[PATCH net 0/4] MPTCP fixes

[PATCH net 0/4] MPTCP fixes

[Mat Martineau]

Here are a few fixes for the -net tree.

Patch 1 fixes an attempt to access a tcp-specific field that does not
exist in mptcp sockets.

Patches 2 and 3 remove warning/error log output that could be flooded.

Patch 4 performs more validation on address advertisement echo packets
to improve RFC 8684 compliance.

Davide Caratti (1):
  mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer

Paolo Abeni (3):
  mptcp: avoid OOB access in setsockopt()
  mptcp: drop unconditional pr_warn on bad opt
  mptcp: avoid error message on infinite mapping

 net/mptcp/options.c    |  3 +--
 net/mptcp/pm_netlink.c |  8 ++++----
 net/mptcp/protocol.c   | 14 +++++++++++---
 net/mptcp/protocol.h   |  3 ++-
 net/mptcp/sockopt.c    |  4 ++--
 net/mptcp/subflow.c    |  1 -
 6 files changed, 20 insertions(+), 13 deletions(-)


base-commit: 8c42a49738f16af0061f9ae5c2f5a955f268d9e3
-- 
2.31.1

[PATCH net 1/4] mptcp: avoid OOB access in setsockopt()

[Mat Martineau]

From: Paolo Abeni <pabeni@redhat.com>

We can't use tcp_set_congestion_control() on an mptcp socket, as
such function can end-up accessing a tcp-specific field -
prior_ssthresh - causing an OOB access.

To allow propagating the correct ca algo on subflow, cache the ca
name at initialization time.

Additionally avoid overriding the user-selected CA (if any) at
clone time.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/182
Fixes: aa1fbd94e5c7 ("mptcp: sockopt: add TCP_CONGESTION and TCP_INFO")
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/protocol.c | 14 +++++++++++---
 net/mptcp/protocol.h |  1 +
 net/mptcp/sockopt.c  |  4 ++--
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2d21a4793d9d..2bc199549a88 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2424,13 +2424,12 @@ static int __mptcp_init_sock(struct sock *sk)
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
 	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
 
-	tcp_assign_congestion_control(sk);
-
 	return 0;
 }
 
 static int mptcp_init_sock(struct sock *sk)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
 	int ret;
 
@@ -2448,6 +2447,16 @@ static int mptcp_init_sock(struct sock *sk)
 	if (ret)
 		return ret;
 
+	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
+	 * propagate the correct value
+	 */
+	tcp_assign_congestion_control(sk);
+	strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);
+
+	/* no need to keep a reference to the ops, the name will suffice */
+	tcp_cleanup_congestion_control(sk);
+	icsk->icsk_ca_ops = NULL;
+
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
 	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
@@ -2622,7 +2631,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sk_stream_kill_queues(sk);
 	xfrm_sk_free_policy(sk);
 
-	tcp_cleanup_congestion_control(sk);
 	sk_refcnt_debug_release(sk);
 	mptcp_dispose_initial_subflow(msk);
 	sock_put(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index edc0128730df..165c8b40b384 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -258,6 +258,7 @@ struct mptcp_sock {
 	} rcvq_space;
 
 	u32 setsockopt_seq;
+	char		ca_name[TCP_CA_NAME_MAX];
 };
 
 #define mptcp_lock_sock(___sk, cb) do {					\
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 00d941b66c1e..a79798189599 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -547,7 +547,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	}
 
 	if (ret == 0)
-		tcp_set_congestion_control(sk, name, false, cap_net_admin);
+		strcpy(msk->ca_name, name);
 
 	release_sock(sk);
 	return ret;
@@ -705,7 +705,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG));
 
 	if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
-		tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true);
+		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
 }
 
 static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
-- 
2.31.1

[PATCH net 2/4] mptcp: drop unconditional pr_warn on bad opt

[Mat Martineau]

From: Paolo Abeni <pabeni@redhat.com>

This is a left-over of early day. A malicious peer can flood
the kernel logs with useless messages, just drop it.

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/options.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 99fc21406168..71c535f4e1ef 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -130,7 +130,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
 			pr_debug("MP_JOIN hmac");
 		} else {
-			pr_warn("MP_JOIN bad option size");
 			mp_opt->mp_join = 0;
 		}
 		break;
-- 
2.31.1

[PATCH net 3/4] mptcp: avoid error message on infinite mapping

[Mat Martineau]

From: Paolo Abeni <pabeni@redhat.com>

Another left-over. Avoid flooding dmesg with useless text,
we already have a MIB for that event.

Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/subflow.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a5ede357cfbc..bde6be77ea73 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -867,7 +867,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 
 	data_len = mpext->data_len;
 	if (data_len == 0) {
-		pr_err("Infinite mapping not handled");
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
 		return MAPPING_INVALID;
 	}
-- 
2.31.1

[PATCH net 4/4] mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer

[Mat Martineau]

From: Davide Caratti <dcaratti@redhat.com>

when Linux receives an echo-ed ADD_ADDR, it checks the IP address against
the list of "announced" addresses. In case of a positive match, the timer
that handles retransmissions is stopped regardless of the 'Address Id' in
the received packet: this behaviour does not comply with RFC8684 3.4.1.

Fix it by validating the 'Address Id' in received echo-ed ADD_ADDRs.
Tested using packetdrill, with the following captured output:

 unpatched kernel:

 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0xfd2e62517888fe29,mptcp dss ack 3007449509], length 0
 In  <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 1 1.2.3.4,mptcp dss ack 3013740213], length 0
 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0xfd2e62517888fe29,mptcp dss ack 3007449509], length 0
 In  <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 90 198.51.100.2,mptcp dss ack 3013740213], length 0
        ^^^ retransmission is stopped here, but 'Address Id' is 90

 patched kernel:

 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0x1cf372d59e05f4b8,mptcp dss ack 3007449509], length 0
 In  <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 1 1.2.3.4,mptcp dss ack 1672384568], length 0
 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0x1cf372d59e05f4b8,mptcp dss ack 3007449509], length 0
 In  <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 90 198.51.100.2,mptcp dss ack 1672384568], length 0
 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0x1cf372d59e05f4b8,mptcp dss ack 3007449509], length 0
 In  <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 1 198.51.100.2,mptcp dss ack 1672384568], length 0
        ^^^ retransmission is stopped here, only when both 'Address Id' and 'IP Address' match

Fixes: 00cfd77b9063 ("mptcp: retransmit ADD_ADDR when timeout")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/options.c    | 2 +-
 net/mptcp/pm_netlink.c | 8 ++++----
 net/mptcp/protocol.h   | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 71c535f4e1ef..6b825fb3fa83 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1023,7 +1023,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
 		} else {
 			mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);
-			mptcp_pm_del_add_timer(msk, &mp_opt.addr);
+			mptcp_pm_del_add_timer(msk, &mp_opt.addr, true);
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
 		}
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 6ba040897738..2469e06a3a9d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -346,18 +346,18 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-		       struct mptcp_addr_info *addr)
+		       struct mptcp_addr_info *addr, bool check_id)
 {
 	struct mptcp_pm_add_entry *entry;
 	struct sock *sk = (struct sock *)msk;
 
 	spin_lock_bh(&msk->pm.lock);
 	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-	if (entry)
+	if (entry && (!check_id || entry->addr.id == addr->id))
 		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
 	spin_unlock_bh(&msk->pm.lock);
 
-	if (entry)
+	if (entry && (!check_id || entry->addr.id == addr->id))
 		sk_stop_timer_sync(sk, &entry->add_timer);
 
 	return entry;
@@ -1064,7 +1064,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
 {
 	struct mptcp_pm_add_entry *entry;
 
-	entry = mptcp_pm_del_add_timer(msk, addr);
+	entry = mptcp_pm_del_add_timer(msk, addr, false);
 	if (entry) {
 		list_del(&entry->list);
 		kfree(entry);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 165c8b40b384..0c6f99c67345 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -672,7 +672,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-		       struct mptcp_addr_info *addr);
+		       struct mptcp_addr_info *addr, bool check_id);
 struct mptcp_pm_add_entry *
 mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,
 				struct mptcp_addr_info *addr);
-- 
2.31.1

Re: [PATCH net 0/4] MPTCP fixes

[patchwork-bot+netdevbpf]

Hello:

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

On Tue, 25 May 2021 14:23:09 -0700 you wrote:
> Here are a few fixes for the -net tree.
> 
> Patch 1 fixes an attempt to access a tcp-specific field that does not
> exist in mptcp sockets.
> 
> Patches 2 and 3 remove warning/error log output that could be flooded.
> 
> [...]

Here is the summary with links:
  - [net,1/4] mptcp: avoid OOB access in setsockopt()
    https://git.kernel.org/netdev/net/c/20b5759f21cf
  - [net,2/4] mptcp: drop unconditional pr_warn on bad opt
    https://git.kernel.org/netdev/net/c/3812ce895047
  - [net,3/4] mptcp: avoid error message on infinite mapping
    https://git.kernel.org/netdev/net/c/3ed0a585bfad
  - [net,4/4] mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer
    https://git.kernel.org/netdev/net/c/d58300c3185b

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