diff options
Diffstat (limited to 'net/ipv4')
39 files changed, 216 insertions, 179 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 91a2557942fa..f48fe6fc7e8c 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -70,11 +70,9 @@ config IP_MULTIPLE_TABLES address into account. Furthermore, the TOS (Type-Of-Service) field of the packet can be used for routing decisions as well. - If you are interested in this, please see the preliminary - documentation at <http://www.compendium.com.ar/policy-routing.txt> - and <ftp://post.tepkom.ru/pub/vol2/Linux/docs/advanced-routing.tex>. - You will need supporting software from - <ftp://ftp.tux.org/pub/net/ip-routing/>. + If you need more information, see the Linux Advanced + Routing and Traffic Control documentation at + <http://lartc.org/howto/lartc.rpdb.html> If unsure, say N. diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index afcb435adfbe..c6c8ad1d4b6d 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Linux TCP/IP (INET) layer. # diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2ae8f54cb321..82178cc69c96 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1951,7 +1951,7 @@ int cipso_v4_req_setattr(struct request_sock *req, buf = NULL; req_inet = inet_rsk(req); - opt = xchg(&req_inet->opt, opt); + opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt); if (opt) kfree_rcu(opt, rcu); @@ -1973,11 +1973,13 @@ req_setattr_failure: * values on failure. * */ -static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) +static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) { + struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1); int hdr_delta = 0; - struct ip_options_rcu *opt = *opt_ptr; + if (!opt || opt->opt.cipso == 0) + return 0; if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) { u8 cipso_len; u8 cipso_off; @@ -2039,14 +2041,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) */ void cipso_v4_sock_delattr(struct sock *sk) { - int hdr_delta; - struct ip_options_rcu *opt; struct inet_sock *sk_inet; + int hdr_delta; sk_inet = inet_sk(sk); - opt = rcu_dereference_protected(sk_inet->inet_opt, 1); - if (!opt || opt->opt.cipso == 0) - return; hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); if (sk_inet->is_icsk && hdr_delta > 0) { @@ -2066,15 +2064,7 @@ void cipso_v4_sock_delattr(struct sock *sk) */ void cipso_v4_req_delattr(struct request_sock *req) { - struct ip_options_rcu *opt; - struct inet_request_sock *req_inet; - - req_inet = inet_rsk(req); - opt = req_inet->opt; - if (!opt || opt->opt.cipso == 0) - return; - - cipso_v4_delopt(&req_inet->opt); + cipso_v4_delopt(&inet_rsk(req)->ireq_opt); } /** diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 5b2af19cfb5b..e6ff282bb7f4 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FIB_LOOKUP_H #define _FIB_LOOKUP_H diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index cfd420b0572c..b804ccbdb241 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/socket.h> diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 57a5d48acee8..01ed22139ac2 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1365,8 +1365,6 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc)) goto nla_put_failure; if (fi->fib_nhs == 1) { - struct in_device *in_dev; - if (fi->fib_nh->nh_gw && nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw)) goto nla_put_failure; @@ -1374,10 +1372,14 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) goto nla_put_failure; if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) { - in_dev = __in_dev_get_rtnl(fi->fib_nh->nh_dev); + struct in_device *in_dev; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rtm->rtm_flags |= RTNH_F_DEAD; + rcu_read_unlock(); } if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD) rtm->rtm_flags |= RTNH_F_OFFLOAD; @@ -1400,18 +1402,20 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; for_nexthops(fi) { - struct in_device *in_dev; - rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); if (!rtnh) goto nla_put_failure; rtnh->rtnh_flags = nh->nh_flags & 0xFF; if (nh->nh_flags & RTNH_F_LINKDOWN) { - in_dev = __in_dev_get_rtnl(nh->nh_dev); + struct in_device *in_dev; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(nh->nh_dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rtnh->rtnh_flags |= RTNH_F_DEAD; + rcu_read_unlock(); } rtnh->rtnh_hops = nh->nh_weight - 1; rtnh->rtnh_ifindex = nh->nh_oif; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 416bb304a281..1859c473b21a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -86,7 +86,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b9c64b40a83a..b47a59cb3573 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -266,7 +266,7 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, #if IS_ENABLED(CONFIG_IPV6) if (tb->fast_sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr, - &sk->sk_v6_rcv_saddr, + inet6_rcv_saddr(sk), tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, @@ -321,13 +321,14 @@ tb_found: goto fail_unlock; } success: - if (!hlist_empty(&tb->owners)) { + if (hlist_empty(&tb->owners)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif @@ -354,6 +355,7 @@ success: tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif @@ -473,6 +475,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } + mem_cgroup_sk_alloc(newsk); out: release_sock(sk); if (req) @@ -537,9 +540,11 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); - struct ip_options_rcu *opt = ireq->opt; + struct ip_options_rcu *opt; struct rtable *rt; + opt = ireq_opt_deref(ireq); + flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -573,10 +578,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct flowi4 *fl4; struct rtable *rt; + opt = rcu_dereference(ireq->ireq_opt); fl4 = &newinet->cork.fl.u.ip4; - rcu_read_lock(); - opt = rcu_dereference(newinet->inet_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -589,13 +593,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; - rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: - rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 597bb4cfe805..e7d15fb0d94d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -456,10 +456,7 @@ static int inet_reuseport_add_sock(struct sock *sk, return reuseport_add_sock(sk, sk2); } - /* Initial allocation may have already happened via setsockopt */ - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return reuseport_alloc(sk); - return 0; + return reuseport_alloc(sk); } int __inet_hash(struct sock *sk, struct sock *osk) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e7eb590c86ce..b20c8ac64081 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -128,9 +128,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, break; } if (cmp == -1) - pp = &(*pp)->rb_left; + pp = &next->rb_left; else - pp = &(*pp)->rb_right; + pp = &next->rb_right; } *parent_p = parent; *pp_p = pp; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 9f0a7b96646f..2dd21c3281a1 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 46408c220d9d..df8fe0503de0 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0162fb955b33..467e44d7587d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel *tunnel; struct erspanhdr *ershdr; const struct iphdr *iph; - __be32 session_id; __be32 index; int len; @@ -275,8 +274,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, /* The original GRE header does not have key field, * Use ERSPAN 10-bit session ID as key. */ - session_id = cpu_to_be32(ntohs(ershdr->session_id)); - tpi->key = session_id; + tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK); index = ershdr->md.index; tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, @@ -733,7 +731,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len > dev->mtu) { + if (skb->len - dev->hard_header_len > dev->mtu) { pskb_trim(skb, dev->mtu); truncate = true; } @@ -1223,6 +1221,7 @@ static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } @@ -1246,13 +1245,16 @@ static int erspan_tunnel_init(struct net_device *dev) tunnel->tun_hlen = 8; tunnel->parms.iph.protocol = IPPROTO_GRE; - t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr); + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + + sizeof(struct erspanhdr); + t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fa2dc8f692c6..57fc13c6ab2b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -311,9 +311,10 @@ drop: static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - struct rtable *rt; + int (*edemux)(struct sk_buff *skb); struct net_device *dev = skb->dev; - void (*edemux)(struct sk_buff *skb); + struct rtable *rt; + int err; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - edemux(skb); + err = edemux(skb); + if (unlikely(err)) + goto drop_error; /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } @@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (!skb_valid_dst(skb)) { - int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, dev); - if (unlikely(err)) { - if (err == -EXDEV) - __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); - goto drop; - } + err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, dev); + if (unlikely(err)) + goto drop_error; } #ifdef CONFIG_IP_ROUTE_CLASSID @@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) drop: kfree_skb(skb); return NET_RX_DROP; + +drop_error: + if (err == -EXDEV) + __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); + goto drop; } /* diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 525ae88d1e58..ed194d46c00e 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index a599aa83fdad..60fb1eb7d7d8 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 5ed63d250950..89453cf62158 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_parm *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ + int pkt_len = skb->len; int err; int mtu; @@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) - err = skb->len; + err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 4c5dfe6bd34d..abdebca848c9 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Automatic Configuration of IP -- use DHCP, BOOTP, RARP, or * user-supplied information to configure own IP address and routes. diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index fb1ad22b5e29..cdd627355ed1 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -128,43 +128,68 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly; static int ipip_err(struct sk_buff *skb, u32 info) { - -/* All the routers (except for Linux) return only - 8 bytes of packet payload. It means, that precise relaying of - ICMP in the real Internet is absolutely infeasible. - */ + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; - struct ip_tunnel *t; - int err; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; + struct ip_tunnel *t; + int err = 0; + + switch (type) { + case ICMP_DEST_UNREACH: + switch (code) { + case ICMP_SR_FAILED: + /* Impossible event. */ + goto out; + default: + /* All others are translated to HOST_UNREACH. + * rfc2003 contains "deep thoughts" about NET_UNREACH, + * I believe they are just ether pollution. --ANK + */ + break; + } + break; + + case ICMP_TIME_EXCEEDED: + if (code != ICMP_EXC_TTL) + goto out; + break; + + case ICMP_REDIRECT: + break; + + default: + goto out; + } - err = -ENOENT; t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); - if (!t) + if (!t) { + err = -ENOENT; goto out; + } if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->parms.link, 0, iph->protocol, 0); - err = 0; + ipv4_update_pmtu(skb, net, info, t->parms.link, 0, + iph->protocol, 0); goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, - iph->protocol, 0); - err = 0; + ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0); goto out; } - if (t->parms.iph.daddr == 0) + if (t->parms.iph.daddr == 0) { + err = -ENOENT; goto out; + } - err = 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index f462fee66ac8..adcdae358365 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the netfilter modules on top of IPv4. # diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 811689e523c3..f75fc6b53115 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, if (synproxy == NULL) return NF_ACCEPT; - if (nf_is_loopback_packet(skb)) + if (nf_is_loopback_packet(skb) || + ip_hdr(skb)->protocol != IPPROTO_TCP) return NF_ACCEPT; thoff = ip_hdrlen(skb); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index eeacbdaf7cdf..5cd06ba3535d 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -132,6 +132,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) goto free_nskb; + niph = ip_hdr(nskb); + /* "Never happens" */ if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 94d4cd2d5ea4..3d9f1c2f81c5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1520,43 +1520,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev, EXPORT_SYMBOL(rt_dst_alloc); /* called in rcu_read_lock() section */ -static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, int our) +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + struct in_device *in_dev, u32 *itag) { - struct rtable *rth; - struct in_device *in_dev = __in_dev_get_rcu(dev); - unsigned int flags = RTCF_MULTICAST; - u32 itag = 0; int err; /* Primary sanity checks. */ - if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) - goto e_inval; + return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) - goto e_inval; + return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) - goto e_inval; + return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, - in_dev, &itag); + in_dev, itag); if (err < 0) - goto e_err; + return err; } + return 0; +} + +/* called in rcu_read_lock() section */ +static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, int our) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + unsigned int flags = RTCF_MULTICAST; + struct rtable *rth; + u32 itag = 0; + int err; + + err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); + if (err) + return err; + if (our) flags |= RTCF_LOCAL; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) - goto e_nobufs; + return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; @@ -1572,13 +1585,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb_dst_set(skb, &rth->dst); return 0; - -e_nobufs: - return -ENOBUFS; -e_inval: - return -EINVAL; -e_err: - return err; } @@ -2507,7 +2513,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; - rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b1bb1b3a1082..77cf32a80952 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ - ireq->opt = tcp_v4_save_options(sock_net(sk), skb); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb)); if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d3c038d7b04..0989e739d098 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem. * diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e3c33220c418..fbbeda647774 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/crypto.h> #include <linux/err.h> #include <linux/init.h> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c5d7656beeee..5a87a00641d3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket @@ -6196,7 +6197,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct inet_request_sock *ireq = inet_rsk(req); kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; + ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d9416b5162bc..5b027c69cbc5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq->opt); + ireq_opt_deref(ireq)); err = net_xmit_eval(err); } @@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { - kfree(inet_rsk(req)->opt); + kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG @@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); + struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); - ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, @@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, 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); - ireq->opt = NULL; + newinet->inet_saddr = ireq->ir_loc_addr; + inet_opt = rcu_dereference(ireq->ireq_opt); + RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; @@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); - if (*own_req) + if (likely(*own_req)) { tcp_move_syn(newtp, req); - + ireq->ireq_opt = NULL; + } else { + newinet->inet_opt = NULL; + } return newsk; exit_overflow: @@ -1416,6 +1419,7 @@ exit: tcp_listendrop(sk); return NULL; put_and_exit: + newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; @@ -1503,23 +1507,23 @@ csum_err: } EXPORT_SYMBOL(tcp_v4_do_rcv); -void tcp_v4_early_demux(struct sk_buff *skb) +int tcp_v4_early_demux(struct sk_buff *skb) { const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) - return; + return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) - return; + return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) - return; + return 0; sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, @@ -1538,6 +1542,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb_dst_set_noref(skb, dst); } } + return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 102b2c90bb80..0f0d740f6c8b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/jiffies.h> diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 1ff73982e28c..125fc1450b01 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -252,7 +252,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) /* rate in 100's bits per second */ rate64 = ((u64)sample->in_flight) * 8000000; - rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100)); + rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100); /* Remember the maximum rate seen during this RTT * Note: It may be more than one RTT. This function should be diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1c839c99114c..478909f4694d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -739,8 +739,10 @@ static void tcp_tsq_handler(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); if (tp->lost_out > tp->retrans_out && - tp->snd_cwnd > tcp_packets_in_flight(tp)) + tp->snd_cwnd > tcp_packets_in_flight(tp)) { + tcp_mstamp_refresh(tp); tcp_xmit_retransmit_queue(sk); + } tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); @@ -1806,40 +1808,6 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, return !after(end_seq, tcp_wnd_end(tp)); } -/* This checks if the data bearing packet SKB (usually tcp_send_head(sk)) - * should be put on the wire right now. If so, it returns the number of - * packets allowed by the congestion window. - */ -static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb, - unsigned int cur_mss, int nonagle) -{ - const struct tcp_sock *tp = tcp_sk(sk); - unsigned int cwnd_quota; - - tcp_init_tso_segs(skb, cur_mss); - - if (!tcp_nagle_test(tp, skb, cur_mss, nonagle)) - return 0; - - cwnd_quota = tcp_cwnd_test(tp, skb); - if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss)) - cwnd_quota = 0; - - return cwnd_quota; -} - -/* Test if sending is allowed right now. */ -bool tcp_may_send_now(struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_send_head(sk); - - return skb && - tcp_snd_test(sk, skb, tcp_current_mss(sk), - (tcp_skb_is_last(sk, skb) ? - tp->nonagle : TCP_NAGLE_PUSH)); -} - /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions @@ -2094,6 +2062,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb->ip_summed = skb->ip_summed; tcp_insert_write_queue_before(nskb, skb, sk); + tcp_highest_sack_replace(sk, skb, nskb); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { @@ -2271,6 +2240,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, sent_pkts = 0; + tcp_mstamp_refresh(tp); if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); @@ -2282,7 +2252,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } max_segs = tcp_tso_segs(sk, mss_now); - tcp_mstamp_refresh(tp); while ((skb = tcp_send_head(sk))) { unsigned int limit; @@ -2697,7 +2666,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) else if (!skb_shift(skb, next_skb, next_skb_size)) return false; } - tcp_highest_sack_combine(sk, next_skb, skb); + tcp_highest_sack_replace(sk, next_skb, skb); tcp_unlink_write_queue(next_skb, sk); @@ -2875,8 +2844,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; - if (!err) + if (!err) { skb->skb_mstamp = tp->tcp_mstamp; + tcp_rate_skb_sent(sk, skb); + } } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } @@ -3209,13 +3180,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; - /* Setting of flags are superfluous here for callers (and ECE is - * not even correctly set) - */ - tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, - TCPHDR_SYN | TCPHDR_ACK); - - th->seq = htonl(TCP_SKB_CB(skb)->seq); + skb->ip_summed = CHECKSUM_PARTIAL; + th->seq = htonl(tcp_rsk(req)->snt_isn); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); @@ -3423,6 +3389,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto done; } + /* data was not sent, this is our new send_head */ + sk->sk_send_head = syn_data; + tp->packets_out -= tcp_skb_pcount(syn_data); + fallback: /* Send a regular SYN with Fast Open cookie request option */ if (fo->cookie.len > 0) @@ -3475,6 +3445,11 @@ int tcp_connect(struct sock *sk) */ tp->snd_nxt = tp->write_seq; tp->pushed_seq = tp->write_seq; + buff = tcp_send_head(sk); + if (unlikely(buff)) { + tp->snd_nxt = TCP_SKB_CB(buff)->seq; + tp->pushed_seq = TCP_SKB_CB(buff)->seq; + } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 449cd914d58e..be8ef1e5dfef 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/tcp.h> #include <net/tcp.h> diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h index 248cfc0ff9ae..4f24d0e37d9c 100644 --- a/net/ipv4/tcp_vegas.h +++ b/net/ipv4/tcp_vegas.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * TCP Vegas congestion control interface */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ef29df8648e4..ebfbccae62fd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) } } - /* Initial allocation may have already happened via setsockopt */ - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return reuseport_alloc(sk); - return 0; + return reuseport_alloc(sk); } /** @@ -1061,7 +1058,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - net_dbg_ratelimited("cork app bug 2\n"); + net_dbg_ratelimited("socket already corked\n"); err = -EINVAL; goto out; } @@ -1144,7 +1141,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, if (unlikely(!up->pending)) { release_sock(sk); - net_dbg_ratelimited("udp cork app bug 3\n"); + net_dbg_ratelimited("cork failed\n"); return -EINVAL; } @@ -2221,9 +2218,10 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, return NULL; } -void udp_v4_early_demux(struct sk_buff *skb) +int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct in_device *in_dev = NULL; const struct iphdr *iph; const struct udphdr *uh; struct sock *sk = NULL; @@ -2234,25 +2232,21 @@ void udp_v4_early_demux(struct sk_buff *skb) /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) - return; + return 0; iph = ip_hdr(skb); uh = udp_hdr(skb); - if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + if (skb->pkt_type == PACKET_MULTICAST) { + in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) - return; + return 0; - /* we are supposed to accept bcast packets */ - if (skb->pkt_type == PACKET_MULTICAST) { - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return; - } + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, @@ -2263,7 +2257,7 @@ void udp_v4_early_demux(struct sk_buff *skb) } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) - return; + return 0; skb->sk = sk; skb->destructor = sock_efree; @@ -2272,12 +2266,23 @@ void udp_v4_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, 0); if (dst) { + u32 itag = 0; + /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); + + /* for unconnected multicast sockets we need to validate + * the source on each packet + */ + if (!inet_sk(sk)->inet_daddr && in_dev) + return ip_mc_validate_source(skb, iph->daddr, + iph->saddr, iph->tos, + skb->dev, in_dev, &itag); } + return 0; } int udp_rcv(struct sk_buff *skb) diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index a8cf8c6fb60c..e7d18b140287 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _UDP4_IMPL_H #define _UDP4_IMPL_H #include <net/udp.h> diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 97658bfc1b58..e360d55be555 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -120,7 +120,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 1fc684111ce6..e50b7fea57ee 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * xfrm4_input.c * diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index d7bf0b041885..05017e2c849c 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * xfrm4_policy.c * diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index d6660a8c0ea5..80c40b4981bb 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * xfrm4_state.c * |