dm: implement REQ_FLUSH/FUA support for bio-based dm
This patch converts bio-based dm to support REQ_FLUSH/FUA instead of
now deprecated REQ_HARDBARRIER.
* -EOPNOTSUPP handling logic dropped.
* Preflush is handled as before but postflush is dropped and replaced
with passing down REQ_FUA to member request_queues. This replaces
one array wide cache flush w/ member specific FUA writes.
* __split_and_process_bio() now calls __clone_and_map_flush() directly
for flushes and guarantees all FLUSH bio's going to targets are zero
` length.
* It's now guaranteed that all FLUSH bio's which are passed onto dm
targets are zero length. bio_empty_barrier() tests are replaced
with REQ_FLUSH tests.
* Empty WRITE_BARRIERs are replaced with WRITE_FLUSHes.
* Dropped unlikely() around REQ_FLUSH tests. Flushes are not unlikely
enough to be marked with unlikely().
* Block layer now filters out REQ_FLUSH/FUA bio's if the request_queue
doesn't support cache flushing. Advertise REQ_FLUSH | REQ_FUA
capability.
* Request based dm isn't converted yet. dm_init_request_based_queue()
resets flush support to 0 for now. To avoid disturbing request
based dm code, dm->flush_error is added for bio based dm while
requested based dm continues to use dm->barrier_error.
Lightly tested linear, stripe, raid1, snap and crypt targets. Please
proceed with caution as I'm not familiar with the code base.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: dm-devel@redhat.com
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 0590c75..136d4f7 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -31,7 +31,6 @@
*/
struct io {
unsigned long error_bits;
- unsigned long eopnotsupp_bits;
atomic_t count;
struct task_struct *sleeper;
struct dm_io_client *client;
@@ -130,11 +129,8 @@
*---------------------------------------------------------------*/
static void dec_count(struct io *io, unsigned int region, int error)
{
- if (error) {
+ if (error)
set_bit(region, &io->error_bits);
- if (error == -EOPNOTSUPP)
- set_bit(region, &io->eopnotsupp_bits);
- }
if (atomic_dec_and_test(&io->count)) {
if (io->sleeper)
@@ -310,8 +306,8 @@
sector_t remaining = where->count;
/*
- * where->count may be zero if rw holds a write barrier and we
- * need to send a zero-sized barrier.
+ * where->count may be zero if rw holds a flush and we need to
+ * send a zero-sized flush.
*/
do {
/*
@@ -364,7 +360,7 @@
*/
for (i = 0; i < num_regions; i++) {
*dp = old_pages;
- if (where[i].count || (rw & REQ_HARDBARRIER))
+ if (where[i].count || (rw & REQ_FLUSH))
do_region(rw, i, where + i, dp, io);
}
@@ -393,9 +389,7 @@
return -EIO;
}
-retry:
io->error_bits = 0;
- io->eopnotsupp_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->sleeper = current;
io->client = client;
@@ -412,11 +406,6 @@
}
set_current_state(TASK_RUNNING);
- if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) {
- rw &= ~REQ_HARDBARRIER;
- goto retry;
- }
-
if (error_bits)
*error_bits = io->error_bits;
@@ -437,7 +426,6 @@
io = mempool_alloc(client->pool, GFP_NOIO);
io->error_bits = 0;
- io->eopnotsupp_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->sleeper = NULL;
io->client = client;