[PATCH] tun: support NAPI to accelerate packet processing

[Harold Huang <baymaxhuang@gmail.com>]

In tun, NAPI is supported and we can also use NAPI in the path of
batched XDP buffs to accelerate packet processing. What is more, after
we use NPAI, GRO is also supported. The iperf shows that the throughput
could be improved from 4.5Gbsp to 9.2Gbps per stream.

Reported-at: https://lore.kernel.org/netdev/CAHJXk3Y9_Fh04sakMMbcAkef7kOTEc-kf84Ne3DtWD7EAp13cg@mail.gmail.com/T/#t
Signed-off-by: Harold Huang <baymaxhuang@gmail.com>
---
 drivers/net/tun.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fed85447701a..4e1cea659b42 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2388,6 +2388,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	struct virtio_net_hdr *gso = &hdr->gso;
 	struct bpf_prog *xdp_prog;
 	struct sk_buff *skb = NULL;
+	struct sk_buff_head *queue;
 	u32 rxhash = 0, act;
 	int buflen = hdr->buflen;
 	int err = 0;
@@ -2464,7 +2465,14 @@ static int tun_xdp_one(struct tun_struct *tun,
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
-	netif_receive_skb(skb);
+	if (tfile->napi_enabled) {
+		queue = &tfile->sk.sk_write_queue;
+		spin_lock(&queue->lock);
+		__skb_queue_tail(queue, skb);
+		spin_unlock(&queue->lock);
+	} else {
+		netif_receive_skb(skb);
+	}
 
 	/* No need to disable preemption here since this function is
 	 * always called with bh disabled
@@ -2507,6 +2515,9 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		if (flush)
 			xdp_do_flush();
 
+		if (tfile->napi_enabled)
+			napi_schedule(&tfile->napi);
+
 		rcu_read_unlock();
 		local_bh_enable();
 
-- 
2.27.0