From 00fd38d938db3f1ab1c486549afc450cb7e751b1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Nov 2015 08:43:18 -0800 Subject: tcp: ensure proper barriers in lockless contexts Some functions access TCP sockets without holding a lock and might output non consistent data, depending on compiler and or architecture. tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... Introduce sk_state_load() and sk_state_store() to fix the issues, and more clearly document where this lack of locking is happening. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 950e28c0cdf2..ba09016d1bfd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2158,6 +2158,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); int rx_queue; + int state; if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || @@ -2175,17 +2176,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) timer_expires = jiffies; } - if (sk->sk_state == TCP_LISTEN) + state = sk_state_load(sk); + if (state == TCP_LISTEN) rx_queue = sk->sk_ack_backlog; else - /* - * because we dont lock socket, we might find a transient negative value + /* Because we don't lock the socket, + * we might find a transient negative value. */ rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", - i, src, srcp, dest, destp, sk->sk_state, + i, src, srcp, dest, destp, state, tp->write_seq - tp->snd_una, rx_queue, timer_active, @@ -2199,8 +2201,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - sk->sk_state == TCP_LISTEN ? - (fastopenq ? fastopenq->max_qlen : 0) : + state == TCP_LISTEN ? + fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } -- cgit v1.2.3 From 1b8e6a01e19f001e9f93b39c32387961c91ed3cc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 12:40:13 -0800 Subject: tcp: md5: fix lockdep annotation When a passive TCP is created, we eventually call tcp_md5_do_add() with sk pointing to the child. It is not owner by the user yet (we will add this socket into listener accept queue a bit later anyway) But we do own the spinlock, so amend the lockdep annotation to avoid following splat : [ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage! [ 8451.090932] [ 8451.090932] other info that might help us debug this: [ 8451.090932] [ 8451.090934] [ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1 [ 8451.090936] 3 locks held by socket_sockopt_/214795: [ 8451.090936] #0: (rcu_read_lock){.+.+..}, at: [] __netif_receive_skb_core+0x151/0xe90 [ 8451.090947] #1: (rcu_read_lock){.+.+..}, at: [] ip_local_deliver_finish+0x43/0x2b0 [ 8451.090952] #2: (slock-AF_INET){+.-...}, at: [] sk_clone_lock+0x1c5/0x500 [ 8451.090958] [ 8451.090958] stack backtrace: [ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_ [ 8451.091215] Call Trace: [ 8451.091216] [] dump_stack+0x55/0x76 [ 8451.091229] [] lockdep_rcu_suspicious+0xeb/0x110 [ 8451.091235] [] tcp_md5_do_add+0x1bf/0x1e0 [ 8451.091239] [] tcp_v4_syn_recv_sock+0x1f1/0x4c0 [ 8451.091242] [] ? tcp_v4_md5_hash_skb+0x167/0x190 [ 8451.091246] [] tcp_check_req+0x3c8/0x500 [ 8451.091249] [] ? tcp_v4_inbound_md5_hash+0x11e/0x190 [ 8451.091253] [] tcp_v4_rcv+0x3c0/0x9f0 [ 8451.091256] [] ? ip_local_deliver_finish+0x43/0x2b0 [ 8451.091260] [] ip_local_deliver_finish+0xb6/0x2b0 [ 8451.091263] [] ? ip_local_deliver_finish+0x43/0x2b0 [ 8451.091267] [] ip_local_deliver+0x48/0x80 [ 8451.091270] [] ip_rcv_finish+0x160/0x700 [ 8451.091273] [] ip_rcv+0x29e/0x3d0 [ 8451.091277] [] __netif_receive_skb_core+0xb47/0xe90 Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU") Signed-off-by: Eric Dumazet Reported-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ba09016d1bfd..db003438aaf5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -921,7 +921,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } md5sig = rcu_dereference_protected(tp->md5sig_info, - sock_owned_by_user(sk)); + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); if (!md5sig) { md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) -- cgit v1.2.3 From 5037e9ef9454917b047f9f3a19b4dd179fbf7cd4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Dec 2015 14:08:53 -0800 Subject: net: fix IP early demux races David Wilder reported crashes caused by dst reuse. I am seeing a crash on a distro V4.2.3 kernel caused by a double release of a dst_entry. In ipv4_dst_destroy() the call to list_empty() finds a poisoned next pointer, indicating the dst_entry has already been removed from the list and freed. The crash occurs 18 to 24 hours into a run of a network stress exerciser. Thanks to his detailed report and analysis, we were able to understand the core issue. IP early demux can associate a dst to skb, after a lookup in TCP/UDP sockets. When socket cache is not properly set, we want to store into sk->sk_dst_cache the dst for future IP early demux lookups, by acquiring a stable refcount on the dst. Problem is this acquisition is simply using an atomic_inc(), which works well, unless the dst was queued for destruction from dst_release() noticing dst refcount went to zero, if DST_NOCACHE was set on dst. We need to make sure current refcount is not zero before incrementing it, or risk double free as David reported. This patch, being a stable candidate, adds two new helpers, and use them only from IP early demux problematic paths. It might be possible to merge in net-next skb_dst_force() and skb_dst_force_safe(), but I prefer having the smallest patch for stable kernels : Maybe some skb_dst_force() callers do not expect skb->dst can suddenly be cleared. Can probably be backported back to linux-3.6 kernels Reported-by: David J. Wilder Tested-by: David J. Wilder Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db003438aaf5..d8841a2f1569 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1493,7 +1493,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (likely(sk->sk_rx_dst)) skb_dst_drop(skb); else - skb_dst_force(skb); + skb_dst_force_safe(skb); __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; @@ -1721,8 +1721,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { - dst_hold(dst); + if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } -- cgit v1.2.3 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 --- 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 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); -- 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 +++++------ 1 file changed, 5 insertions(+), 6 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) { -- 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 +++++++++--- 1 file changed, 9 insertions(+), 3 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; -- 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 --- net/ipv4/tcp_ipv4.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/tcp_ipv4.c') 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); -- 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 --- 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 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: -- 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 --- 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 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: -- cgit v1.2.3 From 3d596f7b907b0281b997cf30c92994a71ad0a1a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:05 -0800 Subject: net: tcp_memcontrol: protect all tcp_memcontrol calls by jump-label Move the jump-label from sock_update_memcg() and sock_release_memcg() to the callsite, and so eliminate those function calls when socket accounting is not enabled. This also eliminates the need for dummy functions because the calls will be optimized away if the Kconfig options are not enabled. Signed-off-by: Johannes Weiner Acked-by: David S. Miller Reviewed-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- net/ipv4/tcp_ipv4.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 65947c1f4733..eb39e02899e5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1818,7 +1818,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); - sock_release_memcg(sk); + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); -- cgit v1.2.3 From baac50bbc3cdfd184ebf586b1704edbfcee866df Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:17 -0800 Subject: net: tcp_memcontrol: simplify linkage between socket and page counter There won't be any separate counters for socket memory consumed by protocols other than TCP in the future. Remove the indirection and link sockets directly to their owning memory cgroup. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- net/ipv4/tcp_ipv4.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eb39e02899e5..c7d1fb50f381 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1819,7 +1819,7 @@ void tcp_v4_destroy_sock(struct sock *sk) sk_sockets_allocated_dec(sk); - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + if (mem_cgroup_sockets_enabled && sk->sk_memcg) sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2343,11 +2343,6 @@ struct proto tcp_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, -#endif -#ifdef CONFIG_MEMCG_KMEM - .init_cgroup = tcp_init_cgroup, - .destroy_cgroup = tcp_destroy_cgroup, - .proto_cgroup = tcp_proto_cgroup, #endif .diag_destroy = tcp_abort, }; -- cgit v1.2.3 From d55f90bfab40e3b5db323711d28186ff09461692 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 20 Jan 2016 15:02:44 -0800 Subject: net: drop tcp_memcontrol.c tcp_memcontrol.c only contains legacy memory.tcp.kmem.* file definitions and mem_cgroup->tcp_mem init/destroy stuff. This doesn't belong to network subsys. Let's move it to memcontrol.c. This also allows us to reuse generic code for handling legacy memcg files. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: "David S. Miller" Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- net/ipv4/tcp_ipv4.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c7d1fb50f381..5ced3e4013e3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -73,7 +73,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3