nvmet-rdma: disable interrupts under rsp_wr_wait_lock

rsp_wr_wait_lock protects the list of commands waiting for room in the
send queue, and it's taken with plain spin_lock(). But
nvmet_rdma_queue_response() calls nvmet_rdma_release_rsp() directly if
ib_post_send() fails, and that processes the wait list. The call chain
starts in nvmet_req_complete(), which for a block device namespace runs
from the bio end_io callback, which can be in hard interrupt context.
An interrupt that completes a command on a CPU holding the lock for the
same queue spins forever. Lockdep over siw with a null_blk namespace:

  inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage

Use spin_lock_irqsave() for both takers. The processing loop still
drops the lock, and restores the caller's interrupt state, around
nvmet_rdma_execute_command().

Fixes: 8f000cac6e7a ("nvmet-rdma: add a NVMe over Fabrics RDMA target driver")
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Chris Mason <mason@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Keith Busch <kbusch@kernel.org>

1 files changed, 9 insertions, 6 deletions

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index ed11263ea93f..279d0d097b55 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -513,7 +513,9 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 
 static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
 {
-	spin_lock(&queue->rsp_wr_wait_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&queue->rsp_wr_wait_lock, flags);
 	while (!list_empty(&queue->rsp_wr_wait_list)) {
 		struct nvmet_rdma_rsp *rsp;
 		bool ret;
@@ -522,16 +524,16 @@ static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
 				struct nvmet_rdma_rsp, wait_list);
 		list_del(&rsp->wait_list);
 
-		spin_unlock(&queue->rsp_wr_wait_lock);
+		spin_unlock_irqrestore(&queue->rsp_wr_wait_lock, flags);
 		ret = nvmet_rdma_execute_command(rsp);
-		spin_lock(&queue->rsp_wr_wait_lock);
+		spin_lock_irqsave(&queue->rsp_wr_wait_lock, flags);
 
 		if (!ret) {
 			list_add(&rsp->wait_list, &queue->rsp_wr_wait_list);
 			break;
 		}
 	}
-	spin_unlock(&queue->rsp_wr_wait_lock);
+	spin_unlock_irqrestore(&queue->rsp_wr_wait_lock, flags);
 }
 
 static u16 nvmet_rdma_check_pi_status(struct ib_mr *sig_mr)
@@ -977,6 +979,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp)
 static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 		struct nvmet_rdma_rsp *cmd)
 {
+	unsigned long flags;
 	u16 status;
 
 	ib_dma_sync_single_for_cpu(queue->dev->device,
@@ -994,9 +997,9 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 		goto out_err;
 
 	if (unlikely(!nvmet_rdma_execute_command(cmd))) {
-		spin_lock(&queue->rsp_wr_wait_lock);
+		spin_lock_irqsave(&queue->rsp_wr_wait_lock, flags);
 		list_add_tail(&cmd->wait_list, &queue->rsp_wr_wait_list);
-		spin_unlock(&queue->rsp_wr_wait_lock);
+		spin_unlock_irqrestore(&queue->rsp_wr_wait_lock, flags);
 	}
 
 	return;