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:   David Howells <dhowells@redhat.com>
To:     netdev@vger.kernel.org
Cc:     David Howells <dhowells@redhat.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
        David Ahern <dsahern@kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        Jens Axboe <axboe@kernel.dk>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, Chuck Lever <chuck.lever@oracle.com>,
        Boris Pismenny <borisp@nvidia.com>,
        John Fastabend <john.fastabend@gmail.com>
Subject: [PATCH net-next 09/12] tls/sw: Support MSG_SPLICE_PAGES
Date:   Wed, 24 May 2023 16:33:08 +0100
Message-Id: <20230524153311.3625329-10-dhowells@redhat.com>
In-Reply-To: <20230524153311.3625329-1-dhowells@redhat.com>
References: <20230524153311.3625329-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Make TLS's sendmsg() support MSG_SPLICE_PAGES.  This causes pages to be
spliced from the source iterator if possible and copied the data if not.

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

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Chuck Lever <chuck.lever@oracle.com>
cc: Boris Pismenny <borisp@nvidia.com>
cc: John Fastabend <john.fastabend@gmail.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
---
 net/tls/tls_sw.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 635b8bf6b937..0ccef8aa9951 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -929,6 +929,49 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags)
 				   &copied, flags);
 }
 
+static int rls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg,
+				 struct sk_msg *msg_pl, size_t try_to_copy,
+				 ssize_t *copied)
+{
+	struct page *page = NULL, **pages = &page;
+
+	do {
+		ssize_t part;
+		size_t off;
+		bool put = false;
+
+		part = iov_iter_extract_pages(&msg->msg_iter, &pages,
+					      try_to_copy, 1, 0, &off);
+		if (part <= 0)
+			return part ?: -EIO;
+
+		if (!sendpage_ok(page)) {
+			const void *p = kmap_local_page(page);
+			void *q;
+
+			q = page_frag_memdup(NULL, p + off, part,
+					     sk->sk_allocation, ULONG_MAX);
+			kunmap_local(p);
+			if (!q) {
+				iov_iter_revert(&msg->msg_iter, part);
+				return -ENOMEM;
+			}
+			page = virt_to_page(q);
+			off = offset_in_page(q);
+			put = true;
+		}
+
+		sk_msg_page_add(msg_pl, page, part, off);
+		sk_mem_charge(sk, part);
+		if (put)
+			put_page(page);
+		*copied += part;
+		try_to_copy -= part;
+	} while (try_to_copy && !sk_msg_full(msg_pl));
+
+	return 0;
+}
+
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
@@ -1018,6 +1061,17 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			full_record = true;
 		}
 
+		if (try_to_copy && (msg->msg_flags & MSG_SPLICE_PAGES)) {
+			ret = rls_sw_sendmsg_splice(sk, msg, msg_pl,
+						    try_to_copy, &copied);
+			if (ret < 0)
+				goto send_end;
+			tls_ctx->pending_open_record_frags = true;
+			if (full_record || eor || sk_msg_full(msg_pl))
+				goto copied;
+			continue;
+		}
+
 		if (!is_kvec && (full_record || eor) && !async_capable) {
 			u32 first = msg_pl->sg.end;
 
@@ -1080,8 +1134,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		/* Open records defined only if successfully copied, otherwise
 		 * we would trim the sg but not reset the open record frags.
 		 */
-		tls_ctx->pending_open_record_frags = true;
 		copied += try_to_copy;
+copied:
+		tls_ctx->pending_open_record_frags = true;
 		if (full_record || eor) {
 			ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
 						  record_type, &copied,