[PATCH 3.2 72/94] ocfs2: fstrim: Fix start offset of first cluster group during fstrim

[Ben Hutchings]

3.2.97-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Ashish Samant <ashish.samant@xxxxxxxxxx>

commit 105ddc93f06ebe3e553f58563d11ed63dbcd59f0 upstream.

The first cluster group descriptor is not stored at the start of the
group but at an offset from the start.  We need to take this into
account while doing fstrim on the first cluster group.  Otherwise we
will wrongly start fstrim a few blocks after the desired start block and
the range can cross over into the next cluster group and zero out the
group descriptor there.  This can cause filesytem corruption that cannot
be fixed by fsck.

Link: http://lkml.kernel.org/r/1507835579-7308-1-git-send-email-ashish.samant@xxxxxxxxxx
Signed-off-by: Ashish Samant <ashish.samant@xxxxxxxxxx>
Reviewed-by: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Reviewed-by: Joseph Qi <jiangqi903@xxxxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 fs/ocfs2/alloc.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7188,13 +7188,24 @@ out:
 
 static int ocfs2_trim_extent(struct super_block *sb,
 			     struct ocfs2_group_desc *gd,
-			     u32 start, u32 count)
+			     u64 group, u32 start, u32 count)
 {
 	u64 discard, bcount;
+	struct ocfs2_super *osb = OCFS2_SB(sb);
 
 	bcount = ocfs2_clusters_to_blocks(sb, count);
-	discard = le64_to_cpu(gd->bg_blkno) +
-			ocfs2_clusters_to_blocks(sb, start);
+	discard = ocfs2_clusters_to_blocks(sb, start);
+
+	/*
+	 * For the first cluster group, the gd->bg_blkno is not at the start
+	 * of the group, but at an offset from the start. If we add it while
+	 * calculating discard for first group, we will wrongly start fstrim a
+	 * few blocks after the desried start block and the range can cross
+	 * over into the next cluster group. So, add it only if this is not
+	 * the first cluster group.
+	 */
+	if (group != osb->first_cluster_group_blkno)
+		discard += le64_to_cpu(gd->bg_blkno);
 
 	trace_ocfs2_trim_extent(sb, (unsigned long long)discard, bcount);
 
@@ -7202,7 +7213,7 @@ static int ocfs2_trim_extent(struct supe
 }
 
 static int ocfs2_trim_group(struct super_block *sb,
-			    struct ocfs2_group_desc *gd,
+			    struct ocfs2_group_desc *gd, u64 group,
 			    u32 start, u32 max, u32 minbits)
 {
 	int ret = 0, count = 0, next;
@@ -7221,7 +7232,7 @@ static int ocfs2_trim_group(struct super
 		next = ocfs2_find_next_bit(bitmap, max, start);
 
 		if ((next - start) >= minbits) {
-			ret = ocfs2_trim_extent(sb, gd,
+			ret = ocfs2_trim_extent(sb, gd, group,
 						start, next - start);
 			if (ret < 0) {
 				mlog_errno(ret);
@@ -7323,7 +7334,8 @@ int ocfs2_trim_fs(struct super_block *sb
 		}
 
 		gd = (struct ocfs2_group_desc *)gd_bh->b_data;
-		cnt = ocfs2_trim_group(sb, gd, first_bit, last_bit, minlen);
+		cnt = ocfs2_trim_group(sb, gd, group,
+				       first_bit, last_bit, minlen);
 		brelse(gd_bh);
 		gd_bh = NULL;
 		if (cnt < 0) {