From 4c63c2454eff996c5e27991221106eb511f7db38 Mon Sep 17 00:00:00 2001 From: Luke Dashjr Date: Thu, 29 Oct 2015 08:22:21 +0000 Subject: btrfs: bugfix: handle FS_IOC32_{GETFLAGS,SETFLAGS,GETVERSION} in btrfs_ioctl 32-bit ioctl uses these rather than the regular FS_IOC_* versions. They can be handled in btrfs using the same code. Without this, 32-bit {ch,ls}attr fail. Signed-off-by: Luke Dashjr Cc: stable@vger.kernel.org Reviewed-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2aaba58b4856..167fc3d49450 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10184,7 +10184,7 @@ static const struct file_operations btrfs_dir_file_operations = { .iterate = btrfs_real_readdir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = btrfs_ioctl, + .compat_ioctl = btrfs_compat_ioctl, #endif .release = btrfs_release_file, .fsync = btrfs_sync_file, -- cgit From 91166212e0ffbb4db50aa8a238548e967008b33d Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 26 Apr 2016 23:54:39 +0200 Subject: btrfs: sink gfp parameter to clear_extent_bits Callers pass GFP_NOFS and GFP_KERNEL. No need to pass the flags around. Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 2 +- fs/btrfs/extent-tree.c | 8 ++++---- fs/btrfs/extent_io.c | 4 ++-- fs/btrfs/extent_io.h | 5 +++-- fs/btrfs/inode.c | 3 +-- fs/btrfs/relocation.c | 3 +-- fs/btrfs/scrub.c | 2 +- fs/btrfs/tests/extent-io-tests.c | 2 +- fs/btrfs/tree-log.c | 2 +- 9 files changed, 15 insertions(+), 16 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4e47849d7427..3bc88b4b0032 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4357,7 +4357,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, if (ret) break; - clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS); + clear_extent_bits(dirty_pages, start, end, mark); while (start <= end) { eb = btrfs_find_tree_block(root->fs_info, start); start += root->nodesize; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0cfddbe8abba..b1c6d7634e88 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -246,9 +246,9 @@ static void free_excluded_extents(struct btrfs_root *root, end = start + cache->key.offset - 1; clear_extent_bits(&root->fs_info->freed_extents[0], - start, end, EXTENT_UPTODATE, GFP_NOFS); + start, end, EXTENT_UPTODATE); clear_extent_bits(&root->fs_info->freed_extents[1], - start, end, EXTENT_UPTODATE, GFP_NOFS); + start, end, EXTENT_UPTODATE); } static int exclude_super_stripes(struct btrfs_root *root, @@ -10526,14 +10526,14 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) */ mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = clear_extent_bits(&fs_info->freed_extents[0], start, end, - EXTENT_DIRTY, GFP_NOFS); + EXTENT_DIRTY); if (ret) { mutex_unlock(&fs_info->unused_bg_unpin_mutex); btrfs_dec_block_group_ro(root, block_group); goto end_trans; } ret = clear_extent_bits(&fs_info->freed_extents[1], start, end, - EXTENT_DIRTY, GFP_NOFS); + EXTENT_DIRTY); if (ret) { mutex_unlock(&fs_info->unused_bg_unpin_mutex); btrfs_dec_block_group_ro(root, block_group); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3b53d217066c..2946c1522870 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1975,13 +1975,13 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec) set_state_failrec(failure_tree, rec->start, NULL); ret = clear_extent_bits(failure_tree, rec->start, rec->start + rec->len - 1, - EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS); + EXTENT_LOCKED | EXTENT_DIRTY); if (ret) err = ret; ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start, rec->start + rec->len - 1, - EXTENT_DAMAGED, GFP_NOFS); + EXTENT_DAMAGED); if (ret && !err) err = ret; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 447c6e6ff88c..90c5c8176162 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -241,14 +241,15 @@ static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start, } static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, - u64 end, unsigned bits, gfp_t mask) + u64 end, unsigned bits) { int wake = 0; if (bits & EXTENT_LOCKED) wake = 1; - return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask); + return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, + GFP_NOFS); } int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2aaba58b4856..d37997f4eb98 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3103,8 +3103,7 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio, if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID && test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) { - clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM, - GFP_NOFS); + clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM); return 0; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 78cbfb530de6..bd5ea1a8a9f1 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4059,8 +4059,7 @@ restart: } btrfs_release_path(path); - clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY, - GFP_NOFS); + clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY); if (trans) { btrfs_end_transaction_throttle(trans, rc->extent_root); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 9d24375eed1f..841dae874a21 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -763,7 +763,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) end, EXTENT_DAMAGED, 0, NULL); if (!corrected) clear_extent_bits(&BTRFS_I(inode)->io_tree, offset, end, - EXTENT_DAMAGED, GFP_NOFS); + EXTENT_DAMAGED); } out: diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 70948b13bc81..88e28e5d2c38 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -262,7 +262,7 @@ static int test_find_delalloc(void) } ret = 0; out_bits: - clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL); + clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1); out: if (locked_page) put_page(locked_page); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 517d0ccb351e..a111e275ab9e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3001,7 +3001,7 @@ static void free_log_tree(struct btrfs_trans_handle *trans, break; clear_extent_bits(&log->dirty_log_pages, start, end, - EXTENT_DIRTY | EXTENT_NEW, GFP_NOFS); + EXTENT_DIRTY | EXTENT_NEW); } /* -- cgit From 7cd8c7527cb3ad3b397fecfa1bdc8eec9fa33dd8 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 26 Apr 2016 23:54:39 +0200 Subject: btrfs: sink gfp parameter to set_extent_delalloc Callers pass GFP_NOFS and tests pass GFP_KERNEL, but using NOFS there does not hurt. No need to pass the flags around. Signed-off-by: David Sterba --- fs/btrfs/extent_io.h | 4 ++-- fs/btrfs/inode.c | 2 +- fs/btrfs/tests/extent-io-tests.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 9e987ee03361..e99a6befdbf5 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -291,11 +291,11 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state, gfp_t mask) + u64 end, struct extent_state **cached_state) { return set_extent_bit(tree, start, end, EXTENT_DELALLOC | EXTENT_UPTODATE, - NULL, cached_state, mask); + NULL, cached_state, GFP_NOFS); } static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d37997f4eb98..1a4bd193962c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1962,7 +1962,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, { WARN_ON((end & (PAGE_SIZE - 1)) == 0); return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end, - cached_state, GFP_NOFS); + cached_state); } /* see btrfs_writepage_start_hook for details on why this is required */ diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 88e28e5d2c38..c190d2a520d1 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -113,7 +113,7 @@ static int test_find_delalloc(void) * |--- delalloc ---| * |--- search ---| */ - set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL); + set_extent_delalloc(&tmp, 0, 4095, NULL); start = 0; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -144,7 +144,7 @@ static int test_find_delalloc(void) test_msg("Couldn't find the locked page\n"); goto out_bits; } - set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL); + set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -199,7 +199,7 @@ static int test_find_delalloc(void) * * We are re-using our test_start from above since it works out well. */ - set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL); + set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, -- cgit From c8b8e32d700fe943a935e435ae251364d016c497 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 7 Apr 2016 08:51:58 -0700 Subject: direct-io: eliminate the offset argument to ->direct_IO Including blkdev_direct_IO and dax_do_io. It has to be ki_pos to actually work, so eliminate the superflous argument. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- Documentation/filesystems/Locking | 2 +- Documentation/filesystems/vfs.txt | 2 +- drivers/staging/lustre/lustre/llite/rw26.c | 4 ++-- fs/9p/vfs_addr.c | 3 ++- fs/affs/file.c | 5 +++-- fs/block_dev.c | 6 +++--- fs/btrfs/inode.c | 6 +++--- fs/ceph/addr.c | 3 +-- fs/cifs/file.c | 2 +- fs/dax.c | 4 ++-- fs/direct-io.c | 7 ++++--- fs/exofs/inode.c | 3 +-- fs/ext2/inode.c | 8 ++++---- fs/ext4/ext4.h | 3 +-- fs/ext4/indirect.c | 12 ++++++------ fs/ext4/inode.c | 18 +++++++++--------- fs/f2fs/data.c | 6 +++--- fs/fat/inode.c | 6 +++--- fs/fuse/file.c | 3 ++- fs/gfs2/aops.c | 6 +++--- fs/hfs/inode.c | 7 +++---- fs/hfsplus/inode.c | 7 +++---- fs/jfs/inode.c | 7 +++---- fs/nfs/direct.c | 17 +++++++---------- fs/nfs/file.c | 2 +- fs/nilfs2/inode.c | 4 ++-- fs/ocfs2/aops.c | 9 ++++----- fs/reiserfs/inode.c | 7 +++---- fs/udf/file.c | 3 +-- fs/udf/inode.c | 7 +++---- fs/xfs/xfs_aops.c | 7 +++---- fs/xfs/xfs_file.c | 2 +- include/linux/dax.h | 2 +- include/linux/fs.h | 9 ++++----- include/linux/nfs_fs.h | 5 ++--- mm/filemap.c | 5 ++--- mm/page_io.c | 2 +- 37 files changed, 99 insertions(+), 112 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 619af9bfdcb3..75eea7ce3d7c 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -194,7 +194,7 @@ prototypes: void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); - int (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset); + int (*direct_IO)(struct kiocb *, struct iov_iter *iter); int (*migratepage)(struct address_space *, struct page *, struct page *); int (*launder_page)(struct page *); int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long); diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 4164bd6397a2..c61a223ef3ff 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -591,7 +591,7 @@ struct address_space_operations { void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); - ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset); + ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* migrate the contents of a page to the specified target */ int (*migratepage) (struct page *, struct page *); int (*launder_page) (struct page *); diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c index 69aa15e8e3ef..0c3459c1a518 100644 --- a/drivers/staging/lustre/lustre/llite/rw26.c +++ b/drivers/staging/lustre/lustre/llite/rw26.c @@ -358,14 +358,14 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io, */ #define MAX_DIO_SIZE ((KMALLOC_MAX_SIZE / sizeof(struct brw_page) * \ PAGE_SIZE) & ~(DT_MAX_BRW_SIZE - 1)) -static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter, - loff_t file_offset) +static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter) { struct lu_env *env; struct cl_io *io; struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ccc_object *obj = cl_inode2ccc(inode); + loff_t file_offset = iocb->ki_pos; ssize_t count = iov_iter_count(iter); ssize_t tot_bytes = 0, result = 0; struct ll_inode_info *lli = ll_i2info(inode); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index ac9225e86bf3..c37fb9c08970 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -245,9 +245,10 @@ static int v9fs_launder_page(struct page *page) * */ static ssize_t -v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; + loff_t pos = iocb->ki_pos; ssize_t n; int err = 0; if (iov_iter_rw(iter) == WRITE) { diff --git a/fs/affs/file.c b/fs/affs/file.c index 0cde550050e8..0deec9cc2362 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -389,12 +389,13 @@ static void affs_write_failed(struct address_space *mapping, loff_t to) } static ssize_t -affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { @@ -404,7 +405,7 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) return 0; } - ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, affs_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) affs_write_failed(mapping, offset + count); return ret; diff --git a/fs/block_dev.c b/fs/block_dev.c index 20a2c02b77c4..9e1f3fe25753 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -162,15 +162,15 @@ static struct inode *bdev_file_inode(struct file *file) } static ssize_t -blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = bdev_file_inode(file); if (IS_DAX(inode)) - return dax_do_io(iocb, inode, iter, offset, blkdev_get_block, + return dax_do_io(iocb, inode, iter, blkdev_get_block, NULL, DIO_SKIP_DIO_COUNT); - return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset, + return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, blkdev_get_block, NULL, NULL, DIO_SKIP_DIO_COUNT); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2aaba58b4856..352d4e1dc985 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8541,13 +8541,13 @@ out: return retval; } -static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_dio_data dio_data = { 0 }; + loff_t offset = iocb->ki_pos; size_t count = 0; int flags = 0; bool wakeup = true; @@ -8607,7 +8607,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, ret = __blockdev_direct_IO(iocb, inode, BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, - iter, offset, btrfs_get_blocks_direct, NULL, + iter, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (iov_iter_rw(iter) == WRITE) { current->journal_info = NULL; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 4801571f51cb..43098cd9602b 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1292,8 +1292,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, * intercept O_DIRECT reads and writes early, this function should * never get called. */ -static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos) +static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter) { WARN_ON(1); return -EINVAL; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c03d0744648b..cb070aa88e57 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3854,7 +3854,7 @@ void cifs_oplock_break(struct work_struct *work) * Direct IO is not yet supported in the cached mode. */ static ssize_t -cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter) { /* * FIXME diff --git a/fs/dax.c b/fs/dax.c index 75ba46d82a76..0dbe4e0f16fe 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -244,7 +244,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, * @iocb: The control block for this I/O * @inode: The file which the I/O is directed at * @iter: The addresses to do I/O from or to - * @pos: The file offset where the I/O starts * @get_block: The filesystem method used to translate file offsets to blocks * @end_io: A filesystem callback for I/O completion * @flags: See below @@ -257,11 +256,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, * is in progress. */ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode, - struct iov_iter *iter, loff_t pos, get_block_t get_block, + struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags) { struct buffer_head bh; ssize_t retval = -EINVAL; + loff_t pos = iocb->ki_pos; loff_t end = pos + iov_iter_count(iter); memset(&bh, 0, sizeof(bh)); diff --git a/fs/direct-io.c b/fs/direct-io.c index 472037732daf..8949d3e35756 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1113,7 +1113,7 @@ static inline int drop_refcount(struct dio *dio) static inline ssize_t do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, - loff_t offset, get_block_t get_block, dio_iodone_t end_io, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits); @@ -1121,6 +1121,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; loff_t end = offset + count; struct dio *dio; struct dio_submit sdio = { 0, }; @@ -1328,7 +1329,7 @@ out: ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, - loff_t offset, get_block_t get_block, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { @@ -1344,7 +1345,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, prefetch(bdev->bd_queue); prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES); - return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block, + return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, end_io, submit_io, flags); } diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 49e1bd00b4ec..9dc4c6dbf3c9 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -960,8 +960,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset, /* TODO: Should be easy enough to do proprly */ -static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { return 0; } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 6bd58e6ff038..b675610391b8 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -854,20 +854,20 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block) } static ssize_t -ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL, + ret = dax_do_io(iocb, inode, iter, ext2_get_block, NULL, DIO_LOCKING); else - ret = blockdev_direct_IO(iocb, inode, iter, offset, - ext2_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) ext2_write_failed(mapping, offset + count); return ret; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 349afebe21ee..72f4c9e00e97 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2581,8 +2581,7 @@ extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk, /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset); +extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 3027fa681de5..627b7e8f9ef3 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -659,12 +659,12 @@ out: * crashes then stale disk data _may_ be exposed inside the file. But current * VFS code falls back into buffered path in that case so we are safe. */ -ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); + loff_t offset = iocb->ki_pos; handle_t *handle; ssize_t ret; int orphan = 0; @@ -707,21 +707,21 @@ retry: goto locked; } if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, + ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0); else ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - offset, ext4_dio_get_block, + ext4_dio_get_block, NULL, NULL, 0); inode_dio_end(inode); } else { locked: if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, + ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, DIO_LOCKING); else - ret = blockdev_direct_IO(iocb, inode, iter, offset, + ret = blockdev_direct_IO(iocb, inode, iter, ext4_dio_get_block); if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 981a1fc30eaa..79b298d397b4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3334,12 +3334,12 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset, * if the machine crashes during the write. * */ -static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; + loff_t offset = iocb->ki_pos; size_t count = iov_iter_count(iter); int overwrite = 0; get_block_t *get_block_func = NULL; @@ -3348,7 +3348,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, /* Use the old path for reads and writes beyond i_size. */ if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size) - return ext4_ind_direct_IO(iocb, iter, offset); + return ext4_ind_direct_IO(iocb, iter); BUG_ON(iocb->private == NULL); @@ -3400,11 +3400,11 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); #endif if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, get_block_func, + ret = dax_do_io(iocb, inode, iter, get_block_func, ext4_end_io_dio, dio_flags); else ret = __blockdev_direct_IO(iocb, inode, - inode->i_sb->s_bdev, iter, offset, + inode->i_sb->s_bdev, iter, get_block_func, ext4_end_io_dio, NULL, dio_flags); @@ -3431,12 +3431,12 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return ret; } -static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; #ifdef CONFIG_EXT4_FS_ENCRYPTION @@ -3456,9 +3456,9 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_direct_IO(iocb, iter, offset); + ret = ext4_ext_direct_IO(iocb, iter); else - ret = ext4_ind_direct_IO(iocb, iter, offset); + ret = ext4_ind_direct_IO(iocb, iter); trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); return ret; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 53fec0872e60..a4c5da5bfe1e 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1655,12 +1655,12 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter, return 0; } -static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; int err; err = check_direct_IO(inode, iter, offset); @@ -1672,7 +1672,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); + err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio); if (err < 0 && iov_iter_rw(iter) == WRITE) f2fs_write_failed(mapping, offset + count); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 226281068a46..3bcf57925dca 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -244,13 +244,13 @@ static int fat_write_end(struct file *file, struct address_space *mapping, return err; } -static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { @@ -272,7 +272,7 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(iocb, inode, iter, offset, fat_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) fat_write_failed(mapping, offset + count); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 7e8c4603d43a..02279073bf64 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2837,7 +2837,7 @@ static inline loff_t fuse_round_up(loff_t off) } static ssize_t -fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { DECLARE_COMPLETION_ONSTACK(wait); ssize_t ret = 0; @@ -2848,6 +2848,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) struct inode *inode; loff_t i_size; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; struct fuse_io_priv *io; bool is_sync = is_sync_kiocb(iocb); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 1bbbee945f46..8524c0e322fc 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1042,13 +1042,13 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset) -static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct address_space *mapping = inode->i_mapping; struct gfs2_inode *ip = GFS2_I(inode); + loff_t offset = iocb->ki_pos; struct gfs2_holder gh; int rv; @@ -1099,7 +1099,7 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - offset, gfs2_get_block_direct, NULL, NULL, 0); + gfs2_get_block_direct, NULL, NULL, 0); out: gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index cb1e5faa2fb7..c82331a9cf9b 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -124,8 +124,7 @@ static int hfs_releasepage(struct page *page, gfp_t mask) return res ? try_to_free_buffers(page) : 0; } -static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -133,7 +132,7 @@ static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, hfs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, hfs_get_block); /* * In case of error extending write may have instantiated a few @@ -141,7 +140,7 @@ static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if (end > isize) hfs_write_failed(mapping, end); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b28f39865c3a..2ad34a5eb5ad 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -122,8 +122,7 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) return res ? try_to_free_buffers(page) : 0; } -static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -131,7 +130,7 @@ static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, hfsplus_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, hfsplus_get_block); /* * In case of error extending write may have instantiated a few @@ -139,7 +138,7 @@ static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if (end > isize) hfsplus_write_failed(mapping, end); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 9d9bae63ae2a..f6a2a78121b0 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -332,8 +332,7 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, jfs_get_block); } -static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -341,7 +340,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, jfs_get_block); /* * In case of error extending write may have instantiated a few @@ -349,7 +348,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if (end > isize) jfs_write_failed(mapping, end); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index c93826e4a8c6..346b5d85ce92 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -250,7 +250,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, * shunt off direct read and write requests before the VFS gets them, * so this method is only ever called for swap. */ -ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -261,7 +261,7 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (iov_iter_rw(iter) == READ) - return nfs_file_direct_read(iocb, iter, pos); + return nfs_file_direct_read(iocb, iter); return nfs_file_direct_write(iocb, iter); } @@ -545,7 +545,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers into which to read data - * @pos: byte offset in file where reading starts * * We use this function for direct reads instead of calling * generic_file_aio_read() in order to avoid gfar's check to see if @@ -561,8 +560,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos) +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -574,7 +572,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", - file, count, (long long) pos); + file, count, (long long) iocb->ki_pos); result = 0; if (!count) @@ -594,7 +592,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, dreq->inode = inode; dreq->bytes_left = count; - dreq->io_start = pos; + dreq->io_start = iocb->ki_pos; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { @@ -606,14 +604,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, dreq->iocb = iocb; NFS_I(inode)->read_io += count; - result = nfs_direct_read_schedule_iovec(dreq, iter, pos); + result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); inode_unlock(inode); if (!result) { result = nfs_direct_wait(dreq); if (result > 0) - iocb->ki_pos = pos + result; + iocb->ki_pos += result; } nfs_direct_req_release(dreq); @@ -969,7 +967,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers from which to write data - * @pos: byte offset in file where writing starts * * We use this function for direct writes instead of calling * generic_file_aio_write() in order to avoid taking the inode diff --git a/fs/nfs/file.c b/fs/nfs/file.c index be01095b97ae..717a8d6af52d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -164,7 +164,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) ssize_t result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_read(iocb, to, iocb->ki_pos); + return nfs_file_direct_read(iocb, to); dprintk("NFS: read(%pD2, %zu@%lu)\n", iocb->ki_filp, diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 534631358b13..cfebcd2fc7f3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -305,7 +305,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, } static ssize_t -nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = file_inode(iocb->ki_filp); @@ -313,7 +313,7 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) return 0; /* Needs synchronization with the cleaner */ - return blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block); + return blockdev_direct_IO(iocb, inode, iter, nilfs_get_block); } const struct address_space_operations nilfs_aops = { diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index ad1577348a92..6c66c62d4a7e 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2423,13 +2423,11 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, return 0; } -static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file)->i_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - loff_t end = offset + iter->count; get_block_t *get_block; /* @@ -2440,7 +2438,8 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return 0; /* Fallback to buffered I/O if we do not support append dio. */ - if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb)) + if (iocb->ki_pos + iter->count > i_size_read(inode) && + !ocfs2_supports_append_dio(osb)) return 0; if (iov_iter_rw(iter) == READ) @@ -2449,7 +2448,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, get_block = ocfs2_dio_get_block; return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, offset, get_block, + iter, get_block, ocfs2_dio_end_io, NULL, 0); } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index d5c2e9c865de..825455d3e4ba 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3279,15 +3279,14 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) * We thank Mingming Cao for helping us understand in great detail what * to do in this section of the code. */ -static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, + ret = blockdev_direct_IO(iocb, inode, iter, reiserfs_get_blocks_direct_io); /* @@ -3296,7 +3295,7 @@ static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if ((end > isize) && inode_newsize_ok(inode, isize) == 0) { truncate_setsize(inode, isize); diff --git a/fs/udf/file.c b/fs/udf/file.c index 877ba1c9b461..7ab8d8196e90 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -99,8 +99,7 @@ static int udf_adinicb_write_begin(struct file *file, return 0; } -static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* Fallback to buffered I/O. */ return 0; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 2dc461eeb415..f323aff740ef 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -214,8 +214,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, return ret; } -static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -223,9 +222,9 @@ static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, udf_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, udf_get_block); if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE)) - udf_write_failed(mapping, offset + count); + udf_write_failed(mapping, iocb->ki_pos + count); return ret; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e49b2406d15d..c535887c60a8 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1406,8 +1406,7 @@ xfs_end_io_direct_write( STATIC ssize_t xfs_vm_direct_IO( struct kiocb *iocb, - struct iov_iter *iter, - loff_t offset) + struct iov_iter *iter) { struct inode *inode = iocb->ki_filp->f_mapping->host; dio_iodone_t *endio = NULL; @@ -1420,12 +1419,12 @@ xfs_vm_direct_IO( } if (IS_DAX(inode)) { - return dax_do_io(iocb, inode, iter, offset, + return dax_do_io(iocb, inode, iter, xfs_get_blocks_direct, endio, 0); } bdev = xfs_find_bdev_for_inode(inode); - return __blockdev_direct_IO(iocb, inode, bdev, iter, offset, + return __blockdev_direct_IO(iocb, inode, bdev, iter, xfs_get_blocks_direct, endio, NULL, flags); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 92f72fb05497..5de047ab2411 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -794,7 +794,7 @@ xfs_file_dio_aio_write( trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); data = *from; - ret = mapping->a_ops->direct_IO(iocb, &data, iocb->ki_pos); + ret = mapping->a_ops->direct_IO(iocb, &data); /* see generic_file_direct_write() for why this is necessary */ if (mapping->nrpages) { diff --git a/include/linux/dax.h b/include/linux/dax.h index 636dd59ab505..982a6c4a62f3 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -5,7 +5,7 @@ #include #include -ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, +ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, get_block_t, dio_iodone_t, int flags); int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); diff --git a/include/linux/fs.h b/include/linux/fs.h index e9eaa2074061..e6b2de159736 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -394,7 +394,7 @@ struct address_space_operations { void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); - ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset); + ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. @@ -2766,18 +2766,17 @@ void dio_end_io(struct bio *bio, int error); ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, - loff_t offset, get_block_t get_block, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct iov_iter *iter, loff_t offset, + struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - offset, get_block, NULL, NULL, - DIO_LOCKING | DIO_SKIP_HOLES); + get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 67300f8e5f2f..cede8f6a7e2d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -445,10 +445,9 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *, loff_t); +extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); extern ssize_t nfs_file_direct_read(struct kiocb *iocb, - struct iov_iter *iter, - loff_t pos); + struct iov_iter *iter); extern ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter); diff --git a/mm/filemap.c b/mm/filemap.c index e7108c31346d..cb36db9f4107 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1853,8 +1853,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) iocb->ki_pos + count - 1); if (!retval) { struct iov_iter data = *iter; - retval = mapping->a_ops->direct_IO(iocb, &data, - iocb->ki_pos); + retval = mapping->a_ops->direct_IO(iocb, &data); } if (retval > 0) { @@ -2538,7 +2537,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) } data = *from; - written = mapping->a_ops->direct_IO(iocb, &data, pos); + written = mapping->a_ops->direct_IO(iocb, &data); /* * Finally, try again to invalidate clean pages which might have been diff --git a/mm/page_io.c b/mm/page_io.c index cd92e3d67a32..89275601d399 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -279,7 +279,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, set_page_writeback(page); unlock_page(page); - ret = mapping->a_ops->direct_IO(&kiocb, &from, kiocb.ki_pos); + ret = mapping->a_ops->direct_IO(&kiocb, &from); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); ret = 0; -- cgit From 972b241f8441dc37a3f89dcd7e71d7f013873d13 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 4 May 2016 16:24:53 -0400 Subject: btrfs: switch to ->iterate_shared() Signed-off-by: Al Viro --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2aaba58b4856..3e2ada1267f3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10181,7 +10181,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = { static const struct file_operations btrfs_dir_file_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = btrfs_real_readdir, + .iterate_shared = btrfs_real_readdir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_ioctl, -- cgit From 9cfa3e34e20e6798a671236000d9e97c8aa5d318 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 26 Apr 2016 15:39:32 +0100 Subject: Btrfs: don't do unnecessary delalloc flushes when relocating Before we start the actual relocation process of a block group, we do calls to flush delalloc of all inodes and then wait for ordered extents to complete. However we do these flush calls just to make sure we don't race with concurrent tasks that have actually already started to run delalloc and have allocated an extent from the block group we want to relocate, right before we set it to readonly mode, but have not yet created the respective ordered extents. The flush calls make us wait for such concurrent tasks because they end up calling filemap_fdatawrite_range() (through btrfs_start_delalloc_roots() -> __start_delalloc_inodes() -> btrfs_alloc_delalloc_work() -> btrfs_run_delalloc_work()) which ends up serializing us with those tasks due to attempts to lock the same pages (and the delalloc flush procedure calls the allocator and creates the ordered extents before unlocking the pages). These flushing calls not only make us waste time (cpu, IO) but also reduce the chances of writing larger extents (applications might be writing to contiguous ranges and we flush before they finish dirtying the whole ranges). So make sure we don't flush delalloc and just wait for concurrent tasks that have already started flushing delalloc and have allocated an extent from the block group we are about to relocate. This change also ends up fixing a race with direct IO writes that makes relocation not wait for direct IO ordered extents. This race is illustrated by the following diagram: CPU 1 CPU 2 btrfs_relocate_block_group(bg X) starts direct IO write, target inode currently has no ordered extents ongoing nor dirty pages (delalloc regions), therefore the root for our inode is not in the list fs_info->ordered_roots btrfs_direct_IO() __blockdev_direct_IO() btrfs_get_blocks_direct() btrfs_lock_extent_direct() locks range in the io tree btrfs_new_extent_direct() btrfs_reserve_extent() --> extent allocated from bg X btrfs_inc_block_group_ro(bg X) btrfs_start_delalloc_roots() __start_delalloc_inodes() --> does nothing, no dealloc ranges in the inode's io tree so the inode's root is not in the list fs_info->delalloc_roots btrfs_wait_ordered_roots() --> does not find the inode's root in the list fs_info->ordered_roots --> ends up not waiting for the direct IO write started by the task at CPU 2 relocate_block_group(rc->stage == MOVE_DATA_EXTENTS) prepare_to_relocate() btrfs_commit_transaction() iterates the extent tree, using its commit root and moves extents into new locations btrfs_add_ordered_extent_dio() --> now a ordered extent is created and added to the list root->ordered_extents and the root added to the list fs_info->ordered_roots --> this is too late and the task at CPU 1 already started the relocation btrfs_commit_transaction() btrfs_finish_ordered_io() btrfs_alloc_reserved_file_extent() --> adds delayed data reference for the extent allocated from bg X relocate_block_group(rc->stage == UPDATE_DATA_PTRS) prepare_to_relocate() btrfs_commit_transaction() --> delayed refs are run, so an extent item for the allocated extent from bg X is added to extent tree --> commit roots are switched, so the next scan in the extent tree will see the extent item sees the extent in the extent tree When this happens the relocation produces the following warning when it finishes: [ 7260.832836] ------------[ cut here ]------------ [ 7260.834653] WARNING: CPU: 5 PID: 6765 at fs/btrfs/relocation.c:4318 btrfs_relocate_block_group+0x245/0x2a1 [btrfs]() [ 7260.838268] Modules linked in: btrfs crc32c_generic xor ppdev raid6_pq psmouse sg acpi_cpufreq evdev i2c_piix4 tpm_tis serio_raw tpm i2c_core pcspkr parport_pc [ 7260.850935] CPU: 5 PID: 6765 Comm: btrfs Not tainted 4.5.0-rc6-btrfs-next-28+ #1 [ 7260.852998] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014 [ 7260.852998] 0000000000000000 ffff88020bf57bc0 ffffffff812648b3 0000000000000000 [ 7260.852998] 0000000000000009 ffff88020bf57bf8 ffffffff81051608 ffffffffa03c1b2d [ 7260.852998] ffff8800b2bbb800 0000000000000000 ffff8800b17bcc58 ffff8800399dd000 [ 7260.852998] Call Trace: [ 7260.852998] [] dump_stack+0x67/0x90 [ 7260.852998] [] warn_slowpath_common+0x99/0xb2 [ 7260.852998] [] ? btrfs_relocate_block_group+0x245/0x2a1 [btrfs] [ 7260.852998] [] warn_slowpath_null+0x1a/0x1c [ 7260.852998] [] btrfs_relocate_block_group+0x245/0x2a1 [btrfs] [ 7260.852998] [] btrfs_relocate_chunk.isra.29+0x66/0xdb [btrfs] [ 7260.852998] [] btrfs_balance+0xde1/0xe4e [btrfs] [ 7260.852998] [] ? debug_smp_processor_id+0x17/0x19 [ 7260.852998] [] btrfs_ioctl_balance+0x255/0x2d3 [btrfs] [ 7260.852998] [] btrfs_ioctl+0x11e0/0x1dff [btrfs] [ 7260.852998] [] ? handle_mm_fault+0x443/0xd63 [ 7260.852998] [] ? _raw_spin_unlock+0x31/0x44 [ 7260.852998] [] ? arch_local_irq_save+0x9/0xc [ 7260.852998] [] vfs_ioctl+0x18/0x34 [ 7260.852998] [] do_vfs_ioctl+0x550/0x5be [ 7260.852998] [] ? __fget_light+0x4d/0x71 [ 7260.852998] [] SyS_ioctl+0x57/0x79 [ 7260.852998] [] entry_SYSCALL_64_fastpath+0x12/0x6b [ 7260.893268] ---[ end trace eb7803b24ebab8ad ]--- This is because at the end of the first stage, in relocate_block_group(), we commit the current transaction, which makes delayed refs run, the commit roots are switched and so the second stage will find the extent item that the ordered extent added to the delayed refs. But this extent was not moved (ordered extent completed after first stage finished), so at the end of the relocation our block group item still has a positive used bytes counter, triggering a warning at the end of btrfs_relocate_block_group(). Later on when trying to read the extent contents from disk we hit a BUG_ON() due to the inability to map a block with a logical address that belongs to the block group we relocated and is no longer valid, resulting in the following trace: [ 7344.885290] BTRFS critical (device sdi): unable to find logical 12845056 len 4096 [ 7344.887518] ------------[ cut here ]------------ [ 7344.888431] kernel BUG at fs/btrfs/inode.c:1833! [ 7344.888431] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [ 7344.888431] Modules linked in: btrfs crc32c_generic xor ppdev raid6_pq psmouse sg acpi_cpufreq evdev i2c_piix4 tpm_tis serio_raw tpm i2c_core pcspkr parport_pc [ 7344.888431] CPU: 0 PID: 6831 Comm: od Tainted: G W 4.5.0-rc6-btrfs-next-28+ #1 [ 7344.888431] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014 [ 7344.888431] task: ffff880215818600 ti: ffff880204684000 task.ti: ffff880204684000 [ 7344.888431] RIP: 0010:[] [] btrfs_merge_bio_hook+0x54/0x6b [btrfs] [ 7344.888431] RSP: 0018:ffff8802046878f0 EFLAGS: 00010282 [ 7344.888431] RAX: 00000000ffffffea RBX: 0000000000001000 RCX: 0000000000000001 [ 7344.888431] RDX: ffff88023ec0f950 RSI: ffffffff8183b638 RDI: 00000000ffffffff [ 7344.888431] RBP: ffff880204687908 R08: 0000000000000001 R09: 0000000000000000 [ 7344.888431] R10: ffff880204687770 R11: ffffffff82f2d52d R12: 0000000000001000 [ 7344.888431] R13: ffff88021afbfee8 R14: 0000000000006208 R15: ffff88006cd199b0 [ 7344.888431] FS: 00007f1f9e1d6700(0000) GS:ffff88023ec00000(0000) knlGS:0000000000000000 [ 7344.888431] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7344.888431] CR2: 00007f1f9dc8cb60 CR3: 000000023e3b6000 CR4: 00000000000006f0 [ 7344.888431] Stack: [ 7344.888431] 0000000000001000 0000000000001000 ffff880204687b98 ffff880204687950 [ 7344.888431] ffffffffa0395c8f ffffea0004d64d48 0000000000000000 0000000000001000 [ 7344.888431] ffffea0004d64d48 0000000000001000 0000000000000000 0000000000000000 [ 7344.888431] Call Trace: [ 7344.888431] [] submit_extent_page+0xf5/0x16f [btrfs] [ 7344.888431] [] __do_readpage+0x4a0/0x4f1 [btrfs] [ 7344.888431] [] ? btrfs_create_repair_bio+0xcb/0xcb [btrfs] [ 7344.888431] [] ? btrfs_writepage_start_hook+0xbc/0xbc [btrfs] [ 7344.888431] [] ? trace_hardirqs_on+0xd/0xf [ 7344.888431] [] __do_contiguous_readpages.constprop.26+0xc2/0xe4 [btrfs] [ 7344.888431] [] ? btrfs_writepage_start_hook+0xbc/0xbc [btrfs] [ 7344.888431] [] __extent_readpages.constprop.25+0xed/0x100 [btrfs] [ 7344.888431] [] ? lru_cache_add+0xe/0x10 [ 7344.888431] [] extent_readpages+0x160/0x1aa [btrfs] [ 7344.888431] [] ? btrfs_writepage_start_hook+0xbc/0xbc [btrfs] [ 7344.888431] [] ? alloc_pages_current+0xa9/0xcd [ 7344.888431] [] btrfs_readpages+0x1f/0x21 [btrfs] [ 7344.888431] [] __do_page_cache_readahead+0x168/0x1fc [ 7344.888431] [] ondemand_readahead+0x1f6/0x207 [ 7344.888431] [] ? ondemand_readahead+0x1f6/0x207 [ 7344.888431] [] ? pagecache_get_page+0x2b/0x154 [ 7344.888431] [] page_cache_sync_readahead+0x3d/0x3f [ 7344.888431] [] generic_file_read_iter+0x197/0x4e1 [ 7344.888431] [] __vfs_read+0x79/0x9d [ 7344.888431] [] vfs_read+0x8f/0xd2 [ 7344.888431] [] SyS_read+0x50/0x7e [ 7344.888431] [] entry_SYSCALL_64_fastpath+0x12/0x6b [ 7344.888431] Code: 8d 4d e8 45 31 c9 45 31 c0 48 8b 00 48 c1 e2 09 48 8b 80 80 fc ff ff 4c 89 65 e8 48 8b b8 f0 01 00 00 e8 1d 42 02 00 85 c0 79 02 <0f> 0b 4c 0 [ 7344.888431] RIP [] btrfs_merge_bio_hook+0x54/0x6b [btrfs] [ 7344.888431] RSP [ 7344.970544] ---[ end trace eb7803b24ebab8ae ]--- Signed-off-by: Filipe Manana Reviewed-by: Josef Bacik Reviewed-by: Liu Bo --- fs/btrfs/ctree.h | 14 ++++++++++++ fs/btrfs/extent-tree.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++-- fs/btrfs/inode.c | 8 +++++++ fs/btrfs/relocation.c | 6 +----- 4 files changed, 79 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 84a6a5b3384a..90e70e21e479 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1408,6 +1408,17 @@ struct btrfs_block_group_cache { struct btrfs_io_ctl io_ctl; + /* + * Incremented when doing extent allocations and holding a read lock + * on the space_info's groups_sem semaphore. + * Decremented when an ordered extent that represents an IO against this + * block group's range is created (after it's added to its inode's + * root's list of ordered extents) or immediately after the allocation + * if it's a metadata extent or fallocate extent (for these cases we + * don't create ordered extents). + */ + atomic_t reservations; + /* Lock for free space tree operations. */ struct mutex free_space_lock; @@ -3499,6 +3510,9 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root); +void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, + const u64 start); +void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg); void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, unsigned long count); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 251452a2b72c..09aad7b447f5 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6175,6 +6175,57 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log, return 0; } +static void +btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg) +{ + atomic_inc(&bg->reservations); +} + +void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, + const u64 start) +{ + struct btrfs_block_group_cache *bg; + + bg = btrfs_lookup_block_group(fs_info, start); + ASSERT(bg); + if (atomic_dec_and_test(&bg->reservations)) + wake_up_atomic_t(&bg->reservations); + btrfs_put_block_group(bg); +} + +static int btrfs_wait_bg_reservations_atomic_t(atomic_t *a) +{ + schedule(); + return 0; +} + +void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) +{ + struct btrfs_space_info *space_info = bg->space_info; + + ASSERT(bg->ro); + + if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA)) + return; + + /* + * Our block group is read only but before we set it to read only, + * some task might have had allocated an extent from it already, but it + * has not yet created a respective ordered extent (and added it to a + * root's list of ordered extents). + * Therefore wait for any task currently allocating extents, since the + * block group's reservations counter is incremented while a read lock + * on the groups' semaphore is held and decremented after releasing + * the read access on that semaphore and creating the ordered extent. + */ + down_write(&space_info->groups_sem); + up_write(&space_info->groups_sem); + + wait_on_atomic_t(&bg->reservations, + btrfs_wait_bg_reservations_atomic_t, + TASK_UNINTERRUPTIBLE); +} + /** * btrfs_update_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating @@ -7434,6 +7485,7 @@ checks: btrfs_add_free_space(block_group, offset, num_bytes); goto loop; } + btrfs_inc_block_group_reservations(block_group); /* we are all good, lets return */ ins->objectid = search_start; @@ -7615,8 +7667,10 @@ again: WARN_ON(num_bytes < root->sectorsize); ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, flags, delalloc); - - if (ret == -ENOSPC) { + if (!ret && !is_data) { + btrfs_dec_block_group_reservations(root->fs_info, + ins->objectid); + } else if (ret == -ENOSPC) { if (!final_tried && ins->offset) { num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2aaba58b4856..3991d8a74f61 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -824,6 +824,7 @@ retry: async_extent->ram_size - 1, 0); goto out_free_reserve; } + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); /* * clear dirty, set writeback and unlock the pages. @@ -861,6 +862,7 @@ retry: } return; out_free_reserve: + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_free: extent_clear_unlock_delalloc(inode, async_extent->start, @@ -1038,6 +1040,8 @@ static noinline int cow_file_range(struct inode *inode, goto out_drop_extent_cache; } + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); + if (disk_num_bytes < cur_alloc_size) break; @@ -1066,6 +1070,7 @@ out: out_drop_extent_cache: btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0); out_reserve: + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_unlock: extent_clear_unlock_delalloc(inode, start, end, locked_page, @@ -7162,6 +7167,8 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, return ERR_PTR(ret); } + 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)) { @@ -9942,6 +9949,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, btrfs_end_transaction(trans, root); break; } + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); last_alloc = ins.offset; ret = insert_reserved_file_extent(trans, inode, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 30f77ed60133..e78f8e44bd9a 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4254,11 +4254,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu", rc->block_group->key.objectid, rc->block_group->flags); - ret = btrfs_start_delalloc_roots(fs_info, 0, -1); - if (ret < 0) { - err = ret; - goto out; - } + btrfs_wait_block_group_reservations(rc->block_group); btrfs_wait_ordered_roots(fs_info, -1, rc->block_group->key.objectid, rc->block_group->key.offset); -- cgit From 3dc9e8f76720fbbd9c56a11775932733fe13d214 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 29 Apr 2016 11:34:22 +0100 Subject: Btrfs: unpin log if rename operation fails If rename operations fail at some point after we pinned the log, we end up aborting the current transaction but never unpin the log, which leaves concurrent tasks that are trying to sync the log (as part of an fsync request from user space) blocked forever and preventing the filesystem from being unmountable. Fix this by safely unpinning the log. Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3991d8a74f61..4594a263a5f8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9406,6 +9406,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, u64 root_objectid; int ret; u64 old_ino = btrfs_ino(old_inode); + bool log_pinned = false; if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9493,6 +9494,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, * we unlink the name but before we add the new name back in. */ btrfs_pin_log_trans(root); + log_pinned = true; } inode_inc_iversion(old_dir); @@ -9559,12 +9561,36 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (old_inode->i_nlink == 1) BTRFS_I(old_inode)->dir_index = index; - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + if (log_pinned) { struct dentry *parent = new_dentry->d_parent; + btrfs_log_new_name(trans, old_inode, old_dir, parent); btrfs_end_log_trans(root); + log_pinned = false; } out_fail: + /* + * If we have pinned the log and an error happened, we unpin tasks + * trying to sync the log and force them to fallback to a transaction + * commit if the log currently contains any of the inodes involved in + * this rename operation (to ensure we do not persist a log with an + * inconsistent state for any of these inodes or leading to any + * inconsistencies when replayed). If the transaction was aborted, the + * abortion reason is propagated to userspace when attempting to commit + * the transaction. If the log does not contain any of these inodes, we + * allow the tasks to sync it. + */ + if (ret && log_pinned) { + if (btrfs_inode_in_log(old_dir, root->fs_info->generation) || + btrfs_inode_in_log(new_dir, root->fs_info->generation) || + btrfs_inode_in_log(old_inode, root->fs_info->generation) || + (new_inode && + btrfs_inode_in_log(new_inode, root->fs_info->generation))) + btrfs_set_log_full_commit(root->fs_info, trans); + + btrfs_end_log_trans(root); + log_pinned = false; + } btrfs_end_transaction(trans, root); out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) -- cgit From c4aba9545430ed0f842d0833072f990a42da90f0 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 29 Apr 2016 13:14:42 +0100 Subject: Btrfs: pin log earlier when renaming We were pinning the log right after the first step in the rename operation (inserting inode ref for the new name in the destination directory) instead of doing it before. This behaviour was introduced in 2009 for some reason that was not mentioned neither on the changelog nor any comment, with the drawback of a small time window where concurrent log writers can end up logging the new inode reference for the inode we are renaming while the rename operation is in progress (so that we can end up with a log containing both the new and old references). As of today there's no reason to not pin the log before that first step anymore, so just fix this. Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4594a263a5f8..422833e70d00 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9479,6 +9479,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(root->fs_info, trans); } else { + btrfs_pin_log_trans(root); + log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -9486,15 +9488,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, btrfs_ino(new_dir), index); if (ret) goto out_fail; - /* - * this is an ugly little race, but the rename is required - * to make sure that if we crash, the inode is either at the - * old name or the new one. pinning the log transaction lets - * us make sure we don't allow a log commit to come in after - * we unlink the name but before we add the new name back in. - */ - btrfs_pin_log_trans(root); - log_pinned = true; } inode_inc_iversion(old_dir); -- cgit From cdd1fedf8261cd7a73c0596298902ff4f0f04492 Mon Sep 17 00:00:00 2001 From: Dan Fuhry Date: Thu, 17 Mar 2016 15:23:38 +0100 Subject: btrfs: add support for RENAME_EXCHANGE and RENAME_WHITEOUT Two new flags, RENAME_EXCHANGE and RENAME_WHITEOUT, provide for new behavior in the renameat2() syscall. This behavior is primarily used by overlayfs. This patch adds support for these flags to btrfs, enabling it to be used as a fully functional upper layer for overlayfs. RENAME_EXCHANGE support was written by Davide Italiano originally submitted on 2 April 2015. Signed-off-by: Davide Italiano Signed-off-by: Dan Fuhry [ remove unlikely ] Signed-off-by: David Sterba Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 264 +++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 257 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 422833e70d00..452cfefbf4b8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9394,8 +9394,244 @@ static int btrfs_getattr(struct vfsmount *mnt, return 0; } +static int btrfs_rename_exchange(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry) +{ + struct btrfs_trans_handle *trans; + struct btrfs_root *root = BTRFS_I(old_dir)->root; + struct btrfs_root *dest = BTRFS_I(new_dir)->root; + struct inode *new_inode = new_dentry->d_inode; + struct inode *old_inode = old_dentry->d_inode; + struct timespec ctime = CURRENT_TIME; + struct dentry *parent; + u64 old_ino = btrfs_ino(old_inode); + u64 new_ino = btrfs_ino(new_inode); + u64 old_idx = 0; + u64 new_idx = 0; + u64 root_objectid; + int ret; + + /* we only allow rename subvolume link between subvolumes */ + if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) + return -EXDEV; + + /* close the race window with snapshot create/destroy ioctl */ + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + down_read(&root->fs_info->subvol_sem); + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + down_read(&dest->fs_info->subvol_sem); + + /* + * We want to reserve the absolute worst case amount of items. So if + * both inodes are subvols and we need to unlink them then that would + * require 4 item modifications, but if they are both normal inodes it + * would require 5 item modifications, so we'll assume their normal + * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items + * should cover the worst case number of items we'll modify. + */ + trans = btrfs_start_transaction(root, 12); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_notrans; + } + + /* + * We need to find a free sequence number both in the source and + * in the destination directory for the exchange. + */ + ret = btrfs_set_inode_index(new_dir, &old_idx); + if (ret) + goto out_fail; + ret = btrfs_set_inode_index(old_dir, &new_idx); + if (ret) + goto out_fail; + + BTRFS_I(old_inode)->dir_index = 0ULL; + BTRFS_I(new_inode)->dir_index = 0ULL; + + /* Reference for the source. */ + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { + /* force full log commit if subvolume involved. */ + btrfs_set_log_full_commit(root->fs_info, trans); + } else { + ret = btrfs_insert_inode_ref(trans, dest, + new_dentry->d_name.name, + new_dentry->d_name.len, + old_ino, + btrfs_ino(new_dir), old_idx); + if (ret) + goto out_fail; + btrfs_pin_log_trans(root); + } + + /* And now for the dest. */ + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { + /* force full log commit if subvolume involved. */ + btrfs_set_log_full_commit(dest->fs_info, trans); + } else { + ret = btrfs_insert_inode_ref(trans, root, + old_dentry->d_name.name, + old_dentry->d_name.len, + new_ino, + btrfs_ino(old_dir), new_idx); + if (ret) + goto out_fail; + btrfs_pin_log_trans(dest); + } + + /* Update inode version and ctime/mtime. */ + inode_inc_iversion(old_dir); + inode_inc_iversion(new_dir); + inode_inc_iversion(old_inode); + inode_inc_iversion(new_inode); + old_dir->i_ctime = old_dir->i_mtime = ctime; + new_dir->i_ctime = new_dir->i_mtime = ctime; + old_inode->i_ctime = ctime; + new_inode->i_ctime = ctime; + + if (old_dentry->d_parent != new_dentry->d_parent) { + btrfs_record_unlink_dir(trans, old_dir, old_inode, 1); + btrfs_record_unlink_dir(trans, new_dir, new_inode, 1); + } + + /* src is a subvolume */ + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { + root_objectid = BTRFS_I(old_inode)->root->root_key.objectid; + ret = btrfs_unlink_subvol(trans, root, old_dir, + root_objectid, + old_dentry->d_name.name, + old_dentry->d_name.len); + } else { /* src is an inode */ + ret = __btrfs_unlink_inode(trans, root, old_dir, + old_dentry->d_inode, + old_dentry->d_name.name, + old_dentry->d_name.len); + if (!ret) + ret = btrfs_update_inode(trans, root, old_inode); + } + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + /* dest is a subvolume */ + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { + root_objectid = BTRFS_I(new_inode)->root->root_key.objectid; + ret = btrfs_unlink_subvol(trans, dest, new_dir, + root_objectid, + new_dentry->d_name.name, + new_dentry->d_name.len); + } else { /* dest is an inode */ + ret = __btrfs_unlink_inode(trans, dest, new_dir, + new_dentry->d_inode, + new_dentry->d_name.name, + new_dentry->d_name.len); + if (!ret) + ret = btrfs_update_inode(trans, dest, new_inode); + } + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + ret = btrfs_add_link(trans, new_dir, old_inode, + new_dentry->d_name.name, + new_dentry->d_name.len, 0, old_idx); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + ret = btrfs_add_link(trans, old_dir, new_inode, + old_dentry->d_name.name, + old_dentry->d_name.len, 0, new_idx); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + if (old_inode->i_nlink == 1) + BTRFS_I(old_inode)->dir_index = old_idx; + if (new_inode->i_nlink == 1) + BTRFS_I(new_inode)->dir_index = new_idx; + + if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + parent = new_dentry->d_parent; + btrfs_log_new_name(trans, old_inode, old_dir, parent); + btrfs_end_log_trans(root); + } + if (new_ino != BTRFS_FIRST_FREE_OBJECTID) { + parent = old_dentry->d_parent; + btrfs_log_new_name(trans, new_inode, new_dir, parent); + btrfs_end_log_trans(dest); + } +out_fail: + ret = btrfs_end_transaction(trans, root); +out_notrans: + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + up_read(&dest->fs_info->subvol_sem); + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + up_read(&root->fs_info->subvol_sem); + + return ret; +} + +static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct inode *dir, + struct dentry *dentry) +{ + int ret; + struct inode *inode; + u64 objectid; + u64 index; + + ret = btrfs_find_free_ino(root, &objectid); + if (ret) + return ret; + + inode = btrfs_new_inode(trans, root, dir, + dentry->d_name.name, + dentry->d_name.len, + btrfs_ino(dir), + objectid, + S_IFCHR | WHITEOUT_MODE, + &index); + + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + return ret; + } + + inode->i_op = &btrfs_special_inode_operations; + init_special_inode(inode, inode->i_mode, + WHITEOUT_DEV); + + ret = btrfs_init_inode_security(trans, inode, dir, + &dentry->d_name); + if (ret) + return ret; + + ret = btrfs_add_nondir(trans, dir, dentry, + inode, 0, index); + if (ret) + return ret; + + ret = btrfs_update_inode(trans, root, inode); + if (ret) + return ret; + + unlock_new_inode(inode); + iput(inode); + + return 0; +} + static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(old_dir)->root; @@ -9457,15 +9693,15 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, * We want to reserve the absolute worst case amount of items. So if * both inodes are subvols and we need to unlink them then that would * require 4 item modifications, but if they are both normal inodes it - * would require 5 item modifications, so we'll assume their normal + * would require 5 item modifications, so we'll assume they are normal * inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items * should cover the worst case number of items we'll modify. */ trans = btrfs_start_transaction(root, 11); if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - goto out_notrans; - } + ret = PTR_ERR(trans); + goto out_notrans; + } if (dest != root) btrfs_record_root_in_trans(trans, dest); @@ -9561,6 +9797,16 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, btrfs_end_log_trans(root); log_pinned = false; } + + if (flags & RENAME_WHITEOUT) { + ret = btrfs_whiteout_for_rename(trans, root, old_dir, + old_dentry); + + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + } out_fail: /* * If we have pinned the log and an error happened, we unpin tasks @@ -9596,10 +9842,14 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - if (flags & ~RENAME_NOREPLACE) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; - return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry); + if (flags & RENAME_EXCHANGE) + return btrfs_rename_exchange(old_dir, old_dentry, new_dir, + new_dentry); + + return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } static void btrfs_run_delalloc_work(struct btrfs_work *work) -- cgit From c990161888f387db136856337c237aa8d5003292 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 5 May 2016 01:41:57 +0100 Subject: Btrfs: fix inode leak on failure to setup whiteout inode in rename If we failed to fully setup the whiteout inode during a rename operation with the whiteout flag, we ended up leaking the inode, not decrementing its link count nor removing all its items from the fs/subvol tree. Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 452cfefbf4b8..98c119b02916 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9612,21 +9612,21 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, ret = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); if (ret) - return ret; + goto out; ret = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); if (ret) - return ret; + goto out; ret = btrfs_update_inode(trans, root, inode); - if (ret) - return ret; - +out: unlock_new_inode(inode); + if (ret) + inode_dec_link_count(inode); iput(inode); - return 0; + return ret; } static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, -- cgit From 86e8aa0e772caba5f0e0471d5f836b2b997dcb3e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 5 May 2016 02:02:27 +0100 Subject: Btrfs: unpin logs if rename exchange operation fails If rename exchange operations fail at some point after we pinned any of the logs, we end up aborting the current transaction but never unpin the logs, which leaves concurrent tasks that are trying to sync the logs (as part of an fsync request from user space) blocked forever and preventing the filesystem from being unmountable. Fix this by safely unpinning the log. Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 98c119b02916..c92d9b83bb38 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9412,6 +9412,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, u64 new_idx = 0; u64 root_objectid; int ret; + bool root_log_pinned = false; + bool dest_log_pinned = false; /* we only allow rename subvolume link between subvolumes */ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) @@ -9464,6 +9466,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (ret) goto out_fail; btrfs_pin_log_trans(root); + root_log_pinned = true; } /* And now for the dest. */ @@ -9479,6 +9482,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (ret) goto out_fail; btrfs_pin_log_trans(dest); + dest_log_pinned = true; } /* Update inode version and ctime/mtime. */ @@ -9557,17 +9561,47 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (new_inode->i_nlink == 1) BTRFS_I(new_inode)->dir_index = new_idx; - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + if (root_log_pinned) { parent = new_dentry->d_parent; btrfs_log_new_name(trans, old_inode, old_dir, parent); btrfs_end_log_trans(root); + root_log_pinned = false; } - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) { + if (dest_log_pinned) { parent = old_dentry->d_parent; btrfs_log_new_name(trans, new_inode, new_dir, parent); btrfs_end_log_trans(dest); + dest_log_pinned = false; } out_fail: + /* + * If we have pinned a log and an error happened, we unpin tasks + * trying to sync the log and force them to fallback to a transaction + * commit if the log currently contains any of the inodes involved in + * this rename operation (to ensure we do not persist a log with an + * inconsistent state for any of these inodes or leading to any + * inconsistencies when replayed). If the transaction was aborted, the + * abortion reason is propagated to userspace when attempting to commit + * the transaction. If the log does not contain any of these inodes, we + * allow the tasks to sync it. + */ + if (ret && (root_log_pinned || dest_log_pinned)) { + if (btrfs_inode_in_log(old_dir, root->fs_info->generation) || + btrfs_inode_in_log(new_dir, root->fs_info->generation) || + btrfs_inode_in_log(old_inode, root->fs_info->generation) || + (new_inode && + btrfs_inode_in_log(new_inode, root->fs_info->generation))) + btrfs_set_log_full_commit(root->fs_info, trans); + + if (root_log_pinned) { + btrfs_end_log_trans(root); + root_log_pinned = false; + } + if (dest_log_pinned) { + btrfs_end_log_trans(dest); + dest_log_pinned = false; + } + } ret = btrfs_end_transaction(trans, root); out_notrans: if (new_ino == BTRFS_FIRST_FREE_OBJECTID) -- cgit From 376e5a57bf7f1466031a957d04bf8b8f6801ee6d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 5 May 2016 02:08:56 +0100 Subject: Btrfs: pin logs earlier when doing a rename exchange operation The btrfs_rename_exchange() started as a copy-paste from btrfs_rename(), which had a race fixed by my previous patch titled "Btrfs: pin log earlier when renaming", and so it suffers from the same problem. We pin the logs of the affected roots after we insert the new inode references, leaving a time window where concurrent tasks logging the inodes can end up logging both the new and old references, resulting in log trees that when replayed can turn the metadata into inconsistent states. This behaviour was added to btrfs_rename() in 2009 without any explanation about why not pinning the logs earlier, just leaving a comment about the posibility for the race. As of today it's perfectly safe and sane to pin the logs before we start doing any of the steps involved in the rename operation. Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c92d9b83bb38..a7db3ed6ac88 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9458,6 +9458,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(root->fs_info, trans); } else { + btrfs_pin_log_trans(root); + root_log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -9465,8 +9467,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, btrfs_ino(new_dir), old_idx); if (ret) goto out_fail; - btrfs_pin_log_trans(root); - root_log_pinned = true; } /* And now for the dest. */ @@ -9474,6 +9474,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(dest->fs_info, trans); } else { + btrfs_pin_log_trans(dest); + dest_log_pinned = true; ret = btrfs_insert_inode_ref(trans, root, old_dentry->d_name.name, old_dentry->d_name.len, @@ -9481,8 +9483,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, btrfs_ino(old_dir), new_idx); if (ret) goto out_fail; - btrfs_pin_log_trans(dest); - dest_log_pinned = true; } /* Update inode version and ctime/mtime. */ -- cgit From 5062af35c3c6e49110ab1ec99295339259298a3d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 5 May 2016 10:26:26 +0100 Subject: Btrfs: fix number of transaction units for renames with whiteout When we do a rename with the whiteout flag, we need to create the whiteout inode, which in the worst case requires 5 transaction units (1 inode item, 1 inode ref, 2 dir items and 1 xattr if selinux is enabled). So bump the number of transaction units from 11 to 16 if the whiteout flag is set. Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a7db3ed6ac88..0921d2b07f1d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9668,6 +9668,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int flags) { struct btrfs_trans_handle *trans; + unsigned int trans_num_items; struct btrfs_root *root = BTRFS_I(old_dir)->root; struct btrfs_root *dest = BTRFS_I(new_dir)->root; struct inode *new_inode = d_inode(new_dentry); @@ -9730,8 +9731,14 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, * would require 5 item modifications, so we'll assume they are normal * inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items * should cover the worst case number of items we'll modify. + * If our rename has the whiteout flag, we need more 5 units for the + * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item + * when selinux is enabled). */ - trans = btrfs_start_transaction(root, 11); + trans_num_items = 11; + if (flags & RENAME_WHITEOUT) + trans_num_items += 5; + trans = btrfs_start_transaction(root, trans_num_items); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_notrans; -- cgit From 0b901916a00bc7b14ee83cc8e41c3b0d561a8f22 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 9 May 2016 13:15:27 +0100 Subject: Btrfs: fix race between fsync and direct IO writes for prealloc extents When we do a direct IO write against a preallocated extent (fallocate) that does not go beyond the i_size of the inode, we do the write operation without holding the inode's i_mutex (an optimization that landed in commit 38851cc19adb ("Btrfs: implement unlocked dio write")). This allows for a very tiny time window where a race can happen with a concurrent fsync using the fast code path, as the direct IO write path creates first a new extent map (no longer flagged as a prealloc extent) and then it creates the ordered extent, while the fast fsync path first collects ordered extents and then it collects extent maps. This allows for the possibility of the fast fsync path to collect the new extent map without collecting the new ordered extent, and therefore logging an extent item based on the extent map without waiting for the ordered extent to be created and complete. This can result in a situation where after a log replay we end up with an extent not marked anymore as prealloc but it was only partially written (or not written at all), exposing random, stale or garbage data corresponding to the unwritten pages and without any checksums in the csum tree covering the extent's range. This is an extension of what was done in commit de0ee0edb21f ("Btrfs: fix race between fsync and lockless direct IO writes"). So fix this by creating first the ordered extent and then the extent map, so that this way if the fast fsync patch collects the new extent map it also collects the corresponding ordered extent. Signed-off-by: Filipe Manana Reviewed-by: Josef Bacik --- fs/btrfs/inode.c | 43 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 37 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0921d2b07f1d..45d0dafbbf40 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7658,6 +7658,25 @@ 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) { + + /* + * 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); + 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, @@ -7666,17 +7685,29 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, 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; } } - ret = btrfs_add_ordered_extent_dio(inode, start, - block_start, len, len, type); - if (ret) { - free_extent_map(em); - goto unlock_err; - } goto unlock; } } -- cgit From f78c436c3931e7df713688028f2b4faf72bf9f2a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 9 May 2016 13:15:41 +0100 Subject: Btrfs: fix race between block group relocation and nocow writes Relocation of a block group waits for all existing tasks flushing dellaloc, starting direct IO writes and any ordered extents before starting the relocation process. However for direct IO writes that end up doing nocow (inode either has the flag nodatacow set or the write is against a prealloc extent) we have a short time window that allows for a race that makes relocation proceed without waiting for the direct IO write to complete first, resulting in data loss after the relocation finishes. This is illustrated by the following diagram: CPU 1 CPU 2 btrfs_relocate_block_group(bg X) direct IO write starts against an extent in block group X using nocow mode (inode has the nodatacow flag or the write is for a prealloc extent) btrfs_direct_IO() btrfs_get_blocks_direct() --> can_nocow_extent() returns 1 btrfs_inc_block_group_ro(bg X) --> turns block group into RO mode btrfs_wait_ordered_roots() --> returns and does not know about the DIO write happening at CPU 2 (the task there has not created yet an ordered extent) relocate_block_group(bg X) --> rc->stage == MOVE_DATA_EXTENTS find_next_extent() --> returns extent that the DIO write is going to write to relocate_data_extent() relocate_file_extent_cluster() --> reads the extent from disk into pages belonging to the relocation inode and dirties them --> creates DIO ordered extent btrfs_submit_direct() --> submits bio against a location on disk obtained from an extent map before the relocation started btrfs_wait_ordered_range() --> writes all the pages read before to disk (belonging to the relocation inode) relocation finishes bio completes and wrote new data to the old location of the block group So fix this by tracking the number of nocow writers for a block group and make sure relocation waits for that number to go down to 0 before starting to move the extents. The same race can also happen with buffered writes in nocow mode since the patch I recently made titled "Btrfs: don't do unnecessary delalloc flushes when relocating", because we are no longer flushing all delalloc which served as a synchonization mechanism (due to page locking) and ensured the ordered extents for nocow buffered writes were created before we called btrfs_wait_ordered_roots(). The race with direct IO writes in nocow mode existed before that patch (no pages are locked or used during direct IO) and that fixed only races with direct IO writes that do cow. Signed-off-by: Filipe Manana Reviewed-by: Josef Bacik --- fs/btrfs/ctree.h | 13 +++++++++++++ fs/btrfs/extent-tree.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/inode.c | 15 +++++++++++++- fs/btrfs/relocation.c | 1 + 4 files changed, 81 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 90e70e21e479..7ae758685c7b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1419,6 +1419,16 @@ struct btrfs_block_group_cache { */ atomic_t reservations; + /* + * Incremented while holding the spinlock *lock* by a task checking if + * it can perform a nocow write (incremented if the value for the *ro* + * field is 0). Decremented by such tasks once they create an ordered + * extent or before that if some error happens before reaching that step. + * This is to prevent races between block group relocation and nocow + * writes through direct IO. + */ + atomic_t nocow_writers; + /* Lock for free space tree operations. */ struct mutex free_space_lock; @@ -3513,6 +3523,9 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, const u64 start); void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg); +bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); +void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); +void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg); void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, unsigned long count); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 09aad7b447f5..dcf89bfa990d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3824,6 +3824,59 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr) return readonly; } +bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_block_group_cache *bg; + bool ret = true; + + bg = btrfs_lookup_block_group(fs_info, bytenr); + if (!bg) + return false; + + spin_lock(&bg->lock); + if (bg->ro) + ret = false; + else + atomic_inc(&bg->nocow_writers); + spin_unlock(&bg->lock); + + /* no put on block group, done by btrfs_dec_nocow_writers */ + if (!ret) + btrfs_put_block_group(bg); + + return ret; + +} + +void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_block_group_cache *bg; + + bg = btrfs_lookup_block_group(fs_info, bytenr); + ASSERT(bg); + if (atomic_dec_and_test(&bg->nocow_writers)) + wake_up_atomic_t(&bg->nocow_writers); + /* + * Once for our lookup and once for the lookup done by a previous call + * to btrfs_inc_nocow_writers() + */ + btrfs_put_block_group(bg); + btrfs_put_block_group(bg); +} + +static int btrfs_wait_nocow_writers_atomic_t(atomic_t *a) +{ + schedule(); + return 0; +} + +void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg) +{ + wait_on_atomic_t(&bg->nocow_writers, + btrfs_wait_nocow_writers_atomic_t, + TASK_UNINTERRUPTIBLE); +} + static const char *alloc_name(u64 flags) { switch (flags) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 45d0dafbbf40..ee9be4199e7c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1382,6 +1382,9 @@ next_slot: */ if (csum_exist_in_range(root, disk_bytenr, num_bytes)) goto out_check; + if (!btrfs_inc_nocow_writers(root->fs_info, + disk_bytenr)) + goto out_check; nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + @@ -1396,6 +1399,9 @@ out_check: path->slots[0]++; if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); + if (nocow) + btrfs_dec_nocow_writers(root->fs_info, + disk_bytenr); goto next_slot; } if (!nocow) { @@ -1416,6 +1422,9 @@ out_check: if (ret) { if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); + if (nocow) + btrfs_dec_nocow_writers(root->fs_info, + disk_bytenr); goto error; } cow_start = (u64)-1; @@ -1458,6 +1467,8 @@ out_check: ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr, num_bytes, num_bytes, type); + if (nocow) + btrfs_dec_nocow_writers(root->fs_info, disk_bytenr); BUG_ON(ret); /* -ENOMEM */ if (root->root_key.objectid == @@ -7657,7 +7668,8 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, 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) == 1 && + btrfs_inc_nocow_writers(root->fs_info, block_start)) { /* * Create the ordered extent before the extent map. This @@ -7672,6 +7684,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, */ ret = btrfs_add_ordered_extent_dio(inode, start, block_start, len, len, type); + btrfs_dec_nocow_writers(root->fs_info, block_start); if (ret) { free_extent_map(em); goto unlock_err; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e78f8e44bd9a..054d9a80e77e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4255,6 +4255,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) rc->block_group->key.objectid, rc->block_group->flags); btrfs_wait_block_group_reservations(rc->block_group); + btrfs_wait_nocow_writers(rc->block_group); btrfs_wait_ordered_roots(fs_info, -1, rc->block_group->key.objectid, rc->block_group->key.offset); -- cgit 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/inode.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 From e0d46f5c6e0ba3a79e64cd60e62b7b7191ed93f3 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 22 Apr 2016 22:36:44 +0200 Subject: btrfs: Switch to generic xattr handlers The btrfs_{set,remove}xattr inode operations check for a read-only root (btrfs_root_readonly) before calling into generic_{set,remove}xattr. If this check is moved into __btrfs_setxattr, we can get rid of btrfs_{set,remove}xattr. This patch applies to mainline, I would like to keep it together with the other xattr cleanups if possible, though. Could you please review? Thanks, Andreas Signed-off-by: Andreas Gruenbacher Signed-off-by: Al Viro --- fs/btrfs/inode.c | 16 ++++++++-------- fs/btrfs/xattr.c | 22 +++------------------- fs/btrfs/xattr.h | 3 --- 3 files changed, 11 insertions(+), 30 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 41a5688ffdfe..0077b3b49e5e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10160,10 +10160,10 @@ static const struct inode_operations btrfs_dir_inode_operations = { .symlink = btrfs_symlink, .setattr = btrfs_setattr, .mknod = btrfs_mknod, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .permission = btrfs_permission, .get_acl = btrfs_get_acl, .set_acl = btrfs_set_acl, @@ -10237,10 +10237,10 @@ static const struct address_space_operations btrfs_symlink_aops = { static const struct inode_operations btrfs_file_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .permission = btrfs_permission, .fiemap = btrfs_fiemap, .get_acl = btrfs_get_acl, @@ -10251,10 +10251,10 @@ static const struct inode_operations btrfs_special_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .get_acl = btrfs_get_acl, .set_acl = btrfs_set_acl, .update_time = btrfs_update_time, @@ -10265,10 +10265,10 @@ static const struct inode_operations btrfs_symlink_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .update_time = btrfs_update_time, }; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 03224b00ea70..3bfb252206c7 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -237,6 +237,9 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans, struct btrfs_root *root = BTRFS_I(inode)->root; int ret; + if (btrfs_root_readonly(root)) + return -EROFS; + if (trans) return do_setxattr(trans, inode, name, value, size, flags); @@ -432,25 +435,6 @@ const struct xattr_handler *btrfs_xattr_handlers[] = { NULL, }; -int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) -{ - struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - - if (btrfs_root_readonly(root)) - return -EROFS; - return generic_setxattr(dentry, name, value, size, flags); -} - -int btrfs_removexattr(struct dentry *dentry, const char *name) -{ - struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - - if (btrfs_root_readonly(root)) - return -EROFS; - return generic_removexattr(dentry, name); -} - static int btrfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 96807b3d22f5..15fc4743dc70 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -28,9 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name, extern int __btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags); -extern int btrfs_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -extern int btrfs_removexattr(struct dentry *dentry, const char *name); extern int btrfs_xattr_security_init(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir, -- cgit From fe742fd4f90fa53cf31296bc5131ae1cdd6d84bb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 18 May 2016 13:15:05 -0400 Subject: Revert "btrfs: switch to ->iterate_shared()" This reverts commit 972b241f8441dc37a3f89dcd7e71d7f013873d13. Quoth Chris: didn't take the delayed inode stuff into account it got an rbtree of items and it pulls things out so in shared mode, its hugely racey sorry, lets revert and fix it for real inside of btrfs Signed-off-by: Chris Mason Signed-off-by: Al Viro --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3e2ada1267f3..2aaba58b4856 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10181,7 +10181,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = { static const struct file_operations btrfs_dir_file_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate_shared = btrfs_real_readdir, + .iterate = btrfs_real_readdir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_ioctl, -- cgit From 0132761017e012ab4dc8584d679503f2ba26ca86 Mon Sep 17 00:00:00 2001 From: Nicholas D Steeves Date: Thu, 19 May 2016 21:18:45 -0400 Subject: btrfs: fix string and comment grammatical issues and typos Signed-off-by: Nicholas D Steeves Signed-off-by: David Sterba --- fs/btrfs/backref.c | 2 +- fs/btrfs/btrfs_inode.h | 2 +- fs/btrfs/check-integrity.c | 2 +- fs/btrfs/ctree.c | 14 +++++++------- fs/btrfs/ctree.h | 6 +++--- fs/btrfs/delayed-ref.h | 2 +- fs/btrfs/dev-replace.c | 2 +- fs/btrfs/disk-io.c | 10 +++++----- fs/btrfs/extent-tree.c | 32 ++++++++++++++++---------------- fs/btrfs/extent_io.c | 4 ++-- fs/btrfs/extent_map.c | 2 +- fs/btrfs/file.c | 4 ++-- fs/btrfs/free-space-cache.c | 2 +- fs/btrfs/free-space-cache.h | 2 +- fs/btrfs/inode.c | 22 +++++++++++----------- fs/btrfs/ioctl.c | 10 +++++----- fs/btrfs/ordered-data.h | 2 +- fs/btrfs/qgroup.c | 16 ++++++++-------- fs/btrfs/raid56.c | 6 +++--- fs/btrfs/relocation.c | 12 ++++++------ fs/btrfs/root-tree.c | 4 ++-- fs/btrfs/scrub.c | 4 ++-- fs/btrfs/send.c | 6 +++--- fs/btrfs/struct-funcs.c | 2 +- fs/btrfs/super.c | 8 ++++---- fs/btrfs/tests/extent-io-tests.c | 2 +- fs/btrfs/tests/free-space-tests.c | 7 ++++--- fs/btrfs/tests/inode-tests.c | 2 +- fs/btrfs/tests/qgroup-tests.c | 2 +- fs/btrfs/transaction.h | 2 +- fs/btrfs/tree-log.c | 8 ++++---- fs/btrfs/ulist.c | 2 +- fs/btrfs/volumes.c | 8 ++++---- 33 files changed, 106 insertions(+), 105 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 80e8472d618b..b8b598740bbd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1939,7 +1939,7 @@ static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off, * from ipath->fspath->val[i]. * when it returns, there are ipath->fspath->elem_cnt number of paths available * in ipath->fspath->val[]. when the allocated space wasn't sufficient, the - * number of missed paths in recored in ipath->fspath->elem_missed, otherwise, + * number of missed paths is recorded in ipath->fspath->elem_missed, otherwise, * it's zero. ipath->fspath->bytes_missing holds the number of bytes that would * have been needed to return all paths. */ diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 61205e3bbefa..c0a2018761f9 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -303,7 +303,7 @@ struct btrfs_dio_private { struct bio *dio_bio; /* - * The original bio may be splited to several sub-bios, this is + * The original bio may be split to several sub-bios, this is * done during endio of sub-bios */ int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 516e19d1d202..b677a6ea6001 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -1939,7 +1939,7 @@ again: /* * Clear all references of this block. Do not free * the block itself even if is not referenced anymore - * because it still carries valueable information + * because it still carries valuable information * like whether it was ever written and IO completed. */ list_for_each_entry_safe(l, tmp, &block->ref_to_list, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index ec7928a27aaa..4997f175b446 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -156,7 +156,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root) /* * RCU really hurts here, we could free up the root node because - * it was cow'ed but we may not get the new root node yet so do + * it was COWed but we may not get the new root node yet so do * the inc_not_zero dance and if it doesn't work then * synchronize_rcu and try again. */ @@ -955,7 +955,7 @@ int btrfs_block_can_be_shared(struct btrfs_root *root, struct extent_buffer *buf) { /* - * Tree blocks not in refernece counted trees and tree roots + * Tree blocks not in reference counted trees and tree roots * are never shared. If a block was allocated after the last * snapshot and the block was not allocated by tree relocation, * we know the block is not shared. @@ -1270,7 +1270,7 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, /* * tm is a pointer to the first operation to rewind within eb. then, all - * previous operations will be rewinded (until we reach something older than + * previous operations will be rewound (until we reach something older than * time_seq). */ static void @@ -1345,7 +1345,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, } /* - * Called with eb read locked. If the buffer cannot be rewinded, the same buffer + * Called with eb read locked. If the buffer cannot be rewound, the same buffer * is returned. If rewind operations happen, a fresh buffer is returned. The * returned buffer is always read-locked. If the returned buffer is not the * input buffer, the lock on the input buffer is released and the input buffer @@ -1516,7 +1516,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans, * 3) the root is not forced COW. * * What is forced COW: - * when we create snapshot during commiting the transaction, + * when we create snapshot during committing the transaction, * after we've finished coping src root, we must COW the shared * block to ensure the metadata consistency. */ @@ -1531,7 +1531,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans, /* * cows a single block, see __btrfs_cow_block for the real work. - * This version of it has extra checks so that a block isn't cow'd more than + * This version of it has extra checks so that a block isn't COWed more than * once per transaction, as long as it hasn't been written yet */ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, @@ -2986,7 +2986,7 @@ again: btrfs_unlock_up_safe(p, level + 1); /* - * Since we can unwind eb's we want to do a real search every + * Since we can unwind ebs we want to do a real search every * time. */ prev_cmp = -1; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 84a6a5b3384a..65e7a9fa881f 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -186,7 +186,7 @@ static const int btrfs_csum_sizes[] = { 4 }; /* four bytes for CRC32 */ #define BTRFS_EMPTY_DIR_SIZE 0 -/* spefic to btrfs_map_block(), therefore not in include/linux/blk_types.h */ +/* specific to btrfs_map_block(), therefore not in include/linux/blk_types.h */ #define REQ_GET_READ_MIRRORS (1 << 30) #define BTRFS_FT_UNKNOWN 0 @@ -1221,7 +1221,7 @@ struct btrfs_space_info { * bytes_pinned does not reflect the bytes that will be pinned once the * delayed refs are flushed, so this counter is inc'ed every time we * call btrfs_free_extent so it is a realtime count of what will be - * freed once the transaction is committed. It will be zero'ed every + * freed once the transaction is committed. It will be zeroed every * time the transaction commits. */ struct percpu_counter total_bytes_pinned; @@ -2392,7 +2392,7 @@ static inline void btrfs_init_map_token (struct btrfs_map_token *token) token->kaddr = NULL; } -/* some macros to generate set/get funcs for the struct fields. This +/* some macros to generate set/get functions for the struct fields. This * assumes there is a lefoo_to_cpu for every type, so lets make a simple * one for u8: */ diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index c24b653c7343..5fca9534a271 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -188,7 +188,7 @@ struct btrfs_delayed_ref_root { /* * To make qgroup to skip given root. - * This is for snapshot, as btrfs_qgroup_inherit() will manully + * This is for snapshot, as btrfs_qgroup_inherit() will manually * modify counters for snapshot and its source, so we should skip * the snapshot in new_root/old_roots or it will get calculated twice */ diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 26bcb487f958..0584b6c2df57 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -441,7 +441,7 @@ leave: } /* - * blocked until all flighting bios are finished. + * blocked until all in-flight bios operations are finished. */ static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 263823f28ba4..aacc707ef952 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -384,7 +384,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, /* * Things reading via commit roots that don't have normal protection, * like send, can have a really old block in cache that may point at a - * block that has been free'd and re-allocated. So don't clear uptodate + * block that has been freed and re-allocated. So don't clear uptodate * if we find an eb that is under IO (dirty/writeback) because we could * end up reading in the stale data and then writing it back out and * making everybody very sad. @@ -418,7 +418,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb) /* * The super_block structure does not span the whole * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space - * is filled with zeros and is included in the checkum. + * is filled with zeros and is included in the checksum. */ crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE, crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); @@ -600,7 +600,7 @@ static noinline int check_leaf(struct btrfs_root *root, /* * Check to make sure that we don't point outside of the leaf, - * just incase all the items are consistent to eachother, but + * just in case all the items are consistent to each other, but * all point outside of the leaf. */ if (btrfs_item_end_nr(leaf, slot) > @@ -3017,7 +3017,7 @@ retry_root_backup: } /* - * Mount does not set all options immediatelly, we can do it now and do + * Mount does not set all options immediately, we can do it now and do * not have to wait for transaction commit */ btrfs_apply_pending_changes(fs_info); @@ -3245,7 +3245,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) btrfs_warn_rl_in_rcu(device->dev_root->fs_info, "lost page write due to IO error on %s", rcu_str_deref(device->name)); - /* note, we dont' set_buffer_write_io_error because we have + /* note, we don't set_buffer_write_io_error because we have * our own ways of dealing with the IO errors */ clear_buffer_uptodate(bh); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0ddc996a40e1..939a043eabfa 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -980,7 +980,7 @@ out_free: * event that tree block loses its owner tree's reference and do the * back refs conversion. * - * When a tree block is COW'd through a tree, there are four cases: + * When a tree block is COWed through a tree, there are four cases: * * The reference count of the block is one and the tree is the block's * owner tree. Nothing to do in this case. @@ -2595,7 +2595,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, } /* - * Need to drop our head ref lock and re-aqcuire the + * Need to drop our head ref lock and re-acquire the * delayed ref lock and then re-check to make sure * nobody got added. */ @@ -2747,7 +2747,7 @@ static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads) /* * We don't ever fill up leaves all the way so multiply by 2 just to be - * closer to what we're really going to want to ouse. + * closer to what we're really going to want to use. */ return div_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(root)); } @@ -2851,7 +2851,7 @@ static void delayed_ref_async_start(struct btrfs_work *work) } /* - * trans->sync means that when we call end_transaciton, we won't + * trans->sync means that when we call end_transaction, we won't * wait on delayed refs */ trans->sync = true; @@ -4243,7 +4243,7 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, * Called if we need to clear a data reservation for this inode * Normally in a error case. * - * This one will handle the per-indoe data rsv map for accurate reserved + * This one will handle the per-inode data rsv map for accurate reserved * space framework. */ void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) @@ -4911,7 +4911,7 @@ void btrfs_init_async_reclaim_work(struct work_struct *work) * @orig_bytes - the number of bytes we want * @flush - whether or not we can flush to make our reservation * - * This will reserve orgi_bytes number of bytes from the space info associated + * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to * flush out space to make room. It will do this by flushing delalloc if * possible or committing the transaction. If flush is 0 then no attempts to @@ -5516,7 +5516,7 @@ void btrfs_orphan_release_metadata(struct inode *inode) * common file/directory operations, they change two fs/file trees * and root tree, the number of items that the qgroup reserves is * different with the free space reservation. So we can not use - * the space reseravtion mechanism in start_transaction(). + * the space reservation mechanism in start_transaction(). */ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, @@ -5565,7 +5565,7 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root, /** * drop_outstanding_extent - drop an outstanding extent * @inode: the inode we're dropping the extent for - * @num_bytes: the number of bytes we're relaseing. + * @num_bytes: the number of bytes we're releasing. * * This is called when we are freeing up an outstanding extent, either called * after an error or after an extent is written. This will return the number of @@ -5591,7 +5591,7 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes) drop_inode_space = 1; /* - * If we have more or the same amount of outsanding extents than we have + * If we have more or the same amount of outstanding extents than we have * reserved then we need to leave the reserved extents count alone. */ if (BTRFS_I(inode)->outstanding_extents >= @@ -5605,8 +5605,8 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes) } /** - * calc_csum_metadata_size - return the amount of metada space that must be - * reserved/free'd for the given bytes. + * calc_csum_metadata_size - return the amount of metadata space that must be + * reserved/freed for the given bytes. * @inode: the inode we're manipulating * @num_bytes: the number of bytes in question * @reserve: 1 if we are reserving space, 0 if we are freeing space @@ -5758,7 +5758,7 @@ out_fail: /* * This is tricky, but first we need to figure out how much we - * free'd from any free-ers that occurred during this + * freed from any free-ers that occurred during this * reservation, so we reset ->csum_bytes to the csum_bytes * before we dropped our lock, and then call the free for the * number of bytes that were freed while we were trying our @@ -5780,7 +5780,7 @@ out_fail: /* * Now reset ->csum_bytes to what it should be. If bytes is - * more than to_free then we would have free'd more space had we + * more than to_free then we would have freed more space had we * not had an artificially high ->csum_bytes, so we need to free * the remainder. If bytes is the same or less then we don't * need to do anything, the other free-ers did the correct @@ -7471,7 +7471,7 @@ loop: if (loop == LOOP_CACHING_NOWAIT) { /* * We want to skip the LOOP_CACHING_WAIT step if we - * don't have any unached bgs and we've alrelady done a + * don't have any uncached bgs and we've already done a * full search through. */ if (orig_have_caching_bg || !full_search) @@ -7873,7 +7873,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, /* * Mixed block groups will exclude before processing the log so we only - * need to do the exlude dance if this fs isn't mixed. + * need to do the exclude dance if this fs isn't mixed. */ if (!btrfs_fs_incompat(root->fs_info, MIXED_GROUPS)) { ret = __exclude_logged_extent(root, ins->objectid, ins->offset); @@ -9317,7 +9317,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo) u64 free_bytes = 0; int factor; - /* It's df, we don't care if it's racey */ + /* It's df, we don't care if it's racy */ if (list_empty(&sinfo->ro_bgs)) return 0; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c1139bcf8870..5fdf1fcb03c9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4591,7 +4591,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb) if (mapped) spin_unlock(&page->mapping->private_lock); - /* One for when we alloced the page */ + /* One for when we allocated the page */ put_page(page); } while (index != 0); } @@ -5751,7 +5751,7 @@ int try_release_extent_buffer(struct page *page) struct extent_buffer *eb; /* - * We need to make sure noboody is attaching this page to an eb right + * We need to make sure nobody is attaching this page to an eb right * now. */ spin_lock(&page->mapping->private_lock); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 318b048eb254..e0715fcfb11e 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -62,7 +62,7 @@ struct extent_map *alloc_extent_map(void) /** * free_extent_map - drop reference count of an extent_map - * @em: extent map being releasead + * @em: extent map being released * * Drops the reference out on @em by one and free the structure * if the reference count hits zero. diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 8d7b5a45c005..50dac40d9561 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2024,7 +2024,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) BTRFS_I(inode)->last_trans <= root->fs_info->last_trans_committed)) { /* - * We'v had everything committed since the last time we were + * We've had everything committed since the last time we were * modified so clear this flag in case it was set for whatever * reason, it's no longer relevant. */ @@ -2372,7 +2372,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) /* Check the aligned pages after the first unaligned page, * if offset != orig_start, which means the first unaligned page - * including serveral following pages are already in holes, + * including several following pages are already in holes, * the extra check can be skipped */ if (offset == orig_start) { /* after truncate page, check hole again */ diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 5e6062c26129..c6dc1183f542 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1983,7 +1983,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl, /* * If this block group has some small extents we don't want to * use up all of our free slots in the cache with them, we want - * to reserve them to larger extents, however if we have plent + * to reserve them to larger extents, however if we have plenty * of cache left then go ahead an dadd them, no sense in adding * the overhead of a bitmap if we don't have to. */ diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 33178c490ace..3af651c2bbc7 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -123,7 +123,7 @@ int btrfs_return_cluster_to_free_space( int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen); -/* Support functions for runnint our sanity tests */ +/* Support functions for running our sanity tests */ #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int test_add_free_space_entry(struct btrfs_block_group_cache *cache, u64 offset, u64 bytes, bool bitmap); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1a4bd193962c..2027bbd4b05e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -455,7 +455,7 @@ again: /* * skip compression for a small file range(<=blocksize) that - * isn't an inline extent, since it dosen't save disk space at all. + * isn't an inline extent, since it doesn't save disk space at all. */ if (total_compressed <= blocksize && (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) @@ -3705,7 +3705,7 @@ cache_index: * and doesn't have an inode ref with the name "bar" anymore. * * Setting last_unlink_trans to last_trans is a pessimistic approach, - * but it guarantees correctness at the expense of ocassional full + * but it guarantees correctness at the expense of occasional full * transaction commits on fsync if our inode is a directory, or if our * inode is not a directory, logging its parent unnecessarily. */ @@ -4961,7 +4961,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) * be instantly completed which will give us extents that need * to be truncated. If we fail to get an orphan inode down we * could have left over extents that were never meant to live, - * so we need to garuntee from this point on that everything + * so we need to guarantee from this point on that everything * will be consistent. */ ret = btrfs_orphan_add(trans, inode); @@ -5231,7 +5231,7 @@ void btrfs_evict_inode(struct inode *inode) } /* - * We can't just steal from the global reserve, we need tomake + * We can't just steal from the global reserve, we need to make * sure there is room to do it, if not we need to commit and try * again. */ @@ -7407,7 +7407,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, cached_state); /* * We're concerned with the entire range that we're going to be - * doing DIO to, so we need to make sure theres no ordered + * doing DIO to, so we need to make sure there's no ordered * extents in this range. */ ordered = btrfs_lookup_ordered_range(inode, lockstart, @@ -7569,7 +7569,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, if (current->journal_info) { /* * Need to pull our outstanding extents and set journal_info to NULL so - * that anything that needs to check if there's a transction doesn't get + * that anything that needs to check if there's a transaction doesn't get * confused. */ dio_data = current->journal_info; @@ -7602,7 +7602,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * decompress it, so there will be buffering required no matter what we * do, so go ahead and fallback to buffered. * - * We return -ENOTBLK because thats what makes DIO go ahead and go back + * We return -ENOTBLK because that's what makes DIO go ahead and go back * to buffered IO. Don't blame me, this is the price we pay for using * the generic code. */ @@ -9018,7 +9018,7 @@ static int btrfs_truncate(struct inode *inode) return ret; /* - * Yes ladies and gentelment, this is indeed ugly. The fact is we have + * Yes ladies and gentlemen, this is indeed ugly. The fact is we have * 3 things going on here * * 1) We need to reserve space for our orphan item and the space to @@ -9032,15 +9032,15 @@ static int btrfs_truncate(struct inode *inode) * space reserved in case it uses space during the truncate (thank you * very much snapshotting). * - * And we need these to all be seperate. The fact is we can use alot of + * And we need these to all be separate. The fact is we can use a lot of * space doing the truncate, and we have no earthly idea how much space - * we will use, so we need the truncate reservation to be seperate so it + * we will use, so we need the truncate reservation to be separate so it * doesn't end up using space reserved for updating the inode or * removing the orphan item. We also need to be able to stop the * transaction and start a new one, which means we need to be able to * update the inode several times, and we have no idea of knowing how * many times that will be, so we can't just reserve 1 item for the - * entirety of the opration, so that has to be done seperately as well. + * entirety of the operation, so that has to be done separately as well. * Then there is the orphan item, which does indeed need to be held on * to for the whole operation, and we need nobody to touch this reserved * space except the orphan code. diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 72f48252a55d..972cd0b00b21 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -296,7 +296,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } } else { /* - * Revert back under same assuptions as above + * Revert back under same assumptions as above */ if (S_ISREG(mode)) { if (inode->i_size == 0) @@ -461,7 +461,7 @@ static noinline int create_subvol(struct inode *dir, /* * Don't create subvolume whose level is not zero. Or qgroup will be - * screwed up since it assume subvolme qgroup's level to be 0. + * screwed up since it assumes subvolume qgroup's level to be 0. */ if (btrfs_qgroup_level(objectid)) return -ENOSPC; @@ -771,7 +771,7 @@ free_pending: * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability - * 6. If the victim is append-only or immutable we can't do antyhing with + * 6. If the victim is append-only or immutable we can't do anything with * links pointing to it. * 7. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 8. If we were asked to remove a non-directory and victim isn't one - EISDIR. @@ -4585,7 +4585,7 @@ again: } /* - * mut. excl. ops lock is locked. Three possibilites: + * mut. excl. ops lock is locked. Three possibilities: * (1) some other op is running * (2) balance is running * (3) balance is paused -- special case (think resume) @@ -5490,7 +5490,7 @@ long btrfs_ioctl(struct file *file, unsigned int ret = btrfs_sync_fs(file_inode(file)->i_sb, 1); /* * The transaction thread may want to do more work, - * namely it pokes the cleaner ktread that will start + * namely it pokes the cleaner kthread that will start * processing uncleaned subvols. */ wake_up_process(root->fs_info->transaction_kthread); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 23c96059cef2..ae068bbddc0d 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -58,7 +58,7 @@ struct btrfs_ordered_sum { #define BTRFS_ORDERED_COMPRESSED 3 /* writing a zlib compressed extent */ -#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */ +#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to preallocated extent */ #define BTRFS_ORDERED_DIRECT 5 /* set when we're doing DIO with this extent */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 34af959b4e0f..9d4c05b14f6e 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -85,7 +85,7 @@ struct btrfs_qgroup { /* * temp variables for accounting operations - * Refer to qgroup_shared_accouting() for details. + * Refer to qgroup_shared_accounting() for details. */ u64 old_refcnt; u64 new_refcnt; @@ -499,7 +499,7 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) } /* * we call btrfs_free_qgroup_config() when umounting - * filesystem and disabling quota, so we set qgroup_ulit + * filesystem and disabling quota, so we set qgroup_ulist * to be null here to avoid double free. */ ulist_free(fs_info->qgroup_ulist); @@ -1036,7 +1036,7 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info, /* * The easy accounting, if we are adding/removing the only ref for an extent - * then this qgroup and all of the parent qgroups get their refrence and + * then this qgroup and all of the parent qgroups get their reference and * exclusive counts adjusted. * * Caller should hold fs_info->qgroup_lock. @@ -1436,7 +1436,7 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, /* * No need to do lock, since this function will only be called in - * btrfs_commmit_transaction(). + * btrfs_commit_transaction(). */ node = rb_first(&delayed_refs->dirty_extent_root); while (node) { @@ -1557,7 +1557,7 @@ static int qgroup_update_refcnt(struct btrfs_fs_info *fs_info, * A: cur_old_roots < nr_old_roots (not exclusive before) * !A: cur_old_roots == nr_old_roots (possible exclusive before) * B: cur_new_roots < nr_new_roots (not exclusive now) - * !B: cur_new_roots == nr_new_roots (possible exclsuive now) + * !B: cur_new_roots == nr_new_roots (possible exclusive now) * * Results: * +: Possible sharing -> exclusive -: Possible exclusive -> sharing @@ -1851,7 +1851,7 @@ out: } /* - * Copy the acounting information between qgroups. This is necessary + * Copy the accounting information between qgroups. This is necessary * when a snapshot or a subvolume is created. Throwing an error will * cause a transaction abort so we take extra care here to only error * when a readonly fs is a reasonable outcome. @@ -2340,7 +2340,7 @@ out: mutex_unlock(&fs_info->qgroup_rescan_lock); /* - * only update status, since the previous part has alreay updated the + * only update status, since the previous part has already updated the * qgroup info. */ trans = btrfs_start_transaction(fs_info->quota_root, 1); @@ -2670,7 +2670,7 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) } /* - * Check qgroup reserved space leaking, normally at destory inode + * Check qgroup reserved space leaking, normally at destroy inode * time */ void btrfs_qgroup_check_reserved_leak(struct inode *inode) diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 0b7792e02dd5..f8b6d411a034 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -576,7 +576,7 @@ static int rbio_can_merge(struct btrfs_raid_bio *last, * we can't merge with cached rbios, since the * idea is that when we merge the destination * rbio is going to run our IO for us. We can - * steal from cached rbio's though, other functions + * steal from cached rbios though, other functions * handle that. */ if (test_bit(RBIO_CACHE_BIT, &last->flags) || @@ -2368,7 +2368,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, run_xor(pointers + 1, nr_data - 1, PAGE_SIZE); } - /* Check scrubbing pairty and repair it */ + /* Check scrubbing parity and repair it */ p = rbio_stripe_page(rbio, rbio->scrubp, pagenr); parity = kmap(p); if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE)) @@ -2493,7 +2493,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio) /* * Here means we got one corrupted data stripe and one * corrupted parity on RAID6, if the corrupted parity - * is scrubbing parity, luckly, use the other one to repair + * is scrubbing parity, luckily, use the other one to repair * the data, or we can not repair the data stripe. */ if (failp != rbio->scrubp) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index bd5ea1a8a9f1..852be779a834 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -668,8 +668,8 @@ int find_inline_backref(struct extent_buffer *leaf, int slot, * roots of b-trees that reference the tree block. * * the basic idea of this function is check backrefs of a given block - * to find upper level blocks that refernece the block, and then check - * bakcrefs of these upper level blocks recursively. the recursion stop + * to find upper level blocks that reference the block, and then check + * backrefs of these upper level blocks recursively. the recursion stop * when tree root is reached or backrefs for the block is cached. * * NOTE: if we find backrefs for a block are cached, we know backrefs @@ -1160,7 +1160,7 @@ out: if (!RB_EMPTY_NODE(&upper->rb_node)) continue; - /* Add this guy's upper edges to the list to proces */ + /* Add this guy's upper edges to the list to process */ list_for_each_entry(edge, &upper->upper, list[LOWER]) list_add_tail(&edge->list[UPPER], &list); if (list_empty(&upper->upper)) @@ -2396,7 +2396,7 @@ again: } /* - * we keep the old last snapshod transid in rtranid when we + * we keep the old last snapshot transid in rtranid when we * created the relocation tree. */ last_snap = btrfs_root_rtransid(&reloc_root->root_item); @@ -2616,7 +2616,7 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans, * only one thread can access block_rsv at this point, * so we don't need hold lock to protect block_rsv. * we expand more reservation size here to allow enough - * space for relocation and we will return eailer in + * space for relocation and we will return earlier in * enospc case. */ rc->block_rsv->size = tmp + rc->extent_root->nodesize * @@ -4591,7 +4591,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, /* * called before creating snapshot. it calculates metadata reservation - * requried for relocating tree blocks in the snapshot + * required for relocating tree blocks in the snapshot */ void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending, u64 *bytes_to_reserve) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 9fcd6dfc3266..5ddf14e1b2d2 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -71,9 +71,9 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot, * search_key: the key to search * path: the path we search * root_item: the root item of the tree we look for - * root_key: the reak key of the tree we look for + * root_key: the root key of the tree we look for * - * If ->offset of 'seach_key' is -1ULL, it means we are not sure the offset + * If ->offset of 'search_key' is -1ULL, it means we are not sure the offset * of the search key, just lookup the root with the highest offset for a * given objectid. * diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 841dae874a21..6838b2ca3cab 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1044,7 +1044,7 @@ nodatasum_case: /* * !is_metadata and !have_csum, this means that the data - * might not be COW'ed, that it might be modified + * might not be COWed, that it might be modified * concurrently. The general strategy to work on the * commit root does not help in the case when COW is not * used. @@ -1125,7 +1125,7 @@ nodatasum_case: * the 2nd page of mirror #1 faces I/O errors, and the 2nd page * of mirror #2 is readable but the final checksum test fails, * then the 2nd page of mirror #3 could be tried, whether now - * the final checksum succeedes. But this would be a rare + * the final checksum succeeds. But this would be a rare * exception and is therefore not implemented. At least it is * avoided that the good copy is overwritten. * A more useful improvement would be to pick the sectors diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 8d358c547c59..e9710f461008 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1831,7 +1831,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, /* * If we have a parent root we need to verify that the parent dir was - * not delted and then re-created, if it was then we have no overwrite + * not deleted and then re-created, if it was then we have no overwrite * and we can just unlink this entry. */ if (sctx->parent_root) { @@ -4192,9 +4192,9 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key, return -ENOMEM; /* - * This hack is needed because empty acl's are stored as zero byte + * This hack is needed because empty acls are stored as zero byte * data in xattrs. Problem with that is, that receiving these zero byte - * acl's will fail later. To fix this, we send a dummy acl list that + * acls will fail later. To fix this, we send a dummy acl list that * only contains the version number and no entries. */ if (!strncmp(name, XATTR_NAME_POSIX_ACL_ACCESS, name_len) || diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c index e05619f241be..875c757e73e2 100644 --- a/fs/btrfs/struct-funcs.c +++ b/fs/btrfs/struct-funcs.c @@ -36,7 +36,7 @@ static inline void put_unaligned_le8(u8 val, void *p) * * The end result is that anyone who #includes ctree.h gets a * declaration for the btrfs_set_foo functions and btrfs_foo functions, - * which are wappers of btrfs_set_token_#bits functions and + * which are wrappers of btrfs_set_token_#bits functions and * btrfs_get_token_#bits functions, which are defined in this file. * * These setget functions do all the extent_buffer related mapping diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 00b8f37cc306..01ef1865db63 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -121,7 +121,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info) * Note that a running device replace operation is not * canceled here although there is no way to update * the progress. It would add the risk of a deadlock, - * therefore the canceling is ommited. The only penalty + * therefore the canceling is omitted. The only penalty * is that some I/O remains active until the procedure * completes. The next time when the filesystem is * mounted writeable again, the device replace @@ -1881,7 +1881,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) int ret; /* - * We aren't under the device list lock, so this is racey-ish, but good + * We aren't under the device list lock, so this is racy-ish, but good * enough for our purposes. */ nr_devices = fs_info->fs_devices->open_devices; @@ -1900,7 +1900,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) if (!devices_info) return -ENOMEM; - /* calc min stripe number for data space alloction */ + /* calc min stripe number for data space allocation */ type = btrfs_get_alloc_profile(root, 1); if (type & BTRFS_BLOCK_GROUP_RAID0) { min_stripes = 2; @@ -1936,7 +1936,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) avail_space *= BTRFS_STRIPE_LEN; /* - * In order to avoid overwritting the superblock on the drive, + * In order to avoid overwriting the superblock on the drive, * btrfs starts at an offset of at least 1MB when doing chunk * allocation. */ diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index c190d2a520d1..55724607f79b 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -176,7 +176,7 @@ static int test_find_delalloc(void) locked_page = find_lock_page(inode->i_mapping, test_start >> PAGE_SHIFT); if (!locked_page) { - test_msg("Could'nt find the locked page\n"); + test_msg("Couldn't find the locked page\n"); goto out_bits; } start = test_start; diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index 514247515312..0eeb8f3d6b67 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -25,7 +25,7 @@ #define BITS_PER_BITMAP (PAGE_SIZE * 8) /* - * This test just does basic sanity checking, making sure we can add an exten + * This test just does basic sanity checking, making sure we can add an extent * entry and remove space from either end and the middle, and make sure we can * remove space that covers adjacent extent entries. */ @@ -396,8 +396,9 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache) * wasn't optimal as they could be spread all over the block group while under * concurrency (extra overhead and fragmentation). * - * This stealing approach is benefical, since we always prefer to allocate from - * extent entries, both for clustered and non-clustered allocation requests. + * This stealing approach is beneficial, since we always prefer to allocate + * from extent entries, both for clustered and non-clustered allocation + * requests. */ static int test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache) diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 863a6a3af1f8..8a25fe8b7c45 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -264,7 +264,7 @@ static noinline int test_btrfs_get_extent(void) /* * We will just free a dummy node if it's ref count is 2 so we need an - * extra ref so our searches don't accidently release our page. + * extra ref so our searches don't accidentally release our page. */ extent_buffer_get(root->node); btrfs_set_header_nritems(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 8ea5d34bc5a2..8aa4ded31326 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -234,7 +234,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root) } /* - * Since the test trans doesn't havee the complicated delayed refs, + * Since the test trans doesn't have the complicated delayed refs, * we can only call btrfs_qgroup_account_extent() directly to test * quota. */ diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 72be51f7ca2f..9fe0ec2bf0fe 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -144,7 +144,7 @@ struct btrfs_pending_snapshot { /* block reservation for the operation */ struct btrfs_block_rsv block_rsv; u64 qgroup_reserved; - /* extra metadata reseration for relocation */ + /* extra metadata reservation for relocation */ int error; bool readonly; struct list_head list; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index a111e275ab9e..f3a8939d63fb 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2330,7 +2330,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, break; /* for regular files, make sure corresponding - * orhpan item exist. extents past the new EOF + * orphan item exist. extents past the new EOF * will be truncated later by orphan cleanup. */ if (S_ISREG(mode)) { @@ -4937,7 +4937,7 @@ out_unlock: * the actual unlink operation, so if we do this check before a concurrent task * sets last_unlink_trans it means we've logged a consistent version/state of * all the inode items, otherwise we are not sure and must do a transaction - * commit (the concurrent task migth have only updated last_unlink_trans before + * commit (the concurrent task might have only updated last_unlink_trans before * we logged the inode or it might have also done the unlink). */ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, @@ -4996,7 +4996,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, while (1) { /* * If we are logging a directory then we start with our inode, - * not our parents inode, so we need to skipp setting the + * not our parent's inode, so we need to skip setting the * logged_trans so that further down in the log code we don't * think this inode has already been logged. */ @@ -5375,7 +5375,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, log_dentries = true; /* - * On unlink we must make sure all our current and old parent directores + * On unlink we must make sure all our current and old parent directory * inodes are fully logged. This is to prevent leaving dangling * directory index entries in directories that were our parents but are * not anymore. Not doing this results in old parent directory being diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c index 91feb2bdefee..b1434bb57e36 100644 --- a/fs/btrfs/ulist.c +++ b/fs/btrfs/ulist.c @@ -28,7 +28,7 @@ * } * ulist_free(ulist); * - * This assumes the graph nodes are adressable by u64. This stems from the + * This assumes the graph nodes are addressable by u64. This stems from the * usage for tree enumeration in btrfs, where the logical addresses are * 64 bit. * diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bd0f45fb38c4..8fe7fff5ffb7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2165,7 +2165,7 @@ static int btrfs_prepare_sprout(struct btrfs_root *root) } /* - * strore the expected generation for seed devices in device items. + * Store the expected generation for seed devices in device items. */ static int btrfs_finish_sprout(struct btrfs_trans_handle *trans, struct btrfs_root *root) @@ -3362,7 +3362,7 @@ static int should_balance_chunk(struct btrfs_root *root, } else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) { /* * Same logic as the 'limit' filter; the minimum cannot be - * determined here because we do not have the global informatoin + * determined here because we do not have the global information * about the count of all chunks that satisfy the filters. */ if (bargs->limit_max == 0) @@ -6032,7 +6032,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) { atomic_inc(&bbio->error); if (atomic_dec_and_test(&bbio->stripes_pending)) { - /* Shoud be the original bio. */ + /* Should be the original bio. */ WARN_ON(bio != bbio->orig_bio); btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; @@ -6516,7 +6516,7 @@ int btrfs_read_sys_array(struct btrfs_root *root) set_extent_buffer_uptodate(sb); btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0); /* - * The sb extent buffer is artifical and just used to read the system array. + * The sb extent buffer is artificial and just used to read the system array. * set_extent_buffer_uptodate() call does not properly mark all it's * pages up-to-date when the page is larger: extent does not cover the * whole page and consequently check_page_uptodate does not find all -- cgit From 8dff9c85341032767d7b519217a79ea04cd676b0 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Sat, 19 Sep 2015 11:28:25 -0700 Subject: Btrfs: deal with duplciates during extent_map insertion in btrfs_get_extent When dealing with inline extents, btrfs_get_extent will incorrectly try to insert a duplicate extent_map. The dup hits -EEXIST from add_extent_map, but then we try to merge with the existing one and end up trying to insert a zero length extent_map. This actually works most of the time, except when there are extent maps past the end of the inline extent. rocksdb will trigger this sometimes because it preallocates an extent and then truncates down. Josef made a script to trigger with xfs_io: #!/bin/bash xfs_io -f -c "pwrite 0 1000" inline xfs_io -c "falloc -k 4k 1M" inline xfs_io -c "pread 0 1000" -c "fadvise -d 0 1000" -c "pread 0 1000" inline xfs_io -c "fadvise -d 0 1000" inline cat inline You'll get EIOs trying to read inline after this because add_extent_map is returning EEXIST Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2debd42c4660..e5558d9e396e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6979,7 +6979,18 @@ insert: * existing will always be non-NULL, since there must be * extent causing the -EEXIST. */ - if (start >= extent_map_end(existing) || + if (existing->start == em->start && + extent_map_end(existing) == extent_map_end(em) && + em->block_start == existing->block_start) { + /* + * these two extents are the same, it happens + * with inlines especially + */ + free_extent_map(em); + em = existing; + err = 0; + + } else if (start >= extent_map_end(existing) || start <= existing->start) { /* * The existing extent map is the one nearest to -- cgit