From d8926bb3badd36670fecf2de4a062c78bc37430b Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Wed, 13 Jul 2011 10:38:47 -0700 Subject: btrfs: don't BUG_ON btrfs_alloc_path() errors This patch fixes many callers of btrfs_alloc_path() which BUG_ON allocation failure. All the sites that are fixed in this patch were checked by me to be fairly trivial to fix because of at least one of two criteria: - Callers of the function catch errors from it already so bubbling the error up will be handled. - Callers of the function might BUG_ON any nonzero return code in which case there is no behavior changed (but we still got to remove a BUG_ON) The following functions were updated: btrfs_lookup_extent, alloc_reserved_tree_block, btrfs_remove_block_group, btrfs_lookup_csums_range, btrfs_csum_file_blocks, btrfs_mark_extent_written, btrfs_inode_by_name, btrfs_new_inode, btrfs_symlink, insert_reserved_file_extent, and run_delalloc_nocow Signed-off-by: Mark Fasheh --- fs/btrfs/file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index fa4ef18b66b1..23d1d811e2b2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -855,7 +855,8 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, btrfs_drop_extent_cache(inode, start, end - 1, 0); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; again: recow = 0; split = start; -- cgit v1.2.3 From b26751575a9aa55fd6dbf3febde3ff06dfadc44f Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 18 Jul 2011 13:21:36 -0400 Subject: Btrfs: implement our own ->llseek In order to handle SEEK_HOLE/SEEK_DATA we need to implement our own llseek. Basically for the normal SEEK_*'s we will just defer to the generic helper, and for SEEK_HOLE/SEEK_DATA we will use our fiemap helper to figure out the nearest hole or data. Currently this helper doesn't check for delalloc bytes for prealloc space, so for now treat prealloc as data until that is fixed. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- fs/btrfs/file.c | 148 +++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 147 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index fa4ef18b66b1..bd4d061c6e4d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1664,8 +1664,154 @@ out: return ret; } +static int find_desired_extent(struct inode *inode, loff_t *offset, int origin) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + struct extent_map *em; + struct extent_state *cached_state = NULL; + u64 lockstart = *offset; + u64 lockend = i_size_read(inode); + u64 start = *offset; + u64 orig_start = *offset; + u64 len = i_size_read(inode); + u64 last_end = 0; + int ret = 0; + + lockend = max_t(u64, root->sectorsize, lockend); + if (lockend <= lockstart) + lockend = lockstart + root->sectorsize; + + len = lockend - lockstart + 1; + + len = max_t(u64, len, root->sectorsize); + if (inode->i_size == 0) + return -ENXIO; + + lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0, + &cached_state, GFP_NOFS); + + /* + * Delalloc is such a pain. If we have a hole and we have pending + * delalloc for a portion of the hole we will get back a hole that + * exists for the entire range since it hasn't been actually written + * yet. So to take care of this case we need to look for an extent just + * before the position we want in case there is outstanding delalloc + * going on here. + */ + if (origin == SEEK_HOLE && start != 0) { + if (start <= root->sectorsize) + em = btrfs_get_extent_fiemap(inode, NULL, 0, 0, + root->sectorsize, 0); + else + em = btrfs_get_extent_fiemap(inode, NULL, 0, + start - root->sectorsize, + root->sectorsize, 0); + if (IS_ERR(em)) { + ret = -ENXIO; + goto out; + } + last_end = em->start + em->len; + if (em->block_start == EXTENT_MAP_DELALLOC) + last_end = min_t(u64, last_end, inode->i_size); + free_extent_map(em); + } + + while (1) { + em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0); + if (IS_ERR(em)) { + ret = -ENXIO; + break; + } + + if (em->block_start == EXTENT_MAP_HOLE) { + if (test_bit(EXTENT_FLAG_VACANCY, &em->flags)) { + if (last_end <= orig_start) { + free_extent_map(em); + ret = -ENXIO; + break; + } + } + + if (origin == SEEK_HOLE) { + *offset = start; + free_extent_map(em); + break; + } + } else { + if (origin == SEEK_DATA) { + if (em->block_start == EXTENT_MAP_DELALLOC) { + if (start >= inode->i_size) { + free_extent_map(em); + ret = -ENXIO; + break; + } + } + + *offset = start; + free_extent_map(em); + break; + } + } + + start = em->start + em->len; + last_end = em->start + em->len; + + if (em->block_start == EXTENT_MAP_DELALLOC) + last_end = min_t(u64, last_end, inode->i_size); + + if (test_bit(EXTENT_FLAG_VACANCY, &em->flags)) { + free_extent_map(em); + ret = -ENXIO; + break; + } + free_extent_map(em); + cond_resched(); + } + if (!ret) + *offset = min(*offset, inode->i_size); +out: + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, + &cached_state, GFP_NOFS); + return ret; +} + +static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) +{ + struct inode *inode = file->f_mapping->host; + int ret; + + mutex_lock(&inode->i_mutex); + switch (origin) { + case SEEK_END: + case SEEK_CUR: + offset = generic_file_llseek_unlocked(file, offset, origin); + goto out; + case SEEK_DATA: + case SEEK_HOLE: + ret = find_desired_extent(inode, &offset, origin); + if (ret) { + mutex_unlock(&inode->i_mutex); + return ret; + } + } + + if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) + return -EINVAL; + if (offset > inode->i_sb->s_maxbytes) + return -EINVAL; + + /* Special lock needed here? */ + if (offset != file->f_pos) { + file->f_pos = offset; + file->f_version = 0; + } +out: + mutex_unlock(&inode->i_mutex); + return offset; +} + const struct file_operations btrfs_file_operations = { - .llseek = generic_file_llseek, + .llseek = btrfs_file_llseek, .read = do_sync_read, .write = do_sync_write, .aio_read = generic_file_aio_read, -- cgit v1.2.3 From 02c24a82187d5a628c68edfe71ae60dc135cd178 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Sat, 16 Jul 2011 20:44:56 -0400 Subject: fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers Btrfs needs to be able to control how filemap_write_and_wait_range() is called in fsync to make it less of a painful operation, so push down taking i_mutex and the calling of filemap_write_and_wait() down into the ->fsync() handlers. Some file systems can drop taking the i_mutex altogether it seems, like ext3 and ocfs2. For correctness sake I just pushed everything down in all cases to make sure that we keep the current behavior the same for everybody, and then each individual fs maintainer can make up their mind about what to do from there. Thanks, Acked-by: Jan Kara Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- fs/btrfs/file.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index bd4d061c6e4d..59cbdb120ad0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1452,7 +1452,7 @@ int btrfs_release_file(struct inode *inode, struct file *filp) * important optimization for directories because holding the mutex prevents * new operations on the dir while we write to disk. */ -int btrfs_sync_file(struct file *file, int datasync) +int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; @@ -1462,9 +1462,13 @@ int btrfs_sync_file(struct file *file, int datasync) trace_btrfs_sync_file(file, datasync); + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret) + return ret; + mutex_lock(&inode->i_mutex); + /* we wait first, since the writeback may change the inode */ root->log_batch++; - /* the VFS called filemap_fdatawrite for us */ btrfs_wait_ordered_range(inode, 0, (u64)-1); root->log_batch++; @@ -1472,8 +1476,10 @@ int btrfs_sync_file(struct file *file, int datasync) * check the transaction that last modified this inode * and see if its already been committed */ - if (!BTRFS_I(inode)->last_trans) + if (!BTRFS_I(inode)->last_trans) { + mutex_unlock(&inode->i_mutex); goto out; + } /* * if the last transaction that changed this file was before @@ -1484,6 +1490,7 @@ int btrfs_sync_file(struct file *file, int datasync) if (BTRFS_I(inode)->last_trans <= root->fs_info->last_trans_committed) { BTRFS_I(inode)->last_trans = 0; + mutex_unlock(&inode->i_mutex); goto out; } @@ -1496,12 +1503,15 @@ int btrfs_sync_file(struct file *file, int datasync) trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + mutex_unlock(&inode->i_mutex); goto out; } ret = btrfs_log_dentry_safe(trans, root, dentry); - if (ret < 0) + if (ret < 0) { + mutex_unlock(&inode->i_mutex); goto out; + } /* we've logged all the items and now have a consistent * version of the file in the log. It is possible that @@ -1513,7 +1523,7 @@ int btrfs_sync_file(struct file *file, int datasync) * file again, but that will end up using the synchronization * inside btrfs_sync_log to keep things safe. */ - mutex_unlock(&dentry->d_inode->i_mutex); + mutex_unlock(&inode->i_mutex); if (ret != BTRFS_NO_LOG_SYNC) { if (ret > 0) { @@ -1528,7 +1538,6 @@ int btrfs_sync_file(struct file *file, int datasync) } else { ret = btrfs_end_transaction(trans, root); } - mutex_lock(&dentry->d_inode->i_mutex); out: return ret > 0 ? -EIO : ret; } -- cgit v1.2.3 From a94733d0bc630edaedc6ca156752dd5a7cb82521 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 11 Jul 2011 10:47:06 -0400 Subject: Btrfs: use find_or_create_page instead of grab_cache_page grab_cache_page will use mapping_gfp_mask(), which for all inodes is set to GFP_HIGHUSER_MOVABLE. So instead use find_or_create_page in all cases where we need GFP_NOFS so we don't deadlock. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index fa4ef18b66b1..bd6bbb877ff2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1081,7 +1081,8 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, again: for (i = 0; i < num_pages; i++) { - pages[i] = grab_cache_page(inode->i_mapping, index + i); + pages[i] = find_or_create_page(inode->i_mapping, index + i, + GFP_NOFS); if (!pages[i]) { faili = i - 1; err = -ENOMEM; -- cgit v1.2.3 From 9e0baf60dea69f31ac3b1adeb35b03b02a53e8e1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 15 Jul 2011 15:16:44 +0000 Subject: Btrfs: fix enospc problems with delalloc So I had this brilliant idea to use atomic counters for outstanding and reserved extents, but this turned out to be a bad idea. Consider this where we have 1 outstanding extent and 1 reserved extent Reserver Releaser atomic_dec(outstanding) now 0 atomic_read(outstanding)+1 get 1 atomic_read(reserved) get 1 don't actually reserve anything because they are the same atomic_cmpxchg(reserved, 1, 0) atomic_inc(outstanding) atomic_add(0, reserved) free reserved space for 1 extent Then the reserver now has no actual space reserved for it, and when it goes to finish the ordered IO it won't have enough space to do it's allocation and you get those lovely warnings. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index bd6bbb877ff2..6e56a468d1f5 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1239,9 +1239,11 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, * managed to copy. */ if (num_pages > dirty_pages) { - if (copied > 0) - atomic_inc( - &BTRFS_I(inode)->outstanding_extents); + if (copied > 0) { + spin_lock(&BTRFS_I(inode)->lock); + BTRFS_I(inode)->outstanding_extents++; + spin_unlock(&BTRFS_I(inode)->lock); + } btrfs_delalloc_release_space(inode, (num_pages - dirty_pages) << PAGE_CACHE_SHIFT); -- cgit v1.2.3 From a0f98dde11a1afe9fbf5c98f57968e086e98b6f5 Mon Sep 17 00:00:00 2001 From: Wanlong Gao Date: Mon, 18 Jul 2011 12:19:35 +0000 Subject: Btrfs:don't check the return value of __btrfs_add_inode_defrag Don't need to check the return value of __btrfs_add_inode_defrag(), since it will always return 0. Signed-off-by: Wanlong Gao Signed-off-by: Chris Mason --- fs/btrfs/file.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 41ca5fdaee6c..7f134a730efb 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -74,7 +74,7 @@ struct inode_defrag { * If an existing record is found the defrag item you * pass in is freed */ -static int __btrfs_add_inode_defrag(struct inode *inode, +static void __btrfs_add_inode_defrag(struct inode *inode, struct inode_defrag *defrag) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -106,11 +106,11 @@ static int __btrfs_add_inode_defrag(struct inode *inode, BTRFS_I(inode)->in_defrag = 1; rb_link_node(&defrag->rb_node, parent, p); rb_insert_color(&defrag->rb_node, &root->fs_info->defrag_inodes); - return 0; + return; exists: kfree(defrag); - return 0; + return; } @@ -123,7 +123,6 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, { struct btrfs_root *root = BTRFS_I(inode)->root; struct inode_defrag *defrag; - int ret = 0; u64 transid; if (!btrfs_test_opt(root, AUTO_DEFRAG)) @@ -150,9 +149,9 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, spin_lock(&root->fs_info->defrag_inodes_lock); if (!BTRFS_I(inode)->in_defrag) - ret = __btrfs_add_inode_defrag(inode, defrag); + __btrfs_add_inode_defrag(inode, defrag); spin_unlock(&root->fs_info->defrag_inodes_lock); - return ret; + return 0; } /* -- cgit v1.2.3 From 341d14f161a475ebdbc9adff1f7e681e1185dee9 Mon Sep 17 00:00:00 2001 From: Mitch Harder Date: Tue, 12 Jul 2011 19:43:45 +0000 Subject: Btrfs: Remove unused variable 'last_index' in file.c The variable 'last_index' is calculated in the __btrfs_buffered_write function and passed as a parameter to the prepare_pages function, but is not used anywhere in the prepare_pages function. Remove instances of 'last_index' in these functions. Signed-off-by: Mitch Harder Signed-off-by: Chris Mason --- fs/btrfs/file.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7f134a730efb..010aec8be824 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1059,7 +1059,7 @@ static int prepare_uptodate_page(struct page *page, u64 pos) static noinline int prepare_pages(struct btrfs_root *root, struct file *file, struct page **pages, size_t num_pages, loff_t pos, unsigned long first_index, - unsigned long last_index, size_t write_bytes) + size_t write_bytes) { struct extent_state *cached_state = NULL; int i; @@ -1159,7 +1159,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; unsigned long first_index; - unsigned long last_index; size_t num_written = 0; int nrptrs; int ret = 0; @@ -1172,7 +1171,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, return -ENOMEM; first_index = pos >> PAGE_CACHE_SHIFT; - last_index = (pos + iov_iter_count(i)) >> PAGE_CACHE_SHIFT; while (iov_iter_count(i) > 0) { size_t offset = pos & (PAGE_CACHE_SIZE - 1); @@ -1206,8 +1204,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, * contents of pages from loop to loop */ ret = prepare_pages(root, file, pages, num_pages, - pos, first_index, last_index, - write_bytes); + pos, first_index, write_bytes); if (ret) { btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT); -- cgit v1.2.3