diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/devinet.c | 10 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 6 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 7 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 3 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 36 | ||||
-rw-r--r-- | net/ipv4/ip_forward.c | 1 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 3 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 9 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 2 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 1 | ||||
-rw-r--r-- | net/ipv4/route.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 14 | ||||
-rw-r--r-- | net/ipv4/tcp_bpf.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 13 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 9 | ||||
-rw-r--r-- | net/ipv4/udp.c | 6 |
16 files changed, 78 insertions, 53 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 9cf64ee47dd2..ca0ff15dc8fa 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -355,14 +355,14 @@ static void __inet_del_ifa(struct in_device *in_dev, { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; - struct in_ifaddr *last_prim; + struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); - last_prim = rtnl_dereference(in_dev->ifa_list); + last_prim = ifap; if (in_dev->dead) goto no_promotions; @@ -376,7 +376,7 @@ static void __inet_del_ifa(struct in_device *in_dev, while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) - last_prim = ifa; + last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || @@ -440,9 +440,9 @@ no_promotions: rcu_assign_pointer(prev_prom->ifa_next, next_sec); - last_sec = rtnl_dereference(last_prim->ifa_next); + last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); - rcu_assign_pointer(last_prim->ifa_next, promote); + rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 65ba18a91865..1ea82bc33ef1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -278,7 +278,8 @@ void fib_release_info(struct fib_info *fi) hlist_del(&nexthop_nh->nh_hash); } endfor_nexthops(fi) } - fi->fib_dead = 1; + /* Paired with READ_ONCE() from fib_table_lookup() */ + WRITE_ONCE(fi->fib_dead, 1); fib_info_put(fi); } spin_unlock_bh(&fib_info_lock); @@ -1581,6 +1582,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, link_it: ofi = fib_find_info(fi); if (ofi) { + /* fib_table_lookup() should not see @fi yet. */ fi->fib_dead = 1; free_fib_info(fi); refcount_inc(&ofi->fib_treeref); @@ -1619,6 +1621,7 @@ err_inval: failure: if (fi) { + /* fib_table_lookup() should not see @fi yet. */ fi->fib_dead = 1; free_fib_info(fi); } @@ -1884,6 +1887,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; + fi->pfsrc_removed = true; ret++; } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 74d403dbd2b4..9bdfdab906fe 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1582,7 +1582,8 @@ found: if (fa->fa_dscp && inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) continue; - if (fi->fib_dead) + /* Paired with WRITE_ONCE() in fib_release_info() */ + if (READ_ONCE(fi->fib_dead)) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; @@ -2026,6 +2027,7 @@ void fib_table_flush_external(struct fib_table *tb) int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; + struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; @@ -2088,6 +2090,9 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); + if (fi->pfsrc_removed) + rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, + KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 0c9e768e5628..418e5fb58fd3 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -353,8 +353,9 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - unsigned int size = mtu; + unsigned int size; + size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7876b7d703cb..c32f5e28758b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -815,41 +815,45 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { + if (!net_eq(ib2_net(tb), net) || tb->port != port || + tb->l3mdev != l3mdev) + return false; + #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) + if (sk->sk_family != tb->family) { + if (sk->sk_family == AF_INET) + return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) && + tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; + return false; + } if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); - else + return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); #endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr; + return tb->rcv_saddr == sk->sk_rcv_saddr; } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { + if (!net_eq(ib2_net(tb), net) || tb->port != port || + tb->l3mdev != l3mdev) + return false; + #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family != tb->family) { if (sk->sk_family == AF_INET) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_any(&tb->v6_rcv_saddr); + return ipv6_addr_any(&tb->v6_rcv_saddr) || + ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr); return false; } if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_any(&tb->v6_rcv_saddr); - else + return ipv6_addr_any(&tb->v6_rcv_saddr); #endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == 0; + return tb->rcv_saddr == 0; } /* The socket's bhash2 hashbucket spinlock must be held when this is called */ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e18931a6d153..66fac1216d46 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -67,7 +67,6 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s struct ip_options *opt = &(IPCB(skb)->opt); __IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); - __IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len); #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fe9ead9ee863..5e9c8156656a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -584,7 +584,8 @@ static void ip_sublist_rcv_finish(struct list_head *head) static struct sk_buff *ip_extract_route_hint(const struct net *net, struct sk_buff *skb, int rt_type) { - if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST) + if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST || + IPCB(skb)->flags & IPSKB_MULTIPATH) return NULL; return skb; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 43ba4b77b248..4ab877cf6d35 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -207,6 +207,9 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); + /* OUTOCTETS should be counted after fragment */ + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) @@ -366,8 +369,6 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) /* * If the indicated interface is up and running, send the packet. */ - IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); - skb->dev = dev; skb->protocol = htons(ETH_P_IP); @@ -424,8 +425,6 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; - IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); - skb->dev = dev; skb->protocol = htons(ETH_P_IP); @@ -982,7 +981,7 @@ static int __ip_append_data(struct sock *sk, paged = !!cork->gso_size; if (cork->tx_flags & SKBTX_ANY_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d1c73660b844..cce9cb25f3b3 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -511,7 +511,7 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk, * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ info = PKTINFO_SKB_CB(skb); - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) || + if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) || !info->ipi_ifindex) return false; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3f0c6d602fb7..9e222a57bc2b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1804,7 +1804,6 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); - IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d8c99bdc6170..b214b5a2e045 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) @@ -2144,6 +2146,7 @@ static int ip_mkroute_input(struct sk_buff *skb, int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); + IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif @@ -3414,6 +3417,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = + READ_ONCE(fa->offload_failed); break; } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b1559481898d..3f66cdeef7de 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1621,16 +1621,13 @@ EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; struct sk_buff *skb; int copied = 0; - u32 offset; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; @@ -1643,13 +1640,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) copied = used; break; } - seq += used; copied += used; - if (tcp_flags & TCPHDR_FIN) { - ++seq; + if (tcp_flags & TCPHDR_FIN) break; - } } return copied; } @@ -2256,14 +2250,14 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, } } - if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { - if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 81f0dff69e0b..327268203001 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -222,6 +222,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int *addr_len) { struct tcp_sock *tcp = tcp_sk(sk); + int peek = flags & MSG_PEEK; u32 seq = tcp->copied_seq; struct sk_psock *psock; int copied = 0; @@ -311,7 +312,8 @@ msg_bytes_ready: copied = -EAGAIN; } out: - WRITE_ONCE(tcp->copied_seq, seq); + if (!peek) + WRITE_ONCE(tcp->copied_seq, seq); tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 06fe1cf645d5..8afb0950a697 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -253,6 +253,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); + /* If the skb has a len of exactly 1*MSS and has the PSH bit + * set then it is likely the end of an application write. So + * more data may not be arriving soon, and yet the data sender + * may be waiting for an ACK if cwnd-bound or using TX zero + * copy. So we set ICSK_ACK_PUSHED here so that + * tcp_cleanup_rbuf() will send an ACK immediately if the app + * reads all of the data and is not ping-pong. If len > MSS + * then this logic does not matter (and does not hurt) because + * tcp_cleanup_rbuf() will always ACK immediately if the app + * reads data and there is more than an MSS of unACKed data. + */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e6b4fbd642f7..aa0fc8c766e5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -177,8 +177,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1387,7 +1386,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -3474,7 +3473,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) if (delta <= 0) return; amt = sk_mem_pages(delta); - sk->sk_forward_alloc += amt << PAGE_SHIFT; + sk_forward_alloc_add(sk, amt << PAGE_SHIFT); sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0794a2c46a56..f39b9c844580 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1414,9 +1414,9 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, spin_lock(&sk_queue->lock); - sk->sk_forward_alloc += size; + sk_forward_alloc_add(sk, size); amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); - sk->sk_forward_alloc -= amt; + sk_forward_alloc_add(sk, -amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); @@ -1527,7 +1527,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) goto uncharge_drop; } - sk->sk_forward_alloc -= size; + sk_forward_alloc_add(sk, -size); /* no need to setup a destructor, we will explicitly release the * forward allocated memory on dequeue |