[PATCH net-next v3 5/7] tcp: allow tls to decrypt directly from the tcp rcv queue

[Jakub Kicinski <kuba@kernel.org>]

Expose TCP rx queue accessor and cleanup, so that TLS can
decrypt directly from the TCP queue. The expectation
is that the caller can access the skb returned from
tcp_recv_skb() and up to inq bytes worth of data (some
of which may be in ->next skbs) and then call
tcp_read_done() when data has been consumed.
The socket lock must be held continuously across
those two operations.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
v3: drop unnecessay tcp_recv_skb() (Paolo)

CC: yoshfuji@linux-ipv6.org
CC: dsahern@kernel.org
---
 include/net/tcp.h |  2 ++
 net/ipv4/tcp.c    | 42 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f9e7c85ea829..b8620be32f8f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -673,6 +673,8 @@ void tcp_get_info(struct sock *, struct tcp_info *);
 int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		  sk_read_actor_t recv_actor);
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
+struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
+void tcp_read_done(struct sock *sk, size_t len);
 
 void tcp_initialize_rcv_mss(struct sock *sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ba2bdc811374..dc7cc3ce6a53 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1635,7 +1635,7 @@ static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
-static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
+struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
 	u32 offset;
@@ -1658,6 +1658,7 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(tcp_recv_skb);
 
 /*
  * This routine provides an alternative to tcp_recvmsg() for routines
@@ -1788,6 +1789,45 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 }
 EXPORT_SYMBOL(tcp_read_skb);
 
+void tcp_read_done(struct sock *sk, size_t len)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 seq = tp->copied_seq;
+	struct sk_buff *skb;
+	size_t left;
+	u32 offset;
+
+	if (sk->sk_state == TCP_LISTEN)
+		return;
+
+	left = len;
+	while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
+		int used;
+
+		used = min_t(size_t, skb->len - offset, left);
+		seq += used;
+		left -= used;
+
+		if (skb->len > offset + used)
+			break;
+
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
+			tcp_eat_recv_skb(sk, skb);
+			++seq;
+			break;
+		}
+		tcp_eat_recv_skb(sk, skb);
+	}
+	WRITE_ONCE(tp->copied_seq, seq);
+
+	tcp_rcv_space_adjust(sk);
+
+	/* Clean up data we have read: This will do ACK frames. */
+	if (left != len)
+		tcp_cleanup_rbuf(sk, len - left);
+}
+EXPORT_SYMBOL(tcp_read_done);
+
 int tcp_peek_len(struct socket *sock)
 {
 	return tcp_inq(sock->sk);
-- 
2.37.1