From a0731952d9cddc9c11a8352922f449e6ab2f7537 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn.topel@intel.com>
Date: Mon, 30 Nov 2020 19:52:00 +0100
Subject: [PATCH] xsk: Add busy-poll support for {recv,send}msg()
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

Wire-up XDP socket busy-poll support for recvmsg() and sendmsg(). If
the XDP socket prefers busy-polling, make sure that no wakeup/IPI is
performed.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20201130185205.196029-6-bjorn.topel@gmail.com
---
 net/xdp/xsk.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index c72b4db..a8501a5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -23,6 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/rculist.h>
 #include <net/xdp_sock_drv.h>
+#include <net/busy_poll.h>
 #include <net/xdp.h>
 
 #include "xsk_queue.h"
@@ -517,6 +518,17 @@ static int __xsk_sendmsg(struct sock *sk)
 	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
 }
 
+static bool xsk_no_wakeup(struct sock *sk)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* Prefer busy-polling, skip the wakeup. */
+	return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) &&
+		READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID;
+#else
+	return false;
+#endif
+}
+
 static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
@@ -529,6 +541,12 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 	if (unlikely(need_wait))
 		return -EOPNOTSUPP;
 
+	if (sk_can_busy_loop(sk))
+		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+
+	if (xsk_no_wakeup(sk))
+		return 0;
+
 	pool = xs->pool;
 	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
 		return __xsk_sendmsg(sk);
@@ -550,6 +568,12 @@ static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int fl
 	if (unlikely(need_wait))
 		return -EOPNOTSUPP;
 
+	if (sk_can_busy_loop(sk))
+		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+
+	if (xsk_no_wakeup(sk))
+		return 0;
+
 	if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc)
 		return xsk_wakeup(xs, XDP_WAKEUP_RX);
 	return 0;
-- 
2.7.4