1 files changed, 191 insertions, 142 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1ab5b0c1b9b7..f84e3f9fad84 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1249,7 +1249,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	free_extent_map(em);
 
 	ordered = btrfs_alloc_ordered_extent(inode, start, &file_extent,
-					     1 << BTRFS_ORDERED_COMPRESSED);
+					     1U << BTRFS_ORDERED_COMPRESSED);
 	if (IS_ERR(ordered)) {
 		btrfs_drop_extent_map_range(inode, start, end, false);
 		ret = PTR_ERR(ordered);
@@ -1409,6 +1409,17 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 	alloc_hint = btrfs_get_extent_allocation_hint(inode, start, num_bytes);
 
 	/*
+	 * We're not doing compressed IO, don't unlock the first page (which
+	 * the caller expects to stay locked), don't clear any dirty bits and
+	 * don't set any writeback bits.
+	 *
+	 * Do set the Ordered (Private2) bit so we know this page was properly
+	 * setup for writepage.
+	 */
+	page_ops = (keep_locked ? 0 : PAGE_UNLOCK);
+	page_ops |= PAGE_SET_ORDERED;
+
+	/*
 	 * Relocation relies on the relocated extents to have exactly the same
 	 * size as the original extents. Normally writeback for relocation data
 	 * extents follows a NOCOW path because relocation preallocates the
@@ -1452,8 +1463,13 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 				continue;
 			}
 			if (done_offset) {
-				*done_offset = start - 1;
-				return 0;
+				/*
+				 * Move @end to the end of the processed range,
+				 * and exit the loop to unlock the processed extents.
+				 */
+				end = start - 1;
+				ret = 0;
+				break;
 			}
 			ret = -ENOSPC;
 		}
@@ -1470,6 +1486,10 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		file_extent.offset = 0;
 		file_extent.compression = BTRFS_COMPRESS_NONE;
 
+		/*
+		 * Locked range will be released either during error clean up or
+		 * after the whole range is finished.
+		 */
 		lock_extent(&inode->io_tree, start, start + ram_size - 1,
 			    &cached);
 
@@ -1484,7 +1504,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		free_extent_map(em);
 
 		ordered = btrfs_alloc_ordered_extent(inode, start, &file_extent,
-						     1 << BTRFS_ORDERED_REGULAR);
+						     1U << BTRFS_ORDERED_REGULAR);
 		if (IS_ERR(ordered)) {
 			unlock_extent(&inode->io_tree, start,
 				      start + ram_size - 1, &cached);
@@ -1515,27 +1535,12 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 
 		btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 
-		/*
-		 * We're not doing compressed IO, don't unlock the first page
-		 * (which the caller expects to stay locked), don't clear any
-		 * dirty bits and don't set any writeback bits
-		 *
-		 * Do set the Ordered (Private2) bit so we know this page was
-		 * properly setup for writepage.
-		 */
-		page_ops = (keep_locked ? 0 : PAGE_UNLOCK);
-		page_ops |= PAGE_SET_ORDERED;
-
-		extent_clear_unlock_delalloc(inode, start, start + ram_size - 1,
-					     locked_folio, &cached,
-					     EXTENT_LOCKED | EXTENT_DELALLOC,
-					     page_ops);
-		if (num_bytes < cur_alloc_size)
+		if (num_bytes < ram_size)
 			num_bytes = 0;
 		else
-			num_bytes -= cur_alloc_size;
+			num_bytes -= ram_size;
 		alloc_hint = ins.objectid + ins.offset;
-		start += cur_alloc_size;
+		start += ram_size;
 		extent_reserved = false;
 
 		/*
@@ -1546,6 +1551,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		if (ret)
 			goto out_unlock;
 	}
+	extent_clear_unlock_delalloc(inode, orig_start, end, locked_folio, &cached,
+				     EXTENT_LOCKED | EXTENT_DELALLOC, page_ops);
 done:
 	if (done_offset)
 		*done_offset = end;
@@ -1561,40 +1568,35 @@ out_unlock:
 	 * Now, we have three regions to clean up:
 	 *
 	 * |-------(1)----|---(2)---|-------------(3)----------|
-	 * `- orig_start  `- start  `- start + cur_alloc_size  `- end
+	 * `- orig_start  `- start  `- start + ram_size  `- end
 	 *
 	 * We process each region below.
 	 */
 
-	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
-		EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
-	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
-
 	/*
 	 * For the range (1). We have already instantiated the ordered extents
 	 * for this region. They are cleaned up by
 	 * btrfs_cleanup_ordered_extents() in e.g,
-	 * btrfs_run_delalloc_range(). EXTENT_LOCKED | EXTENT_DELALLOC are
-	 * already cleared in the above loop. And, EXTENT_DELALLOC_NEW |
-	 * EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV are handled by the cleanup
-	 * function.
+	 * btrfs_run_delalloc_range().
+	 * EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV
+	 * are also handled by the cleanup function.
 	 *
-	 * However, in case of @keep_locked, we still need to unlock the pages
-	 * (except @locked_folio) to ensure all the pages are unlocked.
+	 * So here we only clear EXTENT_LOCKED and EXTENT_DELALLOC flag, and
+	 * finish the writeback of the involved folios, which will be never submitted.
 	 */
-	if (keep_locked && orig_start < start) {
+	if (orig_start < start) {
+		clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC;
+		page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
+
 		if (!locked_folio)
 			mapping_set_error(inode->vfs_inode.i_mapping, ret);
 		extent_clear_unlock_delalloc(inode, orig_start, start - 1,
-					     locked_folio, NULL, 0, page_ops);
+					     locked_folio, NULL, clear_bits, page_ops);
 	}
 
-	/*
-	 * At this point we're unlocked, we want to make sure we're only
-	 * clearing these flags under the extent lock, so lock the rest of the
-	 * range and clear everything up.
-	 */
-	lock_extent(&inode->io_tree, start, end, NULL);
+	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+		     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
+	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
 
 	/*
 	 * For the range (2). If we reserved an extent for our delalloc range
@@ -1608,11 +1610,11 @@ out_unlock:
 	 */
 	if (extent_reserved) {
 		extent_clear_unlock_delalloc(inode, start,
-					     start + cur_alloc_size - 1,
+					     start + ram_size - 1,
 					     locked_folio, &cached, clear_bits,
 					     page_ops);
-		btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
-		start += cur_alloc_size;
+		btrfs_qgroup_free_data(inode, NULL, start, ram_size, NULL);
+		start += ram_size;
 	}
 
 	/*
@@ -2055,6 +2057,63 @@ static void cleanup_dirty_folios(struct btrfs_inode *inode,
 	mapping_set_error(mapping, error);
 }
 
+static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio,
+			   struct extent_state **cached,
+			   struct can_nocow_file_extent_args *nocow_args,
+			   u64 file_pos, bool is_prealloc)
+{
+	struct btrfs_ordered_extent *ordered;
+	u64 len = nocow_args->file_extent.num_bytes;
+	u64 end = file_pos + len - 1;
+	int ret = 0;
+
+	lock_extent(&inode->io_tree, file_pos, end, cached);
+
+	if (is_prealloc) {
+		struct extent_map *em;
+
+		em = btrfs_create_io_em(inode, file_pos, &nocow_args->file_extent,
+					BTRFS_ORDERED_PREALLOC);
+		if (IS_ERR(em)) {
+			unlock_extent(&inode->io_tree, file_pos, end, cached);
+			return PTR_ERR(em);
+		}
+		free_extent_map(em);
+	}
+
+	ordered = btrfs_alloc_ordered_extent(inode, file_pos, &nocow_args->file_extent,
+					     is_prealloc
+					     ? (1U << BTRFS_ORDERED_PREALLOC)
+					     : (1U << BTRFS_ORDERED_NOCOW));
+	if (IS_ERR(ordered)) {
+		if (is_prealloc)
+			btrfs_drop_extent_map_range(inode, file_pos, end, false);
+		unlock_extent(&inode->io_tree, file_pos, end, cached);
+		return PTR_ERR(ordered);
+	}
+
+	if (btrfs_is_data_reloc_root(inode->root))
+		/*
+		 * Errors are handled later, as we must prevent
+		 * extent_clear_unlock_delalloc() in error handler from freeing
+		 * metadata of the created ordered extent.
+		 */
+		ret = btrfs_reloc_clone_csums(ordered);
+	btrfs_put_ordered_extent(ordered);
+
+	extent_clear_unlock_delalloc(inode, file_pos, end, locked_folio, cached,
+				     EXTENT_LOCKED | EXTENT_DELALLOC |
+				     EXTENT_CLEAR_DATA_RESV,
+				     PAGE_UNLOCK | PAGE_SET_ORDERED);
+
+	/*
+	 * btrfs_reloc_clone_csums() error, now we're OK to call error handler,
+	 * as metadata for created ordered extent will only be freed by
+	 * btrfs_finish_ordered_io().
+	 */
+	return ret;
+}
+
 /*
  * when nowcow writeback call back.  This checks for snapshots or COW copies
  * of the extents that exist in the file, and COWs the file as required.
@@ -2099,15 +2158,12 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 
 	while (cur_offset <= end) {
 		struct btrfs_block_group *nocow_bg = NULL;
-		struct btrfs_ordered_extent *ordered;
 		struct btrfs_key found_key;
 		struct btrfs_file_extent_item *fi;
 		struct extent_buffer *leaf;
 		struct extent_state *cached_state = NULL;
 		u64 extent_end;
-		u64 nocow_end;
 		int extent_type;
-		bool is_prealloc;
 
 		ret = btrfs_lookup_file_extent(NULL, root, path, ino,
 					       cur_offset, 0);
@@ -2242,67 +2298,13 @@ must_cow:
 			}
 		}
 
-		nocow_end = cur_offset + nocow_args.file_extent.num_bytes - 1;
-		lock_extent(&inode->io_tree, cur_offset, nocow_end, &cached_state);
-
-		is_prealloc = extent_type == BTRFS_FILE_EXTENT_PREALLOC;
-		if (is_prealloc) {
-			struct extent_map *em;
-
-			em = btrfs_create_io_em(inode, cur_offset,
-						&nocow_args.file_extent,
-						BTRFS_ORDERED_PREALLOC);
-			if (IS_ERR(em)) {
-				unlock_extent(&inode->io_tree, cur_offset,
-					      nocow_end, &cached_state);
-				btrfs_dec_nocow_writers(nocow_bg);
-				ret = PTR_ERR(em);
-				goto error;
-			}
-			free_extent_map(em);
-		}
-
-		ordered = btrfs_alloc_ordered_extent(inode, cur_offset,
-				&nocow_args.file_extent,
-				is_prealloc
-				? (1 << BTRFS_ORDERED_PREALLOC)
-				: (1 << BTRFS_ORDERED_NOCOW));
+		ret = nocow_one_range(inode, locked_folio, &cached_state,
+				      &nocow_args, cur_offset,
+				      extent_type == BTRFS_FILE_EXTENT_PREALLOC);
 		btrfs_dec_nocow_writers(nocow_bg);
-		if (IS_ERR(ordered)) {
-			if (is_prealloc) {
-				btrfs_drop_extent_map_range(inode, cur_offset,
-							    nocow_end, false);
-			}
-			unlock_extent(&inode->io_tree, cur_offset,
-				      nocow_end, &cached_state);
-			ret = PTR_ERR(ordered);
+		if (ret < 0)
 			goto error;
-		}
-
-		if (btrfs_is_data_reloc_root(root))
-			/*
-			 * Error handled later, as we must prevent
-			 * extent_clear_unlock_delalloc() in error handler
-			 * from freeing metadata of created ordered extent.
-			 */
-			ret = btrfs_reloc_clone_csums(ordered);
-		btrfs_put_ordered_extent(ordered);
-
-		extent_clear_unlock_delalloc(inode, cur_offset, nocow_end,
-					     locked_folio, &cached_state,
-					     EXTENT_LOCKED | EXTENT_DELALLOC |
-					     EXTENT_CLEAR_DATA_RESV,
-					     PAGE_UNLOCK | PAGE_SET_ORDERED);
-
 		cur_offset = extent_end;
-
-		/*
-		 * btrfs_reloc_clone_csums() error, now we're OK to call error
-		 * handler, as metadata for created ordered extent will only
-		 * be freed by btrfs_finish_ordered_io().
-		 */
-		if (ret)
-			goto error;
 	}
 	btrfs_release_path(path);
 
@@ -4732,7 +4734,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	int ret = 0;
 	struct btrfs_trans_handle *trans;
-	u64 last_unlink_trans;
 	struct fscrypt_name fname;
 
 	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
@@ -4758,6 +4759,23 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		goto out_notrans;
 	}
 
+	/*
+	 * Propagate the last_unlink_trans value of the deleted dir to its
+	 * parent directory. This is to prevent an unrecoverable log tree in the
+	 * case we do something like this:
+	 * 1) create dir foo
+	 * 2) create snapshot under dir foo
+	 * 3) delete the snapshot
+	 * 4) rmdir foo
+	 * 5) mkdir foo
+	 * 6) fsync foo or some file inside foo
+	 *
+	 * This is because we can't unlink other roots when replaying the dir
+	 * deletes for directory foo.
+	 */
+	if (BTRFS_I(inode)->last_unlink_trans >= trans->transid)
+		btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
+
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 		ret = btrfs_unlink_subvol(trans, BTRFS_I(dir), dentry);
 		goto out;
@@ -4767,27 +4785,11 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (ret)
 		goto out;
 
-	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
-
 	/* now the directory is empty */
 	ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
 				 &fname.disk_name);
-	if (!ret) {
+	if (!ret)
 		btrfs_i_size_write(BTRFS_I(inode), 0);
-		/*
-		 * Propagate the last_unlink_trans value of the deleted dir to
-		 * its parent directory. This is to prevent an unrecoverable
-		 * log tree in the case we do something like this:
-		 * 1) create dir foo
-		 * 2) create snapshot under dir foo
-		 * 3) delete the snapshot
-		 * 4) rmdir foo
-		 * 5) mkdir foo
-		 * 6) fsync foo or some file inside foo
-		 */
-		if (last_unlink_trans >= trans->transid)
-			BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
-	}
 out:
 	btrfs_end_transaction(trans);
 out_notrans:
@@ -7997,6 +7999,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	int ret;
 	int ret2;
 	bool need_abort = false;
+	bool logs_pinned = false;
 	struct fscrypt_name old_fname, new_fname;
 	struct fscrypt_str *old_name, *new_name;
 
@@ -8120,6 +8123,31 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	inode_inc_iversion(new_inode);
 	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
 
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID &&
+	    new_ino != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * If we are renaming in the same directory (and it's not for
+		 * root entries) pin the log early to prevent any concurrent
+		 * task from logging the directory after we removed the old
+		 * entries and before we add the new entries, otherwise that
+		 * task can sync a log without any entry for the inodes we are
+		 * renaming and therefore replaying that log, if a power failure
+		 * happens after syncing the log, would result in deleting the
+		 * inodes.
+		 *
+		 * If the rename affects two different directories, we want to
+		 * make sure the that there's no log commit that contains
+		 * updates for only one of the directories but not for the
+		 * other.
+		 *
+		 * If we are renaming an entry for a root, we don't care about
+		 * log updates since we called btrfs_set_log_full_commit().
+		 */
+		btrfs_pin_log_trans(root);
+		btrfs_pin_log_trans(dest);
+		logs_pinned = true;
+	}
+
 	if (old_dentry->d_parent != new_dentry->d_parent) {
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
 					BTRFS_I(old_inode), true);
@@ -8177,30 +8205,23 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		BTRFS_I(new_inode)->dir_index = new_idx;
 
 	/*
-	 * Now pin the logs of the roots. We do it to ensure that no other task
-	 * can sync the logs while we are in progress with the rename, because
-	 * that could result in an inconsistency in case any of the inodes that
-	 * are part of this rename operation were logged before.
+	 * Do the log updates for all inodes.
+	 *
+	 * If either entry is for a root we don't need to update the logs since
+	 * we've called btrfs_set_log_full_commit() before.
 	 */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_pin_log_trans(root);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_pin_log_trans(dest);
-
-	/* Do the log updates for all inodes. */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (logs_pinned) {
 		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   old_rename_ctx.index, new_dentry->d_parent);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
 		btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
 				   new_rename_ctx.index, old_dentry->d_parent);
+	}
 
-	/* Now unpin the logs. */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+out_fail:
+	if (logs_pinned) {
 		btrfs_end_log_trans(root);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
 		btrfs_end_log_trans(dest);
-out_fail:
+	}
 	ret2 = btrfs_end_transaction(trans);
 	ret = ret ? ret : ret2;
 out_notrans:
@@ -8250,6 +8271,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	int ret2;
 	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
 	struct fscrypt_name old_fname, new_fname;
+	bool logs_pinned = false;
 
 	if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return -EPERM;
@@ -8384,6 +8406,29 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	inode_inc_iversion(old_inode);
 	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
 
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * If we are renaming in the same directory (and it's not a
+		 * root entry) pin the log to prevent any concurrent task from
+		 * logging the directory after we removed the old entry and
+		 * before we add the new entry, otherwise that task can sync
+		 * a log without any entry for the inode we are renaming and
+		 * therefore replaying that log, if a power failure happens
+		 * after syncing the log, would result in deleting the inode.
+		 *
+		 * If the rename affects two different directories, we want to
+		 * make sure the that there's no log commit that contains
+		 * updates for only one of the directories but not for the
+		 * other.
+		 *
+		 * If we are renaming an entry for a root, we don't care about
+		 * log updates since we called btrfs_set_log_full_commit().
+		 */
+		btrfs_pin_log_trans(root);
+		btrfs_pin_log_trans(dest);
+		logs_pinned = true;
+	}
+
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
 					BTRFS_I(old_inode), true);
@@ -8432,7 +8477,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	if (old_inode->i_nlink == 1)
 		BTRFS_I(old_inode)->dir_index = index;
 
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (logs_pinned)
 		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   rename_ctx.index, new_dentry->d_parent);
 
@@ -8448,6 +8493,10 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 		}
 	}
 out_fail:
+	if (logs_pinned) {
+		btrfs_end_log_trans(root);
+		btrfs_end_log_trans(dest);
+	}
 	ret2 = btrfs_end_transaction(trans);
 	ret = ret ? ret : ret2;
 out_notrans:
@@ -9683,8 +9732,8 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	free_extent_map(em);
 
 	ordered = btrfs_alloc_ordered_extent(inode, start, &file_extent,
-				       (1 << BTRFS_ORDERED_ENCODED) |
-				       (1 << BTRFS_ORDERED_COMPRESSED));
+				       (1U << BTRFS_ORDERED_ENCODED) |
+				       (1U << BTRFS_ORDERED_COMPRESSED));
 	if (IS_ERR(ordered)) {
 		btrfs_drop_extent_map_range(inode, start, end, false);
 		ret = PTR_ERR(ordered);