[PATCH 4/7] nvme-tcp: receive data in softirq

[Hannes Reinecke]

From: Sagi Grimberg <sagi at grimberg.me>

Network interrupts are already delivered in softirq, so there is
no need to punt things over to a workqueue. This patch adds a
module parameter 'softirq_rx' to process rx packets directly
from the softirq context.

Signed-off-by: Sagi Grimberg <sagi at grimberg.me>
Signed-off-by: Hannes Reinecke <hare at kernel.org>
---
 drivers/nvme/host/tcp.c | 52 ++++++++++++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 16 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index faab55ff86fe..599d4ebf888f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -46,6 +46,13 @@ 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)");
 
+/*
+ * RX context runs in softirq
+ */
+static bool softirq_rx;
+module_param(softirq_rx, bool, 0644);
+MODULE_PARM_DESC(softirq_rx, "nvme-tcp RX context in softirq");
+
 /*
  * TLS handshake timeout
  */
@@ -957,6 +964,20 @@ static int nvme_tcp_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 	return consumed;
 }
 
+static int nvme_tcp_try_recv_locked(struct nvme_tcp_queue *queue)
+{
+	struct socket *sock = queue->sock;
+	struct sock *sk = sock->sk;
+	read_descriptor_t rd_desc;
+	int consumed;
+
+	rd_desc.arg.data = queue;
+	rd_desc.count = 1;
+	queue->nr_cqe = 0;
+	consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
+	return consumed;
+}
+
 static void nvme_tcp_data_ready(struct sock *sk)
 {
 	struct nvme_tcp_queue *queue;
@@ -966,8 +987,12 @@ static void nvme_tcp_data_ready(struct sock *sk)
 	read_lock_bh(&sk->sk_callback_lock);
 	queue = sk->sk_user_data;
 	if (likely(queue && queue->rd_enabled) &&
-	    !test_bit(NVME_TCP_Q_POLLING, &queue->flags))
-		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
+	    !test_bit(NVME_TCP_Q_POLLING, &queue->flags)) {
+		if (softirq_rx)
+			nvme_tcp_try_recv_locked(queue);
+		else
+			queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
+	}
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
@@ -1253,16 +1278,11 @@ static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)
 
 static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
 {
-	struct socket *sock = queue->sock;
-	struct sock *sk = sock->sk;
-	read_descriptor_t rd_desc;
+	struct sock *sk = queue->sock->sk;
 	int consumed;
 
-	rd_desc.arg.data = queue;
-	rd_desc.count = 1;
 	lock_sock(sk);
-	queue->nr_cqe = 0;
-	consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
+	consumed = nvme_tcp_try_recv_locked(queue);
 	release_sock(sk);
 	return consumed;
 }
@@ -1285,13 +1305,13 @@ static void nvme_tcp_io_work(struct work_struct *w)
 			else if (unlikely(result < 0))
 				break;
 		}
-
-		result = nvme_tcp_try_recv(queue);
-		if (result > 0)
-			pending = true;
-		else if (unlikely(result < 0))
-			return;
-
+		if (!softirq_rx) {
+			result = nvme_tcp_try_recv(queue);
+			if (result > 0)
+				pending = true;
+			else if (unlikely(result < 0))
+				return;
+		}
 		if (!pending || !queue->rd_enabled)
 			return;
 
-- 
2.35.3