block: fix use-after-free on cached last_lookup partition

delete_partition() clears the cached last_lookup partition. However the
.last_lookup cache may be overwritten by one IO path after it is cleared
from delete_partition(). Then another IO path may use the cached deleting
partition after hd_struct_free() is called, then use-after-free is triggered
on the cached partition.

Fixes the issue by the following approach:

1) always get the partition's refcount via hd_struct_try_get() before
setting .last_lookup

2) move clearing .last_lookup from delete_partition() to hd_struct_free()
which is the release handle of the partition's percpu-refcount, so that no
IO path can cache deleteing partition via .last_lookup.

It is one candidate approach of Yufen's patch[1] which adds overhead
in fast path by indirect lookup which may introduce one extra cacheline
in IO path. Also this patch relies on percpu-refcount's protection, and
it is easier to understand and verify.

[1] https://lore.kernel.org/linux-block/20200109013551.GB9655@ming.t460p/T/#t

Reported-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@infradead.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 23 insertions, 16 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 538cbc725620..409e1a6b73b0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1362,18 +1362,6 @@ void blk_account_io_start(struct request *rq, bool new_io)
 		part_stat_inc(part, merges[rw]);
 	} else {
 		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
-		if (!hd_struct_try_get(part)) {
-			/*
-			 * The partition is already being removed,
-			 * the request will be accounted on the disk only
-			 *
-			 * We take a reference on disk->part0 although that
-			 * partition will never be deleted, so we can treat
-			 * it as any other partition.
-			 */
-			part = &rq->rq_disk->part0;
-			hd_struct_get(part);
-		}
 		part_inc_in_flight(rq->q, part, rw);
 		rq->part = part;
 	}
diff --git a/block/genhd.c b/block/genhd.c
index 27511b3d164d..af6cba2a9332 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -344,11 +344,12 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector)
  * primarily used for stats accounting.
  *
  * CONTEXT:
- * RCU read locked.  The returned partition pointer is valid only
- * while preemption is disabled.
+ * RCU read locked.  The returned partition pointer is always valid
+ * because its refcount is grabbed.
  *
  * RETURNS:
  * Found partition on success, part0 is returned if no partition matches
+ * or the matched partition is being deleted.
  */
 struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 {
@@ -359,17 +360,25 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 	ptbl = rcu_dereference(disk->part_tbl);
 
 	part = rcu_dereference(ptbl->last_lookup);
-	if (part && sector_in_part(part, sector))
+	if (part && sector_in_part(part, sector) && hd_struct_try_get(part))
 		return part;
 
 	for (i = 1; i < ptbl->len; i++) {
 		part = rcu_dereference(ptbl->part[i]);
 
 		if (part && sector_in_part(part, sector)) {
+			/*
+			 * only live partition can be cached for lookup,
+			 * so use-after-free on cached & deleting partition
+			 * can be avoided
+			 */
+			if (!hd_struct_try_get(part))
+				break;
 			rcu_assign_pointer(ptbl->last_lookup, part);
 			return part;
 		}
 	}
+	hd_struct_get(&disk->part0);
 	return &disk->part0;
 }
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 873999e2e2f2..8d8c87207fc2 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -288,6 +288,12 @@ static void hd_struct_free_work(struct work_struct *work)
 static void hd_struct_free(struct percpu_ref *ref)
 {
 	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
+	struct gendisk *disk = part_to_disk(part);
+	struct disk_part_tbl *ptbl =
+		rcu_dereference_protected(disk->part_tbl, 1);
+
+	rcu_assign_pointer(ptbl->last_lookup, NULL);
+	put_device(disk_to_dev(disk));
 
 	INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
 	queue_rcu_work(system_wq, &part->rcu_work);
@@ -309,8 +315,12 @@ void delete_partition(struct gendisk *disk, struct hd_struct *part)
 	struct disk_part_tbl *ptbl =
 		rcu_dereference_protected(disk->part_tbl, 1);
 
+	/*
+	 * ->part_tbl is referenced in this part's release handler, so
+	 *  we have to hold the disk device
+	 */
+	get_device(disk_to_dev(part_to_disk(part)));
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
-	rcu_assign_pointer(ptbl->last_lookup, NULL);
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));