From:   Pavel Begunkov <asml.silence@gmail.com>
To:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        "David S . Miller" <davem@davemloft.net>,
        Willem de Bruijn <willemb@google.com>,
        Eric Dumazet <edumazet@google.com>,
        David Ahern <dsahern@kernel.org>, Jens Axboe <axboe@kernel.dk>,
        Pavel Begunkov <asml.silence@gmail.com>
Subject: [RFC v2 06/19] ipv4/udp: add support msgdr::msg_ubuf
Date:   Tue, 21 Dec 2021 15:35:28 +0000
Message-Id: <92234ed7fe28f63c475b22c25cdc271adadd640d.1640029579.git.asml.silence@gmail.com>
In-Reply-To: <cover.1640029579.git.asml.silence@gmail.com>
References: <cover.1640029579.git.asml.silence@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Make ipv4/udp to use ubuf_info passed in struct msghdr if it was
specified.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 net/ipv4/ip_output.c | 50 ++++++++++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9bca57ef8b83..f820288092ab 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -953,7 +953,6 @@ static int __ip_append_data(struct sock *sk,
 	struct inet_sock *inet = inet_sk(sk);
 	struct ubuf_info *uarg = NULL;
 	struct sk_buff *skb;
-
 	struct ip_options *opt = cork->opt;
 	int hh_len;
 	int exthdrlen;
@@ -967,6 +966,7 @@ static int __ip_append_data(struct sock *sk,
 	unsigned int wmem_alloc_delta = 0;
 	bool paged, extra_uref = false;
 	u32 tskey = 0;
+	bool zc = false;
 
 	skb = skb_peek_tail(queue);
 
@@ -1001,17 +1001,37 @@ static int __ip_append_data(struct sock *sk,
 	    (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
 		csummode = CHECKSUM_PARTIAL;
 
-	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
-		uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
-		if (!uarg)
-			return -ENOBUFS;
-		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
-		if (rt->dst.dev->features & NETIF_F_SG &&
-		    csummode == CHECKSUM_PARTIAL) {
-			paged = true;
-		} else {
-			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg, &extra_uref);
+	if ((flags & MSG_ZEROCOPY) && length) {
+		struct msghdr *msg = from;
+
+		if (getfrag == ip_generic_getfrag && msg->msg_ubuf) {
+			uarg = msg->msg_ubuf;
+			if (skb_zcopy(skb) && uarg != skb_zcopy(skb))
+				return -EINVAL;
+
+			if (rt->dst.dev->features & NETIF_F_SG &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+			} else {
+				/* Drop uarg if can't zerocopy, callers should
+				 * be able to handle it.
+				 */
+				uarg = NULL;
+			}
+		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			if (!uarg)
+				return -ENOBUFS;
+			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
+			if (rt->dst.dev->features & NETIF_F_SG &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+			} else {
+				uarg->zerocopy = 0;
+				skb_zcopy_set(skb, uarg, &extra_uref);
+			}
 		}
 	}
 
@@ -1172,9 +1192,13 @@ static int __ip_append_data(struct sock *sk,
 				err = -EFAULT;
 				goto error;
 			}
-		} else if (!uarg || !uarg->zerocopy) {
+		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;
 
+			if (skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAGS) {
+				err = -EFAULT;
+				goto error;
+			}
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
-- 
2.34.1