ext4: mark group as trimmed only if it was fully scanned

Otherwise nonaligned fstrim calls will works inconveniently for iterative
scanners, for example:

// trim [0,16MB] for group-1, but mark full group as trimmed
fstrim  -o $((1024*1024*128)) -l $((1024*1024*16)) ./m
// handle [16MB,16MB] for group-1, do nothing because group already has the flag.
fstrim  -o $((1024*1024*144)) -l $((1024*1024*16)) ./m

[ Update function documentation for ext4_trim_all_free -- TYT ]

Signed-off-by: Dmitry Monakhov <dmtrmonakhov@yandex-team.ru>
Link: https://lore.kernel.org/r/1650214995-860245-1-git-send-email-dmtrmonakhov@yandex-team.ru
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org

1 files changed, 12 insertions, 6 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 3e715b837e70..bc90635b757c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -6395,6 +6395,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
  * @start:		first group block to examine
  * @max:		last group block to examine
  * @minblocks:		minimum extent block count
+ * @set_trimmed:	set the trimmed flag if at least one block is trimmed
  *
  * ext4_trim_all_free walks through group's block bitmap searching for free
  * extents. When the free extent is found, mark it as used in group buddy
@@ -6404,7 +6405,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 static ext4_grpblk_t
 ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 		   ext4_grpblk_t start, ext4_grpblk_t max,
-		   ext4_grpblk_t minblocks)
+		   ext4_grpblk_t minblocks, bool set_trimmed)
 {
 	struct ext4_buddy e4b;
 	int ret;
@@ -6423,7 +6424,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 	if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
 	    minblocks < EXT4_SB(sb)->s_last_trim_minblks) {
 		ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
-		if (ret >= 0)
+		if (ret >= 0 && set_trimmed)
 			EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
 	} else {
 		ret = 0;
@@ -6460,6 +6461,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
 	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
+	bool whole_group, eof = false;
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
@@ -6478,8 +6480,10 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		if (minlen > EXT4_CLUSTERS_PER_GROUP(sb))
 			goto out;
 	}
-	if (end >= max_blks)
+	if (end >= max_blks - 1) {
 		end = max_blks - 1;
+		eof = true;
+	}
 	if (end <= first_data_blk)
 		goto out;
 	if (start < first_data_blk)
@@ -6493,6 +6497,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 
 	/* end now represents the last cluster to discard in this group */
 	end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+	whole_group = true;
 
 	for (group = first_group; group <= last_group; group++) {
 		grp = ext4_get_group_info(sb, group);
@@ -6509,12 +6514,13 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		 * change it for the last group, note that last_cluster is
 		 * already computed earlier by ext4_get_group_no_and_offset()
 		 */
-		if (group == last_group)
+		if (group == last_group) {
 			end = last_cluster;
-
+			whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+		}
 		if (grp->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, group, first_cluster,
-						end, minlen);
+						 end, minlen, whole_group);
 			if (cnt < 0) {
 				ret = cnt;
 				break;