Merge tag 'for-5.17-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Several fixes for defragmentation that got broken in 5.16 after
  refactoring and added subpage support. The observed bugs are excessive
  IO or uninterruptible ioctl.

  All stable material"

* tag 'for-5.17-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: update writeback index when starting defrag
  btrfs: add back missing dirty page rate limiting to defrag
  btrfs: fix deadlock when reserving space during defrag
  btrfs: defrag: properly update range->start for autodefrag
  btrfs: defrag: fix wrong number of defragged sectors
  btrfs: allow defrag to be interruptible
  btrfs: fix too long loop when defragging a 1 byte file

fs/btrfs/ioctl.c

@@ -1213,6 +1213,35 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 		if (em->generation < newer_than)
 			goto next;
 
+		/*
+		 * Our start offset might be in the middle of an existing extent
+		 * map, so take that into account.
+		 */
+		range_len = em->len - (cur - em->start);
+		/*
+		 * If this range of the extent map is already flagged for delalloc,
+		 * skip it, because:
+		 *
+		 * 1) We could deadlock later, when trying to reserve space for
+		 *    delalloc, because in case we can't immediately reserve space
+		 *    the flusher can start delalloc and wait for the respective
+		 *    ordered extents to complete. The deadlock would happen
+		 *    because we do the space reservation while holding the range
+		 *    locked, and starting writeback, or finishing an ordered
+		 *    extent, requires locking the range;
+		 *
+		 * 2) If there's delalloc there, it means there's dirty pages for
+		 *    which writeback has not started yet (we clean the delalloc
+		 *    flag when starting writeback and after creating an ordered
+		 *    extent). If we mark pages in an adjacent range for defrag,
+		 *    then we will have a larger contiguous range for delalloc,
+		 *    very likely resulting in a larger extent after writeback is
+		 *    triggered (except in a case of free space fragmentation).
+		 */
+		if (test_range_bit(&inode->io_tree, cur, cur + range_len - 1,
+				   EXTENT_DELALLOC, 0, NULL))
+			goto next;
+
 		/*
 		 * For do_compress case, we want to compress all valid file
 		 * extents, thus no @extent_thresh or mergeable check.
@@ -1221,7 +1250,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 			goto add;
 
 		/* Skip too large extent */
-		if (em->len >= extent_thresh)
+		if (range_len >= extent_thresh)
 			goto next;
 
 		next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
@@ -1442,9 +1471,11 @@ static int defrag_one_cluster(struct btrfs_inode *inode,
 	list_for_each_entry(entry, &target_list, list) {
 		u32 range_len = entry->len;
 
-		/* Reached the limit */
-		if (max_sectors && max_sectors == *sectors_defragged)
+		/* Reached or beyond the limit */
+		if (max_sectors && *sectors_defragged >= max_sectors) {
+			ret = 1;
 			break;
+		}
 
 		if (max_sectors)
 			range_len = min_t(u32, range_len,
@@ -1465,7 +1496,8 @@ static int defrag_one_cluster(struct btrfs_inode *inode,
 				       extent_thresh, newer_than, do_compress);
 		if (ret < 0)
 			break;
-		*sectors_defragged += range_len;
+		*sectors_defragged += range_len >>
+				      inode->root->fs_info->sectorsize_bits;
 	}
 out:
 	list_for_each_entry_safe(entry, tmp, &target_list, list) {
@@ -1484,6 +1516,12 @@ static int defrag_one_cluster(struct btrfs_inode *inode,
  * @newer_than:	   minimum transid to defrag
  * @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode
  *		   will be defragged.
+ *
+ * Return <0 for error.
+ * Return >=0 for the number of sectors defragged, and range->start will be updated
+ * to indicate the file offset where next defrag should be started at.
+ * (Mostly for autodefrag, which sets @max_to_defrag thus we may exit early without
+ *  defragging all the range).
  */
 int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 		      struct btrfs_ioctl_defrag_range_args *range,
@@ -1499,6 +1537,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 	int compress_type = BTRFS_COMPRESS_ZLIB;
 	int ret = 0;
 	u32 extent_thresh = range->extent_thresh;
+	pgoff_t start_index;
 
 	if (isize == 0)
 		return 0;
@@ -1518,12 +1557,16 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 
 	if (range->start + range->len > range->start) {
 		/* Got a specific range */
-		last_byte = min(isize, range->start + range->len) - 1;
+		last_byte = min(isize, range->start + range->len);
 	} else {
 		/* Defrag until file end */
-		last_byte = isize - 1;
+		last_byte = isize;
 	}
 
+	/* Align the range */
+	cur = round_down(range->start, fs_info->sectorsize);
+	last_byte = round_up(last_byte, fs_info->sectorsize) - 1;
+
 	/*
 	 * If we were not given a ra, allocate a readahead context. As
 	 * readahead is just an optimization, defrag will work without it so
@@ -1536,16 +1579,26 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 			file_ra_state_init(ra, inode->i_mapping);
 	}
 
-	/* Align the range */
-	cur = round_down(range->start, fs_info->sectorsize);
-	last_byte = round_up(last_byte, fs_info->sectorsize) - 1;
+	/*
+	 * Make writeback start from the beginning of the range, so that the
+	 * defrag range can be written sequentially.
+	 */
+	start_index = cur >> PAGE_SHIFT;
+	if (start_index < inode->i_mapping->writeback_index)
+		inode->i_mapping->writeback_index = start_index;
 
 	while (cur < last_byte) {
+		const unsigned long prev_sectors_defragged = sectors_defragged;
 		u64 cluster_end;
 
 		/* The cluster size 256K should always be page aligned */
 		BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE));
 
+		if (btrfs_defrag_cancelled(fs_info)) {
+			ret = -EAGAIN;
+			break;
+		}
+
 		/* We want the cluster end at page boundary when possible */
 		cluster_end = (((cur >> PAGE_SHIFT) +
 			       (SZ_256K >> PAGE_SHIFT)) << PAGE_SHIFT) - 1;
@@ -1567,14 +1620,27 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 				cluster_end + 1 - cur, extent_thresh,
 				newer_than, do_compress,
 				&sectors_defragged, max_to_defrag);
+
+		if (sectors_defragged > prev_sectors_defragged)
+			balance_dirty_pages_ratelimited(inode->i_mapping);
+
 		btrfs_inode_unlock(inode, 0);
 		if (ret < 0)
 			break;
 		cur = cluster_end + 1;
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
 	}
 
 	if (ra_allocated)
 		kfree(ra);
+	/*
+	 * Update range.start for autodefrag, this will indicate where to start
+	 * in next run.
+	 */
+	range->start = cur;
 	if (sectors_defragged) {
 		/*
 		 * We have defragged some sectors, for compression case they