[PATCH] x86-64: suppress mce boot log on Fam 10 and 11

[PATCH] x86-64: suppress mce boot log on Fam 10 and 11

[Jan Beulich]

At least on my Barcelona, I see MCE log entries after cold boot caused
by BIOS not properly clearing the respective registers. Therefore, this
patch extends the workaround to families 0x10 and 0x11 (the latter just
for completeness, I have nothing to verify this against).
At the same time, provide a way to make these entries visible via the
'mce=bootlog' command line option even on these machines.

Signed-off-by: Jan Beulich <jbeulich@novell.com>

 arch/x86/kernel/cpu/mcheck/mce_64.c |   20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

--- linux-2.6.24-rc4/arch/x86/kernel/cpu/mcheck/mce_64.c	2007-12-10 16:11:18.000000000 +0100
+++ 2.6.24-rc4-x86_64-amd-fam10-mce-clear/arch/x86/kernel/cpu/mcheck/mce_64.c	2007-12-04 16:09:33.000000000 +0100
@@ -49,7 +49,7 @@ static int banks;
 static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
 static unsigned long notify_user;
 static int rip_msr;
-static int mce_bootlog = 1;
+static int mce_bootlog = -1;
 static atomic_t mce_events;
 
 static char trigger[128];
@@ -63,7 +63,7 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait)
  * separate MCEs from kernel messages to avoid bogus bug reports.
  */
 
-struct mce_log mcelog = {
+static struct mce_log mcelog = {
 	MCE_LOG_SIGNATURE,
 	MCE_LOG_LEN,
 };
@@ -471,13 +471,15 @@ static void mce_init(void *dummy)
 static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
 {
 	/* This should be disabled by the BIOS, but isn't always */
-	if (c->x86_vendor == X86_VENDOR_AMD && c->x86 == 15) {
-		/* disable GART TBL walk error reporting, which trips off
-		   incorrectly with the IOMMU & 3ware & Cerberus. */
-		clear_bit(10, &bank[4]);
-		/* Lots of broken BIOS around that don't clear them
-		   by default and leave crap in there. Don't log. */
-		mce_bootlog = 0;
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if(c->x86 == 15)
+			/* disable GART TBL walk error reporting, which trips off
+			   incorrectly with the IOMMU & 3ware & Cerberus. */
+			clear_bit(10, &bank[4]);
+		if(c->x86 <= 17 && mce_bootlog < 0)
+			/* Lots of broken BIOS around that don't clear them
+			   by default and leave crap in there. Don't log. */
+			mce_bootlog = 0;
 	}
 
 }