From d48300120627a1cb98914738fff38b424625b8ad Mon Sep 17 00:00:00 2001 From: Li Lingfeng Date: Mon, 5 Jun 2023 15:03:16 +0800 Subject: dm thin metadata: Fix ABBA deadlock by resetting dm_bufio_client As described in commit 8111964f1b85 ("dm thin: Fix ABBA deadlock between shrink_slab and dm_pool_abort_metadata"), ABBA deadlocks will be triggered because shrinker_rwsem currently needs to held by dm_pool_abort_metadata() as a side-effect of thin-pool metadata operation failure. The following three problem scenarios have been noticed: 1) Described by commit 8111964f1b85 ("dm thin: Fix ABBA deadlock between shrink_slab and dm_pool_abort_metadata") 2) shrinker_rwsem and throttle->lock P1(drop cache) P2(kworker) drop_caches_sysctl_handler drop_slab shrink_slab down_read(&shrinker_rwsem) - LOCK A do_shrink_slab super_cache_scan prune_icache_sb dispose_list evict ext4_evict_inode ext4_clear_inode ext4_discard_preallocations ext4_mb_load_buddy_gfp ext4_mb_init_cache ext4_wait_block_bitmap __ext4_error ext4_handle_error ext4_commit_super ... dm_submit_bio do_worker throttle_work_update down_write(&t->lock) -- LOCK B process_deferred_bios commit metadata_operation_failed dm_pool_abort_metadata dm_block_manager_create dm_bufio_client_create register_shrinker down_write(&shrinker_rwsem) -- LOCK A thin_map thin_bio_map thin_defer_bio_with_throttle throttle_lock down_read(&t->lock) - LOCK B 3) shrinker_rwsem and wait_on_buffer P1(drop cache) P2(kworker) drop_caches_sysctl_handler drop_slab shrink_slab down_read(&shrinker_rwsem) - LOCK A do_shrink_slab ... ext4_wait_block_bitmap __ext4_error ext4_handle_error jbd2_journal_abort jbd2_journal_update_sb_errno jbd2_write_superblock submit_bh // LOCK B // RELEASE B do_worker throttle_work_update down_write(&t->lock) - LOCK B process_deferred_bios process_bio commit metadata_operation_failed dm_pool_abort_metadata dm_block_manager_create dm_bufio_client_create register_shrinker register_shrinker_prepared down_write(&shrinker_rwsem) - LOCK A bio_endio wait_on_buffer __wait_on_buffer Fix these by resetting dm_bufio_client without holding shrinker_rwsem. Fixes: 8111964f1b85 ("dm thin: Fix ABBA deadlock between shrink_slab and dm_pool_abort_metadata") Cc: stable@vger.kernel.org Signed-off-by: Li Lingfeng Signed-off-by: Mike Snitzer --- drivers/md/dm-bufio.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers/md/dm-bufio.c') diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index eea977662e81..a7079b38756a 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -2592,6 +2592,13 @@ void dm_bufio_client_destroy(struct dm_bufio_client *c) } EXPORT_SYMBOL_GPL(dm_bufio_client_destroy); +void dm_bufio_client_reset(struct dm_bufio_client *c) +{ + drop_buffers(c); + flush_work(&c->shrink_work); +} +EXPORT_SYMBOL_GPL(dm_bufio_client_reset); + void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start) { c->start = start; -- cgit v1.2.3-73-gaa49b