From: Sagi Grimberg <sagi@grimberg.me>
Date: Wed, 5 Aug 2020 18:13:58 -0700
Subject: [PATCH] nvme-rdma: serialize controller teardown sequences
Git-commit: 5110f40241d08334375eb0495f174b1d2c07657e
Patch-mainline: v5.9-rc4
References: bsc#1179519

In the timeout handler we may need to complete a request because the
request that timed out may be an I/O that is a part of a serial sequence
of controller teardown or initialization. In order to complete the
request, we need to fence any other context that may compete with us
and complete the request that is timing out.

In this case, we could have a potential double completion in case
a hard-irq or a different competing context triggered error recovery
and is running inflight request cancellation concurrently with the
timeout handler.

Protect using a ctrl teardown_lock to serialize contexts that may
complete a cancelled request due to error recovery or a reset.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Hannes Reinecke <hare@suse.com>
---
 drivers/nvme/host/rdma.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 4c5660201009..ed387f61f8f7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -122,6 +122,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -997,6 +998,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
@@ -1007,11 +1009,13 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
@@ -1025,6 +1029,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -2278,6 +2283,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
-- 
2.16.4