nvme-rdma: Fix possible double free in reconnect flow

The fact that we free the async event buffer in
nvme_rdma_destroy_admin_queue can cause us to free it
more than once because this happens in every reconnect
attempt since commit 31fdf1840170. we rely on the queue
state flags DELETING to avoid this for other resources.

A more complete fix is to not destroy the admin/io queues
unconditionally on every reconnect attempt, but its a bit
more extensive and will go in the next release.

Fixes: 31fdf1840170 ("nvme-rdma: reuse configure/destroy_admin_queue")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
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 92a03ff..4dbee89 100644 (file)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -571,6 +571,12 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
        if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
                return;
 
+       if (nvme_rdma_queue_idx(queue) == 0) {
+               nvme_rdma_free_qe(queue->device->dev,
+                       &queue->ctrl->async_event_sqe,
+                       sizeof(struct nvme_command), DMA_TO_DEVICE);
+       }
+
        nvme_rdma_destroy_queue_ib(queue);
        rdma_destroy_id(queue->cm_id);
 }
@@ -739,8 +745,6 @@ out:
 static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
                bool remove)
 {
-       nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
-                       sizeof(struct nvme_command), DMA_TO_DEVICE);
        nvme_rdma_stop_queue(&ctrl->queues[0]);
        if (remove) {
                blk_cleanup_queue(ctrl->ctrl.admin_q);