From 4e3fd7a06dc20b2d8ec6892233ad2012968fe7b6 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 21 Nov 2011 03:39:03 +0000 Subject: net: remove ipv6_addr_copy() C assignment can handle struct in6_addr copying. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 46 ++++++++++++++++++++++------------------------ 1 file changed, 22 insertions(+), 24 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 36131d122a6f..fd98dd010fcb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -153,7 +153,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } @@ -195,7 +195,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->write_seq = 0; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); + np->daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -244,9 +244,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, saddr = &np->rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, - (saddr ? saddr : &np->saddr)); + fl6.daddr = np->daddr; + fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; @@ -264,11 +263,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - ipv6_addr_copy(&np->rcv_saddr, saddr); + np->rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); + np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; @@ -398,8 +397,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; @@ -489,8 +488,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); - ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.daddr = treq->rmt_addr; + fl6.saddr = treq->loc_addr; fl6.flowlabel = 0; fl6.flowi6_oif = treq->iif; fl6.flowi6_mark = sk->sk_mark; @@ -512,7 +511,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + fl6.daddr = treq->rmt_addr; err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -617,8 +616,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, tp->md5sig_info->alloced6++; } - ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr, - peer); + tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer; tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey; tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen; @@ -750,8 +748,8 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, bp = &hp->md5_blk.ip6; /* 1. TCP pseudo-header (RFC2460) */ - ipv6_addr_copy(&bp->saddr, saddr); - ipv6_addr_copy(&bp->daddr, daddr); + bp->saddr = *saddr; + bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); @@ -1039,8 +1037,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, #endif memset(&fl6, 0, sizeof(fl6)); - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr); + fl6.daddr = ipv6_hdr(skb)->saddr; + fl6.saddr = ipv6_hdr(skb)->daddr; buff->ip_summed = CHECKSUM_PARTIAL; buff->csum = 0; @@ -1250,8 +1248,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); treq = inet6_rsk(req); - ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); + treq->rmt_addr = ipv6_hdr(skb)->saddr; + treq->loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, tcp_hdr(skb)); @@ -1380,7 +1378,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newnp->rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1444,9 +1442,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr); - ipv6_addr_copy(&newnp->saddr, &treq->loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr); + newnp->daddr = treq->rmt_addr; + newnp->saddr = treq->loc_addr; + newnp->rcv_saddr = treq->loc_addr; newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... -- cgit v1.2.3 From 180d8cd942ce336b2c869d324855c40c5db478ad Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Sun, 11 Dec 2011 21:47:02 +0000 Subject: foundations of per-cgroup memory pressure controlling. This patch replaces all uses of struct sock fields' memory_pressure, memory_allocated, sockets_allocated, and sysctl_mem to acessor macros. Those macros can either receive a socket argument, or a mem_cgroup argument, depending on the context they live in. Since we're only doing a macro wrapping here, no performance impact at all is expected in the case where we don't have cgroups disabled. Signed-off-by: Glauber Costa Reviewed-by: Hiroyouki Kamezawa CC: David S. Miller CC: Eric W. Biederman CC: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++- include/net/tcp.h | 3 +- net/core/sock.c | 57 ++++++++++++++++++------------ net/ipv4/proc.c | 6 ++-- net/ipv4/tcp_input.c | 12 +++---- net/ipv4/tcp_ipv4.c | 4 +-- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 145 insertions(+), 39 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/include/net/sock.h b/include/net/sock.h index 8ac338cb39ce..ed0dbf034539 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -53,6 +53,7 @@ #include #include #include +#include #include #include @@ -867,6 +868,99 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ +static inline bool sk_has_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure != NULL; +} + +static inline bool sk_under_memory_pressure(const struct sock *sk) +{ + if (!sk->sk_prot->memory_pressure) + return false; + return !!*sk->sk_prot->memory_pressure; +} + +static inline void sk_leave_memory_pressure(struct sock *sk) +{ + int *memory_pressure = sk->sk_prot->memory_pressure; + + if (memory_pressure && *memory_pressure) + *memory_pressure = 0; +} + +static inline void sk_enter_memory_pressure(struct sock *sk) +{ + if (sk->sk_prot->enter_memory_pressure) + sk->sk_prot->enter_memory_pressure(sk); +} + +static inline long sk_prot_mem_limits(const struct sock *sk, int index) +{ + long *prot = sk->sk_prot->sysctl_mem; + return prot[index]; +} + +static inline long +sk_memory_allocated(const struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + return atomic_long_read(prot->memory_allocated); +} + +static inline long +sk_memory_allocated_add(struct sock *sk, int amt) +{ + struct proto *prot = sk->sk_prot; + return atomic_long_add_return(amt, prot->memory_allocated); +} + +static inline void +sk_memory_allocated_sub(struct sock *sk, int amt) +{ + struct proto *prot = sk->sk_prot; + atomic_long_sub(amt, prot->memory_allocated); +} + +static inline void sk_sockets_allocated_dec(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + percpu_counter_dec(prot->sockets_allocated); +} + +static inline void sk_sockets_allocated_inc(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + percpu_counter_inc(prot->sockets_allocated); +} + +static inline int +sk_sockets_allocated_read_positive(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + return percpu_counter_sum_positive(prot->sockets_allocated); +} + +static inline int +proto_sockets_allocated_sum_positive(struct proto *prot) +{ + return percpu_counter_sum_positive(prot->sockets_allocated); +} + +static inline long +proto_memory_allocated(struct proto *prot) +{ + return atomic_long_read(prot->memory_allocated); +} + +static inline bool +proto_memory_pressure(struct proto *prot) +{ + if (!prot->memory_pressure) + return false; + return !!*prot->memory_pressure; +} + #ifdef CONFIG_PROC_FS /* Called with local bh disabled */ @@ -1674,7 +1768,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk) page = alloc_pages(sk->sk_allocation, 0); if (!page) { - sk->sk_prot->enter_memory_pressure(sk); + sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return page; diff --git a/include/net/tcp.h b/include/net/tcp.h index 02f070d339ba..913473b4eda7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -44,6 +44,7 @@ #include #include +#include extern struct inet_hashinfo tcp_hashinfo; @@ -285,7 +286,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) } if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]) + sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } diff --git a/net/core/sock.c b/net/core/sock.c index 9777da86aeac..a3d4205e7238 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1323,7 +1323,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_wq = NULL; if (newsk->sk_prot->sockets_allocated) - percpu_counter_inc(newsk->sk_prot->sockets_allocated); + sk_sockets_allocated_inc(newsk); if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); @@ -1713,28 +1713,28 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) long allocated; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = atomic_long_add_return(amt, prot->memory_allocated); + + allocated = sk_memory_allocated_add(sk, amt); /* Under limit. */ - if (allocated <= prot->sysctl_mem[0]) { - if (prot->memory_pressure && *prot->memory_pressure) - *prot->memory_pressure = 0; + if (allocated <= sk_prot_mem_limits(sk, 0)) { + sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ - if (allocated > prot->sysctl_mem[1]) - if (prot->enter_memory_pressure) - prot->enter_memory_pressure(sk); + if (allocated > sk_prot_mem_limits(sk, 1)) + sk_enter_memory_pressure(sk); /* Over hard limit. */ - if (allocated > prot->sysctl_mem[2]) + if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0]) return 1; + } else { /* SK_MEM_SEND */ if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) @@ -1744,13 +1744,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) return 1; } - if (prot->memory_pressure) { + if (sk_has_memory_pressure(sk)) { int alloc; - if (!*prot->memory_pressure) + if (!sk_under_memory_pressure(sk)) return 1; - alloc = percpu_counter_read_positive(prot->sockets_allocated); - if (prot->sysctl_mem[2] > alloc * + alloc = sk_sockets_allocated_read_positive(sk); + if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) @@ -1773,7 +1773,9 @@ suppress_allocation: /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - atomic_long_sub(amt, prot->memory_allocated); + + sk_memory_allocated_sub(sk, amt); + return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -1784,15 +1786,13 @@ EXPORT_SYMBOL(__sk_mem_schedule); */ void __sk_mem_reclaim(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, - prot->memory_allocated); + sk_memory_allocated_sub(sk, + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; - if (prot->memory_pressure && *prot->memory_pressure && - (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0])) - *prot->memory_pressure = 0; + if (sk_under_memory_pressure(sk) && + (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) + sk_leave_memory_pressure(sk); } EXPORT_SYMBOL(__sk_mem_reclaim); @@ -2507,16 +2507,27 @@ static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } +static long sock_prot_memory_allocated(struct proto *proto) +{ + return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L; +} + +static char *sock_prot_memory_pressure(struct proto *proto) +{ + return proto->memory_pressure != NULL ? + proto_memory_pressure(proto) ? "yes" : "no" : "NI"; +} static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { + seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), - proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L, - proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI", + sock_prot_memory_allocated(proto), + sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 961eed4f510a..3569d8ecaeac 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -56,17 +56,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) local_bh_disable(); orphans = percpu_counter_sum_positive(&tcp_orphan_count); - sockets = percpu_counter_sum_positive(&tcp_sockets_allocated); + sockets = proto_sockets_allocated_sum_positive(&tcp_prot); local_bh_enable(); socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, tcp_death_row.tw_count, sockets, - atomic_long_read(&tcp_memory_allocated)); + proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), - atomic_long_read(&udp_memory_allocated)); + proto_memory_allocated(&udp_prot)); seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b9cbc351c511..f131d92d25ee 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -322,7 +322,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* Check #1 */ if (tp->rcv_ssthresh < tp->window_clamp && (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_memory_pressure) { + !sk_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -411,8 +411,8 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && - !tcp_memory_pressure && - atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { + !sk_under_memory_pressure(sk) && + sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } @@ -4866,7 +4866,7 @@ static int tcp_prune_queue(struct sock *sk) if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); - else if (tcp_memory_pressure) + else if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); tcp_collapse_ofo_queue(sk); @@ -4932,11 +4932,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk) return 0; /* If we are under global TCP memory pressure, do not expand. */ - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) return 0; /* If we are under soft global TCP memory pressure, do not expand. */ - if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0)) return 0; /* If we filled the congestion window, do not expand. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c4b8b09db9f5..f48bf312cfe8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1917,7 +1917,7 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); + sk_sockets_allocated_inc(sk); local_bh_enable(); return 0; @@ -1973,7 +1973,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tp->cookie_values = NULL; } - percpu_counter_dec(&tcp_sockets_allocated); + sk_sockets_allocated_dec(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cf3068038942..8c8de2780c7a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1922,7 +1922,7 @@ u32 __tcp_select_window(struct sock *sk) if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index aa39a692f4c8..40a41f077981 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -261,7 +261,7 @@ static void tcp_delack_timer(unsigned long data) } out: - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); out_unlock: bh_unlock_sock(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9d74eee334d6..b69c7030aba9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1994,7 +1994,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); + sk_sockets_allocated_inc(sk); local_bh_enable(); return 0; -- cgit v1.2.3 From d1a4c0b37c296e600ffe08edb0db2dc1b8f550d7 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Sun, 11 Dec 2011 21:47:04 +0000 Subject: tcp memory pressure controls This patch introduces memory pressure controls for the tcp protocol. It uses the generic socket memory pressure code introduced in earlier patches, and fills in the necessary data in cg_proto struct. Signed-off-by: Glauber Costa Reviewed-by: KAMEZAWA Hiroyuki CC: Eric W. Biederman Signed-off-by: David S. Miller --- Documentation/cgroups/memory.txt | 2 ++ include/linux/memcontrol.h | 1 + include/net/sock.h | 2 ++ include/net/tcp_memcontrol.h | 17 +++++++++ mm/memcontrol.c | 40 +++++++++++++++++++++- net/core/sock.c | 43 +++++++++++++++++++++-- net/ipv4/Makefile | 1 + net/ipv4/tcp_ipv4.c | 9 ++++- net/ipv4/tcp_memcontrol.c | 74 ++++++++++++++++++++++++++++++++++++++++ net/ipv6/tcp_ipv6.c | 5 +++ 10 files changed, 189 insertions(+), 5 deletions(-) create mode 100644 include/net/tcp_memcontrol.h create mode 100644 net/ipv4/tcp_memcontrol.c (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 23a8dc5319a3..687dea5bf1fd 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -293,6 +293,8 @@ to trigger slab reclaim when those limits are reached. thresholds. The Memory Controller allows them to be controlled individually per cgroup, instead of globally. +* tcp memory pressure: sockets memory pressure for the tcp protocol. + 3. User Interface 0. Configuration diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f15021b9f734..1513994ce207 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -86,6 +86,7 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); +extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont); static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) diff --git a/include/net/sock.h b/include/net/sock.h index d5eab256167c..18ecc9919d29 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -64,6 +64,8 @@ #include #include +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss); +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss); /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h new file mode 100644 index 000000000000..5f5e1582d764 --- /dev/null +++ b/include/net/tcp_memcontrol.h @@ -0,0 +1,17 @@ +#ifndef _TCP_MEMCG_H +#define _TCP_MEMCG_H + +struct tcp_memcontrol { + struct cg_proto cg_proto; + /* per-cgroup tcp memory pressure knobs */ + struct res_counter tcp_memory_allocated; + struct percpu_counter tcp_sockets_allocated; + /* those two are read-mostly, leave them at the end */ + long tcp_prot_mem[3]; + int tcp_memory_pressure; +}; + +struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); +int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +#endif /* _TCP_MEMCG_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3de3901ae0a7..7266202fa7cf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -50,6 +50,8 @@ #include #include #include "internal.h" +#include +#include #include @@ -295,6 +297,10 @@ struct mem_cgroup { */ struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; + +#ifdef CONFIG_INET + struct tcp_memcontrol tcp_mem; +#endif }; /* Stuffs for move charges at task migration. */ @@ -384,6 +390,7 @@ static void mem_cgroup_put(struct mem_cgroup *memcg); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM #ifdef CONFIG_INET #include +#include static bool mem_cgroup_is_root(struct mem_cgroup *memcg); void sock_update_memcg(struct sock *sk) @@ -418,6 +425,15 @@ void sock_release_memcg(struct sock *sk) mem_cgroup_put(memcg); } } + +struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) +{ + if (!memcg || mem_cgroup_is_root(memcg)) + return NULL; + + return &memcg->tcp_mem.cg_proto; +} +EXPORT_SYMBOL(tcp_proto_cgroup); #endif /* CONFIG_INET */ #endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ @@ -800,7 +816,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) preempt_enable(); } -static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) +struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { return container_of(cgroup_subsys_state(cont, mem_cgroup_subsys_id), struct mem_cgroup, @@ -4732,14 +4748,34 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) ret = cgroup_add_files(cont, ss, kmem_cgroup_files, ARRAY_SIZE(kmem_cgroup_files)); + + /* + * Part of this would be better living in a separate allocation + * function, leaving us with just the cgroup tree population work. + * We, however, depend on state such as network's proto_list that + * is only initialized after cgroup creation. I found the less + * cumbersome way to deal with it to defer it all to populate time + */ + if (!ret) + ret = mem_cgroup_sockets_init(cont, ss); return ret; }; +static void kmem_cgroup_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + mem_cgroup_sockets_destroy(cont, ss); +} #else static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) { return 0; } + +static void kmem_cgroup_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ +} #endif static struct cftype mem_cgroup_files[] = { @@ -5098,6 +5134,8 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + kmem_cgroup_destroy(ss, cont); + mem_cgroup_put(memcg); } diff --git a/net/core/sock.c b/net/core/sock.c index 6a871b8fdd20..5a6a90620656 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -136,6 +136,46 @@ #include #endif +static DEFINE_RWLOCK(proto_list_lock); +static LIST_HEAD(proto_list); + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct proto *proto; + int ret = 0; + + read_lock(&proto_list_lock); + list_for_each_entry(proto, &proto_list, node) { + if (proto->init_cgroup) { + ret = proto->init_cgroup(cgrp, ss); + if (ret) + goto out; + } + } + + read_unlock(&proto_list_lock); + return ret; +out: + list_for_each_entry_continue_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(cgrp, ss); + read_unlock(&proto_list_lock); + return ret; +} + +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct proto *proto; + + read_lock(&proto_list_lock); + list_for_each_entry_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(cgrp, ss); + read_unlock(&proto_list_lock); +} +#endif + /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -2291,9 +2331,6 @@ void sk_common_release(struct sock *sk) } EXPORT_SYMBOL(sk_common_release); -static DEFINE_RWLOCK(proto_list_lock); -static LIST_HEAD(proto_list); - #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index e9d98e621112..ff75d3bbcd6a 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o +obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f48bf312cfe8..42714cb1fef3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -73,6 +73,7 @@ #include #include #include +#include #include #include @@ -1917,6 +1918,7 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); @@ -1974,6 +1976,7 @@ void tcp_v4_destroy_sock(struct sock *sk) } sk_sockets_allocated_dec(sk); + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2634,10 +2637,14 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + .init_cgroup = tcp_init_cgroup, + .destroy_cgroup = tcp_destroy_cgroup, + .proto_cgroup = tcp_proto_cgroup, +#endif }; EXPORT_SYMBOL(tcp_prot); - static int __net_init tcp_sk_init(struct net *net) { return inet_ctl_sock_create(&net->ipv4.tcp_sock, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c new file mode 100644 index 000000000000..4a68d2c24556 --- /dev/null +++ b/net/ipv4/tcp_memcontrol.c @@ -0,0 +1,74 @@ +#include +#include +#include +#include +#include + +static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) +{ + return container_of(cg_proto, struct tcp_memcontrol, cg_proto); +} + +static void memcg_tcp_enter_memory_pressure(struct sock *sk) +{ + if (!sk->sk_cgrp->memory_pressure) + *sk->sk_cgrp->memory_pressure = 1; +} +EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); + +int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + /* + * The root cgroup does not use res_counters, but rather, + * rely on the data already collected by the network + * subsystem + */ + struct res_counter *res_parent = NULL; + struct cg_proto *cg_proto, *parent_cg; + struct tcp_memcontrol *tcp; + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return 0; + + tcp = tcp_from_cgproto(cg_proto); + + tcp->tcp_prot_mem[0] = sysctl_tcp_mem[0]; + tcp->tcp_prot_mem[1] = sysctl_tcp_mem[1]; + tcp->tcp_prot_mem[2] = sysctl_tcp_mem[2]; + tcp->tcp_memory_pressure = 0; + + parent_cg = tcp_prot.proto_cgroup(parent); + if (parent_cg) + res_parent = parent_cg->memory_allocated; + + res_counter_init(&tcp->tcp_memory_allocated, res_parent); + percpu_counter_init(&tcp->tcp_sockets_allocated, 0); + + cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure; + cg_proto->memory_pressure = &tcp->tcp_memory_pressure; + cg_proto->sysctl_mem = tcp->tcp_prot_mem; + cg_proto->memory_allocated = &tcp->tcp_memory_allocated; + cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; + cg_proto->memcg = memcg; + + return 0; +} +EXPORT_SYMBOL(tcp_init_cgroup); + +void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct cg_proto *cg_proto; + struct tcp_memcontrol *tcp; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return; + + tcp = tcp_from_cgproto(cg_proto); + percpu_counter_destroy(&tcp->tcp_sockets_allocated); +} +EXPORT_SYMBOL(tcp_destroy_cgroup); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b69c7030aba9..95d3cfb65d39 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -62,6 +62,7 @@ #include #include #include +#include #include @@ -1994,6 +1995,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); @@ -2227,6 +2229,9 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + .proto_cgroup = tcp_proto_cgroup, +#endif }; static const struct inet6_protocol tcpv6_protocol = { -- cgit v1.2.3 From 3dc43e3e4d0b52197d3205214fe8f162f9e0c334 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Sun, 11 Dec 2011 21:47:05 +0000 Subject: per-netns ipv4 sysctl_tcp_mem This patch allows each namespace to independently set up its levels for tcp memory pressure thresholds. This patch alone does not buy much: we need to make this values per group of process somehow. This is achieved in the patches that follows in this patchset. Signed-off-by: Glauber Costa Reviewed-by: KAMEZAWA Hiroyuki CC: David S. Miller CC: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/af_inet.c | 2 ++ net/ipv4/sysctl_net_ipv4.c | 51 +++++++++++++++++++++++++++++++++++++++------- net/ipv4/tcp.c | 11 ++-------- net/ipv4/tcp_ipv4.c | 1 - net/ipv4/tcp_memcontrol.c | 9 +++++--- net/ipv6/af_inet6.c | 2 ++ net/ipv6/tcp_ipv6.c | 1 - 9 files changed, 57 insertions(+), 22 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d786b4fc02a4..bbd023a1c9b9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -55,6 +55,7 @@ struct netns_ipv4 { int current_rt_cache_rebuild_count; unsigned int sysctl_ping_group_range[2]; + long sysctl_tcp_mem[3]; atomic_t rt_genid; atomic_t dev_addr_genid; diff --git a/include/net/tcp.h b/include/net/tcp.h index 913473b4eda7..a4f52e154843 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -230,7 +230,6 @@ extern int sysctl_tcp_fack; extern int sysctl_tcp_reordering; extern int sysctl_tcp_ecn; extern int sysctl_tcp_dsack; -extern long sysctl_tcp_mem[3]; extern int sysctl_tcp_wmem[3]; extern int sysctl_tcp_rmem[3]; extern int sysctl_tcp_app_win; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 15dc4c4828de..f7b5670744f0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1672,6 +1672,8 @@ static int __init inet_init(void) ip_static_sysctl_init(); #endif + tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; + /* * Add all the base protocols. */ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 69fd7201129a..bbd67abcb51d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -174,6 +175,36 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return ret; } +static int ipv4_tcp_mem(ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + unsigned long vec[3]; + struct net *net = current->nsproxy->net_ns; + + ctl_table tmp = { + .data = &vec, + .maxlen = sizeof(vec), + .mode = ctl->mode, + }; + + if (!write) { + ctl->data = &net->ipv4.sysctl_tcp_mem; + return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos); + } + + ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); + if (ret) + return ret; + + net->ipv4.sysctl_tcp_mem[0] = vec[0]; + net->ipv4.sysctl_tcp_mem[1] = vec[1]; + net->ipv4.sysctl_tcp_mem[2] = vec[2]; + + return 0; +} + static struct ctl_table ipv4_table[] = { { .procname = "tcp_timestamps", @@ -432,13 +463,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_mem", - .data = &sysctl_tcp_mem, - .maxlen = sizeof(sysctl_tcp_mem), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax - }, { .procname = "tcp_wmem", .data = &sysctl_tcp_wmem, @@ -721,6 +745,12 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = ipv4_ping_group_range, }, + { + .procname = "tcp_mem", + .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), + .mode = 0644, + .proc_handler = ipv4_tcp_mem, + }, { } }; @@ -734,6 +764,7 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; + unsigned long limit; table = ipv4_net_table; if (!net_eq(net, &init_net)) { @@ -769,6 +800,12 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_rt_cache_rebuild_count = 4; + limit = nr_free_buffer_pages() / 8; + limit = max(limit, 128UL); + net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; + net->ipv4.sysctl_tcp_mem[1] = limit; + net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; + net->ipv4.ipv4_hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); if (net->ipv4.ipv4_hdr == NULL) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 43dfccce62e9..9bcdec3ad772 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,11 +282,9 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); -long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); @@ -3278,14 +3276,9 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - limit = nr_free_buffer_pages() / 8; - limit = max(limit, 128UL); - sysctl_tcp_mem[0] = limit / 4 * 3; - sysctl_tcp_mem[1] = limit; - sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; - /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7); + limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1]) + << (PAGE_SHIFT - 7); max_share = min(4UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 42714cb1fef3..1eb4ad57670e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2623,7 +2623,6 @@ struct proto tcp_prot = { .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, - .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 4a68d2c24556..bfb0c2b8df46 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -1,6 +1,8 @@ #include #include #include +#include +#include #include #include @@ -28,6 +30,7 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) struct tcp_memcontrol *tcp; struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct net *net = current->nsproxy->net_ns; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) @@ -35,9 +38,9 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) tcp = tcp_from_cgproto(cg_proto); - tcp->tcp_prot_mem[0] = sysctl_tcp_mem[0]; - tcp->tcp_prot_mem[1] = sysctl_tcp_mem[1]; - tcp->tcp_prot_mem[2] = sysctl_tcp_mem[2]; + tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0]; + tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1]; + tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2]; tcp->tcp_memory_pressure = 0; parent_cg = tcp_prot.proto_cgroup(parent); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7694c82e629d..273f48d1df2e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1116,6 +1116,8 @@ static int __init inet6_init(void) if (err) goto static_sysctl_fail; #endif + tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; + /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 95d3cfb65d39..906c7ca43542 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2215,7 +2215,6 @@ struct proto tcpv6_prot = { .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, - .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, -- cgit v1.2.3