[PATCH 6.6.y 0/3] Backport of "mptcp: fix full TCP keep-alive support"

[PATCH 6.6.y 0/3] Backport of "mptcp: fix full TCP keep-alive support"

[Matthieu Baerts (NGI0)]

It looks like the patch "mptcp: fix full TCP keep-alive support" has
been backported up to v6.8 recently (thanks!), but not before due to
conflicts.

I had to adapt a bit the code not to backport new features, but the 
modifications were simple, and isolated from the rest. MPTCP sockopt 
tests have been executed, and no issues have been reported.

Matthieu Baerts (NGI0) (1):
  mptcp: fix full TCP keep-alive support

Paolo Abeni (2):
  mptcp: avoid some duplicate code in socket option handling
  mptcp: cleanup SOL_TCP handling

 net/mptcp/protocol.h |   3 ++
 net/mptcp/sockopt.c  | 123 +++++++++++++++++++++++++++++--------------
 2 files changed, 87 insertions(+), 39 deletions(-)

-- 
2.43.0

[PATCH 6.6.y 1/3] mptcp: avoid some duplicate code in socket option handling

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

commit a74762675f700a5473ebe54a671a0788a5b23cc9 upstream.

The mptcp_get_int_option() helper is needless open-coded in a
couple of places, replace the duplicate code with the helper
call.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stable-dep-of: bd11dc4fb969 ("mptcp: fix full TCP keep-alive support")
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/sockopt.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 1afa8245f27c..f29949efd7a3 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -626,13 +626,11 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
-	int val;
+	int val, ret;
 
-	if (optlen < sizeof(int))
-		return -EINVAL;
-
-	if (copy_from_sockptr(&val, optval, sizeof(val)))
-		return -EFAULT;
+	ret = mptcp_get_int_option(msk, optval, optlen, &val);
+	if (ret)
+		return ret;
 
 	lock_sock(sk);
 	sockopt_seq_inc(msk);
@@ -656,13 +654,11 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
-	int val;
+	int val, ret;
 
-	if (optlen < sizeof(int))
-		return -EINVAL;
-
-	if (copy_from_sockptr(&val, optval, sizeof(val)))
-		return -EFAULT;
+	ret = mptcp_get_int_option(msk, optval, optlen, &val);
+	if (ret)
+		return ret;
 
 	lock_sock(sk);
 	sockopt_seq_inc(msk);
-- 
2.43.0

[PATCH 6.6.y 2/3] mptcp: cleanup SOL_TCP handling

[Matthieu Baerts (NGI0)]

From: Paolo Abeni <pabeni@redhat.com>

commit 7f71a337b5152ea0e7bef408d1af53778a919316 upstream.

Most TCP-level socket options get an integer from user space, and
set the corresponding field under the msk-level socket lock.

Reduce the code duplication moving such operations in the common code.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stable-dep-of: bd11dc4fb969 ("mptcp: fix full TCP keep-alive support")
[ Without TCP_NOTSENT_LOWAT support, as it is not in this version, see
  commit 29b5e5ef8739 ("mptcp: implement TCP_NOTSENT_LOWAT support") ]
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/sockopt.c | 61 +++++++++++++++++++--------------------------
 1 file changed, 26 insertions(+), 35 deletions(-)

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index f29949efd7a3..e33d721ed37e 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -621,18 +621,11 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	return ret;
 }
 
-static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval,
-					 unsigned int optlen)
+static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
-	int val, ret;
 
-	ret = mptcp_get_int_option(msk, optval, optlen, &val);
-	if (ret)
-		return ret;
-
-	lock_sock(sk);
 	sockopt_seq_inc(msk);
 	msk->cork = !!val;
 	mptcp_for_each_subflow(msk, subflow) {
@@ -644,23 +637,15 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva
 	}
 	if (!val)
 		mptcp_check_and_set_pending(sk);
-	release_sock(sk);
 
 	return 0;
 }
 
-static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval,
-					    unsigned int optlen)
+static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val)
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
-	int val, ret;
 
-	ret = mptcp_get_int_option(msk, optval, optlen, &val);
-	if (ret)
-		return ret;
-
-	lock_sock(sk);
 	sockopt_seq_inc(msk);
 	msk->nodelay = !!val;
 	mptcp_for_each_subflow(msk, subflow) {
@@ -672,8 +657,6 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op
 	}
 	if (val)
 		mptcp_check_and_set_pending(sk);
-	release_sock(sk);
-
 	return 0;
 }
 
@@ -786,25 +769,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 	int ret, val;
 
 	switch (optname) {
-	case TCP_INQ:
-		ret = mptcp_get_int_option(msk, optval, optlen, &val);
-		if (ret)
-			return ret;
-		if (val < 0 || val > 1)
-			return -EINVAL;
-
-		lock_sock(sk);
-		msk->recvmsg_inq = !!val;
-		release_sock(sk);
-		return 0;
 	case TCP_ULP:
 		return -EOPNOTSUPP;
 	case TCP_CONGESTION:
 		return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
-	case TCP_CORK:
-		return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen);
-	case TCP_NODELAY:
-		return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen);
 	case TCP_DEFER_ACCEPT:
 		/* See tcp.c: TCP_DEFER_ACCEPT does not fail */
 		mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen);
@@ -817,7 +785,30 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 						      optval, optlen);
 	}
 
-	return -EOPNOTSUPP;
+	ret = mptcp_get_int_option(msk, optval, optlen, &val);
+	if (ret)
+		return ret;
+
+	lock_sock(sk);
+	switch (optname) {
+	case TCP_INQ:
+		if (val < 0 || val > 1)
+			ret = -EINVAL;
+		else
+			msk->recvmsg_inq = !!val;
+		break;
+	case TCP_CORK:
+		ret = __mptcp_setsockopt_sol_tcp_cork(msk, val);
+		break;
+	case TCP_NODELAY:
+		ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
+		break;
+	default:
+		ret = -ENOPROTOOPT;
+	}
+
+	release_sock(sk);
+	return ret;
 }
 
 int mptcp_setsockopt(struct sock *sk, int level, int optname,
-- 
2.43.0

[PATCH 6.6.y 3/3] mptcp: fix full TCP keep-alive support

[Matthieu Baerts (NGI0)]

commit bd11dc4fb969ec148e50cd87f88a78246dbc4d0b upstream.

SO_KEEPALIVE support has been added a while ago, as part of a series
"adding SOL_SOCKET" support. To have a full control of this keep-alive
feature, it is important to also support TCP_KEEP* socket options at the
SOL_TCP level.

Supporting them on the setsockopt() part is easy, it is just a matter of
remembering each value in the MPTCP sock structure, and calling
tcp_sock_set_keep*() helpers on each subflow. If the value is not
modified (0), calling these helpers will not do anything. For the
getsockopt() part, the corresponding value from the MPTCP sock structure
or the default one is simply returned. All of this is very similar to
other TCP_* socket options supported by MPTCP.

It looks important for kernels supporting SO_KEEPALIVE, to also support
TCP_KEEP* options as well: some apps seem to (wrongly) consider that if
the former is supported, the latter ones will be supported as well. But
also, not having this simple and isolated change is preventing MPTCP
support in some apps, and libraries like GoLang [1]. This is why this
patch is seen as a fix.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/383
Fixes: 1b3e7ede1365 ("mptcp: setsockopt: handle SO_KEEPALIVE and SO_PRIORITY")
Link: https://github.com/golang/go/issues/56539 [1]
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20240514011335.176158-3-martineau@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[ conflicts in the same context, because commit 29b5e5ef8739 ("mptcp:
  implement TCP_NOTSENT_LOWAT support") is not in this version ]
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/protocol.h |  3 +++
 net/mptcp/sockopt.c  | 58 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index cf30b0b1dc7c..93ba48f4ae38 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -303,6 +303,9 @@ struct mptcp_sock {
 			in_accept_queue:1,
 			free_first:1,
 			rcvspace_init:1;
+	int		keepalive_cnt;
+	int		keepalive_idle;
+	int		keepalive_intvl;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index e33d721ed37e..cc04b5e29dd3 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -621,6 +621,31 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	return ret;
 }
 
+static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk, int max,
+				      int (*set_val)(struct sock *, int),
+				      int *msk_val, int val)
+{
+	struct mptcp_subflow_context *subflow;
+	int err = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int ret;
+
+		lock_sock(ssk);
+		ret = set_val(ssk, val);
+		err = err ? : ret;
+		release_sock(ssk);
+	}
+
+	if (!err) {
+		*msk_val = val;
+		sockopt_seq_inc(msk);
+	}
+
+	return err;
+}
+
 static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
 {
 	struct mptcp_subflow_context *subflow;
@@ -803,6 +828,22 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 	case TCP_NODELAY:
 		ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
 		break;
+	case TCP_KEEPIDLE:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPIDLE,
+						 &tcp_sock_set_keepidle_locked,
+						 &msk->keepalive_idle, val);
+		break;
+	case TCP_KEEPINTVL:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPINTVL,
+						 &tcp_sock_set_keepintvl,
+						 &msk->keepalive_intvl, val);
+		break;
+	case TCP_KEEPCNT:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPCNT,
+						 &tcp_sock_set_keepcnt,
+						 &msk->keepalive_cnt,
+						 val);
+		break;
 	default:
 		ret = -ENOPROTOOPT;
 	}
@@ -1303,6 +1344,8 @@ static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
 static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 				    char __user *optval, int __user *optlen)
 {
+	struct sock *sk = (void *)msk;
+
 	switch (optname) {
 	case TCP_ULP:
 	case TCP_CONGESTION:
@@ -1321,6 +1364,18 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 		return mptcp_put_int_option(msk, optval, optlen, msk->cork);
 	case TCP_NODELAY:
 		return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
+	case TCP_KEEPIDLE:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_idle ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_time) / HZ);
+	case TCP_KEEPINTVL:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_intvl ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_intvl) / HZ);
+	case TCP_KEEPCNT:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_cnt ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes));
 	}
 	return -EOPNOTSUPP;
 }
@@ -1430,6 +1485,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
 	__tcp_sock_set_cork(ssk, !!msk->cork);
 	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
+	tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle);
+	tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl);
+	tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt);
 
 	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
-- 
2.43.0

Re: [PATCH 6.6.y 0/3] Backport of "mptcp: fix full TCP keep-alive support"

[Greg KH]

On Wed, May 29, 2024 at 11:58:18AM +0200, Matthieu Baerts (NGI0) wrote:
> It looks like the patch "mptcp: fix full TCP keep-alive support" has
> been backported up to v6.8 recently (thanks!), but not before due to
> conflicts.
> 
> I had to adapt a bit the code not to backport new features, but the 
> modifications were simple, and isolated from the rest. MPTCP sockopt 
> tests have been executed, and no issues have been reported.
> 
> Matthieu Baerts (NGI0) (1):
>   mptcp: fix full TCP keep-alive support
> 
> Paolo Abeni (2):
>   mptcp: avoid some duplicate code in socket option handling
>   mptcp: cleanup SOL_TCP handling
> 
>  net/mptcp/protocol.h |   3 ++
>  net/mptcp/sockopt.c  | 123 +++++++++++++++++++++++++++++--------------
>  2 files changed, 87 insertions(+), 39 deletions(-)
> 
> -- 
> 2.43.0
> 
> 

All backports now queued up, thanks so much for them!

greg k-h