PATCH] x86_64: Don't run NMI watchdog during machine checks

Machine checks can stall the machine for a long time and
it's not good to trigger the nmi watchdog during that.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 21 insertions, 1 deletions

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 10b3e348fc9..6f0790e8b6d 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -29,6 +29,8 @@
 #define MISC_MCELOG_MINOR 227
 #define NR_BANKS 6
 
+atomic_t mce_entry;
+
 static int mce_dont_init;
 
 /* 0: always panic, 1: panic if deadlock possible, 2: try to avoid panic,
@@ -172,10 +174,12 @@ void do_machine_check(struct pt_regs * regs, long error_code)
         int i;
         int panicm_found = 0;
 
+        atomic_inc(&mce_entry);
+
         if (regs)
                 notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL);
         if (!banks)
-                return;
+                goto out2;
 
         memset(&m, 0, sizeof(struct mce));
         m.cpu = safe_smp_processor_id();
@@ -266,6 +270,8 @@ void do_machine_check(struct pt_regs * regs, long error_code)
  out:
         /* Last thing done in the machine check exception to clear state. */
         wrmsrl(MSR_IA32_MCG_STATUS, 0);
+ out2:
+        atomic_dec(&mce_entry);
 }
 
 /*
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index d9e4067faf0..4e6357fe0ec 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -34,6 +34,7 @@
 #include <asm/proto.h>
 #include <asm/kdebug.h>
 #include <asm/local.h>
+#include <asm/mce.h>
 
 /*
  * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
@@ -480,6 +481,12 @@ void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
                 __get_cpu_var(nmi_touch) = 0;
                 touched = 1;
         }
+#ifdef CONFIG_X86_MCE
+        /* Could check oops_in_progress here too, but it's safer
+           not too */
+        if (atomic_read(&mce_entry) > 0)
+                touched = 1;
+#endif
         if (!touched && __get_cpu_var(last_irq_sum) == sum) {
                 /*
                  * Ayiee, looks like this CPU is stuck ...
diff --git a/include/asm-x86_64/mce.h b/include/asm-x86_64/mce.h
index 5d298b799a9..7229785094e 100644
--- a/include/asm-x86_64/mce.h
+++ b/include/asm-x86_64/mce.h
@@ -70,6 +70,9 @@ struct mce_log {
 #define MCE_THRESHOLD_BASE      MCE_EXTENDED_BANK + 1 /* MCE_AMD */
 #define MCE_THRESHOLD_DRAM_ECC  MCE_THRESHOLD_BASE + 4
 
+#ifdef __KERNEL__
+#include <asm/atomic.h>
+
 void mce_log(struct mce *m);
 #ifdef CONFIG_X86_MCE_INTEL
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
@@ -87,4 +90,8 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)
 }
 #endif
 
+extern atomic_t mce_entry;
+
+#endif
+
 #endif