ext4: mballoc: use lock for checking free blocks while retrying

Currently while doing block allocation grp->bb_free may be getting
modified if discard is happening in parallel.
For e.g. consider a case where there are lot of threads who have
preallocated lot of blocks and there is a thread which is trying
to discard all of this group's PA. Now it could happen that
we see all of those group's bb_free is zero and fail the allocation
while there is sufficient space if we free up all the PA.

So this patch adds another flag "EXT4_MB_STRICT_CHECK" which will be set
if we are unable to allocate any blocks in the first try (since we may
not have considered blocks about to be discarded from PA lists).
So during retry attempt to allocate blocks we will use ext4_lock_group()
for checking if the group is good or not.

Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Link: https://lore.kernel.org/r/9cb740a117c958c36596f167b12af1beae9a68b7.1589955723.git.riteshh@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

3 files changed, 16 insertions, 2 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index af60be906528..dbc36e377eb0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -150,6 +150,8 @@ enum SHIFT_DIRECTION {
 #define EXT4_MB_USE_ROOT_BLOCKS		0x1000
 /* Use blocks from reserved pool */
 #define EXT4_MB_USE_RESERVED		0x2000
+/* Do strict check for free blocks while retrying block allocation */
+#define EXT4_MB_STRICT_CHECK		0x4000
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c9297c878a90..a9083113a8c0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2176,9 +2176,13 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 				     ext4_group_t group, int cr)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
+	struct super_block *sb = ac->ac_sb;
+	bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK;
 	ext4_grpblk_t free;
 	int ret = 0;
 
+	if (should_lock)
+		ext4_lock_group(sb, group);
 	free = grp->bb_free;
 	if (free == 0)
 		goto out;
@@ -2186,6 +2190,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 		goto out;
 	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
 		goto out;
+	if (should_lock)
+		ext4_unlock_group(sb, group);
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
@@ -2194,8 +2200,12 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 			return ret;
 	}
 
+	if (should_lock)
+		ext4_lock_group(sb, group);
 	ret = ext4_mb_good_group(ac, group, cr);
 out:
+	if (should_lock)
+		ext4_unlock_group(sb, group);
 	return ret;
 }
 
@@ -4610,7 +4620,8 @@ static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb,
 		goto out_dbg;
 	}
 	seq_retry = ext4_get_discard_pa_seq_sum();
-	if (seq_retry != *seq) {
+	if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) {
+		ac->ac_flags |= EXT4_MB_STRICT_CHECK;
 		*seq = seq_retry;
 		ret = true;
 	}
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 280475c1cecc..cc41d692ae8e 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -35,7 +35,8 @@ struct partial_cluster;
 	{ EXT4_MB_DELALLOC_RESERVED,	"DELALLOC_RESV" },	\
 	{ EXT4_MB_STREAM_ALLOC,		"STREAM_ALLOC" },	\
 	{ EXT4_MB_USE_ROOT_BLOCKS,	"USE_ROOT_BLKS" },	\
-	{ EXT4_MB_USE_RESERVED,		"USE_RESV" })
+	{ EXT4_MB_USE_RESERVED,		"USE_RESV" },		\
+	{ EXT4_MB_STRICT_CHECK,		"STRICT_CHECK" })
 
 #define show_map_flags(flags) __print_flags(flags, "|",			\
 	{ EXT4_GET_BLOCKS_CREATE,		"CREATE" },		\