From c965d6402f24adcd3d4d0dd9b1f30a0578b6255c Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 28 Jul 2020 20:25:41 +0900 Subject: btrfs: handle errors from async submission Btrfs' async submit mechanism is able to handle errors in the submission path and the meta-data async submit function correctly passes the error code to the caller. In btrfs_submit_bio_start() and btrfs_submit_bio_start_direct_io() we're not handling the errors returned by btrfs_csum_one_bio() correctly though and simply call BUG_ON(). This is unnecessary as the caller of these two functions - run_one_async_start - correctly checks for the return values and sets the status of the async_submit_bio. The actual bio submission will be handled later on by run_one_async_done only if async_submit_bio::status is 0, so the data won't be written if we encountered an error in the checksum process. Simply return the error from btrfs_csum_one_bio() to the async submitters, like it's done in btree_submit_bio_start(). Reviewed-by: Josef Bacik Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 16ce82039dcf..4ad0323b3684 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2160,11 +2160,8 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio, u64 bio_offset) { struct inode *inode = private_data; - blk_status_t ret = 0; - ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); - BUG_ON(ret); /* -ENOMEM */ - return 0; + return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } /* @@ -7618,10 +7615,8 @@ static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data, struct bio *bio, u64 offset) { struct inode *inode = private_data; - blk_status_t ret; - ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1); - BUG_ON(ret); /* -ENOMEM */ - return 0; + + return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1); } static void btrfs_end_dio_bio(struct bio *bio) -- cgit v1.2.3 From 282dd7d7718444679b046b769d872b188818ca35 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Mon, 3 Aug 2020 16:55:01 -0300 Subject: btrfs: reset compression level for lzo on remount Currently a user can set mount "-o compress" which will set the compression algorithm to zlib, and use the default compress level for zlib (3): relatime,compress=zlib:3,space_cache If the user remounts the fs using "-o compress=lzo", then the old compress_level is used: relatime,compress=lzo:3,space_cache But lzo does not expose any tunable compression level. The same happens if we set any compress argument with different level, also with zstd. Fix this by resetting the compress_level when compress=lzo is specified. With the fix applied, lzo is shown without compress level: relatime,compress=lzo,space_cache CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Marcos Paulo de Souza Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/super.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/btrfs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index e529ddb35b87..25967ecaaf0a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -625,6 +625,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } else if (strncmp(args[0].from, "lzo", 3) == 0) { compress_type = "lzo"; info->compress_type = BTRFS_COMPRESS_LZO; + info->compress_level = 0; btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); -- cgit v1.2.3 From 604997b4a3803f33e70799b2696bd3dbfed7276c Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 27 Jul 2020 17:38:19 +0200 Subject: btrfs: use the correct const function attribute for btrfs_get_num_csums The build robot reports compiler: h8300-linux-gcc (GCC) 9.3.0 In file included from fs/btrfs/tests/extent-map-tests.c:8: >> fs/btrfs/tests/../ctree.h:2166:8: warning: type qualifiers ignored on function return type [-Wignored-qualifiers] 2166 | size_t __const btrfs_get_num_csums(void); | ^~~~~~~ The function attribute for const does not follow the expected scheme and in this case is confused with a const type qualifier. Reported-by: kernel test robot Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 2 +- fs/btrfs/ctree.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 70e49d8d4f6c..cd1cd673bc0b 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -68,7 +68,7 @@ const char *btrfs_super_csum_driver(u16 csum_type) btrfs_csums[csum_type].name; } -size_t __const btrfs_get_num_csums(void) +size_t __attribute_const__ btrfs_get_num_csums(void) { return ARRAY_SIZE(btrfs_csums); } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9c7e466f27a9..729b5b80014a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2262,7 +2262,7 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, int btrfs_super_csum_size(const struct btrfs_super_block *s); const char *btrfs_super_csum_name(u16 csum_type); const char *btrfs_super_csum_driver(u16 csum_type); -size_t __const btrfs_get_num_csums(void); +size_t __attribute_const__ btrfs_get_num_csums(void); /* -- cgit v1.2.3 From bbc37d6e475eee8ffa2156ec813efc6bbb43c06d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 14 Aug 2020 11:04:09 +0100 Subject: btrfs: fix space cache memory leak after transaction abort If a transaction aborts it can cause a memory leak of the pages array of a block group's io_ctl structure. The following steps explain how that can happen: 1) Transaction N is committing, currently in state TRANS_STATE_UNBLOCKED and it's about to start writing out dirty extent buffers; 2) Transaction N + 1 already started and another task, task A, just called btrfs_commit_transaction() on it; 3) Block group B was dirtied (extents allocated from it) by transaction N + 1, so when task A calls btrfs_start_dirty_block_groups(), at the very beginning of the transaction commit, it starts writeback for the block group's space cache by calling btrfs_write_out_cache(), which allocates the pages array for the block group's io_ctl with a call to io_ctl_init(). Block group A is added to the io_list of transaction N + 1 by btrfs_start_dirty_block_groups(); 4) While transaction N's commit is writing out the extent buffers, it gets an IO error and aborts transaction N, also setting the file system to RO mode; 5) Task A has already returned from btrfs_start_dirty_block_groups(), is at btrfs_commit_transaction() and has set transaction N + 1 state to TRANS_STATE_COMMIT_START. Immediately after that it checks that the filesystem was turned to RO mode, due to transaction N's abort, and jumps to the "cleanup_transaction" label. After that we end up at btrfs_cleanup_one_transaction() which calls btrfs_cleanup_dirty_bgs(). That helper finds block group B in the transaction's io_list but it never releases the pages array of the block group's io_ctl, resulting in a memory leak. In fact at the point when we are at btrfs_cleanup_dirty_bgs(), the pages array points to pages that were already released by us at __btrfs_write_out_cache() through the call to io_ctl_drop_pages(). We end up freeing the pages array only after waiting for the ordered extent to complete through btrfs_wait_cache_io(), which calls io_ctl_free() to do that. But in the transaction abort case we don't wait for the space cache's ordered extent to complete through a call to btrfs_wait_cache_io(), so that's why we end up with a memory leak - we wait for the ordered extent to complete indirectly by shutting down the work queues and waiting for any jobs in them to complete before returning from close_ctree(). We can solve the leak simply by freeing the pages array right after releasing the pages (with the call to io_ctl_drop_pages()) at __btrfs_write_out_cache(), since we will never use it anymore after that and the pages array points to already released pages at that point, which is currently not a problem since no one will use it after that, but not a good practice anyway since it can easily lead to use-after-free issues. So fix this by freeing the pages array right after releasing the pages at __btrfs_write_out_cache(). This issue can often be reproduced with test case generic/475 from fstests and kmemleak can detect it and reports it with the following trace: unreferenced object 0xffff9bbf009fa600 (size 512): comm "fsstress", pid 38807, jiffies 4298504428 (age 22.028s) hex dump (first 32 bytes): 00 a0 7c 4d 3d ed ff ff 40 a0 7c 4d 3d ed ff ff ..|M=...@.|M=... 80 a0 7c 4d 3d ed ff ff c0 a0 7c 4d 3d ed ff ff ..|M=.....|M=... backtrace: [<00000000f4b5cfe2>] __kmalloc+0x1a8/0x3e0 [<0000000028665e7f>] io_ctl_init+0xa7/0x120 [btrfs] [<00000000a1f95b2d>] __btrfs_write_out_cache+0x86/0x4a0 [btrfs] [<00000000207ea1b0>] btrfs_write_out_cache+0x7f/0xf0 [btrfs] [<00000000af21f534>] btrfs_start_dirty_block_groups+0x27b/0x580 [btrfs] [<00000000c3c23d44>] btrfs_commit_transaction+0xa6f/0xe70 [btrfs] [<000000009588930c>] create_subvol+0x581/0x9a0 [btrfs] [<000000009ef2fd7f>] btrfs_mksubvol+0x3fb/0x4a0 [btrfs] [<00000000474e5187>] __btrfs_ioctl_snap_create+0x119/0x1a0 [btrfs] [<00000000708ee349>] btrfs_ioctl_snap_create_v2+0xb0/0xf0 [btrfs] [<00000000ea60106f>] btrfs_ioctl+0x12c/0x3130 [btrfs] [<000000005c923d6d>] __x64_sys_ioctl+0x83/0xb0 [<0000000043ace2c9>] do_syscall_64+0x33/0x80 [<00000000904efbce>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 CC: stable@vger.kernel.org # 4.9+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 1 + fs/btrfs/free-space-cache.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c850d7f44fbe..465bc8372e09 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4574,6 +4574,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) cache->io_ctl.inode = NULL; iput(inode); } + ASSERT(cache->io_ctl.pages == NULL); btrfs_put_block_group(cache); } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ef0fd7afb0b1..dc82fd0c80cb 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1186,7 +1186,6 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root, ret = update_cache_item(trans, root, inode, path, offset, io_ctl->entries, io_ctl->bitmaps); out: - io_ctl_free(io_ctl); if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; @@ -1347,6 +1346,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * them out later */ io_ctl_drop_pages(io_ctl); + io_ctl_free(io_ctl); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state); -- cgit v1.2.3 From fb2fecbad50964b9f27a3b182e74e437b40753ef Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 10 Aug 2020 17:31:16 -0400 Subject: btrfs: check the right error variable in btrfs_del_dir_entries_in_log With my new locking code dbench is so much faster that I tripped over a transaction abort from ENOSPC. This turned out to be because btrfs_del_dir_entries_in_log was checking for ret == -ENOSPC, but this function sets err on error, and returns err. So instead of properly marking the inode as needing a full commit, we were returning -ENOSPC and aborting in __btrfs_unlink_inode. Fix this by checking the proper variable so that we return the correct thing in the case of ENOSPC. The ENOENT needs to be checked, because btrfs_lookup_dir_item_index() can return -ENOENT if the dir item isn't in the tree log (which would happen if we hadn't fsync'ed this guy). We actually handle that case in __btrfs_unlink_inode, so it's an expected error to get back. Fixes: 4a500fd178c8 ("Btrfs: Metadata ENOSPC handling for tree log") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Reviewed-by: David Sterba [ add note and comment about ENOENT ] Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 696dd861cc3c..39da9db35278 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3449,11 +3449,13 @@ fail: btrfs_free_path(path); out_unlock: mutex_unlock(&dir->log_mutex); - if (ret == -ENOSPC) { + if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); - ret = 0; - } else if (ret < 0) - btrfs_abort_transaction(trans, ret); + err = 0; + } else if (err < 0 && err != -ENOENT) { + /* ENOENT can be returned if the entry hasn't been fsynced yet */ + btrfs_abort_transaction(trans, err); + } btrfs_end_log_trans(root); -- cgit v1.2.3 From a84d5d429f9eb56f81b388609841ed993f0ddfca Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Tue, 18 Aug 2020 11:00:05 -0700 Subject: btrfs: detect nocow for swap after snapshot delete can_nocow_extent and btrfs_cross_ref_exist both rely on a heuristic for detecting a must cow condition which is not exactly accurate, but saves unnecessary tree traversal. The incorrect assumption is that if the extent was created in a generation smaller than the last snapshot generation, it must be referenced by that snapshot. That is true, except the snapshot could have since been deleted, without affecting the last snapshot generation. The original patch claimed a performance win from this check, but it also leads to a bug where you are unable to use a swapfile if you ever snapshotted the subvolume it's in. Make the check slower and more strict for the swapon case, without modifying the general cow checks as a compromise. Turning swap on does not seem to be a particularly performance sensitive operation, so incurring a possibly unnecessary btrfs_search_slot seems worthwhile for the added usability. Note: Until the snapshot is competely cleaned after deletion, check_committed_refs will still cause the logic to think that cow is necessary, so the user must until 'btrfs subvolu sync' finished before activating the swapfile swapon. CC: stable@vger.kernel.org # 5.4+ Suggested-by: Omar Sandoval Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 4 ++-- fs/btrfs/extent-tree.c | 17 +++++++++++------ fs/btrfs/file.c | 2 +- fs/btrfs/inode.c | 18 +++++++++++------- 4 files changed, 25 insertions(+), 16 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 729b5b80014a..9a72896bed2e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2518,7 +2518,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes); int btrfs_exclude_logged_extents(struct extent_buffer *eb); int btrfs_cross_ref_exist(struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr); + u64 objectid, u64 offset, u64 bytenr, bool strict); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, @@ -2934,7 +2934,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, u64 start, u64 len); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, - u64 *ram_bytes); + u64 *ram_bytes, bool strict); void __btrfs_del_delalloc_inode(struct btrfs_root *root, struct btrfs_inode *inode); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index de6fe176fdfb..5871ef78edba 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2306,7 +2306,8 @@ static noinline int check_delayed_ref(struct btrfs_root *root, static noinline int check_committed_ref(struct btrfs_root *root, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr) + u64 objectid, u64 offset, u64 bytenr, + bool strict) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *extent_root = fs_info->extent_root; @@ -2348,9 +2349,13 @@ static noinline int check_committed_ref(struct btrfs_root *root, btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY)) goto out; - /* If extent created before last snapshot => it's definitely shared */ - if (btrfs_extent_generation(leaf, ei) <= - btrfs_root_last_snapshot(&root->root_item)) + /* + * If extent created before last snapshot => it's shared unless the + * snapshot has been deleted. Use the heuristic if strict is false. + */ + if (!strict && + (btrfs_extent_generation(leaf, ei) <= + btrfs_root_last_snapshot(&root->root_item))) goto out; iref = (struct btrfs_extent_inline_ref *)(ei + 1); @@ -2375,7 +2380,7 @@ out: } int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, - u64 bytenr) + u64 bytenr, bool strict) { struct btrfs_path *path; int ret; @@ -2386,7 +2391,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, do { ret = check_committed_ref(root, path, objectid, - offset, bytenr); + offset, bytenr, strict); if (ret && ret != -ENOENT) goto out; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 841c516079a9..3abaff4d2cff 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1571,7 +1571,7 @@ static int check_can_nocow(struct btrfs_inode *inode, loff_t pos, } ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, - NULL, NULL, NULL); + NULL, NULL, NULL, false); if (ret <= 0) { ret = 0; if (!nowait) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4ad0323b3684..46e04247193a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1609,7 +1609,7 @@ next_slot: goto out_check; ret = btrfs_cross_ref_exist(root, ino, found_key.offset - - extent_offset, disk_bytenr); + extent_offset, disk_bytenr, false); if (ret) { /* * ret could be -EIO if the above fails to read @@ -6949,6 +6949,8 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, * @orig_start: (optional) Return the original file offset of the file extent * @orig_len: (optional) Return the original on-disk length of the file extent * @ram_bytes: (optional) Return the ram_bytes of the file extent + * @strict: if true, omit optimizations that might force us into unnecessary + * cow. e.g., don't trust generation number. * * This function will flush ordered extents in the range to ensure proper * nocow checks for (nowait == false) case. @@ -6963,7 +6965,7 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, */ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, - u64 *ram_bytes) + u64 *ram_bytes, bool strict) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_path *path; @@ -7041,8 +7043,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, * Do the same check as in btrfs_cross_ref_exist but without the * unnecessary search. */ - if (btrfs_file_extent_generation(leaf, fi) <= - btrfs_root_last_snapshot(&root->root_item)) + if (!strict && + (btrfs_file_extent_generation(leaf, fi) <= + btrfs_root_last_snapshot(&root->root_item))) goto out; backref_offset = btrfs_file_extent_offset(leaf, fi); @@ -7078,7 +7081,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, */ ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)), - key.offset - backref_offset, disk_bytenr); + key.offset - backref_offset, disk_bytenr, + strict); if (ret) { ret = 0; goto out; @@ -7299,7 +7303,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, block_start = em->block_start + (start - em->start); if (can_nocow_extent(inode, start, &len, &orig_start, - &orig_block_len, &ram_bytes) == 1 && + &orig_block_len, &ram_bytes, false) == 1 && btrfs_inc_nocow_writers(fs_info, block_start)) { struct extent_map *em2; @@ -10130,7 +10134,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, free_extent_map(em); em = NULL; - ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL); + ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true); if (ret < 0) { goto out; } else if (ret) { -- cgit v1.2.3 From e3e39c72b99f93bbd0420d38c858e7c4a061bb63 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Fri, 21 Aug 2020 11:54:44 -0300 Subject: btrfs: block-group: fix free-space bitmap threshold [BUG] After commit 9afc66498a0b ("btrfs: block-group: refactor how we read one block group item"), cache->length is being assigned after calling btrfs_create_block_group_cache. This causes a problem since set_free_space_tree_thresholds calculates the free-space threshold to decide if the free-space tree should convert from extents to bitmaps. The current code calls set_free_space_tree_thresholds with cache->length being 0, which then makes cache->bitmap_high_thresh zero. This implies the system will always use bitmap instead of extents, which is not desired if the block group is not fragmented. This behavior can be seen by a test that expects to repair systems with FREE_SPACE_EXTENT and FREE_SPACE_BITMAP, but the current code only created FREE_SPACE_BITMAP. [FIX] Call set_free_space_tree_thresholds after setting cache->length. There is now a WARN_ON in set_free_space_tree_thresholds to help preventing the same mistake to happen again in the future. Link: https://github.com/kdave/btrfs-progs/issues/251 Fixes: 9afc66498a0b ("btrfs: block-group: refactor how we read one block group item") CC: stable@vger.kernel.org # 5.8+ Reviewed-by: Qu Wenruo Reviewed-by: Filipe Manana Signed-off-by: Marcos Paulo de Souza Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 4 +++- fs/btrfs/free-space-tree.c | 4 ++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 613920c17ac1..ea8aaf36647e 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1798,7 +1798,6 @@ static struct btrfs_block_group *btrfs_create_block_group_cache( cache->fs_info = fs_info; cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start); - set_free_space_tree_thresholds(cache); cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED; @@ -1912,6 +1911,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, if (ret < 0) goto error; + set_free_space_tree_thresholds(cache); + if (need_clear) { /* * When we mount with old space cache, we need to @@ -2132,6 +2133,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, return -ENOMEM; cache->length = size; + set_free_space_tree_thresholds(cache); cache->used = bytes_used; cache->flags = type; cache->last_byte_to_unpin = (u64)-1; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 8b1f5c8897b7..6b9faf3b0e96 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -22,6 +22,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group *cache) size_t bitmap_size; u64 num_bitmaps, total_bitmap_size; + if (WARN_ON(cache->length == 0)) + btrfs_warn(cache->fs_info, "block group %llu length is zero", + cache->start); + /* * We convert to bitmaps when the disk space required for using extents * exceeds that required for using bitmaps. -- cgit v1.2.3 From 9771a5cf937129307d9f58922d60484d58ababe7 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 10 Aug 2020 11:42:26 -0400 Subject: btrfs: drop path before adding new uuid tree entry With the conversion of the tree locks to rwsem I got the following lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 5.8.0-rc7-00167-g0d7ba0c5b375-dirty #925 Not tainted ------------------------------------------------------ btrfs-uuid/7955 is trying to acquire lock: ffff88bfbafec0f8 (btrfs-root-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180 but task is already holding lock: ffff88bfbafef2a8 (btrfs-uuid-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (btrfs-uuid-00){++++}-{3:3}: down_read_nested+0x3e/0x140 __btrfs_tree_read_lock+0x39/0x180 __btrfs_read_lock_root_node+0x3a/0x50 btrfs_search_slot+0x4bd/0x990 btrfs_uuid_tree_add+0x89/0x2d0 btrfs_uuid_scan_kthread+0x330/0x390 kthread+0x133/0x150 ret_from_fork+0x1f/0x30 -> #0 (btrfs-root-00){++++}-{3:3}: __lock_acquire+0x1272/0x2310 lock_acquire+0x9e/0x360 down_read_nested+0x3e/0x140 __btrfs_tree_read_lock+0x39/0x180 __btrfs_read_lock_root_node+0x3a/0x50 btrfs_search_slot+0x4bd/0x990 btrfs_find_root+0x45/0x1b0 btrfs_read_tree_root+0x61/0x100 btrfs_get_root_ref.part.50+0x143/0x630 btrfs_uuid_tree_iterate+0x207/0x314 btrfs_uuid_rescan_kthread+0x12/0x50 kthread+0x133/0x150 ret_from_fork+0x1f/0x30 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(btrfs-uuid-00); lock(btrfs-root-00); lock(btrfs-uuid-00); lock(btrfs-root-00); *** DEADLOCK *** 1 lock held by btrfs-uuid/7955: #0: ffff88bfbafef2a8 (btrfs-uuid-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180 stack backtrace: CPU: 73 PID: 7955 Comm: btrfs-uuid Kdump: loaded Not tainted 5.8.0-rc7-00167-g0d7ba0c5b375-dirty #925 Hardware name: Quanta Tioga Pass Single Side 01-0030993006/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018 Call Trace: dump_stack+0x78/0xa0 check_noncircular+0x165/0x180 __lock_acquire+0x1272/0x2310 lock_acquire+0x9e/0x360 ? __btrfs_tree_read_lock+0x39/0x180 ? btrfs_root_node+0x1c/0x1d0 down_read_nested+0x3e/0x140 ? __btrfs_tree_read_lock+0x39/0x180 __btrfs_tree_read_lock+0x39/0x180 __btrfs_read_lock_root_node+0x3a/0x50 btrfs_search_slot+0x4bd/0x990 btrfs_find_root+0x45/0x1b0 btrfs_read_tree_root+0x61/0x100 btrfs_get_root_ref.part.50+0x143/0x630 btrfs_uuid_tree_iterate+0x207/0x314 ? btree_readpage+0x20/0x20 btrfs_uuid_rescan_kthread+0x12/0x50 kthread+0x133/0x150 ? kthread_create_on_node+0x60/0x60 ret_from_fork+0x1f/0x30 This problem exists because we have two different rescan threads, btrfs_uuid_scan_kthread which creates the uuid tree, and btrfs_uuid_tree_iterate that goes through and updates or deletes any out of date roots. The problem is they both do things in different order. btrfs_uuid_scan_kthread() reads the tree_root, and then inserts entries into the uuid_root. btrfs_uuid_tree_iterate() scans the uuid_root, but then does a btrfs_get_fs_root() which can read from the tree_root. It's actually easy enough to not be holding the path in btrfs_uuid_scan_kthread() when we add a uuid entry, as we already drop it further down and re-start the search when we loop. So simply move the path release before we add our entry to the uuid tree. This also fixes a problem where we're holding a path open after we do btrfs_end_transaction(), which has it's own problems. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ee96c5869f57..214856c4ccb1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4462,6 +4462,7 @@ int btrfs_uuid_scan_kthread(void *data) goto skip; } update_tree: + btrfs_release_path(path); if (!btrfs_is_empty_uuid(root_item.uuid)) { ret = btrfs_uuid_tree_add(trans, root_item.uuid, BTRFS_UUID_KEY_SUBVOL, @@ -4486,6 +4487,7 @@ update_tree: } skip: + btrfs_release_path(path); if (trans) { ret = btrfs_end_transaction(trans); trans = NULL; @@ -4493,7 +4495,6 @@ skip: break; } - btrfs_release_path(path); if (key.offset < (u64)-1) { key.offset++; } else if (key.type < BTRFS_ROOT_ITEM_KEY) { -- cgit v1.2.3 From a48b73eca4ceb9b8a4b97f290a065335dbcd8a04 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 10 Aug 2020 11:42:27 -0400 Subject: btrfs: fix potential deadlock in the search ioctl With the conversion of the tree locks to rwsem I got the following lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 5.8.0-rc7-00165-g04ec4da5f45f-dirty #922 Not tainted ------------------------------------------------------ compsize/11122 is trying to acquire lock: ffff889fabca8768 (&mm->mmap_lock#2){++++}-{3:3}, at: __might_fault+0x3e/0x90 but task is already holding lock: ffff889fe720fe40 (btrfs-fs-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (btrfs-fs-00){++++}-{3:3}: down_write_nested+0x3b/0x70 __btrfs_tree_lock+0x24/0x120 btrfs_search_slot+0x756/0x990 btrfs_lookup_inode+0x3a/0xb4 __btrfs_update_delayed_inode+0x93/0x270 btrfs_async_run_delayed_root+0x168/0x230 btrfs_work_helper+0xd4/0x570 process_one_work+0x2ad/0x5f0 worker_thread+0x3a/0x3d0 kthread+0x133/0x150 ret_from_fork+0x1f/0x30 -> #1 (&delayed_node->mutex){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 btrfs_delayed_update_inode+0x50/0x440 btrfs_update_inode+0x8a/0xf0 btrfs_dirty_inode+0x5b/0xd0 touch_atime+0xa1/0xd0 btrfs_file_mmap+0x3f/0x60 mmap_region+0x3a4/0x640 do_mmap+0x376/0x580 vm_mmap_pgoff+0xd5/0x120 ksys_mmap_pgoff+0x193/0x230 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #0 (&mm->mmap_lock#2){++++}-{3:3}: __lock_acquire+0x1272/0x2310 lock_acquire+0x9e/0x360 __might_fault+0x68/0x90 _copy_to_user+0x1e/0x80 copy_to_sk.isra.32+0x121/0x300 search_ioctl+0x106/0x200 btrfs_ioctl_tree_search_v2+0x7b/0xf0 btrfs_ioctl+0x106f/0x30a0 ksys_ioctl+0x83/0xc0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 other info that might help us debug this: Chain exists of: &mm->mmap_lock#2 --> &delayed_node->mutex --> btrfs-fs-00 Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(btrfs-fs-00); lock(&delayed_node->mutex); lock(btrfs-fs-00); lock(&mm->mmap_lock#2); *** DEADLOCK *** 1 lock held by compsize/11122: #0: ffff889fe720fe40 (btrfs-fs-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180 stack backtrace: CPU: 17 PID: 11122 Comm: compsize Kdump: loaded Not tainted 5.8.0-rc7-00165-g04ec4da5f45f-dirty #922 Hardware name: Quanta Tioga Pass Single Side 01-0030993006/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018 Call Trace: dump_stack+0x78/0xa0 check_noncircular+0x165/0x180 __lock_acquire+0x1272/0x2310 lock_acquire+0x9e/0x360 ? __might_fault+0x3e/0x90 ? find_held_lock+0x72/0x90 __might_fault+0x68/0x90 ? __might_fault+0x3e/0x90 _copy_to_user+0x1e/0x80 copy_to_sk.isra.32+0x121/0x300 ? btrfs_search_forward+0x2a6/0x360 search_ioctl+0x106/0x200 btrfs_ioctl_tree_search_v2+0x7b/0xf0 btrfs_ioctl+0x106f/0x30a0 ? __do_sys_newfstat+0x5a/0x70 ? ksys_ioctl+0x83/0xc0 ksys_ioctl+0x83/0xc0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The problem is we're doing a copy_to_user() while holding tree locks, which can deadlock if we have to do a page fault for the copy_to_user(). This exists even without my locking changes, so it needs to be fixed. Rework the search ioctl to do the pre-fault and then copy_to_user_nofault for the copying. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 8 ++++---- fs/btrfs/extent_io.h | 6 +++--- fs/btrfs/ioctl.c | 27 ++++++++++++++++++++------- 3 files changed, 27 insertions(+), 14 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 617ea38e6fd7..c15ab6c1897f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5653,9 +5653,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, } } -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dstv, - unsigned long start, unsigned long len) +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dstv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; @@ -5675,7 +5675,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb, cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); - if (copy_to_user(dst, kaddr + offset, cur)) { + if (copy_to_user_nofault(dst, kaddr + offset, cur)) { ret = -EFAULT; break; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 00a88f2eb5ab..30794ae58498 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -241,9 +241,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, void read_extent_buffer(const struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); -int read_extent_buffer_to_user(const struct extent_buffer *eb, - void __user *dst, unsigned long start, - unsigned long len); +int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, + void __user *dst, unsigned long start, + unsigned long len); void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src); void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb, const void *src); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bd3511c5ca81..ac45f022b495 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2086,9 +2086,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, sh.len = item_len; sh.transid = found_transid; - /* copy search result header */ - if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { - ret = -EFAULT; + /* + * Copy search result header. If we fault then loop again so we + * can fault in the pages and -EFAULT there if there's a + * problem. Otherwise we'll fault and then copy the buffer in + * properly this next time through + */ + if (copy_to_user_nofault(ubuf + *sk_offset, &sh, sizeof(sh))) { + ret = 0; goto out; } @@ -2096,10 +2101,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, if (item_len) { char __user *up = ubuf + *sk_offset; - /* copy the item */ - if (read_extent_buffer_to_user(leaf, up, - item_off, item_len)) { - ret = -EFAULT; + /* + * Copy the item, same behavior as above, but reset the + * * sk_offset so we copy the full thing again. + */ + if (read_extent_buffer_to_user_nofault(leaf, up, + item_off, item_len)) { + ret = 0; + *sk_offset -= sizeof(sh); goto out; } @@ -2184,6 +2193,10 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { + ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset); + if (ret) + break; + ret = btrfs_search_forward(root, &key, path, sk->min_transid); if (ret != 0) { if (ret > 0) -- cgit v1.2.3 From e89c4a9c8e6ce3a84cab4f342687d3fbbb1234eb Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 10 Aug 2020 11:42:29 -0400 Subject: btrfs: allocate scrub workqueues outside of locks I got the following lockdep splat while testing: ====================================================== WARNING: possible circular locking dependency detected 5.8.0-rc7-00172-g021118712e59 #932 Not tainted ------------------------------------------------------ btrfs/229626 is trying to acquire lock: ffffffff828513f0 (cpu_hotplug_lock){++++}-{0:0}, at: alloc_workqueue+0x378/0x450 but task is already holding lock: ffff889dd3889518 (&fs_info->scrub_lock){+.+.}-{3:3}, at: btrfs_scrub_dev+0x11c/0x630 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #7 (&fs_info->scrub_lock){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 btrfs_scrub_dev+0x11c/0x630 btrfs_dev_replace_by_ioctl.cold.21+0x10a/0x1d4 btrfs_ioctl+0x2799/0x30a0 ksys_ioctl+0x83/0xc0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #6 (&fs_devs->device_list_mutex){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 btrfs_run_dev_stats+0x49/0x480 commit_cowonly_roots+0xb5/0x2a0 btrfs_commit_transaction+0x516/0xa60 sync_filesystem+0x6b/0x90 generic_shutdown_super+0x22/0x100 kill_anon_super+0xe/0x30 btrfs_kill_super+0x12/0x20 deactivate_locked_super+0x29/0x60 cleanup_mnt+0xb8/0x140 task_work_run+0x6d/0xb0 __prepare_exit_to_usermode+0x1cc/0x1e0 do_syscall_64+0x5c/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #5 (&fs_info->tree_log_mutex){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 btrfs_commit_transaction+0x4bb/0xa60 sync_filesystem+0x6b/0x90 generic_shutdown_super+0x22/0x100 kill_anon_super+0xe/0x30 btrfs_kill_super+0x12/0x20 deactivate_locked_super+0x29/0x60 cleanup_mnt+0xb8/0x140 task_work_run+0x6d/0xb0 __prepare_exit_to_usermode+0x1cc/0x1e0 do_syscall_64+0x5c/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #4 (&fs_info->reloc_mutex){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 btrfs_record_root_in_trans+0x43/0x70 start_transaction+0xd1/0x5d0 btrfs_dirty_inode+0x42/0xd0 touch_atime+0xa1/0xd0 btrfs_file_mmap+0x3f/0x60 mmap_region+0x3a4/0x640 do_mmap+0x376/0x580 vm_mmap_pgoff+0xd5/0x120 ksys_mmap_pgoff+0x193/0x230 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #3 (&mm->mmap_lock#2){++++}-{3:3}: __might_fault+0x68/0x90 _copy_to_user+0x1e/0x80 perf_read+0x141/0x2c0 vfs_read+0xad/0x1b0 ksys_read+0x5f/0xe0 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #2 (&cpuctx_mutex){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 perf_event_init_cpu+0x88/0x150 perf_event_init+0x1db/0x20b start_kernel+0x3ae/0x53c secondary_startup_64+0xa4/0xb0 -> #1 (pmus_lock){+.+.}-{3:3}: __mutex_lock+0x9f/0x930 perf_event_init_cpu+0x4f/0x150 cpuhp_invoke_callback+0xb1/0x900 _cpu_up.constprop.26+0x9f/0x130 cpu_up+0x7b/0xc0 bringup_nonboot_cpus+0x4f/0x60 smp_init+0x26/0x71 kernel_init_freeable+0x110/0x258 kernel_init+0xa/0x103 ret_from_fork+0x1f/0x30 -> #0 (cpu_hotplug_lock){++++}-{0:0}: __lock_acquire+0x1272/0x2310 lock_acquire+0x9e/0x360 cpus_read_lock+0x39/0xb0 alloc_workqueue+0x378/0x450 __btrfs_alloc_workqueue+0x15d/0x200 btrfs_alloc_workqueue+0x51/0x160 scrub_workers_get+0x5a/0x170 btrfs_scrub_dev+0x18c/0x630 btrfs_dev_replace_by_ioctl.cold.21+0x10a/0x1d4 btrfs_ioctl+0x2799/0x30a0 ksys_ioctl+0x83/0xc0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 other info that might help us debug this: Chain exists of: cpu_hotplug_lock --> &fs_devs->device_list_mutex --> &fs_info->scrub_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&fs_info->scrub_lock); lock(&fs_devs->device_list_mutex); lock(&fs_info->scrub_lock); lock(cpu_hotplug_lock); *** DEADLOCK *** 2 locks held by btrfs/229626: #0: ffff88bfe8bb86e0 (&fs_devs->device_list_mutex){+.+.}-{3:3}, at: btrfs_scrub_dev+0xbd/0x630 #1: ffff889dd3889518 (&fs_info->scrub_lock){+.+.}-{3:3}, at: btrfs_scrub_dev+0x11c/0x630 stack backtrace: CPU: 15 PID: 229626 Comm: btrfs Kdump: loaded Not tainted 5.8.0-rc7-00172-g021118712e59 #932 Hardware name: Quanta Tioga Pass Single Side 01-0030993006/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018 Call Trace: dump_stack+0x78/0xa0 check_noncircular+0x165/0x180 __lock_acquire+0x1272/0x2310 lock_acquire+0x9e/0x360 ? alloc_workqueue+0x378/0x450 cpus_read_lock+0x39/0xb0 ? alloc_workqueue+0x378/0x450 alloc_workqueue+0x378/0x450 ? rcu_read_lock_sched_held+0x52/0x80 __btrfs_alloc_workqueue+0x15d/0x200 btrfs_alloc_workqueue+0x51/0x160 scrub_workers_get+0x5a/0x170 btrfs_scrub_dev+0x18c/0x630 ? start_transaction+0xd1/0x5d0 btrfs_dev_replace_by_ioctl.cold.21+0x10a/0x1d4 btrfs_ioctl+0x2799/0x30a0 ? do_sigaction+0x102/0x250 ? lockdep_hardirqs_on_prepare+0xca/0x160 ? _raw_spin_unlock_irq+0x24/0x30 ? trace_hardirqs_on+0x1c/0xe0 ? _raw_spin_unlock_irq+0x24/0x30 ? do_sigaction+0x102/0x250 ? ksys_ioctl+0x83/0xc0 ksys_ioctl+0x83/0xc0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 This happens because we're allocating the scrub workqueues under the scrub and device list mutex, which brings in a whole host of other dependencies. Because the work queue allocation is done with GFP_KERNEL, it can trigger reclaim, which can lead to a transaction commit, which in turns needs the device_list_mutex, it can lead to a deadlock. A different problem for which this fix is a solution. Fix this by moving the actual allocation outside of the scrub lock, and then only take the lock once we're ready to actually assign them to the fs_info. We'll now have to cleanup the workqueues in a few more places, so I've added a helper to do the refcount dance to safely free the workqueues. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/scrub.c | 122 +++++++++++++++++++++++++++++++------------------------ 1 file changed, 70 insertions(+), 52 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 5a6cb9db512e..354ab9985a34 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3716,50 +3716,84 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, return 0; } +static void scrub_workers_put(struct btrfs_fs_info *fs_info) +{ + if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, + &fs_info->scrub_lock)) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; + + scrub_workers = fs_info->scrub_workers; + scrub_wr_comp = fs_info->scrub_wr_completion_workers; + scrub_parity = fs_info->scrub_parity_workers; + + fs_info->scrub_workers = NULL; + fs_info->scrub_wr_completion_workers = NULL; + fs_info->scrub_parity_workers = NULL; + mutex_unlock(&fs_info->scrub_lock); + + btrfs_destroy_workqueue(scrub_workers); + btrfs_destroy_workqueue(scrub_wr_comp); + btrfs_destroy_workqueue(scrub_parity); + } +} + /* * get a reference count on fs_info->scrub_workers. start worker if necessary */ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { + struct btrfs_workqueue *scrub_workers = NULL; + struct btrfs_workqueue *scrub_wr_comp = NULL; + struct btrfs_workqueue *scrub_parity = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; + int ret = -ENOMEM; - lockdep_assert_held(&fs_info->scrub_lock); + if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) + return 0; - if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { - ASSERT(fs_info->scrub_workers == NULL); - fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", - flags, is_dev_replace ? 1 : max_active, 4); - if (!fs_info->scrub_workers) - goto fail_scrub_workers; - - ASSERT(fs_info->scrub_wr_completion_workers == NULL); - fs_info->scrub_wr_completion_workers = - btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, - max_active, 2); - if (!fs_info->scrub_wr_completion_workers) - goto fail_scrub_wr_completion_workers; + scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags, + is_dev_replace ? 1 : max_active, 4); + if (!scrub_workers) + goto fail_scrub_workers; - ASSERT(fs_info->scrub_parity_workers == NULL); - fs_info->scrub_parity_workers = - btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, max_active, 2); - if (!fs_info->scrub_parity_workers) - goto fail_scrub_parity_workers; + if (!scrub_wr_comp) + goto fail_scrub_wr_completion_workers; + scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags, + max_active, 2); + if (!scrub_parity) + goto fail_scrub_parity_workers; + + mutex_lock(&fs_info->scrub_lock); + if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { + ASSERT(fs_info->scrub_workers == NULL && + fs_info->scrub_wr_completion_workers == NULL && + fs_info->scrub_parity_workers == NULL); + fs_info->scrub_workers = scrub_workers; + fs_info->scrub_wr_completion_workers = scrub_wr_comp; + fs_info->scrub_parity_workers = scrub_parity; refcount_set(&fs_info->scrub_workers_refcnt, 1); - } else { - refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + return 0; } - return 0; + /* Other thread raced in and created the workers for us */ + refcount_inc(&fs_info->scrub_workers_refcnt); + mutex_unlock(&fs_info->scrub_lock); + ret = 0; + btrfs_destroy_workqueue(scrub_parity); fail_scrub_parity_workers: - btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers); + btrfs_destroy_workqueue(scrub_wr_comp); fail_scrub_wr_completion_workers: - btrfs_destroy_workqueue(fs_info->scrub_workers); + btrfs_destroy_workqueue(scrub_workers); fail_scrub_workers: - return -ENOMEM; + return ret; } int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, @@ -3770,9 +3804,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, int ret; struct btrfs_device *dev; unsigned int nofs_flag; - struct btrfs_workqueue *scrub_workers = NULL; - struct btrfs_workqueue *scrub_wr_comp = NULL; - struct btrfs_workqueue *scrub_parity = NULL; if (btrfs_fs_closing(fs_info)) return -EAGAIN; @@ -3819,13 +3850,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (IS_ERR(sctx)) return PTR_ERR(sctx); + ret = scrub_workers_get(fs_info, is_dev_replace); + if (ret) + goto out_free_ctx; + mutex_lock(&fs_info->fs_devices->device_list_mutex); dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) && !is_dev_replace)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -ENODEV; - goto out_free_ctx; + goto out; } if (!is_dev_replace && !readonly && @@ -3834,7 +3869,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", rcu_str_deref(dev->name)); ret = -EROFS; - goto out_free_ctx; + goto out; } mutex_lock(&fs_info->scrub_lock); @@ -3843,7 +3878,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EIO; - goto out_free_ctx; + goto out; } down_read(&fs_info->dev_replace.rwsem); @@ -3854,17 +3889,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EINPROGRESS; - goto out_free_ctx; + goto out; } up_read(&fs_info->dev_replace.rwsem); - ret = scrub_workers_get(fs_info, is_dev_replace); - if (ret) { - mutex_unlock(&fs_info->scrub_lock); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); - goto out_free_ctx; - } - sctx->readonly = readonly; dev->scrub_ctx = sctx; mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -3917,24 +3945,14 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, mutex_lock(&fs_info->scrub_lock); dev->scrub_ctx = NULL; - if (refcount_dec_and_test(&fs_info->scrub_workers_refcnt)) { - scrub_workers = fs_info->scrub_workers; - scrub_wr_comp = fs_info->scrub_wr_completion_workers; - scrub_parity = fs_info->scrub_parity_workers; - - fs_info->scrub_workers = NULL; - fs_info->scrub_wr_completion_workers = NULL; - fs_info->scrub_parity_workers = NULL; - } mutex_unlock(&fs_info->scrub_lock); - btrfs_destroy_workqueue(scrub_workers); - btrfs_destroy_workqueue(scrub_wr_comp); - btrfs_destroy_workqueue(scrub_parity); + scrub_workers_put(fs_info); scrub_put_ctx(sctx); return ret; - +out: + scrub_workers_put(fs_info); out_free_ctx: scrub_free_ctx(sctx); -- cgit v1.2.3 From ad24466588ab7d7c879053c5afd919b0c555fec0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 10 Aug 2020 11:42:30 -0400 Subject: btrfs: set the correct lockdep class for new nodes When flipping over to the rw_semaphore I noticed I'd get a lockdep splat in replace_path(), which is weird because we're swapping the reloc root with the actual target root. Turns out this is because we're using the root->root_key.objectid as the root id for the newly allocated tree block when setting the lockdep class, however we need to be using the actual owner of this new block, which is saved in owner. The affected path is through btrfs_copy_root as all other callers of btrfs_alloc_tree_block (which calls init_new_buffer) have root_objectid == root->root_key.objectid . CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5871ef78edba..e9eedc053fc5 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4527,7 +4527,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, return ERR_PTR(-EUCLEAN); } - btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); + btrfs_set_buffer_lockdep_class(owner, buf, level); btrfs_tree_lock(buf); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); -- cgit v1.2.3 From d3beaa253fd6fa40b8b18a216398e6e5376a9d21 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 10 Aug 2020 11:42:31 -0400 Subject: btrfs: set the lockdep class for log tree extent buffers These are special extent buffers that get rewound in order to lookup the state of the tree at a specific point in time. As such they do not go through the normal initialization paths that set their lockdep class, so handle them appropriately when they are created and before they are locked. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cd1cd673bc0b..cd392da69b81 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1297,6 +1297,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin), + eb_rewin, btrfs_header_level(eb_rewin)); btrfs_tree_read_lock(eb_rewin); __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm); WARN_ON(btrfs_header_nritems(eb_rewin) > @@ -1370,7 +1372,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq) if (!eb) return NULL; - btrfs_tree_read_lock(eb); if (old_root) { btrfs_set_header_bytenr(eb, eb->start); btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); @@ -1378,6 +1379,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, + btrfs_header_level(eb)); + btrfs_tree_read_lock(eb); if (tm) __tree_mod_log_rewind(fs_info, eb, time_seq, tm); else -- cgit v1.2.3 From f96d6960abbc52e26ad124e69e6815283d3e1674 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 25 Aug 2020 21:42:51 +0800 Subject: btrfs: tree-checker: fix the error message for transid error The error message for inode transid is the same as for inode generation, which makes us unable to detect the real problem. Reported-by: Tyler Richmond Fixes: 496245cac57e ("btrfs: tree-checker: Verify inode item") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Marcos Paulo de Souza Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 517b44300a05..7b1fee630f97 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -984,7 +984,7 @@ static int check_inode_item(struct extent_buffer *leaf, /* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */ if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) { inode_item_err(leaf, slot, - "invalid inode generation: has %llu expect [0, %llu]", + "invalid inode transid: has %llu expect [0, %llu]", btrfs_inode_transid(leaf, iitem), super_gen + 1); return -EUCLEAN; } -- cgit v1.2.3