Merge tag 'for-5.19-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - zoned relocation fixes:
      - fix critical section end for extent writeback, this could lead
        to out of order write
      - prevent writing to previous data relocation block group if space
        gets low

 - reflink fixes:
      - fix race between reflinking and ordered extent completion
      - proper error handling when block reserve migration fails
      - add missing inode iversion/mtime/ctime updates on each iteration
        when replacing extents

 - fix deadlock when running fsync/fiemap/commit at the same time

 - fix false-positive KCSAN report regarding pid tracking for read locks
   and data race

 - minor documentation update and link to new site

* tag 'for-5.19-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  Documentation: update btrfs list of features and link to readthedocs.io
  btrfs: fix deadlock with fsync+fiemap+transaction commit
  btrfs: don't set lock_owner when locking extent buffer for reading
  btrfs: zoned: fix critical section of relocation inode writeback
  btrfs: zoned: prevent allocation from previous data relocation BG
  btrfs: do not BUG_ON() on failure to migrate space when replacing extents
  btrfs: add missing inode updates on each iteration when replacing extents
  btrfs: fix race between reflinking and ordered extent completion

Author: torvalds

Documentation/filesystems/btrfs.rst

@@ -19,13 +19,23 @@ The main Btrfs features include:
     * Subvolumes (separate internal filesystem roots)
     * Object level mirroring and striping
     * Checksums on data and metadata (multiple algorithms available)
-    * Compression
+    * Compression (multiple algorithms available)
+    * Reflink, deduplication
+    * Scrub (on-line checksum verification)
+    * Hierarchical quota groups (subvolume and snapshot support)
     * Integrated multiple device support, with several raid algorithms
     * Offline filesystem check
-    * Efficient incremental backup and FS mirroring
+    * Efficient incremental backup and FS mirroring (send/receive)
+    * Trim/discard
     * Online filesystem defragmentation
+    * Swapfile support
+    * Zoned mode
+    * Read/write metadata verification
+    * Online resize (shrink, grow)
 
-For more information please refer to the wiki
+For more information please refer to the documentation site or wiki
+
+  https://btrfs.readthedocs.io
 
   https://btrfs.wiki.kernel.org
 

fs/btrfs/block-group.h

@@ -104,6 +104,7 @@ struct btrfs_block_group {
 	unsigned int relocating_repair:1;
 	unsigned int chunk_item_inserted:1;
 	unsigned int zone_is_active:1;
+	unsigned int zoned_data_reloc_ongoing:1;
 
 	int disk_cache_state;
 

fs/btrfs/ctree.h

@@ -1330,6 +1330,8 @@ struct btrfs_replace_extent_info {
 	 * existing extent into a file range.
 	 */
 	bool is_new_extent;
+	/* Indicate if we should update the inode's mtime and ctime. */
+	bool update_times;
 	/* Meaningful only if is_new_extent is true. */
 	int qgroup_reserved;
 	/*

fs/btrfs/extent-tree.c

@@ -3832,7 +3832,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 	       block_group->start == fs_info->data_reloc_bg ||
 	       fs_info->data_reloc_bg == 0);
 
-	if (block_group->ro) {
+	if (block_group->ro || block_group->zoned_data_reloc_ongoing) {
 		ret = 1;
 		goto out;
 	}
@@ -3894,8 +3894,24 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 out:
 	if (ret && ffe_ctl->for_treelog)
 		fs_info->treelog_bg = 0;
-	if (ret && ffe_ctl->for_data_reloc)
+	if (ret && ffe_ctl->for_data_reloc &&
+	    fs_info->data_reloc_bg == block_group->start) {
+		/*
+		 * Do not allow further allocations from this block group.
+		 * Compared to increasing the ->ro, setting the
+		 * ->zoned_data_reloc_ongoing flag still allows nocow
+		 *  writers to come in. See btrfs_inc_nocow_writers().
+		 *
+		 * We need to disable an allocation to avoid an allocation of
+		 * regular (non-relocation data) extent. With mix of relocation
+		 * extents and regular extents, we can dispatch WRITE commands
+		 * (for relocation extents) and ZONE APPEND commands (for
+		 * regular extents) at the same time to the same zone, which
+		 * easily break the write pointer.
+		 */
+		block_group->zoned_data_reloc_ongoing = 1;
 		fs_info->data_reloc_bg = 0;
+	}
 	spin_unlock(&fs_info->relocation_bg_lock);
 	spin_unlock(&fs_info->treelog_bg_lock);
 	spin_unlock(&block_group->lock);

fs/btrfs/extent_io.c

@@ -5241,13 +5241,14 @@ int extent_writepages(struct address_space *mapping,
 	 */
 	btrfs_zoned_data_reloc_lock(BTRFS_I(inode));
 	ret = extent_write_cache_pages(mapping, wbc, &epd);
-	btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
 	ASSERT(ret <= 0);
 	if (ret < 0) {
+		btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
 		end_write_bio(&epd, ret);
 		return ret;
 	}
 	flush_write_bio(&epd);
+	btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
 	return ret;
 }
 

fs/btrfs/file.c

@@ -2323,25 +2323,62 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
 
-	if (ret != BTRFS_NO_LOG_SYNC) {
+	if (ret == BTRFS_NO_LOG_SYNC) {
+		ret = btrfs_end_transaction(trans);
+		goto out;
+	}
+
+	/* We successfully logged the inode, attempt to sync the log. */
+	if (!ret) {
+		ret = btrfs_sync_log(trans, root, &ctx);
 		if (!ret) {
-			ret = btrfs_sync_log(trans, root, &ctx);
-			if (!ret) {
-				ret = btrfs_end_transaction(trans);
-				goto out;
-			}
-		}
-		if (!full_sync) {
-			ret = btrfs_wait_ordered_range(inode, start, len);
-			if (ret) {
-				btrfs_end_transaction(trans);
-				goto out;
-			}
+			ret = btrfs_end_transaction(trans);
+			goto out;
 		}
-		ret = btrfs_commit_transaction(trans);
-	} else {
+	}
+
+	/*
+	 * At this point we need to commit the transaction because we had
+	 * btrfs_need_log_full_commit() or some other error.
+	 *
+	 * If we didn't do a full sync we have to stop the trans handle, wait on
+	 * the ordered extents, start it again and commit the transaction.  If
+	 * we attempt to wait on the ordered extents here we could deadlock with
+	 * something like fallocate() that is holding the extent lock trying to
+	 * start a transaction while some other thread is trying to commit the
+	 * transaction while we (fsync) are currently holding the transaction
+	 * open.
+	 */
+	if (!full_sync) {
 		ret = btrfs_end_transaction(trans);
+		if (ret)
+			goto out;
+		ret = btrfs_wait_ordered_range(inode, start, len);
+		if (ret)
+			goto out;
+
+		/*
+		 * This is safe to use here because we're only interested in
+		 * making sure the transaction that had the ordered extents is
+		 * committed.  We aren't waiting on anything past this point,
+		 * we're purely getting the transaction and committing it.
+		 */
+		trans = btrfs_attach_transaction_barrier(root);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+
+			/*
+			 * We committed the transaction and there's no currently
+			 * running transaction, this means everything we care
+			 * about made it to disk and we are done.
+			 */
+			if (ret == -ENOENT)
+				ret = 0;
+			goto out;
+		}
 	}
+
+	ret = btrfs_commit_transaction(trans);
 out:
 	ASSERT(list_empty(&ctx.list));
 	err = file_check_and_advance_wb_err(file);
@@ -2719,7 +2756,8 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 
 	ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv,
 				      min_size, false);
-	BUG_ON(ret);
+	if (WARN_ON(ret))
+		goto out_trans;
 	trans->block_rsv = rsv;
 
 	cur_offset = start;
@@ -2803,6 +2841,25 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 			extent_info->file_offset += replace_len;
 		}
 
+		/*
+		 * We are releasing our handle on the transaction, balance the
+		 * dirty pages of the btree inode and flush delayed items, and
+		 * then get a new transaction handle, which may now point to a
+		 * new transaction in case someone else may have committed the
+		 * transaction we used to replace/drop file extent items. So
+		 * bump the inode's iversion and update mtime and ctime except
+		 * if we are called from a dedupe context. This is because a
+		 * power failure/crash may happen after the transaction is
+		 * committed and before we finish replacing/dropping all the
+		 * file extent items we need.
+		 */
+		inode_inc_iversion(&inode->vfs_inode);
+
+		if (!extent_info || extent_info->update_times) {
+			inode->vfs_inode.i_mtime = current_time(&inode->vfs_inode);
+			inode->vfs_inode.i_ctime = inode->vfs_inode.i_mtime;
+		}
+
 		ret = btrfs_update_inode(trans, root, inode);
 		if (ret)
 			break;
@@ -2819,7 +2876,8 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 
 		ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
 					      rsv, min_size, false);
-		BUG_ON(ret);	/* shouldn't happen */
+		if (WARN_ON(ret))
+			break;
 		trans->block_rsv = rsv;
 
 		cur_offset = drop_args.drop_end;

fs/btrfs/inode.c

@@ -3195,6 +3195,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
 						logical_len);
+		btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr,
+						  ordered_extent->disk_num_bytes);
 	} else {
 		BUG_ON(root == fs_info->tree_root);
 		ret = insert_ordered_extent_file_extent(trans, ordered_extent);
@@ -9897,6 +9899,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	extent_info.file_offset = file_offset;
 	extent_info.extent_buf = (char *)&stack_fi;
 	extent_info.is_new_extent = true;
+	extent_info.update_times = true;
 	extent_info.qgroup_reserved = qgroup_released;
 	extent_info.insertions = 0;
 

fs/btrfs/locking.c

@@ -45,7 +45,6 @@ void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting ne
 		start_ns = ktime_get_ns();
 
 	down_read_nested(&eb->lock, nest);
-	eb->lock_owner = current->pid;
 	trace_btrfs_tree_read_lock(eb, start_ns);
 }
 
@@ -62,7 +61,6 @@ void btrfs_tree_read_lock(struct extent_buffer *eb)
 int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 {
 	if (down_read_trylock(&eb->lock)) {
-		eb->lock_owner = current->pid;
 		trace_btrfs_try_tree_read_lock(eb);
 		return 1;
 	}
@@ -90,7 +88,6 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
 	trace_btrfs_tree_read_unlock(eb);
-	eb->lock_owner = 0;
 	up_read(&eb->lock);
 }
 

fs/btrfs/reflink.c

@@ -344,6 +344,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	int ret;
 	const u64 len = olen_aligned;
 	u64 last_dest_end = destoff;
+	u64 prev_extent_end = off;
 
 	ret = -ENOMEM;
 	buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
@@ -363,7 +364,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	key.offset = off;
 
 	while (1) {
-		u64 next_key_min_offset = key.offset + 1;
 		struct btrfs_file_extent_item *extent;
 		u64 extent_gen;
 		int type;
@@ -431,14 +431,21 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		 * The first search might have left us at an extent item that
 		 * ends before our target range's start, can happen if we have
 		 * holes and NO_HOLES feature enabled.
+		 *
+		 * Subsequent searches may leave us on a file range we have
+		 * processed before - this happens due to a race with ordered
+		 * extent completion for a file range that is outside our source
+		 * range, but that range was part of a file extent item that
+		 * also covered a leading part of our source range.
 		 */
-		if (key.offset + datal <= off) {
+		if (key.offset + datal <= prev_extent_end) {
 			path->slots[0]++;
 			goto process_slot;
 		} else if (key.offset >= off + len) {
 			break;
 		}
-		next_key_min_offset = key.offset + datal;
+
+		prev_extent_end = key.offset + datal;
 		size = btrfs_item_size(leaf, slot);
 		read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot),
 				   size);
@@ -489,6 +496,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 			clone_info.file_offset = new_key.offset;
 			clone_info.extent_buf = buf;
 			clone_info.is_new_extent = false;
+			clone_info.update_times = !no_time_update;
 			ret = btrfs_replace_file_extents(BTRFS_I(inode), path,
 					drop_start, new_key.offset + datal - 1,
 					&clone_info, &trans);
@@ -550,7 +558,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 			break;
 
 		btrfs_release_path(path);
-		key.offset = next_key_min_offset;
+		key.offset = prev_extent_end;
 
 		if (fatal_signal_pending(current)) {
 			ret = -EINTR;

fs/btrfs/zoned.c

@@ -2139,3 +2139,30 @@ bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info)
 	factor = div64_u64(used * 100, total);
 	return factor >= fs_info->bg_reclaim_threshold;
 }
+
+void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
+				       u64 length)
+{
+	struct btrfs_block_group *block_group;
+
+	if (!btrfs_is_zoned(fs_info))
+		return;
+
+	block_group = btrfs_lookup_block_group(fs_info, logical);
+	/* It should be called on a previous data relocation block group. */
+	ASSERT(block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA));
+
+	spin_lock(&block_group->lock);
+	if (!block_group->zoned_data_reloc_ongoing)
+		goto out;
+
+	/* All relocation extents are written. */
+	if (block_group->start + block_group->alloc_offset == logical + length) {
+		/* Now, release this block group for further allocations. */
+		block_group->zoned_data_reloc_ongoing = 0;
+	}
+
+out:
+	spin_unlock(&block_group->lock);
+	btrfs_put_block_group(block_group);
+}