From 2099b145d77c1d53f5711f029c37cc537897cee6 Mon Sep 17 00:00:00 2001 From: Nikos Tsironis Date: Fri, 22 Jan 2021 17:19:31 +0200 Subject: dm era: Update in-core bitset after committing the metadata In case of a system crash, dm-era might fail to mark blocks as written in its metadata, although the corresponding writes to these blocks were passed down to the origin device and completed successfully. Consider the following sequence of events: 1. We write to a block that has not been yet written in the current era 2. era_map() checks the in-core bitmap for the current era and sees that the block is not marked as written. 3. The write is deferred for submission after the metadata have been updated and committed. 4. The worker thread processes the deferred write (process_deferred_bios()) and marks the block as written in the in-core bitmap, **before** committing the metadata. 5. The worker thread starts committing the metadata. 6. We do more writes that map to the same block as the write of step (1) 7. era_map() checks the in-core bitmap and sees that the block is marked as written, **although the metadata have not been committed yet**. 8. These writes are passed down to the origin device immediately and the device reports them as completed. 9. The system crashes, e.g., power failure, before the commit from step (5) finishes. When the system recovers and we query the dm-era target for the list of written blocks it doesn't report the aforementioned block as written, although the writes of step (6) completed successfully. The issue is that era_map() decides whether to defer or not a write based on non committed information. The root cause of the bug is that we update the in-core bitmap, **before** committing the metadata. Fix this by updating the in-core bitmap **after** successfully committing the metadata. Fixes: eec40579d84873 ("dm: add era target") Cc: stable@vger.kernel.org # v3.15+ Signed-off-by: Nikos Tsironis Signed-off-by: Mike Snitzer --- drivers/md/dm-era-target.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 854b1be8b452..62f679faf9e7 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -134,7 +134,7 @@ static int writeset_test_and_set(struct dm_disk_bitset *info, { int r; - if (!test_and_set_bit(block, ws->bits)) { + if (!test_bit(block, ws->bits)) { r = dm_bitset_set_bit(info, ws->md.root, block, &ws->md.root); if (r) { /* FIXME: fail mode */ @@ -1226,8 +1226,10 @@ static void process_deferred_bios(struct era *era) int r; struct bio_list deferred_bios, marked_bios; struct bio *bio; + struct blk_plug plug; bool commit_needed = false; bool failed = false; + struct writeset *ws = era->md->current_writeset; bio_list_init(&deferred_bios); bio_list_init(&marked_bios); @@ -1237,9 +1239,11 @@ static void process_deferred_bios(struct era *era) bio_list_init(&era->deferred_bios); spin_unlock(&era->deferred_lock); + if (bio_list_empty(&deferred_bios)) + return; + while ((bio = bio_list_pop(&deferred_bios))) { - r = writeset_test_and_set(&era->md->bitset_info, - era->md->current_writeset, + r = writeset_test_and_set(&era->md->bitset_info, ws, get_block(era, bio)); if (r < 0) { /* @@ -1247,7 +1251,6 @@ static void process_deferred_bios(struct era *era) * FIXME: finish. */ failed = true; - } else if (r == 0) commit_needed = true; @@ -1263,9 +1266,19 @@ static void process_deferred_bios(struct era *era) if (failed) while ((bio = bio_list_pop(&marked_bios))) bio_io_error(bio); - else - while ((bio = bio_list_pop(&marked_bios))) + else { + blk_start_plug(&plug); + while ((bio = bio_list_pop(&marked_bios))) { + /* + * Only update the in-core writeset if the on-disk one + * was updated too. + */ + if (commit_needed) + set_bit(get_block(era, bio), ws->bits); submit_bio_noacct(bio); + } + blk_finish_plug(&plug); + } } static void process_rpc_calls(struct era *era) -- cgit v1.2.3