From c1e64e298b8cad309091b95d8436a0255c84f54a Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Wed, 16 Dec 2015 12:30:05 +0900 Subject: net: diag: Support destroying TCP sockets. This implements SOCK_DESTROY for TCP sockets. It causes all blocking calls on the socket to fail fast with ECONNABORTED and causes a protocol close of the socket. It informs the other end of the connection by sending a RST, i.e., initiating a TCP ABORT as per RFC 793. ECONNABORTED was chosen for consistency with FreeBSD. Signed-off-by: Lorenzo Colitti Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db003438aaf5..7aa13bd3de29 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2342,6 +2342,7 @@ struct proto tcp_prot = { .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, #endif + .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); -- cgit v1.2.3 From 6dd9a14e92e54895e143f10fef4d0b9abe109aa9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 16 Dec 2015 13:20:44 -0800 Subject: net: Allow accepted sockets to be bound to l3mdev domain Allow accepted sockets to derive their sk_bound_dev_if setting from the l3mdev domain in which the packets originated. A sysctl setting is added to control the behavior which is similar to sk_mark and sysctl_tcp_fwmark_accept. This effectively allow a process to have a "VRF-global" listen socket, with child sockets bound to the VRF device in which the packet originated. A similar behavior can be achieved using sk_mark, but a solution using marks is incomplete as it does not handle duplicate addresses in different L3 domains/VRFs. Allowing sockets to inherit the sk_bound_dev_if from l3mdev domain provides a complete solution. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 8 ++++++++ include/net/inet_sock.h | 14 ++++++++++++++ include/net/netns/ipv4.h | 3 +++ net/ipv4/syncookies.c | 4 ++-- net/ipv4/sysctl_net_ipv4.c | 11 +++++++++++ net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 1 + net/ipv6/syncookies.c | 4 ++-- 8 files changed, 42 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 5de632ed0ec0..ceb44a095a27 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -335,6 +335,14 @@ tcp_keepalive_intvl - INTEGER after probes started. Default value: 75sec i.e. connection will be aborted after ~11 minutes of retries. +tcp_l3mdev_accept - BOOLEAN + Enables child sockets to inherit the L3 master device index. + Enabling this option allows a "global" listen socket to work + across L3 master domains (e.g., VRFs) with connected sockets + derived from the listen socket to be bound to the L3 domain in + which the packets originated. Only valid when the kernel was + compiled with CONFIG_NET_L3_MASTER_DEV. + tcp_low_latency - BOOLEAN If set, the TCP stack makes decisions that prefer lower latency as opposed to higher throughput. By default, this diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 625bdf95d673..012b1f91f3ec 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -28,6 +28,7 @@ #include #include #include +#include /** struct ip_options - IP Options * @@ -113,6 +114,19 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) return sk->sk_mark; } +static inline int inet_request_bound_dev_if(const struct sock *sk, + struct sk_buff *skb) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + struct net *net = sock_net(sk); + + if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + return l3mdev_master_ifindex_by_index(net, skb->skb_iif); +#endif + + return sk->sk_bound_dev_if; +} + struct inet_cork { unsigned int flags; __be32 addr; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c68926b4899c..d75be32650ba 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -86,6 +86,9 @@ struct netns_ipv4 { int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; +#ifdef CONFIG_NET_L3_MASTER_DEV + int sysctl_tcp_l3mdev_accept; +#endif int sysctl_tcp_mtu_probing; int sysctl_tcp_base_mss; int sysctl_tcp_probe_threshold; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 4cbe9f0a4281..643a86c49020 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -351,7 +351,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->snt_synack.v64 = 0; treq->tfo_listener = false; - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -371,7 +371,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark, + flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a0bd7a55193e..41ff1f87dfd7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -915,6 +915,17 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "tcp_l3mdev_accept", + .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d656eef7f8e..7b1fddc47019 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6204,7 +6204,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init(req, &tmp_opt, skb, sk); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ - inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; + inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); af_ops->init_req(req, sk, skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 205e6745393f..46e92fbd26a8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1276,6 +1276,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, ireq = inet_rsk(req); sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); + newsk->sk_bound_dev_if = ireq->ir_iif; newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = ireq->opt; rcu_assign_pointer(newinet->inet_opt, inet_opt); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index eaf7ac496d50..2906ef20795e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -193,7 +193,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->pktopts = skb; } - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) @@ -224,7 +224,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_oif = ireq->ir_iif; fl6.flowi6_mark = ireq->ir_mark; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; -- cgit v1.2.3 From e46787f0dd9385449fd77246d4fddb8634350af8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 21 Dec 2015 21:29:25 +0100 Subject: tcp: send_reset: test for non-NULL sk first tcp_md5_do_lookup requires a full socket, so once we extend _send_reset() to also accept timewait socket we would have to change if (!sk && hash_location) to something like if ((!sk || !sk_fullsock(sk)) && hash_location) { ... } else { (sk && sk_fullsock(sk)) tcp_md5_do_lookup() } Switch the two branches: check if we have a socket first, then fall back to a listener lookup if we saw a md5 option (hash_location). Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 11 +++++------ net/ipv6/tcp_ipv6.c | 6 +++--- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 46e92fbd26a8..eb29c2f5bcea 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -587,7 +587,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) } rep; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; + struct tcp_md5sig_key *key = NULL; const __u8 *hash_location = NULL; unsigned char newhash[16]; int genhash; @@ -627,7 +627,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (!sk && hash_location) { + if (sk) { + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, AF_INET); + } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -651,10 +654,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; - } else { - key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, - AF_INET) : NULL; } if (key) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f03d2b0445fd..32fa0de9982a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -854,7 +854,9 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (!sk && hash_location) { + if (sk) { + key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr); + } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -877,8 +879,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; - } else { - key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL; } #endif -- cgit v1.2.3 From 271c3b9b7bdae09c7da467ac1ae96e3298754977 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 21 Dec 2015 21:29:26 +0100 Subject: tcp: honour SO_BINDTODEVICE for TW_RST case too Hannes points out that when we generate tcp reset for timewait sockets we pretend we found no socket and pass NULL sk to tcp_vX_send_reset(). Make it cope with inet tw sockets and then provide tw sk. This makes RSTs appear on correct interface when SO_BINDTODEVICE is used. Packetdrill test case: // want default route to be used, we rely on BINDTODEVICE `ip route del 192.0.2.0/24 via 192.168.0.2 dev tun0` 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 // test case still works due to BINDTODEVICE 0.001 setsockopt(3, SOL_SOCKET, SO_BINDTODEVICE, "tun0", 4) = 0 0.100...0.200 connect(3, ..., ...) = 0 0.100 > S 0:0(0) 0.200 < S. 0:0(0) ack 1 win 32792 0.200 > . 1:1(0) ack 1 0.210 close(3) = 0 0.210 > F. 1:1(0) ack 1 win 29200 0.300 < . 1:1(0) ack 2 win 46 // more data while in FIN_WAIT2, expect RST 1.300 < P. 1:1001(1000) ack 1 win 46 // fails without this change -- default route is used 1.301 > R 1:1(0) win 0 Reported-by: Hannes Frederic Sowa Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 12 +++++++++--- net/ipv4/tcp_minisocks.c | 7 ++----- net/ipv6/tcp_ipv6.c | 6 ++++-- 3 files changed, 15 insertions(+), 10 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eb29c2f5bcea..fc4f72686705 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -627,7 +627,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (sk) { + if (sk && sk_fullsock(sk)) { key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) &ip_hdr(skb)->saddr, AF_INET); } else if (hash_location) { @@ -674,7 +674,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; - arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. @@ -682,6 +683,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; + BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != + offsetof(struct inet_timewait_sock, tw_bound_dev_if)); + arg.tos = ip_hdr(skb)->tos; ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -1705,7 +1709,9 @@ do_time_wait: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: - goto no_tcp_socket; + tcp_v4_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ac6b1961ffeb..75632a925824 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -131,7 +131,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, goto kill; if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt)) - goto kill_with_rst; + return TCP_TW_RST; /* Dup ACK? */ if (!th->ack || @@ -145,11 +145,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * reset. */ if (!th->fin || - TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { -kill_with_rst: - inet_twsk_deschedule_put(tw); + TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) return TCP_TW_RST; - } /* FIN arrived, enter true time-wait state. */ tw->tw_substate = TCP_TIME_WAIT; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 32fa0de9982a..9ecb012291cf 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -854,7 +854,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (sk) { + if (sk && sk_fullsock(sk)) { key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr); } else if (hash_location) { /* @@ -1516,7 +1516,9 @@ do_time_wait: break; case TCP_TW_RST: tcp_v6_restore_cb(skb); - goto no_tcp_socket; + tcp_v6_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; case TCP_TW_SUCCESS: ; } -- cgit v1.2.3 From 13b287e8d1cad951634389f85b8c9b816bd3bb1e Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 7 Jan 2016 16:38:43 +0200 Subject: ipv4: Namespaceify tcp_keepalive_time sysctl knob Different net namespaces might have different requirements as to the keepalive time of tcp sockets. This might be required in cases where different firewall rules are in place which require tcp timeout sockets to be increased/decreased independently of the host. Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 ++ include/net/tcp.h | 5 +++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 2 ++ net/ipv4/tcp_timer.c | 1 - 5 files changed, 14 insertions(+), 10 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d75be32650ba..9e9bbebaebd1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -94,6 +94,8 @@ struct netns_ipv4 { int sysctl_tcp_probe_threshold; u32 sysctl_tcp_probe_interval; + int sysctl_tcp_keepalive_time; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/include/net/tcp.h b/include/net/tcp.h index f33fecf4e282..cb4d4cf25744 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ 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_keepalive_time; extern int sysctl_tcp_keepalive_probes; extern int sysctl_tcp_keepalive_intvl; extern int sysctl_tcp_syn_retries; @@ -1230,7 +1229,9 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp) static inline int keepalive_time_when(const struct tcp_sock *tp) { - return tp->keepalive_time ? : sysctl_tcp_keepalive_time; + struct net *net = sock_net((struct sock *)tp); + + return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time; } static inline int keepalive_probes(const struct tcp_sock *tp) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 41ff1f87dfd7..1886cc842871 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -336,13 +336,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_keepalive_time", - .data = &sysctl_tcp_keepalive_time, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, { .procname = "tcp_keepalive_probes", .data = &sysctl_tcp_keepalive_probes, @@ -961,6 +954,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_keepalive_time", + .data = &init_net.ipv4.sysctl_tcp_keepalive_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fc4f72686705..6e14ff9a8580 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2385,6 +2385,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; + return 0; fail: tcp_sk_exit(net); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 193ba1fa8a9a..166f27b43cc0 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -24,7 +24,6 @@ int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_time __read_mostly = TCP_KEEPALIVE_TIME; int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES; int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; -- cgit v1.2.3 From 9bd6861bd4326e3afd3f14a9ec8a723771fb20bb Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 7 Jan 2016 16:38:44 +0200 Subject: ipv4: Namespecify tcp_keepalive_probes sysctl knob This is required to have full tcp keepalive mechanism namespace support. Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 5 +++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_timer.c | 1 - 5 files changed, 12 insertions(+), 10 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9e9bbebaebd1..6e26ea2d0374 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -95,6 +95,7 @@ struct netns_ipv4 { u32 sysctl_tcp_probe_interval; int sysctl_tcp_keepalive_time; + int sysctl_tcp_keepalive_probes; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index cb4d4cf25744..0646521400bf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ 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_keepalive_probes; extern int sysctl_tcp_keepalive_intvl; extern int sysctl_tcp_syn_retries; extern int sysctl_tcp_synack_retries; @@ -1236,7 +1235,9 @@ static inline int keepalive_time_when(const struct tcp_sock *tp) static inline int keepalive_probes(const struct tcp_sock *tp) { - return tp->keepalive_probes ? : sysctl_tcp_keepalive_probes; + struct net *net = sock_net((struct sock *)tp); + + return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes; } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1886cc842871..e99fbb77dba7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -336,13 +336,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_keepalive_probes", - .data = &sysctl_tcp_keepalive_probes, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_keepalive_intvl", .data = &sysctl_tcp_keepalive_intvl, @@ -961,6 +954,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "tcp_keepalive_probes", + .data = &init_net.ipv4.sysctl_tcp_keepalive_probes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6e14ff9a8580..ed98de85871e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2386,6 +2386,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; + net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; return 0; fail: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 166f27b43cc0..0ccb120d591a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -24,7 +24,6 @@ int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES; int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; -- cgit v1.2.3 From b840d15d39128d08ed4486085e5507d2617b9ae1 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 7 Jan 2016 16:38:45 +0200 Subject: ipv4: Namespecify the tcp_keepalive_intvl sysctl knob This is the final part required to namespaceify the tcp keep alive mechanism. Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 5 +++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_timer.c | 1 - 5 files changed, 12 insertions(+), 10 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6e26ea2d0374..2b7907a35568 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -96,6 +96,7 @@ struct netns_ipv4 { int sysctl_tcp_keepalive_time; int sysctl_tcp_keepalive_probes; + int sysctl_tcp_keepalive_intvl; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 0646521400bf..a80255f4ca33 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ 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_keepalive_intvl; extern int sysctl_tcp_syn_retries; extern int sysctl_tcp_synack_retries; extern int sysctl_tcp_retries1; @@ -1223,7 +1222,9 @@ void tcp_enter_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { - return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl; + struct net *net = sock_net((struct sock *)tp); + + return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl; } static inline int keepalive_time_when(const struct tcp_sock *tp) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e99fbb77dba7..46ce410703b1 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -336,13 +336,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_keepalive_intvl", - .data = &sysctl_tcp_keepalive_intvl, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, { .procname = "tcp_retries1", .data = &sysctl_tcp_retries1, @@ -961,6 +954,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_keepalive_intvl", + .data = &init_net.ipv4.sysctl_tcp_keepalive_intvl, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ed98de85871e..65947c1f4733 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2387,6 +2387,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; + net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; return 0; fail: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0ccb120d591a..a4730a28b220 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -24,7 +24,6 @@ int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; -- cgit v1.2.3