block: only call sched requeue_request() for scheduled requests

Yang Yang reported the following crash caused by requeueing a flush
request in Kyber:

  [    2.517297] Unable to handle kernel paging request at virtual address ffffffd8071c0b00
  ...
  [    2.517468] pc : clear_bit+0x18/0x2c
  [    2.517502] lr : sbitmap_queue_clear+0x40/0x228
  [    2.517503] sp : ffffff800832bc60 pstate : 00c00145
  ...
  [    2.517599] Process ksoftirqd/5 (pid: 51, stack limit = 0xffffff8008328000)
  [    2.517602] Call trace:
  [    2.517606]  clear_bit+0x18/0x2c
  [    2.517619]  kyber_finish_request+0x74/0x80
  [    2.517627]  blk_mq_requeue_request+0x3c/0xc0
  [    2.517637]  __scsi_queue_insert+0x11c/0x148
  [    2.517640]  scsi_softirq_done+0x114/0x130
  [    2.517643]  blk_done_softirq+0x7c/0xb0
  [    2.517651]  __do_softirq+0x208/0x3bc
  [    2.517657]  run_ksoftirqd+0x34/0x60
  [    2.517663]  smpboot_thread_fn+0x1c4/0x2c0
  [    2.517667]  kthread+0x110/0x120
  [    2.517669]  ret_from_fork+0x10/0x18

This happens because Kyber doesn't track flush requests, so
kyber_finish_request() reads a garbage domain token. Only call the
scheduler's requeue_request() hook if RQF_ELVPRIV is set (like we do for
the finish_request() hook in blk_mq_free_request()). Now that we're
handling it in blk-mq, also remove the check from BFQ.

Reported-by: Yang Yang <yang.yang@vivo.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a4c0bec920cbde6bef9f61909efc353937de85d4..ee767fa000e4f8eb681850a85f70d63cff9ddb9a 100644 (file)
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5895,18 +5895,6 @@ static void bfq_finish_requeue_request(struct request *rq)
        struct bfq_queue *bfqq = RQ_BFQQ(rq);
        struct bfq_data *bfqd;
 
-       /*
-        * Requeue and finish hooks are invoked in blk-mq without
-        * checking whether the involved request is actually still
-        * referenced in the scheduler. To handle this fact, the
-        * following two checks make this function exit in case of
-        * spurious invocations, for which there is nothing to do.
-        *
-        * First, check whether rq has nothing to do with an elevator.
-        */
-       if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
-               return;
-
        /*
         * rq either is not associated with any icq, or is an already
         * requeued request that has not (yet) been re-inserted into

diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 126021fc3a11f9308a5fe0745ba2a6f9f1ee2ee5..e81ca1bf6e10b6dfcb3838f2424ee71ca89aea87 100644 (file)
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -66,7 +66,7 @@ static inline void blk_mq_sched_requeue_request(struct request *rq)
        struct request_queue *q = rq->q;
        struct elevator_queue *e = q->elevator;
 
-       if (e && e->type->ops.requeue_request)
+       if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
                e->type->ops.requeue_request(rq);
 }