From e1cfcbe82b4534bd0f99fef92a6d33843fd85e0e Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:40 +0800
Subject: ipv4: Namespaceify tcp_fastopen knob

Different namespace application might require enable TCP Fast Open
feature independently of the host.

This patch series continues making more of the TCP Fast Open related
sysctl knobs be per net-namespace.

Reported-by: Luca BRUNO <lucab@debian.org>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_fastopen.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e3c33220c418..31b08ec38cb8 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -9,8 +9,6 @@
 #include <net/inetpeer.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE;
-
 struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 
 static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
@@ -279,21 +277,22 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc)
 {
-	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+	int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	struct sock *child;
 
 	if (foc->len == 0) /* Client requests a cookie */
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
 
-	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	if (!((tcp_fastopen & TFO_SERVER_ENABLE) &&
 	      (syn_data || foc->len >= 0) &&
 	      tcp_fastopen_queue_check(sk))) {
 		foc->len = -1;
 		return NULL;
 	}
 
-	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+	if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
 		goto fastopen;
 
 	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
@@ -347,7 +346,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 		return false;
 	}
 
-	if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+	if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
 		cookie->len = -1;
 		return true;
 	}
-- 
cgit v1.2.3


From dd000598a39b6937fcefdf143720ec9fb5250e72 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:41 +0800
Subject: ipv4: Remove the 'publish' logic in tcp_fastopen_init_key_once
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 'publish' logic is not necessary after commit dfea2aa65424 ("tcp:
Do not call tcp_fastopen_reset_cipher from interrupt context"), because
in tcp_fastopen_cookie_gen，it wouldn't call tcp_fastopen_init_key_once.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h          | 2 +-
 net/ipv4/af_inet.c         | 2 +-
 net/ipv4/sysctl_net_ipv4.c | 5 -----
 net/ipv4/tcp.c             | 2 +-
 net/ipv4/tcp_fastopen.c    | 4 ++--
 5 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9e414a99034f..d9376e2458e9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1555,7 +1555,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc);
-void tcp_fastopen_init_key_once(bool publish);
+void tcp_fastopen_init_key_once(void);
 bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			     struct tcp_fastopen_cookie *cookie);
 bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ddd126d120ac..e73ce79d7176 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -222,7 +222,7 @@ int inet_listen(struct socket *sock, int backlog)
 		    (tcp_fastopen & TFO_SERVER_ENABLE) &&
 		    !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
 			fastopen_queue_tune(sk, backlog);
-			tcp_fastopen_init_key_once(true);
+			tcp_fastopen_init_key_once();
 		}
 
 		err = inet_csk_listen_start(sk, backlog);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e31e853cf486..f6324ead0e19 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -282,11 +282,6 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		/* Generate a dummy secret but don't publish it. This
-		 * is needed so we don't regenerate a new key on the
-		 * first invocation of tcp_fastopen_cookie_gen
-		 */
-		tcp_fastopen_init_key_once(false);
 		tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
 	}
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dac56c4ad357..4e395452d69f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2749,7 +2749,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
 		    TCPF_LISTEN))) {
-			tcp_fastopen_init_key_once(true);
+			tcp_fastopen_init_key_once();
 
 			fastopen_queue_tune(sk, val);
 		} else {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 31b08ec38cb8..8c8f0f0af59d 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -13,7 +13,7 @@ struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 
 static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
 
-void tcp_fastopen_init_key_once(bool publish)
+void tcp_fastopen_init_key_once(void)
 {
 	static u8 key[TCP_FASTOPEN_KEY_LENGTH];
 
@@ -23,7 +23,7 @@ void tcp_fastopen_init_key_once(bool publish)
 	 * All call sites of tcp_fastopen_cookie_gen also check
 	 * for a valid cookie, so this is an acceptable risk.
 	 */
-	if (net_get_random_once(key, sizeof(key)) && publish)
+	if (net_get_random_once(key, sizeof(key)))
 		tcp_fastopen_reset_cipher(key, sizeof(key));
 }
 
-- 
cgit v1.2.3


From 437138485656c41e32b8c63c0987cfa0348be0e6 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:42 +0800
Subject: ipv4: Namespaceify tcp_fastopen_key knob

Different namespace application might require different tcp_fastopen_key
independently of the host.

David Miller pointed out there is a leak without releasing the context
of tcp_fastopen_key during netns teardown. So add the release action in
exit_batch path.

Tested:
1. Container namespace:
# cat /proc/sys/net/ipv4/tcp_fastopen_key:
2817fff2-f803cf97-eadfd1f3-78c0992b

cookie key in tcp syn packets:
Fast Open Cookie
    Kind: TCP Fast Open Cookie (34)
    Length: 10
    Fast Open Cookie: 1e5dd82a8c492ca9

2. Host:
# cat /proc/sys/net/ipv4/tcp_fastopen_key:
107d7c5f-68eb2ac7-02fb06e6-ed341702

cookie key in tcp syn packets:
Fast Open Cookie
    Kind: TCP Fast Open Cookie (34)
    Length: 10
    Fast Open Cookie: e213c02bf0afbc8a

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h   |  4 +++
 include/net/tcp.h          |  6 ++---
 net/ipv4/af_inet.c         |  2 +-
 net/ipv4/sysctl_net_ipv4.c | 21 ++++++++-------
 net/ipv4/tcp.c             |  2 +-
 net/ipv4/tcp_fastopen.c    | 64 +++++++++++++++++++++++++++++++---------------
 net/ipv4/tcp_ipv4.c        |  6 +++++
 7 files changed, 70 insertions(+), 35 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 16420ccaef15..7bb9603ff66c 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -36,6 +36,8 @@ struct inet_timewait_death_row {
 	int			sysctl_max_tw_buckets;
 };
 
+struct tcp_fastopen_context;
+
 struct netns_ipv4 {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*forw_hdr;
@@ -129,6 +131,8 @@ struct netns_ipv4 {
 	struct inet_timewait_death_row tcp_death_row;
 	int sysctl_max_syn_backlog;
 	int sysctl_tcp_fastopen;
+	struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
+	spinlock_t tcp_fastopen_ctx_lock;
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	int sysctl_udp_l3mdev_accept;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d9376e2458e9..6d25d8305054 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1549,13 +1549,13 @@ struct tcp_fastopen_request {
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
 
-extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-int tcp_fastopen_reset_cipher(void *key, unsigned int len);
+void tcp_fastopen_ctx_destroy(struct net *net);
+int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len);
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc);
-void tcp_fastopen_init_key_once(void);
+void tcp_fastopen_init_key_once(struct net *net);
 bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			     struct tcp_fastopen_cookie *cookie);
 bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e73ce79d7176..43a1bbed7a42 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -222,7 +222,7 @@ int inet_listen(struct socket *sock, int backlog)
 		    (tcp_fastopen & TFO_SERVER_ENABLE) &&
 		    !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
 			fastopen_queue_tune(sk, backlog);
-			tcp_fastopen_init_key_once();
+			tcp_fastopen_init_key_once(sock_net(sk));
 		}
 
 		err = inet_csk_listen_start(sk, backlog);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index f6324ead0e19..20e19fe78dbd 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -251,10 +251,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
 	return ret;
 }
 
-static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos)
 {
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_tcp_fastopen);
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
 	int ret;
@@ -265,7 +267,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 		return -ENOMEM;
 
 	rcu_read_lock();
-	ctxt = rcu_dereference(tcp_fastopen_ctx);
+	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctxt)
 		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
@@ -282,7 +284,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+		tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
@@ -395,12 +397,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "tcp_fastopen_key",
-		.mode		= 0600,
-		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
-		.proc_handler	= proc_tcp_fastopen_key,
-	},
 	{
 		.procname	= "tcp_fastopen_blackhole_timeout_sec",
 		.data		= &sysctl_tcp_fastopen_blackhole_timeout,
@@ -1080,6 +1076,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_fastopen_key",
+		.mode		= 0600,
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen,
+		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
+		.proc_handler	= proc_tcp_fastopen_key,
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4e395452d69f..23225c98d287 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2749,7 +2749,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
 		    TCPF_LISTEN))) {
-			tcp_fastopen_init_key_once();
+			tcp_fastopen_init_key_once(net);
 
 			fastopen_queue_tune(sk, val);
 		} else {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 8c8f0f0af59d..4eae44ac3cb0 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -9,13 +9,18 @@
 #include <net/inetpeer.h>
 #include <net/tcp.h>
 
-struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-
-static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
-
-void tcp_fastopen_init_key_once(void)
+void tcp_fastopen_init_key_once(struct net *net)
 {
-	static u8 key[TCP_FASTOPEN_KEY_LENGTH];
+	u8 key[TCP_FASTOPEN_KEY_LENGTH];
+	struct tcp_fastopen_context *ctxt;
+
+	rcu_read_lock();
+	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+	if (ctxt) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
 
 	/* tcp_fastopen_reset_cipher publishes the new context
 	 * atomically, so we allow this race happening here.
@@ -23,8 +28,8 @@ void tcp_fastopen_init_key_once(void)
 	 * All call sites of tcp_fastopen_cookie_gen also check
 	 * for a valid cookie, so this is an acceptable risk.
 	 */
-	if (net_get_random_once(key, sizeof(key)))
-		tcp_fastopen_reset_cipher(key, sizeof(key));
+	get_random_bytes(key, sizeof(key));
+	tcp_fastopen_reset_cipher(net, key, sizeof(key));
 }
 
 static void tcp_fastopen_ctx_free(struct rcu_head *head)
@@ -35,7 +40,22 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
 	kfree(ctx);
 }
 
-int tcp_fastopen_reset_cipher(void *key, unsigned int len)
+void tcp_fastopen_ctx_destroy(struct net *net)
+{
+	struct tcp_fastopen_context *ctxt;
+
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+	ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+				lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+	rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL);
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+	if (ctxt)
+		call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
+}
+
+int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len)
 {
 	int err;
 	struct tcp_fastopen_context *ctx, *octx;
@@ -59,26 +79,27 @@ error:		kfree(ctx);
 	}
 	memcpy(ctx->key, key, len);
 
-	spin_lock(&tcp_fastopen_ctx_lock);
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
 
-	octx = rcu_dereference_protected(tcp_fastopen_ctx,
-				lockdep_is_held(&tcp_fastopen_ctx_lock));
-	rcu_assign_pointer(tcp_fastopen_ctx, ctx);
-	spin_unlock(&tcp_fastopen_ctx_lock);
+	octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+				lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+	rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
 
 	if (octx)
 		call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
 	return err;
 }
 
-static bool __tcp_fastopen_cookie_gen(const void *path,
+static bool __tcp_fastopen_cookie_gen(struct net *net,
+				      const void *path,
 				      struct tcp_fastopen_cookie *foc)
 {
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
 	rcu_read_lock();
-	ctx = rcu_dereference(tcp_fastopen_ctx);
+	ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctx) {
 		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
@@ -94,7 +115,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
  *
  * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
  */
-static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+static bool tcp_fastopen_cookie_gen(struct net *net,
+				    struct request_sock *req,
 				    struct sk_buff *syn,
 				    struct tcp_fastopen_cookie *foc)
 {
@@ -102,7 +124,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		const struct iphdr *iph = ip_hdr(syn);
 
 		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
-		return __tcp_fastopen_cookie_gen(path, foc);
+		return __tcp_fastopen_cookie_gen(net, path, foc);
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -110,13 +132,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
 		struct tcp_fastopen_cookie tmp;
 
-		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+		if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) {
 			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
 				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
-			return __tcp_fastopen_cookie_gen(buf, foc);
+			return __tcp_fastopen_cookie_gen(net, buf, foc);
 		}
 	}
 #endif
@@ -296,7 +318,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 		goto fastopen;
 
 	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
-	    tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) &&
 	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
 	    foc->len == valid_foc.len &&
 	    !memcmp(foc->val, valid_foc.val, foc->len)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 88409b13c9d2..49c74c0d0d21 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2473,6 +2473,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_timestamps = 1;
 
 	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
+	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
 
 	return 0;
 fail:
@@ -2483,7 +2484,12 @@ fail:
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
+	struct net *net;
+
 	inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
+	list_for_each_entry(net, net_exit_list, exit_list)
+		tcp_fastopen_ctx_destroy(net);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {
-- 
cgit v1.2.3


From 3733be14a32bae288b61ed28341e593baba983af Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:43 +0800
Subject: ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob

Different namespace application might require different time period in
second to disable Fastopen on active TCP sockets.

Tested:
Simulate following similar situation that the server's data gets dropped
after 3WHS.
C ---- syn-data ---> S
C <--- syn/ack ----- S
C ---- ack --------> S
S (accept & write)
C?  X <- data ------ S
	[retry and timeout]

And then print netstat of TCPFastOpenBlackhole, the counter increased as
expected when the firewall blackhole issue is detected and active TFO is
disabled.
# cat /proc/net/netstat | awk '{print $91}'
TCPFastOpenBlackhole
1

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h   |  3 +++
 net/ipv4/sysctl_net_ipv4.c | 20 +++++++++++---------
 net/ipv4/tcp_fastopen.c    | 30 +++++++++++-------------------
 net/ipv4/tcp_ipv4.c        |  2 ++
 4 files changed, 27 insertions(+), 28 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 7bb9603ff66c..2c4222a5d102 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -133,6 +133,9 @@ struct netns_ipv4 {
 	int sysctl_tcp_fastopen;
 	struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 	spinlock_t tcp_fastopen_ctx_lock;
+	unsigned int sysctl_tcp_fastopen_blackhole_timeout;
+	atomic_t tfo_active_disable_times;
+	unsigned long tfo_active_disable_stamp;
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	int sysctl_udp_l3mdev_accept;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 20e19fe78dbd..cac8dd309f39 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -355,11 +355,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
 					     void __user *buffer,
 					     size_t *lenp, loff_t *ppos)
 {
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_tcp_fastopen_blackhole_timeout);
 	int ret;
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		tcp_fastopen_active_timeout_reset();
+		atomic_set(&net->ipv4.tfo_active_disable_times, 0);
 
 	return ret;
 }
@@ -397,14 +399,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "tcp_fastopen_blackhole_timeout_sec",
-		.data		= &sysctl_tcp_fastopen_blackhole_timeout,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_tfo_blackhole_detect_timeout,
-		.extra1		= &zero,
-	},
 	{
 		.procname	= "tcp_abort_on_overflow",
 		.data		= &sysctl_tcp_abort_on_overflow,
@@ -1083,6 +1077,14 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
 		.proc_handler	= proc_tcp_fastopen_key,
 	},
+	{
+		.procname	= "tcp_fastopen_blackhole_timeout_sec",
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_tfo_blackhole_detect_timeout,
+		.extra1		= &zero,
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 4eae44ac3cb0..de470e7e586f 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -422,25 +422,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect);
  * TFO connection with data exchanges.
  */
 
-/* Default to 1hr */
-unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60;
-static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0);
-static unsigned long tfo_active_disable_stamp __read_mostly;
-
 /* Disable active TFO and record current jiffies and
  * tfo_active_disable_times
  */
 void tcp_fastopen_active_disable(struct sock *sk)
 {
-	atomic_inc(&tfo_active_disable_times);
-	tfo_active_disable_stamp = jiffies;
-	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE);
-}
+	struct net *net = sock_net(sk);
 
-/* Reset tfo_active_disable_times to 0 */
-void tcp_fastopen_active_timeout_reset(void)
-{
-	atomic_set(&tfo_active_disable_times, 0);
+	atomic_inc(&net->ipv4.tfo_active_disable_times);
+	net->ipv4.tfo_active_disable_stamp = jiffies;
+	NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
 }
 
 /* Calculate timeout for tfo active disable
@@ -449,17 +440,18 @@ void tcp_fastopen_active_timeout_reset(void)
  */
 bool tcp_fastopen_active_should_disable(struct sock *sk)
 {
-	int tfo_da_times = atomic_read(&tfo_active_disable_times);
-	int multiplier;
+	unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+	int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
 	unsigned long timeout;
+	int multiplier;
 
 	if (!tfo_da_times)
 		return false;
 
 	/* Limit timout to max: 2^6 * initial timeout */
 	multiplier = 1 << min(tfo_da_times - 1, 6);
-	timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ;
-	if (time_before(jiffies, tfo_active_disable_stamp + timeout))
+	timeout = multiplier * tfo_bh_timeout * HZ;
+	if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
 		return true;
 
 	/* Mark check bit so we can check for successful active TFO
@@ -495,10 +487,10 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
 			}
 		}
 	} else if (tp->syn_fastopen_ch &&
-		   atomic_read(&tfo_active_disable_times)) {
+		   atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
 		dst = sk_dst_get(sk);
 		if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
-			tcp_fastopen_active_timeout_reset();
+			atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
 		dst_release(dst);
 	}
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 49c74c0d0d21..ad3b5bbaf942 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2474,6 +2474,8 @@ static int __net_init tcp_sk_init(struct net *net)
 
 	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
 	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
+	net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+	atomic_set(&net->ipv4.tfo_active_disable_times, 0);
 
 	return 0;
 fail:
-- 
cgit v1.2.3


From 27204aaa9dc67b833b77179fdac556288ec3a4bf Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 4 Oct 2017 10:03:44 -0700
Subject: tcp: uniform the set up of sockets after successful connection

Currently in the TCP code, the initialization sequence for cached
metrics, congestion control, BPF, etc, after successful connection
is very inconsistent. This introduces inconsistent bevhavior and is
prone to bugs. The current call sequence is as follows:

(1) for active case (tcp_finish_connect() case):
        tcp_mtup_init(sk);
        icsk->icsk_af_ops->rebuild_header(sk);
        tcp_init_metrics(sk);
        tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
        tcp_init_congestion_control(sk);
        tcp_init_buffer_space(sk);

(2) for passive case (tcp_rcv_state_process() TCP_SYN_RECV case):
        icsk->icsk_af_ops->rebuild_header(sk);
        tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
        tcp_init_congestion_control(sk);
        tcp_mtup_init(sk);
        tcp_init_buffer_space(sk);
        tcp_init_metrics(sk);

(3) for TFO passive case (tcp_fastopen_create_child()):
        inet_csk(child)->icsk_af_ops->rebuild_header(child);
        tcp_init_congestion_control(child);
        tcp_mtup_init(child);
        tcp_init_metrics(child);
        tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
        tcp_init_buffer_space(child);

This commit uniforms the above functions to have the following sequence:
        tcp_mtup_init(sk);
        icsk->icsk_af_ops->rebuild_header(sk);
        tcp_init_metrics(sk);
        tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE/PASSIVE_ESTABLISHED_CB);
        tcp_init_congestion_control(sk);
        tcp_init_buffer_space(sk);
This sequence is the same as the (1) active case. We pick this sequence
because this order correctly allows BPF to override the settings
including congestion control module and initial cwnd, etc from
the route, and then allows the CC module to see those settings.

Suggested-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h       |  1 +
 net/ipv4/tcp.c          | 12 ++++++++++++
 net/ipv4/tcp_fastopen.c |  7 +------
 net/ipv4/tcp_input.c    | 21 +++------------------
 4 files changed, 17 insertions(+), 24 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7a3a8af56fd6..426c2e986016 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -416,6 +416,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_disable_fack(struct tcp_sock *tp);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
+void tcp_init_transfer(struct sock *sk, int bpf_op);
 unsigned int tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 23225c98d287..c115e37ca608 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -456,6 +456,18 @@ void tcp_init_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
+void tcp_init_transfer(struct sock *sk, int bpf_op)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	tcp_mtup_init(sk);
+	icsk->icsk_af_ops->rebuild_header(sk);
+	tcp_init_metrics(sk);
+	tcp_call_bpf(sk, bpf_op);
+	tcp_init_congestion_control(sk);
+	tcp_init_buffer_space(sk);
+}
+
 static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
 {
 	if (tsflags && skb) {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index de470e7e586f..29fff14d5a53 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -236,12 +236,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	refcount_set(&req->rsk_refcnt, 2);
 
 	/* Now finish processing the fastopen child socket. */
-	inet_csk(child)->icsk_af_ops->rebuild_header(child);
-	tcp_init_congestion_control(child);
-	tcp_mtup_init(child);
-	tcp_init_metrics(child);
-	tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-	tcp_init_buffer_space(child);
+	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index db9bb46b5776..bd3a35f5dbf2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5513,20 +5513,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		security_inet_conn_established(sk, skb);
 	}
 
-	/* Make sure socket is routed, for correct metrics.  */
-	icsk->icsk_af_ops->rebuild_header(sk);
-
-	tcp_init_metrics(sk);
-	tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
-	tcp_init_congestion_control(sk);
+	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
 	 * packet.
 	 */
 	tp->lsndtime = tcp_jiffies32;
 
-	tcp_init_buffer_space(sk);
-
 	if (sock_flag(sk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
 
@@ -5693,7 +5686,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		if (tcp_is_sack(tp) && sysctl_tcp_fack)
 			tcp_enable_fack(tp);
 
-		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
@@ -5920,14 +5912,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			inet_csk(sk)->icsk_retransmits = 0;
 			reqsk_fastopen_remove(sk, req, false);
 		} else {
-			/* Make sure socket is routed, for correct metrics. */
-			icsk->icsk_af_ops->rebuild_header(sk);
-			tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tcp_init_congestion_control(sk);
-
-			tcp_mtup_init(sk);
+			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 			tp->copied_seq = tp->rcv_nxt;
-			tcp_init_buffer_space(sk);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
@@ -5957,8 +5943,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			 * are sent out.
 			 */
 			tcp_rearm_rto(sk);
-		} else
-			tcp_init_metrics(sk);
+		}
 
 		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
 			tcp_update_pacing_rate(sk);
-- 
cgit v1.2.3


From 18a4c0eab2623cc95be98a1e6af1ad18e7695977 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Oct 2017 22:21:21 -0700
Subject: net: add rb_to_skb() and other rb tree helpers

Geeralize private netem_rb_to_skb()

TCP rtx queue will soon be converted to rb-tree,
so we will need skb_rbtree_walk() helpers.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h  | 18 ++++++++++++++++++
 net/ipv4/tcp_fastopen.c |  8 +++-----
 net/ipv4/tcp_input.c    | 33 ++++++++++++---------------------
 net/sched/sch_netem.c   | 14 ++++----------
 4 files changed, 37 insertions(+), 36 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 01a985937867..03634ec2f918 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3158,6 +3158,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 	return __skb_grow(skb, len);
 }
 
+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+#define skb_rb_first(root) rb_to_skb(rb_first(root))
+#define skb_rb_last(root)  rb_to_skb(rb_last(root))
+#define skb_rb_next(skb)   rb_to_skb(rb_next(&(skb)->rbnode))
+#define skb_rb_prev(skb)   rb_to_skb(rb_prev(&(skb)->rbnode))
+
 #define skb_queue_walk(queue, skb) \
 		for (skb = (queue)->next;					\
 		     skb != (struct sk_buff *)(queue);				\
@@ -3172,6 +3178,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 		for (; skb != (struct sk_buff *)(queue);			\
 		     skb = skb->next)
 
+#define skb_rbtree_walk(skb, root)						\
+		for (skb = skb_rb_first(root); skb != NULL;			\
+		     skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from(skb)						\
+		for (; skb != NULL;						\
+		     skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from_safe(skb, tmp)					\
+		for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL);	\
+		     skb = tmp)
+
 #define skb_queue_walk_from_safe(queue, skb, tmp)				\
 		for (tmp = skb->next;						\
 		     skb != (struct sk_buff *)(queue);				\
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 29fff14d5a53..7ee4aadcdd71 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -465,17 +465,15 @@ bool tcp_fastopen_active_should_disable(struct sock *sk)
 void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node *p;
-	struct sk_buff *skb;
 	struct dst_entry *dst;
+	struct sk_buff *skb;
 
 	if (!tp->syn_fastopen)
 		return;
 
 	if (!tp->data_segs_in) {
-		p = rb_first(&tp->out_of_order_queue);
-		if (p && !rb_next(p)) {
-			skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = skb_rb_first(&tp->out_of_order_queue);
+		if (skb && !skb_rb_next(skb)) {
 			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
 				tcp_fastopen_active_disable(sk);
 				return;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fb0d7ed84b94..90afe4143596 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4335,7 +4335,7 @@ static void tcp_ofo_queue(struct sock *sk)
 
 	p = rb_first(&tp->out_of_order_queue);
 	while (p) {
-		skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = rb_to_skb(p);
 		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
 			break;
 
@@ -4399,7 +4399,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
 static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node **p, *q, *parent;
+	struct rb_node **p, *parent;
 	struct sk_buff *skb1;
 	u32 seq, end_seq;
 	bool fragstolen;
@@ -4458,7 +4458,7 @@ coalesce_done:
 	parent = NULL;
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(seq, TCP_SKB_CB(skb1)->seq)) {
 			p = &parent->rb_left;
 			continue;
@@ -4503,9 +4503,7 @@ insert:
 
 merge_right:
 	/* Remove other segments covered by skb. */
-	while ((q = rb_next(&skb->rbnode)) != NULL) {
-		skb1 = rb_entry(q, struct sk_buff, rbnode);
-
+	while ((skb1 = skb_rb_next(skb)) != NULL) {
 		if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
 			break;
 		if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
@@ -4520,7 +4518,7 @@ merge_right:
 		tcp_drop(sk, skb1);
 	}
 	/* If there is no skb after us, we are the last_skb ! */
-	if (!q)
+	if (!skb1)
 		tp->ooo_last_skb = skb;
 
 add_sack:
@@ -4706,7 +4704,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li
 	if (list)
 		return !skb_queue_is_last(list, skb) ? skb->next : NULL;
 
-	return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode);
+	return skb_rb_next(skb);
 }
 
 static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
@@ -4735,7 +4733,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
 
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
 			p = &parent->rb_left;
 		else
@@ -4854,26 +4852,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb, *head;
-	struct rb_node *p;
 	u32 start, end;
 
-	p = rb_first(&tp->out_of_order_queue);
-	skb = rb_entry_safe(p, struct sk_buff, rbnode);
+	skb = skb_rb_first(&tp->out_of_order_queue);
 new_range:
 	if (!skb) {
-		p = rb_last(&tp->out_of_order_queue);
-		/* Note: This is possible p is NULL here. We do not
-		 * use rb_entry_safe(), as ooo_last_skb is valid only
-		 * if rbtree is not empty.
-		 */
-		tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode);
+		tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue);
 		return;
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
 
 	for (head = skb;;) {
-		skb = tcp_skb_next(skb, NULL);
+		skb = skb_rb_next(skb);
 
 		/* Range is terminated when we see a gap or when
 		 * we are at the queue end.
@@ -4916,14 +4907,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
-		tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
+		tcp_drop(sk, rb_to_skb(node));
 		sk_mem_reclaim(sk);
 		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
 		    !tcp_under_memory_pressure(sk))
 			break;
 		node = prev;
 	} while (node);
-	tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
+	tp->ooo_last_skb = rb_to_skb(prev);
 
 	/* Reset SACK state.  A conforming SACK implementation will
 	 * do the same at a timeout based retransmit.  When a connection
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5a4f10080290..db0228a65e8c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -148,12 +148,6 @@ struct netem_skb_cb {
 	psched_time_t	time_to_send;
 };
 
-
-static struct sk_buff *netem_rb_to_skb(struct rb_node *rb)
-{
-	return rb_entry(rb, struct sk_buff, rbnode);
-}
-
 static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
 {
 	/* we assume we can use skb next/prev/tstamp as storage for rb_node */
@@ -364,7 +358,7 @@ static void tfifo_reset(struct Qdisc *sch)
 	struct rb_node *p = rb_first(&q->t_root);
 
 	while (p) {
-		struct sk_buff *skb = netem_rb_to_skb(p);
+		struct sk_buff *skb = rb_to_skb(p);
 
 		p = rb_next(p);
 		rb_erase(&skb->rbnode, &q->t_root);
@@ -382,7 +376,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		struct sk_buff *skb;
 
 		parent = *p;
-		skb = netem_rb_to_skb(parent);
+		skb = rb_to_skb(parent);
 		if (tnext >= netem_skb_cb(skb)->time_to_send)
 			p = &parent->rb_right;
 		else
@@ -538,7 +532,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 				struct sk_buff *t_skb;
 				struct netem_skb_cb *t_last;
 
-				t_skb = netem_rb_to_skb(rb_last(&q->t_root));
+				t_skb = skb_rb_last(&q->t_root);
 				t_last = netem_skb_cb(t_skb);
 				if (!last ||
 				    t_last->time_to_send > last->time_to_send) {
@@ -617,7 +611,7 @@ deliver:
 	if (p) {
 		psched_time_t time_to_send;
 
-		skb = netem_rb_to_skb(p);
+		skb = rb_to_skb(p);
 
 		/* if more time remaining? */
 		time_to_send = netem_skb_cb(skb)->time_to_send;
-- 
cgit v1.2.3


From 1fba70e5b6bed53496ba1f1f16127f5be01b5fb6 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Oct 2017 11:22:51 -0700
Subject: tcp: socket option to set TCP fast open key

New socket option TCP_FASTOPEN_KEY to allow different keys per
listener.  The listener by default uses the global key until the
socket option is set.  The key is a 16 bytes long binary data. This
option has no effect on regular non-listener TCP sockets.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/request_sock.h |  2 ++
 include/net/tcp.h          |  5 +++--
 include/uapi/linux/tcp.h   |  1 +
 net/ipv4/sysctl_net_ipv4.c |  3 ++-
 net/ipv4/tcp.c             | 33 +++++++++++++++++++++++++++
 net/ipv4/tcp_fastopen.c    | 56 +++++++++++++++++++++++++++++++++-------------
 net/ipv4/tcp_ipv4.c        |  1 +
 7 files changed, 82 insertions(+), 19 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 23e22054aa60..347015515a7d 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -150,6 +150,8 @@ struct fastopen_queue {
 	spinlock_t	lock;
 	int		qlen;		/* # of pending (TCP_SYN_RECV) reqs */
 	int		max_qlen;	/* != 0 iff TFO is currently enabled */
+
+	struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */
 };
 
 /** struct request_sock_queue - queue of request_socks
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3b3b9b968e2d..1efe8365cb28 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1555,9 +1555,10 @@ struct tcp_fastopen_request {
 	int				copied;	/* queued in tcp_connect() */
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
-
+void tcp_fastopen_destroy_cipher(struct sock *sk);
 void tcp_fastopen_ctx_destroy(struct net *net);
-int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len);
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+			      void *key, unsigned int len);
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 15c25eccab2b..69c7493e42f8 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -119,6 +119,7 @@ enum {
 #define TCP_FASTOPEN_CONNECT	30	/* Attempt FastOpen with connect */
 #define TCP_ULP			31	/* Attach a ULP to a TCP connection */
 #define TCP_MD5SIG_EXT		32	/* TCP MD5 Signature with extensions */
+#define TCP_FASTOPEN_KEY	33	/* Set the key for Fast Open (cookie) */
 
 struct tcp_repair_opt {
 	__u32	opt_code;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index cac8dd309f39..81d218346cf7 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -284,7 +284,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH);
+		tcp_fastopen_reset_cipher(net, NULL, user_key,
+					  TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3b34850d361f..8b1fa4dd4538 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2571,6 +2571,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		release_sock(sk);
 		return err;
 	}
+	case TCP_FASTOPEN_KEY: {
+		__u8 key[TCP_FASTOPEN_KEY_LENGTH];
+
+		if (optlen != sizeof(key))
+			return -EINVAL;
+
+		if (copy_from_user(key, optval, optlen))
+			return -EFAULT;
+
+		return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key));
+	}
 	default:
 		/* fallthru */
 		break;
@@ -3157,6 +3168,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		return 0;
 
+	case TCP_FASTOPEN_KEY: {
+		__u8 key[TCP_FASTOPEN_KEY_LENGTH];
+		struct tcp_fastopen_context *ctx;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		rcu_read_lock();
+		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+		if (ctx)
+			memcpy(key, ctx->key, sizeof(key));
+		else
+			len = 0;
+		rcu_read_unlock();
+
+		len = min_t(unsigned int, len, sizeof(key));
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, key, len))
+			return -EFAULT;
+		return 0;
+	}
 	case TCP_THIN_LINEAR_TIMEOUTS:
 		val = tp->thin_lto;
 		break;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 7ee4aadcdd71..21075ce19cb6 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -29,7 +29,7 @@ void tcp_fastopen_init_key_once(struct net *net)
 	 * for a valid cookie, so this is an acceptable risk.
 	 */
 	get_random_bytes(key, sizeof(key));
-	tcp_fastopen_reset_cipher(net, key, sizeof(key));
+	tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key));
 }
 
 static void tcp_fastopen_ctx_free(struct rcu_head *head)
@@ -40,6 +40,16 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
 	kfree(ctx);
 }
 
+void tcp_fastopen_destroy_cipher(struct sock *sk)
+{
+	struct tcp_fastopen_context *ctx;
+
+	ctx = rcu_dereference_protected(
+			inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1);
+	if (ctx)
+		call_rcu(&ctx->rcu, tcp_fastopen_ctx_free);
+}
+
 void tcp_fastopen_ctx_destroy(struct net *net)
 {
 	struct tcp_fastopen_context *ctxt;
@@ -55,10 +65,12 @@ void tcp_fastopen_ctx_destroy(struct net *net)
 		call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
 }
 
-int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len)
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+			      void *key, unsigned int len)
 {
-	int err;
 	struct tcp_fastopen_context *ctx, *octx;
+	struct fastopen_queue *q;
+	int err;
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -79,27 +91,39 @@ error:		kfree(ctx);
 	}
 	memcpy(ctx->key, key, len);
 
-	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
 
-	octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
-				lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
-	rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
-	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+	if (sk) {
+		q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
+		spin_lock_bh(&q->lock);
+		octx = rcu_dereference_protected(q->ctx,
+						 lockdep_is_held(&q->lock));
+		rcu_assign_pointer(q->ctx, ctx);
+		spin_unlock_bh(&q->lock);
+	} else {
+		spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+		octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+		rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
+		spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+	}
 
 	if (octx)
 		call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
 	return err;
 }
 
-static bool __tcp_fastopen_cookie_gen(struct net *net,
-				      const void *path,
+static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path,
 				      struct tcp_fastopen_cookie *foc)
 {
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
 	rcu_read_lock();
-	ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+
+	ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
+	if (!ctx)
+		ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
+
 	if (ctx) {
 		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
@@ -115,7 +139,7 @@ static bool __tcp_fastopen_cookie_gen(struct net *net,
  *
  * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
  */
-static bool tcp_fastopen_cookie_gen(struct net *net,
+static bool tcp_fastopen_cookie_gen(struct sock *sk,
 				    struct request_sock *req,
 				    struct sk_buff *syn,
 				    struct tcp_fastopen_cookie *foc)
@@ -124,7 +148,7 @@ static bool tcp_fastopen_cookie_gen(struct net *net,
 		const struct iphdr *iph = ip_hdr(syn);
 
 		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
-		return __tcp_fastopen_cookie_gen(net, path, foc);
+		return __tcp_fastopen_cookie_gen(sk, path, foc);
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -132,13 +156,13 @@ static bool tcp_fastopen_cookie_gen(struct net *net,
 		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
 		struct tcp_fastopen_cookie tmp;
 
-		if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) {
+		if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) {
 			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
 				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
-			return __tcp_fastopen_cookie_gen(net, buf, foc);
+			return __tcp_fastopen_cookie_gen(sk, buf, foc);
 		}
 	}
 #endif
@@ -313,7 +337,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 		goto fastopen;
 
 	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
-	    tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) &&
+	    tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) &&
 	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
 	    foc->len == valid_foc.len &&
 	    !memcmp(foc->val, valid_foc.val, foc->len)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ecee4ddb24c5..28ca4e177047 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1893,6 +1893,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
+	tcp_fastopen_destroy_cipher(sk);
 	tcp_saved_syn_free(tp);
 
 	sk_sockets_allocated_dec(sk);
-- 
cgit v1.2.3


From 71c02379c762cb616c00fd5c4ed253fbf6bbe11b Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 23 Oct 2017 13:22:23 -0700
Subject: tcp: Configure TFO without cookie per socket and/or per route

We already allow to enable TFO without a cookie by using the
fastopen-sysctl and setting it to TFO_SERVER_COOKIE_NOT_REQD (or
TFO_CLIENT_NO_COOKIE).
This is safe to do in certain environments where we know that there
isn't a malicous host (aka., data-centers) or when the
application-protocol already provides an authentication mechanism in the
first flight of data.

A server however might be providing multiple services or talking to both
sides (public Internet and data-center). So, this server would want to
enable cookie-less TFO for certain services and/or for connections that
go to the data-center.

This patch exposes a socket-option and a per-route attribute to enable such
fine-grained configurations.

Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h            |  3 ++-
 include/net/tcp.h              |  3 ++-
 include/uapi/linux/rtnetlink.h |  2 ++
 include/uapi/linux/tcp.h       |  1 +
 net/ipv4/tcp.c                 | 12 ++++++++++++
 net/ipv4/tcp_fastopen.c        | 20 +++++++++++++++++---
 net/ipv4/tcp_input.c           |  2 +-
 7 files changed, 37 insertions(+), 6 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1d2c44e09e31..173a7c2f9636 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -215,7 +215,8 @@ struct tcp_sock {
 	u8	chrono_type:2,	/* current chronograph type */
 		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
-		unused:4;
+		fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
+		unused:3;
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		unused1	    : 1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2c13484704cb..2392f74074e7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1567,7 +1567,8 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
-			      struct tcp_fastopen_cookie *foc);
+			      struct tcp_fastopen_cookie *foc,
+			      const struct dst_entry *dst);
 void tcp_fastopen_init_key_once(struct net *net);
 bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			     struct tcp_fastopen_cookie *cookie);
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index dab7dad9e01a..fe6679268901 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -430,6 +430,8 @@ enum {
 #define RTAX_QUICKACK RTAX_QUICKACK
 	RTAX_CC_ALGO,
 #define RTAX_CC_ALGO RTAX_CC_ALGO
+	RTAX_FASTOPEN_NO_COOKIE,
+#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE
 	__RTAX_MAX
 };
 
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 69c7493e42f8..d67e1d40c6d6 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -120,6 +120,7 @@ enum {
 #define TCP_ULP			31	/* Attach a ULP to a TCP connection */
 #define TCP_MD5SIG_EXT		32	/* TCP MD5 Signature with extensions */
 #define TCP_FASTOPEN_KEY	33	/* Set the key for Fast Open (cookie) */
+#define TCP_FASTOPEN_NO_COOKIE	34	/* Enable TFO without a TFO cookie */
 
 struct tcp_repair_opt {
 	__u32	opt_code;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index be07e9b6dbdd..8f36277e82e9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2836,6 +2836,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EOPNOTSUPP;
 		}
 		break;
+	case TCP_FASTOPEN_NO_COOKIE:
+		if (val > 1 || val < 0)
+			err = -EINVAL;
+		else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+			err = -EINVAL;
+		else
+			tp->fastopen_no_cookie = val;
+		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
 			err = -EPERM;
@@ -3256,6 +3264,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = tp->fastopen_connect;
 		break;
 
+	case TCP_FASTOPEN_NO_COOKIE:
+		val = tp->fastopen_no_cookie;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp_raw() + tp->tsoffset;
 		break;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 21075ce19cb6..e0a4b56644aa 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -310,13 +310,23 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 	return true;
 }
 
+static bool tcp_fastopen_no_cookie(const struct sock *sk,
+				   const struct dst_entry *dst,
+				   int flag)
+{
+	return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+	       tcp_sk(sk)->fastopen_no_cookie ||
+	       (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
+}
+
 /* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
  * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
  * cookie request (foc->len == 0).
  */
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
-			      struct tcp_fastopen_cookie *foc)
+			      struct tcp_fastopen_cookie *foc,
+			      const struct dst_entry *dst)
 {
 	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
 	int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
@@ -333,7 +343,8 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 		return NULL;
 	}
 
-	if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+	if (syn_data &&
+	    tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
 		goto fastopen;
 
 	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
@@ -370,6 +381,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			       struct tcp_fastopen_cookie *cookie)
 {
 	unsigned long last_syn_loss = 0;
+	const struct dst_entry *dst;
 	int syn_loss = 0;
 
 	tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss);
@@ -387,7 +399,9 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 		return false;
 	}
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+	dst = __sk_dst_get(sk);
+
+	if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) {
 		cookie->len = -1;
 		return true;
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5e64d4b5839..893286db4623 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6332,7 +6332,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tcp_openreq_init_rwin(req, sk, dst);
 	if (!want_cookie) {
 		tcp_reqsk_record_syn(sk, req, skb);
-		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc);
+		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
 	}
 	if (fastopen_sk) {
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
-- 
cgit v1.2.3


From 9eba9353388da7bfac9694dfe94c15365d49ebd6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Nov 2017 11:53:04 -0700
Subject: tcp: fix a lockdep issue in tcp_fastopen_reset_cipher()

icsk_accept_queue.fastopenq.lock is only fully initialized at listen()
time.

LOCKDEP is not happy if we attempt a spin_lock_bh() on it, because
of missing annotation. (Although kernel runs just fine)

Lets use net->ipv4.tcp_fastopen_ctx_lock to protect ctx access.

Fixes: 1fba70e5b6be ("tcp: socket option to set TCP fast open key")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_fastopen.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'net/ipv4/tcp_fastopen.c')

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e0a4b56644aa..91762be58acc 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -92,20 +92,18 @@ error:		kfree(ctx);
 	memcpy(ctx->key, key, len);
 
 
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
 	if (sk) {
 		q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
-		spin_lock_bh(&q->lock);
 		octx = rcu_dereference_protected(q->ctx,
-						 lockdep_is_held(&q->lock));
+			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
 		rcu_assign_pointer(q->ctx, ctx);
-		spin_unlock_bh(&q->lock);
 	} else {
-		spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
 		octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
 			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
 		rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
-		spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
 	}
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
 
 	if (octx)
 		call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
-- 
cgit v1.2.3