[PATCH v2 -next 0/3] tcp: honour SO_BINDTODEVICE for TW_RST case too

[PATCH v2 -next 0/3] tcp: honour SO_BINDTODEVICE for TW_RST case too

[Florian Westphal]

This is V2, this time as a small series since I followed Erics advice
to split this into smaller chunks, I hope this makes it easier to
review.

First patch adds inet_sk_transparent helper.
Second patch contains an if/else swap that I split from the
original TW_RST v1 one.
Third patch is the actual change without the superfluous sock_net change.

Thanks,
Florian

[PATCH -next 1/3] net: add inet_sk_transparent() helper

[Florian Westphal]

Avoids cluttering tcp_v4_send_reset when followup patch extends
it to deal with timewait sockets.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/request_sock.h |  2 +-
 include/net/tcp.h          | 12 ++++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index a0dde04..f49759d 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -68,7 +68,7 @@ struct request_sock {
 	u32				peer_secid;
 };
 
-static inline struct request_sock *inet_reqsk(struct sock *sk)
+static inline struct request_sock *inet_reqsk(const struct sock *sk)
 {
 	return (struct request_sock *)sk;
 }
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3077735b..f33fecf 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1620,6 +1620,18 @@ static inline void tcp_highest_sack_combine(struct sock *sk,
 		tcp_sk(sk)->highest_sack = new;
 }
 
+/* This helper checks if socket has IP_TRANSPARENT set */
+static inline bool inet_sk_transparent(const struct sock *sk)
+{
+	switch (sk->sk_state) {
+	case TCP_TIME_WAIT:
+		return inet_twsk(sk)->tw_transparent;
+	case TCP_NEW_SYN_RECV:
+		return inet_rsk(inet_reqsk(sk))->no_srccheck;
+	}
+	return inet_sk(sk)->transparent;
+}
+
 /* Determines whether this is a thin stream (which may suffer from
  * increased latency). Used to trigger latency-reducing mechanisms.
  */
-- 
2.4.10

[PATCH -next 2/3] tcp: send_reset: test for non-NULL sk first

[Florian Westphal]

tcp_md5_do_lookup requires a full socket, so once we extend
_send_reset() to also accept timewait socket we would have to change

if (!sk && hash_location)

to something like

if ((!sk || !sk_fullsock(sk)) && hash_location) {
  ...
} else {
  (sk && sk_fullsock(sk)) tcp_md5_do_lookup()
}

Switch the two branches: check if we have a socket first, then
fall back to a listener lookup if we saw a md5 option (hash_location).

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/ipv4/tcp_ipv4.c | 11 +++++------
 net/ipv6/tcp_ipv6.c |  6 +++---
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 46e92fb..eb29c2f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -587,7 +587,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	} rep;
 	struct ip_reply_arg arg;
 #ifdef CONFIG_TCP_MD5SIG
-	struct tcp_md5sig_key *key;
+	struct tcp_md5sig_key *key = NULL;
 	const __u8 *hash_location = NULL;
 	unsigned char newhash[16];
 	int genhash;
@@ -627,7 +627,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 #ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
-	if (!sk && hash_location) {
+	if (sk) {
+		key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
+					&ip_hdr(skb)->saddr, AF_INET);
+	} else if (hash_location) {
 		/*
 		 * active side is lost. Try to find listening socket through
 		 * source port, and then find md5 key through listening socket.
@@ -651,10 +654,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
 			goto release_sk1;
-	} else {
-		key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
-					     &ip_hdr(skb)->saddr,
-					     AF_INET) : NULL;
 	}
 
 	if (key) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f03d2b0..32fa0de 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -854,7 +854,9 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
-	if (!sk && hash_location) {
+	if (sk) {
+		key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
+	} else if (hash_location) {
 		/*
 		 * active side is lost. Try to find listening socket through
 		 * source port, and then find md5 key through listening socket.
@@ -877,8 +879,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 		genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
 			goto release_sk1;
-	} else {
-		key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL;
 	}
 #endif
 
-- 
2.4.10

[PATCH v2 -next 3/3] tcp: honour SO_BINDTODEVICE for TW_RST case too

[Florian Westphal]

Hannes points out that when we generate tcp reset for timewait sockets we
pretend we found no socket and pass NULL sk to tcp_vX_send_reset().

Make it cope with inet tw sockets and then provide tw sk.

This makes RSTs appear on correct interface when SO_BINDTODEVICE is used.

Packetdrill test case:
// want default route to be used, we rely on BINDTODEVICE
`ip route del 192.0.2.0/24 via 192.168.0.2 dev tun0`

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
// test case still works due to BINDTODEVICE
0.001 setsockopt(3, SOL_SOCKET, SO_BINDTODEVICE, "tun0", 4) = 0
0.100...0.200 connect(3, ..., ...) = 0

0.100 > S 0:0(0) <mss 1460,sackOK,nop,nop>
0.200 < S. 0:0(0) ack 1 win 32792 <mss 1460,sackOK,nop,nop>
0.200 > . 1:1(0) ack 1

0.210 close(3) = 0

0.210 > F. 1:1(0) ack 1 win 29200
0.300 < . 1:1(0) ack 2 win 46

// more data while in FIN_WAIT2, expect RST
1.300 < P. 1:1001(1000) ack 1 win 46

// fails without this change -- default route is used
1.301 > R 1:1(0) win 0

Reported-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 Changes since v1:
 follow all of Erics suggestions, namely:
  - drop unneeded special-casing of sock_net(), it handles TW sk just fine
  - use new inet_sk_transparent() helper to reduce clutter
  - tcp_v6_send_response also handles TW sockets, no need to set
  TW sk to NULL
  - split if/else md5 change to extra patch

 net/ipv4/tcp_ipv4.c      | 12 +++++++++---
 net/ipv4/tcp_minisocks.c |  7 ++-----
 net/ipv6/tcp_ipv6.c      |  6 ++++--
 3 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index eb29c2f..fc4f726 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -627,7 +627,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 #ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
-	if (sk) {
+	if (sk && sk_fullsock(sk)) {
 		key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
 					&ip_hdr(skb)->saddr, AF_INET);
 	} else if (hash_location) {
@@ -674,7 +674,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 				      ip_hdr(skb)->saddr, /* XXX */
 				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
-	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
+	arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0;
+
 	/* When socket is gone, all binding information is lost.
 	 * routing might fail in this case. No choice here, if we choose to force
 	 * input interface, we will misroute in case of asymmetric route.
@@ -682,6 +683,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
+	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
+		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
+
 	arg.tos = ip_hdr(skb)->tos;
 	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -1705,7 +1709,9 @@ do_time_wait:
 		tcp_v4_timewait_ack(sk, skb);
 		break;
 	case TCP_TW_RST:
-		goto no_tcp_socket;
+		tcp_v4_send_reset(sk, skb);
+		inet_twsk_deschedule_put(inet_twsk(sk));
+		goto discard_it;
 	case TCP_TW_SUCCESS:;
 	}
 	goto discard_it;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ac6b196..75632a9 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -131,7 +131,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			goto kill;
 
 		if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt))
-			goto kill_with_rst;
+			return TCP_TW_RST;
 
 		/* Dup ACK? */
 		if (!th->ack ||
@@ -145,11 +145,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		 * reset.
 		 */
 		if (!th->fin ||
-		    TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) {
-kill_with_rst:
-			inet_twsk_deschedule_put(tw);
+		    TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1)
 			return TCP_TW_RST;
-		}
 
 		/* FIN arrived, enter true time-wait state. */
 		tw->tw_substate	  = TCP_TIME_WAIT;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 32fa0de..9ecb012 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -854,7 +854,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
-	if (sk) {
+	if (sk && sk_fullsock(sk)) {
 		key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
 	} else if (hash_location) {
 		/*
@@ -1516,7 +1516,9 @@ do_time_wait:
 		break;
 	case TCP_TW_RST:
 		tcp_v6_restore_cb(skb);
-		goto no_tcp_socket;
+		tcp_v6_send_reset(sk, skb);
+		inet_twsk_deschedule_put(inet_twsk(sk));
+		goto discard_it;
 	case TCP_TW_SUCCESS:
 		;
 	}
-- 
2.4.10

Re: [PATCH -next 1/3] net: add inet_sk_transparent() helper

[Eric Dumazet]

On Mon, 2015-12-21 at 21:29 +0100, Florian Westphal wrote:
> Avoids cluttering tcp_v4_send_reset when followup patch extends
> it to deal with timewait sockets.
> 
> Suggested-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Florian Westphal <fw@strlen.de>
> ---

Acked-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH -next 2/3] tcp: send_reset: test for non-NULL sk first

[Eric Dumazet]

On Mon, 2015-12-21 at 21:29 +0100, Florian Westphal wrote:
> tcp_md5_do_lookup requires a full socket, so once we extend
> _send_reset() to also accept timewait socket we would have to change
> 

Acked-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH v2 -next 3/3] tcp: honour SO_BINDTODEVICE for TW_RST case too

[Eric Dumazet]

On Mon, 2015-12-21 at 21:29 +0100, Florian Westphal wrote:
> Hannes points out that when we generate tcp reset for timewait sockets we
> pretend we found no socket and pass NULL sk to tcp_vX_send_reset().
> 
> Make it cope with inet tw sockets and then provide tw sk.
> 
> This makes RSTs appear on correct interface when SO_BINDTODEVICE is used.

Acked-by: Eric Dumazet <edumazet@google.com>

Thanks Florian !

Re: [PATCH -next 1/3] net: add inet_sk_transparent() helper

[Hannes Frederic Sowa]

On 21.12.2015 21:29, Florian Westphal wrote:
> Avoids cluttering tcp_v4_send_reset when followup patch extends
> it to deal with timewait sockets.
> 
> Suggested-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Florian Westphal <fw@strlen.de>

Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>

Re: [PATCH -next 2/3] tcp: send_reset: test for non-NULL sk first

[Hannes Frederic Sowa]

On 21.12.2015 21:29, Florian Westphal wrote:
> tcp_md5_do_lookup requires a full socket, so once we extend
> _send_reset() to also accept timewait socket we would have to change
> 
> if (!sk && hash_location)
> 
> to something like
> 
> if ((!sk || !sk_fullsock(sk)) && hash_location) {
>   ...
> } else {
>   (sk && sk_fullsock(sk)) tcp_md5_do_lookup()
> }
> 
> Switch the two branches: check if we have a socket first, then
> fall back to a listener lookup if we saw a md5 option (hash_location).
> 
> Signed-off-by: Florian Westphal <fw@strlen.de>

Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>

Re: [PATCH v2 -next 3/3] tcp: honour SO_BINDTODEVICE for TW_RST case too

[Hannes Frederic Sowa]

On 21.12.2015 21:29, Florian Westphal wrote:
> Hannes points out that when we generate tcp reset for timewait sockets we
> pretend we found no socket and pass NULL sk to tcp_vX_send_reset().
> 
> Make it cope with inet tw sockets and then provide tw sk.
> 
> This makes RSTs appear on correct interface when SO_BINDTODEVICE is used.
> 
> Packetdrill test case:
> // want default route to be used, we rely on BINDTODEVICE
> `ip route del 192.0.2.0/24 via 192.168.0.2 dev tun0`
> 
> 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
> // test case still works due to BINDTODEVICE
> 0.001 setsockopt(3, SOL_SOCKET, SO_BINDTODEVICE, "tun0", 4) = 0
> 0.100...0.200 connect(3, ..., ...) = 0
> 
> 0.100 > S 0:0(0) <mss 1460,sackOK,nop,nop>
> 0.200 < S. 0:0(0) ack 1 win 32792 <mss 1460,sackOK,nop,nop>
> 0.200 > . 1:1(0) ack 1
> 
> 0.210 close(3) = 0
> 
> 0.210 > F. 1:1(0) ack 1 win 29200
> 0.300 < . 1:1(0) ack 2 win 46
> 
> // more data while in FIN_WAIT2, expect RST
> 1.300 < P. 1:1001(1000) ack 1 win 46
> 
> // fails without this change -- default route is used
> 1.301 > R 1:1(0) win 0
> 
> Reported-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
> Signed-off-by: Florian Westphal <fw@strlen.de>

Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>

Tested and works fine, thanks Florian and Eric!

Re: [PATCH v2 -next 0/3] tcp: honour SO_BINDTODEVICE for TW_RST case too

[David Miller]

From: Florian Westphal <fw@strlen.de>
Date: Mon, 21 Dec 2015 21:29:23 +0100

> This is V2, this time as a small series since I followed Erics advice
> to split this into smaller chunks, I hope this makes it easier to
> review.
> 
> First patch adds inet_sk_transparent helper.
> Second patch contains an if/else swap that I split from the
> original TW_RST v1 one.
> Third patch is the actual change without the superfluous sock_net change.

Looks good, series applied, thanks Florian!