From 4921487cb0a15e3fb28bc0b2410890f8fe7b161e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 26 Oct 2011 10:31:04 +1100 Subject: md/raid5: fix bug that could result in reads from a failed device. commit 355840e7a7e56bb2834fd3b0da64da5465f8aeaa upstream. This bug was introduced in 415e72d034c50520ddb7ff79e7d1792c1306f0c9 which was in 2.6.36. There is a small window of time between when a device fails and when it is removed from the array. During this time we might still read from it, but we won't write to it - so it is possible that we could read stale data. We didn't need the test of 'Faulty' before because the test on In_sync is sufficient. Since we started allowing reads from the early part of non-In_sync devices we need a test on Faulty too. This is suitable for any kernel from 2.6.36 onwards, though the patch might need a bit of tweaking in 3.0 and earlier. Signed-off-by: NeilBrown Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ac5e8b57e50f..f40448874a65 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3069,7 +3069,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) } } else if (test_bit(In_sync, &rdev->flags)) set_bit(R5_Insync, &dev->flags); - else { + else if (!test_bit(Faulty, &rdev->flags)) { /* in sync if before recovery_offset */ if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) set_bit(R5_Insync, &dev->flags); -- cgit v1.2.3