raid5: fix unending write sequence
<debug output from Joel's system>
handling stripe 7629696, state=0x14 cnt=1, pd_idx=2 ops=0:0:0
check 5: state 0x6 toread 0000000000000000 read 0000000000000000 write fffff800ffcffcc0 written 0000000000000000
check 4: state 0x6 toread 0000000000000000 read 0000000000000000 write fffff800fdd4e360 written 0000000000000000
check 3: state 0x1 toread 0000000000000000 read 0000000000000000 write 0000000000000000 written 0000000000000000
check 2: state 0x1 toread 0000000000000000 read 0000000000000000 write 0000000000000000 written 0000000000000000
check 1: state 0x6 toread 0000000000000000 read 0000000000000000 write fffff800ff517e40 written 0000000000000000
check 0: state 0x6 toread 0000000000000000 read 0000000000000000 write fffff800fd4cae60 written 0000000000000000
locked=4 uptodate=2 to_read=0 to_write=4 failed=0 failed_num=0
for sector 7629696, rmw=0 rcw=0
</debug>
These blocks were prepared to be written out, but were never handled in
ops_run_biodrain(), so they remain locked forever. The operations flags
are all clear which means handle_stripe() thinks nothing else needs to be
done.
This state suggests that the STRIPE_OP_PREXOR bit was sampled 'set' when it
should not have been. This patch cleans up cases where the code looks at
sh->ops.pending when it should be looking at the consistent stack-based
snapshot of the operations flags.
Report from Joel:
Resync done. Patch fix this bug.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Joel Bertrand <joel.bertrand@systella.fr>
Cc: <stable@kernel.org>
Cc: Neil Brown <neilb@suse.de>
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 1cfc984..a5aad8c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -688,7 +688,8 @@
}
static struct dma_async_tx_descriptor *
-ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
+ unsigned long pending)
{
int disks = sh->disks;
int pd_idx = sh->pd_idx, i;
@@ -696,7 +697,7 @@
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (Wantprexor)
*/
- int prexor = test_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
+ int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
@@ -773,7 +774,8 @@
}
static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
+ unsigned long pending)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
@@ -781,7 +783,7 @@
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
- int prexor = test_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
+ int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
unsigned long flags;
dma_async_tx_callback callback;
@@ -808,7 +810,7 @@
}
/* check whether this postxor is part of a write */
- callback = test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending) ?
+ callback = test_bit(STRIPE_OP_BIODRAIN, &pending) ?
ops_complete_write : ops_complete_postxor;
/* 1/ if we prexor'd then the dest is reused as a source
@@ -896,12 +898,12 @@
tx = ops_run_prexor(sh, tx);
if (test_bit(STRIPE_OP_BIODRAIN, &pending)) {
- tx = ops_run_biodrain(sh, tx);
+ tx = ops_run_biodrain(sh, tx, pending);
overlap_clear++;
}
if (test_bit(STRIPE_OP_POSTXOR, &pending))
- ops_run_postxor(sh, tx);
+ ops_run_postxor(sh, tx, pending);
if (test_bit(STRIPE_OP_CHECK, &pending))
ops_run_check(sh);