nvme-rdma: fix possible double free of controller async event buffer

If reconnect/reset failed where the controller async event buffer
was freed, we might end up freeing it again as we call
nvme_rdma_destroy_admin_queue again in the remove path. Given that
the sequence is guaranteed to serialize by .ctrl_stop, we simply
set ctrl->async_event_sqe.data to NULL and don't free it in future
visits.

Reported-by: Max Gurtovoy <maxg@mellanox.com>
Tested-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 9544625..518c5b0 100644 (file)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -732,8 +732,11 @@ static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
                blk_cleanup_queue(ctrl->ctrl.admin_q);
                nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
        }
-       nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
-               sizeof(struct nvme_command), DMA_TO_DEVICE);
+       if (ctrl->async_event_sqe.data) {
+               nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+                               sizeof(struct nvme_command), DMA_TO_DEVICE);
+               ctrl->async_event_sqe.data = NULL;
+       }
        nvme_rdma_free_queue(&ctrl->queues[0]);
 }