Merge branch 'tcp-io_uring-zc-opts'

Merge branch 'tcp-io_uring-zc-opts'

Pavel Begunkov says:

====================
minor tcp io_uring zc optimisations

Patch 1 is a simple cleanup, patch 2 gives removes 2 atomics from the
io_uring zc TCP submission path, which yielded extra 0.5% for my
throughput CPU bound tests based on liburing/examples/send-zerocopy.c
====================

Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

net/ipv4/tcp.c

@@ -1229,13 +1229,11 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	flags = msg->msg_flags;
 
 	if ((flags & MSG_ZEROCOPY) && size) {
-		skb = tcp_write_queue_tail(sk);
-
 		if (msg->msg_ubuf) {
 			uarg = msg->msg_ubuf;
-			net_zcopy_get(uarg);
 			zc = sk->sk_route_caps & NETIF_F_SG;
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			skb = tcp_write_queue_tail(sk);
 			uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
 			if (!uarg) {
 				err = -ENOBUFS;
@@ -1459,7 +1457,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	}
 out_nopush:
-	net_zcopy_put(uarg);
+	/* msg->msg_ubuf is pinned by the caller so we don't take extra refs */
+	if (uarg && !msg->msg_ubuf)
+		net_zcopy_put(uarg);
 	return copied + copied_syn;
 
 do_error:
@@ -1468,7 +1468,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	if (copied + copied_syn)
 		goto out;
 out_err:
-	net_zcopy_put_abort(uarg, true);
+	/* msg->msg_ubuf is pinned by the caller so we don't take extra refs */
+	if (uarg && !msg->msg_ubuf)
+		net_zcopy_put_abort(uarg, true);
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
 	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {