md: raid5: fix clearing of biofill operations
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 <dan.j.williams@intel.com>
Tested-by: Joel Bertrand <joel.bertrand@systella.fr>
Signed-off-by: Neil Brown <neilb@suse.de>
Cc: Stable <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8ee181a..80a67d7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -376,7 +376,12 @@
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;
}
@@ -550,8 +555,7 @@
}
}
}
- 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);
@@ -2893,6 +2897,13 @@
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;