diff options
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/esp4.c | 24 | ||||
| -rw-r--r-- | net/ipv4/inet_connection_sock.c | 3 | ||||
| -rw-r--r-- | net/ipv4/inetpeer.c | 16 | ||||
| -rw-r--r-- | net/ipv4/ip_forward.c | 1 | ||||
| -rw-r--r-- | net/ipv4/ipmr.c | 1 | ||||
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 9 | ||||
| -rw-r--r-- | net/ipv4/tcp_memcontrol.c | 34 |
7 files changed, 58 insertions, 30 deletions
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 89a47b35905..cb982a61536 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -459,28 +459,22 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4); u32 align = max_t(u32, blksize, esp->padlen); - u32 rem; - - mtu -= x->props.header_len + crypto_aead_authsize(esp->aead); - rem = mtu & (align - 1); - mtu &= ~(align - 1); + unsigned int net_adj; switch (x->props.mode) { - case XFRM_MODE_TUNNEL: - break; - default: case XFRM_MODE_TRANSPORT: - /* The worst case */ - mtu -= blksize - 4; - mtu += min_t(u32, blksize - 4, rem); - break; case XFRM_MODE_BEET: - /* The worst case. */ - mtu += min_t(u32, IPV4_BEET_PHMAXLEN, rem); + net_adj = sizeof(struct iphdr); break; + case XFRM_MODE_TUNNEL: + net_adj = 0; + break; + default: + BUG(); } - return mtu - 2; + return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - + net_adj) & ~(align - 1)) + (net_adj - 2); } static void esp4_err(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 95e61596e60..f9ee7417f6a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -377,7 +377,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, - sk->sk_protocol, inet_sk_flowi_flags(sk), + sk->sk_protocol, + inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS, (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); security_req_classify_flow(req, flowi4_to_flowi(fl4)); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d4d61b694fa..dfba343b250 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -560,6 +560,17 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) } EXPORT_SYMBOL(inet_peer_xrlim_allow); +static void inetpeer_inval_rcu(struct rcu_head *head) +{ + struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu); + + spin_lock_bh(&gc_lock); + list_add_tail(&p->gc_list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} + void inetpeer_invalidate_tree(int family) { struct inet_peer *old, *new, *prev; @@ -576,10 +587,7 @@ void inetpeer_invalidate_tree(int family) prev = cmpxchg(&base->root, old, new); if (prev == old) { base->total = 0; - spin_lock(&gc_lock); - list_add_tail(&prev->gc_list, &gc_list); - spin_unlock(&gc_lock); - schedule_delayed_work(&gc_work, gc_delay); + call_rcu(&prev->gc_rcu, inetpeer_inval_rcu); } out: diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e5c44fc586a..ab09b126423 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -44,6 +44,7 @@ static int ip_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9e519ad6db..c94bbc6f2ba 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1574,6 +1574,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a43b87dfe80..c8d28c433b2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -824,7 +824,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, */ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp, + u16 queue_mapping) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -840,6 +841,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); + skb_set_queue_mapping(skb, queue_mapping); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, ireq->opt); @@ -854,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp); + return tcp_v4_send_synack(sk, NULL, req, rvp, 0); } /* @@ -1422,7 +1424,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->snt_synack = tcp_time_stamp; if (tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext) || + (struct request_values *)&tmp_ext, + skb_get_queue_mapping(skb)) || want_cookie) goto drop_and_free; diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 151703791bb..b6f3583ddfe 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -74,9 +74,6 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) percpu_counter_destroy(&tcp->tcp_sockets_allocated); val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); - - if (val != RESOURCE_MAX) - static_key_slow_dec(&memcg_socket_limit_enabled); } EXPORT_SYMBOL(tcp_destroy_cgroup); @@ -107,10 +104,33 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, net->ipv4.sysctl_tcp_mem[i]); - if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX) - static_key_slow_dec(&memcg_socket_limit_enabled); - else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX) - static_key_slow_inc(&memcg_socket_limit_enabled); + if (val == RESOURCE_MAX) + clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + else if (val != RESOURCE_MAX) { + /* + * The active bit needs to be written after the static_key + * update. This is what guarantees that the socket activation + * function is the last one to run. See sock_update_memcg() for + * details, and note that we don't mark any socket as belonging + * to this memcg until that flag is up. + * + * We need to do this, because static_keys will span multiple + * sites, but we can't control their order. If we mark a socket + * as accounted, but the accounting functions are not patched in + * yet, we'll lose accounting. + * + * We never race with the readers in sock_update_memcg(), + * because when this value change, the code to process it is not + * patched in yet. + * + * The activated bit is used to guarantee that no two writers + * will do the update in the same memcg. Without that, we can't + * properly shutdown the static key. + */ + if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) + static_key_slow_inc(&memcg_socket_limit_enabled); + set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + } return 0; } |