From 34d9700702f4042ce10d68a092ab7f79575e7a3b Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Wed, 16 Mar 2016 16:43:06 +0800 Subject: btrfs: rename btrfs_std_error to btrfs_handle_fs_error btrfs_std_error() handles errors, puts FS into readonly mode (as of now). So its good idea to rename it to btrfs_handle_fs_error(). Signed-off-by: Anand Jain Reviewed-by: David Sterba [ edit changelog ] Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 517d0ccb351e..16a74d1a2720 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5519,7 +5519,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) ret = walk_log_tree(trans, log_root_tree, &wc); if (ret) { - btrfs_std_error(fs_info, ret, "Failed to pin buffers while " + btrfs_handle_fs_error(fs_info, ret, "Failed to pin buffers while " "recovering log root tree."); goto error; } @@ -5533,7 +5533,7 @@ again: ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (ret < 0) { - btrfs_std_error(fs_info, ret, + btrfs_handle_fs_error(fs_info, ret, "Couldn't find tree log root."); goto error; } @@ -5551,7 +5551,7 @@ again: log = btrfs_read_fs_root(log_root_tree, &found_key); if (IS_ERR(log)) { ret = PTR_ERR(log); - btrfs_std_error(fs_info, ret, + btrfs_handle_fs_error(fs_info, ret, "Couldn't read tree log root."); goto error; } @@ -5566,7 +5566,7 @@ again: free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); - btrfs_std_error(fs_info, ret, "Couldn't read target root " + btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root " "for tree log recovery."); goto error; } -- cgit v1.2.3 From 657ed1aa4898c8304500e0d13f240d5a67e8be5f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 6 Apr 2016 17:11:56 +0100 Subject: Btrfs: fix for incorrect directory entries after fsync log replay MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we move a directory to a new parent and later log that parent and don't explicitly log the old parent, when we replay the log we can end up with entries for the moved directory in both the old and new parent directories. Besides being ilegal to have directories with multiple hard links in linux, it also resulted in the leaving the inode item with a link count of 1. A similar issue also happens if we move a regular file - after the log tree is replayed the file has a link in both the old and new parent directories, when it should be only at the new directory. Sample reproducer: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ mkdir /mnt/x $ mkdir /mnt/y $ touch /mnt/x/foo $ mkdir /mnt/y/z $ sync $ ln /mnt/x/foo /mnt/x/bar $ mv /mnt/y/z /mnt/x/z < power fail > $ mount /dev/sdc /mnt $ ls -1Ri /mnt /mnt: 257 x 258 y /mnt/x: 259 bar 259 foo 260 z /mnt/x/z: /mnt/y: 260 z /mnt/y/z: $ umount /dev/sdc $ btrfs check /dev/sdc Checking filesystem on /dev/sdc UUID: a67e2c4a-a4b4-4fdc-b015-9d9af1e344be checking extents checking free space cache checking fs roots root 5 inode 260 errors 2000, link count wrong unresolved ref dir 257 index 4 namelen 1 name z filetype 2 errors 0 unresolved ref dir 258 index 2 namelen 1 name z filetype 2 errors 0 (...) Attempting to remove the directory becomes impossible: $ mount /dev/sdc /mnt $ rmdir /mnt/y/z $ ls -lh /mnt/y ls: cannot access /mnt/y/z: No such file or directory total 0 d????????? ? ? ? ? ? z $ rmdir /mnt/x/z rmdir: failed to remove ‘/mnt/x/z’: Stale file handle $ ls -lh /mnt/x ls: cannot access /mnt/x/z: Stale file handle total 0 -rw-r--r-- 2 root root 0 Apr 6 18:06 bar -rw-r--r-- 2 root root 0 Apr 6 18:06 foo d????????? ? ? ? ? ? z So make sure that on rename we set the last_unlink_trans value for our inode, even if it's a directory, to the value of the current transaction's ID and that if the new parent directory is logged that we fallback to a transaction commit. A test case for fstests is being submitted as well. Signed-off-by: Filipe Manana --- fs/btrfs/tree-log.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 517d0ccb351e..4709932c62fb 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5278,11 +5278,16 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, if (IS_ERR(dir_inode)) continue; + if (ctx) + ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, root, dir_inode, LOG_INODE_ALL, 0, LLONG_MAX, ctx); if (!ret && btrfs_must_commit_transaction(trans, dir_inode)) ret = 1; + if (!ret && ctx && ctx->log_new_dentries) + ret = log_new_dir_dentries(trans, root, + dir_inode, ctx); iput(dir_inode); if (ret) goto out; @@ -5652,11 +5657,9 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, * into the file. When the file is logged we check it and * don't log the parents if the file is fully on disk. */ - if (S_ISREG(inode->i_mode)) { - mutex_lock(&BTRFS_I(inode)->log_mutex); - BTRFS_I(inode)->last_unlink_trans = trans->transid; - mutex_unlock(&BTRFS_I(inode)->log_mutex); - } + mutex_lock(&BTRFS_I(inode)->log_mutex); + BTRFS_I(inode)->last_unlink_trans = trans->transid; + mutex_unlock(&BTRFS_I(inode)->log_mutex); /* * if this directory was already logged any new -- cgit v1.2.3 From 3f9749f6e9edcf8ec569fb542efc3be35e06e84a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 25 Apr 2016 04:45:02 +0100 Subject: Btrfs: fix empty symlink after creating symlink and fsync parent dir If we create a symlink, fsync its parent directory, crash/power fail and mount the filesystem, we end up with an empty symlink, which not only is useless it's also not allowed in linux (the man page symlink(2) is well explicit about that). So we just need to make sure to fully log an inode if it's a symlink, to ensure its inline extent gets logged, ensuring the same behaviour as ext3, ext4, xfs, reiserfs, f2fs, nilfs2, etc. Example reproducer: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ mkdir /mnt/testdir $ sync $ ln -s /mnt/foo /mnt/testdir/bar $ xfs_io -c fsync /mnt/testdir $ mount /dev/sdb /mnt $ readlink /mnt/testdir/bar A test case for fstests follows soon. Signed-off-by: Filipe Manana --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 4709932c62fb..a24a0ba523d6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5158,7 +5158,7 @@ process_leaf: } ctx->log_new_dentries = false; - if (type == BTRFS_FT_DIR) + if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) log_mode = LOG_INODE_ALL; btrfs_release_path(path); ret = btrfs_log_inode(trans, root, di_inode, -- cgit v1.2.3 From 5f9a8a51d8b95505d8de8b7191ae2ed8c504d4af Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 12 May 2016 13:53:36 +0100 Subject: Btrfs: add semaphore to synchronize direct IO writes with fsync Due to the optimization of lockless direct IO writes (the inode's i_mutex is not held) introduced in commit 38851cc19adb ("Btrfs: implement unlocked dio write"), we started having races between such writes with concurrent fsync operations that use the fast fsync path. These races were addressed in the patches titled "Btrfs: fix race between fsync and lockless direct IO writes" and "Btrfs: fix race between fsync and direct IO writes for prealloc extents". The races happened because the direct IO path, like every other write path, does create extent maps followed by the corresponding ordered extents while the fast fsync path collected first ordered extents and then it collected extent maps. This made it possible to log file extent items (based on the collected extent maps) without waiting for the corresponding ordered extents to complete (get their IO done). The two fixes mentioned before added a solution that consists of making the direct IO path create first the ordered extents and then the extent maps, while the fsync path attempts to collect any new ordered extents once it collects the extent maps. This was simple and did not require adding any synchonization primitive to any data structure (struct btrfs_inode for example) but it makes things more fragile for future development endeavours and adds an exceptional approach compared to the other write paths. This change adds a read-write semaphore to the btrfs inode structure and makes the direct IO path create the extent maps and the ordered extents while holding read access on that semaphore, while the fast fsync path collects extent maps and ordered extents while holding write access on that semaphore. The logic for direct IO write path is encapsulated in a new helper function that is used both for cow and nocow direct IO writes. Signed-off-by: Filipe Manana Reviewed-by: Josef Bacik --- fs/btrfs/btrfs_inode.h | 10 ++++ fs/btrfs/inode.c | 134 +++++++++++++++++++------------------------------ fs/btrfs/tree-log.c | 51 ++++++------------- 3 files changed, 77 insertions(+), 118 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 61205e3bbefa..1da5753d886d 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -196,6 +196,16 @@ struct btrfs_inode { struct list_head delayed_iput; long delayed_iput_count; + /* + * To avoid races between lockless (i_mutex not held) direct IO writes + * and concurrent fsync requests. Direct IO writes must acquire read + * access on this semaphore for creating an extent map and its + * corresponding ordered extent. The fast fsync path must acquire write + * access on this semaphore before it collects ordered extents and + * extent maps. + */ + struct rw_semaphore dio_sem; + struct inode vfs_inode; }; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ee9be4199e7c..c1ee4ade2d87 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7145,6 +7145,43 @@ out: return em; } +static struct extent_map *btrfs_create_dio_extent(struct inode *inode, + const u64 start, + const u64 len, + const u64 orig_start, + const u64 block_start, + const u64 block_len, + const u64 orig_block_len, + const u64 ram_bytes, + const int type) +{ + struct extent_map *em = NULL; + int ret; + + down_read(&BTRFS_I(inode)->dio_sem); + if (type != BTRFS_ORDERED_NOCOW) { + em = create_pinned_em(inode, start, len, orig_start, + block_start, block_len, orig_block_len, + ram_bytes, type); + if (IS_ERR(em)) + goto out; + } + ret = btrfs_add_ordered_extent_dio(inode, start, block_start, + len, block_len, type); + if (ret) { + if (em) { + free_extent_map(em); + btrfs_drop_extent_cache(inode, start, + start + len - 1, 0); + } + em = ERR_PTR(ret); + } + out: + up_read(&BTRFS_I(inode)->dio_sem); + + return em; +} + static struct extent_map *btrfs_new_extent_direct(struct inode *inode, u64 start, u64 len) { @@ -7160,43 +7197,13 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, if (ret) return ERR_PTR(ret); - /* - * Create the ordered extent before the extent map. This is to avoid - * races with the fast fsync path that would lead to it logging file - * extent items that point to disk extents that were not yet written to. - * The fast fsync path collects ordered extents into a local list and - * then collects all the new extent maps, so we must create the ordered - * extent first and make sure the fast fsync path collects any new - * ordered extents after collecting new extent maps as well. - * The fsync path simply can not rely on inode_dio_wait() because it - * causes deadlock with AIO. - */ - ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, - ins.offset, ins.offset, 0); - if (ret) { - btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - return ERR_PTR(ret); - } - + em = btrfs_create_dio_extent(inode, start, ins.offset, start, + ins.objectid, ins.offset, ins.offset, + ins.offset, 0); btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); - - em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, - ins.offset, ins.offset, ins.offset, 0); - if (IS_ERR(em)) { - struct btrfs_ordered_extent *oe; - + if (IS_ERR(em)) btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - oe = btrfs_lookup_ordered_extent(inode, start); - ASSERT(oe); - if (WARN_ON(!oe)) - return em; - set_bit(BTRFS_ORDERED_IOERR, &oe->flags); - set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags); - btrfs_remove_ordered_extent(inode, oe); - /* Once for our lookup and once for the ordered extents tree. */ - btrfs_put_ordered_extent(oe); - btrfs_put_ordered_extent(oe); - } + return em; } @@ -7670,57 +7677,21 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, if (can_nocow_extent(inode, start, &len, &orig_start, &orig_block_len, &ram_bytes) == 1 && btrfs_inc_nocow_writers(root->fs_info, block_start)) { + struct extent_map *em2; - /* - * Create the ordered extent before the extent map. This - * is to avoid races with the fast fsync path because it - * collects ordered extents into a local list and then - * collects all the new extent maps, so we must create - * the ordered extent first and make sure the fast fsync - * path collects any new ordered extents after - * collecting new extent maps as well. The fsync path - * simply can not rely on inode_dio_wait() because it - * causes deadlock with AIO. - */ - ret = btrfs_add_ordered_extent_dio(inode, start, - block_start, len, len, type); + em2 = btrfs_create_dio_extent(inode, start, len, + orig_start, block_start, + len, orig_block_len, + ram_bytes, type); btrfs_dec_nocow_writers(root->fs_info, block_start); - if (ret) { - free_extent_map(em); - goto unlock_err; - } - if (type == BTRFS_ORDERED_PREALLOC) { free_extent_map(em); - em = create_pinned_em(inode, start, len, - orig_start, - block_start, len, - orig_block_len, - ram_bytes, type); - if (IS_ERR(em)) { - struct btrfs_ordered_extent *oe; - - ret = PTR_ERR(em); - oe = btrfs_lookup_ordered_extent(inode, - start); - ASSERT(oe); - if (WARN_ON(!oe)) - goto unlock_err; - set_bit(BTRFS_ORDERED_IOERR, - &oe->flags); - set_bit(BTRFS_ORDERED_IO_DONE, - &oe->flags); - btrfs_remove_ordered_extent(inode, oe); - /* - * Once for our lookup and once for the - * ordered extents tree. - */ - btrfs_put_ordered_extent(oe); - btrfs_put_ordered_extent(oe); - goto unlock_err; - } + em = em2; + } + if (em2 && IS_ERR(em2)) { + ret = PTR_ERR(em2); + goto unlock_err; } - goto unlock; } } @@ -9281,6 +9252,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ei->delalloc_inodes); INIT_LIST_HEAD(&ei->delayed_iput); RB_CLEAR_NODE(&ei->rb_node); + init_rwsem(&ei->dio_sem); return inode; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index a24a0ba523d6..003a826f4cff 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4141,6 +4141,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, INIT_LIST_HEAD(&extents); + down_write(&BTRFS_I(inode)->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; @@ -4169,13 +4170,20 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); + btrfs_get_logged_extents(inode, logged_list, start, end); /* - * Collect any new ordered extents within the range. This is to - * prevent logging file extent items without waiting for the disk - * location they point to being written. We do this only to deal - * with races against concurrent lockless direct IO writes. + * Some ordered extents started by fsync might have completed + * before we could collect them into the list logged_list, which + * means they're gone, not in our logged_list nor in the inode's + * ordered tree. We want the application/user space to know an + * error happened while attempting to persist file data so that + * it can take proper action. If such error happened, we leave + * without writing to the log tree and the fsync must report the + * file data write error and not commit the current transaction. */ - btrfs_get_logged_extents(inode, logged_list, start, end); + ret = btrfs_inode_check_errors(inode); + if (ret) + ctx->io_err = ret; process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); @@ -4202,6 +4210,7 @@ process: } WARN_ON(!list_empty(&extents)); write_unlock(&tree->lock); + up_write(&BTRFS_I(inode)->dio_sem); btrfs_release_path(path); return ret; @@ -4622,23 +4631,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, mutex_lock(&BTRFS_I(inode)->log_mutex); - /* - * Collect ordered extents only if we are logging data. This is to - * ensure a subsequent request to log this inode in LOG_INODE_ALL mode - * will process the ordered extents if they still exists at the time, - * because when we collect them we test and set for the flag - * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the - * same ordered extents. The consequence for the LOG_INODE_ALL log mode - * not processing the ordered extents is that we end up logging the - * corresponding file extent items, based on the extent maps in the - * inode's extent_map_tree's modified_list, without logging the - * respective checksums (since the may still be only attached to the - * ordered extents and have not been inserted in the csum tree by - * btrfs_finish_ordered_io() yet). - */ - if (inode_only == LOG_INODE_ALL) - btrfs_get_logged_extents(inode, &logged_list, start, end); - /* * a brute force approach to making sure we get the most uptodate * copies of everything. @@ -4846,21 +4838,6 @@ log_extents: goto out_unlock; } if (fast_search) { - /* - * Some ordered extents started by fsync might have completed - * before we collected the ordered extents in logged_list, which - * means they're gone, not in our logged_list nor in the inode's - * ordered tree. We want the application/user space to know an - * error happened while attempting to persist file data so that - * it can take proper action. If such error happened, we leave - * without writing to the log tree and the fsync must report the - * file data write error and not commit the current transaction. - */ - err = btrfs_inode_check_errors(inode); - if (err) { - ctx->io_err = err; - goto out_unlock; - } ret = btrfs_log_changed_extents(trans, root, inode, dst_path, &logged_list, ctx, start, end); if (ret) { -- cgit v1.2.3