[PATCH net-next 0/5] mptcp: Compatibility with common msg flags

[PATCH net-next 0/5] mptcp: Compatibility with common msg flags

[Mat Martineau]

These patches from the MPTCP tree handle some of the msg flags that are
typically used with TCP, to make it easier to adapt userspace programs
for use with MPTCP.

Patches 1, 2, and 4 add support for MSG_ERRQUEUE (no-op for now),
MSG_TRUNC, and MSG_PEEK on the receive side.

Patch 3 ignores unsupported msg flags for send and receive.

Patch 5 adds a selftest for MSG_PEEK.


Paolo Abeni (3):
  mptcp: implement dummy MSG_ERRQUEUE support
  mptcp: implement MSG_TRUNC support
  mptcp: ignore unsupported msg flags

Yonglong Li (2):
  mptcp: add MSG_PEEK support
  selftests: mptcp: add a test case for MSG_PEEK

 net/mptcp/protocol.c                          | 49 ++++++++++++-------
 .../selftests/net/mptcp/mptcp_connect.c       | 48 +++++++++++++++++-
 .../selftests/net/mptcp/mptcp_connect.sh      | 29 ++++++++---
 3 files changed, 99 insertions(+), 27 deletions(-)


base-commit: cad4162a90aeff737a16c0286987f51e927f003a
-- 
2.31.1

[PATCH net-next 1/5] mptcp: implement dummy MSG_ERRQUEUE support

[Mat Martineau]

From: Paolo Abeni <pabeni@redhat.com>

mptcp_recvmsg() currently silently ignores MSG_ERRQUEUE, returning
input data instead of error cmsg.

This change provides a dummy implementation for MSG_ERRQUEUE - always
returns no data. That is consistent with the current lack of a suitable
IP_RECVERR setsockopt() support.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/protocol.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c14ac2975736..1d5f23bd640c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1945,6 +1945,10 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int target;
 	long timeo;
 
+	/* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
 	if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT))
 		return -EOPNOTSUPP;
 
-- 
2.31.1

[PATCH net-next 2/5] mptcp: implement MSG_TRUNC support

[Mat Martineau]

From: Paolo Abeni <pabeni@redhat.com>

The mentioned flag is currently silenlty ignored. This
change implements the TCP-like behaviour, dropping the
pending data up to the specified length.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Sigend-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/protocol.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1d5f23bd640c..ae08c563c712 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1739,7 +1739,7 @@ static void mptcp_wait_data(struct sock *sk, long *timeo)
 
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
-				size_t len)
+				size_t len, int flags)
 {
 	struct sk_buff *skb;
 	int copied = 0;
@@ -1750,11 +1750,13 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 		u32 count = min_t(size_t, len - copied, data_len);
 		int err;
 
-		err = skb_copy_datagram_msg(skb, offset, msg, count);
-		if (unlikely(err < 0)) {
-			if (!copied)
-				return err;
-			break;
+		if (!(flags & MSG_TRUNC)) {
+			err = skb_copy_datagram_msg(skb, offset, msg, count);
+			if (unlikely(err < 0)) {
+				if (!copied)
+					return err;
+				break;
+			}
 		}
 
 		copied += count;
@@ -1966,7 +1968,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	while (copied < len) {
 		int bytes_read;
 
-		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied);
+		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
-- 
2.31.1

[PATCH net-next 3/5] mptcp: ignore unsupported msg flags

[Mat Martineau]

From: Paolo Abeni <pabeni@redhat.com>

Currently mptcp_sendmsg() fails with EOPNOTSUPP if the
user-space provides some unsupported flag. That is unexpected
and may foul existing applications migrated to MPTCP, which
expect a different behavior.

Change the mentioned function to silently ignore the unsupported
flags except MSG_FASTOPEN. This is the only flags currently not
supported by MPTCP with user-space visible side-effects.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/162
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/protocol.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ae08c563c712..a996dd5bb0c2 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1614,9 +1614,13 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int ret = 0;
 	long timeo;
 
-	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
+	/* we don't support FASTOPEN yet */
+	if (msg->msg_flags & MSG_FASTOPEN)
 		return -EOPNOTSUPP;
 
+	/* silently ignore everything else */
+	msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL;
+
 	mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, min_t(size_t, 1 << 20, len)));
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
@@ -1951,9 +1955,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
 
-	if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT))
-		return -EOPNOTSUPP;
-
 	mptcp_lock_sock(sk, __mptcp_splice_receive_queue(sk));
 	if (unlikely(sk->sk_state == TCP_LISTEN)) {
 		copied = -ENOTCONN;
-- 
2.31.1

[PATCH net-next 4/5] mptcp: add MSG_PEEK support

[Mat Martineau]

From: Yonglong Li <liyonglong@chinatelecom.cn>

This patch adds support for MSG_PEEK flag. Packets are not removed
from the receive_queue if MSG_PEEK set in recv() system call.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Yonglong Li <liyonglong@chinatelecom.cn>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/protocol.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a996dd5bb0c2..8bf21996734d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1745,10 +1745,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
 				size_t len, int flags)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb, *tmp;
 	int copied = 0;
 
-	while ((skb = skb_peek(&msk->receive_queue)) != NULL) {
+	skb_queue_walk_safe(&msk->receive_queue, skb, tmp) {
 		u32 offset = MPTCP_SKB_CB(skb)->offset;
 		u32 data_len = skb->len - offset;
 		u32 count = min_t(size_t, len - copied, data_len);
@@ -1766,15 +1766,18 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 		copied += count;
 
 		if (count < data_len) {
-			MPTCP_SKB_CB(skb)->offset += count;
+			if (!(flags & MSG_PEEK))
+				MPTCP_SKB_CB(skb)->offset += count;
 			break;
 		}
 
-		/* we will bulk release the skb memory later */
-		skb->destructor = NULL;
-		msk->rmem_released += skb->truesize;
-		__skb_unlink(skb, &msk->receive_queue);
-		__kfree_skb(skb);
+		if (!(flags & MSG_PEEK)) {
+			/* we will bulk release the skb memory later */
+			skb->destructor = NULL;
+			msk->rmem_released += skb->truesize;
+			__skb_unlink(skb, &msk->receive_queue);
+			__kfree_skb(skb);
+		}
 
 		if (copied >= len)
 			break;
@@ -2053,7 +2056,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
 		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
 		 skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
-	mptcp_rcv_space_adjust(msk, copied);
+	if (!(flags & MSG_PEEK))
+		mptcp_rcv_space_adjust(msk, copied);
 
 	release_sock(sk);
 	return copied;
-- 
2.31.1

[PATCH net-next 5/5] selftests: mptcp: add a test case for MSG_PEEK

[Mat Martineau]

From: Yonglong Li <liyonglong@chinatelecom.cn>

Extend mptcp_connect tool with MSG_PEEK support and add a test case in
mptcp_connect.sh that checks the data received from/after recv() with
MSG_PEEK.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Yonglong Li <liyonglong@chinatelecom.cn>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 .../selftests/net/mptcp/mptcp_connect.c       | 48 ++++++++++++++++++-
 .../selftests/net/mptcp/mptcp_connect.sh      | 29 ++++++++---
 2 files changed, 69 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 2f207cf33661..d88e1fdfb147 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -45,7 +45,14 @@ enum cfg_mode {
 	CFG_MODE_SENDFILE,
 };
 
+enum cfg_peek {
+	CFG_NONE_PEEK,
+	CFG_WITH_PEEK,
+	CFG_AFTER_PEEK,
+};
+
 static enum cfg_mode cfg_mode = CFG_MODE_POLL;
+static enum cfg_peek cfg_peek = CFG_NONE_PEEK;
 static const char *cfg_host;
 static const char *cfg_port	= "12000";
 static int cfg_sock_proto	= IPPROTO_MPTCP;
@@ -73,6 +80,8 @@ static void die_usage(void)
 	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
+	fprintf(stderr,
+		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
 	exit(1);
 }
 
@@ -331,6 +340,8 @@ static size_t do_write(const int fd, char *buf, const size_t len)
 
 static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 {
+	int ret = 0;
+	char tmp[16384];
 	size_t cap = rand();
 
 	cap &= 0xffff;
@@ -340,7 +351,17 @@ static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 	else if (cap > len)
 		cap = len;
 
-	return read(fd, buf, cap);
+	if (cfg_peek == CFG_WITH_PEEK) {
+		ret = recv(fd, buf, cap, MSG_PEEK);
+		ret = (ret < 0) ? ret : read(fd, tmp, ret);
+	} else if (cfg_peek == CFG_AFTER_PEEK) {
+		ret = recv(fd, buf, cap, MSG_PEEK);
+		ret = (ret < 0) ? ret : read(fd, buf, cap);
+	} else {
+		ret = read(fd, buf, cap);
+	}
+
+	return ret;
 }
 
 static void set_nonblock(int fd)
@@ -819,6 +840,26 @@ int parse_mode(const char *mode)
 	return 0;
 }
 
+int parse_peek(const char *mode)
+{
+	if (!strcasecmp(mode, "saveWithPeek"))
+		return CFG_WITH_PEEK;
+	if (!strcasecmp(mode, "saveAfterPeek"))
+		return CFG_AFTER_PEEK;
+
+	fprintf(stderr, "Unknown: %s\n", mode);
+	fprintf(stderr, "Supported MSG_PEEK mode are:\n");
+	fprintf(stderr,
+		"\t\t\"saveWithPeek\" - recv data with flags 'MSG_PEEK' and save the peek data into file\n");
+	fprintf(stderr,
+		"\t\t\"saveAfterPeek\" - read and save data into file after recv with flags 'MSG_PEEK'\n");
+
+	die_usage();
+
+	/* silence compiler warning */
+	return 0;
+}
+
 static int parse_int(const char *size)
 {
 	unsigned long s;
@@ -846,7 +887,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -899,6 +940,9 @@ static void parse_opts(int argc, char **argv)
 		case 'M':
 			cfg_mark = strtol(optarg, NULL, 0);
 			break;
+		case 'P':
+			cfg_peek = parse_peek(optarg);
+			break;
 		}
 	}
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 385cdc98aed8..9236609731b1 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -375,7 +375,7 @@ do_transfer()
 	local srv_proto="$4"
 	local connect_addr="$5"
 	local local_addr="$6"
-	local extra_args=""
+	local extra_args="$7"
 
 	local port
 	port=$((10000+$TEST_COUNT))
@@ -394,9 +394,9 @@ do_transfer()
 	fi
 
 	if [ -n "$extra_args" ] && $options_log; then
-		options_log=false
 		echo "INFO: extra options: $extra_args"
 	fi
+	options_log=false
 
 	:> "$cout"
 	:> "$sout"
@@ -589,6 +589,7 @@ run_tests_lo()
 	local connector_ns="$2"
 	local connect_addr="$3"
 	local loopback="$4"
+	local extra_args="$5"
 	local lret=0
 
 	# skip if test programs are running inside same netns for subsequent runs.
@@ -608,7 +609,8 @@ run_tests_lo()
 		local_addr="0.0.0.0"
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${local_addr}
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
@@ -622,14 +624,16 @@ run_tests_lo()
 		fi
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr}
+	do_transfer ${listener_ns} ${connector_ns} MPTCP TCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		return 1
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr}
+	do_transfer ${listener_ns} ${connector_ns} TCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
@@ -637,7 +641,8 @@ run_tests_lo()
 	fi
 
 	if [ $do_tcp -gt 1 ] ;then
-		do_transfer ${listener_ns} ${connector_ns} TCP TCP ${connect_addr} ${local_addr}
+		do_transfer ${listener_ns} ${connector_ns} TCP TCP \
+			    ${connect_addr} ${local_addr} "${extra_args}"
 		lret=$?
 		if [ $lret -ne 0 ]; then
 			ret=$lret
@@ -653,6 +658,15 @@ run_tests()
 	run_tests_lo $1 $2 $3 0
 }
 
+run_tests_peekmode()
+{
+	local peekmode="$1"
+
+	echo "INFO: with peek mode: ${peekmode}"
+	run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}"
+	run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}"
+}
+
 make_file "$cin" "client"
 make_file "$sin" "server"
 
@@ -732,6 +746,9 @@ for sender in $ns1 $ns2 $ns3 $ns4;do
 	run_tests "$ns4" $sender dead:beef:3::1
 done
 
+run_tests_peekmode "saveWithPeek"
+run_tests_peekmode "saveAfterPeek"
+
 time_end=$(date +%s)
 time_run=$((time_end-time_start))
 
-- 
2.31.1

Re: [PATCH net-next 0/5] mptcp: Compatibility with common msg flags

[patchwork-bot+netdevbpf]

Hello:

This series was applied to netdev/net-next.git (refs/heads/master):

On Fri, 23 Apr 2021 11:17:04 -0700 you wrote:
> These patches from the MPTCP tree handle some of the msg flags that are
> typically used with TCP, to make it easier to adapt userspace programs
> for use with MPTCP.
> 
> Patches 1, 2, and 4 add support for MSG_ERRQUEUE (no-op for now),
> MSG_TRUNC, and MSG_PEEK on the receive side.
> 
> [...]

Here is the summary with links:
  - [net-next,1/5] mptcp: implement dummy MSG_ERRQUEUE support
    https://git.kernel.org/netdev/net-next/c/cb9d80f4940e
  - [net-next,2/5] mptcp: implement MSG_TRUNC support
    https://git.kernel.org/netdev/net-next/c/d976092ce1b0
  - [net-next,3/5] mptcp: ignore unsupported msg flags
    https://git.kernel.org/netdev/net-next/c/987858e5d026
  - [net-next,4/5] mptcp: add MSG_PEEK support
    https://git.kernel.org/netdev/net-next/c/ca4fb892579f
  - [net-next,5/5] selftests: mptcp: add a test case for MSG_PEEK
    https://git.kernel.org/netdev/net-next/c/df8aee6d6fa5

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html