[dm-devel] [PATCH] dm-cache: fix bugs when a GFP_NOWAIT allocation fails

[Mikulas Patocka]

GFP_NOWAIT allocation can fail anytime - it doesn't wait for memory being
available and it fails if the mempool is exhausted and there is not enough
memory.

If we go down this path:
  map_bio -> mg_start -> alloc_migration -> mempool_alloc(GFP_NOWAIT)
we can see that map_bio doesn't check the return value of mg_start, and
the bio is leaked.

If we go down this path:
  map_bio -> mg_start -> mg_lock_writes -> alloc_prison_cell ->
  dm_bio_prison_alloc_cell_v2 -> mempool_alloc(GFP_NOWAIT) ->
  mg_lock_writes -> mg_complete
the bio is ended with an error - it is unacceptable because it could cause
filesystem corruption if the machine ran out of memory temporarily.

This pactch changes GFP_NOWAIT to GFP_NOIO, so that the mempool code will
properly wait until memory becomes available. mempool_alloc with GFP_NOIO
can't fail, so I deleted the code paths that deal with the failure.

Signed-off-by: Mikulas Patocka <mpatocka at redhat.com>
Cc: stable at vger.kernel.org

---
 drivers/md/dm-cache-target.c |   28 ++--------------------------
 1 file changed, 2 insertions(+), 26 deletions(-)

Index: linux-2.6/drivers/md/dm-cache-target.c
===================================================================
--- linux-2.6.orig/drivers/md/dm-cache-target.c	2019-10-10 16:52:03.000000000 +0200
+++ linux-2.6/drivers/md/dm-cache-target.c	2019-10-16 13:23:13.000000000 +0200
@@ -542,7 +542,7 @@ static void wake_migration_worker(struct
 
 static struct dm_bio_prison_cell_v2 *alloc_prison_cell(struct cache *cache)
 {
-	return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOWAIT);
+	return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOIO);
 }
 
 static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell_v2 *cell)
@@ -554,9 +554,7 @@ static struct dm_cache_migration *alloc_
 {
 	struct dm_cache_migration *mg;
 
-	mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT);
-	if (!mg)
-		return NULL;
+	mg = mempool_alloc(&cache->migration_pool, GFP_NOIO);
 
 	memset(mg, 0, sizeof(*mg));
 
@@ -664,10 +662,6 @@ static bool bio_detain_shared(struct cac
 	struct dm_bio_prison_cell_v2 *cell_prealloc, *cell;
 
 	cell_prealloc = alloc_prison_cell(cache); /* FIXME: allow wait if calling from worker */
-	if (!cell_prealloc) {
-		defer_bio(cache, bio);
-		return false;
-	}
 
 	build_key(oblock, end, &key);
 	r = dm_cell_get_v2(cache->prison, &key, lock_level(bio), bio, cell_prealloc, &cell);
@@ -1493,11 +1487,6 @@ static int mg_lock_writes(struct dm_cach
 	struct dm_bio_prison_cell_v2 *prealloc;
 
 	prealloc = alloc_prison_cell(cache);
-	if (!prealloc) {
-		DMERR_LIMIT("%s: alloc_prison_cell failed", cache_device_name(cache));
-		mg_complete(mg, false);
-		return -ENOMEM;
-	}
 
 	/*
 	 * Prevent writes to the block, but allow reads to continue.
@@ -1535,11 +1524,6 @@ static int mg_start(struct cache *cache,
 	}
 
 	mg = alloc_migration(cache);
-	if (!mg) {
-		policy_complete_background_work(cache->policy, op, false);
-		background_work_end(cache);
-		return -ENOMEM;
-	}
 
 	mg->op = op;
 	mg->overwrite_bio = bio;
@@ -1628,10 +1612,6 @@ static int invalidate_lock(struct dm_cac
 	struct dm_bio_prison_cell_v2 *prealloc;
 
 	prealloc = alloc_prison_cell(cache);
-	if (!prealloc) {
-		invalidate_complete(mg, false);
-		return -ENOMEM;
-	}
 
 	build_key(mg->invalidate_oblock, oblock_succ(mg->invalidate_oblock), &key);
 	r = dm_cell_lock_v2(cache->prison, &key,
@@ -1669,10 +1649,6 @@ static int invalidate_start(struct cache
 		return -EPERM;
 
 	mg = alloc_migration(cache);
-	if (!mg) {
-		background_work_end(cache);
-		return -ENOMEM;
-	}
 
 	mg->overwrite_bio = bio;
 	mg->invalidate_cblock = cblock;