[PATCH 1/4] btrfs: skip superblocks during discard

[jeffm@suse.com]

From: Jeff Mahoney <jeffm@suse.com>

Btrfs doesn't track superblocks with extent records so there is nothing
persistent on-disk to indicate that those blocks are in use.  We track
the superblocks in memory to ensure they don't get used by removing them
from the free space cache when we load a block group from disk.  Prior
to 47ab2a6c6a (Btrfs: remove empty block groups automatically), that
was fine since the block group would never be reclaimed so the superblock
was always safe.  Once we started removing the empty block groups, we
were protected by the fact that discards weren't being properly issued
for unused space either via FITRIM or -odiscard.  The block groups were
still being released, but the blocks remained on disk.

In order to properly discard unused block groups, we need to filter out
the superblocks from the discard range.  Superblocks are located at fixed
locations on each device, so it makes sense to filter them out in
btrfs_issue_discard, which is used by both -odiscard and FITRIM.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/extent-tree.c | 50 ++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 44 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0ec3acd..75d0226 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1884,10 +1884,47 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static int btrfs_issue_discard(struct block_device *bdev,
-				u64 start, u64 len)
+#define in_range(b, first, len)	((b) >= (first) && (b) < (first) + (len))
+static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
+			       u64 *discarded_bytes)
 {
-	return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0);
+	u64 skipped = 0;
+	u64 bytes_left = len;
+	int ret = 0 , j;
+
+	*discarded_bytes = 0;
+
+	/* Skip any superblocks on this device. */
+	for (j = 0; j < BTRFS_SUPER_MIRROR_MAX; j++) {
+		u64 sb_offset = btrfs_sb_offset(j);
+		u64 size = sb_offset - start;
+
+		if (!in_range(sb_offset, start, bytes_left))
+			continue;
+
+		if (size) {
+			ret = blkdev_issue_discard(bdev, start >> 9, size >> 9,
+						   GFP_NOFS, 0);
+			if (!ret)
+				*discarded_bytes += size;
+			else if (ret != -EOPNOTSUPP)
+				return ret;
+		}
+
+		start = sb_offset + BTRFS_SUPER_INFO_SIZE;
+		if (start > len)
+			start = len;
+		bytes_left = len - start;
+		skipped += BTRFS_SUPER_INFO_SIZE;
+	}
+
+	if (bytes_left) {
+		ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9,
+					   GFP_NOFS, 0);
+		if (!ret)
+			*discarded_bytes += bytes_left;
+	}
+	return ret;
 }
 
 int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
@@ -1906,16 +1943,17 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 		struct btrfs_bio_stripe *stripe = bbio->stripes;
 		int i;
 
-
 		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
+			u64 bytes;
+
 			if (!stripe->dev->can_discard)
 				continue;
 
 			ret = btrfs_issue_discard(stripe->dev->bdev,
 						  stripe->physical,
-						  stripe->length);
+						  stripe->length, &bytes);
 			if (!ret)
-				discarded_bytes += stripe->length;
+				discarded_bytes += bytes;
 			else if (ret != -EOPNOTSUPP)
 				break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
 
-- 
1.8.4.5