[PATCH 5/7] nvmet-tcp: add wq_unbound module parameter

[Hannes Reinecke <hare@kernel.org>]

For high loads the default scheme of queueing work on the receiving
cpu might lead to cpu starvation and 'CPU hogged' messages.
This patch provides an 'wq_unbound' module parameter to let the
workqueue mechanism do scheduling decisions.

Signed-off-by: Hannes Reinecke <hare@kernel.org>
---
 drivers/nvme/target/tcp.c | 34 ++++++++++++++++++++++++++--------
 1 file changed, 26 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index d305d7162dde..572e4f474c68 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -73,6 +73,14 @@ device_param_cb(idle_poll_period_usecs, &set_param_ops,
 MODULE_PARM_DESC(idle_poll_period_usecs,
 		"nvmet tcp io_work poll till idle time period in usecs: Default 0");
 
+/*
+ * Use the unbound workqueue for nvme_tcp_wq, then we can set the cpu affinity
+ * from sysfs.
+ */
+static bool wq_unbound;
+module_param(wq_unbound, bool, 0644);
+MODULE_PARM_DESC(wq_unbound, "Use unbound workqueue for nvme-tcp IO context (default false)");
+
 #ifdef CONFIG_NVME_TARGET_TCP_TLS
 /*
  * TLS handshake timeout
@@ -566,6 +574,15 @@ static struct nvmet_tcp_cmd *nvmet_tcp_fetch_cmd(struct nvmet_tcp_queue *queue)
 	return queue->snd_cmd;
 }
 
+static void nvmet_tcp_queue_work(struct nvmet_tcp_queue *queue)
+{
+	if (wq_unbound)
+		queue_work(nvmet_tcp_wq, &queue->io_work);
+	else
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq,
+			      &queue->io_work);
+}
+
 static void nvmet_tcp_queue_response(struct nvmet_req *req)
 {
 	struct nvmet_tcp_cmd *cmd =
@@ -590,7 +607,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 	}
 
 	llist_add(&cmd->lentry, &queue->resp_list);
-	queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &cmd->queue->io_work);
+	nvmet_tcp_queue_work(queue);
 }
 
 static void nvmet_tcp_execute_request(struct nvmet_tcp_cmd *cmd)
@@ -1452,7 +1469,7 @@ static void nvmet_tcp_io_work(struct work_struct *w)
 	 * ops activity was recorded during the do-while loop above.
 	 */
 	if (nvmet_tcp_check_queue_deadline(queue, ops) || pending)
-		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
+		nvmet_tcp_queue_work(queue);
 }
 
 static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
@@ -1628,8 +1645,7 @@ static void nvmet_tcp_data_ready(struct sock *sk)
 		if (queue->data_ready)
 			queue->data_ready(sk);
 		if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)
-			queue_work_on(queue_cpu(queue), nvmet_tcp_wq,
-				      &queue->io_work);
+			nvmet_tcp_queue_work(queue);
 	}
 	read_unlock_bh(&sk->sk_callback_lock);
 }
@@ -1650,7 +1666,7 @@ static void nvmet_tcp_write_space(struct sock *sk)
 
 	if (sk_stream_is_writeable(sk)) {
 		clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
+		nvmet_tcp_queue_work(queue);
 	}
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -1731,7 +1747,7 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 		sock->sk->sk_write_space = nvmet_tcp_write_space;
 		if (idle_poll_period_usecs)
 			nvmet_tcp_arm_queue_deadline(queue);
-		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
+		nvmet_tcp_queue_work(queue);
 	}
 	write_unlock_bh(&sock->sk->sk_callback_lock);
 
@@ -2182,9 +2198,11 @@ static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
 static int __init nvmet_tcp_init(void)
 {
 	int ret;
+	unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS;
 
-	nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq",
-				WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+	if (wq_unbound)
+		wq_flags |= WQ_UNBOUND;
+	nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq", wq_flags, 0);
 	if (!nvmet_tcp_wq)
 		return -ENOMEM;
 
-- 
2.35.3