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,
        Linus Torvalds <torvalds@linux-foundation.org>
Cc:     David Howells <dhowells@redhat.com>,
        Chuck Lever <chuck.lever@oracle.com>,
        Boris Pismenny <borisp@nvidia.com>,
        John Fastabend <john.fastabend@gmail.com>,
        Jakub Kicinski <kuba@kernel.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        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
Subject: [PATCH net-next v5 05/14] tls/sw: Use splice_eof() to flush
Date:   Wed,  7 Jun 2023 15:05:50 +0100
Message-ID: <20230607140559.2263470-6-dhowells@redhat.com>
In-Reply-To: <20230607140559.2263470-1-dhowells@redhat.com>
References: <20230607140559.2263470-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Allow splice to end a TLS record after prematurely ending a splice/sendfile
due to getting an EOF condition (->splice_read() returned 0) after splice
had called TLS with a sendmsg() with MSG_MORE set when the user didn't set
MSG_MORE.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wh=V579PDYvkpnTobCLGczbgxpMgGmmhqiTyE34Cpi5Gg@mail.gmail.com/
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.h      |  1 +
 net/tls/tls_main.c |  2 ++
 net/tls/tls_sw.c   | 74 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 77 insertions(+)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index 0672acab2773..4922668fefaa 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -97,6 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx);
 void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
 void tls_sw_strparser_done(struct tls_context *tls_ctx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+void tls_sw_splice_eof(struct socket *sock);
 int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
 			   int offset, size_t size, int flags);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index e02a0d882ed3..82ec5c654f32 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -957,6 +957,7 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG]
 	ops[TLS_BASE][TLS_BASE] = *base;
 
 	ops[TLS_SW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_SW  ][TLS_BASE].splice_eof	= tls_sw_splice_eof;
 	ops[TLS_SW  ][TLS_BASE].sendpage_locked	= tls_sw_sendpage_locked;
 
 	ops[TLS_BASE][TLS_SW  ] = ops[TLS_BASE][TLS_BASE];
@@ -1027,6 +1028,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 
 	prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_SW][TLS_BASE].sendmsg		= tls_sw_sendmsg;
+	prot[TLS_SW][TLS_BASE].splice_eof	= tls_sw_splice_eof;
 	prot[TLS_SW][TLS_BASE].sendpage		= tls_sw_sendpage;
 
 	prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 38acc27a0dd0..a2fb0256ff1c 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1157,6 +1157,80 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	return copied > 0 ? copied : ret;
 }
 
+/*
+ * Handle unexpected EOF during splice without SPLICE_F_MORE set.
+ */
+void tls_sw_splice_eof(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
+	struct tls_rec *rec;
+	struct sk_msg *msg_pl;
+	ssize_t copied = 0;
+	bool retrying = false;
+	int ret = 0;
+	int pending;
+
+	if (!ctx->open_rec)
+		return;
+
+	mutex_lock(&tls_ctx->tx_lock);
+	lock_sock(sk);
+
+retry:
+	rec = ctx->open_rec;
+	if (!rec)
+		goto unlock;
+
+	msg_pl = &rec->msg_plaintext;
+
+	/* Check the BPF advisor and perform transmission. */
+	ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA,
+				  &copied, 0);
+	switch (ret) {
+	case 0:
+	case -EAGAIN:
+		if (retrying)
+			goto unlock;
+		retrying = true;
+		goto retry;
+	case -EINPROGRESS:
+		break;
+	default:
+		goto unlock;
+	}
+
+	/* Wait for pending encryptions to get completed */
+	spin_lock_bh(&ctx->encrypt_compl_lock);
+	ctx->async_notify = true;
+
+	pending = atomic_read(&ctx->encrypt_pending);
+	spin_unlock_bh(&ctx->encrypt_compl_lock);
+	if (pending)
+		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	else
+		reinit_completion(&ctx->async_wait.completion);
+
+	/* There can be no concurrent accesses, since we have no pending
+	 * encrypt operations
+	 */
+	WRITE_ONCE(ctx->async_notify, false);
+
+	if (ctx->async_wait.err)
+		goto unlock;
+
+	/* Transmit if any encryptions have completed */
+	if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+		cancel_delayed_work(&ctx->tx_work.work);
+		tls_tx_records(sk, 0);
+	}
+
+unlock:
+	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
+}
+
 static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 			      int offset, size_t size, int flags)
 {