raid5: fix clearing of biofill operations From: Dan Williams ops_complete_biofill() runs outside of spin_lock(&sh->lock) and clears the 'pending' and 'ack' bits. Since the test_and_ack_op() macro only checks against 'complete' it can get an inconsistent snapshot of pending work. Move the clearing of these bits to handle_stripe5(), under the lock. Signed-off-by: Dan Williams Tested-by: Joel Bertrand Signed-off-by: Neil Brown --- drivers/md/raid5.c | 17 ++++++++++++++--- 1 files changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f96dea9..3808f52 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -377,7 +377,12 @@ static unsigned long get_stripe_work(struct stripe_head *sh) ack++; sh->ops.count -= ack; - BUG_ON(sh->ops.count < 0); + if (unlikely(sh->ops.count < 0)) { + printk(KERN_ERR "pending: %#lx ops.pending: %#lx ops.ack: %#lx " + "ops.complete: %#lx\n", pending, sh->ops.pending, + sh->ops.ack, sh->ops.complete); + BUG(); + } return pending; } @@ -551,8 +556,7 @@ static void ops_complete_biofill(void *stripe_head_ref) } } } - clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack); - clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending); + set_bit(STRIPE_OP_BIOFILL, &sh->ops.complete); return_io(return_bi); @@ -2630,6 +2634,13 @@ static void handle_stripe5(struct stripe_head *sh) s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); /* Now to look around and see what can be done */ + /* clean-up completed biofill operations */ + if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) { + clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending); + clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack); + clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete); + } + rcu_read_lock(); for (i=disks; i--; ) { mdk_rdev_t *rdev;