[PATCH] x86-64: Remove code to resume machine check state of other CPUs.

[pandora-kernel.git] / arch / x86_64 / kernel / mce.c

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 8aa5673..969365c 100644 (file)
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -17,6 +17,7 @@
 #include <linux/fs.h>
 #include <linux/cpu.h>
 #include <linux/percpu.h>
+#include <linux/ctype.h>
 #include <asm/processor.h> 
 #include <asm/msr.h>
 #include <asm/mce.h>
@@ -56,15 +57,19 @@ void mce_log(struct mce *mce)
        smp_wmb();
        for (;;) {
                entry = rcu_dereference(mcelog.next);
-               /* When the buffer fills up discard new entries. Assume 
-                  that the earlier errors are the more interesting. */
-               if (entry >= MCE_LOG_LEN) {
-                       set_bit(MCE_OVERFLOW, &mcelog.flags);
-                       return;
+               for (;;) {
+                       /* When the buffer fills up discard new entries. Assume
+                          that the earlier errors are the more interesting. */
+                       if (entry >= MCE_LOG_LEN) {
+                               set_bit(MCE_OVERFLOW, &mcelog.flags);
+                               return;
+                       }
+                       /* Old left over entry. Skip. */
+                       if (mcelog.entry[entry].finished) {
+                               entry++;
+                               continue;
+                       }
                }
-               /* Old left over entry. Skip. */
-               if (mcelog.entry[entry].finished)
-                       continue;
                smp_rmb();
                next = entry + 1;
                if (cmpxchg(&mcelog.next, entry, next) == entry)
@@ -404,9 +409,15 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff
        }
 
        err = 0;
-       for (i = 0; i < next; i++) {
-               if (!mcelog.entry[i].finished)
-                       continue;
+       for (i = 0; i < next; i++) {            
+               unsigned long start = jiffies;
+               while (!mcelog.entry[i].finished) {
+                       if (!time_before(jiffies, start + 2)) {
+                               memset(mcelog.entry + i,0, sizeof(struct mce));
+                               continue;
+                       }
+                       cpu_relax();
+               }
                smp_rmb();
                err |= copy_to_user(buf, mcelog.entry + i, sizeof(struct mce));
                buf += sizeof(struct mce); 
@@ -479,6 +490,7 @@ 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.  */
 static int __init mcheck_enable(char *str)
@@ -489,6 +501,8 @@ static int __init mcheck_enable(char *str)
                mce_dont_init = 1;
        else if (!strcmp(str, "bootlog"))
                mce_bootlog = 1;
+       else if (isdigit(str[0]))
+               get_option(&str, &tolerant);
        else
                printk("mce= argument %s ignored. Please use /sys", str); 
        return 0;
@@ -501,10 +515,12 @@ __setup("mce", mcheck_enable);
  * Sysfs support
  */ 
 
-/* On resume clear all MCE state. Don't want to see leftovers from the BIOS. */
+/* On resume clear all MCE state. Don't want to see leftovers from the BIOS.
+   Only one CPU is active at this time, the others get readded later using
+   CPU hotplug. */
 static int mce_resume(struct sys_device *dev)
 {
-       on_each_cpu(mce_init, NULL, 1, 1);
+       mce_init(NULL);
        return 0;
 }