nvmet-rdma: use a private workqueue for delete

Queue deletion is done asynchronous when the last reference on the queue
is dropped.  Thus, in order to make sure we don't over allocate under a
connect/disconnect storm, we let queue deletion complete before making
forward progress.

However, given that we flush the system_wq from rdma_cm context which
runs from a workqueue context, we can have a circular locking complaint
[1]. Fix that by using a private workqueue for queue deletion.

[1]:
======================================================
WARNING: possible circular locking dependency detected
4.19.0-rc4-dbg+ #3 Not tainted
------------------------------------------------------
kworker/5:0/39 is trying to acquire lock:
00000000a10b6db9 (&id_priv->handler_mutex){+.+.}, at: rdma_destroy_id+0x6f/0x440 [rdma_cm]

but task is already holding lock:
00000000331b4e2c ((work_completion)(&queue->release_work)){+.+.}, at: process_one_work+0x3ed/0xa20

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #3 ((work_completion)(&queue->release_work)){+.+.}:
       process_one_work+0x474/0xa20
       worker_thread+0x63/0x5a0
       kthread+0x1cf/0x1f0
       ret_from_fork+0x24/0x30

-> #2 ((wq_completion)"events"){+.+.}:
       flush_workqueue+0xf3/0x970
       nvmet_rdma_cm_handler+0x133d/0x1734 [nvmet_rdma]
       cma_ib_req_handler+0x72f/0xf90 [rdma_cm]
       cm_process_work+0x2e/0x110 [ib_cm]
       cm_req_handler+0x135b/0x1c30 [ib_cm]
       cm_work_handler+0x2b7/0x38cd [ib_cm]
       process_one_work+0x4ae/0xa20
nvmet_rdma:nvmet_rdma_cm_handler: nvmet_rdma: disconnected (10): status 0 id 0000000040357082
       worker_thread+0x63/0x5a0
       kthread+0x1cf/0x1f0
       ret_from_fork+0x24/0x30
nvme nvme0: Reconnecting in 10 seconds...

-> #1 (&id_priv->handler_mutex/1){+.+.}:
       __mutex_lock+0xfe/0xbe0
       mutex_lock_nested+0x1b/0x20
       cma_ib_req_handler+0x6aa/0xf90 [rdma_cm]
       cm_process_work+0x2e/0x110 [ib_cm]
       cm_req_handler+0x135b/0x1c30 [ib_cm]
       cm_work_handler+0x2b7/0x38cd [ib_cm]
       process_one_work+0x4ae/0xa20
       worker_thread+0x63/0x5a0
       kthread+0x1cf/0x1f0
       ret_from_fork+0x24/0x30

-> #0 (&id_priv->handler_mutex){+.+.}:
       lock_acquire+0xc5/0x200
       __mutex_lock+0xfe/0xbe0
       mutex_lock_nested+0x1b/0x20
       rdma_destroy_id+0x6f/0x440 [rdma_cm]
       nvmet_rdma_release_queue_work+0x8e/0x1b0 [nvmet_rdma]
       process_one_work+0x4ae/0xa20
       worker_thread+0x63/0x5a0
       kthread+0x1cf/0x1f0
       ret_from_fork+0x24/0x30

Fixes: 777dc82395de ("nvmet-rdma: occasionally flush ongoing controller teardown")
Reported-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index bfc4da660bb4036c9d53764793824f5befb3edb2..5becca88ccbe1e933d31b9f088696b57f4ba88e2 100644 (file)
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -122,6 +122,7 @@ struct nvmet_rdma_device {
        int                     inline_page_count;
 };
 
+struct workqueue_struct *nvmet_rdma_delete_wq;
 static bool nvmet_rdma_use_srq;
 module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
 MODULE_PARM_DESC(use_srq, "Use shared receive queue.");
@@ -1267,12 +1268,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 
        if (queue->host_qid == 0) {
                /* Let inflight controller teardown complete */
-               flush_scheduled_work();
+               flush_workqueue(nvmet_rdma_delete_wq);
        }
 
        ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
        if (ret) {
-               schedule_work(&queue->release_work);
+               queue_work(nvmet_rdma_delete_wq, &queue->release_work);
                /* Destroying rdma_cm id is not needed here */
                return 0;
        }
@@ -1337,7 +1338,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
 
        if (disconnect) {
                rdma_disconnect(queue->cm_id);
-               schedule_work(&queue->release_work);
+               queue_work(nvmet_rdma_delete_wq, &queue->release_work);
        }
 }
 
@@ -1367,7 +1368,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
        mutex_unlock(&nvmet_rdma_queue_mutex);
 
        pr_err("failed to connect queue %d\n", queue->idx);
-       schedule_work(&queue->release_work);
+       queue_work(nvmet_rdma_delete_wq, &queue->release_work);
 }
 
 /**
@@ -1649,8 +1650,17 @@ static int __init nvmet_rdma_init(void)
        if (ret)
                goto err_ib_client;
 
+       nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq",
+                       WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+       if (!nvmet_rdma_delete_wq) {
+               ret = -ENOMEM;
+               goto err_unreg_transport;
+       }
+
        return 0;
 
+err_unreg_transport:
+       nvmet_unregister_transport(&nvmet_rdma_ops);
 err_ib_client:
        ib_unregister_client(&nvmet_rdma_ib_client);
        return ret;
@@ -1658,6 +1668,7 @@ err_ib_client:
 
 static void __exit nvmet_rdma_exit(void)
 {
+       destroy_workqueue(nvmet_rdma_delete_wq);
        nvmet_unregister_transport(&nvmet_rdma_ops);
        ib_unregister_client(&nvmet_rdma_ib_client);
        WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list));