[PATCH] x86_64: Log machine checks from boot on Intel systems

The logging for boot errors was turned off because it was broken
on some AMD systems. But give Intel EM64T systems a chance because they are
supposed to be correct there.

The advantage is that there is a chance to actually log uncorrected
machine checks after the reset.

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

diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt
index a831396..aaabb58 100644 (file)
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86_64/boot-options.txt
@@ -7,10 +7,12 @@ Machine check
 
    mce=off disable machine check
    mce=bootlog Enable logging of machine checks left over from booting.
-               Disabled by default because some BIOS leave bogus ones.
+               Disabled by default on AMD because some BIOS leave bogus ones.
                If your BIOS doesn't do that it's a good idea to enable though
                to make sure you log even machine check events that result
-               in a reboot.
+               in a reboot. On Intel systems it is enabled by default.
+   mce=nobootlog
+               Disable boot machine check logging.
    mce=tolerancelevel (number)
                0: always panic, 1: panic if deadlock possible,
                2: try to avoid panic, 3: never panic or exit (for testing)

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index cf8a76f..183dc61 100644 (file)
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -37,7 +37,7 @@ static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
 static unsigned long console_logged;
 static int notify_user;
 static int rip_msr;
-static int mce_bootlog;
+static int mce_bootlog = 1;
 
 /*
  * Lockless MCE logging infrastructure.
@@ -347,7 +347,11 @@ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
                /* 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;
        }
+
 }                      
 
 static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
@@ -498,16 +502,16 @@ static int __init mcheck_disable(char *str)
 /* mce=off disables machine check. Note you can reenable it later
    using sysfs.
    mce=TOLERANCELEVEL (number, see above)
-   mce=bootlog Log MCEs from before booting. Disabled by default to work
-   around buggy BIOS that leave bogus MCEs.  */
+   mce=bootlog Log MCEs from before booting. Disabled by default on AMD.
+   mce=nobootlog Don't log MCEs from before booting. */
 static int __init mcheck_enable(char *str)
 {
        if (*str == '=')
                str++;
        if (!strcmp(str, "off"))
                mce_dont_init = 1;
-       else if (!strcmp(str, "bootlog"))
-               mce_bootlog = 1;
+       else if (!strcmp(str, "bootlog") || !strcmp(str,"nobootlog"))
+               mce_bootlog = str[0] == 'b';
        else if (isdigit(str[0]))
                get_option(&str, &tolerant);
        else