x86/mce: Detect local MCEs properly

Check the MCG_STATUS_LMCES bit on Intel to verify that current MCE is
local. It is always local on AMD.

Signed-off-by: Yazen Ghannam <[email protected]>
[ Massaged it a bit. Reflowed comments. Shut up -Wmaybe-uninitialized. ]
Signed-off-by: Borislav Petkov <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Brian Gerst <[email protected]>
Cc: Denys Vlasenko <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: linux-edac <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

1 files changed, 20 insertions, 13 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index c356f47894c9..aeda44684758 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1038,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int i;
 	int worst = 0;
 	int severity;
+
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
-	int order;
+	int order = -1;
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
@@ -1056,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
-	int lmce = 0;
+
+	/*
+	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
+	 * on Intel.
+	 */
+	int lmce = 1;
 
 	/* If this CPU is offline, just bail out. */
 	if (cpu_is_offline(smp_processor_id())) {
@@ -1095,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Check if this MCE is signaled to only this logical processor
+	 * Check if this MCE is signaled to only this logical processor,
+	 * on Intel only.
 	 */
-	if (m.mcgstatus & MCG_STATUS_LMCES)
-		lmce = 1;
-	else {
-		/*
-		 * Go through all the banks in exclusion of the other CPUs.
-		 * This way we don't report duplicated events on shared banks
-		 * because the first one to see it will clear it.
-		 * If this is a Local MCE, then no need to perform rendezvous.
-		 */
+	if (m.cpuvendor == X86_VENDOR_INTEL)
+		lmce = m.mcgstatus & MCG_STATUS_LMCES;
+
+	/*
+	 * Go through all banks in exclusion of the other CPUs. This way we
+	 * don't report duplicated events on shared banks because the first one
+	 * to see it will clear it. If this is a Local MCE, then no need to
+	 * perform rendezvous.
+	 */
+	if (!lmce)
 		order = mce_start(&no_way_out);
-	}
 
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);