Commit aa83aa40 authored by Dave Jones's avatar Dave Jones Committed by Linus Torvalds

[PATCH] single bit flip detector

In cases where we detect a single bit has been flipped, we spew the usual
slab corruption message, which users instantly think is a kernel bug.  In a
lot of cases, single bit errors are down to bad memory, or other hardware
failure.

This patch adds an extra line to the slab debug messages in those cases, in
the hope that users will try memtest before they report a bug.

000: 6b 6b 6b 6b 6a 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b
Single bit error detected. Possibly bad RAM. Run memtest86.

[akpm@osdl.org: cleanups]
Signed-off-by: default avatarDave Jones <davej@redhat.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent 527063ba
...@@ -1683,10 +1683,32 @@ static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) ...@@ -1683,10 +1683,32 @@ static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
static void dump_line(char *data, int offset, int limit) static void dump_line(char *data, int offset, int limit)
{ {
int i; int i;
unsigned char error = 0;
int bad_count = 0;
printk(KERN_ERR "%03x:", offset); printk(KERN_ERR "%03x:", offset);
for (i = 0; i < limit; i++) for (i = 0; i < limit; i++) {
if (data[offset + i] != POISON_FREE) {
error = data[offset + i];
bad_count++;
}
printk(" %02x", (unsigned char)data[offset + i]); printk(" %02x", (unsigned char)data[offset + i]);
}
printk("\n"); printk("\n");
if (bad_count == 1) {
error ^= POISON_FREE;
if (!(error & (error - 1))) {
printk(KERN_ERR "Single bit error detected. Probably "
"bad RAM.\n");
#ifdef CONFIG_X86
printk(KERN_ERR "Run memtest86+ or a similar memory "
"test tool.\n");
#else
printk(KERN_ERR "Run a memory test tool.\n");
#endif
}
}
} }
#endif #endif
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment