summaryrefslogtreecommitdiff
path: root/block/blk-core.c
diff options
context:
space:
mode:
authorBart Van Assche <bart.vanassche@wdc.com>2018-02-28 10:15:32 -0800
committerJens Axboe <axboe@kernel.dk>2018-02-28 12:23:35 -0700
commit498f6650aec864e331cae7575fec5f07781d0bf3 (patch)
tree48b9bdc433ec5c8729e317d55e5d2c5d2fec11c4 /block/blk-core.c
parent5ee0524ba137fe928a88b440d014e3c8451fb32c (diff)
block: Fix a race between the cgroup code and request queue initialization
Initialize the request queue lock earlier such that the following race can no longer occur: blk_init_queue_node() blkcg_print_blkgs() blk_alloc_queue_node (1) q->queue_lock = &q->__queue_lock (2) blkcg_init_queue(q) (3) spin_lock_irq(blkg->q->queue_lock) (4) q->queue_lock = lock (5) spin_unlock_irq(blkg->q->queue_lock) (6) (1) allocate an uninitialized queue; (2) initialize queue_lock to its default internal lock; (3) initialize blkcg part of request queue, which will create blkg and then insert it to blkg_list; (4) traverse blkg_list and find the created blkg, and then take its queue lock, here it is the default *internal lock*; (5) *race window*, now queue_lock is overridden with *driver specified lock*; (6) now unlock *driver specified lock*, not the locked *internal lock*, unlock balance breaks. The changes in this patch are as follows: - Move the .queue_lock initialization from blk_init_queue_node() into blk_alloc_queue_node(). - Only override the .queue_lock pointer for legacy queues because it is not useful for blk-mq queues to override this pointer. - For all all block drivers that initialize .queue_lock explicitly, change the blk_alloc_queue() call in the driver into a blk_alloc_queue_node() call and remove the explicit .queue_lock initialization. Additionally, initialize the spin lock that will be used as queue lock earlier if necessary. Reported-by: Joseph Qi <joseph.qi@linux.alibaba.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-core.c')
-rw-r--r--block/blk-core.c24
1 files changed, 16 insertions, 8 deletions
diff --git a/block/blk-core.c b/block/blk-core.c
index e873a24bf82d..41c74b37be85 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -888,6 +888,19 @@ static void blk_rq_timed_out_timer(struct timer_list *t)
kblockd_schedule_work(&q->timeout_work);
}
+/**
+ * blk_alloc_queue_node - allocate a request queue
+ * @gfp_mask: memory allocation flags
+ * @node_id: NUMA node to allocate memory from
+ * @lock: For legacy queues, pointer to a spinlock that will be used to e.g.
+ * serialize calls to the legacy .request_fn() callback. Ignored for
+ * blk-mq request queues.
+ *
+ * Note: pass the queue lock as the third argument to this function instead of
+ * setting the queue lock pointer explicitly to avoid triggering a sporadic
+ * crash in the blkcg code. This function namely calls blkcg_init_queue() and
+ * the queue lock pointer must be set before blkcg_init_queue() is called.
+ */
struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
spinlock_t *lock)
{
@@ -940,11 +953,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
mutex_init(&q->sysfs_lock);
spin_lock_init(&q->__queue_lock);
- /*
- * By default initialize queue_lock to internal lock and driver can
- * override it later if need be.
- */
- q->queue_lock = &q->__queue_lock;
+ if (!q->mq_ops)
+ q->queue_lock = lock ? : &q->__queue_lock;
/*
* A queue starts its life with bypass turned on to avoid
@@ -1031,13 +1041,11 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
struct request_queue *q;
- q = blk_alloc_queue_node(GFP_KERNEL, node_id, NULL);
+ q = blk_alloc_queue_node(GFP_KERNEL, node_id, lock);
if (!q)
return NULL;
q->request_fn = rfn;
- if (lock)
- q->queue_lock = lock;
if (blk_init_allocated_queue(q) < 0) {
blk_cleanup_queue(q);
return NULL;