tcp: add support for SO_PEEK_OFF socket option

When reading received messages from a socket with MSG_PEEK, we may want
to read the contents with an offset, like we can do with pread/preadv()
when reading files. Currently, it is not possible to do that.

In this commit, we add support for the SO_PEEK_OFF socket option for TCP,
in a similar way it is done for Unix Domain sockets.

In the iperf3 log examples shown below, we can observe a throughput
improvement of 15-20 % in the direction host->namespace when using the
protocol splicer 'pasta' (https://passt.top).
This is a consistent result.

pasta(1) and passt(1) implement user-mode networking for network
namespaces (containers) and virtual machines by means of a translation
layer between Layer-2 network interface and native Layer-4 sockets
(TCP, UDP, ICMP/ICMPv6 echo).

Received, pending TCP data to the container/guest is kept in kernel
buffers until acknowledged, so the tool routinely needs to fetch new
data from socket, skipping data that was already sent.

At the moment this is implemented using a dummy buffer passed to
recvmsg(). With this change, we don't need a dummy buffer and the
related buffer copy (copy_to_user()) anymore.

passt and pasta are supported in KubeVirt and libvirt/qemu.

jmaloy@freyr:~/passt$ perf record -g ./pasta --config-net -f
SO_PEEK_OFF not supported by kernel.

jmaloy@freyr:~/passt# iperf3 -s
-----------------------------------------------------------
Server listening on 5201 (test #1)
-----------------------------------------------------------
Accepted connection from 192.168.122.1, port 44822
[  5] local 192.168.122.180 port 5201 connected to 192.168.122.1 port 44832
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.00   sec  1.02 GBytes  8.78 Gbits/sec
[  5]   1.00-2.00   sec  1.06 GBytes  9.08 Gbits/sec
[  5]   2.00-3.00   sec  1.07 GBytes  9.15 Gbits/sec
[  5]   3.00-4.00   sec  1.10 GBytes  9.46 Gbits/sec
[  5]   4.00-5.00   sec  1.03 GBytes  8.85 Gbits/sec
[  5]   5.00-6.00   sec  1.10 GBytes  9.44 Gbits/sec
[  5]   6.00-7.00   sec  1.11 GBytes  9.56 Gbits/sec
[  5]   7.00-8.00   sec  1.07 GBytes  9.20 Gbits/sec
[  5]   8.00-9.00   sec   667 MBytes  5.59 Gbits/sec
[  5]   9.00-10.00  sec  1.03 GBytes  8.83 Gbits/sec
[  5]  10.00-10.04  sec  30.1 MBytes  6.36 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-10.04  sec  10.3 GBytes  8.78 Gbits/sec   receiver
-----------------------------------------------------------
Server listening on 5201 (test #2)
-----------------------------------------------------------
^Ciperf3: interrupt - the server has terminated
jmaloy@freyr:~/passt#
logout
[ perf record: Woken up 23 times to write data ]
[ perf record: Captured and wrote 5.696 MB perf.data (35580 samples) ]
jmaloy@freyr:~/passt$

jmaloy@freyr:~/passt$ perf record -g ./pasta --config-net -f
SO_PEEK_OFF supported by kernel.

jmaloy@freyr:~/passt# iperf3 -s
-----------------------------------------------------------
Server listening on 5201 (test #1)
-----------------------------------------------------------
Accepted connection from 192.168.122.1, port 52084
[  5] local 192.168.122.180 port 5201 connected to 192.168.122.1 port 52098
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.00   sec  1.32 GBytes  11.3 Gbits/sec
[  5]   1.00-2.00   sec  1.19 GBytes  10.2 Gbits/sec
[  5]   2.00-3.00   sec  1.26 GBytes  10.8 Gbits/sec
[  5]   3.00-4.00   sec  1.36 GBytes  11.7 Gbits/sec
[  5]   4.00-5.00   sec  1.33 GBytes  11.4 Gbits/sec
[  5]   5.00-6.00   sec  1.21 GBytes  10.4 Gbits/sec
[  5]   6.00-7.00   sec  1.31 GBytes  11.2 Gbits/sec
[  5]   7.00-8.00   sec  1.25 GBytes  10.7 Gbits/sec
[  5]   8.00-9.00   sec  1.33 GBytes  11.5 Gbits/sec
[  5]   9.00-10.00  sec  1.24 GBytes  10.7 Gbits/sec
[  5]  10.00-10.04  sec  56.0 MBytes  12.1 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-10.04  sec  12.9 GBytes  11.0 Gbits/sec  receiver
-----------------------------------------------------------
Server listening on 5201 (test #2)
-----------------------------------------------------------
^Ciperf3: interrupt - the server has terminated
logout
[ perf record: Woken up 20 times to write data ]
[ perf record: Captured and wrote 5.040 MB perf.data (33411 samples) ]
jmaloy@freyr:~/passt$

The perf record confirms this result. Below, we can observe that the
CPU spends significantly less time in the function ____sys_recvmsg()
when we have offset support.

Without offset support:
----------------------
jmaloy@freyr:~/passt$ perf report -q --symbol-filter=do_syscall_64 \
                       -p ____sys_recvmsg -x --stdio -i  perf.data | head -1
46.32%     0.00%  passt.avx2  [kernel.vmlinux]  [k] do_syscall_64  ____sys_recvmsg

With offset support:
----------------------
jmaloy@freyr:~/passt$ perf report -q --symbol-filter=do_syscall_64 \
                       -p ____sys_recvmsg -x --stdio -i  perf.data | head -1
28.12%     0.00%  passt.avx2  [kernel.vmlinux]  [k] do_syscall_64  ____sys_recvmsg

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240409152805.913891-1-jmaloy@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 11 insertions, 6 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 55bd72997b31..a7cfeda28bb2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1072,6 +1072,7 @@ const struct proto_ops inet_stream_ops = {
 #endif
 	.splice_eof	   = inet_splice_eof,
 	.splice_read	   = tcp_splice_read,
+	.set_peek_off      = sk_set_peek_off,
 	.read_sock	   = tcp_read_sock,
 	.read_skb	   = tcp_read_skb,
 	.sendmsg_locked    = tcp_sendmsg_locked,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e1bf468e0d22..f23b97777ea5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1419,8 +1419,6 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 	struct sk_buff *skb;
 	int copied = 0, err = 0;
 
-	/* XXX -- need to support SO_PEEK_OFF */
-
 	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
 		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
@@ -2331,6 +2329,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct sk_buff *skb, *last;
+	u32 peek_offset = 0;
 	u32 urg_hole = 0;
 
 	err = -ENOTCONN;
@@ -2364,7 +2363,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 
 	seq = &tp->copied_seq;
 	if (flags & MSG_PEEK) {
-		peek_seq = tp->copied_seq;
+		peek_offset = max(sk_peek_offset(sk, flags), 0);
+		peek_seq = tp->copied_seq + peek_offset;
 		seq = &peek_seq;
 	}
 
@@ -2467,11 +2467,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		if ((flags & MSG_PEEK) &&
-		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
+		    (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) {
 			net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
 					    current->comm,
 					    task_pid_nr(current));
-			peek_seq = tp->copied_seq;
+			peek_seq = tp->copied_seq + peek_offset;
 		}
 		continue;
 
@@ -2512,7 +2512,10 @@ found_ok_skb:
 		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
-
+		if (flags & MSG_PEEK)
+			sk_peek_offset_fwd(sk, used);
+		else
+			sk_peek_offset_bwd(sk, used);
 		tcp_rcv_space_adjust(sk);
 
 skip_copy:
@@ -3013,6 +3016,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	__skb_queue_purge(&sk->sk_receive_queue);
 	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 	WRITE_ONCE(tp->urg_data, 0);
+	sk_set_peek_off(sk, -1);
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
 	skb_rbtree_purge(&tp->out_of_order_queue);