From 7cddc193924ef6ce679ef0977e01e96d0aedfd1d Mon Sep 17 00:00:00 2001 From: Jie Liu Date: Fri, 28 Jun 2013 13:15:52 +0800 Subject: [PATCH 01/10] btrfs: fix file truncation if FALLOC_FL_KEEP_SIZE is specified Create a small file and fallocate it to a big size with FALLOC_FL_KEEP_SIZE option, then truncate it back to the small size again, the disk free space is not changed back in this case. i.e, total 4 -rw-r--r-- 1 root root 512 Jun 28 11:35 test Filesystem Size Used Avail Use% Mounted on .... /dev/sdb1 8.0G 56K 7.2G 1% /mnt -rw-r--r-- 1 root root 512 Jun 28 11:35 /mnt/test Filesystem Size Used Avail Use% Mounted on .... /dev/sdb1 8.0G 5.1G 2.2G 70% /mnt Filesystem Size Used Avail Use% Mounted on .... /dev/sdb1 8.0G 5.1G 2.2G 70% /mnt With this fix, the truncated up space is back as: Filesystem Size Used Avail Use% Mounted on .... /dev/sdb1 8.0G 56K 7.2G 1% /mnt Signed-off-by: Jie Liu Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6d1b93c8aafb..0fd7647c8932 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4391,9 +4391,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) int mask = attr->ia_valid; int ret; - if (newsize == oldsize) - return 0; - /* * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a * special case where we need to update the times despite not having From e68afa49aec5f0851e550ee1de48fcc3a9bf5ef7 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Mon, 1 Jul 2013 22:13:26 +0800 Subject: [PATCH 02/10] Btrfs: fix a bug of snapshot-aware defrag to make it work on partial extents For partial extents, snapshot-aware defrag does not work as expected, since a) we use the wrong logical offset to search for parents, which should be disk_bytenr + extent_offset, not just disk_bytenr, b) 'offset' returned by the backref walking just refers to key.offset, not the 'offset' stored in btrfs_extent_data_ref which is (key.offset - extent_offset). The reproducer: $ mkfs.btrfs sda $ mount sda /mnt $ btrfs sub create /mnt/sub $ for i in `seq 5 -1 1`; do dd if=/dev/zero of=/mnt/sub/foo bs=5k count=1 seek=$i conv=notrunc oflag=sync; done $ btrfs sub snap /mnt/sub /mnt/snap1 $ btrfs sub snap /mnt/sub /mnt/snap2 $ sync; btrfs filesystem defrag /mnt/sub/foo; $ umount /mnt $ btrfs-debug-tree sda (Here we can check whether the defrag operation is snapshot-awared. This addresses the above two problems. Signed-off-by: Liu Bo Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0fd7647c8932..c72033ee6017 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2166,16 +2166,23 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id, if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr) continue; - extent_offset = btrfs_file_extent_offset(leaf, extent); - if (key.offset - extent_offset != offset) + /* + * 'offset' refers to the exact key.offset, + * NOT the 'offset' field in btrfs_extent_data_ref, ie. + * (key.offset - extent_offset). + */ + if (key.offset != offset) continue; + extent_offset = btrfs_file_extent_offset(leaf, extent); num_bytes = btrfs_file_extent_num_bytes(leaf, extent); + if (extent_offset >= old->extent_offset + old->offset + old->len || extent_offset + num_bytes <= old->extent_offset + old->offset) continue; + ret = 0; break; } @@ -2187,7 +2194,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id, backref->root_id = root_id; backref->inum = inum; - backref->file_pos = offset + extent_offset; + backref->file_pos = offset; backref->num_bytes = num_bytes; backref->extent_offset = extent_offset; backref->generation = btrfs_file_extent_generation(leaf, extent); @@ -2210,7 +2217,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path, new->path = path; list_for_each_entry_safe(old, tmp, &new->head, list) { - ret = iterate_inodes_from_logical(old->bytenr, fs_info, + ret = iterate_inodes_from_logical(old->bytenr + + old->extent_offset, fs_info, path, record_one_backref, old); BUG_ON(ret < 0 && ret != -ENOENT); From b5b9b5b318f9b6fef1bd3e2c8c63d0bff47703a1 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 3 Jul 2013 14:40:44 +0800 Subject: [PATCH 03/10] Btrfs: fix extent buffer leak after backref walking commit 47fb091fb787420cd195e66f162737401cce023f(Btrfs: fix unlock after free on rewinded tree blocks) takes an extra increment on the reference of allocated dummy extent buffer, so now we cannot free this dummy one, and end up with extent buffer leak. Signed-off-by: Liu Bo Reviewed-by: Jan Schmidt Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5bf4c39e2ad6..ed504607d8ec 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1271,7 +1271,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, BUG_ON(!eb_rewin); } - extent_buffer_get(eb_rewin); btrfs_tree_read_unlock(eb); free_extent_buffer(eb); From b76bb70136375c32d3b0bbbe2ebef738913d5b90 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 5 Jul 2013 13:52:51 -0400 Subject: [PATCH 04/10] Btrfs: do not offset physical if we're compressed xfstest btrfs/276 was freaking out on slower boxes partly because fiemap was offsetting the physical based on the extent offset. This is perfectly fine with uncompressed extents, however the extent offset is into the uncompressed area, not the compressed. So we can return a physical value that isn't at all within the area we have allocated on disk. Fix this by returning the start of the extent if it is compressed no matter what the offset. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent_io.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 583d98bd065e..fe443fece851 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4048,7 +4048,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } while (!end) { - u64 offset_in_extent; + u64 offset_in_extent = 0; /* break if the extent we found is outside the range */ if (em->start >= max || extent_map_end(em) < off) @@ -4064,9 +4064,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* * record the offset from the start of the extent - * for adjusting the disk offset below + * for adjusting the disk offset below. Only do this if the + * extent isn't compressed since our in ram offset may be past + * what we have actually allocated on disk. */ - offset_in_extent = em_start - em->start; + if (!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) + offset_in_extent = em_start - em->start; em_end = extent_map_end(em); em_len = em_end - em_start; emflags = em->flags; From 8ca15e05e6ac2745725d2d62394cfbe4ac335e84 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 5 Jul 2013 13:58:19 -0400 Subject: [PATCH 05/10] Btrfs: fix backref walking when we hit a compressed extent If you do btrfs inspect-internal logical-resolve on a compressed extent that has been partly overwritten it won't find anything. This is because we try and match the extent offset we've searched for based on the extent offset in the data extent entry. However this doesn't work for compressed extents because the offsets are for the uncompressed size, not the compressed size. So instead only do this check if we are not compressed, that way we can get an actual entry for the physical offset rather than nothing for compressed. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/backref.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index eaf133384a8f..30dbe1c61857 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -36,16 +36,23 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb, u64 extent_item_pos, struct extent_inode_elem **eie) { - u64 data_offset; - u64 data_len; + u64 offset = 0; struct extent_inode_elem *e; - data_offset = btrfs_file_extent_offset(eb, fi); - data_len = btrfs_file_extent_num_bytes(eb, fi); + if (!btrfs_file_extent_compression(eb, fi) && + !btrfs_file_extent_encryption(eb, fi) && + !btrfs_file_extent_other_encoding(eb, fi)) { + u64 data_offset; + u64 data_len; - if (extent_item_pos < data_offset || - extent_item_pos >= data_offset + data_len) - return 1; + data_offset = btrfs_file_extent_offset(eb, fi); + data_len = btrfs_file_extent_num_bytes(eb, fi); + + if (extent_item_pos < data_offset || + extent_item_pos >= data_offset + data_len) + return 1; + offset = extent_item_pos - data_offset; + } e = kmalloc(sizeof(*e), GFP_NOFS); if (!e) @@ -53,7 +60,7 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb, e->next = *eie; e->inum = key->objectid; - e->offset = key->offset + (extent_item_pos - data_offset); + e->offset = key->offset + offset; *eie = e; return 0; From ed8c4913da4951957bf8afc788522788881ff405 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 5 Jul 2013 14:03:47 -0400 Subject: [PATCH 06/10] Btrfs: make sure the backref walker catches all refs to our extent Because we don't mess with the offset into the extent for compressed we will properly find both extents for this case [extent a][extent b][rest of extent a] but because we already added a ref for the front half we won't add the inode information for the second half. This causes us to leak that memory and not print out the other offset when we do logical-resolve. So fix this by calling ulist_add_merge and then add our eie to the existing entry if there is one. With this patch we get both offsets out of logical-resolve. With this and the other 2 patches I've sent we now pass btrfs/276 on my vm with compress-force=lzo set. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/backref.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 30dbe1c61857..8bc5e8ccb091 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -196,7 +196,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb; struct btrfs_key key; struct btrfs_file_extent_item *fi; - struct extent_inode_elem *eie = NULL; + struct extent_inode_elem *eie = NULL, *old = NULL; u64 disk_byte; if (level != 0) { @@ -230,6 +230,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, if (disk_byte == wanted_disk_byte) { eie = NULL; + old = NULL; if (extent_item_pos) { ret = check_extent_in_eb(&key, eb, fi, *extent_item_pos, @@ -237,18 +238,20 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, if (ret < 0) break; } - if (!ret) { - ret = ulist_add(parents, eb->start, - (uintptr_t)eie, GFP_NOFS); - if (ret < 0) - break; - if (!extent_item_pos) { - ret = btrfs_next_old_leaf(root, path, - time_seq); - continue; - } + if (ret > 0) + goto next; + ret = ulist_add_merge(parents, eb->start, + (uintptr_t)eie, + (u64 *)&old, GFP_NOFS); + if (ret < 0) + break; + if (!ret && extent_item_pos) { + while (old->next) + old = old->next; + old->next = eie; } } +next: ret = btrfs_next_old_item(root, path, time_seq); } From ee20a98314e52a6675e94d1a07ca205ffdf09a72 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 11 Jul 2013 10:34:59 -0400 Subject: [PATCH 07/10] Btrfs: allow splitting of hole em's when dropping extent cache I noticed while running multi-threaded fsync tests that sometimes fsck would complain about an improper gap. This happens because we fail to add a hole extent to the file, which was happening when we'd split a hole EM because btrfs_drop_extent_cache was just discarding the whole em instead of splitting it. So this patch fixes this by allowing us to split a hole em properly, which means that added holes actually get logged properly and we no longer see this fsck error. Thankfully we're tolerant of these sort of problems so a user would not see any adverse effects of this bug, other than fsck complaining. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 64 +++++++++++++++++++++++++++++++------------------ 1 file changed, 41 insertions(+), 23 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a005fe2c072a..8e686a427ce2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -596,20 +596,29 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, if (no_splits) goto next; - if (em->block_start < EXTENT_MAP_LAST_BYTE && - em->start < start) { + if (em->start < start) { split->start = em->start; split->len = start - em->start; - split->orig_start = em->orig_start; - split->block_start = em->block_start; - if (compressed) - split->block_len = em->block_len; - else - split->block_len = split->len; - split->ram_bytes = em->ram_bytes; - split->orig_block_len = max(split->block_len, - em->orig_block_len); + if (em->block_start < EXTENT_MAP_LAST_BYTE) { + split->orig_start = em->orig_start; + split->block_start = em->block_start; + + if (compressed) + split->block_len = em->block_len; + else + split->block_len = split->len; + split->orig_block_len = max(split->block_len, + em->orig_block_len); + split->ram_bytes = em->ram_bytes; + } else { + split->orig_start = split->start; + split->block_len = 0; + split->block_start = em->block_start; + split->orig_block_len = 0; + split->ram_bytes = split->len; + } + split->generation = gen; split->bdev = em->bdev; split->flags = flags; @@ -620,8 +629,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split = split2; split2 = NULL; } - if (em->block_start < EXTENT_MAP_LAST_BYTE && - testend && em->start + em->len > start + len) { + if (testend && em->start + em->len > start + len) { u64 diff = start + len - em->start; split->start = start + len; @@ -630,18 +638,28 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split->flags = flags; split->compress_type = em->compress_type; split->generation = gen; - split->orig_block_len = max(em->block_len, - em->orig_block_len); - split->ram_bytes = em->ram_bytes; - if (compressed) { - split->block_len = em->block_len; - split->block_start = em->block_start; - split->orig_start = em->orig_start; + if (em->block_start < EXTENT_MAP_LAST_BYTE) { + split->orig_block_len = max(em->block_len, + em->orig_block_len); + + split->ram_bytes = em->ram_bytes; + if (compressed) { + split->block_len = em->block_len; + split->block_start = em->block_start; + split->orig_start = em->orig_start; + } else { + split->block_len = split->len; + split->block_start = em->block_start + + diff; + split->orig_start = em->orig_start; + } } else { - split->block_len = split->len; - split->block_start = em->block_start + diff; - split->orig_start = em->orig_start; + split->ram_bytes = split->len; + split->orig_start = split->start; + split->block_len = 0; + split->block_start = em->block_start; + split->orig_block_len = 0; } ret = add_extent_mapping(em_tree, split, modified); From f3b15ccdbb9a79781578249a63318805e55a6c34 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 22 Jul 2013 12:54:30 -0400 Subject: [PATCH 08/10] Btrfs: release both paths before logging dir/changed extents The ceph guys tripped over this bug where we were still holding onto the original path that we used to copy the inode with when logging. This is based on Chris's fix which was reported to fix the problem. We need to drop the paths in two cases anyway so just move the drop up so that we don't have duplicate code. Thanks, Cc: stable@vger.kernel.org Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2c6791493637..ff60d8978ae2 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3746,8 +3746,9 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } log_extents: + btrfs_release_path(path); + btrfs_release_path(dst_path); if (fast_search) { - btrfs_release_path(dst_path); ret = btrfs_log_changed_extents(trans, root, inode, dst_path); if (ret) { err = ret; @@ -3764,8 +3765,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) { - btrfs_release_path(path); - btrfs_release_path(dst_path); ret = log_directory_changes(trans, root, inode, path, dst_path); if (ret) { err = ret; From cfad392b22163eba71d882950e17d2c4d43b2bad Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 25 Jul 2013 15:11:47 -0400 Subject: [PATCH 09/10] Btrfs: check to see if root_list is empty before adding it to dead roots A user reported a panic when running with autodefrag and deleting snapshots. This is because we could end up trying to add the root to the dead roots list twice. To fix this check to see if we are empty before adding ourselves to the dead roots list. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 8 ++++---- fs/btrfs/transaction.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index d58cce77fc6c..af1931a5960d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -983,12 +983,12 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, * a dirty root struct and adds it into the list of dead roots that need to * be deleted */ -int btrfs_add_dead_root(struct btrfs_root *root) +void btrfs_add_dead_root(struct btrfs_root *root) { spin_lock(&root->fs_info->trans_lock); - list_add_tail(&root->root_list, &root->fs_info->dead_roots); + if (list_empty(&root->root_list)) + list_add_tail(&root->root_list, &root->fs_info->dead_roots); spin_unlock(&root->fs_info->trans_lock); - return 0; } /* @@ -1925,7 +1925,7 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root) } root = list_first_entry(&fs_info->dead_roots, struct btrfs_root, root_list); - list_del(&root->root_list); + list_del_init(&root->root_list); spin_unlock(&fs_info->trans_lock); pr_debug("btrfs: cleaner removing %llu\n", diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 005b0375d18c..defbc4269897 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -143,7 +143,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid); int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); -int btrfs_add_dead_root(struct btrfs_root *root); +void btrfs_add_dead_root(struct btrfs_root *root); int btrfs_defrag_root(struct btrfs_root *root); int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root); int btrfs_commit_transaction(struct btrfs_trans_handle *trans, From db62efbbf883c099d44b0fafe18f8ad8f0396892 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Thu, 11 Jul 2013 16:19:42 -0700 Subject: [PATCH 10/10] btrfs: don't loop on large offsets in readdir When btrfs readdir() hits the last entry it sets the readdir offset to a huge value to stop buggy apps from breaking when the same name is returned by readdir() with concurrent rename()s. But unconditionally setting the offset to INT_MAX causes readdir() to loop returning any entries with offsets past INT_MAX. It only takes a few hours of constant file creation and removal to create entries past INT_MAX. So let's set the huge offset to LLONG_MAX if the last entry has already overflowed 32bit loff_t. Without large offsets behaviour is identical. With large offsets 64bit apps will work and 32bit apps will be no more broken than they currently are if they see large offsets. Signed-off-by: Zach Brown Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 33 +++++++++++++++++++++++++-------- 1 file changed, 25 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c72033ee6017..021694c08181 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5170,14 +5170,31 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) } /* Reached end of directory/root. Bump pos past the last item. */ - if (key_type == BTRFS_DIR_INDEX_KEY) - /* - * 32-bit glibc will use getdents64, but then strtol - - * so the last number we can serve is this. - */ - ctx->pos = 0x7fffffff; - else - ctx->pos++; + ctx->pos++; + + /* + * Stop new entries from being returned after we return the last + * entry. + * + * New directory entries are assigned a strictly increasing + * offset. This means that new entries created during readdir + * are *guaranteed* to be seen in the future by that readdir. + * This has broken buggy programs which operate on names as + * they're returned by readdir. Until we re-use freed offsets + * we have this hack to stop new entries from being returned + * under the assumption that they'll never reach this huge + * offset. + * + * This is being careful not to overflow 32bit loff_t unless the + * last entry requires it because doing so has broken 32bit apps + * in the past. + */ + if (key_type == BTRFS_DIR_INDEX_KEY) { + if (ctx->pos >= INT_MAX) + ctx->pos = LLONG_MAX; + else + ctx->pos = INT_MAX; + } nopos: ret = 0; err: