When a bio is allocated from the mempool with REQ_ALLOC_CACHE set and
later completed, bio_put() places it into the per-cpu bio_alloc_cache
via bio_put_percpu_cache() instead of freeing it back to the
mempool/slab. The slab allocation remains tracked by kmemleak, but the
only reference to the bio is through the percpu cache's free_list,
which kmemleak fails to trace through percpu memory. This causes
kmemleak to report the cached bios as unreferenced objects.

Use symmetric kmemleak_free()/kmemleak_alloc() calls to properly track
bios across percpu cache transitions:

 - bio_put_percpu_cache: call kmemleak_free() when a bio enters the
   cache, unregistering it from kmemleak tracking.

 - bio_alloc_percpu_cache: call kmemleak_alloc() when a bio is taken
   from the cache for reuse, re-registering it so that genuine leaks
   of reused bios remain detectable.

 - __bio_alloc_cache_prune: call kmemleak_alloc() before bio_free() so
   that kmem_cache_free()'s internal kmemleak_free() has a matching
   allocation to pair with.

Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
V2:
	- rebase on for-7.1/block
	- add helper of bio_slab_addr()

 block/bio.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/block/bio.c b/block/bio.c
index 77067fa346d3..c8234d347fc5 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -18,6 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/blk-crypto.h>
 #include <linux/xarray.h>
+#include <linux/kmemleak.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
@@ -116,6 +117,11 @@ static inline unsigned int bs_bio_slab_size(struct bio_set *bs)
 	return bs->front_pad + sizeof(struct bio) + bs->back_pad;
 }
 
+static inline void *bio_slab_addr(struct bio *bio)
+{
+	return (void *)bio - bio->bi_pool->front_pad;
+}
+
 static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs)
 {
 	unsigned int size = bs_bio_slab_size(bs);
@@ -486,6 +492,9 @@ static struct bio *bio_alloc_percpu_cache(struct bio_set *bs)
 	cache->nr--;
 	put_cpu();
 	bio->bi_pool = bs;
+
+	kmemleak_alloc(bio_slab_addr(bio),
+		       kmem_cache_size(bs->bio_slab), 1, GFP_NOIO);
 	return bio;
 }
 
@@ -728,6 +737,9 @@ static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache,
 	while ((bio = cache->free_list) != NULL) {
 		cache->free_list = bio->bi_next;
 		cache->nr--;
+		kmemleak_alloc(bio_slab_addr(bio),
+			       kmem_cache_size(bio->bi_pool->bio_slab),
+			       1, GFP_KERNEL);
 		bio_free(bio);
 		if (++i == nr)
 			break;
@@ -791,6 +803,7 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 		bio->bi_bdev = NULL;
 		cache->free_list = bio;
 		cache->nr++;
+		kmemleak_free(bio_slab_addr(bio));
 	} else if (in_hardirq()) {
 		lockdep_assert_irqs_disabled();
 
@@ -798,6 +811,7 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 		bio->bi_next = cache->free_list_irq;
 		cache->free_list_irq = bio;
 		cache->nr_irq++;
+		kmemleak_free(bio_slab_addr(bio));
 	} else {
 		goto out_free;
 	}
-- 
2.53.0