[PATCH v5 1/4] ipv4: Namespaceify tcp_fastopen knob

[PATCH v5 1/4] ipv4: Namespaceify tcp_fastopen knob

[Haishuang Yan]

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>

---
Changes since v5:
  * Splite patch #2 into two changes
  * Fix potential leak issue
  * Fix typo error
  * Split the patches to be per-sysctl
  * Remove unrelated change by mistake
---
 include/net/netns/ipv4.h   |  1 +
 include/net/tcp.h          |  1 -
 net/ipv4/af_inet.c         |  7 ++++---
 net/ipv4/sysctl_net_ipv4.c | 14 +++++++-------
 net/ipv4/tcp.c             |  4 ++--
 net/ipv4/tcp_fastopen.c    | 11 +++++------
 net/ipv4/tcp_ipv4.c        |  2 ++
 7 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 20d061c..ce6dde0 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -127,6 +127,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_timestamps;
 	struct inet_timewait_death_row tcp_death_row;
 	int sysctl_max_syn_backlog;
+	int sysctl_tcp_fastopen;
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	int sysctl_udp_l3mdev_accept;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b510f28..f628967 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -240,7 +240,6 @@
 
 
 /* sysctl variables for tcp */
-extern int sysctl_tcp_fastopen;
 extern int sysctl_tcp_retrans_collapse;
 extern int sysctl_tcp_stdurg;
 extern int sysctl_tcp_rfc1337;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e31108e..ddd126d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
 	unsigned char old_state;
-	int err;
+	int err, tcp_fastopen;
 
 	lock_sock(sk);
 
@@ -217,8 +217,9 @@ int inet_listen(struct socket *sock, int backlog)
 		 * because the socket was in TCP_LISTEN state previously but
 		 * was shutdown() rather than close().
 		 */
-		if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
-		    (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+		tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+		if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
+		    (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);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0d3c038..e31e853c 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -401,13 +401,6 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_fastopen",
-		.data		= &sysctl_tcp_fastopen,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
 		.procname	= "tcp_fastopen_key",
 		.mode		= 0600,
 		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
@@ -1085,6 +1078,13 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_fastopen",
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402..dac56c4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1126,7 +1126,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
 	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
 	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
@@ -2759,7 +2759,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN_CONNECT:
 		if (val > 1 || val < 0) {
 			err = -EINVAL;
-		} else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+		} else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
 			if (sk->sk_state == TCP_CLOSE)
 				tp->fastopen_connect = val;
 			else
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e3c3322..31b08ec 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;
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d9416b5..88409b1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2472,6 +2472,8 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;
 
+	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
+
 	return 0;
 fail:
 	tcp_sk_exit(net);
-- 
1.8.3.1

[PATCH v5 2/4] ipv4: Remove the 'publish' logic in tcp_fastopen_init_key_once

[Haishuang Yan]

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>
---
 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(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f628967..061c128 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1562,7 +1562,7 @@ struct tcp_fastopen_request {
 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 ddd126d..e73ce79 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 e31e853c..f6324ea 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 dac56c4..4e39545 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 31b08ec..8c8f0f0 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -13,7 +13,7 @@
 
 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));
 }
 
-- 
1.8.3.1

[PATCH v5 3/4] ipv4: Namespaceify tcp_fastopen_key knob

[Haishuang Yan]

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>
---
 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(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index ce6dde0..66b8335 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;
@@ -128,6 +130,8 @@ 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 061c128..e27bd18 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1556,13 +1556,13 @@ 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 e73ce79..43a1bbe 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 f6324ea..20e19fe 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:
@@ -396,12 +398,6 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 		.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,
 		.maxlen		= sizeof(int),
@@ -1080,6 +1076,13 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 		.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 4e39545..23225c9 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 8c8f0f0..4eae44a 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 @@ int tcp_fastopen_reset_cipher(void *key, unsigned int len)
 	}
 	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 88409b1..49c74c0 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 @@ static int __net_init tcp_sk_init(struct net *net)
 
 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 = {
-- 
1.8.3.1

[PATCH v5 4/4] ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob

[Haishuang Yan]

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>
---
 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(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 66b8335..d76edde 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -132,6 +132,9 @@ 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 20e19fe..cac8dd3 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;
 }
@@ -398,14 +400,6 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 		.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,
 		.maxlen		= sizeof(int),
@@ -1083,6 +1077,14 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 		.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 4eae44a..de470e7 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -422,25 +422,16 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
  * 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 49c74c0..ad3b5bb 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:
-- 
1.8.3.1

Re: [PATCH v5 1/4] ipv4: Namespaceify tcp_fastopen knob

[David Miller]

From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:40 +0800

> 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>

Applied.

Re: [PATCH v5 2/4] ipv4: Remove the 'publish' logic in tcp_fastopen_init_key_once

[David Miller]

From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:41 +0800

> 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>

Applied.

Re: [PATCH v5 3/4] ipv4: Namespaceify tcp_fastopen_key knob

[David Miller]

From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:42 +0800

> 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>

Applied.

Re: [PATCH v5 4/4] ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob

[David Miller]

From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:43 +0800

> 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>

Applied.