Merge branch 'ns-tcp-sysctls'

Nikolay Borisov says:

====================
Namespaceify more of the tcp sysctl knobs

This patch series continues making more of the tcp-related
sysctl knobs be per net-namespace. Most of these apply per
socket and have global defaults so should be safe and I
don't expect any breakages.

Having those per net-namespace is useful when multiple
containers are hosted and it is required to tune the
tcp settings for each independently of the host node.

I've split the patches to be per-sysctl but after
the review if the outcome is positive I'm happy
to either send it in one big blob or just.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/netns/ipv4.h

@@ -98,6 +98,16 @@ struct netns_ipv4 {
 	int sysctl_tcp_keepalive_probes;
 	int sysctl_tcp_keepalive_intvl;
 
+	int sysctl_tcp_syn_retries;
+	int sysctl_tcp_synack_retries;
+	int sysctl_tcp_syncookies;
+	int sysctl_tcp_reordering;
+	int sysctl_tcp_retries1;
+	int sysctl_tcp_retries2;
+	int sysctl_tcp_orphan_retries;
+	int sysctl_tcp_fin_timeout;
+	unsigned int sysctl_tcp_notsent_lowat;
+
 	struct ping_group_range ping_group_range;
 
 	atomic_t dev_addr_genid;

include/net/tcp.h

@@ -239,13 +239,6 @@ extern struct inet_timewait_death_row tcp_death_row;
 extern int sysctl_tcp_timestamps;
 extern int sysctl_tcp_window_scaling;
 extern int sysctl_tcp_sack;
-extern int sysctl_tcp_fin_timeout;
-extern int sysctl_tcp_syn_retries;
-extern int sysctl_tcp_synack_retries;
-extern int sysctl_tcp_retries1;
-extern int sysctl_tcp_retries2;
-extern int sysctl_tcp_orphan_retries;
-extern int sysctl_tcp_syncookies;
 extern int sysctl_tcp_fastopen;
 extern int sysctl_tcp_retrans_collapse;
 extern int sysctl_tcp_stdurg;
@@ -274,7 +267,6 @@ extern int sysctl_tcp_thin_dupack;
 extern int sysctl_tcp_early_retrans;
 extern int sysctl_tcp_limit_output_bytes;
 extern int sysctl_tcp_challenge_ack_limit;
-extern unsigned int sysctl_tcp_notsent_lowat;
 extern int sysctl_tcp_min_tso_segs;
 extern int sysctl_tcp_min_rtt_wlen;
 extern int sysctl_tcp_autocorking;
@@ -964,9 +956,11 @@ static inline void tcp_enable_fack(struct tcp_sock *tp)
  */
 static inline void tcp_enable_early_retrans(struct tcp_sock *tp)
 {
+	struct net *net = sock_net((struct sock *)tp);
+
 	tp->do_early_retrans = sysctl_tcp_early_retrans &&
 		sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack &&
-		sysctl_tcp_reordering == 3;
+		net->ipv4.sysctl_tcp_reordering == 3;
 }
 
 static inline void tcp_disable_early_retrans(struct tcp_sock *tp)
@@ -1253,7 +1247,7 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
 
 static inline int tcp_fin_time(const struct sock *sk)
 {
-	int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
+	int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
 	const int rto = inet_csk(sk)->icsk_rto;
 
 	if (fin_timeout < (rto << 2) - (rto >> 1))
@@ -1687,7 +1681,8 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
 
 static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 {
-	return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat;
+	struct net *net = sock_net((struct sock *)tp);
+	return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
 }
 
 static inline bool tcp_stream_memory_free(const struct sock *sk)

net/ipv4/inet_connection_sock.c

@@ -482,10 +482,6 @@ EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
 #define AF_INET_FAMILY(fam) true
 #endif
 
-/* Only thing we need from tcp.h */
-extern int sysctl_tcp_synack_retries;
-
-
 /* Decide when to expire the request and when to resend SYN-ACK */
 static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
 				  const int max_retries,
@@ -557,6 +553,7 @@ static void reqsk_timer_handler(unsigned long data)
 {
 	struct request_sock *req = (struct request_sock *)data;
 	struct sock *sk_listener = req->rsk_listener;
+	struct net *net = sock_net(sk_listener);
 	struct inet_connection_sock *icsk = inet_csk(sk_listener);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	int qlen, expire = 0, resend = 0;
@@ -566,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data)
 	if (sk_state_load(sk_listener) != TCP_LISTEN)
 		goto drop;
 
-	max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
 	thresh = max_retries;
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.

net/ipv4/syncookies.c

@@ -19,8 +19,6 @@
 #include <net/tcp.h>
 #include <net/route.h>
 
-extern int sysctl_tcp_syncookies;
-
 static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 
 #define COOKIEBITS 24	/* Upper bits store count */
@@ -307,7 +305,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	__u8 rcv_wscale;
 	struct flowi4 fl4;
 
-	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
+	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
 
 	if (tcp_synq_no_recent_overflow(sk))

net/ipv4/sysctl_net_ipv4.c

@@ -291,22 +291,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &ip_ttl_min,
 		.extra2		= &ip_ttl_max,
 	},
-	{
-		.procname	= "tcp_syn_retries",
-		.data		= &sysctl_tcp_syn_retries,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &tcp_syn_retries_min,
-		.extra2		= &tcp_syn_retries_max
-	},
-	{
-		.procname	= "tcp_synack_retries",
-		.data		= &sysctl_tcp_synack_retries,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tcp_max_orphans",
 		.data		= &sysctl_tcp_max_orphans,
@@ -335,37 +319,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "tcp_retries1",
-		.data		= &sysctl_tcp_retries1,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra2		= &tcp_retr1_max
-	},
-	{
-		.procname	= "tcp_retries2",
-		.data		= &sysctl_tcp_retries2,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_fin_timeout",
-		.data		= &sysctl_tcp_fin_timeout,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-#ifdef CONFIG_SYN_COOKIES
-	{
-		.procname	= "tcp_syncookies",
-		.data		= &sysctl_tcp_syncookies,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-#endif
 	{
 		.procname	= "tcp_fastopen",
 		.data		= &sysctl_tcp_fastopen,
@@ -459,13 +412,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{
-		.procname	= "tcp_orphan_retries",
-		.data		= &sysctl_tcp_orphan_retries,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tcp_fack",
 		.data		= &sysctl_tcp_fack,
@@ -480,13 +426,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "tcp_reordering",
-		.data		= &sysctl_tcp_reordering,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tcp_max_reordering",
 		.data		= &sysctl_tcp_max_reordering,
@@ -516,13 +455,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &one,
 	},
-	{
-		.procname	= "tcp_notsent_lowat",
-		.data		= &sysctl_tcp_notsent_lowat,
-		.maxlen		= sizeof(sysctl_tcp_notsent_lowat),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "tcp_rmem",
 		.data		= &sysctl_tcp_rmem,
@@ -960,6 +892,74 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+	{
+		.procname	= "tcp_syn_retries",
+		.data		= &init_net.ipv4.sysctl_tcp_syn_retries,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_syn_retries_min,
+		.extra2		= &tcp_syn_retries_max
+	},
+	{
+		.procname	= "tcp_synack_retries",
+		.data		= &init_net.ipv4.sysctl_tcp_synack_retries,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#ifdef CONFIG_SYN_COOKIES
+	{
+		.procname	= "tcp_syncookies",
+		.data		= &init_net.ipv4.sysctl_tcp_syncookies,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif
+	{
+		.procname	= "tcp_reordering",
+		.data		= &init_net.ipv4.sysctl_tcp_reordering,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_retries1",
+		.data		= &init_net.ipv4.sysctl_tcp_retries1,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra2		= &tcp_retr1_max
+	},
+	{
+		.procname	= "tcp_retries2",
+		.data		= &init_net.ipv4.sysctl_tcp_retries2,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_orphan_retries",
+		.data		= &init_net.ipv4.sysctl_tcp_orphan_retries,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_fin_timeout",
+		.data		= &init_net.ipv4.sysctl_tcp_fin_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "tcp_notsent_lowat",
+		.data		= &init_net.ipv4.sysctl_tcp_notsent_lowat,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 

net/ipv4/tcp.c

@@ -282,8 +282,6 @@
 #include <asm/unaligned.h>
 #include <net/busy_poll.h>
 
-int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
-
 int sysctl_tcp_min_tso_segs __read_mostly = 2;
 
 int sysctl_tcp_autocorking __read_mostly = 1;
@@ -406,7 +404,7 @@ void tcp_init_sock(struct sock *sk)
 	tp->mss_cache = TCP_MSS_DEFAULT;
 	u64_stats_init(&tp->syncp);
 
-	tp->reordering = sysctl_tcp_reordering;
+	tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
 	tcp_enable_early_retrans(tp);
 	tcp_assign_congestion_control(sk);
 
@@ -2330,6 +2328,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct net *net = sock_net(sk);
 	int val;
 	int err = 0;
 
@@ -2526,7 +2525,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_LINGER2:
 		if (val < 0)
 			tp->linger2 = -1;
-		else if (val > sysctl_tcp_fin_timeout / HZ)
+		else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ)
 			tp->linger2 = 0;
 		else
 			tp->linger2 = val * HZ;
@@ -2731,6 +2730,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	int val, len;
 
 	if (get_user(len, optlen))
@@ -2765,12 +2765,12 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = keepalive_probes(tp);
 		break;
 	case TCP_SYNCNT:
-		val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+		val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
 		break;
 	case TCP_LINGER2:
 		val = tp->linger2;
 		if (val >= 0)
-			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
+			val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
 		val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,

net/ipv4/tcp_input.c

@@ -80,9 +80,7 @@ int sysctl_tcp_timestamps __read_mostly = 1;
 int sysctl_tcp_window_scaling __read_mostly = 1;
 int sysctl_tcp_sack __read_mostly = 1;
 int sysctl_tcp_fack __read_mostly = 1;
-int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
 int sysctl_tcp_max_reordering __read_mostly = 300;
-EXPORT_SYMBOL(sysctl_tcp_reordering);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 1;
@@ -1883,6 +1881,7 @@ void tcp_enter_loss(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	struct sk_buff *skb;
 	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
@@ -1933,9 +1932,9 @@ void tcp_enter_loss(struct sock *sk)
 	 * suggests that the degree of reordering is over-estimated.
 	 */
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
-	    tp->sacked_out >= sysctl_tcp_reordering)
+	    tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
 		tp->reordering = min_t(unsigned int, tp->reordering,
-				       sysctl_tcp_reordering);
+				       net->ipv4.sysctl_tcp_reordering);
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
@@ -2119,6 +2118,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 packets_out;
+	int tcp_reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
 
 	/* Trick#1: The loss is proven. */
 	if (tp->lost_out)
@@ -2133,7 +2133,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 	 */
 	packets_out = tp->packets_out;
 	if (packets_out <= tp->reordering &&
-	    tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
+	    tp->sacked_out >= max_t(__u32, packets_out/2, tcp_reordering) &&
 	    !tcp_may_send_now(sk)) {
 		/* We have nothing to send. This connection is limited
 		 * either by receiver window or by application.
@@ -3317,7 +3317,7 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
 	 * new SACK or ECE mark may first advance cwnd here and later reduce
 	 * cwnd in tcp_fastretrans_alert() based on more states.
 	 */
-	if (tcp_sk(sk)->reordering > sysctl_tcp_reordering)
+	if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
 		return flag & FLAG_FORWARD_PROGRESS;
 
 	return flag & FLAG_DATA_ACKED;
@@ -6163,9 +6163,10 @@ static bool tcp_syn_flood_action(const struct sock *sk,
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	const char *msg = "Dropping request";
 	bool want_cookie = false;
+	struct net *net = sock_net(sk);
 
 #ifdef CONFIG_SYN_COOKIES
-	if (sysctl_tcp_syncookies) {
+	if (net->ipv4.sysctl_tcp_syncookies) {
 		msg = "Sending cookies";
 		want_cookie = true;
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
@@ -6174,7 +6175,7 @@ static bool tcp_syn_flood_action(const struct sock *sk,
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
 
 	if (!queue->synflood_warned &&
-	    sysctl_tcp_syncookies != 2 &&
+	    net->ipv4.sysctl_tcp_syncookies != 2 &&
 	    xchg(&queue->synflood_warned, 1) == 0)
 		pr_info("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
 			proto, ntohs(tcp_hdr(skb)->dest), msg);
@@ -6207,6 +6208,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
 	struct tcp_options_received tmp_opt;
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	struct sock *fastopen_sk = NULL;
 	struct dst_entry *dst = NULL;
 	struct request_sock *req;
@@ -6217,7 +6219,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	 * limitations, they conserve resources and peer is
 	 * evidently real one.
 	 */
-	if ((sysctl_tcp_syncookies == 2 ||
+	if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
 	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
 		want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
 		if (!want_cookie)
@@ -6283,7 +6285,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			}
 		}
 		/* Kill the following clause, if you dislike this way. */
-		else if (!sysctl_tcp_syncookies &&
+		else if (!net->ipv4.sysctl_tcp_syncookies &&
 			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
 			  (sysctl_max_syn_backlog >> 2)) &&
 			 !tcp_peer_is_proven(req, dst, false,

net/ipv4/tcp_ipv4.c

@@ -860,7 +860,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
 	kfree(inet_rsk(req)->opt);
 }
 
-
 #ifdef CONFIG_TCP_MD5SIG
 /*
  * RFC2385 MD5 checksumming requires a mapping of
@@ -2388,6 +2387,16 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
 	net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
 
+	net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES;
+	net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES;
+	net->ipv4.sysctl_tcp_syncookies = 0;
+	net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH;
+	net->ipv4.sysctl_tcp_retries1 = TCP_RETR1;
+	net->ipv4.sysctl_tcp_retries2 = TCP_RETR2;
+	net->ipv4.sysctl_tcp_orphan_retries = 0;
+	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
+	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+
 	return 0;
 fail:
 	tcp_sk_exit(net);

net/ipv4/tcp_metrics.c

@@ -369,6 +369,7 @@ void tcp_update_metrics(struct sock *sk)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	struct tcp_metrics_block *tm;
 	unsigned long rtt;
 	u32 val;
@@ -473,7 +474,7 @@ void tcp_update_metrics(struct sock *sk)
 		if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
 			val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
 			if (val < tp->reordering &&
-			    tp->reordering != sysctl_tcp_reordering)
+			    tp->reordering != net->ipv4.sysctl_tcp_reordering)
 				tcp_metric_set(tm, TCP_METRIC_REORDERING,
 					       tp->reordering);
 		}

net/ipv4/tcp_minisocks.c

@@ -27,9 +27,6 @@
 #include <net/inet_common.h>
 #include <net/xfrm.h>
 
-int sysctl_tcp_syncookies __read_mostly = 1;
-EXPORT_SYMBOL(sysctl_tcp_syncookies);
-
 int sysctl_tcp_abort_on_overflow __read_mostly;
 
 struct inet_timewait_death_row tcp_death_row = {

net/ipv4/tcp_output.c

@@ -62,9 +62,6 @@ int sysctl_tcp_tso_win_divisor __read_mostly = 3;
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
-unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
-EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);
-
 static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			   int push_one, gfp_t gfp);
 
@@ -3476,6 +3473,7 @@ void tcp_send_probe0(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	unsigned long probe_max;
 	int err;
 
@@ -3489,7 +3487,7 @@ void tcp_send_probe0(struct sock *sk)
 	}
 
 	if (err <= 0) {
-		if (icsk->icsk_backoff < sysctl_tcp_retries2)
+		if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
 			icsk->icsk_backoff++;
 		icsk->icsk_probes_out++;
 		probe_max = TCP_RTO_MAX;

net/ipv4/tcp_timer.c

@@ -22,11 +22,6 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES;
-int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES;
-int sysctl_tcp_retries1 __read_mostly = TCP_RETR1;
-int sysctl_tcp_retries2 __read_mostly = TCP_RETR2;
-int sysctl_tcp_orphan_retries __read_mostly;
 int sysctl_tcp_thin_linear_timeouts __read_mostly;
 
 static void tcp_write_err(struct sock *sk)
@@ -82,7 +77,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 /* Calculate maximal number or retries on an orphaned socket. */
 static int tcp_orphan_retries(struct sock *sk, bool alive)
 {
-	int retries = sysctl_tcp_orphan_retries; /* May be zero. */
+	int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */
 
 	/* We know from an ICMP that something is wrong. */
 	if (sk->sk_err_soft && !alive)
@@ -157,6 +152,7 @@ static int tcp_write_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	int retry_until;
 	bool do_reset, syn_set = false;
 
@@ -169,10 +165,10 @@ static int tcp_write_timeout(struct sock *sk)
 				NET_INC_STATS_BH(sock_net(sk),
 						 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		}
-		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
 		syn_set = true;
 	} else {
-		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+		if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) {
 			/* Some middle-boxes may black-hole Fast Open _after_
 			 * the handshake. Therefore we conservatively disable
 			 * Fast Open on this path on recurring timeouts with
@@ -181,7 +177,7 @@ static int tcp_write_timeout(struct sock *sk)
 			if (tp->syn_data_acked &&
 			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
 				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
-				if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+				if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1)
 					NET_INC_STATS_BH(sock_net(sk),
 							 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 			}
@@ -191,7 +187,7 @@ static int tcp_write_timeout(struct sock *sk)
 			dst_negative_advice(sk);
 		}
 
-		retry_until = sysctl_tcp_retries2;
+		retry_until = net->ipv4.sysctl_tcp_retries2;
 		if (sock_flag(sk, SOCK_DEAD)) {
 			const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
 
@@ -305,7 +301,7 @@ static void tcp_probe_timer(struct sock *sk)
 		 (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout)
 		goto abort;
 
-	max_probes = sysctl_tcp_retries2;
+	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
 	if (sock_flag(sk, SOCK_DEAD)) {
 		const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
 
@@ -332,7 +328,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int max_retries = icsk->icsk_syn_retries ? :
-	    sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
+	    sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
 	struct request_sock *req;
 
 	req = tcp_sk(sk)->fastopen_rsk;
@@ -360,6 +356,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 void tcp_retransmit_timer(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (tp->fastopen_rsk) {
@@ -490,7 +487,7 @@ out_reset_timer:
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
-	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0))
+	if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0))
 		__sk_dst_reset(sk);
 
 out:;

net/ipv6/syncookies.c

@@ -148,7 +148,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
 
-	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
+	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
 
 	if (tcp_synq_no_recent_overflow(sk))