[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: Dave Jones <davej@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 23 insertions, 1 deletions

diff --git a/mm/slab.c b/mm/slab.c
index 792bfe3..3dbd6f4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -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)
 {
 	int i;
+	unsigned char error = 0;
+	int bad_count = 0;
+
 	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("\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