summaryrefslogtreecommitdiff
path: root/drivers/md/dm.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-02-21 23:11:41 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2017-02-21 23:11:41 +0300
commit7a771ceac771d009f7203c40b256b0608d7ea2f8 (patch)
tree940260bccb165f47669397515c00900629c01803 /drivers/md/dm.c
parente67bd12d6036ae3de9eeb0ba52e43691264ec850 (diff)
parentd67a5f4b5947aba4bfe9a80a2b86079c215ca755 (diff)
downloadlinux-7a771ceac771d009f7203c40b256b0608d7ea2f8.tar.xz
Merge tag 'dm-4.11-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper updates from Mike Snitzer: - Fix dm-raid transient device failure processing and other smaller tweaks. - Add journal support to the DM raid target to close the 'write hole' on raid 4/5/6. - Fix dm-cache corruption, due to rounding bug, when cache exceeds 2TB. - Add 'metadata2' feature to dm-cache to separate the dirty bitset out from other cache metadata. This improves speed of shutting down a large cache device (which implies writing out dirty bits). - Fix a memory leak during dm-stats data structure destruction. - Fix a DM multipath round-robin path selector performance regression that was caused by less precise balancing across all paths. - Lastly, introduce a DM core fix for a long-standing DM snapshot deadlock that is rooted in the complexity of the device stack used in conjunction with block core maintaining bios on current->bio_list to manage recursion in generic_make_request(). A more comprehensive fix to block core (and its hook in the cpu scheduler) would be wonderful but this DM-specific fix is pragmatic considering how difficult it has been to make progress on a generic fix. * tag 'dm-4.11-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (22 commits) dm: flush queued bios when process blocks to avoid deadlock dm round robin: revert "use percpu 'repeat_count' and 'current_path'" dm stats: fix a leaked s->histogram_boundaries array dm space map metadata: constify dm_space_map structures dm cache metadata: use cursor api in blocks_are_clean_separate_dirty() dm persistent data: add cursor skip functions to the cursor APIs dm cache metadata: use dm_bitset_new() to create the dirty bitset in format 2 dm bitset: add dm_bitset_new() dm cache metadata: name the cache block that couldn't be loaded dm cache metadata: add "metadata2" feature dm cache metadata: use bitset cursor api to load discard bitset dm bitset: introduce cursor api dm btree: use GFP_NOFS in dm_btree_del() dm space map common: memcpy the disk root to ensure it's arch aligned dm block manager: add unlikely() annotations on dm_bufio error paths dm cache: fix corruption seen when using cache > 2TB dm raid: cleanup awkward branching in raid_message() option processing dm raid: use mddev rather than rdev->mddev dm raid: use read_disk_sb() throughout dm raid: add raid4/5/6 journaling support ...
Diffstat (limited to 'drivers/md/dm.c')
-rw-r--r--drivers/md/dm.c55
1 files changed, 55 insertions, 0 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5bd9ab06a562..9f37d7fc2786 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -974,10 +974,61 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
}
EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
+/*
+ * Flush current->bio_list when the target map method blocks.
+ * This fixes deadlocks in snapshot and possibly in other targets.
+ */
+struct dm_offload {
+ struct blk_plug plug;
+ struct blk_plug_cb cb;
+};
+
+static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct dm_offload *o = container_of(cb, struct dm_offload, cb);
+ struct bio_list list;
+ struct bio *bio;
+
+ INIT_LIST_HEAD(&o->cb.list);
+
+ if (unlikely(!current->bio_list))
+ return;
+
+ list = *current->bio_list;
+ bio_list_init(current->bio_list);
+
+ while ((bio = bio_list_pop(&list))) {
+ struct bio_set *bs = bio->bi_pool;
+ if (unlikely(!bs) || bs == fs_bio_set) {
+ bio_list_add(current->bio_list, bio);
+ continue;
+ }
+
+ spin_lock(&bs->rescue_lock);
+ bio_list_add(&bs->rescue_list, bio);
+ queue_work(bs->rescue_workqueue, &bs->rescue_work);
+ spin_unlock(&bs->rescue_lock);
+ }
+}
+
+static void dm_offload_start(struct dm_offload *o)
+{
+ blk_start_plug(&o->plug);
+ o->cb.callback = flush_current_bio_list;
+ list_add(&o->cb.list, &current->plug->cb_list);
+}
+
+static void dm_offload_end(struct dm_offload *o)
+{
+ list_del(&o->cb.list);
+ blk_finish_plug(&o->plug);
+}
+
static void __map_bio(struct dm_target_io *tio)
{
int r;
sector_t sector;
+ struct dm_offload o;
struct bio *clone = &tio->clone;
struct dm_target *ti = tio->ti;
@@ -990,7 +1041,11 @@ static void __map_bio(struct dm_target_io *tio)
*/
atomic_inc(&tio->io->io_count);
sector = clone->bi_iter.bi_sector;
+
+ dm_offload_start(&o);
r = ti->type->map(ti, clone);
+ dm_offload_end(&o);
+
if (r == DM_MAPIO_REMAPPED) {
/* the bio has been remapped so dispatch it */