diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 2 | ||||
-rw-r--r-- | net/ipv4/esp4.c | 24 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 12 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 13 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 3 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_snmp_basic.c | 4 | ||||
-rw-r--r-- | net/ipv4/ping.c | 11 | ||||
-rw-r--r-- | net/ipv4/route.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 5 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 10 | ||||
-rw-r--r-- | net/ipv4/tcp_memcontrol.c | 111 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 20 | ||||
-rw-r--r-- | net/ipv4/udp.c | 30 |
15 files changed, 140 insertions, 112 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c8f7aee587d..e4e8e00a2c9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -553,7 +553,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; - return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len); + return sk->sk_prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); 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/fib_semantics.c b/net/ipv4/fib_semantics.c index a8bdf740543..e5b7182fa09 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -145,6 +145,12 @@ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + change_nexthops(fi) { + if (nexthop_nh->nh_dev) + dev_put(nexthop_nh->nh_dev); + } endfor_nexthops(fi); + + release_net(fi->fib_net); if (fi->fib_metrics != (u32 *) dst_default_metrics) kfree(fi->fib_metrics); kfree(fi); @@ -156,13 +162,7 @@ void free_fib_info(struct fib_info *fi) pr_warn("Freeing alive fib_info %p\n", fi); return; } - change_nexthops(fi) { - if (nexthop_nh->nh_dev) - dev_put(nexthop_nh->nh_dev); - nexthop_nh->nh_dev = NULL; - } endfor_nexthops(fi); fib_info_cnt--; - release_net(fi->fib_net); call_rcu(&fi->rcu, free_fib_info_rcu); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 30b88d7b4bd..18cbc15b20d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1007,9 +1007,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) while (tn != NULL && (tp = node_parent((struct rt_trie_node *)tn)) != NULL) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); wasfull = tnode_full(tp, tnode_get_child(tp, cindex)); - tn = (struct tnode *) resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); - tnode_put_child_reorg((struct tnode *)tp, cindex, + tnode_put_child_reorg(tp, cindex, (struct rt_trie_node *)tn, wasfull); tp = node_parent((struct rt_trie_node *) tn); @@ -1024,7 +1024,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) /* Handle last (top) tnode */ if (IS_TNODE(tn)) - tn = (struct tnode *)resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); @@ -1125,7 +1125,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, (struct rt_trie_node *)l); + put_child(t, tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1160,8 +1160,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, - (struct rt_trie_node *)tn); + put_child(t, tp, cindex, (struct rt_trie_node *)tn); } else { rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; @@ -1620,7 +1619,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, NULL); + put_child(t, tp, cindex, NULL); trie_rebalance(t, tp); } else RCU_INIT_POINTER(t->trie, NULL); 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/ip_output.c b/net/ipv4/ip_output.c index 451f97c42eb..b99ca4e154b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -200,7 +200,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) } if (skb->sk) skb_set_owner_w(skb2, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skb2; } @@ -709,7 +709,7 @@ slow_path: IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES); } - kfree_skb(skb); + consume_skb(skb); IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS); return err; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 746edec8b86..bac712293fd 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -405,7 +405,7 @@ static unsigned char asn1_octets_decode(struct asn1_ctx *ctx, ptr = *octets; while (ctx->pointer < eoc) { - if (!asn1_octet_decode(ctx, (unsigned char *)ptr++)) { + if (!asn1_octet_decode(ctx, ptr++)) { kfree(*octets); *octets = NULL; return 0; @@ -759,7 +759,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, } break; case SNMP_OBJECTID: - if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { + if (!asn1_oid_decode(ctx, end, &lp, &len)) { kfree(id); return 0; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 6e930c7174d..2c00e8bf684 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -207,17 +207,22 @@ static int ping_init_sock(struct sock *sk) gid_t range[2]; struct group_info *group_info = get_current_groups(); int i, j, count = group_info->ngroups; + kgid_t low, high; inet_get_ping_group_range_net(net, range, range+1); + low = make_kgid(&init_user_ns, range[0]); + high = make_kgid(&init_user_ns, range[1]); + if (!gid_valid(low) || !gid_valid(high) || gid_lt(high, low)) + return -EACCES; + if (range[0] <= group && group <= range[1]) return 0; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); - for (j = 0; j < cp_count; j++) { - group = group_info->blocks[i][j]; - if (range[0] <= group && group <= range[1]) + kgid_t gid = group_info->blocks[i][j]; + if (gid_lte(low, gid) && gid_lte(gid, high)) return 0; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ffcb3b01684..98b30d08efe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3452,6 +3452,7 @@ int __init ip_rt_init(void) 0, &rt_hash_log, &rt_hash_mask, + 0, rhash_entries ? 0 : 512 * 1024); memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); rt_hash_lock_init(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bb485fcb077..3ba605f60e4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3514,6 +3514,7 @@ void __init tcp_init(void) 0, NULL, &tcp_hashinfo.ehash_mask, + 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) { INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); @@ -3530,6 +3531,7 @@ void __init tcp_init(void) 0, &tcp_hashinfo.bhash_size, NULL, + 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cfa2aa12834..b224eb8bce8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4555,6 +4555,11 @@ static bool tcp_try_coalesce(struct sock *sk, if (tcp_hdr(from)->fin) return false; + + /* Its possible this segment overlaps with prior segment in queue */ + if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) + return false; + if (!skb_try_coalesce(to, from, fragstolen, &delta)) return false; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a43b87dfe80..3d9c1a4b881 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; @@ -840,13 +841,13 @@ 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); err = net_xmit_eval(err); } - dst_release(dst); return err; } @@ -854,7 +855,7 @@ 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 +1423,8 @@ 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 e795272fbe9..b6f3583ddfe 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -6,37 +6,6 @@ #include <linux/memcontrol.h> #include <linux/module.h> -static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft); -static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft, - const char *buffer); -static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event); - -static struct cftype tcp_files[] = { - { - .name = "kmem.tcp.limit_in_bytes", - .write_string = tcp_cgroup_write, - .read_u64 = tcp_cgroup_read, - .private = RES_LIMIT, - }, - { - .name = "kmem.tcp.usage_in_bytes", - .read_u64 = tcp_cgroup_read, - .private = RES_USAGE, - }, - { - .name = "kmem.tcp.failcnt", - .private = RES_FAILCNT, - .trigger = tcp_cgroup_reset, - .read_u64 = tcp_cgroup_read, - }, - { - .name = "kmem.tcp.max_usage_in_bytes", - .private = RES_MAX_USAGE, - .trigger = tcp_cgroup_reset, - .read_u64 = tcp_cgroup_read, - }, -}; - static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) { return container_of(cg_proto, struct tcp_memcontrol, cg_proto); @@ -49,7 +18,7 @@ static void memcg_tcp_enter_memory_pressure(struct sock *sk) } EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); -int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { /* * The root cgroup does not use res_counters, but rather, @@ -59,13 +28,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) 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); struct net *net = current->nsproxy->net_ns; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) - goto create_files; + return 0; tcp = tcp_from_cgproto(cg_proto); @@ -88,15 +56,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; cg_proto->memcg = memcg; -create_files: - return cgroup_add_files(cgrp, ss, tcp_files, - ARRAY_SIZE(tcp_files)); + return 0; } EXPORT_SYMBOL(tcp_init_cgroup); -void tcp_destroy_cgroup(struct cgroup *cgrp) +void tcp_destroy_cgroup(struct mem_cgroup *memcg) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct cg_proto *cg_proto; struct tcp_memcontrol *tcp; u64 val; @@ -109,9 +74,6 @@ void tcp_destroy_cgroup(struct cgroup *cgrp) 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); @@ -142,10 +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; } @@ -270,3 +255,37 @@ void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx) tcp->tcp_prot_mem[idx] = val; } + +static struct cftype tcp_files[] = { + { + .name = "kmem.tcp.limit_in_bytes", + .write_string = tcp_cgroup_write, + .read_u64 = tcp_cgroup_read, + .private = RES_LIMIT, + }, + { + .name = "kmem.tcp.usage_in_bytes", + .read_u64 = tcp_cgroup_read, + .private = RES_USAGE, + }, + { + .name = "kmem.tcp.failcnt", + .private = RES_FAILCNT, + .trigger = tcp_cgroup_reset, + .read_u64 = tcp_cgroup_read, + }, + { + .name = "kmem.tcp.max_usage_in_bytes", + .private = RES_MAX_USAGE, + .trigger = tcp_cgroup_reset, + .read_u64 = tcp_cgroup_read, + }, + { } /* terminate */ +}; + +static int __init tcp_memcontrol_init(void) +{ + WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files)); + return 0; +} +__initcall(tcp_memcontrol_init); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 803cbfe82fb..c465d3e51e2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2442,7 +2442,16 @@ int tcp_send_synack(struct sock *sk) return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } -/* Prepare a SYN-ACK. */ +/** + * tcp_make_synack - Prepare a SYN-ACK. + * sk: listener socket + * dst: dst entry attached to the SYNACK + * req: request_sock pointer + * rvp: request_values pointer + * + * Allocate one skb and build a SYNACK packet. + * @dst is consumed : Caller should not use it again. + */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct request_values *rvp) @@ -2461,14 +2470,15 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) s_data_desired = cvp->s_data_desired; - skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1, GFP_ATOMIC); - if (skb == NULL) + skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC); + if (unlikely(!skb)) { + dst_release(dst); return NULL; - + } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); - skb_dst_set(skb, dst_clone(dst)); + skb_dst_set(skb, dst); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 609397ee78f..eaca73644e7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2192,26 +2192,16 @@ void __init udp_table_init(struct udp_table *table, const char *name) { unsigned int i; - if (!CONFIG_BASE_SMALL) - table->hash = alloc_large_system_hash(name, - 2 * sizeof(struct udp_hslot), - uhash_entries, - 21, /* one slot per 2 MB */ - 0, - &table->log, - &table->mask, - 64 * 1024); - /* - * Make sure hash table has the minimum size - */ - if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) { - table->hash = kmalloc(UDP_HTABLE_SIZE_MIN * - 2 * sizeof(struct udp_hslot), GFP_KERNEL); - if (!table->hash) - panic(name); - table->log = ilog2(UDP_HTABLE_SIZE_MIN); - table->mask = UDP_HTABLE_SIZE_MIN - 1; - } + table->hash = alloc_large_system_hash(name, + 2 * sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + UDP_HTABLE_SIZE_MIN, + 64 * 1024); + table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); |