Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Pavel Begunkov <asml.silence@gmail.com>
To:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     "David S . Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        Willem de Bruijn <willemb@google.com>,
        Jens Axboe <axboe@kernel.dk>, kernel-team@fb.com,
        Pavel Begunkov <asml.silence@gmail.com>
Subject: [RFC net-next v3 09/29] ipv4/udp: support zc with managed data
Date:   Tue, 28 Jun 2022 19:56:31 +0100
Message-Id: <1904009c2af0197b922e413254ef2ff2c527f743.1653992701.git.asml.silence@gmail.com>
In-Reply-To: <cover.1653992701.git.asml.silence@gmail.com>
References: <cover.1653992701.git.asml.silence@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Teach ipv4/udp about managed data. Make it recognise and use
msg->msg_ubuf, and also set/propagate SKBFL_MANAGED_FRAG_REFS
down to skb_zerocopy_iter_dgram().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 net/ipv4/ip_output.c | 57 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 43 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 581d1e233260..3fd1bf675598 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1017,18 +1017,35 @@ 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;
-			zc = 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) {
+			if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb))
+				return -EINVAL;
+
+			/* Leave uarg NULL if can't zerocopy, callers should
+			 * be able to handle it.
+			 */
+			if ((rt->dst.dev->features & NETIF_F_SG) &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+				uarg = msg->msg_ubuf;
+			}
+		} 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);
+			}
 		}
 	}
 
@@ -1192,13 +1209,14 @@ 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;
 
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
 
+			skb_zcopy_downgrade_managed(skb);
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
 				err = -EMSGSIZE;
@@ -1223,7 +1241,18 @@ static int __ip_append_data(struct sock *sk,
 			skb->truesize += copy;
 			wmem_alloc_delta += copy;
 		} else {
-			err = skb_zerocopy_iter_dgram(skb, from, copy);
+			struct msghdr *msg = from;
+
+			if (!skb_shinfo(skb)->nr_frags) {
+				if (msg->msg_managed_data)
+					skb_shinfo(skb)->flags |= SKBFL_MANAGED_FRAG_REFS;
+			} else {
+				/* appending, don't mix managed and unmanaged */
+				if (!msg->msg_managed_data)
+					skb_zcopy_downgrade_managed(skb);
+			}
+
+			err = skb_zerocopy_iter_dgram(skb, msg, copy);
 			if (err < 0)
 				goto error;
 		}
-- 
2.36.1