nvme-rdma: fix possible use-after-free in connect error flow

When start_queue fails, we need to make sure to drain the
queue cq before freeing the rdma resources because we might
still race with the completion path. Have start_queue() error
path safely stop the queue.

--
[30371.808111] nvme nvme1: Failed reconnect attempt 11
[30371.808113] nvme nvme1: Reconnecting in 10 seconds...
[...]
[30382.069315] nvme nvme1: creating 4 I/O queues.
[30382.257058] nvme nvme1: Connect Invalid SQE Parameter, qid 4
[30382.257061] nvme nvme1: failed to connect queue: 4 ret=386
[30382.305001] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
[30382.305022] IP: qedr_poll_cq+0x8a3/0x1170 [qedr]
[30382.305028] PGD 0 P4D 0
[30382.305037] Oops: 0000 [#1] SMP PTI
[...]
[30382.305153] Call Trace:
[30382.305166]  ? __switch_to_asm+0x34/0x70
[30382.305187]  __ib_process_cq+0x56/0xd0 [ib_core]
[30382.305201]  ib_poll_handler+0x26/0x70 [ib_core]
[30382.305213]  irq_poll_softirq+0x88/0x110
[30382.305223]  ? sort_range+0x20/0x20
[30382.305232]  __do_softirq+0xde/0x2c6
[30382.305241]  ? sort_range+0x20/0x20
[30382.305249]  run_ksoftirqd+0x1c/0x60
[30382.305258]  smpboot_thread_fn+0xef/0x160
[30382.305265]  kthread+0x113/0x130
[30382.305273]  ? kthread_create_worker_on_cpu+0x50/0x50
[30382.305281]  ret_from_fork+0x35/0x40
--

Reported-by: Nicolas Morey-Chaisemartin <NMoreyChaisemartin@suse.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index a249db528d543dcad37e9b5162cc4b196a2f41e1..1a6449bc547b91ab7460b817fd6aada3ca5b5acd 100644 (file)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -562,13 +562,17 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
        return ret;
 }
 
+static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
+{
+       rdma_disconnect(queue->cm_id);
+       ib_drain_qp(queue->qp);
+}
+
 static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
 {
        if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags))
                return;
-
-       rdma_disconnect(queue->cm_id);
-       ib_drain_qp(queue->qp);
+       __nvme_rdma_stop_queue(queue);
 }
 
 static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
@@ -607,11 +611,13 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
        else
                ret = nvmf_connect_admin_queue(&ctrl->ctrl);
 
-       if (!ret)
+       if (!ret) {
                set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
-       else
+       } else {
+               __nvme_rdma_stop_queue(queue);
                dev_info(ctrl->ctrl.device,
                        "failed to connect queue: %d ret=%d\n", idx, ret);
+       }
        return ret;
 }