netdev - [RFC PATCH 03/28] tcp: Support MSG_SPLICE

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230316152618.711970-4-dhowells@redhat.com>
Date:   Thu, 16 Mar 2023 15:25:53 +0000
From:   David Howells <dhowells@...hat.com>
To:     Matthew Wilcox <willy@...radead.org>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>
Cc:     David Howells <dhowells@...hat.com>,
        Al Viro <viro@...iv.linux.org.uk>,
        Christoph Hellwig <hch@...radead.org>,
        Jens Axboe <axboe@...nel.dk>, Jeff Layton <jlayton@...nel.org>,
        Christian Brauner <brauner@...nel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        netdev@...r.kernel.org, linux-fsdevel@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: [RFC PATCH 03/28] tcp: Support MSG_SPLICE_PAGES

Make TCP's sendmsg() support MSG_SPLICE_PAGES.  This causes pages to be
spliced from the source iterator if possible (the iterator must be
ITER_BVEC and the pages must be spliceable).

This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.

Signed-off-by: David Howells <dhowells@...hat.com>
cc: Eric Dumazet <edumazet@...gle.com>
cc: "David S. Miller" <davem@...emloft.net>
cc: Jakub Kicinski <kuba@...nel.org>
cc: Paolo Abeni <pabeni@...hat.com>
cc: Jens Axboe <axboe@...nel.dk>
cc: Matthew Wilcox <willy@...radead.org>
cc: netdev@...r.kernel.org
---
 net/ipv4/tcp.c | 59 +++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 288693981b00..77c0c69208a5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1220,7 +1220,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	int flags, err, copied = 0;
 	int mss_now = 0, size_goal, copied_syn = 0;
 	int process_backlog = 0;
-	bool zc = false;
+	int zc = 0;
 	long timeo;
 
 	flags = msg->msg_flags;
@@ -1231,17 +1231,24 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		if (msg->msg_ubuf) {
 			uarg = msg->msg_ubuf;
 			net_zcopy_get(uarg);
-			zc = sk->sk_route_caps & NETIF_F_SG;
+			if (sk->sk_route_caps & NETIF_F_SG)
+				zc = 1;
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
 			uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
 			if (!uarg) {
 				err = -ENOBUFS;
 				goto out_err;
 			}
-			zc = sk->sk_route_caps & NETIF_F_SG;
-			if (!zc)
+			if (sk->sk_route_caps & NETIF_F_SG)
+				zc = 1;
+			else
 				uarg_to_msgzc(uarg)->zerocopy = 0;
 		}
+	} else if (unlikely(flags & MSG_SPLICE_PAGES) && size) {
+		if (!iov_iter_is_bvec(&msg->msg_iter))
+			return -EINVAL;
+		if (sk->sk_route_caps & NETIF_F_SG)
+			zc = 2;
 	}
 
 	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
@@ -1345,7 +1352,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		if (copy > msg_data_left(msg))
 			copy = msg_data_left(msg);
 
-		if (!zc) {
+		if (zc == 0) {
 			bool merge = true;
 			int i = skb_shinfo(skb)->nr_frags;
 			struct page_frag *pfrag = sk_page_frag(sk);
@@ -1390,7 +1397,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 				page_ref_inc(pfrag->page);
 			}
 			pfrag->offset += copy;
-		} else {
+		} else if (zc == 1)  {
 			/* First append to a fragless skb builds initial
 			 * pure zerocopy skb
 			 */
@@ -1411,6 +1418,46 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			if (err < 0)
 				goto do_error;
 			copy = err;
+		} else if (zc == 2) {
+			/* Splice in data. */
+			const struct bio_vec *bv = msg->msg_iter.bvec;
+			size_t seg = iov_iter_single_seg_count(&msg->msg_iter);
+			size_t off = bv->bv_offset + msg->msg_iter.iov_offset;
+			bool can_coalesce;
+			int i = skb_shinfo(skb)->nr_frags;
+
+			if (copy > seg)
+				copy = seg;
+
+			can_coalesce = skb_can_coalesce(skb, i, bv->bv_page, off);
+			if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
+				tcp_mark_push(tp, skb);
+				goto new_segment;
+			}
+			if (tcp_downgrade_zcopy_pure(sk, skb))
+				goto wait_for_space;
+
+			copy = tcp_wmem_schedule(sk, copy);
+			if (!copy)
+				goto wait_for_space;
+
+			if (can_coalesce) {
+				skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+			} else {
+				get_page(bv->bv_page);
+				skb_fill_page_desc_noacc(skb, i, bv->bv_page, off, copy);
+			}
+			iov_iter_advance(&msg->msg_iter, copy);
+
+			if (!(flags & MSG_NO_SHARED_FRAGS))
+				skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
+
+			skb->len += copy;
+			skb->data_len += copy;
+			skb->truesize += copy;
+			sk_wmem_queued_add(sk, copy);
+			sk_mem_charge(sk, copy);
+
 		}
 
 		if (!copied)