[PATCH] x86_64: ignore machine checks from boot time

Don't log machine check events left over from boot.  Too many BIOSes leave
bogus events in there.

This unfortunately also makes it impossible to log events that caused a
reboot.  For people with non broken BIOS there is mce=bootlog

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
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 476c0c2..678e8f1 100644 (file)
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86_64/boot-options.txt
@@ -6,6 +6,11 @@ only the AMD64 specific ones are listed here.
 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.
+               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.
 
    nomce (for compatibility with i386): same as mce=off
 

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 3b267c9..8aa5673 100644 (file)
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -36,6 +36,7 @@ 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;
 
 /*
  * Lockless MCE logging infrastructure.
@@ -197,10 +198,11 @@ void do_machine_check(struct pt_regs * regs, long error_code)
                        rdmsrl(MSR_IA32_MC0_ADDR + i*4, m.addr);
 
                mce_get_rip(&m, regs);
-               if (error_code != -1)
+               if (error_code >= 0)
                        rdtscll(m.tsc);
                wrmsrl(MSR_IA32_MC0_STATUS + i*4, 0);
-               mce_log(&m);
+               if (error_code != -2)
+                       mce_log(&m);
 
                /* Did this bank cause the exception? */
                /* Assume that the bank with uncorrectable errors did it,
@@ -315,7 +317,7 @@ static void mce_init(void *dummy)
 
        /* Log the machine checks left over from the previous reset.
           This also clears all registers */
-       do_machine_check(NULL, -1);
+       do_machine_check(NULL, mce_bootlog ? -1 : -2);
 
        set_in_cr4(X86_CR4_MCE);
 
@@ -476,11 +478,17 @@ static int __init mcheck_disable(char *str)
 }
 
 /* mce=off disables machine check. Note you can reenable it later
-   using sysfs */
+   using sysfs.
+   mce=bootlog Log MCEs from before booting. Disabled by default to work
+   around buggy BIOS that leave bogus MCEs.  */
 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
                printk("mce= argument %s ignored. Please use /sys", str); 
        return 0;