nvmet-rdma: update queue list during ib_device removal

A NULL deref happens when nvmet_rdma_remove_one() is called more than once
(e.g. while connected via 2 ports).
The first call frees the queues related to the first ib_device but
doesn't remove them from the queue list.
While calling nvmet_rdma_remove_one() for the second ib_device it goes over
the full queue list again and we get the NULL deref.

Fixes: f1d4ef7d ("nvmet-rdma: register ib_client to not deadlock in device removal")
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grmberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 76d2bb793afe5087656747232752cc9206eb14ab..3333d417b248ba6de431adbb1562e40e9a9da751 100644 (file)
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1512,15 +1512,17 @@ static struct nvmet_fabrics_ops nvmet_rdma_ops = {
 
 static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
 {
-       struct nvmet_rdma_queue *queue;
+       struct nvmet_rdma_queue *queue, *tmp;
 
        /* Device is being removed, delete all queues using this device */
        mutex_lock(&nvmet_rdma_queue_mutex);
-       list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) {
+       list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list,
+                                queue_list) {
                if (queue->dev->device != ib_device)
                        continue;
 
                pr_info("Removing queue %d\n", queue->idx);
+               list_del_init(&queue->queue_list);
                __nvmet_rdma_queue_disconnect(queue);
        }
        mutex_unlock(&nvmet_rdma_queue_mutex);