[RFC v2] tcp: add support for read with offset when using MSG_PEEK

[Jon Maloy <jmaloy@redhat.com>]

When reading received messages with MSG_PEEK, we sometines have to read
the leading bytes of the stream several times, only to reach the bytes
we really want. This is clearly non-optimal.

What we would want is something similar to pread/preadv(), but working
even for tcp sockets. At the same time, we obviously don't want to add
any new arguments to the recv/recvmsg() calls.

In this commit, we allow the user to set iovec.iov_base in the first
vector entry to NULL. This tells the socket to skip the first entry,
hence making the iov_len field of that entry indicate the offset value.
This way, there is no need to add any new arguments.

This change is simple and non-intrusive, and should be safe addition to
the socket API. We have measured it to give a throughput improvement of
8-10 % for the protocol splicer 'passst', which is used in KubeVirt
containers.

Signed-off-by: Jon Maloy <jmaloy@redhat.com>

works with original msghdr

Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
 net/ipv4/tcp.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 33f559f491c8..1d89337e89b6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2428,6 +2428,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	struct tcp_sock *tp = tcp_sk(sk);
 	int copied = 0;
 	u32 peek_seq;
+	u32 peek_offset;
 	u32 *seq;
 	unsigned long used;
 	int err;
@@ -2435,7 +2436,6 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	long timeo;
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
-
 	err = -ENOTCONN;
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
@@ -2469,6 +2469,14 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_PEEK) {
 		peek_seq = tp->copied_seq;
 		seq = &peek_seq;
+		if (msg->msg_iter.iov[0].iov_base == NULL) {
+			peek_offset = msg->msg_iter.iov[0].iov_len;
+			msg->msg_iter.iov = &msg->msg_iter.iov[1];
+			msg->msg_iter.nr_segs -= 1;
+			msg->msg_iter.count -= peek_offset;
+			len -= peek_offset;
+			*seq += peek_offset;
+		}
 	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
-- 
@@ -2428,6 +2428,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	struct tcp_sock *tp = tcp_sk(sk);
 	int copied = 0;
 	u32 peek_seq;
+	u32 peek_offset;
 	u32 *seq;
 	unsigned long used;
 	int err;
@@ -2435,7 +2436,6 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	long timeo;
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
-
 	err = -ENOTCONN;
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
@@ -2469,6 +2469,14 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_PEEK) {
 		peek_seq = tp->copied_seq;
 		seq = &peek_seq;
+		if (msg->msg_iter.iov[0].iov_base == NULL) {
+			peek_offset = msg->msg_iter.iov[0].iov_len;
+			msg->msg_iter.iov = &msg->msg_iter.iov[1];
+			msg->msg_iter.nr_segs -= 1;
+			msg->msg_iter.count -= peek_offset;
+			len -= peek_offset;
+			*seq += peek_offset;
+		}
 	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
-- 
2.39.0